Date: 2019-12-25 21:10:41 CET, cola version: 1.3.2
Document is loading...
All available functions which can be applied to this res_list object:
res_list
#> A 'ConsensusPartitionList' object with 24 methods.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows are extracted by 'SD, CV, MAD, ATC' methods.
#> Subgroups are detected by 'hclust, kmeans, skmeans, pam, mclust, NMF' method.
#> Number of partitions are tried for k = 2, 3, 4, 5, 6.
#> Performed in total 30000 partitions by row resampling.
#>
#> Following methods can be applied to this 'ConsensusPartitionList' object:
#> [1] "cola_report" "collect_classes" "collect_plots" "collect_stats"
#> [5] "colnames" "functional_enrichment" "get_anno_col" "get_anno"
#> [9] "get_classes" "get_matrix" "get_membership" "get_stats"
#> [13] "is_best_k" "is_stable_k" "ncol" "nrow"
#> [17] "rownames" "show" "suggest_best_k" "test_to_known_factors"
#> [21] "top_rows_heatmap" "top_rows_overlap"
#>
#> You can get result for a single method by, e.g. object["SD", "hclust"] or object["SD:hclust"]
#> or a subset of methods by object[c("SD", "CV")], c("hclust", "kmeans")]
The call of run_all_consensus_partition_methods() was:
#> run_all_consensus_partition_methods(data = mat, mc.cores = 4, anno = anno)
Dimension of the input matrix:
mat = get_matrix(res_list)
dim(mat)
#> [1] 51941 120
The density distribution for each sample is visualized as in one column in the following heatmap. The clustering is based on the distance which is the Kolmogorov-Smirnov statistic between two distributions.
library(ComplexHeatmap)
densityHeatmap(mat, top_annotation = HeatmapAnnotation(df = get_anno(res_list),
col = get_anno_col(res_list)), ylab = "value", cluster_columns = TRUE, show_column_names = FALSE,
mc.cores = 4)
Folowing table shows the best k (number of partitions) for each combination
of top-value methods and partition methods. Clicking on the method name in
the table goes to the section for a single combination of methods.
The cola vignette explains the definition of the metrics used for determining the best number of partitions.
suggest_best_k(res_list)
| The best k | 1-PAC | Mean silhouette | Concordance | Optional k | ||
|---|---|---|---|---|---|---|
| ATC:hclust | 3 | 1.000 | 0.985 | 0.992 | ** | 2 |
| ATC:kmeans | 2 | 1.000 | 0.989 | 0.996 | ** | |
| ATC:skmeans | 2 | 1.000 | 0.999 | 1.000 | ** | |
| ATC:pam | 2 | 1.000 | 0.998 | 0.999 | ** | |
| ATC:mclust | 5 | 1.000 | 0.966 | 0.984 | ** | 2 |
| ATC:NMF | 2 | 1.000 | 1.000 | 1.000 | ** | |
| MAD:skmeans | 2 | 0.948 | 0.936 | 0.975 | * | |
| SD:skmeans | 2 | 0.931 | 0.936 | 0.974 | * | |
| SD:kmeans | 2 | 0.931 | 0.903 | 0.956 | * | |
| MAD:kmeans | 2 | 0.922 | 0.913 | 0.950 | * | |
| SD:NMF | 2 | 0.897 | 0.928 | 0.970 | ||
| MAD:NMF | 2 | 0.897 | 0.923 | 0.968 | ||
| SD:pam | 3 | 0.690 | 0.797 | 0.911 | ||
| CV:mclust | 6 | 0.601 | 0.593 | 0.722 | ||
| MAD:hclust | 2 | 0.533 | 0.790 | 0.896 | ||
| SD:hclust | 2 | 0.519 | 0.724 | 0.887 | ||
| MAD:mclust | 2 | 0.508 | 0.921 | 0.924 | ||
| CV:kmeans | 2 | 0.505 | 0.858 | 0.910 | ||
| SD:mclust | 2 | 0.495 | 0.902 | 0.901 | ||
| CV:NMF | 2 | 0.480 | 0.830 | 0.907 | ||
| MAD:pam | 3 | 0.420 | 0.690 | 0.827 | ||
| CV:skmeans | 2 | 0.369 | 0.719 | 0.861 | ||
| CV:pam | 2 | 0.118 | 0.551 | 0.776 | ||
| CV:hclust | 3 | 0.048 | 0.470 | 0.700 |
**: 1-PAC > 0.95, *: 1-PAC > 0.9
Cumulative distribution function curves of consensus matrix for all methods.
collect_plots(res_list, fun = plot_ecdf)
Consensus heatmaps for all methods. (What is a consensus heatmap?)
collect_plots(res_list, k = 2, fun = consensus_heatmap, mc.cores = 4)
collect_plots(res_list, k = 3, fun = consensus_heatmap, mc.cores = 4)
collect_plots(res_list, k = 4, fun = consensus_heatmap, mc.cores = 4)
collect_plots(res_list, k = 5, fun = consensus_heatmap, mc.cores = 4)
collect_plots(res_list, k = 6, fun = consensus_heatmap, mc.cores = 4)
Membership heatmaps for all methods. (What is a membership heatmap?)
collect_plots(res_list, k = 2, fun = membership_heatmap, mc.cores = 4)
collect_plots(res_list, k = 3, fun = membership_heatmap, mc.cores = 4)
collect_plots(res_list, k = 4, fun = membership_heatmap, mc.cores = 4)
collect_plots(res_list, k = 5, fun = membership_heatmap, mc.cores = 4)
collect_plots(res_list, k = 6, fun = membership_heatmap, mc.cores = 4)
Signature heatmaps for all methods. (What is a signature heatmap?)
Note in following heatmaps, rows are scaled.
collect_plots(res_list, k = 2, fun = get_signatures, mc.cores = 4)
collect_plots(res_list, k = 3, fun = get_signatures, mc.cores = 4)
collect_plots(res_list, k = 4, fun = get_signatures, mc.cores = 4)
collect_plots(res_list, k = 5, fun = get_signatures, mc.cores = 4)
collect_plots(res_list, k = 6, fun = get_signatures, mc.cores = 4)
The statistics used for measuring the stability of consensus partitioning. (How are they defined?)
get_stats(res_list, k = 2)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 2 0.897 0.928 0.970 0.500 0.499 0.499
#> CV:NMF 2 0.480 0.830 0.907 0.501 0.497 0.497
#> MAD:NMF 2 0.897 0.923 0.968 0.500 0.501 0.501
#> ATC:NMF 2 1.000 1.000 1.000 0.505 0.496 0.496
#> SD:skmeans 2 0.931 0.936 0.974 0.504 0.496 0.496
#> CV:skmeans 2 0.369 0.719 0.861 0.504 0.496 0.496
#> MAD:skmeans 2 0.948 0.936 0.975 0.504 0.496 0.496
#> ATC:skmeans 2 1.000 0.999 1.000 0.505 0.496 0.496
#> SD:mclust 2 0.495 0.902 0.901 0.495 0.496 0.496
#> CV:mclust 2 0.327 0.494 0.751 0.477 0.576 0.576
#> MAD:mclust 2 0.508 0.921 0.924 0.504 0.496 0.496
#> ATC:mclust 2 1.000 1.000 1.000 0.505 0.496 0.496
#> SD:kmeans 2 0.931 0.903 0.956 0.502 0.497 0.497
#> CV:kmeans 2 0.505 0.858 0.910 0.496 0.498 0.498
#> MAD:kmeans 2 0.922 0.913 0.950 0.503 0.498 0.498
#> ATC:kmeans 2 1.000 0.989 0.996 0.505 0.496 0.496
#> SD:pam 2 0.468 0.708 0.866 0.450 0.532 0.532
#> CV:pam 2 0.118 0.551 0.776 0.474 0.532 0.532
#> MAD:pam 2 0.139 0.445 0.698 0.475 0.523 0.523
#> ATC:pam 2 1.000 0.998 0.999 0.505 0.496 0.496
#> SD:hclust 2 0.519 0.724 0.887 0.474 0.505 0.505
#> CV:hclust 2 0.183 0.831 0.813 0.203 0.967 0.967
#> MAD:hclust 2 0.533 0.790 0.896 0.482 0.496 0.496
#> ATC:hclust 2 1.000 1.000 1.000 0.505 0.496 0.496
get_stats(res_list, k = 3)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 3 0.5763 0.720 0.855 0.290 0.801 0.620
#> CV:NMF 3 0.3611 0.503 0.722 0.308 0.749 0.536
#> MAD:NMF 3 0.5623 0.684 0.847 0.324 0.748 0.538
#> ATC:NMF 3 0.7597 0.733 0.883 0.188 0.943 0.885
#> SD:skmeans 3 0.7631 0.817 0.904 0.294 0.800 0.616
#> CV:skmeans 3 0.1942 0.446 0.647 0.319 0.812 0.647
#> MAD:skmeans 3 0.6083 0.746 0.786 0.303 0.806 0.625
#> ATC:skmeans 3 0.8265 0.914 0.914 0.147 0.948 0.895
#> SD:mclust 3 0.3951 0.673 0.788 0.195 0.951 0.901
#> CV:mclust 3 0.3571 0.297 0.629 0.258 0.570 0.410
#> MAD:mclust 3 0.5811 0.659 0.824 0.184 0.992 0.983
#> ATC:mclust 3 0.7871 0.931 0.931 0.130 0.955 0.908
#> SD:kmeans 3 0.5685 0.680 0.824 0.273 0.798 0.615
#> CV:kmeans 3 0.4732 0.574 0.768 0.249 0.961 0.923
#> MAD:kmeans 3 0.5114 0.585 0.741 0.277 0.913 0.826
#> ATC:kmeans 3 0.6781 0.610 0.772 0.229 0.961 0.922
#> SD:pam 3 0.6896 0.797 0.911 0.458 0.714 0.506
#> CV:pam 3 0.2070 0.529 0.736 0.367 0.713 0.508
#> MAD:pam 3 0.4200 0.690 0.827 0.388 0.675 0.453
#> ATC:pam 3 0.7223 0.883 0.827 0.243 0.866 0.731
#> SD:hclust 3 0.4684 0.632 0.823 0.180 0.948 0.897
#> CV:hclust 3 0.0478 0.470 0.700 0.771 0.906 0.903
#> MAD:hclust 3 0.5358 0.748 0.868 0.176 0.942 0.882
#> ATC:hclust 3 1.0000 0.985 0.992 0.123 0.936 0.870
get_stats(res_list, k = 4)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 4 0.5612 0.625 0.789 0.1318 0.882 0.683
#> CV:NMF 4 0.3849 0.448 0.644 0.1228 0.859 0.613
#> MAD:NMF 4 0.4822 0.512 0.738 0.1018 0.791 0.481
#> ATC:NMF 4 0.6260 0.720 0.849 0.0611 0.914 0.817
#> SD:skmeans 4 0.5925 0.665 0.800 0.1186 0.927 0.794
#> CV:skmeans 4 0.1978 0.242 0.456 0.1272 0.867 0.676
#> MAD:skmeans 4 0.4782 0.559 0.726 0.1337 0.878 0.657
#> ATC:skmeans 4 0.8715 0.922 0.950 0.1966 0.874 0.716
#> SD:mclust 4 0.6092 0.794 0.803 0.2514 0.751 0.472
#> CV:mclust 4 0.4408 0.505 0.726 0.1444 0.703 0.460
#> MAD:mclust 4 0.6673 0.858 0.857 0.2379 0.748 0.488
#> ATC:mclust 4 0.6789 0.801 0.779 0.2206 0.768 0.507
#> SD:kmeans 4 0.5333 0.599 0.725 0.1242 0.854 0.617
#> CV:kmeans 4 0.4887 0.361 0.671 0.1346 0.830 0.637
#> MAD:kmeans 4 0.5201 0.298 0.576 0.1311 0.756 0.472
#> ATC:kmeans 4 0.6392 0.685 0.730 0.1207 0.804 0.578
#> SD:pam 4 0.7317 0.744 0.886 0.0803 0.951 0.858
#> CV:pam 4 0.3468 0.469 0.705 0.1378 0.798 0.498
#> MAD:pam 4 0.4859 0.558 0.713 0.1248 0.845 0.583
#> ATC:pam 4 0.8938 0.879 0.945 0.1872 0.871 0.659
#> SD:hclust 4 0.5361 0.597 0.806 0.1186 0.798 0.612
#> CV:hclust 4 0.0792 0.576 0.676 0.3378 0.568 0.518
#> MAD:hclust 4 0.4872 0.565 0.711 0.1491 0.845 0.672
#> ATC:hclust 4 0.8238 0.735 0.883 0.1751 0.898 0.763
get_stats(res_list, k = 5)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 5 0.5229 0.517 0.719 0.0504 0.855 0.556
#> CV:NMF 5 0.4271 0.317 0.564 0.0729 0.840 0.499
#> MAD:NMF 5 0.4943 0.485 0.706 0.0691 0.829 0.465
#> ATC:NMF 5 0.6319 0.713 0.841 0.0360 0.947 0.879
#> SD:skmeans 5 0.5724 0.486 0.657 0.0647 0.913 0.724
#> CV:skmeans 5 0.2619 0.207 0.457 0.0659 0.770 0.405
#> MAD:skmeans 5 0.4818 0.428 0.613 0.0634 0.919 0.706
#> ATC:skmeans 5 0.8874 0.914 0.925 0.1009 0.914 0.730
#> SD:mclust 5 0.7294 0.826 0.857 0.0641 0.866 0.541
#> CV:mclust 5 0.5762 0.495 0.728 0.0707 0.813 0.512
#> MAD:mclust 5 0.6973 0.677 0.834 0.0561 0.904 0.655
#> ATC:mclust 5 1.0000 0.966 0.984 0.0825 0.983 0.934
#> SD:kmeans 5 0.6232 0.683 0.772 0.0619 0.918 0.725
#> CV:kmeans 5 0.5133 0.504 0.694 0.0764 0.878 0.634
#> MAD:kmeans 5 0.5611 0.457 0.646 0.0707 0.783 0.375
#> ATC:kmeans 5 0.6775 0.740 0.729 0.0813 0.907 0.678
#> SD:pam 5 0.6749 0.566 0.801 0.0816 0.908 0.708
#> CV:pam 5 0.4311 0.473 0.679 0.0669 0.919 0.698
#> MAD:pam 5 0.6038 0.613 0.785 0.0756 0.893 0.612
#> ATC:pam 5 0.8575 0.845 0.927 0.0349 0.977 0.911
#> SD:hclust 5 0.6038 0.662 0.800 0.1272 0.822 0.575
#> CV:hclust 5 0.0998 0.544 0.698 0.1902 0.953 0.905
#> MAD:hclust 5 0.5038 0.596 0.716 0.0979 0.885 0.686
#> ATC:hclust 5 0.7170 0.606 0.793 0.0689 0.964 0.897
get_stats(res_list, k = 6)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 6 0.531 0.410 0.628 0.0428 0.926 0.710
#> CV:NMF 6 0.473 0.299 0.524 0.0444 0.828 0.405
#> MAD:NMF 6 0.510 0.329 0.608 0.0497 0.949 0.779
#> ATC:NMF 6 0.595 0.589 0.800 0.0423 0.977 0.946
#> SD:skmeans 6 0.596 0.430 0.636 0.0442 0.925 0.730
#> CV:skmeans 6 0.340 0.221 0.437 0.0426 0.904 0.622
#> MAD:skmeans 6 0.512 0.391 0.580 0.0402 0.947 0.773
#> ATC:skmeans 6 0.872 0.879 0.912 0.0471 0.954 0.810
#> SD:mclust 6 0.732 0.684 0.771 0.0322 0.931 0.702
#> CV:mclust 6 0.601 0.593 0.722 0.0689 0.888 0.578
#> MAD:mclust 6 0.720 0.710 0.814 0.0367 0.938 0.741
#> ATC:mclust 6 0.769 0.707 0.843 0.0559 0.924 0.710
#> SD:kmeans 6 0.646 0.458 0.725 0.0465 0.978 0.912
#> CV:kmeans 6 0.558 0.508 0.677 0.0464 0.913 0.663
#> MAD:kmeans 6 0.618 0.548 0.658 0.0411 0.898 0.586
#> ATC:kmeans 6 0.661 0.744 0.766 0.0610 0.959 0.803
#> SD:pam 6 0.750 0.743 0.871 0.0628 0.904 0.629
#> CV:pam 6 0.479 0.391 0.656 0.0287 0.980 0.906
#> MAD:pam 6 0.682 0.638 0.808 0.0361 0.959 0.797
#> ATC:pam 6 0.886 0.851 0.916 0.0355 0.945 0.777
#> SD:hclust 6 0.606 0.612 0.774 0.0517 0.970 0.891
#> CV:hclust 6 0.142 0.461 0.670 0.0993 0.940 0.874
#> MAD:hclust 6 0.537 0.627 0.706 0.0524 0.960 0.852
#> ATC:hclust 6 0.716 0.625 0.763 0.0575 0.873 0.633
Following heatmap plots the partition for each combination of methods and the lightness correspond to the silhouette scores for samples in each method. On top the consensus subgroup is inferred from all methods by taking the mean silhouette scores as weight.
collect_stats(res_list, k = 2)
collect_stats(res_list, k = 3)
collect_stats(res_list, k = 4)
collect_stats(res_list, k = 5)
collect_stats(res_list, k = 6)
Collect partitions from all methods:
collect_classes(res_list, k = 2)
collect_classes(res_list, k = 3)
collect_classes(res_list, k = 4)
collect_classes(res_list, k = 5)
collect_classes(res_list, k = 6)
Overlap of top rows from different top-row methods:
top_rows_overlap(res_list, top_n = 1000, method = "euler")
top_rows_overlap(res_list, top_n = 2000, method = "euler")
top_rows_overlap(res_list, top_n = 3000, method = "euler")
top_rows_overlap(res_list, top_n = 4000, method = "euler")
top_rows_overlap(res_list, top_n = 5000, method = "euler")
Also visualize the correspondance of rankings between different top-row methods:
top_rows_overlap(res_list, top_n = 1000, method = "correspondance")
top_rows_overlap(res_list, top_n = 2000, method = "correspondance")
top_rows_overlap(res_list, top_n = 3000, method = "correspondance")
top_rows_overlap(res_list, top_n = 4000, method = "correspondance")
top_rows_overlap(res_list, top_n = 5000, method = "correspondance")
Heatmaps of the top rows:
top_rows_heatmap(res_list, top_n = 1000)
top_rows_heatmap(res_list, top_n = 2000)
top_rows_heatmap(res_list, top_n = 3000)
top_rows_heatmap(res_list, top_n = 4000)
top_rows_heatmap(res_list, top_n = 5000)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res_list, k = 2)
#> n agent(p) individual(p) k
#> SD:NMF 114 1.00e+00 1.11e-05 2
#> CV:NMF 114 9.87e-01 2.30e-05 2
#> MAD:NMF 116 1.00e+00 2.31e-05 2
#> ATC:NMF 120 4.67e-27 1.00e+00 2
#> SD:skmeans 116 1.00e+00 9.49e-06 2
#> CV:skmeans 109 9.20e-01 2.01e-05 2
#> MAD:skmeans 115 1.00e+00 8.53e-06 2
#> ATC:skmeans 120 4.67e-27 1.00e+00 2
#> SD:mclust 120 4.67e-27 1.00e+00 2
#> CV:mclust 69 1.00e+00 3.59e-04 2
#> MAD:mclust 120 4.67e-27 1.00e+00 2
#> ATC:mclust 120 4.67e-27 1.00e+00 2
#> SD:kmeans 112 1.00e+00 8.99e-06 2
#> CV:kmeans 119 9.23e-01 1.05e-05 2
#> MAD:kmeans 116 1.00e+00 6.52e-06 2
#> ATC:kmeans 119 7.74e-27 1.00e+00 2
#> SD:pam 107 1.02e-03 1.94e-02 2
#> CV:pam 84 1.00e+00 4.84e-03 2
#> MAD:pam 87 1.84e-07 2.38e-01 2
#> ATC:pam 120 4.67e-27 1.00e+00 2
#> SD:hclust 102 1.00e+00 2.01e-05 2
#> CV:hclust 116 1.00e+00 6.52e-06 2
#> MAD:hclust 108 1.00e+00 1.24e-05 2
#> ATC:hclust 120 4.67e-27 1.00e+00 2
test_to_known_factors(res_list, k = 3)
#> n agent(p) individual(p) k
#> SD:NMF 102 2.69e-01 6.56e-07 3
#> CV:NMF 72 9.60e-01 2.82e-05 3
#> MAD:NMF 101 4.46e-10 2.67e-01 3
#> ATC:NMF 99 1.87e-22 1.00e+00 3
#> SD:skmeans 112 9.37e-01 1.77e-09 3
#> CV:skmeans 60 5.85e-01 1.03e-04 3
#> MAD:skmeans 116 1.27e-14 4.30e-01 3
#> ATC:skmeans 120 8.76e-27 1.00e+00 3
#> SD:mclust 116 4.78e-25 8.07e-01 3
#> CV:mclust 31 1.00e+00 1.35e-02 3
#> MAD:mclust 110 7.26e-25 1.00e+00 3
#> ATC:mclust 120 8.76e-27 1.00e+00 3
#> SD:kmeans 89 9.36e-01 4.67e-08 3
#> CV:kmeans 86 8.82e-01 2.25e-04 3
#> MAD:kmeans 101 8.39e-02 5.75e-08 3
#> ATC:kmeans 105 1.58e-23 1.00e+00 3
#> SD:pam 105 4.30e-04 2.81e-04 3
#> CV:pam 81 6.01e-01 8.58e-04 3
#> MAD:pam 105 3.58e-13 4.65e-01 3
#> ATC:pam 118 2.38e-26 1.00e+00 3
#> SD:hclust 96 1.00e+00 1.07e-08 3
#> CV:hclust 70 1.00e+00 4.01e-04 3
#> MAD:hclust 108 1.00e+00 1.61e-09 3
#> ATC:hclust 120 8.76e-27 1.00e+00 3
test_to_known_factors(res_list, k = 4)
#> n agent(p) individual(p) k
#> SD:NMF 94 5.29e-04 1.17e-04 4
#> CV:NMF 57 7.84e-01 2.24e-05 4
#> MAD:NMF 71 3.32e-06 4.73e-03 4
#> ATC:NMF 104 2.61e-23 5.00e-01 4
#> SD:skmeans 102 1.00e+00 9.61e-13 4
#> CV:skmeans 12 NA NA 4
#> MAD:skmeans 90 2.19e-19 9.52e-01 4
#> ATC:skmeans 119 1.27e-25 1.00e+00 4
#> SD:mclust 119 1.27e-25 1.00e+00 4
#> CV:mclust 77 9.99e-01 4.92e-09 4
#> MAD:mclust 119 1.27e-25 1.00e+00 4
#> ATC:mclust 111 6.69e-24 9.98e-01 4
#> SD:kmeans 88 1.00e+00 2.57e-11 4
#> CV:kmeans 56 9.57e-01 1.31e-05 4
#> MAD:kmeans 41 1.25e-09 6.19e-01 4
#> ATC:kmeans 113 2.48e-24 9.99e-01 4
#> SD:pam 103 7.57e-04 1.30e-06 4
#> CV:pam 63 6.11e-01 5.77e-03 4
#> MAD:pam 85 4.15e-13 4.42e-01 4
#> ATC:pam 115 9.21e-25 9.98e-01 4
#> SD:hclust 78 1.00e+00 2.70e-10 4
#> CV:hclust 96 9.96e-01 3.34e-11 4
#> MAD:hclust 68 1.00e+00 9.01e-07 4
#> ATC:hclust 99 2.55e-21 9.88e-01 4
test_to_known_factors(res_list, k = 5)
#> n agent(p) individual(p) k
#> SD:NMF 69 4.95e-01 1.02e-07 5
#> CV:NMF 32 7.39e-01 2.20e-02 5
#> MAD:NMF 65 2.39e-01 1.79e-05 5
#> ATC:NMF 105 1.58e-23 4.78e-01 5
#> SD:skmeans 69 1.00e+00 3.59e-04 5
#> CV:skmeans 0 NA NA 5
#> MAD:skmeans 55 1.14e-12 7.66e-01 5
#> ATC:skmeans 118 1.43e-24 9.97e-01 5
#> SD:mclust 113 9.48e-21 4.43e-01 5
#> CV:mclust 86 9.98e-01 5.88e-13 5
#> MAD:mclust 96 1.13e-20 9.97e-01 5
#> ATC:mclust 119 8.73e-25 9.97e-01 5
#> SD:kmeans 104 1.00e+00 1.26e-16 5
#> CV:kmeans 76 9.86e-01 1.29e-09 5
#> MAD:kmeans 59 9.61e-13 1.82e-01 5
#> ATC:kmeans 111 4.45e-23 9.88e-01 5
#> SD:pam 78 5.91e-05 1.05e-03 5
#> CV:pam 63 7.88e-01 5.35e-05 5
#> MAD:pam 94 2.01e-11 1.62e-01 5
#> ATC:pam 117 2.34e-24 9.96e-01 5
#> SD:hclust 98 1.00e+00 8.18e-16 5
#> CV:hclust 86 1.00e+00 5.88e-13 5
#> MAD:hclust 83 9.99e-01 1.81e-13 5
#> ATC:hclust 93 3.03e-19 9.97e-01 5
test_to_known_factors(res_list, k = 6)
#> n agent(p) individual(p) k
#> SD:NMF 47 9.82e-01 1.11e-03 6
#> CV:NMF 13 1.00e+00 7.21e-02 6
#> MAD:NMF 38 4.34e-01 1.19e-03 6
#> ATC:NMF 90 1.76e-20 1.00e+00 6
#> SD:skmeans 54 9.07e-03 3.93e-05 6
#> CV:skmeans 0 NA NA 6
#> MAD:skmeans 48 3.78e-11 6.32e-01 6
#> ATC:skmeans 115 3.59e-23 9.92e-01 6
#> SD:mclust 106 2.87e-21 9.87e-01 6
#> CV:mclust 96 9.99e-01 3.65e-18 6
#> MAD:mclust 109 6.67e-22 9.89e-01 6
#> ATC:mclust 99 1.61e-20 8.19e-01 6
#> SD:kmeans 62 7.47e-01 2.68e-10 6
#> CV:kmeans 81 9.97e-01 1.66e-14 6
#> MAD:kmeans 74 4.71e-11 2.06e-04 6
#> ATC:kmeans 111 2.52e-22 9.58e-01 6
#> SD:pam 108 1.39e-07 4.44e-05 6
#> CV:pam 47 8.37e-01 7.83e-04 6
#> MAD:pam 93 6.14e-10 5.15e-03 6
#> ATC:pam 113 9.51e-23 9.88e-01 6
#> SD:hclust 92 1.00e+00 2.88e-18 6
#> CV:hclust 61 8.78e-01 1.09e-08 6
#> MAD:hclust 95 1.00e+00 2.21e-18 6
#> ATC:hclust 102 2.00e-20 9.97e-01 6
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["SD", "hclust"]
# you can also extract it by
# res = res_list["SD:hclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'SD' method.
#> Subgroups are detected by 'hclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.519 0.724 0.887 0.4738 0.505 0.505
#> 3 3 0.468 0.632 0.823 0.1795 0.948 0.897
#> 4 4 0.536 0.597 0.806 0.1186 0.798 0.612
#> 5 5 0.604 0.662 0.800 0.1272 0.822 0.575
#> 6 6 0.606 0.612 0.774 0.0517 0.970 0.891
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 2 0.3733 0.8269 0.072 0.928
#> GSM486737 2 0.0672 0.8550 0.008 0.992
#> GSM486739 2 0.5737 0.7849 0.136 0.864
#> GSM486741 2 0.0672 0.8550 0.008 0.992
#> GSM486743 2 0.1414 0.8521 0.020 0.980
#> GSM486745 2 0.5737 0.7849 0.136 0.864
#> GSM486747 1 0.8608 0.5899 0.716 0.284
#> GSM486749 2 0.0672 0.8550 0.008 0.992
#> GSM486751 1 0.8955 0.5405 0.688 0.312
#> GSM486753 2 0.0938 0.8537 0.012 0.988
#> GSM486755 2 0.0672 0.8550 0.008 0.992
#> GSM486757 1 0.6148 0.7627 0.848 0.152
#> GSM486759 1 0.0376 0.8683 0.996 0.004
#> GSM486761 1 0.0000 0.8681 1.000 0.000
#> GSM486763 1 0.2236 0.8568 0.964 0.036
#> GSM486765 1 0.0000 0.8681 1.000 0.000
#> GSM486767 1 0.9970 0.1088 0.532 0.468
#> GSM486769 2 0.2948 0.8362 0.052 0.948
#> GSM486771 2 0.0938 0.8549 0.012 0.988
#> GSM486773 2 0.9996 0.0351 0.488 0.512
#> GSM486775 1 0.0000 0.8681 1.000 0.000
#> GSM486777 1 0.0000 0.8681 1.000 0.000
#> GSM486779 2 0.0938 0.8539 0.012 0.988
#> GSM486781 2 0.9954 0.1385 0.460 0.540
#> GSM486783 2 0.0672 0.8550 0.008 0.992
#> GSM486785 1 0.0000 0.8681 1.000 0.000
#> GSM486787 1 0.0376 0.8683 0.996 0.004
#> GSM486789 2 0.1184 0.8531 0.016 0.984
#> GSM486791 1 0.2043 0.8585 0.968 0.032
#> GSM486793 1 0.0000 0.8681 1.000 0.000
#> GSM486795 1 0.8443 0.6227 0.728 0.272
#> GSM486797 1 0.9686 0.3546 0.604 0.396
#> GSM486799 1 0.0000 0.8681 1.000 0.000
#> GSM486801 1 0.0376 0.8683 0.996 0.004
#> GSM486803 1 0.0938 0.8659 0.988 0.012
#> GSM486805 1 0.9998 0.0181 0.508 0.492
#> GSM486807 1 0.0376 0.8679 0.996 0.004
#> GSM486809 2 0.6887 0.7367 0.184 0.816
#> GSM486811 1 0.0000 0.8681 1.000 0.000
#> GSM486813 2 0.0672 0.8550 0.008 0.992
#> GSM486815 1 0.0000 0.8681 1.000 0.000
#> GSM486817 1 0.9661 0.3644 0.608 0.392
#> GSM486819 1 0.8555 0.6067 0.720 0.280
#> GSM486822 2 0.0672 0.8550 0.008 0.992
#> GSM486824 1 0.0938 0.8657 0.988 0.012
#> GSM486828 2 0.9988 0.0665 0.480 0.520
#> GSM486831 1 0.0376 0.8683 0.996 0.004
#> GSM486833 1 0.9754 0.3202 0.592 0.408
#> GSM486835 1 0.0376 0.8683 0.996 0.004
#> GSM486837 2 0.8081 0.6408 0.248 0.752
#> GSM486839 1 0.0000 0.8681 1.000 0.000
#> GSM486841 1 0.0000 0.8681 1.000 0.000
#> GSM486843 1 0.2603 0.8482 0.956 0.044
#> GSM486845 2 0.9954 0.1391 0.460 0.540
#> GSM486847 1 0.0000 0.8681 1.000 0.000
#> GSM486849 2 0.0672 0.8550 0.008 0.992
#> GSM486851 1 0.2043 0.8585 0.968 0.032
#> GSM486853 2 0.0672 0.8550 0.008 0.992
#> GSM486855 2 0.0672 0.8550 0.008 0.992
#> GSM486857 2 0.8608 0.5814 0.284 0.716
#> GSM486736 2 0.3733 0.8269 0.072 0.928
#> GSM486738 2 0.0672 0.8550 0.008 0.992
#> GSM486740 2 0.5737 0.7849 0.136 0.864
#> GSM486742 2 0.0672 0.8550 0.008 0.992
#> GSM486744 2 0.1414 0.8521 0.020 0.980
#> GSM486746 2 0.5737 0.7849 0.136 0.864
#> GSM486748 1 0.8608 0.5899 0.716 0.284
#> GSM486750 2 0.0672 0.8550 0.008 0.992
#> GSM486752 1 0.8955 0.5405 0.688 0.312
#> GSM486754 2 0.0938 0.8537 0.012 0.988
#> GSM486756 2 0.0672 0.8550 0.008 0.992
#> GSM486758 1 0.6148 0.7627 0.848 0.152
#> GSM486760 1 0.0376 0.8683 0.996 0.004
#> GSM486762 1 0.0000 0.8681 1.000 0.000
#> GSM486764 1 0.2236 0.8568 0.964 0.036
#> GSM486766 1 0.0000 0.8681 1.000 0.000
#> GSM486768 1 0.9970 0.1088 0.532 0.468
#> GSM486770 2 0.2948 0.8362 0.052 0.948
#> GSM486772 2 0.0938 0.8549 0.012 0.988
#> GSM486774 2 0.9996 0.0351 0.488 0.512
#> GSM486776 1 0.0000 0.8681 1.000 0.000
#> GSM486778 1 0.0000 0.8681 1.000 0.000
#> GSM486780 2 0.0938 0.8539 0.012 0.988
#> GSM486782 2 0.9954 0.1385 0.460 0.540
#> GSM486784 2 0.0672 0.8550 0.008 0.992
#> GSM486786 1 0.0000 0.8681 1.000 0.000
#> GSM486788 1 0.0376 0.8683 0.996 0.004
#> GSM486790 2 0.1184 0.8531 0.016 0.984
#> GSM486792 1 0.2043 0.8585 0.968 0.032
#> GSM486794 1 0.0000 0.8681 1.000 0.000
#> GSM486796 1 0.8443 0.6227 0.728 0.272
#> GSM486798 1 0.9686 0.3546 0.604 0.396
#> GSM486800 1 0.0000 0.8681 1.000 0.000
#> GSM486802 1 0.0376 0.8683 0.996 0.004
#> GSM486804 1 0.0938 0.8659 0.988 0.012
#> GSM486806 1 0.9998 0.0181 0.508 0.492
#> GSM486808 1 0.0376 0.8679 0.996 0.004
#> GSM486810 2 0.6887 0.7367 0.184 0.816
#> GSM486812 1 0.0000 0.8681 1.000 0.000
#> GSM486814 2 0.0672 0.8550 0.008 0.992
#> GSM486816 1 0.0000 0.8681 1.000 0.000
#> GSM486818 1 0.9661 0.3644 0.608 0.392
#> GSM486821 1 0.8555 0.6067 0.720 0.280
#> GSM486823 2 0.0672 0.8550 0.008 0.992
#> GSM486826 1 0.0938 0.8657 0.988 0.012
#> GSM486830 2 0.9988 0.0665 0.480 0.520
#> GSM486832 1 0.0376 0.8683 0.996 0.004
#> GSM486834 1 0.9754 0.3202 0.592 0.408
#> GSM486836 1 0.0376 0.8683 0.996 0.004
#> GSM486838 2 0.8081 0.6408 0.248 0.752
#> GSM486840 1 0.0000 0.8681 1.000 0.000
#> GSM486842 1 0.0000 0.8681 1.000 0.000
#> GSM486844 1 0.2603 0.8482 0.956 0.044
#> GSM486846 2 0.9954 0.1391 0.460 0.540
#> GSM486848 1 0.0000 0.8681 1.000 0.000
#> GSM486850 2 0.0672 0.8550 0.008 0.992
#> GSM486852 1 0.2043 0.8585 0.968 0.032
#> GSM486854 2 0.0672 0.8550 0.008 0.992
#> GSM486856 2 0.0672 0.8550 0.008 0.992
#> GSM486858 2 0.8608 0.5814 0.284 0.716
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 2 0.5905 0.61547 0.000 0.648 0.352
#> GSM486737 2 0.1643 0.75626 0.000 0.956 0.044
#> GSM486739 2 0.6542 0.68566 0.060 0.736 0.204
#> GSM486741 2 0.2959 0.74711 0.000 0.900 0.100
#> GSM486743 2 0.3715 0.75086 0.004 0.868 0.128
#> GSM486745 2 0.6495 0.68767 0.060 0.740 0.200
#> GSM486747 1 0.6597 0.51710 0.696 0.268 0.036
#> GSM486749 2 0.3340 0.73904 0.000 0.880 0.120
#> GSM486751 1 0.6998 0.48385 0.664 0.292 0.044
#> GSM486753 2 0.3340 0.75066 0.000 0.880 0.120
#> GSM486755 2 0.2165 0.75562 0.000 0.936 0.064
#> GSM486757 1 0.5136 0.64556 0.824 0.132 0.044
#> GSM486759 1 0.0237 0.77509 0.996 0.004 0.000
#> GSM486761 1 0.0000 0.77465 1.000 0.000 0.000
#> GSM486763 3 0.5465 0.99269 0.288 0.000 0.712
#> GSM486765 1 0.0000 0.77465 1.000 0.000 0.000
#> GSM486767 1 0.9252 0.05051 0.448 0.396 0.156
#> GSM486769 2 0.5760 0.63685 0.000 0.672 0.328
#> GSM486771 2 0.1399 0.75917 0.004 0.968 0.028
#> GSM486773 2 0.8637 0.00338 0.444 0.456 0.100
#> GSM486775 1 0.0000 0.77465 1.000 0.000 0.000
#> GSM486777 1 0.0237 0.77198 0.996 0.000 0.004
#> GSM486779 2 0.1878 0.75342 0.004 0.952 0.044
#> GSM486781 2 0.8316 0.09312 0.424 0.496 0.080
#> GSM486783 2 0.1643 0.75442 0.000 0.956 0.044
#> GSM486785 1 0.0000 0.77465 1.000 0.000 0.000
#> GSM486787 1 0.0475 0.77418 0.992 0.004 0.004
#> GSM486789 2 0.3686 0.74619 0.000 0.860 0.140
#> GSM486791 3 0.5529 0.99236 0.296 0.000 0.704
#> GSM486793 1 0.0237 0.77198 0.996 0.000 0.004
#> GSM486795 1 0.6585 0.52338 0.712 0.244 0.044
#> GSM486797 1 0.8179 0.34681 0.564 0.352 0.084
#> GSM486799 1 0.0000 0.77465 1.000 0.000 0.000
#> GSM486801 1 0.0237 0.77509 0.996 0.004 0.000
#> GSM486803 1 0.0829 0.77101 0.984 0.012 0.004
#> GSM486805 1 0.8404 0.02762 0.464 0.452 0.084
#> GSM486807 1 0.0475 0.77312 0.992 0.004 0.004
#> GSM486809 2 0.6771 0.49600 0.012 0.548 0.440
#> GSM486811 1 0.0000 0.77465 1.000 0.000 0.000
#> GSM486813 2 0.1643 0.75442 0.000 0.956 0.044
#> GSM486815 1 0.0237 0.77198 0.996 0.000 0.004
#> GSM486817 1 0.7710 0.35787 0.576 0.368 0.056
#> GSM486819 1 0.9673 -0.20551 0.400 0.212 0.388
#> GSM486822 2 0.5016 0.68441 0.000 0.760 0.240
#> GSM486824 1 0.0592 0.77158 0.988 0.012 0.000
#> GSM486828 2 0.8398 0.03588 0.440 0.476 0.084
#> GSM486831 1 0.0475 0.77418 0.992 0.004 0.004
#> GSM486833 1 0.8196 0.32958 0.560 0.356 0.084
#> GSM486835 1 0.0475 0.77418 0.992 0.004 0.004
#> GSM486837 2 0.6402 0.56556 0.236 0.724 0.040
#> GSM486839 1 0.0000 0.77465 1.000 0.000 0.000
#> GSM486841 1 0.0000 0.77465 1.000 0.000 0.000
#> GSM486843 1 0.1878 0.74985 0.952 0.044 0.004
#> GSM486845 2 0.8113 0.08783 0.428 0.504 0.068
#> GSM486847 1 0.0000 0.77465 1.000 0.000 0.000
#> GSM486849 2 0.0892 0.75860 0.000 0.980 0.020
#> GSM486851 3 0.5497 0.99473 0.292 0.000 0.708
#> GSM486853 2 0.1529 0.75541 0.000 0.960 0.040
#> GSM486855 2 0.1411 0.75611 0.000 0.964 0.036
#> GSM486857 2 0.6632 0.51927 0.272 0.692 0.036
#> GSM486736 2 0.5905 0.61547 0.000 0.648 0.352
#> GSM486738 2 0.1643 0.75626 0.000 0.956 0.044
#> GSM486740 2 0.6542 0.68566 0.060 0.736 0.204
#> GSM486742 2 0.2959 0.74711 0.000 0.900 0.100
#> GSM486744 2 0.3715 0.75086 0.004 0.868 0.128
#> GSM486746 2 0.6495 0.68767 0.060 0.740 0.200
#> GSM486748 1 0.6597 0.51710 0.696 0.268 0.036
#> GSM486750 2 0.3340 0.73904 0.000 0.880 0.120
#> GSM486752 1 0.6998 0.48385 0.664 0.292 0.044
#> GSM486754 2 0.3340 0.75066 0.000 0.880 0.120
#> GSM486756 2 0.2165 0.75562 0.000 0.936 0.064
#> GSM486758 1 0.5136 0.64556 0.824 0.132 0.044
#> GSM486760 1 0.0237 0.77509 0.996 0.004 0.000
#> GSM486762 1 0.0000 0.77465 1.000 0.000 0.000
#> GSM486764 3 0.5465 0.99269 0.288 0.000 0.712
#> GSM486766 1 0.0000 0.77465 1.000 0.000 0.000
#> GSM486768 1 0.9252 0.05051 0.448 0.396 0.156
#> GSM486770 2 0.5760 0.63685 0.000 0.672 0.328
#> GSM486772 2 0.1399 0.75917 0.004 0.968 0.028
#> GSM486774 2 0.8637 0.00338 0.444 0.456 0.100
#> GSM486776 1 0.0000 0.77465 1.000 0.000 0.000
#> GSM486778 1 0.0237 0.77198 0.996 0.000 0.004
#> GSM486780 2 0.1878 0.75342 0.004 0.952 0.044
#> GSM486782 2 0.8316 0.09312 0.424 0.496 0.080
#> GSM486784 2 0.1643 0.75442 0.000 0.956 0.044
#> GSM486786 1 0.0000 0.77465 1.000 0.000 0.000
#> GSM486788 1 0.0475 0.77418 0.992 0.004 0.004
#> GSM486790 2 0.3686 0.74619 0.000 0.860 0.140
#> GSM486792 3 0.5529 0.99236 0.296 0.000 0.704
#> GSM486794 1 0.0237 0.77198 0.996 0.000 0.004
#> GSM486796 1 0.6585 0.52338 0.712 0.244 0.044
#> GSM486798 1 0.8179 0.34681 0.564 0.352 0.084
#> GSM486800 1 0.0000 0.77465 1.000 0.000 0.000
#> GSM486802 1 0.0237 0.77509 0.996 0.004 0.000
#> GSM486804 1 0.0829 0.77101 0.984 0.012 0.004
#> GSM486806 1 0.8404 0.02762 0.464 0.452 0.084
#> GSM486808 1 0.0475 0.77312 0.992 0.004 0.004
#> GSM486810 2 0.6771 0.49600 0.012 0.548 0.440
#> GSM486812 1 0.0000 0.77465 1.000 0.000 0.000
#> GSM486814 2 0.1643 0.75442 0.000 0.956 0.044
#> GSM486816 1 0.0237 0.77198 0.996 0.000 0.004
#> GSM486818 1 0.7710 0.35787 0.576 0.368 0.056
#> GSM486821 1 0.9673 -0.20551 0.400 0.212 0.388
#> GSM486823 2 0.5016 0.68441 0.000 0.760 0.240
#> GSM486826 1 0.0592 0.77158 0.988 0.012 0.000
#> GSM486830 2 0.8398 0.03588 0.440 0.476 0.084
#> GSM486832 1 0.0475 0.77418 0.992 0.004 0.004
#> GSM486834 1 0.8196 0.32958 0.560 0.356 0.084
#> GSM486836 1 0.0475 0.77418 0.992 0.004 0.004
#> GSM486838 2 0.6402 0.56556 0.236 0.724 0.040
#> GSM486840 1 0.0000 0.77465 1.000 0.000 0.000
#> GSM486842 1 0.0000 0.77465 1.000 0.000 0.000
#> GSM486844 1 0.1878 0.74985 0.952 0.044 0.004
#> GSM486846 2 0.8113 0.08783 0.428 0.504 0.068
#> GSM486848 1 0.0000 0.77465 1.000 0.000 0.000
#> GSM486850 2 0.0892 0.75860 0.000 0.980 0.020
#> GSM486852 3 0.5497 0.99473 0.292 0.000 0.708
#> GSM486854 2 0.1529 0.75541 0.000 0.960 0.040
#> GSM486856 2 0.1411 0.75611 0.000 0.964 0.036
#> GSM486858 2 0.6632 0.51927 0.272 0.692 0.036
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 4 0.2198 0.551 0.000 0.008 0.072 0.920
#> GSM486737 2 0.2589 0.674 0.000 0.884 0.000 0.116
#> GSM486739 4 0.7342 0.486 0.036 0.336 0.080 0.548
#> GSM486741 2 0.4843 0.124 0.000 0.604 0.000 0.396
#> GSM486743 4 0.5143 0.412 0.004 0.456 0.000 0.540
#> GSM486745 4 0.7356 0.481 0.036 0.340 0.080 0.544
#> GSM486747 1 0.6172 0.612 0.692 0.208 0.016 0.084
#> GSM486749 4 0.4977 0.239 0.000 0.460 0.000 0.540
#> GSM486751 1 0.6598 0.580 0.660 0.228 0.024 0.088
#> GSM486753 4 0.4948 0.443 0.000 0.440 0.000 0.560
#> GSM486755 2 0.4040 0.466 0.000 0.752 0.000 0.248
#> GSM486757 1 0.4630 0.703 0.820 0.096 0.020 0.064
#> GSM486759 1 0.0188 0.783 0.996 0.004 0.000 0.000
#> GSM486761 1 0.0000 0.783 1.000 0.000 0.000 0.000
#> GSM486763 3 0.0336 0.762 0.000 0.000 0.992 0.008
#> GSM486765 1 0.0000 0.783 1.000 0.000 0.000 0.000
#> GSM486767 1 0.9189 0.217 0.416 0.292 0.104 0.188
#> GSM486769 4 0.2060 0.560 0.000 0.016 0.052 0.932
#> GSM486771 2 0.1902 0.724 0.004 0.932 0.000 0.064
#> GSM486773 1 0.8369 0.234 0.436 0.344 0.036 0.184
#> GSM486775 1 0.0000 0.783 1.000 0.000 0.000 0.000
#> GSM486777 1 0.0188 0.781 0.996 0.000 0.004 0.000
#> GSM486779 2 0.1489 0.722 0.000 0.952 0.004 0.044
#> GSM486781 1 0.7958 0.179 0.424 0.384 0.016 0.176
#> GSM486783 2 0.0336 0.747 0.000 0.992 0.000 0.008
#> GSM486785 1 0.0000 0.783 1.000 0.000 0.000 0.000
#> GSM486787 1 0.0376 0.782 0.992 0.004 0.004 0.000
#> GSM486789 4 0.4866 0.489 0.000 0.404 0.000 0.596
#> GSM486791 3 0.0376 0.762 0.004 0.000 0.992 0.004
#> GSM486793 1 0.0188 0.781 0.996 0.000 0.004 0.000
#> GSM486795 1 0.5677 0.615 0.708 0.232 0.016 0.044
#> GSM486797 1 0.7648 0.450 0.556 0.280 0.032 0.132
#> GSM486799 1 0.0000 0.783 1.000 0.000 0.000 0.000
#> GSM486801 1 0.0188 0.783 0.996 0.004 0.000 0.000
#> GSM486803 1 0.0657 0.781 0.984 0.012 0.004 0.000
#> GSM486805 1 0.8275 0.270 0.456 0.344 0.040 0.160
#> GSM486807 1 0.0376 0.782 0.992 0.000 0.004 0.004
#> GSM486809 4 0.3768 0.464 0.000 0.008 0.184 0.808
#> GSM486811 1 0.0000 0.783 1.000 0.000 0.000 0.000
#> GSM486813 2 0.0336 0.747 0.000 0.992 0.000 0.008
#> GSM486815 1 0.0188 0.781 0.996 0.000 0.004 0.000
#> GSM486817 1 0.7171 0.451 0.568 0.320 0.028 0.084
#> GSM486819 3 0.9101 0.206 0.276 0.136 0.448 0.140
#> GSM486822 4 0.2281 0.589 0.000 0.096 0.000 0.904
#> GSM486824 1 0.0469 0.781 0.988 0.012 0.000 0.000
#> GSM486828 1 0.8153 0.209 0.432 0.372 0.028 0.168
#> GSM486831 1 0.0376 0.782 0.992 0.004 0.004 0.000
#> GSM486833 1 0.7613 0.433 0.548 0.300 0.032 0.120
#> GSM486835 1 0.0376 0.782 0.992 0.004 0.004 0.000
#> GSM486837 2 0.6464 0.359 0.236 0.644 0.004 0.116
#> GSM486839 1 0.0000 0.783 1.000 0.000 0.000 0.000
#> GSM486841 1 0.0000 0.783 1.000 0.000 0.000 0.000
#> GSM486843 1 0.1635 0.766 0.948 0.044 0.008 0.000
#> GSM486845 1 0.7678 0.165 0.428 0.412 0.012 0.148
#> GSM486847 1 0.0000 0.783 1.000 0.000 0.000 0.000
#> GSM486849 2 0.1389 0.736 0.000 0.952 0.000 0.048
#> GSM486851 3 0.0188 0.762 0.000 0.000 0.996 0.004
#> GSM486853 2 0.0469 0.747 0.000 0.988 0.000 0.012
#> GSM486855 2 0.0817 0.741 0.000 0.976 0.000 0.024
#> GSM486857 2 0.6650 0.314 0.272 0.612 0.004 0.112
#> GSM486736 4 0.2198 0.551 0.000 0.008 0.072 0.920
#> GSM486738 2 0.2589 0.674 0.000 0.884 0.000 0.116
#> GSM486740 4 0.7342 0.486 0.036 0.336 0.080 0.548
#> GSM486742 2 0.4843 0.124 0.000 0.604 0.000 0.396
#> GSM486744 4 0.5143 0.412 0.004 0.456 0.000 0.540
#> GSM486746 4 0.7356 0.481 0.036 0.340 0.080 0.544
#> GSM486748 1 0.6172 0.612 0.692 0.208 0.016 0.084
#> GSM486750 4 0.4977 0.239 0.000 0.460 0.000 0.540
#> GSM486752 1 0.6598 0.580 0.660 0.228 0.024 0.088
#> GSM486754 4 0.4948 0.443 0.000 0.440 0.000 0.560
#> GSM486756 2 0.4040 0.466 0.000 0.752 0.000 0.248
#> GSM486758 1 0.4630 0.703 0.820 0.096 0.020 0.064
#> GSM486760 1 0.0188 0.783 0.996 0.004 0.000 0.000
#> GSM486762 1 0.0000 0.783 1.000 0.000 0.000 0.000
#> GSM486764 3 0.0336 0.762 0.000 0.000 0.992 0.008
#> GSM486766 1 0.0000 0.783 1.000 0.000 0.000 0.000
#> GSM486768 1 0.9189 0.217 0.416 0.292 0.104 0.188
#> GSM486770 4 0.2060 0.560 0.000 0.016 0.052 0.932
#> GSM486772 2 0.1902 0.724 0.004 0.932 0.000 0.064
#> GSM486774 1 0.8369 0.234 0.436 0.344 0.036 0.184
#> GSM486776 1 0.0000 0.783 1.000 0.000 0.000 0.000
#> GSM486778 1 0.0188 0.781 0.996 0.000 0.004 0.000
#> GSM486780 2 0.1489 0.722 0.000 0.952 0.004 0.044
#> GSM486782 1 0.7958 0.179 0.424 0.384 0.016 0.176
#> GSM486784 2 0.0336 0.747 0.000 0.992 0.000 0.008
#> GSM486786 1 0.0000 0.783 1.000 0.000 0.000 0.000
#> GSM486788 1 0.0376 0.782 0.992 0.004 0.004 0.000
#> GSM486790 4 0.4866 0.489 0.000 0.404 0.000 0.596
#> GSM486792 3 0.0376 0.762 0.004 0.000 0.992 0.004
#> GSM486794 1 0.0188 0.781 0.996 0.000 0.004 0.000
#> GSM486796 1 0.5677 0.615 0.708 0.232 0.016 0.044
#> GSM486798 1 0.7648 0.450 0.556 0.280 0.032 0.132
#> GSM486800 1 0.0000 0.783 1.000 0.000 0.000 0.000
#> GSM486802 1 0.0188 0.783 0.996 0.004 0.000 0.000
#> GSM486804 1 0.0657 0.781 0.984 0.012 0.004 0.000
#> GSM486806 1 0.8275 0.270 0.456 0.344 0.040 0.160
#> GSM486808 1 0.0376 0.782 0.992 0.000 0.004 0.004
#> GSM486810 4 0.3768 0.464 0.000 0.008 0.184 0.808
#> GSM486812 1 0.0000 0.783 1.000 0.000 0.000 0.000
#> GSM486814 2 0.0336 0.747 0.000 0.992 0.000 0.008
#> GSM486816 1 0.0188 0.781 0.996 0.000 0.004 0.000
#> GSM486818 1 0.7171 0.451 0.568 0.320 0.028 0.084
#> GSM486821 3 0.9101 0.206 0.276 0.136 0.448 0.140
#> GSM486823 4 0.2281 0.589 0.000 0.096 0.000 0.904
#> GSM486826 1 0.0469 0.781 0.988 0.012 0.000 0.000
#> GSM486830 1 0.8153 0.209 0.432 0.372 0.028 0.168
#> GSM486832 1 0.0376 0.782 0.992 0.004 0.004 0.000
#> GSM486834 1 0.7613 0.433 0.548 0.300 0.032 0.120
#> GSM486836 1 0.0376 0.782 0.992 0.004 0.004 0.000
#> GSM486838 2 0.6464 0.359 0.236 0.644 0.004 0.116
#> GSM486840 1 0.0000 0.783 1.000 0.000 0.000 0.000
#> GSM486842 1 0.0000 0.783 1.000 0.000 0.000 0.000
#> GSM486844 1 0.1635 0.766 0.948 0.044 0.008 0.000
#> GSM486846 1 0.7678 0.165 0.428 0.412 0.012 0.148
#> GSM486848 1 0.0000 0.783 1.000 0.000 0.000 0.000
#> GSM486850 2 0.1389 0.736 0.000 0.952 0.000 0.048
#> GSM486852 3 0.0188 0.762 0.000 0.000 0.996 0.004
#> GSM486854 2 0.0469 0.747 0.000 0.988 0.000 0.012
#> GSM486856 2 0.0817 0.741 0.000 0.976 0.000 0.024
#> GSM486858 2 0.6650 0.314 0.272 0.612 0.004 0.112
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 4 0.3419 0.6093 0.000 0.000 0.180 0.804 0.016
#> GSM486737 2 0.2824 0.7800 0.000 0.864 0.020 0.116 0.000
#> GSM486739 3 0.6561 -0.2843 0.000 0.096 0.472 0.400 0.032
#> GSM486741 2 0.4930 0.3454 0.000 0.580 0.032 0.388 0.000
#> GSM486743 4 0.6649 0.4879 0.000 0.284 0.268 0.448 0.000
#> GSM486745 3 0.6600 -0.2802 0.000 0.100 0.468 0.400 0.032
#> GSM486747 1 0.5363 -0.0262 0.548 0.040 0.404 0.008 0.000
#> GSM486749 4 0.5137 0.0964 0.000 0.424 0.040 0.536 0.000
#> GSM486751 1 0.5574 -0.1971 0.504 0.044 0.440 0.012 0.000
#> GSM486753 4 0.6596 0.5130 0.000 0.256 0.280 0.464 0.000
#> GSM486755 2 0.5373 0.5137 0.000 0.652 0.112 0.236 0.000
#> GSM486757 1 0.4235 0.5039 0.656 0.000 0.336 0.008 0.000
#> GSM486759 1 0.0404 0.8863 0.988 0.000 0.012 0.000 0.000
#> GSM486761 1 0.0880 0.8760 0.968 0.000 0.032 0.000 0.000
#> GSM486763 5 0.0963 0.9741 0.000 0.000 0.036 0.000 0.964
#> GSM486765 1 0.0000 0.8868 1.000 0.000 0.000 0.000 0.000
#> GSM486767 3 0.5433 0.6708 0.192 0.028 0.716 0.024 0.040
#> GSM486769 4 0.2237 0.5945 0.000 0.004 0.084 0.904 0.008
#> GSM486771 2 0.3289 0.7621 0.000 0.844 0.108 0.048 0.000
#> GSM486773 3 0.4996 0.7029 0.204 0.052 0.720 0.024 0.000
#> GSM486775 1 0.0000 0.8868 1.000 0.000 0.000 0.000 0.000
#> GSM486777 1 0.1205 0.8653 0.956 0.000 0.040 0.004 0.000
#> GSM486779 2 0.2067 0.7875 0.000 0.920 0.048 0.032 0.000
#> GSM486781 3 0.5295 0.7002 0.192 0.092 0.700 0.016 0.000
#> GSM486783 2 0.0579 0.8343 0.000 0.984 0.008 0.008 0.000
#> GSM486785 1 0.0000 0.8868 1.000 0.000 0.000 0.000 0.000
#> GSM486787 1 0.0963 0.8797 0.964 0.000 0.036 0.000 0.000
#> GSM486789 4 0.6463 0.5398 0.000 0.212 0.300 0.488 0.000
#> GSM486791 5 0.0324 0.9838 0.004 0.000 0.004 0.000 0.992
#> GSM486793 1 0.1502 0.8519 0.940 0.000 0.056 0.004 0.000
#> GSM486795 1 0.5726 0.2942 0.604 0.080 0.304 0.012 0.000
#> GSM486797 3 0.5241 0.5918 0.356 0.040 0.596 0.008 0.000
#> GSM486799 1 0.0162 0.8860 0.996 0.000 0.004 0.000 0.000
#> GSM486801 1 0.0703 0.8837 0.976 0.000 0.024 0.000 0.000
#> GSM486803 1 0.1197 0.8726 0.952 0.000 0.048 0.000 0.000
#> GSM486805 3 0.5145 0.7056 0.224 0.052 0.700 0.024 0.000
#> GSM486807 1 0.0671 0.8851 0.980 0.000 0.016 0.004 0.000
#> GSM486809 4 0.5004 0.5330 0.000 0.000 0.216 0.692 0.092
#> GSM486811 1 0.0290 0.8860 0.992 0.000 0.008 0.000 0.000
#> GSM486813 2 0.0693 0.8333 0.000 0.980 0.008 0.012 0.000
#> GSM486815 1 0.1704 0.8435 0.928 0.000 0.068 0.004 0.000
#> GSM486817 3 0.5220 0.6105 0.340 0.036 0.612 0.012 0.000
#> GSM486819 3 0.5889 0.2079 0.104 0.000 0.504 0.000 0.392
#> GSM486822 4 0.2473 0.6032 0.000 0.072 0.032 0.896 0.000
#> GSM486824 1 0.0963 0.8789 0.964 0.000 0.036 0.000 0.000
#> GSM486828 3 0.5354 0.7066 0.208 0.080 0.692 0.020 0.000
#> GSM486831 1 0.0963 0.8797 0.964 0.000 0.036 0.000 0.000
#> GSM486833 3 0.5046 0.6318 0.328 0.020 0.632 0.020 0.000
#> GSM486835 1 0.0963 0.8797 0.964 0.000 0.036 0.000 0.000
#> GSM486837 3 0.6064 0.3907 0.096 0.392 0.504 0.008 0.000
#> GSM486839 1 0.0000 0.8868 1.000 0.000 0.000 0.000 0.000
#> GSM486841 1 0.0162 0.8860 0.996 0.000 0.004 0.000 0.000
#> GSM486843 1 0.2179 0.8210 0.896 0.004 0.100 0.000 0.000
#> GSM486845 3 0.5553 0.6968 0.204 0.124 0.664 0.008 0.000
#> GSM486847 1 0.0000 0.8868 1.000 0.000 0.000 0.000 0.000
#> GSM486849 2 0.2473 0.8055 0.000 0.896 0.072 0.032 0.000
#> GSM486851 5 0.0162 0.9844 0.000 0.000 0.004 0.000 0.996
#> GSM486853 2 0.0798 0.8347 0.000 0.976 0.016 0.008 0.000
#> GSM486855 2 0.1357 0.8237 0.000 0.948 0.048 0.004 0.000
#> GSM486857 3 0.6480 0.4626 0.124 0.372 0.488 0.016 0.000
#> GSM486736 4 0.3419 0.6093 0.000 0.000 0.180 0.804 0.016
#> GSM486738 2 0.2824 0.7800 0.000 0.864 0.020 0.116 0.000
#> GSM486740 3 0.6561 -0.2843 0.000 0.096 0.472 0.400 0.032
#> GSM486742 2 0.4930 0.3454 0.000 0.580 0.032 0.388 0.000
#> GSM486744 4 0.6649 0.4879 0.000 0.284 0.268 0.448 0.000
#> GSM486746 3 0.6600 -0.2802 0.000 0.100 0.468 0.400 0.032
#> GSM486748 1 0.5363 -0.0262 0.548 0.040 0.404 0.008 0.000
#> GSM486750 4 0.5137 0.0964 0.000 0.424 0.040 0.536 0.000
#> GSM486752 1 0.5574 -0.1971 0.504 0.044 0.440 0.012 0.000
#> GSM486754 4 0.6596 0.5130 0.000 0.256 0.280 0.464 0.000
#> GSM486756 2 0.5373 0.5137 0.000 0.652 0.112 0.236 0.000
#> GSM486758 1 0.4235 0.5039 0.656 0.000 0.336 0.008 0.000
#> GSM486760 1 0.0404 0.8863 0.988 0.000 0.012 0.000 0.000
#> GSM486762 1 0.0880 0.8760 0.968 0.000 0.032 0.000 0.000
#> GSM486764 5 0.0963 0.9741 0.000 0.000 0.036 0.000 0.964
#> GSM486766 1 0.0000 0.8868 1.000 0.000 0.000 0.000 0.000
#> GSM486768 3 0.5433 0.6708 0.192 0.028 0.716 0.024 0.040
#> GSM486770 4 0.2237 0.5945 0.000 0.004 0.084 0.904 0.008
#> GSM486772 2 0.3289 0.7621 0.000 0.844 0.108 0.048 0.000
#> GSM486774 3 0.4996 0.7029 0.204 0.052 0.720 0.024 0.000
#> GSM486776 1 0.0000 0.8868 1.000 0.000 0.000 0.000 0.000
#> GSM486778 1 0.1205 0.8653 0.956 0.000 0.040 0.004 0.000
#> GSM486780 2 0.2067 0.7875 0.000 0.920 0.048 0.032 0.000
#> GSM486782 3 0.5295 0.7002 0.192 0.092 0.700 0.016 0.000
#> GSM486784 2 0.0579 0.8343 0.000 0.984 0.008 0.008 0.000
#> GSM486786 1 0.0000 0.8868 1.000 0.000 0.000 0.000 0.000
#> GSM486788 1 0.0963 0.8797 0.964 0.000 0.036 0.000 0.000
#> GSM486790 4 0.6463 0.5398 0.000 0.212 0.300 0.488 0.000
#> GSM486792 5 0.0324 0.9838 0.004 0.000 0.004 0.000 0.992
#> GSM486794 1 0.1502 0.8519 0.940 0.000 0.056 0.004 0.000
#> GSM486796 1 0.5726 0.2942 0.604 0.080 0.304 0.012 0.000
#> GSM486798 3 0.5241 0.5918 0.356 0.040 0.596 0.008 0.000
#> GSM486800 1 0.0162 0.8860 0.996 0.000 0.004 0.000 0.000
#> GSM486802 1 0.0703 0.8837 0.976 0.000 0.024 0.000 0.000
#> GSM486804 1 0.1197 0.8726 0.952 0.000 0.048 0.000 0.000
#> GSM486806 3 0.5145 0.7056 0.224 0.052 0.700 0.024 0.000
#> GSM486808 1 0.0671 0.8851 0.980 0.000 0.016 0.004 0.000
#> GSM486810 4 0.5004 0.5330 0.000 0.000 0.216 0.692 0.092
#> GSM486812 1 0.0290 0.8860 0.992 0.000 0.008 0.000 0.000
#> GSM486814 2 0.0693 0.8333 0.000 0.980 0.008 0.012 0.000
#> GSM486816 1 0.1704 0.8435 0.928 0.000 0.068 0.004 0.000
#> GSM486818 3 0.5220 0.6105 0.340 0.036 0.612 0.012 0.000
#> GSM486821 3 0.5889 0.2079 0.104 0.000 0.504 0.000 0.392
#> GSM486823 4 0.2473 0.6032 0.000 0.072 0.032 0.896 0.000
#> GSM486826 1 0.0963 0.8789 0.964 0.000 0.036 0.000 0.000
#> GSM486830 3 0.5354 0.7066 0.208 0.080 0.692 0.020 0.000
#> GSM486832 1 0.0963 0.8797 0.964 0.000 0.036 0.000 0.000
#> GSM486834 3 0.5046 0.6318 0.328 0.020 0.632 0.020 0.000
#> GSM486836 1 0.0963 0.8797 0.964 0.000 0.036 0.000 0.000
#> GSM486838 3 0.6064 0.3907 0.096 0.392 0.504 0.008 0.000
#> GSM486840 1 0.0000 0.8868 1.000 0.000 0.000 0.000 0.000
#> GSM486842 1 0.0162 0.8860 0.996 0.000 0.004 0.000 0.000
#> GSM486844 1 0.2179 0.8210 0.896 0.004 0.100 0.000 0.000
#> GSM486846 3 0.5553 0.6968 0.204 0.124 0.664 0.008 0.000
#> GSM486848 1 0.0000 0.8868 1.000 0.000 0.000 0.000 0.000
#> GSM486850 2 0.2473 0.8055 0.000 0.896 0.072 0.032 0.000
#> GSM486852 5 0.0162 0.9844 0.000 0.000 0.004 0.000 0.996
#> GSM486854 2 0.0798 0.8347 0.000 0.976 0.016 0.008 0.000
#> GSM486856 2 0.1357 0.8237 0.000 0.948 0.048 0.004 0.000
#> GSM486858 3 0.6480 0.4626 0.124 0.372 0.488 0.016 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 6 0.4819 0.2163 0.000 0.000 0.416 0.056 0.000 0.528
#> GSM486737 2 0.2847 0.7474 0.000 0.852 0.016 0.012 0.000 0.120
#> GSM486739 4 0.7269 -0.4668 0.000 0.072 0.352 0.376 0.016 0.184
#> GSM486741 2 0.4585 0.2871 0.000 0.564 0.016 0.016 0.000 0.404
#> GSM486743 3 0.7718 0.6271 0.000 0.236 0.272 0.224 0.000 0.268
#> GSM486745 4 0.7305 -0.4658 0.000 0.076 0.352 0.372 0.016 0.184
#> GSM486747 1 0.4732 -0.1517 0.488 0.016 0.020 0.476 0.000 0.000
#> GSM486749 6 0.5015 0.1470 0.000 0.404 0.032 0.024 0.000 0.540
#> GSM486751 4 0.4791 0.2562 0.444 0.020 0.020 0.516 0.000 0.000
#> GSM486753 3 0.7679 0.6493 0.000 0.204 0.296 0.228 0.000 0.272
#> GSM486755 2 0.6040 0.4238 0.000 0.604 0.080 0.124 0.000 0.192
#> GSM486757 1 0.6062 0.0829 0.396 0.000 0.268 0.336 0.000 0.000
#> GSM486759 1 0.0713 0.8681 0.972 0.000 0.000 0.028 0.000 0.000
#> GSM486761 1 0.1765 0.8488 0.924 0.000 0.052 0.024 0.000 0.000
#> GSM486763 5 0.1765 0.9304 0.000 0.000 0.096 0.000 0.904 0.000
#> GSM486765 1 0.0363 0.8694 0.988 0.000 0.012 0.000 0.000 0.000
#> GSM486767 4 0.4334 0.6194 0.100 0.012 0.080 0.784 0.020 0.004
#> GSM486769 6 0.2800 0.5005 0.000 0.004 0.100 0.036 0.000 0.860
#> GSM486771 2 0.3656 0.7233 0.000 0.808 0.048 0.124 0.000 0.020
#> GSM486773 4 0.3181 0.6589 0.112 0.028 0.020 0.840 0.000 0.000
#> GSM486775 1 0.0363 0.8694 0.988 0.000 0.012 0.000 0.000 0.000
#> GSM486777 1 0.2165 0.8103 0.884 0.000 0.108 0.008 0.000 0.000
#> GSM486779 2 0.2978 0.7219 0.000 0.860 0.072 0.056 0.000 0.012
#> GSM486781 4 0.3355 0.6537 0.100 0.064 0.008 0.828 0.000 0.000
#> GSM486783 2 0.0717 0.8079 0.000 0.976 0.000 0.016 0.000 0.008
#> GSM486785 1 0.0000 0.8702 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486787 1 0.1204 0.8581 0.944 0.000 0.000 0.056 0.000 0.000
#> GSM486789 3 0.7550 0.6319 0.000 0.160 0.336 0.232 0.000 0.272
#> GSM486791 5 0.0260 0.9641 0.000 0.000 0.008 0.000 0.992 0.000
#> GSM486793 1 0.2909 0.7756 0.836 0.000 0.136 0.028 0.000 0.000
#> GSM486795 1 0.5520 0.2283 0.556 0.064 0.036 0.344 0.000 0.000
#> GSM486797 4 0.4162 0.6100 0.264 0.020 0.016 0.700 0.000 0.000
#> GSM486799 1 0.0146 0.8707 0.996 0.000 0.004 0.000 0.000 0.000
#> GSM486801 1 0.0937 0.8645 0.960 0.000 0.000 0.040 0.000 0.000
#> GSM486803 1 0.1913 0.8366 0.908 0.000 0.012 0.080 0.000 0.000
#> GSM486805 4 0.3657 0.6637 0.128 0.028 0.036 0.808 0.000 0.000
#> GSM486807 1 0.0725 0.8706 0.976 0.000 0.012 0.012 0.000 0.000
#> GSM486809 3 0.5123 -0.2881 0.000 0.000 0.528 0.056 0.012 0.404
#> GSM486811 1 0.0547 0.8684 0.980 0.000 0.020 0.000 0.000 0.000
#> GSM486813 2 0.0820 0.8067 0.000 0.972 0.000 0.012 0.000 0.016
#> GSM486815 1 0.3652 0.7104 0.768 0.000 0.188 0.044 0.000 0.000
#> GSM486817 4 0.4592 0.6223 0.232 0.012 0.064 0.692 0.000 0.000
#> GSM486819 4 0.6040 0.1939 0.072 0.000 0.064 0.492 0.372 0.000
#> GSM486822 6 0.1701 0.5064 0.000 0.072 0.000 0.008 0.000 0.920
#> GSM486824 1 0.0865 0.8668 0.964 0.000 0.000 0.036 0.000 0.000
#> GSM486828 4 0.3817 0.6620 0.120 0.056 0.024 0.800 0.000 0.000
#> GSM486831 1 0.1267 0.8561 0.940 0.000 0.000 0.060 0.000 0.000
#> GSM486833 4 0.4368 0.6256 0.224 0.004 0.056 0.712 0.000 0.004
#> GSM486835 1 0.1267 0.8561 0.940 0.000 0.000 0.060 0.000 0.000
#> GSM486837 4 0.5209 0.3795 0.048 0.356 0.020 0.572 0.000 0.004
#> GSM486839 1 0.0000 0.8702 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486841 1 0.0291 0.8703 0.992 0.000 0.004 0.004 0.000 0.000
#> GSM486843 1 0.2755 0.7705 0.844 0.004 0.012 0.140 0.000 0.000
#> GSM486845 4 0.3611 0.6503 0.108 0.096 0.000 0.796 0.000 0.000
#> GSM486847 1 0.0000 0.8702 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486849 2 0.2863 0.7710 0.000 0.864 0.036 0.088 0.000 0.012
#> GSM486851 5 0.0146 0.9645 0.000 0.000 0.004 0.000 0.996 0.000
#> GSM486853 2 0.0972 0.8084 0.000 0.964 0.000 0.028 0.000 0.008
#> GSM486855 2 0.2189 0.7859 0.000 0.904 0.032 0.060 0.000 0.004
#> GSM486857 4 0.5085 0.4116 0.048 0.340 0.016 0.592 0.000 0.004
#> GSM486736 6 0.4819 0.2163 0.000 0.000 0.416 0.056 0.000 0.528
#> GSM486738 2 0.2847 0.7474 0.000 0.852 0.016 0.012 0.000 0.120
#> GSM486740 4 0.7269 -0.4668 0.000 0.072 0.352 0.376 0.016 0.184
#> GSM486742 2 0.4585 0.2871 0.000 0.564 0.016 0.016 0.000 0.404
#> GSM486744 3 0.7718 0.6271 0.000 0.236 0.272 0.224 0.000 0.268
#> GSM486746 4 0.7305 -0.4658 0.000 0.076 0.352 0.372 0.016 0.184
#> GSM486748 1 0.4732 -0.1517 0.488 0.016 0.020 0.476 0.000 0.000
#> GSM486750 6 0.5015 0.1470 0.000 0.404 0.032 0.024 0.000 0.540
#> GSM486752 4 0.4791 0.2562 0.444 0.020 0.020 0.516 0.000 0.000
#> GSM486754 3 0.7679 0.6493 0.000 0.204 0.296 0.228 0.000 0.272
#> GSM486756 2 0.6040 0.4238 0.000 0.604 0.080 0.124 0.000 0.192
#> GSM486758 1 0.6062 0.0829 0.396 0.000 0.268 0.336 0.000 0.000
#> GSM486760 1 0.0713 0.8681 0.972 0.000 0.000 0.028 0.000 0.000
#> GSM486762 1 0.1765 0.8488 0.924 0.000 0.052 0.024 0.000 0.000
#> GSM486764 5 0.1765 0.9304 0.000 0.000 0.096 0.000 0.904 0.000
#> GSM486766 1 0.0363 0.8694 0.988 0.000 0.012 0.000 0.000 0.000
#> GSM486768 4 0.4334 0.6194 0.100 0.012 0.080 0.784 0.020 0.004
#> GSM486770 6 0.2800 0.5005 0.000 0.004 0.100 0.036 0.000 0.860
#> GSM486772 2 0.3656 0.7233 0.000 0.808 0.048 0.124 0.000 0.020
#> GSM486774 4 0.3181 0.6589 0.112 0.028 0.020 0.840 0.000 0.000
#> GSM486776 1 0.0363 0.8694 0.988 0.000 0.012 0.000 0.000 0.000
#> GSM486778 1 0.2165 0.8103 0.884 0.000 0.108 0.008 0.000 0.000
#> GSM486780 2 0.2978 0.7219 0.000 0.860 0.072 0.056 0.000 0.012
#> GSM486782 4 0.3355 0.6537 0.100 0.064 0.008 0.828 0.000 0.000
#> GSM486784 2 0.0717 0.8079 0.000 0.976 0.000 0.016 0.000 0.008
#> GSM486786 1 0.0000 0.8702 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486788 1 0.1204 0.8581 0.944 0.000 0.000 0.056 0.000 0.000
#> GSM486790 3 0.7550 0.6319 0.000 0.160 0.336 0.232 0.000 0.272
#> GSM486792 5 0.0260 0.9641 0.000 0.000 0.008 0.000 0.992 0.000
#> GSM486794 1 0.2909 0.7756 0.836 0.000 0.136 0.028 0.000 0.000
#> GSM486796 1 0.5520 0.2283 0.556 0.064 0.036 0.344 0.000 0.000
#> GSM486798 4 0.4162 0.6100 0.264 0.020 0.016 0.700 0.000 0.000
#> GSM486800 1 0.0146 0.8707 0.996 0.000 0.004 0.000 0.000 0.000
#> GSM486802 1 0.0937 0.8645 0.960 0.000 0.000 0.040 0.000 0.000
#> GSM486804 1 0.1913 0.8366 0.908 0.000 0.012 0.080 0.000 0.000
#> GSM486806 4 0.3657 0.6637 0.128 0.028 0.036 0.808 0.000 0.000
#> GSM486808 1 0.0725 0.8706 0.976 0.000 0.012 0.012 0.000 0.000
#> GSM486810 3 0.5123 -0.2881 0.000 0.000 0.528 0.056 0.012 0.404
#> GSM486812 1 0.0547 0.8684 0.980 0.000 0.020 0.000 0.000 0.000
#> GSM486814 2 0.0820 0.8067 0.000 0.972 0.000 0.012 0.000 0.016
#> GSM486816 1 0.3652 0.7104 0.768 0.000 0.188 0.044 0.000 0.000
#> GSM486818 4 0.4592 0.6223 0.232 0.012 0.064 0.692 0.000 0.000
#> GSM486821 4 0.6040 0.1939 0.072 0.000 0.064 0.492 0.372 0.000
#> GSM486823 6 0.1701 0.5064 0.000 0.072 0.000 0.008 0.000 0.920
#> GSM486826 1 0.0865 0.8668 0.964 0.000 0.000 0.036 0.000 0.000
#> GSM486830 4 0.3817 0.6620 0.120 0.056 0.024 0.800 0.000 0.000
#> GSM486832 1 0.1267 0.8561 0.940 0.000 0.000 0.060 0.000 0.000
#> GSM486834 4 0.4368 0.6256 0.224 0.004 0.056 0.712 0.000 0.004
#> GSM486836 1 0.1267 0.8561 0.940 0.000 0.000 0.060 0.000 0.000
#> GSM486838 4 0.5209 0.3795 0.048 0.356 0.020 0.572 0.000 0.004
#> GSM486840 1 0.0000 0.8702 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486842 1 0.0291 0.8703 0.992 0.000 0.004 0.004 0.000 0.000
#> GSM486844 1 0.2755 0.7705 0.844 0.004 0.012 0.140 0.000 0.000
#> GSM486846 4 0.3611 0.6503 0.108 0.096 0.000 0.796 0.000 0.000
#> GSM486848 1 0.0000 0.8702 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486850 2 0.2863 0.7710 0.000 0.864 0.036 0.088 0.000 0.012
#> GSM486852 5 0.0146 0.9645 0.000 0.000 0.004 0.000 0.996 0.000
#> GSM486854 2 0.0972 0.8084 0.000 0.964 0.000 0.028 0.000 0.008
#> GSM486856 2 0.2189 0.7859 0.000 0.904 0.032 0.060 0.000 0.004
#> GSM486858 4 0.5085 0.4116 0.048 0.340 0.016 0.592 0.000 0.004
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> SD:hclust 102 1 2.01e-05 2
#> SD:hclust 96 1 1.07e-08 3
#> SD:hclust 78 1 2.70e-10 4
#> SD:hclust 98 1 8.18e-16 5
#> SD:hclust 92 1 2.88e-18 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["SD", "kmeans"]
# you can also extract it by
# res = res_list["SD:kmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'SD' method.
#> Subgroups are detected by 'kmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.931 0.903 0.956 0.5024 0.497 0.497
#> 3 3 0.569 0.680 0.824 0.2726 0.798 0.615
#> 4 4 0.533 0.599 0.725 0.1242 0.854 0.617
#> 5 5 0.623 0.683 0.772 0.0619 0.918 0.725
#> 6 6 0.646 0.458 0.725 0.0465 0.978 0.912
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 2 0.1414 0.9779 0.020 0.980
#> GSM486737 2 0.1414 0.9779 0.020 0.980
#> GSM486739 2 0.1414 0.9779 0.020 0.980
#> GSM486741 2 0.1414 0.9779 0.020 0.980
#> GSM486743 2 0.1414 0.9779 0.020 0.980
#> GSM486745 2 0.1414 0.9779 0.020 0.980
#> GSM486747 1 0.0000 0.9318 1.000 0.000
#> GSM486749 2 0.1414 0.9779 0.020 0.980
#> GSM486751 1 0.0000 0.9318 1.000 0.000
#> GSM486753 2 0.1414 0.9779 0.020 0.980
#> GSM486755 2 0.1414 0.9779 0.020 0.980
#> GSM486757 1 0.0000 0.9318 1.000 0.000
#> GSM486759 1 0.0000 0.9318 1.000 0.000
#> GSM486761 1 0.0000 0.9318 1.000 0.000
#> GSM486763 1 0.7376 0.7278 0.792 0.208
#> GSM486765 1 0.0000 0.9318 1.000 0.000
#> GSM486767 2 0.1414 0.9779 0.020 0.980
#> GSM486769 2 0.1414 0.9779 0.020 0.980
#> GSM486771 2 0.1414 0.9779 0.020 0.980
#> GSM486773 2 0.1414 0.9779 0.020 0.980
#> GSM486775 1 0.0000 0.9318 1.000 0.000
#> GSM486777 1 0.0000 0.9318 1.000 0.000
#> GSM486779 2 0.1414 0.9779 0.020 0.980
#> GSM486781 2 0.1414 0.9779 0.020 0.980
#> GSM486783 2 0.1414 0.9779 0.020 0.980
#> GSM486785 1 0.0000 0.9318 1.000 0.000
#> GSM486787 1 0.0000 0.9318 1.000 0.000
#> GSM486789 2 0.1414 0.9779 0.020 0.980
#> GSM486791 1 0.0000 0.9318 1.000 0.000
#> GSM486793 1 0.0000 0.9318 1.000 0.000
#> GSM486795 1 0.2603 0.9031 0.956 0.044
#> GSM486797 1 0.9552 0.4290 0.624 0.376
#> GSM486799 1 0.0000 0.9318 1.000 0.000
#> GSM486801 1 0.0000 0.9318 1.000 0.000
#> GSM486803 1 0.0000 0.9318 1.000 0.000
#> GSM486805 2 0.4431 0.9035 0.092 0.908
#> GSM486807 1 0.0000 0.9318 1.000 0.000
#> GSM486809 2 0.1414 0.9779 0.020 0.980
#> GSM486811 1 0.0000 0.9318 1.000 0.000
#> GSM486813 2 0.1414 0.9779 0.020 0.980
#> GSM486815 1 0.0000 0.9318 1.000 0.000
#> GSM486817 1 0.9983 0.1438 0.524 0.476
#> GSM486819 1 0.9996 0.1007 0.512 0.488
#> GSM486822 2 0.1414 0.9779 0.020 0.980
#> GSM486824 1 0.0000 0.9318 1.000 0.000
#> GSM486828 2 0.1414 0.9779 0.020 0.980
#> GSM486831 1 0.0000 0.9318 1.000 0.000
#> GSM486833 1 0.9710 0.3722 0.600 0.400
#> GSM486835 1 0.0000 0.9318 1.000 0.000
#> GSM486837 2 0.1414 0.9779 0.020 0.980
#> GSM486839 1 0.0000 0.9318 1.000 0.000
#> GSM486841 1 0.0000 0.9318 1.000 0.000
#> GSM486843 1 0.0000 0.9318 1.000 0.000
#> GSM486845 2 0.1414 0.9779 0.020 0.980
#> GSM486847 1 0.0000 0.9318 1.000 0.000
#> GSM486849 2 0.1414 0.9779 0.020 0.980
#> GSM486851 1 0.0000 0.9318 1.000 0.000
#> GSM486853 2 0.1414 0.9779 0.020 0.980
#> GSM486855 2 0.1414 0.9779 0.020 0.980
#> GSM486857 2 0.1414 0.9779 0.020 0.980
#> GSM486736 2 0.0000 0.9782 0.000 1.000
#> GSM486738 2 0.0000 0.9782 0.000 1.000
#> GSM486740 2 0.0000 0.9782 0.000 1.000
#> GSM486742 2 0.0000 0.9782 0.000 1.000
#> GSM486744 2 0.0000 0.9782 0.000 1.000
#> GSM486746 2 0.0000 0.9782 0.000 1.000
#> GSM486748 1 0.1414 0.9318 0.980 0.020
#> GSM486750 2 0.0000 0.9782 0.000 1.000
#> GSM486752 1 0.1414 0.9318 0.980 0.020
#> GSM486754 2 0.0000 0.9782 0.000 1.000
#> GSM486756 2 0.0000 0.9782 0.000 1.000
#> GSM486758 1 0.1414 0.9318 0.980 0.020
#> GSM486760 1 0.1414 0.9318 0.980 0.020
#> GSM486762 1 0.1414 0.9318 0.980 0.020
#> GSM486764 1 0.7745 0.7278 0.772 0.228
#> GSM486766 1 0.1414 0.9318 0.980 0.020
#> GSM486768 2 0.0000 0.9782 0.000 1.000
#> GSM486770 2 0.0000 0.9782 0.000 1.000
#> GSM486772 2 0.0000 0.9782 0.000 1.000
#> GSM486774 2 0.0000 0.9782 0.000 1.000
#> GSM486776 1 0.1414 0.9318 0.980 0.020
#> GSM486778 1 0.1414 0.9318 0.980 0.020
#> GSM486780 2 0.0000 0.9782 0.000 1.000
#> GSM486782 2 0.0000 0.9782 0.000 1.000
#> GSM486784 2 0.0000 0.9782 0.000 1.000
#> GSM486786 1 0.1414 0.9318 0.980 0.020
#> GSM486788 1 0.1414 0.9318 0.980 0.020
#> GSM486790 2 0.0000 0.9782 0.000 1.000
#> GSM486792 1 0.1414 0.9318 0.980 0.020
#> GSM486794 1 0.1414 0.9318 0.980 0.020
#> GSM486796 1 0.3274 0.9064 0.940 0.060
#> GSM486798 1 0.9909 0.3091 0.556 0.444
#> GSM486800 1 0.1414 0.9318 0.980 0.020
#> GSM486802 1 0.1414 0.9318 0.980 0.020
#> GSM486804 1 0.1414 0.9318 0.980 0.020
#> GSM486806 2 0.0376 0.9759 0.004 0.996
#> GSM486808 1 0.1414 0.9318 0.980 0.020
#> GSM486810 2 0.0000 0.9782 0.000 1.000
#> GSM486812 1 0.1414 0.9318 0.980 0.020
#> GSM486814 2 0.0000 0.9782 0.000 1.000
#> GSM486816 1 0.1414 0.9318 0.980 0.020
#> GSM486818 1 0.9850 0.3507 0.572 0.428
#> GSM486821 2 0.9977 -0.0537 0.472 0.528
#> GSM486823 2 0.0000 0.9782 0.000 1.000
#> GSM486826 1 0.1414 0.9318 0.980 0.020
#> GSM486830 2 0.0000 0.9782 0.000 1.000
#> GSM486832 1 0.1414 0.9318 0.980 0.020
#> GSM486834 1 0.9866 0.3418 0.568 0.432
#> GSM486836 1 0.1414 0.9318 0.980 0.020
#> GSM486838 2 0.0000 0.9782 0.000 1.000
#> GSM486840 1 0.1414 0.9318 0.980 0.020
#> GSM486842 1 0.1414 0.9318 0.980 0.020
#> GSM486844 1 0.1414 0.9318 0.980 0.020
#> GSM486846 2 0.0000 0.9782 0.000 1.000
#> GSM486848 1 0.1414 0.9318 0.980 0.020
#> GSM486850 2 0.0000 0.9782 0.000 1.000
#> GSM486852 1 0.1414 0.9318 0.980 0.020
#> GSM486854 2 0.0000 0.9782 0.000 1.000
#> GSM486856 2 0.0000 0.9782 0.000 1.000
#> GSM486858 2 0.0000 0.9782 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 1 0.6274 0.161 0.544 0.456 0.000
#> GSM486737 2 0.1411 0.809 0.036 0.964 0.000
#> GSM486739 1 0.5968 0.413 0.636 0.364 0.000
#> GSM486741 2 0.1753 0.804 0.048 0.952 0.000
#> GSM486743 2 0.0747 0.820 0.016 0.984 0.000
#> GSM486745 1 0.6180 0.393 0.584 0.416 0.000
#> GSM486747 3 0.4399 0.740 0.188 0.000 0.812
#> GSM486749 2 0.3340 0.777 0.120 0.880 0.000
#> GSM486751 3 0.7159 0.197 0.448 0.024 0.528
#> GSM486753 2 0.3686 0.759 0.140 0.860 0.000
#> GSM486755 2 0.3038 0.786 0.104 0.896 0.000
#> GSM486757 3 0.6299 0.230 0.476 0.000 0.524
#> GSM486759 3 0.0892 0.880 0.020 0.000 0.980
#> GSM486761 3 0.1163 0.879 0.028 0.000 0.972
#> GSM486763 1 0.5407 0.538 0.804 0.040 0.156
#> GSM486765 3 0.0592 0.881 0.012 0.000 0.988
#> GSM486767 1 0.6204 0.430 0.576 0.424 0.000
#> GSM486769 2 0.6215 0.226 0.428 0.572 0.000
#> GSM486771 2 0.0747 0.818 0.016 0.984 0.000
#> GSM486773 1 0.6215 0.416 0.572 0.428 0.000
#> GSM486775 3 0.0424 0.881 0.008 0.000 0.992
#> GSM486777 3 0.2356 0.862 0.072 0.000 0.928
#> GSM486779 2 0.2165 0.790 0.064 0.936 0.000
#> GSM486781 2 0.5529 0.511 0.296 0.704 0.000
#> GSM486783 2 0.0237 0.819 0.004 0.996 0.000
#> GSM486785 3 0.1031 0.880 0.024 0.000 0.976
#> GSM486787 3 0.0892 0.880 0.020 0.000 0.980
#> GSM486789 2 0.4931 0.650 0.232 0.768 0.000
#> GSM486791 3 0.6252 0.340 0.444 0.000 0.556
#> GSM486793 3 0.2625 0.858 0.084 0.000 0.916
#> GSM486795 3 0.7727 0.370 0.336 0.064 0.600
#> GSM486797 1 0.9585 0.432 0.456 0.212 0.332
#> GSM486799 3 0.0892 0.880 0.020 0.000 0.980
#> GSM486801 3 0.1031 0.880 0.024 0.000 0.976
#> GSM486803 3 0.1163 0.879 0.028 0.000 0.972
#> GSM486805 1 0.8044 0.531 0.600 0.312 0.088
#> GSM486807 3 0.1031 0.879 0.024 0.000 0.976
#> GSM486809 1 0.5560 0.473 0.700 0.300 0.000
#> GSM486811 3 0.1031 0.880 0.024 0.000 0.976
#> GSM486813 2 0.0237 0.819 0.004 0.996 0.000
#> GSM486815 3 0.2356 0.862 0.072 0.000 0.928
#> GSM486817 1 0.9582 0.497 0.472 0.228 0.300
#> GSM486819 1 0.5263 0.576 0.828 0.088 0.084
#> GSM486822 2 0.5254 0.606 0.264 0.736 0.000
#> GSM486824 3 0.0892 0.880 0.020 0.000 0.980
#> GSM486828 1 0.6180 0.437 0.584 0.416 0.000
#> GSM486831 3 0.1163 0.879 0.028 0.000 0.972
#> GSM486833 1 0.8290 0.571 0.632 0.164 0.204
#> GSM486835 3 0.1163 0.879 0.028 0.000 0.972
#> GSM486837 2 0.4555 0.627 0.200 0.800 0.000
#> GSM486839 3 0.0892 0.880 0.020 0.000 0.980
#> GSM486841 3 0.0892 0.880 0.020 0.000 0.980
#> GSM486843 3 0.1163 0.879 0.028 0.000 0.972
#> GSM486845 2 0.4931 0.598 0.232 0.768 0.000
#> GSM486847 3 0.0892 0.880 0.020 0.000 0.980
#> GSM486849 2 0.0592 0.818 0.012 0.988 0.000
#> GSM486851 1 0.5650 0.326 0.688 0.000 0.312
#> GSM486853 2 0.0424 0.819 0.008 0.992 0.000
#> GSM486855 2 0.1964 0.794 0.056 0.944 0.000
#> GSM486857 2 0.4504 0.629 0.196 0.804 0.000
#> GSM486736 1 0.6274 0.161 0.544 0.456 0.000
#> GSM486738 2 0.1411 0.809 0.036 0.964 0.000
#> GSM486740 1 0.5968 0.413 0.636 0.364 0.000
#> GSM486742 2 0.1753 0.804 0.048 0.952 0.000
#> GSM486744 2 0.0424 0.820 0.008 0.992 0.000
#> GSM486746 1 0.6180 0.393 0.584 0.416 0.000
#> GSM486748 3 0.4931 0.736 0.212 0.004 0.784
#> GSM486750 2 0.3340 0.777 0.120 0.880 0.000
#> GSM486752 3 0.7063 0.241 0.464 0.020 0.516
#> GSM486754 2 0.3192 0.781 0.112 0.888 0.000
#> GSM486756 2 0.3038 0.786 0.104 0.896 0.000
#> GSM486758 3 0.6309 0.237 0.500 0.000 0.500
#> GSM486760 3 0.1643 0.880 0.044 0.000 0.956
#> GSM486762 3 0.1860 0.880 0.052 0.000 0.948
#> GSM486764 1 0.4676 0.539 0.848 0.040 0.112
#> GSM486766 3 0.1753 0.880 0.048 0.000 0.952
#> GSM486768 1 0.6204 0.430 0.576 0.424 0.000
#> GSM486770 2 0.6215 0.226 0.428 0.572 0.000
#> GSM486772 2 0.0747 0.818 0.016 0.984 0.000
#> GSM486774 1 0.6215 0.416 0.572 0.428 0.000
#> GSM486776 3 0.1643 0.880 0.044 0.000 0.956
#> GSM486778 3 0.2878 0.864 0.096 0.000 0.904
#> GSM486780 2 0.2165 0.790 0.064 0.936 0.000
#> GSM486782 2 0.5497 0.521 0.292 0.708 0.000
#> GSM486784 2 0.0237 0.819 0.004 0.996 0.000
#> GSM486786 3 0.1753 0.880 0.048 0.000 0.952
#> GSM486788 3 0.1643 0.880 0.044 0.000 0.956
#> GSM486790 2 0.4931 0.650 0.232 0.768 0.000
#> GSM486792 3 0.6307 0.342 0.488 0.000 0.512
#> GSM486794 3 0.3116 0.860 0.108 0.000 0.892
#> GSM486796 3 0.7841 0.375 0.360 0.064 0.576
#> GSM486798 1 0.9519 0.461 0.484 0.224 0.292
#> GSM486800 3 0.1643 0.880 0.044 0.000 0.956
#> GSM486802 3 0.1753 0.880 0.048 0.000 0.952
#> GSM486804 3 0.1860 0.880 0.052 0.000 0.948
#> GSM486806 1 0.6832 0.479 0.604 0.376 0.020
#> GSM486808 3 0.1753 0.880 0.048 0.000 0.952
#> GSM486810 1 0.5560 0.473 0.700 0.300 0.000
#> GSM486812 3 0.1753 0.880 0.048 0.000 0.952
#> GSM486814 2 0.0237 0.819 0.004 0.996 0.000
#> GSM486816 3 0.2878 0.864 0.096 0.000 0.904
#> GSM486818 1 0.9461 0.488 0.496 0.224 0.280
#> GSM486821 1 0.4289 0.577 0.868 0.092 0.040
#> GSM486823 2 0.5254 0.606 0.264 0.736 0.000
#> GSM486826 3 0.1643 0.880 0.044 0.000 0.956
#> GSM486830 1 0.6180 0.437 0.584 0.416 0.000
#> GSM486832 3 0.1860 0.880 0.052 0.000 0.948
#> GSM486834 1 0.8028 0.569 0.656 0.168 0.176
#> GSM486836 3 0.1860 0.880 0.052 0.000 0.948
#> GSM486838 2 0.4883 0.612 0.208 0.788 0.004
#> GSM486840 3 0.1643 0.880 0.044 0.000 0.956
#> GSM486842 3 0.1643 0.880 0.044 0.000 0.956
#> GSM486844 3 0.1860 0.880 0.052 0.000 0.948
#> GSM486846 2 0.4931 0.598 0.232 0.768 0.000
#> GSM486848 3 0.1643 0.880 0.044 0.000 0.956
#> GSM486850 2 0.0592 0.818 0.012 0.988 0.000
#> GSM486852 1 0.5291 0.326 0.732 0.000 0.268
#> GSM486854 2 0.0424 0.819 0.008 0.992 0.000
#> GSM486856 2 0.1964 0.794 0.056 0.944 0.000
#> GSM486858 2 0.4291 0.653 0.180 0.820 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 4 0.5913 0.5263 0.124 0.180 0.000 0.696
#> GSM486737 2 0.2714 0.6639 0.004 0.884 0.000 0.112
#> GSM486739 4 0.6756 0.5115 0.252 0.148 0.000 0.600
#> GSM486741 2 0.2814 0.6485 0.000 0.868 0.000 0.132
#> GSM486743 2 0.1854 0.7139 0.048 0.940 0.000 0.012
#> GSM486745 4 0.7416 0.2402 0.392 0.168 0.000 0.440
#> GSM486747 3 0.5558 0.0222 0.432 0.000 0.548 0.020
#> GSM486749 2 0.5442 0.4404 0.040 0.672 0.000 0.288
#> GSM486751 1 0.5758 0.5541 0.696 0.028 0.248 0.028
#> GSM486753 2 0.6444 0.3541 0.104 0.612 0.000 0.284
#> GSM486755 2 0.4988 0.5319 0.036 0.728 0.000 0.236
#> GSM486757 1 0.6419 0.4707 0.640 0.016 0.276 0.068
#> GSM486759 3 0.1388 0.8899 0.028 0.000 0.960 0.012
#> GSM486761 3 0.2124 0.8805 0.068 0.000 0.924 0.008
#> GSM486763 4 0.5790 0.3501 0.304 0.004 0.044 0.648
#> GSM486765 3 0.0817 0.8948 0.024 0.000 0.976 0.000
#> GSM486767 1 0.6595 0.5001 0.628 0.212 0.000 0.160
#> GSM486769 4 0.5964 0.4774 0.096 0.228 0.000 0.676
#> GSM486771 2 0.1488 0.7157 0.032 0.956 0.000 0.012
#> GSM486773 1 0.6118 0.5371 0.672 0.208 0.000 0.120
#> GSM486775 3 0.0592 0.8972 0.016 0.000 0.984 0.000
#> GSM486777 3 0.3471 0.8392 0.072 0.000 0.868 0.060
#> GSM486779 2 0.3245 0.6815 0.100 0.872 0.000 0.028
#> GSM486781 1 0.6762 0.3206 0.536 0.360 0.000 0.104
#> GSM486783 2 0.0336 0.7137 0.008 0.992 0.000 0.000
#> GSM486785 3 0.1584 0.8884 0.036 0.000 0.952 0.012
#> GSM486787 3 0.1488 0.8893 0.032 0.000 0.956 0.012
#> GSM486789 2 0.7003 -0.0165 0.116 0.460 0.000 0.424
#> GSM486791 4 0.7853 0.1248 0.292 0.000 0.308 0.400
#> GSM486793 3 0.4022 0.8166 0.096 0.000 0.836 0.068
#> GSM486795 1 0.6707 0.5055 0.592 0.052 0.328 0.028
#> GSM486797 1 0.5854 0.6152 0.724 0.096 0.168 0.012
#> GSM486799 3 0.1151 0.8900 0.024 0.000 0.968 0.008
#> GSM486801 3 0.1706 0.8879 0.036 0.000 0.948 0.016
#> GSM486803 3 0.1888 0.8858 0.044 0.000 0.940 0.016
#> GSM486805 1 0.5771 0.6114 0.748 0.128 0.100 0.024
#> GSM486807 3 0.2198 0.8801 0.072 0.000 0.920 0.008
#> GSM486809 4 0.5633 0.5521 0.184 0.100 0.000 0.716
#> GSM486811 3 0.1356 0.8893 0.032 0.000 0.960 0.008
#> GSM486813 2 0.0469 0.7145 0.012 0.988 0.000 0.000
#> GSM486815 3 0.3761 0.8306 0.080 0.000 0.852 0.068
#> GSM486817 1 0.6272 0.6234 0.700 0.132 0.152 0.016
#> GSM486819 1 0.7089 0.0715 0.512 0.036 0.052 0.400
#> GSM486822 4 0.6209 -0.0160 0.052 0.456 0.000 0.492
#> GSM486824 3 0.1706 0.8890 0.036 0.000 0.948 0.016
#> GSM486828 1 0.5889 0.5535 0.688 0.212 0.000 0.100
#> GSM486831 3 0.1798 0.8868 0.040 0.000 0.944 0.016
#> GSM486833 1 0.5576 0.5973 0.768 0.056 0.128 0.048
#> GSM486835 3 0.1888 0.8858 0.044 0.000 0.940 0.016
#> GSM486837 2 0.5731 0.0783 0.428 0.544 0.000 0.028
#> GSM486839 3 0.1151 0.8904 0.024 0.000 0.968 0.008
#> GSM486841 3 0.1209 0.8895 0.032 0.000 0.964 0.004
#> GSM486843 3 0.2142 0.8820 0.056 0.000 0.928 0.016
#> GSM486845 2 0.5764 -0.0249 0.452 0.520 0.000 0.028
#> GSM486847 3 0.1297 0.8893 0.016 0.000 0.964 0.020
#> GSM486849 2 0.1305 0.7147 0.036 0.960 0.000 0.004
#> GSM486851 4 0.6911 0.2775 0.304 0.000 0.136 0.560
#> GSM486853 2 0.0336 0.7137 0.008 0.992 0.000 0.000
#> GSM486855 2 0.3143 0.6824 0.100 0.876 0.000 0.024
#> GSM486857 2 0.5279 0.1670 0.400 0.588 0.000 0.012
#> GSM486736 4 0.5923 0.5263 0.128 0.176 0.000 0.696
#> GSM486738 2 0.3325 0.6640 0.024 0.864 0.000 0.112
#> GSM486740 4 0.6747 0.5117 0.264 0.140 0.000 0.596
#> GSM486742 2 0.3501 0.6488 0.020 0.848 0.000 0.132
#> GSM486744 2 0.2101 0.7160 0.060 0.928 0.000 0.012
#> GSM486746 4 0.7282 0.2396 0.416 0.148 0.000 0.436
#> GSM486748 1 0.5281 -0.0418 0.528 0.000 0.464 0.008
#> GSM486750 2 0.5815 0.4412 0.060 0.652 0.000 0.288
#> GSM486752 1 0.4486 0.5450 0.784 0.008 0.188 0.020
#> GSM486754 2 0.6592 0.3703 0.116 0.600 0.000 0.284
#> GSM486756 2 0.5386 0.5326 0.056 0.708 0.000 0.236
#> GSM486758 1 0.5292 0.4600 0.724 0.000 0.216 0.060
#> GSM486760 3 0.2799 0.8910 0.108 0.000 0.884 0.008
#> GSM486762 3 0.3208 0.8808 0.148 0.000 0.848 0.004
#> GSM486764 4 0.5540 0.3531 0.320 0.004 0.028 0.648
#> GSM486766 3 0.2647 0.8892 0.120 0.000 0.880 0.000
#> GSM486768 1 0.6388 0.5004 0.652 0.192 0.000 0.156
#> GSM486770 4 0.6010 0.4770 0.104 0.220 0.000 0.676
#> GSM486772 2 0.1854 0.7163 0.048 0.940 0.000 0.012
#> GSM486774 1 0.5889 0.5374 0.696 0.188 0.000 0.116
#> GSM486776 3 0.2469 0.8913 0.108 0.000 0.892 0.000
#> GSM486778 3 0.4562 0.8432 0.152 0.000 0.792 0.056
#> GSM486780 2 0.3542 0.6814 0.120 0.852 0.000 0.028
#> GSM486782 1 0.6649 0.3198 0.560 0.340 0.000 0.100
#> GSM486784 2 0.0921 0.7137 0.028 0.972 0.000 0.000
#> GSM486786 3 0.2918 0.8893 0.116 0.000 0.876 0.008
#> GSM486788 3 0.2859 0.8905 0.112 0.000 0.880 0.008
#> GSM486790 2 0.7187 -0.0149 0.136 0.440 0.000 0.424
#> GSM486792 4 0.7835 0.1246 0.336 0.000 0.268 0.396
#> GSM486794 3 0.4979 0.8211 0.176 0.000 0.760 0.064
#> GSM486796 1 0.5684 0.5063 0.696 0.032 0.252 0.020
#> GSM486798 1 0.4362 0.6151 0.828 0.076 0.088 0.008
#> GSM486800 3 0.2593 0.8908 0.104 0.000 0.892 0.004
#> GSM486802 3 0.3047 0.8896 0.116 0.000 0.872 0.012
#> GSM486804 3 0.3161 0.8877 0.124 0.000 0.864 0.012
#> GSM486806 1 0.4256 0.6084 0.824 0.132 0.012 0.032
#> GSM486808 3 0.3257 0.8807 0.152 0.000 0.844 0.004
#> GSM486810 4 0.5632 0.5520 0.196 0.092 0.000 0.712
#> GSM486812 3 0.2714 0.8901 0.112 0.000 0.884 0.004
#> GSM486814 2 0.1022 0.7145 0.032 0.968 0.000 0.000
#> GSM486816 3 0.4804 0.8342 0.160 0.000 0.776 0.064
#> GSM486818 1 0.4852 0.6218 0.800 0.112 0.076 0.012
#> GSM486821 1 0.6389 0.0782 0.544 0.032 0.020 0.404
#> GSM486823 4 0.6330 -0.0172 0.060 0.448 0.000 0.492
#> GSM486826 3 0.3047 0.8902 0.116 0.000 0.872 0.012
#> GSM486830 1 0.5653 0.5537 0.712 0.192 0.000 0.096
#> GSM486832 3 0.3105 0.8887 0.120 0.000 0.868 0.012
#> GSM486834 1 0.4015 0.6002 0.860 0.036 0.056 0.048
#> GSM486836 3 0.3161 0.8877 0.124 0.000 0.864 0.012
#> GSM486838 2 0.5688 0.0499 0.464 0.512 0.000 0.024
#> GSM486840 3 0.2593 0.8912 0.104 0.000 0.892 0.004
#> GSM486842 3 0.2530 0.8903 0.112 0.000 0.888 0.000
#> GSM486844 3 0.3324 0.8839 0.136 0.000 0.852 0.012
#> GSM486846 2 0.5693 -0.0102 0.472 0.504 0.000 0.024
#> GSM486848 3 0.2861 0.8902 0.096 0.000 0.888 0.016
#> GSM486850 2 0.1743 0.7148 0.056 0.940 0.000 0.004
#> GSM486852 4 0.6794 0.2779 0.328 0.000 0.116 0.556
#> GSM486854 2 0.0921 0.7137 0.028 0.972 0.000 0.000
#> GSM486856 2 0.3441 0.6824 0.120 0.856 0.000 0.024
#> GSM486858 2 0.5220 0.1676 0.424 0.568 0.000 0.008
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 4 0.4507 0.662 0.000 0.120 0.044 0.788 0.048
#> GSM486737 2 0.2685 0.751 0.000 0.880 0.000 0.092 0.028
#> GSM486739 4 0.6233 0.558 0.000 0.068 0.188 0.648 0.096
#> GSM486741 2 0.3085 0.735 0.000 0.852 0.000 0.116 0.032
#> GSM486743 2 0.3485 0.746 0.000 0.852 0.072 0.060 0.016
#> GSM486745 4 0.6901 0.388 0.000 0.100 0.360 0.484 0.056
#> GSM486747 3 0.5912 0.382 0.248 0.000 0.628 0.020 0.104
#> GSM486749 2 0.5301 0.282 0.000 0.576 0.024 0.380 0.020
#> GSM486751 3 0.4456 0.619 0.048 0.024 0.804 0.016 0.108
#> GSM486753 2 0.6136 0.183 0.000 0.536 0.076 0.364 0.024
#> GSM486755 2 0.5523 0.503 0.000 0.652 0.044 0.268 0.036
#> GSM486757 3 0.6173 0.404 0.056 0.020 0.628 0.032 0.264
#> GSM486759 1 0.4267 0.833 0.784 0.000 0.092 0.004 0.120
#> GSM486761 1 0.5283 0.814 0.720 0.000 0.112 0.024 0.144
#> GSM486763 5 0.5297 0.716 0.008 0.000 0.060 0.292 0.640
#> GSM486765 1 0.4503 0.832 0.776 0.000 0.096 0.012 0.116
#> GSM486767 3 0.4886 0.638 0.000 0.072 0.756 0.140 0.032
#> GSM486769 4 0.4062 0.673 0.000 0.168 0.028 0.788 0.016
#> GSM486771 2 0.1483 0.788 0.000 0.952 0.028 0.012 0.008
#> GSM486773 3 0.4076 0.689 0.000 0.076 0.812 0.096 0.016
#> GSM486775 1 0.3906 0.838 0.812 0.000 0.080 0.004 0.104
#> GSM486777 1 0.6099 0.705 0.600 0.000 0.100 0.024 0.276
#> GSM486779 2 0.4004 0.706 0.000 0.824 0.080 0.028 0.068
#> GSM486781 3 0.4535 0.679 0.000 0.128 0.772 0.088 0.012
#> GSM486783 2 0.0451 0.786 0.000 0.988 0.008 0.000 0.004
#> GSM486785 1 0.4960 0.819 0.740 0.000 0.100 0.016 0.144
#> GSM486787 1 0.4267 0.833 0.784 0.000 0.092 0.004 0.120
#> GSM486789 4 0.6135 0.514 0.000 0.296 0.120 0.572 0.012
#> GSM486791 5 0.5742 0.670 0.116 0.000 0.056 0.128 0.700
#> GSM486793 1 0.6484 0.639 0.548 0.000 0.100 0.036 0.316
#> GSM486795 3 0.6170 0.473 0.148 0.024 0.664 0.016 0.148
#> GSM486797 3 0.3460 0.664 0.024 0.036 0.860 0.004 0.076
#> GSM486799 1 0.3849 0.834 0.808 0.000 0.080 0.000 0.112
#> GSM486801 1 0.4267 0.833 0.784 0.000 0.092 0.004 0.120
#> GSM486803 1 0.4640 0.829 0.764 0.000 0.096 0.012 0.128
#> GSM486805 3 0.2547 0.700 0.012 0.036 0.912 0.028 0.012
#> GSM486807 1 0.4939 0.826 0.744 0.000 0.116 0.016 0.124
#> GSM486809 4 0.4985 0.493 0.000 0.044 0.056 0.748 0.152
#> GSM486811 1 0.5079 0.815 0.728 0.000 0.100 0.016 0.156
#> GSM486813 2 0.0798 0.786 0.000 0.976 0.008 0.000 0.016
#> GSM486815 1 0.6322 0.658 0.568 0.000 0.088 0.036 0.308
#> GSM486817 3 0.2927 0.694 0.024 0.040 0.892 0.004 0.040
#> GSM486819 5 0.6863 0.507 0.004 0.008 0.348 0.192 0.448
#> GSM486822 4 0.5136 0.469 0.000 0.332 0.016 0.624 0.028
#> GSM486824 1 0.4583 0.833 0.776 0.000 0.084 0.020 0.120
#> GSM486828 3 0.3947 0.691 0.000 0.072 0.824 0.084 0.020
#> GSM486831 1 0.4267 0.833 0.784 0.000 0.092 0.004 0.120
#> GSM486833 3 0.3359 0.684 0.008 0.028 0.868 0.024 0.072
#> GSM486835 1 0.4595 0.830 0.768 0.000 0.096 0.012 0.124
#> GSM486837 3 0.5564 0.555 0.000 0.328 0.596 0.008 0.068
#> GSM486839 1 0.4013 0.836 0.804 0.000 0.084 0.004 0.108
#> GSM486841 1 0.4450 0.832 0.780 0.000 0.092 0.012 0.116
#> GSM486843 1 0.4640 0.829 0.764 0.000 0.096 0.012 0.128
#> GSM486845 3 0.5287 0.606 0.000 0.292 0.648 0.028 0.032
#> GSM486847 1 0.4228 0.836 0.796 0.000 0.076 0.012 0.116
#> GSM486849 2 0.2171 0.782 0.000 0.924 0.032 0.016 0.028
#> GSM486851 5 0.5586 0.741 0.032 0.000 0.060 0.248 0.660
#> GSM486853 2 0.1393 0.784 0.000 0.956 0.012 0.008 0.024
#> GSM486855 2 0.3689 0.711 0.000 0.836 0.084 0.012 0.068
#> GSM486857 3 0.5369 0.552 0.000 0.344 0.600 0.012 0.044
#> GSM486736 4 0.4507 0.662 0.000 0.120 0.044 0.788 0.048
#> GSM486738 2 0.3052 0.751 0.000 0.868 0.008 0.092 0.032
#> GSM486740 4 0.6233 0.558 0.000 0.068 0.188 0.648 0.096
#> GSM486742 2 0.3446 0.736 0.000 0.840 0.008 0.116 0.036
#> GSM486744 2 0.3748 0.757 0.000 0.836 0.088 0.056 0.020
#> GSM486746 4 0.6544 0.388 0.000 0.072 0.396 0.484 0.048
#> GSM486748 3 0.4863 0.423 0.384 0.000 0.592 0.016 0.008
#> GSM486750 2 0.5532 0.282 0.000 0.564 0.032 0.380 0.024
#> GSM486752 3 0.4453 0.617 0.192 0.000 0.756 0.020 0.032
#> GSM486754 2 0.6211 0.205 0.000 0.532 0.076 0.364 0.028
#> GSM486756 2 0.5723 0.503 0.000 0.640 0.052 0.268 0.040
#> GSM486758 3 0.6511 0.428 0.208 0.000 0.596 0.036 0.160
#> GSM486760 1 0.1074 0.834 0.968 0.000 0.012 0.004 0.016
#> GSM486762 1 0.2617 0.816 0.904 0.000 0.036 0.028 0.032
#> GSM486764 5 0.5843 0.716 0.040 0.000 0.052 0.292 0.616
#> GSM486766 1 0.1314 0.831 0.960 0.000 0.016 0.012 0.012
#> GSM486768 3 0.4353 0.639 0.000 0.044 0.788 0.140 0.028
#> GSM486770 4 0.4062 0.673 0.000 0.168 0.028 0.788 0.016
#> GSM486772 2 0.2069 0.788 0.000 0.924 0.052 0.012 0.012
#> GSM486774 3 0.3412 0.688 0.000 0.048 0.848 0.096 0.008
#> GSM486776 1 0.0727 0.835 0.980 0.000 0.004 0.004 0.012
#> GSM486778 1 0.4235 0.708 0.776 0.000 0.024 0.024 0.176
#> GSM486780 2 0.4440 0.706 0.000 0.792 0.108 0.028 0.072
#> GSM486782 3 0.4037 0.680 0.000 0.096 0.808 0.088 0.008
#> GSM486784 2 0.1251 0.786 0.000 0.956 0.036 0.000 0.008
#> GSM486786 1 0.2151 0.820 0.924 0.000 0.020 0.016 0.040
#> GSM486788 1 0.1314 0.832 0.960 0.000 0.012 0.012 0.016
#> GSM486790 4 0.6253 0.514 0.000 0.284 0.128 0.572 0.016
#> GSM486792 5 0.6087 0.671 0.164 0.000 0.048 0.128 0.660
#> GSM486794 1 0.4862 0.642 0.724 0.000 0.028 0.036 0.212
#> GSM486796 3 0.5252 0.480 0.324 0.000 0.624 0.016 0.036
#> GSM486798 3 0.3821 0.663 0.144 0.008 0.816 0.012 0.020
#> GSM486800 1 0.0451 0.835 0.988 0.000 0.004 0.000 0.008
#> GSM486802 1 0.1314 0.832 0.960 0.000 0.012 0.012 0.016
#> GSM486804 1 0.1612 0.828 0.948 0.000 0.024 0.012 0.016
#> GSM486806 3 0.2834 0.703 0.060 0.012 0.888 0.040 0.000
#> GSM486808 1 0.2244 0.825 0.920 0.000 0.040 0.024 0.016
#> GSM486810 4 0.4985 0.493 0.000 0.044 0.056 0.748 0.152
#> GSM486812 1 0.2374 0.816 0.912 0.000 0.020 0.016 0.052
#> GSM486814 2 0.1568 0.786 0.000 0.944 0.036 0.000 0.020
#> GSM486816 1 0.4661 0.661 0.736 0.000 0.020 0.036 0.208
#> GSM486818 3 0.3400 0.694 0.104 0.012 0.852 0.004 0.028
#> GSM486821 5 0.6987 0.506 0.020 0.000 0.352 0.192 0.436
#> GSM486823 4 0.5208 0.469 0.000 0.328 0.020 0.624 0.028
#> GSM486826 1 0.1597 0.832 0.948 0.000 0.008 0.020 0.024
#> GSM486830 3 0.3171 0.692 0.000 0.044 0.864 0.084 0.008
#> GSM486832 1 0.1314 0.832 0.960 0.000 0.016 0.012 0.012
#> GSM486834 3 0.3553 0.689 0.072 0.000 0.852 0.028 0.048
#> GSM486836 1 0.1518 0.830 0.952 0.000 0.020 0.012 0.016
#> GSM486838 3 0.5789 0.563 0.012 0.284 0.628 0.012 0.064
#> GSM486840 1 0.0854 0.836 0.976 0.000 0.008 0.004 0.012
#> GSM486842 1 0.1095 0.834 0.968 0.000 0.012 0.012 0.008
#> GSM486844 1 0.1710 0.827 0.944 0.000 0.024 0.012 0.020
#> GSM486846 3 0.5034 0.606 0.000 0.260 0.684 0.028 0.028
#> GSM486848 1 0.1173 0.835 0.964 0.000 0.004 0.012 0.020
#> GSM486850 2 0.2778 0.782 0.000 0.892 0.060 0.016 0.032
#> GSM486852 5 0.6046 0.741 0.064 0.000 0.056 0.248 0.632
#> GSM486854 2 0.2116 0.784 0.000 0.924 0.040 0.008 0.028
#> GSM486856 2 0.4120 0.711 0.000 0.804 0.112 0.012 0.072
#> GSM486858 3 0.5194 0.547 0.000 0.316 0.632 0.012 0.040
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 6 0.4095 0.6263 0.000 0.036 0.016 0.028 0.128 0.792
#> GSM486737 2 0.4157 0.7139 0.000 0.788 0.072 0.004 0.032 0.104
#> GSM486739 6 0.5645 0.5346 0.000 0.024 0.012 0.148 0.172 0.644
#> GSM486741 2 0.4444 0.6979 0.000 0.764 0.084 0.008 0.024 0.120
#> GSM486743 2 0.4164 0.7232 0.000 0.796 0.036 0.056 0.012 0.100
#> GSM486745 6 0.6580 0.3718 0.000 0.052 0.036 0.328 0.076 0.508
#> GSM486747 4 0.5579 0.3587 0.132 0.000 0.352 0.512 0.004 0.000
#> GSM486749 2 0.5799 0.1026 0.000 0.452 0.064 0.020 0.016 0.448
#> GSM486751 4 0.5001 0.5372 0.036 0.000 0.296 0.636 0.024 0.008
#> GSM486753 6 0.5909 -0.0172 0.000 0.436 0.036 0.052 0.016 0.460
#> GSM486755 2 0.5771 0.4428 0.000 0.584 0.044 0.036 0.028 0.308
#> GSM486757 4 0.5781 0.3895 0.032 0.000 0.392 0.508 0.056 0.012
#> GSM486759 1 0.3634 0.2235 0.696 0.000 0.296 0.008 0.000 0.000
#> GSM486761 1 0.4699 -0.4250 0.496 0.000 0.468 0.028 0.008 0.000
#> GSM486763 5 0.4006 0.7087 0.000 0.000 0.048 0.044 0.792 0.116
#> GSM486765 1 0.3899 -0.0745 0.592 0.000 0.404 0.000 0.004 0.000
#> GSM486767 4 0.4949 0.5976 0.000 0.044 0.044 0.744 0.040 0.128
#> GSM486769 6 0.3406 0.6472 0.000 0.060 0.032 0.016 0.040 0.852
#> GSM486771 2 0.3041 0.7629 0.000 0.872 0.020 0.028 0.020 0.060
#> GSM486773 4 0.3733 0.6544 0.000 0.024 0.040 0.824 0.016 0.096
#> GSM486775 1 0.3871 0.2107 0.676 0.000 0.308 0.000 0.016 0.000
#> GSM486777 1 0.5302 -0.6976 0.468 0.000 0.456 0.004 0.064 0.008
#> GSM486779 2 0.4903 0.6741 0.000 0.748 0.112 0.076 0.032 0.032
#> GSM486781 4 0.4168 0.6520 0.000 0.064 0.032 0.804 0.024 0.076
#> GSM486783 2 0.1439 0.7736 0.000 0.952 0.016 0.012 0.012 0.008
#> GSM486785 1 0.4067 -0.2252 0.548 0.000 0.444 0.000 0.008 0.000
#> GSM486787 1 0.3703 0.2274 0.688 0.000 0.304 0.004 0.004 0.000
#> GSM486789 6 0.4759 0.6070 0.000 0.184 0.012 0.076 0.012 0.716
#> GSM486791 5 0.4963 0.6827 0.056 0.000 0.140 0.044 0.736 0.024
#> GSM486793 3 0.5986 0.9001 0.392 0.000 0.488 0.028 0.080 0.012
#> GSM486795 4 0.6641 0.3312 0.120 0.016 0.376 0.452 0.024 0.012
#> GSM486797 4 0.4313 0.6346 0.008 0.016 0.196 0.748 0.020 0.012
#> GSM486799 1 0.3861 0.1399 0.640 0.000 0.352 0.000 0.000 0.008
#> GSM486801 1 0.3809 0.2271 0.684 0.000 0.304 0.008 0.004 0.000
#> GSM486803 1 0.4399 0.1609 0.616 0.000 0.352 0.028 0.004 0.000
#> GSM486805 4 0.3364 0.6705 0.000 0.020 0.104 0.840 0.012 0.024
#> GSM486807 1 0.4269 -0.0741 0.568 0.000 0.412 0.020 0.000 0.000
#> GSM486809 6 0.4585 0.5386 0.000 0.016 0.020 0.028 0.224 0.712
#> GSM486811 1 0.4184 -0.2459 0.556 0.000 0.432 0.000 0.008 0.004
#> GSM486813 2 0.2145 0.7704 0.000 0.916 0.040 0.012 0.028 0.004
#> GSM486815 3 0.6008 0.8987 0.396 0.000 0.476 0.020 0.096 0.012
#> GSM486817 4 0.3865 0.6651 0.016 0.020 0.116 0.816 0.016 0.016
#> GSM486819 5 0.6181 0.3762 0.008 0.012 0.048 0.388 0.492 0.052
#> GSM486822 6 0.4941 0.5789 0.000 0.172 0.064 0.008 0.040 0.716
#> GSM486824 1 0.4528 0.2021 0.632 0.000 0.328 0.016 0.024 0.000
#> GSM486828 4 0.3381 0.6594 0.000 0.032 0.032 0.852 0.016 0.068
#> GSM486831 1 0.3915 0.2194 0.680 0.000 0.304 0.008 0.008 0.000
#> GSM486833 4 0.3911 0.6454 0.000 0.004 0.172 0.776 0.024 0.024
#> GSM486835 1 0.4074 0.2109 0.656 0.000 0.324 0.016 0.004 0.000
#> GSM486837 4 0.6427 0.4905 0.000 0.260 0.128 0.552 0.032 0.028
#> GSM486839 1 0.4008 0.2096 0.672 0.000 0.308 0.000 0.016 0.004
#> GSM486841 1 0.3797 -0.1115 0.580 0.000 0.420 0.000 0.000 0.000
#> GSM486843 1 0.4315 0.1759 0.624 0.000 0.348 0.024 0.004 0.000
#> GSM486845 4 0.5518 0.5666 0.000 0.220 0.072 0.656 0.028 0.024
#> GSM486847 1 0.4315 0.1357 0.624 0.000 0.348 0.000 0.024 0.004
#> GSM486849 2 0.3342 0.7629 0.000 0.856 0.052 0.048 0.016 0.028
#> GSM486851 5 0.3912 0.7315 0.004 0.000 0.072 0.044 0.812 0.068
#> GSM486853 2 0.2177 0.7715 0.000 0.916 0.044 0.016 0.012 0.012
#> GSM486855 2 0.4848 0.6699 0.000 0.752 0.100 0.088 0.028 0.032
#> GSM486857 4 0.5645 0.5430 0.000 0.252 0.080 0.624 0.024 0.020
#> GSM486736 6 0.4095 0.6263 0.000 0.036 0.016 0.028 0.128 0.792
#> GSM486738 2 0.4084 0.7138 0.000 0.792 0.072 0.004 0.028 0.104
#> GSM486740 6 0.5637 0.5345 0.000 0.020 0.012 0.164 0.164 0.640
#> GSM486742 2 0.4365 0.6979 0.000 0.768 0.084 0.008 0.020 0.120
#> GSM486744 2 0.3997 0.7240 0.000 0.800 0.028 0.076 0.004 0.092
#> GSM486746 6 0.6303 0.3711 0.000 0.044 0.024 0.356 0.072 0.504
#> GSM486748 4 0.5597 0.4010 0.344 0.000 0.104 0.536 0.016 0.000
#> GSM486750 2 0.5789 0.1025 0.000 0.452 0.064 0.024 0.012 0.448
#> GSM486752 4 0.5239 0.5316 0.192 0.000 0.116 0.664 0.028 0.000
#> GSM486754 6 0.5795 -0.0585 0.000 0.444 0.036 0.056 0.008 0.456
#> GSM486756 2 0.5702 0.4425 0.000 0.588 0.044 0.036 0.024 0.308
#> GSM486758 4 0.6601 0.3881 0.192 0.000 0.204 0.536 0.060 0.008
#> GSM486760 1 0.0779 0.4727 0.976 0.000 0.008 0.008 0.008 0.000
#> GSM486762 1 0.3777 0.2512 0.756 0.000 0.208 0.028 0.008 0.000
#> GSM486764 5 0.4042 0.7067 0.012 0.000 0.020 0.056 0.796 0.116
#> GSM486766 1 0.2402 0.3753 0.856 0.000 0.140 0.000 0.004 0.000
#> GSM486768 4 0.4107 0.5996 0.000 0.036 0.012 0.792 0.036 0.124
#> GSM486770 6 0.3406 0.6472 0.000 0.060 0.032 0.016 0.040 0.852
#> GSM486772 2 0.2911 0.7635 0.000 0.876 0.012 0.048 0.012 0.052
#> GSM486774 4 0.2822 0.6554 0.000 0.016 0.012 0.872 0.012 0.088
#> GSM486776 1 0.1719 0.4539 0.924 0.000 0.060 0.000 0.016 0.000
#> GSM486778 1 0.4469 0.0919 0.724 0.000 0.192 0.004 0.072 0.008
#> GSM486780 2 0.4765 0.6769 0.000 0.752 0.104 0.096 0.024 0.024
#> GSM486782 4 0.3441 0.6528 0.000 0.064 0.008 0.840 0.016 0.072
#> GSM486784 2 0.1431 0.7736 0.000 0.952 0.016 0.016 0.008 0.008
#> GSM486786 1 0.2743 0.3389 0.828 0.000 0.164 0.000 0.008 0.000
#> GSM486788 1 0.1138 0.4718 0.960 0.000 0.024 0.004 0.012 0.000
#> GSM486790 6 0.4731 0.6070 0.000 0.180 0.012 0.084 0.008 0.716
#> GSM486792 5 0.4976 0.6851 0.108 0.000 0.076 0.048 0.744 0.024
#> GSM486794 1 0.5647 -0.1131 0.628 0.000 0.240 0.032 0.088 0.012
#> GSM486796 4 0.6271 0.3309 0.368 0.012 0.100 0.488 0.028 0.004
#> GSM486798 4 0.4600 0.6134 0.108 0.008 0.096 0.760 0.024 0.004
#> GSM486800 1 0.1584 0.4529 0.928 0.000 0.064 0.000 0.000 0.008
#> GSM486802 1 0.1251 0.4711 0.956 0.000 0.024 0.008 0.012 0.000
#> GSM486804 1 0.2680 0.4217 0.880 0.000 0.060 0.048 0.012 0.000
#> GSM486806 4 0.2807 0.6727 0.016 0.012 0.056 0.888 0.008 0.020
#> GSM486808 1 0.3002 0.3950 0.836 0.000 0.136 0.020 0.008 0.000
#> GSM486810 6 0.4630 0.5386 0.000 0.016 0.020 0.032 0.220 0.712
#> GSM486812 1 0.2925 0.3313 0.832 0.000 0.148 0.000 0.016 0.004
#> GSM486814 2 0.2159 0.7704 0.000 0.916 0.040 0.016 0.024 0.004
#> GSM486816 1 0.5581 -0.1239 0.624 0.000 0.244 0.020 0.100 0.012
#> GSM486818 4 0.3319 0.6644 0.056 0.012 0.048 0.860 0.016 0.008
#> GSM486821 5 0.5669 0.3621 0.016 0.008 0.012 0.420 0.496 0.048
#> GSM486823 6 0.4941 0.5789 0.000 0.172 0.064 0.008 0.040 0.716
#> GSM486826 1 0.2400 0.4493 0.896 0.000 0.064 0.016 0.024 0.000
#> GSM486830 4 0.2307 0.6604 0.000 0.024 0.000 0.900 0.012 0.064
#> GSM486832 1 0.1364 0.4698 0.952 0.000 0.020 0.012 0.016 0.000
#> GSM486834 4 0.3671 0.6485 0.032 0.000 0.096 0.828 0.028 0.016
#> GSM486836 1 0.1838 0.4592 0.928 0.000 0.040 0.020 0.012 0.000
#> GSM486838 4 0.6128 0.4897 0.004 0.256 0.112 0.584 0.024 0.020
#> GSM486840 1 0.1464 0.4617 0.944 0.000 0.036 0.000 0.016 0.004
#> GSM486842 1 0.2389 0.3803 0.864 0.000 0.128 0.000 0.008 0.000
#> GSM486844 1 0.2546 0.4304 0.888 0.000 0.060 0.040 0.012 0.000
#> GSM486846 4 0.4968 0.5661 0.000 0.220 0.048 0.692 0.020 0.020
#> GSM486848 1 0.2320 0.4375 0.892 0.000 0.080 0.000 0.024 0.004
#> GSM486850 2 0.3163 0.7642 0.000 0.860 0.044 0.068 0.008 0.020
#> GSM486852 5 0.3863 0.7328 0.032 0.000 0.020 0.056 0.824 0.068
#> GSM486854 2 0.2164 0.7716 0.000 0.916 0.044 0.020 0.008 0.012
#> GSM486856 2 0.4683 0.6728 0.000 0.756 0.092 0.108 0.020 0.024
#> GSM486858 4 0.5065 0.5343 0.000 0.260 0.056 0.656 0.016 0.012
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> SD:kmeans 112 1.000 8.99e-06 2
#> SD:kmeans 89 0.936 4.67e-08 3
#> SD:kmeans 88 1.000 2.57e-11 4
#> SD:kmeans 104 1.000 1.26e-16 5
#> SD:kmeans 62 0.747 2.68e-10 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["SD", "skmeans"]
# you can also extract it by
# res = res_list["SD:skmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'SD' method.
#> Subgroups are detected by 'skmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.931 0.936 0.974 0.5043 0.496 0.496
#> 3 3 0.763 0.817 0.904 0.2941 0.800 0.616
#> 4 4 0.592 0.665 0.800 0.1186 0.927 0.794
#> 5 5 0.572 0.486 0.657 0.0647 0.913 0.724
#> 6 6 0.596 0.430 0.636 0.0442 0.925 0.730
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 2 0.0000 0.983 0.000 1.000
#> GSM486737 2 0.0000 0.983 0.000 1.000
#> GSM486739 2 0.0000 0.983 0.000 1.000
#> GSM486741 2 0.0000 0.983 0.000 1.000
#> GSM486743 2 0.0000 0.983 0.000 1.000
#> GSM486745 2 0.0000 0.983 0.000 1.000
#> GSM486747 1 0.0000 0.963 1.000 0.000
#> GSM486749 2 0.0000 0.983 0.000 1.000
#> GSM486751 1 0.0376 0.959 0.996 0.004
#> GSM486753 2 0.0000 0.983 0.000 1.000
#> GSM486755 2 0.0000 0.983 0.000 1.000
#> GSM486757 1 0.0000 0.963 1.000 0.000
#> GSM486759 1 0.0000 0.963 1.000 0.000
#> GSM486761 1 0.0000 0.963 1.000 0.000
#> GSM486763 1 0.7056 0.754 0.808 0.192
#> GSM486765 1 0.0000 0.963 1.000 0.000
#> GSM486767 2 0.0000 0.983 0.000 1.000
#> GSM486769 2 0.0000 0.983 0.000 1.000
#> GSM486771 2 0.0000 0.983 0.000 1.000
#> GSM486773 2 0.0000 0.983 0.000 1.000
#> GSM486775 1 0.0000 0.963 1.000 0.000
#> GSM486777 1 0.0000 0.963 1.000 0.000
#> GSM486779 2 0.0000 0.983 0.000 1.000
#> GSM486781 2 0.0000 0.983 0.000 1.000
#> GSM486783 2 0.0000 0.983 0.000 1.000
#> GSM486785 1 0.0000 0.963 1.000 0.000
#> GSM486787 1 0.0000 0.963 1.000 0.000
#> GSM486789 2 0.0000 0.983 0.000 1.000
#> GSM486791 1 0.0000 0.963 1.000 0.000
#> GSM486793 1 0.0000 0.963 1.000 0.000
#> GSM486795 1 0.0376 0.959 0.996 0.004
#> GSM486797 1 0.7602 0.719 0.780 0.220
#> GSM486799 1 0.0000 0.963 1.000 0.000
#> GSM486801 1 0.0000 0.963 1.000 0.000
#> GSM486803 1 0.0000 0.963 1.000 0.000
#> GSM486805 2 0.0672 0.975 0.008 0.992
#> GSM486807 1 0.0000 0.963 1.000 0.000
#> GSM486809 2 0.0000 0.983 0.000 1.000
#> GSM486811 1 0.0000 0.963 1.000 0.000
#> GSM486813 2 0.0000 0.983 0.000 1.000
#> GSM486815 1 0.0000 0.963 1.000 0.000
#> GSM486817 2 0.9552 0.373 0.376 0.624
#> GSM486819 2 0.9087 0.511 0.324 0.676
#> GSM486822 2 0.0000 0.983 0.000 1.000
#> GSM486824 1 0.0000 0.963 1.000 0.000
#> GSM486828 2 0.0000 0.983 0.000 1.000
#> GSM486831 1 0.0000 0.963 1.000 0.000
#> GSM486833 1 0.9248 0.505 0.660 0.340
#> GSM486835 1 0.0000 0.963 1.000 0.000
#> GSM486837 2 0.0000 0.983 0.000 1.000
#> GSM486839 1 0.0000 0.963 1.000 0.000
#> GSM486841 1 0.0000 0.963 1.000 0.000
#> GSM486843 1 0.0000 0.963 1.000 0.000
#> GSM486845 2 0.0000 0.983 0.000 1.000
#> GSM486847 1 0.0000 0.963 1.000 0.000
#> GSM486849 2 0.0000 0.983 0.000 1.000
#> GSM486851 1 0.0000 0.963 1.000 0.000
#> GSM486853 2 0.0000 0.983 0.000 1.000
#> GSM486855 2 0.0000 0.983 0.000 1.000
#> GSM486857 2 0.0000 0.983 0.000 1.000
#> GSM486736 2 0.0000 0.983 0.000 1.000
#> GSM486738 2 0.0000 0.983 0.000 1.000
#> GSM486740 2 0.0000 0.983 0.000 1.000
#> GSM486742 2 0.0000 0.983 0.000 1.000
#> GSM486744 2 0.0000 0.983 0.000 1.000
#> GSM486746 2 0.0000 0.983 0.000 1.000
#> GSM486748 1 0.0000 0.963 1.000 0.000
#> GSM486750 2 0.0000 0.983 0.000 1.000
#> GSM486752 1 0.0000 0.963 1.000 0.000
#> GSM486754 2 0.0000 0.983 0.000 1.000
#> GSM486756 2 0.0000 0.983 0.000 1.000
#> GSM486758 1 0.0000 0.963 1.000 0.000
#> GSM486760 1 0.0000 0.963 1.000 0.000
#> GSM486762 1 0.0000 0.963 1.000 0.000
#> GSM486764 1 0.7056 0.754 0.808 0.192
#> GSM486766 1 0.0000 0.963 1.000 0.000
#> GSM486768 2 0.0000 0.983 0.000 1.000
#> GSM486770 2 0.0000 0.983 0.000 1.000
#> GSM486772 2 0.0000 0.983 0.000 1.000
#> GSM486774 2 0.0000 0.983 0.000 1.000
#> GSM486776 1 0.0000 0.963 1.000 0.000
#> GSM486778 1 0.0000 0.963 1.000 0.000
#> GSM486780 2 0.0000 0.983 0.000 1.000
#> GSM486782 2 0.0000 0.983 0.000 1.000
#> GSM486784 2 0.0000 0.983 0.000 1.000
#> GSM486786 1 0.0000 0.963 1.000 0.000
#> GSM486788 1 0.0000 0.963 1.000 0.000
#> GSM486790 2 0.0000 0.983 0.000 1.000
#> GSM486792 1 0.0000 0.963 1.000 0.000
#> GSM486794 1 0.0000 0.963 1.000 0.000
#> GSM486796 1 0.0376 0.959 0.996 0.004
#> GSM486798 1 0.9460 0.453 0.636 0.364
#> GSM486800 1 0.0000 0.963 1.000 0.000
#> GSM486802 1 0.0000 0.963 1.000 0.000
#> GSM486804 1 0.0000 0.963 1.000 0.000
#> GSM486806 2 0.0000 0.983 0.000 1.000
#> GSM486808 1 0.0000 0.963 1.000 0.000
#> GSM486810 2 0.0000 0.983 0.000 1.000
#> GSM486812 1 0.0000 0.963 1.000 0.000
#> GSM486814 2 0.0000 0.983 0.000 1.000
#> GSM486816 1 0.0000 0.963 1.000 0.000
#> GSM486818 1 0.9954 0.169 0.540 0.460
#> GSM486821 2 0.7883 0.680 0.236 0.764
#> GSM486823 2 0.0000 0.983 0.000 1.000
#> GSM486826 1 0.0000 0.963 1.000 0.000
#> GSM486830 2 0.0000 0.983 0.000 1.000
#> GSM486832 1 0.0000 0.963 1.000 0.000
#> GSM486834 1 0.9710 0.361 0.600 0.400
#> GSM486836 1 0.0000 0.963 1.000 0.000
#> GSM486838 2 0.0000 0.983 0.000 1.000
#> GSM486840 1 0.0000 0.963 1.000 0.000
#> GSM486842 1 0.0000 0.963 1.000 0.000
#> GSM486844 1 0.0000 0.963 1.000 0.000
#> GSM486846 2 0.0000 0.983 0.000 1.000
#> GSM486848 1 0.0000 0.963 1.000 0.000
#> GSM486850 2 0.0000 0.983 0.000 1.000
#> GSM486852 1 0.0000 0.963 1.000 0.000
#> GSM486854 2 0.0000 0.983 0.000 1.000
#> GSM486856 2 0.0000 0.983 0.000 1.000
#> GSM486858 2 0.0000 0.983 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 1 0.2959 0.8227 0.900 0.100 0.000
#> GSM486737 2 0.0237 0.9084 0.004 0.996 0.000
#> GSM486739 1 0.2796 0.8242 0.908 0.092 0.000
#> GSM486741 2 0.0237 0.9084 0.004 0.996 0.000
#> GSM486743 2 0.0424 0.9076 0.008 0.992 0.000
#> GSM486745 1 0.2959 0.8237 0.900 0.100 0.000
#> GSM486747 3 0.2711 0.9079 0.088 0.000 0.912
#> GSM486749 2 0.2261 0.8783 0.068 0.932 0.000
#> GSM486751 3 0.5681 0.7373 0.236 0.016 0.748
#> GSM486753 2 0.4235 0.7743 0.176 0.824 0.000
#> GSM486755 2 0.1964 0.8867 0.056 0.944 0.000
#> GSM486757 3 0.6169 0.5313 0.360 0.004 0.636
#> GSM486759 3 0.1643 0.9316 0.044 0.000 0.956
#> GSM486761 3 0.1643 0.9316 0.044 0.000 0.956
#> GSM486763 1 0.2116 0.8136 0.948 0.040 0.012
#> GSM486765 3 0.1529 0.9321 0.040 0.000 0.960
#> GSM486767 1 0.4399 0.7635 0.812 0.188 0.000
#> GSM486769 1 0.4002 0.7883 0.840 0.160 0.000
#> GSM486771 2 0.0237 0.9086 0.004 0.996 0.000
#> GSM486773 1 0.4291 0.7451 0.820 0.180 0.000
#> GSM486775 3 0.1411 0.9324 0.036 0.000 0.964
#> GSM486777 3 0.1753 0.9302 0.048 0.000 0.952
#> GSM486779 2 0.0000 0.9088 0.000 1.000 0.000
#> GSM486781 2 0.5016 0.7175 0.240 0.760 0.000
#> GSM486783 2 0.0000 0.9088 0.000 1.000 0.000
#> GSM486785 3 0.1753 0.9302 0.048 0.000 0.952
#> GSM486787 3 0.1529 0.9321 0.040 0.000 0.960
#> GSM486789 2 0.5760 0.5143 0.328 0.672 0.000
#> GSM486791 1 0.6126 0.2301 0.600 0.000 0.400
#> GSM486793 3 0.1643 0.9316 0.044 0.000 0.956
#> GSM486795 3 0.6775 0.7287 0.112 0.144 0.744
#> GSM486797 1 0.9299 0.0298 0.432 0.160 0.408
#> GSM486799 3 0.1643 0.9316 0.044 0.000 0.956
#> GSM486801 3 0.1643 0.9316 0.044 0.000 0.956
#> GSM486803 3 0.1753 0.9302 0.048 0.000 0.952
#> GSM486805 1 0.5905 0.6798 0.772 0.184 0.044
#> GSM486807 3 0.1643 0.9316 0.044 0.000 0.956
#> GSM486809 1 0.2796 0.8241 0.908 0.092 0.000
#> GSM486811 3 0.1643 0.9316 0.044 0.000 0.956
#> GSM486813 2 0.0000 0.9088 0.000 1.000 0.000
#> GSM486815 3 0.1643 0.9316 0.044 0.000 0.956
#> GSM486817 2 0.9951 -0.0572 0.324 0.380 0.296
#> GSM486819 1 0.1999 0.8040 0.952 0.012 0.036
#> GSM486822 2 0.5138 0.6599 0.252 0.748 0.000
#> GSM486824 3 0.1753 0.9302 0.048 0.000 0.952
#> GSM486828 1 0.2711 0.8140 0.912 0.088 0.000
#> GSM486831 3 0.1753 0.9302 0.048 0.000 0.952
#> GSM486833 1 0.0475 0.8028 0.992 0.004 0.004
#> GSM486835 3 0.1643 0.9316 0.044 0.000 0.956
#> GSM486837 2 0.1860 0.8806 0.052 0.948 0.000
#> GSM486839 3 0.1643 0.9316 0.044 0.000 0.956
#> GSM486841 3 0.1643 0.9316 0.044 0.000 0.956
#> GSM486843 3 0.1643 0.9316 0.044 0.000 0.956
#> GSM486845 2 0.2165 0.8845 0.064 0.936 0.000
#> GSM486847 3 0.1643 0.9316 0.044 0.000 0.956
#> GSM486849 2 0.0000 0.9088 0.000 1.000 0.000
#> GSM486851 1 0.2959 0.7674 0.900 0.000 0.100
#> GSM486853 2 0.0000 0.9088 0.000 1.000 0.000
#> GSM486855 2 0.0000 0.9088 0.000 1.000 0.000
#> GSM486857 2 0.1860 0.8861 0.052 0.948 0.000
#> GSM486736 1 0.2959 0.8227 0.900 0.100 0.000
#> GSM486738 2 0.0237 0.9092 0.004 0.996 0.000
#> GSM486740 1 0.2796 0.8242 0.908 0.092 0.000
#> GSM486742 2 0.0237 0.9092 0.004 0.996 0.000
#> GSM486744 2 0.0237 0.9092 0.004 0.996 0.000
#> GSM486746 1 0.2878 0.8237 0.904 0.096 0.000
#> GSM486748 3 0.1411 0.9129 0.036 0.000 0.964
#> GSM486750 2 0.2066 0.8848 0.060 0.940 0.000
#> GSM486752 3 0.2796 0.8723 0.092 0.000 0.908
#> GSM486754 2 0.3267 0.8399 0.116 0.884 0.000
#> GSM486756 2 0.1529 0.8966 0.040 0.960 0.000
#> GSM486758 3 0.4555 0.7420 0.200 0.000 0.800
#> GSM486760 3 0.0000 0.9326 0.000 0.000 1.000
#> GSM486762 3 0.0000 0.9326 0.000 0.000 1.000
#> GSM486764 1 0.3356 0.8146 0.908 0.036 0.056
#> GSM486766 3 0.0000 0.9326 0.000 0.000 1.000
#> GSM486768 1 0.5733 0.5640 0.676 0.324 0.000
#> GSM486770 1 0.4121 0.7818 0.832 0.168 0.000
#> GSM486772 2 0.0237 0.9092 0.004 0.996 0.000
#> GSM486774 1 0.5859 0.4682 0.656 0.344 0.000
#> GSM486776 3 0.0000 0.9326 0.000 0.000 1.000
#> GSM486778 3 0.0000 0.9326 0.000 0.000 1.000
#> GSM486780 2 0.0237 0.9092 0.004 0.996 0.000
#> GSM486782 2 0.4654 0.7657 0.208 0.792 0.000
#> GSM486784 2 0.0237 0.9092 0.004 0.996 0.000
#> GSM486786 3 0.0000 0.9326 0.000 0.000 1.000
#> GSM486788 3 0.0000 0.9326 0.000 0.000 1.000
#> GSM486790 2 0.5431 0.6032 0.284 0.716 0.000
#> GSM486792 1 0.6291 0.1530 0.532 0.000 0.468
#> GSM486794 3 0.0000 0.9326 0.000 0.000 1.000
#> GSM486796 3 0.3528 0.8444 0.016 0.092 0.892
#> GSM486798 3 0.9806 -0.0543 0.292 0.276 0.432
#> GSM486800 3 0.0000 0.9326 0.000 0.000 1.000
#> GSM486802 3 0.0000 0.9326 0.000 0.000 1.000
#> GSM486804 3 0.0000 0.9326 0.000 0.000 1.000
#> GSM486806 1 0.7636 0.2608 0.556 0.396 0.048
#> GSM486808 3 0.0237 0.9312 0.004 0.000 0.996
#> GSM486810 1 0.2796 0.8242 0.908 0.092 0.000
#> GSM486812 3 0.0000 0.9326 0.000 0.000 1.000
#> GSM486814 2 0.0237 0.9092 0.004 0.996 0.000
#> GSM486816 3 0.0000 0.9326 0.000 0.000 1.000
#> GSM486818 3 0.9574 0.0656 0.292 0.232 0.476
#> GSM486821 1 0.3456 0.8149 0.904 0.036 0.060
#> GSM486823 2 0.5058 0.6768 0.244 0.756 0.000
#> GSM486826 3 0.0000 0.9326 0.000 0.000 1.000
#> GSM486830 1 0.3532 0.8041 0.884 0.108 0.008
#> GSM486832 3 0.0000 0.9326 0.000 0.000 1.000
#> GSM486834 1 0.2063 0.8057 0.948 0.008 0.044
#> GSM486836 3 0.0000 0.9326 0.000 0.000 1.000
#> GSM486838 2 0.2636 0.8715 0.048 0.932 0.020
#> GSM486840 3 0.0000 0.9326 0.000 0.000 1.000
#> GSM486842 3 0.0000 0.9326 0.000 0.000 1.000
#> GSM486844 3 0.0000 0.9326 0.000 0.000 1.000
#> GSM486846 2 0.1643 0.8887 0.044 0.956 0.000
#> GSM486848 3 0.0000 0.9326 0.000 0.000 1.000
#> GSM486850 2 0.0237 0.9092 0.004 0.996 0.000
#> GSM486852 1 0.3619 0.7726 0.864 0.000 0.136
#> GSM486854 2 0.0237 0.9092 0.004 0.996 0.000
#> GSM486856 2 0.0237 0.9092 0.004 0.996 0.000
#> GSM486858 2 0.1643 0.8887 0.044 0.956 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 4 0.1635 0.6845 0.008 0.044 0.000 0.948
#> GSM486737 2 0.1938 0.8265 0.012 0.936 0.000 0.052
#> GSM486739 4 0.1510 0.6884 0.028 0.016 0.000 0.956
#> GSM486741 2 0.2101 0.8260 0.012 0.928 0.000 0.060
#> GSM486743 2 0.3117 0.8206 0.028 0.880 0.000 0.092
#> GSM486745 4 0.3128 0.6772 0.076 0.040 0.000 0.884
#> GSM486747 1 0.4989 -0.2181 0.528 0.000 0.472 0.000
#> GSM486749 2 0.4617 0.7578 0.032 0.764 0.000 0.204
#> GSM486751 1 0.5121 0.5800 0.772 0.004 0.128 0.096
#> GSM486753 2 0.5812 0.6048 0.048 0.624 0.000 0.328
#> GSM486755 2 0.4365 0.7686 0.028 0.784 0.000 0.188
#> GSM486757 1 0.4898 0.5295 0.780 0.000 0.116 0.104
#> GSM486759 3 0.3444 0.8170 0.184 0.000 0.816 0.000
#> GSM486761 3 0.4356 0.7567 0.292 0.000 0.708 0.000
#> GSM486763 4 0.4283 0.5899 0.256 0.000 0.004 0.740
#> GSM486765 3 0.3400 0.8223 0.180 0.000 0.820 0.000
#> GSM486767 4 0.4780 0.6357 0.116 0.096 0.000 0.788
#> GSM486769 4 0.2928 0.6462 0.012 0.108 0.000 0.880
#> GSM486771 2 0.2443 0.8259 0.024 0.916 0.000 0.060
#> GSM486773 4 0.6101 0.1921 0.388 0.052 0.000 0.560
#> GSM486775 3 0.3219 0.8202 0.164 0.000 0.836 0.000
#> GSM486777 3 0.4535 0.7530 0.292 0.000 0.704 0.004
#> GSM486779 2 0.1913 0.8201 0.040 0.940 0.000 0.020
#> GSM486781 2 0.7717 0.2887 0.288 0.448 0.000 0.264
#> GSM486783 2 0.1059 0.8248 0.012 0.972 0.000 0.016
#> GSM486785 3 0.3837 0.8040 0.224 0.000 0.776 0.000
#> GSM486787 3 0.3356 0.8169 0.176 0.000 0.824 0.000
#> GSM486789 2 0.6197 0.3633 0.052 0.508 0.000 0.440
#> GSM486791 4 0.7227 0.1690 0.368 0.000 0.148 0.484
#> GSM486793 3 0.4855 0.6867 0.352 0.000 0.644 0.004
#> GSM486795 3 0.8190 0.1433 0.368 0.144 0.448 0.040
#> GSM486797 1 0.6008 0.5574 0.744 0.112 0.044 0.100
#> GSM486799 3 0.3400 0.8158 0.180 0.000 0.820 0.000
#> GSM486801 3 0.3528 0.8110 0.192 0.000 0.808 0.000
#> GSM486803 3 0.4072 0.7713 0.252 0.000 0.748 0.000
#> GSM486805 1 0.5302 0.4594 0.720 0.044 0.004 0.232
#> GSM486807 3 0.3907 0.7987 0.232 0.000 0.768 0.000
#> GSM486809 4 0.2002 0.6889 0.044 0.020 0.000 0.936
#> GSM486811 3 0.3837 0.8032 0.224 0.000 0.776 0.000
#> GSM486813 2 0.1297 0.8245 0.016 0.964 0.000 0.020
#> GSM486815 3 0.4509 0.7621 0.288 0.000 0.708 0.004
#> GSM486817 1 0.7919 0.5253 0.608 0.120 0.120 0.152
#> GSM486819 4 0.4707 0.6001 0.236 0.012 0.008 0.744
#> GSM486822 2 0.5323 0.5879 0.020 0.628 0.000 0.352
#> GSM486824 3 0.3356 0.8152 0.176 0.000 0.824 0.000
#> GSM486828 4 0.6755 0.0722 0.448 0.092 0.000 0.460
#> GSM486831 3 0.3870 0.8058 0.208 0.000 0.788 0.004
#> GSM486833 1 0.4372 0.4162 0.728 0.000 0.004 0.268
#> GSM486835 3 0.3668 0.8141 0.188 0.000 0.808 0.004
#> GSM486837 2 0.4936 0.5730 0.280 0.700 0.000 0.020
#> GSM486839 3 0.3444 0.8104 0.184 0.000 0.816 0.000
#> GSM486841 3 0.3726 0.8062 0.212 0.000 0.788 0.000
#> GSM486843 3 0.3610 0.8065 0.200 0.000 0.800 0.000
#> GSM486845 2 0.5309 0.7094 0.164 0.744 0.000 0.092
#> GSM486847 3 0.3444 0.8146 0.184 0.000 0.816 0.000
#> GSM486849 2 0.1520 0.8252 0.024 0.956 0.000 0.020
#> GSM486851 4 0.5161 0.5195 0.300 0.000 0.024 0.676
#> GSM486853 2 0.1411 0.8247 0.020 0.960 0.000 0.020
#> GSM486855 2 0.1388 0.8199 0.028 0.960 0.000 0.012
#> GSM486857 2 0.4375 0.7237 0.180 0.788 0.000 0.032
#> GSM486736 4 0.1824 0.6810 0.004 0.060 0.000 0.936
#> GSM486738 2 0.1389 0.8268 0.000 0.952 0.000 0.048
#> GSM486740 4 0.1624 0.6889 0.028 0.020 0.000 0.952
#> GSM486742 2 0.1489 0.8266 0.004 0.952 0.000 0.044
#> GSM486744 2 0.2489 0.8218 0.020 0.912 0.000 0.068
#> GSM486746 4 0.3004 0.6774 0.048 0.060 0.000 0.892
#> GSM486748 3 0.5189 0.0379 0.372 0.012 0.616 0.000
#> GSM486750 2 0.4426 0.7479 0.024 0.772 0.000 0.204
#> GSM486752 1 0.6188 0.5634 0.596 0.012 0.352 0.040
#> GSM486754 2 0.5078 0.6800 0.028 0.700 0.000 0.272
#> GSM486756 2 0.3946 0.7794 0.020 0.812 0.000 0.168
#> GSM486758 1 0.6825 0.5332 0.556 0.008 0.348 0.088
#> GSM486760 3 0.0188 0.8170 0.004 0.000 0.996 0.000
#> GSM486762 3 0.1867 0.8010 0.072 0.000 0.928 0.000
#> GSM486764 4 0.4781 0.6004 0.212 0.000 0.036 0.752
#> GSM486766 3 0.0817 0.8162 0.024 0.000 0.976 0.000
#> GSM486768 4 0.5690 0.5368 0.084 0.216 0.000 0.700
#> GSM486770 4 0.2918 0.6456 0.008 0.116 0.000 0.876
#> GSM486772 2 0.1706 0.8266 0.016 0.948 0.000 0.036
#> GSM486774 4 0.7568 0.0383 0.380 0.168 0.004 0.448
#> GSM486776 3 0.0336 0.8199 0.008 0.000 0.992 0.000
#> GSM486778 3 0.2675 0.7923 0.100 0.000 0.892 0.008
#> GSM486780 2 0.0895 0.8202 0.020 0.976 0.000 0.004
#> GSM486782 2 0.7293 0.4301 0.248 0.536 0.000 0.216
#> GSM486784 2 0.0336 0.8217 0.008 0.992 0.000 0.000
#> GSM486786 3 0.1389 0.8238 0.048 0.000 0.952 0.000
#> GSM486788 3 0.0000 0.8182 0.000 0.000 1.000 0.000
#> GSM486790 2 0.6114 0.3937 0.048 0.524 0.000 0.428
#> GSM486792 4 0.7538 0.1811 0.248 0.000 0.260 0.492
#> GSM486794 3 0.3401 0.7471 0.152 0.000 0.840 0.008
#> GSM486796 3 0.6747 0.2960 0.184 0.136 0.660 0.020
#> GSM486798 1 0.8648 0.5061 0.528 0.168 0.192 0.112
#> GSM486800 3 0.0336 0.8178 0.008 0.000 0.992 0.000
#> GSM486802 3 0.0188 0.8170 0.004 0.000 0.996 0.000
#> GSM486804 3 0.1474 0.7966 0.052 0.000 0.948 0.000
#> GSM486806 1 0.8526 0.3514 0.508 0.124 0.096 0.272
#> GSM486808 3 0.2011 0.7913 0.080 0.000 0.920 0.000
#> GSM486810 4 0.2214 0.6894 0.044 0.028 0.000 0.928
#> GSM486812 3 0.1302 0.8215 0.044 0.000 0.956 0.000
#> GSM486814 2 0.0336 0.8217 0.008 0.992 0.000 0.000
#> GSM486816 3 0.2593 0.7948 0.104 0.000 0.892 0.004
#> GSM486818 1 0.8583 0.5454 0.488 0.096 0.296 0.120
#> GSM486821 4 0.5112 0.6132 0.188 0.016 0.036 0.760
#> GSM486823 2 0.4999 0.6172 0.012 0.660 0.000 0.328
#> GSM486826 3 0.0592 0.8195 0.016 0.000 0.984 0.000
#> GSM486830 4 0.6966 0.1692 0.396 0.100 0.004 0.500
#> GSM486832 3 0.0469 0.8180 0.012 0.000 0.988 0.000
#> GSM486834 1 0.6775 0.4038 0.612 0.012 0.100 0.276
#> GSM486836 3 0.0469 0.8150 0.012 0.000 0.988 0.000
#> GSM486838 2 0.5248 0.5943 0.248 0.716 0.024 0.012
#> GSM486840 3 0.0000 0.8182 0.000 0.000 1.000 0.000
#> GSM486842 3 0.0921 0.8170 0.028 0.000 0.972 0.000
#> GSM486844 3 0.0921 0.8083 0.028 0.000 0.972 0.000
#> GSM486846 2 0.4153 0.7503 0.132 0.820 0.000 0.048
#> GSM486848 3 0.0188 0.8180 0.004 0.000 0.996 0.000
#> GSM486850 2 0.0592 0.8208 0.016 0.984 0.000 0.000
#> GSM486852 4 0.5820 0.5339 0.232 0.000 0.084 0.684
#> GSM486854 2 0.0469 0.8216 0.012 0.988 0.000 0.000
#> GSM486856 2 0.0779 0.8196 0.016 0.980 0.000 0.004
#> GSM486858 2 0.2179 0.7987 0.064 0.924 0.000 0.012
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 5 0.1893 0.49857 0.000 0.028 0.024 0.012 0.936
#> GSM486737 2 0.2722 0.76349 0.000 0.872 0.000 0.020 0.108
#> GSM486739 5 0.3745 0.46652 0.000 0.008 0.096 0.068 0.828
#> GSM486741 2 0.3098 0.73967 0.000 0.836 0.000 0.016 0.148
#> GSM486743 2 0.5663 0.62870 0.000 0.664 0.020 0.100 0.216
#> GSM486745 5 0.4742 0.46603 0.000 0.032 0.084 0.112 0.772
#> GSM486747 1 0.6133 -0.00647 0.496 0.000 0.136 0.368 0.000
#> GSM486749 2 0.5280 0.37078 0.000 0.560 0.008 0.036 0.396
#> GSM486751 4 0.6889 0.37646 0.248 0.004 0.160 0.552 0.036
#> GSM486753 5 0.5873 0.00341 0.000 0.412 0.012 0.068 0.508
#> GSM486755 2 0.5030 0.50211 0.000 0.624 0.008 0.032 0.336
#> GSM486757 4 0.7653 0.29393 0.248 0.004 0.208 0.472 0.068
#> GSM486759 1 0.1774 0.66564 0.932 0.000 0.052 0.016 0.000
#> GSM486761 1 0.4593 0.56667 0.748 0.000 0.124 0.128 0.000
#> GSM486763 5 0.6602 0.09759 0.008 0.000 0.380 0.164 0.448
#> GSM486765 1 0.3578 0.69048 0.820 0.000 0.132 0.048 0.000
#> GSM486767 5 0.6698 0.38334 0.000 0.104 0.088 0.204 0.604
#> GSM486769 5 0.2407 0.49204 0.000 0.088 0.004 0.012 0.896
#> GSM486771 2 0.3844 0.74607 0.000 0.808 0.008 0.040 0.144
#> GSM486773 5 0.6447 0.08076 0.000 0.092 0.028 0.396 0.484
#> GSM486775 1 0.2574 0.69958 0.876 0.000 0.112 0.012 0.000
#> GSM486777 1 0.4000 0.59019 0.788 0.000 0.164 0.044 0.004
#> GSM486779 2 0.2592 0.76484 0.000 0.892 0.052 0.056 0.000
#> GSM486781 5 0.7464 0.12370 0.000 0.284 0.032 0.332 0.352
#> GSM486783 2 0.0798 0.78449 0.000 0.976 0.000 0.016 0.008
#> GSM486785 1 0.2754 0.65750 0.880 0.000 0.080 0.040 0.000
#> GSM486787 1 0.1740 0.68665 0.932 0.000 0.056 0.012 0.000
#> GSM486789 5 0.5572 0.28251 0.000 0.296 0.016 0.064 0.624
#> GSM486791 3 0.7973 0.06063 0.128 0.000 0.428 0.172 0.272
#> GSM486793 1 0.5574 0.42443 0.652 0.000 0.212 0.132 0.004
#> GSM486795 1 0.7960 0.02195 0.540 0.148 0.128 0.148 0.036
#> GSM486797 4 0.7356 0.42833 0.204 0.048 0.132 0.576 0.040
#> GSM486799 1 0.1893 0.68335 0.928 0.000 0.048 0.024 0.000
#> GSM486801 1 0.1914 0.67917 0.924 0.000 0.060 0.016 0.000
#> GSM486803 1 0.3291 0.61717 0.848 0.000 0.088 0.064 0.000
#> GSM486805 4 0.6265 0.49602 0.100 0.028 0.060 0.692 0.120
#> GSM486807 1 0.3535 0.64404 0.832 0.000 0.080 0.088 0.000
#> GSM486809 5 0.3053 0.48045 0.000 0.008 0.076 0.044 0.872
#> GSM486811 1 0.3134 0.64346 0.848 0.000 0.120 0.032 0.000
#> GSM486813 2 0.1483 0.78384 0.000 0.952 0.008 0.028 0.012
#> GSM486815 1 0.4540 0.58233 0.748 0.000 0.180 0.068 0.004
#> GSM486817 4 0.8720 0.40188 0.200 0.092 0.136 0.468 0.104
#> GSM486819 5 0.7237 0.05093 0.016 0.004 0.368 0.236 0.376
#> GSM486822 5 0.4900 0.06055 0.000 0.412 0.004 0.020 0.564
#> GSM486824 1 0.2006 0.68113 0.916 0.000 0.072 0.012 0.000
#> GSM486828 4 0.6941 0.06101 0.000 0.068 0.092 0.496 0.344
#> GSM486831 1 0.3365 0.61555 0.836 0.000 0.120 0.044 0.000
#> GSM486833 4 0.6860 0.44412 0.112 0.000 0.140 0.604 0.144
#> GSM486835 1 0.2685 0.67818 0.880 0.000 0.092 0.028 0.000
#> GSM486837 2 0.5550 0.50327 0.012 0.628 0.072 0.288 0.000
#> GSM486839 1 0.0992 0.68041 0.968 0.000 0.024 0.008 0.000
#> GSM486841 1 0.2694 0.65483 0.884 0.000 0.076 0.040 0.000
#> GSM486843 1 0.2859 0.63235 0.876 0.000 0.056 0.068 0.000
#> GSM486845 2 0.6432 0.53274 0.000 0.608 0.048 0.228 0.116
#> GSM486847 1 0.1082 0.68233 0.964 0.000 0.028 0.008 0.000
#> GSM486849 2 0.2444 0.78387 0.000 0.912 0.024 0.028 0.036
#> GSM486851 5 0.7337 -0.00485 0.052 0.000 0.388 0.160 0.400
#> GSM486853 2 0.1403 0.78162 0.000 0.952 0.024 0.024 0.000
#> GSM486855 2 0.2632 0.76730 0.000 0.888 0.040 0.072 0.000
#> GSM486857 2 0.4365 0.71874 0.000 0.776 0.036 0.164 0.024
#> GSM486736 5 0.1989 0.49821 0.000 0.032 0.020 0.016 0.932
#> GSM486738 2 0.2972 0.76060 0.000 0.864 0.004 0.024 0.108
#> GSM486740 5 0.3515 0.47103 0.000 0.008 0.084 0.064 0.844
#> GSM486742 2 0.3099 0.75337 0.000 0.848 0.000 0.028 0.124
#> GSM486744 2 0.4499 0.71047 0.000 0.764 0.020 0.044 0.172
#> GSM486746 5 0.5258 0.45683 0.000 0.040 0.088 0.140 0.732
#> GSM486748 3 0.7112 0.03423 0.240 0.020 0.436 0.304 0.000
#> GSM486750 2 0.5229 0.42008 0.000 0.584 0.004 0.044 0.368
#> GSM486752 4 0.6450 0.10479 0.076 0.004 0.436 0.456 0.028
#> GSM486754 2 0.5976 0.21072 0.000 0.492 0.016 0.068 0.424
#> GSM486756 2 0.5216 0.55420 0.000 0.648 0.012 0.048 0.292
#> GSM486758 3 0.6739 -0.24472 0.100 0.000 0.440 0.420 0.040
#> GSM486760 1 0.3969 0.65733 0.692 0.000 0.304 0.004 0.000
#> GSM486762 1 0.5188 0.62940 0.612 0.000 0.328 0.060 0.000
#> GSM486764 5 0.6447 0.10350 0.004 0.000 0.384 0.156 0.456
#> GSM486766 1 0.4339 0.65287 0.652 0.000 0.336 0.012 0.000
#> GSM486768 5 0.7446 0.36479 0.000 0.220 0.104 0.156 0.520
#> GSM486770 5 0.3056 0.48621 0.000 0.112 0.008 0.020 0.860
#> GSM486772 2 0.3214 0.76849 0.000 0.856 0.008 0.032 0.104
#> GSM486774 5 0.7384 0.03566 0.000 0.116 0.084 0.368 0.432
#> GSM486776 1 0.3861 0.66014 0.712 0.000 0.284 0.004 0.000
#> GSM486778 1 0.5095 0.61548 0.592 0.000 0.368 0.036 0.004
#> GSM486780 2 0.2645 0.76454 0.000 0.888 0.068 0.044 0.000
#> GSM486782 5 0.7859 0.10006 0.000 0.312 0.064 0.292 0.332
#> GSM486784 2 0.0671 0.78285 0.000 0.980 0.000 0.016 0.004
#> GSM486786 1 0.4249 0.67165 0.688 0.000 0.296 0.016 0.000
#> GSM486788 1 0.4066 0.63842 0.672 0.000 0.324 0.004 0.000
#> GSM486790 5 0.5930 0.25873 0.000 0.296 0.028 0.072 0.604
#> GSM486792 3 0.7498 0.09919 0.076 0.000 0.480 0.176 0.268
#> GSM486794 1 0.5905 0.52000 0.516 0.000 0.388 0.092 0.004
#> GSM486796 3 0.8088 -0.08732 0.348 0.108 0.420 0.092 0.032
#> GSM486798 4 0.7915 0.27469 0.060 0.080 0.348 0.448 0.064
#> GSM486800 1 0.3949 0.65396 0.696 0.000 0.300 0.004 0.000
#> GSM486802 1 0.3999 0.63447 0.656 0.000 0.344 0.000 0.000
#> GSM486804 1 0.4722 0.58721 0.608 0.000 0.368 0.024 0.000
#> GSM486806 4 0.6846 0.44550 0.004 0.056 0.164 0.592 0.184
#> GSM486808 1 0.5429 0.57704 0.564 0.000 0.368 0.068 0.000
#> GSM486810 5 0.2741 0.48581 0.000 0.012 0.064 0.032 0.892
#> GSM486812 1 0.4456 0.65616 0.660 0.000 0.320 0.020 0.000
#> GSM486814 2 0.1179 0.78234 0.000 0.964 0.016 0.016 0.004
#> GSM486816 1 0.5256 0.61188 0.592 0.000 0.356 0.048 0.004
#> GSM486818 4 0.8126 0.23157 0.084 0.072 0.384 0.396 0.064
#> GSM486821 5 0.7040 0.06970 0.008 0.004 0.372 0.228 0.388
#> GSM486823 5 0.4958 -0.05624 0.000 0.452 0.004 0.020 0.524
#> GSM486826 1 0.4130 0.66081 0.696 0.000 0.292 0.012 0.000
#> GSM486830 4 0.7648 0.05439 0.000 0.096 0.140 0.424 0.340
#> GSM486832 1 0.3983 0.64040 0.660 0.000 0.340 0.000 0.000
#> GSM486834 4 0.6709 0.43978 0.016 0.016 0.200 0.584 0.184
#> GSM486836 1 0.4371 0.62236 0.644 0.000 0.344 0.012 0.000
#> GSM486838 2 0.5706 0.53326 0.004 0.632 0.132 0.232 0.000
#> GSM486840 1 0.3684 0.66165 0.720 0.000 0.280 0.000 0.000
#> GSM486842 1 0.4384 0.65404 0.660 0.000 0.324 0.016 0.000
#> GSM486844 1 0.4886 0.57907 0.596 0.000 0.372 0.032 0.000
#> GSM486846 2 0.6120 0.59536 0.000 0.656 0.080 0.192 0.072
#> GSM486848 1 0.3715 0.67199 0.736 0.000 0.260 0.004 0.000
#> GSM486850 2 0.2765 0.78545 0.000 0.896 0.036 0.044 0.024
#> GSM486852 5 0.7036 0.01022 0.028 0.000 0.396 0.168 0.408
#> GSM486854 2 0.1310 0.78370 0.000 0.956 0.024 0.020 0.000
#> GSM486856 2 0.2304 0.77569 0.000 0.908 0.044 0.048 0.000
#> GSM486858 2 0.4160 0.73609 0.000 0.804 0.068 0.112 0.016
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 6 0.360 0.5295 0.000 0.020 0.004 0.000 0.220 0.756
#> GSM486737 2 0.386 0.6782 0.000 0.768 0.004 0.028 0.012 0.188
#> GSM486739 6 0.478 0.3489 0.000 0.000 0.028 0.020 0.360 0.592
#> GSM486741 2 0.394 0.6158 0.000 0.724 0.008 0.024 0.000 0.244
#> GSM486743 2 0.579 0.5010 0.000 0.588 0.032 0.072 0.016 0.292
#> GSM486745 6 0.562 0.4660 0.000 0.012 0.048 0.072 0.224 0.644
#> GSM486747 1 0.653 -0.2503 0.404 0.004 0.164 0.400 0.016 0.012
#> GSM486749 6 0.551 0.0738 0.000 0.412 0.016 0.048 0.016 0.508
#> GSM486751 4 0.648 0.4994 0.164 0.008 0.120 0.620 0.044 0.044
#> GSM486753 6 0.476 0.4223 0.000 0.256 0.020 0.032 0.012 0.680
#> GSM486755 6 0.512 -0.1853 0.000 0.472 0.016 0.036 0.004 0.472
#> GSM486757 4 0.750 0.3402 0.216 0.000 0.188 0.436 0.148 0.012
#> GSM486759 1 0.248 0.5627 0.892 0.000 0.064 0.016 0.028 0.000
#> GSM486761 1 0.479 0.4342 0.708 0.000 0.168 0.104 0.020 0.000
#> GSM486763 5 0.159 0.8790 0.008 0.000 0.000 0.008 0.936 0.048
#> GSM486765 1 0.298 0.5613 0.828 0.000 0.152 0.012 0.008 0.000
#> GSM486767 6 0.717 0.3726 0.000 0.064 0.064 0.152 0.184 0.536
#> GSM486769 6 0.343 0.5713 0.000 0.044 0.004 0.004 0.132 0.816
#> GSM486771 2 0.481 0.6658 0.000 0.724 0.028 0.052 0.016 0.180
#> GSM486773 6 0.642 0.1337 0.004 0.036 0.036 0.356 0.064 0.504
#> GSM486775 1 0.191 0.5766 0.900 0.000 0.096 0.004 0.000 0.000
#> GSM486777 1 0.500 0.3971 0.688 0.000 0.188 0.028 0.096 0.000
#> GSM486779 2 0.328 0.7169 0.000 0.852 0.052 0.064 0.004 0.028
#> GSM486781 6 0.759 0.1966 0.000 0.192 0.064 0.260 0.052 0.432
#> GSM486783 2 0.231 0.7405 0.000 0.900 0.008 0.036 0.000 0.056
#> GSM486785 1 0.279 0.5424 0.856 0.000 0.116 0.020 0.008 0.000
#> GSM486787 1 0.232 0.5626 0.884 0.000 0.100 0.008 0.008 0.000
#> GSM486789 6 0.347 0.5698 0.000 0.120 0.016 0.016 0.020 0.828
#> GSM486791 5 0.338 0.7734 0.084 0.000 0.060 0.020 0.836 0.000
#> GSM486793 1 0.640 0.2143 0.552 0.000 0.232 0.100 0.116 0.000
#> GSM486795 1 0.880 -0.2128 0.368 0.128 0.224 0.176 0.064 0.040
#> GSM486797 4 0.675 0.5418 0.112 0.032 0.124 0.628 0.036 0.068
#> GSM486799 1 0.196 0.5772 0.908 0.000 0.080 0.004 0.008 0.000
#> GSM486801 1 0.243 0.5594 0.884 0.000 0.092 0.012 0.012 0.000
#> GSM486803 1 0.441 0.4823 0.768 0.000 0.104 0.060 0.068 0.000
#> GSM486805 4 0.564 0.5555 0.060 0.040 0.040 0.724 0.036 0.100
#> GSM486807 1 0.413 0.4936 0.760 0.000 0.144 0.088 0.008 0.000
#> GSM486809 6 0.462 0.2158 0.000 0.008 0.008 0.012 0.444 0.528
#> GSM486811 1 0.289 0.5358 0.836 0.000 0.144 0.016 0.004 0.000
#> GSM486813 2 0.216 0.7402 0.000 0.908 0.008 0.028 0.000 0.056
#> GSM486815 1 0.443 0.4483 0.736 0.000 0.184 0.036 0.044 0.000
#> GSM486817 4 0.895 0.4031 0.092 0.108 0.200 0.388 0.060 0.152
#> GSM486819 5 0.317 0.8342 0.020 0.000 0.032 0.048 0.868 0.032
#> GSM486822 6 0.463 0.4508 0.000 0.284 0.008 0.004 0.044 0.660
#> GSM486824 1 0.284 0.5532 0.852 0.000 0.116 0.028 0.004 0.000
#> GSM486828 4 0.790 0.1474 0.004 0.072 0.088 0.416 0.132 0.288
#> GSM486831 1 0.358 0.5286 0.820 0.000 0.064 0.020 0.096 0.000
#> GSM486833 4 0.746 0.5498 0.064 0.016 0.124 0.556 0.124 0.116
#> GSM486835 1 0.371 0.5358 0.796 0.000 0.148 0.024 0.032 0.000
#> GSM486837 2 0.677 0.3018 0.020 0.516 0.080 0.308 0.012 0.064
#> GSM486839 1 0.156 0.5689 0.932 0.000 0.056 0.012 0.000 0.000
#> GSM486841 1 0.247 0.5474 0.884 0.000 0.088 0.016 0.012 0.000
#> GSM486843 1 0.361 0.5157 0.812 0.000 0.116 0.056 0.016 0.000
#> GSM486845 2 0.766 0.2111 0.004 0.416 0.076 0.304 0.044 0.156
#> GSM486847 1 0.135 0.5735 0.940 0.000 0.056 0.004 0.000 0.000
#> GSM486849 2 0.366 0.7291 0.000 0.824 0.016 0.080 0.008 0.072
#> GSM486851 5 0.149 0.8852 0.024 0.000 0.004 0.000 0.944 0.028
#> GSM486853 2 0.251 0.7402 0.000 0.892 0.016 0.036 0.000 0.056
#> GSM486855 2 0.359 0.7076 0.000 0.836 0.040 0.072 0.008 0.044
#> GSM486857 2 0.549 0.5801 0.000 0.640 0.048 0.244 0.008 0.060
#> GSM486736 6 0.373 0.5268 0.000 0.020 0.008 0.000 0.224 0.748
#> GSM486738 2 0.365 0.6393 0.000 0.752 0.008 0.016 0.000 0.224
#> GSM486740 6 0.471 0.3514 0.000 0.000 0.024 0.020 0.360 0.596
#> GSM486742 2 0.368 0.6361 0.000 0.748 0.008 0.016 0.000 0.228
#> GSM486744 2 0.468 0.6053 0.000 0.680 0.028 0.040 0.000 0.252
#> GSM486746 6 0.625 0.4262 0.000 0.012 0.060 0.112 0.232 0.584
#> GSM486748 3 0.694 0.2518 0.168 0.012 0.492 0.276 0.016 0.036
#> GSM486750 6 0.525 0.0329 0.000 0.444 0.028 0.016 0.016 0.496
#> GSM486752 4 0.643 0.1601 0.040 0.012 0.408 0.464 0.032 0.044
#> GSM486754 6 0.448 0.2952 0.000 0.336 0.016 0.020 0.000 0.628
#> GSM486756 2 0.512 0.2220 0.000 0.508 0.028 0.032 0.000 0.432
#> GSM486758 3 0.712 -0.2781 0.068 0.000 0.388 0.380 0.144 0.020
#> GSM486760 1 0.446 0.3990 0.584 0.000 0.388 0.008 0.020 0.000
#> GSM486762 1 0.544 0.2873 0.488 0.000 0.424 0.068 0.020 0.000
#> GSM486764 5 0.134 0.8846 0.004 0.000 0.008 0.000 0.948 0.040
#> GSM486766 1 0.425 0.4037 0.576 0.000 0.408 0.008 0.008 0.000
#> GSM486768 6 0.751 0.3738 0.000 0.116 0.072 0.144 0.152 0.516
#> GSM486770 6 0.360 0.5727 0.000 0.052 0.004 0.004 0.136 0.804
#> GSM486772 2 0.389 0.7024 0.000 0.784 0.028 0.036 0.000 0.152
#> GSM486774 6 0.722 0.1033 0.000 0.056 0.120 0.300 0.056 0.468
#> GSM486776 1 0.373 0.4491 0.652 0.000 0.344 0.004 0.000 0.000
#> GSM486778 1 0.557 0.2572 0.452 0.000 0.440 0.012 0.096 0.000
#> GSM486780 2 0.264 0.7259 0.000 0.892 0.036 0.036 0.004 0.032
#> GSM486782 6 0.732 0.2838 0.000 0.232 0.092 0.180 0.024 0.472
#> GSM486784 2 0.190 0.7337 0.000 0.908 0.004 0.004 0.000 0.084
#> GSM486786 1 0.449 0.4170 0.576 0.000 0.396 0.016 0.012 0.000
#> GSM486788 1 0.405 0.3682 0.564 0.000 0.428 0.000 0.008 0.000
#> GSM486790 6 0.327 0.5657 0.000 0.136 0.016 0.012 0.008 0.828
#> GSM486792 5 0.290 0.8079 0.036 0.000 0.084 0.016 0.864 0.000
#> GSM486794 3 0.647 -0.1290 0.364 0.000 0.456 0.084 0.096 0.000
#> GSM486796 3 0.769 0.2618 0.208 0.116 0.508 0.096 0.052 0.020
#> GSM486798 3 0.763 -0.3031 0.036 0.060 0.408 0.368 0.044 0.084
#> GSM486800 1 0.413 0.4242 0.620 0.000 0.364 0.004 0.012 0.000
#> GSM486802 1 0.410 0.3574 0.548 0.000 0.444 0.004 0.004 0.000
#> GSM486804 1 0.492 0.2882 0.512 0.000 0.444 0.024 0.016 0.004
#> GSM486806 4 0.675 0.4435 0.004 0.048 0.192 0.560 0.028 0.168
#> GSM486808 3 0.503 -0.3046 0.452 0.000 0.488 0.052 0.008 0.000
#> GSM486810 6 0.454 0.3229 0.000 0.008 0.012 0.008 0.392 0.580
#> GSM486812 1 0.418 0.4080 0.560 0.000 0.428 0.008 0.004 0.000
#> GSM486814 2 0.204 0.7362 0.000 0.908 0.004 0.016 0.000 0.072
#> GSM486816 1 0.529 0.2821 0.472 0.000 0.452 0.016 0.060 0.000
#> GSM486818 3 0.869 -0.3118 0.052 0.092 0.360 0.300 0.104 0.092
#> GSM486821 5 0.342 0.8067 0.000 0.000 0.068 0.048 0.840 0.044
#> GSM486823 6 0.467 0.4259 0.000 0.300 0.012 0.004 0.036 0.648
#> GSM486826 1 0.389 0.4508 0.640 0.000 0.352 0.004 0.000 0.004
#> GSM486830 6 0.789 -0.0896 0.000 0.052 0.108 0.320 0.152 0.368
#> GSM486832 1 0.513 0.3269 0.524 0.000 0.404 0.008 0.064 0.000
#> GSM486834 4 0.719 0.4935 0.012 0.012 0.208 0.512 0.088 0.168
#> GSM486836 1 0.456 0.2956 0.516 0.000 0.456 0.008 0.020 0.000
#> GSM486838 2 0.680 0.2423 0.000 0.500 0.160 0.260 0.008 0.072
#> GSM486840 1 0.371 0.4582 0.656 0.000 0.340 0.004 0.000 0.000
#> GSM486842 1 0.412 0.4122 0.568 0.000 0.420 0.000 0.012 0.000
#> GSM486844 3 0.465 -0.3369 0.468 0.004 0.504 0.016 0.004 0.004
#> GSM486846 2 0.709 0.3634 0.000 0.508 0.092 0.232 0.024 0.144
#> GSM486848 1 0.371 0.4628 0.656 0.000 0.340 0.000 0.004 0.000
#> GSM486850 2 0.297 0.7393 0.000 0.868 0.020 0.036 0.004 0.072
#> GSM486852 5 0.148 0.8842 0.000 0.000 0.020 0.004 0.944 0.032
#> GSM486854 2 0.210 0.7371 0.000 0.912 0.012 0.020 0.000 0.056
#> GSM486856 2 0.305 0.7220 0.000 0.864 0.044 0.048 0.000 0.044
#> GSM486858 2 0.493 0.6552 0.000 0.724 0.072 0.124 0.000 0.080
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> SD:skmeans 116 1.00000 9.49e-06 2
#> SD:skmeans 112 0.93660 1.77e-09 3
#> SD:skmeans 102 1.00000 9.61e-13 4
#> SD:skmeans 69 1.00000 3.59e-04 5
#> SD:skmeans 54 0.00907 3.93e-05 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["SD", "pam"]
# you can also extract it by
# res = res_list["SD:pam"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'SD' method.
#> Subgroups are detected by 'pam' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 3.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.468 0.708 0.866 0.4503 0.532 0.532
#> 3 3 0.690 0.797 0.911 0.4581 0.714 0.506
#> 4 4 0.732 0.744 0.886 0.0803 0.951 0.858
#> 5 5 0.675 0.566 0.801 0.0816 0.908 0.708
#> 6 6 0.750 0.743 0.871 0.0628 0.904 0.629
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 3
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 2 0.0376 0.8188 0.004 0.996
#> GSM486737 2 0.0000 0.8178 0.000 1.000
#> GSM486739 2 0.1633 0.8200 0.024 0.976
#> GSM486741 2 0.0000 0.8178 0.000 1.000
#> GSM486743 2 0.0376 0.8167 0.004 0.996
#> GSM486745 2 0.1184 0.8200 0.016 0.984
#> GSM486747 2 0.9393 0.5863 0.356 0.644
#> GSM486749 2 0.4161 0.8094 0.084 0.916
#> GSM486751 2 0.9286 0.6054 0.344 0.656
#> GSM486753 2 0.0000 0.8178 0.000 1.000
#> GSM486755 2 0.0000 0.8178 0.000 1.000
#> GSM486757 2 0.9358 0.5934 0.352 0.648
#> GSM486759 1 0.0000 0.8331 1.000 0.000
#> GSM486761 1 0.0000 0.8331 1.000 0.000
#> GSM486763 1 0.0672 0.8290 0.992 0.008
#> GSM486765 1 0.0000 0.8331 1.000 0.000
#> GSM486767 1 0.7453 0.6413 0.788 0.212
#> GSM486769 2 0.0376 0.8187 0.004 0.996
#> GSM486771 2 0.0000 0.8178 0.000 1.000
#> GSM486773 2 0.9209 0.6155 0.336 0.664
#> GSM486775 1 0.0000 0.8331 1.000 0.000
#> GSM486777 1 0.0000 0.8331 1.000 0.000
#> GSM486779 2 0.1184 0.8097 0.016 0.984
#> GSM486781 2 0.6801 0.7560 0.180 0.820
#> GSM486783 2 0.0000 0.8178 0.000 1.000
#> GSM486785 1 0.0000 0.8331 1.000 0.000
#> GSM486787 1 0.0000 0.8331 1.000 0.000
#> GSM486789 2 0.0000 0.8178 0.000 1.000
#> GSM486791 1 0.0000 0.8331 1.000 0.000
#> GSM486793 1 0.0000 0.8331 1.000 0.000
#> GSM486795 2 0.9393 0.5874 0.356 0.644
#> GSM486797 2 0.9552 0.5480 0.376 0.624
#> GSM486799 1 0.0000 0.8331 1.000 0.000
#> GSM486801 1 0.0000 0.8331 1.000 0.000
#> GSM486803 1 0.0000 0.8331 1.000 0.000
#> GSM486805 2 0.9393 0.5867 0.356 0.644
#> GSM486807 1 0.5178 0.7523 0.884 0.116
#> GSM486809 2 0.7376 0.7242 0.208 0.792
#> GSM486811 1 0.2948 0.8069 0.948 0.052
#> GSM486813 2 0.3114 0.7821 0.056 0.944
#> GSM486815 1 0.9933 -0.0156 0.548 0.452
#> GSM486817 1 0.9393 0.4052 0.644 0.356
#> GSM486819 1 0.0376 0.8308 0.996 0.004
#> GSM486822 2 0.2043 0.8193 0.032 0.968
#> GSM486824 1 0.2948 0.8069 0.948 0.052
#> GSM486828 1 0.9427 0.3513 0.640 0.360
#> GSM486831 1 0.0000 0.8331 1.000 0.000
#> GSM486833 2 0.9286 0.6054 0.344 0.656
#> GSM486835 1 0.0000 0.8331 1.000 0.000
#> GSM486837 1 0.9732 0.2164 0.596 0.404
#> GSM486839 1 0.0000 0.8331 1.000 0.000
#> GSM486841 1 0.0000 0.8331 1.000 0.000
#> GSM486843 1 0.2948 0.8073 0.948 0.052
#> GSM486845 2 0.9896 0.3853 0.440 0.560
#> GSM486847 1 0.0000 0.8331 1.000 0.000
#> GSM486849 2 0.0376 0.8187 0.004 0.996
#> GSM486851 1 0.0000 0.8331 1.000 0.000
#> GSM486853 2 0.0000 0.8178 0.000 1.000
#> GSM486855 1 0.9286 0.4599 0.656 0.344
#> GSM486857 2 0.8207 0.6958 0.256 0.744
#> GSM486736 2 0.0376 0.8187 0.004 0.996
#> GSM486738 2 0.0000 0.8178 0.000 1.000
#> GSM486740 2 0.0000 0.8178 0.000 1.000
#> GSM486742 2 0.0000 0.8178 0.000 1.000
#> GSM486744 2 0.0000 0.8178 0.000 1.000
#> GSM486746 2 0.0376 0.8189 0.004 0.996
#> GSM486748 2 0.9286 0.6054 0.344 0.656
#> GSM486750 2 0.3733 0.8124 0.072 0.928
#> GSM486752 2 0.9209 0.6155 0.336 0.664
#> GSM486754 2 0.0000 0.8178 0.000 1.000
#> GSM486756 2 0.0000 0.8178 0.000 1.000
#> GSM486758 2 0.9209 0.6155 0.336 0.664
#> GSM486760 2 0.9933 0.3491 0.452 0.548
#> GSM486762 2 0.9286 0.6054 0.344 0.656
#> GSM486764 1 0.8713 0.5742 0.708 0.292
#> GSM486766 1 0.9922 0.0245 0.552 0.448
#> GSM486768 2 0.1843 0.8195 0.028 0.972
#> GSM486770 2 0.0672 0.8193 0.008 0.992
#> GSM486772 2 0.0000 0.8178 0.000 1.000
#> GSM486774 2 0.4161 0.8094 0.084 0.916
#> GSM486776 1 0.0000 0.8331 1.000 0.000
#> GSM486778 2 0.9286 0.6054 0.344 0.656
#> GSM486780 2 0.0000 0.8178 0.000 1.000
#> GSM486782 2 0.3879 0.8115 0.076 0.924
#> GSM486784 2 0.0000 0.8178 0.000 1.000
#> GSM486786 1 0.9815 0.1467 0.580 0.420
#> GSM486788 2 0.9427 0.5800 0.360 0.640
#> GSM486790 2 0.0000 0.8178 0.000 1.000
#> GSM486792 1 0.7139 0.6612 0.804 0.196
#> GSM486794 2 0.9427 0.5792 0.360 0.640
#> GSM486796 2 0.4022 0.8104 0.080 0.920
#> GSM486798 2 0.4161 0.8094 0.084 0.916
#> GSM486800 1 0.0000 0.8331 1.000 0.000
#> GSM486802 1 0.9977 -0.0941 0.528 0.472
#> GSM486804 2 0.9286 0.6054 0.344 0.656
#> GSM486806 2 0.8555 0.6738 0.280 0.720
#> GSM486808 2 0.9286 0.6054 0.344 0.656
#> GSM486810 2 0.1843 0.8195 0.028 0.972
#> GSM486812 2 0.9286 0.6054 0.344 0.656
#> GSM486814 2 0.0000 0.8178 0.000 1.000
#> GSM486816 2 0.9286 0.6054 0.344 0.656
#> GSM486818 2 0.4022 0.8104 0.080 0.920
#> GSM486821 1 0.7528 0.6413 0.784 0.216
#> GSM486823 2 0.1414 0.8199 0.020 0.980
#> GSM486826 2 0.9286 0.6054 0.344 0.656
#> GSM486830 2 0.4562 0.8047 0.096 0.904
#> GSM486832 1 0.0000 0.8331 1.000 0.000
#> GSM486834 2 0.7674 0.7219 0.224 0.776
#> GSM486836 1 0.9795 0.1641 0.584 0.416
#> GSM486838 2 0.5178 0.7950 0.116 0.884
#> GSM486840 1 0.1184 0.8266 0.984 0.016
#> GSM486842 1 0.9170 0.4167 0.668 0.332
#> GSM486844 2 0.9286 0.6054 0.344 0.656
#> GSM486846 2 0.4161 0.8094 0.084 0.916
#> GSM486848 1 0.9358 0.3680 0.648 0.352
#> GSM486850 2 0.0000 0.8178 0.000 1.000
#> GSM486852 1 0.0000 0.8331 1.000 0.000
#> GSM486854 2 0.0000 0.8178 0.000 1.000
#> GSM486856 2 0.0000 0.8178 0.000 1.000
#> GSM486858 2 0.4161 0.8094 0.084 0.916
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 3 0.5760 0.47003 0.000 0.328 0.672
#> GSM486737 2 0.0237 0.90743 0.000 0.996 0.004
#> GSM486739 3 0.5882 0.42905 0.000 0.348 0.652
#> GSM486741 2 0.0000 0.90842 0.000 1.000 0.000
#> GSM486743 2 0.0000 0.90842 0.000 1.000 0.000
#> GSM486745 2 0.4172 0.79638 0.004 0.840 0.156
#> GSM486747 3 0.0747 0.87104 0.016 0.000 0.984
#> GSM486749 3 0.0892 0.86792 0.000 0.020 0.980
#> GSM486751 3 0.0000 0.87320 0.000 0.000 1.000
#> GSM486753 2 0.0000 0.90842 0.000 1.000 0.000
#> GSM486755 2 0.0000 0.90842 0.000 1.000 0.000
#> GSM486757 3 0.0424 0.87302 0.008 0.000 0.992
#> GSM486759 1 0.0237 0.92268 0.996 0.000 0.004
#> GSM486761 1 0.1860 0.89513 0.948 0.000 0.052
#> GSM486763 1 0.0424 0.92182 0.992 0.000 0.008
#> GSM486765 1 0.0000 0.92387 1.000 0.000 0.000
#> GSM486767 1 0.3995 0.80990 0.868 0.116 0.016
#> GSM486769 2 0.5291 0.63731 0.000 0.732 0.268
#> GSM486771 2 0.4452 0.76164 0.000 0.808 0.192
#> GSM486773 3 0.0237 0.87342 0.004 0.000 0.996
#> GSM486775 1 0.0000 0.92387 1.000 0.000 0.000
#> GSM486777 1 0.0237 0.92268 0.996 0.000 0.004
#> GSM486779 2 0.0424 0.90622 0.000 0.992 0.008
#> GSM486781 3 0.0000 0.87320 0.000 0.000 1.000
#> GSM486783 2 0.0000 0.90842 0.000 1.000 0.000
#> GSM486785 1 0.0237 0.92268 0.996 0.000 0.004
#> GSM486787 1 0.0000 0.92387 1.000 0.000 0.000
#> GSM486789 2 0.0237 0.90743 0.000 0.996 0.004
#> GSM486791 1 0.0000 0.92387 1.000 0.000 0.000
#> GSM486793 1 0.0592 0.92054 0.988 0.000 0.012
#> GSM486795 3 0.4062 0.77004 0.164 0.000 0.836
#> GSM486797 3 0.1529 0.86109 0.040 0.000 0.960
#> GSM486799 1 0.0000 0.92387 1.000 0.000 0.000
#> GSM486801 1 0.0000 0.92387 1.000 0.000 0.000
#> GSM486803 1 0.0000 0.92387 1.000 0.000 0.000
#> GSM486805 3 0.0592 0.87216 0.012 0.000 0.988
#> GSM486807 1 0.4178 0.76818 0.828 0.000 0.172
#> GSM486809 3 0.5598 0.74470 0.052 0.148 0.800
#> GSM486811 1 0.1964 0.89167 0.944 0.000 0.056
#> GSM486813 2 0.0000 0.90842 0.000 1.000 0.000
#> GSM486815 3 0.6252 0.23945 0.444 0.000 0.556
#> GSM486817 1 0.6897 0.16660 0.548 0.016 0.436
#> GSM486819 1 0.0000 0.92387 1.000 0.000 0.000
#> GSM486822 2 0.6008 0.48177 0.000 0.628 0.372
#> GSM486824 1 0.2356 0.87992 0.928 0.000 0.072
#> GSM486828 3 0.6045 0.37729 0.380 0.000 0.620
#> GSM486831 1 0.0000 0.92387 1.000 0.000 0.000
#> GSM486833 3 0.0000 0.87320 0.000 0.000 1.000
#> GSM486835 1 0.0000 0.92387 1.000 0.000 0.000
#> GSM486837 3 0.5785 0.49238 0.332 0.000 0.668
#> GSM486839 1 0.0000 0.92387 1.000 0.000 0.000
#> GSM486841 1 0.0237 0.92268 0.996 0.000 0.004
#> GSM486843 1 0.1964 0.89317 0.944 0.000 0.056
#> GSM486845 3 0.3686 0.78531 0.140 0.000 0.860
#> GSM486847 1 0.0000 0.92387 1.000 0.000 0.000
#> GSM486849 2 0.6180 0.35641 0.000 0.584 0.416
#> GSM486851 1 0.0000 0.92387 1.000 0.000 0.000
#> GSM486853 2 0.0000 0.90842 0.000 1.000 0.000
#> GSM486855 2 0.0424 0.90456 0.008 0.992 0.000
#> GSM486857 3 0.0000 0.87320 0.000 0.000 1.000
#> GSM486736 3 0.6280 0.06184 0.000 0.460 0.540
#> GSM486738 2 0.0000 0.90842 0.000 1.000 0.000
#> GSM486740 2 0.4291 0.77451 0.000 0.820 0.180
#> GSM486742 2 0.0000 0.90842 0.000 1.000 0.000
#> GSM486744 2 0.0000 0.90842 0.000 1.000 0.000
#> GSM486746 2 0.5948 0.49610 0.000 0.640 0.360
#> GSM486748 3 0.0000 0.87320 0.000 0.000 1.000
#> GSM486750 3 0.2261 0.84031 0.000 0.068 0.932
#> GSM486752 3 0.0000 0.87320 0.000 0.000 1.000
#> GSM486754 2 0.0424 0.90567 0.000 0.992 0.008
#> GSM486756 2 0.0592 0.90387 0.000 0.988 0.012
#> GSM486758 3 0.0000 0.87320 0.000 0.000 1.000
#> GSM486760 3 0.4796 0.71026 0.220 0.000 0.780
#> GSM486762 3 0.0237 0.87312 0.004 0.000 0.996
#> GSM486764 1 0.4346 0.75337 0.816 0.000 0.184
#> GSM486766 3 0.5254 0.63009 0.264 0.000 0.736
#> GSM486768 3 0.4750 0.67777 0.000 0.216 0.784
#> GSM486770 2 0.5216 0.67328 0.000 0.740 0.260
#> GSM486772 2 0.0237 0.90733 0.000 0.996 0.004
#> GSM486774 3 0.0000 0.87320 0.000 0.000 1.000
#> GSM486776 1 0.0000 0.92387 1.000 0.000 0.000
#> GSM486778 3 0.0237 0.87312 0.004 0.000 0.996
#> GSM486780 2 0.0000 0.90842 0.000 1.000 0.000
#> GSM486782 3 0.4002 0.75724 0.000 0.160 0.840
#> GSM486784 2 0.0000 0.90842 0.000 1.000 0.000
#> GSM486786 3 0.5650 0.54173 0.312 0.000 0.688
#> GSM486788 3 0.4452 0.74435 0.192 0.000 0.808
#> GSM486790 2 0.0000 0.90842 0.000 1.000 0.000
#> GSM486792 1 0.5138 0.64228 0.748 0.000 0.252
#> GSM486794 3 0.1289 0.86627 0.032 0.000 0.968
#> GSM486796 3 0.0475 0.87293 0.004 0.004 0.992
#> GSM486798 3 0.0000 0.87320 0.000 0.000 1.000
#> GSM486800 1 0.0000 0.92387 1.000 0.000 0.000
#> GSM486802 3 0.6126 0.37834 0.400 0.000 0.600
#> GSM486804 3 0.0747 0.87158 0.016 0.000 0.984
#> GSM486806 3 0.0000 0.87320 0.000 0.000 1.000
#> GSM486808 3 0.0237 0.87312 0.004 0.000 0.996
#> GSM486810 3 0.4702 0.68352 0.000 0.212 0.788
#> GSM486812 3 0.0237 0.87312 0.004 0.000 0.996
#> GSM486814 2 0.0000 0.90842 0.000 1.000 0.000
#> GSM486816 3 0.0237 0.87312 0.004 0.000 0.996
#> GSM486818 3 0.1129 0.86875 0.004 0.020 0.976
#> GSM486821 1 0.0475 0.92156 0.992 0.004 0.004
#> GSM486823 2 0.6095 0.39654 0.000 0.608 0.392
#> GSM486826 3 0.0424 0.87303 0.008 0.000 0.992
#> GSM486830 3 0.0892 0.86859 0.000 0.020 0.980
#> GSM486832 1 0.0000 0.92387 1.000 0.000 0.000
#> GSM486834 3 0.0000 0.87320 0.000 0.000 1.000
#> GSM486836 3 0.6244 0.25113 0.440 0.000 0.560
#> GSM486838 3 0.0000 0.87320 0.000 0.000 1.000
#> GSM486840 1 0.1163 0.91115 0.972 0.000 0.028
#> GSM486842 1 0.6180 0.24375 0.584 0.000 0.416
#> GSM486844 3 0.0237 0.87312 0.004 0.000 0.996
#> GSM486846 3 0.2261 0.84239 0.000 0.068 0.932
#> GSM486848 1 0.6305 -0.00264 0.516 0.000 0.484
#> GSM486850 2 0.1643 0.88563 0.000 0.956 0.044
#> GSM486852 1 0.0237 0.92281 0.996 0.000 0.004
#> GSM486854 2 0.0000 0.90842 0.000 1.000 0.000
#> GSM486856 2 0.0000 0.90842 0.000 1.000 0.000
#> GSM486858 3 0.1753 0.85268 0.000 0.048 0.952
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 4 0.1584 0.77116 0.000 0.036 0.012 0.952
#> GSM486737 2 0.0707 0.85802 0.000 0.980 0.000 0.020
#> GSM486739 4 0.4686 0.73311 0.000 0.144 0.068 0.788
#> GSM486741 2 0.0000 0.86727 0.000 1.000 0.000 0.000
#> GSM486743 2 0.0000 0.86727 0.000 1.000 0.000 0.000
#> GSM486745 4 0.6665 0.25750 0.004 0.440 0.072 0.484
#> GSM486747 3 0.0707 0.85394 0.020 0.000 0.980 0.000
#> GSM486749 3 0.3933 0.72242 0.000 0.008 0.792 0.200
#> GSM486751 3 0.0336 0.85075 0.000 0.000 0.992 0.008
#> GSM486753 2 0.0188 0.86584 0.000 0.996 0.000 0.004
#> GSM486755 2 0.0000 0.86727 0.000 1.000 0.000 0.000
#> GSM486757 3 0.1059 0.85274 0.012 0.000 0.972 0.016
#> GSM486759 1 0.0000 0.89520 1.000 0.000 0.000 0.000
#> GSM486761 1 0.1743 0.87309 0.940 0.000 0.056 0.004
#> GSM486763 1 0.0336 0.89393 0.992 0.000 0.000 0.008
#> GSM486765 1 0.0524 0.89549 0.988 0.000 0.008 0.004
#> GSM486767 1 0.4914 0.72758 0.804 0.092 0.020 0.084
#> GSM486769 4 0.1557 0.77362 0.000 0.056 0.000 0.944
#> GSM486771 2 0.6315 -0.13527 0.000 0.508 0.060 0.432
#> GSM486773 3 0.1635 0.84497 0.008 0.000 0.948 0.044
#> GSM486775 1 0.0804 0.89362 0.980 0.000 0.008 0.012
#> GSM486777 1 0.0921 0.89051 0.972 0.000 0.000 0.028
#> GSM486779 2 0.0524 0.86363 0.000 0.988 0.004 0.008
#> GSM486781 3 0.1716 0.83715 0.000 0.000 0.936 0.064
#> GSM486783 2 0.0817 0.85527 0.000 0.976 0.000 0.024
#> GSM486785 1 0.1042 0.89307 0.972 0.000 0.008 0.020
#> GSM486787 1 0.0707 0.89312 0.980 0.000 0.000 0.020
#> GSM486789 2 0.4679 0.27433 0.000 0.648 0.000 0.352
#> GSM486791 1 0.0188 0.89461 0.996 0.000 0.000 0.004
#> GSM486793 1 0.0895 0.89273 0.976 0.000 0.020 0.004
#> GSM486795 3 0.3812 0.77101 0.140 0.000 0.832 0.028
#> GSM486797 3 0.2500 0.83742 0.044 0.000 0.916 0.040
#> GSM486799 1 0.0188 0.89507 0.996 0.000 0.000 0.004
#> GSM486801 1 0.0000 0.89520 1.000 0.000 0.000 0.000
#> GSM486803 1 0.0000 0.89520 1.000 0.000 0.000 0.000
#> GSM486805 3 0.1610 0.84856 0.016 0.000 0.952 0.032
#> GSM486807 1 0.3486 0.73698 0.812 0.000 0.188 0.000
#> GSM486809 4 0.2198 0.74977 0.000 0.008 0.072 0.920
#> GSM486811 1 0.2466 0.86097 0.916 0.000 0.056 0.028
#> GSM486813 2 0.0817 0.85527 0.000 0.976 0.000 0.024
#> GSM486815 3 0.5708 0.28524 0.416 0.000 0.556 0.028
#> GSM486817 1 0.5876 0.14554 0.540 0.016 0.432 0.012
#> GSM486819 1 0.0188 0.89478 0.996 0.000 0.000 0.004
#> GSM486822 4 0.7324 0.44067 0.000 0.228 0.240 0.532
#> GSM486824 1 0.2489 0.85306 0.912 0.000 0.068 0.020
#> GSM486828 3 0.7265 0.38438 0.288 0.000 0.528 0.184
#> GSM486831 1 0.0000 0.89520 1.000 0.000 0.000 0.000
#> GSM486833 3 0.0336 0.85075 0.000 0.000 0.992 0.008
#> GSM486835 1 0.0000 0.89520 1.000 0.000 0.000 0.000
#> GSM486837 3 0.5812 0.49055 0.328 0.000 0.624 0.048
#> GSM486839 1 0.0000 0.89520 1.000 0.000 0.000 0.000
#> GSM486841 1 0.0000 0.89520 1.000 0.000 0.000 0.000
#> GSM486843 1 0.1474 0.87315 0.948 0.000 0.052 0.000
#> GSM486845 3 0.4514 0.75283 0.136 0.000 0.800 0.064
#> GSM486847 1 0.0592 0.89487 0.984 0.000 0.000 0.016
#> GSM486849 2 0.6170 0.08857 0.000 0.528 0.420 0.052
#> GSM486851 1 0.0188 0.89461 0.996 0.000 0.000 0.004
#> GSM486853 2 0.0817 0.85527 0.000 0.976 0.000 0.024
#> GSM486855 2 0.1356 0.84293 0.008 0.960 0.000 0.032
#> GSM486857 3 0.1716 0.83715 0.000 0.000 0.936 0.064
#> GSM486736 4 0.2796 0.77365 0.000 0.092 0.016 0.892
#> GSM486738 2 0.0000 0.86727 0.000 1.000 0.000 0.000
#> GSM486740 4 0.5112 0.44230 0.000 0.384 0.008 0.608
#> GSM486742 2 0.0000 0.86727 0.000 1.000 0.000 0.000
#> GSM486744 2 0.0000 0.86727 0.000 1.000 0.000 0.000
#> GSM486746 2 0.7398 -0.23757 0.000 0.456 0.168 0.376
#> GSM486748 3 0.0000 0.85209 0.000 0.000 1.000 0.000
#> GSM486750 3 0.1792 0.82786 0.000 0.068 0.932 0.000
#> GSM486752 3 0.0000 0.85209 0.000 0.000 1.000 0.000
#> GSM486754 2 0.0188 0.86569 0.000 0.996 0.004 0.000
#> GSM486756 2 0.0188 0.86569 0.000 0.996 0.004 0.000
#> GSM486758 3 0.0000 0.85209 0.000 0.000 1.000 0.000
#> GSM486760 3 0.4842 0.70722 0.192 0.000 0.760 0.048
#> GSM486762 3 0.0657 0.85286 0.004 0.000 0.984 0.012
#> GSM486764 1 0.6364 0.54044 0.652 0.000 0.144 0.204
#> GSM486766 3 0.5444 0.61324 0.264 0.000 0.688 0.048
#> GSM486768 3 0.5429 0.58382 0.000 0.208 0.720 0.072
#> GSM486770 4 0.2861 0.77209 0.000 0.096 0.016 0.888
#> GSM486772 2 0.0188 0.86543 0.000 0.996 0.004 0.000
#> GSM486774 3 0.1022 0.84730 0.000 0.000 0.968 0.032
#> GSM486776 1 0.1635 0.88266 0.948 0.000 0.008 0.044
#> GSM486778 3 0.1302 0.84711 0.000 0.000 0.956 0.044
#> GSM486780 2 0.0000 0.86727 0.000 1.000 0.000 0.000
#> GSM486782 3 0.3539 0.71831 0.000 0.176 0.820 0.004
#> GSM486784 2 0.0000 0.86727 0.000 1.000 0.000 0.000
#> GSM486786 3 0.5657 0.52158 0.312 0.000 0.644 0.044
#> GSM486788 3 0.4244 0.74262 0.160 0.000 0.804 0.036
#> GSM486790 2 0.0469 0.86097 0.000 0.988 0.000 0.012
#> GSM486792 1 0.4072 0.64342 0.748 0.000 0.252 0.000
#> GSM486794 3 0.1109 0.85199 0.028 0.000 0.968 0.004
#> GSM486796 3 0.1059 0.85164 0.000 0.016 0.972 0.012
#> GSM486798 3 0.0000 0.85209 0.000 0.000 1.000 0.000
#> GSM486800 1 0.1722 0.88139 0.944 0.000 0.008 0.048
#> GSM486802 3 0.5543 0.44627 0.360 0.000 0.612 0.028
#> GSM486804 3 0.1677 0.84685 0.012 0.000 0.948 0.040
#> GSM486806 3 0.0000 0.85209 0.000 0.000 1.000 0.000
#> GSM486808 3 0.0657 0.85286 0.004 0.000 0.984 0.012
#> GSM486810 3 0.6851 0.20247 0.000 0.116 0.540 0.344
#> GSM486812 3 0.1389 0.84584 0.000 0.000 0.952 0.048
#> GSM486814 2 0.0000 0.86727 0.000 1.000 0.000 0.000
#> GSM486816 3 0.1302 0.84711 0.000 0.000 0.956 0.044
#> GSM486818 3 0.1284 0.85082 0.000 0.024 0.964 0.012
#> GSM486821 1 0.1822 0.86880 0.944 0.008 0.004 0.044
#> GSM486823 2 0.7802 -0.19921 0.000 0.420 0.276 0.304
#> GSM486826 3 0.1489 0.84679 0.004 0.000 0.952 0.044
#> GSM486830 3 0.4121 0.71443 0.000 0.020 0.796 0.184
#> GSM486832 1 0.0188 0.89526 0.996 0.000 0.004 0.000
#> GSM486834 3 0.0000 0.85209 0.000 0.000 1.000 0.000
#> GSM486836 3 0.5517 0.31066 0.412 0.000 0.568 0.020
#> GSM486838 3 0.0524 0.85190 0.000 0.008 0.988 0.004
#> GSM486840 1 0.2494 0.86828 0.916 0.000 0.036 0.048
#> GSM486842 1 0.6061 0.22445 0.552 0.000 0.400 0.048
#> GSM486844 3 0.0707 0.85141 0.000 0.000 0.980 0.020
#> GSM486846 3 0.2722 0.81760 0.000 0.064 0.904 0.032
#> GSM486848 1 0.6145 -0.00933 0.492 0.000 0.460 0.048
#> GSM486850 2 0.1302 0.82045 0.000 0.956 0.044 0.000
#> GSM486852 1 0.0524 0.89521 0.988 0.000 0.008 0.004
#> GSM486854 2 0.0000 0.86727 0.000 1.000 0.000 0.000
#> GSM486856 2 0.0000 0.86727 0.000 1.000 0.000 0.000
#> GSM486858 3 0.1557 0.83431 0.000 0.056 0.944 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 5 0.0000 0.79249 0.000 0.000 0.000 0.000 1.000
#> GSM486737 2 0.3949 0.45527 0.000 0.668 0.000 0.332 0.000
#> GSM486739 5 0.4191 0.72516 0.000 0.112 0.036 0.044 0.808
#> GSM486741 2 0.0000 0.86047 0.000 1.000 0.000 0.000 0.000
#> GSM486743 2 0.0000 0.86047 0.000 1.000 0.000 0.000 0.000
#> GSM486745 5 0.6112 0.22711 0.004 0.416 0.068 0.016 0.496
#> GSM486747 3 0.0510 0.73769 0.016 0.000 0.984 0.000 0.000
#> GSM486749 3 0.5956 -0.15209 0.000 0.004 0.472 0.432 0.092
#> GSM486751 3 0.0000 0.73890 0.000 0.000 1.000 0.000 0.000
#> GSM486753 2 0.0162 0.85734 0.000 0.996 0.000 0.000 0.004
#> GSM486755 2 0.0000 0.86047 0.000 1.000 0.000 0.000 0.000
#> GSM486757 3 0.0981 0.73625 0.012 0.000 0.972 0.008 0.008
#> GSM486759 1 0.0162 0.85458 0.996 0.000 0.000 0.004 0.000
#> GSM486761 1 0.1502 0.83246 0.940 0.000 0.056 0.004 0.000
#> GSM486763 1 0.0451 0.85262 0.988 0.000 0.000 0.008 0.004
#> GSM486765 1 0.0609 0.85201 0.980 0.000 0.000 0.020 0.000
#> GSM486767 1 0.7222 0.07873 0.472 0.084 0.020 0.372 0.052
#> GSM486769 5 0.0162 0.79189 0.000 0.000 0.000 0.004 0.996
#> GSM486771 4 0.6067 -0.03778 0.000 0.388 0.004 0.500 0.108
#> GSM486773 3 0.3008 0.66476 0.004 0.000 0.868 0.092 0.036
#> GSM486775 1 0.1341 0.84112 0.944 0.000 0.000 0.056 0.000
#> GSM486777 1 0.3109 0.74177 0.800 0.000 0.000 0.200 0.000
#> GSM486779 2 0.1571 0.81148 0.000 0.936 0.004 0.060 0.000
#> GSM486781 4 0.5157 0.17130 0.000 0.000 0.440 0.520 0.040
#> GSM486783 2 0.4452 0.09108 0.000 0.500 0.000 0.496 0.004
#> GSM486785 1 0.2674 0.80337 0.868 0.000 0.012 0.120 0.000
#> GSM486787 1 0.2648 0.77424 0.848 0.000 0.000 0.152 0.000
#> GSM486789 2 0.3999 0.36345 0.000 0.656 0.000 0.000 0.344
#> GSM486791 1 0.0324 0.85330 0.992 0.000 0.000 0.004 0.004
#> GSM486793 1 0.0865 0.84855 0.972 0.000 0.024 0.004 0.000
#> GSM486795 3 0.3689 0.64260 0.140 0.000 0.820 0.016 0.024
#> GSM486797 3 0.2472 0.71049 0.044 0.000 0.908 0.012 0.036
#> GSM486799 1 0.0162 0.85402 0.996 0.000 0.000 0.004 0.000
#> GSM486801 1 0.0290 0.85404 0.992 0.000 0.000 0.008 0.000
#> GSM486803 1 0.0000 0.85366 1.000 0.000 0.000 0.000 0.000
#> GSM486805 3 0.1891 0.72364 0.016 0.000 0.936 0.016 0.032
#> GSM486807 1 0.3086 0.70052 0.816 0.000 0.180 0.004 0.000
#> GSM486809 5 0.1106 0.78386 0.000 0.000 0.012 0.024 0.964
#> GSM486811 1 0.5019 0.57404 0.632 0.000 0.052 0.316 0.000
#> GSM486813 4 0.4450 -0.15869 0.000 0.488 0.000 0.508 0.004
#> GSM486815 3 0.6665 0.16561 0.260 0.000 0.440 0.300 0.000
#> GSM486817 3 0.7283 -0.09998 0.348 0.016 0.376 0.256 0.004
#> GSM486819 1 0.0162 0.85346 0.996 0.000 0.000 0.004 0.000
#> GSM486822 4 0.6179 -0.15705 0.000 0.060 0.032 0.480 0.428
#> GSM486824 1 0.4017 0.73289 0.788 0.000 0.064 0.148 0.000
#> GSM486828 4 0.6209 0.21178 0.036 0.000 0.396 0.508 0.060
#> GSM486831 1 0.0000 0.85366 1.000 0.000 0.000 0.000 0.000
#> GSM486833 3 0.0000 0.73890 0.000 0.000 1.000 0.000 0.000
#> GSM486835 1 0.0000 0.85366 1.000 0.000 0.000 0.000 0.000
#> GSM486837 4 0.5751 0.19718 0.036 0.000 0.420 0.516 0.028
#> GSM486839 1 0.0000 0.85366 1.000 0.000 0.000 0.000 0.000
#> GSM486841 1 0.0290 0.85387 0.992 0.000 0.000 0.008 0.000
#> GSM486843 1 0.1597 0.83297 0.940 0.000 0.048 0.012 0.000
#> GSM486845 4 0.5499 0.18506 0.012 0.000 0.428 0.520 0.040
#> GSM486847 1 0.1965 0.82781 0.904 0.000 0.000 0.096 0.000
#> GSM486849 4 0.6336 -0.00235 0.000 0.412 0.080 0.480 0.028
#> GSM486851 1 0.0451 0.85262 0.988 0.000 0.000 0.008 0.004
#> GSM486853 4 0.4451 -0.16687 0.000 0.492 0.000 0.504 0.004
#> GSM486855 4 0.4656 -0.14469 0.000 0.480 0.000 0.508 0.012
#> GSM486857 3 0.5178 -0.15260 0.000 0.000 0.484 0.476 0.040
#> GSM486736 5 0.1043 0.79748 0.000 0.040 0.000 0.000 0.960
#> GSM486738 2 0.0000 0.86047 0.000 1.000 0.000 0.000 0.000
#> GSM486740 5 0.4633 0.44734 0.000 0.348 0.004 0.016 0.632
#> GSM486742 2 0.0000 0.86047 0.000 1.000 0.000 0.000 0.000
#> GSM486744 2 0.0000 0.86047 0.000 1.000 0.000 0.000 0.000
#> GSM486746 2 0.6100 -0.19128 0.000 0.448 0.124 0.000 0.428
#> GSM486748 3 0.0000 0.73890 0.000 0.000 1.000 0.000 0.000
#> GSM486750 3 0.1478 0.71525 0.000 0.064 0.936 0.000 0.000
#> GSM486752 3 0.0000 0.73890 0.000 0.000 1.000 0.000 0.000
#> GSM486754 2 0.0000 0.86047 0.000 1.000 0.000 0.000 0.000
#> GSM486756 2 0.0000 0.86047 0.000 1.000 0.000 0.000 0.000
#> GSM486758 3 0.0000 0.73890 0.000 0.000 1.000 0.000 0.000
#> GSM486760 4 0.5998 -0.23276 0.112 0.000 0.424 0.464 0.000
#> GSM486762 3 0.0771 0.73923 0.004 0.000 0.976 0.020 0.000
#> GSM486764 1 0.5756 0.47911 0.628 0.000 0.116 0.008 0.248
#> GSM486766 4 0.6602 -0.02538 0.240 0.000 0.304 0.456 0.000
#> GSM486768 3 0.5897 0.41538 0.000 0.208 0.660 0.040 0.092
#> GSM486770 5 0.1285 0.79712 0.000 0.036 0.004 0.004 0.956
#> GSM486772 2 0.0162 0.85707 0.000 0.996 0.004 0.000 0.000
#> GSM486774 3 0.0794 0.73282 0.000 0.000 0.972 0.000 0.028
#> GSM486776 1 0.4278 0.48051 0.548 0.000 0.000 0.452 0.000
#> GSM486778 3 0.4045 0.47148 0.000 0.000 0.644 0.356 0.000
#> GSM486780 2 0.0000 0.86047 0.000 1.000 0.000 0.000 0.000
#> GSM486782 3 0.2891 0.60778 0.000 0.176 0.824 0.000 0.000
#> GSM486784 2 0.0000 0.86047 0.000 1.000 0.000 0.000 0.000
#> GSM486786 4 0.6752 -0.01125 0.280 0.000 0.316 0.404 0.000
#> GSM486788 3 0.4836 0.46533 0.032 0.000 0.612 0.356 0.000
#> GSM486790 2 0.0609 0.84677 0.000 0.980 0.000 0.000 0.020
#> GSM486792 1 0.3807 0.60363 0.748 0.000 0.240 0.012 0.000
#> GSM486794 3 0.1582 0.72979 0.028 0.000 0.944 0.028 0.000
#> GSM486796 3 0.1168 0.73665 0.000 0.008 0.960 0.032 0.000
#> GSM486798 3 0.0000 0.73890 0.000 0.000 1.000 0.000 0.000
#> GSM486800 1 0.4291 0.46578 0.536 0.000 0.000 0.464 0.000
#> GSM486802 3 0.6326 0.30810 0.208 0.000 0.524 0.268 0.000
#> GSM486804 3 0.4003 0.56179 0.008 0.000 0.704 0.288 0.000
#> GSM486806 3 0.0000 0.73890 0.000 0.000 1.000 0.000 0.000
#> GSM486808 3 0.0566 0.73937 0.004 0.000 0.984 0.012 0.000
#> GSM486810 3 0.6085 0.23180 0.000 0.100 0.512 0.008 0.380
#> GSM486812 3 0.4273 0.36804 0.000 0.000 0.552 0.448 0.000
#> GSM486814 2 0.0000 0.86047 0.000 1.000 0.000 0.000 0.000
#> GSM486816 3 0.3999 0.48304 0.000 0.000 0.656 0.344 0.000
#> GSM486818 3 0.1493 0.73497 0.000 0.024 0.948 0.028 0.000
#> GSM486821 1 0.2338 0.82006 0.916 0.008 0.004 0.024 0.048
#> GSM486823 2 0.6916 -0.16961 0.000 0.376 0.280 0.004 0.340
#> GSM486826 3 0.4196 0.48755 0.004 0.000 0.640 0.356 0.000
#> GSM486830 3 0.5067 0.48765 0.000 0.024 0.700 0.044 0.232
#> GSM486832 1 0.0162 0.85383 0.996 0.000 0.004 0.000 0.000
#> GSM486834 3 0.0000 0.73890 0.000 0.000 1.000 0.000 0.000
#> GSM486836 3 0.6318 0.18095 0.344 0.000 0.488 0.168 0.000
#> GSM486838 3 0.0451 0.73840 0.000 0.008 0.988 0.004 0.000
#> GSM486840 1 0.4740 0.43848 0.516 0.000 0.016 0.468 0.000
#> GSM486842 4 0.6392 -0.15581 0.356 0.000 0.176 0.468 0.000
#> GSM486844 3 0.2732 0.66855 0.000 0.000 0.840 0.160 0.000
#> GSM486846 4 0.4802 0.13288 0.000 0.012 0.480 0.504 0.004
#> GSM486848 4 0.6469 -0.11073 0.336 0.000 0.196 0.468 0.000
#> GSM486850 2 0.1197 0.81244 0.000 0.952 0.048 0.000 0.000
#> GSM486852 1 0.0566 0.85315 0.984 0.000 0.004 0.012 0.000
#> GSM486854 2 0.0000 0.86047 0.000 1.000 0.000 0.000 0.000
#> GSM486856 2 0.0000 0.86047 0.000 1.000 0.000 0.000 0.000
#> GSM486858 3 0.1270 0.72287 0.000 0.052 0.948 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 6 0.0000 0.8032 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM486737 2 0.3747 0.2318 0.000 0.604 0.000 0.396 0.000 0.000
#> GSM486739 6 0.4320 0.6625 0.012 0.032 0.004 0.244 0.000 0.708
#> GSM486741 2 0.0000 0.8838 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486743 2 0.0000 0.8838 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486745 6 0.6627 0.4091 0.012 0.336 0.040 0.148 0.000 0.464
#> GSM486747 3 0.0547 0.8479 0.000 0.000 0.980 0.000 0.020 0.000
#> GSM486749 4 0.4150 0.6519 0.000 0.004 0.204 0.732 0.000 0.060
#> GSM486751 3 0.0000 0.8517 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM486753 2 0.0000 0.8838 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486755 2 0.0000 0.8838 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486757 3 0.1500 0.8374 0.000 0.000 0.936 0.052 0.012 0.000
#> GSM486759 5 0.0146 0.8995 0.004 0.000 0.000 0.000 0.996 0.000
#> GSM486761 5 0.1398 0.8786 0.008 0.000 0.052 0.000 0.940 0.000
#> GSM486763 5 0.0458 0.8981 0.000 0.000 0.000 0.016 0.984 0.000
#> GSM486765 5 0.0937 0.8894 0.040 0.000 0.000 0.000 0.960 0.000
#> GSM486767 4 0.3341 0.5763 0.000 0.012 0.004 0.776 0.208 0.000
#> GSM486769 6 0.0935 0.7988 0.004 0.000 0.000 0.032 0.000 0.964
#> GSM486771 4 0.3139 0.7139 0.000 0.152 0.000 0.816 0.000 0.032
#> GSM486773 3 0.3175 0.6755 0.000 0.000 0.744 0.256 0.000 0.000
#> GSM486775 5 0.1444 0.8762 0.072 0.000 0.000 0.000 0.928 0.000
#> GSM486777 5 0.3221 0.6401 0.264 0.000 0.000 0.000 0.736 0.000
#> GSM486779 2 0.1908 0.7960 0.000 0.900 0.004 0.096 0.000 0.000
#> GSM486781 4 0.1141 0.7507 0.000 0.000 0.052 0.948 0.000 0.000
#> GSM486783 4 0.3515 0.5535 0.000 0.324 0.000 0.676 0.000 0.000
#> GSM486785 5 0.2912 0.7213 0.216 0.000 0.000 0.000 0.784 0.000
#> GSM486787 5 0.2454 0.7879 0.160 0.000 0.000 0.000 0.840 0.000
#> GSM486789 2 0.3804 0.4027 0.008 0.656 0.000 0.000 0.000 0.336
#> GSM486791 5 0.0363 0.8986 0.000 0.000 0.000 0.012 0.988 0.000
#> GSM486793 5 0.0405 0.8990 0.004 0.000 0.008 0.000 0.988 0.000
#> GSM486795 3 0.3316 0.7162 0.028 0.000 0.804 0.004 0.164 0.000
#> GSM486797 3 0.2775 0.7973 0.000 0.000 0.856 0.104 0.040 0.000
#> GSM486799 5 0.0260 0.8989 0.008 0.000 0.000 0.000 0.992 0.000
#> GSM486801 5 0.1863 0.8503 0.104 0.000 0.000 0.000 0.896 0.000
#> GSM486803 5 0.0000 0.8988 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486805 3 0.2623 0.7899 0.000 0.000 0.852 0.132 0.016 0.000
#> GSM486807 5 0.2848 0.7513 0.008 0.000 0.176 0.000 0.816 0.000
#> GSM486809 6 0.1957 0.7729 0.000 0.000 0.000 0.112 0.000 0.888
#> GSM486811 1 0.3190 0.6686 0.772 0.000 0.008 0.000 0.220 0.000
#> GSM486813 4 0.2597 0.7151 0.000 0.176 0.000 0.824 0.000 0.000
#> GSM486815 1 0.4583 0.6714 0.696 0.000 0.128 0.000 0.176 0.000
#> GSM486817 4 0.6276 0.2053 0.000 0.008 0.292 0.404 0.296 0.000
#> GSM486819 5 0.0260 0.8986 0.000 0.000 0.000 0.008 0.992 0.000
#> GSM486822 4 0.3081 0.6200 0.004 0.000 0.000 0.776 0.000 0.220
#> GSM486824 5 0.3835 0.7088 0.188 0.000 0.056 0.000 0.756 0.000
#> GSM486828 4 0.1563 0.7501 0.000 0.000 0.056 0.932 0.012 0.000
#> GSM486831 5 0.0000 0.8988 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486833 3 0.0000 0.8517 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM486835 5 0.0000 0.8988 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486837 4 0.1753 0.7530 0.000 0.000 0.084 0.912 0.004 0.000
#> GSM486839 5 0.0000 0.8988 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486841 5 0.0458 0.8971 0.016 0.000 0.000 0.000 0.984 0.000
#> GSM486843 5 0.2488 0.8485 0.076 0.000 0.044 0.000 0.880 0.000
#> GSM486845 4 0.1082 0.7494 0.000 0.000 0.040 0.956 0.004 0.000
#> GSM486847 5 0.2260 0.8313 0.140 0.000 0.000 0.000 0.860 0.000
#> GSM486849 4 0.3088 0.7032 0.000 0.172 0.020 0.808 0.000 0.000
#> GSM486851 5 0.0363 0.8986 0.000 0.000 0.000 0.012 0.988 0.000
#> GSM486853 4 0.2730 0.7016 0.000 0.192 0.000 0.808 0.000 0.000
#> GSM486855 4 0.1957 0.7450 0.000 0.112 0.000 0.888 0.000 0.000
#> GSM486857 4 0.1910 0.7309 0.000 0.000 0.108 0.892 0.000 0.000
#> GSM486736 6 0.0260 0.8026 0.000 0.000 0.000 0.008 0.000 0.992
#> GSM486738 2 0.0000 0.8838 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486740 6 0.5557 0.6212 0.012 0.232 0.004 0.144 0.000 0.608
#> GSM486742 2 0.0000 0.8838 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486744 2 0.0000 0.8838 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486746 2 0.5700 -0.1800 0.012 0.444 0.112 0.000 0.000 0.432
#> GSM486748 3 0.0000 0.8517 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM486750 3 0.1204 0.8335 0.000 0.056 0.944 0.000 0.000 0.000
#> GSM486752 3 0.0000 0.8517 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM486754 2 0.0000 0.8838 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486756 2 0.0000 0.8838 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486758 3 0.0000 0.8517 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM486760 1 0.0806 0.8109 0.972 0.000 0.020 0.000 0.008 0.000
#> GSM486762 3 0.1007 0.8378 0.044 0.000 0.956 0.000 0.000 0.000
#> GSM486764 5 0.5522 0.4591 0.004 0.000 0.116 0.016 0.608 0.256
#> GSM486766 1 0.2512 0.7942 0.880 0.000 0.060 0.000 0.060 0.000
#> GSM486768 3 0.5606 0.5520 0.012 0.204 0.652 0.040 0.000 0.092
#> GSM486770 6 0.1168 0.8003 0.016 0.000 0.000 0.028 0.000 0.956
#> GSM486772 2 0.0146 0.8803 0.000 0.996 0.004 0.000 0.000 0.000
#> GSM486774 3 0.0146 0.8515 0.000 0.000 0.996 0.004 0.000 0.000
#> GSM486776 1 0.2378 0.7269 0.848 0.000 0.000 0.000 0.152 0.000
#> GSM486778 1 0.2340 0.7719 0.852 0.000 0.148 0.000 0.000 0.000
#> GSM486780 2 0.0000 0.8838 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486782 3 0.2491 0.7425 0.000 0.164 0.836 0.000 0.000 0.000
#> GSM486784 2 0.0000 0.8838 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486786 1 0.1908 0.8004 0.900 0.000 0.096 0.000 0.004 0.000
#> GSM486788 1 0.2821 0.7455 0.832 0.000 0.152 0.000 0.016 0.000
#> GSM486790 2 0.0603 0.8699 0.004 0.980 0.000 0.000 0.000 0.016
#> GSM486792 5 0.3488 0.6505 0.004 0.000 0.244 0.008 0.744 0.000
#> GSM486794 3 0.3168 0.6750 0.192 0.000 0.792 0.000 0.016 0.000
#> GSM486796 3 0.0891 0.8469 0.024 0.008 0.968 0.000 0.000 0.000
#> GSM486798 3 0.0000 0.8517 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM486800 1 0.0790 0.8060 0.968 0.000 0.000 0.000 0.032 0.000
#> GSM486802 1 0.4682 0.5104 0.640 0.000 0.284 0.000 0.076 0.000
#> GSM486804 3 0.4047 0.3682 0.384 0.000 0.604 0.000 0.012 0.000
#> GSM486806 3 0.0000 0.8517 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM486808 3 0.0291 0.8506 0.004 0.000 0.992 0.000 0.004 0.000
#> GSM486810 3 0.5967 0.1953 0.000 0.088 0.488 0.044 0.000 0.380
#> GSM486812 1 0.0865 0.8119 0.964 0.000 0.036 0.000 0.000 0.000
#> GSM486814 2 0.0000 0.8838 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486816 1 0.3240 0.6910 0.752 0.000 0.244 0.000 0.004 0.000
#> GSM486818 3 0.1418 0.8413 0.032 0.024 0.944 0.000 0.000 0.000
#> GSM486821 5 0.3032 0.8373 0.096 0.004 0.004 0.016 0.860 0.020
#> GSM486823 2 0.6756 -0.1412 0.004 0.368 0.276 0.028 0.000 0.324
#> GSM486826 1 0.3881 0.3669 0.600 0.000 0.396 0.000 0.004 0.000
#> GSM486830 3 0.5994 0.4113 0.012 0.012 0.568 0.184 0.000 0.224
#> GSM486832 5 0.0146 0.8987 0.004 0.000 0.000 0.000 0.996 0.000
#> GSM486834 3 0.0000 0.8517 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM486836 3 0.5948 0.0844 0.328 0.000 0.440 0.000 0.232 0.000
#> GSM486838 3 0.0000 0.8517 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM486840 1 0.0777 0.8084 0.972 0.000 0.004 0.000 0.024 0.000
#> GSM486842 1 0.0508 0.8079 0.984 0.000 0.004 0.000 0.012 0.000
#> GSM486844 3 0.3265 0.6517 0.248 0.000 0.748 0.000 0.004 0.000
#> GSM486846 4 0.2996 0.6682 0.000 0.000 0.228 0.772 0.000 0.000
#> GSM486848 1 0.0458 0.8064 0.984 0.000 0.000 0.000 0.016 0.000
#> GSM486850 2 0.1075 0.8385 0.000 0.952 0.048 0.000 0.000 0.000
#> GSM486852 5 0.0508 0.8985 0.004 0.000 0.000 0.012 0.984 0.000
#> GSM486854 2 0.0000 0.8838 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486856 2 0.0000 0.8838 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486858 3 0.1930 0.8250 0.000 0.048 0.916 0.036 0.000 0.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> SD:pam 107 1.02e-03 1.94e-02 2
#> SD:pam 105 4.30e-04 2.81e-04 3
#> SD:pam 103 7.57e-04 1.30e-06 4
#> SD:pam 78 5.91e-05 1.05e-03 5
#> SD:pam 108 1.39e-07 4.44e-05 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["SD", "mclust"]
# you can also extract it by
# res = res_list["SD:mclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'SD' method.
#> Subgroups are detected by 'mclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.495 0.902 0.901 0.4955 0.496 0.496
#> 3 3 0.395 0.673 0.788 0.1945 0.951 0.901
#> 4 4 0.609 0.794 0.803 0.2514 0.751 0.472
#> 5 5 0.729 0.826 0.857 0.0641 0.866 0.541
#> 6 6 0.732 0.684 0.771 0.0322 0.931 0.702
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 1 0.6973 0.903 0.812 0.188
#> GSM486737 1 0.6801 0.909 0.820 0.180
#> GSM486739 1 0.7299 0.901 0.796 0.204
#> GSM486741 1 0.6531 0.909 0.832 0.168
#> GSM486743 1 0.6801 0.909 0.820 0.180
#> GSM486745 1 0.7219 0.902 0.800 0.200
#> GSM486747 1 0.4022 0.912 0.920 0.080
#> GSM486749 1 0.6343 0.912 0.840 0.160
#> GSM486751 1 0.4939 0.916 0.892 0.108
#> GSM486753 1 0.7056 0.903 0.808 0.192
#> GSM486755 1 0.6887 0.908 0.816 0.184
#> GSM486757 1 0.4939 0.916 0.892 0.108
#> GSM486759 1 0.0938 0.886 0.988 0.012
#> GSM486761 1 0.0000 0.886 1.000 0.000
#> GSM486763 1 0.7219 0.902 0.800 0.200
#> GSM486765 1 0.0000 0.886 1.000 0.000
#> GSM486767 1 0.7219 0.902 0.800 0.200
#> GSM486769 1 0.6973 0.903 0.812 0.188
#> GSM486771 1 0.6801 0.909 0.820 0.180
#> GSM486773 1 0.5178 0.916 0.884 0.116
#> GSM486775 1 0.0938 0.886 0.988 0.012
#> GSM486777 1 0.0000 0.886 1.000 0.000
#> GSM486779 1 0.6712 0.911 0.824 0.176
#> GSM486781 1 0.5178 0.916 0.884 0.116
#> GSM486783 1 0.6801 0.909 0.820 0.180
#> GSM486785 1 0.0000 0.886 1.000 0.000
#> GSM486787 1 0.0938 0.886 0.988 0.012
#> GSM486789 1 0.7056 0.902 0.808 0.192
#> GSM486791 1 0.7219 0.902 0.800 0.200
#> GSM486793 1 0.0000 0.886 1.000 0.000
#> GSM486795 1 0.5408 0.916 0.876 0.124
#> GSM486797 1 0.4939 0.916 0.892 0.108
#> GSM486799 1 0.0938 0.886 0.988 0.012
#> GSM486801 1 0.0938 0.886 0.988 0.012
#> GSM486803 1 0.0938 0.886 0.988 0.012
#> GSM486805 1 0.4939 0.916 0.892 0.108
#> GSM486807 1 0.0000 0.886 1.000 0.000
#> GSM486809 1 0.6973 0.903 0.812 0.188
#> GSM486811 1 0.0000 0.886 1.000 0.000
#> GSM486813 1 0.6801 0.909 0.820 0.180
#> GSM486815 1 0.0000 0.886 1.000 0.000
#> GSM486817 1 0.5519 0.916 0.872 0.128
#> GSM486819 1 0.7219 0.902 0.800 0.200
#> GSM486822 1 0.6973 0.903 0.812 0.188
#> GSM486824 1 0.0938 0.886 0.988 0.012
#> GSM486828 1 0.5178 0.916 0.884 0.116
#> GSM486831 1 0.0938 0.886 0.988 0.012
#> GSM486833 1 0.4939 0.916 0.892 0.108
#> GSM486835 1 0.0938 0.886 0.988 0.012
#> GSM486837 1 0.5178 0.916 0.884 0.116
#> GSM486839 1 0.0938 0.886 0.988 0.012
#> GSM486841 1 0.0000 0.886 1.000 0.000
#> GSM486843 1 0.0938 0.886 0.988 0.012
#> GSM486845 1 0.5178 0.916 0.884 0.116
#> GSM486847 1 0.0938 0.886 0.988 0.012
#> GSM486849 1 0.5737 0.915 0.864 0.136
#> GSM486851 1 0.7219 0.902 0.800 0.200
#> GSM486853 1 0.6343 0.911 0.840 0.160
#> GSM486855 1 0.6801 0.909 0.820 0.180
#> GSM486857 1 0.5178 0.916 0.884 0.116
#> GSM486736 2 0.0938 0.904 0.012 0.988
#> GSM486738 2 0.1633 0.911 0.024 0.976
#> GSM486740 2 0.0000 0.904 0.000 1.000
#> GSM486742 2 0.2043 0.911 0.032 0.968
#> GSM486744 2 0.1414 0.912 0.020 0.980
#> GSM486746 2 0.0000 0.904 0.000 1.000
#> GSM486748 2 0.4431 0.916 0.092 0.908
#> GSM486750 2 0.1843 0.911 0.028 0.972
#> GSM486752 2 0.4431 0.916 0.092 0.908
#> GSM486754 2 0.1184 0.911 0.016 0.984
#> GSM486756 2 0.1414 0.912 0.020 0.980
#> GSM486758 2 0.4431 0.916 0.092 0.908
#> GSM486760 2 0.6973 0.884 0.188 0.812
#> GSM486762 2 0.7219 0.884 0.200 0.800
#> GSM486764 2 0.0000 0.904 0.000 1.000
#> GSM486766 2 0.7219 0.884 0.200 0.800
#> GSM486768 2 0.0672 0.908 0.008 0.992
#> GSM486770 2 0.0938 0.904 0.012 0.988
#> GSM486772 2 0.1414 0.912 0.020 0.980
#> GSM486774 2 0.4161 0.917 0.084 0.916
#> GSM486776 2 0.6973 0.884 0.188 0.812
#> GSM486778 2 0.7219 0.884 0.200 0.800
#> GSM486780 2 0.1633 0.913 0.024 0.976
#> GSM486782 2 0.4161 0.917 0.084 0.916
#> GSM486784 2 0.1414 0.912 0.020 0.980
#> GSM486786 2 0.7219 0.884 0.200 0.800
#> GSM486788 2 0.6973 0.884 0.188 0.812
#> GSM486790 2 0.0938 0.904 0.012 0.988
#> GSM486792 2 0.0000 0.904 0.000 1.000
#> GSM486794 2 0.7219 0.884 0.200 0.800
#> GSM486796 2 0.3733 0.917 0.072 0.928
#> GSM486798 2 0.4161 0.917 0.084 0.916
#> GSM486800 2 0.6973 0.884 0.188 0.812
#> GSM486802 2 0.6973 0.884 0.188 0.812
#> GSM486804 2 0.6973 0.884 0.188 0.812
#> GSM486806 2 0.4161 0.917 0.084 0.916
#> GSM486808 2 0.7219 0.884 0.200 0.800
#> GSM486810 2 0.0938 0.904 0.012 0.988
#> GSM486812 2 0.7219 0.884 0.200 0.800
#> GSM486814 2 0.1414 0.912 0.020 0.980
#> GSM486816 2 0.7219 0.884 0.200 0.800
#> GSM486818 2 0.3733 0.917 0.072 0.928
#> GSM486821 2 0.0000 0.904 0.000 1.000
#> GSM486823 2 0.0938 0.904 0.012 0.988
#> GSM486826 2 0.6801 0.888 0.180 0.820
#> GSM486830 2 0.4022 0.917 0.080 0.920
#> GSM486832 2 0.6973 0.884 0.188 0.812
#> GSM486834 2 0.4161 0.917 0.084 0.916
#> GSM486836 2 0.6973 0.884 0.188 0.812
#> GSM486838 2 0.4161 0.917 0.084 0.916
#> GSM486840 2 0.6973 0.884 0.188 0.812
#> GSM486842 2 0.7219 0.884 0.200 0.800
#> GSM486844 2 0.6712 0.890 0.176 0.824
#> GSM486846 2 0.4161 0.917 0.084 0.916
#> GSM486848 2 0.6973 0.884 0.188 0.812
#> GSM486850 2 0.2603 0.914 0.044 0.956
#> GSM486852 2 0.0000 0.904 0.000 1.000
#> GSM486854 2 0.2043 0.911 0.032 0.968
#> GSM486856 2 0.1414 0.912 0.020 0.980
#> GSM486858 2 0.4161 0.917 0.084 0.916
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 2 0.6625 0.3274 0.176 0.744 0.080
#> GSM486737 1 0.8620 0.6487 0.536 0.352 0.112
#> GSM486739 1 0.8280 0.6170 0.516 0.404 0.080
#> GSM486741 1 0.8610 0.6630 0.548 0.336 0.116
#> GSM486743 1 0.8553 0.6640 0.552 0.336 0.112
#> GSM486745 1 0.8512 0.6626 0.552 0.340 0.108
#> GSM486747 1 0.6892 0.7086 0.736 0.152 0.112
#> GSM486749 1 0.8907 0.6846 0.560 0.272 0.168
#> GSM486751 1 0.8171 0.7128 0.644 0.184 0.172
#> GSM486753 1 0.9014 0.5880 0.484 0.380 0.136
#> GSM486755 1 0.8663 0.6397 0.524 0.364 0.112
#> GSM486757 1 0.8171 0.7128 0.644 0.184 0.172
#> GSM486759 1 0.0000 0.6380 1.000 0.000 0.000
#> GSM486761 1 0.3272 0.6554 0.904 0.016 0.080
#> GSM486763 1 0.7920 0.6516 0.572 0.360 0.068
#> GSM486765 1 0.3370 0.6541 0.904 0.024 0.072
#> GSM486767 1 0.8712 0.6659 0.556 0.312 0.132
#> GSM486769 2 0.4035 0.5727 0.040 0.880 0.080
#> GSM486771 1 0.8535 0.6669 0.556 0.332 0.112
#> GSM486773 1 0.8841 0.7032 0.580 0.216 0.204
#> GSM486775 1 0.0424 0.6396 0.992 0.008 0.000
#> GSM486777 1 0.3045 0.6513 0.916 0.020 0.064
#> GSM486779 1 0.8496 0.6711 0.564 0.324 0.112
#> GSM486781 1 0.8913 0.6998 0.572 0.220 0.208
#> GSM486783 1 0.8588 0.6579 0.544 0.344 0.112
#> GSM486785 1 0.2845 0.6519 0.920 0.012 0.068
#> GSM486787 1 0.0000 0.6380 1.000 0.000 0.000
#> GSM486789 2 0.5588 0.5426 0.068 0.808 0.124
#> GSM486791 1 0.7824 0.6568 0.580 0.356 0.064
#> GSM486793 1 0.3530 0.6596 0.900 0.032 0.068
#> GSM486795 1 0.7317 0.7163 0.696 0.208 0.096
#> GSM486797 1 0.8216 0.7126 0.640 0.188 0.172
#> GSM486799 1 0.0000 0.6380 1.000 0.000 0.000
#> GSM486801 1 0.1163 0.6557 0.972 0.028 0.000
#> GSM486803 1 0.1411 0.6588 0.964 0.036 0.000
#> GSM486805 1 0.8433 0.7109 0.620 0.204 0.176
#> GSM486807 1 0.3502 0.6545 0.896 0.020 0.084
#> GSM486809 1 0.8250 0.6295 0.528 0.392 0.080
#> GSM486811 1 0.2749 0.6516 0.924 0.012 0.064
#> GSM486813 1 0.8496 0.6711 0.564 0.324 0.112
#> GSM486815 1 0.3045 0.6513 0.916 0.020 0.064
#> GSM486817 1 0.7458 0.7166 0.692 0.196 0.112
#> GSM486819 1 0.8137 0.6857 0.592 0.316 0.092
#> GSM486822 1 0.8850 0.6375 0.516 0.356 0.128
#> GSM486824 1 0.1411 0.6598 0.964 0.036 0.000
#> GSM486828 1 0.8876 0.7016 0.576 0.220 0.204
#> GSM486831 1 0.0892 0.6372 0.980 0.020 0.000
#> GSM486833 1 0.8216 0.7126 0.640 0.188 0.172
#> GSM486835 1 0.0424 0.6396 0.992 0.008 0.000
#> GSM486837 1 0.8668 0.7079 0.596 0.224 0.180
#> GSM486839 1 0.0000 0.6380 1.000 0.000 0.000
#> GSM486841 1 0.2845 0.6519 0.920 0.012 0.068
#> GSM486843 1 0.1529 0.6615 0.960 0.040 0.000
#> GSM486845 1 0.8838 0.7024 0.580 0.220 0.200
#> GSM486847 1 0.0000 0.6380 1.000 0.000 0.000
#> GSM486849 1 0.8726 0.6857 0.564 0.296 0.140
#> GSM486851 1 0.7920 0.6508 0.572 0.360 0.068
#> GSM486853 1 0.9093 0.5651 0.460 0.400 0.140
#> GSM486855 1 0.8496 0.6711 0.564 0.324 0.112
#> GSM486857 1 0.8624 0.7100 0.596 0.240 0.164
#> GSM486736 2 0.5706 0.5692 0.000 0.680 0.320
#> GSM486738 2 0.6305 0.2685 0.000 0.516 0.484
#> GSM486740 3 0.4346 0.6882 0.000 0.184 0.816
#> GSM486742 3 0.6180 -0.0107 0.000 0.416 0.584
#> GSM486744 3 0.2796 0.7299 0.000 0.092 0.908
#> GSM486746 3 0.3116 0.7303 0.000 0.108 0.892
#> GSM486748 3 0.2550 0.7648 0.040 0.024 0.936
#> GSM486750 3 0.2356 0.7392 0.000 0.072 0.928
#> GSM486752 3 0.2116 0.7638 0.040 0.012 0.948
#> GSM486754 3 0.3038 0.7223 0.000 0.104 0.896
#> GSM486756 3 0.4062 0.6817 0.000 0.164 0.836
#> GSM486758 3 0.2414 0.7641 0.040 0.020 0.940
#> GSM486760 3 0.6839 0.7050 0.272 0.044 0.684
#> GSM486762 3 0.6001 0.7255 0.176 0.052 0.772
#> GSM486764 3 0.4629 0.6958 0.004 0.188 0.808
#> GSM486766 3 0.6138 0.7214 0.172 0.060 0.768
#> GSM486768 3 0.2796 0.7271 0.000 0.092 0.908
#> GSM486770 2 0.5926 0.5259 0.000 0.644 0.356
#> GSM486772 3 0.3267 0.7258 0.000 0.116 0.884
#> GSM486774 3 0.1015 0.7595 0.012 0.008 0.980
#> GSM486776 3 0.6839 0.7050 0.272 0.044 0.684
#> GSM486778 3 0.6488 0.7179 0.192 0.064 0.744
#> GSM486780 3 0.3267 0.7258 0.000 0.116 0.884
#> GSM486782 3 0.0829 0.7585 0.012 0.004 0.984
#> GSM486784 3 0.3482 0.7181 0.000 0.128 0.872
#> GSM486786 3 0.6304 0.7185 0.192 0.056 0.752
#> GSM486788 3 0.6839 0.7050 0.272 0.044 0.684
#> GSM486790 3 0.3412 0.7108 0.000 0.124 0.876
#> GSM486792 3 0.5072 0.7079 0.012 0.196 0.792
#> GSM486794 3 0.6203 0.7200 0.184 0.056 0.760
#> GSM486796 3 0.4232 0.7670 0.084 0.044 0.872
#> GSM486798 3 0.1950 0.7634 0.040 0.008 0.952
#> GSM486800 3 0.6839 0.7050 0.272 0.044 0.684
#> GSM486802 3 0.6735 0.7128 0.260 0.044 0.696
#> GSM486804 3 0.6380 0.7298 0.224 0.044 0.732
#> GSM486806 3 0.1711 0.7629 0.032 0.008 0.960
#> GSM486808 3 0.6098 0.7212 0.176 0.056 0.768
#> GSM486810 3 0.4291 0.6904 0.000 0.180 0.820
#> GSM486812 3 0.6258 0.7188 0.196 0.052 0.752
#> GSM486814 3 0.3340 0.7231 0.000 0.120 0.880
#> GSM486816 3 0.6398 0.7181 0.192 0.060 0.748
#> GSM486818 3 0.3459 0.7668 0.096 0.012 0.892
#> GSM486821 3 0.3715 0.7318 0.004 0.128 0.868
#> GSM486823 3 0.6079 0.0490 0.000 0.388 0.612
#> GSM486826 3 0.6490 0.7200 0.256 0.036 0.708
#> GSM486830 3 0.0829 0.7597 0.012 0.004 0.984
#> GSM486832 3 0.7076 0.7043 0.256 0.060 0.684
#> GSM486834 3 0.2152 0.7630 0.036 0.016 0.948
#> GSM486836 3 0.6839 0.7050 0.272 0.044 0.684
#> GSM486838 3 0.1525 0.7644 0.032 0.004 0.964
#> GSM486840 3 0.6839 0.7050 0.272 0.044 0.684
#> GSM486842 3 0.6258 0.7188 0.196 0.052 0.752
#> GSM486844 3 0.6247 0.7349 0.212 0.044 0.744
#> GSM486846 3 0.1182 0.7575 0.012 0.012 0.976
#> GSM486848 3 0.6839 0.7050 0.272 0.044 0.684
#> GSM486850 3 0.2959 0.7355 0.000 0.100 0.900
#> GSM486852 3 0.4784 0.7016 0.004 0.200 0.796
#> GSM486854 3 0.3686 0.7067 0.000 0.140 0.860
#> GSM486856 3 0.3267 0.7258 0.000 0.116 0.884
#> GSM486858 3 0.1482 0.7608 0.020 0.012 0.968
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 4 0.5732 0.6855 0.264 0.064 0.000 0.672
#> GSM486737 4 0.3569 0.8617 0.000 0.196 0.000 0.804
#> GSM486739 4 0.5759 0.6833 0.268 0.064 0.000 0.668
#> GSM486741 4 0.3444 0.8651 0.000 0.184 0.000 0.816
#> GSM486743 4 0.3486 0.8644 0.000 0.188 0.000 0.812
#> GSM486745 4 0.2825 0.8359 0.056 0.012 0.024 0.908
#> GSM486747 1 0.5574 0.7472 0.668 0.000 0.048 0.284
#> GSM486749 4 0.2909 0.8666 0.020 0.092 0.000 0.888
#> GSM486751 1 0.4800 0.6933 0.656 0.000 0.004 0.340
#> GSM486753 4 0.3862 0.8654 0.024 0.152 0.000 0.824
#> GSM486755 4 0.3444 0.8649 0.000 0.184 0.000 0.816
#> GSM486757 1 0.4781 0.6974 0.660 0.000 0.004 0.336
#> GSM486759 1 0.5256 0.8350 0.700 0.000 0.260 0.040
#> GSM486761 1 0.5515 0.8401 0.732 0.000 0.152 0.116
#> GSM486763 1 0.2892 0.6255 0.896 0.068 0.000 0.036
#> GSM486765 1 0.5395 0.8408 0.732 0.000 0.184 0.084
#> GSM486767 4 0.2807 0.8412 0.044 0.020 0.024 0.912
#> GSM486769 4 0.5732 0.6855 0.264 0.064 0.000 0.672
#> GSM486771 4 0.3528 0.8633 0.000 0.192 0.000 0.808
#> GSM486773 4 0.0817 0.8191 0.024 0.000 0.000 0.976
#> GSM486775 1 0.5256 0.8350 0.700 0.000 0.260 0.040
#> GSM486777 1 0.5371 0.8408 0.732 0.000 0.188 0.080
#> GSM486779 4 0.3528 0.8633 0.000 0.192 0.000 0.808
#> GSM486781 4 0.1520 0.8338 0.020 0.024 0.000 0.956
#> GSM486783 4 0.3569 0.8617 0.000 0.196 0.000 0.804
#> GSM486785 1 0.5395 0.8408 0.732 0.000 0.184 0.084
#> GSM486787 1 0.5256 0.8350 0.700 0.000 0.260 0.040
#> GSM486789 4 0.3999 0.8572 0.036 0.140 0.000 0.824
#> GSM486791 1 0.2892 0.6255 0.896 0.068 0.000 0.036
#> GSM486793 1 0.5395 0.8408 0.732 0.000 0.184 0.084
#> GSM486795 1 0.6194 0.6988 0.632 0.008 0.060 0.300
#> GSM486797 1 0.4936 0.6526 0.624 0.000 0.004 0.372
#> GSM486799 1 0.5256 0.8350 0.700 0.000 0.260 0.040
#> GSM486801 1 0.5763 0.8377 0.700 0.000 0.204 0.096
#> GSM486803 1 0.5710 0.8405 0.708 0.000 0.192 0.100
#> GSM486805 4 0.1867 0.7791 0.072 0.000 0.000 0.928
#> GSM486807 1 0.5417 0.8399 0.732 0.000 0.180 0.088
#> GSM486809 4 0.5732 0.6855 0.264 0.064 0.000 0.672
#> GSM486811 1 0.5371 0.8408 0.732 0.000 0.188 0.080
#> GSM486813 4 0.3528 0.8633 0.000 0.192 0.000 0.808
#> GSM486815 1 0.5371 0.8408 0.732 0.000 0.188 0.080
#> GSM486817 4 0.2744 0.8158 0.024 0.012 0.052 0.912
#> GSM486819 1 0.5314 0.6534 0.676 0.004 0.024 0.296
#> GSM486822 4 0.3907 0.8599 0.044 0.120 0.000 0.836
#> GSM486824 1 0.5803 0.8374 0.700 0.000 0.196 0.104
#> GSM486828 4 0.0817 0.8191 0.024 0.000 0.000 0.976
#> GSM486831 1 0.5137 0.8382 0.716 0.000 0.244 0.040
#> GSM486833 1 0.4661 0.6846 0.652 0.000 0.000 0.348
#> GSM486835 1 0.5256 0.8350 0.700 0.000 0.260 0.040
#> GSM486837 4 0.1697 0.8336 0.016 0.028 0.004 0.952
#> GSM486839 1 0.5256 0.8350 0.700 0.000 0.260 0.040
#> GSM486841 1 0.5371 0.8408 0.732 0.000 0.188 0.080
#> GSM486843 1 0.5803 0.8374 0.700 0.000 0.196 0.104
#> GSM486845 4 0.1114 0.8251 0.016 0.008 0.004 0.972
#> GSM486847 1 0.5256 0.8350 0.700 0.000 0.260 0.040
#> GSM486849 4 0.3123 0.8673 0.000 0.156 0.000 0.844
#> GSM486851 1 0.2892 0.6255 0.896 0.068 0.000 0.036
#> GSM486853 4 0.3172 0.8685 0.000 0.160 0.000 0.840
#> GSM486855 4 0.3528 0.8633 0.000 0.192 0.000 0.808
#> GSM486857 4 0.1985 0.8391 0.016 0.040 0.004 0.940
#> GSM486736 2 0.5337 0.6675 0.260 0.696 0.000 0.044
#> GSM486738 2 0.2124 0.8543 0.000 0.924 0.068 0.008
#> GSM486740 2 0.5227 0.6727 0.256 0.704 0.000 0.040
#> GSM486742 2 0.2635 0.8616 0.000 0.904 0.076 0.020
#> GSM486744 2 0.2546 0.8626 0.000 0.900 0.092 0.008
#> GSM486746 2 0.6333 0.8233 0.052 0.724 0.112 0.112
#> GSM486748 3 0.6416 0.6715 0.024 0.120 0.696 0.160
#> GSM486750 2 0.4882 0.8601 0.032 0.812 0.084 0.072
#> GSM486752 3 0.5952 0.7051 0.024 0.084 0.728 0.164
#> GSM486754 2 0.2821 0.8635 0.004 0.900 0.076 0.020
#> GSM486756 2 0.2412 0.8619 0.000 0.908 0.084 0.008
#> GSM486758 3 0.6014 0.7017 0.024 0.088 0.724 0.164
#> GSM486760 3 0.0188 0.8311 0.004 0.000 0.996 0.000
#> GSM486762 3 0.3047 0.8326 0.040 0.012 0.900 0.048
#> GSM486764 3 0.6873 0.6044 0.264 0.072 0.628 0.036
#> GSM486766 3 0.2313 0.8342 0.032 0.000 0.924 0.044
#> GSM486768 2 0.5825 0.8354 0.028 0.748 0.116 0.108
#> GSM486770 2 0.5337 0.6675 0.260 0.696 0.000 0.044
#> GSM486772 2 0.2334 0.8610 0.000 0.908 0.088 0.004
#> GSM486774 2 0.6116 0.8109 0.024 0.716 0.092 0.168
#> GSM486776 3 0.0188 0.8311 0.004 0.000 0.996 0.000
#> GSM486778 3 0.2411 0.8329 0.040 0.000 0.920 0.040
#> GSM486780 2 0.2334 0.8610 0.000 0.908 0.088 0.004
#> GSM486782 2 0.5795 0.8248 0.020 0.740 0.092 0.148
#> GSM486784 2 0.2266 0.8604 0.000 0.912 0.084 0.004
#> GSM486786 3 0.2500 0.8322 0.040 0.000 0.916 0.044
#> GSM486788 3 0.0000 0.8323 0.000 0.000 1.000 0.000
#> GSM486790 2 0.4314 0.8569 0.036 0.844 0.072 0.048
#> GSM486792 3 0.6873 0.6044 0.264 0.072 0.628 0.036
#> GSM486794 3 0.2411 0.8329 0.040 0.000 0.920 0.040
#> GSM486796 3 0.6493 0.5018 0.004 0.240 0.640 0.116
#> GSM486798 2 0.6448 0.7911 0.024 0.692 0.116 0.168
#> GSM486800 3 0.0188 0.8311 0.004 0.000 0.996 0.000
#> GSM486802 3 0.1004 0.8344 0.004 0.024 0.972 0.000
#> GSM486804 3 0.1637 0.8249 0.000 0.060 0.940 0.000
#> GSM486806 2 0.6116 0.8109 0.024 0.716 0.092 0.168
#> GSM486808 3 0.2399 0.8333 0.032 0.000 0.920 0.048
#> GSM486810 2 0.6147 0.7152 0.232 0.688 0.032 0.048
#> GSM486812 3 0.2411 0.8329 0.040 0.000 0.920 0.040
#> GSM486814 2 0.2266 0.8604 0.000 0.912 0.084 0.004
#> GSM486816 3 0.2411 0.8329 0.040 0.000 0.920 0.040
#> GSM486818 3 0.7267 0.0603 0.008 0.372 0.500 0.120
#> GSM486821 3 0.6388 0.6797 0.064 0.108 0.724 0.104
#> GSM486823 2 0.4480 0.8544 0.036 0.836 0.068 0.060
#> GSM486826 3 0.1492 0.8340 0.004 0.036 0.956 0.004
#> GSM486830 2 0.6057 0.8139 0.020 0.716 0.092 0.172
#> GSM486832 3 0.0469 0.8346 0.012 0.000 0.988 0.000
#> GSM486834 3 0.6777 0.6352 0.024 0.140 0.664 0.172
#> GSM486836 3 0.0000 0.8323 0.000 0.000 1.000 0.000
#> GSM486838 2 0.5779 0.8229 0.016 0.736 0.092 0.156
#> GSM486840 3 0.0188 0.8311 0.004 0.000 0.996 0.000
#> GSM486842 3 0.2319 0.8338 0.036 0.000 0.924 0.040
#> GSM486844 3 0.2053 0.8183 0.000 0.072 0.924 0.004
#> GSM486846 2 0.5837 0.8195 0.012 0.724 0.092 0.172
#> GSM486848 3 0.0188 0.8311 0.004 0.000 0.996 0.000
#> GSM486850 2 0.3243 0.8636 0.000 0.876 0.088 0.036
#> GSM486852 3 0.6873 0.6044 0.264 0.072 0.628 0.036
#> GSM486854 2 0.3082 0.8652 0.000 0.884 0.084 0.032
#> GSM486856 2 0.2334 0.8610 0.000 0.908 0.088 0.004
#> GSM486858 2 0.5337 0.8379 0.016 0.772 0.092 0.120
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 5 0.0963 0.863 0.000 0.000 0.000 0.036 0.964
#> GSM486737 4 0.3123 0.820 0.000 0.184 0.004 0.812 0.000
#> GSM486739 5 0.1043 0.858 0.000 0.000 0.000 0.040 0.960
#> GSM486741 4 0.2921 0.829 0.000 0.148 0.004 0.844 0.004
#> GSM486743 4 0.3048 0.824 0.000 0.176 0.000 0.820 0.004
#> GSM486745 4 0.4123 0.753 0.008 0.004 0.020 0.768 0.200
#> GSM486747 1 0.3950 0.791 0.812 0.008 0.068 0.112 0.000
#> GSM486749 4 0.2464 0.833 0.000 0.048 0.004 0.904 0.044
#> GSM486751 1 0.5797 0.116 0.492 0.008 0.068 0.432 0.000
#> GSM486753 4 0.3859 0.814 0.000 0.072 0.008 0.820 0.100
#> GSM486755 4 0.3764 0.825 0.000 0.156 0.000 0.800 0.044
#> GSM486757 1 0.4305 0.741 0.768 0.008 0.048 0.176 0.000
#> GSM486759 1 0.0162 0.909 0.996 0.000 0.004 0.000 0.000
#> GSM486761 1 0.2208 0.897 0.908 0.000 0.072 0.020 0.000
#> GSM486763 5 0.3058 0.839 0.096 0.000 0.044 0.000 0.860
#> GSM486765 1 0.1908 0.898 0.908 0.000 0.092 0.000 0.000
#> GSM486767 4 0.3299 0.804 0.008 0.016 0.016 0.860 0.100
#> GSM486769 5 0.1043 0.863 0.000 0.000 0.000 0.040 0.960
#> GSM486771 4 0.3123 0.822 0.000 0.184 0.000 0.812 0.004
#> GSM486773 4 0.0740 0.815 0.000 0.004 0.008 0.980 0.008
#> GSM486775 1 0.0162 0.909 0.996 0.000 0.004 0.000 0.000
#> GSM486777 1 0.1965 0.897 0.904 0.000 0.096 0.000 0.000
#> GSM486779 4 0.2929 0.823 0.000 0.180 0.000 0.820 0.000
#> GSM486781 4 0.1087 0.817 0.000 0.008 0.016 0.968 0.008
#> GSM486783 4 0.3123 0.820 0.000 0.184 0.004 0.812 0.000
#> GSM486785 1 0.1732 0.901 0.920 0.000 0.080 0.000 0.000
#> GSM486787 1 0.0162 0.909 0.996 0.000 0.004 0.000 0.000
#> GSM486789 4 0.4113 0.785 0.000 0.048 0.008 0.788 0.156
#> GSM486791 5 0.3758 0.819 0.096 0.000 0.088 0.000 0.816
#> GSM486793 1 0.2077 0.899 0.908 0.000 0.084 0.008 0.000
#> GSM486795 4 0.5683 0.132 0.464 0.008 0.040 0.480 0.008
#> GSM486797 4 0.5379 0.363 0.340 0.008 0.052 0.600 0.000
#> GSM486799 1 0.0162 0.909 0.996 0.000 0.004 0.000 0.000
#> GSM486801 1 0.0324 0.909 0.992 0.000 0.004 0.004 0.000
#> GSM486803 1 0.0324 0.909 0.992 0.000 0.004 0.004 0.000
#> GSM486805 4 0.2875 0.783 0.052 0.008 0.056 0.884 0.000
#> GSM486807 1 0.2189 0.897 0.904 0.000 0.084 0.012 0.000
#> GSM486809 5 0.1410 0.850 0.000 0.000 0.000 0.060 0.940
#> GSM486811 1 0.1965 0.897 0.904 0.000 0.096 0.000 0.000
#> GSM486813 4 0.2929 0.823 0.000 0.180 0.000 0.820 0.000
#> GSM486815 1 0.1965 0.897 0.904 0.000 0.096 0.000 0.000
#> GSM486817 4 0.3336 0.800 0.076 0.008 0.044 0.864 0.008
#> GSM486819 4 0.6089 0.647 0.184 0.004 0.060 0.668 0.084
#> GSM486822 4 0.3518 0.810 0.000 0.048 0.008 0.840 0.104
#> GSM486824 1 0.0162 0.909 0.996 0.000 0.004 0.000 0.000
#> GSM486828 4 0.1186 0.813 0.000 0.008 0.008 0.964 0.020
#> GSM486831 1 0.0963 0.907 0.964 0.000 0.036 0.000 0.000
#> GSM486833 4 0.5370 0.153 0.408 0.008 0.040 0.544 0.000
#> GSM486835 1 0.0162 0.909 0.996 0.000 0.004 0.000 0.000
#> GSM486837 4 0.1408 0.824 0.000 0.044 0.008 0.948 0.000
#> GSM486839 1 0.0162 0.909 0.996 0.000 0.004 0.000 0.000
#> GSM486841 1 0.1851 0.899 0.912 0.000 0.088 0.000 0.000
#> GSM486843 1 0.0324 0.909 0.992 0.000 0.004 0.004 0.000
#> GSM486845 4 0.1124 0.811 0.000 0.004 0.036 0.960 0.000
#> GSM486847 1 0.0162 0.909 0.996 0.000 0.004 0.000 0.000
#> GSM486849 4 0.2411 0.835 0.000 0.108 0.000 0.884 0.008
#> GSM486851 5 0.3201 0.836 0.096 0.000 0.052 0.000 0.852
#> GSM486853 4 0.2570 0.834 0.000 0.108 0.004 0.880 0.008
#> GSM486855 4 0.2929 0.823 0.000 0.180 0.000 0.820 0.000
#> GSM486857 4 0.1124 0.827 0.000 0.036 0.004 0.960 0.000
#> GSM486736 5 0.2331 0.856 0.000 0.080 0.000 0.020 0.900
#> GSM486738 2 0.0671 0.839 0.000 0.980 0.004 0.016 0.000
#> GSM486740 5 0.2358 0.842 0.000 0.104 0.000 0.008 0.888
#> GSM486742 2 0.1205 0.846 0.000 0.956 0.004 0.040 0.000
#> GSM486744 2 0.0566 0.846 0.000 0.984 0.004 0.012 0.000
#> GSM486746 2 0.4148 0.823 0.008 0.816 0.016 0.056 0.104
#> GSM486748 2 0.5946 0.481 0.000 0.508 0.380 0.112 0.000
#> GSM486750 2 0.3536 0.848 0.000 0.840 0.008 0.100 0.052
#> GSM486752 2 0.5039 0.764 0.000 0.700 0.184 0.116 0.000
#> GSM486754 2 0.1673 0.852 0.000 0.944 0.008 0.032 0.016
#> GSM486756 2 0.0771 0.843 0.000 0.976 0.004 0.020 0.000
#> GSM486758 2 0.6032 0.454 0.000 0.492 0.388 0.120 0.000
#> GSM486760 3 0.3074 0.946 0.196 0.000 0.804 0.000 0.000
#> GSM486762 3 0.2470 0.930 0.104 0.000 0.884 0.012 0.000
#> GSM486764 5 0.2516 0.838 0.000 0.000 0.140 0.000 0.860
#> GSM486766 3 0.2074 0.933 0.104 0.000 0.896 0.000 0.000
#> GSM486768 2 0.3627 0.850 0.008 0.856 0.024 0.060 0.052
#> GSM486770 5 0.2423 0.855 0.000 0.080 0.000 0.024 0.896
#> GSM486772 2 0.0404 0.842 0.000 0.988 0.000 0.012 0.000
#> GSM486774 2 0.3421 0.845 0.000 0.816 0.016 0.164 0.004
#> GSM486776 3 0.3074 0.946 0.196 0.000 0.804 0.000 0.000
#> GSM486778 3 0.2074 0.925 0.104 0.000 0.896 0.000 0.000
#> GSM486780 2 0.0566 0.843 0.000 0.984 0.004 0.012 0.000
#> GSM486782 2 0.3283 0.849 0.000 0.832 0.028 0.140 0.000
#> GSM486784 2 0.0404 0.842 0.000 0.988 0.000 0.012 0.000
#> GSM486786 3 0.2280 0.933 0.120 0.000 0.880 0.000 0.000
#> GSM486788 3 0.3039 0.945 0.192 0.000 0.808 0.000 0.000
#> GSM486790 2 0.3333 0.837 0.000 0.856 0.008 0.060 0.076
#> GSM486792 5 0.2966 0.818 0.000 0.000 0.184 0.000 0.816
#> GSM486794 3 0.2462 0.930 0.112 0.000 0.880 0.008 0.000
#> GSM486796 2 0.6079 0.725 0.076 0.684 0.172 0.052 0.016
#> GSM486798 2 0.3531 0.842 0.000 0.816 0.036 0.148 0.000
#> GSM486800 3 0.3074 0.946 0.196 0.000 0.804 0.000 0.000
#> GSM486802 3 0.3074 0.946 0.196 0.000 0.804 0.000 0.000
#> GSM486804 3 0.3053 0.927 0.164 0.008 0.828 0.000 0.000
#> GSM486806 2 0.3595 0.841 0.000 0.816 0.044 0.140 0.000
#> GSM486808 3 0.2464 0.925 0.096 0.000 0.888 0.016 0.000
#> GSM486810 5 0.4835 0.283 0.000 0.384 0.004 0.020 0.592
#> GSM486812 3 0.2127 0.932 0.108 0.000 0.892 0.000 0.000
#> GSM486814 2 0.0566 0.840 0.000 0.984 0.004 0.012 0.000
#> GSM486816 3 0.2074 0.925 0.104 0.000 0.896 0.000 0.000
#> GSM486818 2 0.5353 0.795 0.064 0.748 0.108 0.072 0.008
#> GSM486821 2 0.5684 0.758 0.008 0.716 0.140 0.052 0.084
#> GSM486823 2 0.3523 0.834 0.000 0.844 0.008 0.072 0.076
#> GSM486826 3 0.3074 0.946 0.196 0.000 0.804 0.000 0.000
#> GSM486830 2 0.3421 0.845 0.000 0.816 0.016 0.164 0.004
#> GSM486832 3 0.2773 0.943 0.164 0.000 0.836 0.000 0.000
#> GSM486834 2 0.4764 0.799 0.000 0.732 0.128 0.140 0.000
#> GSM486836 3 0.3039 0.945 0.192 0.000 0.808 0.000 0.000
#> GSM486838 2 0.3400 0.848 0.000 0.828 0.036 0.136 0.000
#> GSM486840 3 0.3074 0.946 0.196 0.000 0.804 0.000 0.000
#> GSM486842 3 0.2127 0.932 0.108 0.000 0.892 0.000 0.000
#> GSM486844 3 0.3171 0.936 0.176 0.008 0.816 0.000 0.000
#> GSM486846 2 0.3595 0.844 0.000 0.816 0.044 0.140 0.000
#> GSM486848 3 0.3109 0.944 0.200 0.000 0.800 0.000 0.000
#> GSM486850 2 0.1764 0.854 0.000 0.928 0.000 0.064 0.008
#> GSM486852 5 0.2605 0.836 0.000 0.000 0.148 0.000 0.852
#> GSM486854 2 0.1956 0.855 0.000 0.916 0.000 0.076 0.008
#> GSM486856 2 0.0404 0.842 0.000 0.988 0.000 0.012 0.000
#> GSM486858 2 0.2753 0.854 0.000 0.856 0.008 0.136 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 3 0.4264 0.59361 0.000 0.000 0.496 0.016 0.000 0.488
#> GSM486737 4 0.2762 0.80772 0.000 0.196 0.000 0.804 0.000 0.000
#> GSM486739 3 0.4256 0.59473 0.000 0.000 0.520 0.016 0.000 0.464
#> GSM486741 4 0.2631 0.81390 0.000 0.152 0.000 0.840 0.000 0.008
#> GSM486743 4 0.3319 0.81078 0.000 0.176 0.016 0.800 0.004 0.004
#> GSM486745 4 0.5735 0.46188 0.000 0.012 0.284 0.572 0.008 0.124
#> GSM486747 5 0.2981 0.78496 0.020 0.000 0.016 0.116 0.848 0.000
#> GSM486749 4 0.3404 0.80204 0.000 0.064 0.012 0.840 0.008 0.076
#> GSM486751 5 0.4378 0.25842 0.000 0.000 0.016 0.452 0.528 0.004
#> GSM486753 4 0.4304 0.78076 0.000 0.068 0.040 0.784 0.008 0.100
#> GSM486755 4 0.3675 0.81032 0.000 0.164 0.028 0.792 0.008 0.008
#> GSM486757 5 0.3669 0.69508 0.000 0.000 0.028 0.208 0.760 0.004
#> GSM486759 5 0.2178 0.85254 0.132 0.000 0.000 0.000 0.868 0.000
#> GSM486761 5 0.0865 0.84028 0.036 0.000 0.000 0.000 0.964 0.000
#> GSM486763 3 0.3714 0.56166 0.000 0.000 0.656 0.000 0.004 0.340
#> GSM486765 5 0.1267 0.82796 0.060 0.000 0.000 0.000 0.940 0.000
#> GSM486767 4 0.2326 0.78694 0.000 0.020 0.040 0.908 0.004 0.028
#> GSM486769 3 0.4264 0.59361 0.000 0.000 0.496 0.016 0.000 0.488
#> GSM486771 4 0.3043 0.80817 0.000 0.196 0.004 0.796 0.004 0.000
#> GSM486773 4 0.1078 0.77887 0.000 0.000 0.012 0.964 0.016 0.008
#> GSM486775 5 0.2178 0.85128 0.132 0.000 0.000 0.000 0.868 0.000
#> GSM486777 5 0.0790 0.84093 0.032 0.000 0.000 0.000 0.968 0.000
#> GSM486779 4 0.2762 0.80772 0.000 0.196 0.000 0.804 0.000 0.000
#> GSM486781 4 0.1036 0.78718 0.000 0.008 0.024 0.964 0.004 0.000
#> GSM486783 4 0.2902 0.80674 0.000 0.196 0.004 0.800 0.000 0.000
#> GSM486785 5 0.0858 0.84551 0.028 0.000 0.000 0.004 0.968 0.000
#> GSM486787 5 0.2135 0.85185 0.128 0.000 0.000 0.000 0.872 0.000
#> GSM486789 4 0.5778 0.59244 0.000 0.028 0.176 0.624 0.008 0.164
#> GSM486791 3 0.3714 0.56166 0.000 0.000 0.656 0.000 0.004 0.340
#> GSM486793 5 0.1075 0.83257 0.048 0.000 0.000 0.000 0.952 0.000
#> GSM486795 5 0.5101 0.23422 0.040 0.000 0.008 0.452 0.492 0.008
#> GSM486797 4 0.4374 -0.06413 0.000 0.000 0.016 0.532 0.448 0.004
#> GSM486799 5 0.2178 0.85254 0.132 0.000 0.000 0.000 0.868 0.000
#> GSM486801 5 0.2092 0.85078 0.124 0.000 0.000 0.000 0.876 0.000
#> GSM486803 5 0.2178 0.85365 0.132 0.000 0.000 0.000 0.868 0.000
#> GSM486805 4 0.2592 0.70934 0.000 0.000 0.016 0.864 0.116 0.004
#> GSM486807 5 0.1444 0.82253 0.072 0.000 0.000 0.000 0.928 0.000
#> GSM486809 3 0.4264 0.59601 0.000 0.000 0.500 0.016 0.000 0.484
#> GSM486811 5 0.0790 0.84093 0.032 0.000 0.000 0.000 0.968 0.000
#> GSM486813 4 0.2762 0.80772 0.000 0.196 0.000 0.804 0.000 0.000
#> GSM486815 5 0.0790 0.83777 0.032 0.000 0.000 0.000 0.968 0.000
#> GSM486817 4 0.2514 0.75604 0.032 0.000 0.016 0.896 0.052 0.004
#> GSM486819 5 0.6426 -0.00650 0.000 0.000 0.192 0.384 0.396 0.028
#> GSM486822 4 0.4070 0.72466 0.000 0.004 0.064 0.768 0.008 0.156
#> GSM486824 5 0.2446 0.84842 0.124 0.000 0.000 0.012 0.864 0.000
#> GSM486828 4 0.1116 0.78042 0.000 0.000 0.028 0.960 0.004 0.008
#> GSM486831 5 0.2003 0.85478 0.116 0.000 0.000 0.000 0.884 0.000
#> GSM486833 4 0.4598 -0.12141 0.000 0.000 0.028 0.504 0.464 0.004
#> GSM486835 5 0.2260 0.85129 0.140 0.000 0.000 0.000 0.860 0.000
#> GSM486837 4 0.1367 0.80522 0.000 0.044 0.000 0.944 0.012 0.000
#> GSM486839 5 0.2234 0.85007 0.124 0.000 0.000 0.004 0.872 0.000
#> GSM486841 5 0.0713 0.83952 0.028 0.000 0.000 0.000 0.972 0.000
#> GSM486843 5 0.2431 0.85188 0.132 0.000 0.000 0.008 0.860 0.000
#> GSM486845 4 0.0458 0.79301 0.000 0.016 0.000 0.984 0.000 0.000
#> GSM486847 5 0.2234 0.85007 0.124 0.000 0.000 0.004 0.872 0.000
#> GSM486849 4 0.2553 0.81484 0.000 0.144 0.000 0.848 0.000 0.008
#> GSM486851 3 0.3714 0.56166 0.000 0.000 0.656 0.000 0.004 0.340
#> GSM486853 4 0.2695 0.81463 0.000 0.144 0.004 0.844 0.000 0.008
#> GSM486855 4 0.2762 0.80772 0.000 0.196 0.000 0.804 0.000 0.000
#> GSM486857 4 0.1219 0.80610 0.000 0.048 0.000 0.948 0.004 0.000
#> GSM486736 6 0.0964 0.61965 0.000 0.004 0.012 0.016 0.000 0.968
#> GSM486738 2 0.2278 0.72160 0.000 0.868 0.128 0.004 0.000 0.000
#> GSM486740 6 0.1773 0.63578 0.000 0.016 0.036 0.016 0.000 0.932
#> GSM486742 2 0.3079 0.73067 0.000 0.836 0.128 0.028 0.000 0.008
#> GSM486744 2 0.1647 0.78231 0.008 0.940 0.032 0.016 0.000 0.004
#> GSM486746 6 0.6869 0.16484 0.004 0.264 0.172 0.080 0.000 0.480
#> GSM486748 1 0.7424 0.42846 0.500 0.156 0.172 0.136 0.036 0.000
#> GSM486750 2 0.3993 0.75017 0.008 0.812 0.040 0.044 0.004 0.092
#> GSM486752 1 0.7544 0.36891 0.468 0.184 0.176 0.144 0.028 0.000
#> GSM486754 2 0.2414 0.77553 0.008 0.904 0.056 0.016 0.004 0.012
#> GSM486756 2 0.2350 0.76750 0.008 0.896 0.076 0.016 0.000 0.004
#> GSM486758 1 0.7282 0.43979 0.512 0.152 0.164 0.144 0.028 0.000
#> GSM486760 1 0.0458 0.78639 0.984 0.000 0.000 0.000 0.016 0.000
#> GSM486762 1 0.2092 0.77414 0.876 0.000 0.000 0.000 0.124 0.000
#> GSM486764 6 0.2527 0.58212 0.000 0.000 0.168 0.000 0.000 0.832
#> GSM486766 1 0.1863 0.77881 0.896 0.000 0.000 0.000 0.104 0.000
#> GSM486768 2 0.4924 0.71525 0.008 0.712 0.160 0.100 0.000 0.020
#> GSM486770 6 0.0964 0.61974 0.000 0.004 0.012 0.016 0.000 0.968
#> GSM486772 2 0.0692 0.77990 0.004 0.976 0.020 0.000 0.000 0.000
#> GSM486774 2 0.5267 0.68368 0.008 0.648 0.160 0.180 0.000 0.004
#> GSM486776 1 0.0458 0.78589 0.984 0.000 0.000 0.000 0.016 0.000
#> GSM486778 1 0.2300 0.77435 0.856 0.000 0.000 0.000 0.144 0.000
#> GSM486780 2 0.0837 0.77581 0.004 0.972 0.020 0.004 0.000 0.000
#> GSM486782 2 0.4780 0.71541 0.008 0.692 0.120 0.180 0.000 0.000
#> GSM486784 2 0.1285 0.76850 0.000 0.944 0.052 0.004 0.000 0.000
#> GSM486786 1 0.2300 0.77335 0.856 0.000 0.000 0.000 0.144 0.000
#> GSM486788 1 0.0363 0.78682 0.988 0.000 0.000 0.000 0.012 0.000
#> GSM486790 2 0.5340 0.60942 0.004 0.664 0.128 0.016 0.004 0.184
#> GSM486792 6 0.2703 0.58283 0.004 0.000 0.172 0.000 0.000 0.824
#> GSM486794 1 0.2135 0.77232 0.872 0.000 0.000 0.000 0.128 0.000
#> GSM486796 1 0.7138 0.23007 0.452 0.264 0.164 0.116 0.004 0.000
#> GSM486798 2 0.6169 0.62224 0.068 0.584 0.168 0.180 0.000 0.000
#> GSM486800 1 0.0363 0.78682 0.988 0.000 0.000 0.000 0.012 0.000
#> GSM486802 1 0.0547 0.78571 0.980 0.000 0.000 0.000 0.020 0.000
#> GSM486804 1 0.1059 0.78634 0.964 0.004 0.016 0.000 0.016 0.000
#> GSM486806 2 0.5694 0.66249 0.020 0.632 0.176 0.160 0.012 0.000
#> GSM486808 1 0.1957 0.77522 0.888 0.000 0.000 0.000 0.112 0.000
#> GSM486810 6 0.2836 0.58130 0.000 0.052 0.060 0.016 0.000 0.872
#> GSM486812 1 0.2003 0.77670 0.884 0.000 0.000 0.000 0.116 0.000
#> GSM486814 2 0.1219 0.76955 0.000 0.948 0.048 0.004 0.000 0.000
#> GSM486816 1 0.2340 0.76895 0.852 0.000 0.000 0.000 0.148 0.000
#> GSM486818 1 0.7413 -0.09415 0.348 0.344 0.164 0.140 0.000 0.004
#> GSM486821 3 0.8507 -0.17550 0.252 0.228 0.264 0.060 0.000 0.196
#> GSM486823 2 0.5673 0.59876 0.004 0.644 0.132 0.032 0.004 0.184
#> GSM486826 1 0.1349 0.77364 0.940 0.004 0.000 0.000 0.056 0.000
#> GSM486830 2 0.5292 0.68362 0.008 0.644 0.156 0.188 0.000 0.004
#> GSM486832 1 0.0632 0.78990 0.976 0.000 0.000 0.000 0.024 0.000
#> GSM486834 1 0.8297 0.00243 0.328 0.300 0.176 0.152 0.020 0.024
#> GSM486836 1 0.0260 0.78955 0.992 0.000 0.000 0.000 0.008 0.000
#> GSM486838 2 0.5505 0.69322 0.024 0.644 0.148 0.180 0.004 0.000
#> GSM486840 1 0.1204 0.77510 0.944 0.000 0.000 0.000 0.056 0.000
#> GSM486842 1 0.2003 0.77537 0.884 0.000 0.000 0.000 0.116 0.000
#> GSM486844 1 0.2619 0.74291 0.884 0.056 0.048 0.000 0.012 0.000
#> GSM486846 2 0.5151 0.68847 0.008 0.648 0.152 0.192 0.000 0.000
#> GSM486848 1 0.1387 0.76978 0.932 0.000 0.000 0.000 0.068 0.000
#> GSM486850 2 0.1957 0.78326 0.000 0.920 0.024 0.048 0.000 0.008
#> GSM486852 6 0.3043 0.59020 0.004 0.004 0.196 0.000 0.000 0.796
#> GSM486854 2 0.3065 0.75761 0.000 0.848 0.096 0.048 0.000 0.008
#> GSM486856 2 0.0858 0.77884 0.000 0.968 0.028 0.004 0.000 0.000
#> GSM486858 2 0.3994 0.74705 0.000 0.768 0.092 0.136 0.004 0.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> SD:mclust 120 4.67e-27 1.000 2
#> SD:mclust 116 4.78e-25 0.807 3
#> SD:mclust 119 1.27e-25 1.000 4
#> SD:mclust 113 9.48e-21 0.443 5
#> SD:mclust 106 2.87e-21 0.987 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["SD", "NMF"]
# you can also extract it by
# res = res_list["SD:NMF"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'SD' method.
#> Subgroups are detected by 'NMF' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.897 0.928 0.970 0.5004 0.499 0.499
#> 3 3 0.576 0.720 0.855 0.2900 0.801 0.620
#> 4 4 0.561 0.625 0.789 0.1318 0.882 0.683
#> 5 5 0.523 0.517 0.719 0.0504 0.855 0.556
#> 6 6 0.531 0.410 0.628 0.0428 0.926 0.710
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 2 0.0000 0.962 0.000 1.000
#> GSM486737 2 0.0000 0.962 0.000 1.000
#> GSM486739 2 0.0000 0.962 0.000 1.000
#> GSM486741 2 0.0000 0.962 0.000 1.000
#> GSM486743 2 0.0000 0.962 0.000 1.000
#> GSM486745 2 0.0000 0.962 0.000 1.000
#> GSM486747 1 0.0000 0.976 1.000 0.000
#> GSM486749 2 0.0000 0.962 0.000 1.000
#> GSM486751 1 0.9661 0.332 0.608 0.392
#> GSM486753 2 0.0000 0.962 0.000 1.000
#> GSM486755 2 0.0000 0.962 0.000 1.000
#> GSM486757 1 0.6438 0.793 0.836 0.164
#> GSM486759 1 0.0000 0.976 1.000 0.000
#> GSM486761 1 0.0000 0.976 1.000 0.000
#> GSM486763 2 0.1633 0.944 0.024 0.976
#> GSM486765 1 0.0000 0.976 1.000 0.000
#> GSM486767 2 0.0000 0.962 0.000 1.000
#> GSM486769 2 0.0000 0.962 0.000 1.000
#> GSM486771 2 0.0000 0.962 0.000 1.000
#> GSM486773 2 0.0000 0.962 0.000 1.000
#> GSM486775 1 0.0000 0.976 1.000 0.000
#> GSM486777 1 0.0000 0.976 1.000 0.000
#> GSM486779 2 0.0000 0.962 0.000 1.000
#> GSM486781 2 0.0000 0.962 0.000 1.000
#> GSM486783 2 0.0000 0.962 0.000 1.000
#> GSM486785 1 0.0000 0.976 1.000 0.000
#> GSM486787 1 0.0000 0.976 1.000 0.000
#> GSM486789 2 0.0000 0.962 0.000 1.000
#> GSM486791 1 0.0000 0.976 1.000 0.000
#> GSM486793 1 0.0000 0.976 1.000 0.000
#> GSM486795 1 0.2603 0.937 0.956 0.044
#> GSM486797 2 0.9580 0.413 0.380 0.620
#> GSM486799 1 0.0000 0.976 1.000 0.000
#> GSM486801 1 0.0000 0.976 1.000 0.000
#> GSM486803 1 0.0000 0.976 1.000 0.000
#> GSM486805 2 0.1414 0.947 0.020 0.980
#> GSM486807 1 0.0000 0.976 1.000 0.000
#> GSM486809 2 0.0000 0.962 0.000 1.000
#> GSM486811 1 0.0000 0.976 1.000 0.000
#> GSM486813 2 0.0000 0.962 0.000 1.000
#> GSM486815 1 0.0000 0.976 1.000 0.000
#> GSM486817 2 0.9286 0.498 0.344 0.656
#> GSM486819 2 0.9909 0.229 0.444 0.556
#> GSM486822 2 0.0000 0.962 0.000 1.000
#> GSM486824 1 0.0000 0.976 1.000 0.000
#> GSM486828 2 0.0000 0.962 0.000 1.000
#> GSM486831 1 0.0000 0.976 1.000 0.000
#> GSM486833 2 0.6048 0.821 0.148 0.852
#> GSM486835 1 0.0000 0.976 1.000 0.000
#> GSM486837 2 0.1184 0.951 0.016 0.984
#> GSM486839 1 0.0000 0.976 1.000 0.000
#> GSM486841 1 0.0000 0.976 1.000 0.000
#> GSM486843 1 0.0000 0.976 1.000 0.000
#> GSM486845 2 0.0000 0.962 0.000 1.000
#> GSM486847 1 0.0000 0.976 1.000 0.000
#> GSM486849 2 0.0000 0.962 0.000 1.000
#> GSM486851 1 0.0376 0.973 0.996 0.004
#> GSM486853 2 0.0000 0.962 0.000 1.000
#> GSM486855 2 0.0000 0.962 0.000 1.000
#> GSM486857 2 0.0000 0.962 0.000 1.000
#> GSM486736 2 0.0000 0.962 0.000 1.000
#> GSM486738 2 0.0000 0.962 0.000 1.000
#> GSM486740 2 0.0000 0.962 0.000 1.000
#> GSM486742 2 0.0000 0.962 0.000 1.000
#> GSM486744 2 0.0000 0.962 0.000 1.000
#> GSM486746 2 0.0000 0.962 0.000 1.000
#> GSM486748 1 0.0000 0.976 1.000 0.000
#> GSM486750 2 0.0000 0.962 0.000 1.000
#> GSM486752 1 0.5629 0.837 0.868 0.132
#> GSM486754 2 0.0000 0.962 0.000 1.000
#> GSM486756 2 0.0000 0.962 0.000 1.000
#> GSM486758 1 0.3114 0.925 0.944 0.056
#> GSM486760 1 0.0000 0.976 1.000 0.000
#> GSM486762 1 0.0000 0.976 1.000 0.000
#> GSM486764 2 0.6438 0.802 0.164 0.836
#> GSM486766 1 0.0000 0.976 1.000 0.000
#> GSM486768 2 0.0000 0.962 0.000 1.000
#> GSM486770 2 0.0000 0.962 0.000 1.000
#> GSM486772 2 0.0000 0.962 0.000 1.000
#> GSM486774 2 0.0000 0.962 0.000 1.000
#> GSM486776 1 0.0000 0.976 1.000 0.000
#> GSM486778 1 0.0000 0.976 1.000 0.000
#> GSM486780 2 0.0000 0.962 0.000 1.000
#> GSM486782 2 0.0000 0.962 0.000 1.000
#> GSM486784 2 0.0000 0.962 0.000 1.000
#> GSM486786 1 0.0000 0.976 1.000 0.000
#> GSM486788 1 0.0000 0.976 1.000 0.000
#> GSM486790 2 0.0000 0.962 0.000 1.000
#> GSM486792 1 0.0000 0.976 1.000 0.000
#> GSM486794 1 0.0000 0.976 1.000 0.000
#> GSM486796 1 0.0938 0.966 0.988 0.012
#> GSM486798 2 0.9460 0.452 0.364 0.636
#> GSM486800 1 0.0000 0.976 1.000 0.000
#> GSM486802 1 0.0000 0.976 1.000 0.000
#> GSM486804 1 0.0000 0.976 1.000 0.000
#> GSM486806 2 0.0000 0.962 0.000 1.000
#> GSM486808 1 0.0000 0.976 1.000 0.000
#> GSM486810 2 0.0000 0.962 0.000 1.000
#> GSM486812 1 0.0000 0.976 1.000 0.000
#> GSM486814 2 0.0000 0.962 0.000 1.000
#> GSM486816 1 0.0000 0.976 1.000 0.000
#> GSM486818 1 0.9795 0.259 0.584 0.416
#> GSM486821 2 0.7674 0.719 0.224 0.776
#> GSM486823 2 0.0000 0.962 0.000 1.000
#> GSM486826 1 0.0000 0.976 1.000 0.000
#> GSM486830 2 0.0000 0.962 0.000 1.000
#> GSM486832 1 0.0000 0.976 1.000 0.000
#> GSM486834 2 0.2423 0.930 0.040 0.960
#> GSM486836 1 0.0000 0.976 1.000 0.000
#> GSM486838 2 0.6343 0.806 0.160 0.840
#> GSM486840 1 0.0000 0.976 1.000 0.000
#> GSM486842 1 0.0000 0.976 1.000 0.000
#> GSM486844 1 0.0000 0.976 1.000 0.000
#> GSM486846 2 0.0000 0.962 0.000 1.000
#> GSM486848 1 0.0000 0.976 1.000 0.000
#> GSM486850 2 0.0000 0.962 0.000 1.000
#> GSM486852 1 0.1184 0.963 0.984 0.016
#> GSM486854 2 0.0000 0.962 0.000 1.000
#> GSM486856 2 0.0000 0.962 0.000 1.000
#> GSM486858 2 0.0000 0.962 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 1 0.3038 0.7049 0.896 0.104 0.000
#> GSM486737 2 0.3038 0.8158 0.104 0.896 0.000
#> GSM486739 1 0.2625 0.7047 0.916 0.084 0.000
#> GSM486741 2 0.4702 0.7446 0.212 0.788 0.000
#> GSM486743 2 0.2959 0.8119 0.100 0.900 0.000
#> GSM486745 1 0.4702 0.6672 0.788 0.212 0.000
#> GSM486747 3 0.3694 0.8669 0.052 0.052 0.896
#> GSM486749 1 0.5363 0.5560 0.724 0.276 0.000
#> GSM486751 3 0.7901 0.4681 0.312 0.080 0.608
#> GSM486753 2 0.5363 0.5983 0.276 0.724 0.000
#> GSM486755 2 0.5431 0.5675 0.284 0.716 0.000
#> GSM486757 1 0.6627 0.3570 0.644 0.020 0.336
#> GSM486759 3 0.1267 0.8984 0.024 0.004 0.972
#> GSM486761 3 0.2301 0.8851 0.060 0.004 0.936
#> GSM486763 1 0.1620 0.6923 0.964 0.024 0.012
#> GSM486765 3 0.0237 0.8998 0.004 0.000 0.996
#> GSM486767 1 0.6244 0.2562 0.560 0.440 0.000
#> GSM486769 1 0.3752 0.6973 0.856 0.144 0.000
#> GSM486771 2 0.3816 0.7731 0.148 0.852 0.000
#> GSM486773 1 0.5431 0.5335 0.716 0.284 0.000
#> GSM486775 3 0.0000 0.8997 0.000 0.000 1.000
#> GSM486777 3 0.3412 0.8481 0.124 0.000 0.876
#> GSM486779 2 0.2301 0.8022 0.060 0.936 0.004
#> GSM486781 2 0.4555 0.7426 0.200 0.800 0.000
#> GSM486783 2 0.1643 0.8200 0.044 0.956 0.000
#> GSM486785 3 0.3031 0.8745 0.076 0.012 0.912
#> GSM486787 3 0.0747 0.8995 0.016 0.000 0.984
#> GSM486789 2 0.6305 0.0186 0.484 0.516 0.000
#> GSM486791 1 0.6476 0.0558 0.548 0.004 0.448
#> GSM486793 3 0.2796 0.8676 0.092 0.000 0.908
#> GSM486795 3 0.6865 0.7299 0.160 0.104 0.736
#> GSM486797 3 0.9074 0.2254 0.352 0.148 0.500
#> GSM486799 3 0.0747 0.8995 0.016 0.000 0.984
#> GSM486801 3 0.2860 0.8789 0.084 0.004 0.912
#> GSM486803 3 0.3722 0.8677 0.088 0.024 0.888
#> GSM486805 2 0.7956 0.2128 0.424 0.516 0.060
#> GSM486807 3 0.0424 0.9000 0.008 0.000 0.992
#> GSM486809 1 0.1753 0.7007 0.952 0.048 0.000
#> GSM486811 3 0.1529 0.8934 0.040 0.000 0.960
#> GSM486813 2 0.2796 0.8137 0.092 0.908 0.000
#> GSM486815 3 0.2066 0.8851 0.060 0.000 0.940
#> GSM486817 2 0.7011 0.5397 0.092 0.720 0.188
#> GSM486819 1 0.4862 0.6334 0.820 0.020 0.160
#> GSM486822 1 0.4702 0.6561 0.788 0.212 0.000
#> GSM486824 3 0.3148 0.8807 0.048 0.036 0.916
#> GSM486828 1 0.6286 0.1530 0.536 0.464 0.000
#> GSM486831 3 0.1647 0.8954 0.036 0.004 0.960
#> GSM486833 1 0.3889 0.6781 0.884 0.032 0.084
#> GSM486835 3 0.0475 0.9001 0.004 0.004 0.992
#> GSM486837 2 0.3091 0.8011 0.072 0.912 0.016
#> GSM486839 3 0.1989 0.8916 0.048 0.004 0.948
#> GSM486841 3 0.2165 0.8862 0.064 0.000 0.936
#> GSM486843 3 0.3692 0.8675 0.056 0.048 0.896
#> GSM486845 2 0.5397 0.6713 0.280 0.720 0.000
#> GSM486847 3 0.2066 0.8897 0.060 0.000 0.940
#> GSM486849 2 0.3192 0.8216 0.112 0.888 0.000
#> GSM486851 1 0.4465 0.6299 0.820 0.004 0.176
#> GSM486853 2 0.2711 0.8249 0.088 0.912 0.000
#> GSM486855 2 0.1860 0.8131 0.052 0.948 0.000
#> GSM486857 2 0.2711 0.8163 0.088 0.912 0.000
#> GSM486736 1 0.3752 0.6968 0.856 0.144 0.000
#> GSM486738 2 0.1031 0.8295 0.024 0.976 0.000
#> GSM486740 1 0.4178 0.6856 0.828 0.172 0.000
#> GSM486742 2 0.2878 0.8182 0.096 0.904 0.000
#> GSM486744 2 0.0892 0.8286 0.020 0.980 0.000
#> GSM486746 1 0.6307 0.0666 0.512 0.488 0.000
#> GSM486748 3 0.6513 0.1274 0.004 0.476 0.520
#> GSM486750 2 0.6111 0.3545 0.396 0.604 0.000
#> GSM486752 3 0.6758 0.4289 0.020 0.360 0.620
#> GSM486754 2 0.2356 0.8260 0.072 0.928 0.000
#> GSM486756 2 0.2796 0.8164 0.092 0.908 0.000
#> GSM486758 3 0.2681 0.8720 0.040 0.028 0.932
#> GSM486760 3 0.0661 0.9000 0.004 0.008 0.988
#> GSM486762 3 0.1031 0.8952 0.000 0.024 0.976
#> GSM486764 1 0.3356 0.6993 0.908 0.056 0.036
#> GSM486766 3 0.0237 0.8996 0.000 0.004 0.996
#> GSM486768 2 0.3551 0.7986 0.132 0.868 0.000
#> GSM486770 1 0.4750 0.6518 0.784 0.216 0.000
#> GSM486772 2 0.1289 0.8299 0.032 0.968 0.000
#> GSM486774 2 0.4110 0.7755 0.152 0.844 0.004
#> GSM486776 3 0.0424 0.8994 0.000 0.008 0.992
#> GSM486778 3 0.0424 0.8994 0.008 0.000 0.992
#> GSM486780 2 0.1015 0.8220 0.012 0.980 0.008
#> GSM486782 2 0.2537 0.8225 0.080 0.920 0.000
#> GSM486784 2 0.0592 0.8264 0.012 0.988 0.000
#> GSM486786 3 0.0237 0.8996 0.000 0.004 0.996
#> GSM486788 3 0.0592 0.8987 0.000 0.012 0.988
#> GSM486790 2 0.5810 0.5066 0.336 0.664 0.000
#> GSM486792 3 0.6126 0.4563 0.352 0.004 0.644
#> GSM486794 3 0.0424 0.8994 0.008 0.000 0.992
#> GSM486796 3 0.6973 0.3387 0.020 0.416 0.564
#> GSM486798 2 0.7037 0.3743 0.036 0.636 0.328
#> GSM486800 3 0.0237 0.8996 0.000 0.004 0.996
#> GSM486802 3 0.0747 0.8976 0.000 0.016 0.984
#> GSM486804 3 0.3349 0.8413 0.004 0.108 0.888
#> GSM486806 2 0.3310 0.8205 0.064 0.908 0.028
#> GSM486808 3 0.0424 0.8994 0.000 0.008 0.992
#> GSM486810 1 0.3038 0.7046 0.896 0.104 0.000
#> GSM486812 3 0.0237 0.8998 0.004 0.000 0.996
#> GSM486814 2 0.1647 0.8220 0.036 0.960 0.004
#> GSM486816 3 0.0424 0.8994 0.008 0.000 0.992
#> GSM486818 2 0.4514 0.6667 0.012 0.832 0.156
#> GSM486821 1 0.8844 0.1752 0.444 0.116 0.440
#> GSM486823 1 0.6192 0.2790 0.580 0.420 0.000
#> GSM486826 3 0.2860 0.8601 0.004 0.084 0.912
#> GSM486830 2 0.4605 0.7307 0.204 0.796 0.000
#> GSM486832 3 0.0661 0.8997 0.008 0.004 0.988
#> GSM486834 1 0.9556 0.2977 0.460 0.332 0.208
#> GSM486836 3 0.1525 0.8931 0.004 0.032 0.964
#> GSM486838 2 0.2939 0.7852 0.012 0.916 0.072
#> GSM486840 3 0.0747 0.8976 0.000 0.016 0.984
#> GSM486842 3 0.0237 0.8998 0.004 0.000 0.996
#> GSM486844 3 0.4887 0.7020 0.000 0.228 0.772
#> GSM486846 2 0.2584 0.8259 0.064 0.928 0.008
#> GSM486848 3 0.0661 0.8998 0.004 0.008 0.988
#> GSM486850 2 0.1643 0.8298 0.044 0.956 0.000
#> GSM486852 1 0.5480 0.5455 0.732 0.004 0.264
#> GSM486854 2 0.1031 0.8293 0.024 0.976 0.000
#> GSM486856 2 0.1015 0.8241 0.012 0.980 0.008
#> GSM486858 2 0.1950 0.8288 0.040 0.952 0.008
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 4 0.1576 0.79417 0.048 0.004 0.000 0.948
#> GSM486737 2 0.4697 0.43560 0.356 0.644 0.000 0.000
#> GSM486739 4 0.0524 0.79590 0.008 0.004 0.000 0.988
#> GSM486741 2 0.5881 0.39882 0.420 0.544 0.000 0.036
#> GSM486743 2 0.3032 0.68612 0.124 0.868 0.000 0.008
#> GSM486745 4 0.5260 0.69639 0.092 0.144 0.004 0.760
#> GSM486747 1 0.5508 0.24268 0.572 0.020 0.408 0.000
#> GSM486749 1 0.4093 0.61684 0.832 0.096 0.000 0.072
#> GSM486751 1 0.2546 0.68557 0.900 0.008 0.092 0.000
#> GSM486753 2 0.5122 0.66517 0.080 0.756 0.000 0.164
#> GSM486755 2 0.5628 0.61677 0.080 0.704 0.000 0.216
#> GSM486757 1 0.2741 0.68020 0.892 0.000 0.096 0.012
#> GSM486759 3 0.3829 0.77440 0.152 0.004 0.828 0.016
#> GSM486761 1 0.4972 0.09754 0.544 0.000 0.456 0.000
#> GSM486763 4 0.2654 0.75979 0.108 0.000 0.004 0.888
#> GSM486765 3 0.1022 0.83078 0.032 0.000 0.968 0.000
#> GSM486767 1 0.7728 -0.00752 0.412 0.392 0.004 0.192
#> GSM486769 4 0.1938 0.79198 0.052 0.012 0.000 0.936
#> GSM486771 2 0.4284 0.61734 0.200 0.780 0.000 0.020
#> GSM486773 1 0.3764 0.63484 0.852 0.072 0.000 0.076
#> GSM486775 3 0.1211 0.82919 0.040 0.000 0.960 0.000
#> GSM486777 3 0.5168 0.08654 0.496 0.000 0.500 0.004
#> GSM486779 2 0.5317 0.06623 0.460 0.532 0.004 0.004
#> GSM486781 2 0.6130 0.34023 0.440 0.512 0.000 0.048
#> GSM486783 2 0.1398 0.72032 0.040 0.956 0.000 0.004
#> GSM486785 1 0.4072 0.54849 0.748 0.000 0.252 0.000
#> GSM486787 3 0.2281 0.81357 0.096 0.000 0.904 0.000
#> GSM486789 2 0.6926 0.22390 0.108 0.460 0.000 0.432
#> GSM486791 4 0.6100 0.49294 0.084 0.000 0.272 0.644
#> GSM486793 3 0.3583 0.74126 0.180 0.000 0.816 0.004
#> GSM486795 1 0.4137 0.62758 0.848 0.088 0.036 0.028
#> GSM486797 1 0.2546 0.68548 0.900 0.008 0.092 0.000
#> GSM486799 3 0.2401 0.81268 0.092 0.000 0.904 0.004
#> GSM486801 3 0.6118 0.37914 0.404 0.024 0.556 0.016
#> GSM486803 3 0.6435 0.22232 0.448 0.036 0.500 0.016
#> GSM486805 1 0.3338 0.67349 0.884 0.052 0.056 0.008
#> GSM486807 3 0.1792 0.82010 0.068 0.000 0.932 0.000
#> GSM486809 4 0.1474 0.79437 0.052 0.000 0.000 0.948
#> GSM486811 3 0.3569 0.72902 0.196 0.000 0.804 0.000
#> GSM486813 2 0.5773 0.22820 0.408 0.564 0.004 0.024
#> GSM486815 3 0.2868 0.77907 0.136 0.000 0.864 0.000
#> GSM486817 1 0.5513 0.40657 0.628 0.348 0.016 0.008
#> GSM486819 1 0.6313 0.32975 0.632 0.020 0.048 0.300
#> GSM486822 4 0.5522 0.60553 0.204 0.080 0.000 0.716
#> GSM486824 3 0.5383 0.58634 0.292 0.036 0.672 0.000
#> GSM486828 1 0.6773 0.23975 0.584 0.284 0.000 0.132
#> GSM486831 3 0.3606 0.78516 0.132 0.000 0.844 0.024
#> GSM486833 1 0.3505 0.65360 0.864 0.000 0.048 0.088
#> GSM486835 3 0.2412 0.81512 0.084 0.000 0.908 0.008
#> GSM486837 2 0.5257 0.32192 0.444 0.548 0.008 0.000
#> GSM486839 3 0.4699 0.57273 0.320 0.000 0.676 0.004
#> GSM486841 3 0.4522 0.55373 0.320 0.000 0.680 0.000
#> GSM486843 1 0.6016 0.12491 0.544 0.044 0.412 0.000
#> GSM486845 1 0.4342 0.54522 0.784 0.196 0.012 0.008
#> GSM486847 3 0.4889 0.50126 0.360 0.000 0.636 0.004
#> GSM486849 2 0.5039 0.44375 0.404 0.592 0.000 0.004
#> GSM486851 4 0.4955 0.67924 0.144 0.000 0.084 0.772
#> GSM486853 2 0.4543 0.56539 0.324 0.676 0.000 0.000
#> GSM486855 2 0.3538 0.65490 0.160 0.832 0.004 0.004
#> GSM486857 1 0.4304 0.40207 0.716 0.284 0.000 0.000
#> GSM486736 4 0.1545 0.79490 0.040 0.008 0.000 0.952
#> GSM486738 2 0.1059 0.73040 0.016 0.972 0.000 0.012
#> GSM486740 4 0.0937 0.79645 0.012 0.012 0.000 0.976
#> GSM486742 2 0.3143 0.72424 0.100 0.876 0.000 0.024
#> GSM486744 2 0.0967 0.72939 0.004 0.976 0.004 0.016
#> GSM486746 4 0.4849 0.67501 0.036 0.200 0.004 0.760
#> GSM486748 2 0.6504 0.11834 0.072 0.476 0.452 0.000
#> GSM486750 2 0.6898 0.39260 0.116 0.524 0.000 0.360
#> GSM486752 3 0.6986 0.31470 0.092 0.296 0.592 0.020
#> GSM486754 2 0.2300 0.73330 0.028 0.924 0.000 0.048
#> GSM486756 2 0.2773 0.72985 0.028 0.900 0.000 0.072
#> GSM486758 3 0.4260 0.71689 0.080 0.016 0.840 0.064
#> GSM486760 3 0.1229 0.82903 0.020 0.004 0.968 0.008
#> GSM486762 3 0.0779 0.83070 0.016 0.004 0.980 0.000
#> GSM486764 4 0.1305 0.78926 0.036 0.000 0.004 0.960
#> GSM486766 3 0.0336 0.83205 0.008 0.000 0.992 0.000
#> GSM486768 2 0.4821 0.67355 0.036 0.804 0.032 0.128
#> GSM486770 4 0.2214 0.78582 0.044 0.028 0.000 0.928
#> GSM486772 2 0.0895 0.72913 0.000 0.976 0.004 0.020
#> GSM486774 2 0.6223 0.67672 0.112 0.732 0.052 0.104
#> GSM486776 3 0.0336 0.83298 0.008 0.000 0.992 0.000
#> GSM486778 3 0.0336 0.83240 0.008 0.000 0.992 0.000
#> GSM486780 2 0.0804 0.72192 0.012 0.980 0.008 0.000
#> GSM486782 2 0.3702 0.72270 0.100 0.860 0.012 0.028
#> GSM486784 2 0.0188 0.72467 0.004 0.996 0.000 0.000
#> GSM486786 3 0.0336 0.83205 0.008 0.000 0.992 0.000
#> GSM486788 3 0.0779 0.83206 0.016 0.004 0.980 0.000
#> GSM486790 2 0.6383 0.54689 0.096 0.612 0.000 0.292
#> GSM486792 4 0.5277 0.52574 0.028 0.000 0.304 0.668
#> GSM486794 3 0.0336 0.83205 0.008 0.000 0.992 0.000
#> GSM486796 3 0.6974 0.18321 0.048 0.420 0.500 0.032
#> GSM486798 2 0.7133 0.27481 0.072 0.512 0.392 0.024
#> GSM486800 3 0.1042 0.82986 0.020 0.000 0.972 0.008
#> GSM486802 3 0.1486 0.82948 0.024 0.008 0.960 0.008
#> GSM486804 3 0.4691 0.70912 0.044 0.136 0.804 0.016
#> GSM486806 2 0.6166 0.63082 0.104 0.720 0.148 0.028
#> GSM486808 3 0.0336 0.83205 0.008 0.000 0.992 0.000
#> GSM486810 4 0.1118 0.79550 0.036 0.000 0.000 0.964
#> GSM486812 3 0.0469 0.83247 0.012 0.000 0.988 0.000
#> GSM486814 2 0.1486 0.71737 0.024 0.960 0.008 0.008
#> GSM486816 3 0.0188 0.83259 0.004 0.000 0.996 0.000
#> GSM486818 2 0.4831 0.56786 0.016 0.772 0.188 0.024
#> GSM486821 4 0.6768 0.55458 0.056 0.044 0.264 0.636
#> GSM486823 4 0.6033 0.51480 0.116 0.204 0.000 0.680
#> GSM486826 3 0.2402 0.79790 0.012 0.076 0.912 0.000
#> GSM486830 2 0.6999 0.63059 0.116 0.664 0.048 0.172
#> GSM486832 3 0.1575 0.82502 0.028 0.004 0.956 0.012
#> GSM486834 4 0.7983 0.45180 0.116 0.064 0.268 0.552
#> GSM486836 3 0.1721 0.82422 0.028 0.012 0.952 0.008
#> GSM486838 2 0.3810 0.70902 0.092 0.848 0.060 0.000
#> GSM486840 3 0.0672 0.83403 0.008 0.008 0.984 0.000
#> GSM486842 3 0.0336 0.83205 0.008 0.000 0.992 0.000
#> GSM486844 3 0.4482 0.56533 0.008 0.264 0.728 0.000
#> GSM486846 2 0.3974 0.71843 0.092 0.852 0.040 0.016
#> GSM486848 3 0.0657 0.83357 0.012 0.004 0.984 0.000
#> GSM486850 2 0.2861 0.72684 0.092 0.892 0.004 0.012
#> GSM486852 4 0.2926 0.76967 0.048 0.000 0.056 0.896
#> GSM486854 2 0.2149 0.72611 0.088 0.912 0.000 0.000
#> GSM486856 2 0.0804 0.72192 0.012 0.980 0.008 0.000
#> GSM486858 2 0.3126 0.72547 0.092 0.884 0.016 0.008
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 5 0.3906 0.65627 0.000 0.000 0.292 0.004 0.704
#> GSM486737 3 0.6794 0.00414 0.000 0.320 0.380 0.300 0.000
#> GSM486739 5 0.2719 0.71637 0.000 0.004 0.144 0.000 0.852
#> GSM486741 3 0.5817 0.45969 0.000 0.204 0.612 0.184 0.000
#> GSM486743 2 0.5685 0.49652 0.000 0.620 0.284 0.084 0.012
#> GSM486745 5 0.5117 0.64518 0.004 0.204 0.096 0.000 0.696
#> GSM486747 1 0.4941 0.57446 0.708 0.000 0.208 0.080 0.004
#> GSM486749 4 0.5289 0.17016 0.000 0.012 0.424 0.536 0.028
#> GSM486751 4 0.6742 0.39635 0.296 0.000 0.292 0.412 0.000
#> GSM486753 3 0.5704 0.45206 0.000 0.252 0.648 0.028 0.072
#> GSM486755 3 0.5136 0.45365 0.000 0.252 0.676 0.008 0.064
#> GSM486757 4 0.5372 0.57610 0.180 0.000 0.152 0.668 0.000
#> GSM486759 1 0.4826 0.70557 0.772 0.048 0.000 0.104 0.076
#> GSM486761 1 0.3904 0.69848 0.792 0.000 0.052 0.156 0.000
#> GSM486763 5 0.2682 0.71035 0.032 0.020 0.016 0.024 0.908
#> GSM486765 1 0.1648 0.77778 0.940 0.000 0.040 0.020 0.000
#> GSM486767 2 0.8007 0.14745 0.004 0.424 0.092 0.260 0.220
#> GSM486769 5 0.4201 0.49130 0.000 0.000 0.408 0.000 0.592
#> GSM486771 2 0.4103 0.65382 0.000 0.800 0.132 0.056 0.012
#> GSM486773 3 0.5167 0.06220 0.000 0.004 0.564 0.396 0.036
#> GSM486775 1 0.1200 0.78556 0.964 0.008 0.012 0.016 0.000
#> GSM486777 1 0.4669 0.44627 0.628 0.000 0.008 0.352 0.012
#> GSM486779 2 0.4536 0.55275 0.000 0.712 0.048 0.240 0.000
#> GSM486781 3 0.4820 0.53874 0.000 0.100 0.748 0.140 0.012
#> GSM486783 2 0.4161 0.61637 0.000 0.752 0.208 0.040 0.000
#> GSM486785 4 0.3944 0.49314 0.272 0.004 0.004 0.720 0.000
#> GSM486787 1 0.3394 0.75767 0.864 0.040 0.000 0.044 0.052
#> GSM486789 3 0.4288 0.51432 0.000 0.052 0.764 0.004 0.180
#> GSM486791 5 0.3088 0.68507 0.068 0.044 0.004 0.008 0.876
#> GSM486793 1 0.2349 0.76977 0.900 0.000 0.012 0.084 0.004
#> GSM486795 4 0.4037 0.42447 0.020 0.184 0.000 0.780 0.016
#> GSM486797 4 0.4959 0.56661 0.128 0.004 0.144 0.724 0.000
#> GSM486799 1 0.3081 0.76823 0.880 0.028 0.000 0.044 0.048
#> GSM486801 4 0.7173 0.33052 0.300 0.088 0.000 0.508 0.104
#> GSM486803 4 0.7522 0.38493 0.276 0.144 0.000 0.484 0.096
#> GSM486805 3 0.6149 -0.11730 0.120 0.004 0.504 0.372 0.000
#> GSM486807 1 0.2381 0.77368 0.908 0.004 0.052 0.036 0.000
#> GSM486809 5 0.3607 0.68932 0.000 0.000 0.244 0.004 0.752
#> GSM486811 1 0.3014 0.75739 0.868 0.004 0.008 0.104 0.016
#> GSM486813 2 0.4796 0.59565 0.000 0.744 0.052 0.180 0.024
#> GSM486815 1 0.2241 0.77187 0.908 0.000 0.008 0.076 0.008
#> GSM486817 2 0.6383 0.13206 0.016 0.456 0.072 0.444 0.012
#> GSM486819 5 0.6586 0.42773 0.044 0.232 0.000 0.136 0.588
#> GSM486822 3 0.4928 0.31285 0.000 0.012 0.684 0.040 0.264
#> GSM486824 1 0.6908 0.02647 0.456 0.200 0.000 0.328 0.016
#> GSM486828 3 0.6921 0.38440 0.000 0.164 0.576 0.192 0.068
#> GSM486831 1 0.5864 0.57249 0.672 0.076 0.000 0.056 0.196
#> GSM486833 4 0.6925 0.27507 0.092 0.000 0.400 0.448 0.060
#> GSM486835 1 0.5045 0.68559 0.756 0.088 0.004 0.032 0.120
#> GSM486837 3 0.7218 0.08045 0.012 0.300 0.396 0.288 0.004
#> GSM486839 1 0.5542 0.41268 0.592 0.052 0.004 0.344 0.008
#> GSM486841 1 0.3550 0.65440 0.760 0.000 0.004 0.236 0.000
#> GSM486843 4 0.5640 0.45871 0.276 0.116 0.000 0.608 0.000
#> GSM486845 4 0.5369 0.28147 0.004 0.072 0.296 0.628 0.000
#> GSM486847 1 0.5212 0.25530 0.540 0.036 0.000 0.420 0.004
#> GSM486849 2 0.6273 0.23438 0.000 0.500 0.336 0.164 0.000
#> GSM486851 5 0.3946 0.66459 0.064 0.100 0.000 0.016 0.820
#> GSM486853 3 0.5802 0.17449 0.000 0.388 0.516 0.096 0.000
#> GSM486855 2 0.3339 0.64686 0.000 0.852 0.072 0.072 0.004
#> GSM486857 4 0.5580 0.13704 0.000 0.088 0.336 0.576 0.000
#> GSM486736 5 0.3707 0.66364 0.000 0.000 0.284 0.000 0.716
#> GSM486738 2 0.4306 0.07405 0.000 0.508 0.492 0.000 0.000
#> GSM486740 5 0.2920 0.72188 0.000 0.016 0.132 0.000 0.852
#> GSM486742 3 0.3796 0.43233 0.000 0.300 0.700 0.000 0.000
#> GSM486744 2 0.3932 0.47821 0.000 0.672 0.328 0.000 0.000
#> GSM486746 5 0.4785 0.68538 0.004 0.140 0.116 0.000 0.740
#> GSM486748 1 0.4825 0.46386 0.652 0.024 0.316 0.004 0.004
#> GSM486750 3 0.3657 0.53715 0.000 0.064 0.820 0.000 0.116
#> GSM486752 1 0.4268 0.22645 0.556 0.000 0.444 0.000 0.000
#> GSM486754 3 0.4367 0.31650 0.000 0.372 0.620 0.000 0.008
#> GSM486756 3 0.4101 0.37216 0.000 0.332 0.664 0.000 0.004
#> GSM486758 1 0.5191 0.33154 0.588 0.008 0.376 0.008 0.020
#> GSM486760 1 0.2593 0.77443 0.904 0.048 0.004 0.008 0.036
#> GSM486762 1 0.2729 0.74872 0.876 0.004 0.108 0.008 0.004
#> GSM486764 5 0.2963 0.70838 0.044 0.048 0.016 0.004 0.888
#> GSM486766 1 0.1662 0.77214 0.936 0.000 0.056 0.004 0.004
#> GSM486768 2 0.5986 0.40890 0.012 0.596 0.296 0.004 0.092
#> GSM486770 5 0.4264 0.54440 0.000 0.004 0.376 0.000 0.620
#> GSM486772 2 0.3163 0.64484 0.000 0.824 0.164 0.000 0.012
#> GSM486774 3 0.2227 0.55130 0.032 0.048 0.916 0.000 0.004
#> GSM486776 1 0.1469 0.78306 0.948 0.016 0.036 0.000 0.000
#> GSM486778 1 0.2386 0.78325 0.916 0.016 0.008 0.012 0.048
#> GSM486780 2 0.2629 0.65168 0.000 0.860 0.136 0.000 0.004
#> GSM486782 3 0.3462 0.51510 0.000 0.196 0.792 0.000 0.012
#> GSM486784 2 0.3305 0.61049 0.000 0.776 0.224 0.000 0.000
#> GSM486786 1 0.1243 0.78251 0.960 0.000 0.028 0.008 0.004
#> GSM486788 1 0.2814 0.77200 0.892 0.056 0.004 0.008 0.040
#> GSM486790 3 0.4406 0.53833 0.000 0.108 0.764 0.000 0.128
#> GSM486792 5 0.2915 0.68240 0.092 0.024 0.004 0.004 0.876
#> GSM486794 1 0.1605 0.77973 0.944 0.000 0.040 0.012 0.004
#> GSM486796 2 0.4574 0.43426 0.140 0.776 0.016 0.004 0.064
#> GSM486798 3 0.5836 0.04078 0.428 0.060 0.500 0.008 0.004
#> GSM486800 1 0.1978 0.78018 0.932 0.032 0.000 0.012 0.024
#> GSM486802 1 0.4735 0.69076 0.756 0.132 0.000 0.012 0.100
#> GSM486804 1 0.6252 0.25169 0.492 0.404 0.008 0.008 0.088
#> GSM486806 3 0.4537 0.44191 0.176 0.060 0.756 0.004 0.004
#> GSM486808 1 0.2084 0.77088 0.920 0.004 0.064 0.008 0.004
#> GSM486810 5 0.3752 0.66297 0.000 0.000 0.292 0.000 0.708
#> GSM486812 1 0.1095 0.78355 0.968 0.000 0.012 0.012 0.008
#> GSM486814 2 0.2293 0.64137 0.000 0.900 0.084 0.000 0.016
#> GSM486816 1 0.1173 0.78241 0.964 0.000 0.020 0.012 0.004
#> GSM486818 2 0.5725 0.52821 0.088 0.672 0.212 0.004 0.024
#> GSM486821 5 0.5869 0.44130 0.068 0.344 0.012 0.004 0.572
#> GSM486823 3 0.3805 0.47843 0.000 0.032 0.784 0.000 0.184
#> GSM486826 1 0.3566 0.72984 0.812 0.160 0.024 0.000 0.004
#> GSM486830 3 0.4499 0.53656 0.024 0.120 0.784 0.000 0.072
#> GSM486832 1 0.3654 0.75028 0.844 0.052 0.008 0.008 0.088
#> GSM486834 3 0.4277 0.35355 0.156 0.000 0.768 0.000 0.076
#> GSM486836 1 0.4852 0.70887 0.768 0.132 0.024 0.008 0.068
#> GSM486838 3 0.5327 -0.01099 0.032 0.452 0.508 0.004 0.004
#> GSM486840 1 0.2555 0.78071 0.900 0.072 0.016 0.004 0.008
#> GSM486842 1 0.0865 0.78248 0.972 0.000 0.024 0.004 0.000
#> GSM486844 1 0.5045 0.56748 0.672 0.276 0.040 0.008 0.004
#> GSM486846 3 0.4745 0.14154 0.012 0.424 0.560 0.000 0.004
#> GSM486848 1 0.2061 0.78442 0.924 0.056 0.004 0.004 0.012
#> GSM486850 2 0.4321 0.26587 0.000 0.600 0.396 0.000 0.004
#> GSM486852 5 0.3888 0.65812 0.072 0.112 0.000 0.004 0.812
#> GSM486854 3 0.4283 0.12947 0.000 0.456 0.544 0.000 0.000
#> GSM486856 2 0.2280 0.65363 0.000 0.880 0.120 0.000 0.000
#> GSM486858 3 0.4135 0.35696 0.000 0.340 0.656 0.000 0.004
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 5 0.475 0.36691 0.000 0.000 0.048 0.000 0.496 0.456
#> GSM486737 2 0.745 -0.02267 0.000 0.372 0.140 0.124 0.016 0.348
#> GSM486739 5 0.527 0.49961 0.000 0.012 0.084 0.000 0.576 0.328
#> GSM486741 6 0.669 0.17867 0.000 0.192 0.180 0.104 0.000 0.524
#> GSM486743 2 0.643 0.32880 0.000 0.504 0.320 0.076 0.004 0.096
#> GSM486745 5 0.779 0.32072 0.000 0.128 0.184 0.032 0.408 0.248
#> GSM486747 1 0.450 0.59926 0.720 0.000 0.200 0.020 0.000 0.060
#> GSM486749 6 0.577 0.20703 0.000 0.024 0.080 0.356 0.008 0.532
#> GSM486751 4 0.736 0.31203 0.292 0.000 0.120 0.360 0.000 0.228
#> GSM486753 6 0.671 0.11212 0.000 0.192 0.280 0.016 0.032 0.480
#> GSM486755 6 0.509 0.28038 0.000 0.280 0.064 0.012 0.008 0.636
#> GSM486757 4 0.620 0.35370 0.196 0.000 0.028 0.516 0.000 0.260
#> GSM486759 1 0.479 0.69400 0.764 0.024 0.036 0.088 0.084 0.004
#> GSM486761 1 0.383 0.69033 0.800 0.000 0.072 0.108 0.000 0.020
#> GSM486763 5 0.283 0.61348 0.020 0.016 0.004 0.004 0.876 0.080
#> GSM486765 1 0.170 0.74327 0.936 0.000 0.040 0.008 0.004 0.012
#> GSM486767 5 0.812 0.03883 0.000 0.212 0.188 0.224 0.344 0.032
#> GSM486769 6 0.470 -0.13697 0.000 0.000 0.052 0.000 0.380 0.568
#> GSM486771 2 0.520 0.53578 0.000 0.712 0.144 0.084 0.016 0.044
#> GSM486773 4 0.635 -0.10407 0.000 0.000 0.284 0.404 0.012 0.300
#> GSM486775 1 0.127 0.75088 0.960 0.004 0.012 0.008 0.012 0.004
#> GSM486777 1 0.479 0.50242 0.652 0.000 0.012 0.288 0.040 0.008
#> GSM486779 2 0.495 0.43465 0.000 0.640 0.052 0.288 0.016 0.004
#> GSM486781 3 0.544 0.31427 0.000 0.012 0.620 0.128 0.004 0.236
#> GSM486783 2 0.486 0.49498 0.000 0.696 0.200 0.028 0.000 0.076
#> GSM486785 4 0.416 0.27441 0.376 0.000 0.004 0.608 0.000 0.012
#> GSM486787 1 0.451 0.71113 0.784 0.020 0.040 0.060 0.092 0.004
#> GSM486789 6 0.644 0.15713 0.000 0.068 0.316 0.008 0.096 0.512
#> GSM486791 5 0.299 0.60622 0.076 0.000 0.012 0.012 0.868 0.032
#> GSM486793 1 0.213 0.74731 0.920 0.000 0.012 0.036 0.012 0.020
#> GSM486795 4 0.477 0.31193 0.036 0.220 0.012 0.708 0.008 0.016
#> GSM486797 4 0.399 0.43568 0.088 0.000 0.048 0.800 0.000 0.064
#> GSM486799 1 0.325 0.74512 0.852 0.004 0.020 0.032 0.088 0.004
#> GSM486801 4 0.685 0.14216 0.360 0.036 0.036 0.456 0.108 0.004
#> GSM486803 4 0.706 0.36375 0.264 0.064 0.064 0.516 0.092 0.000
#> GSM486805 3 0.704 0.04073 0.084 0.000 0.424 0.316 0.004 0.172
#> GSM486807 1 0.310 0.71134 0.832 0.000 0.136 0.012 0.000 0.020
#> GSM486809 5 0.456 0.45223 0.000 0.000 0.040 0.000 0.568 0.392
#> GSM486811 1 0.326 0.73982 0.860 0.004 0.028 0.068 0.032 0.008
#> GSM486813 2 0.429 0.52672 0.000 0.784 0.032 0.124 0.024 0.036
#> GSM486815 1 0.216 0.74848 0.920 0.000 0.016 0.020 0.028 0.016
#> GSM486817 4 0.711 -0.15361 0.004 0.316 0.244 0.388 0.016 0.032
#> GSM486819 5 0.545 0.49293 0.028 0.108 0.056 0.100 0.708 0.000
#> GSM486822 6 0.516 0.32596 0.000 0.024 0.220 0.008 0.076 0.672
#> GSM486824 1 0.751 0.07968 0.436 0.228 0.040 0.240 0.052 0.004
#> GSM486828 3 0.607 0.31261 0.004 0.096 0.620 0.032 0.028 0.220
#> GSM486831 1 0.634 0.39358 0.536 0.012 0.060 0.064 0.320 0.008
#> GSM486833 6 0.655 -0.05530 0.104 0.000 0.064 0.360 0.008 0.464
#> GSM486835 1 0.622 0.62950 0.660 0.048 0.116 0.056 0.112 0.008
#> GSM486837 3 0.550 0.32708 0.008 0.092 0.616 0.268 0.004 0.012
#> GSM486839 1 0.581 0.40343 0.564 0.020 0.036 0.328 0.052 0.000
#> GSM486841 1 0.329 0.67538 0.784 0.000 0.008 0.200 0.008 0.000
#> GSM486843 4 0.638 0.33547 0.304 0.064 0.068 0.540 0.024 0.000
#> GSM486845 4 0.549 -0.03835 0.000 0.020 0.368 0.540 0.004 0.068
#> GSM486847 1 0.554 0.43415 0.616 0.024 0.020 0.292 0.040 0.008
#> GSM486849 2 0.713 0.15249 0.000 0.380 0.336 0.104 0.000 0.180
#> GSM486851 5 0.211 0.61541 0.032 0.028 0.008 0.012 0.920 0.000
#> GSM486853 3 0.717 0.18650 0.000 0.280 0.412 0.108 0.000 0.200
#> GSM486855 2 0.598 0.38078 0.000 0.556 0.300 0.108 0.020 0.016
#> GSM486857 4 0.506 0.18612 0.000 0.024 0.220 0.668 0.000 0.088
#> GSM486736 5 0.474 0.39434 0.000 0.000 0.048 0.000 0.516 0.436
#> GSM486738 2 0.588 0.18826 0.000 0.512 0.160 0.000 0.012 0.316
#> GSM486740 5 0.514 0.52156 0.000 0.012 0.084 0.000 0.612 0.292
#> GSM486742 6 0.583 0.10827 0.000 0.304 0.216 0.000 0.000 0.480
#> GSM486744 2 0.501 0.41037 0.000 0.600 0.300 0.000 0.000 0.100
#> GSM486746 5 0.728 0.36681 0.000 0.092 0.192 0.016 0.456 0.244
#> GSM486748 1 0.552 0.45006 0.612 0.024 0.244 0.000 0.000 0.120
#> GSM486750 6 0.463 0.27470 0.000 0.072 0.256 0.000 0.004 0.668
#> GSM486752 1 0.512 0.49378 0.652 0.008 0.148 0.000 0.000 0.192
#> GSM486754 6 0.616 -0.06575 0.000 0.360 0.248 0.000 0.004 0.388
#> GSM486756 6 0.509 0.11283 0.000 0.364 0.076 0.000 0.004 0.556
#> GSM486758 1 0.554 0.27374 0.536 0.008 0.084 0.004 0.004 0.364
#> GSM486760 1 0.302 0.74448 0.872 0.008 0.036 0.016 0.064 0.004
#> GSM486762 1 0.337 0.70690 0.820 0.004 0.132 0.000 0.004 0.040
#> GSM486764 5 0.317 0.61455 0.024 0.032 0.016 0.000 0.864 0.064
#> GSM486766 1 0.204 0.73466 0.908 0.000 0.072 0.000 0.004 0.016
#> GSM486768 3 0.764 0.00538 0.000 0.264 0.360 0.020 0.264 0.092
#> GSM486770 6 0.503 -0.12281 0.000 0.004 0.068 0.000 0.376 0.552
#> GSM486772 2 0.381 0.55950 0.004 0.784 0.132 0.000 0.000 0.080
#> GSM486774 3 0.500 0.20410 0.044 0.020 0.588 0.000 0.000 0.348
#> GSM486776 1 0.155 0.75133 0.944 0.004 0.032 0.000 0.012 0.008
#> GSM486778 1 0.304 0.74413 0.864 0.008 0.032 0.004 0.084 0.008
#> GSM486780 2 0.356 0.53646 0.000 0.836 0.092 0.020 0.024 0.028
#> GSM486782 3 0.496 0.23778 0.004 0.072 0.592 0.000 0.000 0.332
#> GSM486784 2 0.437 0.47754 0.000 0.720 0.164 0.000 0.000 0.116
#> GSM486786 1 0.211 0.75169 0.920 0.012 0.032 0.000 0.008 0.028
#> GSM486788 1 0.400 0.72674 0.816 0.024 0.052 0.020 0.084 0.004
#> GSM486790 6 0.633 0.10576 0.000 0.088 0.348 0.000 0.080 0.484
#> GSM486792 5 0.318 0.60623 0.084 0.000 0.008 0.004 0.848 0.056
#> GSM486794 1 0.158 0.74891 0.944 0.000 0.020 0.004 0.008 0.024
#> GSM486796 2 0.539 0.43666 0.100 0.728 0.084 0.008 0.036 0.044
#> GSM486798 1 0.605 0.28154 0.532 0.028 0.284 0.000 0.000 0.156
#> GSM486800 1 0.291 0.74195 0.872 0.004 0.020 0.020 0.080 0.004
#> GSM486802 1 0.512 0.68334 0.736 0.080 0.040 0.024 0.116 0.004
#> GSM486804 1 0.675 0.34908 0.512 0.304 0.084 0.020 0.076 0.004
#> GSM486806 3 0.515 0.29370 0.172 0.004 0.640 0.000 0.000 0.184
#> GSM486808 1 0.286 0.70155 0.828 0.000 0.156 0.000 0.000 0.016
#> GSM486810 5 0.474 0.38146 0.000 0.008 0.032 0.000 0.524 0.436
#> GSM486812 1 0.204 0.75195 0.924 0.004 0.036 0.004 0.024 0.008
#> GSM486814 2 0.360 0.53407 0.000 0.828 0.084 0.004 0.024 0.060
#> GSM486816 1 0.207 0.74928 0.920 0.000 0.024 0.004 0.012 0.040
#> GSM486818 3 0.659 -0.09348 0.052 0.344 0.512 0.020 0.032 0.040
#> GSM486821 5 0.518 0.51386 0.028 0.152 0.080 0.020 0.716 0.004
#> GSM486823 6 0.528 0.31057 0.000 0.052 0.240 0.000 0.060 0.648
#> GSM486826 1 0.563 0.52850 0.640 0.256 0.024 0.020 0.020 0.040
#> GSM486830 3 0.512 0.31535 0.004 0.068 0.656 0.000 0.024 0.248
#> GSM486832 1 0.455 0.69651 0.756 0.008 0.056 0.020 0.152 0.008
#> GSM486834 6 0.597 0.07485 0.312 0.000 0.164 0.000 0.016 0.508
#> GSM486836 1 0.536 0.67971 0.720 0.052 0.128 0.020 0.072 0.008
#> GSM486838 3 0.453 0.27576 0.012 0.272 0.672 0.000 0.000 0.044
#> GSM486840 1 0.416 0.73360 0.808 0.080 0.052 0.016 0.040 0.004
#> GSM486842 1 0.160 0.74939 0.940 0.000 0.040 0.004 0.008 0.008
#> GSM486844 1 0.576 0.56653 0.640 0.208 0.108 0.020 0.020 0.004
#> GSM486846 3 0.495 0.35630 0.012 0.220 0.676 0.000 0.004 0.088
#> GSM486848 1 0.366 0.73697 0.832 0.084 0.020 0.000 0.044 0.020
#> GSM486850 2 0.570 0.28466 0.004 0.500 0.344 0.000 0.000 0.152
#> GSM486852 5 0.241 0.61500 0.032 0.036 0.012 0.004 0.908 0.008
#> GSM486854 3 0.589 0.06425 0.000 0.368 0.428 0.000 0.000 0.204
#> GSM486856 2 0.410 0.42749 0.000 0.664 0.316 0.008 0.008 0.004
#> GSM486858 3 0.584 0.26746 0.000 0.232 0.488 0.000 0.000 0.280
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> SD:NMF 114 1.000000 1.11e-05 2
#> SD:NMF 102 0.269141 6.56e-07 3
#> SD:NMF 94 0.000529 1.17e-04 4
#> SD:NMF 69 0.495453 1.02e-07 5
#> SD:NMF 47 0.981784 1.11e-03 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["CV", "hclust"]
# you can also extract it by
# res = res_list["CV:hclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'CV' method.
#> Subgroups are detected by 'hclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 3.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.1827 0.831 0.813 0.2033 0.967 0.967
#> 3 3 0.0478 0.470 0.700 0.7711 0.906 0.903
#> 4 4 0.0792 0.576 0.676 0.3378 0.568 0.518
#> 5 5 0.0998 0.544 0.698 0.1902 0.953 0.905
#> 6 6 0.1424 0.461 0.670 0.0993 0.940 0.874
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 3
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 2 0.482 0.831 0.104 0.896
#> GSM486737 2 0.506 0.856 0.112 0.888
#> GSM486739 2 0.494 0.866 0.108 0.892
#> GSM486741 2 0.469 0.864 0.100 0.900
#> GSM486743 2 0.541 0.859 0.124 0.876
#> GSM486745 2 0.584 0.857 0.140 0.860
#> GSM486747 2 0.552 0.851 0.128 0.872
#> GSM486749 2 0.343 0.846 0.064 0.936
#> GSM486751 2 0.469 0.864 0.100 0.900
#> GSM486753 2 0.595 0.856 0.144 0.856
#> GSM486755 2 0.529 0.860 0.120 0.880
#> GSM486757 2 0.753 0.779 0.216 0.784
#> GSM486759 2 0.662 0.850 0.172 0.828
#> GSM486761 2 0.443 0.860 0.092 0.908
#> GSM486763 1 0.697 1.000 0.812 0.188
#> GSM486765 2 0.689 0.819 0.184 0.816
#> GSM486767 2 0.671 0.855 0.176 0.824
#> GSM486769 2 0.494 0.832 0.108 0.892
#> GSM486771 2 0.541 0.856 0.124 0.876
#> GSM486773 2 0.416 0.860 0.084 0.916
#> GSM486775 2 0.714 0.837 0.196 0.804
#> GSM486777 2 0.625 0.838 0.156 0.844
#> GSM486779 2 0.584 0.865 0.140 0.860
#> GSM486781 2 0.295 0.858 0.052 0.948
#> GSM486783 2 0.563 0.853 0.132 0.868
#> GSM486785 2 0.595 0.846 0.144 0.856
#> GSM486787 2 0.738 0.832 0.208 0.792
#> GSM486789 2 0.416 0.854 0.084 0.916
#> GSM486791 2 0.969 0.452 0.396 0.604
#> GSM486793 2 0.662 0.823 0.172 0.828
#> GSM486795 2 0.595 0.863 0.144 0.856
#> GSM486797 2 0.260 0.864 0.044 0.956
#> GSM486799 2 0.738 0.831 0.208 0.792
#> GSM486801 2 0.662 0.848 0.172 0.828
#> GSM486803 2 0.814 0.809 0.252 0.748
#> GSM486805 2 0.343 0.861 0.064 0.936
#> GSM486807 2 0.402 0.866 0.080 0.920
#> GSM486809 2 0.518 0.835 0.116 0.884
#> GSM486811 2 0.563 0.854 0.132 0.868
#> GSM486813 2 0.529 0.862 0.120 0.880
#> GSM486815 2 0.760 0.791 0.220 0.780
#> GSM486817 2 0.714 0.839 0.196 0.804
#> GSM486819 2 0.605 0.863 0.148 0.852
#> GSM486822 2 0.494 0.832 0.108 0.892
#> GSM486824 2 0.730 0.836 0.204 0.796
#> GSM486828 2 0.343 0.848 0.064 0.936
#> GSM486831 2 0.753 0.839 0.216 0.784
#> GSM486833 2 0.443 0.859 0.092 0.908
#> GSM486835 2 0.697 0.843 0.188 0.812
#> GSM486837 2 0.416 0.852 0.084 0.916
#> GSM486839 2 0.730 0.833 0.204 0.796
#> GSM486841 2 0.653 0.830 0.168 0.832
#> GSM486843 2 0.689 0.845 0.184 0.816
#> GSM486845 2 0.260 0.852 0.044 0.956
#> GSM486847 2 0.730 0.834 0.204 0.796
#> GSM486849 2 0.327 0.854 0.060 0.940
#> GSM486851 2 1.000 0.186 0.488 0.512
#> GSM486853 2 0.343 0.848 0.064 0.936
#> GSM486855 2 0.552 0.860 0.128 0.872
#> GSM486857 2 0.388 0.846 0.076 0.924
#> GSM486736 2 0.482 0.831 0.104 0.896
#> GSM486738 2 0.506 0.856 0.112 0.888
#> GSM486740 2 0.494 0.866 0.108 0.892
#> GSM486742 2 0.469 0.864 0.100 0.900
#> GSM486744 2 0.574 0.860 0.136 0.864
#> GSM486746 2 0.605 0.858 0.148 0.852
#> GSM486748 2 0.518 0.861 0.116 0.884
#> GSM486750 2 0.388 0.846 0.076 0.924
#> GSM486752 2 0.443 0.863 0.092 0.908
#> GSM486754 2 0.595 0.856 0.144 0.856
#> GSM486756 2 0.529 0.860 0.120 0.880
#> GSM486758 2 0.753 0.779 0.216 0.784
#> GSM486760 2 0.697 0.847 0.188 0.812
#> GSM486762 2 0.443 0.860 0.092 0.908
#> GSM486764 1 0.697 1.000 0.812 0.188
#> GSM486766 2 0.671 0.827 0.176 0.824
#> GSM486768 2 0.563 0.866 0.132 0.868
#> GSM486770 2 0.469 0.834 0.100 0.900
#> GSM486772 2 0.541 0.859 0.124 0.876
#> GSM486774 2 0.358 0.857 0.068 0.932
#> GSM486776 2 0.722 0.841 0.200 0.800
#> GSM486778 2 0.615 0.839 0.152 0.848
#> GSM486780 2 0.680 0.850 0.180 0.820
#> GSM486782 2 0.311 0.857 0.056 0.944
#> GSM486784 2 0.563 0.853 0.132 0.868
#> GSM486786 2 0.653 0.833 0.168 0.832
#> GSM486788 2 0.753 0.828 0.216 0.784
#> GSM486790 2 0.416 0.857 0.084 0.916
#> GSM486792 2 0.969 0.452 0.396 0.604
#> GSM486794 2 0.671 0.821 0.176 0.824
#> GSM486796 2 0.595 0.863 0.144 0.856
#> GSM486798 2 0.388 0.866 0.076 0.924
#> GSM486800 2 0.671 0.848 0.176 0.824
#> GSM486802 2 0.662 0.848 0.172 0.828
#> GSM486804 2 0.753 0.830 0.216 0.784
#> GSM486806 2 0.327 0.863 0.060 0.940
#> GSM486808 2 0.529 0.856 0.120 0.880
#> GSM486810 2 0.506 0.832 0.112 0.888
#> GSM486812 2 0.574 0.852 0.136 0.864
#> GSM486814 2 0.529 0.863 0.120 0.880
#> GSM486816 2 0.753 0.795 0.216 0.784
#> GSM486818 2 0.722 0.839 0.200 0.800
#> GSM486821 2 0.584 0.862 0.140 0.860
#> GSM486823 2 0.494 0.832 0.108 0.892
#> GSM486826 2 0.745 0.831 0.212 0.788
#> GSM486830 2 0.327 0.849 0.060 0.940
#> GSM486832 2 0.753 0.835 0.216 0.784
#> GSM486834 2 0.443 0.859 0.092 0.908
#> GSM486836 2 0.753 0.827 0.216 0.784
#> GSM486838 2 0.388 0.865 0.076 0.924
#> GSM486840 2 0.730 0.833 0.204 0.796
#> GSM486842 2 0.662 0.822 0.172 0.828
#> GSM486844 2 0.653 0.852 0.168 0.832
#> GSM486846 2 0.260 0.852 0.044 0.956
#> GSM486848 2 0.745 0.832 0.212 0.788
#> GSM486850 2 0.327 0.854 0.060 0.940
#> GSM486852 2 1.000 0.186 0.488 0.512
#> GSM486854 2 0.358 0.846 0.068 0.932
#> GSM486856 2 0.541 0.859 0.124 0.876
#> GSM486858 2 0.416 0.854 0.084 0.916
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 3 0.357 0.5747 0.060 0.040 0.900
#> GSM486737 3 0.512 0.5885 0.188 0.016 0.796
#> GSM486739 3 0.416 0.6223 0.144 0.008 0.848
#> GSM486741 3 0.397 0.6172 0.132 0.008 0.860
#> GSM486743 3 0.441 0.6070 0.172 0.004 0.824
#> GSM486745 3 0.481 0.6076 0.176 0.012 0.812
#> GSM486747 3 0.670 0.4836 0.280 0.036 0.684
#> GSM486749 3 0.230 0.6126 0.036 0.020 0.944
#> GSM486751 3 0.554 0.5920 0.200 0.024 0.776
#> GSM486753 3 0.392 0.6110 0.120 0.012 0.868
#> GSM486755 3 0.451 0.6112 0.156 0.012 0.832
#> GSM486757 1 0.875 0.0858 0.580 0.164 0.256
#> GSM486759 3 0.613 0.4463 0.400 0.000 0.600
#> GSM486761 3 0.568 0.5596 0.212 0.024 0.764
#> GSM486763 2 0.608 1.0000 0.128 0.784 0.088
#> GSM486765 3 0.741 0.2874 0.384 0.040 0.576
#> GSM486767 3 0.674 0.5280 0.300 0.032 0.668
#> GSM486769 3 0.379 0.5714 0.060 0.048 0.892
#> GSM486771 3 0.447 0.6096 0.176 0.004 0.820
#> GSM486773 3 0.374 0.6174 0.072 0.036 0.892
#> GSM486775 3 0.647 0.3651 0.444 0.004 0.552
#> GSM486777 3 0.716 0.3963 0.316 0.044 0.640
#> GSM486779 3 0.651 0.4676 0.300 0.024 0.676
#> GSM486781 3 0.249 0.6239 0.048 0.016 0.936
#> GSM486783 3 0.459 0.5956 0.172 0.008 0.820
#> GSM486785 3 0.784 0.1432 0.408 0.056 0.536
#> GSM486787 3 0.693 0.3385 0.452 0.016 0.532
#> GSM486789 3 0.311 0.6103 0.056 0.028 0.916
#> GSM486791 3 0.986 -0.4245 0.372 0.252 0.376
#> GSM486793 3 0.733 0.2901 0.388 0.036 0.576
#> GSM486795 3 0.514 0.5942 0.252 0.000 0.748
#> GSM486797 3 0.321 0.6363 0.084 0.012 0.904
#> GSM486799 3 0.758 0.1751 0.468 0.040 0.492
#> GSM486801 3 0.658 0.3959 0.420 0.008 0.572
#> GSM486803 1 0.832 0.0648 0.496 0.080 0.424
#> GSM486805 3 0.427 0.6289 0.116 0.024 0.860
#> GSM486807 3 0.527 0.5880 0.212 0.012 0.776
#> GSM486809 3 0.408 0.5745 0.072 0.048 0.880
#> GSM486811 3 0.684 0.4147 0.332 0.028 0.640
#> GSM486813 3 0.582 0.5741 0.236 0.020 0.744
#> GSM486815 3 0.816 0.0530 0.412 0.072 0.516
#> GSM486817 3 0.688 0.3521 0.428 0.016 0.556
#> GSM486819 3 0.562 0.5937 0.244 0.012 0.744
#> GSM486822 3 0.389 0.5702 0.064 0.048 0.888
#> GSM486824 3 0.717 0.2339 0.456 0.024 0.520
#> GSM486828 3 0.253 0.6140 0.044 0.020 0.936
#> GSM486831 3 0.730 0.3598 0.412 0.032 0.556
#> GSM486833 3 0.522 0.5952 0.176 0.024 0.800
#> GSM486835 3 0.715 0.2957 0.440 0.024 0.536
#> GSM486837 3 0.318 0.6238 0.076 0.016 0.908
#> GSM486839 3 0.648 0.3660 0.452 0.004 0.544
#> GSM486841 3 0.702 0.3237 0.392 0.024 0.584
#> GSM486843 3 0.654 0.4125 0.408 0.008 0.584
#> GSM486845 3 0.223 0.6191 0.044 0.012 0.944
#> GSM486847 3 0.680 0.3192 0.456 0.012 0.532
#> GSM486849 3 0.231 0.6202 0.032 0.024 0.944
#> GSM486851 1 0.999 0.4553 0.356 0.332 0.312
#> GSM486853 3 0.337 0.5992 0.052 0.040 0.908
#> GSM486855 3 0.486 0.6106 0.180 0.012 0.808
#> GSM486857 3 0.397 0.5978 0.072 0.044 0.884
#> GSM486736 3 0.368 0.5726 0.060 0.044 0.896
#> GSM486738 3 0.484 0.5941 0.168 0.016 0.816
#> GSM486740 3 0.416 0.6223 0.144 0.008 0.848
#> GSM486742 3 0.350 0.6173 0.116 0.004 0.880
#> GSM486744 3 0.517 0.6162 0.192 0.016 0.792
#> GSM486746 3 0.497 0.6084 0.188 0.012 0.800
#> GSM486748 3 0.607 0.5715 0.236 0.028 0.736
#> GSM486750 3 0.253 0.6096 0.044 0.020 0.936
#> GSM486752 3 0.544 0.5912 0.192 0.024 0.784
#> GSM486754 3 0.392 0.6110 0.120 0.012 0.868
#> GSM486756 3 0.451 0.6112 0.156 0.012 0.832
#> GSM486758 1 0.875 0.0858 0.580 0.164 0.256
#> GSM486760 3 0.642 0.4093 0.424 0.004 0.572
#> GSM486762 3 0.568 0.5596 0.212 0.024 0.764
#> GSM486764 2 0.608 1.0000 0.128 0.784 0.088
#> GSM486766 3 0.725 0.3299 0.368 0.036 0.596
#> GSM486768 3 0.527 0.6171 0.212 0.012 0.776
#> GSM486770 3 0.359 0.5749 0.052 0.048 0.900
#> GSM486772 3 0.441 0.6135 0.160 0.008 0.832
#> GSM486774 3 0.383 0.6194 0.076 0.036 0.888
#> GSM486776 3 0.679 0.3147 0.448 0.012 0.540
#> GSM486778 3 0.714 0.4010 0.312 0.044 0.644
#> GSM486780 3 0.725 0.3618 0.368 0.036 0.596
#> GSM486782 3 0.238 0.6241 0.044 0.016 0.940
#> GSM486784 3 0.459 0.5956 0.172 0.008 0.820
#> GSM486786 3 0.806 0.0294 0.440 0.064 0.496
#> GSM486788 3 0.690 0.3701 0.440 0.016 0.544
#> GSM486790 3 0.355 0.6105 0.064 0.036 0.900
#> GSM486792 3 0.986 -0.4245 0.372 0.252 0.376
#> GSM486794 3 0.741 0.2910 0.384 0.040 0.576
#> GSM486796 3 0.518 0.5927 0.256 0.000 0.744
#> GSM486798 3 0.517 0.6043 0.192 0.016 0.792
#> GSM486800 3 0.694 0.3866 0.404 0.020 0.576
#> GSM486802 3 0.656 0.4009 0.416 0.008 0.576
#> GSM486804 3 0.784 0.1012 0.456 0.052 0.492
#> GSM486806 3 0.391 0.6259 0.104 0.020 0.876
#> GSM486808 3 0.633 0.4882 0.292 0.020 0.688
#> GSM486810 3 0.398 0.5699 0.068 0.048 0.884
#> GSM486812 3 0.687 0.4090 0.336 0.028 0.636
#> GSM486814 3 0.555 0.5854 0.212 0.020 0.768
#> GSM486816 3 0.809 0.0513 0.416 0.068 0.516
#> GSM486818 3 0.749 0.3244 0.408 0.040 0.552
#> GSM486821 3 0.580 0.5898 0.248 0.016 0.736
#> GSM486823 3 0.389 0.5702 0.064 0.048 0.888
#> GSM486826 1 0.719 -0.2439 0.500 0.024 0.476
#> GSM486830 3 0.241 0.6157 0.040 0.020 0.940
#> GSM486832 3 0.733 0.3424 0.424 0.032 0.544
#> GSM486834 3 0.517 0.5952 0.172 0.024 0.804
#> GSM486836 3 0.707 0.2465 0.468 0.020 0.512
#> GSM486838 3 0.461 0.6208 0.128 0.028 0.844
#> GSM486840 3 0.648 0.3660 0.452 0.004 0.544
#> GSM486842 3 0.722 0.3166 0.388 0.032 0.580
#> GSM486844 3 0.636 0.4194 0.404 0.004 0.592
#> GSM486846 3 0.223 0.6191 0.044 0.012 0.944
#> GSM486848 3 0.747 0.2521 0.448 0.036 0.516
#> GSM486850 3 0.231 0.6202 0.032 0.024 0.944
#> GSM486852 1 0.999 0.4553 0.356 0.332 0.312
#> GSM486854 3 0.313 0.5974 0.052 0.032 0.916
#> GSM486856 3 0.502 0.6060 0.192 0.012 0.796
#> GSM486858 3 0.448 0.5950 0.096 0.044 0.860
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 2 0.313 0.6777 0.036 0.900 0.036 0.028
#> GSM486737 2 0.594 0.5967 0.032 0.696 0.236 0.036
#> GSM486739 2 0.415 0.6738 0.016 0.800 0.180 0.004
#> GSM486741 2 0.460 0.6899 0.012 0.796 0.160 0.032
#> GSM486743 2 0.455 0.6780 0.008 0.784 0.184 0.024
#> GSM486745 2 0.455 0.6494 0.012 0.772 0.204 0.012
#> GSM486747 2 0.694 -0.2891 0.080 0.520 0.388 0.012
#> GSM486749 2 0.197 0.7119 0.008 0.932 0.060 0.000
#> GSM486751 2 0.564 0.4158 0.032 0.692 0.260 0.016
#> GSM486753 2 0.449 0.6887 0.020 0.812 0.140 0.028
#> GSM486755 2 0.472 0.6831 0.016 0.788 0.168 0.028
#> GSM486757 1 0.354 1.0000 0.864 0.060 0.076 0.000
#> GSM486759 3 0.506 0.5290 0.004 0.412 0.584 0.000
#> GSM486761 2 0.605 0.0362 0.044 0.620 0.328 0.008
#> GSM486763 4 0.241 1.0000 0.004 0.016 0.060 0.920
#> GSM486765 3 0.728 0.5896 0.092 0.380 0.508 0.020
#> GSM486767 2 0.731 0.2097 0.068 0.512 0.384 0.036
#> GSM486769 2 0.332 0.6750 0.040 0.892 0.036 0.032
#> GSM486771 2 0.457 0.6538 0.008 0.768 0.208 0.016
#> GSM486773 2 0.384 0.7084 0.032 0.860 0.088 0.020
#> GSM486775 3 0.532 0.6253 0.004 0.360 0.624 0.012
#> GSM486777 3 0.716 0.5351 0.064 0.444 0.464 0.028
#> GSM486779 2 0.713 0.2306 0.068 0.480 0.428 0.024
#> GSM486781 2 0.328 0.7017 0.024 0.880 0.088 0.008
#> GSM486783 2 0.474 0.6505 0.004 0.760 0.208 0.028
#> GSM486785 3 0.777 0.5399 0.160 0.340 0.484 0.016
#> GSM486787 3 0.565 0.6473 0.012 0.328 0.640 0.020
#> GSM486789 2 0.298 0.7136 0.024 0.900 0.064 0.012
#> GSM486791 3 0.846 0.4311 0.056 0.196 0.500 0.248
#> GSM486793 3 0.752 0.5922 0.092 0.372 0.504 0.032
#> GSM486795 2 0.545 0.3407 0.008 0.620 0.360 0.012
#> GSM486797 2 0.390 0.6928 0.016 0.836 0.136 0.012
#> GSM486799 3 0.681 0.6624 0.060 0.260 0.636 0.044
#> GSM486801 3 0.530 0.5914 0.004 0.388 0.600 0.008
#> GSM486803 3 0.777 0.4915 0.140 0.156 0.616 0.088
#> GSM486805 2 0.448 0.6672 0.020 0.804 0.156 0.020
#> GSM486807 2 0.527 0.2130 0.016 0.676 0.300 0.008
#> GSM486809 2 0.374 0.6717 0.048 0.872 0.052 0.028
#> GSM486811 3 0.660 0.5654 0.040 0.444 0.496 0.020
#> GSM486813 2 0.627 0.5059 0.032 0.624 0.316 0.028
#> GSM486815 3 0.810 0.5335 0.116 0.308 0.516 0.060
#> GSM486817 3 0.663 0.4975 0.044 0.372 0.560 0.024
#> GSM486819 2 0.561 0.4312 0.016 0.648 0.320 0.016
#> GSM486822 2 0.341 0.6740 0.040 0.888 0.040 0.032
#> GSM486824 3 0.670 0.5724 0.060 0.316 0.600 0.024
#> GSM486828 2 0.249 0.7087 0.016 0.916 0.064 0.004
#> GSM486831 3 0.613 0.6402 0.020 0.372 0.584 0.024
#> GSM486833 2 0.560 0.4233 0.040 0.712 0.232 0.016
#> GSM486835 3 0.601 0.6543 0.032 0.324 0.628 0.016
#> GSM486837 2 0.298 0.6879 0.008 0.880 0.108 0.004
#> GSM486839 3 0.542 0.6179 0.008 0.352 0.628 0.012
#> GSM486841 3 0.693 0.5979 0.064 0.396 0.520 0.020
#> GSM486843 3 0.536 0.6001 0.008 0.368 0.616 0.008
#> GSM486845 2 0.205 0.7028 0.008 0.928 0.064 0.000
#> GSM486847 3 0.589 0.6552 0.016 0.336 0.624 0.024
#> GSM486849 2 0.252 0.7143 0.020 0.916 0.060 0.004
#> GSM486851 3 0.797 0.1341 0.028 0.144 0.460 0.368
#> GSM486853 2 0.331 0.7047 0.028 0.880 0.084 0.008
#> GSM486855 2 0.496 0.6507 0.008 0.732 0.240 0.020
#> GSM486857 2 0.401 0.7004 0.036 0.848 0.100 0.016
#> GSM486736 2 0.322 0.6762 0.040 0.896 0.036 0.028
#> GSM486738 2 0.564 0.6245 0.028 0.724 0.212 0.036
#> GSM486740 2 0.415 0.6738 0.016 0.800 0.180 0.004
#> GSM486742 2 0.426 0.6939 0.012 0.820 0.140 0.028
#> GSM486744 2 0.486 0.6578 0.008 0.744 0.228 0.020
#> GSM486746 2 0.466 0.6436 0.012 0.760 0.216 0.012
#> GSM486748 2 0.552 0.3036 0.032 0.664 0.300 0.004
#> GSM486750 2 0.212 0.7089 0.012 0.932 0.052 0.004
#> GSM486752 2 0.540 0.4056 0.032 0.700 0.260 0.008
#> GSM486754 2 0.449 0.6887 0.020 0.812 0.140 0.028
#> GSM486756 2 0.472 0.6831 0.016 0.788 0.168 0.028
#> GSM486758 1 0.354 1.0000 0.864 0.060 0.076 0.000
#> GSM486760 3 0.529 0.5932 0.004 0.384 0.604 0.008
#> GSM486762 2 0.605 0.0362 0.044 0.620 0.328 0.008
#> GSM486764 4 0.241 1.0000 0.004 0.016 0.060 0.920
#> GSM486766 3 0.732 0.5845 0.084 0.408 0.484 0.024
#> GSM486768 2 0.503 0.5701 0.004 0.696 0.284 0.016
#> GSM486770 2 0.313 0.6765 0.040 0.900 0.032 0.028
#> GSM486772 2 0.439 0.6664 0.004 0.784 0.192 0.020
#> GSM486774 2 0.381 0.6923 0.044 0.856 0.092 0.008
#> GSM486776 3 0.572 0.6590 0.020 0.344 0.624 0.012
#> GSM486778 3 0.716 0.5289 0.064 0.448 0.460 0.028
#> GSM486780 3 0.782 0.0229 0.096 0.352 0.504 0.048
#> GSM486782 2 0.307 0.7000 0.024 0.892 0.076 0.008
#> GSM486784 2 0.474 0.6505 0.004 0.760 0.208 0.028
#> GSM486786 3 0.801 0.5415 0.216 0.268 0.496 0.020
#> GSM486788 3 0.558 0.6342 0.008 0.340 0.632 0.020
#> GSM486790 2 0.318 0.7130 0.024 0.892 0.068 0.016
#> GSM486792 3 0.846 0.4311 0.056 0.196 0.500 0.248
#> GSM486794 3 0.749 0.5909 0.096 0.372 0.504 0.028
#> GSM486796 2 0.547 0.3315 0.008 0.616 0.364 0.012
#> GSM486798 2 0.526 0.4176 0.020 0.716 0.248 0.016
#> GSM486800 3 0.634 0.6519 0.016 0.364 0.580 0.040
#> GSM486802 3 0.544 0.5838 0.008 0.392 0.592 0.008
#> GSM486804 3 0.745 0.5340 0.108 0.264 0.588 0.040
#> GSM486806 2 0.426 0.6614 0.040 0.824 0.128 0.008
#> GSM486808 2 0.658 -0.3103 0.044 0.548 0.388 0.020
#> GSM486810 2 0.349 0.6720 0.044 0.884 0.044 0.028
#> GSM486812 3 0.659 0.5721 0.040 0.436 0.504 0.020
#> GSM486814 2 0.591 0.5716 0.024 0.664 0.284 0.028
#> GSM486816 3 0.812 0.5337 0.112 0.308 0.516 0.064
#> GSM486818 3 0.722 0.5364 0.052 0.340 0.556 0.052
#> GSM486821 2 0.578 0.4276 0.012 0.644 0.316 0.028
#> GSM486823 2 0.341 0.6740 0.040 0.888 0.040 0.032
#> GSM486826 3 0.684 0.5959 0.096 0.260 0.624 0.020
#> GSM486830 2 0.236 0.7067 0.012 0.920 0.064 0.004
#> GSM486832 3 0.615 0.6535 0.020 0.352 0.600 0.028
#> GSM486834 2 0.556 0.4280 0.040 0.716 0.228 0.016
#> GSM486836 3 0.563 0.6657 0.020 0.304 0.660 0.016
#> GSM486838 2 0.478 0.6302 0.028 0.756 0.212 0.004
#> GSM486840 3 0.542 0.6179 0.008 0.352 0.628 0.012
#> GSM486842 3 0.715 0.5994 0.068 0.388 0.516 0.028
#> GSM486844 3 0.588 0.5200 0.016 0.388 0.580 0.016
#> GSM486846 2 0.205 0.7028 0.008 0.928 0.064 0.000
#> GSM486848 3 0.636 0.6697 0.032 0.300 0.632 0.036
#> GSM486850 2 0.252 0.7143 0.020 0.916 0.060 0.004
#> GSM486852 3 0.797 0.1341 0.028 0.144 0.460 0.368
#> GSM486854 2 0.307 0.7032 0.024 0.888 0.084 0.004
#> GSM486856 2 0.515 0.6447 0.012 0.720 0.248 0.020
#> GSM486858 2 0.470 0.6844 0.052 0.808 0.124 0.016
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 4 0.3361 0.65278 0.040 0.056 0.012 0.872 0.020
#> GSM486737 4 0.5761 0.45882 0.184 0.176 0.000 0.636 0.004
#> GSM486739 4 0.4298 0.66887 0.168 0.052 0.000 0.772 0.008
#> GSM486741 4 0.4634 0.64933 0.144 0.100 0.000 0.752 0.004
#> GSM486743 4 0.4812 0.65470 0.172 0.076 0.000 0.740 0.012
#> GSM486745 4 0.4612 0.64157 0.196 0.056 0.000 0.740 0.008
#> GSM486747 1 0.6537 0.38012 0.496 0.056 0.052 0.392 0.004
#> GSM486749 4 0.2619 0.69725 0.072 0.024 0.004 0.896 0.004
#> GSM486751 4 0.5693 0.43140 0.320 0.044 0.024 0.608 0.004
#> GSM486753 4 0.4728 0.65775 0.128 0.088 0.000 0.764 0.020
#> GSM486755 4 0.4826 0.65570 0.156 0.088 0.000 0.744 0.012
#> GSM486757 3 0.0968 0.98089 0.012 0.004 0.972 0.012 0.000
#> GSM486759 1 0.4636 0.48119 0.664 0.024 0.000 0.308 0.004
#> GSM486761 4 0.5889 -0.15793 0.444 0.060 0.016 0.480 0.000
#> GSM486763 5 0.0955 1.00000 0.028 0.000 0.000 0.004 0.968
#> GSM486765 1 0.6585 0.57802 0.620 0.096 0.060 0.216 0.008
#> GSM486767 4 0.7962 -0.12702 0.332 0.196 0.036 0.404 0.032
#> GSM486769 4 0.3464 0.64802 0.032 0.060 0.016 0.868 0.024
#> GSM486771 4 0.4444 0.64813 0.184 0.052 0.000 0.756 0.008
#> GSM486773 4 0.3982 0.69423 0.088 0.084 0.000 0.816 0.012
#> GSM486775 1 0.3954 0.62402 0.772 0.036 0.000 0.192 0.000
#> GSM486777 1 0.6283 0.57484 0.596 0.064 0.040 0.292 0.008
#> GSM486779 2 0.7268 0.61754 0.196 0.456 0.008 0.316 0.024
#> GSM486781 4 0.3885 0.69933 0.120 0.036 0.012 0.824 0.008
#> GSM486783 4 0.4951 0.60780 0.172 0.104 0.000 0.720 0.004
#> GSM486785 1 0.7697 0.29535 0.508 0.216 0.124 0.148 0.004
#> GSM486787 1 0.4551 0.62306 0.768 0.032 0.008 0.172 0.020
#> GSM486789 4 0.3522 0.68843 0.068 0.044 0.008 0.860 0.020
#> GSM486791 1 0.7600 0.25151 0.544 0.152 0.024 0.072 0.208
#> GSM486793 1 0.6611 0.57089 0.628 0.104 0.056 0.200 0.012
#> GSM486795 4 0.5146 0.39354 0.400 0.028 0.000 0.564 0.008
#> GSM486797 4 0.4260 0.69166 0.164 0.052 0.008 0.776 0.000
#> GSM486799 1 0.5326 0.57121 0.736 0.124 0.016 0.108 0.016
#> GSM486801 1 0.4377 0.58862 0.720 0.028 0.000 0.248 0.004
#> GSM486803 1 0.7411 0.16361 0.560 0.248 0.068 0.044 0.080
#> GSM486805 4 0.5028 0.65682 0.180 0.060 0.012 0.736 0.012
#> GSM486807 4 0.5138 0.09975 0.396 0.028 0.008 0.568 0.000
#> GSM486809 4 0.4108 0.63553 0.068 0.060 0.020 0.832 0.020
#> GSM486811 1 0.5605 0.59140 0.620 0.044 0.016 0.312 0.008
#> GSM486813 4 0.6595 0.25432 0.280 0.196 0.004 0.516 0.004
#> GSM486815 1 0.7186 0.37293 0.572 0.208 0.048 0.152 0.020
#> GSM486817 1 0.6479 0.30606 0.572 0.128 0.016 0.276 0.008
#> GSM486819 4 0.5595 0.49638 0.348 0.048 0.004 0.588 0.012
#> GSM486822 4 0.3544 0.64574 0.036 0.060 0.016 0.864 0.024
#> GSM486824 1 0.6856 0.33216 0.612 0.172 0.032 0.156 0.028
#> GSM486828 4 0.3221 0.70193 0.084 0.032 0.008 0.868 0.008
#> GSM486831 1 0.5184 0.62271 0.704 0.052 0.004 0.220 0.020
#> GSM486833 4 0.5448 0.39315 0.308 0.052 0.016 0.624 0.000
#> GSM486835 1 0.5223 0.59126 0.736 0.072 0.016 0.160 0.016
#> GSM486837 4 0.3372 0.69378 0.120 0.036 0.004 0.840 0.000
#> GSM486839 1 0.3953 0.61285 0.780 0.024 0.008 0.188 0.000
#> GSM486841 1 0.6431 0.59595 0.616 0.084 0.048 0.244 0.008
#> GSM486843 1 0.5442 0.56838 0.692 0.060 0.012 0.220 0.016
#> GSM486845 4 0.2767 0.69604 0.088 0.020 0.004 0.884 0.004
#> GSM486847 1 0.4083 0.63013 0.788 0.040 0.004 0.164 0.004
#> GSM486849 4 0.2569 0.69347 0.068 0.032 0.004 0.896 0.000
#> GSM486851 1 0.7098 -0.00538 0.476 0.128 0.008 0.036 0.352
#> GSM486853 4 0.3492 0.66322 0.064 0.080 0.004 0.848 0.004
#> GSM486855 4 0.4998 0.62585 0.200 0.080 0.000 0.712 0.008
#> GSM486857 4 0.4303 0.64764 0.088 0.096 0.012 0.800 0.004
#> GSM486736 4 0.3464 0.65068 0.040 0.056 0.016 0.868 0.020
#> GSM486738 4 0.5496 0.51787 0.168 0.160 0.000 0.668 0.004
#> GSM486740 4 0.4298 0.66887 0.168 0.052 0.000 0.772 0.008
#> GSM486742 4 0.4359 0.65940 0.128 0.092 0.000 0.776 0.004
#> GSM486744 4 0.5155 0.64632 0.216 0.068 0.000 0.700 0.016
#> GSM486746 4 0.4771 0.63202 0.208 0.060 0.000 0.724 0.008
#> GSM486748 4 0.5759 0.29345 0.364 0.044 0.020 0.568 0.004
#> GSM486750 4 0.2325 0.69271 0.068 0.028 0.000 0.904 0.000
#> GSM486752 4 0.5501 0.43228 0.324 0.032 0.024 0.616 0.004
#> GSM486754 4 0.4728 0.65775 0.128 0.088 0.000 0.764 0.020
#> GSM486756 4 0.4826 0.65570 0.156 0.088 0.000 0.744 0.012
#> GSM486758 3 0.0693 0.98087 0.012 0.000 0.980 0.008 0.000
#> GSM486760 1 0.4624 0.58641 0.716 0.028 0.004 0.244 0.008
#> GSM486762 4 0.5887 -0.15310 0.440 0.060 0.016 0.484 0.000
#> GSM486764 5 0.0955 1.00000 0.028 0.000 0.000 0.004 0.968
#> GSM486766 1 0.6420 0.59681 0.620 0.080 0.052 0.240 0.008
#> GSM486768 4 0.5253 0.58812 0.304 0.036 0.000 0.640 0.020
#> GSM486770 4 0.3305 0.65114 0.032 0.056 0.016 0.876 0.020
#> GSM486772 4 0.4339 0.65818 0.168 0.048 0.000 0.772 0.012
#> GSM486774 4 0.4022 0.68425 0.100 0.092 0.004 0.804 0.000
#> GSM486776 1 0.4307 0.63264 0.768 0.040 0.012 0.180 0.000
#> GSM486778 1 0.6300 0.57249 0.592 0.064 0.040 0.296 0.008
#> GSM486780 2 0.6427 0.55555 0.236 0.596 0.012 0.144 0.012
#> GSM486782 4 0.3708 0.69957 0.112 0.032 0.012 0.836 0.008
#> GSM486784 4 0.4951 0.60780 0.172 0.104 0.000 0.720 0.004
#> GSM486786 1 0.7650 0.22572 0.508 0.256 0.136 0.088 0.012
#> GSM486788 1 0.4565 0.61838 0.756 0.024 0.008 0.192 0.020
#> GSM486790 4 0.3584 0.69025 0.072 0.044 0.008 0.856 0.020
#> GSM486792 1 0.7600 0.25151 0.544 0.152 0.024 0.072 0.208
#> GSM486794 1 0.6580 0.57198 0.624 0.108 0.056 0.204 0.008
#> GSM486796 4 0.5155 0.38600 0.404 0.028 0.000 0.560 0.008
#> GSM486798 4 0.5202 0.38707 0.316 0.032 0.012 0.636 0.004
#> GSM486800 1 0.5129 0.63487 0.712 0.060 0.004 0.208 0.016
#> GSM486802 1 0.4482 0.58294 0.712 0.032 0.000 0.252 0.004
#> GSM486804 1 0.7243 0.06081 0.524 0.308 0.036 0.096 0.036
#> GSM486806 4 0.4634 0.66973 0.152 0.044 0.028 0.772 0.004
#> GSM486808 1 0.6084 0.33305 0.484 0.048 0.036 0.432 0.000
#> GSM486810 4 0.3884 0.63762 0.060 0.060 0.020 0.844 0.016
#> GSM486812 1 0.5658 0.59407 0.624 0.044 0.020 0.304 0.008
#> GSM486814 4 0.6211 0.38000 0.256 0.176 0.000 0.564 0.004
#> GSM486816 1 0.7241 0.37153 0.572 0.204 0.048 0.152 0.024
#> GSM486818 1 0.7070 0.30194 0.556 0.140 0.012 0.248 0.044
#> GSM486821 4 0.5830 0.49460 0.340 0.048 0.004 0.584 0.024
#> GSM486823 4 0.3544 0.64574 0.036 0.060 0.016 0.864 0.024
#> GSM486826 1 0.6740 0.31491 0.612 0.220 0.044 0.104 0.020
#> GSM486830 4 0.3137 0.70181 0.084 0.028 0.008 0.872 0.008
#> GSM486832 1 0.5031 0.63204 0.728 0.056 0.004 0.192 0.020
#> GSM486834 4 0.5431 0.39733 0.304 0.052 0.016 0.628 0.000
#> GSM486836 1 0.4595 0.61220 0.772 0.060 0.016 0.148 0.004
#> GSM486838 4 0.5248 0.59670 0.192 0.084 0.012 0.708 0.004
#> GSM486840 1 0.3953 0.61285 0.780 0.024 0.008 0.188 0.000
#> GSM486842 1 0.6535 0.58947 0.620 0.092 0.048 0.228 0.012
#> GSM486844 1 0.5629 0.50253 0.660 0.076 0.012 0.244 0.008
#> GSM486846 4 0.2767 0.69604 0.088 0.020 0.004 0.884 0.004
#> GSM486848 1 0.4651 0.61649 0.768 0.072 0.008 0.144 0.008
#> GSM486850 4 0.2569 0.69347 0.068 0.032 0.004 0.896 0.000
#> GSM486852 1 0.7098 -0.00538 0.476 0.128 0.008 0.036 0.352
#> GSM486854 4 0.3306 0.66165 0.060 0.072 0.004 0.860 0.004
#> GSM486856 4 0.5165 0.61093 0.208 0.088 0.000 0.696 0.008
#> GSM486858 4 0.4820 0.62012 0.088 0.120 0.016 0.768 0.008
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 4 0.3484 0.6507 0.020 0.036 0.004 0.844 0.012 0.084
#> GSM486737 4 0.5708 0.4636 0.148 0.256 0.000 0.580 0.004 0.012
#> GSM486739 4 0.4136 0.6794 0.180 0.048 0.000 0.756 0.004 0.012
#> GSM486741 4 0.4531 0.6478 0.112 0.172 0.000 0.712 0.004 0.000
#> GSM486743 4 0.4775 0.6598 0.144 0.136 0.000 0.708 0.004 0.008
#> GSM486745 4 0.4468 0.6579 0.200 0.064 0.000 0.720 0.000 0.016
#> GSM486747 1 0.6572 0.2730 0.472 0.024 0.020 0.328 0.000 0.156
#> GSM486749 4 0.3212 0.6996 0.056 0.072 0.004 0.852 0.000 0.016
#> GSM486751 4 0.5805 0.3499 0.324 0.040 0.008 0.560 0.000 0.068
#> GSM486753 4 0.4688 0.6665 0.100 0.116 0.000 0.748 0.012 0.024
#> GSM486755 4 0.4774 0.6613 0.136 0.116 0.000 0.724 0.004 0.020
#> GSM486757 3 0.0692 0.9837 0.000 0.000 0.976 0.004 0.000 0.020
#> GSM486759 1 0.4850 0.4372 0.672 0.028 0.008 0.264 0.004 0.024
#> GSM486761 1 0.6285 0.2737 0.440 0.032 0.008 0.404 0.000 0.116
#> GSM486763 5 0.0291 0.2562 0.004 0.000 0.000 0.004 0.992 0.000
#> GSM486765 1 0.5739 0.1782 0.592 0.000 0.028 0.140 0.000 0.240
#> GSM486767 4 0.8189 -0.1640 0.252 0.248 0.032 0.352 0.016 0.100
#> GSM486769 4 0.3509 0.6479 0.012 0.036 0.008 0.844 0.016 0.084
#> GSM486771 4 0.4469 0.6629 0.192 0.072 0.000 0.724 0.004 0.008
#> GSM486773 4 0.4386 0.6972 0.076 0.076 0.004 0.788 0.008 0.048
#> GSM486775 1 0.3573 0.5067 0.816 0.028 0.000 0.120 0.000 0.036
#> GSM486777 1 0.5996 0.2973 0.576 0.020 0.008 0.216 0.000 0.180
#> GSM486779 2 0.6132 0.5601 0.112 0.588 0.000 0.240 0.012 0.048
#> GSM486781 4 0.4155 0.7000 0.100 0.076 0.004 0.792 0.004 0.024
#> GSM486783 4 0.5132 0.6220 0.148 0.152 0.000 0.680 0.004 0.016
#> GSM486785 1 0.7949 -0.3828 0.392 0.108 0.092 0.104 0.000 0.304
#> GSM486787 1 0.3690 0.4987 0.820 0.028 0.000 0.112 0.012 0.028
#> GSM486789 4 0.3395 0.6925 0.048 0.064 0.004 0.852 0.008 0.024
#> GSM486791 1 0.7579 -0.4146 0.412 0.064 0.000 0.048 0.184 0.292
#> GSM486793 1 0.5987 0.1366 0.568 0.012 0.020 0.132 0.000 0.268
#> GSM486795 4 0.5002 0.3181 0.436 0.032 0.004 0.516 0.004 0.008
#> GSM486797 4 0.4551 0.6976 0.136 0.072 0.000 0.748 0.000 0.044
#> GSM486799 1 0.4935 0.2128 0.728 0.060 0.004 0.052 0.004 0.152
#> GSM486801 1 0.3813 0.5004 0.768 0.028 0.000 0.188 0.000 0.016
#> GSM486803 1 0.7163 -0.2888 0.424 0.136 0.016 0.012 0.056 0.356
#> GSM486805 4 0.5123 0.6441 0.192 0.080 0.004 0.688 0.000 0.036
#> GSM486807 4 0.5414 -0.0604 0.424 0.028 0.004 0.500 0.000 0.044
#> GSM486809 4 0.4207 0.6370 0.040 0.036 0.012 0.808 0.016 0.088
#> GSM486811 1 0.5241 0.4099 0.644 0.016 0.004 0.240 0.000 0.096
#> GSM486813 4 0.6819 0.1945 0.236 0.280 0.000 0.428 0.000 0.056
#> GSM486815 6 0.5920 0.6350 0.392 0.024 0.012 0.080 0.000 0.492
#> GSM486817 1 0.6975 0.2160 0.496 0.112 0.000 0.212 0.004 0.176
#> GSM486819 4 0.5442 0.4592 0.364 0.044 0.000 0.552 0.004 0.036
#> GSM486822 4 0.3601 0.6457 0.016 0.036 0.008 0.840 0.016 0.084
#> GSM486824 1 0.6895 0.0905 0.564 0.132 0.012 0.100 0.012 0.180
#> GSM486828 4 0.3626 0.7057 0.088 0.064 0.004 0.824 0.000 0.020
#> GSM486831 1 0.4877 0.4940 0.732 0.040 0.004 0.168 0.016 0.040
#> GSM486833 4 0.6182 0.3196 0.272 0.036 0.008 0.552 0.000 0.132
#> GSM486835 1 0.4984 0.4361 0.744 0.052 0.004 0.100 0.012 0.088
#> GSM486837 4 0.4005 0.6934 0.124 0.068 0.004 0.788 0.000 0.016
#> GSM486839 1 0.3301 0.5088 0.828 0.032 0.000 0.124 0.000 0.016
#> GSM486841 1 0.6024 0.2735 0.592 0.020 0.016 0.172 0.000 0.200
#> GSM486843 1 0.5044 0.4784 0.724 0.048 0.008 0.160 0.008 0.052
#> GSM486845 4 0.3280 0.6986 0.084 0.056 0.004 0.844 0.000 0.012
#> GSM486847 1 0.3993 0.4918 0.800 0.040 0.004 0.108 0.000 0.048
#> GSM486849 4 0.3216 0.6975 0.060 0.068 0.004 0.852 0.000 0.016
#> GSM486851 5 0.7363 0.2218 0.316 0.044 0.000 0.028 0.352 0.260
#> GSM486853 4 0.3709 0.6648 0.036 0.124 0.008 0.812 0.000 0.020
#> GSM486855 4 0.4992 0.6387 0.200 0.124 0.000 0.668 0.004 0.004
#> GSM486857 4 0.4656 0.6275 0.060 0.176 0.012 0.732 0.000 0.020
#> GSM486736 4 0.3595 0.6495 0.020 0.036 0.008 0.840 0.012 0.084
#> GSM486738 4 0.5534 0.5120 0.136 0.240 0.000 0.608 0.004 0.012
#> GSM486740 4 0.4136 0.6794 0.180 0.048 0.000 0.756 0.004 0.012
#> GSM486742 4 0.4259 0.6586 0.096 0.160 0.000 0.740 0.004 0.000
#> GSM486744 4 0.5031 0.6682 0.188 0.116 0.000 0.680 0.012 0.004
#> GSM486746 4 0.4628 0.6486 0.216 0.064 0.000 0.704 0.004 0.012
#> GSM486748 4 0.5998 0.2470 0.344 0.056 0.016 0.536 0.000 0.048
#> GSM486750 4 0.2952 0.6960 0.052 0.068 0.000 0.864 0.000 0.016
#> GSM486752 4 0.5695 0.3526 0.320 0.040 0.008 0.572 0.000 0.060
#> GSM486754 4 0.4732 0.6672 0.104 0.116 0.000 0.744 0.012 0.024
#> GSM486756 4 0.4774 0.6613 0.136 0.116 0.000 0.724 0.004 0.020
#> GSM486758 3 0.0458 0.9838 0.000 0.000 0.984 0.000 0.000 0.016
#> GSM486760 1 0.4471 0.4997 0.744 0.024 0.008 0.188 0.008 0.028
#> GSM486762 1 0.6286 0.2726 0.436 0.032 0.008 0.408 0.000 0.116
#> GSM486764 5 0.0291 0.2562 0.004 0.000 0.000 0.004 0.992 0.000
#> GSM486766 1 0.5703 0.2911 0.616 0.004 0.024 0.156 0.000 0.200
#> GSM486768 4 0.5200 0.6104 0.296 0.048 0.000 0.624 0.012 0.020
#> GSM486770 4 0.3346 0.6509 0.012 0.032 0.008 0.852 0.012 0.084
#> GSM486772 4 0.4401 0.6709 0.176 0.068 0.000 0.740 0.008 0.008
#> GSM486774 4 0.4351 0.6877 0.092 0.068 0.004 0.780 0.000 0.056
#> GSM486776 1 0.4072 0.4929 0.796 0.028 0.008 0.108 0.000 0.060
#> GSM486778 1 0.6017 0.2979 0.572 0.020 0.008 0.220 0.000 0.180
#> GSM486780 2 0.4838 0.4286 0.144 0.732 0.000 0.056 0.004 0.064
#> GSM486782 4 0.3864 0.7027 0.096 0.064 0.004 0.812 0.004 0.020
#> GSM486784 4 0.5099 0.6211 0.148 0.148 0.000 0.684 0.004 0.016
#> GSM486786 6 0.7157 0.2852 0.380 0.100 0.084 0.032 0.000 0.404
#> GSM486788 1 0.3968 0.5125 0.792 0.036 0.000 0.140 0.012 0.020
#> GSM486790 4 0.3263 0.6930 0.040 0.064 0.004 0.860 0.008 0.024
#> GSM486792 1 0.7579 -0.4146 0.412 0.064 0.000 0.048 0.184 0.292
#> GSM486794 1 0.5897 0.1373 0.572 0.008 0.020 0.132 0.000 0.268
#> GSM486796 4 0.5002 0.3197 0.436 0.032 0.004 0.516 0.004 0.008
#> GSM486798 4 0.5523 0.3279 0.324 0.040 0.004 0.584 0.004 0.044
#> GSM486800 1 0.4520 0.4942 0.760 0.028 0.004 0.144 0.008 0.056
#> GSM486802 1 0.4000 0.4996 0.756 0.032 0.000 0.192 0.000 0.020
#> GSM486804 1 0.7050 -0.2279 0.420 0.288 0.000 0.032 0.024 0.236
#> GSM486806 4 0.4959 0.6632 0.152 0.064 0.008 0.724 0.000 0.052
#> GSM486808 1 0.5887 0.3305 0.504 0.012 0.012 0.368 0.000 0.104
#> GSM486810 4 0.3998 0.6396 0.036 0.036 0.012 0.820 0.012 0.084
#> GSM486812 1 0.5238 0.4110 0.648 0.016 0.004 0.232 0.000 0.100
#> GSM486814 4 0.6525 0.3352 0.220 0.252 0.000 0.484 0.000 0.044
#> GSM486816 6 0.5986 0.6356 0.392 0.028 0.012 0.080 0.000 0.488
#> GSM486818 1 0.7613 0.1685 0.468 0.108 0.004 0.188 0.032 0.200
#> GSM486821 4 0.5815 0.4540 0.352 0.060 0.000 0.540 0.012 0.036
#> GSM486823 4 0.3670 0.6466 0.016 0.040 0.008 0.836 0.016 0.084
#> GSM486826 1 0.6595 -0.0161 0.572 0.120 0.020 0.052 0.008 0.228
#> GSM486830 4 0.3617 0.7062 0.092 0.060 0.004 0.824 0.000 0.020
#> GSM486832 1 0.4555 0.4904 0.760 0.044 0.000 0.140 0.016 0.040
#> GSM486834 4 0.6166 0.3236 0.268 0.036 0.008 0.556 0.000 0.132
#> GSM486836 1 0.3818 0.4561 0.812 0.024 0.000 0.088 0.004 0.072
#> GSM486838 4 0.5642 0.5783 0.200 0.116 0.016 0.644 0.000 0.024
#> GSM486840 1 0.3301 0.5088 0.828 0.032 0.000 0.124 0.000 0.016
#> GSM486842 1 0.5841 0.2370 0.600 0.012 0.016 0.156 0.000 0.216
#> GSM486844 1 0.5669 0.4208 0.668 0.088 0.008 0.172 0.004 0.060
#> GSM486846 4 0.3280 0.6986 0.084 0.056 0.004 0.844 0.000 0.012
#> GSM486848 1 0.4025 0.4312 0.812 0.036 0.008 0.076 0.004 0.064
#> GSM486850 4 0.3216 0.6975 0.060 0.068 0.004 0.852 0.000 0.016
#> GSM486852 5 0.7363 0.2218 0.316 0.044 0.000 0.028 0.352 0.260
#> GSM486854 4 0.3785 0.6601 0.036 0.140 0.008 0.800 0.000 0.016
#> GSM486856 4 0.5178 0.6218 0.212 0.136 0.000 0.644 0.004 0.004
#> GSM486858 4 0.5089 0.5963 0.056 0.200 0.016 0.696 0.000 0.032
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> CV:hclust 116 1.000 6.52e-06 2
#> CV:hclust 70 1.000 4.01e-04 3
#> CV:hclust 96 0.996 3.34e-11 4
#> CV:hclust 86 1.000 5.88e-13 5
#> CV:hclust 61 0.878 1.09e-08 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["CV", "kmeans"]
# you can also extract it by
# res = res_list["CV:kmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'CV' method.
#> Subgroups are detected by 'kmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.505 0.858 0.910 0.4961 0.498 0.498
#> 3 3 0.473 0.574 0.768 0.2492 0.961 0.923
#> 4 4 0.489 0.361 0.671 0.1346 0.830 0.637
#> 5 5 0.513 0.504 0.694 0.0764 0.878 0.634
#> 6 6 0.558 0.508 0.677 0.0464 0.913 0.663
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 2 0.0000 0.897 0.000 1.000
#> GSM486737 2 0.6712 0.847 0.176 0.824
#> GSM486739 2 0.6801 0.845 0.180 0.820
#> GSM486741 2 0.0376 0.896 0.004 0.996
#> GSM486743 2 0.6801 0.845 0.180 0.820
#> GSM486745 2 0.6973 0.839 0.188 0.812
#> GSM486747 1 0.7453 0.829 0.788 0.212
#> GSM486749 2 0.0000 0.897 0.000 1.000
#> GSM486751 2 0.2778 0.864 0.048 0.952
#> GSM486753 2 0.6712 0.847 0.176 0.824
#> GSM486755 2 0.6712 0.847 0.176 0.824
#> GSM486757 2 0.9686 0.135 0.396 0.604
#> GSM486759 1 0.1184 0.896 0.984 0.016
#> GSM486761 1 0.7139 0.841 0.804 0.196
#> GSM486763 1 0.1633 0.884 0.976 0.024
#> GSM486765 1 0.7056 0.844 0.808 0.192
#> GSM486767 2 0.7376 0.822 0.208 0.792
#> GSM486769 2 0.0000 0.897 0.000 1.000
#> GSM486771 2 0.6712 0.847 0.176 0.824
#> GSM486773 2 0.0000 0.897 0.000 1.000
#> GSM486775 1 0.1184 0.896 0.984 0.016
#> GSM486777 1 0.7056 0.844 0.808 0.192
#> GSM486779 2 0.6887 0.842 0.184 0.816
#> GSM486781 2 0.0000 0.897 0.000 1.000
#> GSM486783 2 0.6712 0.847 0.176 0.824
#> GSM486785 1 0.7056 0.844 0.808 0.192
#> GSM486787 1 0.1184 0.896 0.984 0.016
#> GSM486789 2 0.0000 0.897 0.000 1.000
#> GSM486791 1 0.0376 0.890 0.996 0.004
#> GSM486793 1 0.7056 0.844 0.808 0.192
#> GSM486795 1 0.6438 0.754 0.836 0.164
#> GSM486797 2 0.0000 0.897 0.000 1.000
#> GSM486799 1 0.1184 0.896 0.984 0.016
#> GSM486801 1 0.1184 0.896 0.984 0.016
#> GSM486803 1 0.1184 0.896 0.984 0.016
#> GSM486805 2 0.0000 0.897 0.000 1.000
#> GSM486807 1 0.7056 0.844 0.808 0.192
#> GSM486809 2 0.0376 0.895 0.004 0.996
#> GSM486811 1 0.7056 0.844 0.808 0.192
#> GSM486813 2 0.7453 0.818 0.212 0.788
#> GSM486815 1 0.6973 0.843 0.812 0.188
#> GSM486817 2 0.8661 0.727 0.288 0.712
#> GSM486819 1 0.8386 0.559 0.732 0.268
#> GSM486822 2 0.0000 0.897 0.000 1.000
#> GSM486824 1 0.1184 0.896 0.984 0.016
#> GSM486828 2 0.0000 0.897 0.000 1.000
#> GSM486831 1 0.1184 0.896 0.984 0.016
#> GSM486833 2 0.3733 0.843 0.072 0.928
#> GSM486835 1 0.1184 0.896 0.984 0.016
#> GSM486837 2 0.0000 0.897 0.000 1.000
#> GSM486839 1 0.1184 0.896 0.984 0.016
#> GSM486841 1 0.7056 0.844 0.808 0.192
#> GSM486843 1 0.1184 0.896 0.984 0.016
#> GSM486845 2 0.0000 0.897 0.000 1.000
#> GSM486847 1 0.1184 0.896 0.984 0.016
#> GSM486849 2 0.0000 0.897 0.000 1.000
#> GSM486851 1 0.0376 0.890 0.996 0.004
#> GSM486853 2 0.0000 0.897 0.000 1.000
#> GSM486855 2 0.6712 0.847 0.176 0.824
#> GSM486857 2 0.0000 0.897 0.000 1.000
#> GSM486736 2 0.0000 0.897 0.000 1.000
#> GSM486738 2 0.6712 0.847 0.176 0.824
#> GSM486740 2 0.6801 0.845 0.180 0.820
#> GSM486742 2 0.0376 0.896 0.004 0.996
#> GSM486744 2 0.6712 0.847 0.176 0.824
#> GSM486746 2 0.6887 0.842 0.184 0.816
#> GSM486748 1 0.8499 0.762 0.724 0.276
#> GSM486750 2 0.0000 0.897 0.000 1.000
#> GSM486752 2 0.6343 0.731 0.160 0.840
#> GSM486754 2 0.6712 0.847 0.176 0.824
#> GSM486756 2 0.6712 0.847 0.176 0.824
#> GSM486758 1 0.7299 0.833 0.796 0.204
#> GSM486760 1 0.1184 0.896 0.984 0.016
#> GSM486762 1 0.7219 0.839 0.800 0.200
#> GSM486764 1 0.1184 0.888 0.984 0.016
#> GSM486766 1 0.7056 0.844 0.808 0.192
#> GSM486768 2 0.6887 0.842 0.184 0.816
#> GSM486770 2 0.0000 0.897 0.000 1.000
#> GSM486772 2 0.6712 0.847 0.176 0.824
#> GSM486774 2 0.0000 0.897 0.000 1.000
#> GSM486776 1 0.1184 0.896 0.984 0.016
#> GSM486778 1 0.7056 0.844 0.808 0.192
#> GSM486780 2 0.7139 0.833 0.196 0.804
#> GSM486782 2 0.0000 0.897 0.000 1.000
#> GSM486784 2 0.6712 0.847 0.176 0.824
#> GSM486786 1 0.7056 0.844 0.808 0.192
#> GSM486788 1 0.1184 0.896 0.984 0.016
#> GSM486790 2 0.0000 0.897 0.000 1.000
#> GSM486792 1 0.0376 0.890 0.996 0.004
#> GSM486794 1 0.7056 0.844 0.808 0.192
#> GSM486796 1 0.1843 0.890 0.972 0.028
#> GSM486798 2 0.0672 0.893 0.008 0.992
#> GSM486800 1 0.1184 0.896 0.984 0.016
#> GSM486802 1 0.1184 0.896 0.984 0.016
#> GSM486804 1 0.1184 0.896 0.984 0.016
#> GSM486806 2 0.0000 0.897 0.000 1.000
#> GSM486808 1 0.7056 0.844 0.808 0.192
#> GSM486810 2 0.0000 0.897 0.000 1.000
#> GSM486812 1 0.7056 0.844 0.808 0.192
#> GSM486814 2 0.6801 0.845 0.180 0.820
#> GSM486816 1 0.6973 0.843 0.812 0.188
#> GSM486818 1 0.6801 0.731 0.820 0.180
#> GSM486821 1 0.7602 0.665 0.780 0.220
#> GSM486823 2 0.0000 0.897 0.000 1.000
#> GSM486826 1 0.1184 0.896 0.984 0.016
#> GSM486830 2 0.0000 0.897 0.000 1.000
#> GSM486832 1 0.1184 0.896 0.984 0.016
#> GSM486834 2 0.2603 0.867 0.044 0.956
#> GSM486836 1 0.1184 0.896 0.984 0.016
#> GSM486838 2 0.0000 0.897 0.000 1.000
#> GSM486840 1 0.1184 0.896 0.984 0.016
#> GSM486842 1 0.7056 0.844 0.808 0.192
#> GSM486844 1 0.1184 0.896 0.984 0.016
#> GSM486846 2 0.0000 0.897 0.000 1.000
#> GSM486848 1 0.1184 0.896 0.984 0.016
#> GSM486850 2 0.0000 0.897 0.000 1.000
#> GSM486852 1 0.0376 0.890 0.996 0.004
#> GSM486854 2 0.0000 0.897 0.000 1.000
#> GSM486856 2 0.6712 0.847 0.176 0.824
#> GSM486858 2 0.0000 0.897 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 2 0.5591 0.7305 0.304 0.696 0.000
#> GSM486737 2 0.3921 0.7021 0.036 0.884 0.080
#> GSM486739 2 0.6266 0.6615 0.156 0.768 0.076
#> GSM486741 2 0.3038 0.7593 0.104 0.896 0.000
#> GSM486743 2 0.4217 0.6906 0.032 0.868 0.100
#> GSM486745 2 0.6910 0.6166 0.144 0.736 0.120
#> GSM486747 3 0.7292 0.0798 0.472 0.028 0.500
#> GSM486749 2 0.5098 0.7622 0.248 0.752 0.000
#> GSM486751 2 0.8330 0.5371 0.356 0.552 0.092
#> GSM486753 2 0.3889 0.7062 0.032 0.884 0.084
#> GSM486755 2 0.4544 0.6973 0.056 0.860 0.084
#> GSM486757 1 0.5810 0.4364 0.796 0.072 0.132
#> GSM486759 3 0.0237 0.6635 0.000 0.004 0.996
#> GSM486761 3 0.6600 0.3092 0.384 0.012 0.604
#> GSM486763 1 0.8949 0.3691 0.532 0.148 0.320
#> GSM486765 3 0.5988 0.4681 0.304 0.008 0.688
#> GSM486767 2 0.8163 0.3918 0.248 0.628 0.124
#> GSM486769 2 0.5591 0.7305 0.304 0.696 0.000
#> GSM486771 2 0.4007 0.6989 0.036 0.880 0.084
#> GSM486773 2 0.5058 0.7637 0.244 0.756 0.000
#> GSM486775 3 0.0747 0.6639 0.016 0.000 0.984
#> GSM486777 3 0.5461 0.5331 0.244 0.008 0.748
#> GSM486779 2 0.7510 0.4966 0.184 0.692 0.124
#> GSM486781 2 0.5016 0.7606 0.240 0.760 0.000
#> GSM486783 2 0.3637 0.7042 0.024 0.892 0.084
#> GSM486785 3 0.6625 0.2062 0.440 0.008 0.552
#> GSM486787 3 0.0000 0.6645 0.000 0.000 1.000
#> GSM486789 2 0.4750 0.7685 0.216 0.784 0.000
#> GSM486791 3 0.4834 0.4719 0.204 0.004 0.792
#> GSM486793 3 0.6047 0.4635 0.312 0.008 0.680
#> GSM486795 3 0.5219 0.4065 0.016 0.196 0.788
#> GSM486797 2 0.5497 0.7286 0.292 0.708 0.000
#> GSM486799 3 0.0237 0.6650 0.004 0.000 0.996
#> GSM486801 3 0.0237 0.6639 0.004 0.000 0.996
#> GSM486803 3 0.5254 0.3378 0.264 0.000 0.736
#> GSM486805 2 0.5623 0.7426 0.280 0.716 0.004
#> GSM486807 3 0.5797 0.4923 0.280 0.008 0.712
#> GSM486809 2 0.5706 0.7252 0.320 0.680 0.000
#> GSM486811 3 0.5292 0.5450 0.228 0.008 0.764
#> GSM486813 2 0.6975 0.5416 0.144 0.732 0.124
#> GSM486815 1 0.6672 -0.1707 0.520 0.008 0.472
#> GSM486817 2 0.9387 0.0760 0.272 0.508 0.220
#> GSM486819 3 0.7835 0.1294 0.112 0.232 0.656
#> GSM486822 2 0.5138 0.7562 0.252 0.748 0.000
#> GSM486824 3 0.4784 0.4464 0.200 0.004 0.796
#> GSM486828 2 0.4931 0.7637 0.232 0.768 0.000
#> GSM486831 3 0.0424 0.6624 0.008 0.000 0.992
#> GSM486833 2 0.7672 0.4689 0.468 0.488 0.044
#> GSM486835 3 0.0592 0.6607 0.012 0.000 0.988
#> GSM486837 2 0.5363 0.7411 0.276 0.724 0.000
#> GSM486839 3 0.0237 0.6650 0.004 0.000 0.996
#> GSM486841 3 0.5461 0.5280 0.244 0.008 0.748
#> GSM486843 3 0.1031 0.6539 0.024 0.000 0.976
#> GSM486845 2 0.4654 0.7658 0.208 0.792 0.000
#> GSM486847 3 0.0424 0.6650 0.008 0.000 0.992
#> GSM486849 2 0.4452 0.7688 0.192 0.808 0.000
#> GSM486851 3 0.6834 0.2866 0.260 0.048 0.692
#> GSM486853 2 0.4555 0.7668 0.200 0.800 0.000
#> GSM486855 2 0.3043 0.7085 0.008 0.908 0.084
#> GSM486857 2 0.5529 0.7366 0.296 0.704 0.000
#> GSM486736 2 0.5591 0.7305 0.304 0.696 0.000
#> GSM486738 2 0.3889 0.6990 0.032 0.884 0.084
#> GSM486740 2 0.6266 0.6615 0.156 0.768 0.076
#> GSM486742 2 0.2625 0.7581 0.084 0.916 0.000
#> GSM486744 2 0.3637 0.7059 0.024 0.892 0.084
#> GSM486746 2 0.7256 0.6285 0.164 0.712 0.124
#> GSM486748 3 0.8173 0.0649 0.420 0.072 0.508
#> GSM486750 2 0.5016 0.7625 0.240 0.760 0.000
#> GSM486752 2 0.9574 0.2046 0.392 0.412 0.196
#> GSM486754 2 0.3889 0.7062 0.032 0.884 0.084
#> GSM486756 2 0.4339 0.7006 0.048 0.868 0.084
#> GSM486758 1 0.5384 0.4239 0.788 0.024 0.188
#> GSM486760 3 0.0237 0.6639 0.004 0.000 0.996
#> GSM486762 3 0.6962 0.2273 0.412 0.020 0.568
#> GSM486764 1 0.8841 0.3581 0.528 0.132 0.340
#> GSM486766 3 0.5692 0.5050 0.268 0.008 0.724
#> GSM486768 2 0.4662 0.6801 0.032 0.844 0.124
#> GSM486770 2 0.5591 0.7305 0.304 0.696 0.000
#> GSM486772 2 0.3889 0.7041 0.032 0.884 0.084
#> GSM486774 2 0.5138 0.7587 0.252 0.748 0.000
#> GSM486776 3 0.0747 0.6639 0.016 0.000 0.984
#> GSM486778 3 0.5420 0.5354 0.240 0.008 0.752
#> GSM486780 2 0.8129 0.3642 0.244 0.632 0.124
#> GSM486782 2 0.5016 0.7606 0.240 0.760 0.000
#> GSM486784 2 0.3502 0.7054 0.020 0.896 0.084
#> GSM486786 3 0.6683 0.0402 0.496 0.008 0.496
#> GSM486788 3 0.0237 0.6639 0.004 0.000 0.996
#> GSM486790 2 0.4062 0.7698 0.164 0.836 0.000
#> GSM486792 3 0.4605 0.4768 0.204 0.000 0.796
#> GSM486794 3 0.5896 0.4863 0.292 0.008 0.700
#> GSM486796 3 0.3129 0.5837 0.008 0.088 0.904
#> GSM486798 2 0.5397 0.7415 0.280 0.720 0.000
#> GSM486800 3 0.0000 0.6645 0.000 0.000 1.000
#> GSM486802 3 0.0237 0.6639 0.004 0.000 0.996
#> GSM486804 3 0.5070 0.4059 0.224 0.004 0.772
#> GSM486806 2 0.5397 0.7419 0.280 0.720 0.000
#> GSM486808 3 0.5692 0.5047 0.268 0.008 0.724
#> GSM486810 2 0.5650 0.7262 0.312 0.688 0.000
#> GSM486812 3 0.5292 0.5450 0.228 0.008 0.764
#> GSM486814 2 0.4708 0.6684 0.036 0.844 0.120
#> GSM486816 3 0.6664 0.1433 0.464 0.008 0.528
#> GSM486818 3 0.9783 -0.3259 0.300 0.264 0.436
#> GSM486821 3 0.8033 0.1052 0.120 0.240 0.640
#> GSM486823 2 0.5098 0.7568 0.248 0.752 0.000
#> GSM486826 3 0.5024 0.4201 0.220 0.004 0.776
#> GSM486830 2 0.4796 0.7646 0.220 0.780 0.000
#> GSM486832 3 0.0237 0.6635 0.004 0.000 0.996
#> GSM486834 2 0.6777 0.6421 0.364 0.616 0.020
#> GSM486836 3 0.0000 0.6645 0.000 0.000 1.000
#> GSM486838 2 0.5775 0.7394 0.260 0.728 0.012
#> GSM486840 3 0.0237 0.6650 0.004 0.000 0.996
#> GSM486842 3 0.5335 0.5386 0.232 0.008 0.760
#> GSM486844 3 0.2918 0.6224 0.044 0.032 0.924
#> GSM486846 2 0.4605 0.7662 0.204 0.796 0.000
#> GSM486848 3 0.0237 0.6650 0.004 0.000 0.996
#> GSM486850 2 0.4452 0.7680 0.192 0.808 0.000
#> GSM486852 3 0.7283 0.2520 0.260 0.068 0.672
#> GSM486854 2 0.4842 0.7616 0.224 0.776 0.000
#> GSM486856 2 0.3769 0.6943 0.016 0.880 0.104
#> GSM486858 2 0.5178 0.7552 0.256 0.744 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 2 0.5511 0.404433 0.032 0.636 0.000 0.332
#> GSM486737 4 0.6225 0.449641 0.008 0.456 0.036 0.500
#> GSM486739 4 0.6538 0.184856 0.052 0.396 0.012 0.540
#> GSM486741 2 0.4897 0.105672 0.000 0.660 0.008 0.332
#> GSM486743 4 0.6242 0.456110 0.004 0.456 0.044 0.496
#> GSM486745 4 0.7290 0.289313 0.040 0.332 0.072 0.556
#> GSM486747 1 0.7529 0.614978 0.508 0.164 0.320 0.008
#> GSM486749 2 0.3743 0.561004 0.016 0.824 0.000 0.160
#> GSM486751 2 0.6385 0.382425 0.224 0.676 0.076 0.024
#> GSM486753 4 0.6268 0.395723 0.012 0.476 0.032 0.480
#> GSM486755 4 0.6426 0.470639 0.020 0.424 0.032 0.524
#> GSM486757 1 0.5499 0.524358 0.756 0.156 0.020 0.068
#> GSM486759 3 0.0469 0.622261 0.012 0.000 0.988 0.000
#> GSM486761 1 0.7497 0.553562 0.444 0.156 0.396 0.004
#> GSM486763 4 0.7369 -0.094427 0.408 0.000 0.160 0.432
#> GSM486765 3 0.5897 -0.335914 0.468 0.020 0.504 0.008
#> GSM486767 4 0.8417 0.430415 0.156 0.332 0.052 0.460
#> GSM486769 2 0.5492 0.406414 0.032 0.640 0.000 0.328
#> GSM486771 4 0.6090 0.460980 0.004 0.448 0.036 0.512
#> GSM486773 2 0.2500 0.594894 0.040 0.916 0.000 0.044
#> GSM486775 3 0.1356 0.614698 0.032 0.000 0.960 0.008
#> GSM486777 3 0.5349 0.031655 0.336 0.024 0.640 0.000
#> GSM486779 4 0.8480 0.435859 0.160 0.300 0.060 0.480
#> GSM486781 2 0.1624 0.601326 0.028 0.952 0.000 0.020
#> GSM486783 4 0.5938 0.424309 0.000 0.480 0.036 0.484
#> GSM486785 1 0.6212 0.561405 0.620 0.024 0.324 0.032
#> GSM486787 3 0.1488 0.616847 0.032 0.000 0.956 0.012
#> GSM486789 2 0.4212 0.501731 0.012 0.772 0.000 0.216
#> GSM486791 3 0.7110 0.282067 0.236 0.000 0.564 0.200
#> GSM486793 3 0.6014 -0.371361 0.484 0.020 0.484 0.012
#> GSM486795 3 0.4327 0.485115 0.016 0.020 0.812 0.152
#> GSM486797 2 0.4057 0.547065 0.120 0.836 0.008 0.036
#> GSM486799 3 0.1284 0.619095 0.024 0.000 0.964 0.012
#> GSM486801 3 0.0336 0.621950 0.000 0.000 0.992 0.008
#> GSM486803 3 0.6516 0.249654 0.308 0.000 0.592 0.100
#> GSM486805 2 0.3575 0.572751 0.092 0.868 0.012 0.028
#> GSM486807 3 0.5735 -0.162511 0.392 0.032 0.576 0.000
#> GSM486809 2 0.5717 0.405913 0.044 0.632 0.000 0.324
#> GSM486811 3 0.5184 0.120724 0.304 0.024 0.672 0.000
#> GSM486813 4 0.7775 0.477532 0.076 0.360 0.060 0.504
#> GSM486815 1 0.5664 0.581499 0.688 0.016 0.264 0.032
#> GSM486817 4 0.9669 0.315761 0.276 0.176 0.184 0.364
#> GSM486819 3 0.7643 0.292726 0.064 0.120 0.608 0.208
#> GSM486822 2 0.4434 0.508182 0.016 0.756 0.000 0.228
#> GSM486824 3 0.5787 0.354775 0.244 0.000 0.680 0.076
#> GSM486828 2 0.2385 0.599815 0.028 0.920 0.000 0.052
#> GSM486831 3 0.0804 0.619019 0.008 0.000 0.980 0.012
#> GSM486833 2 0.6389 0.146118 0.400 0.548 0.028 0.024
#> GSM486835 3 0.0779 0.621677 0.016 0.000 0.980 0.004
#> GSM486837 2 0.3370 0.574748 0.080 0.872 0.000 0.048
#> GSM486839 3 0.0927 0.621123 0.016 0.000 0.976 0.008
#> GSM486841 3 0.5349 0.031026 0.336 0.024 0.640 0.000
#> GSM486843 3 0.2385 0.594461 0.052 0.000 0.920 0.028
#> GSM486845 2 0.2266 0.574421 0.004 0.912 0.000 0.084
#> GSM486847 3 0.0895 0.620301 0.020 0.000 0.976 0.004
#> GSM486849 2 0.2944 0.553308 0.004 0.868 0.000 0.128
#> GSM486851 3 0.7557 0.212720 0.260 0.000 0.488 0.252
#> GSM486853 2 0.2773 0.543874 0.004 0.880 0.000 0.116
#> GSM486855 2 0.5928 -0.424279 0.000 0.508 0.036 0.456
#> GSM486857 2 0.4525 0.527270 0.080 0.804 0.000 0.116
#> GSM486736 2 0.5530 0.399320 0.032 0.632 0.000 0.336
#> GSM486738 4 0.6229 0.450348 0.008 0.464 0.036 0.492
#> GSM486740 4 0.6310 0.160474 0.052 0.404 0.004 0.540
#> GSM486742 2 0.4917 0.061608 0.000 0.656 0.008 0.336
#> GSM486744 2 0.5858 -0.439650 0.000 0.500 0.032 0.468
#> GSM486746 4 0.7744 0.191382 0.052 0.380 0.080 0.488
#> GSM486748 1 0.7826 0.538447 0.400 0.212 0.384 0.004
#> GSM486750 2 0.3764 0.554683 0.012 0.816 0.000 0.172
#> GSM486752 2 0.7230 0.000224 0.272 0.556 0.168 0.004
#> GSM486754 2 0.6156 -0.426567 0.008 0.484 0.032 0.476
#> GSM486756 4 0.6442 0.460259 0.020 0.436 0.032 0.512
#> GSM486758 1 0.5603 0.551090 0.772 0.108 0.052 0.068
#> GSM486760 3 0.0000 0.621388 0.000 0.000 1.000 0.000
#> GSM486762 1 0.7557 0.551590 0.432 0.164 0.400 0.004
#> GSM486764 4 0.7371 -0.102596 0.416 0.000 0.160 0.424
#> GSM486766 3 0.5508 -0.165431 0.408 0.020 0.572 0.000
#> GSM486768 2 0.6306 -0.398136 0.000 0.544 0.064 0.392
#> GSM486770 2 0.5511 0.401839 0.032 0.636 0.000 0.332
#> GSM486772 4 0.5931 0.416182 0.000 0.460 0.036 0.504
#> GSM486774 2 0.2021 0.599606 0.040 0.936 0.000 0.024
#> GSM486776 3 0.1256 0.616868 0.028 0.000 0.964 0.008
#> GSM486778 3 0.5228 0.093547 0.312 0.024 0.664 0.000
#> GSM486780 4 0.8373 0.428235 0.212 0.236 0.048 0.504
#> GSM486782 2 0.1284 0.601507 0.024 0.964 0.000 0.012
#> GSM486784 2 0.5933 -0.435608 0.000 0.500 0.036 0.464
#> GSM486786 1 0.6066 0.571686 0.652 0.016 0.288 0.044
#> GSM486788 3 0.0804 0.622448 0.008 0.000 0.980 0.012
#> GSM486790 2 0.4663 0.406197 0.012 0.716 0.000 0.272
#> GSM486792 3 0.7110 0.282067 0.236 0.000 0.564 0.200
#> GSM486794 3 0.5895 -0.317846 0.464 0.020 0.508 0.008
#> GSM486796 3 0.2101 0.593751 0.012 0.000 0.928 0.060
#> GSM486798 2 0.2915 0.580437 0.088 0.892 0.004 0.016
#> GSM486800 3 0.0000 0.621388 0.000 0.000 1.000 0.000
#> GSM486802 3 0.0188 0.621455 0.000 0.000 0.996 0.004
#> GSM486804 3 0.6194 0.274651 0.288 0.000 0.628 0.084
#> GSM486806 2 0.2596 0.592272 0.068 0.908 0.000 0.024
#> GSM486808 3 0.5835 -0.133042 0.372 0.040 0.588 0.000
#> GSM486810 2 0.5636 0.419821 0.044 0.648 0.000 0.308
#> GSM486812 3 0.5161 0.129910 0.300 0.024 0.676 0.000
#> GSM486814 4 0.6311 0.455188 0.004 0.456 0.048 0.492
#> GSM486816 1 0.5833 0.558693 0.636 0.016 0.324 0.024
#> GSM486818 3 0.9466 -0.051964 0.312 0.120 0.360 0.208
#> GSM486821 3 0.7749 0.280201 0.064 0.124 0.596 0.216
#> GSM486823 2 0.4364 0.514960 0.016 0.764 0.000 0.220
#> GSM486826 3 0.5907 0.333308 0.252 0.000 0.668 0.080
#> GSM486830 2 0.1767 0.599690 0.012 0.944 0.000 0.044
#> GSM486832 3 0.1059 0.618035 0.012 0.000 0.972 0.016
#> GSM486834 2 0.4709 0.479625 0.200 0.768 0.008 0.024
#> GSM486836 3 0.0672 0.622241 0.008 0.000 0.984 0.008
#> GSM486838 2 0.3658 0.565100 0.064 0.864 0.004 0.068
#> GSM486840 3 0.0927 0.621123 0.016 0.000 0.976 0.008
#> GSM486842 3 0.5386 0.008611 0.344 0.024 0.632 0.000
#> GSM486844 3 0.3587 0.566353 0.056 0.016 0.876 0.052
#> GSM486846 2 0.2593 0.562079 0.004 0.892 0.000 0.104
#> GSM486848 3 0.0779 0.620929 0.016 0.000 0.980 0.004
#> GSM486850 2 0.2589 0.557416 0.000 0.884 0.000 0.116
#> GSM486852 3 0.7644 0.192424 0.260 0.000 0.468 0.272
#> GSM486854 2 0.2805 0.547234 0.012 0.888 0.000 0.100
#> GSM486856 2 0.6204 -0.442712 0.000 0.500 0.052 0.448
#> GSM486858 2 0.3821 0.533254 0.040 0.840 0.000 0.120
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 4 0.6048 0.2573 0.000 0.116 0.004 0.536 0.344
#> GSM486737 2 0.3639 0.7932 0.008 0.808 0.000 0.164 0.020
#> GSM486739 5 0.7021 0.1517 0.008 0.296 0.000 0.312 0.384
#> GSM486741 2 0.4218 0.5790 0.000 0.660 0.000 0.332 0.008
#> GSM486743 2 0.4118 0.7983 0.012 0.780 0.000 0.176 0.032
#> GSM486745 2 0.7459 -0.1018 0.036 0.388 0.000 0.256 0.320
#> GSM486747 3 0.6309 0.6450 0.144 0.000 0.588 0.248 0.020
#> GSM486749 4 0.4985 0.5806 0.000 0.124 0.016 0.740 0.120
#> GSM486751 4 0.5624 0.4476 0.052 0.024 0.212 0.692 0.020
#> GSM486753 2 0.4822 0.7317 0.008 0.720 0.004 0.220 0.048
#> GSM486755 2 0.3768 0.7909 0.008 0.812 0.000 0.144 0.036
#> GSM486757 3 0.5041 0.4712 0.000 0.032 0.744 0.080 0.144
#> GSM486759 1 0.0960 0.7113 0.972 0.008 0.004 0.000 0.016
#> GSM486761 3 0.6480 0.6449 0.196 0.000 0.552 0.240 0.012
#> GSM486763 5 0.6941 0.3674 0.068 0.144 0.168 0.012 0.608
#> GSM486765 3 0.4726 0.6570 0.280 0.000 0.684 0.016 0.020
#> GSM486767 2 0.6617 0.5606 0.016 0.636 0.072 0.196 0.080
#> GSM486769 4 0.6020 0.2595 0.000 0.112 0.004 0.536 0.348
#> GSM486771 2 0.3863 0.7915 0.012 0.792 0.000 0.176 0.020
#> GSM486773 4 0.4038 0.6310 0.000 0.132 0.032 0.808 0.028
#> GSM486775 1 0.2011 0.6789 0.908 0.004 0.088 0.000 0.000
#> GSM486777 1 0.5569 -0.2538 0.496 0.000 0.452 0.028 0.024
#> GSM486779 2 0.5219 0.5757 0.024 0.768 0.056 0.056 0.096
#> GSM486781 4 0.3007 0.6373 0.000 0.104 0.028 0.864 0.004
#> GSM486783 2 0.3597 0.7902 0.012 0.800 0.000 0.180 0.008
#> GSM486785 3 0.6493 0.6220 0.212 0.060 0.644 0.032 0.052
#> GSM486787 1 0.1202 0.7066 0.960 0.004 0.032 0.000 0.004
#> GSM486789 4 0.6080 0.4366 0.000 0.204 0.004 0.592 0.200
#> GSM486791 1 0.5797 0.0729 0.512 0.000 0.080 0.004 0.404
#> GSM486793 3 0.4613 0.6568 0.276 0.000 0.692 0.016 0.016
#> GSM486795 1 0.4653 0.5659 0.764 0.168 0.012 0.012 0.044
#> GSM486797 4 0.4342 0.6097 0.000 0.092 0.116 0.784 0.008
#> GSM486799 1 0.1106 0.7070 0.964 0.000 0.024 0.000 0.012
#> GSM486801 1 0.1356 0.7087 0.956 0.004 0.012 0.000 0.028
#> GSM486803 1 0.7046 0.3746 0.572 0.088 0.188 0.000 0.152
#> GSM486805 4 0.3586 0.6297 0.004 0.052 0.092 0.844 0.008
#> GSM486807 3 0.5718 0.4781 0.420 0.000 0.496 0.084 0.000
#> GSM486809 4 0.6103 0.2521 0.000 0.108 0.008 0.532 0.352
#> GSM486811 1 0.5363 -0.1144 0.548 0.000 0.408 0.020 0.024
#> GSM486813 2 0.3861 0.7436 0.012 0.836 0.020 0.100 0.032
#> GSM486815 3 0.4572 0.6428 0.132 0.004 0.772 0.008 0.084
#> GSM486817 2 0.8567 0.0925 0.176 0.488 0.144 0.072 0.120
#> GSM486819 1 0.7128 0.1828 0.568 0.076 0.008 0.120 0.228
#> GSM486822 4 0.5663 0.4148 0.000 0.116 0.004 0.628 0.252
#> GSM486824 1 0.6277 0.4826 0.660 0.092 0.136 0.000 0.112
#> GSM486828 4 0.3584 0.6293 0.000 0.148 0.012 0.820 0.020
#> GSM486831 1 0.0968 0.7081 0.972 0.000 0.012 0.004 0.012
#> GSM486833 4 0.5877 0.0705 0.012 0.044 0.400 0.532 0.012
#> GSM486835 1 0.0566 0.7108 0.984 0.004 0.000 0.000 0.012
#> GSM486837 4 0.4169 0.6236 0.000 0.116 0.072 0.800 0.012
#> GSM486839 1 0.1243 0.7074 0.960 0.004 0.028 0.000 0.008
#> GSM486841 1 0.5076 -0.1932 0.528 0.000 0.444 0.016 0.012
#> GSM486843 1 0.2180 0.6883 0.924 0.032 0.024 0.000 0.020
#> GSM486845 4 0.4260 0.5737 0.000 0.236 0.012 0.736 0.016
#> GSM486847 1 0.1365 0.7032 0.952 0.004 0.040 0.000 0.004
#> GSM486849 4 0.4996 0.4933 0.000 0.304 0.012 0.652 0.032
#> GSM486851 5 0.5883 0.0435 0.420 0.012 0.068 0.000 0.500
#> GSM486853 4 0.4588 0.4880 0.000 0.308 0.012 0.668 0.012
#> GSM486855 2 0.3981 0.7772 0.012 0.764 0.000 0.212 0.012
#> GSM486857 4 0.5033 0.5536 0.000 0.236 0.064 0.692 0.008
#> GSM486736 4 0.6058 0.2523 0.000 0.116 0.004 0.532 0.348
#> GSM486738 2 0.3167 0.7961 0.008 0.836 0.000 0.148 0.008
#> GSM486740 5 0.7014 0.1320 0.008 0.284 0.000 0.324 0.384
#> GSM486742 2 0.4084 0.5776 0.000 0.668 0.000 0.328 0.004
#> GSM486744 2 0.4145 0.7901 0.012 0.772 0.000 0.188 0.028
#> GSM486746 5 0.8051 0.1744 0.088 0.264 0.000 0.320 0.328
#> GSM486748 3 0.6867 0.5627 0.184 0.004 0.476 0.324 0.012
#> GSM486750 4 0.4702 0.5840 0.000 0.116 0.012 0.760 0.112
#> GSM486752 4 0.6185 0.2065 0.080 0.012 0.284 0.604 0.020
#> GSM486754 2 0.4754 0.7254 0.008 0.712 0.000 0.232 0.048
#> GSM486756 2 0.3853 0.7909 0.008 0.804 0.000 0.152 0.036
#> GSM486758 3 0.5081 0.4622 0.000 0.032 0.740 0.080 0.148
#> GSM486760 1 0.0727 0.7103 0.980 0.004 0.004 0.000 0.012
#> GSM486762 3 0.6586 0.6280 0.192 0.000 0.528 0.268 0.012
#> GSM486764 5 0.6874 0.3650 0.068 0.148 0.168 0.008 0.608
#> GSM486766 3 0.4734 0.5938 0.344 0.000 0.632 0.016 0.008
#> GSM486768 2 0.5031 0.7386 0.024 0.692 0.000 0.248 0.036
#> GSM486770 4 0.6020 0.2595 0.000 0.112 0.004 0.536 0.348
#> GSM486772 2 0.4173 0.7719 0.008 0.760 0.000 0.204 0.028
#> GSM486774 4 0.3507 0.6371 0.000 0.104 0.036 0.844 0.016
#> GSM486776 1 0.1928 0.6863 0.920 0.004 0.072 0.000 0.004
#> GSM486778 1 0.5537 -0.1480 0.528 0.000 0.420 0.028 0.024
#> GSM486780 2 0.4717 0.5886 0.012 0.796 0.068 0.048 0.076
#> GSM486782 4 0.2856 0.6394 0.000 0.104 0.016 0.872 0.008
#> GSM486784 2 0.3670 0.7874 0.012 0.792 0.000 0.188 0.008
#> GSM486786 3 0.5683 0.6287 0.128 0.060 0.724 0.012 0.076
#> GSM486788 1 0.0889 0.7096 0.976 0.004 0.004 0.004 0.012
#> GSM486790 4 0.6479 0.2832 0.000 0.288 0.004 0.512 0.196
#> GSM486792 1 0.5797 0.0729 0.512 0.000 0.080 0.004 0.404
#> GSM486794 3 0.4658 0.6518 0.284 0.000 0.684 0.016 0.016
#> GSM486796 1 0.3072 0.6713 0.880 0.064 0.008 0.008 0.040
#> GSM486798 4 0.4130 0.6206 0.000 0.076 0.108 0.804 0.012
#> GSM486800 1 0.0727 0.7092 0.980 0.004 0.012 0.000 0.004
#> GSM486802 1 0.1428 0.7071 0.956 0.004 0.012 0.004 0.024
#> GSM486804 1 0.6931 0.3989 0.592 0.100 0.168 0.000 0.140
#> GSM486806 4 0.3116 0.6373 0.000 0.064 0.076 0.860 0.000
#> GSM486808 3 0.5594 0.4527 0.436 0.000 0.492 0.072 0.000
#> GSM486810 4 0.6020 0.2914 0.000 0.108 0.008 0.560 0.324
#> GSM486812 1 0.5267 -0.0874 0.560 0.000 0.400 0.020 0.020
#> GSM486814 2 0.3234 0.7892 0.012 0.836 0.000 0.144 0.008
#> GSM486816 3 0.4354 0.6689 0.172 0.004 0.772 0.008 0.044
#> GSM486818 1 0.9241 -0.1185 0.320 0.300 0.168 0.068 0.144
#> GSM486821 1 0.7255 0.1628 0.556 0.088 0.008 0.116 0.232
#> GSM486823 4 0.5568 0.4356 0.000 0.116 0.004 0.644 0.236
#> GSM486826 1 0.6529 0.4578 0.636 0.100 0.148 0.000 0.116
#> GSM486830 4 0.3284 0.6270 0.000 0.148 0.000 0.828 0.024
#> GSM486832 1 0.1560 0.7053 0.948 0.000 0.020 0.004 0.028
#> GSM486834 4 0.4860 0.5532 0.012 0.040 0.188 0.744 0.016
#> GSM486836 1 0.0648 0.7095 0.984 0.004 0.004 0.004 0.004
#> GSM486838 4 0.4528 0.5974 0.000 0.172 0.064 0.756 0.008
#> GSM486840 1 0.0932 0.7074 0.972 0.004 0.020 0.000 0.004
#> GSM486842 1 0.4798 -0.2540 0.512 0.000 0.472 0.012 0.004
#> GSM486844 1 0.2538 0.6872 0.904 0.064 0.016 0.004 0.012
#> GSM486846 4 0.4444 0.5483 0.000 0.264 0.012 0.708 0.016
#> GSM486848 1 0.1202 0.7051 0.960 0.004 0.032 0.000 0.004
#> GSM486850 4 0.4630 0.4997 0.000 0.300 0.008 0.672 0.020
#> GSM486852 5 0.6198 0.0908 0.396 0.024 0.076 0.000 0.504
#> GSM486854 4 0.4291 0.5119 0.000 0.276 0.016 0.704 0.004
#> GSM486856 2 0.3740 0.7835 0.012 0.784 0.000 0.196 0.008
#> GSM486858 4 0.4948 0.5204 0.000 0.280 0.036 0.672 0.012
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 6 0.6259 0.6186 0.000 0.124 0.000 0.340 0.048 0.488
#> GSM486737 2 0.2394 0.7822 0.004 0.900 0.000 0.052 0.036 0.008
#> GSM486739 6 0.7497 0.4518 0.004 0.304 0.000 0.180 0.148 0.364
#> GSM486741 2 0.3236 0.6392 0.000 0.796 0.000 0.180 0.024 0.000
#> GSM486743 2 0.2118 0.7872 0.008 0.920 0.000 0.036 0.016 0.020
#> GSM486745 2 0.7674 -0.3293 0.044 0.392 0.000 0.152 0.092 0.320
#> GSM486747 3 0.5637 0.3871 0.072 0.000 0.516 0.384 0.004 0.024
#> GSM486749 4 0.5712 0.1122 0.000 0.196 0.000 0.560 0.008 0.236
#> GSM486751 4 0.4224 0.5513 0.048 0.032 0.144 0.772 0.000 0.004
#> GSM486753 2 0.3617 0.7015 0.000 0.816 0.000 0.080 0.016 0.088
#> GSM486755 2 0.3092 0.7583 0.000 0.860 0.000 0.036 0.040 0.064
#> GSM486757 3 0.6467 0.2618 0.000 0.004 0.572 0.096 0.176 0.152
#> GSM486759 1 0.0436 0.7130 0.988 0.004 0.000 0.000 0.004 0.004
#> GSM486761 3 0.5823 0.4738 0.132 0.004 0.512 0.344 0.004 0.004
#> GSM486763 5 0.3945 0.5528 0.016 0.060 0.032 0.000 0.816 0.076
#> GSM486765 3 0.4117 0.6216 0.228 0.000 0.732 0.016 0.012 0.012
#> GSM486767 2 0.7280 0.4625 0.016 0.560 0.064 0.124 0.064 0.172
#> GSM486769 6 0.6267 0.6173 0.000 0.124 0.000 0.344 0.048 0.484
#> GSM486771 2 0.2322 0.7822 0.008 0.912 0.004 0.024 0.012 0.040
#> GSM486773 4 0.4017 0.6344 0.000 0.120 0.008 0.792 0.016 0.064
#> GSM486775 1 0.2113 0.6718 0.896 0.000 0.092 0.000 0.004 0.008
#> GSM486777 3 0.4958 0.4040 0.424 0.000 0.524 0.036 0.016 0.000
#> GSM486779 2 0.7173 0.3060 0.032 0.492 0.080 0.016 0.076 0.304
#> GSM486781 4 0.3351 0.6779 0.000 0.160 0.000 0.800 0.000 0.040
#> GSM486783 2 0.1894 0.7882 0.004 0.928 0.000 0.040 0.012 0.016
#> GSM486785 3 0.6579 0.4840 0.116 0.004 0.608 0.064 0.040 0.168
#> GSM486787 1 0.1511 0.7084 0.944 0.000 0.012 0.000 0.012 0.032
#> GSM486789 6 0.6292 0.4550 0.000 0.232 0.000 0.372 0.012 0.384
#> GSM486791 5 0.5534 0.5329 0.412 0.000 0.080 0.004 0.492 0.012
#> GSM486793 3 0.3787 0.6143 0.208 0.000 0.760 0.008 0.016 0.008
#> GSM486795 1 0.3999 0.5495 0.800 0.132 0.008 0.024 0.024 0.012
#> GSM486797 4 0.3787 0.6714 0.008 0.124 0.056 0.804 0.004 0.004
#> GSM486799 1 0.1053 0.7120 0.964 0.000 0.012 0.000 0.004 0.020
#> GSM486801 1 0.0841 0.7110 0.976 0.004 0.004 0.004 0.008 0.004
#> GSM486803 1 0.7381 -0.0288 0.380 0.004 0.156 0.004 0.120 0.336
#> GSM486805 4 0.3692 0.6369 0.020 0.064 0.040 0.836 0.000 0.040
#> GSM486807 3 0.5801 0.5089 0.364 0.004 0.496 0.128 0.008 0.000
#> GSM486809 6 0.6488 0.6087 0.000 0.116 0.004 0.348 0.060 0.472
#> GSM486811 1 0.4829 -0.2812 0.520 0.000 0.436 0.032 0.012 0.000
#> GSM486813 2 0.3285 0.7599 0.012 0.864 0.008 0.024 0.036 0.056
#> GSM486815 3 0.4085 0.5434 0.096 0.000 0.804 0.016 0.036 0.048
#> GSM486817 6 0.9025 -0.1960 0.136 0.264 0.140 0.040 0.096 0.324
#> GSM486819 1 0.7346 -0.0307 0.540 0.068 0.012 0.116 0.200 0.064
#> GSM486822 6 0.5984 0.5313 0.000 0.124 0.004 0.404 0.016 0.452
#> GSM486824 1 0.7101 0.0773 0.440 0.020 0.136 0.000 0.076 0.328
#> GSM486828 4 0.4708 0.6400 0.000 0.192 0.008 0.716 0.016 0.068
#> GSM486831 1 0.1296 0.7040 0.952 0.000 0.004 0.012 0.032 0.000
#> GSM486833 4 0.5090 0.2295 0.008 0.044 0.340 0.596 0.008 0.004
#> GSM486835 1 0.1015 0.7102 0.968 0.000 0.004 0.004 0.012 0.012
#> GSM486837 4 0.3275 0.6881 0.000 0.148 0.012 0.820 0.004 0.016
#> GSM486839 1 0.0912 0.7143 0.972 0.004 0.004 0.000 0.008 0.012
#> GSM486841 3 0.4978 0.3365 0.468 0.000 0.484 0.032 0.012 0.004
#> GSM486843 1 0.3107 0.6360 0.860 0.004 0.036 0.008 0.008 0.084
#> GSM486845 4 0.5041 0.5898 0.000 0.316 0.004 0.608 0.008 0.064
#> GSM486847 1 0.1692 0.6990 0.932 0.000 0.048 0.000 0.012 0.008
#> GSM486849 4 0.5893 0.4669 0.000 0.368 0.012 0.512 0.020 0.088
#> GSM486851 5 0.5196 0.6952 0.260 0.020 0.024 0.008 0.660 0.028
#> GSM486853 4 0.5062 0.5515 0.000 0.376 0.004 0.560 0.008 0.052
#> GSM486855 2 0.3022 0.7742 0.016 0.872 0.004 0.072 0.016 0.020
#> GSM486857 4 0.4866 0.6502 0.000 0.200 0.036 0.712 0.020 0.032
#> GSM486736 6 0.6259 0.6186 0.000 0.124 0.000 0.340 0.048 0.488
#> GSM486738 2 0.1899 0.7857 0.004 0.928 0.000 0.028 0.032 0.008
#> GSM486740 6 0.7509 0.4595 0.004 0.300 0.000 0.184 0.148 0.364
#> GSM486742 2 0.3109 0.6500 0.000 0.812 0.000 0.168 0.016 0.004
#> GSM486744 2 0.2521 0.7817 0.008 0.896 0.000 0.056 0.012 0.028
#> GSM486746 6 0.8410 0.4198 0.100 0.284 0.000 0.188 0.108 0.320
#> GSM486748 4 0.6079 -0.2394 0.120 0.004 0.380 0.476 0.008 0.012
#> GSM486750 4 0.5743 0.1154 0.000 0.180 0.000 0.564 0.012 0.244
#> GSM486752 4 0.5048 0.4063 0.076 0.028 0.208 0.684 0.000 0.004
#> GSM486754 2 0.3717 0.6962 0.000 0.808 0.000 0.084 0.016 0.092
#> GSM486756 2 0.3229 0.7528 0.000 0.852 0.000 0.044 0.040 0.064
#> GSM486758 3 0.6380 0.2548 0.000 0.004 0.576 0.080 0.184 0.156
#> GSM486760 1 0.0291 0.7132 0.992 0.000 0.000 0.000 0.004 0.004
#> GSM486762 3 0.5914 0.4132 0.136 0.004 0.472 0.380 0.004 0.004
#> GSM486764 5 0.4016 0.5516 0.016 0.060 0.036 0.000 0.812 0.076
#> GSM486766 3 0.4660 0.5898 0.304 0.000 0.648 0.028 0.008 0.012
#> GSM486768 2 0.4393 0.7170 0.024 0.780 0.000 0.116 0.028 0.052
#> GSM486770 6 0.6267 0.6173 0.000 0.124 0.000 0.344 0.048 0.484
#> GSM486772 2 0.2758 0.7698 0.012 0.888 0.004 0.044 0.008 0.044
#> GSM486774 4 0.3262 0.6835 0.000 0.148 0.004 0.820 0.008 0.020
#> GSM486776 1 0.2062 0.6733 0.900 0.000 0.088 0.000 0.008 0.004
#> GSM486778 1 0.5057 -0.3555 0.476 0.000 0.472 0.032 0.016 0.004
#> GSM486780 2 0.6551 0.3682 0.012 0.532 0.096 0.012 0.048 0.300
#> GSM486782 4 0.3455 0.6675 0.000 0.144 0.000 0.800 0.000 0.056
#> GSM486784 2 0.1557 0.7885 0.008 0.944 0.004 0.036 0.004 0.004
#> GSM486786 3 0.5794 0.3866 0.052 0.004 0.640 0.020 0.056 0.228
#> GSM486788 1 0.1368 0.7087 0.956 0.004 0.004 0.008 0.012 0.016
#> GSM486790 6 0.6458 0.4654 0.000 0.320 0.000 0.288 0.016 0.376
#> GSM486792 5 0.5450 0.5317 0.416 0.000 0.080 0.004 0.492 0.008
#> GSM486794 3 0.3844 0.6130 0.216 0.000 0.752 0.008 0.016 0.008
#> GSM486796 1 0.2877 0.6588 0.888 0.040 0.008 0.024 0.028 0.012
#> GSM486798 4 0.3766 0.6821 0.008 0.136 0.040 0.804 0.004 0.008
#> GSM486800 1 0.0260 0.7147 0.992 0.000 0.000 0.000 0.000 0.008
#> GSM486802 1 0.1057 0.7095 0.968 0.004 0.004 0.008 0.012 0.004
#> GSM486804 1 0.7262 -0.0116 0.376 0.004 0.164 0.004 0.096 0.356
#> GSM486806 4 0.3292 0.6706 0.004 0.112 0.012 0.836 0.000 0.036
#> GSM486808 3 0.5831 0.4867 0.384 0.000 0.476 0.128 0.008 0.004
#> GSM486810 6 0.6434 0.6122 0.000 0.116 0.004 0.344 0.056 0.480
#> GSM486812 1 0.4951 -0.2691 0.524 0.000 0.428 0.032 0.012 0.004
#> GSM486814 2 0.2713 0.7833 0.008 0.896 0.008 0.032 0.028 0.028
#> GSM486816 3 0.4404 0.5648 0.132 0.000 0.772 0.016 0.032 0.048
#> GSM486818 6 0.9160 -0.2923 0.252 0.124 0.156 0.048 0.104 0.316
#> GSM486821 1 0.7320 -0.0330 0.536 0.072 0.012 0.120 0.208 0.052
#> GSM486823 4 0.5871 -0.4846 0.000 0.108 0.004 0.452 0.016 0.420
#> GSM486826 1 0.7364 0.0388 0.412 0.028 0.152 0.000 0.080 0.328
#> GSM486830 4 0.4742 0.6353 0.000 0.196 0.004 0.704 0.012 0.084
#> GSM486832 1 0.1750 0.6950 0.928 0.000 0.008 0.004 0.056 0.004
#> GSM486834 4 0.3520 0.6221 0.008 0.056 0.100 0.828 0.004 0.004
#> GSM486836 1 0.0924 0.7103 0.972 0.000 0.004 0.008 0.008 0.008
#> GSM486838 4 0.4078 0.6843 0.004 0.196 0.016 0.756 0.004 0.024
#> GSM486840 1 0.0798 0.7144 0.976 0.004 0.004 0.000 0.004 0.012
#> GSM486842 3 0.4706 0.3451 0.468 0.000 0.500 0.016 0.012 0.004
#> GSM486844 1 0.5002 0.5470 0.760 0.056 0.036 0.016 0.032 0.100
#> GSM486846 4 0.5083 0.5821 0.000 0.328 0.004 0.596 0.008 0.064
#> GSM486848 1 0.1078 0.7115 0.964 0.000 0.016 0.000 0.012 0.008
#> GSM486850 4 0.5744 0.4874 0.000 0.372 0.012 0.520 0.016 0.080
#> GSM486852 5 0.5280 0.6989 0.248 0.028 0.024 0.008 0.664 0.028
#> GSM486854 4 0.4579 0.6249 0.000 0.316 0.004 0.640 0.008 0.032
#> GSM486856 2 0.3010 0.7747 0.016 0.872 0.008 0.076 0.016 0.012
#> GSM486858 4 0.4834 0.6414 0.000 0.284 0.024 0.656 0.012 0.024
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> CV:kmeans 119 0.923 1.05e-05 2
#> CV:kmeans 86 0.882 2.25e-04 3
#> CV:kmeans 56 0.957 1.31e-05 4
#> CV:kmeans 76 0.986 1.29e-09 5
#> CV:kmeans 81 0.997 1.66e-14 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["CV", "skmeans"]
# you can also extract it by
# res = res_list["CV:skmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'CV' method.
#> Subgroups are detected by 'skmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.369 0.719 0.861 0.5039 0.496 0.496
#> 3 3 0.194 0.446 0.647 0.3187 0.812 0.647
#> 4 4 0.198 0.242 0.456 0.1272 0.867 0.676
#> 5 5 0.262 0.207 0.457 0.0659 0.770 0.405
#> 6 6 0.340 0.221 0.437 0.0426 0.904 0.622
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 2 0.6887 8.25e-01 0.184 0.816
#> GSM486737 2 0.0000 7.88e-01 0.000 1.000
#> GSM486739 2 0.0000 7.88e-01 0.000 1.000
#> GSM486741 2 0.6712 8.26e-01 0.176 0.824
#> GSM486743 2 0.2236 7.69e-01 0.036 0.964
#> GSM486745 2 0.2236 7.69e-01 0.036 0.964
#> GSM486747 1 0.4298 7.12e-01 0.912 0.088
#> GSM486749 2 0.7299 8.20e-01 0.204 0.796
#> GSM486751 2 0.9993 4.31e-01 0.484 0.516
#> GSM486753 2 0.0000 7.88e-01 0.000 1.000
#> GSM486755 2 0.0000 7.88e-01 0.000 1.000
#> GSM486757 1 0.9129 2.12e-01 0.672 0.328
#> GSM486759 1 0.6887 8.29e-01 0.816 0.184
#> GSM486761 1 0.1184 7.75e-01 0.984 0.016
#> GSM486763 1 0.9795 5.73e-01 0.584 0.416
#> GSM486765 1 0.0000 7.84e-01 1.000 0.000
#> GSM486767 2 0.5946 6.58e-01 0.144 0.856
#> GSM486769 2 0.6887 8.25e-01 0.184 0.816
#> GSM486771 2 0.0000 7.88e-01 0.000 1.000
#> GSM486773 2 0.7376 8.18e-01 0.208 0.792
#> GSM486775 1 0.6887 8.29e-01 0.816 0.184
#> GSM486777 1 0.0000 7.84e-01 1.000 0.000
#> GSM486779 2 0.6531 6.20e-01 0.168 0.832
#> GSM486781 2 0.6973 8.24e-01 0.188 0.812
#> GSM486783 2 0.0000 7.88e-01 0.000 1.000
#> GSM486785 1 0.0376 7.82e-01 0.996 0.004
#> GSM486787 1 0.6887 8.29e-01 0.816 0.184
#> GSM486789 2 0.6887 8.25e-01 0.184 0.816
#> GSM486791 1 0.6887 8.29e-01 0.816 0.184
#> GSM486793 1 0.0000 7.84e-01 1.000 0.000
#> GSM486795 1 0.9954 4.78e-01 0.540 0.460
#> GSM486797 2 0.9896 5.37e-01 0.440 0.560
#> GSM486799 1 0.6887 8.29e-01 0.816 0.184
#> GSM486801 1 0.6887 8.29e-01 0.816 0.184
#> GSM486803 1 0.6887 8.29e-01 0.816 0.184
#> GSM486805 2 0.9358 6.88e-01 0.352 0.648
#> GSM486807 1 0.0000 7.84e-01 1.000 0.000
#> GSM486809 2 0.6973 8.25e-01 0.188 0.812
#> GSM486811 1 0.0000 7.84e-01 1.000 0.000
#> GSM486813 2 0.6048 6.51e-01 0.148 0.852
#> GSM486815 1 0.0000 7.84e-01 1.000 0.000
#> GSM486817 2 0.9775 -9.54e-02 0.412 0.588
#> GSM486819 2 0.9954 -2.75e-01 0.460 0.540
#> GSM486822 2 0.6887 8.25e-01 0.184 0.816
#> GSM486824 1 0.6887 8.29e-01 0.816 0.184
#> GSM486828 2 0.6887 8.25e-01 0.184 0.816
#> GSM486831 1 0.6887 8.29e-01 0.816 0.184
#> GSM486833 1 0.9944 -2.77e-01 0.544 0.456
#> GSM486835 1 0.6887 8.29e-01 0.816 0.184
#> GSM486837 2 0.8713 7.58e-01 0.292 0.708
#> GSM486839 1 0.6887 8.29e-01 0.816 0.184
#> GSM486841 1 0.0000 7.84e-01 1.000 0.000
#> GSM486843 1 0.6887 8.29e-01 0.816 0.184
#> GSM486845 2 0.6887 8.25e-01 0.184 0.816
#> GSM486847 1 0.6887 8.29e-01 0.816 0.184
#> GSM486849 2 0.6887 8.25e-01 0.184 0.816
#> GSM486851 1 0.7299 8.20e-01 0.796 0.204
#> GSM486853 2 0.6887 8.25e-01 0.184 0.816
#> GSM486855 2 0.0000 7.88e-01 0.000 1.000
#> GSM486857 2 0.8443 7.75e-01 0.272 0.728
#> GSM486736 2 0.6887 8.25e-01 0.184 0.816
#> GSM486738 2 0.0000 7.88e-01 0.000 1.000
#> GSM486740 2 0.0000 7.88e-01 0.000 1.000
#> GSM486742 2 0.6712 8.26e-01 0.176 0.824
#> GSM486744 2 0.0000 7.88e-01 0.000 1.000
#> GSM486746 2 0.2423 7.67e-01 0.040 0.960
#> GSM486748 1 0.7299 5.35e-01 0.796 0.204
#> GSM486750 2 0.6887 8.25e-01 0.184 0.816
#> GSM486752 1 0.9608 -3.28e-05 0.616 0.384
#> GSM486754 2 0.0000 7.88e-01 0.000 1.000
#> GSM486756 2 0.0000 7.88e-01 0.000 1.000
#> GSM486758 1 0.5408 6.69e-01 0.876 0.124
#> GSM486760 1 0.6887 8.29e-01 0.816 0.184
#> GSM486762 1 0.2236 7.62e-01 0.964 0.036
#> GSM486764 1 0.8327 7.76e-01 0.736 0.264
#> GSM486766 1 0.0000 7.84e-01 1.000 0.000
#> GSM486768 2 0.0672 7.84e-01 0.008 0.992
#> GSM486770 2 0.6887 8.25e-01 0.184 0.816
#> GSM486772 2 0.0000 7.88e-01 0.000 1.000
#> GSM486774 2 0.7376 8.18e-01 0.208 0.792
#> GSM486776 1 0.6887 8.29e-01 0.816 0.184
#> GSM486778 1 0.0000 7.84e-01 1.000 0.000
#> GSM486780 2 0.7376 5.48e-01 0.208 0.792
#> GSM486782 2 0.6887 8.25e-01 0.184 0.816
#> GSM486784 2 0.0000 7.88e-01 0.000 1.000
#> GSM486786 1 0.0000 7.84e-01 1.000 0.000
#> GSM486788 1 0.6887 8.29e-01 0.816 0.184
#> GSM486790 2 0.6887 8.25e-01 0.184 0.816
#> GSM486792 1 0.6887 8.29e-01 0.816 0.184
#> GSM486794 1 0.0000 7.84e-01 1.000 0.000
#> GSM486796 1 0.9661 6.15e-01 0.608 0.392
#> GSM486798 1 1.0000 -3.95e-01 0.504 0.496
#> GSM486800 1 0.6887 8.29e-01 0.816 0.184
#> GSM486802 1 0.6887 8.29e-01 0.816 0.184
#> GSM486804 1 0.6887 8.29e-01 0.816 0.184
#> GSM486806 2 0.7528 8.13e-01 0.216 0.784
#> GSM486808 1 0.0000 7.84e-01 1.000 0.000
#> GSM486810 2 0.6887 8.25e-01 0.184 0.816
#> GSM486812 1 0.0000 7.84e-01 1.000 0.000
#> GSM486814 2 0.2236 7.69e-01 0.036 0.964
#> GSM486816 1 0.0000 7.84e-01 1.000 0.000
#> GSM486818 1 1.0000 3.72e-01 0.500 0.500
#> GSM486821 2 0.9988 -3.34e-01 0.480 0.520
#> GSM486823 2 0.6887 8.25e-01 0.184 0.816
#> GSM486826 1 0.6973 8.28e-01 0.812 0.188
#> GSM486830 2 0.6887 8.25e-01 0.184 0.816
#> GSM486832 1 0.6887 8.29e-01 0.816 0.184
#> GSM486834 2 0.9996 4.21e-01 0.488 0.512
#> GSM486836 1 0.6887 8.29e-01 0.816 0.184
#> GSM486838 2 0.9661 6.30e-01 0.392 0.608
#> GSM486840 1 0.6887 8.29e-01 0.816 0.184
#> GSM486842 1 0.0000 7.84e-01 1.000 0.000
#> GSM486844 1 0.7056 8.26e-01 0.808 0.192
#> GSM486846 2 0.6887 8.25e-01 0.184 0.816
#> GSM486848 1 0.6887 8.29e-01 0.816 0.184
#> GSM486850 2 0.6887 8.25e-01 0.184 0.816
#> GSM486852 1 0.7674 8.07e-01 0.776 0.224
#> GSM486854 2 0.6887 8.25e-01 0.184 0.816
#> GSM486856 2 0.1633 7.76e-01 0.024 0.976
#> GSM486858 2 0.7299 8.19e-01 0.204 0.796
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 2 0.488 0.5890 0.208 0.788 0.004
#> GSM486737 2 0.760 0.5784 0.236 0.668 0.096
#> GSM486739 2 0.696 0.5665 0.184 0.724 0.092
#> GSM486741 2 0.590 0.5770 0.244 0.736 0.020
#> GSM486743 2 0.817 0.4849 0.180 0.644 0.176
#> GSM486745 2 0.930 0.3472 0.244 0.524 0.232
#> GSM486747 1 0.802 0.3697 0.632 0.108 0.260
#> GSM486749 2 0.760 0.3697 0.328 0.612 0.060
#> GSM486751 1 0.899 0.5365 0.560 0.248 0.192
#> GSM486753 2 0.670 0.6000 0.188 0.736 0.076
#> GSM486755 2 0.676 0.5883 0.200 0.728 0.072
#> GSM486757 1 0.876 0.5303 0.584 0.240 0.176
#> GSM486759 3 0.524 0.6312 0.160 0.032 0.808
#> GSM486761 1 0.761 0.1675 0.584 0.052 0.364
#> GSM486763 3 0.989 -0.0512 0.312 0.284 0.404
#> GSM486765 3 0.620 0.4253 0.424 0.000 0.576
#> GSM486767 2 0.993 0.1025 0.312 0.392 0.296
#> GSM486769 2 0.480 0.5863 0.220 0.780 0.000
#> GSM486771 2 0.788 0.5453 0.244 0.648 0.108
#> GSM486773 2 0.750 0.2920 0.412 0.548 0.040
#> GSM486775 3 0.362 0.6470 0.136 0.000 0.864
#> GSM486777 3 0.606 0.4530 0.384 0.000 0.616
#> GSM486779 2 0.976 0.1200 0.360 0.408 0.232
#> GSM486781 2 0.772 0.1540 0.432 0.520 0.048
#> GSM486783 2 0.770 0.5521 0.200 0.676 0.124
#> GSM486785 3 0.767 0.3088 0.456 0.044 0.500
#> GSM486787 3 0.303 0.6505 0.092 0.004 0.904
#> GSM486789 2 0.506 0.5899 0.244 0.756 0.000
#> GSM486791 3 0.531 0.6378 0.192 0.020 0.788
#> GSM486793 3 0.630 0.3803 0.472 0.000 0.528
#> GSM486795 3 0.910 0.2004 0.192 0.264 0.544
#> GSM486797 1 0.939 0.3219 0.440 0.388 0.172
#> GSM486799 3 0.355 0.6419 0.132 0.000 0.868
#> GSM486801 3 0.670 0.5693 0.144 0.108 0.748
#> GSM486803 3 0.642 0.5925 0.228 0.044 0.728
#> GSM486805 1 0.894 0.2900 0.512 0.352 0.136
#> GSM486807 3 0.704 0.3323 0.444 0.020 0.536
#> GSM486809 2 0.694 0.4397 0.372 0.604 0.024
#> GSM486811 3 0.588 0.4942 0.348 0.000 0.652
#> GSM486813 2 0.960 0.1994 0.252 0.476 0.272
#> GSM486815 3 0.694 0.3873 0.468 0.016 0.516
#> GSM486817 3 0.981 -0.0185 0.288 0.280 0.432
#> GSM486819 3 0.950 0.0343 0.224 0.288 0.488
#> GSM486822 2 0.497 0.5741 0.236 0.764 0.000
#> GSM486824 3 0.662 0.5659 0.228 0.052 0.720
#> GSM486828 2 0.769 0.4164 0.344 0.596 0.060
#> GSM486831 3 0.341 0.6526 0.124 0.000 0.876
#> GSM486833 1 0.901 0.5214 0.556 0.256 0.188
#> GSM486835 3 0.504 0.6377 0.172 0.020 0.808
#> GSM486837 1 0.879 0.1481 0.448 0.440 0.112
#> GSM486839 3 0.329 0.6475 0.096 0.008 0.896
#> GSM486841 3 0.597 0.4780 0.364 0.000 0.636
#> GSM486843 3 0.610 0.5856 0.208 0.040 0.752
#> GSM486845 2 0.683 0.4530 0.312 0.656 0.032
#> GSM486847 3 0.423 0.6530 0.160 0.004 0.836
#> GSM486849 2 0.552 0.5645 0.268 0.728 0.004
#> GSM486851 3 0.792 0.4804 0.228 0.120 0.652
#> GSM486853 2 0.529 0.5366 0.268 0.732 0.000
#> GSM486855 2 0.731 0.5598 0.168 0.708 0.124
#> GSM486857 1 0.825 0.2186 0.528 0.392 0.080
#> GSM486736 2 0.511 0.5751 0.228 0.768 0.004
#> GSM486738 2 0.658 0.5823 0.136 0.756 0.108
#> GSM486740 2 0.591 0.5900 0.156 0.784 0.060
#> GSM486742 2 0.506 0.5906 0.208 0.784 0.008
#> GSM486744 2 0.701 0.5843 0.176 0.724 0.100
#> GSM486746 2 0.934 0.2600 0.208 0.512 0.280
#> GSM486748 1 0.882 0.4387 0.564 0.156 0.280
#> GSM486750 2 0.529 0.5313 0.268 0.732 0.000
#> GSM486752 1 0.924 0.5609 0.532 0.244 0.224
#> GSM486754 2 0.573 0.6094 0.164 0.788 0.048
#> GSM486756 2 0.667 0.5862 0.200 0.732 0.068
#> GSM486758 1 0.764 0.3611 0.656 0.088 0.256
#> GSM486760 3 0.350 0.6506 0.116 0.004 0.880
#> GSM486762 1 0.817 0.2600 0.576 0.088 0.336
#> GSM486764 3 0.953 0.1538 0.272 0.240 0.488
#> GSM486766 3 0.614 0.4474 0.404 0.000 0.596
#> GSM486768 2 0.914 0.3591 0.212 0.544 0.244
#> GSM486770 2 0.470 0.5819 0.212 0.788 0.000
#> GSM486772 2 0.509 0.6093 0.112 0.832 0.056
#> GSM486774 2 0.784 0.0398 0.456 0.492 0.052
#> GSM486776 3 0.327 0.6518 0.116 0.000 0.884
#> GSM486778 3 0.728 0.3859 0.404 0.032 0.564
#> GSM486780 2 0.987 0.1291 0.324 0.408 0.268
#> GSM486782 2 0.610 0.4613 0.320 0.672 0.008
#> GSM486784 2 0.697 0.5680 0.144 0.732 0.124
#> GSM486786 3 0.668 0.3418 0.480 0.008 0.512
#> GSM486788 3 0.350 0.6472 0.116 0.004 0.880
#> GSM486790 2 0.406 0.5995 0.164 0.836 0.000
#> GSM486792 3 0.462 0.6459 0.144 0.020 0.836
#> GSM486794 3 0.617 0.4448 0.412 0.000 0.588
#> GSM486796 3 0.905 0.2943 0.224 0.220 0.556
#> GSM486798 2 0.922 -0.3171 0.404 0.444 0.152
#> GSM486800 3 0.254 0.6468 0.080 0.000 0.920
#> GSM486802 3 0.484 0.6222 0.104 0.052 0.844
#> GSM486804 3 0.671 0.5737 0.196 0.072 0.732
#> GSM486806 1 0.813 0.0950 0.488 0.444 0.068
#> GSM486808 3 0.659 0.3918 0.424 0.008 0.568
#> GSM486810 2 0.572 0.5630 0.292 0.704 0.004
#> GSM486812 3 0.568 0.5127 0.316 0.000 0.684
#> GSM486814 2 0.913 0.3729 0.268 0.540 0.192
#> GSM486816 3 0.626 0.4160 0.448 0.000 0.552
#> GSM486818 3 0.964 0.0522 0.280 0.252 0.468
#> GSM486821 3 0.946 0.1513 0.256 0.244 0.500
#> GSM486823 2 0.510 0.5477 0.248 0.752 0.000
#> GSM486826 3 0.733 0.5409 0.276 0.064 0.660
#> GSM486830 2 0.710 0.3886 0.384 0.588 0.028
#> GSM486832 3 0.271 0.6503 0.088 0.000 0.912
#> GSM486834 1 0.854 0.4910 0.580 0.292 0.128
#> GSM486836 3 0.417 0.6488 0.156 0.004 0.840
#> GSM486838 1 0.951 0.4500 0.464 0.336 0.200
#> GSM486840 3 0.303 0.6471 0.076 0.012 0.912
#> GSM486842 3 0.546 0.5363 0.288 0.000 0.712
#> GSM486844 3 0.747 0.4907 0.216 0.100 0.684
#> GSM486846 2 0.691 0.4846 0.324 0.644 0.032
#> GSM486848 3 0.345 0.6513 0.104 0.008 0.888
#> GSM486850 2 0.522 0.5662 0.260 0.740 0.000
#> GSM486852 3 0.839 0.4062 0.200 0.176 0.624
#> GSM486854 2 0.620 0.4625 0.312 0.676 0.012
#> GSM486856 2 0.851 0.4388 0.212 0.612 0.176
#> GSM486858 1 0.729 -0.0428 0.500 0.472 0.028
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 2 0.549 0.38410 0.128 0.752 0.008 0.112
#> GSM486737 1 0.842 -0.26610 0.380 0.316 0.020 0.284
#> GSM486739 2 0.775 0.32086 0.132 0.568 0.044 0.256
#> GSM486741 1 0.783 -0.26220 0.420 0.408 0.016 0.156
#> GSM486743 2 0.933 0.02698 0.240 0.348 0.092 0.320
#> GSM486745 2 0.886 0.12069 0.148 0.440 0.092 0.320
#> GSM486747 1 0.911 -0.00153 0.400 0.076 0.244 0.280
#> GSM486749 2 0.827 0.10343 0.304 0.508 0.076 0.112
#> GSM486751 1 0.980 0.20167 0.312 0.300 0.176 0.212
#> GSM486753 2 0.862 0.25757 0.256 0.444 0.044 0.256
#> GSM486755 2 0.851 0.22342 0.268 0.404 0.028 0.300
#> GSM486757 1 0.949 0.11333 0.372 0.224 0.120 0.284
#> GSM486759 3 0.694 0.42545 0.048 0.048 0.596 0.308
#> GSM486761 1 0.914 -0.10836 0.376 0.072 0.284 0.268
#> GSM486763 4 0.952 0.28983 0.124 0.220 0.296 0.360
#> GSM486765 3 0.753 0.44703 0.216 0.004 0.520 0.260
#> GSM486767 4 0.980 0.20446 0.288 0.256 0.156 0.300
#> GSM486769 2 0.526 0.39444 0.148 0.764 0.008 0.080
#> GSM486771 2 0.886 0.15975 0.252 0.356 0.048 0.344
#> GSM486773 2 0.843 0.01052 0.356 0.424 0.040 0.180
#> GSM486775 3 0.575 0.52950 0.088 0.000 0.696 0.216
#> GSM486777 3 0.856 0.40702 0.212 0.056 0.484 0.248
#> GSM486779 1 0.966 -0.19763 0.328 0.240 0.136 0.296
#> GSM486781 1 0.810 -0.08173 0.428 0.412 0.052 0.108
#> GSM486783 1 0.898 -0.23580 0.372 0.280 0.056 0.292
#> GSM486785 3 0.888 0.28821 0.328 0.056 0.388 0.228
#> GSM486787 3 0.521 0.53048 0.048 0.004 0.736 0.212
#> GSM486789 2 0.591 0.40286 0.236 0.676 0.000 0.088
#> GSM486791 3 0.735 0.33971 0.036 0.084 0.556 0.324
#> GSM486793 3 0.805 0.40709 0.256 0.012 0.456 0.276
#> GSM486795 3 0.942 -0.18612 0.240 0.136 0.416 0.208
#> GSM486797 1 0.930 0.22228 0.448 0.212 0.188 0.152
#> GSM486799 3 0.443 0.53580 0.032 0.004 0.796 0.168
#> GSM486801 3 0.811 0.34592 0.104 0.112 0.576 0.208
#> GSM486803 3 0.715 0.37568 0.052 0.044 0.540 0.364
#> GSM486805 1 0.945 0.16266 0.344 0.324 0.112 0.220
#> GSM486807 3 0.877 0.35804 0.268 0.056 0.440 0.236
#> GSM486809 2 0.718 0.28617 0.252 0.608 0.028 0.112
#> GSM486811 3 0.771 0.47676 0.176 0.032 0.572 0.220
#> GSM486813 4 0.959 0.21184 0.308 0.204 0.140 0.348
#> GSM486815 3 0.836 0.37502 0.228 0.024 0.408 0.340
#> GSM486817 4 0.964 0.30800 0.280 0.128 0.264 0.328
#> GSM486819 3 0.977 -0.24183 0.156 0.240 0.316 0.288
#> GSM486822 2 0.525 0.38090 0.196 0.736 0.000 0.068
#> GSM486824 3 0.771 0.32890 0.124 0.032 0.532 0.312
#> GSM486828 2 0.865 0.12026 0.348 0.424 0.060 0.168
#> GSM486831 3 0.529 0.49637 0.032 0.004 0.700 0.264
#> GSM486833 1 0.955 0.14994 0.400 0.224 0.156 0.220
#> GSM486835 3 0.707 0.44870 0.068 0.048 0.616 0.268
#> GSM486837 1 0.839 0.12319 0.476 0.332 0.072 0.120
#> GSM486839 3 0.551 0.51560 0.064 0.004 0.720 0.212
#> GSM486841 3 0.766 0.48021 0.216 0.020 0.556 0.208
#> GSM486843 3 0.773 0.37313 0.144 0.044 0.580 0.232
#> GSM486845 2 0.769 0.20176 0.408 0.468 0.060 0.064
#> GSM486847 3 0.527 0.52391 0.036 0.008 0.724 0.232
#> GSM486849 2 0.767 0.30017 0.352 0.488 0.016 0.144
#> GSM486851 3 0.847 0.15931 0.068 0.140 0.480 0.312
#> GSM486853 2 0.639 0.28014 0.404 0.528 0.000 0.068
#> GSM486855 2 0.906 0.19667 0.324 0.360 0.064 0.252
#> GSM486857 1 0.841 0.09480 0.460 0.288 0.036 0.216
#> GSM486736 2 0.439 0.39873 0.088 0.832 0.016 0.064
#> GSM486738 2 0.833 0.24487 0.328 0.380 0.016 0.276
#> GSM486740 2 0.749 0.31023 0.084 0.576 0.052 0.288
#> GSM486742 2 0.797 0.27899 0.400 0.408 0.016 0.176
#> GSM486744 2 0.889 0.25514 0.272 0.420 0.060 0.248
#> GSM486746 2 0.943 -0.03585 0.140 0.416 0.208 0.236
#> GSM486748 1 0.985 0.13572 0.328 0.192 0.264 0.216
#> GSM486750 2 0.602 0.37625 0.204 0.700 0.012 0.084
#> GSM486752 1 0.966 0.19261 0.372 0.264 0.172 0.192
#> GSM486754 2 0.739 0.36067 0.200 0.560 0.008 0.232
#> GSM486756 2 0.861 0.23887 0.300 0.412 0.036 0.252
#> GSM486758 4 0.960 -0.14531 0.328 0.160 0.176 0.336
#> GSM486760 3 0.482 0.52411 0.040 0.020 0.796 0.144
#> GSM486762 1 0.946 -0.09137 0.328 0.104 0.320 0.248
#> GSM486764 4 0.948 0.28634 0.136 0.192 0.288 0.384
#> GSM486766 3 0.782 0.44691 0.244 0.016 0.520 0.220
#> GSM486768 2 0.971 -0.05760 0.244 0.344 0.148 0.264
#> GSM486770 2 0.417 0.41274 0.092 0.828 0.000 0.080
#> GSM486772 2 0.815 0.32540 0.188 0.520 0.040 0.252
#> GSM486774 2 0.812 0.05736 0.368 0.456 0.040 0.136
#> GSM486776 3 0.504 0.53428 0.056 0.000 0.748 0.196
#> GSM486778 3 0.832 0.42966 0.192 0.076 0.548 0.184
#> GSM486780 4 0.965 0.22619 0.284 0.220 0.144 0.352
#> GSM486782 2 0.678 0.31051 0.272 0.624 0.024 0.080
#> GSM486784 1 0.916 -0.24220 0.348 0.328 0.072 0.252
#> GSM486786 3 0.812 0.37089 0.288 0.008 0.400 0.304
#> GSM486788 3 0.521 0.48869 0.048 0.004 0.736 0.212
#> GSM486790 2 0.577 0.43110 0.176 0.708 0.000 0.116
#> GSM486792 3 0.662 0.41609 0.016 0.072 0.612 0.300
#> GSM486794 3 0.773 0.44199 0.232 0.008 0.504 0.256
#> GSM486796 3 0.922 0.00482 0.152 0.136 0.428 0.284
#> GSM486798 1 0.936 0.19013 0.372 0.332 0.132 0.164
#> GSM486800 3 0.468 0.53192 0.048 0.000 0.776 0.176
#> GSM486802 3 0.755 0.39627 0.100 0.076 0.620 0.204
#> GSM486804 3 0.835 0.31894 0.132 0.076 0.520 0.272
#> GSM486806 2 0.815 0.06369 0.348 0.484 0.064 0.104
#> GSM486808 3 0.777 0.42856 0.272 0.024 0.536 0.168
#> GSM486810 2 0.641 0.35191 0.192 0.688 0.024 0.096
#> GSM486812 3 0.729 0.49122 0.200 0.020 0.604 0.176
#> GSM486814 4 0.950 -0.03646 0.284 0.292 0.104 0.320
#> GSM486816 3 0.868 0.40410 0.224 0.048 0.432 0.296
#> GSM486818 4 0.948 0.30940 0.212 0.128 0.276 0.384
#> GSM486821 3 0.980 -0.29460 0.196 0.236 0.352 0.216
#> GSM486823 2 0.549 0.36234 0.236 0.708 0.004 0.052
#> GSM486826 3 0.857 0.14854 0.148 0.064 0.436 0.352
#> GSM486830 2 0.804 0.24909 0.312 0.496 0.032 0.160
#> GSM486832 3 0.557 0.51590 0.040 0.020 0.724 0.216
#> GSM486834 1 0.932 0.22769 0.420 0.276 0.144 0.160
#> GSM486836 3 0.534 0.51277 0.044 0.008 0.728 0.220
#> GSM486838 1 0.889 0.13512 0.444 0.316 0.128 0.112
#> GSM486840 3 0.563 0.50439 0.076 0.012 0.736 0.176
#> GSM486842 3 0.642 0.50575 0.176 0.004 0.664 0.156
#> GSM486844 3 0.879 0.11919 0.160 0.080 0.448 0.312
#> GSM486846 2 0.674 0.31356 0.380 0.544 0.016 0.060
#> GSM486848 3 0.610 0.48990 0.064 0.008 0.656 0.272
#> GSM486850 2 0.763 0.30987 0.372 0.492 0.028 0.108
#> GSM486852 3 0.875 0.07141 0.076 0.196 0.480 0.248
#> GSM486854 1 0.717 -0.19939 0.464 0.424 0.008 0.104
#> GSM486856 1 0.943 -0.13620 0.348 0.260 0.100 0.292
#> GSM486858 1 0.848 0.01860 0.472 0.308 0.056 0.164
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 4 0.571 0.28666 0.016 0.100 0.056 0.728 0.100
#> GSM486737 2 0.765 0.30487 0.052 0.520 0.028 0.236 0.164
#> GSM486739 4 0.802 0.03124 0.076 0.276 0.040 0.484 0.124
#> GSM486741 2 0.771 0.14537 0.012 0.448 0.048 0.288 0.204
#> GSM486743 2 0.856 0.28982 0.120 0.424 0.028 0.208 0.220
#> GSM486745 4 0.872 -0.12484 0.132 0.308 0.036 0.372 0.152
#> GSM486747 3 0.795 0.26206 0.080 0.080 0.544 0.092 0.204
#> GSM486749 4 0.853 0.21667 0.060 0.156 0.136 0.488 0.160
#> GSM486751 3 0.897 -0.16617 0.060 0.084 0.332 0.280 0.244
#> GSM486753 2 0.805 0.22126 0.044 0.440 0.052 0.320 0.144
#> GSM486755 2 0.799 0.29211 0.068 0.500 0.044 0.252 0.136
#> GSM486757 3 0.894 -0.03213 0.072 0.092 0.396 0.192 0.248
#> GSM486759 1 0.746 0.40801 0.580 0.076 0.168 0.032 0.144
#> GSM486761 3 0.805 0.35427 0.152 0.064 0.520 0.060 0.204
#> GSM486763 5 0.994 -0.07529 0.212 0.224 0.156 0.184 0.224
#> GSM486765 3 0.578 0.34875 0.252 0.024 0.652 0.008 0.064
#> GSM486767 2 0.901 0.19947 0.120 0.416 0.092 0.136 0.236
#> GSM486769 4 0.476 0.29935 0.004 0.108 0.036 0.780 0.072
#> GSM486771 2 0.755 0.29306 0.044 0.520 0.028 0.252 0.156
#> GSM486773 4 0.888 0.05323 0.032 0.232 0.128 0.352 0.256
#> GSM486775 1 0.643 0.24433 0.548 0.080 0.328 0.000 0.044
#> GSM486777 3 0.756 0.26404 0.276 0.036 0.528 0.084 0.076
#> GSM486779 2 0.934 0.13937 0.140 0.344 0.076 0.208 0.232
#> GSM486781 4 0.883 0.12818 0.048 0.152 0.124 0.372 0.304
#> GSM486783 2 0.672 0.35776 0.056 0.628 0.020 0.196 0.100
#> GSM486785 3 0.832 0.24552 0.288 0.060 0.432 0.048 0.172
#> GSM486787 1 0.622 0.37939 0.648 0.044 0.196 0.004 0.108
#> GSM486789 4 0.677 0.17924 0.016 0.240 0.024 0.580 0.140
#> GSM486791 1 0.881 0.30795 0.436 0.096 0.232 0.080 0.156
#> GSM486793 3 0.612 0.39100 0.188 0.032 0.664 0.012 0.104
#> GSM486795 1 0.920 0.28925 0.404 0.172 0.152 0.088 0.184
#> GSM486797 3 0.953 -0.22449 0.088 0.160 0.284 0.184 0.284
#> GSM486799 1 0.631 0.31883 0.608 0.044 0.248 0.000 0.100
#> GSM486801 1 0.839 0.34710 0.496 0.084 0.184 0.068 0.168
#> GSM486803 1 0.807 0.35044 0.484 0.120 0.164 0.016 0.216
#> GSM486805 4 0.933 -0.01370 0.060 0.148 0.228 0.304 0.260
#> GSM486807 3 0.795 0.34314 0.244 0.048 0.500 0.052 0.156
#> GSM486809 4 0.752 0.21689 0.016 0.100 0.168 0.560 0.156
#> GSM486811 3 0.701 0.19156 0.336 0.020 0.512 0.032 0.100
#> GSM486813 2 0.879 0.19989 0.144 0.468 0.084 0.148 0.156
#> GSM486815 3 0.764 0.30950 0.212 0.048 0.548 0.048 0.144
#> GSM486817 2 0.950 0.04021 0.184 0.348 0.120 0.128 0.220
#> GSM486819 1 0.977 0.01581 0.296 0.220 0.132 0.180 0.172
#> GSM486822 4 0.600 0.27599 0.008 0.184 0.028 0.668 0.112
#> GSM486824 1 0.826 0.36308 0.500 0.152 0.176 0.036 0.136
#> GSM486828 4 0.898 0.12864 0.044 0.232 0.144 0.380 0.200
#> GSM486831 1 0.644 0.41021 0.652 0.036 0.164 0.020 0.128
#> GSM486833 3 0.923 -0.05236 0.084 0.112 0.368 0.208 0.228
#> GSM486835 1 0.725 0.38142 0.576 0.088 0.212 0.016 0.108
#> GSM486837 4 0.941 0.05122 0.084 0.160 0.164 0.328 0.264
#> GSM486839 1 0.708 0.37306 0.592 0.072 0.204 0.016 0.116
#> GSM486841 3 0.710 0.28973 0.308 0.028 0.532 0.036 0.096
#> GSM486843 1 0.798 0.36252 0.516 0.120 0.148 0.024 0.192
#> GSM486845 4 0.893 0.12646 0.060 0.280 0.096 0.368 0.196
#> GSM486847 1 0.750 0.34462 0.532 0.084 0.260 0.020 0.104
#> GSM486849 4 0.799 0.08140 0.036 0.288 0.056 0.464 0.156
#> GSM486851 1 0.938 0.22748 0.388 0.120 0.172 0.148 0.172
#> GSM486853 4 0.752 0.16174 0.004 0.300 0.048 0.448 0.200
#> GSM486855 2 0.796 0.30922 0.088 0.496 0.028 0.252 0.136
#> GSM486857 2 0.919 -0.06012 0.040 0.292 0.172 0.216 0.280
#> GSM486736 4 0.560 0.27926 0.024 0.132 0.036 0.732 0.076
#> GSM486738 2 0.659 0.36199 0.028 0.636 0.040 0.204 0.092
#> GSM486740 4 0.753 0.05679 0.052 0.260 0.040 0.536 0.112
#> GSM486742 2 0.752 0.14651 0.020 0.476 0.036 0.304 0.164
#> GSM486744 2 0.786 0.28361 0.100 0.488 0.016 0.264 0.132
#> GSM486746 4 0.929 -0.08520 0.184 0.200 0.068 0.364 0.184
#> GSM486748 3 0.901 0.13903 0.152 0.064 0.412 0.164 0.208
#> GSM486750 4 0.697 0.28043 0.016 0.184 0.068 0.608 0.124
#> GSM486752 3 0.923 -0.06192 0.112 0.088 0.368 0.244 0.188
#> GSM486754 2 0.726 0.19881 0.032 0.472 0.016 0.344 0.136
#> GSM486756 2 0.780 0.26675 0.028 0.476 0.044 0.268 0.184
#> GSM486758 3 0.889 0.09992 0.120 0.072 0.420 0.144 0.244
#> GSM486760 1 0.637 0.37259 0.652 0.040 0.196 0.020 0.092
#> GSM486762 3 0.888 0.21682 0.208 0.060 0.412 0.108 0.212
#> GSM486764 1 0.986 -0.04434 0.252 0.204 0.200 0.128 0.216
#> GSM486766 3 0.647 0.35561 0.268 0.016 0.596 0.024 0.096
#> GSM486768 2 0.896 0.19189 0.136 0.360 0.044 0.280 0.180
#> GSM486770 4 0.433 0.29265 0.004 0.108 0.016 0.800 0.072
#> GSM486772 2 0.749 0.21591 0.060 0.460 0.040 0.372 0.068
#> GSM486774 4 0.905 0.08849 0.040 0.196 0.152 0.332 0.280
#> GSM486776 1 0.651 0.30179 0.596 0.076 0.252 0.000 0.076
#> GSM486778 3 0.800 0.19333 0.312 0.024 0.448 0.084 0.132
#> GSM486780 2 0.950 0.13974 0.168 0.364 0.124 0.152 0.192
#> GSM486782 4 0.794 0.26339 0.020 0.172 0.088 0.496 0.224
#> GSM486784 2 0.742 0.32670 0.084 0.556 0.024 0.236 0.100
#> GSM486786 3 0.727 0.33011 0.268 0.032 0.524 0.020 0.156
#> GSM486788 1 0.616 0.42953 0.704 0.064 0.116 0.032 0.084
#> GSM486790 4 0.615 0.11580 0.012 0.296 0.008 0.588 0.096
#> GSM486792 1 0.807 0.33139 0.500 0.048 0.240 0.072 0.140
#> GSM486794 3 0.623 0.33685 0.256 0.008 0.620 0.032 0.084
#> GSM486796 1 0.915 0.22372 0.424 0.152 0.104 0.160 0.160
#> GSM486798 4 0.938 -0.07704 0.076 0.124 0.276 0.288 0.236
#> GSM486800 1 0.596 0.36748 0.664 0.068 0.200 0.000 0.068
#> GSM486802 1 0.683 0.41347 0.636 0.076 0.120 0.020 0.148
#> GSM486804 1 0.884 0.26992 0.404 0.140 0.204 0.040 0.212
#> GSM486806 4 0.899 0.11831 0.052 0.156 0.144 0.368 0.280
#> GSM486808 3 0.760 0.29281 0.328 0.024 0.456 0.036 0.156
#> GSM486810 4 0.716 0.25010 0.016 0.168 0.096 0.600 0.120
#> GSM486812 3 0.650 0.13571 0.420 0.016 0.472 0.016 0.076
#> GSM486814 2 0.805 0.33768 0.108 0.524 0.044 0.204 0.120
#> GSM486816 3 0.727 0.32762 0.232 0.020 0.560 0.056 0.132
#> GSM486818 1 0.949 0.00756 0.312 0.236 0.120 0.100 0.232
#> GSM486821 1 0.968 -0.02467 0.316 0.188 0.116 0.208 0.172
#> GSM486823 4 0.585 0.31035 0.016 0.140 0.028 0.700 0.116
#> GSM486826 1 0.866 0.22793 0.372 0.152 0.208 0.016 0.252
#> GSM486830 4 0.846 0.19328 0.020 0.204 0.140 0.436 0.200
#> GSM486832 1 0.707 0.31116 0.588 0.056 0.236 0.032 0.088
#> GSM486834 5 0.914 0.00611 0.088 0.088 0.312 0.188 0.324
#> GSM486836 1 0.599 0.40221 0.684 0.048 0.168 0.008 0.092
#> GSM486838 4 0.967 -0.00488 0.116 0.196 0.148 0.300 0.240
#> GSM486840 1 0.602 0.40168 0.692 0.096 0.140 0.008 0.064
#> GSM486842 3 0.607 0.23167 0.376 0.012 0.536 0.008 0.068
#> GSM486844 1 0.871 0.28013 0.416 0.180 0.184 0.028 0.192
#> GSM486846 4 0.841 0.19528 0.036 0.272 0.080 0.424 0.188
#> GSM486848 1 0.726 0.33611 0.568 0.120 0.204 0.008 0.100
#> GSM486850 4 0.844 0.09144 0.024 0.284 0.096 0.400 0.196
#> GSM486852 1 0.953 0.15440 0.352 0.116 0.148 0.192 0.192
#> GSM486854 4 0.855 0.14486 0.028 0.252 0.088 0.380 0.252
#> GSM486856 2 0.852 0.26974 0.108 0.464 0.048 0.208 0.172
#> GSM486858 5 0.905 -0.15220 0.040 0.284 0.128 0.252 0.296
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 6 0.608 0.39052 0.016 0.108 0.012 0.116 0.084 0.664
#> GSM486737 2 0.736 0.27342 0.032 0.536 0.016 0.188 0.108 0.120
#> GSM486739 6 0.678 0.22131 0.016 0.160 0.016 0.052 0.188 0.568
#> GSM486741 2 0.799 0.12425 0.028 0.412 0.028 0.228 0.072 0.232
#> GSM486743 2 0.859 0.25859 0.092 0.396 0.020 0.124 0.148 0.220
#> GSM486745 6 0.857 0.02628 0.076 0.200 0.032 0.088 0.208 0.396
#> GSM486747 3 0.793 0.32064 0.096 0.060 0.512 0.196 0.068 0.068
#> GSM486749 6 0.846 0.09252 0.036 0.128 0.096 0.208 0.092 0.440
#> GSM486751 4 0.918 0.21063 0.068 0.100 0.248 0.264 0.072 0.248
#> GSM486753 2 0.755 0.14875 0.020 0.428 0.028 0.100 0.088 0.336
#> GSM486755 2 0.818 0.21960 0.036 0.416 0.032 0.096 0.164 0.256
#> GSM486757 3 0.904 0.02493 0.040 0.104 0.364 0.184 0.144 0.164
#> GSM486759 1 0.824 0.16736 0.424 0.084 0.144 0.064 0.256 0.028
#> GSM486761 3 0.767 0.35478 0.148 0.044 0.496 0.220 0.068 0.024
#> GSM486763 5 0.832 0.38095 0.156 0.112 0.060 0.036 0.456 0.180
#> GSM486765 3 0.509 0.40027 0.156 0.016 0.724 0.048 0.052 0.004
#> GSM486767 2 0.939 0.13254 0.100 0.252 0.056 0.136 0.208 0.248
#> GSM486769 6 0.425 0.40402 0.000 0.068 0.016 0.104 0.024 0.788
#> GSM486771 2 0.760 0.26722 0.068 0.484 0.008 0.060 0.144 0.236
#> GSM486773 6 0.883 -0.03161 0.016 0.176 0.104 0.252 0.128 0.324
#> GSM486775 1 0.636 0.19976 0.516 0.028 0.324 0.016 0.112 0.004
#> GSM486777 3 0.792 0.32842 0.172 0.016 0.496 0.092 0.140 0.084
#> GSM486779 2 0.960 0.12078 0.164 0.268 0.068 0.160 0.208 0.132
#> GSM486781 4 0.826 0.10410 0.028 0.136 0.056 0.368 0.088 0.324
#> GSM486783 2 0.707 0.32692 0.068 0.580 0.008 0.132 0.068 0.144
#> GSM486785 3 0.805 0.19733 0.276 0.056 0.432 0.120 0.092 0.024
#> GSM486787 1 0.630 0.34895 0.624 0.028 0.188 0.048 0.104 0.008
#> GSM486789 6 0.673 0.30086 0.004 0.164 0.016 0.196 0.064 0.556
#> GSM486791 5 0.803 0.27574 0.232 0.036 0.168 0.020 0.436 0.108
#> GSM486793 3 0.712 0.40099 0.132 0.040 0.596 0.096 0.104 0.032
#> GSM486795 1 0.955 -0.03518 0.312 0.152 0.116 0.120 0.192 0.108
#> GSM486797 4 0.937 0.22814 0.072 0.180 0.184 0.328 0.108 0.128
#> GSM486799 1 0.673 0.31467 0.528 0.036 0.240 0.032 0.164 0.000
#> GSM486801 1 0.797 0.25023 0.500 0.076 0.108 0.044 0.204 0.068
#> GSM486803 1 0.805 0.18956 0.436 0.076 0.168 0.036 0.248 0.036
#> GSM486805 4 0.915 0.19140 0.044 0.108 0.176 0.308 0.112 0.252
#> GSM486807 3 0.752 0.35592 0.168 0.024 0.532 0.128 0.116 0.032
#> GSM486809 6 0.797 0.19909 0.024 0.108 0.096 0.120 0.140 0.512
#> GSM486811 3 0.763 0.12305 0.340 0.016 0.388 0.120 0.124 0.012
#> GSM486813 2 0.840 0.28191 0.072 0.476 0.060 0.112 0.120 0.160
#> GSM486815 3 0.734 0.36804 0.132 0.056 0.568 0.048 0.156 0.040
#> GSM486817 2 0.960 -0.01919 0.228 0.240 0.092 0.140 0.208 0.092
#> GSM486819 5 0.879 0.32430 0.188 0.112 0.060 0.080 0.416 0.144
#> GSM486822 6 0.612 0.29972 0.000 0.132 0.012 0.180 0.060 0.616
#> GSM486824 1 0.797 0.29145 0.468 0.088 0.112 0.060 0.244 0.028
#> GSM486828 6 0.903 -0.06988 0.048 0.188 0.080 0.272 0.108 0.304
#> GSM486831 1 0.734 0.21865 0.468 0.024 0.184 0.040 0.264 0.020
#> GSM486833 3 0.957 -0.03373 0.100 0.120 0.304 0.168 0.120 0.188
#> GSM486835 1 0.784 0.28417 0.488 0.052 0.172 0.060 0.196 0.032
#> GSM486837 4 0.818 0.27619 0.036 0.112 0.144 0.464 0.048 0.196
#> GSM486839 1 0.748 0.33836 0.520 0.064 0.200 0.044 0.152 0.020
#> GSM486841 3 0.732 0.31173 0.228 0.028 0.516 0.104 0.112 0.012
#> GSM486843 1 0.818 0.29847 0.484 0.128 0.116 0.084 0.160 0.028
#> GSM486845 4 0.854 0.12193 0.048 0.272 0.056 0.328 0.056 0.240
#> GSM486847 1 0.760 0.21950 0.436 0.084 0.300 0.048 0.128 0.004
#> GSM486849 6 0.819 0.10776 0.020 0.244 0.048 0.188 0.092 0.408
#> GSM486851 5 0.822 0.36890 0.184 0.056 0.112 0.036 0.468 0.144
#> GSM486853 4 0.769 0.04469 0.004 0.268 0.040 0.324 0.048 0.316
#> GSM486855 2 0.862 0.26675 0.072 0.416 0.040 0.172 0.112 0.188
#> GSM486857 4 0.904 0.07267 0.036 0.244 0.144 0.328 0.096 0.152
#> GSM486736 6 0.528 0.40023 0.008 0.052 0.024 0.108 0.076 0.732
#> GSM486738 2 0.748 0.32321 0.052 0.528 0.008 0.124 0.116 0.172
#> GSM486740 6 0.671 0.22976 0.020 0.164 0.008 0.056 0.180 0.572
#> GSM486742 2 0.789 0.17592 0.032 0.424 0.036 0.184 0.052 0.272
#> GSM486744 2 0.754 0.25684 0.068 0.484 0.012 0.064 0.104 0.268
#> GSM486746 6 0.892 -0.05306 0.132 0.124 0.040 0.096 0.264 0.344
#> GSM486748 4 0.867 -0.00646 0.148 0.056 0.304 0.340 0.048 0.104
#> GSM486750 6 0.761 0.17487 0.032 0.172 0.040 0.252 0.036 0.468
#> GSM486752 4 0.931 0.24287 0.108 0.076 0.224 0.312 0.092 0.188
#> GSM486754 2 0.770 0.10424 0.036 0.388 0.016 0.128 0.076 0.356
#> GSM486756 2 0.836 0.18261 0.036 0.372 0.040 0.116 0.136 0.300
#> GSM486758 3 0.870 0.21063 0.080 0.088 0.440 0.144 0.168 0.080
#> GSM486760 1 0.742 0.32684 0.484 0.044 0.232 0.032 0.188 0.020
#> GSM486762 3 0.872 0.13141 0.164 0.036 0.356 0.268 0.104 0.072
#> GSM486764 5 0.898 0.33772 0.120 0.112 0.112 0.068 0.400 0.188
#> GSM486766 3 0.552 0.35967 0.216 0.004 0.660 0.052 0.060 0.008
#> GSM486768 2 0.906 0.14481 0.128 0.328 0.032 0.136 0.136 0.240
#> GSM486770 6 0.393 0.40720 0.004 0.068 0.008 0.088 0.020 0.812
#> GSM486772 2 0.753 0.14181 0.092 0.404 0.008 0.076 0.056 0.364
#> GSM486774 4 0.905 0.19718 0.028 0.216 0.164 0.264 0.076 0.252
#> GSM486776 1 0.757 0.26003 0.460 0.052 0.256 0.044 0.176 0.012
#> GSM486778 3 0.879 0.16545 0.268 0.036 0.344 0.108 0.168 0.076
#> GSM486780 2 0.864 0.22153 0.132 0.456 0.116 0.124 0.112 0.060
#> GSM486782 6 0.755 0.03137 0.012 0.136 0.052 0.324 0.048 0.428
#> GSM486784 2 0.811 0.27439 0.092 0.508 0.044 0.132 0.088 0.136
#> GSM486786 3 0.759 0.28400 0.184 0.036 0.520 0.092 0.144 0.024
#> GSM486788 1 0.627 0.33904 0.632 0.044 0.068 0.044 0.200 0.012
#> GSM486790 6 0.655 0.23239 0.008 0.236 0.008 0.140 0.052 0.556
#> GSM486792 5 0.770 0.12781 0.292 0.028 0.176 0.024 0.424 0.056
#> GSM486794 3 0.663 0.40762 0.120 0.020 0.632 0.076 0.116 0.036
#> GSM486796 1 0.897 -0.00375 0.380 0.156 0.072 0.076 0.212 0.104
#> GSM486798 4 0.945 0.25628 0.080 0.100 0.228 0.280 0.112 0.200
#> GSM486800 1 0.611 0.39747 0.632 0.024 0.152 0.028 0.156 0.008
#> GSM486802 1 0.737 0.29234 0.580 0.084 0.068 0.072 0.152 0.044
#> GSM486804 1 0.894 0.19504 0.372 0.120 0.216 0.080 0.160 0.052
#> GSM486806 4 0.757 0.16343 0.016 0.076 0.108 0.476 0.048 0.276
#> GSM486808 3 0.704 0.31588 0.236 0.012 0.524 0.144 0.068 0.016
#> GSM486810 6 0.725 0.31672 0.012 0.144 0.040 0.164 0.088 0.552
#> GSM486812 3 0.734 0.09239 0.380 0.016 0.400 0.064 0.116 0.024
#> GSM486814 2 0.830 0.28421 0.100 0.492 0.048 0.136 0.108 0.116
#> GSM486816 3 0.763 0.33599 0.196 0.072 0.520 0.056 0.132 0.024
#> GSM486818 1 0.948 -0.02073 0.260 0.184 0.124 0.152 0.228 0.052
#> GSM486821 5 0.933 0.24393 0.156 0.136 0.068 0.132 0.348 0.160
#> GSM486823 6 0.598 0.24479 0.004 0.124 0.008 0.240 0.028 0.596
#> GSM486826 1 0.859 0.21735 0.376 0.112 0.196 0.076 0.220 0.020
#> GSM486830 6 0.840 0.01235 0.028 0.148 0.076 0.304 0.076 0.368
#> GSM486832 1 0.700 0.32468 0.552 0.040 0.156 0.036 0.200 0.016
#> GSM486834 4 0.914 0.26563 0.088 0.080 0.204 0.360 0.100 0.168
#> GSM486836 1 0.647 0.34912 0.608 0.040 0.084 0.032 0.216 0.020
#> GSM486838 4 0.884 0.24109 0.076 0.148 0.152 0.428 0.096 0.100
#> GSM486840 1 0.592 0.40781 0.672 0.052 0.144 0.036 0.092 0.004
#> GSM486842 3 0.651 0.14224 0.396 0.012 0.456 0.052 0.076 0.008
#> GSM486844 1 0.874 0.19026 0.392 0.168 0.160 0.112 0.148 0.020
#> GSM486846 4 0.816 0.10203 0.024 0.232 0.072 0.352 0.036 0.284
#> GSM486848 1 0.729 0.35711 0.528 0.092 0.176 0.040 0.160 0.004
#> GSM486850 2 0.777 0.00294 0.016 0.376 0.032 0.280 0.048 0.248
#> GSM486852 5 0.839 0.35356 0.232 0.076 0.060 0.036 0.408 0.188
#> GSM486854 4 0.790 0.16905 0.016 0.252 0.064 0.420 0.044 0.204
#> GSM486856 2 0.763 0.30398 0.084 0.544 0.032 0.164 0.064 0.112
#> GSM486858 4 0.892 0.09502 0.028 0.268 0.112 0.324 0.112 0.156
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> CV:skmeans 109 0.920 2.01e-05 2
#> CV:skmeans 60 0.585 1.03e-04 3
#> CV:skmeans 12 NA NA 4
#> CV:skmeans 0 NA NA 5
#> CV:skmeans 0 NA NA 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["CV", "pam"]
# you can also extract it by
# res = res_list["CV:pam"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'CV' method.
#> Subgroups are detected by 'pam' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.118 0.551 0.776 0.4736 0.532 0.532
#> 3 3 0.207 0.529 0.736 0.3665 0.713 0.508
#> 4 4 0.347 0.469 0.705 0.1378 0.798 0.498
#> 5 5 0.431 0.473 0.679 0.0669 0.919 0.698
#> 6 6 0.479 0.391 0.656 0.0287 0.980 0.906
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 2 0.3114 0.6749 0.056 0.944
#> GSM486737 1 0.7528 0.6543 0.784 0.216
#> GSM486739 2 0.6623 0.6807 0.172 0.828
#> GSM486741 2 0.9608 0.2890 0.384 0.616
#> GSM486743 1 0.9881 -0.2444 0.564 0.436
#> GSM486745 2 0.9896 0.4469 0.440 0.560
#> GSM486747 1 0.9922 0.3758 0.552 0.448
#> GSM486749 2 0.5178 0.6719 0.116 0.884
#> GSM486751 1 0.9580 0.4679 0.620 0.380
#> GSM486753 2 0.7602 0.6550 0.220 0.780
#> GSM486755 2 0.6247 0.6827 0.156 0.844
#> GSM486757 2 0.9970 -0.0380 0.468 0.532
#> GSM486759 1 0.2603 0.7245 0.956 0.044
#> GSM486761 1 0.9944 0.3688 0.544 0.456
#> GSM486763 2 0.9044 0.5677 0.320 0.680
#> GSM486765 1 0.9686 0.4421 0.604 0.396
#> GSM486767 2 0.7139 0.6676 0.196 0.804
#> GSM486769 2 0.3431 0.6795 0.064 0.936
#> GSM486771 2 0.9944 0.4408 0.456 0.544
#> GSM486773 1 0.9922 0.2719 0.552 0.448
#> GSM486775 1 0.1414 0.7162 0.980 0.020
#> GSM486777 1 0.8081 0.6382 0.752 0.248
#> GSM486779 2 0.9358 0.5638 0.352 0.648
#> GSM486781 1 0.9983 0.3398 0.524 0.476
#> GSM486783 1 0.8608 0.5999 0.716 0.284
#> GSM486785 1 0.7056 0.6659 0.808 0.192
#> GSM486787 1 0.1414 0.7207 0.980 0.020
#> GSM486789 2 0.1843 0.6689 0.028 0.972
#> GSM486791 1 0.7453 0.5832 0.788 0.212
#> GSM486793 1 0.9988 0.3071 0.520 0.480
#> GSM486795 1 0.1184 0.7203 0.984 0.016
#> GSM486797 1 0.8144 0.6344 0.748 0.252
#> GSM486799 1 0.4815 0.6828 0.896 0.104
#> GSM486801 1 0.0672 0.7200 0.992 0.008
#> GSM486803 1 0.0938 0.7209 0.988 0.012
#> GSM486805 2 0.9129 0.3542 0.328 0.672
#> GSM486807 1 0.6343 0.6964 0.840 0.160
#> GSM486809 2 0.9286 0.5427 0.344 0.656
#> GSM486811 1 0.2948 0.7238 0.948 0.052
#> GSM486813 1 0.2778 0.7075 0.952 0.048
#> GSM486815 2 0.5059 0.6847 0.112 0.888
#> GSM486817 1 0.9460 0.3964 0.636 0.364
#> GSM486819 1 0.4161 0.6894 0.916 0.084
#> GSM486822 2 0.9209 0.5099 0.336 0.664
#> GSM486824 1 0.3584 0.7258 0.932 0.068
#> GSM486828 2 0.9988 0.3473 0.480 0.520
#> GSM486831 1 0.1843 0.7164 0.972 0.028
#> GSM486833 2 0.9754 0.0558 0.408 0.592
#> GSM486835 1 0.0938 0.7194 0.988 0.012
#> GSM486837 1 0.9977 0.3301 0.528 0.472
#> GSM486839 1 0.0672 0.7185 0.992 0.008
#> GSM486841 1 0.9815 0.4152 0.580 0.420
#> GSM486843 1 0.3431 0.7263 0.936 0.064
#> GSM486845 1 0.7453 0.6596 0.788 0.212
#> GSM486847 1 0.0938 0.7189 0.988 0.012
#> GSM486849 2 0.5737 0.6792 0.136 0.864
#> GSM486851 2 0.9909 0.4529 0.444 0.556
#> GSM486853 2 0.9998 -0.2817 0.492 0.508
#> GSM486855 1 0.8386 0.5952 0.732 0.268
#> GSM486857 1 0.8713 0.6027 0.708 0.292
#> GSM486736 2 0.7376 0.6729 0.208 0.792
#> GSM486738 1 0.9977 -0.1392 0.528 0.472
#> GSM486740 2 0.9661 0.5085 0.392 0.608
#> GSM486742 1 0.7674 0.6522 0.776 0.224
#> GSM486744 2 0.9954 0.4156 0.460 0.540
#> GSM486746 1 0.9933 -0.2814 0.548 0.452
#> GSM486748 1 0.9909 0.3841 0.556 0.444
#> GSM486750 2 0.9552 0.3894 0.376 0.624
#> GSM486752 1 0.9922 0.3701 0.552 0.448
#> GSM486754 2 0.8267 0.6332 0.260 0.740
#> GSM486756 2 0.6623 0.6710 0.172 0.828
#> GSM486758 2 0.4022 0.6790 0.080 0.920
#> GSM486760 1 0.7139 0.6553 0.804 0.196
#> GSM486762 1 0.9954 0.3577 0.540 0.460
#> GSM486764 2 0.9686 0.5160 0.396 0.604
#> GSM486766 1 0.9209 0.5137 0.664 0.336
#> GSM486768 1 0.1843 0.7137 0.972 0.028
#> GSM486770 2 0.2043 0.6699 0.032 0.968
#> GSM486772 1 0.6048 0.6522 0.852 0.148
#> GSM486774 2 0.6973 0.6320 0.188 0.812
#> GSM486776 1 0.2948 0.7254 0.948 0.052
#> GSM486778 1 0.8081 0.6353 0.752 0.248
#> GSM486780 2 0.6712 0.6827 0.176 0.824
#> GSM486782 2 0.3879 0.6753 0.076 0.924
#> GSM486784 1 0.4815 0.6749 0.896 0.104
#> GSM486786 1 0.6531 0.6945 0.832 0.168
#> GSM486788 1 0.0938 0.7174 0.988 0.012
#> GSM486790 2 0.1843 0.6677 0.028 0.972
#> GSM486792 1 0.7219 0.5107 0.800 0.200
#> GSM486794 1 0.5178 0.7058 0.884 0.116
#> GSM486796 1 0.3114 0.7120 0.944 0.056
#> GSM486798 2 0.8016 0.5716 0.244 0.756
#> GSM486800 1 0.0672 0.7168 0.992 0.008
#> GSM486802 1 0.1184 0.7207 0.984 0.016
#> GSM486804 1 0.1414 0.7220 0.980 0.020
#> GSM486806 1 0.9775 0.4209 0.588 0.412
#> GSM486808 1 0.9460 0.4760 0.636 0.364
#> GSM486810 2 0.0938 0.6551 0.012 0.988
#> GSM486812 1 0.2043 0.7207 0.968 0.032
#> GSM486814 1 0.4161 0.7224 0.916 0.084
#> GSM486816 2 0.9635 0.2201 0.388 0.612
#> GSM486818 1 0.7376 0.6822 0.792 0.208
#> GSM486821 1 0.8909 0.3666 0.692 0.308
#> GSM486823 2 0.7950 0.5466 0.240 0.760
#> GSM486826 1 0.4431 0.7196 0.908 0.092
#> GSM486830 2 0.4022 0.6834 0.080 0.920
#> GSM486832 1 0.1843 0.7240 0.972 0.028
#> GSM486834 1 0.9909 0.3732 0.556 0.444
#> GSM486836 1 0.0672 0.7200 0.992 0.008
#> GSM486838 1 0.9795 0.4417 0.584 0.416
#> GSM486840 1 0.0672 0.7169 0.992 0.008
#> GSM486842 1 0.4161 0.7212 0.916 0.084
#> GSM486844 1 0.1184 0.7174 0.984 0.016
#> GSM486846 1 0.7674 0.6524 0.776 0.224
#> GSM486848 1 0.0000 0.7179 1.000 0.000
#> GSM486850 2 0.9866 0.0197 0.432 0.568
#> GSM486852 2 0.9850 0.4631 0.428 0.572
#> GSM486854 2 0.7376 0.5762 0.208 0.792
#> GSM486856 1 0.2948 0.7112 0.948 0.052
#> GSM486858 1 0.9970 0.3339 0.532 0.468
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 2 0.4233 0.631791 0.004 0.836 0.160
#> GSM486737 1 0.7677 0.476582 0.676 0.120 0.204
#> GSM486739 2 0.1636 0.705746 0.020 0.964 0.016
#> GSM486741 3 0.8716 0.507671 0.240 0.172 0.588
#> GSM486743 2 0.7099 0.458867 0.384 0.588 0.028
#> GSM486745 2 0.4750 0.674765 0.216 0.784 0.000
#> GSM486747 3 0.3573 0.645986 0.120 0.004 0.876
#> GSM486749 3 0.7152 -0.000152 0.024 0.444 0.532
#> GSM486751 3 0.6632 0.463790 0.392 0.012 0.596
#> GSM486753 2 0.3155 0.705193 0.040 0.916 0.044
#> GSM486755 2 0.5377 0.712306 0.112 0.820 0.068
#> GSM486757 3 0.8455 0.576855 0.296 0.120 0.584
#> GSM486759 1 0.4137 0.716135 0.872 0.032 0.096
#> GSM486761 3 0.5331 0.657377 0.184 0.024 0.792
#> GSM486763 2 0.3713 0.708852 0.032 0.892 0.076
#> GSM486765 3 0.6673 0.594741 0.224 0.056 0.720
#> GSM486767 2 0.8779 0.487952 0.164 0.576 0.260
#> GSM486769 2 0.3370 0.702912 0.024 0.904 0.072
#> GSM486771 2 0.6361 0.658920 0.232 0.728 0.040
#> GSM486773 1 0.9550 -0.254490 0.436 0.196 0.368
#> GSM486775 1 0.0237 0.722925 0.996 0.004 0.000
#> GSM486777 1 0.8437 0.439908 0.596 0.128 0.276
#> GSM486779 2 0.7319 0.641742 0.128 0.708 0.164
#> GSM486781 3 0.7344 0.604212 0.232 0.084 0.684
#> GSM486783 1 0.8608 -0.065788 0.488 0.100 0.412
#> GSM486785 1 0.6713 0.286333 0.572 0.012 0.416
#> GSM486787 1 0.2772 0.720586 0.916 0.004 0.080
#> GSM486789 2 0.3272 0.700703 0.004 0.892 0.104
#> GSM486791 1 0.7512 0.461157 0.656 0.268 0.076
#> GSM486793 3 0.4007 0.636099 0.084 0.036 0.880
#> GSM486795 1 0.1964 0.725689 0.944 0.000 0.056
#> GSM486797 3 0.7466 -0.051006 0.444 0.036 0.520
#> GSM486799 1 0.7107 0.601935 0.712 0.092 0.196
#> GSM486801 1 0.0237 0.724052 0.996 0.000 0.004
#> GSM486803 1 0.5503 0.666063 0.772 0.020 0.208
#> GSM486805 3 0.6529 0.584550 0.092 0.152 0.756
#> GSM486807 1 0.5061 0.640010 0.784 0.008 0.208
#> GSM486809 2 0.6728 0.632844 0.128 0.748 0.124
#> GSM486811 1 0.5681 0.622622 0.748 0.016 0.236
#> GSM486813 1 0.2681 0.715853 0.932 0.028 0.040
#> GSM486815 2 0.7748 0.210350 0.048 0.500 0.452
#> GSM486817 3 0.9228 0.218791 0.416 0.152 0.432
#> GSM486819 1 0.5891 0.624694 0.780 0.168 0.052
#> GSM486822 2 0.9571 0.117420 0.224 0.472 0.304
#> GSM486824 1 0.5947 0.676245 0.776 0.052 0.172
#> GSM486828 2 0.9760 0.269290 0.280 0.444 0.276
#> GSM486831 1 0.1636 0.726010 0.964 0.016 0.020
#> GSM486833 3 0.2414 0.605274 0.020 0.040 0.940
#> GSM486835 1 0.0747 0.726945 0.984 0.000 0.016
#> GSM486837 3 0.6007 0.615839 0.184 0.048 0.768
#> GSM486839 1 0.0475 0.725329 0.992 0.004 0.004
#> GSM486841 3 0.3933 0.638498 0.092 0.028 0.880
#> GSM486843 1 0.3539 0.721515 0.888 0.012 0.100
#> GSM486845 1 0.7820 0.294384 0.604 0.072 0.324
#> GSM486847 1 0.4228 0.687200 0.844 0.008 0.148
#> GSM486849 3 0.7013 -0.043539 0.020 0.432 0.548
#> GSM486851 2 0.6229 0.651326 0.064 0.764 0.172
#> GSM486853 3 0.6728 0.613804 0.184 0.080 0.736
#> GSM486855 1 0.9847 -0.013402 0.416 0.316 0.268
#> GSM486857 3 0.8268 0.105150 0.440 0.076 0.484
#> GSM486736 2 0.3530 0.714716 0.068 0.900 0.032
#> GSM486738 1 0.9693 -0.183677 0.404 0.216 0.380
#> GSM486740 2 0.2356 0.707025 0.072 0.928 0.000
#> GSM486742 1 0.7841 0.368779 0.636 0.092 0.272
#> GSM486744 2 0.8222 0.473901 0.332 0.576 0.092
#> GSM486746 2 0.5785 0.573449 0.332 0.668 0.000
#> GSM486748 3 0.6962 0.573549 0.316 0.036 0.648
#> GSM486750 2 0.9604 0.034073 0.268 0.476 0.256
#> GSM486752 3 0.7032 0.495305 0.368 0.028 0.604
#> GSM486754 2 0.7085 0.636959 0.096 0.716 0.188
#> GSM486756 2 0.7401 0.399754 0.048 0.612 0.340
#> GSM486758 3 0.7228 0.260140 0.036 0.364 0.600
#> GSM486760 1 0.7533 0.326468 0.564 0.044 0.392
#> GSM486762 3 0.5514 0.651708 0.156 0.044 0.800
#> GSM486764 2 0.3550 0.712669 0.080 0.896 0.024
#> GSM486766 3 0.5656 0.491100 0.264 0.008 0.728
#> GSM486768 1 0.1015 0.723205 0.980 0.012 0.008
#> GSM486770 2 0.1765 0.698125 0.004 0.956 0.040
#> GSM486772 1 0.5173 0.653058 0.816 0.148 0.036
#> GSM486774 3 0.7884 0.493616 0.104 0.252 0.644
#> GSM486776 1 0.5239 0.688821 0.808 0.032 0.160
#> GSM486778 1 0.7112 0.452793 0.648 0.044 0.308
#> GSM486780 2 0.8739 0.204646 0.112 0.496 0.392
#> GSM486782 3 0.6713 0.108893 0.012 0.416 0.572
#> GSM486784 1 0.4836 0.687280 0.848 0.080 0.072
#> GSM486786 1 0.6737 0.408946 0.600 0.016 0.384
#> GSM486788 1 0.0237 0.723395 0.996 0.000 0.004
#> GSM486790 2 0.3349 0.699601 0.004 0.888 0.108
#> GSM486792 1 0.7935 0.501346 0.648 0.236 0.116
#> GSM486794 1 0.6018 0.528257 0.684 0.008 0.308
#> GSM486796 1 0.3129 0.709024 0.904 0.088 0.008
#> GSM486798 3 0.6726 0.572361 0.120 0.132 0.748
#> GSM486800 1 0.1163 0.726444 0.972 0.000 0.028
#> GSM486802 1 0.0424 0.724349 0.992 0.000 0.008
#> GSM486804 1 0.0592 0.726392 0.988 0.000 0.012
#> GSM486806 3 0.6688 0.464819 0.408 0.012 0.580
#> GSM486808 3 0.5578 0.531287 0.240 0.012 0.748
#> GSM486810 3 0.5948 0.302465 0.000 0.360 0.640
#> GSM486812 1 0.5406 0.630691 0.764 0.012 0.224
#> GSM486814 1 0.5961 0.687272 0.792 0.096 0.112
#> GSM486816 3 0.7007 0.594980 0.176 0.100 0.724
#> GSM486818 1 0.7944 0.472596 0.616 0.088 0.296
#> GSM486821 1 0.8297 0.278887 0.560 0.348 0.092
#> GSM486823 3 0.7531 0.503854 0.092 0.236 0.672
#> GSM486826 1 0.5506 0.636235 0.764 0.016 0.220
#> GSM486830 2 0.4002 0.639992 0.000 0.840 0.160
#> GSM486832 1 0.2527 0.727965 0.936 0.020 0.044
#> GSM486834 3 0.4979 0.663547 0.168 0.020 0.812
#> GSM486836 1 0.1170 0.726109 0.976 0.008 0.016
#> GSM486838 3 0.6625 0.501479 0.316 0.024 0.660
#> GSM486840 1 0.0000 0.723251 1.000 0.000 0.000
#> GSM486842 1 0.6113 0.564025 0.688 0.012 0.300
#> GSM486844 1 0.0237 0.722925 0.996 0.004 0.000
#> GSM486846 1 0.7997 0.174604 0.568 0.072 0.360
#> GSM486848 1 0.0592 0.726522 0.988 0.000 0.012
#> GSM486850 3 0.8877 0.576150 0.244 0.184 0.572
#> GSM486852 2 0.6843 0.652539 0.144 0.740 0.116
#> GSM486854 3 0.8223 0.452260 0.108 0.288 0.604
#> GSM486856 1 0.4731 0.647764 0.840 0.032 0.128
#> GSM486858 3 0.7749 0.579173 0.300 0.076 0.624
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 4 0.3903 0.68901 0.080 0.076 0.000 0.844
#> GSM486737 3 0.6538 0.10637 0.012 0.396 0.540 0.052
#> GSM486739 4 0.0336 0.72378 0.000 0.008 0.000 0.992
#> GSM486741 2 0.4476 0.61107 0.080 0.832 0.064 0.024
#> GSM486743 4 0.7031 0.40810 0.032 0.060 0.356 0.552
#> GSM486745 4 0.3569 0.67913 0.000 0.000 0.196 0.804
#> GSM486747 1 0.4050 0.43290 0.820 0.144 0.036 0.000
#> GSM486749 2 0.7752 0.25742 0.348 0.460 0.008 0.184
#> GSM486751 1 0.7735 0.19088 0.468 0.184 0.340 0.008
#> GSM486753 4 0.3681 0.68188 0.000 0.176 0.008 0.816
#> GSM486755 4 0.5442 0.69221 0.016 0.128 0.092 0.764
#> GSM486757 1 0.8370 0.17596 0.484 0.284 0.188 0.044
#> GSM486759 3 0.4720 0.62696 0.212 0.008 0.760 0.020
#> GSM486761 2 0.7430 0.16279 0.392 0.456 0.148 0.004
#> GSM486763 4 0.3263 0.71640 0.100 0.012 0.012 0.876
#> GSM486765 1 0.4614 0.46196 0.792 0.144 0.064 0.000
#> GSM486767 4 0.8422 0.51477 0.184 0.120 0.140 0.556
#> GSM486769 4 0.1929 0.72619 0.036 0.024 0.000 0.940
#> GSM486771 4 0.6492 0.62203 0.008 0.140 0.188 0.664
#> GSM486773 3 0.9471 -0.13062 0.280 0.160 0.396 0.164
#> GSM486775 3 0.0000 0.72093 0.000 0.000 1.000 0.000
#> GSM486777 1 0.8006 0.18568 0.440 0.136 0.392 0.032
#> GSM486779 4 0.7295 0.59149 0.116 0.148 0.080 0.656
#> GSM486781 2 0.5797 0.56958 0.180 0.724 0.084 0.012
#> GSM486783 2 0.4572 0.59819 0.024 0.796 0.164 0.016
#> GSM486785 1 0.6640 0.31192 0.552 0.096 0.352 0.000
#> GSM486787 3 0.3528 0.63131 0.192 0.000 0.808 0.000
#> GSM486789 4 0.1488 0.72929 0.032 0.012 0.000 0.956
#> GSM486791 3 0.6443 0.46498 0.068 0.016 0.636 0.280
#> GSM486793 1 0.2402 0.47504 0.912 0.076 0.012 0.000
#> GSM486795 3 0.2011 0.70994 0.080 0.000 0.920 0.000
#> GSM486797 2 0.7385 0.34032 0.284 0.544 0.164 0.008
#> GSM486799 1 0.5552 0.07009 0.544 0.008 0.440 0.008
#> GSM486801 3 0.0000 0.72093 0.000 0.000 1.000 0.000
#> GSM486803 3 0.6676 0.09996 0.448 0.056 0.484 0.012
#> GSM486805 2 0.5962 0.48870 0.264 0.676 0.032 0.028
#> GSM486807 3 0.6404 0.42850 0.220 0.136 0.644 0.000
#> GSM486809 4 0.7248 0.44858 0.032 0.284 0.096 0.588
#> GSM486811 1 0.5097 0.17789 0.568 0.004 0.428 0.000
#> GSM486813 3 0.2563 0.71046 0.000 0.072 0.908 0.020
#> GSM486815 1 0.5797 0.36332 0.684 0.064 0.004 0.248
#> GSM486817 2 0.8245 0.42571 0.084 0.520 0.292 0.104
#> GSM486819 3 0.5797 0.59476 0.024 0.060 0.728 0.188
#> GSM486822 2 0.4700 0.58688 0.000 0.792 0.084 0.124
#> GSM486824 3 0.6642 0.36474 0.348 0.028 0.580 0.044
#> GSM486828 4 0.9121 -0.08078 0.076 0.328 0.224 0.372
#> GSM486831 3 0.1824 0.71857 0.060 0.004 0.936 0.000
#> GSM486833 1 0.5119 -0.01524 0.556 0.440 0.000 0.004
#> GSM486835 3 0.1305 0.72636 0.036 0.004 0.960 0.000
#> GSM486837 2 0.3853 0.56341 0.160 0.820 0.020 0.000
#> GSM486839 3 0.1118 0.72592 0.036 0.000 0.964 0.000
#> GSM486841 1 0.3280 0.45675 0.860 0.124 0.016 0.000
#> GSM486843 3 0.4314 0.67161 0.152 0.024 0.812 0.012
#> GSM486845 2 0.5282 0.54162 0.036 0.688 0.276 0.000
#> GSM486847 3 0.4933 0.22619 0.432 0.000 0.568 0.000
#> GSM486849 2 0.6552 0.38125 0.328 0.576 0.000 0.096
#> GSM486851 4 0.4936 0.44666 0.340 0.000 0.008 0.652
#> GSM486853 2 0.4519 0.58136 0.140 0.804 0.052 0.004
#> GSM486855 2 0.5802 0.57634 0.008 0.724 0.164 0.104
#> GSM486857 1 0.8220 0.13543 0.408 0.236 0.340 0.016
#> GSM486736 4 0.1631 0.73390 0.016 0.008 0.020 0.956
#> GSM486738 2 0.6016 0.52144 0.016 0.692 0.228 0.064
#> GSM486740 4 0.0336 0.72543 0.000 0.000 0.008 0.992
#> GSM486742 2 0.4695 0.55342 0.012 0.732 0.252 0.004
#> GSM486744 4 0.7973 0.45922 0.060 0.112 0.288 0.540
#> GSM486746 4 0.4832 0.56520 0.004 0.004 0.312 0.680
#> GSM486748 1 0.7767 0.14547 0.432 0.268 0.300 0.000
#> GSM486750 2 0.9153 0.11290 0.076 0.376 0.240 0.308
#> GSM486752 1 0.7730 0.25813 0.512 0.196 0.280 0.012
#> GSM486754 4 0.6108 0.66223 0.096 0.112 0.052 0.740
#> GSM486756 4 0.6851 0.50893 0.208 0.136 0.016 0.640
#> GSM486758 1 0.8078 0.05219 0.464 0.232 0.016 0.288
#> GSM486760 1 0.5400 0.41660 0.684 0.012 0.284 0.020
#> GSM486762 1 0.6249 0.21881 0.580 0.352 0.068 0.000
#> GSM486764 4 0.2353 0.73178 0.040 0.008 0.024 0.928
#> GSM486766 1 0.1059 0.48906 0.972 0.012 0.016 0.000
#> GSM486768 3 0.0937 0.72414 0.000 0.012 0.976 0.012
#> GSM486770 4 0.0188 0.72389 0.000 0.004 0.000 0.996
#> GSM486772 3 0.5457 0.61701 0.016 0.100 0.764 0.120
#> GSM486774 2 0.6946 0.50945 0.196 0.652 0.032 0.120
#> GSM486776 3 0.6343 0.26760 0.392 0.036 0.556 0.016
#> GSM486778 3 0.6956 0.14663 0.352 0.108 0.536 0.004
#> GSM486780 2 0.4726 0.56409 0.004 0.784 0.048 0.164
#> GSM486782 1 0.7876 -0.06917 0.396 0.224 0.004 0.376
#> GSM486784 3 0.5099 0.61507 0.004 0.200 0.748 0.048
#> GSM486786 1 0.6310 0.24134 0.540 0.052 0.404 0.004
#> GSM486788 3 0.0817 0.72452 0.024 0.000 0.976 0.000
#> GSM486790 4 0.1674 0.72947 0.032 0.012 0.004 0.952
#> GSM486792 3 0.7473 0.36216 0.232 0.008 0.548 0.212
#> GSM486794 1 0.5088 0.20806 0.572 0.004 0.424 0.000
#> GSM486796 3 0.3417 0.69985 0.008 0.052 0.880 0.060
#> GSM486798 1 0.6844 0.34640 0.648 0.236 0.044 0.072
#> GSM486800 3 0.2125 0.71516 0.076 0.004 0.920 0.000
#> GSM486802 3 0.0000 0.72093 0.000 0.000 1.000 0.000
#> GSM486804 3 0.0469 0.72451 0.012 0.000 0.988 0.000
#> GSM486806 2 0.8184 0.00942 0.304 0.352 0.336 0.008
#> GSM486808 1 0.2973 0.47462 0.884 0.096 0.020 0.000
#> GSM486810 2 0.4801 0.53813 0.188 0.764 0.000 0.048
#> GSM486812 1 0.4888 0.20041 0.588 0.000 0.412 0.000
#> GSM486814 3 0.7332 0.50318 0.172 0.168 0.624 0.036
#> GSM486816 1 0.3959 0.49003 0.856 0.076 0.052 0.016
#> GSM486818 3 0.7706 0.33353 0.320 0.080 0.540 0.060
#> GSM486821 3 0.7578 0.27922 0.040 0.092 0.532 0.336
#> GSM486823 2 0.6256 0.55697 0.204 0.688 0.016 0.092
#> GSM486826 3 0.5351 0.51385 0.280 0.024 0.688 0.008
#> GSM486830 4 0.5099 0.33063 0.008 0.380 0.000 0.612
#> GSM486832 3 0.2610 0.71426 0.088 0.000 0.900 0.012
#> GSM486834 1 0.6767 0.09949 0.536 0.372 0.088 0.004
#> GSM486836 3 0.1398 0.72455 0.040 0.000 0.956 0.004
#> GSM486838 2 0.7610 0.31026 0.284 0.500 0.212 0.004
#> GSM486840 3 0.0469 0.72354 0.012 0.000 0.988 0.000
#> GSM486842 1 0.5244 0.27429 0.600 0.012 0.388 0.000
#> GSM486844 3 0.0000 0.72093 0.000 0.000 1.000 0.000
#> GSM486846 2 0.5141 0.54928 0.032 0.700 0.268 0.000
#> GSM486848 3 0.0817 0.72541 0.024 0.000 0.976 0.000
#> GSM486850 2 0.5751 0.59343 0.092 0.760 0.108 0.040
#> GSM486852 4 0.6158 0.63144 0.172 0.024 0.092 0.712
#> GSM486854 2 0.7947 0.45233 0.188 0.580 0.060 0.172
#> GSM486856 3 0.4647 0.50232 0.000 0.288 0.704 0.008
#> GSM486858 2 0.6850 0.43506 0.188 0.600 0.212 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 5 0.3427 0.63813 0.008 0.000 0.128 0.028 0.836
#> GSM486737 2 0.6791 0.15622 0.024 0.508 0.048 0.372 0.048
#> GSM486739 5 0.0162 0.68793 0.000 0.000 0.000 0.004 0.996
#> GSM486741 4 0.4464 0.55732 0.020 0.028 0.160 0.780 0.012
#> GSM486743 5 0.7882 0.35519 0.056 0.312 0.072 0.080 0.480
#> GSM486745 5 0.3838 0.65528 0.008 0.176 0.008 0.012 0.796
#> GSM486747 3 0.5714 0.26983 0.412 0.020 0.524 0.044 0.000
#> GSM486749 4 0.7982 0.20852 0.308 0.008 0.100 0.428 0.156
#> GSM486751 3 0.4631 0.56359 0.076 0.164 0.752 0.008 0.000
#> GSM486753 5 0.4965 0.62561 0.020 0.004 0.048 0.200 0.728
#> GSM486755 5 0.6098 0.62810 0.012 0.092 0.060 0.148 0.688
#> GSM486757 3 0.6897 0.51864 0.152 0.108 0.628 0.096 0.016
#> GSM486759 2 0.4908 0.48278 0.324 0.644 0.016 0.004 0.012
#> GSM486761 3 0.5374 0.49747 0.060 0.064 0.724 0.152 0.000
#> GSM486763 5 0.3349 0.66978 0.120 0.008 0.012 0.012 0.848
#> GSM486765 1 0.5881 0.39623 0.656 0.040 0.220 0.084 0.000
#> GSM486767 5 0.8207 0.31480 0.136 0.056 0.296 0.060 0.452
#> GSM486769 5 0.2054 0.67972 0.008 0.000 0.072 0.004 0.916
#> GSM486771 5 0.8007 0.50227 0.044 0.128 0.112 0.180 0.536
#> GSM486773 3 0.6797 0.41720 0.016 0.284 0.556 0.024 0.120
#> GSM486775 2 0.0000 0.69500 0.000 1.000 0.000 0.000 0.000
#> GSM486777 1 0.6211 0.49550 0.572 0.312 0.008 0.096 0.012
#> GSM486779 5 0.7937 0.49060 0.140 0.056 0.144 0.104 0.556
#> GSM486781 4 0.5979 0.36101 0.016 0.060 0.348 0.568 0.008
#> GSM486783 4 0.3001 0.57966 0.012 0.044 0.056 0.884 0.004
#> GSM486785 1 0.7381 0.41808 0.456 0.320 0.164 0.060 0.000
#> GSM486787 2 0.3508 0.50953 0.252 0.748 0.000 0.000 0.000
#> GSM486789 5 0.1877 0.68822 0.000 0.000 0.064 0.012 0.924
#> GSM486791 2 0.6329 0.44418 0.064 0.592 0.064 0.000 0.280
#> GSM486793 1 0.4305 0.46091 0.744 0.004 0.216 0.036 0.000
#> GSM486795 2 0.1732 0.67812 0.080 0.920 0.000 0.000 0.000
#> GSM486797 4 0.8118 0.24915 0.256 0.108 0.192 0.436 0.008
#> GSM486799 1 0.4503 0.59614 0.704 0.256 0.040 0.000 0.000
#> GSM486801 2 0.0000 0.69500 0.000 1.000 0.000 0.000 0.000
#> GSM486803 1 0.5079 0.49810 0.644 0.316 0.012 0.020 0.008
#> GSM486805 3 0.5767 0.14099 0.028 0.012 0.548 0.392 0.020
#> GSM486807 2 0.6885 0.32062 0.208 0.572 0.160 0.060 0.000
#> GSM486809 5 0.6614 0.40340 0.032 0.088 0.012 0.308 0.560
#> GSM486811 1 0.3636 0.64630 0.728 0.272 0.000 0.000 0.000
#> GSM486813 2 0.4308 0.66200 0.024 0.816 0.080 0.068 0.012
#> GSM486815 1 0.5591 0.45392 0.696 0.004 0.088 0.028 0.184
#> GSM486817 4 0.8146 0.35484 0.064 0.188 0.188 0.504 0.056
#> GSM486819 2 0.5316 0.59476 0.028 0.720 0.008 0.060 0.184
#> GSM486822 4 0.2909 0.57630 0.008 0.012 0.048 0.892 0.040
#> GSM486824 2 0.6277 0.03555 0.424 0.488 0.052 0.012 0.024
#> GSM486828 5 0.8738 -0.09258 0.052 0.204 0.076 0.332 0.336
#> GSM486831 2 0.2248 0.68749 0.088 0.900 0.012 0.000 0.000
#> GSM486833 3 0.6736 0.26252 0.344 0.000 0.396 0.260 0.000
#> GSM486835 2 0.2046 0.69668 0.068 0.916 0.016 0.000 0.000
#> GSM486837 4 0.4961 0.32965 0.028 0.004 0.372 0.596 0.000
#> GSM486839 2 0.1043 0.69797 0.040 0.960 0.000 0.000 0.000
#> GSM486841 1 0.4272 0.50866 0.780 0.008 0.152 0.060 0.000
#> GSM486843 2 0.5528 0.57590 0.196 0.696 0.076 0.028 0.004
#> GSM486845 4 0.4197 0.55329 0.036 0.156 0.020 0.788 0.000
#> GSM486847 1 0.4367 0.40653 0.580 0.416 0.004 0.000 0.000
#> GSM486849 4 0.6266 0.43290 0.232 0.000 0.088 0.624 0.056
#> GSM486851 5 0.4524 0.26798 0.420 0.004 0.004 0.000 0.572
#> GSM486853 4 0.4607 0.49283 0.024 0.020 0.212 0.740 0.004
#> GSM486855 4 0.4394 0.56674 0.028 0.068 0.056 0.820 0.028
#> GSM486857 3 0.8721 0.16512 0.200 0.276 0.312 0.204 0.008
#> GSM486736 5 0.1871 0.69620 0.004 0.012 0.020 0.024 0.940
#> GSM486738 4 0.7222 0.42487 0.048 0.148 0.184 0.588 0.032
#> GSM486740 5 0.0162 0.68707 0.000 0.000 0.000 0.004 0.996
#> GSM486742 4 0.5781 0.50642 0.032 0.148 0.140 0.680 0.000
#> GSM486744 5 0.8674 0.39006 0.044 0.228 0.164 0.128 0.436
#> GSM486746 5 0.4804 0.54982 0.020 0.284 0.012 0.004 0.680
#> GSM486748 3 0.6690 0.52339 0.112 0.184 0.612 0.092 0.000
#> GSM486750 4 0.9152 -0.00740 0.028 0.216 0.244 0.260 0.252
#> GSM486752 3 0.5173 0.57584 0.128 0.128 0.728 0.012 0.004
#> GSM486754 5 0.6441 0.38854 0.028 0.020 0.348 0.056 0.548
#> GSM486756 3 0.6747 0.03379 0.044 0.012 0.476 0.064 0.404
#> GSM486758 3 0.3681 0.53213 0.048 0.008 0.848 0.016 0.080
#> GSM486760 1 0.4042 0.64289 0.792 0.156 0.044 0.000 0.008
#> GSM486762 3 0.7241 0.40486 0.288 0.056 0.492 0.164 0.000
#> GSM486764 5 0.2869 0.69489 0.052 0.020 0.012 0.020 0.896
#> GSM486766 1 0.3388 0.51910 0.792 0.008 0.200 0.000 0.000
#> GSM486768 2 0.3613 0.68414 0.040 0.856 0.060 0.040 0.004
#> GSM486770 5 0.0162 0.68707 0.000 0.000 0.000 0.004 0.996
#> GSM486772 2 0.7046 0.50250 0.016 0.612 0.104 0.164 0.104
#> GSM486774 4 0.7686 0.19981 0.076 0.024 0.332 0.468 0.100
#> GSM486776 1 0.5700 0.21707 0.536 0.404 0.040 0.016 0.004
#> GSM486778 2 0.6807 0.04164 0.328 0.520 0.088 0.064 0.000
#> GSM486780 4 0.4706 0.54668 0.040 0.016 0.108 0.792 0.044
#> GSM486782 3 0.5604 0.44971 0.068 0.000 0.712 0.080 0.140
#> GSM486784 2 0.6984 0.46052 0.020 0.576 0.148 0.224 0.032
#> GSM486786 1 0.6016 0.55169 0.576 0.324 0.076 0.024 0.000
#> GSM486788 2 0.1270 0.69724 0.052 0.948 0.000 0.000 0.000
#> GSM486790 5 0.1270 0.68767 0.000 0.000 0.052 0.000 0.948
#> GSM486792 2 0.7150 0.17322 0.336 0.452 0.036 0.000 0.176
#> GSM486794 1 0.4805 0.59611 0.648 0.312 0.040 0.000 0.000
#> GSM486796 2 0.4955 0.66197 0.040 0.792 0.060 0.052 0.056
#> GSM486798 3 0.6757 0.35076 0.336 0.024 0.540 0.056 0.044
#> GSM486800 2 0.3047 0.65953 0.160 0.832 0.004 0.004 0.000
#> GSM486802 2 0.0162 0.69518 0.000 0.996 0.000 0.004 0.000
#> GSM486804 2 0.0727 0.69890 0.012 0.980 0.004 0.004 0.000
#> GSM486806 3 0.5467 0.49705 0.020 0.196 0.688 0.096 0.000
#> GSM486808 1 0.4629 0.42823 0.708 0.012 0.252 0.028 0.000
#> GSM486810 4 0.4311 0.56112 0.116 0.000 0.048 0.800 0.036
#> GSM486812 1 0.3607 0.65040 0.752 0.244 0.004 0.000 0.000
#> GSM486814 2 0.8355 0.30290 0.212 0.436 0.124 0.212 0.016
#> GSM486816 1 0.4845 0.47722 0.736 0.028 0.200 0.032 0.004
#> GSM486818 2 0.7861 0.23642 0.284 0.452 0.192 0.052 0.020
#> GSM486821 2 0.7628 0.22697 0.036 0.484 0.100 0.056 0.324
#> GSM486823 4 0.5539 0.40974 0.020 0.008 0.308 0.628 0.036
#> GSM486826 2 0.6081 0.39003 0.208 0.628 0.148 0.008 0.008
#> GSM486830 5 0.4928 0.18048 0.004 0.000 0.020 0.428 0.548
#> GSM486832 2 0.3938 0.67244 0.112 0.824 0.044 0.012 0.008
#> GSM486834 3 0.5962 0.53278 0.172 0.044 0.668 0.116 0.000
#> GSM486836 2 0.2116 0.69257 0.076 0.912 0.008 0.000 0.004
#> GSM486838 4 0.8343 0.11875 0.192 0.172 0.276 0.360 0.000
#> GSM486840 2 0.0404 0.69668 0.012 0.988 0.000 0.000 0.000
#> GSM486842 1 0.4848 0.60412 0.656 0.304 0.036 0.004 0.000
#> GSM486844 2 0.0000 0.69500 0.000 1.000 0.000 0.000 0.000
#> GSM486846 4 0.4191 0.55267 0.012 0.160 0.044 0.784 0.000
#> GSM486848 2 0.1082 0.69783 0.028 0.964 0.008 0.000 0.000
#> GSM486850 4 0.5332 0.52008 0.032 0.032 0.224 0.700 0.012
#> GSM486852 5 0.5742 0.58353 0.228 0.072 0.024 0.008 0.668
#> GSM486854 3 0.7728 0.00339 0.020 0.056 0.416 0.372 0.136
#> GSM486856 2 0.6004 0.40155 0.020 0.580 0.084 0.316 0.000
#> GSM486858 4 0.7316 0.08420 0.044 0.176 0.380 0.400 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 6 0.3346 0.6194 0.000 0.008 0.140 0.036 0.000 0.816
#> GSM486737 1 0.6521 -0.0655 0.476 0.052 0.020 0.388 0.020 0.044
#> GSM486739 6 0.0146 0.6661 0.000 0.004 0.000 0.000 0.000 0.996
#> GSM486741 4 0.5062 0.4289 0.020 0.128 0.128 0.712 0.004 0.008
#> GSM486743 6 0.7296 0.1555 0.304 0.172 0.012 0.028 0.040 0.444
#> GSM486745 6 0.3352 0.6087 0.176 0.032 0.000 0.000 0.000 0.792
#> GSM486747 3 0.4871 0.2154 0.012 0.000 0.532 0.036 0.420 0.000
#> GSM486749 4 0.7659 0.2178 0.004 0.044 0.088 0.428 0.296 0.140
#> GSM486751 3 0.3208 0.5498 0.120 0.008 0.832 0.000 0.040 0.000
#> GSM486753 6 0.4996 0.5410 0.004 0.232 0.004 0.104 0.000 0.656
#> GSM486755 6 0.6051 0.4987 0.084 0.220 0.012 0.072 0.000 0.612
#> GSM486757 3 0.6797 0.4670 0.076 0.112 0.612 0.088 0.108 0.004
#> GSM486759 1 0.4968 0.4132 0.580 0.048 0.008 0.000 0.360 0.004
#> GSM486761 3 0.5576 0.4405 0.040 0.084 0.660 0.200 0.016 0.000
#> GSM486763 6 0.3463 0.6422 0.008 0.024 0.008 0.008 0.124 0.828
#> GSM486765 5 0.5661 0.3837 0.032 0.008 0.244 0.096 0.620 0.000
#> GSM486767 6 0.7664 0.2483 0.028 0.260 0.244 0.004 0.072 0.392
#> GSM486769 6 0.2245 0.6646 0.000 0.012 0.068 0.012 0.004 0.904
#> GSM486771 6 0.6542 0.1615 0.092 0.416 0.020 0.048 0.000 0.424
#> GSM486773 3 0.7029 0.3899 0.256 0.052 0.536 0.064 0.008 0.084
#> GSM486775 1 0.0000 0.6390 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486777 5 0.5227 0.5202 0.292 0.004 0.008 0.076 0.616 0.004
#> GSM486779 6 0.7457 0.3471 0.040 0.284 0.060 0.044 0.076 0.496
#> GSM486781 4 0.5670 0.3711 0.048 0.064 0.264 0.616 0.004 0.004
#> GSM486783 4 0.4049 0.3521 0.024 0.224 0.012 0.736 0.000 0.004
#> GSM486785 5 0.7165 0.3726 0.304 0.024 0.156 0.068 0.448 0.000
#> GSM486787 1 0.3371 0.4488 0.708 0.000 0.000 0.000 0.292 0.000
#> GSM486789 6 0.1970 0.6658 0.000 0.000 0.092 0.008 0.000 0.900
#> GSM486791 1 0.6294 0.3265 0.576 0.036 0.064 0.000 0.056 0.268
#> GSM486793 5 0.3584 0.4866 0.000 0.004 0.244 0.012 0.740 0.000
#> GSM486795 1 0.1610 0.6367 0.916 0.000 0.000 0.000 0.084 0.000
#> GSM486797 4 0.7798 0.2448 0.088 0.092 0.128 0.496 0.188 0.008
#> GSM486799 5 0.4830 0.5779 0.204 0.048 0.048 0.000 0.700 0.000
#> GSM486801 1 0.0000 0.6390 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486803 5 0.5022 0.5120 0.268 0.060 0.004 0.008 0.652 0.008
#> GSM486805 3 0.4500 0.1990 0.008 0.008 0.612 0.360 0.008 0.004
#> GSM486807 1 0.7582 0.1940 0.500 0.092 0.108 0.100 0.200 0.000
#> GSM486809 6 0.6213 0.3798 0.088 0.024 0.004 0.300 0.028 0.556
#> GSM486811 5 0.2793 0.6404 0.200 0.000 0.000 0.000 0.800 0.000
#> GSM486813 1 0.3602 0.4998 0.784 0.176 0.000 0.032 0.000 0.008
#> GSM486815 5 0.4179 0.5128 0.000 0.000 0.060 0.020 0.760 0.160
#> GSM486817 4 0.8088 0.2494 0.136 0.120 0.188 0.476 0.032 0.048
#> GSM486819 1 0.5074 0.4813 0.704 0.000 0.012 0.060 0.040 0.184
#> GSM486822 4 0.3559 0.4356 0.008 0.116 0.028 0.824 0.000 0.024
#> GSM486824 1 0.6591 -0.0183 0.428 0.092 0.024 0.016 0.420 0.020
#> GSM486828 4 0.8085 0.0361 0.196 0.008 0.068 0.340 0.064 0.324
#> GSM486831 1 0.2763 0.6224 0.868 0.036 0.008 0.000 0.088 0.000
#> GSM486833 3 0.6211 0.2497 0.000 0.008 0.420 0.244 0.328 0.000
#> GSM486835 1 0.2151 0.6418 0.904 0.008 0.016 0.000 0.072 0.000
#> GSM486837 4 0.4405 0.3679 0.004 0.040 0.272 0.680 0.004 0.000
#> GSM486839 1 0.1010 0.6468 0.960 0.000 0.000 0.004 0.036 0.000
#> GSM486841 5 0.3266 0.5673 0.008 0.000 0.132 0.036 0.824 0.000
#> GSM486843 1 0.5600 0.5202 0.672 0.076 0.052 0.012 0.184 0.004
#> GSM486845 4 0.2656 0.4387 0.120 0.000 0.012 0.860 0.008 0.000
#> GSM486847 5 0.4221 0.3917 0.396 0.008 0.008 0.000 0.588 0.000
#> GSM486849 4 0.6747 0.2975 0.000 0.116 0.048 0.536 0.260 0.040
#> GSM486851 6 0.4517 0.1767 0.004 0.012 0.008 0.000 0.440 0.536
#> GSM486853 4 0.3053 0.4851 0.012 0.004 0.172 0.812 0.000 0.000
#> GSM486855 4 0.4785 0.1957 0.040 0.312 0.000 0.632 0.004 0.012
#> GSM486857 3 0.8391 0.2177 0.236 0.048 0.372 0.172 0.160 0.012
#> GSM486736 6 0.2202 0.6731 0.012 0.028 0.024 0.012 0.004 0.920
#> GSM486738 2 0.6543 -0.0669 0.088 0.484 0.056 0.352 0.000 0.020
#> GSM486740 6 0.0146 0.6660 0.000 0.000 0.000 0.004 0.000 0.996
#> GSM486742 4 0.5801 0.0846 0.124 0.284 0.028 0.564 0.000 0.000
#> GSM486744 6 0.7257 0.0385 0.204 0.340 0.028 0.036 0.004 0.388
#> GSM486746 6 0.4289 0.4921 0.276 0.040 0.000 0.000 0.004 0.680
#> GSM486748 3 0.5260 0.5162 0.168 0.008 0.696 0.064 0.064 0.000
#> GSM486750 4 0.9062 -0.1006 0.196 0.196 0.132 0.248 0.008 0.220
#> GSM486752 3 0.4404 0.5564 0.096 0.028 0.788 0.020 0.064 0.004
#> GSM486754 6 0.6288 0.3314 0.008 0.204 0.292 0.012 0.000 0.484
#> GSM486756 3 0.6520 0.0280 0.008 0.176 0.420 0.008 0.012 0.376
#> GSM486758 3 0.3773 0.4789 0.004 0.168 0.788 0.016 0.004 0.020
#> GSM486760 5 0.3854 0.6396 0.116 0.052 0.024 0.000 0.804 0.004
#> GSM486762 3 0.7558 0.3320 0.052 0.060 0.424 0.184 0.280 0.000
#> GSM486764 6 0.4139 0.6358 0.012 0.144 0.020 0.000 0.044 0.780
#> GSM486766 5 0.2854 0.5318 0.000 0.000 0.208 0.000 0.792 0.000
#> GSM486768 1 0.3371 0.5321 0.788 0.192 0.000 0.008 0.008 0.004
#> GSM486770 6 0.0508 0.6668 0.000 0.000 0.004 0.012 0.000 0.984
#> GSM486772 1 0.5894 -0.1096 0.516 0.364 0.008 0.028 0.000 0.084
#> GSM486774 4 0.7229 0.2098 0.016 0.036 0.312 0.480 0.060 0.096
#> GSM486776 5 0.6196 0.2243 0.360 0.140 0.008 0.012 0.476 0.004
#> GSM486778 1 0.6093 0.0150 0.504 0.000 0.072 0.072 0.352 0.000
#> GSM486780 4 0.4814 0.0573 0.008 0.404 0.012 0.556 0.000 0.020
#> GSM486782 3 0.6075 0.3959 0.000 0.212 0.612 0.036 0.024 0.116
#> GSM486784 1 0.6458 -0.3347 0.444 0.416 0.044 0.068 0.004 0.024
#> GSM486786 5 0.5124 0.5653 0.288 0.004 0.044 0.032 0.632 0.000
#> GSM486788 1 0.1141 0.6465 0.948 0.000 0.000 0.000 0.052 0.000
#> GSM486790 6 0.1226 0.6714 0.000 0.000 0.040 0.004 0.004 0.952
#> GSM486792 1 0.7298 0.1465 0.412 0.064 0.032 0.000 0.336 0.156
#> GSM486794 5 0.4266 0.6154 0.252 0.000 0.040 0.008 0.700 0.000
#> GSM486796 1 0.4766 0.5151 0.748 0.152 0.004 0.024 0.032 0.040
#> GSM486798 3 0.7932 0.3156 0.024 0.100 0.416 0.112 0.308 0.040
#> GSM486800 1 0.3295 0.6150 0.816 0.056 0.000 0.000 0.128 0.000
#> GSM486802 1 0.0146 0.6381 0.996 0.004 0.000 0.000 0.000 0.000
#> GSM486804 1 0.0653 0.6432 0.980 0.004 0.004 0.000 0.012 0.000
#> GSM486806 3 0.6714 0.4305 0.160 0.148 0.548 0.140 0.004 0.000
#> GSM486808 5 0.4995 0.4196 0.000 0.040 0.172 0.088 0.700 0.000
#> GSM486810 4 0.3411 0.4700 0.000 0.044 0.016 0.848 0.072 0.020
#> GSM486812 5 0.2814 0.6419 0.172 0.000 0.008 0.000 0.820 0.000
#> GSM486814 2 0.6532 0.1702 0.352 0.484 0.008 0.068 0.084 0.004
#> GSM486816 5 0.4180 0.5065 0.016 0.012 0.204 0.016 0.748 0.004
#> GSM486818 1 0.7690 0.1606 0.432 0.180 0.132 0.020 0.232 0.004
#> GSM486821 1 0.7389 0.0319 0.456 0.140 0.036 0.072 0.004 0.292
#> GSM486823 4 0.5398 0.4011 0.004 0.064 0.288 0.612 0.000 0.032
#> GSM486826 1 0.5895 0.3688 0.604 0.016 0.140 0.012 0.224 0.004
#> GSM486830 6 0.4175 0.0980 0.000 0.000 0.012 0.464 0.000 0.524
#> GSM486832 1 0.4030 0.6035 0.796 0.068 0.028 0.000 0.104 0.004
#> GSM486834 3 0.6537 0.4843 0.028 0.068 0.592 0.172 0.140 0.000
#> GSM486836 1 0.2706 0.6337 0.880 0.040 0.008 0.000 0.068 0.004
#> GSM486838 4 0.8411 0.1184 0.156 0.136 0.184 0.392 0.132 0.000
#> GSM486840 1 0.0363 0.6422 0.988 0.000 0.000 0.000 0.012 0.000
#> GSM486842 5 0.4541 0.6145 0.272 0.012 0.036 0.004 0.676 0.000
#> GSM486844 1 0.0000 0.6390 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486846 4 0.2706 0.4385 0.124 0.000 0.024 0.852 0.000 0.000
#> GSM486848 1 0.1003 0.6453 0.964 0.004 0.004 0.000 0.028 0.000
#> GSM486850 4 0.5603 0.2998 0.016 0.244 0.120 0.612 0.000 0.008
#> GSM486852 6 0.6113 0.5373 0.068 0.088 0.012 0.008 0.192 0.632
#> GSM486854 4 0.7465 0.0169 0.044 0.076 0.324 0.432 0.004 0.120
#> GSM486856 1 0.5536 -0.2054 0.504 0.352 0.000 0.144 0.000 0.000
#> GSM486858 4 0.7015 0.0985 0.156 0.048 0.352 0.420 0.024 0.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> CV:pam 84 1.000 4.84e-03 2
#> CV:pam 81 0.601 8.58e-04 3
#> CV:pam 63 0.611 5.77e-03 4
#> CV:pam 63 0.788 5.35e-05 5
#> CV:pam 47 0.837 7.83e-04 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["CV", "mclust"]
# you can also extract it by
# res = res_list["CV:mclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'CV' method.
#> Subgroups are detected by 'mclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 6.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.327 0.494 0.751 0.4770 0.576 0.576
#> 3 3 0.357 0.297 0.629 0.2575 0.570 0.410
#> 4 4 0.441 0.505 0.726 0.1444 0.703 0.460
#> 5 5 0.576 0.495 0.728 0.0707 0.813 0.512
#> 6 6 0.601 0.593 0.722 0.0689 0.888 0.578
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 6
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 2 0.0376 0.625 0.004 0.996
#> GSM486737 2 0.9933 0.128 0.452 0.548
#> GSM486739 2 0.9944 0.125 0.456 0.544
#> GSM486741 2 0.4298 0.573 0.088 0.912
#> GSM486743 2 0.9933 0.128 0.452 0.548
#> GSM486745 2 0.9933 0.128 0.452 0.548
#> GSM486747 2 0.9795 0.267 0.416 0.584
#> GSM486749 2 0.0000 0.626 0.000 1.000
#> GSM486751 2 0.3879 0.589 0.076 0.924
#> GSM486753 2 0.9933 0.128 0.452 0.548
#> GSM486755 2 0.9933 0.128 0.452 0.548
#> GSM486757 2 0.9427 0.331 0.360 0.640
#> GSM486759 1 0.0376 0.843 0.996 0.004
#> GSM486761 2 0.9815 0.264 0.420 0.580
#> GSM486763 1 0.7674 0.683 0.776 0.224
#> GSM486765 2 0.9850 0.253 0.428 0.572
#> GSM486767 2 0.9933 0.128 0.452 0.548
#> GSM486769 2 0.0376 0.625 0.004 0.996
#> GSM486771 2 0.9933 0.128 0.452 0.548
#> GSM486773 2 0.0000 0.626 0.000 1.000
#> GSM486775 1 0.0376 0.843 0.996 0.004
#> GSM486777 2 0.9909 0.237 0.444 0.556
#> GSM486779 2 0.9933 0.128 0.452 0.548
#> GSM486781 2 0.0000 0.626 0.000 1.000
#> GSM486783 2 0.9933 0.128 0.452 0.548
#> GSM486785 2 0.9850 0.253 0.428 0.572
#> GSM486787 1 0.0376 0.843 0.996 0.004
#> GSM486789 2 0.0000 0.626 0.000 1.000
#> GSM486791 1 0.5294 0.815 0.880 0.120
#> GSM486793 2 0.9850 0.253 0.428 0.572
#> GSM486795 1 0.8861 0.532 0.696 0.304
#> GSM486797 2 0.1414 0.618 0.020 0.980
#> GSM486799 1 0.2043 0.853 0.968 0.032
#> GSM486801 1 0.3114 0.852 0.944 0.056
#> GSM486803 1 0.4161 0.841 0.916 0.084
#> GSM486805 2 0.0000 0.626 0.000 1.000
#> GSM486807 2 0.9996 0.187 0.488 0.512
#> GSM486809 2 0.0376 0.625 0.004 0.996
#> GSM486811 2 0.9998 0.180 0.492 0.508
#> GSM486813 2 0.9933 0.128 0.452 0.548
#> GSM486815 2 0.9850 0.253 0.428 0.572
#> GSM486817 1 0.9909 0.157 0.556 0.444
#> GSM486819 1 0.9522 0.373 0.628 0.372
#> GSM486822 2 0.0000 0.626 0.000 1.000
#> GSM486824 1 0.3114 0.851 0.944 0.056
#> GSM486828 2 0.0000 0.626 0.000 1.000
#> GSM486831 1 0.2948 0.849 0.948 0.052
#> GSM486833 2 0.4690 0.573 0.100 0.900
#> GSM486835 1 0.0376 0.843 0.996 0.004
#> GSM486837 2 0.0000 0.626 0.000 1.000
#> GSM486839 1 0.0376 0.843 0.996 0.004
#> GSM486841 2 0.9998 0.181 0.492 0.508
#> GSM486843 1 0.2043 0.853 0.968 0.032
#> GSM486845 2 0.0000 0.626 0.000 1.000
#> GSM486847 1 0.0376 0.843 0.996 0.004
#> GSM486849 2 0.0000 0.626 0.000 1.000
#> GSM486851 1 0.5294 0.815 0.880 0.120
#> GSM486853 2 0.0000 0.626 0.000 1.000
#> GSM486855 2 0.9933 0.128 0.452 0.548
#> GSM486857 2 0.0000 0.626 0.000 1.000
#> GSM486736 2 0.0376 0.625 0.004 0.996
#> GSM486738 2 0.9933 0.128 0.452 0.548
#> GSM486740 2 0.9944 0.125 0.456 0.544
#> GSM486742 2 0.8144 0.408 0.252 0.748
#> GSM486744 2 0.9933 0.128 0.452 0.548
#> GSM486746 2 0.9933 0.128 0.452 0.548
#> GSM486748 2 0.8861 0.389 0.304 0.696
#> GSM486750 2 0.0000 0.626 0.000 1.000
#> GSM486752 2 0.4815 0.570 0.104 0.896
#> GSM486754 2 0.9933 0.128 0.452 0.548
#> GSM486756 2 0.9933 0.128 0.452 0.548
#> GSM486758 2 0.9795 0.272 0.416 0.584
#> GSM486760 1 0.0672 0.845 0.992 0.008
#> GSM486762 2 0.9775 0.272 0.412 0.588
#> GSM486764 1 0.5294 0.815 0.880 0.120
#> GSM486766 2 0.9983 0.200 0.476 0.524
#> GSM486768 2 0.9933 0.128 0.452 0.548
#> GSM486770 2 0.0376 0.625 0.004 0.996
#> GSM486772 2 0.9933 0.128 0.452 0.548
#> GSM486774 2 0.0000 0.626 0.000 1.000
#> GSM486776 1 0.0672 0.845 0.992 0.008
#> GSM486778 2 0.9896 0.240 0.440 0.560
#> GSM486780 2 0.9933 0.128 0.452 0.548
#> GSM486782 2 0.0000 0.626 0.000 1.000
#> GSM486784 2 0.9933 0.128 0.452 0.548
#> GSM486786 2 0.9850 0.253 0.428 0.572
#> GSM486788 1 0.2236 0.853 0.964 0.036
#> GSM486790 2 0.0376 0.625 0.004 0.996
#> GSM486792 1 0.5294 0.815 0.880 0.120
#> GSM486794 2 0.9881 0.245 0.436 0.564
#> GSM486796 1 0.7950 0.658 0.760 0.240
#> GSM486798 2 0.0376 0.625 0.004 0.996
#> GSM486800 1 0.0376 0.843 0.996 0.004
#> GSM486802 1 0.4939 0.826 0.892 0.108
#> GSM486804 1 0.3431 0.849 0.936 0.064
#> GSM486806 2 0.0000 0.626 0.000 1.000
#> GSM486808 2 0.9993 0.191 0.484 0.516
#> GSM486810 2 0.0376 0.625 0.004 0.996
#> GSM486812 2 1.0000 0.169 0.500 0.500
#> GSM486814 2 0.9933 0.128 0.452 0.548
#> GSM486816 2 0.9850 0.253 0.428 0.572
#> GSM486818 1 0.9580 0.352 0.620 0.380
#> GSM486821 1 0.9491 0.385 0.632 0.368
#> GSM486823 2 0.0000 0.626 0.000 1.000
#> GSM486826 1 0.4161 0.841 0.916 0.084
#> GSM486830 2 0.0000 0.626 0.000 1.000
#> GSM486832 1 0.1184 0.848 0.984 0.016
#> GSM486834 2 0.1633 0.616 0.024 0.976
#> GSM486836 1 0.0376 0.843 0.996 0.004
#> GSM486838 2 0.0000 0.626 0.000 1.000
#> GSM486840 1 0.2043 0.852 0.968 0.032
#> GSM486842 2 0.9993 0.191 0.484 0.516
#> GSM486844 1 0.5059 0.823 0.888 0.112
#> GSM486846 2 0.0000 0.626 0.000 1.000
#> GSM486848 1 0.0376 0.843 0.996 0.004
#> GSM486850 2 0.0000 0.626 0.000 1.000
#> GSM486852 1 0.5408 0.812 0.876 0.124
#> GSM486854 2 0.0000 0.626 0.000 1.000
#> GSM486856 2 0.9933 0.128 0.452 0.548
#> GSM486858 2 0.0000 0.626 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 1 0.9841 -0.2365 0.400 0.252 0.348
#> GSM486737 2 0.0592 0.4728 0.000 0.988 0.012
#> GSM486739 2 0.8322 -0.4814 0.080 0.492 0.428
#> GSM486741 2 0.8122 0.5410 0.184 0.648 0.168
#> GSM486743 2 0.0747 0.4596 0.000 0.984 0.016
#> GSM486745 2 0.6435 0.0493 0.076 0.756 0.168
#> GSM486747 1 0.1585 0.3550 0.964 0.028 0.008
#> GSM486749 2 0.8375 0.5296 0.368 0.540 0.092
#> GSM486751 1 0.8135 -0.4234 0.484 0.448 0.068
#> GSM486753 2 0.0475 0.4731 0.004 0.992 0.004
#> GSM486755 2 0.2056 0.4719 0.024 0.952 0.024
#> GSM486757 1 0.5798 0.1761 0.780 0.044 0.176
#> GSM486759 1 0.9950 0.1896 0.372 0.340 0.288
#> GSM486761 1 0.0661 0.3630 0.988 0.008 0.004
#> GSM486763 3 0.8689 0.9338 0.164 0.248 0.588
#> GSM486765 1 0.1289 0.3603 0.968 0.000 0.032
#> GSM486767 2 0.2187 0.4623 0.028 0.948 0.024
#> GSM486769 1 0.9786 -0.2169 0.400 0.236 0.364
#> GSM486771 2 0.0424 0.4683 0.000 0.992 0.008
#> GSM486773 2 0.8683 0.5373 0.340 0.540 0.120
#> GSM486775 1 0.9959 0.1911 0.368 0.340 0.292
#> GSM486777 1 0.2682 0.3757 0.920 0.004 0.076
#> GSM486779 2 0.0661 0.4682 0.004 0.988 0.008
#> GSM486781 2 0.8518 0.5345 0.356 0.540 0.104
#> GSM486783 2 0.0424 0.4683 0.000 0.992 0.008
#> GSM486785 1 0.1453 0.3611 0.968 0.008 0.024
#> GSM486787 1 0.9946 0.1868 0.368 0.348 0.284
#> GSM486789 2 0.9086 0.4956 0.372 0.484 0.144
#> GSM486791 3 0.9100 0.9562 0.204 0.248 0.548
#> GSM486793 1 0.1289 0.3603 0.968 0.000 0.032
#> GSM486795 2 0.8236 -0.3589 0.416 0.508 0.076
#> GSM486797 2 0.8403 0.5042 0.400 0.512 0.088
#> GSM486799 1 0.9684 0.1600 0.436 0.340 0.224
#> GSM486801 1 0.9569 0.1242 0.420 0.384 0.196
#> GSM486803 1 0.9256 0.1053 0.488 0.344 0.168
#> GSM486805 2 0.8402 0.5233 0.376 0.532 0.092
#> GSM486807 1 0.3686 0.3813 0.860 0.000 0.140
#> GSM486809 1 0.9862 -0.3132 0.412 0.316 0.272
#> GSM486811 1 0.4293 0.3797 0.832 0.004 0.164
#> GSM486813 2 0.1163 0.4461 0.000 0.972 0.028
#> GSM486815 1 0.1964 0.3455 0.944 0.000 0.056
#> GSM486817 2 0.6349 0.1430 0.156 0.764 0.080
#> GSM486819 2 0.9213 -0.4496 0.236 0.536 0.228
#> GSM486822 2 0.9183 0.4960 0.360 0.484 0.156
#> GSM486824 1 0.9642 0.1516 0.440 0.344 0.216
#> GSM486828 2 0.8628 0.5382 0.340 0.544 0.116
#> GSM486831 1 0.9793 0.1555 0.388 0.376 0.236
#> GSM486833 1 0.8285 -0.1507 0.600 0.288 0.112
#> GSM486835 1 0.9953 0.1894 0.368 0.344 0.288
#> GSM486837 2 0.8066 0.5074 0.404 0.528 0.068
#> GSM486839 1 0.9964 0.1923 0.368 0.336 0.296
#> GSM486841 1 0.3752 0.3806 0.856 0.000 0.144
#> GSM486843 1 0.9797 0.1665 0.404 0.356 0.240
#> GSM486845 2 0.8588 0.5386 0.344 0.544 0.112
#> GSM486847 1 0.9964 0.1923 0.368 0.336 0.296
#> GSM486849 2 0.8703 0.5383 0.332 0.544 0.124
#> GSM486851 3 0.9009 0.9613 0.204 0.236 0.560
#> GSM486853 2 0.8503 0.5367 0.352 0.544 0.104
#> GSM486855 2 0.0592 0.4676 0.000 0.988 0.012
#> GSM486857 2 0.8699 0.5198 0.376 0.512 0.112
#> GSM486736 1 0.9820 -0.2268 0.396 0.244 0.360
#> GSM486738 2 0.0592 0.4692 0.000 0.988 0.012
#> GSM486740 2 0.8316 -0.4728 0.080 0.496 0.424
#> GSM486742 2 0.6231 0.5168 0.080 0.772 0.148
#> GSM486744 2 0.0747 0.4687 0.000 0.984 0.016
#> GSM486746 2 0.6572 0.0366 0.080 0.748 0.172
#> GSM486748 1 0.4802 0.2751 0.824 0.156 0.020
#> GSM486750 2 0.8666 0.5384 0.336 0.544 0.120
#> GSM486752 1 0.6869 -0.3261 0.560 0.424 0.016
#> GSM486754 2 0.1129 0.4787 0.004 0.976 0.020
#> GSM486756 2 0.1585 0.4807 0.008 0.964 0.028
#> GSM486758 1 0.5147 0.1882 0.800 0.020 0.180
#> GSM486760 1 0.9959 0.1912 0.368 0.340 0.292
#> GSM486762 1 0.1711 0.3538 0.960 0.032 0.008
#> GSM486764 3 0.8657 0.9372 0.164 0.244 0.592
#> GSM486766 1 0.3038 0.3800 0.896 0.000 0.104
#> GSM486768 2 0.0983 0.4618 0.004 0.980 0.016
#> GSM486770 1 0.9786 -0.2169 0.400 0.236 0.364
#> GSM486772 2 0.0592 0.4676 0.000 0.988 0.012
#> GSM486774 2 0.8066 0.5074 0.404 0.528 0.068
#> GSM486776 1 0.9959 0.1911 0.368 0.340 0.292
#> GSM486778 1 0.3573 0.3824 0.876 0.004 0.120
#> GSM486780 2 0.1182 0.4588 0.012 0.976 0.012
#> GSM486782 2 0.8604 0.5362 0.348 0.540 0.112
#> GSM486784 2 0.0892 0.4677 0.000 0.980 0.020
#> GSM486786 1 0.1411 0.3591 0.964 0.000 0.036
#> GSM486788 1 0.9936 0.1882 0.380 0.336 0.284
#> GSM486790 2 0.9106 0.5330 0.284 0.536 0.180
#> GSM486792 3 0.9100 0.9562 0.204 0.248 0.548
#> GSM486794 1 0.1860 0.3686 0.948 0.000 0.052
#> GSM486796 1 0.8550 -0.0314 0.492 0.412 0.096
#> GSM486798 2 0.7940 0.4959 0.416 0.524 0.060
#> GSM486800 1 0.9964 0.1923 0.368 0.336 0.296
#> GSM486802 1 0.9074 0.0847 0.500 0.352 0.148
#> GSM486804 1 0.9379 0.1260 0.472 0.348 0.180
#> GSM486806 2 0.8191 0.5127 0.396 0.528 0.076
#> GSM486808 1 0.3816 0.3800 0.852 0.000 0.148
#> GSM486810 1 0.9737 -0.3982 0.392 0.384 0.224
#> GSM486812 1 0.4351 0.3791 0.828 0.004 0.168
#> GSM486814 2 0.0424 0.4662 0.000 0.992 0.008
#> GSM486816 1 0.1529 0.3566 0.960 0.000 0.040
#> GSM486818 2 0.7710 -0.0785 0.240 0.660 0.100
#> GSM486821 2 0.9423 -0.4992 0.304 0.492 0.204
#> GSM486823 2 0.8790 0.5370 0.328 0.540 0.132
#> GSM486826 1 0.8973 0.0693 0.500 0.364 0.136
#> GSM486830 2 0.8546 0.5374 0.348 0.544 0.108
#> GSM486832 2 0.9793 -0.4608 0.376 0.388 0.236
#> GSM486834 1 0.6669 -0.4024 0.524 0.468 0.008
#> GSM486836 1 0.9964 0.1923 0.368 0.336 0.296
#> GSM486838 2 0.8120 0.5129 0.396 0.532 0.072
#> GSM486840 1 0.9956 0.1921 0.372 0.336 0.292
#> GSM486842 1 0.2796 0.3794 0.908 0.000 0.092
#> GSM486844 1 0.9098 0.0858 0.456 0.404 0.140
#> GSM486846 2 0.8628 0.5390 0.340 0.544 0.116
#> GSM486848 1 0.9964 0.1923 0.368 0.336 0.296
#> GSM486850 2 0.8666 0.5387 0.336 0.544 0.120
#> GSM486852 3 0.9009 0.9613 0.204 0.236 0.560
#> GSM486854 2 0.8588 0.5387 0.344 0.544 0.112
#> GSM486856 2 0.0424 0.4662 0.000 0.992 0.008
#> GSM486858 2 0.8661 0.5357 0.348 0.536 0.116
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 2 0.5526 0.0973 0.020 0.564 0.000 0.416
#> GSM486737 2 0.6744 0.4908 0.004 0.528 0.084 0.384
#> GSM486739 4 0.5021 0.5491 0.116 0.100 0.004 0.780
#> GSM486741 2 0.3043 0.6543 0.008 0.876 0.004 0.112
#> GSM486743 2 0.6777 0.4894 0.004 0.532 0.088 0.376
#> GSM486745 4 0.7092 0.3257 0.072 0.184 0.084 0.660
#> GSM486747 1 0.5950 0.7807 0.696 0.156 0.148 0.000
#> GSM486749 2 0.0000 0.6760 0.000 1.000 0.000 0.000
#> GSM486751 2 0.2853 0.6468 0.076 0.900 0.016 0.008
#> GSM486753 2 0.6615 0.4820 0.000 0.512 0.084 0.404
#> GSM486755 2 0.6610 0.4318 0.000 0.468 0.080 0.452
#> GSM486757 1 0.7922 0.4121 0.532 0.288 0.040 0.140
#> GSM486759 3 0.0927 0.7003 0.016 0.000 0.976 0.008
#> GSM486761 1 0.6492 0.7903 0.656 0.156 0.184 0.004
#> GSM486763 4 0.7631 0.6380 0.272 0.004 0.224 0.500
#> GSM486765 1 0.6795 0.7931 0.644 0.112 0.224 0.020
#> GSM486767 2 0.7424 0.4568 0.028 0.496 0.088 0.388
#> GSM486769 2 0.5535 0.0875 0.020 0.560 0.000 0.420
#> GSM486771 2 0.6753 0.4878 0.004 0.524 0.084 0.388
#> GSM486773 2 0.0895 0.6748 0.020 0.976 0.000 0.004
#> GSM486775 3 0.1022 0.6976 0.032 0.000 0.968 0.000
#> GSM486777 1 0.7801 0.5789 0.440 0.112 0.416 0.032
#> GSM486779 2 0.7574 0.4676 0.028 0.500 0.104 0.368
#> GSM486781 2 0.0592 0.6763 0.016 0.984 0.000 0.000
#> GSM486783 2 0.6734 0.4911 0.004 0.532 0.084 0.380
#> GSM486785 1 0.6129 0.7993 0.688 0.124 0.184 0.004
#> GSM486787 3 0.0336 0.7004 0.008 0.000 0.992 0.000
#> GSM486789 2 0.2831 0.6101 0.004 0.876 0.000 0.120
#> GSM486791 4 0.7407 0.6360 0.224 0.000 0.260 0.516
#> GSM486793 1 0.6756 0.8005 0.664 0.112 0.196 0.028
#> GSM486795 3 0.7487 0.3454 0.084 0.156 0.640 0.120
#> GSM486797 2 0.1822 0.6686 0.044 0.944 0.004 0.008
#> GSM486799 3 0.2773 0.6579 0.116 0.000 0.880 0.004
#> GSM486801 3 0.2360 0.6904 0.052 0.004 0.924 0.020
#> GSM486803 3 0.4590 0.5822 0.192 0.000 0.772 0.036
#> GSM486805 2 0.1543 0.6709 0.032 0.956 0.004 0.008
#> GSM486807 3 0.7134 -0.5687 0.436 0.112 0.448 0.004
#> GSM486809 2 0.5323 0.2327 0.020 0.628 0.000 0.352
#> GSM486811 3 0.7214 -0.4828 0.388 0.112 0.492 0.008
#> GSM486813 2 0.7342 0.4797 0.020 0.516 0.100 0.364
#> GSM486815 1 0.6943 0.7823 0.672 0.112 0.164 0.052
#> GSM486817 2 0.9540 0.0927 0.132 0.368 0.288 0.212
#> GSM486819 3 0.9303 -0.2272 0.164 0.140 0.424 0.272
#> GSM486822 2 0.2053 0.6474 0.004 0.924 0.000 0.072
#> GSM486824 3 0.3647 0.6388 0.152 0.000 0.832 0.016
#> GSM486828 2 0.0188 0.6760 0.000 0.996 0.000 0.004
#> GSM486831 3 0.2040 0.6873 0.048 0.004 0.936 0.012
#> GSM486833 2 0.6696 0.1948 0.328 0.580 0.008 0.084
#> GSM486835 3 0.0657 0.7022 0.012 0.000 0.984 0.004
#> GSM486837 2 0.1909 0.6683 0.048 0.940 0.004 0.008
#> GSM486839 3 0.0336 0.7007 0.008 0.000 0.992 0.000
#> GSM486841 3 0.7129 -0.5443 0.424 0.112 0.460 0.004
#> GSM486843 3 0.2142 0.6927 0.056 0.000 0.928 0.016
#> GSM486845 2 0.0524 0.6767 0.008 0.988 0.000 0.004
#> GSM486847 3 0.0592 0.7005 0.016 0.000 0.984 0.000
#> GSM486849 2 0.0592 0.6742 0.000 0.984 0.000 0.016
#> GSM486851 4 0.7387 0.6404 0.224 0.000 0.256 0.520
#> GSM486853 2 0.0707 0.6731 0.000 0.980 0.000 0.020
#> GSM486855 2 0.7021 0.4861 0.012 0.524 0.088 0.376
#> GSM486857 2 0.1543 0.6714 0.032 0.956 0.004 0.008
#> GSM486736 2 0.5535 0.0875 0.020 0.560 0.000 0.420
#> GSM486738 2 0.6761 0.4875 0.004 0.520 0.084 0.392
#> GSM486740 4 0.4961 0.5540 0.116 0.096 0.004 0.784
#> GSM486742 2 0.5564 0.5864 0.008 0.712 0.052 0.228
#> GSM486744 2 0.6734 0.4907 0.004 0.532 0.084 0.380
#> GSM486746 4 0.7945 0.3171 0.104 0.212 0.096 0.588
#> GSM486748 2 0.7302 -0.2186 0.332 0.500 0.168 0.000
#> GSM486750 2 0.0895 0.6724 0.004 0.976 0.000 0.020
#> GSM486752 2 0.4900 0.5181 0.200 0.760 0.032 0.008
#> GSM486754 2 0.6615 0.4820 0.000 0.512 0.084 0.404
#> GSM486756 2 0.6554 0.4877 0.000 0.520 0.080 0.400
#> GSM486758 1 0.6994 0.5968 0.668 0.144 0.048 0.140
#> GSM486760 3 0.0376 0.6984 0.004 0.000 0.992 0.004
#> GSM486762 1 0.6476 0.7747 0.644 0.176 0.180 0.000
#> GSM486764 4 0.7551 0.6314 0.272 0.000 0.240 0.488
#> GSM486766 1 0.7044 0.6481 0.516 0.112 0.368 0.004
#> GSM486768 2 0.6977 0.4846 0.008 0.532 0.096 0.364
#> GSM486770 2 0.5535 0.0875 0.020 0.560 0.000 0.420
#> GSM486772 2 0.6769 0.4852 0.004 0.516 0.084 0.396
#> GSM486774 2 0.1443 0.6734 0.028 0.960 0.004 0.008
#> GSM486776 3 0.0817 0.6999 0.024 0.000 0.976 0.000
#> GSM486778 3 0.7702 -0.5141 0.392 0.112 0.468 0.028
#> GSM486780 2 0.7458 0.4692 0.028 0.500 0.092 0.380
#> GSM486782 2 0.0672 0.6763 0.008 0.984 0.000 0.008
#> GSM486784 2 0.6744 0.4908 0.004 0.528 0.084 0.384
#> GSM486786 1 0.6604 0.8036 0.676 0.116 0.184 0.024
#> GSM486788 3 0.0188 0.6997 0.000 0.000 0.996 0.004
#> GSM486790 2 0.1978 0.6537 0.004 0.928 0.000 0.068
#> GSM486792 4 0.7407 0.6360 0.224 0.000 0.260 0.516
#> GSM486794 1 0.7137 0.7425 0.576 0.112 0.296 0.016
#> GSM486796 3 0.6944 0.4509 0.092 0.084 0.684 0.140
#> GSM486798 2 0.2076 0.6656 0.056 0.932 0.004 0.008
#> GSM486800 3 0.0188 0.6997 0.000 0.000 0.996 0.004
#> GSM486802 3 0.4001 0.6253 0.044 0.008 0.844 0.104
#> GSM486804 3 0.4323 0.5924 0.204 0.000 0.776 0.020
#> GSM486806 2 0.1994 0.6671 0.052 0.936 0.004 0.008
#> GSM486808 3 0.7126 -0.5400 0.420 0.112 0.464 0.004
#> GSM486810 2 0.4121 0.5239 0.020 0.796 0.000 0.184
#> GSM486812 3 0.7191 -0.4621 0.376 0.112 0.504 0.008
#> GSM486814 2 0.6907 0.4892 0.008 0.528 0.088 0.376
#> GSM486816 1 0.6860 0.7989 0.664 0.112 0.188 0.036
#> GSM486818 3 0.8648 -0.1348 0.104 0.392 0.404 0.100
#> GSM486821 3 0.9069 -0.0816 0.152 0.132 0.464 0.252
#> GSM486823 2 0.1902 0.6530 0.004 0.932 0.000 0.064
#> GSM486826 3 0.5174 0.5416 0.248 0.004 0.716 0.032
#> GSM486830 2 0.0188 0.6757 0.000 0.996 0.000 0.004
#> GSM486832 3 0.1639 0.6919 0.036 0.004 0.952 0.008
#> GSM486834 2 0.4661 0.4710 0.264 0.724 0.004 0.008
#> GSM486836 3 0.0524 0.7017 0.008 0.000 0.988 0.004
#> GSM486838 2 0.1543 0.6718 0.032 0.956 0.004 0.008
#> GSM486840 3 0.0804 0.7022 0.012 0.000 0.980 0.008
#> GSM486842 1 0.6969 0.5403 0.452 0.112 0.436 0.000
#> GSM486844 3 0.5601 0.5947 0.100 0.028 0.764 0.108
#> GSM486846 2 0.0524 0.6762 0.008 0.988 0.000 0.004
#> GSM486848 3 0.0469 0.7003 0.012 0.000 0.988 0.000
#> GSM486850 2 0.0469 0.6749 0.000 0.988 0.000 0.012
#> GSM486852 4 0.7387 0.6404 0.224 0.000 0.256 0.520
#> GSM486854 2 0.0592 0.6740 0.000 0.984 0.000 0.016
#> GSM486856 2 0.7012 0.4880 0.012 0.528 0.088 0.372
#> GSM486858 2 0.0804 0.6744 0.012 0.980 0.000 0.008
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 4 0.3064 0.3459 0.000 0.036 0.000 0.856 0.108
#> GSM486737 2 0.1282 0.6566 0.000 0.952 0.004 0.044 0.000
#> GSM486739 4 0.6885 -0.4789 0.004 0.260 0.000 0.372 0.364
#> GSM486741 2 0.5057 -0.3725 0.000 0.556 0.004 0.412 0.028
#> GSM486743 2 0.0693 0.6633 0.000 0.980 0.000 0.008 0.012
#> GSM486745 2 0.6370 -0.0528 0.000 0.480 0.000 0.344 0.176
#> GSM486747 3 0.4979 0.6437 0.152 0.008 0.728 0.112 0.000
#> GSM486749 2 0.4307 -0.6068 0.000 0.500 0.000 0.500 0.000
#> GSM486751 4 0.6116 0.5454 0.020 0.440 0.072 0.468 0.000
#> GSM486753 2 0.1106 0.6647 0.000 0.964 0.000 0.024 0.012
#> GSM486755 2 0.3574 0.5398 0.000 0.804 0.000 0.168 0.028
#> GSM486757 3 0.5572 0.2488 0.000 0.008 0.652 0.232 0.108
#> GSM486759 1 0.0290 0.7907 0.992 0.000 0.000 0.000 0.008
#> GSM486761 3 0.4610 0.6654 0.188 0.004 0.740 0.068 0.000
#> GSM486763 5 0.3229 0.9043 0.056 0.032 0.040 0.000 0.872
#> GSM486765 3 0.3774 0.6643 0.196 0.004 0.784 0.004 0.012
#> GSM486767 2 0.2409 0.6465 0.000 0.908 0.012 0.060 0.020
#> GSM486769 4 0.3115 0.3401 0.000 0.036 0.000 0.852 0.112
#> GSM486771 2 0.0794 0.6650 0.000 0.972 0.000 0.028 0.000
#> GSM486773 4 0.4425 0.5871 0.000 0.452 0.004 0.544 0.000
#> GSM486775 1 0.0833 0.7859 0.976 0.004 0.016 0.000 0.004
#> GSM486777 3 0.4796 0.4323 0.468 0.000 0.516 0.004 0.012
#> GSM486779 2 0.3164 0.6297 0.016 0.876 0.012 0.076 0.020
#> GSM486781 4 0.4451 0.5853 0.000 0.492 0.004 0.504 0.000
#> GSM486783 2 0.0865 0.6631 0.000 0.972 0.004 0.024 0.000
#> GSM486785 3 0.3966 0.6718 0.168 0.004 0.788 0.040 0.000
#> GSM486787 1 0.0290 0.7904 0.992 0.000 0.000 0.000 0.008
#> GSM486789 4 0.4677 0.5234 0.000 0.300 0.000 0.664 0.036
#> GSM486791 5 0.3395 0.9347 0.104 0.000 0.004 0.048 0.844
#> GSM486793 3 0.3264 0.6633 0.140 0.000 0.836 0.004 0.020
#> GSM486795 1 0.5798 0.4142 0.624 0.288 0.024 0.004 0.060
#> GSM486797 4 0.5100 0.5817 0.000 0.448 0.036 0.516 0.000
#> GSM486799 1 0.1408 0.7700 0.948 0.000 0.044 0.000 0.008
#> GSM486801 1 0.1517 0.7816 0.952 0.012 0.004 0.004 0.028
#> GSM486803 1 0.3693 0.6496 0.808 0.000 0.156 0.004 0.032
#> GSM486805 4 0.4632 0.5901 0.000 0.448 0.012 0.540 0.000
#> GSM486807 3 0.4278 0.4713 0.452 0.000 0.548 0.000 0.000
#> GSM486809 4 0.3255 0.3820 0.000 0.052 0.000 0.848 0.100
#> GSM486811 1 0.4304 -0.3775 0.516 0.000 0.484 0.000 0.000
#> GSM486813 2 0.1948 0.6512 0.008 0.928 0.004 0.056 0.004
#> GSM486815 3 0.3273 0.6401 0.112 0.000 0.848 0.004 0.036
#> GSM486817 2 0.6820 0.4005 0.188 0.628 0.104 0.048 0.032
#> GSM486819 1 0.7553 -0.0993 0.380 0.296 0.024 0.008 0.292
#> GSM486822 4 0.4382 0.5240 0.000 0.288 0.000 0.688 0.024
#> GSM486824 1 0.3235 0.7076 0.860 0.008 0.104 0.008 0.020
#> GSM486828 2 0.4451 -0.6059 0.000 0.504 0.004 0.492 0.000
#> GSM486831 1 0.1121 0.7777 0.956 0.000 0.000 0.000 0.044
#> GSM486833 3 0.7656 -0.3758 0.004 0.328 0.348 0.284 0.036
#> GSM486835 1 0.0290 0.7904 0.992 0.000 0.000 0.000 0.008
#> GSM486837 4 0.5406 0.5610 0.000 0.468 0.056 0.476 0.000
#> GSM486839 1 0.0162 0.7898 0.996 0.000 0.000 0.000 0.004
#> GSM486841 3 0.4305 0.4013 0.488 0.000 0.512 0.000 0.000
#> GSM486843 1 0.1074 0.7884 0.968 0.004 0.012 0.000 0.016
#> GSM486845 4 0.4443 0.5737 0.000 0.472 0.004 0.524 0.000
#> GSM486847 1 0.0324 0.7902 0.992 0.000 0.004 0.000 0.004
#> GSM486849 4 0.4307 0.5806 0.000 0.500 0.000 0.500 0.000
#> GSM486851 5 0.2747 0.9389 0.060 0.000 0.004 0.048 0.888
#> GSM486853 4 0.4452 0.5758 0.000 0.496 0.004 0.500 0.000
#> GSM486855 2 0.1205 0.6630 0.000 0.956 0.004 0.040 0.000
#> GSM486857 4 0.4390 0.5851 0.000 0.428 0.004 0.568 0.000
#> GSM486736 4 0.3214 0.3362 0.000 0.036 0.000 0.844 0.120
#> GSM486738 2 0.0671 0.6649 0.000 0.980 0.004 0.016 0.000
#> GSM486740 4 0.6876 -0.4825 0.004 0.256 0.000 0.372 0.368
#> GSM486742 2 0.4085 0.2918 0.000 0.760 0.004 0.208 0.028
#> GSM486744 2 0.1282 0.6624 0.000 0.952 0.004 0.044 0.000
#> GSM486746 2 0.7063 -0.1405 0.004 0.424 0.008 0.304 0.260
#> GSM486748 3 0.8615 0.2861 0.284 0.168 0.288 0.256 0.004
#> GSM486750 4 0.4450 0.5861 0.000 0.488 0.004 0.508 0.000
#> GSM486752 2 0.7269 -0.3467 0.040 0.432 0.184 0.344 0.000
#> GSM486754 2 0.0771 0.6653 0.000 0.976 0.004 0.020 0.000
#> GSM486756 2 0.1697 0.6561 0.000 0.932 0.000 0.060 0.008
#> GSM486758 3 0.3682 0.4323 0.000 0.000 0.820 0.072 0.108
#> GSM486760 1 0.0162 0.7904 0.996 0.000 0.000 0.000 0.004
#> GSM486762 3 0.5054 0.6494 0.184 0.004 0.708 0.104 0.000
#> GSM486764 5 0.3096 0.9145 0.084 0.008 0.040 0.000 0.868
#> GSM486766 3 0.4321 0.5346 0.396 0.004 0.600 0.000 0.000
#> GSM486768 2 0.0898 0.6658 0.000 0.972 0.000 0.020 0.008
#> GSM486770 4 0.3339 0.3255 0.000 0.040 0.000 0.836 0.124
#> GSM486772 2 0.1282 0.6650 0.000 0.952 0.004 0.044 0.000
#> GSM486774 4 0.4803 0.5821 0.000 0.444 0.020 0.536 0.000
#> GSM486776 1 0.0324 0.7901 0.992 0.004 0.000 0.000 0.004
#> GSM486778 1 0.4704 -0.3865 0.508 0.000 0.480 0.004 0.008
#> GSM486780 2 0.2144 0.6435 0.000 0.912 0.020 0.068 0.000
#> GSM486782 4 0.4306 0.5842 0.000 0.492 0.000 0.508 0.000
#> GSM486784 2 0.1124 0.6640 0.000 0.960 0.004 0.036 0.000
#> GSM486786 3 0.3629 0.6710 0.156 0.004 0.816 0.012 0.012
#> GSM486788 1 0.0324 0.7909 0.992 0.000 0.000 0.004 0.004
#> GSM486790 4 0.5030 0.5254 0.000 0.352 0.000 0.604 0.044
#> GSM486792 5 0.3342 0.9373 0.100 0.000 0.004 0.048 0.848
#> GSM486794 3 0.4298 0.5779 0.352 0.000 0.640 0.000 0.008
#> GSM486796 1 0.5475 0.5408 0.704 0.180 0.024 0.004 0.088
#> GSM486798 4 0.5047 0.5907 0.004 0.468 0.024 0.504 0.000
#> GSM486800 1 0.0162 0.7898 0.996 0.000 0.000 0.000 0.004
#> GSM486802 1 0.1314 0.7840 0.960 0.008 0.004 0.004 0.024
#> GSM486804 1 0.3779 0.6411 0.800 0.004 0.172 0.008 0.016
#> GSM486806 4 0.5178 0.5741 0.000 0.476 0.040 0.484 0.000
#> GSM486808 3 0.4291 0.4526 0.464 0.000 0.536 0.000 0.000
#> GSM486810 4 0.3888 0.4344 0.000 0.148 0.000 0.796 0.056
#> GSM486812 1 0.4297 -0.3455 0.528 0.000 0.472 0.000 0.000
#> GSM486814 2 0.0963 0.6648 0.000 0.964 0.000 0.036 0.000
#> GSM486816 3 0.3387 0.6532 0.128 0.000 0.836 0.004 0.032
#> GSM486818 2 0.6903 0.2583 0.336 0.524 0.084 0.036 0.020
#> GSM486821 1 0.7308 0.0468 0.440 0.284 0.024 0.004 0.248
#> GSM486823 4 0.4538 0.5574 0.000 0.364 0.000 0.620 0.016
#> GSM486826 1 0.4372 0.5785 0.748 0.008 0.216 0.008 0.020
#> GSM486830 2 0.4307 -0.6057 0.000 0.500 0.000 0.500 0.000
#> GSM486832 1 0.0963 0.7816 0.964 0.000 0.000 0.000 0.036
#> GSM486834 2 0.7049 -0.2466 0.012 0.412 0.272 0.304 0.000
#> GSM486836 1 0.0162 0.7898 0.996 0.000 0.000 0.000 0.004
#> GSM486838 4 0.5234 0.5786 0.000 0.460 0.044 0.496 0.000
#> GSM486840 1 0.0324 0.7904 0.992 0.000 0.000 0.004 0.004
#> GSM486842 3 0.4300 0.4254 0.476 0.000 0.524 0.000 0.000
#> GSM486844 1 0.3687 0.6923 0.836 0.112 0.032 0.004 0.016
#> GSM486846 4 0.4443 0.5737 0.000 0.472 0.004 0.524 0.000
#> GSM486848 1 0.0324 0.7901 0.992 0.004 0.000 0.000 0.004
#> GSM486850 4 0.4596 0.5795 0.000 0.492 0.004 0.500 0.004
#> GSM486852 5 0.2813 0.9411 0.064 0.000 0.004 0.048 0.884
#> GSM486854 4 0.4451 0.5792 0.000 0.492 0.004 0.504 0.000
#> GSM486856 2 0.1205 0.6630 0.000 0.956 0.004 0.040 0.000
#> GSM486858 4 0.4291 0.5935 0.000 0.464 0.000 0.536 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 6 0.4169 0.66187 0.000 0.008 0.000 0.116 0.116 0.760
#> GSM486737 2 0.3967 0.70399 0.000 0.632 0.000 0.356 0.000 0.012
#> GSM486739 5 0.5532 0.34548 0.000 0.136 0.000 0.000 0.480 0.384
#> GSM486741 4 0.3892 0.49911 0.000 0.212 0.000 0.740 0.000 0.048
#> GSM486743 2 0.4351 0.72047 0.000 0.564 0.000 0.416 0.008 0.012
#> GSM486745 2 0.6232 0.00351 0.000 0.468 0.000 0.024 0.176 0.332
#> GSM486747 3 0.5698 0.60661 0.096 0.056 0.700 0.080 0.000 0.068
#> GSM486749 4 0.2070 0.68548 0.000 0.044 0.000 0.908 0.000 0.048
#> GSM486751 4 0.4571 0.65462 0.008 0.156 0.036 0.748 0.000 0.052
#> GSM486753 2 0.4219 0.71785 0.000 0.592 0.000 0.388 0.000 0.020
#> GSM486755 2 0.5769 0.60463 0.000 0.580 0.008 0.236 0.008 0.168
#> GSM486757 3 0.7559 0.19227 0.000 0.120 0.484 0.232 0.076 0.088
#> GSM486759 1 0.1152 0.80278 0.952 0.004 0.000 0.000 0.000 0.044
#> GSM486761 3 0.5513 0.64989 0.132 0.040 0.704 0.060 0.000 0.064
#> GSM486763 5 0.2817 0.70134 0.008 0.076 0.040 0.000 0.872 0.004
#> GSM486765 3 0.2544 0.69098 0.140 0.000 0.852 0.000 0.004 0.004
#> GSM486767 2 0.4625 0.62796 0.000 0.656 0.008 0.296 0.012 0.028
#> GSM486769 6 0.4126 0.65945 0.000 0.008 0.000 0.112 0.116 0.764
#> GSM486771 2 0.4726 0.71527 0.000 0.572 0.000 0.380 0.004 0.044
#> GSM486773 4 0.3062 0.69459 0.000 0.144 0.000 0.824 0.000 0.032
#> GSM486775 1 0.1257 0.80521 0.952 0.000 0.028 0.000 0.000 0.020
#> GSM486777 3 0.4819 0.54752 0.424 0.004 0.532 0.000 0.004 0.036
#> GSM486779 2 0.4447 0.59454 0.016 0.696 0.012 0.260 0.012 0.004
#> GSM486781 4 0.0993 0.70534 0.000 0.024 0.000 0.964 0.000 0.012
#> GSM486783 2 0.4268 0.70535 0.000 0.556 0.004 0.428 0.000 0.012
#> GSM486785 3 0.3944 0.67128 0.112 0.032 0.808 0.024 0.000 0.024
#> GSM486787 1 0.0622 0.80959 0.980 0.000 0.012 0.000 0.000 0.008
#> GSM486789 6 0.5962 0.40964 0.000 0.092 0.008 0.404 0.024 0.472
#> GSM486791 5 0.2221 0.71322 0.072 0.000 0.000 0.000 0.896 0.032
#> GSM486793 3 0.2722 0.66090 0.088 0.016 0.876 0.000 0.008 0.012
#> GSM486795 1 0.6502 0.38255 0.556 0.284 0.004 0.064 0.044 0.048
#> GSM486797 4 0.3753 0.67115 0.000 0.156 0.016 0.788 0.000 0.040
#> GSM486799 1 0.1753 0.77831 0.912 0.000 0.084 0.000 0.004 0.000
#> GSM486801 1 0.2677 0.77883 0.884 0.036 0.000 0.000 0.024 0.056
#> GSM486803 1 0.3879 0.62513 0.748 0.008 0.220 0.000 0.012 0.012
#> GSM486805 4 0.2442 0.69621 0.000 0.144 0.004 0.852 0.000 0.000
#> GSM486807 3 0.4152 0.57523 0.440 0.000 0.548 0.000 0.000 0.012
#> GSM486809 6 0.4682 0.67231 0.000 0.028 0.000 0.148 0.096 0.728
#> GSM486811 3 0.4834 0.46671 0.468 0.004 0.484 0.000 0.000 0.044
#> GSM486813 2 0.3937 0.62413 0.008 0.700 0.008 0.280 0.004 0.000
#> GSM486815 3 0.3115 0.63173 0.060 0.028 0.868 0.000 0.028 0.016
#> GSM486817 2 0.7275 0.25447 0.208 0.504 0.100 0.164 0.016 0.008
#> GSM486819 5 0.7906 0.26409 0.276 0.256 0.004 0.056 0.352 0.056
#> GSM486822 6 0.5450 0.42698 0.000 0.072 0.004 0.412 0.012 0.500
#> GSM486824 1 0.2987 0.71466 0.832 0.008 0.148 0.000 0.008 0.004
#> GSM486828 4 0.2499 0.68364 0.000 0.048 0.000 0.880 0.000 0.072
#> GSM486831 1 0.1788 0.80009 0.928 0.012 0.004 0.000 0.004 0.052
#> GSM486833 4 0.7625 0.29325 0.004 0.208 0.248 0.432 0.036 0.072
#> GSM486835 1 0.0858 0.80993 0.968 0.000 0.004 0.000 0.000 0.028
#> GSM486837 4 0.3948 0.68008 0.008 0.096 0.032 0.808 0.000 0.056
#> GSM486839 1 0.0622 0.80959 0.980 0.000 0.012 0.000 0.000 0.008
#> GSM486841 3 0.4463 0.53109 0.456 0.000 0.516 0.000 0.000 0.028
#> GSM486843 1 0.0935 0.80776 0.964 0.004 0.032 0.000 0.000 0.000
#> GSM486845 4 0.2199 0.66880 0.000 0.088 0.000 0.892 0.000 0.020
#> GSM486847 1 0.1074 0.80681 0.960 0.000 0.028 0.000 0.000 0.012
#> GSM486849 4 0.2685 0.67009 0.000 0.060 0.000 0.868 0.000 0.072
#> GSM486851 5 0.1245 0.72316 0.016 0.000 0.000 0.000 0.952 0.032
#> GSM486853 4 0.2451 0.66418 0.000 0.068 0.004 0.888 0.000 0.040
#> GSM486855 2 0.4234 0.70910 0.000 0.576 0.000 0.408 0.004 0.012
#> GSM486857 4 0.3073 0.65370 0.000 0.204 0.008 0.788 0.000 0.000
#> GSM486736 6 0.4016 0.65244 0.000 0.004 0.000 0.108 0.120 0.768
#> GSM486738 2 0.4109 0.71879 0.000 0.576 0.000 0.412 0.000 0.012
#> GSM486740 5 0.5532 0.34548 0.000 0.136 0.000 0.000 0.480 0.384
#> GSM486742 4 0.4633 -0.34903 0.000 0.392 0.004 0.568 0.000 0.036
#> GSM486744 2 0.4158 0.70900 0.000 0.572 0.000 0.416 0.004 0.008
#> GSM486746 2 0.6850 -0.25869 0.000 0.356 0.000 0.044 0.308 0.292
#> GSM486748 4 0.8135 -0.15705 0.204 0.112 0.264 0.360 0.000 0.060
#> GSM486750 4 0.3667 0.60034 0.000 0.080 0.000 0.788 0.000 0.132
#> GSM486752 4 0.6552 0.51530 0.060 0.104 0.136 0.620 0.000 0.080
#> GSM486754 2 0.4301 0.71272 0.000 0.584 0.000 0.392 0.000 0.024
#> GSM486756 2 0.4420 0.69635 0.000 0.604 0.000 0.360 0.000 0.036
#> GSM486758 3 0.5817 0.44160 0.000 0.104 0.688 0.048 0.076 0.084
#> GSM486760 1 0.1500 0.80062 0.936 0.012 0.000 0.000 0.000 0.052
#> GSM486762 3 0.6027 0.62782 0.136 0.048 0.664 0.084 0.000 0.068
#> GSM486764 5 0.2781 0.70190 0.016 0.060 0.040 0.000 0.880 0.004
#> GSM486766 3 0.4180 0.63344 0.348 0.000 0.628 0.000 0.000 0.024
#> GSM486768 2 0.4144 0.71491 0.000 0.580 0.000 0.408 0.008 0.004
#> GSM486770 6 0.4016 0.65244 0.000 0.004 0.000 0.108 0.120 0.768
#> GSM486772 2 0.4560 0.71738 0.000 0.592 0.000 0.372 0.008 0.028
#> GSM486774 4 0.3275 0.68814 0.000 0.140 0.008 0.820 0.000 0.032
#> GSM486776 1 0.1176 0.80673 0.956 0.000 0.024 0.000 0.000 0.020
#> GSM486778 3 0.5335 0.46287 0.444 0.016 0.476 0.000 0.000 0.064
#> GSM486780 2 0.4073 0.58827 0.012 0.724 0.020 0.240 0.000 0.004
#> GSM486782 4 0.1562 0.69837 0.000 0.032 0.004 0.940 0.000 0.024
#> GSM486784 2 0.4292 0.70944 0.000 0.568 0.004 0.416 0.004 0.008
#> GSM486786 3 0.2451 0.67729 0.108 0.008 0.876 0.000 0.004 0.004
#> GSM486788 1 0.1528 0.80335 0.936 0.016 0.000 0.000 0.000 0.048
#> GSM486790 6 0.5014 0.27857 0.000 0.048 0.004 0.460 0.004 0.484
#> GSM486792 5 0.2046 0.71919 0.060 0.000 0.000 0.000 0.908 0.032
#> GSM486794 3 0.4424 0.63520 0.344 0.000 0.624 0.000 0.012 0.020
#> GSM486796 1 0.5811 0.49074 0.620 0.256 0.004 0.020 0.036 0.064
#> GSM486798 4 0.2868 0.70851 0.000 0.112 0.004 0.852 0.000 0.032
#> GSM486800 1 0.0547 0.81049 0.980 0.000 0.000 0.000 0.000 0.020
#> GSM486802 1 0.2189 0.79095 0.904 0.032 0.000 0.000 0.004 0.060
#> GSM486804 1 0.3941 0.61669 0.748 0.016 0.216 0.000 0.008 0.012
#> GSM486806 4 0.3005 0.69597 0.000 0.060 0.024 0.864 0.000 0.052
#> GSM486808 3 0.4305 0.56944 0.436 0.000 0.544 0.000 0.000 0.020
#> GSM486810 6 0.4761 0.66750 0.000 0.048 0.000 0.212 0.040 0.700
#> GSM486812 1 0.5035 -0.47937 0.472 0.008 0.468 0.000 0.000 0.052
#> GSM486814 2 0.4189 0.71429 0.000 0.572 0.004 0.416 0.004 0.004
#> GSM486816 3 0.2787 0.64749 0.072 0.020 0.880 0.000 0.012 0.016
#> GSM486818 2 0.7634 0.12671 0.312 0.388 0.092 0.184 0.012 0.012
#> GSM486821 1 0.8024 -0.21214 0.328 0.272 0.008 0.056 0.280 0.056
#> GSM486823 4 0.4782 -0.04532 0.000 0.048 0.004 0.568 0.000 0.380
#> GSM486826 1 0.4540 0.54460 0.692 0.036 0.252 0.000 0.008 0.012
#> GSM486830 4 0.2712 0.66522 0.000 0.048 0.000 0.864 0.000 0.088
#> GSM486832 1 0.2119 0.79169 0.912 0.008 0.000 0.000 0.036 0.044
#> GSM486834 4 0.6173 0.48013 0.000 0.172 0.184 0.580 0.000 0.064
#> GSM486836 1 0.0622 0.81081 0.980 0.000 0.008 0.000 0.000 0.012
#> GSM486838 4 0.3772 0.68724 0.008 0.116 0.024 0.812 0.000 0.040
#> GSM486840 1 0.1148 0.81256 0.960 0.004 0.016 0.000 0.000 0.020
#> GSM486842 3 0.3955 0.57735 0.436 0.000 0.560 0.000 0.000 0.004
#> GSM486844 1 0.3179 0.75772 0.856 0.060 0.064 0.000 0.012 0.008
#> GSM486846 4 0.2282 0.66736 0.000 0.088 0.000 0.888 0.000 0.024
#> GSM486848 1 0.1092 0.80690 0.960 0.000 0.020 0.000 0.000 0.020
#> GSM486850 4 0.2568 0.66197 0.000 0.068 0.000 0.876 0.000 0.056
#> GSM486852 5 0.1320 0.72347 0.016 0.000 0.000 0.000 0.948 0.036
#> GSM486854 4 0.1536 0.69042 0.000 0.040 0.004 0.940 0.000 0.016
#> GSM486856 2 0.4144 0.70955 0.000 0.580 0.000 0.408 0.004 0.008
#> GSM486858 4 0.2445 0.70703 0.000 0.120 0.004 0.868 0.000 0.008
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> CV:mclust 69 1.000 3.59e-04 2
#> CV:mclust 31 1.000 1.35e-02 3
#> CV:mclust 77 0.999 4.92e-09 4
#> CV:mclust 86 0.998 5.88e-13 5
#> CV:mclust 96 0.999 3.65e-18 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["CV", "NMF"]
# you can also extract it by
# res = res_list["CV:NMF"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'CV' method.
#> Subgroups are detected by 'NMF' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.480 0.830 0.907 0.5010 0.497 0.497
#> 3 3 0.361 0.503 0.722 0.3079 0.749 0.536
#> 4 4 0.385 0.448 0.644 0.1228 0.859 0.613
#> 5 5 0.427 0.317 0.564 0.0729 0.840 0.499
#> 6 6 0.473 0.299 0.524 0.0444 0.828 0.405
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 2 0.0000 0.905519 0.000 1.000
#> GSM486737 2 0.6247 0.844802 0.156 0.844
#> GSM486739 2 0.6048 0.848983 0.148 0.852
#> GSM486741 2 0.0000 0.905519 0.000 1.000
#> GSM486743 2 0.8813 0.684469 0.300 0.700
#> GSM486745 2 0.7453 0.799207 0.212 0.788
#> GSM486747 1 0.7883 0.758381 0.764 0.236
#> GSM486749 2 0.0376 0.905186 0.004 0.996
#> GSM486751 2 0.0672 0.903614 0.008 0.992
#> GSM486753 2 0.6148 0.846850 0.152 0.848
#> GSM486755 2 0.6048 0.850273 0.148 0.852
#> GSM486757 2 0.4161 0.842435 0.084 0.916
#> GSM486759 1 0.0376 0.878777 0.996 0.004
#> GSM486761 1 0.7139 0.798633 0.804 0.196
#> GSM486763 1 0.9933 0.000376 0.548 0.452
#> GSM486765 1 0.6148 0.829034 0.848 0.152
#> GSM486767 2 0.7883 0.775056 0.236 0.764
#> GSM486769 2 0.0000 0.905519 0.000 1.000
#> GSM486771 2 0.6623 0.834335 0.172 0.828
#> GSM486773 2 0.0376 0.905186 0.004 0.996
#> GSM486775 1 0.0000 0.879679 1.000 0.000
#> GSM486777 1 0.6801 0.810383 0.820 0.180
#> GSM486779 2 0.8499 0.721517 0.276 0.724
#> GSM486781 2 0.0376 0.905186 0.004 0.996
#> GSM486783 2 0.6712 0.831312 0.176 0.824
#> GSM486785 1 0.6148 0.829304 0.848 0.152
#> GSM486787 1 0.0000 0.879679 1.000 0.000
#> GSM486789 2 0.0000 0.905519 0.000 1.000
#> GSM486791 1 0.0000 0.879679 1.000 0.000
#> GSM486793 1 0.6048 0.831618 0.852 0.148
#> GSM486795 1 0.1633 0.870459 0.976 0.024
#> GSM486797 2 0.1184 0.899373 0.016 0.984
#> GSM486799 1 0.0000 0.879679 1.000 0.000
#> GSM486801 1 0.0000 0.879679 1.000 0.000
#> GSM486803 1 0.0376 0.878777 0.996 0.004
#> GSM486805 2 0.0376 0.905186 0.004 0.996
#> GSM486807 1 0.6887 0.806771 0.816 0.184
#> GSM486809 2 0.0376 0.905186 0.004 0.996
#> GSM486811 1 0.5294 0.844505 0.880 0.120
#> GSM486813 2 0.9833 0.418095 0.424 0.576
#> GSM486815 1 0.5842 0.835601 0.860 0.140
#> GSM486817 1 0.9286 0.384100 0.656 0.344
#> GSM486819 1 0.9491 0.309991 0.632 0.368
#> GSM486822 2 0.0000 0.905519 0.000 1.000
#> GSM486824 1 0.0376 0.878777 0.996 0.004
#> GSM486828 2 0.0000 0.905519 0.000 1.000
#> GSM486831 1 0.0000 0.879679 1.000 0.000
#> GSM486833 2 0.4022 0.849935 0.080 0.920
#> GSM486835 1 0.0000 0.879679 1.000 0.000
#> GSM486837 2 0.0376 0.905186 0.004 0.996
#> GSM486839 1 0.0376 0.878777 0.996 0.004
#> GSM486841 1 0.6048 0.831618 0.852 0.148
#> GSM486843 1 0.0000 0.879679 1.000 0.000
#> GSM486845 2 0.0376 0.905186 0.004 0.996
#> GSM486847 1 0.0000 0.879679 1.000 0.000
#> GSM486849 2 0.0376 0.905186 0.004 0.996
#> GSM486851 1 0.0376 0.878777 0.996 0.004
#> GSM486853 2 0.0376 0.905186 0.004 0.996
#> GSM486855 2 0.6247 0.845228 0.156 0.844
#> GSM486857 2 0.0376 0.905186 0.004 0.996
#> GSM486736 2 0.0000 0.905519 0.000 1.000
#> GSM486738 2 0.6148 0.847759 0.152 0.848
#> GSM486740 2 0.6048 0.848983 0.148 0.852
#> GSM486742 2 0.0000 0.905519 0.000 1.000
#> GSM486744 2 0.5842 0.853730 0.140 0.860
#> GSM486746 2 0.8207 0.749097 0.256 0.744
#> GSM486748 1 0.9963 0.350235 0.536 0.464
#> GSM486750 2 0.0000 0.905519 0.000 1.000
#> GSM486752 2 0.2043 0.889190 0.032 0.968
#> GSM486754 2 0.5519 0.858666 0.128 0.872
#> GSM486756 2 0.6247 0.845496 0.156 0.844
#> GSM486758 1 0.9970 0.342463 0.532 0.468
#> GSM486760 1 0.0000 0.879679 1.000 0.000
#> GSM486762 1 0.9000 0.654502 0.684 0.316
#> GSM486764 1 0.2603 0.858649 0.956 0.044
#> GSM486766 1 0.6148 0.829034 0.848 0.152
#> GSM486768 2 0.7056 0.818063 0.192 0.808
#> GSM486770 2 0.0000 0.905519 0.000 1.000
#> GSM486772 2 0.5946 0.851246 0.144 0.856
#> GSM486774 2 0.0376 0.905186 0.004 0.996
#> GSM486776 1 0.0000 0.879679 1.000 0.000
#> GSM486778 1 0.6887 0.808423 0.816 0.184
#> GSM486780 2 0.9000 0.657046 0.316 0.684
#> GSM486782 2 0.0376 0.905186 0.004 0.996
#> GSM486784 2 0.5946 0.851661 0.144 0.856
#> GSM486786 1 0.5946 0.833386 0.856 0.144
#> GSM486788 1 0.0376 0.878777 0.996 0.004
#> GSM486790 2 0.0000 0.905519 0.000 1.000
#> GSM486792 1 0.0000 0.879679 1.000 0.000
#> GSM486794 1 0.6438 0.821236 0.836 0.164
#> GSM486796 1 0.3431 0.845189 0.936 0.064
#> GSM486798 2 0.0376 0.905186 0.004 0.996
#> GSM486800 1 0.0376 0.878777 0.996 0.004
#> GSM486802 1 0.0376 0.878777 0.996 0.004
#> GSM486804 1 0.0376 0.878777 0.996 0.004
#> GSM486806 2 0.0376 0.905186 0.004 0.996
#> GSM486808 1 0.6247 0.827179 0.844 0.156
#> GSM486810 2 0.0000 0.905519 0.000 1.000
#> GSM486812 1 0.4815 0.850697 0.896 0.104
#> GSM486814 2 0.7219 0.811139 0.200 0.800
#> GSM486816 1 0.5842 0.835433 0.860 0.140
#> GSM486818 1 0.7674 0.649133 0.776 0.224
#> GSM486821 1 0.7883 0.630902 0.764 0.236
#> GSM486823 2 0.0376 0.905186 0.004 0.996
#> GSM486826 1 0.0000 0.879679 1.000 0.000
#> GSM486830 2 0.0376 0.905186 0.004 0.996
#> GSM486832 1 0.0376 0.878777 0.996 0.004
#> GSM486834 2 0.0672 0.903608 0.008 0.992
#> GSM486836 1 0.0000 0.879679 1.000 0.000
#> GSM486838 2 0.2043 0.890750 0.032 0.968
#> GSM486840 1 0.0376 0.878777 0.996 0.004
#> GSM486842 1 0.5629 0.839303 0.868 0.132
#> GSM486844 1 0.0376 0.878777 0.996 0.004
#> GSM486846 2 0.0376 0.905186 0.004 0.996
#> GSM486848 1 0.0000 0.879679 1.000 0.000
#> GSM486850 2 0.0000 0.905519 0.000 1.000
#> GSM486852 1 0.1184 0.874325 0.984 0.016
#> GSM486854 2 0.0000 0.905519 0.000 1.000
#> GSM486856 2 0.7950 0.769355 0.240 0.760
#> GSM486858 2 0.0376 0.905186 0.004 0.996
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 2 0.3879 0.7091 0.152 0.848 0.000
#> GSM486737 2 0.6215 0.1572 0.428 0.572 0.000
#> GSM486739 1 0.5785 0.4538 0.668 0.332 0.000
#> GSM486741 2 0.4228 0.7176 0.148 0.844 0.008
#> GSM486743 1 0.5216 0.5414 0.740 0.260 0.000
#> GSM486745 1 0.4702 0.5787 0.788 0.212 0.000
#> GSM486747 3 0.8094 0.4205 0.124 0.240 0.636
#> GSM486749 2 0.5285 0.7411 0.112 0.824 0.064
#> GSM486751 2 0.4902 0.7430 0.064 0.844 0.092
#> GSM486753 2 0.6235 0.0282 0.436 0.564 0.000
#> GSM486755 1 0.6309 0.1399 0.504 0.496 0.000
#> GSM486757 2 0.8098 0.5579 0.140 0.644 0.216
#> GSM486759 1 0.5810 0.2711 0.664 0.000 0.336
#> GSM486761 3 0.7079 0.5084 0.104 0.176 0.720
#> GSM486763 1 0.4206 0.5794 0.872 0.088 0.040
#> GSM486765 3 0.1832 0.6642 0.036 0.008 0.956
#> GSM486767 1 0.6678 0.0637 0.512 0.480 0.008
#> GSM486769 2 0.3551 0.7239 0.132 0.868 0.000
#> GSM486771 1 0.5016 0.5549 0.760 0.240 0.000
#> GSM486773 2 0.4172 0.7335 0.104 0.868 0.028
#> GSM486775 3 0.4291 0.6341 0.180 0.000 0.820
#> GSM486777 3 0.4443 0.6492 0.052 0.084 0.864
#> GSM486779 1 0.6675 0.2455 0.584 0.404 0.012
#> GSM486781 2 0.2434 0.7623 0.024 0.940 0.036
#> GSM486783 2 0.6309 -0.1375 0.496 0.504 0.000
#> GSM486785 3 0.6063 0.5609 0.132 0.084 0.784
#> GSM486787 3 0.4399 0.6245 0.188 0.000 0.812
#> GSM486789 2 0.1643 0.7615 0.044 0.956 0.000
#> GSM486791 1 0.5327 0.3797 0.728 0.000 0.272
#> GSM486793 3 0.2173 0.6602 0.048 0.008 0.944
#> GSM486795 1 0.4834 0.4714 0.792 0.004 0.204
#> GSM486797 2 0.6653 0.6614 0.112 0.752 0.136
#> GSM486799 3 0.3686 0.6451 0.140 0.000 0.860
#> GSM486801 1 0.5859 0.2488 0.656 0.000 0.344
#> GSM486803 3 0.6225 0.3977 0.432 0.000 0.568
#> GSM486805 2 0.3983 0.7444 0.068 0.884 0.048
#> GSM486807 3 0.3043 0.6460 0.008 0.084 0.908
#> GSM486809 2 0.3120 0.7597 0.080 0.908 0.012
#> GSM486811 3 0.3116 0.6537 0.108 0.000 0.892
#> GSM486813 1 0.6570 0.4298 0.668 0.308 0.024
#> GSM486815 3 0.1267 0.6696 0.024 0.004 0.972
#> GSM486817 1 0.8835 0.3386 0.576 0.244 0.180
#> GSM486819 1 0.5339 0.5628 0.824 0.096 0.080
#> GSM486822 2 0.2537 0.7552 0.080 0.920 0.000
#> GSM486824 3 0.6309 0.2504 0.496 0.000 0.504
#> GSM486828 2 0.3213 0.7664 0.060 0.912 0.028
#> GSM486831 1 0.6154 0.0975 0.592 0.000 0.408
#> GSM486833 2 0.7712 0.5664 0.092 0.652 0.256
#> GSM486835 3 0.6302 0.2177 0.480 0.000 0.520
#> GSM486837 2 0.5889 0.6966 0.108 0.796 0.096
#> GSM486839 3 0.6045 0.4345 0.380 0.000 0.620
#> GSM486841 3 0.1751 0.6699 0.028 0.012 0.960
#> GSM486843 3 0.5968 0.4878 0.364 0.000 0.636
#> GSM486845 2 0.2446 0.7645 0.052 0.936 0.012
#> GSM486847 3 0.5098 0.5885 0.248 0.000 0.752
#> GSM486849 2 0.2866 0.7622 0.076 0.916 0.008
#> GSM486851 1 0.4654 0.4625 0.792 0.000 0.208
#> GSM486853 2 0.1289 0.7627 0.032 0.968 0.000
#> GSM486855 1 0.5968 0.4144 0.636 0.364 0.000
#> GSM486857 2 0.6448 0.6784 0.132 0.764 0.104
#> GSM486736 2 0.4605 0.6538 0.204 0.796 0.000
#> GSM486738 2 0.6308 -0.0899 0.492 0.508 0.000
#> GSM486740 1 0.5835 0.4424 0.660 0.340 0.000
#> GSM486742 2 0.3619 0.7251 0.136 0.864 0.000
#> GSM486744 1 0.6308 0.1337 0.508 0.492 0.000
#> GSM486746 1 0.4605 0.5876 0.796 0.204 0.000
#> GSM486748 3 0.8577 -0.0406 0.096 0.436 0.468
#> GSM486750 2 0.3482 0.7262 0.128 0.872 0.000
#> GSM486752 2 0.5780 0.7258 0.080 0.800 0.120
#> GSM486754 2 0.5988 0.2777 0.368 0.632 0.000
#> GSM486756 2 0.6008 0.2472 0.372 0.628 0.000
#> GSM486758 3 0.9027 -0.0616 0.132 0.428 0.440
#> GSM486760 3 0.5785 0.5034 0.332 0.000 0.668
#> GSM486762 3 0.8332 0.3150 0.104 0.316 0.580
#> GSM486764 1 0.5202 0.4311 0.772 0.008 0.220
#> GSM486766 3 0.1919 0.6652 0.024 0.020 0.956
#> GSM486768 1 0.5859 0.4577 0.656 0.344 0.000
#> GSM486770 2 0.4178 0.6889 0.172 0.828 0.000
#> GSM486772 1 0.6260 0.2073 0.552 0.448 0.000
#> GSM486774 2 0.5874 0.6986 0.116 0.796 0.088
#> GSM486776 3 0.4555 0.6181 0.200 0.000 0.800
#> GSM486778 3 0.5981 0.6159 0.132 0.080 0.788
#> GSM486780 1 0.7043 0.2313 0.576 0.400 0.024
#> GSM486782 2 0.0424 0.7654 0.000 0.992 0.008
#> GSM486784 2 0.6244 0.0793 0.440 0.560 0.000
#> GSM486786 3 0.5631 0.5753 0.132 0.064 0.804
#> GSM486788 1 0.6291 -0.0930 0.532 0.000 0.468
#> GSM486790 2 0.3116 0.7407 0.108 0.892 0.000
#> GSM486792 1 0.6468 -0.0522 0.552 0.004 0.444
#> GSM486794 3 0.2176 0.6690 0.020 0.032 0.948
#> GSM486796 1 0.4897 0.5021 0.812 0.016 0.172
#> GSM486798 2 0.5435 0.7231 0.048 0.808 0.144
#> GSM486800 3 0.6045 0.4260 0.380 0.000 0.620
#> GSM486802 1 0.5254 0.3932 0.736 0.000 0.264
#> GSM486804 3 0.6825 0.2681 0.488 0.012 0.500
#> GSM486806 2 0.2903 0.7601 0.028 0.924 0.048
#> GSM486808 3 0.1129 0.6695 0.004 0.020 0.976
#> GSM486810 2 0.3038 0.7413 0.104 0.896 0.000
#> GSM486812 3 0.2448 0.6624 0.076 0.000 0.924
#> GSM486814 1 0.6095 0.3725 0.608 0.392 0.000
#> GSM486816 3 0.1877 0.6664 0.032 0.012 0.956
#> GSM486818 1 0.7564 0.4086 0.692 0.156 0.152
#> GSM486821 1 0.5500 0.5543 0.816 0.084 0.100
#> GSM486823 2 0.2537 0.7533 0.080 0.920 0.000
#> GSM486826 3 0.7256 0.3555 0.440 0.028 0.532
#> GSM486830 2 0.3293 0.7536 0.088 0.900 0.012
#> GSM486832 3 0.6274 0.2670 0.456 0.000 0.544
#> GSM486834 2 0.6595 0.6508 0.076 0.744 0.180
#> GSM486836 3 0.6008 0.4364 0.372 0.000 0.628
#> GSM486838 2 0.8304 0.5442 0.144 0.624 0.232
#> GSM486840 3 0.5785 0.5121 0.332 0.000 0.668
#> GSM486842 3 0.0892 0.6691 0.020 0.000 0.980
#> GSM486844 1 0.7091 -0.1168 0.560 0.024 0.416
#> GSM486846 2 0.2599 0.7673 0.052 0.932 0.016
#> GSM486848 3 0.6192 0.3660 0.420 0.000 0.580
#> GSM486850 2 0.2356 0.7558 0.072 0.928 0.000
#> GSM486852 1 0.4723 0.5096 0.824 0.016 0.160
#> GSM486854 2 0.2599 0.7571 0.052 0.932 0.016
#> GSM486856 1 0.5859 0.4586 0.656 0.344 0.000
#> GSM486858 2 0.6191 0.6891 0.140 0.776 0.084
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 4 0.474 0.6169 0.252 0.020 0.000 0.728
#> GSM486737 2 0.514 0.4982 0.048 0.728 0.000 0.224
#> GSM486739 1 0.506 0.3058 0.692 0.024 0.000 0.284
#> GSM486741 4 0.607 0.3445 0.008 0.464 0.028 0.500
#> GSM486743 2 0.670 0.1957 0.436 0.476 0.000 0.088
#> GSM486745 1 0.582 0.3731 0.704 0.176 0.000 0.120
#> GSM486747 3 0.713 0.3992 0.008 0.188 0.596 0.208
#> GSM486749 4 0.514 0.6724 0.180 0.020 0.036 0.764
#> GSM486751 4 0.457 0.7098 0.024 0.052 0.100 0.824
#> GSM486753 2 0.717 0.2904 0.144 0.496 0.000 0.360
#> GSM486755 2 0.746 0.3806 0.288 0.500 0.000 0.212
#> GSM486757 4 0.810 0.3118 0.008 0.340 0.260 0.392
#> GSM486759 1 0.691 0.2661 0.532 0.348 0.120 0.000
#> GSM486761 3 0.586 0.5391 0.008 0.108 0.720 0.164
#> GSM486763 1 0.603 0.3033 0.644 0.296 0.008 0.052
#> GSM486765 3 0.246 0.6393 0.008 0.036 0.924 0.032
#> GSM486767 2 0.621 0.5253 0.100 0.704 0.020 0.176
#> GSM486769 4 0.474 0.6290 0.240 0.024 0.000 0.736
#> GSM486771 1 0.615 -0.0807 0.492 0.460 0.000 0.048
#> GSM486773 4 0.654 0.5421 0.008 0.332 0.072 0.588
#> GSM486775 3 0.617 0.4889 0.124 0.208 0.668 0.000
#> GSM486777 3 0.531 0.5996 0.164 0.008 0.756 0.072
#> GSM486779 2 0.345 0.5466 0.052 0.868 0.000 0.080
#> GSM486781 4 0.324 0.7140 0.008 0.064 0.040 0.888
#> GSM486783 2 0.615 0.5324 0.112 0.664 0.000 0.224
#> GSM486785 3 0.629 0.4869 0.004 0.240 0.656 0.100
#> GSM486787 3 0.643 0.4874 0.192 0.160 0.648 0.000
#> GSM486789 4 0.323 0.7106 0.072 0.048 0.000 0.880
#> GSM486791 1 0.512 0.4663 0.740 0.028 0.220 0.012
#> GSM486793 3 0.264 0.6315 0.012 0.052 0.916 0.020
#> GSM486795 1 0.676 0.4775 0.648 0.164 0.176 0.012
#> GSM486797 4 0.664 0.6266 0.020 0.144 0.164 0.672
#> GSM486799 3 0.577 0.5590 0.136 0.152 0.712 0.000
#> GSM486801 1 0.693 0.4232 0.580 0.164 0.256 0.000
#> GSM486803 2 0.743 0.0671 0.260 0.512 0.228 0.000
#> GSM486805 4 0.465 0.7059 0.020 0.076 0.084 0.820
#> GSM486807 3 0.319 0.6436 0.048 0.004 0.888 0.060
#> GSM486809 4 0.470 0.6796 0.172 0.036 0.008 0.784
#> GSM486811 3 0.465 0.5861 0.184 0.008 0.780 0.028
#> GSM486813 2 0.495 0.5198 0.180 0.760 0.000 0.060
#> GSM486815 3 0.317 0.6338 0.020 0.080 0.888 0.012
#> GSM486817 2 0.532 0.5275 0.128 0.780 0.036 0.056
#> GSM486819 1 0.528 0.4772 0.784 0.028 0.076 0.112
#> GSM486822 4 0.355 0.7055 0.096 0.044 0.000 0.860
#> GSM486824 2 0.695 0.1375 0.304 0.556 0.140 0.000
#> GSM486828 4 0.340 0.7176 0.064 0.036 0.016 0.884
#> GSM486831 1 0.712 0.2140 0.496 0.136 0.368 0.000
#> GSM486833 4 0.769 0.3967 0.032 0.116 0.332 0.520
#> GSM486835 1 0.785 0.2416 0.400 0.292 0.308 0.000
#> GSM486837 4 0.607 0.6392 0.008 0.180 0.112 0.700
#> GSM486839 3 0.775 0.0774 0.280 0.280 0.440 0.000
#> GSM486841 3 0.350 0.6444 0.084 0.008 0.872 0.036
#> GSM486843 2 0.786 -0.0846 0.288 0.392 0.320 0.000
#> GSM486845 4 0.349 0.7161 0.064 0.040 0.016 0.880
#> GSM486847 3 0.691 0.4307 0.216 0.192 0.592 0.000
#> GSM486849 4 0.501 0.6953 0.060 0.136 0.016 0.788
#> GSM486851 1 0.402 0.5102 0.848 0.068 0.076 0.008
#> GSM486853 4 0.438 0.6623 0.012 0.200 0.008 0.780
#> GSM486855 2 0.769 0.3491 0.308 0.448 0.000 0.244
#> GSM486857 4 0.714 0.5010 0.008 0.328 0.120 0.544
#> GSM486736 4 0.513 0.4968 0.344 0.004 0.008 0.644
#> GSM486738 2 0.669 0.5150 0.160 0.616 0.000 0.224
#> GSM486740 1 0.491 0.2701 0.676 0.012 0.000 0.312
#> GSM486742 4 0.629 0.2621 0.040 0.440 0.008 0.512
#> GSM486744 4 0.790 -0.3873 0.292 0.352 0.000 0.356
#> GSM486746 1 0.514 0.4018 0.744 0.064 0.000 0.192
#> GSM486748 3 0.712 0.1751 0.012 0.100 0.532 0.356
#> GSM486750 4 0.385 0.6730 0.180 0.012 0.000 0.808
#> GSM486752 4 0.515 0.6623 0.088 0.004 0.140 0.768
#> GSM486754 4 0.753 0.0203 0.208 0.316 0.000 0.476
#> GSM486756 2 0.739 0.3598 0.176 0.484 0.000 0.340
#> GSM486758 3 0.830 -0.0423 0.016 0.268 0.392 0.324
#> GSM486760 3 0.604 0.3748 0.332 0.060 0.608 0.000
#> GSM486762 3 0.690 0.3759 0.008 0.124 0.600 0.268
#> GSM486764 1 0.672 0.1762 0.540 0.388 0.052 0.020
#> GSM486766 3 0.164 0.6468 0.012 0.012 0.956 0.020
#> GSM486768 1 0.781 -0.1574 0.416 0.308 0.000 0.276
#> GSM486770 4 0.484 0.5945 0.272 0.012 0.004 0.712
#> GSM486772 1 0.779 -0.1061 0.384 0.244 0.000 0.372
#> GSM486774 4 0.678 0.5713 0.008 0.248 0.124 0.620
#> GSM486776 3 0.674 0.4233 0.160 0.232 0.608 0.000
#> GSM486778 3 0.676 0.4537 0.260 0.008 0.616 0.116
#> GSM486780 2 0.402 0.5511 0.052 0.840 0.004 0.104
#> GSM486782 4 0.255 0.7159 0.012 0.048 0.020 0.920
#> GSM486784 2 0.701 0.4766 0.156 0.560 0.000 0.284
#> GSM486786 3 0.624 0.4589 0.008 0.308 0.624 0.060
#> GSM486788 1 0.761 0.2924 0.476 0.260 0.264 0.000
#> GSM486790 4 0.456 0.6813 0.152 0.056 0.000 0.792
#> GSM486792 1 0.532 0.2326 0.628 0.008 0.356 0.008
#> GSM486794 3 0.313 0.6427 0.068 0.008 0.892 0.032
#> GSM486796 1 0.629 0.4953 0.716 0.148 0.100 0.036
#> GSM486798 4 0.524 0.6660 0.040 0.024 0.172 0.764
#> GSM486800 3 0.744 0.2334 0.252 0.236 0.512 0.000
#> GSM486802 1 0.698 0.3757 0.584 0.268 0.144 0.004
#> GSM486804 2 0.564 0.4133 0.112 0.732 0.152 0.004
#> GSM486806 4 0.319 0.7186 0.020 0.036 0.048 0.896
#> GSM486808 3 0.259 0.6474 0.036 0.012 0.920 0.032
#> GSM486810 4 0.422 0.6715 0.184 0.012 0.008 0.796
#> GSM486812 3 0.415 0.6011 0.156 0.012 0.816 0.016
#> GSM486814 2 0.655 0.4930 0.240 0.624 0.000 0.136
#> GSM486816 3 0.308 0.6400 0.020 0.052 0.900 0.028
#> GSM486818 2 0.584 0.3813 0.276 0.668 0.048 0.008
#> GSM486821 1 0.540 0.5065 0.776 0.116 0.080 0.028
#> GSM486823 4 0.340 0.6952 0.128 0.012 0.004 0.856
#> GSM486826 2 0.553 0.4208 0.092 0.736 0.168 0.004
#> GSM486830 4 0.382 0.6928 0.140 0.016 0.008 0.836
#> GSM486832 3 0.683 0.1565 0.388 0.104 0.508 0.000
#> GSM486834 4 0.612 0.6077 0.008 0.092 0.216 0.684
#> GSM486836 3 0.767 0.0504 0.340 0.224 0.436 0.000
#> GSM486838 4 0.748 0.4877 0.008 0.264 0.188 0.540
#> GSM486840 3 0.783 0.0327 0.280 0.312 0.408 0.000
#> GSM486842 3 0.293 0.6385 0.068 0.024 0.900 0.008
#> GSM486844 2 0.731 0.3474 0.176 0.592 0.216 0.016
#> GSM486846 4 0.453 0.6930 0.032 0.144 0.016 0.808
#> GSM486848 2 0.789 -0.1590 0.324 0.376 0.300 0.000
#> GSM486850 4 0.454 0.7027 0.104 0.072 0.008 0.816
#> GSM486852 1 0.430 0.4972 0.828 0.116 0.044 0.012
#> GSM486854 4 0.477 0.6715 0.020 0.172 0.024 0.784
#> GSM486856 2 0.719 0.4246 0.292 0.536 0.000 0.172
#> GSM486858 4 0.679 0.5497 0.016 0.300 0.084 0.600
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 5 0.488 -0.1105 0.000 0.000 0.024 0.444 0.532
#> GSM486737 3 0.629 0.4120 0.000 0.280 0.580 0.116 0.024
#> GSM486739 5 0.514 0.3687 0.000 0.088 0.024 0.160 0.728
#> GSM486741 3 0.597 0.0154 0.000 0.052 0.548 0.368 0.032
#> GSM486743 2 0.586 0.3176 0.000 0.676 0.144 0.036 0.144
#> GSM486745 5 0.632 0.0430 0.000 0.428 0.056 0.044 0.472
#> GSM486747 1 0.724 0.1578 0.440 0.000 0.268 0.264 0.028
#> GSM486749 4 0.628 0.4170 0.016 0.016 0.080 0.584 0.304
#> GSM486751 4 0.567 0.5948 0.116 0.000 0.092 0.712 0.080
#> GSM486753 2 0.836 -0.1760 0.000 0.300 0.292 0.272 0.136
#> GSM486755 3 0.752 0.3027 0.000 0.208 0.488 0.076 0.228
#> GSM486757 3 0.681 0.1985 0.164 0.000 0.584 0.192 0.060
#> GSM486759 2 0.476 0.4344 0.084 0.768 0.028 0.000 0.120
#> GSM486761 1 0.628 0.4101 0.608 0.004 0.132 0.236 0.020
#> GSM486763 5 0.680 0.0853 0.008 0.308 0.224 0.000 0.460
#> GSM486765 1 0.374 0.6082 0.840 0.000 0.080 0.052 0.028
#> GSM486767 3 0.695 0.3845 0.008 0.336 0.516 0.064 0.076
#> GSM486769 4 0.491 0.1621 0.000 0.000 0.024 0.496 0.480
#> GSM486771 2 0.654 0.2669 0.000 0.548 0.180 0.016 0.256
#> GSM486773 4 0.599 0.2580 0.028 0.004 0.464 0.464 0.040
#> GSM486775 1 0.511 0.4302 0.648 0.304 0.024 0.000 0.024
#> GSM486777 1 0.477 0.6228 0.788 0.024 0.028 0.048 0.112
#> GSM486779 3 0.577 0.4371 0.000 0.292 0.620 0.052 0.036
#> GSM486781 4 0.270 0.6147 0.012 0.000 0.048 0.896 0.044
#> GSM486783 2 0.701 -0.0620 0.000 0.476 0.340 0.144 0.040
#> GSM486785 1 0.704 0.2185 0.504 0.024 0.344 0.100 0.028
#> GSM486787 1 0.580 0.4246 0.604 0.312 0.048 0.000 0.036
#> GSM486789 4 0.563 0.4446 0.000 0.000 0.092 0.572 0.336
#> GSM486791 5 0.737 0.0729 0.244 0.292 0.036 0.000 0.428
#> GSM486793 1 0.416 0.5790 0.804 0.004 0.136 0.028 0.028
#> GSM486795 2 0.790 0.1512 0.200 0.416 0.060 0.012 0.312
#> GSM486797 4 0.735 0.4373 0.180 0.008 0.192 0.548 0.072
#> GSM486799 1 0.555 0.5030 0.668 0.236 0.068 0.000 0.028
#> GSM486801 2 0.699 0.2173 0.268 0.524 0.024 0.008 0.176
#> GSM486803 2 0.720 0.1572 0.108 0.508 0.296 0.000 0.088
#> GSM486805 4 0.538 0.6126 0.084 0.004 0.088 0.744 0.080
#> GSM486807 1 0.451 0.6120 0.792 0.020 0.040 0.132 0.016
#> GSM486809 5 0.651 -0.2148 0.008 0.000 0.148 0.400 0.444
#> GSM486811 1 0.517 0.5953 0.756 0.116 0.020 0.020 0.088
#> GSM486813 2 0.549 -0.2182 0.000 0.476 0.472 0.008 0.044
#> GSM486815 1 0.561 0.5538 0.712 0.016 0.176 0.036 0.060
#> GSM486817 3 0.567 0.3428 0.016 0.360 0.580 0.012 0.032
#> GSM486819 5 0.703 0.2317 0.104 0.316 0.004 0.060 0.516
#> GSM486822 4 0.540 0.4780 0.000 0.000 0.100 0.636 0.264
#> GSM486824 2 0.612 0.3249 0.100 0.640 0.216 0.000 0.044
#> GSM486828 4 0.533 0.5902 0.020 0.004 0.104 0.720 0.152
#> GSM486831 1 0.636 0.1192 0.444 0.436 0.016 0.000 0.104
#> GSM486833 4 0.809 0.2549 0.304 0.000 0.208 0.376 0.112
#> GSM486835 2 0.531 0.3342 0.260 0.672 0.020 0.004 0.044
#> GSM486837 4 0.504 0.5850 0.048 0.020 0.144 0.760 0.028
#> GSM486839 2 0.617 0.2508 0.316 0.576 0.040 0.000 0.068
#> GSM486841 1 0.385 0.6429 0.852 0.028 0.040 0.052 0.028
#> GSM486843 2 0.552 0.4265 0.192 0.704 0.064 0.008 0.032
#> GSM486845 4 0.528 0.5984 0.008 0.040 0.108 0.748 0.096
#> GSM486847 1 0.654 0.2859 0.520 0.352 0.084 0.000 0.044
#> GSM486849 4 0.724 0.3893 0.008 0.012 0.304 0.424 0.252
#> GSM486851 5 0.670 0.1033 0.076 0.396 0.056 0.000 0.472
#> GSM486853 4 0.501 0.5601 0.000 0.028 0.196 0.724 0.052
#> GSM486855 2 0.667 0.2741 0.000 0.616 0.156 0.148 0.080
#> GSM486857 4 0.657 0.3064 0.060 0.004 0.380 0.504 0.052
#> GSM486736 5 0.454 -0.1229 0.000 0.000 0.008 0.452 0.540
#> GSM486738 2 0.687 0.0254 0.000 0.524 0.316 0.092 0.068
#> GSM486740 5 0.483 0.3272 0.000 0.072 0.004 0.208 0.716
#> GSM486742 4 0.740 -0.0842 0.000 0.208 0.364 0.388 0.040
#> GSM486744 2 0.748 0.1455 0.000 0.456 0.096 0.328 0.120
#> GSM486746 5 0.588 0.3322 0.004 0.312 0.004 0.096 0.584
#> GSM486748 4 0.739 0.1292 0.360 0.028 0.112 0.464 0.036
#> GSM486750 4 0.445 0.4860 0.000 0.004 0.028 0.708 0.260
#> GSM486752 4 0.569 0.5414 0.164 0.012 0.028 0.704 0.092
#> GSM486754 4 0.819 0.0960 0.000 0.244 0.176 0.408 0.172
#> GSM486756 3 0.772 0.3527 0.000 0.200 0.496 0.156 0.148
#> GSM486758 3 0.783 0.1784 0.192 0.016 0.500 0.212 0.080
#> GSM486760 1 0.594 0.4294 0.616 0.288 0.020 0.008 0.068
#> GSM486762 1 0.729 0.0977 0.448 0.020 0.132 0.372 0.028
#> GSM486764 5 0.753 -0.0996 0.020 0.328 0.316 0.008 0.328
#> GSM486766 1 0.346 0.6189 0.860 0.012 0.036 0.080 0.012
#> GSM486768 2 0.715 0.2761 0.000 0.540 0.068 0.224 0.168
#> GSM486770 5 0.487 -0.1356 0.000 0.004 0.016 0.444 0.536
#> GSM486772 2 0.813 0.1312 0.000 0.400 0.124 0.240 0.236
#> GSM486774 4 0.564 0.5294 0.052 0.000 0.232 0.668 0.048
#> GSM486776 1 0.579 0.2702 0.540 0.396 0.028 0.004 0.032
#> GSM486778 1 0.654 0.5557 0.656 0.084 0.016 0.084 0.160
#> GSM486780 3 0.571 0.2990 0.000 0.396 0.540 0.036 0.028
#> GSM486782 4 0.334 0.5955 0.004 0.000 0.048 0.848 0.100
#> GSM486784 2 0.753 0.0895 0.000 0.480 0.228 0.220 0.072
#> GSM486786 3 0.699 -0.1068 0.412 0.048 0.460 0.036 0.044
#> GSM486788 2 0.582 0.3469 0.220 0.672 0.028 0.012 0.068
#> GSM486790 4 0.585 0.3681 0.000 0.016 0.064 0.544 0.376
#> GSM486792 1 0.750 0.0392 0.356 0.256 0.028 0.004 0.356
#> GSM486794 1 0.304 0.6380 0.888 0.008 0.020 0.040 0.044
#> GSM486796 2 0.642 0.2147 0.072 0.584 0.024 0.020 0.300
#> GSM486798 4 0.568 0.5555 0.180 0.012 0.040 0.704 0.064
#> GSM486800 1 0.532 0.1792 0.504 0.460 0.020 0.004 0.012
#> GSM486802 2 0.607 0.3964 0.168 0.664 0.028 0.008 0.132
#> GSM486804 3 0.598 0.2877 0.044 0.360 0.560 0.004 0.032
#> GSM486806 4 0.365 0.6098 0.032 0.000 0.056 0.848 0.064
#> GSM486808 1 0.397 0.6126 0.820 0.024 0.024 0.124 0.008
#> GSM486810 4 0.541 0.2272 0.008 0.000 0.040 0.512 0.440
#> GSM486812 1 0.397 0.6178 0.836 0.084 0.016 0.020 0.044
#> GSM486814 2 0.616 0.1714 0.000 0.604 0.280 0.064 0.052
#> GSM486816 1 0.521 0.5692 0.732 0.012 0.176 0.024 0.056
#> GSM486818 2 0.614 0.0617 0.028 0.564 0.340 0.004 0.064
#> GSM486821 2 0.743 0.1164 0.096 0.512 0.016 0.080 0.296
#> GSM486823 4 0.443 0.4921 0.000 0.000 0.036 0.708 0.256
#> GSM486826 3 0.624 0.3453 0.060 0.332 0.568 0.008 0.032
#> GSM486830 4 0.416 0.5365 0.004 0.004 0.016 0.744 0.232
#> GSM486832 1 0.629 0.2797 0.516 0.368 0.020 0.000 0.096
#> GSM486834 4 0.592 0.5381 0.172 0.000 0.112 0.672 0.044
#> GSM486836 2 0.616 0.0742 0.364 0.552 0.016 0.028 0.040
#> GSM486838 4 0.740 0.3927 0.080 0.044 0.256 0.556 0.064
#> GSM486840 2 0.479 0.3664 0.248 0.704 0.020 0.000 0.028
#> GSM486842 1 0.264 0.6366 0.908 0.036 0.024 0.024 0.008
#> GSM486844 2 0.758 0.2535 0.136 0.572 0.180 0.068 0.044
#> GSM486846 4 0.449 0.6081 0.004 0.048 0.100 0.800 0.048
#> GSM486848 2 0.535 0.4010 0.240 0.680 0.048 0.000 0.032
#> GSM486850 4 0.651 0.5154 0.000 0.060 0.096 0.596 0.248
#> GSM486852 5 0.678 0.0765 0.056 0.416 0.060 0.008 0.460
#> GSM486854 4 0.442 0.5886 0.000 0.040 0.108 0.796 0.056
#> GSM486856 2 0.609 0.2686 0.000 0.660 0.180 0.104 0.056
#> GSM486858 4 0.650 0.2935 0.028 0.028 0.380 0.520 0.044
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 6 0.387 0.52225 0.004 0.000 0.008 0.192 0.032 0.764
#> GSM486737 2 0.582 0.30126 0.000 0.600 0.220 0.152 0.008 0.020
#> GSM486739 6 0.526 0.41410 0.000 0.088 0.036 0.016 0.160 0.700
#> GSM486741 4 0.714 -0.02934 0.004 0.352 0.188 0.388 0.008 0.060
#> GSM486743 2 0.628 0.34868 0.000 0.588 0.076 0.032 0.248 0.056
#> GSM486745 6 0.671 -0.17318 0.000 0.232 0.024 0.008 0.348 0.388
#> GSM486747 1 0.673 0.06812 0.408 0.008 0.296 0.268 0.016 0.004
#> GSM486749 6 0.660 0.29338 0.032 0.020 0.068 0.300 0.036 0.544
#> GSM486751 4 0.759 0.21582 0.176 0.012 0.092 0.436 0.016 0.268
#> GSM486753 2 0.741 0.29624 0.000 0.456 0.084 0.200 0.028 0.232
#> GSM486755 2 0.765 0.24796 0.000 0.484 0.148 0.104 0.068 0.196
#> GSM486757 3 0.786 0.30053 0.160 0.080 0.476 0.204 0.012 0.068
#> GSM486759 5 0.601 0.19844 0.048 0.412 0.032 0.008 0.484 0.016
#> GSM486761 1 0.562 0.36610 0.596 0.004 0.160 0.232 0.004 0.004
#> GSM486763 5 0.754 -0.05297 0.004 0.100 0.276 0.008 0.384 0.228
#> GSM486765 1 0.332 0.55715 0.824 0.000 0.132 0.024 0.020 0.000
#> GSM486767 2 0.758 0.20338 0.004 0.452 0.284 0.128 0.052 0.080
#> GSM486769 6 0.326 0.53606 0.000 0.000 0.008 0.184 0.012 0.796
#> GSM486771 2 0.660 0.38597 0.000 0.576 0.044 0.040 0.196 0.144
#> GSM486773 4 0.723 0.33275 0.044 0.100 0.200 0.524 0.000 0.132
#> GSM486775 1 0.655 0.12078 0.536 0.168 0.068 0.004 0.224 0.000
#> GSM486777 1 0.571 0.53150 0.700 0.004 0.068 0.044 0.120 0.064
#> GSM486779 2 0.648 0.15329 0.000 0.488 0.332 0.128 0.040 0.012
#> GSM486781 4 0.456 0.40057 0.024 0.008 0.036 0.732 0.004 0.196
#> GSM486783 2 0.504 0.48291 0.000 0.704 0.064 0.188 0.016 0.028
#> GSM486785 1 0.754 -0.08770 0.376 0.096 0.364 0.132 0.028 0.004
#> GSM486787 5 0.705 0.17231 0.380 0.116 0.108 0.000 0.388 0.008
#> GSM486789 6 0.584 0.29266 0.000 0.048 0.068 0.332 0.004 0.548
#> GSM486791 5 0.615 0.43879 0.140 0.020 0.040 0.000 0.608 0.192
#> GSM486793 1 0.447 0.48795 0.716 0.000 0.224 0.032 0.020 0.008
#> GSM486795 5 0.869 0.25363 0.228 0.236 0.060 0.024 0.332 0.120
#> GSM486797 4 0.764 0.22488 0.316 0.068 0.112 0.436 0.012 0.056
#> GSM486799 1 0.683 0.13844 0.488 0.076 0.148 0.008 0.280 0.000
#> GSM486801 5 0.637 0.44940 0.216 0.092 0.032 0.004 0.604 0.052
#> GSM486803 5 0.699 0.06502 0.016 0.268 0.300 0.008 0.392 0.016
#> GSM486805 4 0.785 0.35209 0.184 0.040 0.100 0.480 0.020 0.176
#> GSM486807 1 0.441 0.57348 0.788 0.004 0.052 0.092 0.052 0.012
#> GSM486809 6 0.636 0.38927 0.028 0.004 0.160 0.144 0.048 0.616
#> GSM486811 1 0.612 0.40053 0.624 0.012 0.036 0.044 0.232 0.052
#> GSM486813 2 0.609 0.32632 0.000 0.584 0.256 0.048 0.100 0.012
#> GSM486815 1 0.607 0.46666 0.644 0.008 0.188 0.044 0.088 0.028
#> GSM486817 2 0.658 0.28383 0.020 0.568 0.256 0.048 0.092 0.016
#> GSM486819 5 0.696 0.40547 0.088 0.052 0.032 0.036 0.576 0.216
#> GSM486822 6 0.489 0.35351 0.000 0.008 0.044 0.352 0.004 0.592
#> GSM486824 2 0.691 -0.05872 0.040 0.380 0.224 0.008 0.348 0.000
#> GSM486828 4 0.693 0.23202 0.056 0.052 0.064 0.500 0.008 0.320
#> GSM486831 5 0.573 0.39617 0.300 0.068 0.032 0.004 0.588 0.008
#> GSM486833 1 0.828 0.06417 0.404 0.040 0.160 0.212 0.016 0.168
#> GSM486835 5 0.708 0.43502 0.212 0.264 0.064 0.012 0.448 0.000
#> GSM486837 4 0.532 0.48696 0.052 0.044 0.064 0.732 0.004 0.104
#> GSM486839 5 0.721 0.33132 0.288 0.292 0.048 0.008 0.360 0.004
#> GSM486841 1 0.434 0.55997 0.780 0.000 0.056 0.064 0.096 0.004
#> GSM486843 5 0.737 0.31396 0.136 0.304 0.104 0.024 0.432 0.000
#> GSM486845 4 0.632 0.37363 0.036 0.100 0.040 0.608 0.004 0.212
#> GSM486847 1 0.703 -0.09570 0.400 0.116 0.140 0.000 0.344 0.000
#> GSM486849 6 0.784 -0.00589 0.024 0.100 0.136 0.348 0.020 0.372
#> GSM486851 5 0.578 0.35149 0.016 0.056 0.084 0.000 0.648 0.196
#> GSM486853 4 0.443 0.45958 0.000 0.104 0.036 0.768 0.004 0.088
#> GSM486855 2 0.596 0.48641 0.000 0.656 0.036 0.152 0.108 0.048
#> GSM486857 4 0.753 0.25642 0.076 0.168 0.200 0.500 0.008 0.048
#> GSM486736 6 0.356 0.53077 0.000 0.004 0.000 0.184 0.032 0.780
#> GSM486738 2 0.371 0.49177 0.000 0.816 0.016 0.120 0.024 0.024
#> GSM486740 6 0.516 0.45059 0.004 0.048 0.016 0.048 0.172 0.712
#> GSM486742 2 0.685 0.08297 0.004 0.428 0.092 0.384 0.012 0.080
#> GSM486744 2 0.755 0.35797 0.000 0.432 0.036 0.288 0.108 0.136
#> GSM486746 5 0.549 0.14635 0.000 0.052 0.012 0.016 0.500 0.420
#> GSM486748 4 0.748 0.09299 0.332 0.032 0.128 0.436 0.040 0.032
#> GSM486750 4 0.497 -0.02065 0.004 0.004 0.016 0.516 0.020 0.440
#> GSM486752 4 0.693 0.24140 0.212 0.000 0.032 0.432 0.020 0.304
#> GSM486754 2 0.769 0.09647 0.000 0.364 0.060 0.256 0.044 0.276
#> GSM486756 2 0.746 0.24158 0.000 0.476 0.180 0.144 0.024 0.176
#> GSM486758 3 0.760 0.40246 0.156 0.056 0.548 0.112 0.032 0.096
#> GSM486760 5 0.512 0.14710 0.440 0.012 0.036 0.000 0.504 0.008
#> GSM486762 1 0.745 0.10992 0.392 0.008 0.188 0.336 0.036 0.040
#> GSM486764 3 0.754 0.02329 0.004 0.152 0.352 0.004 0.336 0.152
#> GSM486766 1 0.294 0.57544 0.868 0.000 0.068 0.048 0.012 0.004
#> GSM486768 2 0.763 0.38112 0.000 0.456 0.036 0.196 0.196 0.116
#> GSM486770 6 0.353 0.53847 0.000 0.004 0.012 0.176 0.016 0.792
#> GSM486772 2 0.718 0.27028 0.000 0.456 0.008 0.160 0.112 0.264
#> GSM486774 4 0.565 0.46804 0.044 0.032 0.168 0.684 0.004 0.068
#> GSM486776 1 0.727 -0.16786 0.412 0.152 0.092 0.016 0.328 0.000
#> GSM486778 1 0.640 0.35454 0.560 0.000 0.024 0.040 0.256 0.120
#> GSM486780 2 0.568 0.34442 0.008 0.652 0.216 0.076 0.036 0.012
#> GSM486782 4 0.481 0.22756 0.008 0.008 0.028 0.620 0.004 0.332
#> GSM486784 2 0.592 0.46708 0.000 0.608 0.024 0.256 0.068 0.044
#> GSM486786 3 0.680 0.30635 0.260 0.112 0.528 0.076 0.024 0.000
#> GSM486788 5 0.640 0.48647 0.164 0.184 0.068 0.008 0.576 0.000
#> GSM486790 6 0.617 0.18361 0.000 0.088 0.036 0.380 0.012 0.484
#> GSM486792 5 0.611 0.41834 0.176 0.004 0.072 0.000 0.608 0.140
#> GSM486794 1 0.383 0.58049 0.824 0.000 0.060 0.020 0.072 0.024
#> GSM486796 5 0.724 0.39970 0.092 0.208 0.020 0.024 0.540 0.116
#> GSM486798 4 0.682 0.39291 0.240 0.020 0.036 0.556 0.028 0.120
#> GSM486800 5 0.669 0.23354 0.384 0.156 0.044 0.008 0.408 0.000
#> GSM486802 5 0.698 0.40663 0.156 0.280 0.028 0.024 0.496 0.016
#> GSM486804 2 0.679 -0.10152 0.036 0.424 0.404 0.036 0.096 0.004
#> GSM486806 4 0.590 0.32294 0.048 0.016 0.052 0.612 0.008 0.264
#> GSM486808 1 0.476 0.55934 0.756 0.004 0.072 0.096 0.068 0.004
#> GSM486810 6 0.509 0.48147 0.008 0.012 0.048 0.228 0.020 0.684
#> GSM486812 1 0.468 0.45469 0.720 0.008 0.020 0.020 0.212 0.020
#> GSM486814 2 0.540 0.47470 0.000 0.700 0.044 0.136 0.100 0.020
#> GSM486816 1 0.520 0.50517 0.704 0.008 0.192 0.040 0.028 0.028
#> GSM486818 2 0.685 0.20798 0.016 0.508 0.232 0.028 0.204 0.012
#> GSM486821 5 0.743 0.36566 0.036 0.140 0.064 0.076 0.572 0.112
#> GSM486823 6 0.464 0.22188 0.000 0.008 0.020 0.416 0.004 0.552
#> GSM486826 3 0.690 -0.06055 0.040 0.384 0.428 0.032 0.112 0.004
#> GSM486830 4 0.561 0.03107 0.008 0.024 0.028 0.492 0.016 0.432
#> GSM486832 5 0.687 0.35751 0.268 0.060 0.104 0.008 0.532 0.028
#> GSM486834 4 0.716 0.40680 0.152 0.012 0.132 0.544 0.016 0.144
#> GSM486836 5 0.724 0.40217 0.240 0.156 0.096 0.024 0.484 0.000
#> GSM486838 4 0.672 0.44073 0.048 0.096 0.184 0.600 0.008 0.064
#> GSM486840 5 0.696 0.33867 0.180 0.336 0.060 0.008 0.416 0.000
#> GSM486842 1 0.420 0.50979 0.760 0.000 0.092 0.012 0.136 0.000
#> GSM486844 2 0.733 0.18376 0.084 0.504 0.068 0.104 0.240 0.000
#> GSM486846 4 0.534 0.40830 0.012 0.100 0.020 0.680 0.004 0.184
#> GSM486848 2 0.712 -0.31614 0.200 0.372 0.076 0.000 0.348 0.004
#> GSM486850 4 0.712 0.24341 0.012 0.108 0.060 0.504 0.032 0.284
#> GSM486852 5 0.631 0.24673 0.004 0.056 0.136 0.004 0.576 0.224
#> GSM486854 4 0.439 0.46155 0.004 0.112 0.016 0.772 0.008 0.088
#> GSM486856 2 0.549 0.47681 0.000 0.644 0.020 0.204 0.124 0.008
#> GSM486858 4 0.570 0.42446 0.008 0.152 0.156 0.652 0.008 0.024
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> CV:NMF 114 0.987 2.30e-05 2
#> CV:NMF 72 0.960 2.82e-05 3
#> CV:NMF 57 0.784 2.24e-05 4
#> CV:NMF 32 0.739 2.20e-02 5
#> CV:NMF 13 1.000 7.21e-02 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["MAD", "hclust"]
# you can also extract it by
# res = res_list["MAD:hclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'MAD' method.
#> Subgroups are detected by 'hclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.533 0.790 0.896 0.4817 0.496 0.496
#> 3 3 0.536 0.748 0.868 0.1764 0.942 0.882
#> 4 4 0.487 0.565 0.711 0.1491 0.845 0.672
#> 5 5 0.504 0.596 0.716 0.0979 0.885 0.686
#> 6 6 0.537 0.627 0.706 0.0524 0.960 0.852
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 2 0.1414 0.855902 0.020 0.980
#> GSM486737 2 0.2236 0.864489 0.036 0.964
#> GSM486739 2 0.5059 0.830531 0.112 0.888
#> GSM486741 2 0.2043 0.864412 0.032 0.968
#> GSM486743 2 0.2043 0.864785 0.032 0.968
#> GSM486745 2 0.5178 0.828575 0.116 0.884
#> GSM486747 1 0.9000 0.475891 0.684 0.316
#> GSM486749 2 0.1184 0.860802 0.016 0.984
#> GSM486751 1 0.9922 0.015360 0.552 0.448
#> GSM486753 2 0.1414 0.862574 0.020 0.980
#> GSM486755 2 0.1633 0.863543 0.024 0.976
#> GSM486757 1 0.5408 0.817291 0.876 0.124
#> GSM486759 1 0.1843 0.903807 0.972 0.028
#> GSM486761 1 0.0938 0.912272 0.988 0.012
#> GSM486763 1 0.4298 0.869814 0.912 0.088
#> GSM486765 1 0.0000 0.911293 1.000 0.000
#> GSM486767 2 0.8016 0.740360 0.244 0.756
#> GSM486769 2 0.1184 0.856244 0.016 0.984
#> GSM486771 2 0.1184 0.860802 0.016 0.984
#> GSM486773 2 0.8713 0.680414 0.292 0.708
#> GSM486775 1 0.0000 0.911293 1.000 0.000
#> GSM486777 1 0.0376 0.910950 0.996 0.004
#> GSM486779 2 0.2236 0.864489 0.036 0.964
#> GSM486781 2 0.8555 0.694946 0.280 0.720
#> GSM486783 2 0.2236 0.864489 0.036 0.964
#> GSM486785 1 0.0000 0.911293 1.000 0.000
#> GSM486787 1 0.0938 0.911992 0.988 0.012
#> GSM486789 2 0.1414 0.862574 0.020 0.980
#> GSM486791 1 0.2423 0.895304 0.960 0.040
#> GSM486793 1 0.0376 0.910950 0.996 0.004
#> GSM486795 1 0.7950 0.653107 0.760 0.240
#> GSM486797 2 0.9993 0.238966 0.484 0.516
#> GSM486799 1 0.0000 0.911293 1.000 0.000
#> GSM486801 1 0.0938 0.911849 0.988 0.012
#> GSM486803 1 0.1414 0.909799 0.980 0.020
#> GSM486805 2 0.9963 0.303727 0.464 0.536
#> GSM486807 1 0.1843 0.904925 0.972 0.028
#> GSM486809 2 0.3584 0.846502 0.068 0.932
#> GSM486811 1 0.0672 0.912022 0.992 0.008
#> GSM486813 2 0.2948 0.862275 0.052 0.948
#> GSM486815 1 0.0000 0.911293 1.000 0.000
#> GSM486817 1 0.9933 0.008429 0.548 0.452
#> GSM486819 1 0.7745 0.699040 0.772 0.228
#> GSM486822 2 0.0938 0.859017 0.012 0.988
#> GSM486824 1 0.1184 0.911324 0.984 0.016
#> GSM486828 2 0.8813 0.667102 0.300 0.700
#> GSM486831 1 0.0938 0.912472 0.988 0.012
#> GSM486833 2 0.9983 0.264339 0.476 0.524
#> GSM486835 1 0.0938 0.911992 0.988 0.012
#> GSM486837 2 0.8386 0.715180 0.268 0.732
#> GSM486839 1 0.0000 0.911293 1.000 0.000
#> GSM486841 1 0.0000 0.911293 1.000 0.000
#> GSM486843 1 0.1633 0.908820 0.976 0.024
#> GSM486845 2 0.8763 0.672014 0.296 0.704
#> GSM486847 1 0.0000 0.911293 1.000 0.000
#> GSM486849 2 0.1633 0.863698 0.024 0.976
#> GSM486851 1 0.4298 0.869814 0.912 0.088
#> GSM486853 2 0.2236 0.864489 0.036 0.964
#> GSM486855 2 0.2236 0.864489 0.036 0.964
#> GSM486857 2 0.7376 0.773971 0.208 0.792
#> GSM486736 2 0.1414 0.855902 0.020 0.980
#> GSM486738 2 0.2236 0.864489 0.036 0.964
#> GSM486740 2 0.5059 0.830531 0.112 0.888
#> GSM486742 2 0.2043 0.864412 0.032 0.968
#> GSM486744 2 0.2043 0.864785 0.032 0.968
#> GSM486746 2 0.5178 0.828575 0.116 0.884
#> GSM486748 1 0.9000 0.477404 0.684 0.316
#> GSM486750 2 0.1184 0.860802 0.016 0.984
#> GSM486752 1 0.9933 0.000925 0.548 0.452
#> GSM486754 2 0.1414 0.862574 0.020 0.980
#> GSM486756 2 0.1633 0.863543 0.024 0.976
#> GSM486758 1 0.5408 0.817291 0.876 0.124
#> GSM486760 1 0.1843 0.903807 0.972 0.028
#> GSM486762 1 0.0938 0.912272 0.988 0.012
#> GSM486764 1 0.4298 0.869814 0.912 0.088
#> GSM486766 1 0.0000 0.911293 1.000 0.000
#> GSM486768 2 0.8016 0.740360 0.244 0.756
#> GSM486770 2 0.1184 0.856244 0.016 0.984
#> GSM486772 2 0.1184 0.860802 0.016 0.984
#> GSM486774 2 0.8713 0.680205 0.292 0.708
#> GSM486776 1 0.0000 0.911293 1.000 0.000
#> GSM486778 1 0.0376 0.910950 0.996 0.004
#> GSM486780 2 0.2236 0.864489 0.036 0.964
#> GSM486782 2 0.8499 0.699885 0.276 0.724
#> GSM486784 2 0.2236 0.864489 0.036 0.964
#> GSM486786 1 0.0000 0.911293 1.000 0.000
#> GSM486788 1 0.0938 0.911992 0.988 0.012
#> GSM486790 2 0.1414 0.862574 0.020 0.980
#> GSM486792 1 0.2423 0.895304 0.960 0.040
#> GSM486794 1 0.0376 0.910950 0.996 0.004
#> GSM486796 1 0.7950 0.653107 0.760 0.240
#> GSM486798 2 0.9983 0.267276 0.476 0.524
#> GSM486800 1 0.0000 0.911293 1.000 0.000
#> GSM486802 1 0.0938 0.911849 0.988 0.012
#> GSM486804 1 0.1414 0.909799 0.980 0.020
#> GSM486806 2 0.9866 0.397870 0.432 0.568
#> GSM486808 1 0.1843 0.904925 0.972 0.028
#> GSM486810 2 0.3584 0.846502 0.068 0.932
#> GSM486812 1 0.0672 0.912022 0.992 0.008
#> GSM486814 2 0.2948 0.862275 0.052 0.948
#> GSM486816 1 0.0000 0.911293 1.000 0.000
#> GSM486818 1 0.9933 0.008429 0.548 0.452
#> GSM486821 1 0.7745 0.699040 0.772 0.228
#> GSM486823 2 0.0938 0.859017 0.012 0.988
#> GSM486826 1 0.1184 0.911324 0.984 0.016
#> GSM486830 2 0.8813 0.667102 0.300 0.700
#> GSM486832 1 0.0938 0.912472 0.988 0.012
#> GSM486834 2 0.9977 0.277646 0.472 0.528
#> GSM486836 1 0.0938 0.911992 0.988 0.012
#> GSM486838 2 0.8016 0.741391 0.244 0.756
#> GSM486840 1 0.0000 0.911293 1.000 0.000
#> GSM486842 1 0.0000 0.911293 1.000 0.000
#> GSM486844 1 0.1843 0.906949 0.972 0.028
#> GSM486846 2 0.8763 0.672014 0.296 0.704
#> GSM486848 1 0.0000 0.911293 1.000 0.000
#> GSM486850 2 0.1633 0.863698 0.024 0.976
#> GSM486852 1 0.4298 0.869814 0.912 0.088
#> GSM486854 2 0.2236 0.864489 0.036 0.964
#> GSM486856 2 0.2236 0.864489 0.036 0.964
#> GSM486858 2 0.7056 0.786417 0.192 0.808
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 2 0.3551 0.77418 0.000 0.868 0.132
#> GSM486737 2 0.1129 0.81018 0.004 0.976 0.020
#> GSM486739 2 0.4602 0.75678 0.016 0.832 0.152
#> GSM486741 2 0.1031 0.81039 0.000 0.976 0.024
#> GSM486743 2 0.1643 0.81027 0.000 0.956 0.044
#> GSM486745 2 0.4663 0.75410 0.016 0.828 0.156
#> GSM486747 1 0.6908 0.46100 0.656 0.308 0.036
#> GSM486749 2 0.1753 0.80819 0.000 0.952 0.048
#> GSM486751 1 0.7466 0.00883 0.520 0.444 0.036
#> GSM486753 2 0.1411 0.81005 0.000 0.964 0.036
#> GSM486755 2 0.1411 0.81073 0.000 0.964 0.036
#> GSM486757 1 0.5004 0.74959 0.840 0.088 0.072
#> GSM486759 1 0.1751 0.87086 0.960 0.028 0.012
#> GSM486761 1 0.1015 0.87613 0.980 0.012 0.008
#> GSM486763 3 0.3295 0.88539 0.096 0.008 0.896
#> GSM486765 1 0.0237 0.87592 0.996 0.000 0.004
#> GSM486767 2 0.6297 0.68999 0.184 0.756 0.060
#> GSM486769 2 0.3482 0.77689 0.000 0.872 0.128
#> GSM486771 2 0.1753 0.81075 0.000 0.952 0.048
#> GSM486773 2 0.6337 0.64348 0.264 0.708 0.028
#> GSM486775 1 0.0747 0.87750 0.984 0.000 0.016
#> GSM486777 1 0.1643 0.85501 0.956 0.000 0.044
#> GSM486779 2 0.1399 0.80926 0.004 0.968 0.028
#> GSM486781 2 0.6303 0.65713 0.248 0.720 0.032
#> GSM486783 2 0.1267 0.80947 0.004 0.972 0.024
#> GSM486785 1 0.0592 0.87637 0.988 0.000 0.012
#> GSM486787 1 0.1620 0.87768 0.964 0.012 0.024
#> GSM486789 2 0.2625 0.79652 0.000 0.916 0.084
#> GSM486791 3 0.4702 0.83185 0.212 0.000 0.788
#> GSM486793 1 0.1753 0.85510 0.952 0.000 0.048
#> GSM486795 1 0.6887 0.55161 0.704 0.236 0.060
#> GSM486797 2 0.7484 0.20101 0.460 0.504 0.036
#> GSM486799 1 0.0747 0.87642 0.984 0.000 0.016
#> GSM486801 1 0.1751 0.87672 0.960 0.012 0.028
#> GSM486803 1 0.2313 0.87174 0.944 0.024 0.032
#> GSM486805 2 0.7526 0.30949 0.424 0.536 0.040
#> GSM486807 1 0.1399 0.86907 0.968 0.028 0.004
#> GSM486809 2 0.4465 0.74492 0.004 0.820 0.176
#> GSM486811 1 0.1453 0.87552 0.968 0.008 0.024
#> GSM486813 2 0.2056 0.81061 0.024 0.952 0.024
#> GSM486815 1 0.0424 0.87732 0.992 0.000 0.008
#> GSM486817 1 0.7913 -0.00221 0.492 0.452 0.056
#> GSM486819 3 0.8216 0.73463 0.172 0.188 0.640
#> GSM486822 2 0.2711 0.79299 0.000 0.912 0.088
#> GSM486824 1 0.1636 0.87721 0.964 0.016 0.020
#> GSM486828 2 0.6633 0.63907 0.260 0.700 0.040
#> GSM486831 1 0.1877 0.87160 0.956 0.012 0.032
#> GSM486833 2 0.7913 0.21891 0.452 0.492 0.056
#> GSM486835 1 0.1482 0.87771 0.968 0.012 0.020
#> GSM486837 2 0.6211 0.67544 0.228 0.736 0.036
#> GSM486839 1 0.0892 0.87619 0.980 0.000 0.020
#> GSM486841 1 0.0592 0.87700 0.988 0.000 0.012
#> GSM486843 1 0.1774 0.87541 0.960 0.024 0.016
#> GSM486845 2 0.6490 0.64455 0.256 0.708 0.036
#> GSM486847 1 0.0892 0.87619 0.980 0.000 0.020
#> GSM486849 2 0.1529 0.81030 0.000 0.960 0.040
#> GSM486851 3 0.3375 0.88665 0.100 0.008 0.892
#> GSM486853 2 0.1267 0.80947 0.004 0.972 0.024
#> GSM486855 2 0.1267 0.80947 0.004 0.972 0.024
#> GSM486857 2 0.5348 0.72396 0.176 0.796 0.028
#> GSM486736 2 0.3551 0.77418 0.000 0.868 0.132
#> GSM486738 2 0.1129 0.81018 0.004 0.976 0.020
#> GSM486740 2 0.4602 0.75678 0.016 0.832 0.152
#> GSM486742 2 0.1031 0.81039 0.000 0.976 0.024
#> GSM486744 2 0.1643 0.81027 0.000 0.956 0.044
#> GSM486746 2 0.4663 0.75410 0.016 0.828 0.156
#> GSM486748 1 0.6908 0.46198 0.656 0.308 0.036
#> GSM486750 2 0.1753 0.80819 0.000 0.952 0.048
#> GSM486752 1 0.7372 0.00296 0.520 0.448 0.032
#> GSM486754 2 0.1411 0.81005 0.000 0.964 0.036
#> GSM486756 2 0.1411 0.81073 0.000 0.964 0.036
#> GSM486758 1 0.5004 0.74959 0.840 0.088 0.072
#> GSM486760 1 0.1751 0.87086 0.960 0.028 0.012
#> GSM486762 1 0.1015 0.87613 0.980 0.012 0.008
#> GSM486764 3 0.3295 0.88539 0.096 0.008 0.896
#> GSM486766 1 0.0237 0.87592 0.996 0.000 0.004
#> GSM486768 2 0.6297 0.68999 0.184 0.756 0.060
#> GSM486770 2 0.3482 0.77689 0.000 0.872 0.128
#> GSM486772 2 0.1753 0.81075 0.000 0.952 0.048
#> GSM486774 2 0.6337 0.64361 0.264 0.708 0.028
#> GSM486776 1 0.0747 0.87750 0.984 0.000 0.016
#> GSM486778 1 0.1643 0.85501 0.956 0.000 0.044
#> GSM486780 2 0.1399 0.80926 0.004 0.968 0.028
#> GSM486782 2 0.6264 0.66114 0.244 0.724 0.032
#> GSM486784 2 0.1267 0.80947 0.004 0.972 0.024
#> GSM486786 1 0.0592 0.87637 0.988 0.000 0.012
#> GSM486788 1 0.1620 0.87768 0.964 0.012 0.024
#> GSM486790 2 0.2625 0.79652 0.000 0.916 0.084
#> GSM486792 3 0.4702 0.83185 0.212 0.000 0.788
#> GSM486794 1 0.1753 0.85510 0.952 0.000 0.048
#> GSM486796 1 0.6887 0.55161 0.704 0.236 0.060
#> GSM486798 2 0.7566 0.23945 0.448 0.512 0.040
#> GSM486800 1 0.0747 0.87642 0.984 0.000 0.016
#> GSM486802 1 0.1751 0.87672 0.960 0.012 0.028
#> GSM486804 1 0.2313 0.87174 0.944 0.024 0.032
#> GSM486806 2 0.7438 0.40289 0.392 0.568 0.040
#> GSM486808 1 0.1399 0.86907 0.968 0.028 0.004
#> GSM486810 2 0.4465 0.74492 0.004 0.820 0.176
#> GSM486812 1 0.1453 0.87552 0.968 0.008 0.024
#> GSM486814 2 0.2056 0.81061 0.024 0.952 0.024
#> GSM486816 1 0.0424 0.87732 0.992 0.000 0.008
#> GSM486818 1 0.7913 -0.00221 0.492 0.452 0.056
#> GSM486821 3 0.8216 0.73463 0.172 0.188 0.640
#> GSM486823 2 0.2711 0.79299 0.000 0.912 0.088
#> GSM486826 1 0.1636 0.87721 0.964 0.016 0.020
#> GSM486830 2 0.6633 0.63907 0.260 0.700 0.040
#> GSM486832 1 0.1877 0.87160 0.956 0.012 0.032
#> GSM486834 2 0.7909 0.23282 0.448 0.496 0.056
#> GSM486836 1 0.1482 0.87771 0.968 0.012 0.020
#> GSM486838 2 0.5891 0.69991 0.200 0.764 0.036
#> GSM486840 1 0.0892 0.87619 0.980 0.000 0.020
#> GSM486842 1 0.0592 0.87700 0.988 0.000 0.012
#> GSM486844 1 0.2050 0.87288 0.952 0.028 0.020
#> GSM486846 2 0.6490 0.64455 0.256 0.708 0.036
#> GSM486848 1 0.0892 0.87619 0.980 0.000 0.020
#> GSM486850 2 0.1529 0.81030 0.000 0.960 0.040
#> GSM486852 3 0.3375 0.88665 0.100 0.008 0.892
#> GSM486854 2 0.1267 0.80947 0.004 0.972 0.024
#> GSM486856 2 0.1267 0.80947 0.004 0.972 0.024
#> GSM486858 2 0.5239 0.73462 0.160 0.808 0.032
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 4 0.5137 0.7766 0.000 0.296 0.024 0.680
#> GSM486737 2 0.1118 0.4713 0.000 0.964 0.000 0.036
#> GSM486739 4 0.6979 0.5898 0.008 0.416 0.088 0.488
#> GSM486741 2 0.2530 0.4302 0.000 0.888 0.000 0.112
#> GSM486743 2 0.3942 0.2467 0.000 0.764 0.000 0.236
#> GSM486745 4 0.7028 0.5718 0.008 0.416 0.092 0.484
#> GSM486747 1 0.7028 0.4543 0.596 0.204 0.004 0.196
#> GSM486749 2 0.4920 -0.2607 0.000 0.628 0.004 0.368
#> GSM486751 1 0.7809 0.1208 0.464 0.276 0.004 0.256
#> GSM486753 2 0.4008 0.2186 0.000 0.756 0.000 0.244
#> GSM486755 2 0.3528 0.3168 0.000 0.808 0.000 0.192
#> GSM486757 1 0.4682 0.6979 0.760 0.004 0.024 0.212
#> GSM486759 1 0.1516 0.8298 0.960 0.016 0.008 0.016
#> GSM486761 1 0.2384 0.8140 0.916 0.008 0.004 0.072
#> GSM486763 3 0.0376 0.8638 0.004 0.000 0.992 0.004
#> GSM486765 1 0.0707 0.8299 0.980 0.000 0.000 0.020
#> GSM486767 2 0.8155 0.2422 0.160 0.524 0.048 0.268
#> GSM486769 4 0.5038 0.7768 0.000 0.296 0.020 0.684
#> GSM486771 2 0.3873 0.2400 0.000 0.772 0.000 0.228
#> GSM486773 2 0.7654 0.2600 0.212 0.420 0.000 0.368
#> GSM486775 1 0.0657 0.8307 0.984 0.000 0.012 0.004
#> GSM486777 1 0.2111 0.8087 0.932 0.000 0.044 0.024
#> GSM486779 2 0.3831 0.3816 0.000 0.792 0.004 0.204
#> GSM486781 2 0.7495 0.3108 0.192 0.468 0.000 0.340
#> GSM486783 2 0.0592 0.4772 0.000 0.984 0.000 0.016
#> GSM486785 1 0.0921 0.8283 0.972 0.000 0.000 0.028
#> GSM486787 1 0.1394 0.8296 0.964 0.008 0.012 0.016
#> GSM486789 4 0.5296 0.5789 0.000 0.492 0.008 0.500
#> GSM486791 3 0.3390 0.8155 0.132 0.000 0.852 0.016
#> GSM486793 1 0.2214 0.8087 0.928 0.000 0.044 0.028
#> GSM486795 1 0.6678 0.5974 0.692 0.156 0.048 0.104
#> GSM486797 1 0.8015 -0.0805 0.396 0.292 0.004 0.308
#> GSM486799 1 0.0804 0.8294 0.980 0.000 0.008 0.012
#> GSM486801 1 0.1631 0.8298 0.956 0.008 0.020 0.016
#> GSM486803 1 0.2089 0.8254 0.940 0.020 0.012 0.028
#> GSM486805 1 0.8072 -0.2079 0.356 0.320 0.004 0.320
#> GSM486807 1 0.2002 0.8242 0.936 0.020 0.000 0.044
#> GSM486809 4 0.5772 0.7388 0.000 0.260 0.068 0.672
#> GSM486811 1 0.1471 0.8277 0.960 0.004 0.012 0.024
#> GSM486813 2 0.2742 0.4701 0.008 0.900 0.008 0.084
#> GSM486815 1 0.0895 0.8292 0.976 0.000 0.004 0.020
#> GSM486817 1 0.8260 0.1384 0.468 0.308 0.032 0.192
#> GSM486819 3 0.6326 0.7195 0.080 0.120 0.728 0.072
#> GSM486822 4 0.5055 0.7511 0.000 0.368 0.008 0.624
#> GSM486824 1 0.1229 0.8302 0.968 0.004 0.008 0.020
#> GSM486828 2 0.7591 0.3128 0.208 0.452 0.000 0.340
#> GSM486831 1 0.2066 0.8248 0.940 0.008 0.028 0.024
#> GSM486833 1 0.7982 -0.0731 0.392 0.260 0.004 0.344
#> GSM486835 1 0.1509 0.8297 0.960 0.008 0.012 0.020
#> GSM486837 2 0.6958 0.3855 0.184 0.584 0.000 0.232
#> GSM486839 1 0.0672 0.8281 0.984 0.000 0.008 0.008
#> GSM486841 1 0.0707 0.8283 0.980 0.000 0.000 0.020
#> GSM486843 1 0.1617 0.8300 0.956 0.012 0.008 0.024
#> GSM486845 2 0.7540 0.3265 0.204 0.468 0.000 0.328
#> GSM486847 1 0.0927 0.8289 0.976 0.000 0.008 0.016
#> GSM486849 2 0.2647 0.4133 0.000 0.880 0.000 0.120
#> GSM486851 3 0.0524 0.8653 0.008 0.000 0.988 0.004
#> GSM486853 2 0.0817 0.4796 0.000 0.976 0.000 0.024
#> GSM486855 2 0.2011 0.4740 0.000 0.920 0.000 0.080
#> GSM486857 2 0.6133 0.4272 0.136 0.676 0.000 0.188
#> GSM486736 4 0.5137 0.7766 0.000 0.296 0.024 0.680
#> GSM486738 2 0.1118 0.4713 0.000 0.964 0.000 0.036
#> GSM486740 4 0.6979 0.5898 0.008 0.416 0.088 0.488
#> GSM486742 2 0.2408 0.4359 0.000 0.896 0.000 0.104
#> GSM486744 2 0.3873 0.2620 0.000 0.772 0.000 0.228
#> GSM486746 4 0.7028 0.5718 0.008 0.416 0.092 0.484
#> GSM486748 1 0.7059 0.4509 0.592 0.204 0.004 0.200
#> GSM486750 2 0.4920 -0.2607 0.000 0.628 0.004 0.368
#> GSM486752 1 0.7634 0.1093 0.464 0.300 0.000 0.236
#> GSM486754 2 0.4008 0.2186 0.000 0.756 0.000 0.244
#> GSM486756 2 0.3528 0.3168 0.000 0.808 0.000 0.192
#> GSM486758 1 0.4682 0.6979 0.760 0.004 0.024 0.212
#> GSM486760 1 0.1516 0.8298 0.960 0.016 0.008 0.016
#> GSM486762 1 0.2384 0.8140 0.916 0.008 0.004 0.072
#> GSM486764 3 0.0376 0.8638 0.004 0.000 0.992 0.004
#> GSM486766 1 0.0707 0.8299 0.980 0.000 0.000 0.020
#> GSM486768 2 0.8174 0.2454 0.160 0.520 0.048 0.272
#> GSM486770 4 0.5038 0.7768 0.000 0.296 0.020 0.684
#> GSM486772 2 0.3873 0.2400 0.000 0.772 0.000 0.228
#> GSM486774 2 0.7654 0.2798 0.212 0.420 0.000 0.368
#> GSM486776 1 0.0657 0.8307 0.984 0.000 0.012 0.004
#> GSM486778 1 0.2111 0.8087 0.932 0.000 0.044 0.024
#> GSM486780 2 0.3831 0.3816 0.000 0.792 0.004 0.204
#> GSM486782 2 0.7486 0.3187 0.188 0.464 0.000 0.348
#> GSM486784 2 0.0592 0.4772 0.000 0.984 0.000 0.016
#> GSM486786 1 0.0921 0.8283 0.972 0.000 0.000 0.028
#> GSM486788 1 0.1394 0.8296 0.964 0.008 0.012 0.016
#> GSM486790 4 0.5296 0.5789 0.000 0.492 0.008 0.500
#> GSM486792 3 0.3390 0.8155 0.132 0.000 0.852 0.016
#> GSM486794 1 0.2214 0.8087 0.928 0.000 0.044 0.028
#> GSM486796 1 0.6678 0.5974 0.692 0.156 0.048 0.104
#> GSM486798 1 0.8031 -0.1239 0.384 0.324 0.004 0.288
#> GSM486800 1 0.0804 0.8294 0.980 0.000 0.008 0.012
#> GSM486802 1 0.1631 0.8298 0.956 0.008 0.020 0.016
#> GSM486804 1 0.2089 0.8254 0.940 0.020 0.012 0.028
#> GSM486806 2 0.7913 0.2203 0.324 0.360 0.000 0.316
#> GSM486808 1 0.2002 0.8242 0.936 0.020 0.000 0.044
#> GSM486810 4 0.5772 0.7388 0.000 0.260 0.068 0.672
#> GSM486812 1 0.1471 0.8277 0.960 0.004 0.012 0.024
#> GSM486814 2 0.2742 0.4701 0.008 0.900 0.008 0.084
#> GSM486816 1 0.0895 0.8292 0.976 0.000 0.004 0.020
#> GSM486818 1 0.8260 0.1384 0.468 0.308 0.032 0.192
#> GSM486821 3 0.6326 0.7195 0.080 0.120 0.728 0.072
#> GSM486823 4 0.5055 0.7511 0.000 0.368 0.008 0.624
#> GSM486826 1 0.1229 0.8302 0.968 0.004 0.008 0.020
#> GSM486830 2 0.7591 0.3128 0.208 0.452 0.000 0.340
#> GSM486832 1 0.2066 0.8248 0.940 0.008 0.028 0.024
#> GSM486834 1 0.7993 -0.0881 0.388 0.264 0.004 0.344
#> GSM486836 1 0.1509 0.8297 0.960 0.008 0.012 0.020
#> GSM486838 2 0.6576 0.3990 0.152 0.628 0.000 0.220
#> GSM486840 1 0.0672 0.8281 0.984 0.000 0.008 0.008
#> GSM486842 1 0.0707 0.8283 0.980 0.000 0.000 0.020
#> GSM486844 1 0.1985 0.8282 0.944 0.020 0.012 0.024
#> GSM486846 2 0.7540 0.3265 0.204 0.468 0.000 0.328
#> GSM486848 1 0.0927 0.8289 0.976 0.000 0.008 0.016
#> GSM486850 2 0.2647 0.4133 0.000 0.880 0.000 0.120
#> GSM486852 3 0.0524 0.8653 0.008 0.000 0.988 0.004
#> GSM486854 2 0.0817 0.4796 0.000 0.976 0.000 0.024
#> GSM486856 2 0.2011 0.4740 0.000 0.920 0.000 0.080
#> GSM486858 2 0.5783 0.4377 0.120 0.708 0.000 0.172
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 4 0.2813 0.7506 0.000 0.168 0.000 0.832 0.000
#> GSM486737 2 0.1626 0.5997 0.000 0.940 0.016 0.044 0.000
#> GSM486739 4 0.7057 0.4826 0.000 0.332 0.088 0.496 0.084
#> GSM486741 2 0.2674 0.5587 0.000 0.856 0.004 0.140 0.000
#> GSM486743 2 0.4646 0.4260 0.000 0.712 0.060 0.228 0.000
#> GSM486745 4 0.7128 0.4609 0.000 0.344 0.088 0.480 0.088
#> GSM486747 1 0.7364 -0.4163 0.396 0.156 0.392 0.056 0.000
#> GSM486749 2 0.4489 -0.0773 0.000 0.572 0.008 0.420 0.000
#> GSM486751 3 0.7875 0.6291 0.232 0.204 0.452 0.112 0.000
#> GSM486753 2 0.4691 0.3588 0.000 0.680 0.044 0.276 0.000
#> GSM486755 2 0.4168 0.4735 0.000 0.756 0.044 0.200 0.000
#> GSM486757 3 0.5122 0.2116 0.312 0.000 0.628 0.060 0.000
#> GSM486759 1 0.1845 0.8635 0.928 0.016 0.056 0.000 0.000
#> GSM486761 1 0.4030 0.7367 0.736 0.008 0.248 0.008 0.000
#> GSM486763 5 0.0404 0.8617 0.000 0.000 0.012 0.000 0.988
#> GSM486765 1 0.1831 0.8612 0.920 0.000 0.076 0.004 0.000
#> GSM486767 2 0.8278 -0.0958 0.056 0.416 0.276 0.216 0.036
#> GSM486769 4 0.3010 0.7511 0.000 0.172 0.004 0.824 0.000
#> GSM486771 2 0.3863 0.4231 0.000 0.740 0.012 0.248 0.000
#> GSM486773 3 0.7799 0.4932 0.068 0.328 0.372 0.232 0.000
#> GSM486775 1 0.1121 0.8718 0.956 0.000 0.044 0.000 0.000
#> GSM486777 1 0.3548 0.8261 0.836 0.000 0.112 0.008 0.044
#> GSM486779 2 0.5759 0.3539 0.000 0.596 0.276 0.128 0.000
#> GSM486781 2 0.7535 -0.4769 0.060 0.384 0.376 0.180 0.000
#> GSM486783 2 0.0865 0.5996 0.000 0.972 0.004 0.024 0.000
#> GSM486785 1 0.2136 0.8547 0.904 0.000 0.088 0.008 0.000
#> GSM486787 1 0.1638 0.8613 0.932 0.004 0.064 0.000 0.000
#> GSM486789 4 0.4908 0.5727 0.000 0.356 0.036 0.608 0.000
#> GSM486791 5 0.3012 0.8130 0.124 0.000 0.024 0.000 0.852
#> GSM486793 1 0.3646 0.8232 0.828 0.000 0.120 0.008 0.044
#> GSM486795 1 0.6771 0.4460 0.648 0.140 0.124 0.048 0.040
#> GSM486797 3 0.8119 0.6491 0.180 0.224 0.428 0.168 0.000
#> GSM486799 1 0.0963 0.8701 0.964 0.000 0.036 0.000 0.000
#> GSM486801 1 0.2116 0.8650 0.924 0.008 0.052 0.004 0.012
#> GSM486803 1 0.2284 0.8455 0.896 0.004 0.096 0.004 0.000
#> GSM486805 3 0.7843 0.6460 0.144 0.244 0.464 0.148 0.000
#> GSM486807 1 0.3336 0.8199 0.832 0.016 0.144 0.008 0.000
#> GSM486809 4 0.3523 0.7093 0.000 0.120 0.004 0.832 0.044
#> GSM486811 1 0.2804 0.8557 0.880 0.004 0.096 0.008 0.012
#> GSM486813 2 0.3459 0.5814 0.000 0.844 0.080 0.072 0.004
#> GSM486815 1 0.3081 0.8193 0.832 0.000 0.156 0.012 0.000
#> GSM486817 3 0.7594 0.4973 0.256 0.220 0.472 0.036 0.016
#> GSM486819 5 0.6135 0.7244 0.048 0.100 0.084 0.056 0.712
#> GSM486822 4 0.3689 0.7210 0.000 0.256 0.004 0.740 0.000
#> GSM486824 1 0.1697 0.8603 0.932 0.000 0.060 0.008 0.000
#> GSM486828 3 0.7355 0.4693 0.052 0.376 0.408 0.164 0.000
#> GSM486831 1 0.2588 0.8620 0.900 0.008 0.068 0.004 0.020
#> GSM486833 3 0.7865 0.6407 0.156 0.176 0.476 0.192 0.000
#> GSM486835 1 0.1928 0.8574 0.920 0.004 0.072 0.004 0.000
#> GSM486837 2 0.6659 -0.1817 0.076 0.520 0.344 0.060 0.000
#> GSM486839 1 0.0290 0.8673 0.992 0.000 0.008 0.000 0.000
#> GSM486841 1 0.1764 0.8619 0.928 0.000 0.064 0.008 0.000
#> GSM486843 1 0.2054 0.8565 0.916 0.004 0.072 0.008 0.000
#> GSM486845 3 0.7388 0.4522 0.060 0.392 0.396 0.152 0.000
#> GSM486847 1 0.0609 0.8687 0.980 0.000 0.020 0.000 0.000
#> GSM486849 2 0.2707 0.5623 0.000 0.860 0.008 0.132 0.000
#> GSM486851 5 0.0324 0.8647 0.004 0.000 0.000 0.004 0.992
#> GSM486853 2 0.1195 0.5990 0.000 0.960 0.012 0.028 0.000
#> GSM486855 2 0.2291 0.5879 0.000 0.908 0.056 0.036 0.000
#> GSM486857 2 0.5781 0.1438 0.032 0.616 0.296 0.056 0.000
#> GSM486736 4 0.2813 0.7506 0.000 0.168 0.000 0.832 0.000
#> GSM486738 2 0.1626 0.5997 0.000 0.940 0.016 0.044 0.000
#> GSM486740 4 0.7057 0.4826 0.000 0.332 0.088 0.496 0.084
#> GSM486742 2 0.2583 0.5628 0.000 0.864 0.004 0.132 0.000
#> GSM486744 2 0.4588 0.4385 0.000 0.720 0.060 0.220 0.000
#> GSM486746 4 0.7128 0.4609 0.000 0.344 0.088 0.480 0.088
#> GSM486748 1 0.7334 -0.3895 0.408 0.160 0.380 0.052 0.000
#> GSM486750 2 0.4489 -0.0773 0.000 0.572 0.008 0.420 0.000
#> GSM486752 3 0.7968 0.6062 0.272 0.228 0.404 0.096 0.000
#> GSM486754 2 0.4691 0.3588 0.000 0.680 0.044 0.276 0.000
#> GSM486756 2 0.4168 0.4735 0.000 0.756 0.044 0.200 0.000
#> GSM486758 3 0.5122 0.2116 0.312 0.000 0.628 0.060 0.000
#> GSM486760 1 0.1774 0.8637 0.932 0.016 0.052 0.000 0.000
#> GSM486762 1 0.4030 0.7367 0.736 0.008 0.248 0.008 0.000
#> GSM486764 5 0.0404 0.8617 0.000 0.000 0.012 0.000 0.988
#> GSM486766 1 0.1831 0.8612 0.920 0.000 0.076 0.004 0.000
#> GSM486768 2 0.8271 -0.0938 0.056 0.416 0.280 0.212 0.036
#> GSM486770 4 0.3010 0.7511 0.000 0.172 0.004 0.824 0.000
#> GSM486772 2 0.3863 0.4231 0.000 0.740 0.012 0.248 0.000
#> GSM486774 3 0.7724 0.5008 0.068 0.336 0.388 0.208 0.000
#> GSM486776 1 0.1121 0.8718 0.956 0.000 0.044 0.000 0.000
#> GSM486778 1 0.3548 0.8261 0.836 0.000 0.112 0.008 0.044
#> GSM486780 2 0.5759 0.3539 0.000 0.596 0.276 0.128 0.000
#> GSM486782 2 0.7409 -0.4658 0.056 0.392 0.388 0.164 0.000
#> GSM486784 2 0.0865 0.5996 0.000 0.972 0.004 0.024 0.000
#> GSM486786 1 0.2136 0.8547 0.904 0.000 0.088 0.008 0.000
#> GSM486788 1 0.1571 0.8612 0.936 0.004 0.060 0.000 0.000
#> GSM486790 4 0.4908 0.5727 0.000 0.356 0.036 0.608 0.000
#> GSM486792 5 0.3012 0.8130 0.124 0.000 0.024 0.000 0.852
#> GSM486794 1 0.3646 0.8232 0.828 0.000 0.120 0.008 0.044
#> GSM486796 1 0.6771 0.4460 0.648 0.140 0.124 0.048 0.040
#> GSM486798 3 0.8095 0.6403 0.180 0.260 0.416 0.144 0.000
#> GSM486800 1 0.0963 0.8701 0.964 0.000 0.036 0.000 0.000
#> GSM486802 1 0.2116 0.8650 0.924 0.008 0.052 0.004 0.012
#> GSM486804 1 0.2228 0.8458 0.900 0.004 0.092 0.004 0.000
#> GSM486806 3 0.7823 0.6248 0.140 0.292 0.440 0.128 0.000
#> GSM486808 1 0.3336 0.8199 0.832 0.016 0.144 0.008 0.000
#> GSM486810 4 0.3523 0.7093 0.000 0.120 0.004 0.832 0.044
#> GSM486812 1 0.2804 0.8557 0.880 0.004 0.096 0.008 0.012
#> GSM486814 2 0.3459 0.5814 0.000 0.844 0.080 0.072 0.004
#> GSM486816 1 0.3081 0.8193 0.832 0.000 0.156 0.012 0.000
#> GSM486818 3 0.7594 0.4973 0.256 0.220 0.472 0.036 0.016
#> GSM486821 5 0.6135 0.7244 0.048 0.100 0.084 0.056 0.712
#> GSM486823 4 0.3689 0.7210 0.000 0.256 0.004 0.740 0.000
#> GSM486826 1 0.1697 0.8603 0.932 0.000 0.060 0.008 0.000
#> GSM486830 3 0.7355 0.4693 0.052 0.376 0.408 0.164 0.000
#> GSM486832 1 0.2588 0.8620 0.900 0.008 0.068 0.004 0.020
#> GSM486834 3 0.7889 0.6409 0.156 0.180 0.472 0.192 0.000
#> GSM486836 1 0.1928 0.8574 0.920 0.004 0.072 0.004 0.000
#> GSM486838 2 0.6192 -0.0663 0.052 0.564 0.332 0.052 0.000
#> GSM486840 1 0.0290 0.8673 0.992 0.000 0.008 0.000 0.000
#> GSM486842 1 0.1764 0.8619 0.928 0.000 0.064 0.008 0.000
#> GSM486844 1 0.2354 0.8522 0.904 0.012 0.076 0.008 0.000
#> GSM486846 3 0.7388 0.4522 0.060 0.392 0.396 0.152 0.000
#> GSM486848 1 0.0609 0.8687 0.980 0.000 0.020 0.000 0.000
#> GSM486850 2 0.2707 0.5623 0.000 0.860 0.008 0.132 0.000
#> GSM486852 5 0.0324 0.8647 0.004 0.000 0.000 0.004 0.992
#> GSM486854 2 0.1195 0.5990 0.000 0.960 0.012 0.028 0.000
#> GSM486856 2 0.2291 0.5879 0.000 0.908 0.056 0.036 0.000
#> GSM486858 2 0.5471 0.2139 0.032 0.652 0.272 0.044 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 6 0.1327 0.7225 0.000 0.064 0.000 0.000 0.000 0.936
#> GSM486737 2 0.1857 0.5807 0.000 0.924 0.028 0.004 0.000 0.044
#> GSM486739 6 0.7044 0.4272 0.000 0.276 0.052 0.092 0.072 0.508
#> GSM486741 2 0.2768 0.5905 0.000 0.832 0.012 0.000 0.000 0.156
#> GSM486743 2 0.5019 0.4931 0.000 0.664 0.044 0.048 0.000 0.244
#> GSM486745 6 0.7149 0.4124 0.000 0.284 0.052 0.096 0.076 0.492
#> GSM486747 4 0.6563 0.4429 0.320 0.120 0.028 0.500 0.000 0.032
#> GSM486749 2 0.4211 0.0462 0.000 0.532 0.004 0.008 0.000 0.456
#> GSM486751 4 0.6889 0.6159 0.152 0.156 0.032 0.564 0.000 0.096
#> GSM486753 2 0.5028 0.4254 0.000 0.628 0.040 0.036 0.000 0.296
#> GSM486755 2 0.4523 0.5378 0.000 0.712 0.044 0.028 0.000 0.216
#> GSM486757 4 0.3926 0.1583 0.036 0.000 0.156 0.780 0.000 0.028
#> GSM486759 1 0.2151 0.8696 0.912 0.016 0.024 0.048 0.000 0.000
#> GSM486761 1 0.4892 0.6578 0.644 0.008 0.064 0.280 0.000 0.004
#> GSM486763 5 0.1285 0.8055 0.000 0.000 0.052 0.000 0.944 0.004
#> GSM486765 1 0.2263 0.8626 0.896 0.000 0.056 0.048 0.000 0.000
#> GSM486767 2 0.8185 -0.2233 0.016 0.332 0.120 0.292 0.024 0.216
#> GSM486769 6 0.1588 0.7262 0.000 0.072 0.000 0.004 0.000 0.924
#> GSM486771 2 0.3964 0.5009 0.000 0.724 0.016 0.016 0.000 0.244
#> GSM486773 4 0.6818 0.5817 0.024 0.236 0.028 0.480 0.000 0.232
#> GSM486775 1 0.1257 0.8781 0.952 0.000 0.028 0.020 0.000 0.000
#> GSM486777 1 0.4264 0.8091 0.776 0.000 0.072 0.108 0.044 0.000
#> GSM486779 3 0.4569 1.0000 0.000 0.304 0.636 0.060 0.000 0.000
#> GSM486781 4 0.6801 0.5548 0.028 0.292 0.024 0.468 0.000 0.188
#> GSM486783 2 0.0909 0.5596 0.000 0.968 0.020 0.000 0.000 0.012
#> GSM486785 1 0.2511 0.8596 0.880 0.000 0.064 0.056 0.000 0.000
#> GSM486787 1 0.1934 0.8660 0.916 0.000 0.040 0.044 0.000 0.000
#> GSM486789 6 0.4334 0.5597 0.000 0.268 0.016 0.028 0.000 0.688
#> GSM486791 5 0.3033 0.7571 0.108 0.000 0.032 0.012 0.848 0.000
#> GSM486793 1 0.4463 0.8033 0.768 0.000 0.080 0.104 0.044 0.004
#> GSM486795 1 0.6905 0.4829 0.620 0.100 0.076 0.124 0.032 0.048
#> GSM486797 4 0.6754 0.6513 0.084 0.148 0.028 0.572 0.000 0.168
#> GSM486799 1 0.0993 0.8765 0.964 0.000 0.012 0.024 0.000 0.000
#> GSM486801 1 0.2501 0.8675 0.896 0.004 0.048 0.040 0.012 0.000
#> GSM486803 1 0.2714 0.8477 0.872 0.000 0.064 0.060 0.000 0.004
#> GSM486805 4 0.6507 0.6571 0.072 0.168 0.020 0.588 0.000 0.152
#> GSM486807 1 0.3708 0.8200 0.800 0.008 0.052 0.136 0.000 0.004
#> GSM486809 6 0.1768 0.6635 0.000 0.012 0.008 0.012 0.032 0.936
#> GSM486811 1 0.3007 0.8619 0.864 0.004 0.056 0.064 0.012 0.000
#> GSM486813 2 0.3659 0.5428 0.000 0.824 0.068 0.064 0.000 0.044
#> GSM486815 1 0.4601 0.7188 0.688 0.000 0.112 0.200 0.000 0.000
#> GSM486817 4 0.7238 0.3883 0.148 0.184 0.144 0.504 0.000 0.020
#> GSM486819 5 0.6068 0.6558 0.028 0.064 0.084 0.072 0.696 0.056
#> GSM486822 6 0.2845 0.6968 0.000 0.172 0.004 0.004 0.000 0.820
#> GSM486824 1 0.1984 0.8634 0.912 0.000 0.056 0.032 0.000 0.000
#> GSM486828 4 0.6424 0.5685 0.020 0.288 0.016 0.504 0.000 0.172
#> GSM486831 1 0.2749 0.8682 0.884 0.004 0.044 0.048 0.020 0.000
#> GSM486833 4 0.6020 0.6191 0.040 0.108 0.032 0.636 0.000 0.184
#> GSM486835 1 0.2325 0.8588 0.892 0.000 0.060 0.048 0.000 0.000
#> GSM486837 2 0.6775 -0.2984 0.052 0.432 0.080 0.396 0.000 0.040
#> GSM486839 1 0.0363 0.8743 0.988 0.000 0.012 0.000 0.000 0.000
#> GSM486841 1 0.2066 0.8649 0.908 0.000 0.052 0.040 0.000 0.000
#> GSM486843 1 0.2328 0.8590 0.892 0.000 0.056 0.052 0.000 0.000
#> GSM486845 4 0.6547 0.5575 0.024 0.300 0.024 0.500 0.000 0.152
#> GSM486847 1 0.0717 0.8751 0.976 0.000 0.016 0.008 0.000 0.000
#> GSM486849 2 0.2905 0.5917 0.000 0.836 0.012 0.008 0.000 0.144
#> GSM486851 5 0.0291 0.8179 0.004 0.000 0.000 0.000 0.992 0.004
#> GSM486853 2 0.2340 0.5372 0.000 0.900 0.060 0.016 0.000 0.024
#> GSM486855 2 0.3054 0.4715 0.000 0.852 0.096 0.036 0.000 0.016
#> GSM486857 2 0.5870 0.0507 0.016 0.552 0.052 0.336 0.000 0.044
#> GSM486736 6 0.1327 0.7225 0.000 0.064 0.000 0.000 0.000 0.936
#> GSM486738 2 0.1857 0.5807 0.000 0.924 0.028 0.004 0.000 0.044
#> GSM486740 6 0.7044 0.4272 0.000 0.276 0.052 0.092 0.072 0.508
#> GSM486742 2 0.2692 0.5889 0.000 0.840 0.012 0.000 0.000 0.148
#> GSM486744 2 0.4973 0.5033 0.000 0.672 0.044 0.048 0.000 0.236
#> GSM486746 6 0.7149 0.4124 0.000 0.284 0.052 0.096 0.076 0.492
#> GSM486748 4 0.6637 0.4191 0.340 0.124 0.032 0.476 0.000 0.028
#> GSM486750 2 0.4211 0.0462 0.000 0.532 0.004 0.008 0.000 0.456
#> GSM486752 4 0.6871 0.5842 0.200 0.176 0.020 0.532 0.000 0.072
#> GSM486754 2 0.5028 0.4254 0.000 0.628 0.040 0.036 0.000 0.296
#> GSM486756 2 0.4523 0.5378 0.000 0.712 0.044 0.028 0.000 0.216
#> GSM486758 4 0.3926 0.1583 0.036 0.000 0.156 0.780 0.000 0.028
#> GSM486760 1 0.2084 0.8701 0.916 0.016 0.024 0.044 0.000 0.000
#> GSM486762 1 0.4892 0.6578 0.644 0.008 0.064 0.280 0.000 0.004
#> GSM486764 5 0.1285 0.8055 0.000 0.000 0.052 0.000 0.944 0.004
#> GSM486766 1 0.2263 0.8626 0.896 0.000 0.056 0.048 0.000 0.000
#> GSM486768 2 0.8178 -0.2220 0.016 0.332 0.120 0.296 0.024 0.212
#> GSM486770 6 0.1588 0.7262 0.000 0.072 0.000 0.004 0.000 0.924
#> GSM486772 2 0.3964 0.5009 0.000 0.724 0.016 0.016 0.000 0.244
#> GSM486774 4 0.6759 0.5895 0.028 0.248 0.024 0.492 0.000 0.208
#> GSM486776 1 0.1257 0.8781 0.952 0.000 0.028 0.020 0.000 0.000
#> GSM486778 1 0.4264 0.8091 0.776 0.000 0.072 0.108 0.044 0.000
#> GSM486780 3 0.4569 1.0000 0.000 0.304 0.636 0.060 0.000 0.000
#> GSM486782 4 0.6723 0.5450 0.028 0.304 0.024 0.476 0.000 0.168
#> GSM486784 2 0.0909 0.5596 0.000 0.968 0.020 0.000 0.000 0.012
#> GSM486786 1 0.2511 0.8596 0.880 0.000 0.064 0.056 0.000 0.000
#> GSM486788 1 0.1865 0.8658 0.920 0.000 0.040 0.040 0.000 0.000
#> GSM486790 6 0.4334 0.5597 0.000 0.268 0.016 0.028 0.000 0.688
#> GSM486792 5 0.3033 0.7571 0.108 0.000 0.032 0.012 0.848 0.000
#> GSM486794 1 0.4463 0.8033 0.768 0.000 0.080 0.104 0.044 0.004
#> GSM486796 1 0.6905 0.4829 0.620 0.100 0.076 0.124 0.032 0.048
#> GSM486798 4 0.6746 0.6434 0.084 0.192 0.024 0.564 0.000 0.136
#> GSM486800 1 0.0993 0.8765 0.964 0.000 0.012 0.024 0.000 0.000
#> GSM486802 1 0.2501 0.8675 0.896 0.004 0.048 0.040 0.012 0.000
#> GSM486804 1 0.2653 0.8479 0.876 0.000 0.064 0.056 0.000 0.004
#> GSM486806 4 0.6427 0.6411 0.072 0.224 0.012 0.572 0.000 0.120
#> GSM486808 1 0.3708 0.8200 0.800 0.008 0.052 0.136 0.000 0.004
#> GSM486810 6 0.1768 0.6635 0.000 0.012 0.008 0.012 0.032 0.936
#> GSM486812 1 0.3007 0.8619 0.864 0.004 0.056 0.064 0.012 0.000
#> GSM486814 2 0.3659 0.5428 0.000 0.824 0.068 0.064 0.000 0.044
#> GSM486816 1 0.4601 0.7188 0.688 0.000 0.112 0.200 0.000 0.000
#> GSM486818 4 0.7238 0.3883 0.148 0.184 0.144 0.504 0.000 0.020
#> GSM486821 5 0.6068 0.6558 0.028 0.064 0.084 0.072 0.696 0.056
#> GSM486823 6 0.2845 0.6968 0.000 0.172 0.004 0.004 0.000 0.820
#> GSM486826 1 0.1984 0.8634 0.912 0.000 0.056 0.032 0.000 0.000
#> GSM486830 4 0.6424 0.5685 0.020 0.288 0.016 0.504 0.000 0.172
#> GSM486832 1 0.2749 0.8682 0.884 0.004 0.044 0.048 0.020 0.000
#> GSM486834 4 0.5951 0.6199 0.040 0.108 0.028 0.640 0.000 0.184
#> GSM486836 1 0.2325 0.8588 0.892 0.000 0.060 0.048 0.000 0.000
#> GSM486838 2 0.6364 -0.1987 0.032 0.476 0.092 0.376 0.000 0.024
#> GSM486840 1 0.0363 0.8743 0.988 0.000 0.012 0.000 0.000 0.000
#> GSM486842 1 0.2066 0.8649 0.908 0.000 0.052 0.040 0.000 0.000
#> GSM486844 1 0.2644 0.8551 0.880 0.008 0.060 0.052 0.000 0.000
#> GSM486846 4 0.6547 0.5575 0.024 0.300 0.024 0.500 0.000 0.152
#> GSM486848 1 0.0717 0.8751 0.976 0.000 0.016 0.008 0.000 0.000
#> GSM486850 2 0.2905 0.5917 0.000 0.836 0.012 0.008 0.000 0.144
#> GSM486852 5 0.0291 0.8179 0.004 0.000 0.000 0.000 0.992 0.004
#> GSM486854 2 0.2340 0.5372 0.000 0.900 0.060 0.016 0.000 0.024
#> GSM486856 2 0.3054 0.4715 0.000 0.852 0.096 0.036 0.000 0.016
#> GSM486858 2 0.5666 0.1265 0.016 0.584 0.056 0.312 0.000 0.032
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> MAD:hclust 108 1.000 1.24e-05 2
#> MAD:hclust 108 1.000 1.61e-09 3
#> MAD:hclust 68 1.000 9.01e-07 4
#> MAD:hclust 83 0.999 1.81e-13 5
#> MAD:hclust 95 1.000 2.21e-18 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["MAD", "kmeans"]
# you can also extract it by
# res = res_list["MAD:kmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'MAD' method.
#> Subgroups are detected by 'kmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.922 0.913 0.950 0.5032 0.498 0.498
#> 3 3 0.511 0.585 0.741 0.2774 0.913 0.826
#> 4 4 0.520 0.298 0.576 0.1311 0.756 0.472
#> 5 5 0.561 0.457 0.646 0.0707 0.783 0.375
#> 6 6 0.618 0.548 0.658 0.0411 0.898 0.586
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 2 0.0000 0.973 0.000 1.000
#> GSM486737 2 0.0376 0.973 0.004 0.996
#> GSM486739 2 0.0376 0.973 0.004 0.996
#> GSM486741 2 0.0000 0.973 0.000 1.000
#> GSM486743 2 0.0376 0.973 0.004 0.996
#> GSM486745 2 0.0376 0.973 0.004 0.996
#> GSM486747 1 0.2778 0.925 0.952 0.048
#> GSM486749 2 0.0000 0.973 0.000 1.000
#> GSM486751 1 0.7453 0.783 0.788 0.212
#> GSM486753 2 0.0376 0.973 0.004 0.996
#> GSM486755 2 0.0376 0.973 0.004 0.996
#> GSM486757 1 0.2778 0.925 0.952 0.048
#> GSM486759 1 0.2603 0.925 0.956 0.044
#> GSM486761 1 0.2778 0.925 0.952 0.048
#> GSM486763 1 0.5946 0.856 0.856 0.144
#> GSM486765 1 0.2778 0.925 0.952 0.048
#> GSM486767 2 0.0376 0.973 0.004 0.996
#> GSM486769 2 0.0000 0.973 0.000 1.000
#> GSM486771 2 0.0376 0.973 0.004 0.996
#> GSM486773 2 0.0000 0.973 0.000 1.000
#> GSM486775 1 0.2603 0.925 0.956 0.044
#> GSM486777 1 0.2778 0.925 0.952 0.048
#> GSM486779 2 0.0376 0.973 0.004 0.996
#> GSM486781 2 0.0000 0.973 0.000 1.000
#> GSM486783 2 0.0376 0.973 0.004 0.996
#> GSM486785 1 0.2778 0.925 0.952 0.048
#> GSM486787 1 0.2603 0.925 0.956 0.044
#> GSM486789 2 0.0000 0.973 0.000 1.000
#> GSM486791 1 0.2603 0.925 0.956 0.044
#> GSM486793 1 0.2778 0.925 0.952 0.048
#> GSM486795 1 0.2603 0.925 0.956 0.044
#> GSM486797 1 0.9850 0.404 0.572 0.428
#> GSM486799 1 0.2603 0.925 0.956 0.044
#> GSM486801 1 0.2603 0.925 0.956 0.044
#> GSM486803 1 0.2603 0.925 0.956 0.044
#> GSM486805 2 0.0000 0.973 0.000 1.000
#> GSM486807 1 0.2778 0.925 0.952 0.048
#> GSM486809 2 0.0000 0.973 0.000 1.000
#> GSM486811 1 0.2778 0.925 0.952 0.048
#> GSM486813 2 0.0376 0.973 0.004 0.996
#> GSM486815 1 0.2778 0.925 0.952 0.048
#> GSM486817 1 0.9983 0.260 0.524 0.476
#> GSM486819 1 0.7815 0.757 0.768 0.232
#> GSM486822 2 0.0000 0.973 0.000 1.000
#> GSM486824 1 0.2603 0.925 0.956 0.044
#> GSM486828 2 0.0000 0.973 0.000 1.000
#> GSM486831 1 0.2603 0.925 0.956 0.044
#> GSM486833 1 0.9608 0.507 0.616 0.384
#> GSM486835 1 0.2603 0.925 0.956 0.044
#> GSM486837 2 0.0000 0.973 0.000 1.000
#> GSM486839 1 0.2603 0.925 0.956 0.044
#> GSM486841 1 0.2778 0.925 0.952 0.048
#> GSM486843 1 0.2603 0.925 0.956 0.044
#> GSM486845 2 0.0000 0.973 0.000 1.000
#> GSM486847 1 0.2603 0.925 0.956 0.044
#> GSM486849 2 0.0000 0.973 0.000 1.000
#> GSM486851 1 0.2603 0.925 0.956 0.044
#> GSM486853 2 0.0000 0.973 0.000 1.000
#> GSM486855 2 0.0376 0.973 0.004 0.996
#> GSM486857 2 0.0000 0.973 0.000 1.000
#> GSM486736 2 0.2603 0.973 0.044 0.956
#> GSM486738 2 0.2778 0.973 0.048 0.952
#> GSM486740 2 0.2778 0.973 0.048 0.952
#> GSM486742 2 0.2603 0.973 0.044 0.956
#> GSM486744 2 0.2778 0.973 0.048 0.952
#> GSM486746 2 0.2778 0.973 0.048 0.952
#> GSM486748 1 0.0376 0.925 0.996 0.004
#> GSM486750 2 0.2603 0.973 0.044 0.956
#> GSM486752 1 0.2948 0.899 0.948 0.052
#> GSM486754 2 0.2778 0.973 0.048 0.952
#> GSM486756 2 0.2778 0.973 0.048 0.952
#> GSM486758 1 0.0376 0.925 0.996 0.004
#> GSM486760 1 0.0000 0.926 1.000 0.000
#> GSM486762 1 0.0376 0.925 0.996 0.004
#> GSM486764 1 0.3431 0.888 0.936 0.064
#> GSM486766 1 0.0376 0.925 0.996 0.004
#> GSM486768 2 0.2778 0.973 0.048 0.952
#> GSM486770 2 0.2603 0.973 0.044 0.956
#> GSM486772 2 0.2778 0.973 0.048 0.952
#> GSM486774 2 0.2603 0.973 0.044 0.956
#> GSM486776 1 0.0000 0.926 1.000 0.000
#> GSM486778 1 0.0376 0.925 0.996 0.004
#> GSM486780 2 0.2778 0.973 0.048 0.952
#> GSM486782 2 0.2603 0.973 0.044 0.956
#> GSM486784 2 0.2778 0.973 0.048 0.952
#> GSM486786 1 0.0376 0.925 0.996 0.004
#> GSM486788 1 0.0000 0.926 1.000 0.000
#> GSM486790 2 0.2603 0.973 0.044 0.956
#> GSM486792 1 0.0000 0.926 1.000 0.000
#> GSM486794 1 0.0376 0.925 0.996 0.004
#> GSM486796 1 0.0000 0.926 1.000 0.000
#> GSM486798 1 0.9988 0.105 0.520 0.480
#> GSM486800 1 0.0000 0.926 1.000 0.000
#> GSM486802 1 0.0000 0.926 1.000 0.000
#> GSM486804 1 0.0000 0.926 1.000 0.000
#> GSM486806 2 0.2603 0.973 0.044 0.956
#> GSM486808 1 0.0376 0.925 0.996 0.004
#> GSM486810 2 0.2603 0.973 0.044 0.956
#> GSM486812 1 0.0376 0.925 0.996 0.004
#> GSM486814 2 0.2778 0.973 0.048 0.952
#> GSM486816 1 0.0376 0.925 0.996 0.004
#> GSM486818 1 0.9661 0.375 0.608 0.392
#> GSM486821 1 0.8267 0.651 0.740 0.260
#> GSM486823 2 0.2603 0.973 0.044 0.956
#> GSM486826 1 0.0000 0.926 1.000 0.000
#> GSM486830 2 0.2603 0.973 0.044 0.956
#> GSM486832 1 0.0000 0.926 1.000 0.000
#> GSM486834 1 0.9209 0.516 0.664 0.336
#> GSM486836 1 0.0000 0.926 1.000 0.000
#> GSM486838 2 0.2603 0.973 0.044 0.956
#> GSM486840 1 0.0000 0.926 1.000 0.000
#> GSM486842 1 0.0376 0.925 0.996 0.004
#> GSM486844 1 0.0000 0.926 1.000 0.000
#> GSM486846 2 0.2603 0.973 0.044 0.956
#> GSM486848 1 0.0000 0.926 1.000 0.000
#> GSM486850 2 0.2603 0.973 0.044 0.956
#> GSM486852 1 0.0000 0.926 1.000 0.000
#> GSM486854 2 0.2603 0.973 0.044 0.956
#> GSM486856 2 0.2778 0.973 0.048 0.952
#> GSM486858 2 0.2603 0.973 0.044 0.956
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 2 0.6274 0.58210 0.456 0.544 0.000
#> GSM486737 2 0.4062 0.73566 0.164 0.836 0.000
#> GSM486739 2 0.6267 0.56854 0.452 0.548 0.000
#> GSM486741 2 0.4235 0.73683 0.176 0.824 0.000
#> GSM486743 2 0.4346 0.73221 0.184 0.816 0.000
#> GSM486745 2 0.6168 0.62035 0.412 0.588 0.000
#> GSM486747 3 0.6235 0.44130 0.436 0.000 0.564
#> GSM486749 2 0.5291 0.72885 0.268 0.732 0.000
#> GSM486751 1 0.6723 0.49950 0.704 0.048 0.248
#> GSM486753 2 0.4796 0.73060 0.220 0.780 0.000
#> GSM486755 2 0.4555 0.73196 0.200 0.800 0.000
#> GSM486757 1 0.5363 0.40686 0.724 0.000 0.276
#> GSM486759 3 0.5216 0.64191 0.260 0.000 0.740
#> GSM486761 3 0.5591 0.62616 0.304 0.000 0.696
#> GSM486763 1 0.5267 0.55124 0.816 0.044 0.140
#> GSM486765 3 0.5465 0.63597 0.288 0.000 0.712
#> GSM486767 2 0.6180 0.61549 0.416 0.584 0.000
#> GSM486769 2 0.6260 0.59521 0.448 0.552 0.000
#> GSM486771 2 0.4291 0.73258 0.180 0.820 0.000
#> GSM486773 2 0.6307 0.55308 0.488 0.512 0.000
#> GSM486775 3 0.5178 0.64221 0.256 0.000 0.744
#> GSM486777 3 0.5621 0.62741 0.308 0.000 0.692
#> GSM486779 2 0.4178 0.73585 0.172 0.828 0.000
#> GSM486781 2 0.6168 0.63341 0.412 0.588 0.000
#> GSM486783 2 0.4062 0.73566 0.164 0.836 0.000
#> GSM486785 3 0.5465 0.63597 0.288 0.000 0.712
#> GSM486787 3 0.5178 0.64221 0.256 0.000 0.744
#> GSM486789 2 0.5465 0.72291 0.288 0.712 0.000
#> GSM486791 3 0.6235 0.43591 0.436 0.000 0.564
#> GSM486793 3 0.5706 0.62022 0.320 0.000 0.680
#> GSM486795 3 0.6813 0.19768 0.468 0.012 0.520
#> GSM486797 1 0.7004 0.60347 0.728 0.112 0.160
#> GSM486799 3 0.5178 0.64221 0.256 0.000 0.744
#> GSM486801 3 0.5216 0.64191 0.260 0.000 0.740
#> GSM486803 3 0.5216 0.64191 0.260 0.000 0.740
#> GSM486805 1 0.5327 0.22508 0.728 0.272 0.000
#> GSM486807 3 0.5560 0.62894 0.300 0.000 0.700
#> GSM486809 1 0.6305 -0.55088 0.516 0.484 0.000
#> GSM486811 3 0.5431 0.63740 0.284 0.000 0.716
#> GSM486813 2 0.4291 0.73456 0.180 0.820 0.000
#> GSM486815 3 0.5678 0.62327 0.316 0.000 0.684
#> GSM486817 1 0.7710 0.60831 0.680 0.144 0.176
#> GSM486819 1 0.4779 0.58041 0.840 0.036 0.124
#> GSM486822 2 0.5810 0.70116 0.336 0.664 0.000
#> GSM486824 3 0.5216 0.64191 0.260 0.000 0.740
#> GSM486828 2 0.6302 0.55859 0.480 0.520 0.000
#> GSM486831 3 0.5216 0.64191 0.260 0.000 0.740
#> GSM486833 1 0.5744 0.61982 0.800 0.072 0.128
#> GSM486835 3 0.5216 0.64191 0.260 0.000 0.740
#> GSM486837 2 0.6079 0.59428 0.388 0.612 0.000
#> GSM486839 3 0.5178 0.64221 0.256 0.000 0.744
#> GSM486841 3 0.5431 0.63740 0.284 0.000 0.716
#> GSM486843 3 0.5216 0.64191 0.260 0.000 0.740
#> GSM486845 2 0.5948 0.67087 0.360 0.640 0.000
#> GSM486847 3 0.5178 0.64221 0.256 0.000 0.744
#> GSM486849 2 0.4504 0.73831 0.196 0.804 0.000
#> GSM486851 1 0.6008 0.18228 0.664 0.004 0.332
#> GSM486853 2 0.4452 0.73693 0.192 0.808 0.000
#> GSM486855 2 0.4178 0.73585 0.172 0.828 0.000
#> GSM486857 2 0.5905 0.65941 0.352 0.648 0.000
#> GSM486736 2 0.5497 0.62612 0.292 0.708 0.000
#> GSM486738 2 0.0000 0.74873 0.000 1.000 0.000
#> GSM486740 2 0.5465 0.61583 0.288 0.712 0.000
#> GSM486742 2 0.0592 0.74961 0.012 0.988 0.000
#> GSM486744 2 0.0000 0.74873 0.000 1.000 0.000
#> GSM486746 2 0.4842 0.67760 0.224 0.776 0.000
#> GSM486748 3 0.7348 0.34950 0.176 0.120 0.704
#> GSM486750 2 0.2878 0.74839 0.096 0.904 0.000
#> GSM486752 3 0.8924 0.00833 0.268 0.172 0.560
#> GSM486754 2 0.1163 0.74927 0.028 0.972 0.000
#> GSM486756 2 0.1031 0.74900 0.024 0.976 0.000
#> GSM486758 3 0.8172 0.18094 0.272 0.112 0.616
#> GSM486760 3 0.0237 0.68646 0.004 0.000 0.996
#> GSM486762 3 0.1753 0.67458 0.048 0.000 0.952
#> GSM486764 3 0.9213 -0.21606 0.396 0.152 0.452
#> GSM486766 3 0.1289 0.68177 0.032 0.000 0.968
#> GSM486768 2 0.4654 0.68615 0.208 0.792 0.000
#> GSM486770 2 0.5327 0.64527 0.272 0.728 0.000
#> GSM486772 2 0.0237 0.74864 0.004 0.996 0.000
#> GSM486774 2 0.5431 0.63116 0.284 0.716 0.000
#> GSM486776 3 0.0000 0.68653 0.000 0.000 1.000
#> GSM486778 3 0.1753 0.67761 0.048 0.000 0.952
#> GSM486780 2 0.0424 0.74869 0.008 0.992 0.000
#> GSM486782 2 0.4750 0.68267 0.216 0.784 0.000
#> GSM486784 2 0.0000 0.74873 0.000 1.000 0.000
#> GSM486786 3 0.1289 0.68177 0.032 0.000 0.968
#> GSM486788 3 0.0237 0.68646 0.004 0.000 0.996
#> GSM486790 2 0.3192 0.74483 0.112 0.888 0.000
#> GSM486792 3 0.4291 0.52968 0.180 0.000 0.820
#> GSM486794 3 0.2066 0.67280 0.060 0.000 0.940
#> GSM486796 3 0.5524 0.45803 0.040 0.164 0.796
#> GSM486798 3 0.9887 -0.29104 0.268 0.336 0.396
#> GSM486800 3 0.0000 0.68653 0.000 0.000 1.000
#> GSM486802 3 0.0237 0.68646 0.004 0.000 0.996
#> GSM486804 3 0.0237 0.68646 0.004 0.000 0.996
#> GSM486806 2 0.8212 0.42816 0.296 0.600 0.104
#> GSM486808 3 0.1860 0.67208 0.052 0.000 0.948
#> GSM486810 2 0.5882 0.56357 0.348 0.652 0.000
#> GSM486812 3 0.1163 0.68286 0.028 0.000 0.972
#> GSM486814 2 0.0592 0.74836 0.012 0.988 0.000
#> GSM486816 3 0.2066 0.67280 0.060 0.000 0.940
#> GSM486818 3 0.9767 -0.28751 0.248 0.320 0.432
#> GSM486821 1 0.9620 0.22935 0.416 0.204 0.380
#> GSM486823 2 0.4062 0.72476 0.164 0.836 0.000
#> GSM486826 3 0.0237 0.68646 0.004 0.000 0.996
#> GSM486830 2 0.5465 0.62383 0.288 0.712 0.000
#> GSM486832 3 0.0237 0.68646 0.004 0.000 0.996
#> GSM486834 3 0.9789 -0.29224 0.368 0.236 0.396
#> GSM486836 3 0.0237 0.68646 0.004 0.000 0.996
#> GSM486838 2 0.6572 0.58053 0.172 0.748 0.080
#> GSM486840 3 0.0000 0.68653 0.000 0.000 1.000
#> GSM486842 3 0.1163 0.68286 0.028 0.000 0.972
#> GSM486844 3 0.0237 0.68646 0.004 0.000 0.996
#> GSM486846 2 0.4235 0.70007 0.176 0.824 0.000
#> GSM486848 3 0.0000 0.68653 0.000 0.000 1.000
#> GSM486850 2 0.1411 0.75016 0.036 0.964 0.000
#> GSM486852 3 0.7705 0.08247 0.348 0.060 0.592
#> GSM486854 2 0.1163 0.74938 0.028 0.972 0.000
#> GSM486856 2 0.0424 0.74869 0.008 0.992 0.000
#> GSM486858 2 0.4062 0.69453 0.164 0.836 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 2 0.7197 0.0546 0.000 0.468 0.140 0.392
#> GSM486737 2 0.0336 0.5031 0.000 0.992 0.008 0.000
#> GSM486739 2 0.6983 0.0955 0.000 0.516 0.124 0.360
#> GSM486741 2 0.1174 0.5019 0.000 0.968 0.020 0.012
#> GSM486743 2 0.1807 0.4967 0.000 0.940 0.008 0.052
#> GSM486745 2 0.6249 0.1982 0.000 0.592 0.072 0.336
#> GSM486747 1 0.6307 0.3948 0.672 0.016 0.080 0.232
#> GSM486749 2 0.5392 0.3112 0.000 0.680 0.040 0.280
#> GSM486751 1 0.8733 0.2192 0.452 0.144 0.084 0.320
#> GSM486753 2 0.4137 0.3919 0.000 0.780 0.012 0.208
#> GSM486755 2 0.3032 0.4529 0.000 0.868 0.008 0.124
#> GSM486757 1 0.8593 0.2874 0.488 0.108 0.108 0.296
#> GSM486759 1 0.0000 0.5629 1.000 0.000 0.000 0.000
#> GSM486761 1 0.2984 0.5453 0.888 0.000 0.084 0.028
#> GSM486763 1 0.9225 0.1821 0.376 0.088 0.316 0.220
#> GSM486765 1 0.2198 0.5523 0.920 0.000 0.072 0.008
#> GSM486767 2 0.5883 0.2218 0.000 0.640 0.060 0.300
#> GSM486769 2 0.7090 0.0895 0.000 0.496 0.132 0.372
#> GSM486771 2 0.1305 0.5006 0.000 0.960 0.004 0.036
#> GSM486773 4 0.5594 -0.0912 0.000 0.460 0.020 0.520
#> GSM486775 1 0.0336 0.5632 0.992 0.000 0.008 0.000
#> GSM486777 1 0.2542 0.5531 0.904 0.000 0.084 0.012
#> GSM486779 2 0.0927 0.4987 0.000 0.976 0.008 0.016
#> GSM486781 2 0.5364 0.1441 0.000 0.592 0.016 0.392
#> GSM486783 2 0.0188 0.5030 0.000 0.996 0.004 0.000
#> GSM486785 1 0.2048 0.5541 0.928 0.000 0.064 0.008
#> GSM486787 1 0.0000 0.5629 1.000 0.000 0.000 0.000
#> GSM486789 2 0.5972 0.2577 0.000 0.632 0.064 0.304
#> GSM486791 1 0.6523 0.3296 0.628 0.000 0.236 0.136
#> GSM486793 1 0.3047 0.5439 0.872 0.000 0.116 0.012
#> GSM486795 1 0.5977 0.4439 0.744 0.128 0.044 0.084
#> GSM486797 1 0.9220 0.0686 0.364 0.228 0.084 0.324
#> GSM486799 1 0.0000 0.5629 1.000 0.000 0.000 0.000
#> GSM486801 1 0.0524 0.5635 0.988 0.000 0.008 0.004
#> GSM486803 1 0.0657 0.5634 0.984 0.000 0.012 0.004
#> GSM486805 4 0.8890 0.0331 0.288 0.296 0.048 0.368
#> GSM486807 1 0.2984 0.5453 0.888 0.000 0.084 0.028
#> GSM486809 4 0.7314 -0.0739 0.000 0.424 0.152 0.424
#> GSM486811 1 0.2048 0.5541 0.928 0.000 0.064 0.008
#> GSM486813 2 0.0657 0.5011 0.000 0.984 0.012 0.004
#> GSM486815 1 0.2675 0.5478 0.892 0.000 0.100 0.008
#> GSM486817 1 0.8673 0.0965 0.428 0.244 0.044 0.284
#> GSM486819 1 0.9000 0.2398 0.440 0.080 0.228 0.252
#> GSM486822 2 0.6222 0.2362 0.000 0.616 0.080 0.304
#> GSM486824 1 0.0376 0.5625 0.992 0.000 0.004 0.004
#> GSM486828 2 0.5508 0.1192 0.000 0.572 0.020 0.408
#> GSM486831 1 0.0524 0.5635 0.988 0.000 0.008 0.004
#> GSM486833 1 0.9185 0.0722 0.360 0.204 0.088 0.348
#> GSM486835 1 0.0524 0.5635 0.988 0.000 0.008 0.004
#> GSM486837 2 0.6557 0.1514 0.060 0.628 0.024 0.288
#> GSM486839 1 0.0000 0.5629 1.000 0.000 0.000 0.000
#> GSM486841 1 0.1970 0.5551 0.932 0.000 0.060 0.008
#> GSM486843 1 0.0657 0.5635 0.984 0.000 0.012 0.004
#> GSM486845 2 0.5038 0.2052 0.000 0.652 0.012 0.336
#> GSM486847 1 0.0000 0.5629 1.000 0.000 0.000 0.000
#> GSM486849 2 0.2111 0.4926 0.000 0.932 0.024 0.044
#> GSM486851 1 0.7905 0.2486 0.480 0.012 0.292 0.216
#> GSM486853 2 0.1820 0.4929 0.000 0.944 0.020 0.036
#> GSM486855 2 0.0804 0.5011 0.000 0.980 0.008 0.012
#> GSM486857 2 0.4957 0.2240 0.000 0.684 0.016 0.300
#> GSM486736 4 0.6993 0.2756 0.000 0.260 0.168 0.572
#> GSM486738 2 0.4482 0.2932 0.000 0.728 0.008 0.264
#> GSM486740 4 0.7066 0.2610 0.000 0.304 0.152 0.544
#> GSM486742 2 0.4855 0.2894 0.000 0.712 0.020 0.268
#> GSM486744 2 0.4776 0.2795 0.000 0.712 0.016 0.272
#> GSM486746 4 0.6634 0.2598 0.000 0.336 0.100 0.564
#> GSM486748 3 0.6815 0.4748 0.136 0.000 0.580 0.284
#> GSM486750 4 0.6323 0.0991 0.000 0.440 0.060 0.500
#> GSM486752 3 0.5915 0.3883 0.036 0.004 0.592 0.368
#> GSM486754 2 0.5517 0.0861 0.000 0.568 0.020 0.412
#> GSM486756 2 0.5284 0.1739 0.000 0.616 0.016 0.368
#> GSM486758 3 0.5898 0.4580 0.056 0.000 0.628 0.316
#> GSM486760 1 0.4996 -0.5197 0.516 0.000 0.484 0.000
#> GSM486762 3 0.5508 0.5531 0.408 0.000 0.572 0.020
#> GSM486764 3 0.6138 0.3424 0.072 0.028 0.708 0.192
#> GSM486766 3 0.5112 0.5449 0.436 0.000 0.560 0.004
#> GSM486768 4 0.6743 0.2535 0.000 0.392 0.096 0.512
#> GSM486770 4 0.7067 0.2695 0.000 0.288 0.160 0.552
#> GSM486772 2 0.4193 0.2945 0.000 0.732 0.000 0.268
#> GSM486774 4 0.5716 0.3485 0.000 0.252 0.068 0.680
#> GSM486776 1 0.4999 -0.5256 0.508 0.000 0.492 0.000
#> GSM486778 3 0.5088 0.5504 0.424 0.000 0.572 0.004
#> GSM486780 2 0.4690 0.2816 0.000 0.712 0.012 0.276
#> GSM486782 4 0.6163 0.2788 0.000 0.364 0.060 0.576
#> GSM486784 2 0.4343 0.2931 0.000 0.732 0.004 0.264
#> GSM486786 3 0.5126 0.5427 0.444 0.000 0.552 0.004
#> GSM486788 1 0.5296 -0.5386 0.496 0.000 0.496 0.008
#> GSM486790 4 0.6702 0.1707 0.000 0.396 0.092 0.512
#> GSM486792 3 0.6560 0.4025 0.248 0.000 0.620 0.132
#> GSM486794 3 0.5028 0.5538 0.400 0.000 0.596 0.004
#> GSM486796 3 0.7048 0.5297 0.288 0.004 0.568 0.140
#> GSM486798 4 0.6536 -0.1265 0.020 0.036 0.456 0.488
#> GSM486800 1 0.4996 -0.5197 0.516 0.000 0.484 0.000
#> GSM486802 1 0.5168 -0.5279 0.504 0.000 0.492 0.004
#> GSM486804 3 0.5295 0.5147 0.488 0.000 0.504 0.008
#> GSM486806 4 0.6617 0.3153 0.000 0.128 0.264 0.608
#> GSM486808 3 0.5793 0.5594 0.384 0.000 0.580 0.036
#> GSM486810 4 0.6941 0.2938 0.000 0.220 0.192 0.588
#> GSM486812 3 0.5126 0.5427 0.444 0.000 0.552 0.004
#> GSM486814 2 0.4720 0.2841 0.000 0.720 0.016 0.264
#> GSM486816 3 0.5050 0.5529 0.408 0.000 0.588 0.004
#> GSM486818 3 0.7827 0.2764 0.084 0.056 0.496 0.364
#> GSM486821 3 0.7243 0.1979 0.072 0.040 0.568 0.320
#> GSM486823 4 0.6859 0.1888 0.000 0.380 0.108 0.512
#> GSM486826 1 0.5165 -0.5226 0.512 0.000 0.484 0.004
#> GSM486830 4 0.6037 0.3196 0.000 0.304 0.068 0.628
#> GSM486832 3 0.5296 0.5053 0.496 0.000 0.496 0.008
#> GSM486834 3 0.5392 0.2819 0.008 0.004 0.564 0.424
#> GSM486836 3 0.5296 0.5104 0.492 0.000 0.500 0.008
#> GSM486838 4 0.6979 0.2149 0.000 0.376 0.120 0.504
#> GSM486840 1 0.4996 -0.5197 0.516 0.000 0.484 0.000
#> GSM486842 3 0.5132 0.5409 0.448 0.000 0.548 0.004
#> GSM486844 3 0.5294 0.5169 0.484 0.000 0.508 0.008
#> GSM486846 4 0.6222 0.2288 0.000 0.412 0.056 0.532
#> GSM486848 1 0.4996 -0.5197 0.516 0.000 0.484 0.000
#> GSM486850 2 0.5038 0.2621 0.000 0.684 0.020 0.296
#> GSM486852 3 0.5940 0.3672 0.120 0.000 0.692 0.188
#> GSM486854 2 0.5013 0.2644 0.000 0.688 0.020 0.292
#> GSM486856 2 0.4539 0.2868 0.000 0.720 0.008 0.272
#> GSM486858 4 0.6200 0.1690 0.000 0.444 0.052 0.504
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 5 0.5850 0.10561 0.000 0.096 0.000 0.428 0.476
#> GSM486737 2 0.5214 0.09197 0.008 0.604 0.000 0.348 0.040
#> GSM486739 5 0.6375 0.01857 0.008 0.128 0.000 0.412 0.452
#> GSM486741 2 0.5394 0.07657 0.008 0.580 0.000 0.364 0.048
#> GSM486743 2 0.5341 -0.04712 0.008 0.524 0.000 0.432 0.036
#> GSM486745 4 0.6035 0.30075 0.016 0.124 0.000 0.612 0.248
#> GSM486747 1 0.5626 0.50903 0.640 0.000 0.080 0.264 0.016
#> GSM486749 4 0.5833 0.31572 0.008 0.144 0.000 0.632 0.216
#> GSM486751 1 0.4865 0.07877 0.536 0.004 0.000 0.444 0.016
#> GSM486753 4 0.5855 0.25146 0.008 0.340 0.000 0.564 0.088
#> GSM486755 4 0.6024 0.09495 0.008 0.432 0.000 0.472 0.088
#> GSM486757 1 0.4538 0.30153 0.620 0.000 0.000 0.364 0.016
#> GSM486759 1 0.4482 0.80734 0.636 0.000 0.348 0.000 0.016
#> GSM486761 1 0.4000 0.76387 0.784 0.000 0.180 0.016 0.020
#> GSM486763 5 0.5906 0.27272 0.324 0.012 0.012 0.060 0.592
#> GSM486765 1 0.4033 0.78606 0.744 0.000 0.236 0.004 0.016
#> GSM486767 4 0.5137 0.49441 0.028 0.188 0.000 0.720 0.064
#> GSM486769 5 0.6180 0.06854 0.008 0.104 0.000 0.432 0.456
#> GSM486771 2 0.5242 0.00444 0.004 0.556 0.000 0.400 0.040
#> GSM486773 4 0.2544 0.53860 0.028 0.064 0.000 0.900 0.008
#> GSM486775 1 0.4938 0.80455 0.632 0.000 0.332 0.008 0.028
#> GSM486777 1 0.3751 0.78530 0.772 0.000 0.212 0.004 0.012
#> GSM486779 2 0.5992 0.04858 0.032 0.540 0.000 0.376 0.052
#> GSM486781 4 0.2909 0.52550 0.012 0.140 0.000 0.848 0.000
#> GSM486783 2 0.5146 0.08977 0.008 0.608 0.000 0.348 0.036
#> GSM486785 1 0.3737 0.79188 0.764 0.000 0.224 0.008 0.004
#> GSM486787 1 0.4804 0.80221 0.624 0.000 0.348 0.004 0.024
#> GSM486789 4 0.6201 0.17607 0.004 0.148 0.000 0.544 0.304
#> GSM486791 1 0.6094 0.21352 0.488 0.000 0.128 0.000 0.384
#> GSM486793 1 0.3769 0.76880 0.796 0.000 0.176 0.012 0.016
#> GSM486795 1 0.6321 0.63408 0.632 0.004 0.152 0.180 0.032
#> GSM486797 4 0.4661 0.37729 0.356 0.004 0.000 0.624 0.016
#> GSM486799 1 0.4984 0.80247 0.620 0.000 0.344 0.008 0.028
#> GSM486801 1 0.4482 0.80734 0.636 0.000 0.348 0.000 0.016
#> GSM486803 1 0.4703 0.80530 0.640 0.000 0.336 0.008 0.016
#> GSM486805 4 0.4089 0.45875 0.244 0.004 0.000 0.736 0.016
#> GSM486807 1 0.3982 0.77373 0.772 0.000 0.200 0.012 0.016
#> GSM486809 5 0.5566 0.14859 0.004 0.060 0.000 0.416 0.520
#> GSM486811 1 0.3550 0.79013 0.760 0.000 0.236 0.000 0.004
#> GSM486813 2 0.5307 0.07986 0.008 0.592 0.000 0.356 0.044
#> GSM486815 1 0.3840 0.77662 0.780 0.000 0.196 0.008 0.016
#> GSM486817 4 0.5855 0.37175 0.288 0.008 0.056 0.624 0.024
#> GSM486819 5 0.7278 0.11791 0.380 0.000 0.036 0.192 0.392
#> GSM486822 4 0.6260 0.01535 0.008 0.120 0.000 0.500 0.372
#> GSM486824 1 0.5072 0.79904 0.620 0.000 0.340 0.012 0.028
#> GSM486828 4 0.3169 0.52560 0.016 0.140 0.000 0.840 0.004
#> GSM486831 1 0.4467 0.80748 0.640 0.000 0.344 0.000 0.016
#> GSM486833 4 0.4701 0.34482 0.368 0.004 0.000 0.612 0.016
#> GSM486835 1 0.4482 0.80734 0.636 0.000 0.348 0.000 0.016
#> GSM486837 4 0.4870 0.46267 0.052 0.224 0.000 0.712 0.012
#> GSM486839 1 0.4890 0.80356 0.628 0.000 0.340 0.008 0.024
#> GSM486841 1 0.3700 0.79131 0.752 0.000 0.240 0.000 0.008
#> GSM486843 1 0.4570 0.80648 0.648 0.000 0.332 0.004 0.016
#> GSM486845 4 0.3851 0.48665 0.004 0.212 0.000 0.768 0.016
#> GSM486847 1 0.4890 0.80356 0.628 0.000 0.340 0.008 0.024
#> GSM486849 2 0.5511 -0.01216 0.004 0.524 0.000 0.416 0.056
#> GSM486851 5 0.6127 0.13766 0.376 0.000 0.052 0.040 0.532
#> GSM486853 2 0.5632 0.03003 0.012 0.540 0.000 0.396 0.052
#> GSM486855 2 0.5576 0.05031 0.016 0.556 0.000 0.384 0.044
#> GSM486857 4 0.3789 0.47494 0.016 0.224 0.000 0.760 0.000
#> GSM486736 5 0.6442 0.24964 0.000 0.300 0.000 0.208 0.492
#> GSM486738 2 0.0613 0.52843 0.004 0.984 0.000 0.004 0.008
#> GSM486740 5 0.6473 0.18588 0.004 0.364 0.000 0.164 0.468
#> GSM486742 2 0.1074 0.52998 0.004 0.968 0.000 0.012 0.016
#> GSM486744 2 0.1369 0.53276 0.008 0.956 0.000 0.008 0.028
#> GSM486746 2 0.7044 0.08197 0.028 0.504 0.004 0.180 0.284
#> GSM486748 3 0.7263 0.50653 0.120 0.064 0.584 0.204 0.028
#> GSM486750 2 0.6492 0.16552 0.016 0.560 0.000 0.184 0.240
#> GSM486752 3 0.7883 0.42902 0.116 0.080 0.524 0.236 0.044
#> GSM486754 2 0.4480 0.41569 0.008 0.772 0.000 0.128 0.092
#> GSM486756 2 0.4034 0.44671 0.008 0.808 0.000 0.100 0.084
#> GSM486758 3 0.7568 0.46760 0.148 0.048 0.540 0.228 0.036
#> GSM486760 3 0.0404 0.75043 0.012 0.000 0.988 0.000 0.000
#> GSM486762 3 0.3463 0.72796 0.156 0.000 0.820 0.008 0.016
#> GSM486764 5 0.6684 0.21986 0.124 0.020 0.268 0.016 0.572
#> GSM486766 3 0.3124 0.73363 0.136 0.000 0.844 0.004 0.016
#> GSM486768 2 0.6637 0.36144 0.036 0.604 0.016 0.240 0.104
#> GSM486770 5 0.6713 0.20421 0.008 0.332 0.000 0.196 0.464
#> GSM486772 2 0.0865 0.53186 0.000 0.972 0.000 0.004 0.024
#> GSM486774 2 0.6550 0.28131 0.028 0.476 0.012 0.416 0.068
#> GSM486776 3 0.1483 0.74930 0.028 0.000 0.952 0.008 0.012
#> GSM486778 3 0.3044 0.73332 0.148 0.000 0.840 0.004 0.008
#> GSM486780 2 0.2351 0.51952 0.028 0.916 0.000 0.036 0.020
#> GSM486782 2 0.6221 0.33905 0.028 0.556 0.008 0.348 0.060
#> GSM486784 2 0.0162 0.53006 0.000 0.996 0.000 0.000 0.004
#> GSM486786 3 0.2956 0.73816 0.140 0.000 0.848 0.008 0.004
#> GSM486788 3 0.0290 0.75341 0.008 0.000 0.992 0.000 0.000
#> GSM486790 2 0.6555 0.04506 0.004 0.492 0.000 0.200 0.304
#> GSM486792 3 0.6092 0.21600 0.132 0.000 0.504 0.000 0.364
#> GSM486794 3 0.3482 0.72484 0.168 0.000 0.812 0.008 0.012
#> GSM486796 3 0.4207 0.66849 0.036 0.092 0.824 0.028 0.020
#> GSM486798 3 0.8755 0.01638 0.064 0.316 0.324 0.240 0.056
#> GSM486800 3 0.1074 0.74672 0.016 0.000 0.968 0.004 0.012
#> GSM486802 3 0.0290 0.75238 0.008 0.000 0.992 0.000 0.000
#> GSM486804 3 0.0771 0.75371 0.020 0.000 0.976 0.004 0.000
#> GSM486806 2 0.8160 0.19749 0.056 0.408 0.104 0.364 0.068
#> GSM486808 3 0.3022 0.74073 0.136 0.000 0.848 0.004 0.012
#> GSM486810 5 0.6378 0.29596 0.004 0.252 0.000 0.204 0.540
#> GSM486812 3 0.2629 0.73670 0.136 0.000 0.860 0.000 0.004
#> GSM486814 2 0.0579 0.53011 0.000 0.984 0.000 0.008 0.008
#> GSM486816 3 0.3544 0.72596 0.164 0.000 0.812 0.008 0.016
#> GSM486818 3 0.8304 0.23456 0.056 0.204 0.456 0.232 0.052
#> GSM486821 5 0.9022 0.24146 0.124 0.120 0.232 0.104 0.420
#> GSM486823 2 0.6887 -0.13002 0.012 0.408 0.000 0.200 0.380
#> GSM486826 3 0.1413 0.74319 0.020 0.000 0.956 0.012 0.012
#> GSM486830 2 0.6443 0.30499 0.028 0.520 0.012 0.376 0.064
#> GSM486832 3 0.0290 0.75434 0.008 0.000 0.992 0.000 0.000
#> GSM486834 3 0.8637 0.27953 0.116 0.120 0.416 0.292 0.056
#> GSM486836 3 0.0162 0.75539 0.000 0.000 0.996 0.004 0.000
#> GSM486838 2 0.6131 0.36405 0.032 0.624 0.024 0.276 0.044
#> GSM486840 3 0.1299 0.74655 0.020 0.000 0.960 0.008 0.012
#> GSM486842 3 0.2127 0.74600 0.108 0.000 0.892 0.000 0.000
#> GSM486844 3 0.0671 0.75428 0.016 0.000 0.980 0.004 0.000
#> GSM486846 2 0.5885 0.36563 0.024 0.608 0.008 0.308 0.052
#> GSM486848 3 0.1299 0.74655 0.020 0.000 0.960 0.008 0.012
#> GSM486850 2 0.1918 0.52751 0.000 0.928 0.000 0.036 0.036
#> GSM486852 5 0.6593 0.14979 0.128 0.004 0.312 0.020 0.536
#> GSM486854 2 0.2075 0.52749 0.004 0.924 0.000 0.040 0.032
#> GSM486856 2 0.1483 0.52700 0.008 0.952 0.000 0.028 0.012
#> GSM486858 2 0.5771 0.37654 0.028 0.636 0.008 0.280 0.048
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 6 0.4162 0.66881 0.000 0.028 0.004 0.116 0.068 0.784
#> GSM486737 2 0.5983 0.44506 0.000 0.568 0.016 0.280 0.020 0.116
#> GSM486739 6 0.5564 0.65425 0.000 0.060 0.012 0.164 0.088 0.676
#> GSM486741 2 0.6124 0.43831 0.000 0.556 0.024 0.280 0.016 0.124
#> GSM486743 2 0.6525 0.37681 0.000 0.460 0.024 0.368 0.028 0.120
#> GSM486745 6 0.6607 0.37413 0.000 0.080 0.020 0.392 0.064 0.444
#> GSM486747 3 0.5248 0.07200 0.036 0.000 0.496 0.440 0.024 0.004
#> GSM486749 6 0.6326 0.24267 0.000 0.140 0.024 0.408 0.008 0.420
#> GSM486751 4 0.4636 0.29375 0.000 0.000 0.376 0.584 0.032 0.008
#> GSM486753 4 0.7115 -0.34538 0.000 0.332 0.024 0.352 0.028 0.264
#> GSM486755 2 0.6945 0.29024 0.000 0.424 0.020 0.312 0.032 0.212
#> GSM486757 4 0.5251 0.09993 0.000 0.000 0.448 0.484 0.036 0.032
#> GSM486759 3 0.3575 0.86120 0.284 0.000 0.708 0.000 0.008 0.000
#> GSM486761 3 0.4239 0.76653 0.132 0.000 0.768 0.072 0.028 0.000
#> GSM486763 5 0.4302 0.67181 0.008 0.000 0.136 0.012 0.764 0.080
#> GSM486765 3 0.3907 0.83462 0.188 0.000 0.768 0.016 0.020 0.008
#> GSM486767 4 0.5425 0.35070 0.000 0.104 0.024 0.696 0.036 0.140
#> GSM486769 6 0.3718 0.67894 0.000 0.032 0.008 0.124 0.024 0.812
#> GSM486771 2 0.5992 0.40184 0.000 0.508 0.020 0.352 0.008 0.112
#> GSM486773 4 0.2903 0.50177 0.000 0.028 0.016 0.872 0.008 0.076
#> GSM486775 3 0.4163 0.85934 0.268 0.000 0.700 0.008 0.016 0.008
#> GSM486777 3 0.3716 0.81431 0.156 0.000 0.796 0.016 0.024 0.008
#> GSM486779 2 0.7056 0.42371 0.000 0.480 0.056 0.292 0.036 0.136
#> GSM486781 4 0.2563 0.50634 0.000 0.040 0.008 0.884 0.000 0.068
#> GSM486783 2 0.5558 0.45088 0.000 0.596 0.012 0.276 0.008 0.108
#> GSM486785 3 0.3546 0.84292 0.188 0.000 0.784 0.008 0.012 0.008
#> GSM486787 3 0.3851 0.85983 0.284 0.000 0.700 0.004 0.008 0.004
#> GSM486789 6 0.5222 0.59443 0.000 0.088 0.008 0.208 0.024 0.672
#> GSM486791 5 0.4891 0.51798 0.068 0.000 0.292 0.004 0.632 0.004
#> GSM486793 3 0.4089 0.78609 0.132 0.000 0.788 0.040 0.032 0.008
#> GSM486795 3 0.5560 0.52124 0.096 0.000 0.636 0.232 0.016 0.020
#> GSM486797 4 0.3883 0.45588 0.000 0.000 0.220 0.744 0.024 0.012
#> GSM486799 3 0.4226 0.85875 0.280 0.000 0.688 0.008 0.016 0.008
#> GSM486801 3 0.3713 0.86181 0.284 0.000 0.704 0.004 0.008 0.000
#> GSM486803 3 0.3916 0.85902 0.276 0.000 0.704 0.008 0.008 0.004
#> GSM486805 4 0.3226 0.51830 0.000 0.000 0.116 0.836 0.028 0.020
#> GSM486807 3 0.3924 0.81760 0.168 0.000 0.772 0.044 0.016 0.000
#> GSM486809 6 0.4698 0.63085 0.000 0.020 0.004 0.116 0.128 0.732
#> GSM486811 3 0.3229 0.84070 0.188 0.000 0.796 0.008 0.004 0.004
#> GSM486813 2 0.5833 0.45279 0.000 0.584 0.020 0.280 0.016 0.100
#> GSM486815 3 0.4602 0.79138 0.156 0.000 0.752 0.032 0.032 0.028
#> GSM486817 4 0.4658 0.45568 0.028 0.004 0.172 0.744 0.024 0.028
#> GSM486819 5 0.6684 0.43408 0.020 0.000 0.172 0.284 0.492 0.032
#> GSM486822 6 0.4141 0.65091 0.000 0.084 0.012 0.140 0.000 0.764
#> GSM486824 3 0.4278 0.85362 0.280 0.000 0.684 0.004 0.024 0.008
#> GSM486828 4 0.2618 0.51015 0.000 0.036 0.012 0.888 0.004 0.060
#> GSM486831 3 0.3575 0.86228 0.284 0.000 0.708 0.000 0.008 0.000
#> GSM486833 4 0.3988 0.48337 0.000 0.000 0.180 0.764 0.028 0.028
#> GSM486835 3 0.3693 0.86060 0.280 0.000 0.708 0.004 0.008 0.000
#> GSM486837 4 0.3298 0.49534 0.000 0.072 0.056 0.848 0.004 0.020
#> GSM486839 3 0.3905 0.86217 0.276 0.000 0.704 0.004 0.012 0.004
#> GSM486841 3 0.3152 0.84495 0.196 0.000 0.792 0.008 0.004 0.000
#> GSM486843 3 0.3746 0.85857 0.272 0.000 0.712 0.004 0.012 0.000
#> GSM486845 4 0.3499 0.46590 0.000 0.068 0.024 0.836 0.004 0.068
#> GSM486847 3 0.4257 0.85783 0.276 0.000 0.688 0.004 0.024 0.008
#> GSM486849 2 0.6340 0.40725 0.000 0.492 0.028 0.336 0.012 0.132
#> GSM486851 5 0.4251 0.67833 0.016 0.000 0.156 0.008 0.764 0.056
#> GSM486853 2 0.6344 0.42167 0.000 0.512 0.032 0.312 0.012 0.132
#> GSM486855 2 0.6335 0.44030 0.000 0.520 0.040 0.312 0.012 0.116
#> GSM486857 4 0.2610 0.48580 0.000 0.088 0.016 0.880 0.004 0.012
#> GSM486736 6 0.4549 0.66067 0.000 0.168 0.004 0.020 0.072 0.736
#> GSM486738 2 0.1363 0.52370 0.000 0.952 0.004 0.004 0.012 0.028
#> GSM486740 6 0.5642 0.63710 0.000 0.236 0.016 0.028 0.088 0.632
#> GSM486742 2 0.1375 0.52345 0.000 0.952 0.008 0.004 0.008 0.028
#> GSM486744 2 0.2460 0.50552 0.000 0.904 0.012 0.020 0.024 0.040
#> GSM486746 6 0.6948 0.33272 0.000 0.372 0.052 0.032 0.116 0.428
#> GSM486748 1 0.7651 0.16691 0.476 0.032 0.064 0.268 0.124 0.036
#> GSM486750 2 0.5730 -0.21392 0.000 0.520 0.036 0.032 0.024 0.388
#> GSM486752 1 0.8131 -0.00879 0.408 0.044 0.068 0.304 0.128 0.048
#> GSM486754 2 0.4233 0.31022 0.000 0.748 0.016 0.016 0.024 0.196
#> GSM486756 2 0.3875 0.39709 0.000 0.800 0.016 0.020 0.028 0.136
#> GSM486758 1 0.8203 0.08944 0.396 0.012 0.120 0.276 0.136 0.060
#> GSM486760 1 0.0458 0.82247 0.984 0.000 0.016 0.000 0.000 0.000
#> GSM486762 1 0.3433 0.78430 0.832 0.000 0.108 0.024 0.032 0.004
#> GSM486764 5 0.3797 0.66895 0.108 0.004 0.012 0.000 0.804 0.072
#> GSM486766 1 0.3139 0.80245 0.852 0.000 0.100 0.012 0.024 0.012
#> GSM486768 2 0.7888 -0.07940 0.008 0.440 0.044 0.248 0.124 0.136
#> GSM486770 6 0.4085 0.66000 0.000 0.200 0.012 0.012 0.024 0.752
#> GSM486772 2 0.1488 0.52000 0.000 0.948 0.008 0.008 0.008 0.028
#> GSM486774 4 0.7955 0.24254 0.012 0.320 0.048 0.392 0.108 0.120
#> GSM486776 1 0.1565 0.82155 0.944 0.000 0.032 0.008 0.008 0.008
#> GSM486778 1 0.3384 0.78502 0.836 0.000 0.108 0.012 0.032 0.012
#> GSM486780 2 0.3469 0.51024 0.000 0.852 0.044 0.028 0.032 0.044
#> GSM486782 4 0.7811 0.21372 0.008 0.348 0.048 0.380 0.100 0.116
#> GSM486784 2 0.0458 0.52702 0.000 0.984 0.000 0.000 0.000 0.016
#> GSM486786 1 0.3182 0.80393 0.852 0.000 0.096 0.012 0.024 0.016
#> GSM486788 1 0.0458 0.82247 0.984 0.000 0.016 0.000 0.000 0.000
#> GSM486790 6 0.5291 0.54181 0.000 0.324 0.016 0.028 0.032 0.600
#> GSM486792 5 0.4424 0.48879 0.340 0.000 0.024 0.004 0.628 0.004
#> GSM486794 1 0.4043 0.76975 0.800 0.000 0.116 0.032 0.036 0.016
#> GSM486796 1 0.4613 0.62686 0.796 0.048 0.052 0.024 0.048 0.032
#> GSM486798 4 0.8954 0.21762 0.252 0.224 0.060 0.300 0.120 0.044
#> GSM486800 1 0.0862 0.82213 0.972 0.000 0.016 0.008 0.000 0.004
#> GSM486802 1 0.0363 0.82299 0.988 0.000 0.012 0.000 0.000 0.000
#> GSM486804 1 0.0798 0.81673 0.976 0.000 0.012 0.004 0.004 0.004
#> GSM486806 4 0.8535 0.30065 0.056 0.252 0.056 0.408 0.128 0.100
#> GSM486808 1 0.3169 0.79172 0.856 0.000 0.088 0.020 0.024 0.012
#> GSM486810 6 0.4907 0.61678 0.000 0.144 0.004 0.012 0.140 0.700
#> GSM486812 1 0.2660 0.80635 0.872 0.000 0.100 0.004 0.016 0.008
#> GSM486814 2 0.0924 0.53026 0.000 0.972 0.004 0.008 0.008 0.008
#> GSM486816 1 0.4451 0.75781 0.780 0.000 0.112 0.032 0.040 0.036
#> GSM486818 4 0.8848 0.18763 0.312 0.144 0.064 0.312 0.116 0.052
#> GSM486821 5 0.7206 0.43460 0.128 0.096 0.020 0.128 0.580 0.048
#> GSM486823 6 0.4002 0.60898 0.000 0.284 0.008 0.016 0.000 0.692
#> GSM486826 1 0.1223 0.81634 0.960 0.000 0.012 0.004 0.016 0.008
#> GSM486830 4 0.7859 0.24986 0.008 0.316 0.052 0.404 0.108 0.112
#> GSM486832 1 0.0260 0.82387 0.992 0.000 0.008 0.000 0.000 0.000
#> GSM486834 4 0.8606 0.26414 0.244 0.080 0.068 0.408 0.136 0.064
#> GSM486836 1 0.0260 0.82273 0.992 0.000 0.008 0.000 0.000 0.000
#> GSM486838 2 0.7795 -0.20709 0.040 0.388 0.068 0.368 0.100 0.036
#> GSM486840 1 0.1036 0.82341 0.964 0.000 0.024 0.000 0.004 0.008
#> GSM486842 1 0.2462 0.81529 0.892 0.000 0.076 0.008 0.016 0.008
#> GSM486844 1 0.0622 0.81794 0.980 0.000 0.012 0.000 0.008 0.000
#> GSM486846 2 0.7631 -0.19993 0.008 0.400 0.056 0.356 0.096 0.084
#> GSM486848 1 0.1490 0.81958 0.948 0.000 0.024 0.004 0.016 0.008
#> GSM486850 2 0.2918 0.49620 0.000 0.880 0.036 0.028 0.012 0.044
#> GSM486852 5 0.3395 0.67603 0.124 0.000 0.004 0.000 0.816 0.056
#> GSM486854 2 0.2527 0.50547 0.000 0.900 0.032 0.036 0.008 0.024
#> GSM486856 2 0.2218 0.52436 0.000 0.916 0.028 0.028 0.008 0.020
#> GSM486858 2 0.7113 -0.17178 0.008 0.436 0.056 0.368 0.096 0.036
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> MAD:kmeans 116 1.00e+00 6.52e-06 2
#> MAD:kmeans 101 8.39e-02 5.75e-08 3
#> MAD:kmeans 41 1.25e-09 6.19e-01 4
#> MAD:kmeans 59 9.61e-13 1.82e-01 5
#> MAD:kmeans 74 4.71e-11 2.06e-04 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["MAD", "skmeans"]
# you can also extract it by
# res = res_list["MAD:skmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'MAD' method.
#> Subgroups are detected by 'skmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.948 0.936 0.975 0.5042 0.496 0.496
#> 3 3 0.608 0.746 0.786 0.3026 0.806 0.625
#> 4 4 0.478 0.559 0.726 0.1337 0.878 0.657
#> 5 5 0.482 0.428 0.613 0.0634 0.919 0.706
#> 6 6 0.512 0.391 0.580 0.0402 0.947 0.773
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 2 0.0000 0.984 0.000 1.000
#> GSM486737 2 0.0000 0.984 0.000 1.000
#> GSM486739 2 0.0000 0.984 0.000 1.000
#> GSM486741 2 0.0000 0.984 0.000 1.000
#> GSM486743 2 0.0000 0.984 0.000 1.000
#> GSM486745 2 0.0000 0.984 0.000 1.000
#> GSM486747 1 0.0000 0.963 1.000 0.000
#> GSM486749 2 0.0000 0.984 0.000 1.000
#> GSM486751 1 0.3733 0.903 0.928 0.072
#> GSM486753 2 0.0000 0.984 0.000 1.000
#> GSM486755 2 0.0000 0.984 0.000 1.000
#> GSM486757 1 0.0000 0.963 1.000 0.000
#> GSM486759 1 0.0000 0.963 1.000 0.000
#> GSM486761 1 0.0000 0.963 1.000 0.000
#> GSM486763 1 0.5178 0.857 0.884 0.116
#> GSM486765 1 0.0000 0.963 1.000 0.000
#> GSM486767 2 0.0000 0.984 0.000 1.000
#> GSM486769 2 0.0000 0.984 0.000 1.000
#> GSM486771 2 0.0000 0.984 0.000 1.000
#> GSM486773 2 0.0000 0.984 0.000 1.000
#> GSM486775 1 0.0000 0.963 1.000 0.000
#> GSM486777 1 0.0000 0.963 1.000 0.000
#> GSM486779 2 0.0000 0.984 0.000 1.000
#> GSM486781 2 0.0000 0.984 0.000 1.000
#> GSM486783 2 0.0000 0.984 0.000 1.000
#> GSM486785 1 0.0000 0.963 1.000 0.000
#> GSM486787 1 0.0000 0.963 1.000 0.000
#> GSM486789 2 0.0000 0.984 0.000 1.000
#> GSM486791 1 0.0000 0.963 1.000 0.000
#> GSM486793 1 0.0000 0.963 1.000 0.000
#> GSM486795 1 0.0000 0.963 1.000 0.000
#> GSM486797 1 0.9833 0.288 0.576 0.424
#> GSM486799 1 0.0000 0.963 1.000 0.000
#> GSM486801 1 0.0000 0.963 1.000 0.000
#> GSM486803 1 0.0000 0.963 1.000 0.000
#> GSM486805 2 0.0000 0.984 0.000 1.000
#> GSM486807 1 0.0000 0.963 1.000 0.000
#> GSM486809 2 0.0000 0.984 0.000 1.000
#> GSM486811 1 0.0000 0.963 1.000 0.000
#> GSM486813 2 0.0000 0.984 0.000 1.000
#> GSM486815 1 0.0000 0.963 1.000 0.000
#> GSM486817 2 0.9954 0.101 0.460 0.540
#> GSM486819 1 0.6148 0.815 0.848 0.152
#> GSM486822 2 0.0000 0.984 0.000 1.000
#> GSM486824 1 0.0000 0.963 1.000 0.000
#> GSM486828 2 0.0000 0.984 0.000 1.000
#> GSM486831 1 0.0000 0.963 1.000 0.000
#> GSM486833 1 0.8016 0.687 0.756 0.244
#> GSM486835 1 0.0000 0.963 1.000 0.000
#> GSM486837 2 0.0000 0.984 0.000 1.000
#> GSM486839 1 0.0000 0.963 1.000 0.000
#> GSM486841 1 0.0000 0.963 1.000 0.000
#> GSM486843 1 0.0000 0.963 1.000 0.000
#> GSM486845 2 0.0000 0.984 0.000 1.000
#> GSM486847 1 0.0000 0.963 1.000 0.000
#> GSM486849 2 0.0000 0.984 0.000 1.000
#> GSM486851 1 0.0000 0.963 1.000 0.000
#> GSM486853 2 0.0000 0.984 0.000 1.000
#> GSM486855 2 0.0000 0.984 0.000 1.000
#> GSM486857 2 0.0000 0.984 0.000 1.000
#> GSM486736 2 0.0000 0.984 0.000 1.000
#> GSM486738 2 0.0000 0.984 0.000 1.000
#> GSM486740 2 0.0000 0.984 0.000 1.000
#> GSM486742 2 0.0000 0.984 0.000 1.000
#> GSM486744 2 0.0000 0.984 0.000 1.000
#> GSM486746 2 0.0000 0.984 0.000 1.000
#> GSM486748 1 0.0000 0.963 1.000 0.000
#> GSM486750 2 0.0000 0.984 0.000 1.000
#> GSM486752 1 0.0938 0.954 0.988 0.012
#> GSM486754 2 0.0000 0.984 0.000 1.000
#> GSM486756 2 0.0000 0.984 0.000 1.000
#> GSM486758 1 0.0000 0.963 1.000 0.000
#> GSM486760 1 0.0000 0.963 1.000 0.000
#> GSM486762 1 0.0000 0.963 1.000 0.000
#> GSM486764 1 0.3733 0.902 0.928 0.072
#> GSM486766 1 0.0000 0.963 1.000 0.000
#> GSM486768 2 0.0000 0.984 0.000 1.000
#> GSM486770 2 0.0000 0.984 0.000 1.000
#> GSM486772 2 0.0000 0.984 0.000 1.000
#> GSM486774 2 0.0000 0.984 0.000 1.000
#> GSM486776 1 0.0000 0.963 1.000 0.000
#> GSM486778 1 0.0000 0.963 1.000 0.000
#> GSM486780 2 0.0000 0.984 0.000 1.000
#> GSM486782 2 0.0000 0.984 0.000 1.000
#> GSM486784 2 0.0000 0.984 0.000 1.000
#> GSM486786 1 0.0000 0.963 1.000 0.000
#> GSM486788 1 0.0000 0.963 1.000 0.000
#> GSM486790 2 0.0000 0.984 0.000 1.000
#> GSM486792 1 0.0000 0.963 1.000 0.000
#> GSM486794 1 0.0000 0.963 1.000 0.000
#> GSM486796 1 0.0000 0.963 1.000 0.000
#> GSM486798 2 0.9732 0.289 0.404 0.596
#> GSM486800 1 0.0000 0.963 1.000 0.000
#> GSM486802 1 0.0000 0.963 1.000 0.000
#> GSM486804 1 0.0000 0.963 1.000 0.000
#> GSM486806 2 0.0000 0.984 0.000 1.000
#> GSM486808 1 0.0000 0.963 1.000 0.000
#> GSM486810 2 0.0000 0.984 0.000 1.000
#> GSM486812 1 0.0000 0.963 1.000 0.000
#> GSM486814 2 0.0000 0.984 0.000 1.000
#> GSM486816 1 0.0000 0.963 1.000 0.000
#> GSM486818 1 0.9866 0.265 0.568 0.432
#> GSM486821 1 0.9460 0.451 0.636 0.364
#> GSM486823 2 0.0000 0.984 0.000 1.000
#> GSM486826 1 0.0000 0.963 1.000 0.000
#> GSM486830 2 0.0000 0.984 0.000 1.000
#> GSM486832 1 0.0000 0.963 1.000 0.000
#> GSM486834 1 0.8661 0.611 0.712 0.288
#> GSM486836 1 0.0000 0.963 1.000 0.000
#> GSM486838 2 0.0000 0.984 0.000 1.000
#> GSM486840 1 0.0000 0.963 1.000 0.000
#> GSM486842 1 0.0000 0.963 1.000 0.000
#> GSM486844 1 0.0000 0.963 1.000 0.000
#> GSM486846 2 0.0000 0.984 0.000 1.000
#> GSM486848 1 0.0000 0.963 1.000 0.000
#> GSM486850 2 0.0000 0.984 0.000 1.000
#> GSM486852 1 0.0000 0.963 1.000 0.000
#> GSM486854 2 0.0000 0.984 0.000 1.000
#> GSM486856 2 0.0000 0.984 0.000 1.000
#> GSM486858 2 0.0000 0.984 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 2 0.1753 0.8095 0.000 0.952 0.048
#> GSM486737 2 0.0747 0.8218 0.000 0.984 0.016
#> GSM486739 2 0.1860 0.8095 0.000 0.948 0.052
#> GSM486741 2 0.0424 0.8214 0.000 0.992 0.008
#> GSM486743 2 0.1163 0.8216 0.000 0.972 0.028
#> GSM486745 2 0.2636 0.7997 0.020 0.932 0.048
#> GSM486747 1 0.5506 0.7391 0.816 0.092 0.092
#> GSM486749 2 0.1163 0.8188 0.000 0.972 0.028
#> GSM486751 1 0.7979 0.6135 0.628 0.272 0.100
#> GSM486753 2 0.1411 0.8194 0.000 0.964 0.036
#> GSM486755 2 0.1289 0.8194 0.000 0.968 0.032
#> GSM486757 1 0.7603 0.6430 0.668 0.236 0.096
#> GSM486759 1 0.0237 0.7978 0.996 0.000 0.004
#> GSM486761 1 0.1964 0.7911 0.944 0.000 0.056
#> GSM486763 1 0.7091 0.6187 0.676 0.268 0.056
#> GSM486765 1 0.2537 0.7668 0.920 0.000 0.080
#> GSM486767 2 0.4290 0.7789 0.064 0.872 0.064
#> GSM486769 2 0.1860 0.8118 0.000 0.948 0.052
#> GSM486771 2 0.0892 0.8196 0.000 0.980 0.020
#> GSM486773 2 0.5970 0.6139 0.160 0.780 0.060
#> GSM486775 1 0.1289 0.7802 0.968 0.000 0.032
#> GSM486777 1 0.1643 0.7950 0.956 0.000 0.044
#> GSM486779 2 0.2443 0.8184 0.028 0.940 0.032
#> GSM486781 2 0.1878 0.8115 0.004 0.952 0.044
#> GSM486783 2 0.1163 0.8259 0.000 0.972 0.028
#> GSM486785 1 0.1753 0.7937 0.952 0.000 0.048
#> GSM486787 1 0.1643 0.7557 0.956 0.000 0.044
#> GSM486789 2 0.1753 0.8187 0.000 0.952 0.048
#> GSM486791 1 0.1163 0.7925 0.972 0.000 0.028
#> GSM486793 1 0.1753 0.7937 0.952 0.000 0.048
#> GSM486795 1 0.5012 0.6927 0.788 0.204 0.008
#> GSM486797 1 0.8055 0.5997 0.612 0.292 0.096
#> GSM486799 1 0.1163 0.7775 0.972 0.000 0.028
#> GSM486801 1 0.0237 0.7957 0.996 0.000 0.004
#> GSM486803 1 0.0000 0.7968 1.000 0.000 0.000
#> GSM486805 1 0.8663 0.4959 0.524 0.364 0.112
#> GSM486807 1 0.1964 0.7920 0.944 0.000 0.056
#> GSM486809 2 0.2903 0.7941 0.028 0.924 0.048
#> GSM486811 1 0.1643 0.7950 0.956 0.000 0.044
#> GSM486813 2 0.1289 0.8269 0.000 0.968 0.032
#> GSM486815 1 0.1753 0.7935 0.952 0.000 0.048
#> GSM486817 1 0.7084 0.5785 0.628 0.336 0.036
#> GSM486819 1 0.6761 0.6373 0.700 0.252 0.048
#> GSM486822 2 0.1163 0.8215 0.000 0.972 0.028
#> GSM486824 1 0.1411 0.7699 0.964 0.000 0.036
#> GSM486828 2 0.4384 0.7467 0.068 0.868 0.064
#> GSM486831 1 0.0237 0.7957 0.996 0.000 0.004
#> GSM486833 1 0.8430 0.5816 0.588 0.292 0.120
#> GSM486835 1 0.0237 0.7959 0.996 0.000 0.004
#> GSM486837 2 0.7003 0.4574 0.248 0.692 0.060
#> GSM486839 1 0.0237 0.7957 0.996 0.000 0.004
#> GSM486841 1 0.1643 0.7952 0.956 0.000 0.044
#> GSM486843 1 0.0000 0.7968 1.000 0.000 0.000
#> GSM486845 2 0.2152 0.8080 0.016 0.948 0.036
#> GSM486847 1 0.0592 0.7911 0.988 0.000 0.012
#> GSM486849 2 0.0747 0.8247 0.000 0.984 0.016
#> GSM486851 1 0.4505 0.7402 0.860 0.092 0.048
#> GSM486853 2 0.0747 0.8237 0.000 0.984 0.016
#> GSM486855 2 0.0892 0.8238 0.000 0.980 0.020
#> GSM486857 2 0.3406 0.7648 0.068 0.904 0.028
#> GSM486736 2 0.5529 0.8208 0.000 0.704 0.296
#> GSM486738 2 0.5497 0.8165 0.000 0.708 0.292
#> GSM486740 2 0.5678 0.8159 0.000 0.684 0.316
#> GSM486742 2 0.5397 0.8182 0.000 0.720 0.280
#> GSM486744 2 0.5431 0.8181 0.000 0.716 0.284
#> GSM486746 2 0.5733 0.8145 0.000 0.676 0.324
#> GSM486748 3 0.4409 0.6841 0.172 0.004 0.824
#> GSM486750 2 0.5529 0.8174 0.000 0.704 0.296
#> GSM486752 3 0.3375 0.6327 0.100 0.008 0.892
#> GSM486754 2 0.5431 0.8181 0.000 0.716 0.284
#> GSM486756 2 0.5529 0.8190 0.000 0.704 0.296
#> GSM486758 3 0.4912 0.6997 0.196 0.008 0.796
#> GSM486760 3 0.6168 0.7739 0.412 0.000 0.588
#> GSM486762 3 0.5948 0.7654 0.360 0.000 0.640
#> GSM486764 3 0.6168 0.6703 0.224 0.036 0.740
#> GSM486766 3 0.6008 0.7679 0.372 0.000 0.628
#> GSM486768 2 0.5905 0.7882 0.000 0.648 0.352
#> GSM486770 2 0.5760 0.8133 0.000 0.672 0.328
#> GSM486772 2 0.5529 0.8160 0.000 0.704 0.296
#> GSM486774 2 0.6154 0.7428 0.000 0.592 0.408
#> GSM486776 3 0.6180 0.7717 0.416 0.000 0.584
#> GSM486778 3 0.6045 0.7640 0.380 0.000 0.620
#> GSM486780 2 0.5591 0.8095 0.000 0.696 0.304
#> GSM486782 2 0.5678 0.8087 0.000 0.684 0.316
#> GSM486784 2 0.5465 0.8165 0.000 0.712 0.288
#> GSM486786 3 0.6045 0.7632 0.380 0.000 0.620
#> GSM486788 3 0.6180 0.7737 0.416 0.000 0.584
#> GSM486790 2 0.5591 0.8162 0.000 0.696 0.304
#> GSM486792 3 0.6204 0.7630 0.424 0.000 0.576
#> GSM486794 3 0.6062 0.7597 0.384 0.000 0.616
#> GSM486796 3 0.4755 0.6568 0.184 0.008 0.808
#> GSM486798 3 0.3141 0.5436 0.020 0.068 0.912
#> GSM486800 3 0.6180 0.7737 0.416 0.000 0.584
#> GSM486802 3 0.6180 0.7737 0.416 0.000 0.584
#> GSM486804 3 0.6154 0.7751 0.408 0.000 0.592
#> GSM486806 3 0.5138 0.0758 0.000 0.252 0.748
#> GSM486808 3 0.5882 0.7634 0.348 0.000 0.652
#> GSM486810 2 0.5529 0.8209 0.000 0.704 0.296
#> GSM486812 3 0.6008 0.7676 0.372 0.000 0.628
#> GSM486814 2 0.5465 0.8165 0.000 0.712 0.288
#> GSM486816 3 0.6095 0.7525 0.392 0.000 0.608
#> GSM486818 3 0.4925 0.5497 0.076 0.080 0.844
#> GSM486821 3 0.5408 0.5608 0.136 0.052 0.812
#> GSM486823 2 0.5591 0.8156 0.000 0.696 0.304
#> GSM486826 3 0.6180 0.7737 0.416 0.000 0.584
#> GSM486830 2 0.6045 0.7715 0.000 0.620 0.380
#> GSM486832 3 0.6168 0.7741 0.412 0.000 0.588
#> GSM486834 3 0.2903 0.5769 0.048 0.028 0.924
#> GSM486836 3 0.6180 0.7737 0.416 0.000 0.584
#> GSM486838 3 0.6235 -0.4476 0.000 0.436 0.564
#> GSM486840 3 0.6180 0.7737 0.416 0.000 0.584
#> GSM486842 3 0.6008 0.7679 0.372 0.000 0.628
#> GSM486844 3 0.6180 0.7737 0.416 0.000 0.584
#> GSM486846 2 0.5678 0.8091 0.000 0.684 0.316
#> GSM486848 3 0.6192 0.7699 0.420 0.000 0.580
#> GSM486850 2 0.5431 0.8166 0.000 0.716 0.284
#> GSM486852 3 0.5465 0.7267 0.288 0.000 0.712
#> GSM486854 2 0.5431 0.8166 0.000 0.716 0.284
#> GSM486856 2 0.5465 0.8165 0.000 0.712 0.288
#> GSM486858 2 0.5785 0.7957 0.000 0.668 0.332
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 4 0.5067 0.512 0.048 0.216 0.000 0.736
#> GSM486737 2 0.5399 -0.444 0.012 0.520 0.000 0.468
#> GSM486739 4 0.4677 0.515 0.048 0.176 0.000 0.776
#> GSM486741 4 0.5402 0.466 0.012 0.472 0.000 0.516
#> GSM486743 4 0.5427 0.530 0.016 0.416 0.000 0.568
#> GSM486745 4 0.5123 0.509 0.044 0.232 0.000 0.724
#> GSM486747 1 0.5886 0.700 0.732 0.020 0.156 0.092
#> GSM486749 4 0.5254 0.594 0.028 0.300 0.000 0.672
#> GSM486751 1 0.5886 0.472 0.640 0.016 0.028 0.316
#> GSM486753 4 0.4792 0.593 0.008 0.312 0.000 0.680
#> GSM486755 4 0.5444 0.516 0.016 0.424 0.000 0.560
#> GSM486757 1 0.4348 0.643 0.780 0.000 0.024 0.196
#> GSM486759 1 0.4277 0.764 0.720 0.000 0.280 0.000
#> GSM486761 1 0.3626 0.762 0.812 0.000 0.184 0.004
#> GSM486763 1 0.6977 0.340 0.584 0.036 0.060 0.320
#> GSM486765 1 0.4584 0.708 0.696 0.000 0.300 0.004
#> GSM486767 4 0.6240 0.477 0.080 0.276 0.004 0.640
#> GSM486769 4 0.4993 0.510 0.028 0.260 0.000 0.712
#> GSM486771 4 0.5638 0.560 0.028 0.388 0.000 0.584
#> GSM486773 4 0.4605 0.550 0.108 0.092 0.000 0.800
#> GSM486775 1 0.4585 0.727 0.668 0.000 0.332 0.000
#> GSM486777 1 0.3486 0.768 0.812 0.000 0.188 0.000
#> GSM486779 2 0.5917 -0.427 0.036 0.520 0.000 0.444
#> GSM486781 4 0.5207 0.551 0.028 0.292 0.000 0.680
#> GSM486783 2 0.5126 -0.378 0.004 0.552 0.000 0.444
#> GSM486785 1 0.3873 0.764 0.772 0.000 0.228 0.000
#> GSM486787 1 0.4624 0.723 0.660 0.000 0.340 0.000
#> GSM486789 4 0.4957 0.518 0.012 0.320 0.000 0.668
#> GSM486791 1 0.5184 0.684 0.732 0.000 0.212 0.056
#> GSM486793 1 0.3172 0.763 0.840 0.000 0.160 0.000
#> GSM486795 1 0.6124 0.680 0.728 0.032 0.108 0.132
#> GSM486797 1 0.7006 0.185 0.508 0.068 0.020 0.404
#> GSM486799 1 0.4679 0.707 0.648 0.000 0.352 0.000
#> GSM486801 1 0.4250 0.765 0.724 0.000 0.276 0.000
#> GSM486803 1 0.4193 0.770 0.732 0.000 0.268 0.000
#> GSM486805 4 0.6052 0.411 0.284 0.076 0.000 0.640
#> GSM486807 1 0.4248 0.757 0.768 0.000 0.220 0.012
#> GSM486809 4 0.5292 0.504 0.088 0.168 0.000 0.744
#> GSM486811 1 0.3801 0.766 0.780 0.000 0.220 0.000
#> GSM486813 2 0.5693 -0.435 0.024 0.504 0.000 0.472
#> GSM486815 1 0.3873 0.762 0.772 0.000 0.228 0.000
#> GSM486817 1 0.7561 0.169 0.480 0.064 0.052 0.404
#> GSM486819 1 0.6356 0.478 0.636 0.012 0.068 0.284
#> GSM486822 4 0.5269 0.485 0.016 0.364 0.000 0.620
#> GSM486824 1 0.4632 0.751 0.688 0.004 0.308 0.000
#> GSM486828 4 0.5458 0.562 0.076 0.204 0.000 0.720
#> GSM486831 1 0.3975 0.768 0.760 0.000 0.240 0.000
#> GSM486833 1 0.5798 0.161 0.524 0.012 0.012 0.452
#> GSM486835 1 0.4454 0.756 0.692 0.000 0.308 0.000
#> GSM486837 4 0.7203 0.402 0.164 0.312 0.000 0.524
#> GSM486839 1 0.4250 0.762 0.724 0.000 0.276 0.000
#> GSM486841 1 0.3764 0.767 0.784 0.000 0.216 0.000
#> GSM486843 1 0.4313 0.771 0.736 0.000 0.260 0.004
#> GSM486845 4 0.5883 0.554 0.064 0.288 0.000 0.648
#> GSM486847 1 0.4356 0.759 0.708 0.000 0.292 0.000
#> GSM486849 4 0.5650 0.510 0.024 0.432 0.000 0.544
#> GSM486851 1 0.5690 0.576 0.708 0.000 0.096 0.196
#> GSM486853 4 0.5510 0.443 0.016 0.480 0.000 0.504
#> GSM486855 4 0.5696 0.456 0.024 0.484 0.000 0.492
#> GSM486857 4 0.6206 0.529 0.088 0.280 0.000 0.632
#> GSM486736 4 0.6147 -0.170 0.048 0.464 0.000 0.488
#> GSM486738 2 0.2675 0.590 0.008 0.892 0.000 0.100
#> GSM486740 2 0.6204 0.186 0.052 0.500 0.000 0.448
#> GSM486742 2 0.2530 0.606 0.000 0.888 0.000 0.112
#> GSM486744 2 0.2530 0.616 0.000 0.896 0.004 0.100
#> GSM486746 2 0.5715 0.440 0.028 0.636 0.008 0.328
#> GSM486748 3 0.6428 0.678 0.080 0.128 0.720 0.072
#> GSM486750 2 0.4123 0.590 0.008 0.772 0.000 0.220
#> GSM486752 3 0.7686 0.598 0.100 0.180 0.620 0.100
#> GSM486754 2 0.3529 0.602 0.012 0.836 0.000 0.152
#> GSM486756 2 0.3494 0.592 0.004 0.824 0.000 0.172
#> GSM486758 3 0.6309 0.693 0.188 0.064 0.704 0.044
#> GSM486760 3 0.1211 0.776 0.040 0.000 0.960 0.000
#> GSM486762 3 0.3351 0.757 0.148 0.000 0.844 0.008
#> GSM486764 3 0.9416 0.274 0.208 0.136 0.416 0.240
#> GSM486766 3 0.2654 0.766 0.108 0.000 0.888 0.004
#> GSM486768 2 0.4687 0.580 0.008 0.776 0.028 0.188
#> GSM486770 2 0.5673 0.393 0.032 0.596 0.000 0.372
#> GSM486772 2 0.2958 0.616 0.004 0.876 0.004 0.116
#> GSM486774 2 0.6193 0.497 0.024 0.624 0.032 0.320
#> GSM486776 3 0.2081 0.762 0.084 0.000 0.916 0.000
#> GSM486778 3 0.2868 0.767 0.136 0.000 0.864 0.000
#> GSM486780 2 0.3108 0.546 0.000 0.872 0.016 0.112
#> GSM486782 2 0.4267 0.579 0.004 0.772 0.008 0.216
#> GSM486784 2 0.1930 0.590 0.004 0.936 0.004 0.056
#> GSM486786 3 0.3074 0.741 0.152 0.000 0.848 0.000
#> GSM486788 3 0.0707 0.778 0.020 0.000 0.980 0.000
#> GSM486790 2 0.4509 0.516 0.004 0.708 0.000 0.288
#> GSM486792 3 0.4839 0.685 0.184 0.000 0.764 0.052
#> GSM486794 3 0.3355 0.755 0.160 0.000 0.836 0.004
#> GSM486796 3 0.4889 0.692 0.044 0.152 0.788 0.016
#> GSM486798 3 0.8303 0.190 0.084 0.392 0.436 0.088
#> GSM486800 3 0.1557 0.774 0.056 0.000 0.944 0.000
#> GSM486802 3 0.1489 0.776 0.044 0.000 0.952 0.004
#> GSM486804 3 0.1520 0.777 0.020 0.024 0.956 0.000
#> GSM486806 2 0.8215 0.340 0.044 0.512 0.176 0.268
#> GSM486808 3 0.2714 0.769 0.112 0.000 0.884 0.004
#> GSM486810 2 0.6737 0.225 0.068 0.484 0.008 0.440
#> GSM486812 3 0.2647 0.767 0.120 0.000 0.880 0.000
#> GSM486814 2 0.1909 0.604 0.008 0.940 0.004 0.048
#> GSM486816 3 0.3444 0.739 0.184 0.000 0.816 0.000
#> GSM486818 3 0.7655 0.455 0.056 0.276 0.572 0.096
#> GSM486821 3 0.9483 0.199 0.148 0.244 0.408 0.200
#> GSM486823 2 0.4647 0.530 0.008 0.704 0.000 0.288
#> GSM486826 3 0.1867 0.765 0.072 0.000 0.928 0.000
#> GSM486830 2 0.5926 0.501 0.028 0.648 0.020 0.304
#> GSM486832 3 0.1022 0.778 0.032 0.000 0.968 0.000
#> GSM486834 3 0.9017 0.421 0.136 0.216 0.484 0.164
#> GSM486836 3 0.1022 0.778 0.032 0.000 0.968 0.000
#> GSM486838 2 0.6031 0.491 0.028 0.732 0.108 0.132
#> GSM486840 3 0.1792 0.768 0.068 0.000 0.932 0.000
#> GSM486842 3 0.1940 0.775 0.076 0.000 0.924 0.000
#> GSM486844 3 0.1786 0.780 0.036 0.008 0.948 0.008
#> GSM486846 2 0.3950 0.572 0.008 0.804 0.004 0.184
#> GSM486848 3 0.2593 0.740 0.104 0.000 0.892 0.004
#> GSM486850 2 0.2714 0.612 0.004 0.884 0.000 0.112
#> GSM486852 3 0.7332 0.547 0.172 0.036 0.624 0.168
#> GSM486854 2 0.2457 0.597 0.004 0.912 0.008 0.076
#> GSM486856 2 0.2048 0.590 0.000 0.928 0.008 0.064
#> GSM486858 2 0.3730 0.581 0.004 0.836 0.016 0.144
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 4 0.455 0.46310 0.000 0.120 0.000 0.752 0.128
#> GSM486737 2 0.572 0.11230 0.008 0.544 0.000 0.380 0.068
#> GSM486739 4 0.485 0.45245 0.004 0.096 0.000 0.728 0.172
#> GSM486741 2 0.552 0.08842 0.004 0.544 0.000 0.392 0.060
#> GSM486743 4 0.588 0.16294 0.004 0.400 0.000 0.508 0.088
#> GSM486745 4 0.549 0.45805 0.008 0.128 0.004 0.688 0.172
#> GSM486747 1 0.627 0.46533 0.636 0.004 0.100 0.044 0.216
#> GSM486749 4 0.538 0.39797 0.004 0.276 0.000 0.640 0.080
#> GSM486751 1 0.717 0.12308 0.504 0.004 0.036 0.188 0.268
#> GSM486753 4 0.535 0.31536 0.004 0.316 0.000 0.616 0.064
#> GSM486755 4 0.547 0.15071 0.004 0.428 0.000 0.516 0.052
#> GSM486757 1 0.614 0.28427 0.588 0.000 0.012 0.136 0.264
#> GSM486759 1 0.409 0.72735 0.756 0.000 0.208 0.000 0.036
#> GSM486761 1 0.473 0.66298 0.752 0.000 0.128 0.008 0.112
#> GSM486763 5 0.743 0.21633 0.296 0.016 0.008 0.312 0.368
#> GSM486765 1 0.433 0.68772 0.740 0.000 0.212 0.000 0.048
#> GSM486767 4 0.691 0.33872 0.032 0.232 0.000 0.528 0.208
#> GSM486769 4 0.485 0.43616 0.004 0.196 0.000 0.720 0.080
#> GSM486771 4 0.583 0.19414 0.012 0.384 0.000 0.536 0.068
#> GSM486773 4 0.515 0.42693 0.032 0.048 0.000 0.708 0.212
#> GSM486775 1 0.411 0.69492 0.700 0.000 0.288 0.000 0.012
#> GSM486777 1 0.316 0.70874 0.860 0.000 0.092 0.004 0.044
#> GSM486779 2 0.644 0.07680 0.024 0.508 0.000 0.364 0.104
#> GSM486781 4 0.655 0.37295 0.028 0.156 0.000 0.572 0.244
#> GSM486783 2 0.548 0.14957 0.008 0.568 0.000 0.372 0.052
#> GSM486785 1 0.292 0.71923 0.856 0.000 0.124 0.000 0.020
#> GSM486787 1 0.434 0.67394 0.684 0.000 0.296 0.000 0.020
#> GSM486789 4 0.501 0.42140 0.008 0.208 0.000 0.708 0.076
#> GSM486791 1 0.679 0.42437 0.560 0.000 0.140 0.048 0.252
#> GSM486793 1 0.432 0.68614 0.780 0.000 0.120 0.004 0.096
#> GSM486795 1 0.755 0.41230 0.572 0.028 0.092 0.144 0.164
#> GSM486797 1 0.813 -0.11913 0.368 0.056 0.016 0.268 0.292
#> GSM486799 1 0.438 0.67061 0.676 0.000 0.304 0.000 0.020
#> GSM486801 1 0.459 0.71372 0.724 0.000 0.212 0.000 0.064
#> GSM486803 1 0.495 0.71788 0.712 0.000 0.208 0.008 0.072
#> GSM486805 4 0.725 0.00187 0.252 0.012 0.008 0.416 0.312
#> GSM486807 1 0.467 0.69013 0.748 0.000 0.148 0.004 0.100
#> GSM486809 4 0.532 0.42237 0.012 0.092 0.004 0.704 0.188
#> GSM486811 1 0.333 0.72241 0.828 0.000 0.144 0.000 0.028
#> GSM486813 2 0.615 0.07340 0.020 0.512 0.000 0.388 0.080
#> GSM486815 1 0.349 0.71007 0.820 0.000 0.144 0.000 0.036
#> GSM486817 4 0.911 -0.11914 0.304 0.076 0.088 0.316 0.216
#> GSM486819 1 0.753 -0.09599 0.392 0.012 0.032 0.188 0.376
#> GSM486822 4 0.521 0.31771 0.000 0.320 0.000 0.616 0.064
#> GSM486824 1 0.491 0.69000 0.680 0.000 0.264 0.004 0.052
#> GSM486828 4 0.637 0.40928 0.040 0.116 0.000 0.604 0.240
#> GSM486831 1 0.453 0.71916 0.724 0.000 0.220 0.000 0.056
#> GSM486833 5 0.762 0.04674 0.308 0.016 0.016 0.328 0.332
#> GSM486835 1 0.462 0.70810 0.700 0.000 0.252 0.000 0.048
#> GSM486837 4 0.869 0.17593 0.204 0.248 0.004 0.296 0.248
#> GSM486839 1 0.379 0.72439 0.768 0.000 0.212 0.000 0.020
#> GSM486841 1 0.268 0.72142 0.872 0.000 0.112 0.000 0.016
#> GSM486843 1 0.448 0.71597 0.756 0.000 0.184 0.012 0.048
#> GSM486845 4 0.693 0.29630 0.024 0.248 0.000 0.504 0.224
#> GSM486847 1 0.394 0.72267 0.756 0.000 0.220 0.000 0.024
#> GSM486849 2 0.625 -0.07330 0.008 0.448 0.004 0.444 0.096
#> GSM486851 1 0.718 0.00335 0.440 0.000 0.044 0.156 0.360
#> GSM486853 2 0.598 0.02464 0.004 0.492 0.000 0.408 0.096
#> GSM486855 2 0.625 0.03778 0.020 0.500 0.000 0.392 0.088
#> GSM486857 4 0.734 0.23391 0.036 0.296 0.000 0.436 0.232
#> GSM486736 4 0.601 0.27499 0.000 0.264 0.000 0.572 0.164
#> GSM486738 2 0.251 0.54511 0.000 0.892 0.000 0.080 0.028
#> GSM486740 4 0.650 0.16934 0.004 0.296 0.004 0.524 0.172
#> GSM486742 2 0.261 0.54930 0.004 0.892 0.000 0.076 0.028
#> GSM486744 2 0.337 0.53793 0.000 0.848 0.004 0.092 0.056
#> GSM486746 2 0.711 0.05047 0.004 0.396 0.012 0.364 0.224
#> GSM486748 3 0.648 0.51285 0.072 0.052 0.636 0.020 0.220
#> GSM486750 2 0.558 0.39685 0.004 0.632 0.000 0.260 0.104
#> GSM486752 3 0.739 0.27677 0.072 0.068 0.528 0.036 0.296
#> GSM486754 2 0.458 0.49590 0.000 0.740 0.004 0.192 0.064
#> GSM486756 2 0.447 0.50110 0.000 0.752 0.000 0.164 0.084
#> GSM486758 3 0.755 0.31457 0.124 0.052 0.508 0.028 0.288
#> GSM486760 3 0.262 0.73279 0.100 0.000 0.880 0.000 0.020
#> GSM486762 3 0.481 0.67095 0.168 0.000 0.724 0.000 0.108
#> GSM486764 5 0.869 0.39373 0.128 0.032 0.236 0.196 0.408
#> GSM486766 3 0.360 0.72146 0.140 0.000 0.816 0.000 0.044
#> GSM486768 2 0.668 0.34547 0.004 0.560 0.020 0.180 0.236
#> GSM486770 4 0.597 -0.05520 0.000 0.440 0.000 0.452 0.108
#> GSM486772 2 0.343 0.53903 0.004 0.848 0.004 0.100 0.044
#> GSM486774 2 0.725 0.22727 0.000 0.448 0.032 0.292 0.228
#> GSM486776 3 0.201 0.73703 0.072 0.000 0.916 0.000 0.012
#> GSM486778 3 0.483 0.68975 0.200 0.000 0.712 0.000 0.088
#> GSM486780 2 0.385 0.52658 0.004 0.828 0.008 0.088 0.072
#> GSM486782 2 0.638 0.38854 0.004 0.588 0.012 0.180 0.216
#> GSM486784 2 0.158 0.54726 0.000 0.944 0.000 0.024 0.032
#> GSM486786 3 0.439 0.69793 0.168 0.000 0.756 0.000 0.076
#> GSM486788 3 0.141 0.73067 0.044 0.000 0.948 0.000 0.008
#> GSM486790 2 0.578 0.25759 0.000 0.528 0.000 0.376 0.096
#> GSM486792 3 0.636 0.35652 0.116 0.000 0.576 0.028 0.280
#> GSM486794 3 0.506 0.66065 0.204 0.000 0.692 0.000 0.104
#> GSM486796 3 0.563 0.52776 0.036 0.112 0.716 0.008 0.128
#> GSM486798 3 0.852 -0.21406 0.048 0.300 0.360 0.052 0.240
#> GSM486800 3 0.167 0.73421 0.076 0.000 0.924 0.000 0.000
#> GSM486802 3 0.282 0.73312 0.096 0.000 0.872 0.000 0.032
#> GSM486804 3 0.268 0.72551 0.048 0.004 0.892 0.000 0.056
#> GSM486806 5 0.840 -0.03317 0.020 0.340 0.128 0.140 0.372
#> GSM486808 3 0.315 0.71744 0.092 0.000 0.856 0.000 0.052
#> GSM486810 4 0.723 0.20774 0.008 0.264 0.024 0.484 0.220
#> GSM486812 3 0.391 0.71759 0.196 0.000 0.772 0.000 0.032
#> GSM486814 2 0.321 0.54452 0.004 0.860 0.000 0.072 0.064
#> GSM486816 3 0.520 0.64473 0.224 0.000 0.672 0.000 0.104
#> GSM486818 3 0.870 -0.09343 0.064 0.172 0.436 0.092 0.236
#> GSM486821 5 0.897 0.34664 0.064 0.124 0.300 0.144 0.368
#> GSM486823 2 0.548 0.30457 0.000 0.584 0.000 0.336 0.080
#> GSM486826 3 0.359 0.71135 0.128 0.008 0.828 0.000 0.036
#> GSM486830 2 0.680 0.30580 0.000 0.488 0.012 0.228 0.272
#> GSM486832 3 0.205 0.73497 0.052 0.000 0.920 0.000 0.028
#> GSM486834 5 0.901 0.19732 0.084 0.128 0.300 0.116 0.372
#> GSM486836 3 0.167 0.73429 0.028 0.000 0.940 0.000 0.032
#> GSM486838 2 0.697 0.34639 0.016 0.608 0.124 0.068 0.184
#> GSM486840 3 0.252 0.72888 0.108 0.000 0.880 0.000 0.012
#> GSM486842 3 0.271 0.73099 0.088 0.000 0.880 0.000 0.032
#> GSM486844 3 0.224 0.73427 0.040 0.004 0.916 0.000 0.040
#> GSM486846 2 0.564 0.46094 0.000 0.660 0.008 0.156 0.176
#> GSM486848 3 0.311 0.71535 0.140 0.000 0.840 0.000 0.020
#> GSM486850 2 0.386 0.53764 0.000 0.812 0.004 0.120 0.064
#> GSM486852 3 0.780 -0.19881 0.096 0.008 0.408 0.124 0.364
#> GSM486854 2 0.278 0.54938 0.000 0.880 0.000 0.048 0.072
#> GSM486856 2 0.276 0.53993 0.000 0.872 0.000 0.024 0.104
#> GSM486858 2 0.573 0.45549 0.008 0.652 0.008 0.096 0.236
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 6 0.575 0.45357 0.000 0.124 0.032 0.000 0.256 0.588
#> GSM486737 2 0.558 0.05054 0.000 0.500 0.036 0.004 0.048 0.412
#> GSM486739 6 0.589 0.41572 0.000 0.076 0.056 0.008 0.264 0.596
#> GSM486741 6 0.524 0.02934 0.000 0.436 0.024 0.004 0.036 0.500
#> GSM486743 6 0.638 0.23012 0.000 0.304 0.104 0.004 0.068 0.520
#> GSM486745 6 0.677 0.36010 0.000 0.104 0.100 0.016 0.248 0.532
#> GSM486747 4 0.715 0.34949 0.100 0.004 0.264 0.512 0.072 0.048
#> GSM486749 6 0.578 0.40254 0.000 0.208 0.068 0.004 0.088 0.632
#> GSM486751 4 0.758 0.05618 0.020 0.004 0.280 0.424 0.108 0.164
#> GSM486753 6 0.514 0.36310 0.000 0.232 0.056 0.004 0.040 0.668
#> GSM486755 6 0.621 0.03867 0.000 0.432 0.048 0.012 0.072 0.436
#> GSM486757 4 0.742 0.26513 0.028 0.004 0.172 0.500 0.180 0.116
#> GSM486759 4 0.488 0.67534 0.212 0.000 0.048 0.692 0.048 0.000
#> GSM486761 4 0.542 0.62073 0.088 0.000 0.100 0.712 0.076 0.024
#> GSM486763 5 0.569 0.48038 0.012 0.008 0.016 0.180 0.648 0.136
#> GSM486765 4 0.462 0.60537 0.236 0.000 0.064 0.688 0.012 0.000
#> GSM486767 6 0.770 0.26624 0.000 0.124 0.156 0.032 0.276 0.412
#> GSM486769 6 0.607 0.44274 0.000 0.164 0.040 0.004 0.208 0.584
#> GSM486771 6 0.547 0.24672 0.000 0.316 0.032 0.000 0.072 0.580
#> GSM486773 6 0.623 0.28383 0.004 0.020 0.184 0.040 0.140 0.612
#> GSM486775 4 0.422 0.59301 0.304 0.000 0.028 0.664 0.004 0.000
#> GSM486777 4 0.400 0.66947 0.104 0.000 0.048 0.796 0.052 0.000
#> GSM486779 2 0.715 0.07324 0.000 0.444 0.104 0.040 0.072 0.340
#> GSM486781 6 0.684 0.19107 0.000 0.128 0.288 0.012 0.080 0.492
#> GSM486783 2 0.563 0.18287 0.000 0.556 0.076 0.000 0.036 0.332
#> GSM486785 4 0.376 0.68876 0.112 0.000 0.044 0.812 0.028 0.004
#> GSM486787 4 0.453 0.63451 0.264 0.000 0.020 0.684 0.028 0.004
#> GSM486789 6 0.562 0.41794 0.000 0.200 0.060 0.000 0.100 0.640
#> GSM486791 4 0.627 0.12540 0.084 0.000 0.040 0.480 0.380 0.016
#> GSM486793 4 0.507 0.61582 0.092 0.000 0.096 0.724 0.084 0.004
#> GSM486795 4 0.788 0.37691 0.060 0.048 0.124 0.532 0.132 0.104
#> GSM486797 4 0.762 -0.02276 0.004 0.028 0.324 0.384 0.080 0.180
#> GSM486799 4 0.474 0.60699 0.292 0.000 0.052 0.644 0.012 0.000
#> GSM486801 4 0.517 0.67219 0.184 0.000 0.052 0.700 0.048 0.016
#> GSM486803 4 0.579 0.63501 0.172 0.000 0.060 0.660 0.088 0.020
#> GSM486805 3 0.809 0.10347 0.000 0.056 0.324 0.228 0.096 0.296
#> GSM486807 4 0.501 0.65007 0.116 0.000 0.116 0.724 0.032 0.012
#> GSM486809 6 0.603 0.29268 0.000 0.068 0.048 0.008 0.372 0.504
#> GSM486811 4 0.384 0.68918 0.132 0.000 0.036 0.800 0.028 0.004
#> GSM486813 2 0.636 0.10648 0.000 0.480 0.068 0.004 0.088 0.360
#> GSM486815 4 0.424 0.66595 0.128 0.000 0.040 0.772 0.060 0.000
#> GSM486817 4 0.882 -0.10954 0.028 0.044 0.204 0.288 0.188 0.248
#> GSM486819 5 0.691 0.39542 0.020 0.004 0.076 0.248 0.528 0.124
#> GSM486822 6 0.648 0.28866 0.000 0.292 0.072 0.000 0.132 0.504
#> GSM486824 4 0.542 0.62856 0.264 0.000 0.048 0.632 0.048 0.008
#> GSM486828 6 0.729 0.13776 0.000 0.088 0.276 0.032 0.136 0.468
#> GSM486831 4 0.577 0.62223 0.180 0.000 0.044 0.632 0.140 0.004
#> GSM486833 3 0.834 0.07599 0.024 0.012 0.300 0.260 0.168 0.236
#> GSM486835 4 0.548 0.64977 0.240 0.000 0.048 0.648 0.048 0.016
#> GSM486837 3 0.810 0.04340 0.004 0.172 0.348 0.096 0.060 0.320
#> GSM486839 4 0.383 0.67933 0.200 0.000 0.020 0.760 0.020 0.000
#> GSM486841 4 0.289 0.68635 0.108 0.000 0.016 0.856 0.020 0.000
#> GSM486843 4 0.533 0.66655 0.144 0.000 0.052 0.712 0.056 0.036
#> GSM486845 6 0.711 0.23755 0.000 0.196 0.204 0.008 0.108 0.484
#> GSM486847 4 0.405 0.67343 0.220 0.000 0.028 0.736 0.016 0.000
#> GSM486849 2 0.572 0.02799 0.000 0.468 0.048 0.000 0.056 0.428
#> GSM486851 5 0.546 0.35035 0.024 0.000 0.008 0.328 0.580 0.060
#> GSM486853 2 0.555 0.08146 0.000 0.492 0.056 0.000 0.036 0.416
#> GSM486855 2 0.623 -0.00326 0.000 0.444 0.104 0.000 0.052 0.400
#> GSM486857 6 0.742 0.12931 0.000 0.232 0.224 0.036 0.064 0.444
#> GSM486736 6 0.678 0.30832 0.000 0.220 0.064 0.000 0.256 0.460
#> GSM486738 2 0.347 0.49144 0.000 0.828 0.032 0.000 0.036 0.104
#> GSM486740 6 0.704 0.25278 0.000 0.236 0.080 0.000 0.268 0.416
#> GSM486742 2 0.347 0.50464 0.000 0.828 0.056 0.000 0.020 0.096
#> GSM486744 2 0.429 0.49291 0.000 0.764 0.088 0.000 0.024 0.124
#> GSM486746 2 0.776 -0.04051 0.016 0.344 0.136 0.000 0.204 0.300
#> GSM486748 1 0.660 0.34182 0.496 0.044 0.356 0.056 0.040 0.008
#> GSM486750 2 0.635 0.29919 0.000 0.544 0.116 0.000 0.084 0.256
#> GSM486752 1 0.698 0.07608 0.424 0.032 0.412 0.048 0.044 0.040
#> GSM486754 2 0.489 0.38813 0.000 0.680 0.044 0.000 0.044 0.232
#> GSM486756 2 0.522 0.40952 0.000 0.684 0.056 0.004 0.064 0.192
#> GSM486758 1 0.786 0.23582 0.408 0.012 0.284 0.144 0.128 0.024
#> GSM486760 1 0.266 0.72590 0.880 0.000 0.024 0.076 0.020 0.000
#> GSM486762 1 0.521 0.67098 0.700 0.004 0.100 0.156 0.036 0.004
#> GSM486764 5 0.615 0.47681 0.124 0.044 0.036 0.040 0.680 0.076
#> GSM486766 1 0.399 0.70289 0.776 0.000 0.040 0.156 0.028 0.000
#> GSM486768 2 0.793 0.13037 0.044 0.416 0.176 0.000 0.220 0.144
#> GSM486770 6 0.700 0.09927 0.000 0.344 0.080 0.000 0.192 0.384
#> GSM486772 2 0.405 0.48429 0.000 0.780 0.048 0.000 0.032 0.140
#> GSM486774 3 0.810 0.15456 0.044 0.284 0.372 0.008 0.104 0.188
#> GSM486776 1 0.311 0.71144 0.840 0.000 0.024 0.120 0.016 0.000
#> GSM486778 1 0.501 0.64970 0.680 0.000 0.032 0.212 0.076 0.000
#> GSM486780 2 0.452 0.50026 0.016 0.772 0.096 0.000 0.032 0.084
#> GSM486782 2 0.685 0.14659 0.016 0.464 0.300 0.000 0.044 0.176
#> GSM486784 2 0.237 0.51150 0.000 0.900 0.024 0.000 0.020 0.056
#> GSM486786 1 0.526 0.61452 0.656 0.000 0.052 0.228 0.064 0.000
#> GSM486788 1 0.233 0.72208 0.904 0.000 0.024 0.044 0.028 0.000
#> GSM486790 2 0.656 0.13111 0.000 0.468 0.108 0.000 0.088 0.336
#> GSM486792 1 0.635 0.02466 0.444 0.004 0.044 0.088 0.412 0.008
#> GSM486794 1 0.578 0.58877 0.608 0.000 0.088 0.240 0.064 0.000
#> GSM486796 1 0.704 0.34866 0.568 0.192 0.104 0.020 0.092 0.024
#> GSM486798 3 0.852 0.26496 0.216 0.264 0.352 0.056 0.076 0.036
#> GSM486800 1 0.195 0.71690 0.912 0.000 0.004 0.072 0.012 0.000
#> GSM486802 1 0.327 0.71945 0.848 0.000 0.032 0.072 0.048 0.000
#> GSM486804 1 0.373 0.71747 0.824 0.008 0.088 0.044 0.036 0.000
#> GSM486806 3 0.734 0.34299 0.068 0.152 0.552 0.008 0.084 0.136
#> GSM486808 1 0.426 0.69944 0.764 0.000 0.120 0.096 0.020 0.000
#> GSM486810 5 0.737 -0.27136 0.000 0.232 0.100 0.004 0.364 0.300
#> GSM486812 1 0.445 0.66281 0.716 0.000 0.044 0.216 0.024 0.000
#> GSM486814 2 0.343 0.50525 0.000 0.840 0.048 0.000 0.056 0.056
#> GSM486816 1 0.509 0.63951 0.672 0.000 0.040 0.220 0.068 0.000
#> GSM486818 1 0.826 -0.11995 0.356 0.116 0.348 0.044 0.092 0.044
#> GSM486821 5 0.768 0.31690 0.144 0.092 0.136 0.024 0.536 0.068
#> GSM486823 2 0.645 0.18457 0.000 0.516 0.092 0.000 0.104 0.288
#> GSM486826 1 0.460 0.64540 0.740 0.004 0.052 0.164 0.040 0.000
#> GSM486830 3 0.785 0.11233 0.028 0.304 0.380 0.004 0.136 0.148
#> GSM486832 1 0.370 0.72141 0.816 0.000 0.032 0.056 0.096 0.000
#> GSM486834 3 0.852 0.21028 0.232 0.076 0.404 0.044 0.176 0.068
#> GSM486836 1 0.324 0.72091 0.852 0.000 0.060 0.040 0.048 0.000
#> GSM486838 2 0.707 -0.02847 0.116 0.456 0.340 0.008 0.028 0.052
#> GSM486840 1 0.292 0.69716 0.840 0.000 0.012 0.136 0.012 0.000
#> GSM486842 1 0.270 0.72074 0.864 0.000 0.008 0.108 0.020 0.000
#> GSM486844 1 0.356 0.71038 0.840 0.004 0.072 0.036 0.044 0.004
#> GSM486846 2 0.653 0.20199 0.004 0.516 0.288 0.000 0.080 0.112
#> GSM486848 1 0.347 0.67105 0.804 0.000 0.016 0.156 0.024 0.000
#> GSM486850 2 0.497 0.50134 0.000 0.720 0.120 0.000 0.060 0.100
#> GSM486852 5 0.528 0.41092 0.256 0.000 0.024 0.040 0.652 0.028
#> GSM486854 2 0.359 0.51336 0.000 0.812 0.124 0.000 0.020 0.044
#> GSM486856 2 0.419 0.49758 0.000 0.776 0.120 0.000 0.032 0.072
#> GSM486858 2 0.627 0.23788 0.016 0.552 0.292 0.000 0.056 0.084
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> MAD:skmeans 115 1.00e+00 8.53e-06 2
#> MAD:skmeans 116 1.27e-14 4.30e-01 3
#> MAD:skmeans 90 2.19e-19 9.52e-01 4
#> MAD:skmeans 55 1.14e-12 7.66e-01 5
#> MAD:skmeans 48 3.78e-11 6.32e-01 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["MAD", "pam"]
# you can also extract it by
# res = res_list["MAD:pam"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'MAD' method.
#> Subgroups are detected by 'pam' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 3.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.139 0.445 0.698 0.4749 0.523 0.523
#> 3 3 0.420 0.690 0.827 0.3884 0.675 0.453
#> 4 4 0.486 0.558 0.713 0.1248 0.845 0.583
#> 5 5 0.604 0.613 0.785 0.0756 0.893 0.612
#> 6 6 0.682 0.638 0.808 0.0361 0.959 0.797
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 3
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 2 0.2948 0.57922 0.052 0.948
#> GSM486737 2 0.6801 0.30919 0.180 0.820
#> GSM486739 2 0.5408 0.41210 0.124 0.876
#> GSM486741 2 0.3431 0.49013 0.064 0.936
#> GSM486743 2 0.6247 0.38037 0.156 0.844
#> GSM486745 2 0.9286 0.61950 0.344 0.656
#> GSM486747 1 0.9993 -0.38178 0.516 0.484
#> GSM486749 2 0.0000 0.54159 0.000 1.000
#> GSM486751 2 0.9608 0.60270 0.384 0.616
#> GSM486753 2 0.0938 0.53398 0.012 0.988
#> GSM486755 2 0.4562 0.60432 0.096 0.904
#> GSM486757 2 0.9209 0.56644 0.336 0.664
#> GSM486759 1 0.0000 0.58569 1.000 0.000
#> GSM486761 1 0.4431 0.57732 0.908 0.092
#> GSM486763 1 0.8081 0.57617 0.752 0.248
#> GSM486765 1 0.1184 0.59212 0.984 0.016
#> GSM486767 1 0.9993 0.41811 0.516 0.484
#> GSM486769 2 0.2423 0.57169 0.040 0.960
#> GSM486771 2 0.5294 0.42377 0.120 0.880
#> GSM486773 2 0.9358 0.30980 0.352 0.648
#> GSM486775 1 0.6623 0.60066 0.828 0.172
#> GSM486777 1 0.9286 0.52352 0.656 0.344
#> GSM486779 1 0.9977 0.41862 0.528 0.472
#> GSM486781 2 0.2778 0.52501 0.048 0.952
#> GSM486783 2 0.3879 0.47633 0.076 0.924
#> GSM486785 1 0.7139 0.59541 0.804 0.196
#> GSM486787 1 0.0000 0.58569 1.000 0.000
#> GSM486789 2 0.0000 0.54159 0.000 1.000
#> GSM486791 1 0.0376 0.58531 0.996 0.004
#> GSM486793 1 0.9393 0.52151 0.644 0.356
#> GSM486795 2 0.9552 0.22466 0.376 0.624
#> GSM486797 1 0.9996 0.41342 0.512 0.488
#> GSM486799 1 0.0938 0.59180 0.988 0.012
#> GSM486801 1 0.8499 0.55988 0.724 0.276
#> GSM486803 1 0.9393 0.51598 0.644 0.356
#> GSM486805 2 0.7815 0.59753 0.232 0.768
#> GSM486807 1 0.6438 0.59515 0.836 0.164
#> GSM486809 2 0.8955 -0.05802 0.312 0.688
#> GSM486811 1 0.2423 0.59999 0.960 0.040
#> GSM486813 2 0.8813 0.00718 0.300 0.700
#> GSM486815 1 0.9248 0.03729 0.660 0.340
#> GSM486817 1 0.9850 0.47760 0.572 0.428
#> GSM486819 1 0.9491 0.50598 0.632 0.368
#> GSM486822 2 0.0376 0.54388 0.004 0.996
#> GSM486824 1 0.2043 0.59456 0.968 0.032
#> GSM486828 2 0.9988 -0.40448 0.480 0.520
#> GSM486831 1 0.7602 0.58786 0.780 0.220
#> GSM486833 2 0.9795 0.49726 0.416 0.584
#> GSM486835 1 0.1633 0.59542 0.976 0.024
#> GSM486837 2 0.9933 -0.37104 0.452 0.548
#> GSM486839 1 0.8713 0.54976 0.708 0.292
#> GSM486841 1 0.7299 0.59361 0.796 0.204
#> GSM486843 1 0.6531 0.60258 0.832 0.168
#> GSM486845 2 0.9988 -0.40189 0.480 0.520
#> GSM486847 1 0.8608 0.55493 0.716 0.284
#> GSM486849 2 0.0000 0.54159 0.000 1.000
#> GSM486851 1 0.9358 0.51996 0.648 0.352
#> GSM486853 2 0.0376 0.53940 0.004 0.996
#> GSM486855 1 0.9909 0.44451 0.556 0.444
#> GSM486857 2 0.8016 0.18551 0.244 0.756
#> GSM486736 2 0.6712 0.63760 0.176 0.824
#> GSM486738 2 0.6712 0.63506 0.176 0.824
#> GSM486740 2 0.9000 0.63960 0.316 0.684
#> GSM486742 2 0.6148 0.61927 0.152 0.848
#> GSM486744 2 0.9000 0.63870 0.316 0.684
#> GSM486746 2 0.9491 0.61244 0.368 0.632
#> GSM486748 2 0.9815 0.57819 0.420 0.580
#> GSM486750 2 0.9323 0.62450 0.348 0.652
#> GSM486752 2 0.9896 0.55881 0.440 0.560
#> GSM486754 2 0.9170 0.63279 0.332 0.668
#> GSM486756 2 0.8763 0.64184 0.296 0.704
#> GSM486758 2 0.9866 0.56730 0.432 0.568
#> GSM486760 1 0.9896 -0.39720 0.560 0.440
#> GSM486762 2 0.9896 0.55881 0.440 0.560
#> GSM486764 1 0.6438 0.43099 0.836 0.164
#> GSM486766 2 0.9944 0.54401 0.456 0.544
#> GSM486768 2 0.8608 0.61370 0.284 0.716
#> GSM486770 2 0.8713 0.64267 0.292 0.708
#> GSM486772 2 0.9954 0.53139 0.460 0.540
#> GSM486774 2 0.9000 0.63876 0.316 0.684
#> GSM486776 1 0.0000 0.58569 1.000 0.000
#> GSM486778 2 0.9963 0.53661 0.464 0.536
#> GSM486780 2 0.6247 0.62688 0.156 0.844
#> GSM486782 2 0.8763 0.64155 0.296 0.704
#> GSM486784 2 0.6048 0.62389 0.148 0.852
#> GSM486786 2 0.9970 0.52986 0.468 0.532
#> GSM486788 1 0.9993 -0.46714 0.516 0.484
#> GSM486790 2 0.8763 0.64155 0.296 0.704
#> GSM486792 1 0.9977 -0.44018 0.528 0.472
#> GSM486794 2 0.9954 0.53843 0.460 0.540
#> GSM486796 2 0.9795 0.57977 0.416 0.584
#> GSM486798 2 0.9850 0.57119 0.428 0.572
#> GSM486800 1 0.0672 0.58361 0.992 0.008
#> GSM486802 1 0.9661 -0.29124 0.608 0.392
#> GSM486804 1 0.9909 -0.40962 0.556 0.444
#> GSM486806 2 0.9522 0.61586 0.372 0.628
#> GSM486808 2 0.9909 0.55588 0.444 0.556
#> GSM486810 2 0.7815 0.64641 0.232 0.768
#> GSM486812 2 0.9970 0.53259 0.468 0.532
#> GSM486814 2 0.6148 0.50786 0.152 0.848
#> GSM486816 2 0.9922 0.55188 0.448 0.552
#> GSM486818 2 0.9775 0.58320 0.412 0.588
#> GSM486821 1 0.9248 0.16742 0.660 0.340
#> GSM486823 2 0.8608 0.64395 0.284 0.716
#> GSM486826 2 0.9970 0.53204 0.468 0.532
#> GSM486830 2 0.5737 0.62098 0.136 0.864
#> GSM486832 1 0.5294 0.47931 0.880 0.120
#> GSM486834 2 0.9850 0.57110 0.428 0.572
#> GSM486836 1 0.9129 -0.03142 0.672 0.328
#> GSM486838 2 0.9393 0.61975 0.356 0.644
#> GSM486840 1 0.9460 -0.21894 0.636 0.364
#> GSM486842 1 0.9775 -0.29135 0.588 0.412
#> GSM486844 2 0.9933 0.54711 0.452 0.548
#> GSM486846 2 0.1414 0.54565 0.020 0.980
#> GSM486848 1 0.3274 0.54690 0.940 0.060
#> GSM486850 2 0.8713 0.64652 0.292 0.708
#> GSM486852 1 0.4431 0.53205 0.908 0.092
#> GSM486854 2 0.8016 0.64763 0.244 0.756
#> GSM486856 2 0.3733 0.51244 0.072 0.928
#> GSM486858 2 0.9248 0.63054 0.340 0.660
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 2 0.4931 0.6635 0.000 0.768 0.232
#> GSM486737 2 0.0592 0.7811 0.000 0.988 0.012
#> GSM486739 2 0.0000 0.7820 0.000 1.000 0.000
#> GSM486741 2 0.0892 0.7809 0.000 0.980 0.020
#> GSM486743 2 0.2448 0.7684 0.000 0.924 0.076
#> GSM486745 3 0.5318 0.7080 0.016 0.204 0.780
#> GSM486747 3 0.5860 0.6307 0.228 0.024 0.748
#> GSM486749 2 0.4062 0.7452 0.000 0.836 0.164
#> GSM486751 3 0.1774 0.7891 0.024 0.016 0.960
#> GSM486753 2 0.0747 0.7803 0.000 0.984 0.016
#> GSM486755 2 0.4121 0.7137 0.000 0.832 0.168
#> GSM486757 3 0.6567 0.6404 0.088 0.160 0.752
#> GSM486759 1 0.1163 0.8659 0.972 0.000 0.028
#> GSM486761 1 0.3377 0.8460 0.896 0.012 0.092
#> GSM486763 1 0.4930 0.7958 0.836 0.120 0.044
#> GSM486765 1 0.2448 0.8518 0.924 0.000 0.076
#> GSM486767 2 0.4033 0.7360 0.136 0.856 0.008
#> GSM486769 2 0.3551 0.7592 0.000 0.868 0.132
#> GSM486771 2 0.0747 0.7846 0.016 0.984 0.000
#> GSM486773 2 0.7874 0.5063 0.064 0.568 0.368
#> GSM486775 1 0.0237 0.8643 0.996 0.000 0.004
#> GSM486777 1 0.3129 0.8296 0.904 0.088 0.008
#> GSM486779 2 0.7339 0.2301 0.392 0.572 0.036
#> GSM486781 2 0.5292 0.7360 0.028 0.800 0.172
#> GSM486783 2 0.0000 0.7820 0.000 1.000 0.000
#> GSM486785 1 0.0661 0.8655 0.988 0.004 0.008
#> GSM486787 1 0.0592 0.8630 0.988 0.000 0.012
#> GSM486789 2 0.0592 0.7811 0.000 0.988 0.012
#> GSM486791 1 0.2448 0.8590 0.924 0.000 0.076
#> GSM486793 1 0.5667 0.7738 0.800 0.060 0.140
#> GSM486795 2 0.9736 0.1952 0.228 0.416 0.356
#> GSM486797 1 0.9285 0.0433 0.448 0.392 0.160
#> GSM486799 1 0.0592 0.8630 0.988 0.000 0.012
#> GSM486801 1 0.3918 0.7915 0.868 0.120 0.012
#> GSM486803 1 0.3031 0.8435 0.912 0.076 0.012
#> GSM486805 3 0.7446 -0.0986 0.036 0.432 0.532
#> GSM486807 1 0.2625 0.8502 0.916 0.000 0.084
#> GSM486809 2 0.1905 0.7871 0.028 0.956 0.016
#> GSM486811 1 0.1129 0.8672 0.976 0.004 0.020
#> GSM486813 2 0.2711 0.7580 0.088 0.912 0.000
#> GSM486815 1 0.6676 -0.0401 0.516 0.008 0.476
#> GSM486817 2 0.5536 0.6153 0.236 0.752 0.012
#> GSM486819 1 0.4351 0.7619 0.828 0.168 0.004
#> GSM486822 2 0.4504 0.7304 0.000 0.804 0.196
#> GSM486824 1 0.3129 0.8535 0.904 0.008 0.088
#> GSM486828 2 0.5060 0.7446 0.100 0.836 0.064
#> GSM486831 1 0.1620 0.8631 0.964 0.024 0.012
#> GSM486833 3 0.7451 0.3097 0.060 0.304 0.636
#> GSM486835 1 0.0892 0.8665 0.980 0.000 0.020
#> GSM486837 2 0.6431 0.7217 0.084 0.760 0.156
#> GSM486839 1 0.0000 0.8643 1.000 0.000 0.000
#> GSM486841 1 0.3112 0.8500 0.916 0.056 0.028
#> GSM486843 1 0.0475 0.8662 0.992 0.004 0.004
#> GSM486845 2 0.6148 0.7323 0.076 0.776 0.148
#> GSM486847 1 0.0592 0.8630 0.988 0.000 0.012
#> GSM486849 2 0.2537 0.7811 0.000 0.920 0.080
#> GSM486851 1 0.3193 0.8272 0.896 0.100 0.004
#> GSM486853 2 0.1031 0.7864 0.000 0.976 0.024
#> GSM486855 2 0.1031 0.7850 0.024 0.976 0.000
#> GSM486857 2 0.5967 0.7080 0.032 0.752 0.216
#> GSM486736 2 0.5968 0.4362 0.000 0.636 0.364
#> GSM486738 2 0.5591 0.5246 0.000 0.696 0.304
#> GSM486740 3 0.5254 0.6521 0.000 0.264 0.736
#> GSM486742 2 0.6299 -0.0503 0.000 0.524 0.476
#> GSM486744 3 0.5016 0.6739 0.000 0.240 0.760
#> GSM486746 3 0.4399 0.7138 0.000 0.188 0.812
#> GSM486748 3 0.1711 0.7911 0.032 0.008 0.960
#> GSM486750 3 0.2066 0.7809 0.000 0.060 0.940
#> GSM486752 3 0.1289 0.7932 0.032 0.000 0.968
#> GSM486754 3 0.4452 0.7112 0.000 0.192 0.808
#> GSM486756 3 0.4974 0.6772 0.000 0.236 0.764
#> GSM486758 3 0.1163 0.7928 0.028 0.000 0.972
#> GSM486760 3 0.5098 0.7166 0.248 0.000 0.752
#> GSM486762 3 0.1529 0.7939 0.040 0.000 0.960
#> GSM486764 1 0.6761 0.5918 0.700 0.048 0.252
#> GSM486766 3 0.3816 0.7848 0.148 0.000 0.852
#> GSM486768 3 0.8608 0.3712 0.104 0.384 0.512
#> GSM486770 3 0.4555 0.7117 0.000 0.200 0.800
#> GSM486772 3 0.6836 0.6627 0.056 0.240 0.704
#> GSM486774 3 0.1031 0.7887 0.000 0.024 0.976
#> GSM486776 1 0.0592 0.8630 0.988 0.000 0.012
#> GSM486778 3 0.3267 0.7837 0.116 0.000 0.884
#> GSM486780 2 0.6047 0.4787 0.008 0.680 0.312
#> GSM486782 3 0.1163 0.7874 0.000 0.028 0.972
#> GSM486784 2 0.7337 0.1140 0.032 0.540 0.428
#> GSM486786 3 0.4002 0.7743 0.160 0.000 0.840
#> GSM486788 3 0.5397 0.6743 0.280 0.000 0.720
#> GSM486790 3 0.4346 0.7162 0.000 0.184 0.816
#> GSM486792 3 0.4974 0.7068 0.236 0.000 0.764
#> GSM486794 3 0.3412 0.7865 0.124 0.000 0.876
#> GSM486796 3 0.4443 0.7919 0.084 0.052 0.864
#> GSM486798 3 0.1163 0.7938 0.028 0.000 0.972
#> GSM486800 1 0.0747 0.8630 0.984 0.000 0.016
#> GSM486802 3 0.5968 0.5581 0.364 0.000 0.636
#> GSM486804 3 0.5465 0.6751 0.288 0.000 0.712
#> GSM486806 3 0.1482 0.7893 0.020 0.012 0.968
#> GSM486808 3 0.1753 0.7928 0.048 0.000 0.952
#> GSM486810 3 0.6209 0.4660 0.004 0.368 0.628
#> GSM486812 3 0.4002 0.7720 0.160 0.000 0.840
#> GSM486814 2 0.5174 0.7348 0.076 0.832 0.092
#> GSM486816 3 0.2959 0.7911 0.100 0.000 0.900
#> GSM486818 3 0.4660 0.7907 0.072 0.072 0.856
#> GSM486821 1 0.9687 -0.1525 0.412 0.216 0.372
#> GSM486823 3 0.2796 0.7531 0.000 0.092 0.908
#> GSM486826 3 0.3551 0.7878 0.132 0.000 0.868
#> GSM486830 2 0.6468 0.4114 0.004 0.552 0.444
#> GSM486832 1 0.4062 0.7825 0.836 0.000 0.164
#> GSM486834 3 0.1031 0.7937 0.024 0.000 0.976
#> GSM486836 3 0.6291 0.1999 0.468 0.000 0.532
#> GSM486838 3 0.1999 0.7909 0.012 0.036 0.952
#> GSM486840 3 0.6126 0.5002 0.400 0.000 0.600
#> GSM486842 3 0.5835 0.5630 0.340 0.000 0.660
#> GSM486844 3 0.3816 0.7767 0.148 0.000 0.852
#> GSM486846 2 0.4887 0.7097 0.000 0.772 0.228
#> GSM486848 1 0.3752 0.7804 0.856 0.000 0.144
#> GSM486850 3 0.3851 0.7593 0.004 0.136 0.860
#> GSM486852 1 0.4452 0.7531 0.808 0.000 0.192
#> GSM486854 3 0.5254 0.6478 0.000 0.264 0.736
#> GSM486856 2 0.2663 0.7753 0.024 0.932 0.044
#> GSM486858 3 0.0747 0.7885 0.000 0.016 0.984
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 4 0.5470 0.58599 0.000 0.168 0.100 0.732
#> GSM486737 4 0.4522 0.43720 0.000 0.320 0.000 0.680
#> GSM486739 4 0.3074 0.73044 0.000 0.152 0.000 0.848
#> GSM486741 4 0.4977 0.01779 0.000 0.460 0.000 0.540
#> GSM486743 2 0.4866 0.27792 0.000 0.596 0.000 0.404
#> GSM486745 2 0.5505 0.46501 0.008 0.744 0.164 0.084
#> GSM486747 3 0.7968 0.46793 0.320 0.212 0.456 0.012
#> GSM486749 4 0.0469 0.77475 0.000 0.000 0.012 0.988
#> GSM486751 3 0.7390 0.57277 0.088 0.320 0.556 0.036
#> GSM486753 4 0.3356 0.67173 0.000 0.176 0.000 0.824
#> GSM486755 2 0.5320 0.25544 0.000 0.572 0.012 0.416
#> GSM486757 3 0.9353 0.42091 0.140 0.256 0.424 0.180
#> GSM486759 1 0.2408 0.79995 0.896 0.000 0.104 0.000
#> GSM486761 1 0.1938 0.79087 0.936 0.012 0.052 0.000
#> GSM486763 1 0.3853 0.76955 0.848 0.016 0.020 0.116
#> GSM486765 1 0.1211 0.79312 0.960 0.000 0.040 0.000
#> GSM486767 4 0.3130 0.76616 0.040 0.052 0.012 0.896
#> GSM486769 4 0.4337 0.69909 0.000 0.140 0.052 0.808
#> GSM486771 4 0.1211 0.77085 0.000 0.040 0.000 0.960
#> GSM486773 4 0.7663 0.40386 0.128 0.044 0.248 0.580
#> GSM486775 1 0.1557 0.80459 0.944 0.000 0.056 0.000
#> GSM486777 1 0.3166 0.75444 0.868 0.000 0.016 0.116
#> GSM486779 2 0.7491 0.26392 0.232 0.500 0.000 0.268
#> GSM486781 4 0.1151 0.77453 0.000 0.024 0.008 0.968
#> GSM486783 4 0.1792 0.76593 0.000 0.068 0.000 0.932
#> GSM486785 1 0.0376 0.80145 0.992 0.000 0.004 0.004
#> GSM486787 1 0.2345 0.80088 0.900 0.000 0.100 0.000
#> GSM486789 4 0.4605 0.48320 0.000 0.336 0.000 0.664
#> GSM486791 1 0.2466 0.80986 0.900 0.000 0.096 0.004
#> GSM486793 1 0.3372 0.77188 0.868 0.000 0.096 0.036
#> GSM486795 4 0.9320 -0.01282 0.192 0.108 0.348 0.352
#> GSM486797 1 0.6101 -0.00523 0.496 0.012 0.024 0.468
#> GSM486799 1 0.2216 0.80407 0.908 0.000 0.092 0.000
#> GSM486801 1 0.6101 0.56171 0.560 0.000 0.388 0.052
#> GSM486803 1 0.2816 0.81087 0.900 0.000 0.064 0.036
#> GSM486805 4 0.8674 0.20087 0.112 0.128 0.256 0.504
#> GSM486807 1 0.1398 0.79713 0.956 0.000 0.040 0.004
#> GSM486809 4 0.4182 0.71905 0.036 0.140 0.004 0.820
#> GSM486811 1 0.4855 0.57747 0.644 0.000 0.352 0.004
#> GSM486813 4 0.1816 0.77260 0.024 0.024 0.004 0.948
#> GSM486815 1 0.7595 -0.11148 0.460 0.108 0.408 0.024
#> GSM486817 4 0.4274 0.66256 0.148 0.000 0.044 0.808
#> GSM486819 1 0.2973 0.74302 0.856 0.000 0.000 0.144
#> GSM486822 4 0.1389 0.77131 0.000 0.048 0.000 0.952
#> GSM486824 1 0.3257 0.79840 0.844 0.000 0.152 0.004
#> GSM486828 4 0.2164 0.76186 0.068 0.004 0.004 0.924
#> GSM486831 1 0.2741 0.80426 0.892 0.000 0.096 0.012
#> GSM486833 3 0.8939 0.23479 0.100 0.144 0.424 0.332
#> GSM486835 1 0.1302 0.80865 0.956 0.000 0.044 0.000
#> GSM486837 4 0.2860 0.74560 0.100 0.004 0.008 0.888
#> GSM486839 1 0.1211 0.80986 0.960 0.000 0.040 0.000
#> GSM486841 1 0.3638 0.77453 0.848 0.000 0.120 0.032
#> GSM486843 1 0.3726 0.73196 0.788 0.000 0.212 0.000
#> GSM486845 4 0.1690 0.77308 0.008 0.032 0.008 0.952
#> GSM486847 1 0.2921 0.79453 0.860 0.000 0.140 0.000
#> GSM486849 4 0.0895 0.77583 0.000 0.020 0.004 0.976
#> GSM486851 1 0.3691 0.79929 0.856 0.000 0.068 0.076
#> GSM486853 4 0.1305 0.77195 0.000 0.036 0.004 0.960
#> GSM486855 4 0.1209 0.77134 0.004 0.032 0.000 0.964
#> GSM486857 4 0.2465 0.76208 0.044 0.012 0.020 0.924
#> GSM486736 2 0.7081 0.23943 0.000 0.512 0.136 0.352
#> GSM486738 2 0.4889 0.35168 0.000 0.636 0.004 0.360
#> GSM486740 2 0.3144 0.59761 0.000 0.884 0.072 0.044
#> GSM486742 2 0.4286 0.63608 0.000 0.812 0.052 0.136
#> GSM486744 2 0.1474 0.62348 0.000 0.948 0.000 0.052
#> GSM486746 2 0.4711 0.33221 0.000 0.740 0.236 0.024
#> GSM486748 3 0.6149 0.58343 0.016 0.356 0.596 0.032
#> GSM486750 2 0.5827 -0.33920 0.000 0.532 0.436 0.032
#> GSM486752 3 0.5598 0.60001 0.004 0.332 0.636 0.028
#> GSM486754 2 0.2300 0.59056 0.000 0.920 0.064 0.016
#> GSM486756 2 0.3088 0.60908 0.000 0.888 0.060 0.052
#> GSM486758 3 0.6826 0.58975 0.060 0.324 0.588 0.028
#> GSM486760 3 0.3986 0.55724 0.132 0.032 0.832 0.004
#> GSM486762 3 0.6325 0.61974 0.056 0.248 0.668 0.028
#> GSM486764 1 0.6660 0.54673 0.628 0.112 0.252 0.008
#> GSM486766 3 0.6011 0.61542 0.124 0.172 0.700 0.004
#> GSM486768 2 0.7758 0.28282 0.032 0.508 0.340 0.120
#> GSM486770 2 0.4175 0.34194 0.000 0.776 0.212 0.012
#> GSM486772 2 0.4238 0.56890 0.000 0.796 0.176 0.028
#> GSM486774 3 0.6393 0.54185 0.008 0.384 0.556 0.052
#> GSM486776 1 0.4790 0.61250 0.620 0.000 0.380 0.000
#> GSM486778 3 0.2438 0.57179 0.048 0.012 0.924 0.016
#> GSM486780 2 0.5300 0.46201 0.000 0.664 0.028 0.308
#> GSM486782 3 0.5738 0.49874 0.000 0.432 0.540 0.028
#> GSM486784 2 0.5226 0.61143 0.000 0.756 0.116 0.128
#> GSM486786 3 0.3356 0.54507 0.176 0.000 0.824 0.000
#> GSM486788 3 0.3311 0.45789 0.172 0.000 0.828 0.000
#> GSM486790 2 0.0188 0.60862 0.000 0.996 0.004 0.000
#> GSM486792 3 0.6039 0.59659 0.148 0.136 0.708 0.008
#> GSM486794 3 0.4883 0.62314 0.048 0.136 0.796 0.020
#> GSM486796 3 0.5878 0.57918 0.024 0.360 0.604 0.012
#> GSM486798 3 0.5560 0.60248 0.004 0.324 0.644 0.028
#> GSM486800 1 0.4955 0.54202 0.556 0.000 0.444 0.000
#> GSM486802 3 0.3791 0.41644 0.200 0.004 0.796 0.000
#> GSM486804 3 0.4285 0.52391 0.156 0.040 0.804 0.000
#> GSM486806 3 0.6609 0.57075 0.040 0.360 0.572 0.028
#> GSM486808 3 0.7020 0.58131 0.108 0.304 0.576 0.012
#> GSM486810 2 0.6531 0.47627 0.000 0.636 0.204 0.160
#> GSM486812 3 0.1978 0.56581 0.068 0.000 0.928 0.004
#> GSM486814 2 0.6821 0.40421 0.000 0.592 0.152 0.256
#> GSM486816 3 0.5041 0.62381 0.044 0.188 0.760 0.008
#> GSM486818 3 0.6102 0.57011 0.024 0.364 0.592 0.020
#> GSM486821 3 0.8394 0.25825 0.240 0.168 0.524 0.068
#> GSM486823 3 0.6735 0.47384 0.000 0.388 0.516 0.096
#> GSM486826 3 0.6059 0.61779 0.064 0.288 0.644 0.004
#> GSM486830 4 0.6724 0.39694 0.000 0.164 0.224 0.612
#> GSM486832 1 0.3873 0.73870 0.772 0.000 0.228 0.000
#> GSM486834 3 0.5773 0.58755 0.004 0.352 0.612 0.032
#> GSM486836 3 0.5829 0.31227 0.268 0.044 0.676 0.012
#> GSM486838 3 0.5872 0.55108 0.000 0.384 0.576 0.040
#> GSM486840 3 0.3801 0.37182 0.220 0.000 0.780 0.000
#> GSM486842 3 0.2921 0.50091 0.140 0.000 0.860 0.000
#> GSM486844 3 0.4452 0.59427 0.052 0.124 0.816 0.008
#> GSM486846 4 0.2174 0.76037 0.000 0.052 0.020 0.928
#> GSM486848 3 0.4948 -0.32857 0.440 0.000 0.560 0.000
#> GSM486850 2 0.6426 -0.05383 0.000 0.568 0.352 0.080
#> GSM486852 1 0.5355 0.54806 0.580 0.004 0.408 0.008
#> GSM486854 2 0.2965 0.60360 0.000 0.892 0.072 0.036
#> GSM486856 2 0.4877 0.24263 0.000 0.592 0.000 0.408
#> GSM486858 3 0.5915 0.53031 0.000 0.400 0.560 0.040
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 4 0.6712 0.40767 0.000 0.256 0.160 0.552 0.032
#> GSM486737 4 0.4060 0.21426 0.000 0.360 0.000 0.640 0.000
#> GSM486739 4 0.4497 0.58327 0.000 0.248 0.008 0.716 0.028
#> GSM486741 2 0.4321 0.48157 0.000 0.600 0.004 0.396 0.000
#> GSM486743 2 0.3835 0.63403 0.000 0.744 0.012 0.244 0.000
#> GSM486745 2 0.6311 0.42865 0.008 0.572 0.320 0.068 0.032
#> GSM486747 3 0.3774 0.55016 0.296 0.000 0.704 0.000 0.000
#> GSM486749 4 0.0671 0.76634 0.000 0.000 0.016 0.980 0.004
#> GSM486751 3 0.0671 0.82215 0.016 0.000 0.980 0.004 0.000
#> GSM486753 4 0.2929 0.61755 0.000 0.180 0.000 0.820 0.000
#> GSM486755 2 0.4275 0.60656 0.000 0.696 0.020 0.284 0.000
#> GSM486757 3 0.4657 0.65506 0.108 0.000 0.740 0.152 0.000
#> GSM486759 1 0.2891 0.77982 0.824 0.000 0.000 0.000 0.176
#> GSM486761 1 0.2036 0.79751 0.920 0.000 0.024 0.000 0.056
#> GSM486763 1 0.2604 0.79134 0.896 0.012 0.000 0.072 0.020
#> GSM486765 1 0.0404 0.80562 0.988 0.000 0.000 0.000 0.012
#> GSM486767 4 0.2151 0.75581 0.040 0.020 0.000 0.924 0.016
#> GSM486769 4 0.5829 0.55378 0.000 0.212 0.096 0.660 0.032
#> GSM486771 4 0.1121 0.76256 0.000 0.044 0.000 0.956 0.000
#> GSM486773 4 0.6247 0.41603 0.116 0.008 0.324 0.548 0.004
#> GSM486775 1 0.3305 0.64714 0.776 0.000 0.000 0.000 0.224
#> GSM486777 1 0.3019 0.76727 0.864 0.000 0.000 0.088 0.048
#> GSM486779 2 0.5964 0.52388 0.180 0.588 0.000 0.232 0.000
#> GSM486781 4 0.0963 0.76737 0.000 0.000 0.036 0.964 0.000
#> GSM486783 4 0.1270 0.75679 0.000 0.052 0.000 0.948 0.000
#> GSM486785 1 0.0794 0.80999 0.972 0.000 0.000 0.000 0.028
#> GSM486787 1 0.2020 0.81363 0.900 0.000 0.000 0.000 0.100
#> GSM486789 2 0.5001 -0.10229 0.000 0.496 0.008 0.480 0.016
#> GSM486791 1 0.1704 0.82211 0.928 0.000 0.004 0.000 0.068
#> GSM486793 1 0.3536 0.72411 0.812 0.000 0.032 0.000 0.156
#> GSM486795 4 0.9013 -0.07570 0.164 0.028 0.232 0.312 0.264
#> GSM486797 1 0.5508 -0.05112 0.476 0.000 0.064 0.460 0.000
#> GSM486799 1 0.1732 0.82165 0.920 0.000 0.000 0.000 0.080
#> GSM486801 5 0.3807 0.55148 0.240 0.000 0.000 0.012 0.748
#> GSM486803 1 0.1638 0.82147 0.932 0.000 0.000 0.004 0.064
#> GSM486805 4 0.5799 0.18955 0.092 0.000 0.416 0.492 0.000
#> GSM486807 1 0.1408 0.80525 0.948 0.000 0.008 0.000 0.044
#> GSM486809 4 0.5766 0.50915 0.028 0.280 0.016 0.640 0.036
#> GSM486811 5 0.3305 0.62096 0.224 0.000 0.000 0.000 0.776
#> GSM486813 4 0.1018 0.76220 0.016 0.016 0.000 0.968 0.000
#> GSM486815 5 0.6901 0.31709 0.320 0.000 0.244 0.008 0.428
#> GSM486817 4 0.3589 0.67720 0.132 0.000 0.004 0.824 0.040
#> GSM486819 1 0.1942 0.79458 0.920 0.000 0.000 0.068 0.012
#> GSM486822 4 0.1725 0.76019 0.000 0.044 0.020 0.936 0.000
#> GSM486824 1 0.2624 0.81194 0.872 0.000 0.012 0.000 0.116
#> GSM486828 4 0.1571 0.75867 0.060 0.004 0.000 0.936 0.000
#> GSM486831 1 0.2561 0.79798 0.856 0.000 0.000 0.000 0.144
#> GSM486833 3 0.5059 0.46505 0.056 0.000 0.660 0.280 0.004
#> GSM486835 1 0.1608 0.82181 0.928 0.000 0.000 0.000 0.072
#> GSM486837 4 0.2331 0.74804 0.080 0.000 0.020 0.900 0.000
#> GSM486839 1 0.2852 0.74629 0.828 0.000 0.000 0.000 0.172
#> GSM486841 1 0.3612 0.56139 0.732 0.000 0.000 0.000 0.268
#> GSM486843 1 0.4171 0.26829 0.604 0.000 0.000 0.000 0.396
#> GSM486845 4 0.1740 0.76544 0.012 0.000 0.056 0.932 0.000
#> GSM486847 1 0.3274 0.74525 0.780 0.000 0.000 0.000 0.220
#> GSM486849 4 0.0671 0.76645 0.000 0.016 0.000 0.980 0.004
#> GSM486851 1 0.2270 0.81969 0.904 0.000 0.000 0.020 0.076
#> GSM486853 4 0.0451 0.76597 0.000 0.004 0.008 0.988 0.000
#> GSM486855 4 0.0671 0.76166 0.000 0.016 0.004 0.980 0.000
#> GSM486857 4 0.2359 0.75766 0.036 0.000 0.060 0.904 0.000
#> GSM486736 2 0.6595 0.35899 0.000 0.580 0.180 0.208 0.032
#> GSM486738 2 0.3993 0.64515 0.000 0.756 0.028 0.216 0.000
#> GSM486740 2 0.3193 0.64342 0.000 0.852 0.112 0.004 0.032
#> GSM486742 2 0.4114 0.68096 0.000 0.776 0.164 0.060 0.000
#> GSM486744 2 0.2514 0.67966 0.000 0.896 0.044 0.060 0.000
#> GSM486746 2 0.4825 0.24125 0.000 0.568 0.408 0.000 0.024
#> GSM486748 3 0.0451 0.82294 0.004 0.000 0.988 0.000 0.008
#> GSM486750 3 0.3456 0.66243 0.000 0.184 0.800 0.016 0.000
#> GSM486752 3 0.0671 0.82156 0.004 0.000 0.980 0.000 0.016
#> GSM486754 2 0.3196 0.65860 0.000 0.804 0.192 0.004 0.000
#> GSM486756 2 0.4497 0.65601 0.000 0.732 0.208 0.060 0.000
#> GSM486758 3 0.0693 0.82331 0.012 0.008 0.980 0.000 0.000
#> GSM486760 5 0.3621 0.65552 0.020 0.000 0.192 0.000 0.788
#> GSM486762 3 0.2843 0.72252 0.008 0.000 0.848 0.000 0.144
#> GSM486764 1 0.6539 0.50248 0.588 0.032 0.176 0.000 0.204
#> GSM486766 5 0.5548 0.10935 0.068 0.000 0.440 0.000 0.492
#> GSM486768 2 0.7538 0.02713 0.000 0.396 0.148 0.076 0.380
#> GSM486770 2 0.5212 0.34400 0.000 0.620 0.332 0.016 0.032
#> GSM486772 2 0.4038 0.64216 0.000 0.808 0.032 0.028 0.132
#> GSM486774 3 0.0579 0.82317 0.000 0.008 0.984 0.008 0.000
#> GSM486776 5 0.3039 0.58625 0.192 0.000 0.000 0.000 0.808
#> GSM486778 5 0.2930 0.68426 0.004 0.000 0.164 0.000 0.832
#> GSM486780 2 0.4468 0.64871 0.000 0.728 0.040 0.228 0.004
#> GSM486782 3 0.0963 0.81801 0.000 0.036 0.964 0.000 0.000
#> GSM486784 2 0.4605 0.69124 0.000 0.780 0.124 0.060 0.036
#> GSM486786 5 0.3971 0.68736 0.100 0.000 0.100 0.000 0.800
#> GSM486788 5 0.1364 0.72283 0.012 0.000 0.036 0.000 0.952
#> GSM486790 2 0.1408 0.67004 0.000 0.948 0.044 0.000 0.008
#> GSM486792 3 0.5604 -0.10919 0.072 0.000 0.468 0.000 0.460
#> GSM486794 5 0.4538 0.23956 0.008 0.000 0.452 0.000 0.540
#> GSM486796 3 0.3278 0.71587 0.000 0.020 0.824 0.000 0.156
#> GSM486798 3 0.0771 0.82221 0.000 0.004 0.976 0.000 0.020
#> GSM486800 5 0.0963 0.70803 0.036 0.000 0.000 0.000 0.964
#> GSM486802 5 0.2903 0.70963 0.080 0.000 0.048 0.000 0.872
#> GSM486804 5 0.2625 0.72368 0.016 0.000 0.108 0.000 0.876
#> GSM486806 3 0.0451 0.82331 0.000 0.004 0.988 0.000 0.008
#> GSM486808 3 0.2248 0.78480 0.088 0.000 0.900 0.000 0.012
#> GSM486810 2 0.6700 0.29889 0.000 0.460 0.380 0.140 0.020
#> GSM486812 5 0.2825 0.71287 0.016 0.000 0.124 0.000 0.860
#> GSM486814 2 0.4986 0.65337 0.000 0.736 0.020 0.164 0.080
#> GSM486816 5 0.4562 -0.00406 0.008 0.000 0.496 0.000 0.496
#> GSM486818 3 0.3602 0.70245 0.000 0.024 0.796 0.000 0.180
#> GSM486821 5 0.8094 0.47475 0.156 0.100 0.168 0.048 0.528
#> GSM486823 3 0.3787 0.72642 0.000 0.120 0.820 0.052 0.008
#> GSM486826 3 0.4003 0.54366 0.008 0.000 0.704 0.000 0.288
#> GSM486830 4 0.6550 0.36126 0.000 0.136 0.356 0.492 0.016
#> GSM486832 1 0.3608 0.78208 0.812 0.000 0.040 0.000 0.148
#> GSM486834 3 0.0566 0.82262 0.004 0.000 0.984 0.000 0.012
#> GSM486836 5 0.4577 0.66117 0.108 0.000 0.144 0.000 0.748
#> GSM486838 3 0.1082 0.81982 0.000 0.028 0.964 0.000 0.008
#> GSM486840 5 0.0992 0.71813 0.008 0.000 0.024 0.000 0.968
#> GSM486842 5 0.1965 0.72643 0.024 0.000 0.052 0.000 0.924
#> GSM486844 5 0.4201 0.32901 0.000 0.000 0.408 0.000 0.592
#> GSM486846 4 0.1851 0.75373 0.000 0.000 0.088 0.912 0.000
#> GSM486848 5 0.0963 0.70747 0.036 0.000 0.000 0.000 0.964
#> GSM486850 3 0.5378 0.38773 0.000 0.284 0.648 0.044 0.024
#> GSM486852 5 0.6045 0.08651 0.400 0.004 0.104 0.000 0.492
#> GSM486854 2 0.3890 0.62081 0.000 0.736 0.252 0.012 0.000
#> GSM486856 2 0.3783 0.61843 0.000 0.740 0.008 0.252 0.000
#> GSM486858 3 0.0579 0.82322 0.000 0.008 0.984 0.008 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 6 0.1901 0.6618 0.000 0.004 0.008 0.076 0.000 0.912
#> GSM486737 4 0.3955 0.2758 0.000 0.384 0.000 0.608 0.000 0.008
#> GSM486739 6 0.4508 0.3621 0.000 0.036 0.000 0.396 0.000 0.568
#> GSM486741 2 0.3694 0.7286 0.000 0.784 0.000 0.140 0.000 0.076
#> GSM486743 2 0.1267 0.8598 0.000 0.940 0.000 0.060 0.000 0.000
#> GSM486745 6 0.6497 0.4607 0.000 0.256 0.128 0.076 0.004 0.536
#> GSM486747 3 0.4127 0.5260 0.000 0.000 0.684 0.004 0.284 0.028
#> GSM486749 4 0.1806 0.7270 0.000 0.000 0.004 0.908 0.000 0.088
#> GSM486751 3 0.0146 0.8257 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM486753 4 0.3806 0.5951 0.000 0.164 0.000 0.768 0.000 0.068
#> GSM486755 2 0.2100 0.8246 0.000 0.884 0.000 0.112 0.000 0.004
#> GSM486757 3 0.4347 0.6523 0.000 0.000 0.744 0.152 0.092 0.012
#> GSM486759 5 0.2805 0.7733 0.184 0.000 0.004 0.000 0.812 0.000
#> GSM486761 5 0.2886 0.7884 0.060 0.000 0.032 0.004 0.876 0.028
#> GSM486763 5 0.2119 0.7992 0.008 0.004 0.000 0.060 0.912 0.016
#> GSM486765 5 0.1457 0.8038 0.016 0.000 0.004 0.004 0.948 0.028
#> GSM486767 4 0.1887 0.7519 0.016 0.012 0.000 0.924 0.048 0.000
#> GSM486769 6 0.1700 0.6509 0.000 0.004 0.000 0.080 0.000 0.916
#> GSM486771 4 0.2250 0.7430 0.000 0.064 0.000 0.896 0.000 0.040
#> GSM486773 4 0.6442 0.4008 0.004 0.000 0.284 0.528 0.104 0.080
#> GSM486775 5 0.3259 0.6573 0.216 0.000 0.000 0.000 0.772 0.012
#> GSM486777 5 0.3287 0.7801 0.056 0.000 0.004 0.060 0.852 0.028
#> GSM486779 2 0.4613 0.6071 0.000 0.696 0.000 0.200 0.100 0.004
#> GSM486781 4 0.1333 0.7658 0.000 0.000 0.048 0.944 0.008 0.000
#> GSM486783 4 0.1588 0.7540 0.000 0.072 0.000 0.924 0.000 0.004
#> GSM486785 5 0.1546 0.8089 0.028 0.000 0.004 0.004 0.944 0.020
#> GSM486787 5 0.1610 0.8133 0.084 0.000 0.000 0.000 0.916 0.000
#> GSM486789 6 0.5896 0.4058 0.000 0.220 0.000 0.324 0.000 0.456
#> GSM486791 5 0.1349 0.8207 0.056 0.000 0.000 0.000 0.940 0.004
#> GSM486793 5 0.3887 0.7236 0.152 0.000 0.028 0.004 0.788 0.028
#> GSM486795 4 0.8130 -0.0939 0.276 0.028 0.224 0.296 0.176 0.000
#> GSM486797 5 0.5402 -0.0146 0.000 0.000 0.052 0.448 0.472 0.028
#> GSM486799 5 0.1444 0.8201 0.072 0.000 0.000 0.000 0.928 0.000
#> GSM486801 1 0.3314 0.5269 0.740 0.000 0.000 0.004 0.256 0.000
#> GSM486803 5 0.1267 0.8192 0.060 0.000 0.000 0.000 0.940 0.000
#> GSM486805 4 0.5684 0.1932 0.000 0.000 0.404 0.488 0.080 0.028
#> GSM486807 5 0.2067 0.8004 0.048 0.000 0.004 0.004 0.916 0.028
#> GSM486809 6 0.2048 0.6520 0.000 0.000 0.000 0.120 0.000 0.880
#> GSM486811 1 0.3526 0.6248 0.792 0.000 0.004 0.004 0.172 0.028
#> GSM486813 4 0.0547 0.7603 0.000 0.000 0.000 0.980 0.020 0.000
#> GSM486815 1 0.6758 0.3381 0.444 0.000 0.236 0.012 0.280 0.028
#> GSM486817 4 0.3676 0.6587 0.052 0.000 0.004 0.796 0.144 0.004
#> GSM486819 5 0.1732 0.7946 0.004 0.000 0.004 0.072 0.920 0.000
#> GSM486822 4 0.3109 0.6385 0.000 0.004 0.000 0.772 0.000 0.224
#> GSM486824 5 0.2311 0.8115 0.104 0.000 0.016 0.000 0.880 0.000
#> GSM486828 4 0.1728 0.7538 0.000 0.000 0.008 0.924 0.064 0.004
#> GSM486831 5 0.2340 0.7925 0.148 0.000 0.000 0.000 0.852 0.000
#> GSM486833 3 0.4487 0.4616 0.004 0.000 0.672 0.276 0.044 0.004
#> GSM486835 5 0.1913 0.8215 0.060 0.000 0.004 0.004 0.920 0.012
#> GSM486837 4 0.2456 0.7439 0.000 0.000 0.028 0.888 0.076 0.008
#> GSM486839 5 0.2632 0.7527 0.164 0.000 0.000 0.000 0.832 0.004
#> GSM486841 5 0.4072 0.5117 0.292 0.000 0.004 0.004 0.684 0.016
#> GSM486843 5 0.3717 0.3044 0.384 0.000 0.000 0.000 0.616 0.000
#> GSM486845 4 0.1707 0.7651 0.000 0.000 0.056 0.928 0.012 0.004
#> GSM486847 5 0.3023 0.7505 0.212 0.000 0.004 0.000 0.784 0.000
#> GSM486849 4 0.1333 0.7577 0.000 0.048 0.000 0.944 0.000 0.008
#> GSM486851 5 0.2036 0.8181 0.064 0.000 0.000 0.008 0.912 0.016
#> GSM486853 4 0.1307 0.7605 0.000 0.008 0.008 0.952 0.000 0.032
#> GSM486855 4 0.0146 0.7584 0.000 0.000 0.000 0.996 0.000 0.004
#> GSM486857 4 0.2237 0.7574 0.000 0.000 0.068 0.896 0.036 0.000
#> GSM486736 6 0.1010 0.6542 0.000 0.036 0.000 0.004 0.000 0.960
#> GSM486738 2 0.0146 0.8621 0.000 0.996 0.000 0.004 0.000 0.000
#> GSM486740 6 0.3620 0.4377 0.000 0.352 0.000 0.000 0.000 0.648
#> GSM486742 2 0.1556 0.8298 0.000 0.920 0.000 0.000 0.000 0.080
#> GSM486744 2 0.1285 0.8617 0.000 0.944 0.000 0.052 0.000 0.004
#> GSM486746 6 0.6029 0.3194 0.000 0.324 0.260 0.000 0.000 0.416
#> GSM486748 3 0.0146 0.8257 0.000 0.000 0.996 0.004 0.000 0.000
#> GSM486750 3 0.4569 0.5926 0.000 0.096 0.700 0.004 0.000 0.200
#> GSM486752 3 0.0146 0.8256 0.004 0.000 0.996 0.000 0.000 0.000
#> GSM486754 2 0.0146 0.8617 0.000 0.996 0.004 0.000 0.000 0.000
#> GSM486756 2 0.1398 0.8607 0.000 0.940 0.008 0.052 0.000 0.000
#> GSM486758 3 0.0000 0.8255 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM486760 1 0.3017 0.6698 0.816 0.000 0.164 0.000 0.020 0.000
#> GSM486762 3 0.2219 0.7206 0.136 0.000 0.864 0.000 0.000 0.000
#> GSM486764 5 0.6201 0.4955 0.204 0.012 0.176 0.000 0.576 0.032
#> GSM486766 1 0.5091 0.1949 0.516 0.000 0.424 0.000 0.040 0.020
#> GSM486768 6 0.8004 0.3387 0.272 0.216 0.104 0.048 0.000 0.360
#> GSM486770 6 0.1682 0.6537 0.000 0.052 0.020 0.000 0.000 0.928
#> GSM486772 2 0.6094 0.1410 0.084 0.560 0.012 0.048 0.000 0.296
#> GSM486774 3 0.0260 0.8256 0.000 0.000 0.992 0.008 0.000 0.000
#> GSM486776 1 0.2697 0.5778 0.812 0.000 0.000 0.000 0.188 0.000
#> GSM486778 1 0.2260 0.6586 0.860 0.000 0.140 0.000 0.000 0.000
#> GSM486780 2 0.1141 0.8621 0.000 0.948 0.000 0.052 0.000 0.000
#> GSM486782 3 0.0790 0.8191 0.000 0.032 0.968 0.000 0.000 0.000
#> GSM486784 2 0.0000 0.8610 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486786 1 0.3687 0.6495 0.824 0.000 0.072 0.004 0.072 0.028
#> GSM486788 1 0.0622 0.6976 0.980 0.000 0.012 0.000 0.008 0.000
#> GSM486790 2 0.3323 0.6070 0.000 0.752 0.008 0.000 0.000 0.240
#> GSM486792 1 0.4941 0.1651 0.492 0.000 0.444 0.000 0.064 0.000
#> GSM486794 1 0.3833 0.2929 0.556 0.000 0.444 0.000 0.000 0.000
#> GSM486796 3 0.2821 0.7120 0.152 0.016 0.832 0.000 0.000 0.000
#> GSM486798 3 0.0405 0.8257 0.008 0.004 0.988 0.000 0.000 0.000
#> GSM486800 1 0.0000 0.6928 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486802 1 0.2361 0.6848 0.884 0.000 0.028 0.000 0.088 0.000
#> GSM486804 1 0.2214 0.6965 0.888 0.000 0.096 0.000 0.016 0.000
#> GSM486806 3 0.0291 0.8256 0.004 0.000 0.992 0.004 0.000 0.000
#> GSM486808 3 0.2432 0.7688 0.004 0.000 0.892 0.004 0.072 0.028
#> GSM486810 6 0.6991 0.2287 0.000 0.180 0.300 0.092 0.000 0.428
#> GSM486812 1 0.2250 0.6962 0.888 0.000 0.092 0.000 0.020 0.000
#> GSM486814 2 0.0547 0.8600 0.000 0.980 0.000 0.020 0.000 0.000
#> GSM486816 1 0.3862 0.1091 0.524 0.000 0.476 0.000 0.000 0.000
#> GSM486818 3 0.3202 0.6977 0.176 0.024 0.800 0.000 0.000 0.000
#> GSM486821 1 0.7866 0.4026 0.520 0.072 0.152 0.048 0.152 0.056
#> GSM486823 3 0.4376 0.4143 0.000 0.004 0.604 0.024 0.000 0.368
#> GSM486826 3 0.3351 0.5371 0.288 0.000 0.712 0.000 0.000 0.000
#> GSM486830 4 0.6034 0.1259 0.004 0.000 0.340 0.440 0.000 0.216
#> GSM486832 5 0.3176 0.7810 0.156 0.000 0.032 0.000 0.812 0.000
#> GSM486834 3 0.0146 0.8256 0.004 0.000 0.996 0.000 0.000 0.000
#> GSM486836 1 0.4104 0.6407 0.748 0.000 0.148 0.000 0.104 0.000
#> GSM486838 3 0.1116 0.8185 0.008 0.028 0.960 0.004 0.000 0.000
#> GSM486840 1 0.0000 0.6928 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486842 1 0.1049 0.7011 0.960 0.000 0.032 0.000 0.008 0.000
#> GSM486844 1 0.3782 0.3131 0.588 0.000 0.412 0.000 0.000 0.000
#> GSM486846 4 0.1957 0.7414 0.000 0.000 0.112 0.888 0.000 0.000
#> GSM486848 1 0.0260 0.6939 0.992 0.000 0.000 0.000 0.008 0.000
#> GSM486850 3 0.5622 0.2965 0.016 0.356 0.540 0.080 0.000 0.008
#> GSM486852 1 0.6014 0.0396 0.468 0.000 0.104 0.000 0.392 0.036
#> GSM486854 2 0.0858 0.8531 0.000 0.968 0.028 0.000 0.000 0.004
#> GSM486856 2 0.0632 0.8669 0.000 0.976 0.000 0.024 0.000 0.000
#> GSM486858 3 0.0405 0.8258 0.000 0.008 0.988 0.004 0.000 0.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> MAD:pam 87 1.84e-07 0.23763 2
#> MAD:pam 105 3.58e-13 0.46516 3
#> MAD:pam 85 4.15e-13 0.44250 4
#> MAD:pam 94 2.01e-11 0.16174 5
#> MAD:pam 93 6.14e-10 0.00515 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["MAD", "mclust"]
# you can also extract it by
# res = res_list["MAD:mclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'MAD' method.
#> Subgroups are detected by 'mclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.508 0.921 0.924 0.5036 0.496 0.496
#> 3 3 0.581 0.659 0.824 0.1838 0.992 0.983
#> 4 4 0.667 0.858 0.857 0.2379 0.748 0.488
#> 5 5 0.697 0.677 0.834 0.0561 0.904 0.655
#> 6 6 0.720 0.710 0.814 0.0367 0.938 0.741
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 1 0.5629 0.921 0.868 0.132
#> GSM486737 1 0.0376 0.923 0.996 0.004
#> GSM486739 1 0.0376 0.923 0.996 0.004
#> GSM486741 1 0.4161 0.925 0.916 0.084
#> GSM486743 1 0.0376 0.923 0.996 0.004
#> GSM486745 1 0.0376 0.923 0.996 0.004
#> GSM486747 1 0.5842 0.921 0.860 0.140
#> GSM486749 1 0.5629 0.921 0.868 0.132
#> GSM486751 1 0.5842 0.921 0.860 0.140
#> GSM486753 1 0.0376 0.923 0.996 0.004
#> GSM486755 1 0.0376 0.923 0.996 0.004
#> GSM486757 1 0.5842 0.921 0.860 0.140
#> GSM486759 1 0.0672 0.922 0.992 0.008
#> GSM486761 1 0.5737 0.921 0.864 0.136
#> GSM486763 1 0.0376 0.923 0.996 0.004
#> GSM486765 1 0.5737 0.921 0.864 0.136
#> GSM486767 1 0.0376 0.923 0.996 0.004
#> GSM486769 1 0.5629 0.921 0.868 0.132
#> GSM486771 1 0.0376 0.923 0.996 0.004
#> GSM486773 1 0.5629 0.921 0.868 0.132
#> GSM486775 1 0.0672 0.922 0.992 0.008
#> GSM486777 1 0.5737 0.921 0.864 0.136
#> GSM486779 1 0.0376 0.923 0.996 0.004
#> GSM486781 1 0.5629 0.921 0.868 0.132
#> GSM486783 1 0.0376 0.923 0.996 0.004
#> GSM486785 1 0.5737 0.921 0.864 0.136
#> GSM486787 1 0.0672 0.922 0.992 0.008
#> GSM486789 1 0.5629 0.921 0.868 0.132
#> GSM486791 1 0.0672 0.922 0.992 0.008
#> GSM486793 1 0.5737 0.921 0.864 0.136
#> GSM486795 1 0.0938 0.923 0.988 0.012
#> GSM486797 1 0.5842 0.921 0.860 0.140
#> GSM486799 1 0.0672 0.922 0.992 0.008
#> GSM486801 1 0.0672 0.922 0.992 0.008
#> GSM486803 1 0.0672 0.922 0.992 0.008
#> GSM486805 1 0.5629 0.921 0.868 0.132
#> GSM486807 1 0.5737 0.921 0.864 0.136
#> GSM486809 1 0.5629 0.921 0.868 0.132
#> GSM486811 1 0.5737 0.921 0.864 0.136
#> GSM486813 1 0.0376 0.923 0.996 0.004
#> GSM486815 1 0.5737 0.921 0.864 0.136
#> GSM486817 1 0.0938 0.923 0.988 0.012
#> GSM486819 1 0.0938 0.923 0.988 0.012
#> GSM486822 1 0.5629 0.921 0.868 0.132
#> GSM486824 1 0.0672 0.922 0.992 0.008
#> GSM486828 1 0.5629 0.921 0.868 0.132
#> GSM486831 1 0.0672 0.922 0.992 0.008
#> GSM486833 1 0.5842 0.921 0.860 0.140
#> GSM486835 1 0.0672 0.922 0.992 0.008
#> GSM486837 1 0.5629 0.921 0.868 0.132
#> GSM486839 1 0.0672 0.922 0.992 0.008
#> GSM486841 1 0.5737 0.921 0.864 0.136
#> GSM486843 1 0.0672 0.922 0.992 0.008
#> GSM486845 1 0.5629 0.921 0.868 0.132
#> GSM486847 1 0.0672 0.922 0.992 0.008
#> GSM486849 1 0.5629 0.921 0.868 0.132
#> GSM486851 1 0.0938 0.923 0.988 0.012
#> GSM486853 1 0.5629 0.921 0.868 0.132
#> GSM486855 1 0.0376 0.923 0.996 0.004
#> GSM486857 1 0.5629 0.921 0.868 0.132
#> GSM486736 2 0.1633 0.914 0.024 0.976
#> GSM486738 2 0.5842 0.923 0.140 0.860
#> GSM486740 2 0.5946 0.921 0.144 0.856
#> GSM486742 2 0.5059 0.926 0.112 0.888
#> GSM486744 2 0.5842 0.923 0.140 0.860
#> GSM486746 2 0.5842 0.923 0.140 0.860
#> GSM486748 2 0.0376 0.920 0.004 0.996
#> GSM486750 2 0.0938 0.920 0.012 0.988
#> GSM486752 2 0.0376 0.920 0.004 0.996
#> GSM486754 2 0.5842 0.923 0.140 0.860
#> GSM486756 2 0.5842 0.923 0.140 0.860
#> GSM486758 2 0.0376 0.920 0.004 0.996
#> GSM486760 2 0.5629 0.922 0.132 0.868
#> GSM486762 2 0.0376 0.919 0.004 0.996
#> GSM486764 2 0.5842 0.919 0.140 0.860
#> GSM486766 2 0.0376 0.919 0.004 0.996
#> GSM486768 2 0.5842 0.923 0.140 0.860
#> GSM486770 2 0.0938 0.920 0.012 0.988
#> GSM486772 2 0.5842 0.923 0.140 0.860
#> GSM486774 2 0.0938 0.920 0.012 0.988
#> GSM486776 2 0.5629 0.922 0.132 0.868
#> GSM486778 2 0.0672 0.920 0.008 0.992
#> GSM486780 2 0.5842 0.923 0.140 0.860
#> GSM486782 2 0.0938 0.920 0.012 0.988
#> GSM486784 2 0.5842 0.923 0.140 0.860
#> GSM486786 2 0.0376 0.919 0.004 0.996
#> GSM486788 2 0.5629 0.922 0.132 0.868
#> GSM486790 2 0.0938 0.920 0.012 0.988
#> GSM486792 2 0.4562 0.926 0.096 0.904
#> GSM486794 2 0.0672 0.920 0.008 0.992
#> GSM486796 2 0.5629 0.922 0.132 0.868
#> GSM486798 2 0.0376 0.920 0.004 0.996
#> GSM486800 2 0.5629 0.922 0.132 0.868
#> GSM486802 2 0.5629 0.922 0.132 0.868
#> GSM486804 2 0.5629 0.922 0.132 0.868
#> GSM486806 2 0.0938 0.920 0.012 0.988
#> GSM486808 2 0.0376 0.919 0.004 0.996
#> GSM486810 2 0.0938 0.920 0.012 0.988
#> GSM486812 2 0.0376 0.919 0.004 0.996
#> GSM486814 2 0.5842 0.923 0.140 0.860
#> GSM486816 2 0.0376 0.919 0.004 0.996
#> GSM486818 2 0.5629 0.922 0.132 0.868
#> GSM486821 2 0.5629 0.922 0.132 0.868
#> GSM486823 2 0.0938 0.920 0.012 0.988
#> GSM486826 2 0.5737 0.922 0.136 0.864
#> GSM486830 2 0.0938 0.920 0.012 0.988
#> GSM486832 2 0.5629 0.922 0.132 0.868
#> GSM486834 2 0.0376 0.920 0.004 0.996
#> GSM486836 2 0.5629 0.922 0.132 0.868
#> GSM486838 2 0.1184 0.921 0.016 0.984
#> GSM486840 2 0.5629 0.922 0.132 0.868
#> GSM486842 2 0.0376 0.919 0.004 0.996
#> GSM486844 2 0.5629 0.922 0.132 0.868
#> GSM486846 2 0.0938 0.920 0.012 0.988
#> GSM486848 2 0.5629 0.922 0.132 0.868
#> GSM486850 2 0.0938 0.920 0.012 0.988
#> GSM486852 2 0.5737 0.921 0.136 0.864
#> GSM486854 2 0.0938 0.920 0.012 0.988
#> GSM486856 2 0.5842 0.923 0.140 0.860
#> GSM486858 2 0.0938 0.920 0.012 0.988
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 1 0.8190 -0.900 0.496 0.432 0.072
#> GSM486737 1 0.1129 0.681 0.976 0.020 0.004
#> GSM486739 1 0.6104 -0.513 0.648 0.348 0.004
#> GSM486741 1 0.3134 0.684 0.916 0.032 0.052
#> GSM486743 1 0.1129 0.681 0.976 0.020 0.004
#> GSM486745 1 0.1878 0.666 0.952 0.044 0.004
#> GSM486747 1 0.4269 0.673 0.872 0.052 0.076
#> GSM486749 1 0.4379 0.661 0.868 0.060 0.072
#> GSM486751 1 0.4658 0.672 0.856 0.068 0.076
#> GSM486753 1 0.1129 0.681 0.976 0.020 0.004
#> GSM486755 1 0.2200 0.653 0.940 0.056 0.004
#> GSM486757 1 0.5331 0.653 0.824 0.100 0.076
#> GSM486759 1 0.3879 0.648 0.848 0.152 0.000
#> GSM486761 1 0.6543 0.631 0.748 0.176 0.076
#> GSM486763 1 0.6081 -0.463 0.652 0.344 0.004
#> GSM486765 1 0.6435 0.638 0.756 0.168 0.076
#> GSM486767 1 0.1765 0.670 0.956 0.040 0.004
#> GSM486769 2 0.8210 0.000 0.460 0.468 0.072
#> GSM486771 1 0.1129 0.681 0.976 0.020 0.004
#> GSM486773 1 0.4838 0.670 0.848 0.076 0.076
#> GSM486775 1 0.3715 0.664 0.868 0.128 0.004
#> GSM486777 1 0.6746 0.614 0.732 0.192 0.076
#> GSM486779 1 0.1129 0.681 0.976 0.020 0.004
#> GSM486781 1 0.4370 0.661 0.868 0.056 0.076
#> GSM486783 1 0.1129 0.681 0.976 0.020 0.004
#> GSM486785 1 0.6646 0.624 0.740 0.184 0.076
#> GSM486787 1 0.3619 0.660 0.864 0.136 0.000
#> GSM486789 1 0.6122 0.501 0.776 0.152 0.072
#> GSM486791 1 0.6180 -0.495 0.660 0.332 0.008
#> GSM486793 1 0.6595 0.627 0.744 0.180 0.076
#> GSM486795 1 0.0829 0.689 0.984 0.012 0.004
#> GSM486797 1 0.4838 0.671 0.848 0.076 0.076
#> GSM486799 1 0.3752 0.653 0.856 0.144 0.000
#> GSM486801 1 0.3752 0.653 0.856 0.144 0.000
#> GSM486803 1 0.3816 0.654 0.852 0.148 0.000
#> GSM486805 1 0.4925 0.670 0.844 0.080 0.076
#> GSM486807 1 0.6380 0.642 0.760 0.164 0.076
#> GSM486809 1 0.8117 -0.707 0.552 0.372 0.076
#> GSM486811 1 0.6148 0.657 0.776 0.148 0.076
#> GSM486813 1 0.1129 0.681 0.976 0.020 0.004
#> GSM486815 1 0.6324 0.645 0.764 0.160 0.076
#> GSM486817 1 0.1267 0.691 0.972 0.024 0.004
#> GSM486819 1 0.1129 0.690 0.976 0.020 0.004
#> GSM486822 1 0.5004 0.628 0.840 0.088 0.072
#> GSM486824 1 0.3425 0.670 0.884 0.112 0.004
#> GSM486828 1 0.4370 0.661 0.868 0.056 0.076
#> GSM486831 1 0.3784 0.660 0.864 0.132 0.004
#> GSM486833 1 0.4469 0.670 0.864 0.060 0.076
#> GSM486835 1 0.3412 0.663 0.876 0.124 0.000
#> GSM486837 1 0.4475 0.667 0.864 0.064 0.072
#> GSM486839 1 0.4062 0.639 0.836 0.164 0.000
#> GSM486841 1 0.6595 0.629 0.744 0.180 0.076
#> GSM486843 1 0.3816 0.655 0.852 0.148 0.000
#> GSM486845 1 0.4370 0.661 0.868 0.056 0.076
#> GSM486847 1 0.4002 0.642 0.840 0.160 0.000
#> GSM486849 1 0.4075 0.668 0.880 0.048 0.072
#> GSM486851 1 0.6081 -0.475 0.652 0.344 0.004
#> GSM486853 1 0.4475 0.658 0.864 0.064 0.072
#> GSM486855 1 0.1267 0.681 0.972 0.024 0.004
#> GSM486857 1 0.4379 0.664 0.868 0.060 0.072
#> GSM486736 3 0.7186 0.207 0.024 0.476 0.500
#> GSM486738 3 0.3933 0.846 0.028 0.092 0.880
#> GSM486740 3 0.7582 0.528 0.048 0.380 0.572
#> GSM486742 3 0.3031 0.852 0.012 0.076 0.912
#> GSM486744 3 0.3765 0.847 0.028 0.084 0.888
#> GSM486746 3 0.3637 0.848 0.024 0.084 0.892
#> GSM486748 3 0.1878 0.848 0.004 0.044 0.952
#> GSM486750 3 0.1315 0.846 0.008 0.020 0.972
#> GSM486752 3 0.1129 0.845 0.004 0.020 0.976
#> GSM486754 3 0.3933 0.845 0.028 0.092 0.880
#> GSM486756 3 0.3933 0.845 0.028 0.092 0.880
#> GSM486758 3 0.1399 0.847 0.004 0.028 0.968
#> GSM486760 3 0.5365 0.821 0.004 0.252 0.744
#> GSM486762 3 0.4293 0.822 0.004 0.164 0.832
#> GSM486764 3 0.8034 0.467 0.068 0.392 0.540
#> GSM486766 3 0.4409 0.819 0.004 0.172 0.824
#> GSM486768 3 0.3461 0.848 0.024 0.076 0.900
#> GSM486770 3 0.6577 0.375 0.008 0.420 0.572
#> GSM486772 3 0.3850 0.846 0.028 0.088 0.884
#> GSM486774 3 0.0983 0.846 0.004 0.016 0.980
#> GSM486776 3 0.5291 0.815 0.000 0.268 0.732
#> GSM486778 3 0.4351 0.821 0.004 0.168 0.828
#> GSM486780 3 0.3850 0.846 0.028 0.088 0.884
#> GSM486782 3 0.0983 0.846 0.004 0.016 0.980
#> GSM486784 3 0.3850 0.846 0.028 0.088 0.884
#> GSM486786 3 0.4351 0.821 0.004 0.168 0.828
#> GSM486788 3 0.5216 0.819 0.000 0.260 0.740
#> GSM486790 3 0.1015 0.850 0.008 0.012 0.980
#> GSM486792 3 0.6793 0.551 0.012 0.452 0.536
#> GSM486794 3 0.4293 0.823 0.004 0.164 0.832
#> GSM486796 3 0.3722 0.849 0.024 0.088 0.888
#> GSM486798 3 0.0983 0.846 0.004 0.016 0.980
#> GSM486800 3 0.5480 0.815 0.004 0.264 0.732
#> GSM486802 3 0.5178 0.820 0.000 0.256 0.744
#> GSM486804 3 0.5254 0.816 0.000 0.264 0.736
#> GSM486806 3 0.0983 0.846 0.004 0.016 0.980
#> GSM486808 3 0.4521 0.816 0.004 0.180 0.816
#> GSM486810 3 0.4575 0.735 0.004 0.184 0.812
#> GSM486812 3 0.4351 0.821 0.004 0.168 0.828
#> GSM486814 3 0.3765 0.847 0.028 0.084 0.888
#> GSM486816 3 0.4351 0.821 0.004 0.168 0.828
#> GSM486818 3 0.3461 0.848 0.024 0.076 0.900
#> GSM486821 3 0.3678 0.847 0.028 0.080 0.892
#> GSM486823 3 0.1950 0.841 0.008 0.040 0.952
#> GSM486826 3 0.5178 0.822 0.000 0.256 0.744
#> GSM486830 3 0.0983 0.846 0.004 0.016 0.980
#> GSM486832 3 0.5580 0.817 0.008 0.256 0.736
#> GSM486834 3 0.1129 0.845 0.004 0.020 0.976
#> GSM486836 3 0.5291 0.815 0.000 0.268 0.732
#> GSM486838 3 0.1129 0.849 0.004 0.020 0.976
#> GSM486840 3 0.5461 0.822 0.008 0.244 0.748
#> GSM486842 3 0.4293 0.822 0.004 0.164 0.832
#> GSM486844 3 0.5016 0.827 0.000 0.240 0.760
#> GSM486846 3 0.0983 0.846 0.004 0.016 0.980
#> GSM486848 3 0.5502 0.821 0.008 0.248 0.744
#> GSM486850 3 0.0661 0.850 0.008 0.004 0.988
#> GSM486852 3 0.7708 0.541 0.048 0.424 0.528
#> GSM486854 3 0.0848 0.850 0.008 0.008 0.984
#> GSM486856 3 0.3765 0.847 0.028 0.084 0.888
#> GSM486858 3 0.1129 0.847 0.004 0.020 0.976
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 4 0.1411 0.843 0.020 0.020 0.000 0.960
#> GSM486737 4 0.4994 0.876 0.208 0.048 0.000 0.744
#> GSM486739 4 0.4171 0.820 0.116 0.060 0.000 0.824
#> GSM486741 4 0.3606 0.889 0.140 0.020 0.000 0.840
#> GSM486743 4 0.4994 0.876 0.208 0.048 0.000 0.744
#> GSM486745 4 0.4405 0.851 0.152 0.048 0.000 0.800
#> GSM486747 1 0.3306 0.874 0.840 0.000 0.004 0.156
#> GSM486749 4 0.2918 0.885 0.116 0.008 0.000 0.876
#> GSM486751 1 0.3539 0.859 0.820 0.000 0.004 0.176
#> GSM486753 4 0.5031 0.875 0.212 0.048 0.000 0.740
#> GSM486755 4 0.4994 0.876 0.208 0.048 0.000 0.744
#> GSM486757 1 0.3123 0.876 0.844 0.000 0.000 0.156
#> GSM486759 1 0.0000 0.895 1.000 0.000 0.000 0.000
#> GSM486761 1 0.3157 0.879 0.852 0.000 0.004 0.144
#> GSM486763 1 0.3962 0.813 0.844 0.052 0.004 0.100
#> GSM486765 1 0.3105 0.880 0.856 0.000 0.004 0.140
#> GSM486767 4 0.4957 0.875 0.204 0.048 0.000 0.748
#> GSM486769 4 0.1411 0.843 0.020 0.020 0.000 0.960
#> GSM486771 4 0.4994 0.876 0.208 0.048 0.000 0.744
#> GSM486773 4 0.2773 0.884 0.116 0.004 0.000 0.880
#> GSM486775 1 0.0000 0.895 1.000 0.000 0.000 0.000
#> GSM486777 1 0.3157 0.879 0.852 0.000 0.004 0.144
#> GSM486779 4 0.5031 0.875 0.212 0.048 0.000 0.740
#> GSM486781 4 0.2773 0.884 0.116 0.004 0.000 0.880
#> GSM486783 4 0.4994 0.876 0.208 0.048 0.000 0.744
#> GSM486785 1 0.2921 0.882 0.860 0.000 0.000 0.140
#> GSM486787 1 0.0000 0.895 1.000 0.000 0.000 0.000
#> GSM486789 4 0.1807 0.867 0.052 0.008 0.000 0.940
#> GSM486791 1 0.3344 0.829 0.868 0.020 0.004 0.108
#> GSM486793 1 0.2973 0.881 0.856 0.000 0.000 0.144
#> GSM486795 1 0.1543 0.880 0.956 0.032 0.004 0.008
#> GSM486797 1 0.4655 0.652 0.684 0.000 0.004 0.312
#> GSM486799 1 0.0000 0.895 1.000 0.000 0.000 0.000
#> GSM486801 1 0.0000 0.895 1.000 0.000 0.000 0.000
#> GSM486803 1 0.0188 0.895 0.996 0.000 0.000 0.004
#> GSM486805 4 0.3391 0.860 0.148 0.004 0.004 0.844
#> GSM486807 1 0.2921 0.881 0.860 0.000 0.000 0.140
#> GSM486809 4 0.1598 0.841 0.020 0.020 0.004 0.956
#> GSM486811 1 0.2868 0.883 0.864 0.000 0.000 0.136
#> GSM486813 4 0.4994 0.876 0.208 0.048 0.000 0.744
#> GSM486815 1 0.3105 0.880 0.856 0.000 0.004 0.140
#> GSM486817 4 0.5905 0.612 0.396 0.040 0.000 0.564
#> GSM486819 1 0.1796 0.878 0.948 0.032 0.004 0.016
#> GSM486822 4 0.2156 0.870 0.060 0.008 0.004 0.928
#> GSM486824 1 0.0336 0.893 0.992 0.008 0.000 0.000
#> GSM486828 4 0.2773 0.884 0.116 0.004 0.000 0.880
#> GSM486831 1 0.0000 0.895 1.000 0.000 0.000 0.000
#> GSM486833 1 0.3444 0.854 0.816 0.000 0.000 0.184
#> GSM486835 1 0.0000 0.895 1.000 0.000 0.000 0.000
#> GSM486837 4 0.2918 0.884 0.116 0.008 0.000 0.876
#> GSM486839 1 0.0188 0.895 0.996 0.000 0.000 0.004
#> GSM486841 1 0.2921 0.882 0.860 0.000 0.000 0.140
#> GSM486843 1 0.0188 0.895 0.996 0.000 0.000 0.004
#> GSM486845 4 0.2773 0.884 0.116 0.004 0.000 0.880
#> GSM486847 1 0.0188 0.895 0.996 0.000 0.000 0.004
#> GSM486849 4 0.2918 0.885 0.116 0.008 0.000 0.876
#> GSM486851 1 0.3619 0.824 0.860 0.036 0.004 0.100
#> GSM486853 4 0.2918 0.885 0.116 0.008 0.000 0.876
#> GSM486855 4 0.4994 0.876 0.208 0.048 0.000 0.744
#> GSM486857 4 0.2773 0.884 0.116 0.004 0.000 0.880
#> GSM486736 2 0.2048 0.818 0.000 0.928 0.008 0.064
#> GSM486738 2 0.4059 0.859 0.000 0.788 0.200 0.012
#> GSM486740 2 0.2530 0.817 0.000 0.896 0.100 0.004
#> GSM486742 2 0.3895 0.866 0.000 0.804 0.184 0.012
#> GSM486744 2 0.4059 0.859 0.000 0.788 0.200 0.012
#> GSM486746 2 0.3024 0.843 0.000 0.852 0.148 0.000
#> GSM486748 3 0.4174 0.861 0.000 0.140 0.816 0.044
#> GSM486750 2 0.3372 0.869 0.000 0.868 0.096 0.036
#> GSM486752 3 0.4405 0.850 0.000 0.152 0.800 0.048
#> GSM486754 2 0.4059 0.859 0.000 0.788 0.200 0.012
#> GSM486756 2 0.4059 0.859 0.000 0.788 0.200 0.012
#> GSM486758 3 0.4153 0.865 0.000 0.132 0.820 0.048
#> GSM486760 3 0.0524 0.884 0.008 0.004 0.988 0.000
#> GSM486762 3 0.4090 0.870 0.004 0.120 0.832 0.044
#> GSM486764 3 0.4648 0.800 0.032 0.164 0.792 0.012
#> GSM486766 3 0.4090 0.870 0.004 0.120 0.832 0.044
#> GSM486768 2 0.4059 0.859 0.000 0.788 0.200 0.012
#> GSM486770 2 0.1635 0.825 0.000 0.948 0.008 0.044
#> GSM486772 2 0.4059 0.859 0.000 0.788 0.200 0.012
#> GSM486774 2 0.3463 0.868 0.000 0.864 0.096 0.040
#> GSM486776 3 0.0524 0.884 0.008 0.004 0.988 0.000
#> GSM486778 3 0.4090 0.870 0.004 0.120 0.832 0.044
#> GSM486780 2 0.4059 0.859 0.000 0.788 0.200 0.012
#> GSM486782 2 0.3372 0.869 0.000 0.868 0.096 0.036
#> GSM486784 2 0.4059 0.859 0.000 0.788 0.200 0.012
#> GSM486786 3 0.4090 0.870 0.004 0.120 0.832 0.044
#> GSM486788 3 0.0524 0.884 0.008 0.004 0.988 0.000
#> GSM486790 2 0.2500 0.855 0.000 0.916 0.044 0.040
#> GSM486792 3 0.4331 0.832 0.004 0.152 0.808 0.036
#> GSM486794 3 0.4145 0.870 0.004 0.124 0.828 0.044
#> GSM486796 3 0.1824 0.861 0.004 0.060 0.936 0.000
#> GSM486798 2 0.4974 0.727 0.000 0.736 0.224 0.040
#> GSM486800 3 0.0524 0.884 0.008 0.004 0.988 0.000
#> GSM486802 3 0.0524 0.884 0.008 0.004 0.988 0.000
#> GSM486804 3 0.0524 0.884 0.008 0.004 0.988 0.000
#> GSM486806 2 0.3463 0.868 0.000 0.864 0.096 0.040
#> GSM486808 3 0.4090 0.870 0.004 0.120 0.832 0.044
#> GSM486810 2 0.1584 0.832 0.000 0.952 0.012 0.036
#> GSM486812 3 0.4090 0.870 0.004 0.120 0.832 0.044
#> GSM486814 2 0.4059 0.859 0.000 0.788 0.200 0.012
#> GSM486816 3 0.4090 0.870 0.004 0.120 0.832 0.044
#> GSM486818 2 0.5336 0.303 0.004 0.496 0.496 0.004
#> GSM486821 3 0.3052 0.803 0.004 0.136 0.860 0.000
#> GSM486823 2 0.2319 0.851 0.000 0.924 0.036 0.040
#> GSM486826 3 0.0524 0.884 0.008 0.004 0.988 0.000
#> GSM486830 2 0.3372 0.869 0.000 0.868 0.096 0.036
#> GSM486832 3 0.0992 0.882 0.008 0.012 0.976 0.004
#> GSM486834 3 0.4801 0.812 0.000 0.188 0.764 0.048
#> GSM486836 3 0.0524 0.884 0.008 0.004 0.988 0.000
#> GSM486838 2 0.3525 0.869 0.000 0.860 0.100 0.040
#> GSM486840 3 0.0524 0.884 0.008 0.004 0.988 0.000
#> GSM486842 3 0.4090 0.870 0.004 0.120 0.832 0.044
#> GSM486844 3 0.0672 0.883 0.008 0.008 0.984 0.000
#> GSM486846 2 0.3463 0.868 0.000 0.864 0.096 0.040
#> GSM486848 3 0.0524 0.884 0.008 0.004 0.988 0.000
#> GSM486850 2 0.3372 0.869 0.000 0.868 0.096 0.036
#> GSM486852 3 0.3873 0.820 0.008 0.144 0.832 0.016
#> GSM486854 2 0.3435 0.870 0.000 0.864 0.100 0.036
#> GSM486856 2 0.4059 0.859 0.000 0.788 0.200 0.012
#> GSM486858 2 0.3463 0.868 0.000 0.864 0.096 0.040
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 4 0.4430 0.08551 0.000 0.004 0.000 0.540 0.456
#> GSM486737 4 0.3257 0.76688 0.124 0.004 0.000 0.844 0.028
#> GSM486739 5 0.6269 -0.13953 0.128 0.004 0.000 0.416 0.452
#> GSM486741 4 0.1992 0.77933 0.044 0.000 0.000 0.924 0.032
#> GSM486743 4 0.3218 0.76636 0.128 0.004 0.000 0.844 0.024
#> GSM486745 4 0.3264 0.76404 0.132 0.004 0.000 0.840 0.024
#> GSM486747 1 0.3752 0.74921 0.780 0.004 0.000 0.200 0.016
#> GSM486749 4 0.0162 0.77894 0.000 0.004 0.000 0.996 0.000
#> GSM486751 4 0.5019 -0.06946 0.436 0.004 0.000 0.536 0.024
#> GSM486753 4 0.3218 0.76652 0.128 0.004 0.000 0.844 0.024
#> GSM486755 4 0.3257 0.76711 0.124 0.004 0.000 0.844 0.028
#> GSM486757 1 0.4776 0.52860 0.612 0.004 0.000 0.364 0.020
#> GSM486759 1 0.0000 0.82750 1.000 0.000 0.000 0.000 0.000
#> GSM486761 1 0.3310 0.79783 0.836 0.004 0.000 0.136 0.024
#> GSM486763 5 0.5002 0.28241 0.424 0.004 0.000 0.024 0.548
#> GSM486765 1 0.3264 0.80041 0.840 0.004 0.000 0.132 0.024
#> GSM486767 4 0.3218 0.76583 0.128 0.004 0.000 0.844 0.024
#> GSM486769 4 0.4446 0.04747 0.000 0.004 0.000 0.520 0.476
#> GSM486771 4 0.3257 0.76688 0.124 0.004 0.000 0.844 0.028
#> GSM486773 4 0.0854 0.77382 0.012 0.004 0.000 0.976 0.008
#> GSM486775 1 0.0162 0.82649 0.996 0.000 0.000 0.004 0.000
#> GSM486777 1 0.3474 0.80360 0.836 0.004 0.000 0.116 0.044
#> GSM486779 4 0.3218 0.76636 0.128 0.004 0.000 0.844 0.024
#> GSM486781 4 0.0162 0.77894 0.000 0.004 0.000 0.996 0.000
#> GSM486783 4 0.3218 0.76636 0.128 0.004 0.000 0.844 0.024
#> GSM486785 1 0.3425 0.80608 0.840 0.004 0.000 0.112 0.044
#> GSM486787 1 0.0000 0.82750 1.000 0.000 0.000 0.000 0.000
#> GSM486789 4 0.0955 0.77662 0.000 0.004 0.000 0.968 0.028
#> GSM486791 5 0.4613 0.30772 0.408 0.004 0.000 0.008 0.580
#> GSM486793 1 0.3449 0.80311 0.836 0.004 0.000 0.120 0.040
#> GSM486795 1 0.4686 0.17804 0.596 0.000 0.000 0.384 0.020
#> GSM486797 4 0.4895 0.16043 0.376 0.004 0.000 0.596 0.024
#> GSM486799 1 0.0000 0.82750 1.000 0.000 0.000 0.000 0.000
#> GSM486801 1 0.0000 0.82750 1.000 0.000 0.000 0.000 0.000
#> GSM486803 1 0.0000 0.82750 1.000 0.000 0.000 0.000 0.000
#> GSM486805 4 0.2568 0.71652 0.092 0.004 0.000 0.888 0.016
#> GSM486807 1 0.3420 0.80211 0.836 0.004 0.000 0.124 0.036
#> GSM486809 4 0.4238 0.30101 0.000 0.004 0.000 0.628 0.368
#> GSM486811 1 0.3425 0.80608 0.840 0.004 0.000 0.112 0.044
#> GSM486813 4 0.3218 0.76636 0.128 0.004 0.000 0.844 0.024
#> GSM486815 1 0.3474 0.80360 0.836 0.004 0.000 0.116 0.044
#> GSM486817 4 0.4675 0.56640 0.336 0.004 0.000 0.640 0.020
#> GSM486819 1 0.4789 0.14623 0.584 0.000 0.000 0.392 0.024
#> GSM486822 4 0.0865 0.77748 0.000 0.004 0.000 0.972 0.024
#> GSM486824 1 0.0000 0.82750 1.000 0.000 0.000 0.000 0.000
#> GSM486828 4 0.0324 0.77837 0.000 0.004 0.000 0.992 0.004
#> GSM486831 1 0.0000 0.82750 1.000 0.000 0.000 0.000 0.000
#> GSM486833 4 0.4995 -0.00525 0.420 0.004 0.000 0.552 0.024
#> GSM486835 1 0.0000 0.82750 1.000 0.000 0.000 0.000 0.000
#> GSM486837 4 0.0290 0.77910 0.000 0.008 0.000 0.992 0.000
#> GSM486839 1 0.0000 0.82750 1.000 0.000 0.000 0.000 0.000
#> GSM486841 1 0.3425 0.80608 0.840 0.004 0.000 0.112 0.044
#> GSM486843 1 0.0162 0.82557 0.996 0.000 0.000 0.000 0.004
#> GSM486845 4 0.0324 0.77837 0.000 0.004 0.000 0.992 0.004
#> GSM486847 1 0.0000 0.82750 1.000 0.000 0.000 0.000 0.000
#> GSM486849 4 0.0324 0.77983 0.000 0.004 0.000 0.992 0.004
#> GSM486851 5 0.4632 0.25210 0.448 0.000 0.000 0.012 0.540
#> GSM486853 4 0.0566 0.77950 0.000 0.004 0.000 0.984 0.012
#> GSM486855 4 0.3218 0.76636 0.128 0.004 0.000 0.844 0.024
#> GSM486857 4 0.0162 0.77894 0.000 0.004 0.000 0.996 0.000
#> GSM486736 5 0.4384 0.43766 0.000 0.228 0.000 0.044 0.728
#> GSM486738 2 0.3373 0.78840 0.000 0.848 0.092 0.004 0.056
#> GSM486740 2 0.5855 0.28969 0.000 0.468 0.072 0.008 0.452
#> GSM486742 2 0.3065 0.79227 0.000 0.872 0.048 0.008 0.072
#> GSM486744 2 0.3359 0.78825 0.000 0.848 0.096 0.004 0.052
#> GSM486746 2 0.3547 0.78691 0.000 0.836 0.100 0.004 0.060
#> GSM486748 2 0.4969 -0.05208 0.000 0.508 0.468 0.004 0.020
#> GSM486750 2 0.0579 0.79794 0.000 0.984 0.000 0.008 0.008
#> GSM486752 2 0.4763 0.33237 0.000 0.616 0.360 0.004 0.020
#> GSM486754 2 0.3384 0.78836 0.000 0.848 0.088 0.004 0.060
#> GSM486756 2 0.3384 0.78836 0.000 0.848 0.088 0.004 0.060
#> GSM486758 2 0.4749 0.34341 0.000 0.620 0.356 0.004 0.020
#> GSM486760 3 0.0000 0.86814 0.000 0.000 1.000 0.000 0.000
#> GSM486762 3 0.3355 0.83018 0.000 0.132 0.832 0.000 0.036
#> GSM486764 5 0.5685 0.32263 0.032 0.016 0.364 0.012 0.576
#> GSM486766 3 0.3321 0.82774 0.000 0.136 0.832 0.000 0.032
#> GSM486768 2 0.3547 0.78631 0.000 0.836 0.100 0.004 0.060
#> GSM486770 5 0.4510 0.10068 0.000 0.432 0.000 0.008 0.560
#> GSM486772 2 0.3373 0.78840 0.000 0.848 0.092 0.004 0.056
#> GSM486774 2 0.0992 0.79543 0.000 0.968 0.000 0.008 0.024
#> GSM486776 3 0.0000 0.86814 0.000 0.000 1.000 0.000 0.000
#> GSM486778 3 0.3386 0.83147 0.000 0.128 0.832 0.000 0.040
#> GSM486780 2 0.3373 0.78840 0.000 0.848 0.092 0.004 0.056
#> GSM486782 2 0.0579 0.79794 0.000 0.984 0.000 0.008 0.008
#> GSM486784 2 0.3359 0.78825 0.000 0.848 0.096 0.004 0.052
#> GSM486786 3 0.3386 0.83147 0.000 0.128 0.832 0.000 0.040
#> GSM486788 3 0.0000 0.86814 0.000 0.000 1.000 0.000 0.000
#> GSM486790 2 0.0693 0.79878 0.000 0.980 0.000 0.008 0.012
#> GSM486792 5 0.5954 0.20447 0.012 0.076 0.400 0.000 0.512
#> GSM486794 3 0.3386 0.83147 0.000 0.128 0.832 0.000 0.040
#> GSM486796 3 0.4434 0.21046 0.000 0.348 0.640 0.004 0.008
#> GSM486798 2 0.2756 0.74085 0.000 0.880 0.092 0.004 0.024
#> GSM486800 3 0.0000 0.86814 0.000 0.000 1.000 0.000 0.000
#> GSM486802 3 0.0000 0.86814 0.000 0.000 1.000 0.000 0.000
#> GSM486804 3 0.0000 0.86814 0.000 0.000 1.000 0.000 0.000
#> GSM486806 2 0.1124 0.79264 0.000 0.960 0.000 0.004 0.036
#> GSM486808 3 0.3355 0.83018 0.000 0.132 0.832 0.000 0.036
#> GSM486810 2 0.4306 0.48389 0.000 0.660 0.000 0.012 0.328
#> GSM486812 3 0.3386 0.83147 0.000 0.128 0.832 0.000 0.040
#> GSM486814 2 0.3342 0.78778 0.000 0.848 0.100 0.004 0.048
#> GSM486816 3 0.3386 0.83147 0.000 0.128 0.832 0.000 0.040
#> GSM486818 2 0.4471 0.65440 0.000 0.684 0.292 0.004 0.020
#> GSM486821 2 0.5338 0.48211 0.000 0.560 0.392 0.008 0.040
#> GSM486823 2 0.0898 0.79703 0.000 0.972 0.000 0.008 0.020
#> GSM486826 3 0.0000 0.86814 0.000 0.000 1.000 0.000 0.000
#> GSM486830 2 0.1082 0.79432 0.000 0.964 0.000 0.008 0.028
#> GSM486832 3 0.0162 0.86634 0.004 0.000 0.996 0.000 0.000
#> GSM486834 2 0.4581 0.52728 0.000 0.696 0.268 0.004 0.032
#> GSM486836 3 0.0000 0.86814 0.000 0.000 1.000 0.000 0.000
#> GSM486838 2 0.0290 0.79966 0.000 0.992 0.000 0.008 0.000
#> GSM486840 3 0.0000 0.86814 0.000 0.000 1.000 0.000 0.000
#> GSM486842 3 0.3355 0.83018 0.000 0.132 0.832 0.000 0.036
#> GSM486844 3 0.0703 0.84926 0.000 0.024 0.976 0.000 0.000
#> GSM486846 2 0.0451 0.79896 0.000 0.988 0.000 0.008 0.004
#> GSM486848 3 0.0000 0.86814 0.000 0.000 1.000 0.000 0.000
#> GSM486850 2 0.0290 0.79966 0.000 0.992 0.000 0.008 0.000
#> GSM486852 5 0.6347 0.19133 0.008 0.096 0.416 0.008 0.472
#> GSM486854 2 0.0290 0.79966 0.000 0.992 0.000 0.008 0.000
#> GSM486856 2 0.3373 0.78840 0.000 0.848 0.092 0.004 0.056
#> GSM486858 2 0.0579 0.79794 0.000 0.984 0.000 0.008 0.008
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 6 0.5114 0.6865 0.000 0.000 0.024 0.160 0.136 0.680
#> GSM486737 4 0.0767 0.7942 0.000 0.008 0.000 0.976 0.004 0.012
#> GSM486739 6 0.3851 0.6093 0.000 0.004 0.008 0.284 0.004 0.700
#> GSM486741 4 0.2417 0.8123 0.000 0.004 0.008 0.888 0.088 0.012
#> GSM486743 4 0.0951 0.7930 0.000 0.008 0.000 0.968 0.004 0.020
#> GSM486745 4 0.4131 0.1684 0.000 0.004 0.004 0.600 0.004 0.388
#> GSM486747 5 0.2350 0.7421 0.000 0.004 0.008 0.064 0.900 0.024
#> GSM486749 4 0.3066 0.7993 0.000 0.004 0.012 0.836 0.136 0.012
#> GSM486751 5 0.4739 0.5146 0.000 0.012 0.012 0.228 0.696 0.052
#> GSM486753 4 0.0935 0.7949 0.000 0.004 0.000 0.964 0.000 0.032
#> GSM486755 4 0.2062 0.7660 0.000 0.008 0.004 0.900 0.000 0.088
#> GSM486757 5 0.4280 0.6174 0.000 0.012 0.012 0.152 0.764 0.060
#> GSM486759 5 0.2784 0.8015 0.008 0.000 0.000 0.012 0.848 0.132
#> GSM486761 5 0.0767 0.7942 0.000 0.000 0.008 0.004 0.976 0.012
#> GSM486763 6 0.5113 0.6274 0.000 0.004 0.040 0.104 0.148 0.704
#> GSM486765 5 0.0622 0.7949 0.000 0.000 0.012 0.000 0.980 0.008
#> GSM486767 4 0.2306 0.7615 0.000 0.004 0.008 0.888 0.004 0.096
#> GSM486769 6 0.4836 0.6852 0.000 0.000 0.012 0.156 0.136 0.696
#> GSM486771 4 0.0582 0.7958 0.000 0.004 0.004 0.984 0.004 0.004
#> GSM486773 4 0.4102 0.7646 0.000 0.012 0.012 0.776 0.152 0.048
#> GSM486775 5 0.2784 0.8015 0.008 0.000 0.000 0.012 0.848 0.132
#> GSM486777 5 0.1168 0.7900 0.000 0.000 0.016 0.000 0.956 0.028
#> GSM486779 4 0.0551 0.7944 0.000 0.008 0.000 0.984 0.004 0.004
#> GSM486781 4 0.3401 0.8000 0.000 0.012 0.004 0.820 0.136 0.028
#> GSM486783 4 0.1261 0.7890 0.000 0.008 0.004 0.956 0.004 0.028
#> GSM486785 5 0.0820 0.7941 0.000 0.000 0.012 0.000 0.972 0.016
#> GSM486787 5 0.2784 0.8015 0.008 0.000 0.000 0.012 0.848 0.132
#> GSM486789 4 0.4964 0.6771 0.000 0.000 0.012 0.680 0.136 0.172
#> GSM486791 6 0.4797 0.5744 0.008 0.000 0.044 0.036 0.200 0.712
#> GSM486793 5 0.1088 0.7916 0.000 0.000 0.016 0.000 0.960 0.024
#> GSM486795 5 0.5174 0.5807 0.000 0.004 0.012 0.260 0.636 0.088
#> GSM486797 5 0.4969 0.4698 0.000 0.012 0.012 0.248 0.668 0.060
#> GSM486799 5 0.2784 0.8015 0.008 0.000 0.000 0.012 0.848 0.132
#> GSM486801 5 0.2784 0.8015 0.008 0.000 0.000 0.012 0.848 0.132
#> GSM486803 5 0.2784 0.8015 0.008 0.000 0.000 0.012 0.848 0.132
#> GSM486805 4 0.4844 0.6189 0.000 0.012 0.012 0.672 0.256 0.048
#> GSM486807 5 0.0767 0.7942 0.000 0.000 0.008 0.004 0.976 0.012
#> GSM486809 6 0.5040 0.6876 0.000 0.004 0.020 0.144 0.136 0.696
#> GSM486811 5 0.0909 0.7936 0.000 0.000 0.012 0.000 0.968 0.020
#> GSM486813 4 0.1299 0.7868 0.000 0.004 0.004 0.952 0.004 0.036
#> GSM486815 5 0.0909 0.7938 0.000 0.000 0.012 0.000 0.968 0.020
#> GSM486817 4 0.5286 0.2965 0.000 0.004 0.012 0.612 0.284 0.088
#> GSM486819 5 0.5831 0.4148 0.000 0.004 0.012 0.324 0.528 0.132
#> GSM486822 4 0.4964 0.6772 0.000 0.000 0.012 0.680 0.136 0.172
#> GSM486824 5 0.2834 0.8008 0.008 0.000 0.000 0.016 0.848 0.128
#> GSM486828 4 0.3683 0.7946 0.000 0.012 0.012 0.808 0.136 0.032
#> GSM486831 5 0.2784 0.8015 0.008 0.000 0.000 0.012 0.848 0.132
#> GSM486833 5 0.4933 0.3955 0.000 0.012 0.012 0.300 0.636 0.040
#> GSM486835 5 0.2784 0.8015 0.008 0.000 0.000 0.012 0.848 0.132
#> GSM486837 4 0.3526 0.7880 0.000 0.016 0.004 0.804 0.156 0.020
#> GSM486839 5 0.2784 0.8015 0.008 0.000 0.000 0.012 0.848 0.132
#> GSM486841 5 0.1074 0.7913 0.000 0.000 0.012 0.000 0.960 0.028
#> GSM486843 5 0.2877 0.7995 0.008 0.000 0.000 0.020 0.848 0.124
#> GSM486845 4 0.3157 0.7978 0.000 0.012 0.004 0.832 0.136 0.016
#> GSM486847 5 0.2834 0.8008 0.008 0.000 0.000 0.016 0.848 0.128
#> GSM486849 4 0.3475 0.7985 0.000 0.004 0.012 0.816 0.136 0.032
#> GSM486851 6 0.5115 0.6210 0.000 0.004 0.040 0.092 0.164 0.700
#> GSM486853 4 0.2868 0.8021 0.000 0.004 0.008 0.844 0.136 0.008
#> GSM486855 4 0.0551 0.7944 0.000 0.008 0.000 0.984 0.004 0.004
#> GSM486857 4 0.3176 0.7976 0.000 0.012 0.008 0.832 0.136 0.012
#> GSM486736 3 0.4062 0.6749 0.000 0.052 0.796 0.012 0.024 0.116
#> GSM486738 2 0.1647 0.7378 0.016 0.940 0.032 0.008 0.000 0.004
#> GSM486740 3 0.4662 0.6421 0.008 0.268 0.676 0.024 0.000 0.024
#> GSM486742 2 0.2009 0.7555 0.008 0.904 0.084 0.000 0.000 0.004
#> GSM486744 2 0.1223 0.7512 0.016 0.960 0.012 0.008 0.000 0.004
#> GSM486746 2 0.4122 0.5489 0.016 0.720 0.244 0.012 0.000 0.008
#> GSM486748 1 0.5713 0.5516 0.624 0.140 0.200 0.004 0.000 0.032
#> GSM486750 2 0.2520 0.7591 0.000 0.844 0.152 0.004 0.000 0.000
#> GSM486752 2 0.6852 0.2257 0.316 0.416 0.216 0.004 0.000 0.048
#> GSM486754 2 0.1325 0.7506 0.016 0.956 0.012 0.012 0.000 0.004
#> GSM486756 2 0.1312 0.7482 0.012 0.956 0.020 0.008 0.000 0.004
#> GSM486758 1 0.6306 0.3970 0.532 0.212 0.220 0.004 0.000 0.032
#> GSM486760 1 0.0000 0.8322 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486762 1 0.3161 0.8039 0.820 0.012 0.156 0.000 0.008 0.004
#> GSM486764 3 0.6779 0.6555 0.104 0.120 0.592 0.024 0.008 0.152
#> GSM486766 1 0.3176 0.8039 0.824 0.016 0.148 0.000 0.008 0.004
#> GSM486768 2 0.2721 0.7355 0.024 0.884 0.068 0.012 0.000 0.012
#> GSM486770 3 0.3434 0.7008 0.000 0.140 0.808 0.004 0.000 0.048
#> GSM486772 2 0.1262 0.7498 0.020 0.956 0.016 0.008 0.000 0.000
#> GSM486774 2 0.3219 0.7476 0.000 0.792 0.192 0.004 0.000 0.012
#> GSM486776 1 0.0146 0.8317 0.996 0.000 0.000 0.000 0.000 0.004
#> GSM486778 1 0.3481 0.7914 0.792 0.012 0.180 0.000 0.008 0.008
#> GSM486780 2 0.1592 0.7379 0.020 0.940 0.032 0.008 0.000 0.000
#> GSM486782 2 0.2738 0.7576 0.000 0.820 0.176 0.004 0.000 0.000
#> GSM486784 2 0.1167 0.7473 0.020 0.960 0.012 0.008 0.000 0.000
#> GSM486786 1 0.3135 0.8033 0.816 0.008 0.164 0.000 0.008 0.004
#> GSM486788 1 0.0000 0.8322 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486790 2 0.3052 0.7228 0.000 0.780 0.216 0.004 0.000 0.000
#> GSM486792 3 0.4977 0.6173 0.212 0.012 0.668 0.000 0.000 0.108
#> GSM486794 1 0.3428 0.7920 0.796 0.016 0.176 0.000 0.008 0.004
#> GSM486796 1 0.6123 0.1239 0.508 0.352 0.080 0.004 0.000 0.056
#> GSM486798 2 0.5261 0.6450 0.072 0.672 0.208 0.004 0.000 0.044
#> GSM486800 1 0.0000 0.8322 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486802 1 0.0000 0.8322 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486804 1 0.0000 0.8322 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486806 2 0.3810 0.7248 0.000 0.752 0.208 0.004 0.000 0.036
#> GSM486808 1 0.2982 0.8054 0.828 0.012 0.152 0.000 0.008 0.000
#> GSM486810 3 0.2996 0.6920 0.000 0.144 0.832 0.008 0.000 0.016
#> GSM486812 1 0.3135 0.8033 0.816 0.008 0.164 0.000 0.008 0.004
#> GSM486814 2 0.0951 0.7494 0.020 0.968 0.004 0.008 0.000 0.000
#> GSM486816 1 0.3447 0.7937 0.796 0.012 0.176 0.000 0.008 0.008
#> GSM486818 2 0.6248 0.2645 0.380 0.472 0.088 0.004 0.000 0.056
#> GSM486821 2 0.7039 0.0304 0.284 0.448 0.200 0.008 0.004 0.056
#> GSM486823 2 0.3476 0.6802 0.000 0.732 0.260 0.004 0.000 0.004
#> GSM486826 1 0.0291 0.8313 0.992 0.004 0.000 0.000 0.000 0.004
#> GSM486830 2 0.3121 0.7493 0.000 0.796 0.192 0.004 0.000 0.008
#> GSM486832 1 0.0260 0.8327 0.992 0.000 0.008 0.000 0.000 0.000
#> GSM486834 2 0.6919 0.1699 0.328 0.388 0.232 0.004 0.000 0.048
#> GSM486836 1 0.0000 0.8322 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486838 2 0.3596 0.7399 0.040 0.784 0.172 0.004 0.000 0.000
#> GSM486840 1 0.0000 0.8322 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486842 1 0.3099 0.8047 0.820 0.008 0.160 0.000 0.008 0.004
#> GSM486844 1 0.0622 0.8236 0.980 0.008 0.012 0.000 0.000 0.000
#> GSM486846 2 0.2737 0.7592 0.000 0.832 0.160 0.004 0.000 0.004
#> GSM486848 1 0.0146 0.8317 0.996 0.000 0.000 0.000 0.000 0.004
#> GSM486850 2 0.2442 0.7598 0.000 0.852 0.144 0.004 0.000 0.000
#> GSM486852 3 0.6687 0.6602 0.156 0.120 0.588 0.012 0.008 0.116
#> GSM486854 2 0.2442 0.7598 0.000 0.852 0.144 0.004 0.000 0.000
#> GSM486856 2 0.1065 0.7483 0.020 0.964 0.008 0.008 0.000 0.000
#> GSM486858 2 0.2402 0.7609 0.000 0.856 0.140 0.004 0.000 0.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> MAD:mclust 120 4.67e-27 1.000 2
#> MAD:mclust 110 7.26e-25 1.000 3
#> MAD:mclust 119 1.27e-25 1.000 4
#> MAD:mclust 96 1.13e-20 0.997 5
#> MAD:mclust 109 6.67e-22 0.989 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["MAD", "NMF"]
# you can also extract it by
# res = res_list["MAD:NMF"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'MAD' method.
#> Subgroups are detected by 'NMF' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.897 0.923 0.968 0.4999 0.501 0.501
#> 3 3 0.562 0.684 0.847 0.3242 0.748 0.538
#> 4 4 0.482 0.512 0.738 0.1018 0.791 0.481
#> 5 5 0.494 0.485 0.706 0.0691 0.829 0.465
#> 6 6 0.510 0.329 0.608 0.0497 0.949 0.779
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 2 0.0000 0.956 0.000 1.000
#> GSM486737 2 0.0000 0.956 0.000 1.000
#> GSM486739 2 0.0000 0.956 0.000 1.000
#> GSM486741 2 0.0000 0.956 0.000 1.000
#> GSM486743 2 0.0000 0.956 0.000 1.000
#> GSM486745 2 0.0000 0.956 0.000 1.000
#> GSM486747 1 0.0000 0.978 1.000 0.000
#> GSM486749 2 0.0000 0.956 0.000 1.000
#> GSM486751 2 0.9795 0.331 0.416 0.584
#> GSM486753 2 0.0000 0.956 0.000 1.000
#> GSM486755 2 0.0000 0.956 0.000 1.000
#> GSM486757 1 0.9460 0.405 0.636 0.364
#> GSM486759 1 0.0000 0.978 1.000 0.000
#> GSM486761 1 0.0000 0.978 1.000 0.000
#> GSM486763 2 0.3733 0.895 0.072 0.928
#> GSM486765 1 0.0000 0.978 1.000 0.000
#> GSM486767 2 0.0000 0.956 0.000 1.000
#> GSM486769 2 0.0000 0.956 0.000 1.000
#> GSM486771 2 0.0000 0.956 0.000 1.000
#> GSM486773 2 0.0000 0.956 0.000 1.000
#> GSM486775 1 0.0000 0.978 1.000 0.000
#> GSM486777 1 0.0000 0.978 1.000 0.000
#> GSM486779 2 0.0000 0.956 0.000 1.000
#> GSM486781 2 0.0000 0.956 0.000 1.000
#> GSM486783 2 0.0000 0.956 0.000 1.000
#> GSM486785 1 0.0000 0.978 1.000 0.000
#> GSM486787 1 0.0000 0.978 1.000 0.000
#> GSM486789 2 0.0000 0.956 0.000 1.000
#> GSM486791 1 0.0000 0.978 1.000 0.000
#> GSM486793 1 0.0000 0.978 1.000 0.000
#> GSM486795 1 0.1414 0.961 0.980 0.020
#> GSM486797 2 0.8813 0.600 0.300 0.700
#> GSM486799 1 0.0000 0.978 1.000 0.000
#> GSM486801 1 0.0000 0.978 1.000 0.000
#> GSM486803 1 0.0000 0.978 1.000 0.000
#> GSM486805 2 0.0000 0.956 0.000 1.000
#> GSM486807 1 0.0000 0.978 1.000 0.000
#> GSM486809 2 0.0000 0.956 0.000 1.000
#> GSM486811 1 0.0000 0.978 1.000 0.000
#> GSM486813 2 0.0000 0.956 0.000 1.000
#> GSM486815 1 0.0000 0.978 1.000 0.000
#> GSM486817 2 0.8608 0.628 0.284 0.716
#> GSM486819 1 0.8861 0.543 0.696 0.304
#> GSM486822 2 0.0000 0.956 0.000 1.000
#> GSM486824 1 0.0000 0.978 1.000 0.000
#> GSM486828 2 0.0000 0.956 0.000 1.000
#> GSM486831 1 0.0000 0.978 1.000 0.000
#> GSM486833 2 0.7528 0.732 0.216 0.784
#> GSM486835 1 0.0000 0.978 1.000 0.000
#> GSM486837 2 0.0000 0.956 0.000 1.000
#> GSM486839 1 0.0000 0.978 1.000 0.000
#> GSM486841 1 0.0000 0.978 1.000 0.000
#> GSM486843 1 0.0000 0.978 1.000 0.000
#> GSM486845 2 0.0000 0.956 0.000 1.000
#> GSM486847 1 0.0000 0.978 1.000 0.000
#> GSM486849 2 0.0000 0.956 0.000 1.000
#> GSM486851 1 0.1184 0.965 0.984 0.016
#> GSM486853 2 0.0000 0.956 0.000 1.000
#> GSM486855 2 0.0000 0.956 0.000 1.000
#> GSM486857 2 0.0000 0.956 0.000 1.000
#> GSM486736 2 0.0000 0.956 0.000 1.000
#> GSM486738 2 0.0000 0.956 0.000 1.000
#> GSM486740 2 0.0000 0.956 0.000 1.000
#> GSM486742 2 0.0000 0.956 0.000 1.000
#> GSM486744 2 0.0000 0.956 0.000 1.000
#> GSM486746 2 0.0000 0.956 0.000 1.000
#> GSM486748 1 0.0000 0.978 1.000 0.000
#> GSM486750 2 0.0000 0.956 0.000 1.000
#> GSM486752 1 0.8661 0.576 0.712 0.288
#> GSM486754 2 0.0000 0.956 0.000 1.000
#> GSM486756 2 0.0000 0.956 0.000 1.000
#> GSM486758 1 0.4161 0.892 0.916 0.084
#> GSM486760 1 0.0000 0.978 1.000 0.000
#> GSM486762 1 0.0000 0.978 1.000 0.000
#> GSM486764 2 0.9909 0.240 0.444 0.556
#> GSM486766 1 0.0000 0.978 1.000 0.000
#> GSM486768 2 0.0000 0.956 0.000 1.000
#> GSM486770 2 0.0000 0.956 0.000 1.000
#> GSM486772 2 0.0000 0.956 0.000 1.000
#> GSM486774 2 0.0000 0.956 0.000 1.000
#> GSM486776 1 0.0000 0.978 1.000 0.000
#> GSM486778 1 0.0000 0.978 1.000 0.000
#> GSM486780 2 0.0000 0.956 0.000 1.000
#> GSM486782 2 0.0000 0.956 0.000 1.000
#> GSM486784 2 0.0000 0.956 0.000 1.000
#> GSM486786 1 0.0000 0.978 1.000 0.000
#> GSM486788 1 0.0000 0.978 1.000 0.000
#> GSM486790 2 0.0000 0.956 0.000 1.000
#> GSM486792 1 0.0000 0.978 1.000 0.000
#> GSM486794 1 0.0000 0.978 1.000 0.000
#> GSM486796 1 0.0938 0.968 0.988 0.012
#> GSM486798 2 0.9358 0.494 0.352 0.648
#> GSM486800 1 0.0000 0.978 1.000 0.000
#> GSM486802 1 0.0000 0.978 1.000 0.000
#> GSM486804 1 0.0000 0.978 1.000 0.000
#> GSM486806 2 0.0000 0.956 0.000 1.000
#> GSM486808 1 0.0000 0.978 1.000 0.000
#> GSM486810 2 0.0000 0.956 0.000 1.000
#> GSM486812 1 0.0000 0.978 1.000 0.000
#> GSM486814 2 0.0000 0.956 0.000 1.000
#> GSM486816 1 0.0000 0.978 1.000 0.000
#> GSM486818 2 0.8813 0.600 0.300 0.700
#> GSM486821 2 0.8555 0.635 0.280 0.720
#> GSM486823 2 0.0000 0.956 0.000 1.000
#> GSM486826 1 0.0000 0.978 1.000 0.000
#> GSM486830 2 0.0000 0.956 0.000 1.000
#> GSM486832 1 0.0000 0.978 1.000 0.000
#> GSM486834 2 0.5519 0.839 0.128 0.872
#> GSM486836 1 0.0000 0.978 1.000 0.000
#> GSM486838 2 0.0672 0.949 0.008 0.992
#> GSM486840 1 0.0000 0.978 1.000 0.000
#> GSM486842 1 0.0000 0.978 1.000 0.000
#> GSM486844 1 0.0000 0.978 1.000 0.000
#> GSM486846 2 0.0000 0.956 0.000 1.000
#> GSM486848 1 0.0000 0.978 1.000 0.000
#> GSM486850 2 0.0000 0.956 0.000 1.000
#> GSM486852 1 0.0672 0.971 0.992 0.008
#> GSM486854 2 0.0000 0.956 0.000 1.000
#> GSM486856 2 0.0000 0.956 0.000 1.000
#> GSM486858 2 0.0000 0.956 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 2 0.6299 0.07635 0.476 0.524 0.000
#> GSM486737 2 0.5835 0.56384 0.340 0.660 0.000
#> GSM486739 2 0.6180 0.34673 0.416 0.584 0.000
#> GSM486741 2 0.5988 0.45374 0.368 0.632 0.000
#> GSM486743 2 0.6154 0.38765 0.408 0.592 0.000
#> GSM486745 1 0.6442 0.12141 0.564 0.432 0.004
#> GSM486747 1 0.6262 0.53044 0.696 0.020 0.284
#> GSM486749 1 0.3879 0.71080 0.848 0.152 0.000
#> GSM486751 1 0.3028 0.74860 0.920 0.048 0.032
#> GSM486753 2 0.6192 0.38631 0.420 0.580 0.000
#> GSM486755 2 0.4452 0.72888 0.192 0.808 0.000
#> GSM486757 1 0.2636 0.74908 0.932 0.048 0.020
#> GSM486759 3 0.4974 0.72066 0.236 0.000 0.764
#> GSM486761 3 0.6309 -0.00343 0.500 0.000 0.500
#> GSM486763 1 0.1170 0.74489 0.976 0.016 0.008
#> GSM486765 3 0.1163 0.87485 0.028 0.000 0.972
#> GSM486767 1 0.6509 -0.03121 0.524 0.472 0.004
#> GSM486769 2 0.4399 0.70080 0.188 0.812 0.000
#> GSM486771 1 0.6126 0.24306 0.600 0.400 0.000
#> GSM486773 1 0.3816 0.71730 0.852 0.148 0.000
#> GSM486775 3 0.1163 0.87602 0.028 0.000 0.972
#> GSM486777 1 0.3619 0.69241 0.864 0.000 0.136
#> GSM486779 1 0.5244 0.56697 0.756 0.240 0.004
#> GSM486781 1 0.6026 0.37535 0.624 0.376 0.000
#> GSM486783 2 0.5178 0.66897 0.256 0.744 0.000
#> GSM486785 1 0.6235 0.14306 0.564 0.000 0.436
#> GSM486787 3 0.2066 0.86521 0.060 0.000 0.940
#> GSM486789 2 0.2356 0.79981 0.072 0.928 0.000
#> GSM486791 3 0.5982 0.57806 0.328 0.004 0.668
#> GSM486793 1 0.5621 0.50068 0.692 0.000 0.308
#> GSM486795 1 0.1163 0.74514 0.972 0.000 0.028
#> GSM486797 1 0.1832 0.74850 0.956 0.036 0.008
#> GSM486799 3 0.1964 0.86817 0.056 0.000 0.944
#> GSM486801 1 0.6260 0.06110 0.552 0.000 0.448
#> GSM486803 1 0.6244 0.08377 0.560 0.000 0.440
#> GSM486805 1 0.2448 0.74367 0.924 0.076 0.000
#> GSM486807 3 0.4291 0.76710 0.180 0.000 0.820
#> GSM486809 1 0.5254 0.60785 0.736 0.264 0.000
#> GSM486811 3 0.5254 0.67343 0.264 0.000 0.736
#> GSM486813 2 0.6483 0.27263 0.452 0.544 0.004
#> GSM486815 3 0.4974 0.70515 0.236 0.000 0.764
#> GSM486817 1 0.1453 0.74287 0.968 0.024 0.008
#> GSM486819 1 0.1337 0.74478 0.972 0.012 0.016
#> GSM486822 2 0.4555 0.69185 0.200 0.800 0.000
#> GSM486824 3 0.4291 0.79235 0.180 0.000 0.820
#> GSM486828 1 0.4887 0.64443 0.772 0.228 0.000
#> GSM486831 3 0.4504 0.76204 0.196 0.000 0.804
#> GSM486833 1 0.2846 0.74745 0.924 0.056 0.020
#> GSM486835 3 0.2625 0.85513 0.084 0.000 0.916
#> GSM486837 1 0.3551 0.72481 0.868 0.132 0.000
#> GSM486839 3 0.4796 0.72777 0.220 0.000 0.780
#> GSM486841 1 0.6235 0.13125 0.564 0.000 0.436
#> GSM486843 1 0.5650 0.42864 0.688 0.000 0.312
#> GSM486845 1 0.2537 0.74198 0.920 0.080 0.000
#> GSM486847 3 0.5905 0.52357 0.352 0.000 0.648
#> GSM486849 2 0.6180 0.28760 0.416 0.584 0.000
#> GSM486851 1 0.1877 0.74434 0.956 0.012 0.032
#> GSM486853 2 0.6095 0.37610 0.392 0.608 0.000
#> GSM486855 1 0.4575 0.64821 0.812 0.184 0.004
#> GSM486857 1 0.4291 0.69495 0.820 0.180 0.000
#> GSM486736 2 0.1163 0.81711 0.028 0.972 0.000
#> GSM486738 2 0.1163 0.81999 0.028 0.972 0.000
#> GSM486740 2 0.1163 0.81860 0.028 0.972 0.000
#> GSM486742 2 0.0747 0.82053 0.016 0.984 0.000
#> GSM486744 2 0.1163 0.81915 0.028 0.972 0.000
#> GSM486746 2 0.1453 0.81821 0.024 0.968 0.008
#> GSM486748 3 0.5156 0.66723 0.008 0.216 0.776
#> GSM486750 2 0.0892 0.81871 0.020 0.980 0.000
#> GSM486752 2 0.6075 0.52168 0.008 0.676 0.316
#> GSM486754 2 0.1031 0.81997 0.024 0.976 0.000
#> GSM486756 2 0.1031 0.81997 0.024 0.976 0.000
#> GSM486758 2 0.6683 0.04276 0.008 0.500 0.492
#> GSM486760 3 0.0424 0.88039 0.008 0.000 0.992
#> GSM486762 3 0.0237 0.88029 0.004 0.000 0.996
#> GSM486764 2 0.6535 0.62505 0.052 0.728 0.220
#> GSM486766 3 0.0237 0.88029 0.004 0.000 0.996
#> GSM486768 2 0.2050 0.81439 0.028 0.952 0.020
#> GSM486770 2 0.0892 0.81871 0.020 0.980 0.000
#> GSM486772 2 0.1411 0.81759 0.036 0.964 0.000
#> GSM486774 2 0.1919 0.81727 0.020 0.956 0.024
#> GSM486776 3 0.0237 0.88050 0.004 0.000 0.996
#> GSM486778 3 0.0237 0.88029 0.004 0.000 0.996
#> GSM486780 2 0.1878 0.81619 0.044 0.952 0.004
#> GSM486782 2 0.1482 0.81957 0.020 0.968 0.012
#> GSM486784 2 0.1289 0.81921 0.032 0.968 0.000
#> GSM486786 3 0.0237 0.88029 0.004 0.000 0.996
#> GSM486788 3 0.0424 0.88039 0.008 0.000 0.992
#> GSM486790 2 0.0237 0.82102 0.004 0.996 0.000
#> GSM486792 3 0.1999 0.86612 0.012 0.036 0.952
#> GSM486794 3 0.0237 0.88029 0.004 0.000 0.996
#> GSM486796 3 0.6264 0.59731 0.028 0.256 0.716
#> GSM486798 2 0.5115 0.64390 0.004 0.768 0.228
#> GSM486800 3 0.0424 0.88039 0.008 0.000 0.992
#> GSM486802 3 0.2056 0.86733 0.024 0.024 0.952
#> GSM486804 3 0.2903 0.84907 0.028 0.048 0.924
#> GSM486806 2 0.3370 0.78929 0.024 0.904 0.072
#> GSM486808 3 0.0475 0.87975 0.004 0.004 0.992
#> GSM486810 2 0.0892 0.81871 0.020 0.980 0.000
#> GSM486812 3 0.0237 0.88029 0.004 0.000 0.996
#> GSM486814 2 0.2200 0.80996 0.056 0.940 0.004
#> GSM486816 3 0.0237 0.88029 0.004 0.000 0.996
#> GSM486818 2 0.5180 0.71305 0.032 0.812 0.156
#> GSM486821 2 0.5847 0.68631 0.048 0.780 0.172
#> GSM486823 2 0.0892 0.81871 0.020 0.980 0.000
#> GSM486826 3 0.1585 0.87235 0.008 0.028 0.964
#> GSM486830 2 0.1781 0.81767 0.020 0.960 0.020
#> GSM486832 3 0.1129 0.87551 0.004 0.020 0.976
#> GSM486834 2 0.4413 0.74733 0.024 0.852 0.124
#> GSM486836 3 0.1711 0.86892 0.008 0.032 0.960
#> GSM486838 2 0.3461 0.78781 0.024 0.900 0.076
#> GSM486840 3 0.0237 0.88050 0.004 0.000 0.996
#> GSM486842 3 0.0237 0.88029 0.004 0.000 0.996
#> GSM486844 3 0.2793 0.85205 0.028 0.044 0.928
#> GSM486846 2 0.1781 0.81829 0.020 0.960 0.020
#> GSM486848 3 0.0592 0.88004 0.012 0.000 0.988
#> GSM486850 2 0.0892 0.81896 0.020 0.980 0.000
#> GSM486852 3 0.6079 0.65376 0.036 0.216 0.748
#> GSM486854 2 0.0892 0.81970 0.020 0.980 0.000
#> GSM486856 2 0.1878 0.81481 0.044 0.952 0.004
#> GSM486858 2 0.1919 0.81817 0.024 0.956 0.020
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 4 0.2706 0.5859 0.020 0.080 0.000 0.900
#> GSM486737 2 0.4472 0.4896 0.220 0.760 0.000 0.020
#> GSM486739 4 0.4687 0.5123 0.020 0.224 0.004 0.752
#> GSM486741 2 0.7796 0.0416 0.360 0.392 0.000 0.248
#> GSM486743 2 0.5778 0.1337 0.356 0.604 0.000 0.040
#> GSM486745 4 0.6879 0.4400 0.112 0.268 0.012 0.608
#> GSM486747 1 0.6747 0.5312 0.596 0.000 0.264 0.140
#> GSM486749 1 0.5256 0.5764 0.692 0.036 0.000 0.272
#> GSM486751 1 0.4775 0.6100 0.740 0.000 0.028 0.232
#> GSM486753 1 0.6529 0.2572 0.532 0.388 0.000 0.080
#> GSM486755 2 0.6846 0.2970 0.184 0.600 0.000 0.216
#> GSM486757 1 0.3836 0.6208 0.816 0.000 0.016 0.168
#> GSM486759 3 0.3768 0.7779 0.120 0.024 0.848 0.008
#> GSM486761 3 0.5229 0.2248 0.428 0.000 0.564 0.008
#> GSM486763 4 0.7684 0.2306 0.304 0.152 0.020 0.524
#> GSM486765 3 0.0524 0.8310 0.004 0.000 0.988 0.008
#> GSM486767 1 0.7529 0.2698 0.464 0.392 0.012 0.132
#> GSM486769 4 0.2704 0.5732 0.000 0.124 0.000 0.876
#> GSM486771 1 0.6077 0.2281 0.496 0.460 0.000 0.044
#> GSM486773 1 0.5475 0.5478 0.656 0.036 0.000 0.308
#> GSM486775 3 0.0000 0.8334 0.000 0.000 1.000 0.000
#> GSM486777 1 0.3810 0.5031 0.804 0.000 0.188 0.008
#> GSM486779 2 0.4302 0.4469 0.236 0.756 0.004 0.004
#> GSM486781 1 0.7550 0.3354 0.480 0.220 0.000 0.300
#> GSM486783 2 0.2542 0.5719 0.084 0.904 0.000 0.012
#> GSM486785 1 0.4990 0.2944 0.640 0.000 0.352 0.008
#> GSM486787 3 0.1247 0.8339 0.004 0.016 0.968 0.012
#> GSM486789 4 0.4957 0.3519 0.016 0.300 0.000 0.684
#> GSM486791 3 0.7998 0.3533 0.048 0.128 0.524 0.300
#> GSM486793 3 0.4936 0.4770 0.340 0.000 0.652 0.008
#> GSM486795 1 0.1545 0.5785 0.952 0.040 0.008 0.000
#> GSM486797 1 0.2401 0.6100 0.904 0.000 0.004 0.092
#> GSM486799 3 0.0992 0.8338 0.004 0.012 0.976 0.008
#> GSM486801 3 0.7000 0.2806 0.420 0.060 0.496 0.024
#> GSM486803 1 0.7688 0.3313 0.504 0.204 0.284 0.008
#> GSM486805 1 0.4464 0.6107 0.760 0.012 0.004 0.224
#> GSM486807 3 0.2124 0.8103 0.068 0.000 0.924 0.008
#> GSM486809 4 0.2408 0.5752 0.044 0.036 0.000 0.920
#> GSM486811 3 0.2741 0.8059 0.096 0.000 0.892 0.012
#> GSM486813 2 0.5586 0.3961 0.216 0.720 0.012 0.052
#> GSM486815 3 0.2256 0.8209 0.056 0.000 0.924 0.020
#> GSM486817 1 0.4392 0.5382 0.768 0.216 0.012 0.004
#> GSM486819 1 0.5787 0.5120 0.720 0.192 0.012 0.076
#> GSM486822 4 0.5031 0.4637 0.048 0.212 0.000 0.740
#> GSM486824 3 0.6678 0.5890 0.164 0.168 0.656 0.012
#> GSM486828 1 0.6280 0.5009 0.604 0.080 0.000 0.316
#> GSM486831 3 0.3775 0.8012 0.080 0.016 0.864 0.040
#> GSM486833 1 0.5323 0.5273 0.628 0.000 0.020 0.352
#> GSM486835 3 0.2099 0.8304 0.012 0.044 0.936 0.008
#> GSM486837 1 0.7937 0.4108 0.512 0.224 0.020 0.244
#> GSM486839 3 0.4746 0.6011 0.276 0.008 0.712 0.004
#> GSM486841 3 0.5295 0.2317 0.488 0.000 0.504 0.008
#> GSM486843 1 0.4376 0.5433 0.796 0.028 0.172 0.004
#> GSM486845 1 0.3925 0.6210 0.808 0.016 0.000 0.176
#> GSM486847 1 0.5443 -0.1438 0.532 0.008 0.456 0.004
#> GSM486849 1 0.7896 0.0657 0.372 0.328 0.000 0.300
#> GSM486851 4 0.8781 0.2153 0.264 0.140 0.108 0.488
#> GSM486853 2 0.7717 0.1600 0.304 0.444 0.000 0.252
#> GSM486855 2 0.5004 0.1638 0.392 0.604 0.000 0.004
#> GSM486857 1 0.6165 0.5765 0.672 0.100 0.004 0.224
#> GSM486736 4 0.2149 0.5872 0.000 0.088 0.000 0.912
#> GSM486738 2 0.1118 0.5886 0.000 0.964 0.000 0.036
#> GSM486740 4 0.3942 0.5206 0.000 0.236 0.000 0.764
#> GSM486742 2 0.4164 0.5064 0.000 0.736 0.000 0.264
#> GSM486744 2 0.0592 0.5865 0.000 0.984 0.000 0.016
#> GSM486746 4 0.4936 0.4397 0.000 0.340 0.008 0.652
#> GSM486748 2 0.7634 0.2153 0.004 0.460 0.352 0.184
#> GSM486750 4 0.4746 0.2244 0.000 0.368 0.000 0.632
#> GSM486752 4 0.7985 0.0365 0.004 0.260 0.348 0.388
#> GSM486754 2 0.2469 0.5712 0.000 0.892 0.000 0.108
#> GSM486756 2 0.2530 0.5607 0.000 0.888 0.000 0.112
#> GSM486758 3 0.7401 0.0122 0.004 0.148 0.476 0.372
#> GSM486760 3 0.1284 0.8335 0.000 0.024 0.964 0.012
#> GSM486762 3 0.1443 0.8297 0.004 0.028 0.960 0.008
#> GSM486764 4 0.5203 0.4726 0.000 0.232 0.048 0.720
#> GSM486766 3 0.0992 0.8316 0.004 0.012 0.976 0.008
#> GSM486768 2 0.3450 0.4951 0.000 0.836 0.008 0.156
#> GSM486770 4 0.2647 0.5760 0.000 0.120 0.000 0.880
#> GSM486772 2 0.1389 0.5757 0.000 0.952 0.000 0.048
#> GSM486774 2 0.4804 0.3687 0.000 0.616 0.000 0.384
#> GSM486776 3 0.1209 0.8327 0.000 0.032 0.964 0.004
#> GSM486778 3 0.1489 0.8286 0.004 0.000 0.952 0.044
#> GSM486780 2 0.0657 0.5891 0.000 0.984 0.004 0.012
#> GSM486782 2 0.4679 0.4129 0.000 0.648 0.000 0.352
#> GSM486784 2 0.0336 0.5869 0.000 0.992 0.000 0.008
#> GSM486786 3 0.0992 0.8316 0.004 0.012 0.976 0.008
#> GSM486788 3 0.2443 0.8248 0.000 0.060 0.916 0.024
#> GSM486790 4 0.4746 0.2200 0.000 0.368 0.000 0.632
#> GSM486792 3 0.5649 0.3749 0.000 0.028 0.580 0.392
#> GSM486794 3 0.0779 0.8314 0.004 0.000 0.980 0.016
#> GSM486796 2 0.6215 0.1768 0.000 0.600 0.328 0.072
#> GSM486798 2 0.6744 0.4066 0.004 0.600 0.116 0.280
#> GSM486800 3 0.1807 0.8299 0.000 0.052 0.940 0.008
#> GSM486802 3 0.3542 0.7805 0.000 0.120 0.852 0.028
#> GSM486804 3 0.5007 0.5237 0.000 0.356 0.636 0.008
#> GSM486806 2 0.5588 0.3713 0.004 0.600 0.020 0.376
#> GSM486808 3 0.1114 0.8316 0.004 0.016 0.972 0.008
#> GSM486810 4 0.2216 0.5865 0.000 0.092 0.000 0.908
#> GSM486812 3 0.0779 0.8316 0.004 0.000 0.980 0.016
#> GSM486814 2 0.0927 0.5724 0.000 0.976 0.008 0.016
#> GSM486816 3 0.0657 0.8312 0.004 0.000 0.984 0.012
#> GSM486818 2 0.2197 0.5384 0.000 0.916 0.080 0.004
#> GSM486821 4 0.7235 0.2718 0.000 0.372 0.148 0.480
#> GSM486823 4 0.4222 0.4174 0.000 0.272 0.000 0.728
#> GSM486826 3 0.4343 0.6537 0.000 0.264 0.732 0.004
#> GSM486830 2 0.4985 0.2049 0.000 0.532 0.000 0.468
#> GSM486832 3 0.1936 0.8308 0.000 0.028 0.940 0.032
#> GSM486834 4 0.4921 0.5240 0.004 0.132 0.080 0.784
#> GSM486836 3 0.2342 0.8203 0.000 0.080 0.912 0.008
#> GSM486838 2 0.4964 0.5095 0.000 0.724 0.032 0.244
#> GSM486840 3 0.2654 0.8053 0.000 0.108 0.888 0.004
#> GSM486842 3 0.0524 0.8310 0.004 0.000 0.988 0.008
#> GSM486844 2 0.5137 -0.1035 0.000 0.544 0.452 0.004
#> GSM486846 2 0.4454 0.4627 0.000 0.692 0.000 0.308
#> GSM486848 3 0.1824 0.8282 0.000 0.060 0.936 0.004
#> GSM486850 2 0.4356 0.4828 0.000 0.708 0.000 0.292
#> GSM486852 4 0.7457 0.2976 0.000 0.220 0.276 0.504
#> GSM486854 2 0.4134 0.5059 0.000 0.740 0.000 0.260
#> GSM486856 2 0.0524 0.5791 0.000 0.988 0.008 0.004
#> GSM486858 2 0.4356 0.4791 0.000 0.708 0.000 0.292
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 5 0.3937 0.6656 0.000 0.004 0.252 0.008 0.736
#> GSM486737 2 0.6454 0.3332 0.000 0.488 0.304 0.208 0.000
#> GSM486739 5 0.3067 0.7029 0.000 0.012 0.140 0.004 0.844
#> GSM486741 3 0.6478 0.4787 0.000 0.196 0.536 0.260 0.008
#> GSM486743 2 0.5996 0.3611 0.000 0.548 0.072 0.360 0.020
#> GSM486745 5 0.5853 0.5295 0.004 0.248 0.068 0.032 0.648
#> GSM486747 1 0.5807 0.1084 0.484 0.000 0.424 0.092 0.000
#> GSM486749 4 0.4286 0.3475 0.000 0.004 0.260 0.716 0.020
#> GSM486751 4 0.6225 0.1374 0.124 0.000 0.400 0.472 0.004
#> GSM486753 4 0.7006 0.1418 0.000 0.232 0.212 0.520 0.036
#> GSM486755 3 0.7128 -0.0720 0.000 0.392 0.436 0.104 0.068
#> GSM486757 4 0.4918 0.4630 0.076 0.000 0.184 0.728 0.012
#> GSM486759 1 0.5855 0.5473 0.676 0.080 0.000 0.188 0.056
#> GSM486761 1 0.4610 0.6002 0.740 0.000 0.168 0.092 0.000
#> GSM486763 5 0.3096 0.6661 0.036 0.044 0.004 0.032 0.884
#> GSM486765 1 0.1857 0.7386 0.928 0.000 0.060 0.008 0.004
#> GSM486767 2 0.7359 0.1845 0.000 0.480 0.080 0.308 0.132
#> GSM486769 5 0.4347 0.5261 0.000 0.004 0.356 0.004 0.636
#> GSM486771 2 0.5207 0.4142 0.000 0.652 0.024 0.292 0.032
#> GSM486773 3 0.4976 0.0996 0.000 0.000 0.504 0.468 0.028
#> GSM486775 1 0.0912 0.7476 0.972 0.016 0.012 0.000 0.000
#> GSM486777 4 0.4551 0.2906 0.348 0.000 0.008 0.636 0.008
#> GSM486779 2 0.3578 0.6316 0.000 0.820 0.048 0.132 0.000
#> GSM486781 3 0.4132 0.5500 0.004 0.032 0.760 0.204 0.000
#> GSM486783 2 0.3778 0.6627 0.000 0.820 0.108 0.068 0.004
#> GSM486785 4 0.5069 -0.0114 0.452 0.008 0.020 0.520 0.000
#> GSM486787 1 0.4233 0.6857 0.788 0.144 0.000 0.012 0.056
#> GSM486789 3 0.4524 0.2742 0.000 0.020 0.644 0.000 0.336
#> GSM486791 5 0.4673 0.4866 0.228 0.052 0.000 0.004 0.716
#> GSM486793 1 0.3446 0.6922 0.840 0.000 0.036 0.116 0.008
#> GSM486795 4 0.5289 0.4667 0.056 0.156 0.000 0.728 0.060
#> GSM486797 4 0.3650 0.4463 0.028 0.000 0.176 0.796 0.000
#> GSM486799 1 0.1243 0.7422 0.960 0.028 0.000 0.004 0.008
#> GSM486801 4 0.8237 0.2206 0.292 0.260 0.000 0.332 0.116
#> GSM486803 4 0.7877 0.2265 0.192 0.320 0.000 0.396 0.092
#> GSM486805 4 0.4767 0.0730 0.020 0.000 0.420 0.560 0.000
#> GSM486807 1 0.3105 0.7134 0.864 0.000 0.088 0.044 0.004
#> GSM486809 5 0.3642 0.6789 0.000 0.000 0.232 0.008 0.760
#> GSM486811 1 0.3114 0.7234 0.868 0.012 0.004 0.096 0.020
#> GSM486813 2 0.4584 0.5923 0.000 0.788 0.048 0.104 0.060
#> GSM486815 1 0.2444 0.7420 0.912 0.000 0.036 0.024 0.028
#> GSM486817 4 0.4373 0.3101 0.004 0.300 0.004 0.684 0.008
#> GSM486819 4 0.6848 0.2126 0.056 0.100 0.000 0.508 0.336
#> GSM486822 3 0.3838 0.3972 0.000 0.004 0.716 0.000 0.280
#> GSM486824 2 0.6804 0.1365 0.240 0.584 0.004 0.108 0.064
#> GSM486828 3 0.5549 0.2557 0.008 0.008 0.548 0.400 0.036
#> GSM486831 1 0.4825 0.6437 0.764 0.052 0.000 0.048 0.136
#> GSM486833 3 0.6096 -0.1203 0.064 0.000 0.472 0.440 0.024
#> GSM486835 1 0.4732 0.6464 0.744 0.176 0.000 0.012 0.068
#> GSM486837 3 0.6316 0.4132 0.008 0.152 0.544 0.296 0.000
#> GSM486839 1 0.5606 0.2822 0.556 0.084 0.000 0.360 0.000
#> GSM486841 1 0.4530 0.3682 0.612 0.004 0.000 0.376 0.008
#> GSM486843 4 0.5312 0.3884 0.096 0.256 0.000 0.648 0.000
#> GSM486845 4 0.3878 0.3507 0.000 0.016 0.236 0.748 0.000
#> GSM486847 4 0.5442 0.1287 0.408 0.052 0.000 0.536 0.004
#> GSM486849 3 0.7268 0.3964 0.000 0.188 0.492 0.268 0.052
#> GSM486851 5 0.4336 0.6028 0.108 0.060 0.000 0.032 0.800
#> GSM486853 3 0.6150 0.4788 0.000 0.236 0.560 0.204 0.000
#> GSM486855 2 0.4024 0.5698 0.000 0.752 0.028 0.220 0.000
#> GSM486857 3 0.5100 0.2420 0.000 0.036 0.516 0.448 0.000
#> GSM486736 5 0.3635 0.6704 0.000 0.004 0.248 0.000 0.748
#> GSM486738 2 0.4060 0.4155 0.000 0.640 0.360 0.000 0.000
#> GSM486740 5 0.3081 0.7037 0.000 0.012 0.156 0.000 0.832
#> GSM486742 3 0.4551 0.3926 0.000 0.368 0.616 0.000 0.016
#> GSM486744 2 0.3819 0.5954 0.000 0.756 0.228 0.000 0.016
#> GSM486746 5 0.4958 0.6021 0.000 0.224 0.084 0.000 0.692
#> GSM486748 3 0.5382 0.3116 0.336 0.072 0.592 0.000 0.000
#> GSM486750 3 0.3844 0.5590 0.000 0.044 0.792 0.000 0.164
#> GSM486752 3 0.4164 0.4334 0.252 0.008 0.728 0.000 0.012
#> GSM486754 2 0.4942 0.2244 0.000 0.540 0.432 0.000 0.028
#> GSM486756 2 0.5171 0.1600 0.000 0.504 0.456 0.000 0.040
#> GSM486758 3 0.4481 0.3216 0.312 0.004 0.668 0.000 0.016
#> GSM486760 1 0.2878 0.7268 0.880 0.068 0.004 0.000 0.048
#> GSM486762 1 0.3109 0.6566 0.800 0.000 0.200 0.000 0.000
#> GSM486764 5 0.2507 0.6806 0.028 0.044 0.020 0.000 0.908
#> GSM486766 1 0.1965 0.7291 0.904 0.000 0.096 0.000 0.000
#> GSM486768 2 0.5125 0.5826 0.000 0.696 0.156 0.000 0.148
#> GSM486770 5 0.3969 0.6183 0.000 0.004 0.304 0.000 0.692
#> GSM486772 2 0.2983 0.6590 0.000 0.864 0.096 0.000 0.040
#> GSM486774 3 0.2635 0.6116 0.016 0.088 0.888 0.000 0.008
#> GSM486776 1 0.2074 0.7510 0.920 0.036 0.044 0.000 0.000
#> GSM486778 1 0.2158 0.7468 0.920 0.008 0.020 0.000 0.052
#> GSM486780 2 0.2813 0.6447 0.000 0.832 0.168 0.000 0.000
#> GSM486782 3 0.3242 0.5828 0.000 0.172 0.816 0.000 0.012
#> GSM486784 2 0.2605 0.6506 0.000 0.852 0.148 0.000 0.000
#> GSM486786 1 0.2377 0.7149 0.872 0.000 0.128 0.000 0.000
#> GSM486788 1 0.5243 0.5845 0.668 0.244 0.004 0.000 0.084
#> GSM486790 3 0.5139 0.4226 0.000 0.072 0.648 0.000 0.280
#> GSM486792 5 0.3671 0.5393 0.236 0.000 0.008 0.000 0.756
#> GSM486794 1 0.1831 0.7346 0.920 0.000 0.076 0.000 0.004
#> GSM486796 2 0.4368 0.4370 0.080 0.772 0.004 0.000 0.144
#> GSM486798 3 0.4884 0.5493 0.128 0.152 0.720 0.000 0.000
#> GSM486800 1 0.3122 0.7210 0.852 0.120 0.004 0.000 0.024
#> GSM486802 1 0.6125 0.3046 0.480 0.404 0.004 0.000 0.112
#> GSM486804 2 0.4871 0.2561 0.316 0.648 0.008 0.000 0.028
#> GSM486806 3 0.3105 0.5881 0.088 0.044 0.864 0.000 0.004
#> GSM486808 1 0.2583 0.7090 0.864 0.000 0.132 0.000 0.004
#> GSM486810 5 0.3990 0.6117 0.000 0.004 0.308 0.000 0.688
#> GSM486812 1 0.1518 0.7478 0.952 0.012 0.016 0.000 0.020
#> GSM486814 2 0.2439 0.6624 0.000 0.876 0.120 0.000 0.004
#> GSM486816 1 0.1892 0.7334 0.916 0.000 0.080 0.000 0.004
#> GSM486818 2 0.4698 0.5396 0.028 0.664 0.304 0.000 0.004
#> GSM486821 5 0.5429 0.3096 0.068 0.368 0.000 0.000 0.564
#> GSM486823 3 0.3916 0.4418 0.000 0.012 0.732 0.000 0.256
#> GSM486826 1 0.5175 0.4151 0.548 0.408 0.044 0.000 0.000
#> GSM486830 3 0.2798 0.6105 0.008 0.060 0.888 0.000 0.044
#> GSM486832 1 0.3384 0.7132 0.848 0.060 0.004 0.000 0.088
#> GSM486834 3 0.2922 0.5488 0.056 0.000 0.872 0.000 0.072
#> GSM486836 1 0.5460 0.5318 0.636 0.280 0.008 0.000 0.076
#> GSM486838 3 0.4151 0.4172 0.004 0.344 0.652 0.000 0.000
#> GSM486840 1 0.4704 0.2602 0.508 0.480 0.004 0.000 0.008
#> GSM486842 1 0.1408 0.7467 0.948 0.008 0.044 0.000 0.000
#> GSM486844 2 0.4352 0.4209 0.244 0.720 0.036 0.000 0.000
#> GSM486846 3 0.3636 0.5222 0.000 0.272 0.728 0.000 0.000
#> GSM486848 1 0.4617 0.5452 0.660 0.316 0.008 0.000 0.016
#> GSM486850 3 0.4533 0.2782 0.000 0.448 0.544 0.000 0.008
#> GSM486852 5 0.3593 0.6282 0.088 0.084 0.000 0.000 0.828
#> GSM486854 3 0.4030 0.4266 0.000 0.352 0.648 0.000 0.000
#> GSM486856 2 0.2329 0.6602 0.000 0.876 0.124 0.000 0.000
#> GSM486858 3 0.3366 0.5407 0.000 0.232 0.768 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 6 0.291 0.61000 0.000 0.000 0.012 0.156 0.004 0.828
#> GSM486737 2 0.617 0.39837 0.000 0.560 0.028 0.176 0.228 0.008
#> GSM486739 6 0.377 0.63814 0.004 0.008 0.088 0.096 0.000 0.804
#> GSM486741 4 0.728 0.14444 0.000 0.296 0.064 0.400 0.224 0.016
#> GSM486743 2 0.646 0.27016 0.000 0.440 0.168 0.024 0.360 0.008
#> GSM486745 6 0.651 0.49129 0.000 0.108 0.260 0.060 0.020 0.552
#> GSM486747 1 0.599 -0.00837 0.452 0.000 0.056 0.420 0.072 0.000
#> GSM486749 5 0.702 0.23754 0.000 0.028 0.096 0.240 0.520 0.116
#> GSM486751 5 0.721 0.15091 0.104 0.000 0.052 0.380 0.404 0.060
#> GSM486753 5 0.680 0.27043 0.000 0.128 0.040 0.216 0.556 0.060
#> GSM486755 2 0.780 0.27008 0.000 0.440 0.104 0.264 0.104 0.088
#> GSM486757 5 0.594 0.42701 0.096 0.004 0.060 0.144 0.668 0.028
#> GSM486759 1 0.612 0.13657 0.540 0.032 0.252 0.000 0.176 0.000
#> GSM486761 1 0.529 0.44273 0.676 0.000 0.048 0.172 0.104 0.000
#> GSM486763 6 0.469 0.60789 0.012 0.020 0.196 0.008 0.036 0.728
#> GSM486765 1 0.101 0.57799 0.960 0.000 0.004 0.036 0.000 0.000
#> GSM486767 2 0.823 0.10478 0.000 0.288 0.280 0.036 0.208 0.188
#> GSM486769 6 0.419 0.47316 0.000 0.004 0.032 0.256 0.004 0.704
#> GSM486771 2 0.693 0.40329 0.000 0.500 0.192 0.044 0.236 0.028
#> GSM486773 5 0.525 0.06810 0.000 0.004 0.012 0.464 0.468 0.052
#> GSM486775 1 0.192 0.57104 0.904 0.008 0.088 0.000 0.000 0.000
#> GSM486777 5 0.550 0.11591 0.384 0.000 0.080 0.004 0.520 0.012
#> GSM486779 2 0.490 0.45335 0.000 0.696 0.172 0.020 0.112 0.000
#> GSM486781 4 0.498 0.42026 0.000 0.040 0.052 0.728 0.156 0.024
#> GSM486783 2 0.350 0.55985 0.000 0.832 0.036 0.048 0.084 0.000
#> GSM486785 5 0.556 0.00496 0.440 0.008 0.052 0.024 0.476 0.000
#> GSM486787 1 0.525 0.26035 0.596 0.084 0.308 0.000 0.004 0.008
#> GSM486789 4 0.585 0.06558 0.000 0.060 0.044 0.460 0.004 0.432
#> GSM486791 6 0.545 0.42442 0.120 0.000 0.304 0.000 0.008 0.568
#> GSM486793 1 0.382 0.53948 0.812 0.000 0.056 0.012 0.104 0.016
#> GSM486795 5 0.501 0.26332 0.032 0.072 0.220 0.000 0.676 0.000
#> GSM486797 5 0.376 0.43875 0.048 0.004 0.008 0.148 0.792 0.000
#> GSM486799 1 0.293 0.51688 0.796 0.000 0.200 0.000 0.004 0.000
#> GSM486801 3 0.732 0.28150 0.304 0.072 0.340 0.000 0.276 0.008
#> GSM486803 5 0.738 -0.31892 0.164 0.112 0.304 0.000 0.408 0.012
#> GSM486805 5 0.517 0.16760 0.032 0.000 0.024 0.420 0.520 0.004
#> GSM486807 1 0.261 0.57370 0.884 0.000 0.032 0.068 0.016 0.000
#> GSM486809 6 0.362 0.61293 0.000 0.008 0.048 0.148 0.000 0.796
#> GSM486811 1 0.370 0.53749 0.784 0.000 0.164 0.008 0.044 0.000
#> GSM486813 2 0.446 0.51579 0.000 0.772 0.116 0.016 0.068 0.028
#> GSM486815 1 0.392 0.55301 0.804 0.000 0.120 0.040 0.020 0.016
#> GSM486817 5 0.522 0.25582 0.000 0.176 0.176 0.000 0.640 0.008
#> GSM486819 5 0.696 -0.05871 0.020 0.020 0.332 0.000 0.348 0.280
#> GSM486822 4 0.585 0.34692 0.000 0.060 0.048 0.576 0.012 0.304
#> GSM486824 3 0.689 0.46177 0.148 0.360 0.412 0.000 0.076 0.004
#> GSM486828 4 0.639 0.10995 0.000 0.048 0.040 0.512 0.344 0.056
#> GSM486831 1 0.548 0.25864 0.572 0.000 0.328 0.000 0.060 0.040
#> GSM486833 5 0.758 0.16368 0.100 0.000 0.060 0.344 0.400 0.096
#> GSM486835 1 0.479 0.36395 0.652 0.016 0.292 0.000 0.028 0.012
#> GSM486837 4 0.643 0.28356 0.024 0.152 0.028 0.548 0.248 0.000
#> GSM486839 1 0.671 -0.17461 0.412 0.064 0.160 0.000 0.364 0.000
#> GSM486841 1 0.487 0.34338 0.624 0.000 0.076 0.004 0.296 0.000
#> GSM486843 5 0.557 0.17155 0.060 0.112 0.176 0.000 0.652 0.000
#> GSM486845 5 0.523 0.29424 0.000 0.068 0.036 0.256 0.640 0.000
#> GSM486847 5 0.650 -0.04154 0.308 0.092 0.104 0.000 0.496 0.000
#> GSM486849 2 0.869 -0.08240 0.004 0.292 0.160 0.276 0.172 0.096
#> GSM486851 6 0.496 0.51799 0.024 0.008 0.340 0.000 0.024 0.604
#> GSM486853 4 0.645 0.29895 0.000 0.248 0.044 0.500 0.208 0.000
#> GSM486855 2 0.593 0.44473 0.000 0.584 0.124 0.048 0.244 0.000
#> GSM486857 5 0.523 0.10261 0.004 0.032 0.028 0.416 0.520 0.000
#> GSM486736 6 0.271 0.61264 0.000 0.000 0.008 0.160 0.000 0.832
#> GSM486738 2 0.385 0.51483 0.000 0.768 0.056 0.172 0.000 0.004
#> GSM486740 6 0.381 0.63970 0.000 0.016 0.096 0.088 0.000 0.800
#> GSM486742 2 0.592 0.07544 0.000 0.500 0.100 0.372 0.008 0.020
#> GSM486744 2 0.451 0.55916 0.000 0.724 0.152 0.116 0.000 0.008
#> GSM486746 6 0.640 0.49195 0.000 0.116 0.280 0.080 0.000 0.524
#> GSM486748 4 0.571 0.19601 0.380 0.044 0.064 0.512 0.000 0.000
#> GSM486750 4 0.672 0.39925 0.000 0.136 0.100 0.540 0.008 0.216
#> GSM486752 4 0.597 0.27889 0.292 0.016 0.052 0.584 0.004 0.052
#> GSM486754 2 0.570 0.27248 0.000 0.552 0.072 0.332 0.000 0.044
#> GSM486756 2 0.657 0.31040 0.000 0.492 0.148 0.300 0.004 0.056
#> GSM486758 4 0.733 0.17664 0.304 0.036 0.140 0.452 0.004 0.064
#> GSM486760 1 0.343 0.48995 0.756 0.016 0.228 0.000 0.000 0.000
#> GSM486762 1 0.436 0.46807 0.716 0.004 0.076 0.204 0.000 0.000
#> GSM486764 6 0.486 0.59659 0.028 0.052 0.228 0.004 0.000 0.688
#> GSM486766 1 0.231 0.56415 0.888 0.000 0.028 0.084 0.000 0.000
#> GSM486768 2 0.666 0.42767 0.000 0.528 0.216 0.112 0.000 0.144
#> GSM486770 6 0.443 0.50642 0.000 0.012 0.052 0.232 0.000 0.704
#> GSM486772 2 0.468 0.50574 0.000 0.708 0.196 0.076 0.000 0.020
#> GSM486774 4 0.406 0.49471 0.060 0.044 0.048 0.816 0.000 0.032
#> GSM486776 1 0.291 0.56434 0.856 0.028 0.104 0.012 0.000 0.000
#> GSM486778 1 0.375 0.54653 0.784 0.004 0.172 0.016 0.000 0.024
#> GSM486780 2 0.393 0.50468 0.000 0.756 0.172 0.072 0.000 0.000
#> GSM486782 4 0.314 0.52215 0.004 0.096 0.028 0.852 0.000 0.020
#> GSM486784 2 0.181 0.55209 0.000 0.920 0.020 0.060 0.000 0.000
#> GSM486786 1 0.468 0.49826 0.728 0.024 0.120 0.128 0.000 0.000
#> GSM486788 1 0.544 -0.04227 0.492 0.124 0.384 0.000 0.000 0.000
#> GSM486790 4 0.635 0.09107 0.000 0.092 0.072 0.436 0.000 0.400
#> GSM486792 6 0.481 0.53744 0.120 0.000 0.220 0.000 0.000 0.660
#> GSM486794 1 0.285 0.56467 0.872 0.000 0.064 0.044 0.000 0.020
#> GSM486796 2 0.521 -0.01684 0.040 0.520 0.416 0.004 0.000 0.020
#> GSM486798 4 0.680 0.41000 0.168 0.152 0.092 0.568 0.008 0.012
#> GSM486800 1 0.392 0.41713 0.692 0.024 0.284 0.000 0.000 0.000
#> GSM486802 1 0.614 -0.33174 0.416 0.188 0.384 0.000 0.000 0.012
#> GSM486804 3 0.624 0.44940 0.308 0.336 0.352 0.000 0.000 0.004
#> GSM486806 4 0.416 0.46996 0.128 0.020 0.044 0.788 0.000 0.020
#> GSM486808 1 0.344 0.53761 0.812 0.004 0.056 0.128 0.000 0.000
#> GSM486810 6 0.423 0.57689 0.000 0.016 0.060 0.176 0.000 0.748
#> GSM486812 1 0.257 0.56441 0.856 0.004 0.132 0.008 0.000 0.000
#> GSM486814 2 0.303 0.54527 0.000 0.856 0.076 0.056 0.000 0.012
#> GSM486816 1 0.387 0.53703 0.796 0.004 0.120 0.068 0.000 0.012
#> GSM486818 2 0.683 0.32822 0.068 0.484 0.240 0.204 0.000 0.004
#> GSM486821 6 0.654 0.27501 0.012 0.152 0.400 0.028 0.000 0.408
#> GSM486823 4 0.569 0.34246 0.000 0.044 0.056 0.576 0.008 0.316
#> GSM486826 1 0.638 -0.33810 0.404 0.360 0.216 0.020 0.000 0.000
#> GSM486830 4 0.464 0.51284 0.028 0.092 0.040 0.772 0.000 0.068
#> GSM486832 1 0.396 0.41236 0.684 0.000 0.292 0.000 0.000 0.024
#> GSM486834 4 0.585 0.38321 0.176 0.008 0.072 0.652 0.004 0.088
#> GSM486836 1 0.582 0.08844 0.528 0.092 0.352 0.016 0.000 0.012
#> GSM486838 4 0.518 0.30829 0.028 0.324 0.052 0.596 0.000 0.000
#> GSM486840 1 0.611 -0.47155 0.360 0.292 0.348 0.000 0.000 0.000
#> GSM486842 1 0.178 0.57971 0.920 0.000 0.064 0.016 0.000 0.000
#> GSM486844 2 0.650 -0.47784 0.240 0.436 0.296 0.028 0.000 0.000
#> GSM486846 4 0.495 0.36125 0.012 0.312 0.044 0.624 0.000 0.008
#> GSM486848 1 0.568 -0.04052 0.528 0.244 0.228 0.000 0.000 0.000
#> GSM486850 2 0.627 0.07554 0.004 0.464 0.156 0.356 0.004 0.016
#> GSM486852 6 0.457 0.54680 0.028 0.016 0.320 0.000 0.000 0.636
#> GSM486854 4 0.493 0.12781 0.000 0.428 0.064 0.508 0.000 0.000
#> GSM486856 2 0.388 0.53600 0.000 0.772 0.120 0.108 0.000 0.000
#> GSM486858 4 0.417 0.46195 0.004 0.204 0.052 0.736 0.000 0.004
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> MAD:NMF 116 1.00e+00 2.31e-05 2
#> MAD:NMF 101 4.46e-10 2.67e-01 3
#> MAD:NMF 71 3.32e-06 4.73e-03 4
#> MAD:NMF 65 2.39e-01 1.79e-05 5
#> MAD:NMF 38 4.34e-01 1.19e-03 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["ATC", "hclust"]
# you can also extract it by
# res = res_list["ATC:hclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'ATC' method.
#> Subgroups are detected by 'hclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 3.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 1.000 1.000 1.000 0.5047 0.496 0.496
#> 3 3 1.000 0.985 0.992 0.1226 0.936 0.870
#> 4 4 0.824 0.735 0.883 0.1751 0.898 0.763
#> 5 5 0.717 0.606 0.793 0.0689 0.964 0.897
#> 6 6 0.716 0.625 0.763 0.0575 0.873 0.633
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 3
#> attr(,"optional")
#> [1] 2
There is also optional best \(k\) = 2 that is worth to check.
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 1 0 1 1 0
#> GSM486737 1 0 1 1 0
#> GSM486739 1 0 1 1 0
#> GSM486741 1 0 1 1 0
#> GSM486743 1 0 1 1 0
#> GSM486745 1 0 1 1 0
#> GSM486747 1 0 1 1 0
#> GSM486749 1 0 1 1 0
#> GSM486751 1 0 1 1 0
#> GSM486753 1 0 1 1 0
#> GSM486755 1 0 1 1 0
#> GSM486757 1 0 1 1 0
#> GSM486759 1 0 1 1 0
#> GSM486761 1 0 1 1 0
#> GSM486763 1 0 1 1 0
#> GSM486765 1 0 1 1 0
#> GSM486767 1 0 1 1 0
#> GSM486769 1 0 1 1 0
#> GSM486771 1 0 1 1 0
#> GSM486773 1 0 1 1 0
#> GSM486775 1 0 1 1 0
#> GSM486777 1 0 1 1 0
#> GSM486779 1 0 1 1 0
#> GSM486781 1 0 1 1 0
#> GSM486783 1 0 1 1 0
#> GSM486785 1 0 1 1 0
#> GSM486787 1 0 1 1 0
#> GSM486789 1 0 1 1 0
#> GSM486791 1 0 1 1 0
#> GSM486793 1 0 1 1 0
#> GSM486795 1 0 1 1 0
#> GSM486797 1 0 1 1 0
#> GSM486799 1 0 1 1 0
#> GSM486801 1 0 1 1 0
#> GSM486803 1 0 1 1 0
#> GSM486805 1 0 1 1 0
#> GSM486807 1 0 1 1 0
#> GSM486809 1 0 1 1 0
#> GSM486811 1 0 1 1 0
#> GSM486813 1 0 1 1 0
#> GSM486815 1 0 1 1 0
#> GSM486817 1 0 1 1 0
#> GSM486819 1 0 1 1 0
#> GSM486822 1 0 1 1 0
#> GSM486824 1 0 1 1 0
#> GSM486828 1 0 1 1 0
#> GSM486831 1 0 1 1 0
#> GSM486833 1 0 1 1 0
#> GSM486835 1 0 1 1 0
#> GSM486837 1 0 1 1 0
#> GSM486839 1 0 1 1 0
#> GSM486841 1 0 1 1 0
#> GSM486843 1 0 1 1 0
#> GSM486845 1 0 1 1 0
#> GSM486847 1 0 1 1 0
#> GSM486849 1 0 1 1 0
#> GSM486851 1 0 1 1 0
#> GSM486853 1 0 1 1 0
#> GSM486855 1 0 1 1 0
#> GSM486857 1 0 1 1 0
#> GSM486736 2 0 1 0 1
#> GSM486738 2 0 1 0 1
#> GSM486740 2 0 1 0 1
#> GSM486742 2 0 1 0 1
#> GSM486744 2 0 1 0 1
#> GSM486746 2 0 1 0 1
#> GSM486748 2 0 1 0 1
#> GSM486750 2 0 1 0 1
#> GSM486752 2 0 1 0 1
#> GSM486754 2 0 1 0 1
#> GSM486756 2 0 1 0 1
#> GSM486758 2 0 1 0 1
#> GSM486760 2 0 1 0 1
#> GSM486762 2 0 1 0 1
#> GSM486764 2 0 1 0 1
#> GSM486766 2 0 1 0 1
#> GSM486768 2 0 1 0 1
#> GSM486770 2 0 1 0 1
#> GSM486772 2 0 1 0 1
#> GSM486774 2 0 1 0 1
#> GSM486776 2 0 1 0 1
#> GSM486778 2 0 1 0 1
#> GSM486780 2 0 1 0 1
#> GSM486782 2 0 1 0 1
#> GSM486784 2 0 1 0 1
#> GSM486786 2 0 1 0 1
#> GSM486788 2 0 1 0 1
#> GSM486790 2 0 1 0 1
#> GSM486792 2 0 1 0 1
#> GSM486794 2 0 1 0 1
#> GSM486796 2 0 1 0 1
#> GSM486798 2 0 1 0 1
#> GSM486800 2 0 1 0 1
#> GSM486802 2 0 1 0 1
#> GSM486804 2 0 1 0 1
#> GSM486806 2 0 1 0 1
#> GSM486808 2 0 1 0 1
#> GSM486810 2 0 1 0 1
#> GSM486812 2 0 1 0 1
#> GSM486814 2 0 1 0 1
#> GSM486816 2 0 1 0 1
#> GSM486818 2 0 1 0 1
#> GSM486821 2 0 1 0 1
#> GSM486823 2 0 1 0 1
#> GSM486826 2 0 1 0 1
#> GSM486830 2 0 1 0 1
#> GSM486832 2 0 1 0 1
#> GSM486834 2 0 1 0 1
#> GSM486836 2 0 1 0 1
#> GSM486838 2 0 1 0 1
#> GSM486840 2 0 1 0 1
#> GSM486842 2 0 1 0 1
#> GSM486844 2 0 1 0 1
#> GSM486846 2 0 1 0 1
#> GSM486848 2 0 1 0 1
#> GSM486850 2 0 1 0 1
#> GSM486852 2 0 1 0 1
#> GSM486854 2 0 1 0 1
#> GSM486856 2 0 1 0 1
#> GSM486858 2 0 1 0 1
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 1 0.000 1.000 1 0.000 0.000
#> GSM486737 1 0.000 1.000 1 0.000 0.000
#> GSM486739 1 0.000 1.000 1 0.000 0.000
#> GSM486741 1 0.000 1.000 1 0.000 0.000
#> GSM486743 1 0.000 1.000 1 0.000 0.000
#> GSM486745 1 0.000 1.000 1 0.000 0.000
#> GSM486747 1 0.000 1.000 1 0.000 0.000
#> GSM486749 1 0.000 1.000 1 0.000 0.000
#> GSM486751 1 0.000 1.000 1 0.000 0.000
#> GSM486753 1 0.000 1.000 1 0.000 0.000
#> GSM486755 1 0.000 1.000 1 0.000 0.000
#> GSM486757 1 0.000 1.000 1 0.000 0.000
#> GSM486759 1 0.000 1.000 1 0.000 0.000
#> GSM486761 1 0.000 1.000 1 0.000 0.000
#> GSM486763 1 0.000 1.000 1 0.000 0.000
#> GSM486765 1 0.000 1.000 1 0.000 0.000
#> GSM486767 1 0.000 1.000 1 0.000 0.000
#> GSM486769 1 0.000 1.000 1 0.000 0.000
#> GSM486771 1 0.000 1.000 1 0.000 0.000
#> GSM486773 1 0.000 1.000 1 0.000 0.000
#> GSM486775 1 0.000 1.000 1 0.000 0.000
#> GSM486777 1 0.000 1.000 1 0.000 0.000
#> GSM486779 1 0.000 1.000 1 0.000 0.000
#> GSM486781 1 0.000 1.000 1 0.000 0.000
#> GSM486783 1 0.000 1.000 1 0.000 0.000
#> GSM486785 1 0.000 1.000 1 0.000 0.000
#> GSM486787 1 0.000 1.000 1 0.000 0.000
#> GSM486789 1 0.000 1.000 1 0.000 0.000
#> GSM486791 1 0.000 1.000 1 0.000 0.000
#> GSM486793 1 0.000 1.000 1 0.000 0.000
#> GSM486795 1 0.000 1.000 1 0.000 0.000
#> GSM486797 1 0.000 1.000 1 0.000 0.000
#> GSM486799 1 0.000 1.000 1 0.000 0.000
#> GSM486801 1 0.000 1.000 1 0.000 0.000
#> GSM486803 1 0.000 1.000 1 0.000 0.000
#> GSM486805 1 0.000 1.000 1 0.000 0.000
#> GSM486807 1 0.000 1.000 1 0.000 0.000
#> GSM486809 1 0.000 1.000 1 0.000 0.000
#> GSM486811 1 0.000 1.000 1 0.000 0.000
#> GSM486813 1 0.000 1.000 1 0.000 0.000
#> GSM486815 1 0.000 1.000 1 0.000 0.000
#> GSM486817 1 0.000 1.000 1 0.000 0.000
#> GSM486819 1 0.000 1.000 1 0.000 0.000
#> GSM486822 1 0.000 1.000 1 0.000 0.000
#> GSM486824 1 0.000 1.000 1 0.000 0.000
#> GSM486828 1 0.000 1.000 1 0.000 0.000
#> GSM486831 1 0.000 1.000 1 0.000 0.000
#> GSM486833 1 0.000 1.000 1 0.000 0.000
#> GSM486835 1 0.000 1.000 1 0.000 0.000
#> GSM486837 1 0.000 1.000 1 0.000 0.000
#> GSM486839 1 0.000 1.000 1 0.000 0.000
#> GSM486841 1 0.000 1.000 1 0.000 0.000
#> GSM486843 1 0.000 1.000 1 0.000 0.000
#> GSM486845 1 0.000 1.000 1 0.000 0.000
#> GSM486847 1 0.000 1.000 1 0.000 0.000
#> GSM486849 1 0.000 1.000 1 0.000 0.000
#> GSM486851 1 0.000 1.000 1 0.000 0.000
#> GSM486853 1 0.000 1.000 1 0.000 0.000
#> GSM486855 1 0.000 1.000 1 0.000 0.000
#> GSM486857 1 0.000 1.000 1 0.000 0.000
#> GSM486736 2 0.000 0.918 0 1.000 0.000
#> GSM486738 3 0.000 0.992 0 0.000 1.000
#> GSM486740 2 0.000 0.918 0 1.000 0.000
#> GSM486742 3 0.000 0.992 0 0.000 1.000
#> GSM486744 3 0.164 0.958 0 0.044 0.956
#> GSM486746 2 0.000 0.918 0 1.000 0.000
#> GSM486748 3 0.000 0.992 0 0.000 1.000
#> GSM486750 3 0.000 0.992 0 0.000 1.000
#> GSM486752 3 0.000 0.992 0 0.000 1.000
#> GSM486754 3 0.164 0.958 0 0.044 0.956
#> GSM486756 2 0.000 0.918 0 1.000 0.000
#> GSM486758 3 0.000 0.992 0 0.000 1.000
#> GSM486760 3 0.000 0.992 0 0.000 1.000
#> GSM486762 3 0.000 0.992 0 0.000 1.000
#> GSM486764 3 0.000 0.992 0 0.000 1.000
#> GSM486766 3 0.000 0.992 0 0.000 1.000
#> GSM486768 3 0.164 0.958 0 0.044 0.956
#> GSM486770 3 0.000 0.992 0 0.000 1.000
#> GSM486772 3 0.000 0.992 0 0.000 1.000
#> GSM486774 3 0.000 0.992 0 0.000 1.000
#> GSM486776 3 0.000 0.992 0 0.000 1.000
#> GSM486778 3 0.000 0.992 0 0.000 1.000
#> GSM486780 3 0.000 0.992 0 0.000 1.000
#> GSM486782 3 0.164 0.958 0 0.044 0.956
#> GSM486784 3 0.000 0.992 0 0.000 1.000
#> GSM486786 3 0.000 0.992 0 0.000 1.000
#> GSM486788 3 0.000 0.992 0 0.000 1.000
#> GSM486790 2 0.470 0.794 0 0.788 0.212
#> GSM486792 2 0.000 0.918 0 1.000 0.000
#> GSM486794 3 0.153 0.961 0 0.040 0.960
#> GSM486796 3 0.000 0.992 0 0.000 1.000
#> GSM486798 3 0.000 0.992 0 0.000 1.000
#> GSM486800 3 0.000 0.992 0 0.000 1.000
#> GSM486802 3 0.000 0.992 0 0.000 1.000
#> GSM486804 3 0.000 0.992 0 0.000 1.000
#> GSM486806 3 0.000 0.992 0 0.000 1.000
#> GSM486808 3 0.000 0.992 0 0.000 1.000
#> GSM486810 3 0.103 0.975 0 0.024 0.976
#> GSM486812 3 0.000 0.992 0 0.000 1.000
#> GSM486814 3 0.164 0.958 0 0.044 0.956
#> GSM486816 3 0.000 0.992 0 0.000 1.000
#> GSM486818 2 0.000 0.918 0 1.000 0.000
#> GSM486821 2 0.470 0.794 0 0.788 0.212
#> GSM486823 3 0.000 0.992 0 0.000 1.000
#> GSM486826 3 0.000 0.992 0 0.000 1.000
#> GSM486830 2 0.470 0.794 0 0.788 0.212
#> GSM486832 3 0.000 0.992 0 0.000 1.000
#> GSM486834 3 0.129 0.968 0 0.032 0.968
#> GSM486836 3 0.000 0.992 0 0.000 1.000
#> GSM486838 3 0.000 0.992 0 0.000 1.000
#> GSM486840 3 0.000 0.992 0 0.000 1.000
#> GSM486842 3 0.000 0.992 0 0.000 1.000
#> GSM486844 3 0.000 0.992 0 0.000 1.000
#> GSM486846 3 0.164 0.958 0 0.044 0.956
#> GSM486848 3 0.000 0.992 0 0.000 1.000
#> GSM486850 3 0.000 0.992 0 0.000 1.000
#> GSM486852 3 0.000 0.992 0 0.000 1.000
#> GSM486854 3 0.000 0.992 0 0.000 1.000
#> GSM486856 3 0.000 0.992 0 0.000 1.000
#> GSM486858 3 0.000 0.992 0 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 4 0.4500 0.4038 0.316 0.000 0.000 0.684
#> GSM486737 1 0.4661 0.4916 0.652 0.000 0.000 0.348
#> GSM486739 4 0.4500 0.4038 0.316 0.000 0.000 0.684
#> GSM486741 4 0.4998 -0.1199 0.488 0.000 0.000 0.512
#> GSM486743 4 0.4855 0.1631 0.400 0.000 0.000 0.600
#> GSM486745 4 0.4500 0.4038 0.316 0.000 0.000 0.684
#> GSM486747 1 0.4998 0.1468 0.512 0.000 0.000 0.488
#> GSM486749 1 0.0188 0.7196 0.996 0.000 0.000 0.004
#> GSM486751 1 0.0000 0.7225 1.000 0.000 0.000 0.000
#> GSM486753 1 0.4972 0.2532 0.544 0.000 0.000 0.456
#> GSM486755 4 0.0188 0.5417 0.004 0.000 0.000 0.996
#> GSM486757 1 0.4382 0.5679 0.704 0.000 0.000 0.296
#> GSM486759 1 0.0000 0.7225 1.000 0.000 0.000 0.000
#> GSM486761 1 0.4998 0.1468 0.512 0.000 0.000 0.488
#> GSM486763 1 0.0336 0.7187 0.992 0.000 0.000 0.008
#> GSM486765 4 0.4996 -0.1056 0.484 0.000 0.000 0.516
#> GSM486767 4 0.4989 -0.0642 0.472 0.000 0.000 0.528
#> GSM486769 1 0.0336 0.7187 0.992 0.000 0.000 0.008
#> GSM486771 1 0.0000 0.7225 1.000 0.000 0.000 0.000
#> GSM486773 1 0.4985 0.2121 0.532 0.000 0.000 0.468
#> GSM486775 4 0.4996 -0.1056 0.484 0.000 0.000 0.516
#> GSM486777 1 0.0000 0.7225 1.000 0.000 0.000 0.000
#> GSM486779 1 0.4382 0.5679 0.704 0.000 0.000 0.296
#> GSM486781 4 0.3837 0.4775 0.224 0.000 0.000 0.776
#> GSM486783 1 0.4382 0.5679 0.704 0.000 0.000 0.296
#> GSM486785 1 0.4382 0.5679 0.704 0.000 0.000 0.296
#> GSM486787 1 0.0000 0.7225 1.000 0.000 0.000 0.000
#> GSM486789 4 0.0188 0.5429 0.004 0.000 0.000 0.996
#> GSM486791 4 0.4500 0.4038 0.316 0.000 0.000 0.684
#> GSM486793 4 0.4382 0.3848 0.296 0.000 0.000 0.704
#> GSM486795 1 0.0000 0.7225 1.000 0.000 0.000 0.000
#> GSM486797 1 0.4985 0.2121 0.532 0.000 0.000 0.468
#> GSM486799 1 0.4999 0.1312 0.508 0.000 0.000 0.492
#> GSM486801 1 0.0000 0.7225 1.000 0.000 0.000 0.000
#> GSM486803 1 0.4382 0.5679 0.704 0.000 0.000 0.296
#> GSM486805 1 0.4898 0.3669 0.584 0.000 0.000 0.416
#> GSM486807 1 0.2469 0.6801 0.892 0.000 0.000 0.108
#> GSM486809 1 0.4998 0.1464 0.512 0.000 0.000 0.488
#> GSM486811 1 0.0000 0.7225 1.000 0.000 0.000 0.000
#> GSM486813 4 0.4134 0.4384 0.260 0.000 0.000 0.740
#> GSM486815 1 0.4382 0.5679 0.704 0.000 0.000 0.296
#> GSM486817 4 0.2647 0.5194 0.120 0.000 0.000 0.880
#> GSM486819 4 0.0188 0.5417 0.004 0.000 0.000 0.996
#> GSM486822 1 0.0336 0.7187 0.992 0.000 0.000 0.008
#> GSM486824 1 0.4382 0.5679 0.704 0.000 0.000 0.296
#> GSM486828 4 0.1118 0.5643 0.036 0.000 0.000 0.964
#> GSM486831 1 0.0469 0.7219 0.988 0.000 0.000 0.012
#> GSM486833 1 0.2011 0.6269 0.920 0.000 0.000 0.080
#> GSM486835 1 0.0000 0.7225 1.000 0.000 0.000 0.000
#> GSM486837 1 0.4454 0.5537 0.692 0.000 0.000 0.308
#> GSM486839 1 0.0336 0.7225 0.992 0.000 0.000 0.008
#> GSM486841 1 0.0000 0.7225 1.000 0.000 0.000 0.000
#> GSM486843 1 0.0000 0.7225 1.000 0.000 0.000 0.000
#> GSM486845 1 0.0707 0.7186 0.980 0.000 0.000 0.020
#> GSM486847 1 0.0469 0.7219 0.988 0.000 0.000 0.012
#> GSM486849 1 0.0336 0.7196 0.992 0.000 0.000 0.008
#> GSM486851 1 0.0000 0.7225 1.000 0.000 0.000 0.000
#> GSM486853 1 0.4522 0.5413 0.680 0.000 0.000 0.320
#> GSM486855 1 0.0469 0.7219 0.988 0.000 0.000 0.012
#> GSM486857 1 0.4382 0.5679 0.704 0.000 0.000 0.296
#> GSM486736 2 0.0000 0.8753 0.000 1.000 0.000 0.000
#> GSM486738 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486740 2 0.0000 0.8753 0.000 1.000 0.000 0.000
#> GSM486742 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486744 3 0.1302 0.9576 0.000 0.044 0.956 0.000
#> GSM486746 2 0.0000 0.8753 0.000 1.000 0.000 0.000
#> GSM486748 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486750 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486752 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486754 3 0.1302 0.9576 0.000 0.044 0.956 0.000
#> GSM486756 2 0.0000 0.8753 0.000 1.000 0.000 0.000
#> GSM486758 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486760 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486762 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486764 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486766 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486768 3 0.1302 0.9576 0.000 0.044 0.956 0.000
#> GSM486770 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486772 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486774 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486776 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486778 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486780 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486782 3 0.1302 0.9576 0.000 0.044 0.956 0.000
#> GSM486784 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486786 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486788 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486790 2 0.3726 0.7571 0.000 0.788 0.212 0.000
#> GSM486792 2 0.0000 0.8753 0.000 1.000 0.000 0.000
#> GSM486794 3 0.1211 0.9611 0.000 0.040 0.960 0.000
#> GSM486796 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486798 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486800 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486802 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486804 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486806 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486808 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486810 3 0.0817 0.9747 0.000 0.024 0.976 0.000
#> GSM486812 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486814 3 0.1302 0.9576 0.000 0.044 0.956 0.000
#> GSM486816 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486818 2 0.0000 0.8753 0.000 1.000 0.000 0.000
#> GSM486821 2 0.3726 0.7571 0.000 0.788 0.212 0.000
#> GSM486823 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486826 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486830 2 0.3726 0.7571 0.000 0.788 0.212 0.000
#> GSM486832 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486834 3 0.1022 0.9683 0.000 0.032 0.968 0.000
#> GSM486836 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486838 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486840 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486842 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486844 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486846 3 0.1302 0.9576 0.000 0.044 0.956 0.000
#> GSM486848 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486850 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486852 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486854 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486856 3 0.0000 0.9922 0.000 0.000 1.000 0.000
#> GSM486858 3 0.0000 0.9922 0.000 0.000 1.000 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 4 0.5049 0.59830 0.296 0.000 0.000 0.644 0.060
#> GSM486737 1 0.4252 0.36145 0.652 0.000 0.000 0.008 0.340
#> GSM486739 4 0.5049 0.59830 0.296 0.000 0.000 0.644 0.060
#> GSM486741 1 0.5504 -0.29756 0.488 0.000 0.000 0.064 0.448
#> GSM486743 5 0.6236 0.53323 0.400 0.000 0.000 0.144 0.456
#> GSM486745 4 0.5049 0.59830 0.296 0.000 0.000 0.644 0.060
#> GSM486747 1 0.4743 -0.12884 0.512 0.000 0.000 0.016 0.472
#> GSM486749 1 0.0162 0.65677 0.996 0.000 0.000 0.004 0.000
#> GSM486751 1 0.0000 0.65957 1.000 0.000 0.000 0.000 0.000
#> GSM486753 1 0.5236 0.00041 0.544 0.000 0.000 0.048 0.408
#> GSM486755 4 0.4182 0.40816 0.000 0.000 0.000 0.600 0.400
#> GSM486757 1 0.4161 0.47432 0.704 0.000 0.000 0.016 0.280
#> GSM486759 1 0.0000 0.65957 1.000 0.000 0.000 0.000 0.000
#> GSM486761 1 0.4743 -0.12884 0.512 0.000 0.000 0.016 0.472
#> GSM486763 1 0.0290 0.65502 0.992 0.000 0.000 0.008 0.000
#> GSM486765 1 0.5178 -0.26180 0.484 0.000 0.000 0.040 0.476
#> GSM486767 1 0.5459 -0.33911 0.472 0.000 0.000 0.060 0.468
#> GSM486769 1 0.0290 0.65502 0.992 0.000 0.000 0.008 0.000
#> GSM486771 1 0.0000 0.65957 1.000 0.000 0.000 0.000 0.000
#> GSM486773 1 0.4437 -0.04186 0.532 0.000 0.000 0.004 0.464
#> GSM486775 1 0.5178 -0.26180 0.484 0.000 0.000 0.040 0.476
#> GSM486777 1 0.0000 0.65957 1.000 0.000 0.000 0.000 0.000
#> GSM486779 1 0.4161 0.47432 0.704 0.000 0.000 0.016 0.280
#> GSM486781 5 0.6621 0.64634 0.224 0.000 0.000 0.348 0.428
#> GSM486783 1 0.4161 0.47432 0.704 0.000 0.000 0.016 0.280
#> GSM486785 1 0.4161 0.47432 0.704 0.000 0.000 0.016 0.280
#> GSM486787 1 0.0000 0.65957 1.000 0.000 0.000 0.000 0.000
#> GSM486789 4 0.4390 0.36186 0.004 0.000 0.000 0.568 0.428
#> GSM486791 4 0.5049 0.59830 0.296 0.000 0.000 0.644 0.060
#> GSM486793 5 0.6627 0.76456 0.296 0.000 0.000 0.252 0.452
#> GSM486795 1 0.0000 0.65957 1.000 0.000 0.000 0.000 0.000
#> GSM486797 1 0.4437 -0.04186 0.532 0.000 0.000 0.004 0.464
#> GSM486799 1 0.4826 -0.14807 0.508 0.000 0.000 0.020 0.472
#> GSM486801 1 0.0000 0.65957 1.000 0.000 0.000 0.000 0.000
#> GSM486803 1 0.4161 0.47432 0.704 0.000 0.000 0.016 0.280
#> GSM486805 1 0.5644 0.17199 0.584 0.000 0.000 0.100 0.316
#> GSM486807 1 0.2448 0.61632 0.892 0.000 0.000 0.020 0.088
#> GSM486809 1 0.5334 -0.16308 0.512 0.000 0.000 0.052 0.436
#> GSM486811 1 0.0000 0.65957 1.000 0.000 0.000 0.000 0.000
#> GSM486813 5 0.6691 0.71663 0.260 0.000 0.000 0.312 0.428
#> GSM486815 1 0.4161 0.47432 0.704 0.000 0.000 0.016 0.280
#> GSM486817 4 0.5263 0.53642 0.100 0.000 0.000 0.660 0.240
#> GSM486819 4 0.4201 0.39944 0.000 0.000 0.000 0.592 0.408
#> GSM486822 1 0.0290 0.65502 0.992 0.000 0.000 0.008 0.000
#> GSM486824 1 0.4161 0.47432 0.704 0.000 0.000 0.016 0.280
#> GSM486828 4 0.4989 0.28778 0.032 0.000 0.000 0.552 0.416
#> GSM486831 1 0.0404 0.65847 0.988 0.000 0.000 0.000 0.012
#> GSM486833 1 0.1908 0.55221 0.908 0.000 0.000 0.092 0.000
#> GSM486835 1 0.0000 0.65957 1.000 0.000 0.000 0.000 0.000
#> GSM486837 1 0.4297 0.45567 0.692 0.000 0.000 0.020 0.288
#> GSM486839 1 0.0290 0.65916 0.992 0.000 0.000 0.000 0.008
#> GSM486841 1 0.0000 0.65957 1.000 0.000 0.000 0.000 0.000
#> GSM486843 1 0.0000 0.65957 1.000 0.000 0.000 0.000 0.000
#> GSM486845 1 0.0693 0.65553 0.980 0.000 0.000 0.008 0.012
#> GSM486847 1 0.0404 0.65847 0.988 0.000 0.000 0.000 0.012
#> GSM486849 1 0.0671 0.64933 0.980 0.000 0.000 0.016 0.004
#> GSM486851 1 0.0000 0.65957 1.000 0.000 0.000 0.000 0.000
#> GSM486853 1 0.4485 0.43973 0.680 0.000 0.000 0.028 0.292
#> GSM486855 1 0.0404 0.65847 0.988 0.000 0.000 0.000 0.012
#> GSM486857 1 0.4161 0.47432 0.704 0.000 0.000 0.016 0.280
#> GSM486736 2 0.5518 0.82663 0.000 0.544 0.000 0.072 0.384
#> GSM486738 3 0.1822 0.83058 0.000 0.036 0.936 0.024 0.004
#> GSM486740 2 0.5518 0.82663 0.000 0.544 0.000 0.072 0.384
#> GSM486742 3 0.0404 0.84421 0.000 0.000 0.988 0.012 0.000
#> GSM486744 3 0.4044 0.65388 0.000 0.252 0.732 0.012 0.004
#> GSM486746 2 0.5518 0.82663 0.000 0.544 0.000 0.072 0.384
#> GSM486748 3 0.0510 0.84388 0.000 0.000 0.984 0.016 0.000
#> GSM486750 3 0.5365 0.69681 0.000 0.000 0.664 0.204 0.132
#> GSM486752 3 0.5365 0.69681 0.000 0.000 0.664 0.204 0.132
#> GSM486754 3 0.4044 0.65388 0.000 0.252 0.732 0.012 0.004
#> GSM486756 2 0.4204 0.82748 0.000 0.756 0.000 0.048 0.196
#> GSM486758 3 0.0566 0.84138 0.000 0.000 0.984 0.012 0.004
#> GSM486760 3 0.5365 0.69681 0.000 0.000 0.664 0.204 0.132
#> GSM486762 3 0.0566 0.84138 0.000 0.000 0.984 0.012 0.004
#> GSM486764 3 0.0798 0.84261 0.000 0.000 0.976 0.016 0.008
#> GSM486766 3 0.0290 0.84394 0.000 0.000 0.992 0.008 0.000
#> GSM486768 3 0.4044 0.65388 0.000 0.252 0.732 0.012 0.004
#> GSM486770 3 0.5365 0.69681 0.000 0.000 0.664 0.204 0.132
#> GSM486772 3 0.5365 0.69681 0.000 0.000 0.664 0.204 0.132
#> GSM486774 3 0.0693 0.84217 0.000 0.000 0.980 0.012 0.008
#> GSM486776 3 0.0566 0.84138 0.000 0.000 0.984 0.012 0.004
#> GSM486778 3 0.5365 0.69681 0.000 0.000 0.664 0.204 0.132
#> GSM486780 3 0.0566 0.84138 0.000 0.000 0.984 0.012 0.004
#> GSM486782 3 0.4044 0.65388 0.000 0.252 0.732 0.012 0.004
#> GSM486784 3 0.0162 0.84380 0.000 0.000 0.996 0.000 0.004
#> GSM486786 3 0.0798 0.84261 0.000 0.000 0.976 0.016 0.008
#> GSM486788 3 0.5365 0.69681 0.000 0.000 0.664 0.204 0.132
#> GSM486790 2 0.0000 0.76046 0.000 1.000 0.000 0.000 0.000
#> GSM486792 2 0.5500 0.82669 0.000 0.552 0.000 0.072 0.376
#> GSM486794 3 0.4017 0.65829 0.000 0.248 0.736 0.012 0.004
#> GSM486796 3 0.5365 0.69681 0.000 0.000 0.664 0.204 0.132
#> GSM486798 3 0.0162 0.84380 0.000 0.000 0.996 0.000 0.004
#> GSM486800 3 0.2504 0.81799 0.000 0.000 0.896 0.064 0.040
#> GSM486802 3 0.5365 0.69681 0.000 0.000 0.664 0.204 0.132
#> GSM486804 3 0.0798 0.84261 0.000 0.000 0.976 0.016 0.008
#> GSM486806 3 0.0854 0.83899 0.000 0.008 0.976 0.012 0.004
#> GSM486808 3 0.0566 0.84138 0.000 0.000 0.984 0.012 0.004
#> GSM486810 3 0.2976 0.76525 0.000 0.132 0.852 0.012 0.004
#> GSM486812 3 0.5365 0.69681 0.000 0.000 0.664 0.204 0.132
#> GSM486814 3 0.4044 0.65388 0.000 0.252 0.732 0.012 0.004
#> GSM486816 3 0.0566 0.84138 0.000 0.000 0.984 0.012 0.004
#> GSM486818 2 0.4204 0.82748 0.000 0.756 0.000 0.048 0.196
#> GSM486821 2 0.0000 0.76046 0.000 1.000 0.000 0.000 0.000
#> GSM486823 3 0.5365 0.69681 0.000 0.000 0.664 0.204 0.132
#> GSM486826 3 0.0798 0.84261 0.000 0.000 0.976 0.016 0.008
#> GSM486830 2 0.0000 0.76046 0.000 1.000 0.000 0.000 0.000
#> GSM486832 3 0.0566 0.84138 0.000 0.000 0.984 0.012 0.004
#> GSM486834 3 0.3597 0.72559 0.000 0.180 0.800 0.012 0.008
#> GSM486836 3 0.2653 0.81172 0.000 0.000 0.880 0.096 0.024
#> GSM486838 3 0.0693 0.84217 0.000 0.000 0.980 0.012 0.008
#> GSM486840 3 0.0324 0.84402 0.000 0.000 0.992 0.004 0.004
#> GSM486842 3 0.4994 0.72106 0.000 0.000 0.704 0.184 0.112
#> GSM486844 3 0.0798 0.84261 0.000 0.000 0.976 0.016 0.008
#> GSM486846 3 0.4044 0.65388 0.000 0.252 0.732 0.012 0.004
#> GSM486848 3 0.0566 0.84138 0.000 0.000 0.984 0.012 0.004
#> GSM486850 3 0.5365 0.69681 0.000 0.000 0.664 0.204 0.132
#> GSM486852 3 0.5197 0.70657 0.000 0.000 0.680 0.204 0.116
#> GSM486854 3 0.0000 0.84344 0.000 0.000 1.000 0.000 0.000
#> GSM486856 3 0.0162 0.84380 0.000 0.000 0.996 0.000 0.004
#> GSM486858 3 0.0451 0.84425 0.000 0.000 0.988 0.004 0.008
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 5 0.3390 0.6092 0.000 0.296 0.000 0.000 0.704 0.000
#> GSM486737 2 0.4175 -0.3724 0.000 0.524 0.000 0.464 0.012 0.000
#> GSM486739 5 0.3390 0.6092 0.000 0.296 0.000 0.000 0.704 0.000
#> GSM486741 4 0.5449 0.7126 0.000 0.368 0.000 0.504 0.128 0.000
#> GSM486743 4 0.5662 0.6558 0.000 0.280 0.000 0.524 0.196 0.000
#> GSM486745 5 0.3390 0.6092 0.000 0.296 0.000 0.000 0.704 0.000
#> GSM486747 4 0.4066 0.7805 0.000 0.392 0.000 0.596 0.012 0.000
#> GSM486749 2 0.0146 0.7386 0.000 0.996 0.000 0.000 0.004 0.000
#> GSM486751 2 0.0000 0.7414 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486753 4 0.4366 0.6909 0.000 0.428 0.000 0.548 0.024 0.000
#> GSM486755 5 0.2378 0.6141 0.000 0.000 0.000 0.152 0.848 0.000
#> GSM486757 2 0.3841 0.0290 0.000 0.616 0.000 0.380 0.004 0.000
#> GSM486759 2 0.0000 0.7414 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486761 4 0.4066 0.7805 0.000 0.392 0.000 0.596 0.012 0.000
#> GSM486763 2 0.0260 0.7367 0.000 0.992 0.000 0.000 0.008 0.000
#> GSM486765 4 0.3992 0.7907 0.000 0.364 0.000 0.624 0.012 0.000
#> GSM486767 4 0.4193 0.7832 0.000 0.352 0.000 0.624 0.024 0.000
#> GSM486769 2 0.0260 0.7367 0.000 0.992 0.000 0.000 0.008 0.000
#> GSM486771 2 0.0000 0.7414 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486773 4 0.4109 0.7520 0.000 0.412 0.000 0.576 0.012 0.000
#> GSM486775 4 0.3992 0.7907 0.000 0.364 0.000 0.624 0.012 0.000
#> GSM486777 2 0.0000 0.7414 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486779 2 0.3841 0.0290 0.000 0.616 0.000 0.380 0.004 0.000
#> GSM486781 5 0.5754 -0.0122 0.000 0.188 0.000 0.328 0.484 0.000
#> GSM486783 2 0.3930 -0.0949 0.000 0.576 0.000 0.420 0.004 0.000
#> GSM486785 2 0.3830 0.0439 0.000 0.620 0.000 0.376 0.004 0.000
#> GSM486787 2 0.0000 0.7414 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486789 5 0.3126 0.5795 0.000 0.000 0.000 0.248 0.752 0.000
#> GSM486791 5 0.3390 0.6092 0.000 0.296 0.000 0.000 0.704 0.000
#> GSM486793 4 0.6060 0.3341 0.000 0.260 0.000 0.376 0.364 0.000
#> GSM486795 2 0.0000 0.7414 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486797 4 0.4109 0.7520 0.000 0.412 0.000 0.576 0.012 0.000
#> GSM486799 4 0.4057 0.7837 0.000 0.388 0.000 0.600 0.012 0.000
#> GSM486801 2 0.0000 0.7414 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486803 2 0.3830 0.0439 0.000 0.620 0.000 0.376 0.004 0.000
#> GSM486805 2 0.5570 -0.1984 0.000 0.552 0.000 0.232 0.216 0.000
#> GSM486807 2 0.2362 0.6048 0.000 0.860 0.000 0.136 0.004 0.000
#> GSM486809 4 0.4379 0.7678 0.000 0.396 0.000 0.576 0.028 0.000
#> GSM486811 2 0.0000 0.7414 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486813 4 0.5578 0.0808 0.000 0.140 0.000 0.456 0.404 0.000
#> GSM486815 2 0.3975 -0.1556 0.000 0.544 0.000 0.452 0.004 0.000
#> GSM486817 5 0.2510 0.6193 0.000 0.100 0.000 0.028 0.872 0.000
#> GSM486819 5 0.2491 0.6137 0.000 0.000 0.000 0.164 0.836 0.000
#> GSM486822 2 0.0260 0.7367 0.000 0.992 0.000 0.000 0.008 0.000
#> GSM486824 2 0.3975 -0.1556 0.000 0.544 0.000 0.452 0.004 0.000
#> GSM486828 5 0.3301 0.6092 0.000 0.024 0.000 0.188 0.788 0.000
#> GSM486831 2 0.0458 0.7347 0.000 0.984 0.000 0.016 0.000 0.000
#> GSM486833 2 0.1714 0.6311 0.000 0.908 0.000 0.000 0.092 0.000
#> GSM486835 2 0.0000 0.7414 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486837 2 0.3862 -0.0143 0.000 0.608 0.000 0.388 0.004 0.000
#> GSM486839 2 0.0363 0.7364 0.000 0.988 0.000 0.012 0.000 0.000
#> GSM486841 2 0.0000 0.7414 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486843 2 0.0000 0.7414 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486845 2 0.0622 0.7353 0.000 0.980 0.000 0.012 0.008 0.000
#> GSM486847 2 0.0458 0.7347 0.000 0.984 0.000 0.016 0.000 0.000
#> GSM486849 2 0.0603 0.7289 0.000 0.980 0.000 0.004 0.016 0.000
#> GSM486851 2 0.0000 0.7414 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486853 2 0.4093 -0.1004 0.000 0.584 0.000 0.404 0.012 0.000
#> GSM486855 2 0.0363 0.7367 0.000 0.988 0.000 0.012 0.000 0.000
#> GSM486857 2 0.3841 0.0290 0.000 0.616 0.000 0.380 0.004 0.000
#> GSM486736 3 0.6006 0.7420 0.000 0.000 0.420 0.200 0.004 0.376
#> GSM486738 1 0.2937 0.7115 0.864 0.000 0.036 0.020 0.000 0.080
#> GSM486740 3 0.6006 0.7420 0.000 0.000 0.420 0.200 0.004 0.376
#> GSM486742 1 0.0865 0.7783 0.964 0.000 0.000 0.000 0.000 0.036
#> GSM486744 1 0.5072 0.5262 0.648 0.000 0.252 0.020 0.000 0.080
#> GSM486746 3 0.6006 0.7420 0.000 0.000 0.420 0.200 0.004 0.376
#> GSM486748 1 0.0937 0.7759 0.960 0.000 0.000 0.000 0.000 0.040
#> GSM486750 6 0.3695 0.9993 0.376 0.000 0.000 0.000 0.000 0.624
#> GSM486752 6 0.3695 0.9993 0.376 0.000 0.000 0.000 0.000 0.624
#> GSM486754 1 0.5072 0.5262 0.648 0.000 0.252 0.020 0.000 0.080
#> GSM486756 3 0.4111 0.7412 0.000 0.000 0.748 0.108 0.000 0.144
#> GSM486758 1 0.0458 0.7846 0.984 0.000 0.000 0.016 0.000 0.000
#> GSM486760 6 0.3695 0.9993 0.376 0.000 0.000 0.000 0.000 0.624
#> GSM486762 1 0.0547 0.7832 0.980 0.000 0.000 0.020 0.000 0.000
#> GSM486764 1 0.1267 0.7550 0.940 0.000 0.000 0.000 0.000 0.060
#> GSM486766 1 0.0713 0.7809 0.972 0.000 0.000 0.000 0.000 0.028
#> GSM486768 1 0.5072 0.5262 0.648 0.000 0.252 0.020 0.000 0.080
#> GSM486770 6 0.3695 0.9993 0.376 0.000 0.000 0.000 0.000 0.624
#> GSM486772 6 0.3695 0.9993 0.376 0.000 0.000 0.000 0.000 0.624
#> GSM486774 1 0.0363 0.7844 0.988 0.000 0.000 0.000 0.000 0.012
#> GSM486776 1 0.0547 0.7832 0.980 0.000 0.000 0.020 0.000 0.000
#> GSM486778 6 0.3695 0.9993 0.376 0.000 0.000 0.000 0.000 0.624
#> GSM486780 1 0.0458 0.7846 0.984 0.000 0.000 0.016 0.000 0.000
#> GSM486782 1 0.5072 0.5262 0.648 0.000 0.252 0.020 0.000 0.080
#> GSM486784 1 0.0790 0.7775 0.968 0.000 0.000 0.000 0.000 0.032
#> GSM486786 1 0.1267 0.7550 0.940 0.000 0.000 0.000 0.000 0.060
#> GSM486788 6 0.3695 0.9993 0.376 0.000 0.000 0.000 0.000 0.624
#> GSM486790 3 0.0000 0.6994 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM486792 3 0.5986 0.7418 0.000 0.000 0.428 0.196 0.004 0.372
#> GSM486794 1 0.5051 0.5297 0.652 0.000 0.248 0.020 0.000 0.080
#> GSM486796 6 0.3695 0.9993 0.376 0.000 0.000 0.000 0.000 0.624
#> GSM486798 1 0.0790 0.7775 0.968 0.000 0.000 0.000 0.000 0.032
#> GSM486800 1 0.2416 0.5863 0.844 0.000 0.000 0.000 0.000 0.156
#> GSM486802 6 0.3695 0.9993 0.376 0.000 0.000 0.000 0.000 0.624
#> GSM486804 1 0.1267 0.7550 0.940 0.000 0.000 0.000 0.000 0.060
#> GSM486806 1 0.0405 0.7863 0.988 0.000 0.008 0.000 0.000 0.004
#> GSM486808 1 0.0260 0.7855 0.992 0.000 0.000 0.008 0.000 0.000
#> GSM486810 1 0.4136 0.6308 0.772 0.000 0.132 0.020 0.000 0.076
#> GSM486812 6 0.3695 0.9993 0.376 0.000 0.000 0.000 0.000 0.624
#> GSM486814 1 0.5072 0.5262 0.648 0.000 0.252 0.020 0.000 0.080
#> GSM486816 1 0.0458 0.7846 0.984 0.000 0.000 0.016 0.000 0.000
#> GSM486818 3 0.4111 0.7412 0.000 0.000 0.748 0.108 0.000 0.144
#> GSM486821 3 0.0000 0.6994 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM486823 6 0.3695 0.9993 0.376 0.000 0.000 0.000 0.000 0.624
#> GSM486826 1 0.1267 0.7550 0.940 0.000 0.000 0.000 0.000 0.060
#> GSM486830 3 0.0000 0.6994 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM486832 1 0.0458 0.7846 0.984 0.000 0.000 0.016 0.000 0.000
#> GSM486834 1 0.4485 0.5853 0.724 0.000 0.180 0.012 0.000 0.084
#> GSM486836 1 0.2697 0.4999 0.812 0.000 0.000 0.000 0.000 0.188
#> GSM486838 1 0.0508 0.7852 0.984 0.000 0.000 0.004 0.000 0.012
#> GSM486840 1 0.0937 0.7723 0.960 0.000 0.000 0.000 0.000 0.040
#> GSM486842 1 0.3804 -0.5387 0.576 0.000 0.000 0.000 0.000 0.424
#> GSM486844 1 0.1267 0.7550 0.940 0.000 0.000 0.000 0.000 0.060
#> GSM486846 1 0.5072 0.5262 0.648 0.000 0.252 0.020 0.000 0.080
#> GSM486848 1 0.0547 0.7832 0.980 0.000 0.000 0.020 0.000 0.000
#> GSM486850 6 0.3706 0.9921 0.380 0.000 0.000 0.000 0.000 0.620
#> GSM486852 1 0.3847 -0.6372 0.544 0.000 0.000 0.000 0.000 0.456
#> GSM486854 1 0.0547 0.7832 0.980 0.000 0.000 0.000 0.000 0.020
#> GSM486856 1 0.0713 0.7793 0.972 0.000 0.000 0.000 0.000 0.028
#> GSM486858 1 0.0790 0.7780 0.968 0.000 0.000 0.000 0.000 0.032
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> ATC:hclust 120 4.67e-27 1.000 2
#> ATC:hclust 120 8.76e-27 1.000 3
#> ATC:hclust 99 2.55e-21 0.988 4
#> ATC:hclust 93 3.03e-19 0.997 5
#> ATC:hclust 102 2.00e-20 0.997 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["ATC", "kmeans"]
# you can also extract it by
# res = res_list["ATC:kmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'ATC' method.
#> Subgroups are detected by 'kmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 1.000 0.989 0.996 0.5046 0.496 0.496
#> 3 3 0.678 0.610 0.772 0.2286 0.961 0.922
#> 4 4 0.639 0.685 0.730 0.1207 0.804 0.578
#> 5 5 0.678 0.740 0.729 0.0813 0.907 0.678
#> 6 6 0.661 0.744 0.766 0.0610 0.959 0.803
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 1 0.000 1.000 1.000 0.000
#> GSM486737 1 0.000 1.000 1.000 0.000
#> GSM486739 1 0.000 1.000 1.000 0.000
#> GSM486741 1 0.000 1.000 1.000 0.000
#> GSM486743 1 0.000 1.000 1.000 0.000
#> GSM486745 1 0.000 1.000 1.000 0.000
#> GSM486747 1 0.000 1.000 1.000 0.000
#> GSM486749 1 0.000 1.000 1.000 0.000
#> GSM486751 1 0.000 1.000 1.000 0.000
#> GSM486753 1 0.000 1.000 1.000 0.000
#> GSM486755 1 0.000 1.000 1.000 0.000
#> GSM486757 1 0.000 1.000 1.000 0.000
#> GSM486759 1 0.000 1.000 1.000 0.000
#> GSM486761 1 0.000 1.000 1.000 0.000
#> GSM486763 1 0.000 1.000 1.000 0.000
#> GSM486765 1 0.000 1.000 1.000 0.000
#> GSM486767 1 0.000 1.000 1.000 0.000
#> GSM486769 1 0.000 1.000 1.000 0.000
#> GSM486771 1 0.000 1.000 1.000 0.000
#> GSM486773 1 0.000 1.000 1.000 0.000
#> GSM486775 1 0.000 1.000 1.000 0.000
#> GSM486777 1 0.000 1.000 1.000 0.000
#> GSM486779 1 0.000 1.000 1.000 0.000
#> GSM486781 1 0.000 1.000 1.000 0.000
#> GSM486783 1 0.000 1.000 1.000 0.000
#> GSM486785 1 0.000 1.000 1.000 0.000
#> GSM486787 1 0.000 1.000 1.000 0.000
#> GSM486789 1 0.000 1.000 1.000 0.000
#> GSM486791 1 0.000 1.000 1.000 0.000
#> GSM486793 1 0.000 1.000 1.000 0.000
#> GSM486795 1 0.000 1.000 1.000 0.000
#> GSM486797 1 0.000 1.000 1.000 0.000
#> GSM486799 1 0.000 1.000 1.000 0.000
#> GSM486801 1 0.000 1.000 1.000 0.000
#> GSM486803 1 0.000 1.000 1.000 0.000
#> GSM486805 1 0.000 1.000 1.000 0.000
#> GSM486807 1 0.000 1.000 1.000 0.000
#> GSM486809 1 0.000 1.000 1.000 0.000
#> GSM486811 1 0.000 1.000 1.000 0.000
#> GSM486813 1 0.000 1.000 1.000 0.000
#> GSM486815 1 0.000 1.000 1.000 0.000
#> GSM486817 1 0.000 1.000 1.000 0.000
#> GSM486819 1 0.000 1.000 1.000 0.000
#> GSM486822 1 0.000 1.000 1.000 0.000
#> GSM486824 1 0.000 1.000 1.000 0.000
#> GSM486828 1 0.000 1.000 1.000 0.000
#> GSM486831 1 0.000 1.000 1.000 0.000
#> GSM486833 1 0.000 1.000 1.000 0.000
#> GSM486835 1 0.000 1.000 1.000 0.000
#> GSM486837 1 0.000 1.000 1.000 0.000
#> GSM486839 1 0.000 1.000 1.000 0.000
#> GSM486841 1 0.000 1.000 1.000 0.000
#> GSM486843 1 0.000 1.000 1.000 0.000
#> GSM486845 1 0.000 1.000 1.000 0.000
#> GSM486847 1 0.000 1.000 1.000 0.000
#> GSM486849 1 0.000 1.000 1.000 0.000
#> GSM486851 1 0.000 1.000 1.000 0.000
#> GSM486853 1 0.000 1.000 1.000 0.000
#> GSM486855 1 0.000 1.000 1.000 0.000
#> GSM486857 1 0.000 1.000 1.000 0.000
#> GSM486736 2 0.994 0.162 0.456 0.544
#> GSM486738 2 0.000 0.992 0.000 1.000
#> GSM486740 2 0.000 0.992 0.000 1.000
#> GSM486742 2 0.000 0.992 0.000 1.000
#> GSM486744 2 0.000 0.992 0.000 1.000
#> GSM486746 2 0.000 0.992 0.000 1.000
#> GSM486748 2 0.000 0.992 0.000 1.000
#> GSM486750 2 0.000 0.992 0.000 1.000
#> GSM486752 2 0.000 0.992 0.000 1.000
#> GSM486754 2 0.000 0.992 0.000 1.000
#> GSM486756 2 0.000 0.992 0.000 1.000
#> GSM486758 2 0.000 0.992 0.000 1.000
#> GSM486760 2 0.000 0.992 0.000 1.000
#> GSM486762 2 0.000 0.992 0.000 1.000
#> GSM486764 2 0.000 0.992 0.000 1.000
#> GSM486766 2 0.000 0.992 0.000 1.000
#> GSM486768 2 0.000 0.992 0.000 1.000
#> GSM486770 2 0.000 0.992 0.000 1.000
#> GSM486772 2 0.000 0.992 0.000 1.000
#> GSM486774 2 0.000 0.992 0.000 1.000
#> GSM486776 2 0.000 0.992 0.000 1.000
#> GSM486778 2 0.000 0.992 0.000 1.000
#> GSM486780 2 0.000 0.992 0.000 1.000
#> GSM486782 2 0.000 0.992 0.000 1.000
#> GSM486784 2 0.000 0.992 0.000 1.000
#> GSM486786 2 0.000 0.992 0.000 1.000
#> GSM486788 2 0.000 0.992 0.000 1.000
#> GSM486790 2 0.000 0.992 0.000 1.000
#> GSM486792 2 0.000 0.992 0.000 1.000
#> GSM486794 2 0.000 0.992 0.000 1.000
#> GSM486796 2 0.000 0.992 0.000 1.000
#> GSM486798 2 0.000 0.992 0.000 1.000
#> GSM486800 2 0.000 0.992 0.000 1.000
#> GSM486802 2 0.000 0.992 0.000 1.000
#> GSM486804 2 0.000 0.992 0.000 1.000
#> GSM486806 2 0.000 0.992 0.000 1.000
#> GSM486808 2 0.000 0.992 0.000 1.000
#> GSM486810 2 0.000 0.992 0.000 1.000
#> GSM486812 2 0.000 0.992 0.000 1.000
#> GSM486814 2 0.000 0.992 0.000 1.000
#> GSM486816 2 0.000 0.992 0.000 1.000
#> GSM486818 2 0.000 0.992 0.000 1.000
#> GSM486821 2 0.000 0.992 0.000 1.000
#> GSM486823 2 0.000 0.992 0.000 1.000
#> GSM486826 2 0.000 0.992 0.000 1.000
#> GSM486830 2 0.000 0.992 0.000 1.000
#> GSM486832 2 0.000 0.992 0.000 1.000
#> GSM486834 2 0.000 0.992 0.000 1.000
#> GSM486836 2 0.000 0.992 0.000 1.000
#> GSM486838 2 0.000 0.992 0.000 1.000
#> GSM486840 2 0.000 0.992 0.000 1.000
#> GSM486842 2 0.000 0.992 0.000 1.000
#> GSM486844 2 0.000 0.992 0.000 1.000
#> GSM486846 2 0.000 0.992 0.000 1.000
#> GSM486848 2 0.000 0.992 0.000 1.000
#> GSM486850 2 0.000 0.992 0.000 1.000
#> GSM486852 2 0.000 0.992 0.000 1.000
#> GSM486854 2 0.000 0.992 0.000 1.000
#> GSM486856 2 0.000 0.992 0.000 1.000
#> GSM486858 2 0.000 0.992 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 1 0.3192 0.786 0.888 0.112 0.000
#> GSM486737 1 0.5706 0.820 0.680 0.320 0.000
#> GSM486739 1 0.3192 0.786 0.888 0.112 0.000
#> GSM486741 1 0.5835 0.819 0.660 0.340 0.000
#> GSM486743 1 0.6079 0.808 0.612 0.388 0.000
#> GSM486745 1 0.3192 0.786 0.888 0.112 0.000
#> GSM486747 1 0.5835 0.819 0.660 0.340 0.000
#> GSM486749 1 0.0592 0.811 0.988 0.012 0.000
#> GSM486751 1 0.0747 0.810 0.984 0.016 0.000
#> GSM486753 1 0.6045 0.810 0.620 0.380 0.000
#> GSM486755 1 0.6204 0.794 0.576 0.424 0.000
#> GSM486757 1 0.5706 0.822 0.680 0.320 0.000
#> GSM486759 1 0.0000 0.814 1.000 0.000 0.000
#> GSM486761 1 0.5835 0.819 0.660 0.340 0.000
#> GSM486763 1 0.0000 0.814 1.000 0.000 0.000
#> GSM486765 1 0.5835 0.819 0.660 0.340 0.000
#> GSM486767 1 0.5835 0.819 0.660 0.340 0.000
#> GSM486769 1 0.3038 0.785 0.896 0.104 0.000
#> GSM486771 1 0.0747 0.810 0.984 0.016 0.000
#> GSM486773 1 0.5835 0.819 0.660 0.340 0.000
#> GSM486775 1 0.5835 0.819 0.660 0.340 0.000
#> GSM486777 1 0.0000 0.814 1.000 0.000 0.000
#> GSM486779 1 0.5706 0.820 0.680 0.320 0.000
#> GSM486781 1 0.6095 0.806 0.608 0.392 0.000
#> GSM486783 1 0.5706 0.820 0.680 0.320 0.000
#> GSM486785 1 0.2537 0.823 0.920 0.080 0.000
#> GSM486787 1 0.0000 0.814 1.000 0.000 0.000
#> GSM486789 1 0.6215 0.793 0.572 0.428 0.000
#> GSM486791 1 0.3038 0.785 0.896 0.104 0.000
#> GSM486793 1 0.6079 0.808 0.612 0.388 0.000
#> GSM486795 1 0.0000 0.814 1.000 0.000 0.000
#> GSM486797 1 0.5835 0.819 0.660 0.340 0.000
#> GSM486799 1 0.5835 0.819 0.660 0.340 0.000
#> GSM486801 1 0.0000 0.814 1.000 0.000 0.000
#> GSM486803 1 0.0000 0.814 1.000 0.000 0.000
#> GSM486805 1 0.6079 0.808 0.612 0.388 0.000
#> GSM486807 1 0.5835 0.819 0.660 0.340 0.000
#> GSM486809 1 0.5835 0.819 0.660 0.340 0.000
#> GSM486811 1 0.0000 0.814 1.000 0.000 0.000
#> GSM486813 1 0.6095 0.806 0.608 0.392 0.000
#> GSM486815 1 0.0237 0.815 0.996 0.004 0.000
#> GSM486817 1 0.3192 0.786 0.888 0.112 0.000
#> GSM486819 1 0.6204 0.794 0.576 0.424 0.000
#> GSM486822 1 0.2261 0.801 0.932 0.068 0.000
#> GSM486824 1 0.5529 0.823 0.704 0.296 0.000
#> GSM486828 1 0.6204 0.794 0.576 0.424 0.000
#> GSM486831 1 0.0000 0.814 1.000 0.000 0.000
#> GSM486833 1 0.2796 0.791 0.908 0.092 0.000
#> GSM486835 1 0.0000 0.814 1.000 0.000 0.000
#> GSM486837 1 0.5835 0.819 0.660 0.340 0.000
#> GSM486839 1 0.0000 0.814 1.000 0.000 0.000
#> GSM486841 1 0.0000 0.814 1.000 0.000 0.000
#> GSM486843 1 0.0000 0.814 1.000 0.000 0.000
#> GSM486845 1 0.2448 0.799 0.924 0.076 0.000
#> GSM486847 1 0.5706 0.820 0.680 0.320 0.000
#> GSM486849 1 0.0424 0.812 0.992 0.008 0.000
#> GSM486851 1 0.0000 0.814 1.000 0.000 0.000
#> GSM486853 1 0.5905 0.817 0.648 0.352 0.000
#> GSM486855 1 0.0000 0.814 1.000 0.000 0.000
#> GSM486857 1 0.5706 0.820 0.680 0.320 0.000
#> GSM486736 2 0.8275 0.387 0.296 0.596 0.108
#> GSM486738 3 0.1411 0.696 0.000 0.036 0.964
#> GSM486740 2 0.6373 0.688 0.004 0.588 0.408
#> GSM486742 3 0.1411 0.696 0.000 0.036 0.964
#> GSM486744 3 0.6280 -0.454 0.000 0.460 0.540
#> GSM486746 2 0.6235 0.686 0.000 0.564 0.436
#> GSM486748 3 0.1411 0.696 0.000 0.036 0.964
#> GSM486750 3 0.3192 0.636 0.000 0.112 0.888
#> GSM486752 3 0.3192 0.636 0.000 0.112 0.888
#> GSM486754 3 0.6280 -0.454 0.000 0.460 0.540
#> GSM486756 3 0.6280 -0.454 0.000 0.460 0.540
#> GSM486758 3 0.1411 0.696 0.000 0.036 0.964
#> GSM486760 3 0.3192 0.636 0.000 0.112 0.888
#> GSM486762 3 0.1411 0.696 0.000 0.036 0.964
#> GSM486764 3 0.0000 0.697 0.000 0.000 1.000
#> GSM486766 3 0.1411 0.696 0.000 0.036 0.964
#> GSM486768 3 0.6274 -0.446 0.000 0.456 0.544
#> GSM486770 2 0.6291 0.650 0.000 0.532 0.468
#> GSM486772 3 0.3192 0.636 0.000 0.112 0.888
#> GSM486774 3 0.1411 0.696 0.000 0.036 0.964
#> GSM486776 3 0.1411 0.696 0.000 0.036 0.964
#> GSM486778 3 0.3192 0.636 0.000 0.112 0.888
#> GSM486780 3 0.1411 0.696 0.000 0.036 0.964
#> GSM486782 3 0.6280 -0.454 0.000 0.460 0.540
#> GSM486784 3 0.0237 0.697 0.000 0.004 0.996
#> GSM486786 3 0.0000 0.697 0.000 0.000 1.000
#> GSM486788 3 0.3192 0.636 0.000 0.112 0.888
#> GSM486790 3 0.6280 -0.454 0.000 0.460 0.540
#> GSM486792 2 0.6235 0.686 0.000 0.564 0.436
#> GSM486794 3 0.6274 -0.446 0.000 0.456 0.544
#> GSM486796 3 0.3116 0.638 0.000 0.108 0.892
#> GSM486798 3 0.0000 0.697 0.000 0.000 1.000
#> GSM486800 3 0.2878 0.647 0.000 0.096 0.904
#> GSM486802 3 0.3192 0.636 0.000 0.112 0.888
#> GSM486804 3 0.0000 0.697 0.000 0.000 1.000
#> GSM486806 3 0.1411 0.696 0.000 0.036 0.964
#> GSM486808 3 0.1411 0.696 0.000 0.036 0.964
#> GSM486810 3 0.6026 -0.264 0.000 0.376 0.624
#> GSM486812 3 0.3192 0.636 0.000 0.112 0.888
#> GSM486814 3 0.6274 -0.446 0.000 0.456 0.544
#> GSM486816 3 0.1411 0.696 0.000 0.036 0.964
#> GSM486818 3 0.6280 -0.454 0.000 0.460 0.540
#> GSM486821 3 0.6280 -0.454 0.000 0.460 0.540
#> GSM486823 3 0.3192 0.636 0.000 0.112 0.888
#> GSM486826 3 0.0000 0.697 0.000 0.000 1.000
#> GSM486830 3 0.6280 -0.454 0.000 0.460 0.540
#> GSM486832 3 0.1411 0.696 0.000 0.036 0.964
#> GSM486834 3 0.6286 -0.465 0.000 0.464 0.536
#> GSM486836 3 0.2959 0.645 0.000 0.100 0.900
#> GSM486838 3 0.1411 0.696 0.000 0.036 0.964
#> GSM486840 3 0.0000 0.697 0.000 0.000 1.000
#> GSM486842 3 0.2959 0.645 0.000 0.100 0.900
#> GSM486844 3 0.0000 0.697 0.000 0.000 1.000
#> GSM486846 3 0.6274 -0.446 0.000 0.456 0.544
#> GSM486848 3 0.1411 0.696 0.000 0.036 0.964
#> GSM486850 3 0.3192 0.636 0.000 0.112 0.888
#> GSM486852 3 0.2959 0.645 0.000 0.100 0.900
#> GSM486854 3 0.1411 0.696 0.000 0.036 0.964
#> GSM486856 3 0.0237 0.697 0.000 0.004 0.996
#> GSM486858 3 0.0000 0.697 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 1 0.7685 0.538 0.456 0.288 0.000 0.256
#> GSM486737 4 0.0672 0.866 0.008 0.008 0.000 0.984
#> GSM486739 1 0.7685 0.538 0.456 0.288 0.000 0.256
#> GSM486741 4 0.0524 0.875 0.004 0.008 0.000 0.988
#> GSM486743 4 0.2048 0.844 0.064 0.008 0.000 0.928
#> GSM486745 1 0.7685 0.538 0.456 0.288 0.000 0.256
#> GSM486747 4 0.0000 0.875 0.000 0.000 0.000 1.000
#> GSM486749 1 0.4697 0.843 0.644 0.000 0.000 0.356
#> GSM486751 1 0.4697 0.843 0.644 0.000 0.000 0.356
#> GSM486753 4 0.2048 0.844 0.064 0.008 0.000 0.928
#> GSM486755 4 0.6084 0.568 0.120 0.204 0.000 0.676
#> GSM486757 4 0.2542 0.779 0.084 0.012 0.000 0.904
#> GSM486759 1 0.4746 0.846 0.632 0.000 0.000 0.368
#> GSM486761 4 0.0000 0.875 0.000 0.000 0.000 1.000
#> GSM486763 1 0.4746 0.846 0.632 0.000 0.000 0.368
#> GSM486765 4 0.0000 0.875 0.000 0.000 0.000 1.000
#> GSM486767 4 0.0524 0.875 0.004 0.008 0.000 0.988
#> GSM486769 1 0.7362 0.603 0.524 0.220 0.000 0.256
#> GSM486771 1 0.4697 0.843 0.644 0.000 0.000 0.356
#> GSM486773 4 0.0000 0.875 0.000 0.000 0.000 1.000
#> GSM486775 4 0.0000 0.875 0.000 0.000 0.000 1.000
#> GSM486777 1 0.5055 0.843 0.624 0.008 0.000 0.368
#> GSM486779 4 0.2924 0.747 0.100 0.016 0.000 0.884
#> GSM486781 4 0.2048 0.844 0.064 0.008 0.000 0.928
#> GSM486783 4 0.0804 0.864 0.008 0.012 0.000 0.980
#> GSM486785 1 0.5417 0.787 0.572 0.016 0.000 0.412
#> GSM486787 1 0.4746 0.846 0.632 0.000 0.000 0.368
#> GSM486789 4 0.5982 0.579 0.112 0.204 0.000 0.684
#> GSM486791 1 0.7387 0.599 0.520 0.224 0.000 0.256
#> GSM486793 4 0.2048 0.844 0.064 0.008 0.000 0.928
#> GSM486795 1 0.4746 0.846 0.632 0.000 0.000 0.368
#> GSM486797 4 0.0000 0.875 0.000 0.000 0.000 1.000
#> GSM486799 4 0.0000 0.875 0.000 0.000 0.000 1.000
#> GSM486801 1 0.4746 0.846 0.632 0.000 0.000 0.368
#> GSM486803 1 0.5284 0.840 0.616 0.016 0.000 0.368
#> GSM486805 4 0.2048 0.844 0.064 0.008 0.000 0.928
#> GSM486807 4 0.0188 0.874 0.000 0.004 0.000 0.996
#> GSM486809 4 0.0672 0.874 0.008 0.008 0.000 0.984
#> GSM486811 1 0.4746 0.846 0.632 0.000 0.000 0.368
#> GSM486813 4 0.2048 0.844 0.064 0.008 0.000 0.928
#> GSM486815 1 0.5313 0.833 0.608 0.016 0.000 0.376
#> GSM486817 1 0.7614 0.525 0.468 0.232 0.000 0.300
#> GSM486819 4 0.6265 0.537 0.124 0.220 0.000 0.656
#> GSM486822 1 0.6016 0.749 0.632 0.068 0.000 0.300
#> GSM486824 4 0.4908 0.209 0.292 0.016 0.000 0.692
#> GSM486828 4 0.6084 0.568 0.120 0.204 0.000 0.676
#> GSM486831 1 0.5217 0.833 0.608 0.012 0.000 0.380
#> GSM486833 1 0.7256 0.617 0.540 0.204 0.000 0.256
#> GSM486835 1 0.4746 0.846 0.632 0.000 0.000 0.368
#> GSM486837 4 0.0188 0.874 0.000 0.004 0.000 0.996
#> GSM486839 1 0.5352 0.821 0.596 0.016 0.000 0.388
#> GSM486841 1 0.4746 0.846 0.632 0.000 0.000 0.368
#> GSM486843 1 0.5284 0.840 0.616 0.016 0.000 0.368
#> GSM486845 1 0.6706 0.701 0.588 0.124 0.000 0.288
#> GSM486847 4 0.2610 0.769 0.088 0.012 0.000 0.900
#> GSM486849 1 0.4920 0.845 0.628 0.004 0.000 0.368
#> GSM486851 1 0.4746 0.846 0.632 0.000 0.000 0.368
#> GSM486853 4 0.0657 0.874 0.012 0.004 0.000 0.984
#> GSM486855 1 0.5352 0.821 0.596 0.016 0.000 0.388
#> GSM486857 4 0.1174 0.855 0.020 0.012 0.000 0.968
#> GSM486736 2 0.4609 0.486 0.156 0.788 0.056 0.000
#> GSM486738 3 0.1637 0.664 0.000 0.060 0.940 0.000
#> GSM486740 2 0.4638 0.612 0.044 0.776 0.180 0.000
#> GSM486742 3 0.1474 0.674 0.000 0.052 0.948 0.000
#> GSM486744 2 0.4992 0.758 0.000 0.524 0.476 0.000
#> GSM486746 2 0.5343 0.658 0.052 0.708 0.240 0.000
#> GSM486748 3 0.1474 0.674 0.000 0.052 0.948 0.000
#> GSM486750 3 0.5809 0.616 0.216 0.092 0.692 0.000
#> GSM486752 3 0.5809 0.616 0.216 0.092 0.692 0.000
#> GSM486754 2 0.4992 0.758 0.000 0.524 0.476 0.000
#> GSM486756 2 0.5681 0.762 0.028 0.568 0.404 0.000
#> GSM486758 3 0.0817 0.696 0.000 0.024 0.976 0.000
#> GSM486760 3 0.5809 0.616 0.216 0.092 0.692 0.000
#> GSM486762 3 0.1022 0.690 0.000 0.032 0.968 0.000
#> GSM486764 3 0.1474 0.714 0.052 0.000 0.948 0.000
#> GSM486766 3 0.1474 0.674 0.000 0.052 0.948 0.000
#> GSM486768 3 0.4998 -0.714 0.000 0.488 0.512 0.000
#> GSM486770 2 0.7686 0.372 0.228 0.436 0.336 0.000
#> GSM486772 3 0.5809 0.616 0.216 0.092 0.692 0.000
#> GSM486774 3 0.0707 0.698 0.000 0.020 0.980 0.000
#> GSM486776 3 0.1716 0.659 0.000 0.064 0.936 0.000
#> GSM486778 3 0.5809 0.616 0.216 0.092 0.692 0.000
#> GSM486780 3 0.0817 0.696 0.000 0.024 0.976 0.000
#> GSM486782 2 0.4992 0.758 0.000 0.524 0.476 0.000
#> GSM486784 3 0.1211 0.714 0.040 0.000 0.960 0.000
#> GSM486786 3 0.2149 0.706 0.088 0.000 0.912 0.000
#> GSM486788 3 0.5809 0.616 0.216 0.092 0.692 0.000
#> GSM486790 2 0.5681 0.762 0.028 0.568 0.404 0.000
#> GSM486792 2 0.5764 0.681 0.052 0.644 0.304 0.000
#> GSM486794 2 0.4992 0.758 0.000 0.524 0.476 0.000
#> GSM486796 3 0.5775 0.618 0.212 0.092 0.696 0.000
#> GSM486798 3 0.1389 0.714 0.048 0.000 0.952 0.000
#> GSM486800 3 0.5716 0.621 0.212 0.088 0.700 0.000
#> GSM486802 3 0.5809 0.616 0.216 0.092 0.692 0.000
#> GSM486804 3 0.1474 0.714 0.052 0.000 0.948 0.000
#> GSM486806 3 0.1716 0.659 0.000 0.064 0.936 0.000
#> GSM486808 3 0.0707 0.698 0.000 0.020 0.980 0.000
#> GSM486810 3 0.4477 -0.212 0.000 0.312 0.688 0.000
#> GSM486812 3 0.5809 0.616 0.216 0.092 0.692 0.000
#> GSM486814 3 0.4998 -0.714 0.000 0.488 0.512 0.000
#> GSM486816 3 0.0817 0.696 0.000 0.024 0.976 0.000
#> GSM486818 2 0.5681 0.762 0.028 0.568 0.404 0.000
#> GSM486821 2 0.4992 0.758 0.000 0.524 0.476 0.000
#> GSM486823 3 0.5809 0.616 0.216 0.092 0.692 0.000
#> GSM486826 3 0.1389 0.714 0.048 0.000 0.952 0.000
#> GSM486830 2 0.4992 0.758 0.000 0.524 0.476 0.000
#> GSM486832 3 0.1022 0.690 0.000 0.032 0.968 0.000
#> GSM486834 2 0.4992 0.758 0.000 0.524 0.476 0.000
#> GSM486836 3 0.5716 0.621 0.212 0.088 0.700 0.000
#> GSM486838 3 0.0895 0.700 0.004 0.020 0.976 0.000
#> GSM486840 3 0.1474 0.714 0.052 0.000 0.948 0.000
#> GSM486842 3 0.5716 0.621 0.212 0.088 0.700 0.000
#> GSM486844 3 0.2149 0.706 0.088 0.000 0.912 0.000
#> GSM486846 3 0.4998 -0.714 0.000 0.488 0.512 0.000
#> GSM486848 3 0.0817 0.696 0.000 0.024 0.976 0.000
#> GSM486850 3 0.5809 0.616 0.216 0.092 0.692 0.000
#> GSM486852 3 0.5716 0.621 0.212 0.088 0.700 0.000
#> GSM486854 3 0.1389 0.677 0.000 0.048 0.952 0.000
#> GSM486856 3 0.1004 0.711 0.024 0.004 0.972 0.000
#> GSM486858 3 0.1302 0.714 0.044 0.000 0.956 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 4 0.6839 0.5007 0.276 0.056 0.000 0.548 0.120
#> GSM486737 5 0.4922 0.8377 0.028 0.008 0.000 0.328 0.636
#> GSM486739 4 0.6839 0.5007 0.276 0.056 0.000 0.548 0.120
#> GSM486741 5 0.4385 0.8609 0.012 0.004 0.000 0.312 0.672
#> GSM486743 5 0.4723 0.8418 0.032 0.008 0.000 0.272 0.688
#> GSM486745 4 0.6839 0.5007 0.276 0.056 0.000 0.548 0.120
#> GSM486747 5 0.4029 0.8608 0.000 0.004 0.000 0.316 0.680
#> GSM486749 4 0.0693 0.8104 0.008 0.000 0.000 0.980 0.012
#> GSM486751 4 0.0693 0.8104 0.008 0.000 0.000 0.980 0.012
#> GSM486753 5 0.4723 0.8418 0.032 0.008 0.000 0.272 0.688
#> GSM486755 5 0.6755 0.4926 0.288 0.012 0.000 0.208 0.492
#> GSM486757 5 0.5399 0.6833 0.028 0.016 0.000 0.440 0.516
#> GSM486759 4 0.0000 0.8143 0.000 0.000 0.000 1.000 0.000
#> GSM486761 5 0.4147 0.8604 0.000 0.008 0.000 0.316 0.676
#> GSM486763 4 0.0000 0.8143 0.000 0.000 0.000 1.000 0.000
#> GSM486765 5 0.4127 0.8615 0.000 0.008 0.000 0.312 0.680
#> GSM486767 5 0.4398 0.8613 0.008 0.008 0.000 0.312 0.672
#> GSM486769 4 0.6408 0.5316 0.276 0.036 0.000 0.580 0.108
#> GSM486771 4 0.0693 0.8104 0.008 0.000 0.000 0.980 0.012
#> GSM486773 5 0.3857 0.8615 0.000 0.000 0.000 0.312 0.688
#> GSM486775 5 0.4147 0.8604 0.000 0.008 0.000 0.316 0.676
#> GSM486777 4 0.0510 0.8089 0.016 0.000 0.000 0.984 0.000
#> GSM486779 5 0.5418 0.6113 0.028 0.016 0.000 0.476 0.480
#> GSM486781 5 0.4700 0.8386 0.032 0.008 0.000 0.268 0.692
#> GSM486783 5 0.5120 0.8338 0.028 0.016 0.000 0.328 0.628
#> GSM486785 4 0.2253 0.7618 0.028 0.016 0.000 0.920 0.036
#> GSM486787 4 0.0000 0.8143 0.000 0.000 0.000 1.000 0.000
#> GSM486789 5 0.6727 0.5016 0.280 0.012 0.000 0.208 0.500
#> GSM486791 4 0.6408 0.5316 0.276 0.036 0.000 0.580 0.108
#> GSM486793 5 0.4723 0.8418 0.032 0.008 0.000 0.272 0.688
#> GSM486795 4 0.0000 0.8143 0.000 0.000 0.000 1.000 0.000
#> GSM486797 5 0.3876 0.8607 0.000 0.000 0.000 0.316 0.684
#> GSM486799 5 0.4147 0.8604 0.000 0.008 0.000 0.316 0.676
#> GSM486801 4 0.0000 0.8143 0.000 0.000 0.000 1.000 0.000
#> GSM486803 4 0.0898 0.8036 0.020 0.008 0.000 0.972 0.000
#> GSM486805 5 0.4723 0.8418 0.032 0.008 0.000 0.272 0.688
#> GSM486807 5 0.5242 0.8558 0.028 0.024 0.000 0.316 0.632
#> GSM486809 5 0.4834 0.8569 0.028 0.008 0.000 0.308 0.656
#> GSM486811 4 0.0000 0.8143 0.000 0.000 0.000 1.000 0.000
#> GSM486813 5 0.4723 0.8418 0.032 0.008 0.000 0.272 0.688
#> GSM486815 4 0.1216 0.8003 0.020 0.020 0.000 0.960 0.000
#> GSM486817 4 0.6751 0.4790 0.296 0.040 0.000 0.536 0.128
#> GSM486819 5 0.6755 0.4926 0.288 0.012 0.000 0.208 0.492
#> GSM486822 4 0.3656 0.7222 0.104 0.008 0.000 0.832 0.056
#> GSM486824 4 0.5276 -0.1876 0.028 0.024 0.000 0.624 0.324
#> GSM486828 5 0.6755 0.4926 0.288 0.012 0.000 0.208 0.492
#> GSM486831 4 0.1806 0.7844 0.028 0.016 0.000 0.940 0.016
#> GSM486833 4 0.5818 0.5627 0.264 0.012 0.000 0.620 0.104
#> GSM486835 4 0.0000 0.8143 0.000 0.000 0.000 1.000 0.000
#> GSM486837 5 0.4721 0.8526 0.012 0.016 0.000 0.316 0.656
#> GSM486839 4 0.1806 0.7844 0.028 0.016 0.000 0.940 0.016
#> GSM486841 4 0.0000 0.8143 0.000 0.000 0.000 1.000 0.000
#> GSM486843 4 0.0898 0.8036 0.020 0.008 0.000 0.972 0.000
#> GSM486845 4 0.5021 0.6592 0.184 0.024 0.000 0.728 0.064
#> GSM486847 5 0.5452 0.7232 0.028 0.020 0.000 0.416 0.536
#> GSM486849 4 0.0451 0.8140 0.000 0.008 0.000 0.988 0.004
#> GSM486851 4 0.0000 0.8143 0.000 0.000 0.000 1.000 0.000
#> GSM486853 5 0.5072 0.8581 0.032 0.016 0.000 0.300 0.652
#> GSM486855 4 0.1806 0.7844 0.028 0.016 0.000 0.940 0.016
#> GSM486857 5 0.5222 0.8086 0.028 0.016 0.000 0.356 0.600
#> GSM486736 2 0.2654 0.6338 0.032 0.904 0.004 0.016 0.044
#> GSM486738 3 0.4962 0.6197 0.048 0.048 0.748 0.000 0.156
#> GSM486740 2 0.2931 0.6557 0.028 0.892 0.032 0.004 0.044
#> GSM486742 3 0.4322 0.6565 0.048 0.016 0.780 0.000 0.156
#> GSM486744 2 0.7011 0.7407 0.048 0.524 0.272 0.000 0.156
#> GSM486746 2 0.3245 0.6539 0.048 0.872 0.036 0.000 0.044
#> GSM486748 3 0.3991 0.6687 0.048 0.004 0.792 0.000 0.156
#> GSM486750 1 0.4101 0.9260 0.628 0.000 0.372 0.000 0.000
#> GSM486752 1 0.4101 0.9260 0.628 0.000 0.372 0.000 0.000
#> GSM486754 2 0.7011 0.7407 0.048 0.524 0.272 0.000 0.156
#> GSM486756 2 0.1851 0.7095 0.000 0.912 0.088 0.000 0.000
#> GSM486758 3 0.0290 0.7985 0.000 0.000 0.992 0.000 0.008
#> GSM486760 1 0.4101 0.9260 0.628 0.000 0.372 0.000 0.000
#> GSM486762 3 0.0451 0.7975 0.004 0.000 0.988 0.000 0.008
#> GSM486764 3 0.2074 0.7067 0.104 0.000 0.896 0.000 0.000
#> GSM486766 3 0.3851 0.6784 0.036 0.004 0.796 0.000 0.164
#> GSM486768 2 0.7186 0.6778 0.048 0.468 0.328 0.000 0.156
#> GSM486770 1 0.4967 0.2696 0.660 0.280 0.060 0.000 0.000
#> GSM486772 1 0.4101 0.9260 0.628 0.000 0.372 0.000 0.000
#> GSM486774 3 0.0000 0.7977 0.000 0.000 1.000 0.000 0.000
#> GSM486776 3 0.2965 0.7368 0.028 0.012 0.876 0.000 0.084
#> GSM486778 1 0.4114 0.9250 0.624 0.000 0.376 0.000 0.000
#> GSM486780 3 0.0290 0.7985 0.000 0.000 0.992 0.000 0.008
#> GSM486782 2 0.7011 0.7407 0.048 0.524 0.272 0.000 0.156
#> GSM486784 3 0.1544 0.7501 0.068 0.000 0.932 0.000 0.000
#> GSM486786 3 0.3143 0.4415 0.204 0.000 0.796 0.000 0.000
#> GSM486788 1 0.4126 0.9232 0.620 0.000 0.380 0.000 0.000
#> GSM486790 2 0.1851 0.7095 0.000 0.912 0.088 0.000 0.000
#> GSM486792 2 0.3610 0.6556 0.056 0.852 0.048 0.000 0.044
#> GSM486794 2 0.7011 0.7407 0.048 0.524 0.272 0.000 0.156
#> GSM486796 1 0.4126 0.9232 0.620 0.000 0.380 0.000 0.000
#> GSM486798 3 0.1965 0.7183 0.096 0.000 0.904 0.000 0.000
#> GSM486800 1 0.4126 0.9218 0.620 0.000 0.380 0.000 0.000
#> GSM486802 1 0.4101 0.9260 0.628 0.000 0.372 0.000 0.000
#> GSM486804 3 0.2127 0.7006 0.108 0.000 0.892 0.000 0.000
#> GSM486806 3 0.4365 0.6601 0.036 0.024 0.776 0.000 0.164
#> GSM486808 3 0.0290 0.7985 0.000 0.000 0.992 0.000 0.008
#> GSM486810 3 0.6792 -0.0795 0.036 0.252 0.548 0.000 0.164
#> GSM486812 1 0.4114 0.9250 0.624 0.000 0.376 0.000 0.000
#> GSM486814 2 0.7186 0.6778 0.048 0.468 0.328 0.000 0.156
#> GSM486816 3 0.0290 0.7985 0.000 0.000 0.992 0.000 0.008
#> GSM486818 2 0.1851 0.7095 0.000 0.912 0.088 0.000 0.000
#> GSM486821 2 0.6641 0.7465 0.032 0.564 0.248 0.000 0.156
#> GSM486823 1 0.4101 0.9260 0.628 0.000 0.372 0.000 0.000
#> GSM486826 3 0.2074 0.7067 0.104 0.000 0.896 0.000 0.000
#> GSM486830 2 0.6710 0.7464 0.036 0.560 0.248 0.000 0.156
#> GSM486832 3 0.0451 0.7975 0.004 0.000 0.988 0.000 0.008
#> GSM486834 2 0.7042 0.7340 0.048 0.516 0.280 0.000 0.156
#> GSM486836 1 0.4273 0.8368 0.552 0.000 0.448 0.000 0.000
#> GSM486838 3 0.0000 0.7977 0.000 0.000 1.000 0.000 0.000
#> GSM486840 3 0.2127 0.7006 0.108 0.000 0.892 0.000 0.000
#> GSM486842 1 0.4268 0.8436 0.556 0.000 0.444 0.000 0.000
#> GSM486844 3 0.3143 0.4415 0.204 0.000 0.796 0.000 0.000
#> GSM486846 2 0.7186 0.6778 0.048 0.468 0.328 0.000 0.156
#> GSM486848 3 0.0290 0.7985 0.000 0.000 0.992 0.000 0.008
#> GSM486850 1 0.4101 0.9260 0.628 0.000 0.372 0.000 0.000
#> GSM486852 1 0.4268 0.8436 0.556 0.000 0.444 0.000 0.000
#> GSM486854 3 0.3452 0.6927 0.032 0.000 0.820 0.000 0.148
#> GSM486856 3 0.0510 0.7905 0.016 0.000 0.984 0.000 0.000
#> GSM486858 3 0.1792 0.7333 0.084 0.000 0.916 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 6 0.4596 0.692 0.000 0.000 0.012 0.032 0.332 0.624
#> GSM486737 4 0.4316 0.814 0.000 0.072 0.000 0.760 0.140 0.028
#> GSM486739 6 0.4596 0.692 0.000 0.000 0.012 0.032 0.332 0.624
#> GSM486741 4 0.2556 0.871 0.000 0.008 0.000 0.864 0.120 0.008
#> GSM486743 4 0.3885 0.841 0.000 0.060 0.004 0.804 0.108 0.024
#> GSM486745 6 0.4596 0.692 0.000 0.000 0.012 0.032 0.332 0.624
#> GSM486747 4 0.2048 0.873 0.000 0.000 0.000 0.880 0.120 0.000
#> GSM486749 5 0.1334 0.829 0.000 0.020 0.000 0.000 0.948 0.032
#> GSM486751 5 0.1334 0.829 0.000 0.020 0.000 0.000 0.948 0.032
#> GSM486753 4 0.3962 0.839 0.000 0.060 0.004 0.800 0.108 0.028
#> GSM486755 6 0.6320 0.477 0.000 0.072 0.004 0.308 0.092 0.524
#> GSM486757 4 0.6027 0.654 0.000 0.120 0.012 0.600 0.228 0.040
#> GSM486759 5 0.0291 0.858 0.000 0.004 0.000 0.004 0.992 0.000
#> GSM486761 4 0.2048 0.873 0.000 0.000 0.000 0.880 0.120 0.000
#> GSM486763 5 0.0603 0.854 0.000 0.016 0.000 0.004 0.980 0.000
#> GSM486765 4 0.2048 0.873 0.000 0.000 0.000 0.880 0.120 0.000
#> GSM486767 4 0.2191 0.873 0.000 0.004 0.000 0.876 0.120 0.000
#> GSM486769 6 0.5017 0.590 0.000 0.020 0.004 0.028 0.408 0.540
#> GSM486771 5 0.1334 0.829 0.000 0.020 0.000 0.000 0.948 0.032
#> GSM486773 4 0.2048 0.873 0.000 0.000 0.000 0.880 0.120 0.000
#> GSM486775 4 0.2048 0.873 0.000 0.000 0.000 0.880 0.120 0.000
#> GSM486777 5 0.1138 0.851 0.000 0.012 0.000 0.004 0.960 0.024
#> GSM486779 4 0.6378 0.553 0.000 0.140 0.012 0.540 0.268 0.040
#> GSM486781 4 0.4019 0.836 0.000 0.064 0.004 0.796 0.108 0.028
#> GSM486783 4 0.5060 0.776 0.000 0.112 0.004 0.708 0.140 0.036
#> GSM486785 5 0.4490 0.713 0.000 0.136 0.012 0.048 0.764 0.040
#> GSM486787 5 0.0405 0.858 0.000 0.008 0.000 0.004 0.988 0.000
#> GSM486789 6 0.6392 0.420 0.000 0.072 0.004 0.336 0.092 0.496
#> GSM486791 6 0.4661 0.664 0.000 0.008 0.004 0.028 0.360 0.600
#> GSM486793 4 0.3885 0.841 0.000 0.060 0.004 0.804 0.108 0.024
#> GSM486795 5 0.0291 0.858 0.000 0.004 0.000 0.004 0.992 0.000
#> GSM486797 4 0.2048 0.873 0.000 0.000 0.000 0.880 0.120 0.000
#> GSM486799 4 0.2048 0.873 0.000 0.000 0.000 0.880 0.120 0.000
#> GSM486801 5 0.0291 0.858 0.000 0.004 0.000 0.004 0.992 0.000
#> GSM486803 5 0.3086 0.798 0.000 0.088 0.008 0.008 0.856 0.040
#> GSM486805 4 0.3962 0.839 0.000 0.060 0.004 0.800 0.108 0.028
#> GSM486807 4 0.4863 0.835 0.000 0.120 0.012 0.728 0.120 0.020
#> GSM486809 4 0.3248 0.863 0.000 0.024 0.004 0.836 0.120 0.016
#> GSM486811 5 0.0405 0.858 0.000 0.008 0.000 0.004 0.988 0.000
#> GSM486813 4 0.4019 0.836 0.000 0.064 0.004 0.796 0.108 0.028
#> GSM486815 5 0.3833 0.764 0.000 0.120 0.012 0.020 0.808 0.040
#> GSM486817 6 0.4761 0.691 0.000 0.024 0.000 0.032 0.312 0.632
#> GSM486819 6 0.6308 0.481 0.000 0.072 0.004 0.304 0.092 0.528
#> GSM486822 5 0.4037 0.499 0.000 0.024 0.000 0.028 0.752 0.196
#> GSM486824 5 0.6422 0.234 0.000 0.140 0.012 0.280 0.528 0.040
#> GSM486828 6 0.6320 0.477 0.000 0.072 0.004 0.308 0.092 0.524
#> GSM486831 5 0.3035 0.807 0.000 0.084 0.008 0.008 0.860 0.040
#> GSM486833 6 0.5354 0.568 0.000 0.040 0.004 0.028 0.420 0.508
#> GSM486835 5 0.0146 0.858 0.000 0.000 0.000 0.004 0.996 0.000
#> GSM486837 4 0.3964 0.846 0.000 0.068 0.004 0.792 0.120 0.016
#> GSM486839 5 0.3281 0.795 0.000 0.104 0.008 0.008 0.840 0.040
#> GSM486841 5 0.0146 0.858 0.000 0.000 0.000 0.004 0.996 0.000
#> GSM486843 5 0.1780 0.842 0.000 0.024 0.004 0.004 0.932 0.036
#> GSM486845 5 0.5714 0.248 0.000 0.108 0.008 0.028 0.612 0.244
#> GSM486847 4 0.6396 0.540 0.000 0.124 0.012 0.528 0.292 0.044
#> GSM486849 5 0.1524 0.845 0.000 0.060 0.008 0.000 0.932 0.000
#> GSM486851 5 0.0405 0.857 0.000 0.008 0.000 0.004 0.988 0.000
#> GSM486853 4 0.4892 0.840 0.000 0.104 0.008 0.732 0.120 0.036
#> GSM486855 5 0.3417 0.793 0.000 0.116 0.008 0.008 0.828 0.040
#> GSM486857 4 0.5690 0.724 0.000 0.136 0.012 0.656 0.156 0.040
#> GSM486736 3 0.3076 0.595 0.000 0.028 0.852 0.024 0.000 0.096
#> GSM486738 1 0.5549 0.511 0.652 0.032 0.084 0.016 0.000 0.216
#> GSM486740 3 0.3101 0.596 0.000 0.032 0.852 0.024 0.000 0.092
#> GSM486742 1 0.4799 0.603 0.708 0.032 0.032 0.016 0.000 0.212
#> GSM486744 3 0.6448 0.741 0.192 0.032 0.544 0.016 0.000 0.216
#> GSM486746 3 0.3265 0.600 0.004 0.036 0.848 0.024 0.000 0.088
#> GSM486748 1 0.4253 0.643 0.740 0.032 0.008 0.016 0.000 0.204
#> GSM486750 2 0.3528 0.934 0.296 0.700 0.000 0.004 0.000 0.000
#> GSM486752 2 0.3528 0.934 0.296 0.700 0.000 0.004 0.000 0.000
#> GSM486754 3 0.6448 0.741 0.192 0.032 0.544 0.016 0.000 0.216
#> GSM486756 3 0.0713 0.666 0.028 0.000 0.972 0.000 0.000 0.000
#> GSM486758 1 0.0858 0.790 0.968 0.004 0.000 0.028 0.000 0.000
#> GSM486760 2 0.3390 0.935 0.296 0.704 0.000 0.000 0.000 0.000
#> GSM486762 1 0.0508 0.788 0.984 0.000 0.000 0.012 0.000 0.004
#> GSM486764 1 0.2737 0.724 0.868 0.084 0.000 0.044 0.000 0.004
#> GSM486766 1 0.4100 0.670 0.772 0.032 0.008 0.024 0.000 0.164
#> GSM486768 3 0.6668 0.698 0.236 0.032 0.500 0.016 0.000 0.216
#> GSM486770 2 0.3651 0.385 0.004 0.736 0.248 0.008 0.000 0.004
#> GSM486772 2 0.3528 0.934 0.296 0.700 0.000 0.004 0.000 0.000
#> GSM486774 1 0.0260 0.790 0.992 0.008 0.000 0.000 0.000 0.000
#> GSM486776 1 0.3389 0.718 0.844 0.028 0.016 0.020 0.000 0.092
#> GSM486778 2 0.3390 0.935 0.296 0.704 0.000 0.000 0.000 0.000
#> GSM486780 1 0.0858 0.790 0.968 0.004 0.000 0.028 0.000 0.000
#> GSM486782 3 0.6448 0.741 0.192 0.032 0.544 0.016 0.000 0.216
#> GSM486784 1 0.1923 0.755 0.916 0.064 0.000 0.016 0.000 0.004
#> GSM486786 1 0.3728 0.522 0.772 0.180 0.000 0.044 0.000 0.004
#> GSM486788 2 0.3390 0.935 0.296 0.704 0.000 0.000 0.000 0.000
#> GSM486790 3 0.0713 0.666 0.028 0.000 0.972 0.000 0.000 0.000
#> GSM486792 3 0.3401 0.600 0.004 0.044 0.840 0.024 0.000 0.088
#> GSM486794 3 0.6554 0.740 0.192 0.032 0.544 0.024 0.000 0.208
#> GSM486796 2 0.3409 0.932 0.300 0.700 0.000 0.000 0.000 0.000
#> GSM486798 1 0.2149 0.740 0.900 0.080 0.000 0.016 0.000 0.004
#> GSM486800 2 0.3428 0.929 0.304 0.696 0.000 0.000 0.000 0.000
#> GSM486802 2 0.3390 0.935 0.296 0.704 0.000 0.000 0.000 0.000
#> GSM486804 1 0.2737 0.724 0.868 0.084 0.000 0.044 0.000 0.004
#> GSM486806 1 0.4788 0.618 0.724 0.032 0.032 0.024 0.000 0.188
#> GSM486808 1 0.0405 0.790 0.988 0.008 0.000 0.004 0.000 0.000
#> GSM486810 1 0.6956 -0.188 0.468 0.032 0.280 0.032 0.000 0.188
#> GSM486812 2 0.3390 0.935 0.296 0.704 0.000 0.000 0.000 0.000
#> GSM486814 3 0.6668 0.698 0.236 0.032 0.500 0.016 0.000 0.216
#> GSM486816 1 0.0935 0.790 0.964 0.004 0.000 0.032 0.000 0.000
#> GSM486818 3 0.0713 0.666 0.028 0.000 0.972 0.000 0.000 0.000
#> GSM486821 3 0.6364 0.743 0.184 0.032 0.576 0.024 0.000 0.184
#> GSM486823 2 0.3634 0.933 0.296 0.696 0.000 0.008 0.000 0.000
#> GSM486826 1 0.2685 0.727 0.872 0.080 0.000 0.044 0.000 0.004
#> GSM486830 3 0.6341 0.743 0.184 0.032 0.572 0.020 0.000 0.192
#> GSM486832 1 0.0508 0.788 0.984 0.000 0.000 0.012 0.000 0.004
#> GSM486834 3 0.6667 0.733 0.204 0.032 0.532 0.028 0.000 0.204
#> GSM486836 2 0.4435 0.834 0.364 0.604 0.000 0.028 0.000 0.004
#> GSM486838 1 0.0260 0.790 0.992 0.008 0.000 0.000 0.000 0.000
#> GSM486840 1 0.2373 0.731 0.888 0.084 0.000 0.024 0.000 0.004
#> GSM486842 2 0.4399 0.852 0.352 0.616 0.000 0.028 0.000 0.004
#> GSM486844 1 0.3728 0.522 0.772 0.180 0.000 0.044 0.000 0.004
#> GSM486846 3 0.6684 0.693 0.240 0.032 0.496 0.016 0.000 0.216
#> GSM486848 1 0.0603 0.790 0.980 0.004 0.000 0.016 0.000 0.000
#> GSM486850 2 0.3528 0.934 0.296 0.700 0.000 0.004 0.000 0.000
#> GSM486852 2 0.4399 0.852 0.352 0.616 0.000 0.028 0.000 0.004
#> GSM486854 1 0.4102 0.660 0.760 0.032 0.008 0.016 0.000 0.184
#> GSM486856 1 0.1442 0.774 0.944 0.040 0.000 0.012 0.000 0.004
#> GSM486858 1 0.2380 0.747 0.892 0.068 0.000 0.036 0.000 0.004
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> ATC:kmeans 119 7.74e-27 1.000 2
#> ATC:kmeans 105 1.58e-23 1.000 3
#> ATC:kmeans 113 2.48e-24 0.999 4
#> ATC:kmeans 111 4.45e-23 0.988 5
#> ATC:kmeans 111 2.52e-22 0.958 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["ATC", "skmeans"]
# you can also extract it by
# res = res_list["ATC:skmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'ATC' method.
#> Subgroups are detected by 'skmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 1.000 0.999 1.000 0.5047 0.496 0.496
#> 3 3 0.827 0.914 0.914 0.1472 0.948 0.895
#> 4 4 0.872 0.922 0.950 0.1966 0.874 0.716
#> 5 5 0.887 0.914 0.925 0.1009 0.914 0.730
#> 6 6 0.872 0.879 0.912 0.0471 0.954 0.810
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 1 0.000 1.000 1.000 0.000
#> GSM486737 1 0.000 1.000 1.000 0.000
#> GSM486739 1 0.000 1.000 1.000 0.000
#> GSM486741 1 0.000 1.000 1.000 0.000
#> GSM486743 1 0.000 1.000 1.000 0.000
#> GSM486745 1 0.000 1.000 1.000 0.000
#> GSM486747 1 0.000 1.000 1.000 0.000
#> GSM486749 1 0.000 1.000 1.000 0.000
#> GSM486751 1 0.000 1.000 1.000 0.000
#> GSM486753 1 0.000 1.000 1.000 0.000
#> GSM486755 1 0.000 1.000 1.000 0.000
#> GSM486757 1 0.000 1.000 1.000 0.000
#> GSM486759 1 0.000 1.000 1.000 0.000
#> GSM486761 1 0.000 1.000 1.000 0.000
#> GSM486763 1 0.000 1.000 1.000 0.000
#> GSM486765 1 0.000 1.000 1.000 0.000
#> GSM486767 1 0.000 1.000 1.000 0.000
#> GSM486769 1 0.000 1.000 1.000 0.000
#> GSM486771 1 0.000 1.000 1.000 0.000
#> GSM486773 1 0.000 1.000 1.000 0.000
#> GSM486775 1 0.000 1.000 1.000 0.000
#> GSM486777 1 0.000 1.000 1.000 0.000
#> GSM486779 1 0.000 1.000 1.000 0.000
#> GSM486781 1 0.000 1.000 1.000 0.000
#> GSM486783 1 0.000 1.000 1.000 0.000
#> GSM486785 1 0.000 1.000 1.000 0.000
#> GSM486787 1 0.000 1.000 1.000 0.000
#> GSM486789 1 0.000 1.000 1.000 0.000
#> GSM486791 1 0.000 1.000 1.000 0.000
#> GSM486793 1 0.000 1.000 1.000 0.000
#> GSM486795 1 0.000 1.000 1.000 0.000
#> GSM486797 1 0.000 1.000 1.000 0.000
#> GSM486799 1 0.000 1.000 1.000 0.000
#> GSM486801 1 0.000 1.000 1.000 0.000
#> GSM486803 1 0.000 1.000 1.000 0.000
#> GSM486805 1 0.000 1.000 1.000 0.000
#> GSM486807 1 0.000 1.000 1.000 0.000
#> GSM486809 1 0.000 1.000 1.000 0.000
#> GSM486811 1 0.000 1.000 1.000 0.000
#> GSM486813 1 0.000 1.000 1.000 0.000
#> GSM486815 1 0.000 1.000 1.000 0.000
#> GSM486817 1 0.000 1.000 1.000 0.000
#> GSM486819 1 0.000 1.000 1.000 0.000
#> GSM486822 1 0.000 1.000 1.000 0.000
#> GSM486824 1 0.000 1.000 1.000 0.000
#> GSM486828 1 0.000 1.000 1.000 0.000
#> GSM486831 1 0.000 1.000 1.000 0.000
#> GSM486833 1 0.000 1.000 1.000 0.000
#> GSM486835 1 0.000 1.000 1.000 0.000
#> GSM486837 1 0.000 1.000 1.000 0.000
#> GSM486839 1 0.000 1.000 1.000 0.000
#> GSM486841 1 0.000 1.000 1.000 0.000
#> GSM486843 1 0.000 1.000 1.000 0.000
#> GSM486845 1 0.000 1.000 1.000 0.000
#> GSM486847 1 0.000 1.000 1.000 0.000
#> GSM486849 1 0.000 1.000 1.000 0.000
#> GSM486851 1 0.000 1.000 1.000 0.000
#> GSM486853 1 0.000 1.000 1.000 0.000
#> GSM486855 1 0.000 1.000 1.000 0.000
#> GSM486857 1 0.000 1.000 1.000 0.000
#> GSM486736 2 0.278 0.950 0.048 0.952
#> GSM486738 2 0.000 0.999 0.000 1.000
#> GSM486740 2 0.000 0.999 0.000 1.000
#> GSM486742 2 0.000 0.999 0.000 1.000
#> GSM486744 2 0.000 0.999 0.000 1.000
#> GSM486746 2 0.000 0.999 0.000 1.000
#> GSM486748 2 0.000 0.999 0.000 1.000
#> GSM486750 2 0.000 0.999 0.000 1.000
#> GSM486752 2 0.000 0.999 0.000 1.000
#> GSM486754 2 0.000 0.999 0.000 1.000
#> GSM486756 2 0.000 0.999 0.000 1.000
#> GSM486758 2 0.000 0.999 0.000 1.000
#> GSM486760 2 0.000 0.999 0.000 1.000
#> GSM486762 2 0.000 0.999 0.000 1.000
#> GSM486764 2 0.000 0.999 0.000 1.000
#> GSM486766 2 0.000 0.999 0.000 1.000
#> GSM486768 2 0.000 0.999 0.000 1.000
#> GSM486770 2 0.000 0.999 0.000 1.000
#> GSM486772 2 0.000 0.999 0.000 1.000
#> GSM486774 2 0.000 0.999 0.000 1.000
#> GSM486776 2 0.000 0.999 0.000 1.000
#> GSM486778 2 0.000 0.999 0.000 1.000
#> GSM486780 2 0.000 0.999 0.000 1.000
#> GSM486782 2 0.000 0.999 0.000 1.000
#> GSM486784 2 0.000 0.999 0.000 1.000
#> GSM486786 2 0.000 0.999 0.000 1.000
#> GSM486788 2 0.000 0.999 0.000 1.000
#> GSM486790 2 0.000 0.999 0.000 1.000
#> GSM486792 2 0.000 0.999 0.000 1.000
#> GSM486794 2 0.000 0.999 0.000 1.000
#> GSM486796 2 0.000 0.999 0.000 1.000
#> GSM486798 2 0.000 0.999 0.000 1.000
#> GSM486800 2 0.000 0.999 0.000 1.000
#> GSM486802 2 0.000 0.999 0.000 1.000
#> GSM486804 2 0.000 0.999 0.000 1.000
#> GSM486806 2 0.000 0.999 0.000 1.000
#> GSM486808 2 0.000 0.999 0.000 1.000
#> GSM486810 2 0.000 0.999 0.000 1.000
#> GSM486812 2 0.000 0.999 0.000 1.000
#> GSM486814 2 0.000 0.999 0.000 1.000
#> GSM486816 2 0.000 0.999 0.000 1.000
#> GSM486818 2 0.000 0.999 0.000 1.000
#> GSM486821 2 0.000 0.999 0.000 1.000
#> GSM486823 2 0.000 0.999 0.000 1.000
#> GSM486826 2 0.000 0.999 0.000 1.000
#> GSM486830 2 0.000 0.999 0.000 1.000
#> GSM486832 2 0.000 0.999 0.000 1.000
#> GSM486834 2 0.000 0.999 0.000 1.000
#> GSM486836 2 0.000 0.999 0.000 1.000
#> GSM486838 2 0.000 0.999 0.000 1.000
#> GSM486840 2 0.000 0.999 0.000 1.000
#> GSM486842 2 0.000 0.999 0.000 1.000
#> GSM486844 2 0.000 0.999 0.000 1.000
#> GSM486846 2 0.000 0.999 0.000 1.000
#> GSM486848 2 0.000 0.999 0.000 1.000
#> GSM486850 2 0.000 0.999 0.000 1.000
#> GSM486852 2 0.000 0.999 0.000 1.000
#> GSM486854 2 0.000 0.999 0.000 1.000
#> GSM486856 2 0.000 0.999 0.000 1.000
#> GSM486858 2 0.000 0.999 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486737 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486739 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486741 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486743 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486745 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486747 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486749 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486751 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486753 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486755 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486757 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486759 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486761 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486763 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486765 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486767 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486769 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486771 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486773 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486775 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486777 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486779 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486781 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486783 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486785 1 0.0237 0.844 0.996 0.004 0.000
#> GSM486787 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486789 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486791 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486793 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486795 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486797 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486799 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486801 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486803 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486805 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486807 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486809 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486811 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486813 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486815 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486817 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486819 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486822 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486824 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486828 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486831 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486833 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486835 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486837 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486839 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486841 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486843 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486845 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486847 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486849 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486851 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486853 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486855 1 0.0000 0.844 1.000 0.000 0.000
#> GSM486857 1 0.5431 0.846 0.716 0.284 0.000
#> GSM486736 2 0.5623 0.564 0.280 0.716 0.004
#> GSM486738 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486740 2 0.5431 0.920 0.000 0.716 0.284
#> GSM486742 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486744 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486746 2 0.5431 0.920 0.000 0.716 0.284
#> GSM486748 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486750 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486752 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486754 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486756 2 0.5431 0.920 0.000 0.716 0.284
#> GSM486758 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486760 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486762 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486764 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486766 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486768 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486770 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486772 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486774 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486776 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486778 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486780 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486782 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486784 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486786 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486788 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486790 2 0.5431 0.920 0.000 0.716 0.284
#> GSM486792 2 0.5431 0.920 0.000 0.716 0.284
#> GSM486794 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486796 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486798 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486800 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486802 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486804 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486806 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486808 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486810 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486812 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486814 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486816 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486818 2 0.5431 0.920 0.000 0.716 0.284
#> GSM486821 3 0.0892 0.973 0.000 0.020 0.980
#> GSM486823 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486826 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486830 3 0.0892 0.973 0.000 0.020 0.980
#> GSM486832 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486834 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486836 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486838 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486840 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486842 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486844 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486846 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486848 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486850 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486852 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486854 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486856 3 0.0000 0.999 0.000 0.000 1.000
#> GSM486858 3 0.0000 0.999 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486737 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486739 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486741 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486743 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486745 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486747 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486749 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486751 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486753 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486755 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486757 2 0.3610 0.776 0.200 0.800 0.000 0.000
#> GSM486759 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486761 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486763 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486765 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486767 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486769 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486771 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486773 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486775 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486777 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486779 2 0.3172 0.833 0.160 0.840 0.000 0.000
#> GSM486781 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486783 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486785 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486787 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486789 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486791 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486793 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486795 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486797 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486799 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486801 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486803 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486805 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486807 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486809 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486811 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486813 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486815 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486817 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486819 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486822 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486824 1 0.4961 0.103 0.552 0.448 0.000 0.000
#> GSM486828 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486831 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486833 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486835 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486837 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486839 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486841 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486843 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486845 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486847 2 0.1792 0.950 0.068 0.932 0.000 0.000
#> GSM486849 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486851 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486853 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486855 1 0.0000 0.981 1.000 0.000 0.000 0.000
#> GSM486857 2 0.1118 0.985 0.036 0.964 0.000 0.000
#> GSM486736 4 0.0000 0.883 0.000 0.000 0.000 1.000
#> GSM486738 3 0.0000 0.922 0.000 0.000 1.000 0.000
#> GSM486740 4 0.0000 0.883 0.000 0.000 0.000 1.000
#> GSM486742 3 0.0000 0.922 0.000 0.000 1.000 0.000
#> GSM486744 3 0.0188 0.920 0.000 0.004 0.996 0.000
#> GSM486746 4 0.0000 0.883 0.000 0.000 0.000 1.000
#> GSM486748 3 0.0000 0.922 0.000 0.000 1.000 0.000
#> GSM486750 3 0.4375 0.810 0.000 0.032 0.788 0.180
#> GSM486752 3 0.4375 0.810 0.000 0.032 0.788 0.180
#> GSM486754 3 0.0188 0.920 0.000 0.004 0.996 0.000
#> GSM486756 4 0.3583 0.845 0.000 0.004 0.180 0.816
#> GSM486758 3 0.0000 0.922 0.000 0.000 1.000 0.000
#> GSM486760 3 0.4375 0.810 0.000 0.032 0.788 0.180
#> GSM486762 3 0.0000 0.922 0.000 0.000 1.000 0.000
#> GSM486764 3 0.0188 0.921 0.000 0.004 0.996 0.000
#> GSM486766 3 0.0000 0.922 0.000 0.000 1.000 0.000
#> GSM486768 3 0.0188 0.920 0.000 0.004 0.996 0.000
#> GSM486770 3 0.4932 0.749 0.000 0.032 0.728 0.240
#> GSM486772 3 0.4375 0.810 0.000 0.032 0.788 0.180
#> GSM486774 3 0.0000 0.922 0.000 0.000 1.000 0.000
#> GSM486776 3 0.0000 0.922 0.000 0.000 1.000 0.000
#> GSM486778 3 0.4375 0.810 0.000 0.032 0.788 0.180
#> GSM486780 3 0.0000 0.922 0.000 0.000 1.000 0.000
#> GSM486782 3 0.0188 0.920 0.000 0.004 0.996 0.000
#> GSM486784 3 0.0000 0.922 0.000 0.000 1.000 0.000
#> GSM486786 3 0.1022 0.910 0.000 0.032 0.968 0.000
#> GSM486788 3 0.4375 0.810 0.000 0.032 0.788 0.180
#> GSM486790 4 0.3583 0.845 0.000 0.004 0.180 0.816
#> GSM486792 4 0.0000 0.883 0.000 0.000 0.000 1.000
#> GSM486794 3 0.0188 0.920 0.000 0.004 0.996 0.000
#> GSM486796 3 0.4375 0.810 0.000 0.032 0.788 0.180
#> GSM486798 3 0.0000 0.922 0.000 0.000 1.000 0.000
#> GSM486800 3 0.4008 0.832 0.000 0.032 0.820 0.148
#> GSM486802 3 0.4375 0.810 0.000 0.032 0.788 0.180
#> GSM486804 3 0.0188 0.921 0.000 0.004 0.996 0.000
#> GSM486806 3 0.0000 0.922 0.000 0.000 1.000 0.000
#> GSM486808 3 0.0000 0.922 0.000 0.000 1.000 0.000
#> GSM486810 3 0.0000 0.922 0.000 0.000 1.000 0.000
#> GSM486812 3 0.4375 0.810 0.000 0.032 0.788 0.180
#> GSM486814 3 0.0188 0.920 0.000 0.004 0.996 0.000
#> GSM486816 3 0.0188 0.921 0.000 0.004 0.996 0.000
#> GSM486818 4 0.3583 0.845 0.000 0.004 0.180 0.816
#> GSM486821 3 0.2593 0.828 0.000 0.004 0.892 0.104
#> GSM486823 3 0.4375 0.810 0.000 0.032 0.788 0.180
#> GSM486826 3 0.0188 0.921 0.000 0.004 0.996 0.000
#> GSM486830 3 0.2593 0.828 0.000 0.004 0.892 0.104
#> GSM486832 3 0.0000 0.922 0.000 0.000 1.000 0.000
#> GSM486834 3 0.0188 0.921 0.000 0.004 0.996 0.000
#> GSM486836 3 0.4057 0.830 0.000 0.032 0.816 0.152
#> GSM486838 3 0.0000 0.922 0.000 0.000 1.000 0.000
#> GSM486840 3 0.0188 0.921 0.000 0.004 0.996 0.000
#> GSM486842 3 0.4057 0.830 0.000 0.032 0.816 0.152
#> GSM486844 3 0.0336 0.920 0.000 0.008 0.992 0.000
#> GSM486846 3 0.0188 0.920 0.000 0.004 0.996 0.000
#> GSM486848 3 0.0000 0.922 0.000 0.000 1.000 0.000
#> GSM486850 3 0.4375 0.810 0.000 0.032 0.788 0.180
#> GSM486852 3 0.4057 0.830 0.000 0.032 0.816 0.152
#> GSM486854 3 0.0000 0.922 0.000 0.000 1.000 0.000
#> GSM486856 3 0.0000 0.922 0.000 0.000 1.000 0.000
#> GSM486858 3 0.0188 0.921 0.000 0.004 0.996 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 4 0.1557 0.943 0.052 0.008 0.000 0.940 0.000
#> GSM486737 5 0.0162 0.978 0.000 0.000 0.000 0.004 0.996
#> GSM486739 4 0.1557 0.943 0.052 0.008 0.000 0.940 0.000
#> GSM486741 5 0.0162 0.978 0.000 0.000 0.000 0.004 0.996
#> GSM486743 5 0.0162 0.978 0.000 0.000 0.000 0.004 0.996
#> GSM486745 4 0.1557 0.943 0.052 0.008 0.000 0.940 0.000
#> GSM486747 5 0.0162 0.978 0.000 0.000 0.000 0.004 0.996
#> GSM486749 4 0.0162 0.960 0.004 0.000 0.000 0.996 0.000
#> GSM486751 4 0.0162 0.960 0.004 0.000 0.000 0.996 0.000
#> GSM486753 5 0.0162 0.978 0.000 0.000 0.000 0.004 0.996
#> GSM486755 5 0.1357 0.947 0.048 0.000 0.000 0.004 0.948
#> GSM486757 5 0.3129 0.788 0.008 0.004 0.000 0.156 0.832
#> GSM486759 4 0.0000 0.960 0.000 0.000 0.000 1.000 0.000
#> GSM486761 5 0.0162 0.978 0.000 0.000 0.000 0.004 0.996
#> GSM486763 4 0.0000 0.960 0.000 0.000 0.000 1.000 0.000
#> GSM486765 5 0.0162 0.978 0.000 0.000 0.000 0.004 0.996
#> GSM486767 5 0.0162 0.978 0.000 0.000 0.000 0.004 0.996
#> GSM486769 4 0.1430 0.945 0.052 0.004 0.000 0.944 0.000
#> GSM486771 4 0.0290 0.960 0.008 0.000 0.000 0.992 0.000
#> GSM486773 5 0.0162 0.978 0.000 0.000 0.000 0.004 0.996
#> GSM486775 5 0.0162 0.978 0.000 0.000 0.000 0.004 0.996
#> GSM486777 4 0.0000 0.960 0.000 0.000 0.000 1.000 0.000
#> GSM486779 5 0.2520 0.869 0.012 0.004 0.000 0.096 0.888
#> GSM486781 5 0.0162 0.978 0.000 0.000 0.000 0.004 0.996
#> GSM486783 5 0.0162 0.978 0.000 0.000 0.000 0.004 0.996
#> GSM486785 4 0.0566 0.955 0.012 0.004 0.000 0.984 0.000
#> GSM486787 4 0.0000 0.960 0.000 0.000 0.000 1.000 0.000
#> GSM486789 5 0.1357 0.947 0.048 0.000 0.000 0.004 0.948
#> GSM486791 4 0.1430 0.945 0.052 0.004 0.000 0.944 0.000
#> GSM486793 5 0.0162 0.978 0.000 0.000 0.000 0.004 0.996
#> GSM486795 4 0.0000 0.960 0.000 0.000 0.000 1.000 0.000
#> GSM486797 5 0.0162 0.978 0.000 0.000 0.000 0.004 0.996
#> GSM486799 5 0.0162 0.978 0.000 0.000 0.000 0.004 0.996
#> GSM486801 4 0.0000 0.960 0.000 0.000 0.000 1.000 0.000
#> GSM486803 4 0.0451 0.957 0.008 0.004 0.000 0.988 0.000
#> GSM486805 5 0.0162 0.978 0.000 0.000 0.000 0.004 0.996
#> GSM486807 5 0.0162 0.978 0.000 0.000 0.000 0.004 0.996
#> GSM486809 5 0.0162 0.978 0.000 0.000 0.000 0.004 0.996
#> GSM486811 4 0.0000 0.960 0.000 0.000 0.000 1.000 0.000
#> GSM486813 5 0.0162 0.978 0.000 0.000 0.000 0.004 0.996
#> GSM486815 4 0.0451 0.957 0.008 0.004 0.000 0.988 0.000
#> GSM486817 4 0.1430 0.945 0.052 0.004 0.000 0.944 0.000
#> GSM486819 5 0.1430 0.944 0.052 0.000 0.000 0.004 0.944
#> GSM486822 4 0.1430 0.945 0.052 0.004 0.000 0.944 0.000
#> GSM486824 4 0.4764 0.164 0.012 0.004 0.000 0.548 0.436
#> GSM486828 5 0.1357 0.947 0.048 0.000 0.000 0.004 0.948
#> GSM486831 4 0.0290 0.958 0.008 0.000 0.000 0.992 0.000
#> GSM486833 4 0.1430 0.945 0.052 0.004 0.000 0.944 0.000
#> GSM486835 4 0.0000 0.960 0.000 0.000 0.000 1.000 0.000
#> GSM486837 5 0.0324 0.976 0.004 0.000 0.000 0.004 0.992
#> GSM486839 4 0.0290 0.958 0.008 0.000 0.000 0.992 0.000
#> GSM486841 4 0.0000 0.960 0.000 0.000 0.000 1.000 0.000
#> GSM486843 4 0.0162 0.959 0.004 0.000 0.000 0.996 0.000
#> GSM486845 4 0.1270 0.946 0.052 0.000 0.000 0.948 0.000
#> GSM486847 5 0.1717 0.929 0.008 0.004 0.000 0.052 0.936
#> GSM486849 4 0.1197 0.948 0.048 0.000 0.000 0.952 0.000
#> GSM486851 4 0.0000 0.960 0.000 0.000 0.000 1.000 0.000
#> GSM486853 5 0.0162 0.978 0.000 0.000 0.000 0.004 0.996
#> GSM486855 4 0.0609 0.959 0.020 0.000 0.000 0.980 0.000
#> GSM486857 5 0.0162 0.978 0.000 0.000 0.000 0.004 0.996
#> GSM486736 2 0.0794 0.936 0.028 0.972 0.000 0.000 0.000
#> GSM486738 3 0.0324 0.890 0.004 0.000 0.992 0.000 0.004
#> GSM486740 2 0.0794 0.936 0.028 0.972 0.000 0.000 0.000
#> GSM486742 3 0.0324 0.890 0.004 0.000 0.992 0.000 0.004
#> GSM486744 3 0.3484 0.797 0.144 0.028 0.824 0.000 0.004
#> GSM486746 2 0.0880 0.935 0.032 0.968 0.000 0.000 0.000
#> GSM486748 3 0.0324 0.890 0.004 0.000 0.992 0.000 0.004
#> GSM486750 1 0.3177 0.981 0.792 0.000 0.208 0.000 0.000
#> GSM486752 1 0.3177 0.981 0.792 0.000 0.208 0.000 0.000
#> GSM486754 3 0.3484 0.797 0.144 0.028 0.824 0.000 0.004
#> GSM486756 2 0.2416 0.917 0.100 0.888 0.012 0.000 0.000
#> GSM486758 3 0.0703 0.884 0.024 0.000 0.976 0.000 0.000
#> GSM486760 1 0.3177 0.981 0.792 0.000 0.208 0.000 0.000
#> GSM486762 3 0.0162 0.891 0.004 0.000 0.996 0.000 0.000
#> GSM486764 3 0.2377 0.796 0.128 0.000 0.872 0.000 0.000
#> GSM486766 3 0.0000 0.891 0.000 0.000 1.000 0.000 0.000
#> GSM486768 3 0.3398 0.800 0.144 0.024 0.828 0.000 0.004
#> GSM486770 1 0.3930 0.906 0.792 0.056 0.152 0.000 0.000
#> GSM486772 1 0.3177 0.981 0.792 0.000 0.208 0.000 0.000
#> GSM486774 3 0.0162 0.891 0.004 0.000 0.996 0.000 0.000
#> GSM486776 3 0.0000 0.891 0.000 0.000 1.000 0.000 0.000
#> GSM486778 1 0.3177 0.981 0.792 0.000 0.208 0.000 0.000
#> GSM486780 3 0.0703 0.884 0.024 0.000 0.976 0.000 0.000
#> GSM486782 3 0.3398 0.800 0.144 0.024 0.828 0.000 0.004
#> GSM486784 3 0.0703 0.884 0.024 0.000 0.976 0.000 0.000
#> GSM486786 1 0.3480 0.949 0.752 0.000 0.248 0.000 0.000
#> GSM486788 1 0.3177 0.981 0.792 0.000 0.208 0.000 0.000
#> GSM486790 2 0.2909 0.894 0.140 0.848 0.012 0.000 0.000
#> GSM486792 2 0.1121 0.929 0.044 0.956 0.000 0.000 0.000
#> GSM486794 3 0.3398 0.800 0.144 0.024 0.828 0.000 0.004
#> GSM486796 1 0.3177 0.981 0.792 0.000 0.208 0.000 0.000
#> GSM486798 3 0.0703 0.884 0.024 0.000 0.976 0.000 0.000
#> GSM486800 1 0.3612 0.928 0.732 0.000 0.268 0.000 0.000
#> GSM486802 1 0.3177 0.981 0.792 0.000 0.208 0.000 0.000
#> GSM486804 3 0.2377 0.796 0.128 0.000 0.872 0.000 0.000
#> GSM486806 3 0.0000 0.891 0.000 0.000 1.000 0.000 0.000
#> GSM486808 3 0.0162 0.891 0.004 0.000 0.996 0.000 0.000
#> GSM486810 3 0.0290 0.889 0.008 0.000 0.992 0.000 0.000
#> GSM486812 1 0.3177 0.981 0.792 0.000 0.208 0.000 0.000
#> GSM486814 3 0.3398 0.800 0.144 0.024 0.828 0.000 0.004
#> GSM486816 3 0.1851 0.837 0.088 0.000 0.912 0.000 0.000
#> GSM486818 2 0.2305 0.920 0.092 0.896 0.012 0.000 0.000
#> GSM486821 3 0.3567 0.793 0.144 0.032 0.820 0.000 0.004
#> GSM486823 1 0.3177 0.981 0.792 0.000 0.208 0.000 0.000
#> GSM486826 3 0.2424 0.791 0.132 0.000 0.868 0.000 0.000
#> GSM486830 3 0.3567 0.793 0.144 0.032 0.820 0.000 0.004
#> GSM486832 3 0.0162 0.891 0.004 0.000 0.996 0.000 0.000
#> GSM486834 3 0.2690 0.757 0.156 0.000 0.844 0.000 0.000
#> GSM486836 1 0.3366 0.966 0.768 0.000 0.232 0.000 0.000
#> GSM486838 3 0.0162 0.891 0.004 0.000 0.996 0.000 0.000
#> GSM486840 3 0.2020 0.826 0.100 0.000 0.900 0.000 0.000
#> GSM486842 1 0.3366 0.966 0.768 0.000 0.232 0.000 0.000
#> GSM486844 3 0.3932 0.346 0.328 0.000 0.672 0.000 0.000
#> GSM486846 3 0.3398 0.800 0.144 0.024 0.828 0.000 0.004
#> GSM486848 3 0.0703 0.884 0.024 0.000 0.976 0.000 0.000
#> GSM486850 1 0.3177 0.981 0.792 0.000 0.208 0.000 0.000
#> GSM486852 1 0.3366 0.966 0.768 0.000 0.232 0.000 0.000
#> GSM486854 3 0.0162 0.890 0.004 0.000 0.996 0.000 0.000
#> GSM486856 3 0.0510 0.887 0.016 0.000 0.984 0.000 0.000
#> GSM486858 3 0.2424 0.791 0.132 0.000 0.868 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 5 0.3280 0.8554 0.000 0.160 0.004 0.000 0.808 0.028
#> GSM486737 4 0.0000 0.9528 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486739 5 0.3280 0.8554 0.000 0.160 0.004 0.000 0.808 0.028
#> GSM486741 4 0.0000 0.9528 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486743 4 0.0000 0.9528 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486745 5 0.3280 0.8554 0.000 0.160 0.004 0.000 0.808 0.028
#> GSM486747 4 0.0260 0.9526 0.000 0.008 0.000 0.992 0.000 0.000
#> GSM486749 5 0.0508 0.9095 0.000 0.012 0.000 0.000 0.984 0.004
#> GSM486751 5 0.0508 0.9095 0.000 0.012 0.000 0.000 0.984 0.004
#> GSM486753 4 0.0260 0.9506 0.000 0.008 0.000 0.992 0.000 0.000
#> GSM486755 4 0.2462 0.8644 0.000 0.096 0.000 0.876 0.000 0.028
#> GSM486757 4 0.3458 0.7620 0.000 0.032 0.004 0.804 0.156 0.004
#> GSM486759 5 0.0146 0.9094 0.000 0.000 0.000 0.000 0.996 0.004
#> GSM486761 4 0.0260 0.9526 0.000 0.008 0.000 0.992 0.000 0.000
#> GSM486763 5 0.0260 0.9099 0.000 0.008 0.000 0.000 0.992 0.000
#> GSM486765 4 0.0260 0.9526 0.000 0.008 0.000 0.992 0.000 0.000
#> GSM486767 4 0.0000 0.9528 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486769 5 0.3139 0.8574 0.000 0.160 0.000 0.000 0.812 0.028
#> GSM486771 5 0.1643 0.8979 0.000 0.068 0.000 0.000 0.924 0.008
#> GSM486773 4 0.0260 0.9526 0.000 0.008 0.000 0.992 0.000 0.000
#> GSM486775 4 0.0260 0.9526 0.000 0.008 0.000 0.992 0.000 0.000
#> GSM486777 5 0.0146 0.9094 0.000 0.000 0.000 0.000 0.996 0.004
#> GSM486779 4 0.3196 0.8137 0.000 0.040 0.004 0.836 0.116 0.004
#> GSM486781 4 0.0146 0.9520 0.000 0.000 0.000 0.996 0.000 0.004
#> GSM486783 4 0.0632 0.9468 0.000 0.024 0.000 0.976 0.000 0.000
#> GSM486785 5 0.1299 0.8889 0.000 0.036 0.004 0.004 0.952 0.004
#> GSM486787 5 0.0146 0.9094 0.000 0.000 0.000 0.000 0.996 0.004
#> GSM486789 4 0.2361 0.8717 0.000 0.088 0.000 0.884 0.000 0.028
#> GSM486791 5 0.3062 0.8594 0.000 0.160 0.000 0.000 0.816 0.024
#> GSM486793 4 0.0000 0.9528 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486795 5 0.0146 0.9094 0.000 0.000 0.000 0.000 0.996 0.004
#> GSM486797 4 0.0260 0.9526 0.000 0.008 0.000 0.992 0.000 0.000
#> GSM486799 4 0.0260 0.9526 0.000 0.008 0.000 0.992 0.000 0.000
#> GSM486801 5 0.0146 0.9094 0.000 0.000 0.000 0.000 0.996 0.004
#> GSM486803 5 0.0748 0.9015 0.000 0.016 0.004 0.000 0.976 0.004
#> GSM486805 4 0.0000 0.9528 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486807 4 0.0508 0.9513 0.000 0.012 0.000 0.984 0.000 0.004
#> GSM486809 4 0.0000 0.9528 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486811 5 0.0146 0.9094 0.000 0.000 0.000 0.000 0.996 0.004
#> GSM486813 4 0.0146 0.9520 0.000 0.000 0.000 0.996 0.000 0.004
#> GSM486815 5 0.0922 0.9040 0.000 0.024 0.004 0.000 0.968 0.004
#> GSM486817 5 0.3390 0.8530 0.000 0.160 0.000 0.008 0.804 0.028
#> GSM486819 4 0.3027 0.8099 0.000 0.148 0.000 0.824 0.000 0.028
#> GSM486822 5 0.3062 0.8594 0.000 0.160 0.000 0.000 0.816 0.024
#> GSM486824 5 0.4702 0.3514 0.000 0.040 0.004 0.344 0.608 0.004
#> GSM486828 4 0.2696 0.8449 0.000 0.116 0.000 0.856 0.000 0.028
#> GSM486831 5 0.0458 0.9051 0.000 0.016 0.000 0.000 0.984 0.000
#> GSM486833 5 0.3139 0.8574 0.000 0.160 0.000 0.000 0.812 0.028
#> GSM486835 5 0.0000 0.9092 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486837 4 0.0547 0.9486 0.000 0.020 0.000 0.980 0.000 0.000
#> GSM486839 5 0.0692 0.9020 0.000 0.020 0.004 0.000 0.976 0.000
#> GSM486841 5 0.0000 0.9092 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486843 5 0.0508 0.9047 0.000 0.012 0.004 0.000 0.984 0.000
#> GSM486845 5 0.3210 0.8548 0.000 0.168 0.000 0.000 0.804 0.028
#> GSM486847 4 0.2776 0.8471 0.000 0.032 0.004 0.860 0.104 0.000
#> GSM486849 5 0.2790 0.8709 0.000 0.132 0.000 0.000 0.844 0.024
#> GSM486851 5 0.0000 0.9092 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486853 4 0.0260 0.9519 0.000 0.008 0.000 0.992 0.000 0.000
#> GSM486855 5 0.2592 0.8840 0.000 0.116 0.004 0.000 0.864 0.016
#> GSM486857 4 0.0865 0.9401 0.000 0.036 0.000 0.964 0.000 0.000
#> GSM486736 3 0.0146 0.9931 0.000 0.000 0.996 0.000 0.000 0.004
#> GSM486738 1 0.2300 0.7690 0.856 0.144 0.000 0.000 0.000 0.000
#> GSM486740 3 0.0146 0.9931 0.000 0.000 0.996 0.000 0.000 0.004
#> GSM486742 1 0.2178 0.7870 0.868 0.132 0.000 0.000 0.000 0.000
#> GSM486744 2 0.3390 0.8118 0.296 0.704 0.000 0.000 0.000 0.000
#> GSM486746 3 0.0146 0.9931 0.000 0.000 0.996 0.000 0.000 0.004
#> GSM486748 1 0.2048 0.8038 0.880 0.120 0.000 0.000 0.000 0.000
#> GSM486750 6 0.0865 0.9946 0.036 0.000 0.000 0.000 0.000 0.964
#> GSM486752 6 0.0865 0.9946 0.036 0.000 0.000 0.000 0.000 0.964
#> GSM486754 2 0.3390 0.8118 0.296 0.704 0.000 0.000 0.000 0.000
#> GSM486756 2 0.3838 -0.0119 0.000 0.552 0.448 0.000 0.000 0.000
#> GSM486758 1 0.0260 0.9274 0.992 0.000 0.000 0.000 0.000 0.008
#> GSM486760 6 0.0865 0.9946 0.036 0.000 0.000 0.000 0.000 0.964
#> GSM486762 1 0.0000 0.9262 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486764 1 0.0865 0.9112 0.964 0.000 0.000 0.000 0.000 0.036
#> GSM486766 1 0.0260 0.9227 0.992 0.008 0.000 0.000 0.000 0.000
#> GSM486768 2 0.3390 0.8118 0.296 0.704 0.000 0.000 0.000 0.000
#> GSM486770 6 0.0935 0.9897 0.032 0.000 0.004 0.000 0.000 0.964
#> GSM486772 6 0.0865 0.9946 0.036 0.000 0.000 0.000 0.000 0.964
#> GSM486774 1 0.0000 0.9262 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486776 1 0.0000 0.9262 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486778 6 0.0865 0.9946 0.036 0.000 0.000 0.000 0.000 0.964
#> GSM486780 1 0.0260 0.9274 0.992 0.000 0.000 0.000 0.000 0.008
#> GSM486782 2 0.3390 0.8118 0.296 0.704 0.000 0.000 0.000 0.000
#> GSM486784 1 0.0260 0.9274 0.992 0.000 0.000 0.000 0.000 0.008
#> GSM486786 1 0.3330 0.5650 0.716 0.000 0.000 0.000 0.000 0.284
#> GSM486788 6 0.0865 0.9946 0.036 0.000 0.000 0.000 0.000 0.964
#> GSM486790 2 0.3547 0.2300 0.000 0.668 0.332 0.000 0.000 0.000
#> GSM486792 3 0.0547 0.9791 0.000 0.000 0.980 0.000 0.000 0.020
#> GSM486794 2 0.3390 0.8118 0.296 0.704 0.000 0.000 0.000 0.000
#> GSM486796 6 0.0865 0.9946 0.036 0.000 0.000 0.000 0.000 0.964
#> GSM486798 1 0.0260 0.9274 0.992 0.000 0.000 0.000 0.000 0.008
#> GSM486800 6 0.1285 0.9776 0.052 0.004 0.000 0.000 0.000 0.944
#> GSM486802 6 0.0865 0.9946 0.036 0.000 0.000 0.000 0.000 0.964
#> GSM486804 1 0.0790 0.9140 0.968 0.000 0.000 0.000 0.000 0.032
#> GSM486806 1 0.0260 0.9227 0.992 0.008 0.000 0.000 0.000 0.000
#> GSM486808 1 0.0000 0.9262 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486810 1 0.0146 0.9248 0.996 0.004 0.000 0.000 0.000 0.000
#> GSM486812 6 0.0865 0.9946 0.036 0.000 0.000 0.000 0.000 0.964
#> GSM486814 2 0.3390 0.8118 0.296 0.704 0.000 0.000 0.000 0.000
#> GSM486816 1 0.0363 0.9258 0.988 0.000 0.000 0.000 0.000 0.012
#> GSM486818 2 0.3854 -0.0564 0.000 0.536 0.464 0.000 0.000 0.000
#> GSM486821 2 0.3050 0.7735 0.236 0.764 0.000 0.000 0.000 0.000
#> GSM486823 6 0.0865 0.9946 0.036 0.000 0.000 0.000 0.000 0.964
#> GSM486826 1 0.0865 0.9110 0.964 0.000 0.000 0.000 0.000 0.036
#> GSM486830 2 0.3023 0.7749 0.232 0.768 0.000 0.000 0.000 0.000
#> GSM486832 1 0.0000 0.9262 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486834 1 0.4034 0.4595 0.652 0.020 0.000 0.000 0.000 0.328
#> GSM486836 6 0.1075 0.9850 0.048 0.000 0.000 0.000 0.000 0.952
#> GSM486838 1 0.0000 0.9262 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486840 1 0.0632 0.9194 0.976 0.000 0.000 0.000 0.000 0.024
#> GSM486842 6 0.1075 0.9850 0.048 0.000 0.000 0.000 0.000 0.952
#> GSM486844 1 0.2048 0.8102 0.880 0.000 0.000 0.000 0.000 0.120
#> GSM486846 2 0.3390 0.8118 0.296 0.704 0.000 0.000 0.000 0.000
#> GSM486848 1 0.0260 0.9274 0.992 0.000 0.000 0.000 0.000 0.008
#> GSM486850 6 0.0865 0.9946 0.036 0.000 0.000 0.000 0.000 0.964
#> GSM486852 6 0.1075 0.9850 0.048 0.000 0.000 0.000 0.000 0.952
#> GSM486854 1 0.0632 0.9110 0.976 0.024 0.000 0.000 0.000 0.000
#> GSM486856 1 0.0260 0.9274 0.992 0.000 0.000 0.000 0.000 0.008
#> GSM486858 1 0.0937 0.9073 0.960 0.000 0.000 0.000 0.000 0.040
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> ATC:skmeans 120 4.67e-27 1.000 2
#> ATC:skmeans 120 8.76e-27 1.000 3
#> ATC:skmeans 119 1.27e-25 1.000 4
#> ATC:skmeans 118 1.43e-24 0.997 5
#> ATC:skmeans 115 3.59e-23 0.992 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["ATC", "pam"]
# you can also extract it by
# res = res_list["ATC:pam"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'ATC' method.
#> Subgroups are detected by 'pam' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 1.000 0.998 0.999 0.5047 0.496 0.496
#> 3 3 0.722 0.883 0.827 0.2435 0.866 0.731
#> 4 4 0.894 0.879 0.945 0.1872 0.871 0.659
#> 5 5 0.857 0.845 0.927 0.0349 0.977 0.911
#> 6 6 0.886 0.851 0.916 0.0355 0.945 0.777
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 1 0.000 1.000 1.000 0.000
#> GSM486737 1 0.000 1.000 1.000 0.000
#> GSM486739 1 0.000 1.000 1.000 0.000
#> GSM486741 1 0.000 1.000 1.000 0.000
#> GSM486743 1 0.000 1.000 1.000 0.000
#> GSM486745 1 0.000 1.000 1.000 0.000
#> GSM486747 1 0.000 1.000 1.000 0.000
#> GSM486749 1 0.000 1.000 1.000 0.000
#> GSM486751 1 0.000 1.000 1.000 0.000
#> GSM486753 1 0.000 1.000 1.000 0.000
#> GSM486755 1 0.000 1.000 1.000 0.000
#> GSM486757 1 0.000 1.000 1.000 0.000
#> GSM486759 1 0.000 1.000 1.000 0.000
#> GSM486761 1 0.000 1.000 1.000 0.000
#> GSM486763 1 0.000 1.000 1.000 0.000
#> GSM486765 1 0.000 1.000 1.000 0.000
#> GSM486767 1 0.000 1.000 1.000 0.000
#> GSM486769 1 0.000 1.000 1.000 0.000
#> GSM486771 1 0.000 1.000 1.000 0.000
#> GSM486773 1 0.000 1.000 1.000 0.000
#> GSM486775 1 0.000 1.000 1.000 0.000
#> GSM486777 1 0.000 1.000 1.000 0.000
#> GSM486779 1 0.000 1.000 1.000 0.000
#> GSM486781 1 0.000 1.000 1.000 0.000
#> GSM486783 1 0.000 1.000 1.000 0.000
#> GSM486785 1 0.000 1.000 1.000 0.000
#> GSM486787 1 0.000 1.000 1.000 0.000
#> GSM486789 1 0.000 1.000 1.000 0.000
#> GSM486791 1 0.000 1.000 1.000 0.000
#> GSM486793 1 0.000 1.000 1.000 0.000
#> GSM486795 1 0.000 1.000 1.000 0.000
#> GSM486797 1 0.000 1.000 1.000 0.000
#> GSM486799 1 0.000 1.000 1.000 0.000
#> GSM486801 1 0.000 1.000 1.000 0.000
#> GSM486803 1 0.000 1.000 1.000 0.000
#> GSM486805 1 0.000 1.000 1.000 0.000
#> GSM486807 1 0.000 1.000 1.000 0.000
#> GSM486809 1 0.000 1.000 1.000 0.000
#> GSM486811 1 0.000 1.000 1.000 0.000
#> GSM486813 1 0.000 1.000 1.000 0.000
#> GSM486815 1 0.000 1.000 1.000 0.000
#> GSM486817 1 0.000 1.000 1.000 0.000
#> GSM486819 1 0.000 1.000 1.000 0.000
#> GSM486822 1 0.000 1.000 1.000 0.000
#> GSM486824 1 0.000 1.000 1.000 0.000
#> GSM486828 1 0.000 1.000 1.000 0.000
#> GSM486831 1 0.000 1.000 1.000 0.000
#> GSM486833 1 0.000 1.000 1.000 0.000
#> GSM486835 1 0.000 1.000 1.000 0.000
#> GSM486837 1 0.000 1.000 1.000 0.000
#> GSM486839 1 0.000 1.000 1.000 0.000
#> GSM486841 1 0.000 1.000 1.000 0.000
#> GSM486843 1 0.000 1.000 1.000 0.000
#> GSM486845 1 0.000 1.000 1.000 0.000
#> GSM486847 1 0.000 1.000 1.000 0.000
#> GSM486849 1 0.000 1.000 1.000 0.000
#> GSM486851 1 0.000 1.000 1.000 0.000
#> GSM486853 1 0.000 1.000 1.000 0.000
#> GSM486855 1 0.000 1.000 1.000 0.000
#> GSM486857 1 0.000 1.000 1.000 0.000
#> GSM486736 2 0.506 0.874 0.112 0.888
#> GSM486738 2 0.000 0.998 0.000 1.000
#> GSM486740 2 0.000 0.998 0.000 1.000
#> GSM486742 2 0.000 0.998 0.000 1.000
#> GSM486744 2 0.000 0.998 0.000 1.000
#> GSM486746 2 0.000 0.998 0.000 1.000
#> GSM486748 2 0.000 0.998 0.000 1.000
#> GSM486750 2 0.000 0.998 0.000 1.000
#> GSM486752 2 0.000 0.998 0.000 1.000
#> GSM486754 2 0.000 0.998 0.000 1.000
#> GSM486756 2 0.000 0.998 0.000 1.000
#> GSM486758 2 0.000 0.998 0.000 1.000
#> GSM486760 2 0.000 0.998 0.000 1.000
#> GSM486762 2 0.000 0.998 0.000 1.000
#> GSM486764 2 0.000 0.998 0.000 1.000
#> GSM486766 2 0.000 0.998 0.000 1.000
#> GSM486768 2 0.000 0.998 0.000 1.000
#> GSM486770 2 0.000 0.998 0.000 1.000
#> GSM486772 2 0.000 0.998 0.000 1.000
#> GSM486774 2 0.000 0.998 0.000 1.000
#> GSM486776 2 0.000 0.998 0.000 1.000
#> GSM486778 2 0.000 0.998 0.000 1.000
#> GSM486780 2 0.000 0.998 0.000 1.000
#> GSM486782 2 0.000 0.998 0.000 1.000
#> GSM486784 2 0.000 0.998 0.000 1.000
#> GSM486786 2 0.000 0.998 0.000 1.000
#> GSM486788 2 0.000 0.998 0.000 1.000
#> GSM486790 2 0.000 0.998 0.000 1.000
#> GSM486792 2 0.000 0.998 0.000 1.000
#> GSM486794 2 0.000 0.998 0.000 1.000
#> GSM486796 2 0.000 0.998 0.000 1.000
#> GSM486798 2 0.000 0.998 0.000 1.000
#> GSM486800 2 0.000 0.998 0.000 1.000
#> GSM486802 2 0.000 0.998 0.000 1.000
#> GSM486804 2 0.000 0.998 0.000 1.000
#> GSM486806 2 0.000 0.998 0.000 1.000
#> GSM486808 2 0.000 0.998 0.000 1.000
#> GSM486810 2 0.000 0.998 0.000 1.000
#> GSM486812 2 0.000 0.998 0.000 1.000
#> GSM486814 2 0.000 0.998 0.000 1.000
#> GSM486816 2 0.000 0.998 0.000 1.000
#> GSM486818 2 0.000 0.998 0.000 1.000
#> GSM486821 2 0.000 0.998 0.000 1.000
#> GSM486823 2 0.000 0.998 0.000 1.000
#> GSM486826 2 0.000 0.998 0.000 1.000
#> GSM486830 2 0.000 0.998 0.000 1.000
#> GSM486832 2 0.000 0.998 0.000 1.000
#> GSM486834 2 0.000 0.998 0.000 1.000
#> GSM486836 2 0.000 0.998 0.000 1.000
#> GSM486838 2 0.000 0.998 0.000 1.000
#> GSM486840 2 0.000 0.998 0.000 1.000
#> GSM486842 2 0.000 0.998 0.000 1.000
#> GSM486844 2 0.000 0.998 0.000 1.000
#> GSM486846 2 0.000 0.998 0.000 1.000
#> GSM486848 2 0.000 0.998 0.000 1.000
#> GSM486850 2 0.000 0.998 0.000 1.000
#> GSM486852 2 0.000 0.998 0.000 1.000
#> GSM486854 2 0.000 0.998 0.000 1.000
#> GSM486856 2 0.000 0.998 0.000 1.000
#> GSM486858 2 0.000 0.998 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 1 0.6244 0.89794 0.560 0.440 0.000
#> GSM486737 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486739 1 0.6244 0.89794 0.560 0.440 0.000
#> GSM486741 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486743 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486745 1 0.6244 0.89794 0.560 0.440 0.000
#> GSM486747 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486749 1 0.6126 0.93875 0.600 0.400 0.000
#> GSM486751 1 0.6126 0.93875 0.600 0.400 0.000
#> GSM486753 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486755 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486757 2 0.2625 0.85149 0.084 0.916 0.000
#> GSM486759 1 0.6126 0.93875 0.600 0.400 0.000
#> GSM486761 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486763 1 0.6126 0.93875 0.600 0.400 0.000
#> GSM486765 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486767 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486769 1 0.6140 0.93502 0.596 0.404 0.000
#> GSM486771 1 0.6126 0.93875 0.600 0.400 0.000
#> GSM486773 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486775 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486777 1 0.6126 0.93875 0.600 0.400 0.000
#> GSM486779 2 0.1860 0.90728 0.052 0.948 0.000
#> GSM486781 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486783 2 0.0237 0.97324 0.004 0.996 0.000
#> GSM486785 2 0.4796 0.48271 0.220 0.780 0.000
#> GSM486787 1 0.6126 0.93875 0.600 0.400 0.000
#> GSM486789 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486791 1 0.6126 0.93875 0.600 0.400 0.000
#> GSM486793 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486795 1 0.6126 0.93875 0.600 0.400 0.000
#> GSM486797 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486799 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486801 1 0.6126 0.93875 0.600 0.400 0.000
#> GSM486803 1 0.6126 0.93875 0.600 0.400 0.000
#> GSM486805 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486807 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486809 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486811 1 0.6126 0.93875 0.600 0.400 0.000
#> GSM486813 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486815 1 0.6126 0.93875 0.600 0.400 0.000
#> GSM486817 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486819 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486822 1 0.6244 0.89794 0.560 0.440 0.000
#> GSM486824 2 0.2796 0.83892 0.092 0.908 0.000
#> GSM486828 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486831 2 0.0237 0.97324 0.004 0.996 0.000
#> GSM486833 1 0.6309 0.79144 0.504 0.496 0.000
#> GSM486835 1 0.6126 0.93875 0.600 0.400 0.000
#> GSM486837 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486839 2 0.0237 0.97324 0.004 0.996 0.000
#> GSM486841 1 0.6126 0.93875 0.600 0.400 0.000
#> GSM486843 1 0.6126 0.93875 0.600 0.400 0.000
#> GSM486845 1 0.6244 0.89794 0.560 0.440 0.000
#> GSM486847 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486849 1 0.6126 0.93875 0.600 0.400 0.000
#> GSM486851 1 0.6126 0.93875 0.600 0.400 0.000
#> GSM486853 2 0.0000 0.97710 0.000 1.000 0.000
#> GSM486855 2 0.0747 0.95916 0.016 0.984 0.000
#> GSM486857 2 0.0424 0.96870 0.008 0.992 0.000
#> GSM486736 1 0.6280 0.00391 0.540 0.000 0.460
#> GSM486738 3 0.0747 0.87135 0.016 0.000 0.984
#> GSM486740 3 0.2711 0.84985 0.088 0.000 0.912
#> GSM486742 3 0.0000 0.87110 0.000 0.000 1.000
#> GSM486744 3 0.0000 0.87110 0.000 0.000 1.000
#> GSM486746 3 0.1860 0.86649 0.052 0.000 0.948
#> GSM486748 3 0.0000 0.87110 0.000 0.000 1.000
#> GSM486750 3 0.6111 0.78362 0.396 0.000 0.604
#> GSM486752 3 0.6111 0.78362 0.396 0.000 0.604
#> GSM486754 3 0.0000 0.87110 0.000 0.000 1.000
#> GSM486756 3 0.0237 0.86985 0.004 0.000 0.996
#> GSM486758 3 0.1529 0.87058 0.040 0.000 0.960
#> GSM486760 3 0.6111 0.78362 0.396 0.000 0.604
#> GSM486762 3 0.0592 0.87206 0.012 0.000 0.988
#> GSM486764 3 0.6079 0.78627 0.388 0.000 0.612
#> GSM486766 3 0.0000 0.87110 0.000 0.000 1.000
#> GSM486768 3 0.0000 0.87110 0.000 0.000 1.000
#> GSM486770 3 0.5058 0.82154 0.244 0.000 0.756
#> GSM486772 3 0.6111 0.78362 0.396 0.000 0.604
#> GSM486774 3 0.1031 0.87197 0.024 0.000 0.976
#> GSM486776 3 0.0000 0.87110 0.000 0.000 1.000
#> GSM486778 3 0.6111 0.78362 0.396 0.000 0.604
#> GSM486780 3 0.0592 0.87206 0.012 0.000 0.988
#> GSM486782 3 0.0000 0.87110 0.000 0.000 1.000
#> GSM486784 3 0.4002 0.84831 0.160 0.000 0.840
#> GSM486786 3 0.6111 0.78362 0.396 0.000 0.604
#> GSM486788 3 0.6111 0.78362 0.396 0.000 0.604
#> GSM486790 3 0.0237 0.86985 0.004 0.000 0.996
#> GSM486792 3 0.4931 0.82504 0.232 0.000 0.768
#> GSM486794 3 0.0000 0.87110 0.000 0.000 1.000
#> GSM486796 3 0.6111 0.78362 0.396 0.000 0.604
#> GSM486798 3 0.4235 0.84747 0.176 0.000 0.824
#> GSM486800 3 0.5363 0.81740 0.276 0.000 0.724
#> GSM486802 3 0.6111 0.78362 0.396 0.000 0.604
#> GSM486804 3 0.6095 0.78502 0.392 0.000 0.608
#> GSM486806 3 0.0000 0.87110 0.000 0.000 1.000
#> GSM486808 3 0.0592 0.87206 0.012 0.000 0.988
#> GSM486810 3 0.0000 0.87110 0.000 0.000 1.000
#> GSM486812 3 0.6111 0.78362 0.396 0.000 0.604
#> GSM486814 3 0.0000 0.87110 0.000 0.000 1.000
#> GSM486816 3 0.0592 0.87206 0.012 0.000 0.988
#> GSM486818 3 0.0237 0.86985 0.004 0.000 0.996
#> GSM486821 3 0.0000 0.87110 0.000 0.000 1.000
#> GSM486823 3 0.4346 0.84361 0.184 0.000 0.816
#> GSM486826 3 0.4796 0.83825 0.220 0.000 0.780
#> GSM486830 3 0.0000 0.87110 0.000 0.000 1.000
#> GSM486832 3 0.0592 0.87206 0.012 0.000 0.988
#> GSM486834 3 0.0000 0.87110 0.000 0.000 1.000
#> GSM486836 3 0.6111 0.78362 0.396 0.000 0.604
#> GSM486838 3 0.0592 0.87206 0.012 0.000 0.988
#> GSM486840 3 0.4842 0.83665 0.224 0.000 0.776
#> GSM486842 3 0.6111 0.78362 0.396 0.000 0.604
#> GSM486844 3 0.6111 0.78362 0.396 0.000 0.604
#> GSM486846 3 0.0000 0.87110 0.000 0.000 1.000
#> GSM486848 3 0.0592 0.87206 0.012 0.000 0.988
#> GSM486850 3 0.6111 0.78362 0.396 0.000 0.604
#> GSM486852 3 0.6111 0.78362 0.396 0.000 0.604
#> GSM486854 3 0.0000 0.87110 0.000 0.000 1.000
#> GSM486856 3 0.3941 0.84924 0.156 0.000 0.844
#> GSM486858 3 0.4062 0.84828 0.164 0.000 0.836
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 4 0.1474 0.9238 0.052 0.000 0.000 0.948
#> GSM486737 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486739 4 0.1389 0.9267 0.048 0.000 0.000 0.952
#> GSM486741 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486743 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486745 4 0.1389 0.9267 0.048 0.000 0.000 0.952
#> GSM486747 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486749 4 0.0000 0.9549 0.000 0.000 0.000 1.000
#> GSM486751 4 0.0000 0.9549 0.000 0.000 0.000 1.000
#> GSM486753 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486755 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486757 1 0.3907 0.7102 0.768 0.000 0.000 0.232
#> GSM486759 4 0.0000 0.9549 0.000 0.000 0.000 1.000
#> GSM486761 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486763 4 0.0000 0.9549 0.000 0.000 0.000 1.000
#> GSM486765 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486767 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486769 4 0.0188 0.9526 0.004 0.000 0.000 0.996
#> GSM486771 4 0.0000 0.9549 0.000 0.000 0.000 1.000
#> GSM486773 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486775 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486777 4 0.0000 0.9549 0.000 0.000 0.000 1.000
#> GSM486779 1 0.3172 0.8159 0.840 0.000 0.000 0.160
#> GSM486781 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486783 1 0.0188 0.9757 0.996 0.000 0.000 0.004
#> GSM486785 4 0.4998 -0.0144 0.488 0.000 0.000 0.512
#> GSM486787 4 0.0000 0.9549 0.000 0.000 0.000 1.000
#> GSM486789 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486791 4 0.0000 0.9549 0.000 0.000 0.000 1.000
#> GSM486793 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486795 4 0.0000 0.9549 0.000 0.000 0.000 1.000
#> GSM486797 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486799 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486801 4 0.0000 0.9549 0.000 0.000 0.000 1.000
#> GSM486803 4 0.0000 0.9549 0.000 0.000 0.000 1.000
#> GSM486805 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486807 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486809 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486811 4 0.0000 0.9549 0.000 0.000 0.000 1.000
#> GSM486813 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486815 4 0.0000 0.9549 0.000 0.000 0.000 1.000
#> GSM486817 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486819 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486822 4 0.1474 0.9238 0.052 0.000 0.000 0.948
#> GSM486824 1 0.3942 0.7096 0.764 0.000 0.000 0.236
#> GSM486828 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486831 1 0.0469 0.9703 0.988 0.000 0.000 0.012
#> GSM486833 4 0.3649 0.7537 0.204 0.000 0.000 0.796
#> GSM486835 4 0.0000 0.9549 0.000 0.000 0.000 1.000
#> GSM486837 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486839 1 0.0188 0.9757 0.996 0.000 0.000 0.004
#> GSM486841 4 0.0000 0.9549 0.000 0.000 0.000 1.000
#> GSM486843 4 0.0000 0.9549 0.000 0.000 0.000 1.000
#> GSM486845 4 0.2149 0.8907 0.088 0.000 0.000 0.912
#> GSM486847 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486849 4 0.0000 0.9549 0.000 0.000 0.000 1.000
#> GSM486851 4 0.0000 0.9549 0.000 0.000 0.000 1.000
#> GSM486853 1 0.0000 0.9783 1.000 0.000 0.000 0.000
#> GSM486855 1 0.1302 0.9427 0.956 0.000 0.000 0.044
#> GSM486857 1 0.0336 0.9729 0.992 0.000 0.000 0.008
#> GSM486736 2 0.7055 0.0327 0.000 0.480 0.396 0.124
#> GSM486738 2 0.1474 0.8692 0.000 0.948 0.052 0.000
#> GSM486740 2 0.4866 0.2823 0.000 0.596 0.404 0.000
#> GSM486742 2 0.0000 0.9020 0.000 1.000 0.000 0.000
#> GSM486744 2 0.0000 0.9020 0.000 1.000 0.000 0.000
#> GSM486746 2 0.4866 0.2823 0.000 0.596 0.404 0.000
#> GSM486748 2 0.0000 0.9020 0.000 1.000 0.000 0.000
#> GSM486750 3 0.0592 0.9276 0.000 0.016 0.984 0.000
#> GSM486752 3 0.0592 0.9276 0.000 0.016 0.984 0.000
#> GSM486754 2 0.0000 0.9020 0.000 1.000 0.000 0.000
#> GSM486756 2 0.0592 0.8924 0.000 0.984 0.016 0.000
#> GSM486758 2 0.1474 0.8799 0.000 0.948 0.052 0.000
#> GSM486760 3 0.0592 0.9276 0.000 0.016 0.984 0.000
#> GSM486762 2 0.0817 0.8963 0.000 0.976 0.024 0.000
#> GSM486764 3 0.3400 0.7529 0.000 0.180 0.820 0.000
#> GSM486766 2 0.0000 0.9020 0.000 1.000 0.000 0.000
#> GSM486768 2 0.0000 0.9020 0.000 1.000 0.000 0.000
#> GSM486770 3 0.3942 0.7138 0.000 0.236 0.764 0.000
#> GSM486772 3 0.0592 0.9276 0.000 0.016 0.984 0.000
#> GSM486774 2 0.1389 0.8828 0.000 0.952 0.048 0.000
#> GSM486776 2 0.0000 0.9020 0.000 1.000 0.000 0.000
#> GSM486778 3 0.0592 0.9276 0.000 0.016 0.984 0.000
#> GSM486780 2 0.0817 0.8963 0.000 0.976 0.024 0.000
#> GSM486782 2 0.0000 0.9020 0.000 1.000 0.000 0.000
#> GSM486784 2 0.3873 0.7050 0.000 0.772 0.228 0.000
#> GSM486786 3 0.0592 0.9276 0.000 0.016 0.984 0.000
#> GSM486788 3 0.0592 0.9276 0.000 0.016 0.984 0.000
#> GSM486790 2 0.0592 0.8924 0.000 0.984 0.016 0.000
#> GSM486792 3 0.4008 0.6854 0.000 0.244 0.756 0.000
#> GSM486794 2 0.0000 0.9020 0.000 1.000 0.000 0.000
#> GSM486796 3 0.0592 0.9276 0.000 0.016 0.984 0.000
#> GSM486798 2 0.4222 0.6542 0.000 0.728 0.272 0.000
#> GSM486800 3 0.3486 0.7720 0.000 0.188 0.812 0.000
#> GSM486802 3 0.0592 0.9276 0.000 0.016 0.984 0.000
#> GSM486804 3 0.2345 0.8555 0.000 0.100 0.900 0.000
#> GSM486806 2 0.0000 0.9020 0.000 1.000 0.000 0.000
#> GSM486808 2 0.0817 0.8963 0.000 0.976 0.024 0.000
#> GSM486810 2 0.0000 0.9020 0.000 1.000 0.000 0.000
#> GSM486812 3 0.0592 0.9276 0.000 0.016 0.984 0.000
#> GSM486814 2 0.0000 0.9020 0.000 1.000 0.000 0.000
#> GSM486816 2 0.0817 0.8963 0.000 0.976 0.024 0.000
#> GSM486818 2 0.0592 0.8924 0.000 0.984 0.016 0.000
#> GSM486821 2 0.0000 0.9020 0.000 1.000 0.000 0.000
#> GSM486823 3 0.4697 0.4861 0.000 0.356 0.644 0.000
#> GSM486826 2 0.4564 0.5529 0.000 0.672 0.328 0.000
#> GSM486830 2 0.0000 0.9020 0.000 1.000 0.000 0.000
#> GSM486832 2 0.0817 0.8963 0.000 0.976 0.024 0.000
#> GSM486834 2 0.0000 0.9020 0.000 1.000 0.000 0.000
#> GSM486836 3 0.0592 0.9276 0.000 0.016 0.984 0.000
#> GSM486838 2 0.0817 0.8963 0.000 0.976 0.024 0.000
#> GSM486840 2 0.4624 0.5279 0.000 0.660 0.340 0.000
#> GSM486842 3 0.0592 0.9276 0.000 0.016 0.984 0.000
#> GSM486844 3 0.0592 0.9276 0.000 0.016 0.984 0.000
#> GSM486846 2 0.0000 0.9020 0.000 1.000 0.000 0.000
#> GSM486848 2 0.0817 0.8963 0.000 0.976 0.024 0.000
#> GSM486850 3 0.0592 0.9276 0.000 0.016 0.984 0.000
#> GSM486852 3 0.0592 0.9276 0.000 0.016 0.984 0.000
#> GSM486854 2 0.0000 0.9020 0.000 1.000 0.000 0.000
#> GSM486856 2 0.3801 0.7148 0.000 0.780 0.220 0.000
#> GSM486858 2 0.3907 0.7013 0.000 0.768 0.232 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 4 0.1270 0.9093 0.000 0.000 0.000 0.948 0.052
#> GSM486737 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486739 4 0.1197 0.9127 0.000 0.000 0.000 0.952 0.048
#> GSM486741 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486743 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486745 4 0.1197 0.9127 0.000 0.000 0.000 0.952 0.048
#> GSM486747 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486749 4 0.0000 0.9466 0.000 0.000 0.000 1.000 0.000
#> GSM486751 4 0.0000 0.9466 0.000 0.000 0.000 1.000 0.000
#> GSM486753 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486755 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486757 5 0.3366 0.7011 0.000 0.000 0.000 0.232 0.768
#> GSM486759 4 0.0000 0.9466 0.000 0.000 0.000 1.000 0.000
#> GSM486761 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486763 4 0.0000 0.9466 0.000 0.000 0.000 1.000 0.000
#> GSM486765 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486767 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486769 4 0.0162 0.9439 0.000 0.000 0.000 0.996 0.004
#> GSM486771 4 0.0000 0.9466 0.000 0.000 0.000 1.000 0.000
#> GSM486773 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486775 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486777 4 0.0000 0.9466 0.000 0.000 0.000 1.000 0.000
#> GSM486779 5 0.2732 0.8015 0.000 0.000 0.000 0.160 0.840
#> GSM486781 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486783 5 0.0162 0.9723 0.000 0.000 0.000 0.004 0.996
#> GSM486785 4 0.4305 -0.0141 0.000 0.000 0.000 0.512 0.488
#> GSM486787 4 0.0000 0.9466 0.000 0.000 0.000 1.000 0.000
#> GSM486789 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486791 4 0.0000 0.9466 0.000 0.000 0.000 1.000 0.000
#> GSM486793 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486795 4 0.0000 0.9466 0.000 0.000 0.000 1.000 0.000
#> GSM486797 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486799 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486801 4 0.0000 0.9466 0.000 0.000 0.000 1.000 0.000
#> GSM486803 4 0.0000 0.9466 0.000 0.000 0.000 1.000 0.000
#> GSM486805 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486807 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486809 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486811 4 0.0000 0.9466 0.000 0.000 0.000 1.000 0.000
#> GSM486813 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486815 4 0.0000 0.9466 0.000 0.000 0.000 1.000 0.000
#> GSM486817 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486819 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486822 4 0.1270 0.9093 0.000 0.000 0.000 0.948 0.052
#> GSM486824 5 0.3395 0.6994 0.000 0.000 0.000 0.236 0.764
#> GSM486828 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486831 5 0.0404 0.9662 0.000 0.000 0.000 0.012 0.988
#> GSM486833 4 0.3143 0.7083 0.000 0.000 0.000 0.796 0.204
#> GSM486835 4 0.0000 0.9466 0.000 0.000 0.000 1.000 0.000
#> GSM486837 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486839 5 0.0162 0.9723 0.000 0.000 0.000 0.004 0.996
#> GSM486841 4 0.0000 0.9466 0.000 0.000 0.000 1.000 0.000
#> GSM486843 4 0.0000 0.9466 0.000 0.000 0.000 1.000 0.000
#> GSM486845 4 0.1851 0.8688 0.000 0.000 0.000 0.912 0.088
#> GSM486847 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486849 4 0.0000 0.9466 0.000 0.000 0.000 1.000 0.000
#> GSM486851 4 0.0000 0.9466 0.000 0.000 0.000 1.000 0.000
#> GSM486853 5 0.0000 0.9753 0.000 0.000 0.000 0.000 1.000
#> GSM486855 5 0.1121 0.9354 0.000 0.000 0.000 0.044 0.956
#> GSM486857 5 0.0290 0.9691 0.000 0.000 0.000 0.008 0.992
#> GSM486736 2 0.1544 0.8100 0.068 0.932 0.000 0.000 0.000
#> GSM486738 3 0.3003 0.7206 0.188 0.000 0.812 0.000 0.000
#> GSM486740 2 0.1544 0.8100 0.068 0.932 0.000 0.000 0.000
#> GSM486742 3 0.2648 0.7557 0.152 0.000 0.848 0.000 0.000
#> GSM486744 3 0.4049 0.7516 0.056 0.164 0.780 0.000 0.000
#> GSM486746 2 0.1544 0.8100 0.068 0.932 0.000 0.000 0.000
#> GSM486748 3 0.1544 0.8167 0.068 0.000 0.932 0.000 0.000
#> GSM486750 1 0.0000 0.8848 1.000 0.000 0.000 0.000 0.000
#> GSM486752 1 0.0000 0.8848 1.000 0.000 0.000 0.000 0.000
#> GSM486754 3 0.3771 0.7659 0.040 0.164 0.796 0.000 0.000
#> GSM486756 3 0.4287 0.2616 0.000 0.460 0.540 0.000 0.000
#> GSM486758 3 0.2046 0.7893 0.016 0.068 0.916 0.000 0.000
#> GSM486760 1 0.0000 0.8848 1.000 0.000 0.000 0.000 0.000
#> GSM486762 3 0.0000 0.8266 0.000 0.000 1.000 0.000 0.000
#> GSM486764 1 0.4708 0.6729 0.712 0.068 0.220 0.000 0.000
#> GSM486766 3 0.1430 0.8268 0.004 0.052 0.944 0.000 0.000
#> GSM486768 3 0.2773 0.7917 0.000 0.164 0.836 0.000 0.000
#> GSM486770 1 0.2462 0.7726 0.880 0.008 0.112 0.000 0.000
#> GSM486772 1 0.0000 0.8848 1.000 0.000 0.000 0.000 0.000
#> GSM486774 3 0.0404 0.8246 0.012 0.000 0.988 0.000 0.000
#> GSM486776 3 0.0000 0.8266 0.000 0.000 1.000 0.000 0.000
#> GSM486778 1 0.0000 0.8848 1.000 0.000 0.000 0.000 0.000
#> GSM486780 3 0.1544 0.7978 0.000 0.068 0.932 0.000 0.000
#> GSM486782 3 0.2773 0.7917 0.000 0.164 0.836 0.000 0.000
#> GSM486784 3 0.3814 0.6925 0.124 0.068 0.808 0.000 0.000
#> GSM486786 1 0.2645 0.8404 0.888 0.068 0.044 0.000 0.000
#> GSM486788 1 0.0000 0.8848 1.000 0.000 0.000 0.000 0.000
#> GSM486790 3 0.3366 0.7280 0.000 0.232 0.768 0.000 0.000
#> GSM486792 2 0.2074 0.7735 0.104 0.896 0.000 0.000 0.000
#> GSM486794 3 0.2732 0.7938 0.000 0.160 0.840 0.000 0.000
#> GSM486796 1 0.0000 0.8848 1.000 0.000 0.000 0.000 0.000
#> GSM486798 3 0.3814 0.6925 0.124 0.068 0.808 0.000 0.000
#> GSM486800 1 0.2280 0.7867 0.880 0.000 0.120 0.000 0.000
#> GSM486802 1 0.0000 0.8848 1.000 0.000 0.000 0.000 0.000
#> GSM486804 1 0.4708 0.6729 0.712 0.068 0.220 0.000 0.000
#> GSM486806 3 0.1732 0.8220 0.000 0.080 0.920 0.000 0.000
#> GSM486808 3 0.0000 0.8266 0.000 0.000 1.000 0.000 0.000
#> GSM486810 3 0.2230 0.8122 0.000 0.116 0.884 0.000 0.000
#> GSM486812 1 0.0000 0.8848 1.000 0.000 0.000 0.000 0.000
#> GSM486814 3 0.2773 0.7917 0.000 0.164 0.836 0.000 0.000
#> GSM486816 3 0.1544 0.7978 0.000 0.068 0.932 0.000 0.000
#> GSM486818 2 0.4307 -0.2935 0.000 0.504 0.496 0.000 0.000
#> GSM486821 3 0.2773 0.7917 0.000 0.164 0.836 0.000 0.000
#> GSM486823 1 0.3561 0.5587 0.740 0.000 0.260 0.000 0.000
#> GSM486826 3 0.4618 0.5785 0.208 0.068 0.724 0.000 0.000
#> GSM486830 3 0.2773 0.7917 0.000 0.164 0.836 0.000 0.000
#> GSM486832 3 0.0000 0.8266 0.000 0.000 1.000 0.000 0.000
#> GSM486834 3 0.3983 0.7556 0.052 0.164 0.784 0.000 0.000
#> GSM486836 1 0.1544 0.8609 0.932 0.068 0.000 0.000 0.000
#> GSM486838 3 0.0000 0.8266 0.000 0.000 1.000 0.000 0.000
#> GSM486840 3 0.4679 0.5660 0.216 0.068 0.716 0.000 0.000
#> GSM486842 1 0.2992 0.8246 0.868 0.068 0.064 0.000 0.000
#> GSM486844 1 0.4455 0.7073 0.744 0.068 0.188 0.000 0.000
#> GSM486846 3 0.2773 0.7917 0.000 0.164 0.836 0.000 0.000
#> GSM486848 3 0.0000 0.8266 0.000 0.000 1.000 0.000 0.000
#> GSM486850 1 0.0000 0.8848 1.000 0.000 0.000 0.000 0.000
#> GSM486852 1 0.1282 0.8712 0.952 0.044 0.004 0.000 0.000
#> GSM486854 3 0.0000 0.8266 0.000 0.000 1.000 0.000 0.000
#> GSM486856 3 0.2179 0.7601 0.112 0.000 0.888 0.000 0.000
#> GSM486858 3 0.3814 0.6925 0.124 0.068 0.808 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 5 0.1749 0.9005 0.016 0.000 0.004 0.044 0.932 0.004
#> GSM486737 4 0.0000 0.9729 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486739 5 0.1680 0.9040 0.016 0.000 0.004 0.040 0.936 0.004
#> GSM486741 4 0.0000 0.9729 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486743 4 0.0000 0.9729 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486745 5 0.1680 0.9040 0.016 0.000 0.004 0.040 0.936 0.004
#> GSM486747 4 0.0000 0.9729 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486749 5 0.0000 0.9417 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486751 5 0.0000 0.9417 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486753 4 0.0000 0.9729 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486755 4 0.0291 0.9704 0.004 0.000 0.000 0.992 0.000 0.004
#> GSM486757 4 0.2883 0.7205 0.000 0.000 0.000 0.788 0.212 0.000
#> GSM486759 5 0.0000 0.9417 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486761 4 0.0000 0.9729 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486763 5 0.0000 0.9417 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486765 4 0.0000 0.9729 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486767 4 0.0000 0.9729 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486769 5 0.0508 0.9336 0.012 0.000 0.004 0.000 0.984 0.000
#> GSM486771 5 0.0000 0.9417 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486773 4 0.0000 0.9729 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486775 4 0.0000 0.9729 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486777 5 0.0000 0.9417 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486779 4 0.2340 0.8155 0.000 0.000 0.000 0.852 0.148 0.000
#> GSM486781 4 0.0146 0.9722 0.000 0.000 0.000 0.996 0.000 0.004
#> GSM486783 4 0.0363 0.9662 0.000 0.000 0.000 0.988 0.012 0.000
#> GSM486785 5 0.3867 -0.0215 0.000 0.000 0.000 0.488 0.512 0.000
#> GSM486787 5 0.0000 0.9417 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486789 4 0.0146 0.9722 0.000 0.000 0.000 0.996 0.000 0.004
#> GSM486791 5 0.0603 0.9317 0.016 0.000 0.004 0.000 0.980 0.000
#> GSM486793 4 0.0146 0.9722 0.000 0.000 0.000 0.996 0.000 0.004
#> GSM486795 5 0.0000 0.9417 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486797 4 0.0000 0.9729 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486799 4 0.0000 0.9729 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486801 5 0.0000 0.9417 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486803 5 0.0000 0.9417 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486805 4 0.0146 0.9722 0.000 0.000 0.000 0.996 0.000 0.004
#> GSM486807 4 0.0146 0.9717 0.000 0.000 0.000 0.996 0.004 0.000
#> GSM486809 4 0.0000 0.9729 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486811 5 0.0000 0.9417 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486813 4 0.0146 0.9722 0.000 0.000 0.000 0.996 0.000 0.004
#> GSM486815 5 0.0000 0.9417 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486817 4 0.0748 0.9602 0.016 0.000 0.004 0.976 0.000 0.004
#> GSM486819 4 0.0146 0.9722 0.000 0.000 0.000 0.996 0.000 0.004
#> GSM486822 5 0.1327 0.8930 0.000 0.000 0.000 0.064 0.936 0.000
#> GSM486824 4 0.3023 0.6986 0.000 0.000 0.000 0.768 0.232 0.000
#> GSM486828 4 0.0146 0.9722 0.000 0.000 0.000 0.996 0.000 0.004
#> GSM486831 4 0.0632 0.9585 0.000 0.000 0.000 0.976 0.024 0.000
#> GSM486833 5 0.2912 0.6798 0.000 0.000 0.000 0.216 0.784 0.000
#> GSM486835 5 0.0000 0.9417 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486837 4 0.0000 0.9729 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486839 4 0.0458 0.9646 0.000 0.000 0.000 0.984 0.016 0.000
#> GSM486841 5 0.0000 0.9417 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486843 5 0.0000 0.9417 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486845 5 0.1714 0.8608 0.000 0.000 0.000 0.092 0.908 0.000
#> GSM486847 4 0.0146 0.9717 0.000 0.000 0.000 0.996 0.004 0.000
#> GSM486849 5 0.0000 0.9417 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486851 5 0.0000 0.9417 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486853 4 0.0000 0.9729 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486855 4 0.1007 0.9391 0.000 0.000 0.000 0.956 0.044 0.000
#> GSM486857 4 0.0458 0.9634 0.000 0.000 0.000 0.984 0.016 0.000
#> GSM486736 3 0.0146 1.0000 0.000 0.004 0.996 0.000 0.000 0.000
#> GSM486738 2 0.3490 0.7072 0.040 0.784 0.000 0.000 0.000 0.176
#> GSM486740 3 0.0146 1.0000 0.000 0.004 0.996 0.000 0.000 0.000
#> GSM486742 2 0.3790 0.7800 0.104 0.780 0.000 0.000 0.000 0.116
#> GSM486744 2 0.0000 0.8020 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486746 3 0.0146 1.0000 0.000 0.004 0.996 0.000 0.000 0.000
#> GSM486748 2 0.3454 0.7969 0.208 0.768 0.000 0.000 0.000 0.024
#> GSM486750 6 0.0146 0.9805 0.004 0.000 0.000 0.000 0.000 0.996
#> GSM486752 6 0.0146 0.9805 0.004 0.000 0.000 0.000 0.000 0.996
#> GSM486754 2 0.0000 0.8020 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486756 2 0.3499 0.4816 0.000 0.680 0.320 0.000 0.000 0.000
#> GSM486758 1 0.1863 0.7088 0.896 0.104 0.000 0.000 0.000 0.000
#> GSM486760 6 0.0146 0.9805 0.004 0.000 0.000 0.000 0.000 0.996
#> GSM486762 2 0.3684 0.6406 0.372 0.628 0.000 0.000 0.000 0.000
#> GSM486764 1 0.0458 0.7852 0.984 0.000 0.000 0.000 0.000 0.016
#> GSM486766 2 0.2912 0.7997 0.216 0.784 0.000 0.000 0.000 0.000
#> GSM486768 2 0.0000 0.8020 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486770 6 0.0547 0.9581 0.000 0.020 0.000 0.000 0.000 0.980
#> GSM486772 6 0.0146 0.9805 0.004 0.000 0.000 0.000 0.000 0.996
#> GSM486774 2 0.3747 0.6194 0.396 0.604 0.000 0.000 0.000 0.000
#> GSM486776 2 0.3023 0.7922 0.232 0.768 0.000 0.000 0.000 0.000
#> GSM486778 6 0.0146 0.9805 0.004 0.000 0.000 0.000 0.000 0.996
#> GSM486780 1 0.3499 0.2998 0.680 0.320 0.000 0.000 0.000 0.000
#> GSM486782 2 0.0000 0.8020 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486784 1 0.0458 0.7852 0.984 0.000 0.000 0.000 0.000 0.016
#> GSM486786 1 0.2883 0.6516 0.788 0.000 0.000 0.000 0.000 0.212
#> GSM486788 6 0.0146 0.9805 0.004 0.000 0.000 0.000 0.000 0.996
#> GSM486790 2 0.0363 0.7965 0.000 0.988 0.012 0.000 0.000 0.000
#> GSM486792 3 0.0146 1.0000 0.000 0.004 0.996 0.000 0.000 0.000
#> GSM486794 2 0.0146 0.8037 0.004 0.996 0.000 0.000 0.000 0.000
#> GSM486796 6 0.0146 0.9805 0.004 0.000 0.000 0.000 0.000 0.996
#> GSM486798 1 0.0458 0.7852 0.984 0.000 0.000 0.000 0.000 0.016
#> GSM486800 6 0.1682 0.8972 0.052 0.020 0.000 0.000 0.000 0.928
#> GSM486802 6 0.0146 0.9805 0.004 0.000 0.000 0.000 0.000 0.996
#> GSM486804 1 0.0458 0.7852 0.984 0.000 0.000 0.000 0.000 0.016
#> GSM486806 2 0.2912 0.7997 0.216 0.784 0.000 0.000 0.000 0.000
#> GSM486808 2 0.3023 0.7922 0.232 0.768 0.000 0.000 0.000 0.000
#> GSM486810 2 0.2378 0.8154 0.152 0.848 0.000 0.000 0.000 0.000
#> GSM486812 6 0.0146 0.9805 0.004 0.000 0.000 0.000 0.000 0.996
#> GSM486814 2 0.0000 0.8020 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486816 1 0.3499 0.2998 0.680 0.320 0.000 0.000 0.000 0.000
#> GSM486818 2 0.3659 0.3987 0.000 0.636 0.364 0.000 0.000 0.000
#> GSM486821 2 0.1714 0.8179 0.092 0.908 0.000 0.000 0.000 0.000
#> GSM486823 6 0.1327 0.9061 0.000 0.064 0.000 0.000 0.000 0.936
#> GSM486826 1 0.0458 0.7852 0.984 0.000 0.000 0.000 0.000 0.016
#> GSM486830 2 0.1714 0.8179 0.092 0.908 0.000 0.000 0.000 0.000
#> GSM486832 2 0.3023 0.7922 0.232 0.768 0.000 0.000 0.000 0.000
#> GSM486834 2 0.2389 0.8055 0.052 0.888 0.000 0.000 0.000 0.060
#> GSM486836 1 0.3695 0.4203 0.624 0.000 0.000 0.000 0.000 0.376
#> GSM486838 2 0.3464 0.7346 0.312 0.688 0.000 0.000 0.000 0.000
#> GSM486840 1 0.0458 0.7852 0.984 0.000 0.000 0.000 0.000 0.016
#> GSM486842 1 0.3428 0.5616 0.696 0.000 0.000 0.000 0.000 0.304
#> GSM486844 1 0.1814 0.7395 0.900 0.000 0.000 0.000 0.000 0.100
#> GSM486846 2 0.0000 0.8020 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486848 2 0.3695 0.6349 0.376 0.624 0.000 0.000 0.000 0.000
#> GSM486850 6 0.0146 0.9805 0.004 0.000 0.000 0.000 0.000 0.996
#> GSM486852 1 0.3854 0.2134 0.536 0.000 0.000 0.000 0.000 0.464
#> GSM486854 2 0.3023 0.7922 0.232 0.768 0.000 0.000 0.000 0.000
#> GSM486856 2 0.4168 0.5860 0.400 0.584 0.000 0.000 0.000 0.016
#> GSM486858 1 0.0713 0.7813 0.972 0.000 0.000 0.000 0.000 0.028
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> ATC:pam 120 4.67e-27 1.000 2
#> ATC:pam 118 2.38e-26 1.000 3
#> ATC:pam 115 9.21e-25 0.998 4
#> ATC:pam 117 2.34e-24 0.996 5
#> ATC:pam 113 9.51e-23 0.988 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["ATC", "mclust"]
# you can also extract it by
# res = res_list["ATC:mclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'ATC' method.
#> Subgroups are detected by 'mclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 5.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 1.000 1.000 1.000 0.5047 0.496 0.496
#> 3 3 0.787 0.931 0.931 0.1303 0.955 0.908
#> 4 4 0.679 0.801 0.779 0.2206 0.768 0.507
#> 5 5 1.000 0.966 0.984 0.0825 0.983 0.934
#> 6 6 0.769 0.707 0.843 0.0559 0.924 0.710
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 5
#> attr(,"optional")
#> [1] 2
There is also optional best \(k\) = 2 that is worth to check.
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 1 0 1 1 0
#> GSM486737 1 0 1 1 0
#> GSM486739 1 0 1 1 0
#> GSM486741 1 0 1 1 0
#> GSM486743 1 0 1 1 0
#> GSM486745 1 0 1 1 0
#> GSM486747 1 0 1 1 0
#> GSM486749 1 0 1 1 0
#> GSM486751 1 0 1 1 0
#> GSM486753 1 0 1 1 0
#> GSM486755 1 0 1 1 0
#> GSM486757 1 0 1 1 0
#> GSM486759 1 0 1 1 0
#> GSM486761 1 0 1 1 0
#> GSM486763 1 0 1 1 0
#> GSM486765 1 0 1 1 0
#> GSM486767 1 0 1 1 0
#> GSM486769 1 0 1 1 0
#> GSM486771 1 0 1 1 0
#> GSM486773 1 0 1 1 0
#> GSM486775 1 0 1 1 0
#> GSM486777 1 0 1 1 0
#> GSM486779 1 0 1 1 0
#> GSM486781 1 0 1 1 0
#> GSM486783 1 0 1 1 0
#> GSM486785 1 0 1 1 0
#> GSM486787 1 0 1 1 0
#> GSM486789 1 0 1 1 0
#> GSM486791 1 0 1 1 0
#> GSM486793 1 0 1 1 0
#> GSM486795 1 0 1 1 0
#> GSM486797 1 0 1 1 0
#> GSM486799 1 0 1 1 0
#> GSM486801 1 0 1 1 0
#> GSM486803 1 0 1 1 0
#> GSM486805 1 0 1 1 0
#> GSM486807 1 0 1 1 0
#> GSM486809 1 0 1 1 0
#> GSM486811 1 0 1 1 0
#> GSM486813 1 0 1 1 0
#> GSM486815 1 0 1 1 0
#> GSM486817 1 0 1 1 0
#> GSM486819 1 0 1 1 0
#> GSM486822 1 0 1 1 0
#> GSM486824 1 0 1 1 0
#> GSM486828 1 0 1 1 0
#> GSM486831 1 0 1 1 0
#> GSM486833 1 0 1 1 0
#> GSM486835 1 0 1 1 0
#> GSM486837 1 0 1 1 0
#> GSM486839 1 0 1 1 0
#> GSM486841 1 0 1 1 0
#> GSM486843 1 0 1 1 0
#> GSM486845 1 0 1 1 0
#> GSM486847 1 0 1 1 0
#> GSM486849 1 0 1 1 0
#> GSM486851 1 0 1 1 0
#> GSM486853 1 0 1 1 0
#> GSM486855 1 0 1 1 0
#> GSM486857 1 0 1 1 0
#> GSM486736 2 0 1 0 1
#> GSM486738 2 0 1 0 1
#> GSM486740 2 0 1 0 1
#> GSM486742 2 0 1 0 1
#> GSM486744 2 0 1 0 1
#> GSM486746 2 0 1 0 1
#> GSM486748 2 0 1 0 1
#> GSM486750 2 0 1 0 1
#> GSM486752 2 0 1 0 1
#> GSM486754 2 0 1 0 1
#> GSM486756 2 0 1 0 1
#> GSM486758 2 0 1 0 1
#> GSM486760 2 0 1 0 1
#> GSM486762 2 0 1 0 1
#> GSM486764 2 0 1 0 1
#> GSM486766 2 0 1 0 1
#> GSM486768 2 0 1 0 1
#> GSM486770 2 0 1 0 1
#> GSM486772 2 0 1 0 1
#> GSM486774 2 0 1 0 1
#> GSM486776 2 0 1 0 1
#> GSM486778 2 0 1 0 1
#> GSM486780 2 0 1 0 1
#> GSM486782 2 0 1 0 1
#> GSM486784 2 0 1 0 1
#> GSM486786 2 0 1 0 1
#> GSM486788 2 0 1 0 1
#> GSM486790 2 0 1 0 1
#> GSM486792 2 0 1 0 1
#> GSM486794 2 0 1 0 1
#> GSM486796 2 0 1 0 1
#> GSM486798 2 0 1 0 1
#> GSM486800 2 0 1 0 1
#> GSM486802 2 0 1 0 1
#> GSM486804 2 0 1 0 1
#> GSM486806 2 0 1 0 1
#> GSM486808 2 0 1 0 1
#> GSM486810 2 0 1 0 1
#> GSM486812 2 0 1 0 1
#> GSM486814 2 0 1 0 1
#> GSM486816 2 0 1 0 1
#> GSM486818 2 0 1 0 1
#> GSM486821 2 0 1 0 1
#> GSM486823 2 0 1 0 1
#> GSM486826 2 0 1 0 1
#> GSM486830 2 0 1 0 1
#> GSM486832 2 0 1 0 1
#> GSM486834 2 0 1 0 1
#> GSM486836 2 0 1 0 1
#> GSM486838 2 0 1 0 1
#> GSM486840 2 0 1 0 1
#> GSM486842 2 0 1 0 1
#> GSM486844 2 0 1 0 1
#> GSM486846 2 0 1 0 1
#> GSM486848 2 0 1 0 1
#> GSM486850 2 0 1 0 1
#> GSM486852 2 0 1 0 1
#> GSM486854 2 0 1 0 1
#> GSM486856 2 0 1 0 1
#> GSM486858 2 0 1 0 1
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 1 0.0424 0.897 0.992 0.008 0.000
#> GSM486737 1 0.0000 0.898 1.000 0.000 0.000
#> GSM486739 1 0.0237 0.897 0.996 0.004 0.000
#> GSM486741 1 0.3686 0.880 0.860 0.140 0.000
#> GSM486743 1 0.3686 0.880 0.860 0.140 0.000
#> GSM486745 1 0.0237 0.897 0.996 0.004 0.000
#> GSM486747 1 0.3686 0.880 0.860 0.140 0.000
#> GSM486749 1 0.3879 0.850 0.848 0.152 0.000
#> GSM486751 1 0.3879 0.850 0.848 0.152 0.000
#> GSM486753 1 0.3686 0.880 0.860 0.140 0.000
#> GSM486755 1 0.3752 0.879 0.856 0.144 0.000
#> GSM486757 1 0.3879 0.881 0.848 0.152 0.000
#> GSM486759 1 0.3879 0.850 0.848 0.152 0.000
#> GSM486761 1 0.3686 0.880 0.860 0.140 0.000
#> GSM486763 1 0.3879 0.850 0.848 0.152 0.000
#> GSM486765 1 0.3686 0.880 0.860 0.140 0.000
#> GSM486767 1 0.3752 0.879 0.856 0.144 0.000
#> GSM486769 1 0.0424 0.897 0.992 0.008 0.000
#> GSM486771 1 0.2878 0.872 0.904 0.096 0.000
#> GSM486773 1 0.3686 0.880 0.860 0.140 0.000
#> GSM486775 1 0.3752 0.879 0.856 0.144 0.000
#> GSM486777 1 0.3879 0.850 0.848 0.152 0.000
#> GSM486779 1 0.0424 0.897 0.992 0.008 0.000
#> GSM486781 1 0.3686 0.880 0.860 0.140 0.000
#> GSM486783 1 0.0000 0.898 1.000 0.000 0.000
#> GSM486785 1 0.3752 0.854 0.856 0.144 0.000
#> GSM486787 1 0.3879 0.850 0.848 0.152 0.000
#> GSM486789 1 0.3752 0.879 0.856 0.144 0.000
#> GSM486791 1 0.0592 0.896 0.988 0.012 0.000
#> GSM486793 1 0.3686 0.880 0.860 0.140 0.000
#> GSM486795 1 0.3879 0.850 0.848 0.152 0.000
#> GSM486797 1 0.3816 0.881 0.852 0.148 0.000
#> GSM486799 1 0.3686 0.880 0.860 0.140 0.000
#> GSM486801 1 0.3879 0.850 0.848 0.152 0.000
#> GSM486803 1 0.3879 0.850 0.848 0.152 0.000
#> GSM486805 1 0.3686 0.880 0.860 0.140 0.000
#> GSM486807 1 0.0000 0.898 1.000 0.000 0.000
#> GSM486809 1 0.3686 0.880 0.860 0.140 0.000
#> GSM486811 1 0.3879 0.850 0.848 0.152 0.000
#> GSM486813 1 0.3752 0.879 0.856 0.144 0.000
#> GSM486815 1 0.0237 0.897 0.996 0.004 0.000
#> GSM486817 1 0.3752 0.879 0.856 0.144 0.000
#> GSM486819 1 0.0237 0.897 0.996 0.004 0.000
#> GSM486822 1 0.1031 0.894 0.976 0.024 0.000
#> GSM486824 1 0.0592 0.896 0.988 0.012 0.000
#> GSM486828 1 0.3752 0.879 0.856 0.144 0.000
#> GSM486831 1 0.3879 0.850 0.848 0.152 0.000
#> GSM486833 1 0.0237 0.897 0.996 0.004 0.000
#> GSM486835 1 0.3879 0.850 0.848 0.152 0.000
#> GSM486837 1 0.3686 0.880 0.860 0.140 0.000
#> GSM486839 1 0.3879 0.850 0.848 0.152 0.000
#> GSM486841 1 0.3879 0.850 0.848 0.152 0.000
#> GSM486843 1 0.3879 0.850 0.848 0.152 0.000
#> GSM486845 1 0.0237 0.897 0.996 0.004 0.000
#> GSM486847 1 0.4062 0.880 0.836 0.164 0.000
#> GSM486849 1 0.0237 0.897 0.996 0.004 0.000
#> GSM486851 1 0.3879 0.850 0.848 0.152 0.000
#> GSM486853 1 0.3879 0.881 0.848 0.152 0.000
#> GSM486855 1 0.0000 0.898 1.000 0.000 0.000
#> GSM486857 1 0.0000 0.898 1.000 0.000 0.000
#> GSM486736 2 0.5529 0.968 0.000 0.704 0.296
#> GSM486738 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486740 2 0.5529 0.968 0.000 0.704 0.296
#> GSM486742 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486744 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486746 2 0.5591 0.971 0.000 0.696 0.304
#> GSM486748 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486750 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486752 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486754 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486756 2 0.5785 0.964 0.000 0.668 0.332
#> GSM486758 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486760 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486762 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486764 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486766 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486768 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486770 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486772 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486774 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486776 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486778 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486780 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486782 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486784 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486786 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486788 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486790 3 0.4452 0.610 0.000 0.192 0.808
#> GSM486792 2 0.5760 0.964 0.000 0.672 0.328
#> GSM486794 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486796 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486798 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486800 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486802 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486804 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486806 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486808 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486810 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486812 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486814 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486816 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486818 2 0.5785 0.964 0.000 0.668 0.332
#> GSM486821 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486823 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486826 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486830 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486832 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486834 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486836 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486838 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486840 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486842 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486844 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486846 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486848 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486850 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486852 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486854 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486856 3 0.0000 0.995 0.000 0.000 1.000
#> GSM486858 3 0.0000 0.995 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 1 0.4872 0.712 0.728 0.000 0.028 0.244
#> GSM486737 4 0.4406 0.938 0.192 0.000 0.028 0.780
#> GSM486739 1 0.5050 0.686 0.704 0.000 0.028 0.268
#> GSM486741 4 0.3852 0.947 0.192 0.000 0.008 0.800
#> GSM486743 4 0.3528 0.947 0.192 0.000 0.000 0.808
#> GSM486745 1 0.5050 0.686 0.704 0.000 0.028 0.268
#> GSM486747 4 0.3569 0.948 0.196 0.000 0.000 0.804
#> GSM486749 1 0.0000 0.830 1.000 0.000 0.000 0.000
#> GSM486751 1 0.0000 0.830 1.000 0.000 0.000 0.000
#> GSM486753 4 0.3726 0.938 0.212 0.000 0.000 0.788
#> GSM486755 4 0.4057 0.915 0.160 0.000 0.028 0.812
#> GSM486757 4 0.4697 0.720 0.356 0.000 0.000 0.644
#> GSM486759 1 0.0000 0.830 1.000 0.000 0.000 0.000
#> GSM486761 4 0.3610 0.948 0.200 0.000 0.000 0.800
#> GSM486763 1 0.0000 0.830 1.000 0.000 0.000 0.000
#> GSM486765 4 0.3528 0.947 0.192 0.000 0.000 0.808
#> GSM486767 4 0.4406 0.938 0.192 0.000 0.028 0.780
#> GSM486769 1 0.5050 0.686 0.704 0.000 0.028 0.268
#> GSM486771 1 0.3224 0.779 0.864 0.000 0.016 0.120
#> GSM486773 4 0.3528 0.947 0.192 0.000 0.000 0.808
#> GSM486775 4 0.4204 0.942 0.192 0.000 0.020 0.788
#> GSM486777 1 0.0000 0.830 1.000 0.000 0.000 0.000
#> GSM486779 4 0.3649 0.945 0.204 0.000 0.000 0.796
#> GSM486781 4 0.3528 0.947 0.192 0.000 0.000 0.808
#> GSM486783 4 0.3569 0.948 0.196 0.000 0.000 0.804
#> GSM486785 1 0.4477 0.359 0.688 0.000 0.000 0.312
#> GSM486787 1 0.0000 0.830 1.000 0.000 0.000 0.000
#> GSM486789 4 0.4152 0.913 0.160 0.000 0.032 0.808
#> GSM486791 1 0.4524 0.732 0.768 0.000 0.028 0.204
#> GSM486793 4 0.3610 0.948 0.200 0.000 0.000 0.800
#> GSM486795 1 0.0000 0.830 1.000 0.000 0.000 0.000
#> GSM486797 4 0.3610 0.948 0.200 0.000 0.000 0.800
#> GSM486799 4 0.3610 0.948 0.200 0.000 0.000 0.800
#> GSM486801 1 0.0000 0.830 1.000 0.000 0.000 0.000
#> GSM486803 1 0.0000 0.830 1.000 0.000 0.000 0.000
#> GSM486805 4 0.3942 0.916 0.236 0.000 0.000 0.764
#> GSM486807 4 0.3610 0.948 0.200 0.000 0.000 0.800
#> GSM486809 4 0.3610 0.948 0.200 0.000 0.000 0.800
#> GSM486811 1 0.0000 0.830 1.000 0.000 0.000 0.000
#> GSM486813 4 0.4152 0.913 0.160 0.000 0.032 0.808
#> GSM486815 1 0.5543 0.428 0.612 0.000 0.028 0.360
#> GSM486817 1 0.5207 0.648 0.680 0.000 0.028 0.292
#> GSM486819 4 0.4057 0.915 0.160 0.000 0.028 0.812
#> GSM486822 1 0.4323 0.733 0.788 0.000 0.028 0.184
#> GSM486824 4 0.4406 0.934 0.192 0.000 0.028 0.780
#> GSM486828 4 0.4149 0.913 0.168 0.000 0.028 0.804
#> GSM486831 1 0.0000 0.830 1.000 0.000 0.000 0.000
#> GSM486833 1 0.4964 0.671 0.716 0.000 0.028 0.256
#> GSM486835 1 0.0000 0.830 1.000 0.000 0.000 0.000
#> GSM486837 4 0.3610 0.948 0.200 0.000 0.000 0.800
#> GSM486839 1 0.0000 0.830 1.000 0.000 0.000 0.000
#> GSM486841 1 0.0000 0.830 1.000 0.000 0.000 0.000
#> GSM486843 1 0.0000 0.830 1.000 0.000 0.000 0.000
#> GSM486845 1 0.4524 0.721 0.768 0.000 0.028 0.204
#> GSM486847 4 0.4830 0.661 0.392 0.000 0.000 0.608
#> GSM486849 1 0.4840 0.686 0.732 0.000 0.028 0.240
#> GSM486851 1 0.0000 0.830 1.000 0.000 0.000 0.000
#> GSM486853 4 0.4643 0.743 0.344 0.000 0.000 0.656
#> GSM486855 1 0.5423 0.488 0.640 0.000 0.028 0.332
#> GSM486857 4 0.3688 0.944 0.208 0.000 0.000 0.792
#> GSM486736 3 0.4332 0.466 0.000 0.040 0.800 0.160
#> GSM486738 2 0.0000 0.866 0.000 1.000 0.000 0.000
#> GSM486740 3 0.4332 0.466 0.000 0.040 0.800 0.160
#> GSM486742 2 0.0817 0.856 0.000 0.976 0.024 0.000
#> GSM486744 2 0.0336 0.861 0.000 0.992 0.008 0.000
#> GSM486746 3 0.4332 0.466 0.000 0.040 0.800 0.160
#> GSM486748 2 0.0000 0.866 0.000 1.000 0.000 0.000
#> GSM486750 3 0.4855 0.807 0.000 0.400 0.600 0.000
#> GSM486752 3 0.4855 0.807 0.000 0.400 0.600 0.000
#> GSM486754 2 0.1302 0.828 0.000 0.956 0.044 0.000
#> GSM486756 2 0.7272 0.191 0.000 0.496 0.344 0.160
#> GSM486758 2 0.0000 0.866 0.000 1.000 0.000 0.000
#> GSM486760 3 0.4855 0.807 0.000 0.400 0.600 0.000
#> GSM486762 2 0.0000 0.866 0.000 1.000 0.000 0.000
#> GSM486764 2 0.3123 0.757 0.000 0.844 0.156 0.000
#> GSM486766 2 0.0000 0.866 0.000 1.000 0.000 0.000
#> GSM486768 2 0.0188 0.864 0.000 0.996 0.004 0.000
#> GSM486770 3 0.4888 0.786 0.000 0.412 0.588 0.000
#> GSM486772 3 0.4855 0.807 0.000 0.400 0.600 0.000
#> GSM486774 2 0.2973 0.770 0.000 0.856 0.144 0.000
#> GSM486776 2 0.0000 0.866 0.000 1.000 0.000 0.000
#> GSM486778 3 0.4855 0.807 0.000 0.400 0.600 0.000
#> GSM486780 2 0.0000 0.866 0.000 1.000 0.000 0.000
#> GSM486782 2 0.0469 0.858 0.000 0.988 0.012 0.000
#> GSM486784 2 0.3123 0.757 0.000 0.844 0.156 0.000
#> GSM486786 2 0.3172 0.751 0.000 0.840 0.160 0.000
#> GSM486788 3 0.4855 0.807 0.000 0.400 0.600 0.000
#> GSM486790 2 0.3718 0.637 0.000 0.820 0.168 0.012
#> GSM486792 3 0.4417 0.467 0.000 0.044 0.796 0.160
#> GSM486794 2 0.0336 0.861 0.000 0.992 0.008 0.000
#> GSM486796 3 0.4855 0.807 0.000 0.400 0.600 0.000
#> GSM486798 2 0.3123 0.757 0.000 0.844 0.156 0.000
#> GSM486800 3 0.4855 0.807 0.000 0.400 0.600 0.000
#> GSM486802 3 0.4855 0.807 0.000 0.400 0.600 0.000
#> GSM486804 2 0.3123 0.757 0.000 0.844 0.156 0.000
#> GSM486806 2 0.0000 0.866 0.000 1.000 0.000 0.000
#> GSM486808 2 0.3024 0.766 0.000 0.852 0.148 0.000
#> GSM486810 2 0.0000 0.866 0.000 1.000 0.000 0.000
#> GSM486812 3 0.4855 0.807 0.000 0.400 0.600 0.000
#> GSM486814 2 0.0188 0.864 0.000 0.996 0.004 0.000
#> GSM486816 2 0.0000 0.866 0.000 1.000 0.000 0.000
#> GSM486818 2 0.7272 0.191 0.000 0.496 0.344 0.160
#> GSM486821 2 0.1389 0.823 0.000 0.952 0.048 0.000
#> GSM486823 3 0.4866 0.800 0.000 0.404 0.596 0.000
#> GSM486826 2 0.2149 0.816 0.000 0.912 0.088 0.000
#> GSM486830 2 0.1211 0.832 0.000 0.960 0.040 0.000
#> GSM486832 2 0.0000 0.866 0.000 1.000 0.000 0.000
#> GSM486834 2 0.0000 0.866 0.000 1.000 0.000 0.000
#> GSM486836 3 0.4855 0.807 0.000 0.400 0.600 0.000
#> GSM486838 2 0.3024 0.766 0.000 0.852 0.148 0.000
#> GSM486840 2 0.3123 0.757 0.000 0.844 0.156 0.000
#> GSM486842 3 0.4855 0.807 0.000 0.400 0.600 0.000
#> GSM486844 2 0.3123 0.757 0.000 0.844 0.156 0.000
#> GSM486846 2 0.0000 0.866 0.000 1.000 0.000 0.000
#> GSM486848 2 0.0000 0.866 0.000 1.000 0.000 0.000
#> GSM486850 3 0.4855 0.807 0.000 0.400 0.600 0.000
#> GSM486852 3 0.4855 0.807 0.000 0.400 0.600 0.000
#> GSM486854 2 0.0707 0.859 0.000 0.980 0.020 0.000
#> GSM486856 2 0.3024 0.766 0.000 0.852 0.148 0.000
#> GSM486858 2 0.3123 0.757 0.000 0.844 0.156 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 4 0.1121 0.955 0.000 0.044 0.000 0.956 0.000
#> GSM486737 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486739 4 0.1121 0.955 0.000 0.044 0.000 0.956 0.000
#> GSM486741 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486743 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486745 4 0.1121 0.955 0.000 0.044 0.000 0.956 0.000
#> GSM486747 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486749 4 0.0000 0.985 0.000 0.000 0.000 1.000 0.000
#> GSM486751 4 0.0000 0.985 0.000 0.000 0.000 1.000 0.000
#> GSM486753 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486755 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486757 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486759 4 0.0000 0.985 0.000 0.000 0.000 1.000 0.000
#> GSM486761 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486763 4 0.0000 0.985 0.000 0.000 0.000 1.000 0.000
#> GSM486765 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486767 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486769 4 0.0290 0.983 0.000 0.008 0.000 0.992 0.000
#> GSM486771 4 0.0000 0.985 0.000 0.000 0.000 1.000 0.000
#> GSM486773 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486775 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486777 4 0.0000 0.985 0.000 0.000 0.000 1.000 0.000
#> GSM486779 2 0.0609 0.954 0.000 0.980 0.000 0.020 0.000
#> GSM486781 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486783 2 0.0794 0.946 0.000 0.972 0.000 0.028 0.000
#> GSM486785 2 0.4210 0.321 0.000 0.588 0.000 0.412 0.000
#> GSM486787 4 0.0000 0.985 0.000 0.000 0.000 1.000 0.000
#> GSM486789 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486791 4 0.0290 0.983 0.000 0.008 0.000 0.992 0.000
#> GSM486793 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486795 4 0.0000 0.985 0.000 0.000 0.000 1.000 0.000
#> GSM486797 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486799 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486801 4 0.0000 0.985 0.000 0.000 0.000 1.000 0.000
#> GSM486803 4 0.0000 0.985 0.000 0.000 0.000 1.000 0.000
#> GSM486805 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486807 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486809 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486811 4 0.0000 0.985 0.000 0.000 0.000 1.000 0.000
#> GSM486813 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486815 4 0.0703 0.971 0.000 0.024 0.000 0.976 0.000
#> GSM486817 4 0.1270 0.946 0.000 0.052 0.000 0.948 0.000
#> GSM486819 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486822 4 0.0290 0.983 0.000 0.008 0.000 0.992 0.000
#> GSM486824 2 0.1270 0.921 0.000 0.948 0.000 0.052 0.000
#> GSM486828 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486831 4 0.0162 0.984 0.000 0.004 0.000 0.996 0.000
#> GSM486833 4 0.0794 0.969 0.000 0.028 0.000 0.972 0.000
#> GSM486835 4 0.0000 0.985 0.000 0.000 0.000 1.000 0.000
#> GSM486837 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486839 4 0.0000 0.985 0.000 0.000 0.000 1.000 0.000
#> GSM486841 4 0.0000 0.985 0.000 0.000 0.000 1.000 0.000
#> GSM486843 4 0.0000 0.985 0.000 0.000 0.000 1.000 0.000
#> GSM486845 4 0.1121 0.955 0.000 0.044 0.000 0.956 0.000
#> GSM486847 2 0.2127 0.839 0.000 0.892 0.000 0.108 0.000
#> GSM486849 4 0.0290 0.983 0.000 0.008 0.000 0.992 0.000
#> GSM486851 4 0.0000 0.985 0.000 0.000 0.000 1.000 0.000
#> GSM486853 2 0.0000 0.972 0.000 1.000 0.000 0.000 0.000
#> GSM486855 4 0.0510 0.978 0.000 0.016 0.000 0.984 0.000
#> GSM486857 2 0.0963 0.937 0.000 0.964 0.000 0.036 0.000
#> GSM486736 5 0.0000 0.991 0.000 0.000 0.000 0.000 1.000
#> GSM486738 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486740 5 0.0000 0.991 0.000 0.000 0.000 0.000 1.000
#> GSM486742 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486744 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486746 5 0.0000 0.991 0.000 0.000 0.000 0.000 1.000
#> GSM486748 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486750 1 0.0000 0.999 1.000 0.000 0.000 0.000 0.000
#> GSM486752 1 0.0000 0.999 1.000 0.000 0.000 0.000 0.000
#> GSM486754 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486756 3 0.2929 0.803 0.000 0.000 0.820 0.000 0.180
#> GSM486758 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486760 1 0.0000 0.999 1.000 0.000 0.000 0.000 0.000
#> GSM486762 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486764 3 0.0963 0.958 0.036 0.000 0.964 0.000 0.000
#> GSM486766 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486768 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486770 1 0.0162 0.994 0.996 0.000 0.004 0.000 0.000
#> GSM486772 1 0.0000 0.999 1.000 0.000 0.000 0.000 0.000
#> GSM486774 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486776 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486778 1 0.0000 0.999 1.000 0.000 0.000 0.000 0.000
#> GSM486780 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486782 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486784 3 0.0963 0.958 0.036 0.000 0.964 0.000 0.000
#> GSM486786 3 0.2329 0.864 0.124 0.000 0.876 0.000 0.000
#> GSM486788 1 0.0000 0.999 1.000 0.000 0.000 0.000 0.000
#> GSM486790 3 0.0794 0.963 0.000 0.000 0.972 0.000 0.028
#> GSM486792 5 0.0609 0.974 0.000 0.000 0.020 0.000 0.980
#> GSM486794 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486796 1 0.0000 0.999 1.000 0.000 0.000 0.000 0.000
#> GSM486798 3 0.1121 0.952 0.044 0.000 0.956 0.000 0.000
#> GSM486800 1 0.0162 0.994 0.996 0.000 0.004 0.000 0.000
#> GSM486802 1 0.0000 0.999 1.000 0.000 0.000 0.000 0.000
#> GSM486804 3 0.1121 0.952 0.044 0.000 0.956 0.000 0.000
#> GSM486806 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486808 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486810 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486812 1 0.0000 0.999 1.000 0.000 0.000 0.000 0.000
#> GSM486814 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486816 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486818 3 0.2929 0.803 0.000 0.000 0.820 0.000 0.180
#> GSM486821 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486823 1 0.0000 0.999 1.000 0.000 0.000 0.000 0.000
#> GSM486826 3 0.0609 0.967 0.020 0.000 0.980 0.000 0.000
#> GSM486830 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486832 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486834 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486836 1 0.0000 0.999 1.000 0.000 0.000 0.000 0.000
#> GSM486838 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486840 3 0.1121 0.952 0.044 0.000 0.956 0.000 0.000
#> GSM486842 1 0.0000 0.999 1.000 0.000 0.000 0.000 0.000
#> GSM486844 3 0.1121 0.952 0.044 0.000 0.956 0.000 0.000
#> GSM486846 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486848 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486850 1 0.0000 0.999 1.000 0.000 0.000 0.000 0.000
#> GSM486852 1 0.0000 0.999 1.000 0.000 0.000 0.000 0.000
#> GSM486854 3 0.0000 0.977 0.000 0.000 1.000 0.000 0.000
#> GSM486856 3 0.0963 0.958 0.036 0.000 0.964 0.000 0.000
#> GSM486858 3 0.0963 0.958 0.036 0.000 0.964 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 3 0.5838 -0.3891 0.000 0.000 0.412 0.188 0.400 0.000
#> GSM486737 4 0.0790 0.9078 0.000 0.000 0.032 0.968 0.000 0.000
#> GSM486739 3 0.5838 -0.3891 0.000 0.000 0.412 0.188 0.400 0.000
#> GSM486741 4 0.0000 0.9206 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486743 4 0.0000 0.9206 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486745 3 0.5838 -0.3891 0.000 0.000 0.412 0.188 0.400 0.000
#> GSM486747 4 0.0000 0.9206 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486749 5 0.0000 0.7850 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486751 5 0.0000 0.7850 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486753 4 0.0000 0.9206 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486755 4 0.3390 0.7289 0.000 0.000 0.296 0.704 0.000 0.000
#> GSM486757 4 0.0000 0.9206 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486759 5 0.0000 0.7850 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486761 4 0.0000 0.9206 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486763 5 0.0000 0.7850 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486765 4 0.0000 0.9206 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486767 4 0.1714 0.8700 0.000 0.000 0.092 0.908 0.000 0.000
#> GSM486769 5 0.4954 0.6434 0.000 0.000 0.112 0.260 0.628 0.000
#> GSM486771 5 0.1967 0.7581 0.000 0.000 0.012 0.084 0.904 0.000
#> GSM486773 4 0.0000 0.9206 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486775 4 0.0458 0.9151 0.000 0.000 0.016 0.984 0.000 0.000
#> GSM486777 5 0.0000 0.7850 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486779 4 0.1267 0.8813 0.000 0.000 0.000 0.940 0.060 0.000
#> GSM486781 4 0.0000 0.9206 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486783 4 0.0777 0.9079 0.000 0.000 0.004 0.972 0.024 0.000
#> GSM486785 5 0.3862 0.4559 0.000 0.000 0.004 0.388 0.608 0.000
#> GSM486787 5 0.0000 0.7850 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486789 4 0.3428 0.7217 0.000 0.000 0.304 0.696 0.000 0.000
#> GSM486791 5 0.4750 0.6555 0.000 0.000 0.096 0.252 0.652 0.000
#> GSM486793 4 0.0000 0.9206 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486795 5 0.0000 0.7850 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486797 4 0.0000 0.9206 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486799 4 0.0000 0.9206 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486801 5 0.0000 0.7850 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486803 5 0.0000 0.7850 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486805 4 0.0000 0.9206 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486807 4 0.0000 0.9206 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486809 4 0.0000 0.9206 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486811 5 0.0000 0.7850 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486813 4 0.3371 0.7330 0.000 0.000 0.292 0.708 0.000 0.000
#> GSM486815 5 0.4939 0.6253 0.000 0.000 0.096 0.292 0.612 0.000
#> GSM486817 4 0.4987 0.5739 0.000 0.000 0.328 0.584 0.088 0.000
#> GSM486819 4 0.3390 0.7289 0.000 0.000 0.296 0.704 0.000 0.000
#> GSM486822 5 0.4769 0.6515 0.000 0.000 0.092 0.264 0.644 0.000
#> GSM486824 5 0.5223 0.3074 0.000 0.000 0.092 0.436 0.472 0.000
#> GSM486828 4 0.3390 0.7289 0.000 0.000 0.296 0.704 0.000 0.000
#> GSM486831 5 0.3052 0.7059 0.000 0.000 0.004 0.216 0.780 0.000
#> GSM486833 5 0.4911 0.6388 0.000 0.000 0.100 0.276 0.624 0.000
#> GSM486835 5 0.0000 0.7850 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486837 4 0.0000 0.9206 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486839 5 0.0363 0.7824 0.000 0.000 0.000 0.012 0.988 0.000
#> GSM486841 5 0.0000 0.7850 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486843 5 0.0000 0.7850 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486845 5 0.5127 0.5228 0.000 0.000 0.092 0.364 0.544 0.000
#> GSM486847 4 0.1124 0.8971 0.000 0.000 0.008 0.956 0.036 0.000
#> GSM486849 5 0.4789 0.6489 0.000 0.000 0.092 0.268 0.640 0.000
#> GSM486851 5 0.0000 0.7850 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM486853 4 0.0000 0.9206 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM486855 5 0.4845 0.6393 0.000 0.000 0.092 0.280 0.628 0.000
#> GSM486857 4 0.2278 0.8045 0.000 0.000 0.004 0.868 0.128 0.000
#> GSM486736 6 0.0000 1.0000 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM486738 1 0.0547 0.7384 0.980 0.000 0.020 0.000 0.000 0.000
#> GSM486740 6 0.0000 1.0000 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM486742 1 0.0146 0.7418 0.996 0.000 0.004 0.000 0.000 0.000
#> GSM486744 1 0.4787 0.3499 0.656 0.000 0.236 0.000 0.000 0.108
#> GSM486746 6 0.0000 1.0000 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM486748 1 0.0000 0.7421 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486750 2 0.0000 0.9790 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486752 2 0.0000 0.9790 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486754 3 0.5391 0.3776 0.308 0.000 0.552 0.000 0.000 0.140
#> GSM486756 3 0.4531 0.0308 0.036 0.000 0.556 0.000 0.000 0.408
#> GSM486758 1 0.1501 0.7200 0.924 0.000 0.076 0.000 0.000 0.000
#> GSM486760 2 0.0000 0.9790 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486762 1 0.3499 0.4848 0.680 0.000 0.320 0.000 0.000 0.000
#> GSM486764 1 0.3003 0.6879 0.812 0.172 0.016 0.000 0.000 0.000
#> GSM486766 1 0.0632 0.7376 0.976 0.000 0.024 0.000 0.000 0.000
#> GSM486768 1 0.4459 0.4311 0.700 0.000 0.204 0.000 0.000 0.096
#> GSM486770 2 0.2558 0.7927 0.004 0.840 0.000 0.000 0.000 0.156
#> GSM486772 2 0.0000 0.9790 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486774 1 0.0000 0.7421 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486776 1 0.3515 0.4787 0.676 0.000 0.324 0.000 0.000 0.000
#> GSM486778 2 0.0000 0.9790 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486780 1 0.3499 0.4848 0.680 0.000 0.320 0.000 0.000 0.000
#> GSM486782 3 0.5507 0.1798 0.424 0.000 0.448 0.000 0.000 0.128
#> GSM486784 1 0.3037 0.6851 0.808 0.176 0.016 0.000 0.000 0.000
#> GSM486786 1 0.3126 0.6249 0.752 0.248 0.000 0.000 0.000 0.000
#> GSM486788 2 0.0000 0.9790 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486790 3 0.5232 0.1763 0.104 0.000 0.536 0.000 0.000 0.360
#> GSM486792 6 0.0000 1.0000 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM486794 3 0.5011 0.2788 0.368 0.000 0.552 0.000 0.000 0.080
#> GSM486796 2 0.0000 0.9790 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486798 1 0.3290 0.6591 0.776 0.208 0.016 0.000 0.000 0.000
#> GSM486800 2 0.1267 0.9075 0.060 0.940 0.000 0.000 0.000 0.000
#> GSM486802 2 0.0000 0.9790 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486804 1 0.3320 0.6551 0.772 0.212 0.016 0.000 0.000 0.000
#> GSM486806 1 0.3244 0.5534 0.732 0.000 0.268 0.000 0.000 0.000
#> GSM486808 1 0.0146 0.7418 0.996 0.000 0.004 0.000 0.000 0.000
#> GSM486810 1 0.3727 0.3547 0.612 0.000 0.388 0.000 0.000 0.000
#> GSM486812 2 0.0000 0.9790 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486814 3 0.5270 0.2068 0.404 0.000 0.496 0.000 0.000 0.100
#> GSM486816 1 0.3198 0.5649 0.740 0.000 0.260 0.000 0.000 0.000
#> GSM486818 3 0.4531 0.0308 0.036 0.000 0.556 0.000 0.000 0.408
#> GSM486821 3 0.5514 0.4094 0.272 0.000 0.552 0.000 0.000 0.176
#> GSM486823 2 0.0865 0.9419 0.036 0.964 0.000 0.000 0.000 0.000
#> GSM486826 1 0.2219 0.7121 0.864 0.136 0.000 0.000 0.000 0.000
#> GSM486830 3 0.5650 0.3554 0.332 0.000 0.500 0.000 0.000 0.168
#> GSM486832 1 0.2340 0.6751 0.852 0.000 0.148 0.000 0.000 0.000
#> GSM486834 1 0.2020 0.7082 0.896 0.000 0.096 0.000 0.000 0.008
#> GSM486836 2 0.0000 0.9790 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486838 1 0.0000 0.7421 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486840 1 0.3200 0.6696 0.788 0.196 0.016 0.000 0.000 0.000
#> GSM486842 2 0.0000 0.9790 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486844 1 0.3348 0.6522 0.768 0.216 0.016 0.000 0.000 0.000
#> GSM486846 1 0.3453 0.5941 0.804 0.000 0.132 0.000 0.000 0.064
#> GSM486848 1 0.3499 0.4848 0.680 0.000 0.320 0.000 0.000 0.000
#> GSM486850 2 0.0000 0.9790 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486852 2 0.0000 0.9790 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM486854 1 0.0000 0.7421 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM486856 1 0.2494 0.7119 0.864 0.120 0.016 0.000 0.000 0.000
#> GSM486858 1 0.2783 0.7010 0.836 0.148 0.016 0.000 0.000 0.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> ATC:mclust 120 4.67e-27 1.000 2
#> ATC:mclust 120 8.76e-27 1.000 3
#> ATC:mclust 111 6.69e-24 0.998 4
#> ATC:mclust 119 8.73e-25 0.997 5
#> ATC:mclust 99 1.61e-20 0.819 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["ATC", "NMF"]
# you can also extract it by
# res = res_list["ATC:NMF"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 120 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'ATC' method.
#> Subgroups are detected by 'NMF' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 1.000 1.000 1.000 0.5047 0.496 0.496
#> 3 3 0.760 0.733 0.883 0.1878 0.943 0.885
#> 4 4 0.626 0.720 0.849 0.0611 0.914 0.817
#> 5 5 0.632 0.713 0.841 0.0360 0.947 0.879
#> 6 6 0.595 0.589 0.800 0.0423 0.977 0.946
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM486735 1 0 1 1 0
#> GSM486737 1 0 1 1 0
#> GSM486739 1 0 1 1 0
#> GSM486741 1 0 1 1 0
#> GSM486743 1 0 1 1 0
#> GSM486745 1 0 1 1 0
#> GSM486747 1 0 1 1 0
#> GSM486749 1 0 1 1 0
#> GSM486751 1 0 1 1 0
#> GSM486753 1 0 1 1 0
#> GSM486755 1 0 1 1 0
#> GSM486757 1 0 1 1 0
#> GSM486759 1 0 1 1 0
#> GSM486761 1 0 1 1 0
#> GSM486763 1 0 1 1 0
#> GSM486765 1 0 1 1 0
#> GSM486767 1 0 1 1 0
#> GSM486769 1 0 1 1 0
#> GSM486771 1 0 1 1 0
#> GSM486773 1 0 1 1 0
#> GSM486775 1 0 1 1 0
#> GSM486777 1 0 1 1 0
#> GSM486779 1 0 1 1 0
#> GSM486781 1 0 1 1 0
#> GSM486783 1 0 1 1 0
#> GSM486785 1 0 1 1 0
#> GSM486787 1 0 1 1 0
#> GSM486789 1 0 1 1 0
#> GSM486791 1 0 1 1 0
#> GSM486793 1 0 1 1 0
#> GSM486795 1 0 1 1 0
#> GSM486797 1 0 1 1 0
#> GSM486799 1 0 1 1 0
#> GSM486801 1 0 1 1 0
#> GSM486803 1 0 1 1 0
#> GSM486805 1 0 1 1 0
#> GSM486807 1 0 1 1 0
#> GSM486809 1 0 1 1 0
#> GSM486811 1 0 1 1 0
#> GSM486813 1 0 1 1 0
#> GSM486815 1 0 1 1 0
#> GSM486817 1 0 1 1 0
#> GSM486819 1 0 1 1 0
#> GSM486822 1 0 1 1 0
#> GSM486824 1 0 1 1 0
#> GSM486828 1 0 1 1 0
#> GSM486831 1 0 1 1 0
#> GSM486833 1 0 1 1 0
#> GSM486835 1 0 1 1 0
#> GSM486837 1 0 1 1 0
#> GSM486839 1 0 1 1 0
#> GSM486841 1 0 1 1 0
#> GSM486843 1 0 1 1 0
#> GSM486845 1 0 1 1 0
#> GSM486847 1 0 1 1 0
#> GSM486849 1 0 1 1 0
#> GSM486851 1 0 1 1 0
#> GSM486853 1 0 1 1 0
#> GSM486855 1 0 1 1 0
#> GSM486857 1 0 1 1 0
#> GSM486736 2 0 1 0 1
#> GSM486738 2 0 1 0 1
#> GSM486740 2 0 1 0 1
#> GSM486742 2 0 1 0 1
#> GSM486744 2 0 1 0 1
#> GSM486746 2 0 1 0 1
#> GSM486748 2 0 1 0 1
#> GSM486750 2 0 1 0 1
#> GSM486752 2 0 1 0 1
#> GSM486754 2 0 1 0 1
#> GSM486756 2 0 1 0 1
#> GSM486758 2 0 1 0 1
#> GSM486760 2 0 1 0 1
#> GSM486762 2 0 1 0 1
#> GSM486764 2 0 1 0 1
#> GSM486766 2 0 1 0 1
#> GSM486768 2 0 1 0 1
#> GSM486770 2 0 1 0 1
#> GSM486772 2 0 1 0 1
#> GSM486774 2 0 1 0 1
#> GSM486776 2 0 1 0 1
#> GSM486778 2 0 1 0 1
#> GSM486780 2 0 1 0 1
#> GSM486782 2 0 1 0 1
#> GSM486784 2 0 1 0 1
#> GSM486786 2 0 1 0 1
#> GSM486788 2 0 1 0 1
#> GSM486790 2 0 1 0 1
#> GSM486792 2 0 1 0 1
#> GSM486794 2 0 1 0 1
#> GSM486796 2 0 1 0 1
#> GSM486798 2 0 1 0 1
#> GSM486800 2 0 1 0 1
#> GSM486802 2 0 1 0 1
#> GSM486804 2 0 1 0 1
#> GSM486806 2 0 1 0 1
#> GSM486808 2 0 1 0 1
#> GSM486810 2 0 1 0 1
#> GSM486812 2 0 1 0 1
#> GSM486814 2 0 1 0 1
#> GSM486816 2 0 1 0 1
#> GSM486818 2 0 1 0 1
#> GSM486821 2 0 1 0 1
#> GSM486823 2 0 1 0 1
#> GSM486826 2 0 1 0 1
#> GSM486830 2 0 1 0 1
#> GSM486832 2 0 1 0 1
#> GSM486834 2 0 1 0 1
#> GSM486836 2 0 1 0 1
#> GSM486838 2 0 1 0 1
#> GSM486840 2 0 1 0 1
#> GSM486842 2 0 1 0 1
#> GSM486844 2 0 1 0 1
#> GSM486846 2 0 1 0 1
#> GSM486848 2 0 1 0 1
#> GSM486850 2 0 1 0 1
#> GSM486852 2 0 1 0 1
#> GSM486854 2 0 1 0 1
#> GSM486856 2 0 1 0 1
#> GSM486858 2 0 1 0 1
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM486735 1 0.0424 0.90902 0.992 0.008 0.000
#> GSM486737 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486739 1 0.0424 0.90902 0.992 0.008 0.000
#> GSM486741 1 0.6126 0.21967 0.600 0.400 0.000
#> GSM486743 1 0.0424 0.90785 0.992 0.008 0.000
#> GSM486745 1 0.0424 0.90902 0.992 0.008 0.000
#> GSM486747 2 0.6274 0.17031 0.456 0.544 0.000
#> GSM486749 1 0.1753 0.88357 0.952 0.048 0.000
#> GSM486751 1 0.1753 0.88358 0.952 0.048 0.000
#> GSM486753 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486755 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486757 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486759 1 0.0892 0.90294 0.980 0.020 0.000
#> GSM486761 1 0.6280 -0.00461 0.540 0.460 0.000
#> GSM486763 1 0.0424 0.90902 0.992 0.008 0.000
#> GSM486765 1 0.6215 0.12431 0.572 0.428 0.000
#> GSM486767 2 0.6244 0.20941 0.440 0.560 0.000
#> GSM486769 1 0.1289 0.89540 0.968 0.032 0.000
#> GSM486771 1 0.0592 0.90723 0.988 0.012 0.000
#> GSM486773 1 0.6180 0.16021 0.584 0.416 0.000
#> GSM486775 2 0.6260 0.19250 0.448 0.552 0.000
#> GSM486777 1 0.1163 0.89909 0.972 0.028 0.000
#> GSM486779 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486781 1 0.0237 0.90987 0.996 0.004 0.000
#> GSM486783 1 0.0424 0.90785 0.992 0.008 0.000
#> GSM486785 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486787 1 0.4702 0.70508 0.788 0.212 0.000
#> GSM486789 1 0.0424 0.90785 0.992 0.008 0.000
#> GSM486791 1 0.1163 0.89813 0.972 0.028 0.000
#> GSM486793 1 0.0237 0.90987 0.996 0.004 0.000
#> GSM486795 1 0.3267 0.81966 0.884 0.116 0.000
#> GSM486797 1 0.5905 0.35426 0.648 0.352 0.000
#> GSM486799 1 0.4002 0.73706 0.840 0.160 0.000
#> GSM486801 1 0.5397 0.60666 0.720 0.280 0.000
#> GSM486803 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486805 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486807 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486809 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486811 1 0.6095 0.42210 0.608 0.392 0.000
#> GSM486813 1 0.5591 0.47420 0.696 0.304 0.000
#> GSM486815 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486817 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486819 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486822 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486824 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486828 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486831 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486833 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486835 1 0.2356 0.86327 0.928 0.072 0.000
#> GSM486837 1 0.0424 0.90785 0.992 0.008 0.000
#> GSM486839 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486841 1 0.3752 0.78849 0.856 0.144 0.000
#> GSM486843 1 0.0237 0.91044 0.996 0.004 0.000
#> GSM486845 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486847 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486849 1 0.0237 0.91039 0.996 0.004 0.000
#> GSM486851 1 0.0892 0.90294 0.980 0.020 0.000
#> GSM486853 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486855 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486857 1 0.0000 0.91141 1.000 0.000 0.000
#> GSM486736 3 0.6111 0.48639 0.000 0.396 0.604
#> GSM486738 3 0.0000 0.84175 0.000 0.000 1.000
#> GSM486740 3 0.6045 0.50684 0.000 0.380 0.620
#> GSM486742 3 0.0424 0.84100 0.000 0.008 0.992
#> GSM486744 3 0.0237 0.84153 0.000 0.004 0.996
#> GSM486746 3 0.6111 0.48639 0.000 0.396 0.604
#> GSM486748 3 0.0424 0.84100 0.000 0.008 0.992
#> GSM486750 3 0.1964 0.81985 0.000 0.056 0.944
#> GSM486752 3 0.1860 0.82230 0.000 0.052 0.948
#> GSM486754 3 0.2796 0.78483 0.000 0.092 0.908
#> GSM486756 2 0.6215 0.38355 0.000 0.572 0.428
#> GSM486758 3 0.3752 0.72552 0.000 0.144 0.856
#> GSM486760 3 0.5678 0.58257 0.000 0.316 0.684
#> GSM486762 2 0.6244 0.36547 0.000 0.560 0.440
#> GSM486764 3 0.0000 0.84175 0.000 0.000 1.000
#> GSM486766 3 0.0424 0.84100 0.000 0.008 0.992
#> GSM486768 3 0.1289 0.83196 0.000 0.032 0.968
#> GSM486770 3 0.5968 0.52705 0.000 0.364 0.636
#> GSM486772 3 0.5327 0.62973 0.000 0.272 0.728
#> GSM486774 3 0.4062 0.69882 0.000 0.164 0.836
#> GSM486776 2 0.6225 0.37884 0.000 0.568 0.432
#> GSM486778 3 0.5138 0.65228 0.000 0.252 0.748
#> GSM486780 3 0.2448 0.80045 0.000 0.076 0.924
#> GSM486782 3 0.0747 0.83931 0.000 0.016 0.984
#> GSM486784 3 0.0424 0.84100 0.000 0.008 0.992
#> GSM486786 3 0.0237 0.84132 0.000 0.004 0.996
#> GSM486788 3 0.1860 0.82220 0.000 0.052 0.948
#> GSM486790 3 0.0892 0.83808 0.000 0.020 0.980
#> GSM486792 3 0.6079 0.49687 0.000 0.388 0.612
#> GSM486794 3 0.1860 0.81904 0.000 0.052 0.948
#> GSM486796 3 0.1411 0.83043 0.000 0.036 0.964
#> GSM486798 3 0.0237 0.84153 0.000 0.004 0.996
#> GSM486800 3 0.0592 0.83967 0.000 0.012 0.988
#> GSM486802 3 0.5988 0.52296 0.000 0.368 0.632
#> GSM486804 3 0.0000 0.84175 0.000 0.000 1.000
#> GSM486806 3 0.2261 0.80675 0.000 0.068 0.932
#> GSM486808 3 0.1031 0.83594 0.000 0.024 0.976
#> GSM486810 2 0.6309 0.21310 0.000 0.504 0.496
#> GSM486812 3 0.5138 0.65169 0.000 0.252 0.748
#> GSM486814 3 0.6235 -0.09518 0.000 0.436 0.564
#> GSM486816 3 0.0892 0.83762 0.000 0.020 0.980
#> GSM486818 3 0.6309 -0.31137 0.000 0.496 0.504
#> GSM486821 3 0.6309 -0.32477 0.000 0.500 0.500
#> GSM486823 3 0.1411 0.83043 0.000 0.036 0.964
#> GSM486826 3 0.0000 0.84175 0.000 0.000 1.000
#> GSM486830 3 0.3267 0.76007 0.000 0.116 0.884
#> GSM486832 3 0.5291 0.49396 0.000 0.268 0.732
#> GSM486834 3 0.0000 0.84175 0.000 0.000 1.000
#> GSM486836 3 0.0592 0.83967 0.000 0.012 0.988
#> GSM486838 3 0.3619 0.73722 0.000 0.136 0.864
#> GSM486840 3 0.0000 0.84175 0.000 0.000 1.000
#> GSM486842 3 0.0592 0.83967 0.000 0.012 0.988
#> GSM486844 3 0.0237 0.84132 0.000 0.004 0.996
#> GSM486846 3 0.0592 0.84004 0.000 0.012 0.988
#> GSM486848 3 0.3686 0.73283 0.000 0.140 0.860
#> GSM486850 3 0.1529 0.82853 0.000 0.040 0.960
#> GSM486852 3 0.0592 0.83967 0.000 0.012 0.988
#> GSM486854 3 0.1031 0.83594 0.000 0.024 0.976
#> GSM486856 3 0.0747 0.83901 0.000 0.016 0.984
#> GSM486858 3 0.0000 0.84175 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM486735 1 0.5355 0.4788 0.620 0.000 0.020 0.360
#> GSM486737 1 0.1452 0.8898 0.956 0.000 0.036 0.008
#> GSM486739 4 0.5399 -0.0921 0.468 0.000 0.012 0.520
#> GSM486741 1 0.3942 0.7642 0.764 0.000 0.236 0.000
#> GSM486743 1 0.2101 0.8859 0.928 0.000 0.060 0.012
#> GSM486745 4 0.5337 0.0682 0.424 0.000 0.012 0.564
#> GSM486747 1 0.5013 0.6602 0.688 0.000 0.292 0.020
#> GSM486749 1 0.2660 0.8843 0.908 0.000 0.036 0.056
#> GSM486751 1 0.2586 0.8844 0.912 0.000 0.040 0.048
#> GSM486753 1 0.2021 0.8855 0.936 0.000 0.024 0.040
#> GSM486755 1 0.4114 0.8304 0.828 0.000 0.060 0.112
#> GSM486757 1 0.0927 0.8905 0.976 0.000 0.008 0.016
#> GSM486759 1 0.2032 0.8885 0.936 0.000 0.028 0.036
#> GSM486761 1 0.4004 0.8155 0.812 0.000 0.164 0.024
#> GSM486763 1 0.1724 0.8883 0.948 0.000 0.020 0.032
#> GSM486765 1 0.3908 0.7839 0.784 0.000 0.212 0.004
#> GSM486767 3 0.4866 -0.1680 0.404 0.000 0.596 0.000
#> GSM486769 1 0.3760 0.8358 0.836 0.000 0.028 0.136
#> GSM486771 1 0.2399 0.8843 0.920 0.000 0.032 0.048
#> GSM486773 1 0.3355 0.8343 0.836 0.000 0.160 0.004
#> GSM486775 1 0.5138 0.5025 0.600 0.000 0.392 0.008
#> GSM486777 1 0.3015 0.8693 0.884 0.000 0.024 0.092
#> GSM486779 1 0.1151 0.8902 0.968 0.000 0.008 0.024
#> GSM486781 1 0.2411 0.8839 0.920 0.000 0.040 0.040
#> GSM486783 1 0.2466 0.8803 0.916 0.000 0.056 0.028
#> GSM486785 1 0.2706 0.8754 0.900 0.000 0.020 0.080
#> GSM486787 1 0.4104 0.8410 0.832 0.000 0.088 0.080
#> GSM486789 1 0.5742 0.6962 0.712 0.000 0.120 0.168
#> GSM486791 1 0.3160 0.8612 0.872 0.000 0.020 0.108
#> GSM486793 1 0.1256 0.8893 0.964 0.000 0.028 0.008
#> GSM486795 1 0.3009 0.8757 0.892 0.000 0.052 0.056
#> GSM486797 1 0.3105 0.8564 0.868 0.000 0.120 0.012
#> GSM486799 1 0.2882 0.8712 0.892 0.000 0.084 0.024
#> GSM486801 1 0.4163 0.8412 0.828 0.000 0.096 0.076
#> GSM486803 1 0.2699 0.8795 0.904 0.000 0.028 0.068
#> GSM486805 1 0.1174 0.8894 0.968 0.000 0.020 0.012
#> GSM486807 1 0.0657 0.8899 0.984 0.000 0.012 0.004
#> GSM486809 1 0.1109 0.8894 0.968 0.000 0.028 0.004
#> GSM486811 1 0.6231 0.6601 0.668 0.000 0.148 0.184
#> GSM486813 1 0.5815 0.5937 0.652 0.000 0.288 0.060
#> GSM486815 1 0.1174 0.8902 0.968 0.000 0.012 0.020
#> GSM486817 1 0.2775 0.8708 0.896 0.000 0.020 0.084
#> GSM486819 1 0.3899 0.8388 0.840 0.000 0.052 0.108
#> GSM486822 1 0.1807 0.8854 0.940 0.000 0.008 0.052
#> GSM486824 1 0.3694 0.8418 0.844 0.000 0.032 0.124
#> GSM486828 1 0.3716 0.8476 0.852 0.000 0.052 0.096
#> GSM486831 1 0.1059 0.8905 0.972 0.000 0.012 0.016
#> GSM486833 1 0.2179 0.8815 0.924 0.000 0.012 0.064
#> GSM486835 1 0.2844 0.8792 0.900 0.000 0.052 0.048
#> GSM486837 1 0.1938 0.8867 0.936 0.000 0.052 0.012
#> GSM486839 1 0.2813 0.8764 0.896 0.000 0.024 0.080
#> GSM486841 1 0.4055 0.8436 0.832 0.000 0.060 0.108
#> GSM486843 1 0.3598 0.8508 0.848 0.000 0.028 0.124
#> GSM486845 1 0.1722 0.8861 0.944 0.000 0.008 0.048
#> GSM486847 1 0.1724 0.8877 0.948 0.000 0.020 0.032
#> GSM486849 1 0.1767 0.8886 0.944 0.000 0.012 0.044
#> GSM486851 1 0.1837 0.8880 0.944 0.000 0.028 0.028
#> GSM486853 1 0.1059 0.8897 0.972 0.000 0.012 0.016
#> GSM486855 1 0.1174 0.8901 0.968 0.000 0.012 0.020
#> GSM486857 1 0.0927 0.8905 0.976 0.000 0.008 0.016
#> GSM486736 4 0.4137 0.5183 0.012 0.208 0.000 0.780
#> GSM486738 2 0.0188 0.8210 0.000 0.996 0.004 0.000
#> GSM486740 4 0.4088 0.5193 0.000 0.232 0.004 0.764
#> GSM486742 2 0.0657 0.8199 0.000 0.984 0.004 0.012
#> GSM486744 2 0.1807 0.8095 0.000 0.940 0.008 0.052
#> GSM486746 4 0.5200 0.4854 0.000 0.264 0.036 0.700
#> GSM486748 2 0.0336 0.8200 0.000 0.992 0.008 0.000
#> GSM486750 2 0.2412 0.7940 0.000 0.908 0.084 0.008
#> GSM486752 2 0.2408 0.7836 0.000 0.896 0.104 0.000
#> GSM486754 2 0.5573 0.0402 0.000 0.604 0.368 0.028
#> GSM486756 4 0.7426 0.3890 0.000 0.224 0.264 0.512
#> GSM486758 2 0.3024 0.7233 0.000 0.852 0.148 0.000
#> GSM486760 2 0.3757 0.7263 0.000 0.828 0.152 0.020
#> GSM486762 3 0.5137 0.3675 0.000 0.452 0.544 0.004
#> GSM486764 2 0.0188 0.8210 0.000 0.996 0.004 0.000
#> GSM486766 2 0.0707 0.8196 0.000 0.980 0.020 0.000
#> GSM486768 2 0.3205 0.7416 0.000 0.872 0.104 0.024
#> GSM486770 2 0.5102 0.6558 0.000 0.764 0.136 0.100
#> GSM486772 2 0.3529 0.7288 0.000 0.836 0.152 0.012
#> GSM486774 2 0.4164 0.5132 0.000 0.736 0.264 0.000
#> GSM486776 3 0.4804 0.4321 0.000 0.384 0.616 0.000
#> GSM486778 2 0.3907 0.7326 0.000 0.828 0.140 0.032
#> GSM486780 2 0.1902 0.8026 0.000 0.932 0.064 0.004
#> GSM486782 2 0.4046 0.6980 0.000 0.828 0.124 0.048
#> GSM486784 2 0.0188 0.8205 0.000 0.996 0.004 0.000
#> GSM486786 2 0.2300 0.8098 0.000 0.924 0.028 0.048
#> GSM486788 2 0.3335 0.7614 0.000 0.860 0.120 0.020
#> GSM486790 4 0.6316 0.4363 0.000 0.300 0.088 0.612
#> GSM486792 2 0.6658 -0.1163 0.000 0.472 0.084 0.444
#> GSM486794 2 0.3852 0.6359 0.000 0.800 0.192 0.008
#> GSM486796 2 0.2480 0.7928 0.000 0.904 0.088 0.008
#> GSM486798 2 0.0000 0.8206 0.000 1.000 0.000 0.000
#> GSM486800 2 0.1022 0.8187 0.000 0.968 0.032 0.000
#> GSM486802 2 0.4197 0.7078 0.000 0.808 0.156 0.036
#> GSM486804 2 0.0469 0.8215 0.000 0.988 0.000 0.012
#> GSM486806 2 0.3257 0.7005 0.000 0.844 0.152 0.004
#> GSM486808 2 0.0817 0.8165 0.000 0.976 0.024 0.000
#> GSM486810 2 0.4994 -0.3260 0.000 0.520 0.480 0.000
#> GSM486812 2 0.3907 0.7326 0.000 0.828 0.140 0.032
#> GSM486814 2 0.5345 -0.1734 0.000 0.560 0.428 0.012
#> GSM486816 2 0.1004 0.8191 0.000 0.972 0.024 0.004
#> GSM486818 4 0.7828 0.1711 0.000 0.296 0.292 0.412
#> GSM486821 3 0.5937 0.2501 0.000 0.472 0.492 0.036
#> GSM486823 2 0.2197 0.8125 0.000 0.928 0.048 0.024
#> GSM486826 2 0.1211 0.8170 0.000 0.960 0.000 0.040
#> GSM486830 2 0.5537 0.4022 0.000 0.688 0.256 0.056
#> GSM486832 2 0.4164 0.5161 0.000 0.736 0.264 0.000
#> GSM486834 2 0.1305 0.8157 0.000 0.960 0.004 0.036
#> GSM486836 2 0.2021 0.8140 0.000 0.936 0.040 0.024
#> GSM486838 2 0.3873 0.5883 0.000 0.772 0.228 0.000
#> GSM486840 2 0.1109 0.8197 0.000 0.968 0.004 0.028
#> GSM486842 2 0.2300 0.8097 0.000 0.924 0.048 0.028
#> GSM486844 2 0.1388 0.8195 0.000 0.960 0.012 0.028
#> GSM486846 2 0.2546 0.7826 0.000 0.912 0.060 0.028
#> GSM486848 2 0.2125 0.7951 0.000 0.920 0.076 0.004
#> GSM486850 2 0.2281 0.7895 0.000 0.904 0.096 0.000
#> GSM486852 2 0.1489 0.8153 0.000 0.952 0.044 0.004
#> GSM486854 2 0.1576 0.8053 0.000 0.948 0.048 0.004
#> GSM486856 2 0.0469 0.8193 0.000 0.988 0.012 0.000
#> GSM486858 2 0.0188 0.8205 0.000 0.996 0.004 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM486735 4 0.6127 0.0818 0.000 0.316 0.000 0.532 0.152
#> GSM486737 4 0.2017 0.7735 0.008 0.000 0.000 0.912 0.080
#> GSM486739 2 0.6166 -0.2003 0.000 0.512 0.000 0.340 0.148
#> GSM486741 4 0.2554 0.7531 0.036 0.000 0.000 0.892 0.072
#> GSM486743 4 0.1281 0.7911 0.012 0.000 0.000 0.956 0.032
#> GSM486745 2 0.6054 -0.1394 0.000 0.548 0.000 0.304 0.148
#> GSM486747 4 0.3949 0.3565 0.004 0.000 0.000 0.696 0.300
#> GSM486749 4 0.2864 0.7893 0.012 0.000 0.000 0.852 0.136
#> GSM486751 4 0.2997 0.7873 0.012 0.000 0.000 0.840 0.148
#> GSM486753 4 0.1197 0.7992 0.000 0.000 0.000 0.952 0.048
#> GSM486755 4 0.3331 0.7694 0.024 0.044 0.000 0.864 0.068
#> GSM486757 4 0.2424 0.7955 0.000 0.000 0.000 0.868 0.132
#> GSM486759 4 0.3146 0.7944 0.028 0.000 0.000 0.844 0.128
#> GSM486761 4 0.3086 0.6735 0.004 0.000 0.000 0.816 0.180
#> GSM486763 4 0.3055 0.7855 0.016 0.000 0.000 0.840 0.144
#> GSM486765 4 0.3720 0.5731 0.012 0.000 0.000 0.760 0.228
#> GSM486767 4 0.4284 0.5425 0.040 0.004 0.000 0.752 0.204
#> GSM486769 4 0.3326 0.7711 0.000 0.024 0.000 0.824 0.152
#> GSM486771 4 0.2719 0.7858 0.000 0.004 0.000 0.852 0.144
#> GSM486773 4 0.1894 0.7735 0.008 0.000 0.000 0.920 0.072
#> GSM486775 4 0.4313 0.1943 0.008 0.000 0.000 0.636 0.356
#> GSM486777 4 0.3828 0.7701 0.072 0.000 0.000 0.808 0.120
#> GSM486779 4 0.2488 0.7955 0.004 0.000 0.000 0.872 0.124
#> GSM486781 4 0.1484 0.7899 0.008 0.000 0.000 0.944 0.048
#> GSM486783 4 0.2920 0.7284 0.016 0.000 0.000 0.852 0.132
#> GSM486785 4 0.3375 0.7881 0.056 0.000 0.000 0.840 0.104
#> GSM486787 4 0.4931 0.7092 0.124 0.012 0.000 0.740 0.124
#> GSM486789 4 0.5724 0.4318 0.072 0.152 0.000 0.700 0.076
#> GSM486791 4 0.3733 0.7641 0.008 0.028 0.000 0.808 0.156
#> GSM486793 4 0.1282 0.7904 0.004 0.000 0.000 0.952 0.044
#> GSM486795 4 0.3106 0.7928 0.020 0.000 0.000 0.840 0.140
#> GSM486797 4 0.2020 0.7579 0.000 0.000 0.000 0.900 0.100
#> GSM486799 4 0.2719 0.7182 0.004 0.000 0.000 0.852 0.144
#> GSM486801 4 0.5195 0.7080 0.108 0.028 0.000 0.732 0.132
#> GSM486803 4 0.3622 0.7778 0.056 0.000 0.000 0.820 0.124
#> GSM486805 4 0.0880 0.7919 0.000 0.000 0.000 0.968 0.032
#> GSM486807 4 0.1197 0.7853 0.000 0.000 0.000 0.952 0.048
#> GSM486809 4 0.1357 0.7958 0.004 0.000 0.000 0.948 0.048
#> GSM486811 1 0.6774 0.0000 0.600 0.084 0.000 0.192 0.124
#> GSM486813 5 0.6779 0.0000 0.156 0.020 0.000 0.356 0.468
#> GSM486815 4 0.4946 0.6785 0.120 0.000 0.000 0.712 0.168
#> GSM486817 4 0.3441 0.7743 0.004 0.028 0.000 0.828 0.140
#> GSM486819 4 0.3254 0.7683 0.020 0.052 0.000 0.868 0.060
#> GSM486822 4 0.2648 0.7821 0.000 0.000 0.000 0.848 0.152
#> GSM486824 4 0.4679 0.6626 0.124 0.000 0.000 0.740 0.136
#> GSM486828 4 0.2610 0.7848 0.020 0.020 0.000 0.900 0.060
#> GSM486831 4 0.1571 0.7929 0.004 0.000 0.000 0.936 0.060
#> GSM486833 4 0.2886 0.7815 0.000 0.008 0.000 0.844 0.148
#> GSM486835 4 0.2416 0.8011 0.012 0.000 0.000 0.888 0.100
#> GSM486837 4 0.2020 0.7602 0.000 0.000 0.000 0.900 0.100
#> GSM486839 4 0.4216 0.6661 0.120 0.000 0.000 0.780 0.100
#> GSM486841 4 0.5274 0.5912 0.192 0.000 0.000 0.676 0.132
#> GSM486843 4 0.4057 0.7419 0.088 0.000 0.000 0.792 0.120
#> GSM486845 4 0.2536 0.7973 0.000 0.004 0.000 0.868 0.128
#> GSM486847 4 0.1956 0.7800 0.008 0.000 0.000 0.916 0.076
#> GSM486849 4 0.2424 0.7952 0.000 0.000 0.000 0.868 0.132
#> GSM486851 4 0.2488 0.7966 0.004 0.000 0.000 0.872 0.124
#> GSM486853 4 0.0794 0.7919 0.000 0.000 0.000 0.972 0.028
#> GSM486855 4 0.2046 0.7954 0.016 0.000 0.000 0.916 0.068
#> GSM486857 4 0.0703 0.7985 0.000 0.000 0.000 0.976 0.024
#> GSM486736 2 0.0510 0.5020 0.000 0.984 0.016 0.000 0.000
#> GSM486738 3 0.1757 0.8686 0.048 0.012 0.936 0.000 0.004
#> GSM486740 2 0.0771 0.5063 0.004 0.976 0.020 0.000 0.000
#> GSM486742 3 0.1012 0.8706 0.020 0.012 0.968 0.000 0.000
#> GSM486744 3 0.4403 0.7888 0.064 0.056 0.804 0.000 0.076
#> GSM486746 2 0.1981 0.4955 0.048 0.924 0.028 0.000 0.000
#> GSM486748 3 0.1195 0.8715 0.028 0.000 0.960 0.000 0.012
#> GSM486750 3 0.3555 0.8127 0.124 0.052 0.824 0.000 0.000
#> GSM486752 3 0.3165 0.8276 0.116 0.036 0.848 0.000 0.000
#> GSM486754 3 0.6753 0.2443 0.104 0.044 0.500 0.000 0.352
#> GSM486756 2 0.5459 0.4691 0.156 0.716 0.052 0.000 0.076
#> GSM486758 3 0.2304 0.8504 0.044 0.000 0.908 0.000 0.048
#> GSM486760 3 0.5117 0.6383 0.276 0.072 0.652 0.000 0.000
#> GSM486762 3 0.3567 0.7943 0.032 0.004 0.820 0.000 0.144
#> GSM486764 3 0.1205 0.8696 0.040 0.000 0.956 0.000 0.004
#> GSM486766 3 0.1444 0.8669 0.012 0.000 0.948 0.000 0.040
#> GSM486768 3 0.1405 0.8687 0.016 0.008 0.956 0.000 0.020
#> GSM486770 3 0.5312 0.6547 0.124 0.208 0.668 0.000 0.000
#> GSM486772 3 0.4317 0.7685 0.160 0.076 0.764 0.000 0.000
#> GSM486774 3 0.1106 0.8672 0.024 0.000 0.964 0.000 0.012
#> GSM486776 3 0.4941 0.5324 0.044 0.000 0.628 0.000 0.328
#> GSM486778 3 0.4284 0.7382 0.224 0.040 0.736 0.000 0.000
#> GSM486780 3 0.1661 0.8630 0.036 0.000 0.940 0.000 0.024
#> GSM486782 3 0.5522 0.6679 0.080 0.048 0.708 0.000 0.164
#> GSM486784 3 0.0324 0.8692 0.004 0.000 0.992 0.000 0.004
#> GSM486786 3 0.2116 0.8692 0.076 0.004 0.912 0.000 0.008
#> GSM486788 3 0.2915 0.8329 0.116 0.024 0.860 0.000 0.000
#> GSM486790 2 0.4788 0.4978 0.144 0.760 0.068 0.000 0.028
#> GSM486792 2 0.5417 0.3284 0.116 0.648 0.236 0.000 0.000
#> GSM486794 3 0.3387 0.8087 0.020 0.008 0.832 0.000 0.140
#> GSM486796 3 0.2519 0.8441 0.100 0.016 0.884 0.000 0.000
#> GSM486798 3 0.0404 0.8696 0.012 0.000 0.988 0.000 0.000
#> GSM486800 3 0.2583 0.8415 0.132 0.004 0.864 0.000 0.000
#> GSM486802 3 0.5483 0.3743 0.424 0.064 0.512 0.000 0.000
#> GSM486804 3 0.1124 0.8699 0.036 0.000 0.960 0.000 0.004
#> GSM486806 3 0.0671 0.8699 0.004 0.000 0.980 0.000 0.016
#> GSM486808 3 0.0671 0.8677 0.016 0.000 0.980 0.000 0.004
#> GSM486810 3 0.2344 0.8517 0.032 0.000 0.904 0.000 0.064
#> GSM486812 3 0.4547 0.7037 0.252 0.044 0.704 0.000 0.000
#> GSM486814 3 0.5197 0.6364 0.068 0.012 0.684 0.000 0.236
#> GSM486816 3 0.3416 0.8171 0.072 0.000 0.840 0.000 0.088
#> GSM486818 2 0.7147 0.2620 0.076 0.464 0.360 0.000 0.100
#> GSM486821 3 0.5364 0.6997 0.108 0.044 0.728 0.000 0.120
#> GSM486823 3 0.2905 0.8413 0.096 0.036 0.868 0.000 0.000
#> GSM486826 3 0.1522 0.8682 0.044 0.000 0.944 0.000 0.012
#> GSM486830 3 0.3483 0.8244 0.088 0.032 0.852 0.000 0.028
#> GSM486832 3 0.1493 0.8645 0.028 0.000 0.948 0.000 0.024
#> GSM486834 3 0.1243 0.8716 0.028 0.008 0.960 0.000 0.004
#> GSM486836 3 0.1704 0.8624 0.068 0.004 0.928 0.000 0.000
#> GSM486838 3 0.0912 0.8688 0.012 0.000 0.972 0.000 0.016
#> GSM486840 3 0.0609 0.8695 0.020 0.000 0.980 0.000 0.000
#> GSM486842 3 0.1831 0.8592 0.076 0.004 0.920 0.000 0.000
#> GSM486844 3 0.0963 0.8704 0.036 0.000 0.964 0.000 0.000
#> GSM486846 3 0.3912 0.7851 0.028 0.020 0.808 0.000 0.144
#> GSM486848 3 0.2588 0.8486 0.048 0.000 0.892 0.000 0.060
#> GSM486850 3 0.2408 0.8479 0.092 0.016 0.892 0.000 0.000
#> GSM486852 3 0.1638 0.8614 0.064 0.004 0.932 0.000 0.000
#> GSM486854 3 0.0740 0.8702 0.008 0.004 0.980 0.000 0.008
#> GSM486856 3 0.0451 0.8691 0.008 0.000 0.988 0.000 0.004
#> GSM486858 3 0.0703 0.8702 0.024 0.000 0.976 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM486735 4 0.5343 0.1279 0.000 0.000 0.000 0.580 0.156 0.264
#> GSM486737 4 0.1477 0.7525 0.000 0.008 0.004 0.940 0.048 0.000
#> GSM486739 6 0.5797 -0.3467 0.000 0.000 0.004 0.392 0.156 0.448
#> GSM486741 4 0.1478 0.7279 0.000 0.020 0.004 0.944 0.032 0.000
#> GSM486743 4 0.1296 0.7360 0.000 0.012 0.004 0.952 0.032 0.000
#> GSM486745 6 0.5592 -0.2488 0.000 0.000 0.000 0.340 0.156 0.504
#> GSM486747 4 0.4222 0.4699 0.000 0.160 0.012 0.752 0.076 0.000
#> GSM486749 4 0.2527 0.7111 0.000 0.000 0.000 0.832 0.168 0.000
#> GSM486751 4 0.2527 0.7091 0.000 0.000 0.000 0.832 0.168 0.000
#> GSM486753 4 0.1615 0.7479 0.000 0.004 0.004 0.928 0.064 0.000
#> GSM486755 4 0.3219 0.6796 0.000 0.012 0.004 0.848 0.052 0.084
#> GSM486757 4 0.2260 0.7335 0.000 0.000 0.000 0.860 0.140 0.000
#> GSM486759 4 0.3037 0.7004 0.000 0.000 0.016 0.808 0.176 0.000
#> GSM486761 4 0.3011 0.6564 0.000 0.036 0.012 0.852 0.100 0.000
#> GSM486763 4 0.2697 0.7066 0.000 0.000 0.000 0.812 0.188 0.000
#> GSM486765 4 0.4234 0.4257 0.000 0.100 0.004 0.744 0.152 0.000
#> GSM486767 4 0.3830 0.5453 0.000 0.072 0.008 0.796 0.120 0.004
#> GSM486769 4 0.3175 0.7034 0.000 0.000 0.000 0.808 0.164 0.028
#> GSM486771 4 0.2454 0.7123 0.000 0.000 0.000 0.840 0.160 0.000
#> GSM486773 4 0.1401 0.7292 0.000 0.020 0.004 0.948 0.028 0.000
#> GSM486775 4 0.6114 -0.3872 0.000 0.252 0.008 0.468 0.272 0.000
#> GSM486777 4 0.4024 0.6358 0.000 0.000 0.072 0.744 0.184 0.000
#> GSM486779 4 0.3023 0.6797 0.000 0.000 0.004 0.784 0.212 0.000
#> GSM486781 4 0.1313 0.7310 0.000 0.016 0.004 0.952 0.028 0.000
#> GSM486783 4 0.2689 0.7082 0.000 0.080 0.004 0.876 0.036 0.004
#> GSM486785 4 0.3953 0.3474 0.000 0.000 0.016 0.656 0.328 0.000
#> GSM486787 4 0.4100 0.6559 0.000 0.000 0.064 0.752 0.176 0.008
#> GSM486789 4 0.5871 0.1110 0.000 0.092 0.004 0.624 0.072 0.208
#> GSM486791 4 0.4067 0.6554 0.000 0.000 0.008 0.756 0.172 0.064
#> GSM486793 4 0.1390 0.7290 0.000 0.016 0.004 0.948 0.032 0.000
#> GSM486795 4 0.3014 0.6971 0.000 0.000 0.012 0.804 0.184 0.000
#> GSM486797 4 0.1605 0.7246 0.000 0.016 0.004 0.936 0.044 0.000
#> GSM486799 4 0.2663 0.6863 0.000 0.028 0.012 0.876 0.084 0.000
#> GSM486801 4 0.4094 0.6388 0.000 0.000 0.080 0.740 0.180 0.000
#> GSM486803 4 0.3865 0.5952 0.000 0.000 0.032 0.720 0.248 0.000
#> GSM486805 4 0.1346 0.7307 0.000 0.016 0.008 0.952 0.024 0.000
#> GSM486807 4 0.1737 0.7357 0.000 0.020 0.008 0.932 0.040 0.000
#> GSM486809 4 0.1464 0.7326 0.000 0.016 0.004 0.944 0.036 0.000
#> GSM486811 3 0.5313 0.0000 0.000 0.004 0.660 0.128 0.188 0.020
#> GSM486813 2 0.5360 -0.5200 0.000 0.508 0.004 0.420 0.036 0.032
#> GSM486815 5 0.4918 0.3905 0.000 0.000 0.052 0.432 0.512 0.004
#> GSM486817 4 0.4728 0.4442 0.000 0.000 0.000 0.680 0.144 0.176
#> GSM486819 4 0.2100 0.7379 0.000 0.008 0.004 0.916 0.048 0.024
#> GSM486822 4 0.2454 0.7169 0.000 0.000 0.000 0.840 0.160 0.000
#> GSM486824 5 0.5767 -0.0267 0.004 0.012 0.132 0.268 0.580 0.004
#> GSM486828 4 0.2113 0.7391 0.000 0.008 0.004 0.916 0.044 0.028
#> GSM486831 4 0.1524 0.7400 0.000 0.000 0.008 0.932 0.060 0.000
#> GSM486833 4 0.2473 0.7246 0.000 0.000 0.000 0.856 0.136 0.008
#> GSM486835 4 0.2896 0.7124 0.000 0.000 0.016 0.824 0.160 0.000
#> GSM486837 4 0.2595 0.7110 0.000 0.056 0.008 0.888 0.044 0.004
#> GSM486839 4 0.4040 0.5827 0.000 0.008 0.116 0.780 0.092 0.004
#> GSM486841 4 0.5480 0.0392 0.000 0.000 0.252 0.564 0.184 0.000
#> GSM486843 4 0.4082 0.6003 0.000 0.000 0.084 0.756 0.156 0.004
#> GSM486845 4 0.2804 0.7386 0.000 0.024 0.004 0.852 0.120 0.000
#> GSM486847 4 0.2062 0.7306 0.000 0.000 0.008 0.900 0.088 0.004
#> GSM486849 4 0.2300 0.7245 0.000 0.000 0.000 0.856 0.144 0.000
#> GSM486851 4 0.2491 0.7125 0.000 0.000 0.000 0.836 0.164 0.000
#> GSM486853 4 0.0951 0.7401 0.000 0.004 0.008 0.968 0.020 0.000
#> GSM486855 4 0.3277 0.7230 0.000 0.024 0.020 0.828 0.128 0.000
#> GSM486857 4 0.1080 0.7407 0.000 0.004 0.004 0.960 0.032 0.000
#> GSM486736 6 0.0964 0.4881 0.004 0.012 0.016 0.000 0.000 0.968
#> GSM486738 1 0.2680 0.7479 0.856 0.124 0.016 0.000 0.000 0.004
#> GSM486740 6 0.1167 0.4920 0.008 0.012 0.020 0.000 0.000 0.960
#> GSM486742 1 0.1897 0.7721 0.908 0.084 0.004 0.000 0.000 0.004
#> GSM486744 1 0.4904 0.4168 0.620 0.316 0.024 0.000 0.000 0.040
#> GSM486746 6 0.2250 0.4748 0.020 0.000 0.092 0.000 0.000 0.888
#> GSM486748 1 0.2695 0.7402 0.844 0.144 0.008 0.000 0.004 0.000
#> GSM486750 1 0.2933 0.7637 0.844 0.016 0.128 0.000 0.000 0.012
#> GSM486752 1 0.2982 0.7619 0.844 0.016 0.124 0.000 0.000 0.016
#> GSM486754 2 0.4591 -0.3975 0.464 0.500 0.000 0.000 0.000 0.036
#> GSM486756 6 0.5170 0.4429 0.064 0.140 0.012 0.000 0.068 0.716
#> GSM486758 1 0.4746 0.4660 0.620 0.020 0.032 0.000 0.328 0.000
#> GSM486760 1 0.3991 0.6767 0.724 0.008 0.240 0.000 0.000 0.028
#> GSM486762 1 0.4113 0.6520 0.744 0.056 0.008 0.000 0.192 0.000
#> GSM486764 1 0.2704 0.7718 0.876 0.012 0.036 0.000 0.076 0.000
#> GSM486766 1 0.2825 0.7613 0.868 0.064 0.008 0.000 0.060 0.000
#> GSM486768 1 0.2377 0.7537 0.868 0.124 0.004 0.000 0.000 0.004
#> GSM486770 1 0.4168 0.7124 0.764 0.016 0.144 0.000 0.000 0.076
#> GSM486772 1 0.3272 0.7522 0.820 0.016 0.144 0.000 0.000 0.020
#> GSM486774 1 0.1218 0.7837 0.956 0.028 0.004 0.000 0.012 0.000
#> GSM486776 1 0.6363 -0.0424 0.404 0.236 0.016 0.000 0.344 0.000
#> GSM486778 1 0.3582 0.7242 0.776 0.008 0.192 0.000 0.000 0.024
#> GSM486780 1 0.3834 0.6696 0.760 0.020 0.020 0.000 0.200 0.000
#> GSM486782 1 0.4631 0.1511 0.536 0.428 0.004 0.000 0.000 0.032
#> GSM486784 1 0.0603 0.7848 0.980 0.016 0.004 0.000 0.000 0.000
#> GSM486786 1 0.3994 0.6841 0.752 0.008 0.048 0.000 0.192 0.000
#> GSM486788 1 0.2892 0.7615 0.840 0.004 0.136 0.000 0.000 0.020
#> GSM486790 6 0.3628 0.4907 0.084 0.060 0.008 0.000 0.020 0.828
#> GSM486792 6 0.5321 0.2611 0.232 0.000 0.156 0.000 0.004 0.608
#> GSM486794 1 0.5208 0.4432 0.624 0.248 0.008 0.000 0.120 0.000
#> GSM486796 1 0.2376 0.7750 0.884 0.008 0.096 0.000 0.000 0.012
#> GSM486798 1 0.0909 0.7854 0.968 0.020 0.012 0.000 0.000 0.000
#> GSM486800 1 0.3016 0.7793 0.852 0.048 0.092 0.000 0.000 0.008
#> GSM486802 1 0.4310 0.6665 0.712 0.024 0.236 0.000 0.000 0.028
#> GSM486804 1 0.2556 0.7724 0.884 0.012 0.028 0.000 0.076 0.000
#> GSM486806 1 0.0713 0.7857 0.972 0.028 0.000 0.000 0.000 0.000
#> GSM486808 1 0.0767 0.7840 0.976 0.008 0.004 0.000 0.012 0.000
#> GSM486810 1 0.2202 0.7799 0.908 0.028 0.012 0.000 0.052 0.000
#> GSM486812 1 0.3761 0.6999 0.744 0.008 0.228 0.000 0.000 0.020
#> GSM486814 1 0.3950 0.5694 0.708 0.268 0.004 0.000 0.004 0.016
#> GSM486816 1 0.5161 0.2272 0.496 0.020 0.044 0.000 0.440 0.000
#> GSM486818 6 0.6653 0.3045 0.092 0.060 0.036 0.000 0.268 0.544
#> GSM486821 1 0.6268 0.4037 0.616 0.136 0.012 0.000 0.096 0.140
#> GSM486823 1 0.2617 0.7741 0.872 0.016 0.100 0.000 0.000 0.012
#> GSM486826 1 0.4217 0.6022 0.700 0.016 0.024 0.000 0.260 0.000
#> GSM486830 1 0.2781 0.7525 0.868 0.040 0.008 0.000 0.000 0.084
#> GSM486832 1 0.1882 0.7761 0.920 0.012 0.008 0.000 0.060 0.000
#> GSM486834 1 0.3099 0.7803 0.864 0.012 0.056 0.000 0.056 0.012
#> GSM486836 1 0.2056 0.7842 0.904 0.004 0.080 0.000 0.012 0.000
#> GSM486838 1 0.0748 0.7836 0.976 0.016 0.004 0.000 0.004 0.000
#> GSM486840 1 0.0692 0.7892 0.976 0.000 0.020 0.000 0.004 0.000
#> GSM486842 1 0.2020 0.7823 0.896 0.000 0.096 0.000 0.008 0.000
#> GSM486844 1 0.1708 0.7885 0.932 0.004 0.040 0.000 0.024 0.000
#> GSM486846 1 0.4516 0.2151 0.552 0.420 0.008 0.000 0.000 0.020
#> GSM486848 1 0.4265 0.5773 0.680 0.016 0.020 0.000 0.284 0.000
#> GSM486850 1 0.2275 0.7771 0.888 0.008 0.096 0.000 0.000 0.008
#> GSM486852 1 0.2153 0.7824 0.900 0.004 0.084 0.000 0.008 0.004
#> GSM486854 1 0.1493 0.7810 0.936 0.056 0.004 0.000 0.000 0.004
#> GSM486856 1 0.0692 0.7847 0.976 0.020 0.004 0.000 0.000 0.000
#> GSM486858 1 0.1049 0.7878 0.960 0.000 0.032 0.000 0.008 0.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n agent(p) individual(p) k
#> ATC:NMF 120 4.67e-27 1.000 2
#> ATC:NMF 99 1.87e-22 1.000 3
#> ATC:NMF 104 2.61e-23 0.500 4
#> ATC:NMF 105 1.58e-23 0.478 5
#> ATC:NMF 90 1.76e-20 1.000 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
sessionInfo()
#> R version 3.6.0 (2019-04-26)
#> Platform: x86_64-pc-linux-gnu (64-bit)
#> Running under: CentOS Linux 7 (Core)
#>
#> Matrix products: default
#> BLAS: /usr/lib64/libblas.so.3.4.2
#> LAPACK: /usr/lib64/liblapack.so.3.4.2
#>
#> locale:
#> [1] LC_CTYPE=en_GB.UTF-8 LC_NUMERIC=C LC_TIME=en_GB.UTF-8
#> [4] LC_COLLATE=en_GB.UTF-8 LC_MONETARY=en_GB.UTF-8 LC_MESSAGES=en_GB.UTF-8
#> [7] LC_PAPER=en_GB.UTF-8 LC_NAME=C LC_ADDRESS=C
#> [10] LC_TELEPHONE=C LC_MEASUREMENT=en_GB.UTF-8 LC_IDENTIFICATION=C
#>
#> attached base packages:
#> [1] grid stats graphics grDevices utils datasets methods base
#>
#> other attached packages:
#> [1] genefilter_1.66.0 ComplexHeatmap_2.3.1 markdown_1.1 knitr_1.26
#> [5] GetoptLong_0.1.7 cola_1.3.2
#>
#> loaded via a namespace (and not attached):
#> [1] circlize_0.4.8 shape_1.4.4 xfun_0.11 slam_0.1-46
#> [5] lattice_0.20-38 splines_3.6.0 colorspace_1.4-1 vctrs_0.2.0
#> [9] stats4_3.6.0 blob_1.2.0 XML_3.98-1.20 survival_2.44-1.1
#> [13] rlang_0.4.2 pillar_1.4.2 DBI_1.0.0 BiocGenerics_0.30.0
#> [17] bit64_0.9-7 RColorBrewer_1.1-2 matrixStats_0.55.0 stringr_1.4.0
#> [21] GlobalOptions_0.1.1 evaluate_0.14 memoise_1.1.0 Biobase_2.44.0
#> [25] IRanges_2.18.3 parallel_3.6.0 AnnotationDbi_1.46.1 highr_0.8
#> [29] Rcpp_1.0.3 xtable_1.8-4 backports_1.1.5 S4Vectors_0.22.1
#> [33] annotate_1.62.0 skmeans_0.2-11 bit_1.1-14 microbenchmark_1.4-7
#> [37] brew_1.0-6 impute_1.58.0 rjson_0.2.20 png_0.1-7
#> [41] digest_0.6.23 stringi_1.4.3 polyclip_1.10-0 clue_0.3-57
#> [45] tools_3.6.0 bitops_1.0-6 magrittr_1.5 eulerr_6.0.0
#> [49] RCurl_1.95-4.12 RSQLite_2.1.4 tibble_2.1.3 cluster_2.1.0
#> [53] crayon_1.3.4 pkgconfig_2.0.3 zeallot_0.1.0 Matrix_1.2-17
#> [57] xml2_1.2.2 httr_1.4.1 R6_2.4.1 mclust_5.4.5
#> [61] compiler_3.6.0