Date: 2019-12-25 21:43:45 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 103 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 103
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:kmeans | 3 | 1.000 | 0.994 | 0.997 | ** | |
| ATC:NMF | 2 | 0.999 | 0.970 | 0.986 | ** | |
| MAD:mclust | 3 | 0.991 | 0.932 | 0.966 | ** | |
| ATC:pam | 3 | 0.986 | 0.955 | 0.982 | ** | 2 |
| ATC:mclust | 3 | 0.979 | 0.933 | 0.956 | ** | 2 |
| SD:skmeans | 2 | 0.915 | 0.900 | 0.956 | * | |
| ATC:skmeans | 5 | 0.900 | 0.883 | 0.953 | * | 2,3 |
| MAD:skmeans | 2 | 0.800 | 0.868 | 0.940 | ||
| CV:skmeans | 3 | 0.793 | 0.846 | 0.925 | ||
| SD:mclust | 5 | 0.752 | 0.809 | 0.885 | ||
| CV:mclust | 3 | 0.724 | 0.787 | 0.909 | ||
| MAD:pam | 2 | 0.704 | 0.848 | 0.928 | ||
| ATC:hclust | 3 | 0.610 | 0.839 | 0.873 | ||
| SD:pam | 4 | 0.603 | 0.661 | 0.845 | ||
| MAD:hclust | 6 | 0.585 | 0.551 | 0.704 | ||
| MAD:NMF | 2 | 0.564 | 0.805 | 0.906 | ||
| MAD:kmeans | 3 | 0.544 | 0.708 | 0.842 | ||
| SD:NMF | 2 | 0.530 | 0.842 | 0.921 | ||
| CV:pam | 5 | 0.519 | 0.454 | 0.731 | ||
| CV:NMF | 2 | 0.495 | 0.782 | 0.841 | ||
| CV:kmeans | 3 | 0.478 | 0.714 | 0.833 | ||
| SD:kmeans | 2 | 0.227 | 0.678 | 0.811 | ||
| SD:hclust | 2 | 0.164 | 0.629 | 0.789 | ||
| CV:hclust | 2 | 0.093 | 0.458 | 0.723 |
**: 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 0.5301 0.842 0.921 0.488 0.520 0.520
#> CV:NMF 2 0.4955 0.782 0.841 0.461 0.530 0.530
#> MAD:NMF 2 0.5638 0.805 0.906 0.487 0.516 0.516
#> ATC:NMF 2 0.9994 0.970 0.986 0.467 0.535 0.535
#> SD:skmeans 2 0.9147 0.900 0.956 0.504 0.496 0.496
#> CV:skmeans 2 0.6244 0.831 0.914 0.504 0.496 0.496
#> MAD:skmeans 2 0.8000 0.868 0.940 0.504 0.495 0.495
#> ATC:skmeans 2 1.0000 0.997 0.998 0.504 0.496 0.496
#> SD:mclust 2 0.2032 0.595 0.778 0.444 0.541 0.541
#> CV:mclust 2 0.2929 0.673 0.823 0.386 0.696 0.696
#> MAD:mclust 2 0.2891 0.580 0.810 0.478 0.535 0.535
#> ATC:mclust 2 1.0000 0.991 0.995 0.397 0.600 0.600
#> SD:kmeans 2 0.2268 0.678 0.811 0.483 0.496 0.496
#> CV:kmeans 2 0.2004 0.630 0.767 0.462 0.495 0.495
#> MAD:kmeans 2 0.2554 0.687 0.825 0.487 0.496 0.496
#> ATC:kmeans 2 0.8358 0.949 0.974 0.494 0.499 0.499
#> SD:pam 2 0.7309 0.878 0.938 0.427 0.560 0.560
#> CV:pam 2 0.6190 0.838 0.926 0.421 0.591 0.591
#> MAD:pam 2 0.7043 0.848 0.928 0.474 0.525 0.525
#> ATC:pam 2 0.9601 0.949 0.977 0.452 0.541 0.541
#> SD:hclust 2 0.1637 0.629 0.789 0.426 0.530 0.530
#> CV:hclust 2 0.0934 0.458 0.723 0.443 0.499 0.499
#> MAD:hclust 2 0.0848 0.342 0.664 0.446 0.639 0.639
#> ATC:hclust 2 0.8353 0.890 0.947 0.419 0.600 0.600
get_stats(res_list, k = 3)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 3 0.5569 0.640 0.843 0.356 0.689 0.471
#> CV:NMF 3 0.5919 0.723 0.870 0.421 0.678 0.461
#> MAD:NMF 3 0.4686 0.606 0.816 0.354 0.688 0.475
#> ATC:NMF 3 0.7008 0.852 0.916 0.314 0.777 0.611
#> SD:skmeans 3 0.7691 0.841 0.926 0.325 0.693 0.457
#> CV:skmeans 3 0.7934 0.846 0.925 0.326 0.716 0.488
#> MAD:skmeans 3 0.7421 0.860 0.934 0.318 0.741 0.525
#> ATC:skmeans 3 0.9712 0.945 0.975 0.195 0.889 0.780
#> SD:mclust 3 0.4740 0.802 0.885 0.348 0.711 0.516
#> CV:mclust 3 0.7240 0.787 0.909 0.639 0.657 0.512
#> MAD:mclust 3 0.9912 0.932 0.966 0.277 0.736 0.555
#> ATC:mclust 3 0.9792 0.933 0.956 0.387 0.772 0.643
#> SD:kmeans 3 0.4774 0.652 0.800 0.328 0.785 0.595
#> CV:kmeans 3 0.4777 0.714 0.833 0.364 0.771 0.573
#> MAD:kmeans 3 0.5445 0.708 0.842 0.297 0.833 0.680
#> ATC:kmeans 3 1.0000 0.994 0.997 0.338 0.706 0.481
#> SD:pam 3 0.4659 0.509 0.769 0.454 0.642 0.451
#> CV:pam 3 0.3348 0.368 0.681 0.495 0.640 0.454
#> MAD:pam 3 0.4313 0.656 0.827 0.374 0.700 0.486
#> ATC:pam 3 0.9856 0.955 0.982 0.434 0.760 0.576
#> SD:hclust 3 0.3079 0.581 0.766 0.373 0.725 0.551
#> CV:hclust 3 0.0979 0.467 0.632 0.380 0.803 0.638
#> MAD:hclust 3 0.1503 0.454 0.619 0.369 0.621 0.472
#> ATC:hclust 3 0.6104 0.839 0.873 0.488 0.721 0.540
get_stats(res_list, k = 4)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 4 0.601 0.700 0.812 0.1277 0.811 0.521
#> CV:NMF 4 0.593 0.633 0.812 0.1342 0.808 0.510
#> MAD:NMF 4 0.691 0.762 0.877 0.1362 0.803 0.510
#> ATC:NMF 4 0.784 0.803 0.886 0.1114 0.870 0.687
#> SD:skmeans 4 0.740 0.701 0.842 0.1068 0.897 0.707
#> CV:skmeans 4 0.612 0.681 0.790 0.1080 0.924 0.775
#> MAD:skmeans 4 0.698 0.652 0.845 0.1152 0.860 0.619
#> ATC:skmeans 4 0.878 0.902 0.951 0.0747 0.951 0.877
#> SD:mclust 4 0.582 0.718 0.842 0.0771 0.664 0.388
#> CV:mclust 4 0.770 0.744 0.880 0.0918 0.943 0.847
#> MAD:mclust 4 0.585 0.787 0.886 0.0298 0.702 0.442
#> ATC:mclust 4 0.839 0.897 0.956 0.1579 0.856 0.696
#> SD:kmeans 4 0.652 0.619 0.784 0.1303 0.862 0.629
#> CV:kmeans 4 0.666 0.765 0.833 0.1372 0.913 0.762
#> MAD:kmeans 4 0.657 0.640 0.826 0.1527 0.796 0.518
#> ATC:kmeans 4 0.661 0.564 0.778 0.1165 0.819 0.533
#> SD:pam 4 0.603 0.661 0.845 0.1324 0.707 0.392
#> CV:pam 4 0.418 0.409 0.716 0.1134 0.713 0.391
#> MAD:pam 4 0.575 0.690 0.829 0.1124 0.857 0.624
#> ATC:pam 4 0.830 0.686 0.848 0.1156 0.934 0.815
#> SD:hclust 4 0.365 0.591 0.694 0.1506 0.869 0.704
#> CV:hclust 4 0.276 0.312 0.564 0.1386 0.695 0.370
#> MAD:hclust 4 0.334 0.507 0.684 0.1677 0.824 0.591
#> ATC:hclust 4 0.718 0.719 0.834 0.1378 0.954 0.862
get_stats(res_list, k = 5)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 5 0.684 0.684 0.828 0.0669 0.904 0.661
#> CV:NMF 5 0.678 0.673 0.823 0.0687 0.891 0.614
#> MAD:NMF 5 0.627 0.601 0.727 0.0640 0.911 0.673
#> ATC:NMF 5 0.789 0.785 0.892 0.1031 0.868 0.613
#> SD:skmeans 5 0.761 0.750 0.853 0.0703 0.888 0.618
#> CV:skmeans 5 0.645 0.607 0.781 0.0740 0.898 0.652
#> MAD:skmeans 5 0.686 0.697 0.824 0.0714 0.906 0.665
#> ATC:skmeans 5 0.900 0.883 0.953 0.0869 0.931 0.809
#> SD:mclust 5 0.752 0.809 0.885 0.2032 0.758 0.436
#> CV:mclust 5 0.752 0.664 0.817 0.1008 0.874 0.627
#> MAD:mclust 5 0.868 0.840 0.931 0.2295 0.799 0.504
#> ATC:mclust 5 0.889 0.876 0.950 0.1664 0.827 0.558
#> SD:kmeans 5 0.677 0.699 0.806 0.0778 0.863 0.551
#> CV:kmeans 5 0.745 0.670 0.828 0.0892 0.893 0.656
#> MAD:kmeans 5 0.700 0.674 0.820 0.0768 0.891 0.625
#> ATC:kmeans 5 0.693 0.509 0.732 0.0590 0.894 0.640
#> SD:pam 5 0.597 0.499 0.752 0.0836 0.907 0.694
#> CV:pam 5 0.519 0.454 0.731 0.0775 0.873 0.606
#> MAD:pam 5 0.610 0.666 0.794 0.0679 0.943 0.796
#> ATC:pam 5 0.838 0.858 0.922 0.0638 0.928 0.762
#> SD:hclust 5 0.449 0.340 0.665 0.0905 0.976 0.928
#> CV:hclust 5 0.461 0.528 0.671 0.0971 0.784 0.386
#> MAD:hclust 5 0.517 0.511 0.675 0.0759 0.962 0.863
#> ATC:hclust 5 0.756 0.726 0.812 0.0557 0.920 0.737
get_stats(res_list, k = 6)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 6 0.694 0.592 0.773 0.0489 0.890 0.550
#> CV:NMF 6 0.679 0.547 0.741 0.0505 0.913 0.628
#> MAD:NMF 6 0.659 0.555 0.735 0.0469 0.899 0.576
#> ATC:NMF 6 0.768 0.671 0.850 0.0355 0.973 0.890
#> SD:skmeans 6 0.765 0.590 0.787 0.0527 0.903 0.582
#> CV:skmeans 6 0.668 0.521 0.705 0.0466 0.914 0.631
#> MAD:skmeans 6 0.700 0.542 0.737 0.0473 0.917 0.638
#> ATC:skmeans 6 0.875 0.861 0.932 0.0442 0.958 0.859
#> SD:mclust 6 0.721 0.626 0.804 0.0402 0.992 0.964
#> CV:mclust 6 0.707 0.567 0.755 0.0413 0.939 0.760
#> MAD:mclust 6 0.776 0.741 0.850 0.0389 0.982 0.921
#> ATC:mclust 6 0.850 0.849 0.924 0.0576 0.932 0.744
#> SD:kmeans 6 0.750 0.693 0.784 0.0499 0.914 0.644
#> CV:kmeans 6 0.770 0.698 0.822 0.0537 0.904 0.608
#> MAD:kmeans 6 0.754 0.681 0.802 0.0527 0.921 0.656
#> ATC:kmeans 6 0.755 0.686 0.772 0.0465 0.846 0.443
#> SD:pam 6 0.677 0.575 0.781 0.0422 0.891 0.602
#> CV:pam 6 0.593 0.541 0.747 0.0570 0.886 0.563
#> MAD:pam 6 0.655 0.650 0.785 0.0530 0.921 0.674
#> ATC:pam 6 0.838 0.739 0.871 0.0592 0.947 0.778
#> SD:hclust 6 0.540 0.567 0.697 0.0557 0.870 0.603
#> CV:hclust 6 0.585 0.507 0.680 0.0457 0.940 0.746
#> MAD:hclust 6 0.585 0.551 0.704 0.0389 0.939 0.762
#> ATC:hclust 6 0.789 0.743 0.876 0.0232 0.981 0.923
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 disease.state(p) tissue(p) other(p) k
#> SD:NMF 99 1.97e-05 1.50e-05 7.31e-07 2
#> CV:NMF 90 4.08e-07 4.56e-07 2.98e-06 2
#> MAD:NMF 96 2.05e-05 1.57e-05 3.00e-07 2
#> ATC:NMF 103 4.46e-01 5.56e-01 7.07e-01 2
#> SD:skmeans 97 7.96e-04 6.10e-05 2.11e-07 2
#> CV:skmeans 95 1.03e-03 6.48e-05 2.49e-07 2
#> MAD:skmeans 95 1.03e-03 3.96e-05 7.66e-07 2
#> ATC:skmeans 103 6.27e-01 7.00e-01 8.46e-01 2
#> SD:mclust 66 NA 3.93e-03 5.09e-04 2
#> CV:mclust 92 9.20e-13 3.91e-13 1.23e-09 2
#> MAD:mclust 70 NA 6.83e-03 1.87e-04 2
#> ATC:mclust 103 1.30e-08 3.82e-11 1.52e-06 2
#> SD:kmeans 96 9.06e-04 6.30e-05 2.95e-07 2
#> CV:kmeans 86 1.14e-03 1.73e-05 9.57e-07 2
#> MAD:kmeans 91 1.74e-03 6.86e-05 5.73e-07 2
#> ATC:kmeans 103 9.88e-01 9.19e-01 7.95e-01 2
#> SD:pam 98 1.67e-07 9.17e-08 5.91e-05 2
#> CV:pam 97 8.07e-09 5.07e-10 4.14e-07 2
#> MAD:pam 94 4.12e-06 1.42e-06 1.45e-03 2
#> ATC:pam 101 6.44e-01 7.28e-01 7.85e-01 2
#> SD:hclust 75 1.22e-02 2.31e-03 3.80e-05 2
#> CV:hclust 64 NA 2.60e-02 7.18e-02 2
#> MAD:hclust 15 2.17e-03 2.17e-03 5.53e-04 2
#> ATC:hclust 101 2.98e-01 3.55e-01 3.52e-01 2
test_to_known_factors(res_list, k = 3)
#> n disease.state(p) tissue(p) other(p) k
#> SD:NMF 75 3.36e-08 4.19e-08 3.01e-07 3
#> CV:NMF 90 1.32e-10 2.45e-11 5.10e-10 3
#> MAD:NMF 77 5.87e-09 1.01e-08 5.73e-08 3
#> ATC:NMF 98 6.35e-14 8.69e-14 8.14e-08 3
#> SD:skmeans 100 1.23e-07 5.81e-09 4.48e-08 3
#> CV:skmeans 97 4.70e-08 1.50e-09 1.74e-07 3
#> MAD:skmeans 98 5.99e-09 4.25e-10 1.99e-08 3
#> ATC:skmeans 101 9.80e-15 6.60e-14 3.83e-09 3
#> SD:mclust 99 4.15e-16 5.02e-18 1.37e-13 3
#> CV:mclust 94 1.85e-16 9.80e-18 6.87e-14 3
#> MAD:mclust 99 2.42e-20 1.26e-21 3.30e-16 3
#> ATC:mclust 102 2.62e-07 2.37e-11 3.96e-05 3
#> SD:kmeans 76 5.21e-10 1.54e-10 1.26e-09 3
#> CV:kmeans 89 1.32e-12 4.99e-14 2.60e-11 3
#> MAD:kmeans 89 1.39e-15 2.08e-16 1.46e-14 3
#> ATC:kmeans 103 1.15e-03 6.16e-03 1.82e-01 3
#> SD:pam 68 6.61e-12 4.31e-12 3.74e-07 3
#> CV:pam 52 2.39e-08 1.24e-09 5.65e-05 3
#> MAD:pam 86 4.23e-10 1.42e-11 5.49e-10 3
#> ATC:pam 101 7.40e-02 1.96e-01 4.52e-01 3
#> SD:hclust 72 7.78e-03 1.75e-04 7.26e-04 3
#> CV:hclust 47 NA NA 4.01e-01 3
#> MAD:hclust 39 NA 1.78e-04 1.47e-01 3
#> ATC:hclust 101 1.60e-04 3.58e-04 5.69e-02 3
test_to_known_factors(res_list, k = 4)
#> n disease.state(p) tissue(p) other(p) k
#> SD:NMF 90 7.26e-10 2.23e-09 1.03e-07 4
#> CV:NMF 82 1.86e-09 6.08e-09 1.07e-05 4
#> MAD:NMF 91 1.26e-10 2.48e-10 4.65e-07 4
#> ATC:NMF 96 4.60e-17 5.43e-20 3.74e-10 4
#> SD:skmeans 86 3.05e-14 3.60e-15 1.87e-12 4
#> CV:skmeans 86 3.05e-14 1.78e-15 5.96e-12 4
#> MAD:skmeans 80 3.30e-13 2.34e-14 8.63e-11 4
#> ATC:skmeans 102 9.96e-18 5.60e-20 4.64e-11 4
#> SD:mclust 89 3.59e-19 9.26e-19 9.81e-13 4
#> CV:mclust 82 4.39e-16 2.28e-17 5.58e-12 4
#> MAD:mclust 95 1.85e-20 3.77e-20 4.27e-14 4
#> ATC:mclust 99 1.86e-19 1.61e-22 9.29e-12 4
#> SD:kmeans 79 3.64e-11 2.36e-12 4.37e-08 4
#> CV:kmeans 96 1.13e-20 2.74e-22 1.24e-15 4
#> MAD:kmeans 76 1.27e-13 1.22e-15 2.23e-09 4
#> ATC:kmeans 67 1.44e-03 3.95e-03 1.02e-01 4
#> SD:pam 84 4.27e-15 1.20e-17 8.35e-11 4
#> CV:pam 38 1.55e-04 5.56e-05 1.20e-02 4
#> MAD:pam 89 5.11e-16 1.04e-18 4.36e-13 4
#> ATC:pam 81 NA 5.92e-01 7.25e-01 4
#> SD:hclust 84 2.91e-03 6.61e-05 2.38e-03 4
#> CV:hclust 25 NA 1.21e-01 3.86e-01 4
#> MAD:hclust 57 3.05e-09 5.03e-11 3.43e-07 4
#> ATC:hclust 87 1.79e-13 3.95e-12 2.20e-06 4
test_to_known_factors(res_list, k = 5)
#> n disease.state(p) tissue(p) other(p) k
#> SD:NMF 84 2.27e-14 5.88e-14 2.01e-08 5
#> CV:NMF 85 6.23e-16 1.02e-15 1.07e-09 5
#> MAD:NMF 74 1.49e-12 9.01e-13 3.83e-08 5
#> ATC:NMF 92 1.27e-15 2.21e-17 1.99e-07 5
#> SD:skmeans 87 1.07e-13 9.29e-15 8.86e-08 5
#> CV:skmeans 78 2.79e-13 1.12e-14 2.59e-07 5
#> MAD:skmeans 84 2.27e-14 2.37e-15 3.36e-08 5
#> ATC:skmeans 99 4.35e-15 7.05e-17 8.12e-08 5
#> SD:mclust 99 1.44e-12 2.47e-13 1.14e-08 5
#> CV:mclust 85 2.56e-12 1.42e-12 3.11e-09 5
#> MAD:mclust 96 1.49e-16 7.09e-17 1.00e-11 5
#> ATC:mclust 96 4.34e-18 2.56e-21 3.37e-10 5
#> SD:kmeans 85 1.52e-17 6.13e-18 1.87e-11 5
#> CV:kmeans 83 4.03e-17 6.09e-18 1.73e-09 5
#> MAD:kmeans 79 9.30e-15 2.99e-16 9.24e-09 5
#> ATC:kmeans 53 4.31e-01 6.96e-01 6.20e-01 5
#> SD:pam 51 1.10e-10 2.23e-10 2.64e-05 5
#> CV:pam 48 6.91e-06 5.60e-07 4.31e-04 5
#> MAD:pam 84 2.27e-14 9.12e-16 2.33e-09 5
#> ATC:pam 101 2.30e-17 3.45e-15 1.29e-08 5
#> SD:hclust 42 NA 1.14e-02 1.49e-01 5
#> CV:hclust 60 1.13e-10 7.55e-12 6.42e-06 5
#> MAD:hclust 56 6.20e-10 3.65e-13 5.00e-09 5
#> ATC:hclust 84 2.47e-17 1.73e-15 1.00e-08 5
test_to_known_factors(res_list, k = 6)
#> n disease.state(p) tissue(p) other(p) k
#> SD:NMF 74 3.90e-13 2.49e-13 1.43e-09 6
#> CV:NMF 58 3.15e-11 3.68e-12 2.82e-06 6
#> MAD:NMF 66 6.95e-13 1.08e-12 1.76e-07 6
#> ATC:NMF 72 1.59e-15 9.18e-18 5.34e-09 6
#> SD:skmeans 62 2.21e-10 1.48e-10 8.94e-06 6
#> CV:skmeans 55 4.07e-09 5.32e-11 6.62e-05 6
#> MAD:skmeans 66 4.18e-11 4.68e-12 7.79e-06 6
#> ATC:skmeans 98 1.22e-15 4.09e-17 3.28e-08 6
#> SD:mclust 78 5.17e-11 6.06e-11 3.44e-09 6
#> CV:mclust 75 1.99e-15 4.68e-15 2.25e-10 6
#> MAD:mclust 93 1.57e-18 1.66e-18 4.09e-16 6
#> ATC:mclust 95 3.42e-17 2.96e-19 7.66e-09 6
#> SD:kmeans 81 5.18e-16 8.57e-20 3.80e-11 6
#> CV:kmeans 79 1.36e-15 2.24e-17 1.17e-10 6
#> MAD:kmeans 85 7.53e-17 5.71e-19 1.56e-11 6
#> ATC:kmeans 86 7.22e-14 1.51e-11 2.30e-06 6
#> SD:pam 64 7.85e-12 1.27e-15 4.77e-10 6
#> CV:pam 66 5.18e-08 9.66e-11 5.33e-05 6
#> MAD:pam 83 1.55e-13 3.27e-15 1.10e-08 6
#> ATC:pam 90 4.16e-16 1.65e-15 1.83e-08 6
#> SD:hclust 62 8.58e-10 5.28e-13 1.09e-06 6
#> CV:hclust 58 2.65e-10 1.19e-11 5.26e-06 6
#> MAD:hclust 67 1.11e-10 1.34e-14 3.19e-07 6
#> ATC:hclust 81 1.83e-01 2.56e-01 6.02e-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 103 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 0.164 0.629 0.789 0.4257 0.530 0.530
#> 3 3 0.308 0.581 0.766 0.3731 0.725 0.551
#> 4 4 0.365 0.591 0.694 0.1506 0.869 0.704
#> 5 5 0.449 0.340 0.665 0.0905 0.976 0.928
#> 6 6 0.540 0.567 0.697 0.0557 0.870 0.603
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
#> GSM425907 2 0.1414 0.7575 0.020 0.980
#> GSM425908 2 0.1843 0.7539 0.028 0.972
#> GSM425909 2 0.8016 0.6282 0.244 0.756
#> GSM425910 1 0.9998 0.0640 0.508 0.492
#> GSM425911 2 0.8861 0.5243 0.304 0.696
#> GSM425912 2 0.9909 0.1667 0.444 0.556
#> GSM425913 2 0.2778 0.7766 0.048 0.952
#> GSM425914 2 0.9129 0.4882 0.328 0.672
#> GSM425915 2 0.9460 0.4405 0.364 0.636
#> GSM425874 1 0.9710 0.3759 0.600 0.400
#> GSM425875 2 0.9358 0.4717 0.352 0.648
#> GSM425876 1 0.9358 0.5311 0.648 0.352
#> GSM425877 1 0.6801 0.7233 0.820 0.180
#> GSM425878 1 0.8016 0.7259 0.756 0.244
#> GSM425879 2 0.1184 0.7659 0.016 0.984
#> GSM425880 2 0.9358 0.4717 0.352 0.648
#> GSM425881 2 0.9608 0.3297 0.384 0.616
#> GSM425882 2 0.2948 0.7746 0.052 0.948
#> GSM425883 1 0.7883 0.7260 0.764 0.236
#> GSM425884 1 0.7056 0.7279 0.808 0.192
#> GSM425885 2 0.8144 0.4580 0.252 0.748
#> GSM425848 1 0.7453 0.7313 0.788 0.212
#> GSM425849 1 0.8016 0.7264 0.756 0.244
#> GSM425850 1 0.8499 0.6748 0.724 0.276
#> GSM425851 1 0.6148 0.7174 0.848 0.152
#> GSM425852 2 0.9358 0.4717 0.352 0.648
#> GSM425893 2 0.5842 0.7333 0.140 0.860
#> GSM425894 2 0.2423 0.7695 0.040 0.960
#> GSM425895 2 0.3114 0.7751 0.056 0.944
#> GSM425896 2 0.1414 0.7575 0.020 0.980
#> GSM425897 2 0.0938 0.7684 0.012 0.988
#> GSM425898 2 0.2423 0.7695 0.040 0.960
#> GSM425899 2 0.5519 0.7472 0.128 0.872
#> GSM425900 2 0.4022 0.7731 0.080 0.920
#> GSM425901 2 0.8016 0.6282 0.244 0.756
#> GSM425902 1 0.9686 0.3818 0.604 0.396
#> GSM425903 2 0.9460 0.4405 0.364 0.636
#> GSM425904 2 0.9358 0.4717 0.352 0.648
#> GSM425905 2 0.1633 0.7609 0.024 0.976
#> GSM425906 2 0.3879 0.7731 0.076 0.924
#> GSM425863 1 0.7674 0.7294 0.776 0.224
#> GSM425864 2 0.0938 0.7633 0.012 0.988
#> GSM425865 2 0.1184 0.7659 0.016 0.984
#> GSM425866 2 0.9358 0.4717 0.352 0.648
#> GSM425867 2 0.9661 0.3863 0.392 0.608
#> GSM425868 2 0.6048 0.6420 0.148 0.852
#> GSM425869 2 0.2236 0.7551 0.036 0.964
#> GSM425870 2 0.8763 0.5365 0.296 0.704
#> GSM425871 1 0.8386 0.7038 0.732 0.268
#> GSM425872 2 0.2603 0.7687 0.044 0.956
#> GSM425873 1 0.8909 0.6150 0.692 0.308
#> GSM425843 1 0.6801 0.7233 0.820 0.180
#> GSM425844 1 0.8386 0.7038 0.732 0.268
#> GSM425845 2 0.9775 0.3461 0.412 0.588
#> GSM425846 2 0.5408 0.7460 0.124 0.876
#> GSM425847 1 0.9998 0.0844 0.508 0.492
#> GSM425886 2 0.7139 0.6857 0.196 0.804
#> GSM425887 2 0.3274 0.7750 0.060 0.940
#> GSM425888 2 0.9635 0.3255 0.388 0.612
#> GSM425889 1 0.7674 0.7264 0.776 0.224
#> GSM425890 1 0.9248 0.5846 0.660 0.340
#> GSM425891 2 0.2423 0.7762 0.040 0.960
#> GSM425892 2 0.4815 0.7021 0.104 0.896
#> GSM425853 1 0.9963 0.1765 0.536 0.464
#> GSM425854 2 0.2603 0.7758 0.044 0.956
#> GSM425855 1 0.7219 0.7228 0.800 0.200
#> GSM425856 2 0.9358 0.4717 0.352 0.648
#> GSM425857 2 0.3733 0.7611 0.072 0.928
#> GSM425858 2 0.3733 0.7715 0.072 0.928
#> GSM425859 2 0.2043 0.7594 0.032 0.968
#> GSM425860 2 0.9977 0.1037 0.472 0.528
#> GSM425861 2 0.9635 0.3255 0.388 0.612
#> GSM425862 1 0.7674 0.7264 0.776 0.224
#> GSM425837 1 0.6712 0.7284 0.824 0.176
#> GSM425838 1 0.9661 0.3842 0.608 0.392
#> GSM425839 2 0.1843 0.7621 0.028 0.972
#> GSM425840 1 0.7219 0.7228 0.800 0.200
#> GSM425841 1 0.9686 0.3816 0.604 0.396
#> GSM425842 1 0.8608 0.6512 0.716 0.284
#> GSM425917 2 0.3733 0.7771 0.072 0.928
#> GSM425922 1 0.9661 0.3838 0.608 0.392
#> GSM425919 1 0.6148 0.7174 0.848 0.152
#> GSM425920 1 0.7602 0.7153 0.780 0.220
#> GSM425923 1 0.7528 0.7216 0.784 0.216
#> GSM425916 1 0.6148 0.7150 0.848 0.152
#> GSM425918 1 0.8144 0.7019 0.748 0.252
#> GSM425921 1 0.9661 0.3838 0.608 0.392
#> GSM425925 1 0.9661 0.3838 0.608 0.392
#> GSM425926 1 0.9661 0.3838 0.608 0.392
#> GSM425927 1 0.7602 0.7153 0.780 0.220
#> GSM425924 2 0.4022 0.7739 0.080 0.920
#> GSM425928 2 0.3584 0.7786 0.068 0.932
#> GSM425929 2 0.3584 0.7786 0.068 0.932
#> GSM425930 2 0.3584 0.7786 0.068 0.932
#> GSM425931 2 0.3584 0.7786 0.068 0.932
#> GSM425932 2 0.3584 0.7786 0.068 0.932
#> GSM425933 2 0.3584 0.7786 0.068 0.932
#> GSM425934 2 0.3584 0.7786 0.068 0.932
#> GSM425935 2 0.3584 0.7786 0.068 0.932
#> GSM425936 2 0.3584 0.7786 0.068 0.932
#> GSM425937 2 0.3584 0.7786 0.068 0.932
#> GSM425938 2 0.3584 0.7786 0.068 0.932
#> GSM425939 2 0.3584 0.7786 0.068 0.932
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.1163 0.7902 0.000 0.972 0.028
#> GSM425908 2 0.1529 0.7897 0.000 0.960 0.040
#> GSM425909 2 0.7184 0.3044 0.472 0.504 0.024
#> GSM425910 1 0.8038 0.5110 0.620 0.280 0.100
#> GSM425911 2 0.6235 0.1842 0.436 0.564 0.000
#> GSM425912 1 0.6608 0.3807 0.628 0.356 0.016
#> GSM425913 2 0.4399 0.7823 0.092 0.864 0.044
#> GSM425914 2 0.6302 0.0381 0.480 0.520 0.000
#> GSM425915 1 0.6062 0.1092 0.616 0.384 0.000
#> GSM425874 3 0.0747 0.8984 0.000 0.016 0.984
#> GSM425875 1 0.6359 0.0403 0.592 0.404 0.004
#> GSM425876 1 0.6250 0.5782 0.776 0.120 0.104
#> GSM425877 1 0.5016 0.5590 0.760 0.000 0.240
#> GSM425878 1 0.6445 0.5254 0.672 0.020 0.308
#> GSM425879 2 0.1453 0.7939 0.008 0.968 0.024
#> GSM425880 1 0.6359 0.0403 0.592 0.404 0.004
#> GSM425881 1 0.7546 0.2501 0.560 0.396 0.044
#> GSM425882 2 0.4179 0.7909 0.072 0.876 0.052
#> GSM425883 1 0.6978 0.5237 0.632 0.032 0.336
#> GSM425884 1 0.5244 0.5537 0.756 0.004 0.240
#> GSM425885 2 0.7013 0.4134 0.028 0.608 0.364
#> GSM425848 1 0.6113 0.5400 0.688 0.012 0.300
#> GSM425849 1 0.6369 0.5213 0.668 0.016 0.316
#> GSM425850 1 0.6254 0.5835 0.756 0.056 0.188
#> GSM425851 1 0.5621 0.4942 0.692 0.000 0.308
#> GSM425852 1 0.6359 0.0403 0.592 0.404 0.004
#> GSM425893 2 0.4968 0.7155 0.188 0.800 0.012
#> GSM425894 2 0.4830 0.7761 0.068 0.848 0.084
#> GSM425895 2 0.5207 0.7627 0.124 0.824 0.052
#> GSM425896 2 0.1774 0.7916 0.016 0.960 0.024
#> GSM425897 2 0.0747 0.7938 0.016 0.984 0.000
#> GSM425898 2 0.4830 0.7761 0.068 0.848 0.084
#> GSM425899 2 0.7666 0.6513 0.148 0.684 0.168
#> GSM425900 2 0.5514 0.7449 0.156 0.800 0.044
#> GSM425901 2 0.7184 0.3044 0.472 0.504 0.024
#> GSM425902 3 0.2050 0.8824 0.020 0.028 0.952
#> GSM425903 1 0.6062 0.1092 0.616 0.384 0.000
#> GSM425904 1 0.6359 0.0403 0.592 0.404 0.004
#> GSM425905 2 0.1031 0.7911 0.000 0.976 0.024
#> GSM425906 2 0.5743 0.7293 0.172 0.784 0.044
#> GSM425863 1 0.6673 0.5132 0.636 0.020 0.344
#> GSM425864 2 0.1585 0.7933 0.008 0.964 0.028
#> GSM425865 2 0.2050 0.7949 0.020 0.952 0.028
#> GSM425866 1 0.6359 0.0403 0.592 0.404 0.004
#> GSM425867 1 0.5722 0.3141 0.704 0.292 0.004
#> GSM425868 2 0.5295 0.7132 0.036 0.808 0.156
#> GSM425869 2 0.3031 0.7835 0.012 0.912 0.076
#> GSM425870 2 0.6192 0.2321 0.420 0.580 0.000
#> GSM425871 1 0.6148 0.5675 0.728 0.028 0.244
#> GSM425872 2 0.5093 0.7705 0.076 0.836 0.088
#> GSM425873 1 0.5764 0.5836 0.800 0.076 0.124
#> GSM425843 1 0.5016 0.5590 0.760 0.000 0.240
#> GSM425844 1 0.6148 0.5675 0.728 0.028 0.244
#> GSM425845 1 0.5443 0.3690 0.736 0.260 0.004
#> GSM425846 2 0.7245 0.6726 0.168 0.712 0.120
#> GSM425847 1 0.7128 0.4917 0.664 0.284 0.052
#> GSM425886 2 0.7102 0.4178 0.420 0.556 0.024
#> GSM425887 2 0.5497 0.7495 0.148 0.804 0.048
#> GSM425888 1 0.8028 0.2808 0.560 0.368 0.072
#> GSM425889 1 0.6896 0.4540 0.588 0.020 0.392
#> GSM425890 3 0.9399 -0.1260 0.372 0.176 0.452
#> GSM425891 2 0.4859 0.7730 0.116 0.840 0.044
#> GSM425892 2 0.4172 0.7323 0.004 0.840 0.156
#> GSM425853 1 0.8542 0.5254 0.608 0.220 0.172
#> GSM425854 2 0.4087 0.7917 0.068 0.880 0.052
#> GSM425855 1 0.5775 0.5623 0.728 0.012 0.260
#> GSM425856 1 0.6359 0.0403 0.592 0.404 0.004
#> GSM425857 2 0.6535 0.6496 0.220 0.728 0.052
#> GSM425858 2 0.5734 0.7345 0.164 0.788 0.048
#> GSM425859 2 0.3272 0.7843 0.016 0.904 0.080
#> GSM425860 1 0.7153 0.4544 0.652 0.300 0.048
#> GSM425861 1 0.8028 0.2808 0.560 0.368 0.072
#> GSM425862 1 0.6896 0.4540 0.588 0.020 0.392
#> GSM425837 1 0.5553 0.5500 0.724 0.004 0.272
#> GSM425838 3 0.2434 0.8796 0.024 0.036 0.940
#> GSM425839 2 0.3550 0.7855 0.024 0.896 0.080
#> GSM425840 1 0.5775 0.5623 0.728 0.012 0.260
#> GSM425841 3 0.1315 0.8976 0.008 0.020 0.972
#> GSM425842 1 0.5659 0.5845 0.796 0.052 0.152
#> GSM425917 2 0.4172 0.7785 0.156 0.840 0.004
#> GSM425922 3 0.0000 0.9013 0.000 0.000 1.000
#> GSM425919 1 0.5621 0.4942 0.692 0.000 0.308
#> GSM425920 1 0.5597 0.5768 0.764 0.020 0.216
#> GSM425923 1 0.6189 0.4393 0.632 0.004 0.364
#> GSM425916 1 0.5678 0.4797 0.684 0.000 0.316
#> GSM425918 1 0.7555 0.3215 0.520 0.040 0.440
#> GSM425921 3 0.0000 0.9013 0.000 0.000 1.000
#> GSM425925 3 0.0000 0.9013 0.000 0.000 1.000
#> GSM425926 3 0.0000 0.9013 0.000 0.000 1.000
#> GSM425927 1 0.5597 0.5768 0.764 0.020 0.216
#> GSM425924 2 0.4293 0.7755 0.164 0.832 0.004
#> GSM425928 2 0.3941 0.7797 0.156 0.844 0.000
#> GSM425929 2 0.3941 0.7797 0.156 0.844 0.000
#> GSM425930 2 0.3941 0.7797 0.156 0.844 0.000
#> GSM425931 2 0.3941 0.7797 0.156 0.844 0.000
#> GSM425932 2 0.3941 0.7797 0.156 0.844 0.000
#> GSM425933 2 0.3941 0.7797 0.156 0.844 0.000
#> GSM425934 2 0.3941 0.7797 0.156 0.844 0.000
#> GSM425935 2 0.3941 0.7797 0.156 0.844 0.000
#> GSM425936 2 0.3941 0.7797 0.156 0.844 0.000
#> GSM425937 2 0.3941 0.7797 0.156 0.844 0.000
#> GSM425938 2 0.3941 0.7797 0.156 0.844 0.000
#> GSM425939 2 0.3941 0.7797 0.156 0.844 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.267 0.7055 0.000 0.892 0.100 0.008
#> GSM425908 2 0.304 0.7030 0.000 0.880 0.100 0.020
#> GSM425909 3 0.636 0.7288 0.180 0.164 0.656 0.000
#> GSM425910 1 0.657 0.2400 0.632 0.164 0.204 0.000
#> GSM425911 2 0.762 -0.0764 0.356 0.436 0.208 0.000
#> GSM425912 1 0.690 0.2608 0.552 0.336 0.108 0.004
#> GSM425913 2 0.350 0.6839 0.052 0.872 0.072 0.004
#> GSM425914 1 0.765 -0.1238 0.400 0.392 0.208 0.000
#> GSM425915 3 0.648 0.7706 0.324 0.092 0.584 0.000
#> GSM425874 4 0.230 0.9549 0.028 0.028 0.012 0.932
#> GSM425875 3 0.611 0.8055 0.284 0.080 0.636 0.000
#> GSM425876 1 0.455 0.5349 0.804 0.104 0.092 0.000
#> GSM425877 1 0.292 0.6299 0.896 0.000 0.044 0.060
#> GSM425878 1 0.534 0.6269 0.768 0.032 0.044 0.156
#> GSM425879 2 0.201 0.7102 0.000 0.920 0.080 0.000
#> GSM425880 3 0.611 0.8055 0.284 0.080 0.636 0.000
#> GSM425881 1 0.708 0.2071 0.476 0.412 0.108 0.004
#> GSM425882 2 0.341 0.7027 0.060 0.884 0.040 0.016
#> GSM425883 1 0.612 0.5696 0.656 0.020 0.044 0.280
#> GSM425884 1 0.303 0.6147 0.888 0.004 0.088 0.020
#> GSM425885 2 0.848 0.1894 0.032 0.428 0.236 0.304
#> GSM425848 1 0.491 0.6220 0.788 0.012 0.056 0.144
#> GSM425849 1 0.534 0.6256 0.764 0.028 0.044 0.164
#> GSM425850 1 0.406 0.6122 0.856 0.052 0.064 0.028
#> GSM425851 1 0.579 0.4700 0.680 0.000 0.244 0.076
#> GSM425852 3 0.617 0.8041 0.284 0.084 0.632 0.000
#> GSM425893 2 0.563 0.5935 0.140 0.724 0.136 0.000
#> GSM425894 2 0.369 0.6785 0.024 0.872 0.068 0.036
#> GSM425895 2 0.423 0.6505 0.080 0.836 0.076 0.008
#> GSM425896 2 0.277 0.7039 0.000 0.880 0.116 0.004
#> GSM425897 2 0.294 0.7061 0.004 0.868 0.128 0.000
#> GSM425898 2 0.369 0.6785 0.024 0.872 0.068 0.036
#> GSM425899 2 0.693 0.5310 0.120 0.688 0.084 0.108
#> GSM425900 2 0.453 0.6301 0.112 0.804 0.084 0.000
#> GSM425901 3 0.636 0.7288 0.180 0.164 0.656 0.000
#> GSM425902 4 0.330 0.9404 0.048 0.028 0.032 0.892
#> GSM425903 3 0.648 0.7706 0.324 0.092 0.584 0.000
#> GSM425904 3 0.611 0.8055 0.284 0.080 0.636 0.000
#> GSM425905 2 0.233 0.7085 0.000 0.908 0.088 0.004
#> GSM425906 2 0.481 0.6088 0.132 0.784 0.084 0.000
#> GSM425863 1 0.577 0.5694 0.668 0.012 0.036 0.284
#> GSM425864 2 0.201 0.7095 0.000 0.920 0.080 0.000
#> GSM425865 2 0.233 0.7106 0.004 0.908 0.088 0.000
#> GSM425866 3 0.614 0.8035 0.288 0.080 0.632 0.000
#> GSM425867 3 0.652 0.5673 0.412 0.076 0.512 0.000
#> GSM425868 2 0.617 0.6301 0.036 0.728 0.112 0.124
#> GSM425869 2 0.267 0.6989 0.004 0.912 0.052 0.032
#> GSM425870 2 0.763 -0.0617 0.340 0.444 0.216 0.000
#> GSM425871 1 0.419 0.6309 0.848 0.028 0.048 0.076
#> GSM425872 2 0.421 0.6666 0.040 0.848 0.076 0.036
#> GSM425873 1 0.380 0.5807 0.856 0.068 0.072 0.004
#> GSM425843 1 0.292 0.6299 0.896 0.000 0.044 0.060
#> GSM425844 1 0.419 0.6309 0.848 0.028 0.048 0.076
#> GSM425845 3 0.650 0.4697 0.444 0.072 0.484 0.000
#> GSM425846 2 0.641 0.5556 0.132 0.720 0.080 0.068
#> GSM425847 1 0.666 0.3561 0.616 0.276 0.100 0.008
#> GSM425886 3 0.659 0.6220 0.148 0.228 0.624 0.000
#> GSM425887 2 0.447 0.6339 0.100 0.816 0.080 0.004
#> GSM425888 1 0.773 0.2237 0.476 0.384 0.108 0.032
#> GSM425889 1 0.616 0.5071 0.616 0.012 0.044 0.328
#> GSM425890 1 0.907 0.1313 0.412 0.152 0.108 0.328
#> GSM425891 2 0.397 0.6606 0.076 0.840 0.084 0.000
#> GSM425892 2 0.557 0.6453 0.012 0.752 0.120 0.116
#> GSM425853 1 0.780 0.1018 0.540 0.080 0.312 0.068
#> GSM425854 2 0.339 0.6968 0.052 0.884 0.052 0.012
#> GSM425855 1 0.349 0.6304 0.864 0.000 0.044 0.092
#> GSM425856 3 0.611 0.8055 0.284 0.080 0.636 0.000
#> GSM425857 3 0.539 0.1149 0.000 0.368 0.612 0.020
#> GSM425858 2 0.471 0.6174 0.116 0.800 0.080 0.004
#> GSM425859 2 0.250 0.6984 0.004 0.920 0.044 0.032
#> GSM425860 1 0.708 0.0527 0.564 0.184 0.252 0.000
#> GSM425861 1 0.773 0.2237 0.476 0.384 0.108 0.032
#> GSM425862 1 0.616 0.5071 0.616 0.012 0.044 0.328
#> GSM425837 1 0.346 0.6364 0.864 0.000 0.040 0.096
#> GSM425838 4 0.476 0.8717 0.112 0.028 0.048 0.812
#> GSM425839 2 0.273 0.6985 0.008 0.912 0.048 0.032
#> GSM425840 1 0.349 0.6304 0.864 0.000 0.044 0.092
#> GSM425841 4 0.273 0.9541 0.036 0.028 0.020 0.916
#> GSM425842 1 0.417 0.6084 0.852 0.044 0.064 0.040
#> GSM425917 2 0.573 0.5989 0.040 0.648 0.308 0.004
#> GSM425922 4 0.121 0.9600 0.032 0.004 0.000 0.964
#> GSM425919 1 0.579 0.4700 0.680 0.000 0.244 0.076
#> GSM425920 1 0.303 0.6234 0.900 0.012 0.056 0.032
#> GSM425923 1 0.553 0.5702 0.728 0.000 0.104 0.168
#> GSM425916 1 0.588 0.4593 0.676 0.000 0.240 0.084
#> GSM425918 1 0.734 0.4043 0.556 0.020 0.116 0.308
#> GSM425921 4 0.111 0.9602 0.028 0.004 0.000 0.968
#> GSM425925 4 0.126 0.9608 0.028 0.008 0.000 0.964
#> GSM425926 4 0.136 0.9609 0.032 0.008 0.000 0.960
#> GSM425927 1 0.303 0.6234 0.900 0.012 0.056 0.032
#> GSM425924 2 0.589 0.5919 0.048 0.640 0.308 0.004
#> GSM425928 2 0.558 0.5988 0.040 0.648 0.312 0.000
#> GSM425929 2 0.558 0.5988 0.040 0.648 0.312 0.000
#> GSM425930 2 0.558 0.5988 0.040 0.648 0.312 0.000
#> GSM425931 2 0.558 0.5988 0.040 0.648 0.312 0.000
#> GSM425932 2 0.558 0.5988 0.040 0.648 0.312 0.000
#> GSM425933 2 0.558 0.5988 0.040 0.648 0.312 0.000
#> GSM425934 2 0.558 0.5988 0.040 0.648 0.312 0.000
#> GSM425935 2 0.558 0.5988 0.040 0.648 0.312 0.000
#> GSM425936 2 0.558 0.5988 0.040 0.648 0.312 0.000
#> GSM425937 2 0.558 0.5988 0.040 0.648 0.312 0.000
#> GSM425938 2 0.558 0.5988 0.040 0.648 0.312 0.000
#> GSM425939 2 0.558 0.5988 0.040 0.648 0.312 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM425907 2 0.376 0.247878 0.000 0.772 0.208 0.000 0.020
#> GSM425908 2 0.398 0.243896 0.000 0.760 0.216 0.004 0.020
#> GSM425909 5 0.462 0.734173 0.136 0.096 0.008 0.000 0.760
#> GSM425910 1 0.713 0.240813 0.568 0.116 0.124 0.000 0.192
#> GSM425911 2 0.830 -0.105517 0.300 0.352 0.160 0.000 0.188
#> GSM425912 1 0.718 0.301926 0.504 0.172 0.272 0.000 0.052
#> GSM425913 2 0.606 -0.519093 0.032 0.524 0.396 0.004 0.044
#> GSM425914 1 0.825 -0.048489 0.348 0.316 0.148 0.000 0.188
#> GSM425915 5 0.454 0.781148 0.264 0.020 0.012 0.000 0.704
#> GSM425874 4 0.325 0.919148 0.028 0.000 0.072 0.868 0.032
#> GSM425875 5 0.355 0.811532 0.236 0.000 0.004 0.000 0.760
#> GSM425876 1 0.508 0.516762 0.748 0.084 0.128 0.000 0.040
#> GSM425877 1 0.421 0.585303 0.824 0.020 0.084 0.052 0.020
#> GSM425878 1 0.486 0.591554 0.764 0.004 0.100 0.112 0.020
#> GSM425879 2 0.400 0.208175 0.000 0.740 0.240 0.000 0.020
#> GSM425880 5 0.355 0.811532 0.236 0.000 0.004 0.000 0.760
#> GSM425881 1 0.732 0.020089 0.424 0.180 0.352 0.000 0.044
#> GSM425882 2 0.554 -0.153121 0.048 0.624 0.308 0.004 0.016
#> GSM425883 1 0.643 0.529476 0.612 0.008 0.112 0.236 0.032
#> GSM425884 1 0.419 0.575292 0.816 0.016 0.104 0.012 0.052
#> GSM425885 2 0.883 0.059531 0.024 0.356 0.148 0.236 0.236
#> GSM425848 1 0.508 0.581197 0.760 0.008 0.096 0.104 0.032
#> GSM425849 1 0.484 0.590015 0.756 0.000 0.104 0.120 0.020
#> GSM425850 1 0.445 0.576634 0.800 0.028 0.124 0.020 0.028
#> GSM425851 1 0.784 0.221570 0.448 0.044 0.320 0.032 0.156
#> GSM425852 5 0.371 0.810995 0.236 0.004 0.004 0.000 0.756
#> GSM425893 2 0.655 0.023601 0.120 0.628 0.168 0.000 0.084
#> GSM425894 2 0.591 -0.529870 0.008 0.496 0.436 0.016 0.044
#> GSM425895 2 0.618 -0.594051 0.048 0.520 0.392 0.004 0.036
#> GSM425896 2 0.406 0.262052 0.000 0.764 0.196 0.000 0.040
#> GSM425897 2 0.366 0.302643 0.000 0.804 0.160 0.000 0.036
#> GSM425898 2 0.591 -0.529870 0.008 0.496 0.436 0.016 0.044
#> GSM425899 3 0.775 0.783236 0.096 0.340 0.464 0.048 0.052
#> GSM425900 2 0.646 -0.752777 0.072 0.452 0.436 0.000 0.040
#> GSM425901 5 0.462 0.734173 0.136 0.096 0.008 0.000 0.760
#> GSM425902 4 0.395 0.896607 0.036 0.000 0.088 0.828 0.048
#> GSM425903 5 0.454 0.781148 0.264 0.020 0.012 0.000 0.704
#> GSM425904 5 0.355 0.811532 0.236 0.000 0.004 0.000 0.760
#> GSM425905 2 0.394 0.214967 0.000 0.748 0.232 0.000 0.020
#> GSM425906 3 0.667 0.693141 0.092 0.428 0.440 0.000 0.040
#> GSM425863 1 0.613 0.527212 0.628 0.004 0.100 0.240 0.028
#> GSM425864 2 0.385 0.220981 0.000 0.752 0.232 0.000 0.016
#> GSM425865 2 0.410 0.212840 0.004 0.744 0.232 0.000 0.020
#> GSM425866 5 0.364 0.807512 0.248 0.000 0.004 0.000 0.748
#> GSM425867 5 0.618 0.584778 0.348 0.052 0.048 0.000 0.552
#> GSM425868 2 0.695 0.102097 0.028 0.592 0.236 0.100 0.044
#> GSM425869 2 0.523 -0.294781 0.000 0.568 0.392 0.012 0.028
#> GSM425870 2 0.831 -0.098066 0.288 0.356 0.156 0.000 0.200
#> GSM425871 1 0.412 0.593958 0.804 0.000 0.128 0.048 0.020
#> GSM425872 2 0.602 -0.608014 0.012 0.468 0.460 0.016 0.044
#> GSM425873 1 0.425 0.551865 0.816 0.052 0.088 0.004 0.040
#> GSM425843 1 0.421 0.585303 0.824 0.020 0.084 0.052 0.020
#> GSM425844 1 0.412 0.593958 0.804 0.000 0.128 0.048 0.020
#> GSM425845 5 0.642 0.495924 0.376 0.060 0.052 0.000 0.512
#> GSM425846 3 0.732 0.820184 0.104 0.368 0.464 0.024 0.040
#> GSM425847 1 0.663 0.387483 0.572 0.116 0.264 0.000 0.048
#> GSM425886 5 0.545 0.664519 0.108 0.176 0.020 0.000 0.696
#> GSM425887 2 0.631 -0.640673 0.068 0.504 0.392 0.000 0.036
#> GSM425888 1 0.733 0.055872 0.424 0.124 0.396 0.012 0.044
#> GSM425889 1 0.643 0.462931 0.568 0.000 0.112 0.288 0.032
#> GSM425890 1 0.949 -0.000882 0.324 0.144 0.184 0.252 0.096
#> GSM425891 2 0.621 -0.637456 0.048 0.480 0.428 0.000 0.044
#> GSM425892 2 0.633 0.173471 0.008 0.644 0.208 0.084 0.056
#> GSM425853 1 0.755 0.040274 0.500 0.056 0.088 0.040 0.316
#> GSM425854 2 0.588 -0.416905 0.036 0.556 0.372 0.004 0.032
#> GSM425855 1 0.414 0.587587 0.832 0.016 0.052 0.068 0.032
#> GSM425856 5 0.361 0.809430 0.244 0.000 0.004 0.000 0.752
#> GSM425857 5 0.511 0.213757 0.000 0.360 0.032 0.008 0.600
#> GSM425858 2 0.657 -0.762748 0.088 0.444 0.432 0.000 0.036
#> GSM425859 2 0.522 -0.293139 0.000 0.572 0.388 0.012 0.028
#> GSM425860 1 0.746 0.041943 0.500 0.160 0.088 0.000 0.252
#> GSM425861 1 0.733 0.055872 0.424 0.124 0.396 0.012 0.044
#> GSM425862 1 0.643 0.462931 0.568 0.000 0.112 0.288 0.032
#> GSM425837 1 0.480 0.589395 0.780 0.008 0.108 0.072 0.032
#> GSM425838 4 0.654 0.770005 0.104 0.012 0.144 0.656 0.084
#> GSM425839 2 0.530 -0.321545 0.000 0.564 0.392 0.012 0.032
#> GSM425840 1 0.414 0.587587 0.832 0.016 0.052 0.068 0.032
#> GSM425841 4 0.355 0.912541 0.032 0.000 0.076 0.852 0.040
#> GSM425842 1 0.448 0.569264 0.816 0.036 0.076 0.032 0.040
#> GSM425917 2 0.320 0.453202 0.012 0.820 0.000 0.000 0.168
#> GSM425922 4 0.130 0.925582 0.028 0.000 0.016 0.956 0.000
#> GSM425919 1 0.784 0.221570 0.448 0.044 0.320 0.032 0.156
#> GSM425920 1 0.309 0.588878 0.880 0.012 0.072 0.012 0.024
#> GSM425923 1 0.726 0.448028 0.588 0.024 0.192 0.120 0.076
#> GSM425916 1 0.781 0.214578 0.448 0.036 0.320 0.036 0.160
#> GSM425918 1 0.835 0.287936 0.464 0.040 0.156 0.244 0.096
#> GSM425921 4 0.120 0.925878 0.028 0.000 0.012 0.960 0.000
#> GSM425925 4 0.140 0.927104 0.028 0.000 0.020 0.952 0.000
#> GSM425926 4 0.149 0.927208 0.028 0.000 0.024 0.948 0.000
#> GSM425927 1 0.309 0.588878 0.880 0.012 0.072 0.012 0.024
#> GSM425924 2 0.340 0.448097 0.020 0.812 0.000 0.000 0.168
#> GSM425928 2 0.313 0.454558 0.008 0.820 0.000 0.000 0.172
#> GSM425929 2 0.313 0.454558 0.008 0.820 0.000 0.000 0.172
#> GSM425930 2 0.313 0.454558 0.008 0.820 0.000 0.000 0.172
#> GSM425931 2 0.313 0.454558 0.008 0.820 0.000 0.000 0.172
#> GSM425932 2 0.313 0.454558 0.008 0.820 0.000 0.000 0.172
#> GSM425933 2 0.313 0.454558 0.008 0.820 0.000 0.000 0.172
#> GSM425934 2 0.313 0.454558 0.008 0.820 0.000 0.000 0.172
#> GSM425935 2 0.313 0.454558 0.008 0.820 0.000 0.000 0.172
#> GSM425936 2 0.313 0.454558 0.008 0.820 0.000 0.000 0.172
#> GSM425937 2 0.313 0.454558 0.008 0.820 0.000 0.000 0.172
#> GSM425938 2 0.313 0.454558 0.008 0.820 0.000 0.000 0.172
#> GSM425939 2 0.313 0.454558 0.008 0.820 0.000 0.000 0.172
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 2 0.5106 0.5064 0.000 0.500 0.440 0.000 0.040 0.020
#> GSM425908 2 0.5238 0.4988 0.000 0.496 0.436 0.000 0.040 0.028
#> GSM425909 5 0.4367 0.7420 0.076 0.024 0.148 0.000 0.752 0.000
#> GSM425910 1 0.7204 0.2816 0.552 0.068 0.136 0.008 0.180 0.056
#> GSM425911 1 0.8367 0.0167 0.296 0.216 0.272 0.004 0.172 0.040
#> GSM425912 1 0.6588 0.4096 0.552 0.280 0.076 0.008 0.028 0.056
#> GSM425913 2 0.4508 0.7259 0.044 0.740 0.180 0.000 0.008 0.028
#> GSM425914 1 0.8327 0.0486 0.340 0.188 0.248 0.004 0.176 0.044
#> GSM425915 5 0.4783 0.7916 0.224 0.016 0.076 0.000 0.684 0.000
#> GSM425874 4 0.3308 0.8316 0.016 0.052 0.000 0.856 0.056 0.020
#> GSM425875 5 0.4249 0.8202 0.188 0.008 0.068 0.000 0.736 0.000
#> GSM425876 1 0.4504 0.5127 0.788 0.060 0.068 0.008 0.012 0.064
#> GSM425877 1 0.4320 0.4276 0.740 0.004 0.008 0.028 0.016 0.204
#> GSM425878 1 0.4416 0.4930 0.796 0.052 0.004 0.056 0.024 0.068
#> GSM425879 2 0.4877 0.5623 0.004 0.536 0.420 0.000 0.028 0.012
#> GSM425880 5 0.4249 0.8202 0.188 0.008 0.068 0.000 0.736 0.000
#> GSM425881 1 0.6624 0.2687 0.472 0.376 0.068 0.008 0.024 0.052
#> GSM425882 2 0.5791 0.6547 0.052 0.584 0.312 0.008 0.024 0.020
#> GSM425883 1 0.6819 0.3839 0.576 0.064 0.004 0.188 0.040 0.128
#> GSM425884 1 0.3442 0.3488 0.756 0.000 0.004 0.004 0.004 0.232
#> GSM425885 3 0.8782 0.0439 0.024 0.236 0.332 0.168 0.180 0.060
#> GSM425848 1 0.5666 0.4563 0.704 0.044 0.008 0.076 0.044 0.124
#> GSM425849 1 0.4389 0.4914 0.792 0.056 0.000 0.056 0.024 0.072
#> GSM425850 1 0.4063 0.5259 0.808 0.076 0.016 0.008 0.012 0.080
#> GSM425851 6 0.3900 0.7909 0.232 0.000 0.040 0.000 0.000 0.728
#> GSM425852 5 0.4402 0.8190 0.188 0.008 0.080 0.000 0.724 0.000
#> GSM425893 2 0.7175 0.3950 0.136 0.404 0.360 0.000 0.080 0.020
#> GSM425894 2 0.3449 0.7206 0.016 0.820 0.140 0.012 0.008 0.004
#> GSM425895 2 0.4738 0.7163 0.052 0.728 0.176 0.000 0.008 0.036
#> GSM425896 2 0.5216 0.4902 0.000 0.488 0.444 0.000 0.048 0.020
#> GSM425897 3 0.4537 -0.2277 0.000 0.384 0.584 0.000 0.020 0.012
#> GSM425898 2 0.3449 0.7206 0.016 0.820 0.140 0.012 0.008 0.004
#> GSM425899 2 0.5115 0.6137 0.108 0.752 0.056 0.028 0.028 0.028
#> GSM425900 2 0.4520 0.6942 0.084 0.760 0.120 0.000 0.008 0.028
#> GSM425901 5 0.4367 0.7420 0.076 0.024 0.148 0.000 0.752 0.000
#> GSM425902 4 0.4641 0.7823 0.028 0.064 0.000 0.776 0.068 0.064
#> GSM425903 5 0.4783 0.7916 0.224 0.016 0.076 0.000 0.684 0.000
#> GSM425904 5 0.4249 0.8202 0.188 0.008 0.068 0.000 0.736 0.000
#> GSM425905 2 0.4810 0.5579 0.000 0.536 0.420 0.000 0.032 0.012
#> GSM425906 2 0.4669 0.6750 0.104 0.748 0.112 0.000 0.008 0.028
#> GSM425863 1 0.6558 0.3786 0.592 0.044 0.004 0.188 0.036 0.136
#> GSM425864 2 0.4883 0.5525 0.004 0.532 0.424 0.000 0.028 0.012
#> GSM425865 2 0.5125 0.5565 0.012 0.528 0.416 0.000 0.032 0.012
#> GSM425866 5 0.4337 0.8167 0.200 0.008 0.068 0.000 0.724 0.000
#> GSM425867 5 0.5980 0.5893 0.324 0.004 0.100 0.000 0.536 0.036
#> GSM425868 2 0.7239 0.4526 0.028 0.452 0.356 0.076 0.040 0.048
#> GSM425869 2 0.3667 0.7155 0.000 0.776 0.192 0.008 0.016 0.008
#> GSM425870 3 0.8390 -0.2019 0.276 0.216 0.284 0.004 0.180 0.040
#> GSM425871 1 0.3733 0.4970 0.800 0.068 0.000 0.012 0.000 0.120
#> GSM425872 2 0.3481 0.7145 0.020 0.828 0.124 0.012 0.008 0.008
#> GSM425873 1 0.3481 0.5268 0.856 0.036 0.040 0.008 0.016 0.044
#> GSM425843 1 0.4320 0.4276 0.740 0.004 0.008 0.028 0.016 0.204
#> GSM425844 1 0.3733 0.4970 0.800 0.068 0.000 0.012 0.000 0.120
#> GSM425845 5 0.6133 0.4893 0.360 0.004 0.108 0.000 0.492 0.036
#> GSM425846 2 0.4791 0.6294 0.116 0.760 0.072 0.016 0.020 0.016
#> GSM425847 1 0.5916 0.4486 0.624 0.244 0.040 0.008 0.020 0.064
#> GSM425886 5 0.5108 0.6694 0.064 0.064 0.180 0.000 0.692 0.000
#> GSM425887 2 0.4999 0.7062 0.076 0.712 0.168 0.000 0.008 0.036
#> GSM425888 1 0.6011 0.2981 0.472 0.424 0.012 0.016 0.020 0.056
#> GSM425889 1 0.6973 0.3143 0.532 0.052 0.000 0.224 0.048 0.144
#> GSM425890 6 0.8968 0.3131 0.276 0.104 0.100 0.172 0.036 0.312
#> GSM425891 2 0.4522 0.7188 0.056 0.744 0.164 0.000 0.004 0.032
#> GSM425892 2 0.6707 0.4203 0.008 0.468 0.376 0.036 0.068 0.044
#> GSM425853 1 0.7340 0.0462 0.472 0.032 0.092 0.020 0.312 0.072
#> GSM425854 2 0.4418 0.7292 0.036 0.732 0.204 0.000 0.012 0.016
#> GSM425855 1 0.4642 0.4729 0.772 0.024 0.008 0.052 0.028 0.116
#> GSM425856 5 0.4308 0.8184 0.196 0.008 0.068 0.000 0.728 0.000
#> GSM425857 5 0.5171 0.1416 0.000 0.068 0.400 0.000 0.524 0.008
#> GSM425858 2 0.4584 0.6921 0.096 0.752 0.116 0.000 0.004 0.032
#> GSM425859 2 0.3385 0.7201 0.000 0.792 0.184 0.004 0.016 0.004
#> GSM425860 1 0.7386 0.0821 0.476 0.048 0.196 0.004 0.228 0.048
#> GSM425861 1 0.6011 0.2981 0.472 0.424 0.012 0.016 0.020 0.056
#> GSM425862 1 0.6973 0.3143 0.532 0.052 0.000 0.224 0.048 0.144
#> GSM425837 1 0.5018 0.4215 0.700 0.012 0.004 0.032 0.044 0.208
#> GSM425838 4 0.8606 0.3032 0.136 0.124 0.000 0.332 0.228 0.180
#> GSM425839 2 0.3435 0.7210 0.004 0.792 0.184 0.004 0.012 0.004
#> GSM425840 1 0.4642 0.4729 0.772 0.024 0.008 0.052 0.028 0.116
#> GSM425841 4 0.3981 0.8158 0.028 0.048 0.000 0.820 0.064 0.040
#> GSM425842 1 0.3407 0.5367 0.864 0.032 0.024 0.024 0.016 0.040
#> GSM425917 3 0.0146 0.8542 0.000 0.000 0.996 0.000 0.000 0.004
#> GSM425922 4 0.1242 0.8388 0.008 0.012 0.000 0.960 0.008 0.012
#> GSM425919 6 0.3900 0.7909 0.232 0.000 0.040 0.000 0.000 0.728
#> GSM425920 1 0.2822 0.4925 0.856 0.032 0.000 0.004 0.000 0.108
#> GSM425923 1 0.6070 -0.1405 0.496 0.016 0.008 0.072 0.020 0.388
#> GSM425916 6 0.3533 0.7766 0.236 0.000 0.012 0.004 0.000 0.748
#> GSM425918 1 0.7690 -0.2456 0.404 0.036 0.036 0.164 0.032 0.328
#> GSM425921 4 0.1242 0.8414 0.012 0.012 0.000 0.960 0.008 0.008
#> GSM425925 4 0.0725 0.8444 0.012 0.012 0.000 0.976 0.000 0.000
#> GSM425926 4 0.0767 0.8443 0.008 0.012 0.000 0.976 0.000 0.004
#> GSM425927 1 0.2822 0.4925 0.856 0.032 0.000 0.004 0.000 0.108
#> GSM425924 3 0.0405 0.8457 0.008 0.000 0.988 0.000 0.000 0.004
#> GSM425928 3 0.0000 0.8582 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425929 3 0.0000 0.8582 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425930 3 0.0000 0.8582 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425931 3 0.0000 0.8582 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425932 3 0.0000 0.8582 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425933 3 0.0000 0.8582 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425934 3 0.0000 0.8582 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425935 3 0.0000 0.8582 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425936 3 0.0000 0.8582 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425937 3 0.0000 0.8582 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425938 3 0.0000 0.8582 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425939 3 0.0000 0.8582 0.000 0.000 1.000 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 disease.state(p) tissue(p) other(p) k
#> SD:hclust 75 1.22e-02 2.31e-03 3.80e-05 2
#> SD:hclust 72 7.78e-03 1.75e-04 7.26e-04 3
#> SD:hclust 84 2.91e-03 6.61e-05 2.38e-03 4
#> SD:hclust 42 NA 1.14e-02 1.49e-01 5
#> SD:hclust 62 8.58e-10 5.28e-13 1.09e-06 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 103 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 0.227 0.678 0.811 0.4832 0.496 0.496
#> 3 3 0.477 0.652 0.800 0.3281 0.785 0.595
#> 4 4 0.652 0.619 0.784 0.1303 0.862 0.629
#> 5 5 0.677 0.699 0.806 0.0778 0.863 0.551
#> 6 6 0.750 0.693 0.784 0.0499 0.914 0.644
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
#> GSM425907 2 0.3733 0.7394 0.072 0.928
#> GSM425908 2 0.7883 0.6622 0.236 0.764
#> GSM425909 2 0.7453 0.7419 0.212 0.788
#> GSM425910 1 0.9977 -0.2309 0.528 0.472
#> GSM425911 2 0.7674 0.7417 0.224 0.776
#> GSM425912 2 0.9896 0.5265 0.440 0.560
#> GSM425913 2 0.6623 0.7083 0.172 0.828
#> GSM425914 2 0.8861 0.6904 0.304 0.696
#> GSM425915 2 0.7376 0.7334 0.208 0.792
#> GSM425874 1 0.7674 0.7122 0.776 0.224
#> GSM425875 1 0.1633 0.7905 0.976 0.024
#> GSM425876 1 0.3584 0.7757 0.932 0.068
#> GSM425877 1 0.0672 0.7991 0.992 0.008
#> GSM425878 1 0.1184 0.8042 0.984 0.016
#> GSM425879 2 0.3584 0.7419 0.068 0.932
#> GSM425880 1 0.7139 0.5997 0.804 0.196
#> GSM425881 1 0.9170 0.4665 0.668 0.332
#> GSM425882 2 0.7883 0.6622 0.236 0.764
#> GSM425883 1 0.1633 0.8037 0.976 0.024
#> GSM425884 1 0.0672 0.7991 0.992 0.008
#> GSM425885 1 0.9977 0.1355 0.528 0.472
#> GSM425848 1 0.6148 0.7549 0.848 0.152
#> GSM425849 1 0.5178 0.7731 0.884 0.116
#> GSM425850 1 0.1633 0.8018 0.976 0.024
#> GSM425851 1 0.0376 0.8009 0.996 0.004
#> GSM425852 1 0.7219 0.5934 0.800 0.200
#> GSM425893 2 0.6343 0.7549 0.160 0.840
#> GSM425894 2 0.7883 0.6622 0.236 0.764
#> GSM425895 2 0.7883 0.6622 0.236 0.764
#> GSM425896 2 0.2948 0.7374 0.052 0.948
#> GSM425897 2 0.3584 0.7397 0.068 0.932
#> GSM425898 2 0.7883 0.6622 0.236 0.764
#> GSM425899 1 0.8499 0.6624 0.724 0.276
#> GSM425900 2 0.8661 0.6164 0.288 0.712
#> GSM425901 2 0.6801 0.7446 0.180 0.820
#> GSM425902 1 0.7674 0.7122 0.776 0.224
#> GSM425903 2 0.8555 0.6905 0.280 0.720
#> GSM425904 1 0.7139 0.5997 0.804 0.196
#> GSM425905 2 0.4939 0.7339 0.108 0.892
#> GSM425906 2 0.7528 0.7051 0.216 0.784
#> GSM425863 1 0.2423 0.8007 0.960 0.040
#> GSM425864 2 0.3584 0.7397 0.068 0.932
#> GSM425865 2 0.7453 0.6820 0.212 0.788
#> GSM425866 1 0.4562 0.7267 0.904 0.096
#> GSM425867 2 0.8267 0.6765 0.260 0.740
#> GSM425868 2 0.7883 0.6622 0.236 0.764
#> GSM425869 2 0.7883 0.6622 0.236 0.764
#> GSM425870 2 0.6712 0.7324 0.176 0.824
#> GSM425871 1 0.5737 0.7658 0.864 0.136
#> GSM425872 2 0.7883 0.6622 0.236 0.764
#> GSM425873 1 0.1843 0.8000 0.972 0.028
#> GSM425843 1 0.0672 0.7991 0.992 0.008
#> GSM425844 1 0.1184 0.8043 0.984 0.016
#> GSM425845 1 0.9993 -0.2483 0.516 0.484
#> GSM425846 1 0.8443 0.6671 0.728 0.272
#> GSM425847 1 0.6438 0.6774 0.836 0.164
#> GSM425886 2 0.6343 0.7502 0.160 0.840
#> GSM425887 1 0.9954 -0.0233 0.540 0.460
#> GSM425888 1 0.8661 0.5791 0.712 0.288
#> GSM425889 1 0.6438 0.7471 0.836 0.164
#> GSM425890 1 0.7674 0.7122 0.776 0.224
#> GSM425891 2 0.5946 0.7252 0.144 0.856
#> GSM425892 2 0.7883 0.6622 0.236 0.764
#> GSM425853 1 0.0938 0.7977 0.988 0.012
#> GSM425854 2 0.7883 0.6622 0.236 0.764
#> GSM425855 1 0.2236 0.8016 0.964 0.036
#> GSM425856 1 0.4562 0.7267 0.904 0.096
#> GSM425857 2 0.6148 0.7333 0.152 0.848
#> GSM425858 2 0.9977 0.0634 0.472 0.528
#> GSM425859 2 0.7883 0.6622 0.236 0.764
#> GSM425860 2 0.9710 0.5706 0.400 0.600
#> GSM425861 1 0.6048 0.7607 0.852 0.148
#> GSM425862 1 0.6531 0.7444 0.832 0.168
#> GSM425837 1 0.0376 0.8009 0.996 0.004
#> GSM425838 1 0.7674 0.7122 0.776 0.224
#> GSM425839 2 0.7883 0.6622 0.236 0.764
#> GSM425840 1 0.0000 0.8020 1.000 0.000
#> GSM425841 1 0.7674 0.7122 0.776 0.224
#> GSM425842 1 0.1414 0.8012 0.980 0.020
#> GSM425917 2 0.9170 0.6940 0.332 0.668
#> GSM425922 1 0.7674 0.7122 0.776 0.224
#> GSM425919 1 0.0672 0.7991 0.992 0.008
#> GSM425920 1 0.0376 0.8009 0.996 0.004
#> GSM425923 1 0.0938 0.8042 0.988 0.012
#> GSM425916 1 0.0376 0.8009 0.996 0.004
#> GSM425918 1 0.0938 0.8042 0.988 0.012
#> GSM425921 1 0.7674 0.7122 0.776 0.224
#> GSM425925 1 0.6531 0.7444 0.832 0.168
#> GSM425926 1 0.7602 0.7153 0.780 0.220
#> GSM425927 1 0.0672 0.7991 0.992 0.008
#> GSM425924 1 0.9815 0.0875 0.580 0.420
#> GSM425928 2 0.7376 0.7272 0.208 0.792
#> GSM425929 2 0.7376 0.7272 0.208 0.792
#> GSM425930 2 0.7376 0.7272 0.208 0.792
#> GSM425931 2 0.7376 0.7272 0.208 0.792
#> GSM425932 2 0.7376 0.7272 0.208 0.792
#> GSM425933 2 0.7376 0.7272 0.208 0.792
#> GSM425934 2 0.7056 0.7309 0.192 0.808
#> GSM425935 2 0.6247 0.7389 0.156 0.844
#> GSM425936 2 0.7376 0.7272 0.208 0.792
#> GSM425937 2 0.7376 0.7272 0.208 0.792
#> GSM425938 2 0.7376 0.7272 0.208 0.792
#> GSM425939 2 0.7376 0.7272 0.208 0.792
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.0475 7.94e-01 0.004 0.992 0.004
#> GSM425908 2 0.1129 8.01e-01 0.020 0.976 0.004
#> GSM425909 3 0.6659 6.65e-01 0.028 0.304 0.668
#> GSM425910 1 0.7360 9.64e-05 0.528 0.440 0.032
#> GSM425911 2 0.0000 7.93e-01 0.000 1.000 0.000
#> GSM425912 2 0.6798 3.43e-01 0.400 0.584 0.016
#> GSM425913 2 0.0661 7.97e-01 0.008 0.988 0.004
#> GSM425914 2 0.6529 4.05e-01 0.368 0.620 0.012
#> GSM425915 3 0.5860 7.61e-01 0.024 0.228 0.748
#> GSM425874 1 0.8622 4.58e-01 0.572 0.296 0.132
#> GSM425875 1 0.5012 6.60e-01 0.788 0.008 0.204
#> GSM425876 1 0.5253 6.05e-01 0.792 0.188 0.020
#> GSM425877 1 0.1031 7.70e-01 0.976 0.000 0.024
#> GSM425878 1 0.0892 7.65e-01 0.980 0.000 0.020
#> GSM425879 2 0.0237 7.92e-01 0.000 0.996 0.004
#> GSM425880 1 0.6540 3.65e-01 0.584 0.008 0.408
#> GSM425881 2 0.7063 2.15e-01 0.464 0.516 0.020
#> GSM425882 2 0.1877 7.91e-01 0.032 0.956 0.012
#> GSM425883 1 0.3340 7.53e-01 0.880 0.000 0.120
#> GSM425884 1 0.0892 7.65e-01 0.980 0.000 0.020
#> GSM425885 2 0.9070 -1.73e-01 0.428 0.436 0.136
#> GSM425848 1 0.4915 7.33e-01 0.832 0.036 0.132
#> GSM425849 1 0.1525 7.67e-01 0.964 0.004 0.032
#> GSM425850 1 0.1636 7.61e-01 0.964 0.016 0.020
#> GSM425851 1 0.2796 7.58e-01 0.908 0.000 0.092
#> GSM425852 1 0.6467 3.70e-01 0.604 0.008 0.388
#> GSM425893 2 0.0237 7.92e-01 0.000 0.996 0.004
#> GSM425894 2 0.1129 8.01e-01 0.020 0.976 0.004
#> GSM425895 2 0.1129 8.01e-01 0.020 0.976 0.004
#> GSM425896 2 0.0237 7.92e-01 0.000 0.996 0.004
#> GSM425897 2 0.0237 7.92e-01 0.000 0.996 0.004
#> GSM425898 2 0.1129 8.01e-01 0.020 0.976 0.004
#> GSM425899 2 0.5486 6.62e-01 0.196 0.780 0.024
#> GSM425900 2 0.2959 7.50e-01 0.100 0.900 0.000
#> GSM425901 3 0.6659 6.65e-01 0.028 0.304 0.668
#> GSM425902 1 0.8622 4.58e-01 0.572 0.296 0.132
#> GSM425903 3 0.8464 4.10e-01 0.280 0.128 0.592
#> GSM425904 1 0.6553 3.57e-01 0.580 0.008 0.412
#> GSM425905 2 0.0475 7.94e-01 0.004 0.992 0.004
#> GSM425906 2 0.0747 7.97e-01 0.016 0.984 0.000
#> GSM425863 1 0.0747 7.69e-01 0.984 0.000 0.016
#> GSM425864 2 0.0237 7.92e-01 0.000 0.996 0.004
#> GSM425865 2 0.0661 7.97e-01 0.008 0.988 0.004
#> GSM425866 1 0.6318 4.61e-01 0.636 0.008 0.356
#> GSM425867 3 0.5000 6.71e-01 0.124 0.044 0.832
#> GSM425868 2 0.3973 7.31e-01 0.032 0.880 0.088
#> GSM425869 2 0.1315 8.00e-01 0.020 0.972 0.008
#> GSM425870 3 0.6890 7.41e-01 0.028 0.340 0.632
#> GSM425871 1 0.2400 7.65e-01 0.932 0.004 0.064
#> GSM425872 2 0.1129 8.01e-01 0.020 0.976 0.004
#> GSM425873 1 0.1636 7.62e-01 0.964 0.016 0.020
#> GSM425843 1 0.0892 7.65e-01 0.980 0.000 0.020
#> GSM425844 1 0.2711 7.59e-01 0.912 0.000 0.088
#> GSM425845 1 0.9285 8.07e-02 0.448 0.160 0.392
#> GSM425846 2 0.5384 6.66e-01 0.188 0.788 0.024
#> GSM425847 1 0.6849 1.77e-01 0.600 0.380 0.020
#> GSM425886 3 0.5948 6.52e-01 0.000 0.360 0.640
#> GSM425887 2 0.6869 3.09e-01 0.424 0.560 0.016
#> GSM425888 2 0.6952 1.79e-01 0.480 0.504 0.016
#> GSM425889 1 0.3784 7.49e-01 0.864 0.004 0.132
#> GSM425890 1 0.8435 4.79e-01 0.592 0.284 0.124
#> GSM425891 2 0.0424 7.98e-01 0.008 0.992 0.000
#> GSM425892 2 0.1129 8.01e-01 0.020 0.976 0.004
#> GSM425853 1 0.2280 7.53e-01 0.940 0.008 0.052
#> GSM425854 2 0.0892 8.00e-01 0.020 0.980 0.000
#> GSM425855 1 0.1031 7.70e-01 0.976 0.000 0.024
#> GSM425856 1 0.6318 4.61e-01 0.636 0.008 0.356
#> GSM425857 3 0.7715 4.02e-01 0.048 0.428 0.524
#> GSM425858 2 0.5723 6.17e-01 0.240 0.744 0.016
#> GSM425859 2 0.1129 8.01e-01 0.020 0.976 0.004
#> GSM425860 2 0.8059 1.74e-01 0.444 0.492 0.064
#> GSM425861 1 0.6627 3.09e-01 0.644 0.336 0.020
#> GSM425862 1 0.3784 7.49e-01 0.864 0.004 0.132
#> GSM425837 1 0.0892 7.69e-01 0.980 0.000 0.020
#> GSM425838 1 0.8512 4.60e-01 0.580 0.296 0.124
#> GSM425839 2 0.1129 8.01e-01 0.020 0.976 0.004
#> GSM425840 1 0.0592 7.68e-01 0.988 0.000 0.012
#> GSM425841 1 0.8622 4.58e-01 0.572 0.296 0.132
#> GSM425842 1 0.1129 7.64e-01 0.976 0.004 0.020
#> GSM425917 3 0.8901 5.27e-01 0.232 0.196 0.572
#> GSM425922 1 0.8546 4.77e-01 0.584 0.284 0.132
#> GSM425919 1 0.0892 7.65e-01 0.980 0.000 0.020
#> GSM425920 1 0.1163 7.69e-01 0.972 0.000 0.028
#> GSM425923 1 0.3192 7.53e-01 0.888 0.000 0.112
#> GSM425916 1 0.2796 7.58e-01 0.908 0.000 0.092
#> GSM425918 1 0.2959 7.55e-01 0.900 0.000 0.100
#> GSM425921 1 0.8546 4.77e-01 0.584 0.284 0.132
#> GSM425925 1 0.3784 7.49e-01 0.864 0.004 0.132
#> GSM425926 1 0.8520 4.82e-01 0.588 0.280 0.132
#> GSM425927 1 0.1129 7.64e-01 0.976 0.004 0.020
#> GSM425924 3 0.8630 3.68e-01 0.328 0.120 0.552
#> GSM425928 3 0.5578 8.34e-01 0.012 0.240 0.748
#> GSM425929 3 0.5578 8.34e-01 0.012 0.240 0.748
#> GSM425930 3 0.5578 8.34e-01 0.012 0.240 0.748
#> GSM425931 3 0.5578 8.34e-01 0.012 0.240 0.748
#> GSM425932 3 0.5578 8.34e-01 0.012 0.240 0.748
#> GSM425933 3 0.5578 8.34e-01 0.012 0.240 0.748
#> GSM425934 3 0.5325 8.26e-01 0.004 0.248 0.748
#> GSM425935 3 0.5578 8.34e-01 0.012 0.240 0.748
#> GSM425936 3 0.5578 8.34e-01 0.012 0.240 0.748
#> GSM425937 3 0.5578 8.34e-01 0.012 0.240 0.748
#> GSM425938 3 0.5578 8.34e-01 0.012 0.240 0.748
#> GSM425939 3 0.5578 8.34e-01 0.012 0.240 0.748
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.0804 0.8662 0.012 0.980 0.000 0.008
#> GSM425908 2 0.0804 0.8662 0.012 0.980 0.000 0.008
#> GSM425909 3 0.7782 0.5193 0.268 0.212 0.508 0.012
#> GSM425910 1 0.4877 0.5234 0.752 0.204 0.000 0.044
#> GSM425911 2 0.2011 0.8438 0.080 0.920 0.000 0.000
#> GSM425912 2 0.6137 0.1488 0.448 0.504 0.000 0.048
#> GSM425913 2 0.1022 0.8642 0.032 0.968 0.000 0.000
#> GSM425914 2 0.5686 0.4008 0.376 0.592 0.000 0.032
#> GSM425915 3 0.7380 0.5190 0.288 0.200 0.512 0.000
#> GSM425874 4 0.2011 0.7390 0.000 0.080 0.000 0.920
#> GSM425875 1 0.4781 0.5191 0.796 0.004 0.088 0.112
#> GSM425876 1 0.5396 0.5436 0.740 0.156 0.000 0.104
#> GSM425877 4 0.5292 -0.2280 0.480 0.000 0.008 0.512
#> GSM425878 1 0.4564 0.5401 0.672 0.000 0.000 0.328
#> GSM425879 2 0.1211 0.8630 0.040 0.960 0.000 0.000
#> GSM425880 1 0.4867 0.5137 0.784 0.004 0.144 0.068
#> GSM425881 2 0.6147 0.1037 0.464 0.488 0.000 0.048
#> GSM425882 2 0.1716 0.8604 0.064 0.936 0.000 0.000
#> GSM425883 4 0.3933 0.5940 0.200 0.000 0.008 0.792
#> GSM425884 1 0.4543 0.5441 0.676 0.000 0.000 0.324
#> GSM425885 4 0.3074 0.6636 0.000 0.152 0.000 0.848
#> GSM425848 4 0.1545 0.7399 0.040 0.008 0.000 0.952
#> GSM425849 1 0.4888 0.4702 0.588 0.000 0.000 0.412
#> GSM425850 1 0.4797 0.5657 0.720 0.020 0.000 0.260
#> GSM425851 4 0.4769 0.4618 0.308 0.000 0.008 0.684
#> GSM425852 1 0.4037 0.5289 0.832 0.000 0.112 0.056
#> GSM425893 2 0.2149 0.8362 0.088 0.912 0.000 0.000
#> GSM425894 2 0.0895 0.8660 0.004 0.976 0.000 0.020
#> GSM425895 2 0.0804 0.8694 0.008 0.980 0.000 0.012
#> GSM425896 2 0.0657 0.8670 0.012 0.984 0.000 0.004
#> GSM425897 2 0.0592 0.8678 0.016 0.984 0.000 0.000
#> GSM425898 2 0.0779 0.8675 0.004 0.980 0.000 0.016
#> GSM425899 2 0.2882 0.8247 0.084 0.892 0.000 0.024
#> GSM425900 2 0.2125 0.8495 0.076 0.920 0.000 0.004
#> GSM425901 3 0.7782 0.5193 0.268 0.212 0.508 0.012
#> GSM425902 4 0.2149 0.7341 0.000 0.088 0.000 0.912
#> GSM425903 1 0.5990 0.0165 0.608 0.056 0.336 0.000
#> GSM425904 1 0.4916 0.5106 0.780 0.004 0.148 0.068
#> GSM425905 2 0.0188 0.8690 0.004 0.996 0.000 0.000
#> GSM425906 2 0.1557 0.8580 0.056 0.944 0.000 0.000
#> GSM425863 1 0.4967 0.4032 0.548 0.000 0.000 0.452
#> GSM425864 2 0.0469 0.8676 0.012 0.988 0.000 0.000
#> GSM425865 2 0.0657 0.8670 0.012 0.984 0.000 0.004
#> GSM425866 1 0.4592 0.5242 0.804 0.004 0.128 0.064
#> GSM425867 3 0.4843 0.4519 0.396 0.000 0.604 0.000
#> GSM425868 2 0.1302 0.8559 0.000 0.956 0.000 0.044
#> GSM425869 2 0.1022 0.8623 0.000 0.968 0.000 0.032
#> GSM425870 3 0.7728 0.2833 0.232 0.352 0.416 0.000
#> GSM425871 1 0.5163 0.1669 0.516 0.000 0.004 0.480
#> GSM425872 2 0.0779 0.8675 0.004 0.980 0.000 0.016
#> GSM425873 1 0.4767 0.5656 0.724 0.020 0.000 0.256
#> GSM425843 1 0.4643 0.5287 0.656 0.000 0.000 0.344
#> GSM425844 4 0.5007 0.3573 0.356 0.000 0.008 0.636
#> GSM425845 1 0.3377 0.5118 0.848 0.012 0.140 0.000
#> GSM425846 2 0.3161 0.8153 0.124 0.864 0.000 0.012
#> GSM425847 1 0.5677 0.4919 0.680 0.256 0.000 0.064
#> GSM425886 3 0.7421 0.5224 0.268 0.220 0.512 0.000
#> GSM425887 2 0.6052 0.2994 0.396 0.556 0.000 0.048
#> GSM425888 2 0.6271 0.1297 0.452 0.492 0.000 0.056
#> GSM425889 4 0.0817 0.7407 0.024 0.000 0.000 0.976
#> GSM425890 4 0.2302 0.7506 0.008 0.060 0.008 0.924
#> GSM425891 2 0.1022 0.8642 0.032 0.968 0.000 0.000
#> GSM425892 2 0.0804 0.8662 0.012 0.980 0.000 0.008
#> GSM425853 1 0.4122 0.5772 0.760 0.000 0.004 0.236
#> GSM425854 2 0.0927 0.8684 0.008 0.976 0.000 0.016
#> GSM425855 4 0.4967 -0.1617 0.452 0.000 0.000 0.548
#> GSM425856 1 0.4644 0.5224 0.800 0.004 0.132 0.064
#> GSM425857 1 0.9995 -0.3031 0.264 0.244 0.240 0.252
#> GSM425858 2 0.3501 0.7995 0.132 0.848 0.000 0.020
#> GSM425859 2 0.0707 0.8655 0.000 0.980 0.000 0.020
#> GSM425860 1 0.5592 0.4267 0.656 0.300 0.000 0.044
#> GSM425861 1 0.6316 0.4351 0.612 0.300 0.000 0.088
#> GSM425862 4 0.0817 0.7407 0.024 0.000 0.000 0.976
#> GSM425837 1 0.4916 0.4448 0.576 0.000 0.000 0.424
#> GSM425838 4 0.2342 0.7418 0.008 0.080 0.000 0.912
#> GSM425839 2 0.0657 0.8683 0.004 0.984 0.000 0.012
#> GSM425840 1 0.4790 0.4932 0.620 0.000 0.000 0.380
#> GSM425841 4 0.2011 0.7390 0.000 0.080 0.000 0.920
#> GSM425842 1 0.4331 0.5589 0.712 0.000 0.000 0.288
#> GSM425917 3 0.7043 0.5544 0.060 0.080 0.652 0.208
#> GSM425922 4 0.1637 0.7495 0.000 0.060 0.000 0.940
#> GSM425919 1 0.4917 0.5291 0.656 0.000 0.008 0.336
#> GSM425920 1 0.5244 0.3289 0.556 0.000 0.008 0.436
#> GSM425923 4 0.3545 0.6359 0.164 0.000 0.008 0.828
#> GSM425916 4 0.4769 0.4618 0.308 0.000 0.008 0.684
#> GSM425918 4 0.4567 0.5093 0.276 0.000 0.008 0.716
#> GSM425921 4 0.1637 0.7495 0.000 0.060 0.000 0.940
#> GSM425925 4 0.0336 0.7432 0.008 0.000 0.000 0.992
#> GSM425926 4 0.1637 0.7495 0.000 0.060 0.000 0.940
#> GSM425927 1 0.4454 0.5536 0.692 0.000 0.000 0.308
#> GSM425924 3 0.7598 0.3636 0.164 0.028 0.576 0.232
#> GSM425928 3 0.2081 0.8102 0.000 0.084 0.916 0.000
#> GSM425929 3 0.2081 0.8102 0.000 0.084 0.916 0.000
#> GSM425930 3 0.2081 0.8102 0.000 0.084 0.916 0.000
#> GSM425931 3 0.2081 0.8102 0.000 0.084 0.916 0.000
#> GSM425932 3 0.2081 0.8102 0.000 0.084 0.916 0.000
#> GSM425933 3 0.2081 0.8102 0.000 0.084 0.916 0.000
#> GSM425934 3 0.2081 0.8102 0.000 0.084 0.916 0.000
#> GSM425935 3 0.2081 0.8102 0.000 0.084 0.916 0.000
#> GSM425936 3 0.2081 0.8102 0.000 0.084 0.916 0.000
#> GSM425937 3 0.2081 0.8102 0.000 0.084 0.916 0.000
#> GSM425938 3 0.2081 0.8102 0.000 0.084 0.916 0.000
#> GSM425939 3 0.2081 0.8102 0.000 0.084 0.916 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM425907 2 0.3609 0.8486 0.036 0.836 0.000 0.016 0.112
#> GSM425908 2 0.3609 0.8486 0.036 0.836 0.000 0.016 0.112
#> GSM425909 5 0.4801 0.7257 0.000 0.064 0.204 0.008 0.724
#> GSM425910 1 0.2761 0.5971 0.872 0.024 0.000 0.000 0.104
#> GSM425911 2 0.4587 0.8031 0.096 0.744 0.000 0.000 0.160
#> GSM425912 1 0.5607 0.1444 0.540 0.380 0.000 0.000 0.080
#> GSM425913 2 0.1018 0.8676 0.016 0.968 0.000 0.000 0.016
#> GSM425914 2 0.6299 0.3459 0.380 0.464 0.000 0.000 0.156
#> GSM425915 5 0.4539 0.7259 0.008 0.044 0.212 0.000 0.736
#> GSM425874 4 0.0510 0.8660 0.000 0.016 0.000 0.984 0.000
#> GSM425875 5 0.5106 0.7394 0.260 0.000 0.012 0.052 0.676
#> GSM425876 1 0.1788 0.6307 0.932 0.008 0.000 0.004 0.056
#> GSM425877 1 0.6186 0.4169 0.548 0.000 0.004 0.300 0.148
#> GSM425878 1 0.2761 0.6626 0.872 0.000 0.000 0.104 0.024
#> GSM425879 2 0.3192 0.8504 0.040 0.848 0.000 0.000 0.112
#> GSM425880 5 0.5103 0.7803 0.244 0.000 0.052 0.016 0.688
#> GSM425881 1 0.5359 0.1605 0.532 0.412 0.000 0.000 0.056
#> GSM425882 2 0.3164 0.8537 0.044 0.852 0.000 0.000 0.104
#> GSM425883 4 0.5756 0.2439 0.312 0.000 0.000 0.576 0.112
#> GSM425884 1 0.3222 0.6603 0.852 0.000 0.004 0.108 0.036
#> GSM425885 4 0.2623 0.7796 0.004 0.096 0.000 0.884 0.016
#> GSM425848 4 0.3154 0.7987 0.104 0.012 0.000 0.860 0.024
#> GSM425849 1 0.4181 0.5724 0.712 0.000 0.000 0.268 0.020
#> GSM425850 1 0.2459 0.6549 0.904 0.004 0.000 0.040 0.052
#> GSM425851 1 0.6437 0.1913 0.464 0.000 0.004 0.376 0.156
#> GSM425852 5 0.4587 0.7223 0.276 0.000 0.024 0.008 0.692
#> GSM425893 2 0.3710 0.8360 0.048 0.808 0.000 0.000 0.144
#> GSM425894 2 0.0671 0.8651 0.004 0.980 0.000 0.016 0.000
#> GSM425895 2 0.0451 0.8659 0.004 0.988 0.000 0.008 0.000
#> GSM425896 2 0.3609 0.8486 0.036 0.836 0.000 0.016 0.112
#> GSM425897 2 0.3115 0.8507 0.036 0.852 0.000 0.000 0.112
#> GSM425898 2 0.0867 0.8638 0.008 0.976 0.000 0.008 0.008
#> GSM425899 2 0.2213 0.8465 0.040 0.924 0.004 0.016 0.016
#> GSM425900 2 0.2632 0.8171 0.072 0.888 0.000 0.000 0.040
#> GSM425901 5 0.4801 0.7257 0.000 0.064 0.204 0.008 0.724
#> GSM425902 4 0.1124 0.8569 0.000 0.036 0.000 0.960 0.004
#> GSM425903 5 0.4735 0.7819 0.132 0.012 0.100 0.000 0.756
#> GSM425904 5 0.5176 0.7844 0.236 0.000 0.060 0.016 0.688
#> GSM425905 2 0.2707 0.8629 0.024 0.888 0.000 0.008 0.080
#> GSM425906 2 0.2830 0.8083 0.080 0.876 0.000 0.000 0.044
#> GSM425863 1 0.4668 0.4712 0.624 0.000 0.000 0.352 0.024
#> GSM425864 2 0.3396 0.8506 0.036 0.844 0.000 0.008 0.112
#> GSM425865 2 0.3396 0.8506 0.036 0.844 0.000 0.008 0.112
#> GSM425866 5 0.5138 0.7725 0.260 0.000 0.048 0.016 0.676
#> GSM425867 5 0.4866 0.6853 0.052 0.000 0.284 0.000 0.664
#> GSM425868 2 0.1012 0.8663 0.000 0.968 0.000 0.020 0.012
#> GSM425869 2 0.0671 0.8659 0.000 0.980 0.000 0.016 0.004
#> GSM425870 2 0.8213 0.2622 0.164 0.388 0.172 0.000 0.276
#> GSM425871 1 0.3326 0.6495 0.824 0.000 0.000 0.152 0.024
#> GSM425872 2 0.0867 0.8638 0.008 0.976 0.000 0.008 0.008
#> GSM425873 1 0.2299 0.6507 0.912 0.004 0.000 0.032 0.052
#> GSM425843 1 0.3595 0.6550 0.828 0.000 0.004 0.120 0.048
#> GSM425844 1 0.6109 0.3137 0.532 0.000 0.000 0.320 0.148
#> GSM425845 5 0.4481 0.7557 0.232 0.000 0.048 0.000 0.720
#> GSM425846 2 0.2260 0.8427 0.048 0.920 0.004 0.012 0.016
#> GSM425847 1 0.4010 0.5605 0.784 0.160 0.000 0.000 0.056
#> GSM425886 5 0.4801 0.7257 0.000 0.064 0.204 0.008 0.724
#> GSM425887 2 0.5304 0.2892 0.384 0.560 0.000 0.000 0.056
#> GSM425888 1 0.5337 0.1270 0.508 0.440 0.000 0.000 0.052
#> GSM425889 4 0.1965 0.8446 0.052 0.000 0.000 0.924 0.024
#> GSM425890 4 0.2899 0.8014 0.028 0.004 0.000 0.872 0.096
#> GSM425891 2 0.1753 0.8690 0.032 0.936 0.000 0.000 0.032
#> GSM425892 2 0.3507 0.8521 0.036 0.844 0.000 0.016 0.104
#> GSM425853 1 0.2974 0.6411 0.868 0.000 0.000 0.052 0.080
#> GSM425854 2 0.0451 0.8659 0.004 0.988 0.000 0.008 0.000
#> GSM425855 1 0.5113 0.4208 0.576 0.000 0.000 0.380 0.044
#> GSM425856 5 0.5138 0.7725 0.260 0.000 0.048 0.016 0.676
#> GSM425857 5 0.5591 0.7138 0.000 0.084 0.100 0.096 0.720
#> GSM425858 2 0.3289 0.7796 0.108 0.844 0.000 0.000 0.048
#> GSM425859 2 0.0671 0.8659 0.000 0.980 0.000 0.016 0.004
#> GSM425860 1 0.4605 0.5123 0.732 0.192 0.000 0.000 0.076
#> GSM425861 1 0.4969 0.4628 0.652 0.292 0.000 0.000 0.056
#> GSM425862 4 0.1965 0.8446 0.052 0.000 0.000 0.924 0.024
#> GSM425837 1 0.4798 0.5616 0.684 0.000 0.004 0.268 0.044
#> GSM425838 4 0.1836 0.8559 0.032 0.036 0.000 0.932 0.000
#> GSM425839 2 0.0451 0.8659 0.004 0.988 0.000 0.008 0.000
#> GSM425840 1 0.4393 0.6212 0.752 0.000 0.004 0.192 0.052
#> GSM425841 4 0.0794 0.8615 0.000 0.028 0.000 0.972 0.000
#> GSM425842 1 0.2376 0.6575 0.904 0.000 0.000 0.044 0.052
#> GSM425917 3 0.7076 0.4629 0.076 0.008 0.588 0.176 0.152
#> GSM425922 4 0.0566 0.8640 0.000 0.004 0.000 0.984 0.012
#> GSM425919 1 0.5113 0.5864 0.708 0.000 0.004 0.128 0.160
#> GSM425920 1 0.5491 0.5472 0.668 0.000 0.004 0.176 0.152
#> GSM425923 4 0.6229 0.1841 0.312 0.000 0.004 0.536 0.148
#> GSM425916 1 0.6447 0.1757 0.456 0.000 0.004 0.384 0.156
#> GSM425918 1 0.6438 0.1163 0.436 0.000 0.004 0.408 0.152
#> GSM425921 4 0.0451 0.8645 0.000 0.004 0.000 0.988 0.008
#> GSM425925 4 0.0898 0.8611 0.020 0.000 0.000 0.972 0.008
#> GSM425926 4 0.0162 0.8661 0.000 0.004 0.000 0.996 0.000
#> GSM425927 1 0.1872 0.6714 0.928 0.000 0.000 0.052 0.020
#> GSM425924 3 0.8132 0.0976 0.272 0.000 0.404 0.176 0.148
#> GSM425928 3 0.0290 0.9097 0.000 0.008 0.992 0.000 0.000
#> GSM425929 3 0.0290 0.9097 0.000 0.008 0.992 0.000 0.000
#> GSM425930 3 0.0290 0.9097 0.000 0.008 0.992 0.000 0.000
#> GSM425931 3 0.0290 0.9097 0.000 0.008 0.992 0.000 0.000
#> GSM425932 3 0.0290 0.9097 0.000 0.008 0.992 0.000 0.000
#> GSM425933 3 0.0290 0.9097 0.000 0.008 0.992 0.000 0.000
#> GSM425934 3 0.0290 0.9097 0.000 0.008 0.992 0.000 0.000
#> GSM425935 3 0.0290 0.9097 0.000 0.008 0.992 0.000 0.000
#> GSM425936 3 0.0290 0.9097 0.000 0.008 0.992 0.000 0.000
#> GSM425937 3 0.0290 0.9097 0.000 0.008 0.992 0.000 0.000
#> GSM425938 3 0.0290 0.9097 0.000 0.008 0.992 0.000 0.000
#> GSM425939 3 0.0290 0.9097 0.000 0.008 0.992 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 2 0.4100 0.7932 0.008 0.756 0.000 0.004 0.052 0.180
#> GSM425908 2 0.4100 0.7932 0.008 0.756 0.000 0.004 0.052 0.180
#> GSM425909 5 0.2759 0.8998 0.012 0.032 0.044 0.008 0.892 0.012
#> GSM425910 6 0.2806 0.5288 0.136 0.004 0.000 0.000 0.016 0.844
#> GSM425911 2 0.4990 0.5754 0.012 0.552 0.000 0.000 0.048 0.388
#> GSM425912 6 0.3979 0.5777 0.028 0.256 0.000 0.000 0.004 0.712
#> GSM425913 2 0.1267 0.8169 0.000 0.940 0.000 0.000 0.000 0.060
#> GSM425914 6 0.3404 0.4009 0.000 0.224 0.000 0.000 0.016 0.760
#> GSM425915 5 0.3052 0.8993 0.012 0.040 0.044 0.004 0.876 0.024
#> GSM425874 4 0.0820 0.8696 0.012 0.016 0.000 0.972 0.000 0.000
#> GSM425875 5 0.1714 0.9042 0.024 0.000 0.000 0.024 0.936 0.016
#> GSM425876 6 0.3470 0.4711 0.248 0.000 0.000 0.000 0.012 0.740
#> GSM425877 1 0.3852 0.6071 0.796 0.000 0.000 0.120 0.064 0.020
#> GSM425878 1 0.5765 0.1587 0.464 0.000 0.000 0.044 0.064 0.428
#> GSM425879 2 0.3867 0.7947 0.008 0.760 0.000 0.000 0.040 0.192
#> GSM425880 5 0.1887 0.9082 0.024 0.000 0.008 0.020 0.932 0.016
#> GSM425881 6 0.4219 0.5768 0.036 0.304 0.000 0.000 0.000 0.660
#> GSM425882 2 0.4139 0.7850 0.008 0.732 0.000 0.000 0.048 0.212
#> GSM425883 1 0.6206 0.4082 0.472 0.000 0.000 0.296 0.016 0.216
#> GSM425884 1 0.5099 0.3453 0.588 0.000 0.000 0.016 0.060 0.336
#> GSM425885 4 0.2653 0.8379 0.004 0.060 0.000 0.888 0.024 0.024
#> GSM425848 4 0.4873 0.6495 0.172 0.004 0.000 0.716 0.072 0.036
#> GSM425849 6 0.7018 -0.2299 0.304 0.000 0.000 0.232 0.072 0.392
#> GSM425850 6 0.3809 0.4517 0.264 0.000 0.000 0.008 0.012 0.716
#> GSM425851 1 0.1787 0.6101 0.920 0.000 0.000 0.068 0.004 0.008
#> GSM425852 5 0.2123 0.8902 0.052 0.000 0.000 0.012 0.912 0.024
#> GSM425893 2 0.4380 0.7737 0.012 0.716 0.000 0.000 0.056 0.216
#> GSM425894 2 0.0748 0.8166 0.000 0.976 0.000 0.016 0.004 0.004
#> GSM425895 2 0.0508 0.8166 0.000 0.984 0.000 0.012 0.000 0.004
#> GSM425896 2 0.4255 0.7896 0.012 0.748 0.000 0.004 0.056 0.180
#> GSM425897 2 0.4239 0.7878 0.012 0.736 0.000 0.000 0.056 0.196
#> GSM425898 2 0.0993 0.8093 0.000 0.964 0.000 0.012 0.000 0.024
#> GSM425899 2 0.2685 0.7528 0.000 0.872 0.000 0.044 0.004 0.080
#> GSM425900 2 0.2631 0.6803 0.000 0.820 0.000 0.000 0.000 0.180
#> GSM425901 5 0.2759 0.8998 0.012 0.032 0.044 0.008 0.892 0.012
#> GSM425902 4 0.1381 0.8667 0.004 0.020 0.000 0.952 0.004 0.020
#> GSM425903 5 0.2750 0.9038 0.012 0.008 0.036 0.004 0.888 0.052
#> GSM425904 5 0.1887 0.9082 0.024 0.000 0.008 0.020 0.932 0.016
#> GSM425905 2 0.3279 0.8103 0.008 0.816 0.000 0.000 0.028 0.148
#> GSM425906 2 0.3023 0.6080 0.000 0.768 0.000 0.000 0.000 0.232
#> GSM425863 1 0.7075 0.3082 0.340 0.000 0.000 0.268 0.068 0.324
#> GSM425864 2 0.3960 0.7942 0.008 0.760 0.000 0.000 0.052 0.180
#> GSM425865 2 0.3960 0.7942 0.008 0.760 0.000 0.000 0.052 0.180
#> GSM425866 5 0.1774 0.9069 0.024 0.000 0.004 0.020 0.936 0.016
#> GSM425867 5 0.2526 0.8909 0.004 0.000 0.096 0.000 0.876 0.024
#> GSM425868 2 0.1337 0.8197 0.008 0.956 0.000 0.008 0.016 0.012
#> GSM425869 2 0.0862 0.8183 0.000 0.972 0.000 0.016 0.008 0.004
#> GSM425870 6 0.6024 0.1765 0.012 0.236 0.056 0.000 0.092 0.604
#> GSM425871 1 0.5169 0.1229 0.476 0.000 0.000 0.044 0.020 0.460
#> GSM425872 2 0.1074 0.8074 0.000 0.960 0.000 0.012 0.000 0.028
#> GSM425873 6 0.3882 0.4566 0.260 0.000 0.000 0.012 0.012 0.716
#> GSM425843 1 0.5324 0.4612 0.640 0.000 0.000 0.052 0.060 0.248
#> GSM425844 1 0.3207 0.5874 0.828 0.000 0.000 0.044 0.004 0.124
#> GSM425845 5 0.2265 0.8893 0.004 0.008 0.008 0.000 0.896 0.084
#> GSM425846 2 0.2145 0.7733 0.000 0.900 0.000 0.028 0.000 0.072
#> GSM425847 6 0.4043 0.5690 0.128 0.116 0.000 0.000 0.000 0.756
#> GSM425886 5 0.2759 0.8998 0.012 0.032 0.044 0.008 0.892 0.012
#> GSM425887 6 0.4241 0.5124 0.020 0.348 0.000 0.004 0.000 0.628
#> GSM425888 6 0.4209 0.4693 0.012 0.396 0.000 0.004 0.000 0.588
#> GSM425889 4 0.3875 0.7624 0.124 0.000 0.000 0.796 0.052 0.028
#> GSM425890 4 0.4094 0.5885 0.324 0.000 0.000 0.652 0.000 0.024
#> GSM425891 2 0.1957 0.8160 0.000 0.888 0.000 0.000 0.000 0.112
#> GSM425892 2 0.3911 0.7990 0.008 0.772 0.000 0.004 0.044 0.172
#> GSM425853 6 0.6378 -0.1113 0.356 0.000 0.000 0.020 0.216 0.408
#> GSM425854 2 0.0508 0.8166 0.000 0.984 0.000 0.012 0.000 0.004
#> GSM425855 1 0.6916 0.4270 0.428 0.000 0.000 0.272 0.068 0.232
#> GSM425856 5 0.1774 0.9069 0.024 0.000 0.004 0.020 0.936 0.016
#> GSM425857 5 0.2921 0.8935 0.012 0.036 0.024 0.024 0.888 0.016
#> GSM425858 2 0.3601 0.4214 0.000 0.684 0.000 0.004 0.000 0.312
#> GSM425859 2 0.0862 0.8183 0.000 0.972 0.000 0.016 0.008 0.004
#> GSM425860 6 0.3917 0.5922 0.080 0.132 0.000 0.000 0.008 0.780
#> GSM425861 6 0.4586 0.5827 0.052 0.260 0.000 0.012 0.000 0.676
#> GSM425862 4 0.3875 0.7624 0.124 0.000 0.000 0.796 0.052 0.028
#> GSM425837 1 0.6422 0.4815 0.536 0.000 0.000 0.148 0.072 0.244
#> GSM425838 4 0.2775 0.8539 0.060 0.016 0.000 0.884 0.012 0.028
#> GSM425839 2 0.0653 0.8170 0.000 0.980 0.000 0.012 0.004 0.004
#> GSM425840 1 0.6035 0.4498 0.564 0.000 0.000 0.104 0.060 0.272
#> GSM425841 4 0.0717 0.8698 0.008 0.016 0.000 0.976 0.000 0.000
#> GSM425842 6 0.3948 0.4390 0.272 0.000 0.000 0.012 0.012 0.704
#> GSM425917 1 0.4817 0.1309 0.564 0.000 0.388 0.036 0.000 0.012
#> GSM425922 4 0.1556 0.8463 0.080 0.000 0.000 0.920 0.000 0.000
#> GSM425919 1 0.1493 0.6013 0.936 0.000 0.000 0.004 0.004 0.056
#> GSM425920 1 0.1949 0.5958 0.904 0.000 0.000 0.004 0.004 0.088
#> GSM425923 1 0.3129 0.5276 0.820 0.000 0.000 0.152 0.004 0.024
#> GSM425916 1 0.1788 0.6083 0.916 0.000 0.000 0.076 0.004 0.004
#> GSM425918 1 0.1814 0.5993 0.900 0.000 0.000 0.100 0.000 0.000
#> GSM425921 4 0.1556 0.8463 0.080 0.000 0.000 0.920 0.000 0.000
#> GSM425925 4 0.0964 0.8610 0.016 0.000 0.000 0.968 0.012 0.004
#> GSM425926 4 0.0820 0.8703 0.016 0.012 0.000 0.972 0.000 0.000
#> GSM425927 6 0.4408 -0.0496 0.468 0.000 0.000 0.012 0.008 0.512
#> GSM425924 1 0.4885 0.4016 0.656 0.000 0.268 0.028 0.000 0.048
#> GSM425928 3 0.0508 0.9887 0.004 0.000 0.984 0.000 0.000 0.012
#> GSM425929 3 0.0000 0.9974 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425930 3 0.0000 0.9974 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425931 3 0.0000 0.9974 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425932 3 0.0000 0.9974 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425933 3 0.0000 0.9974 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425934 3 0.0000 0.9974 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425935 3 0.0146 0.9955 0.000 0.000 0.996 0.000 0.000 0.004
#> GSM425936 3 0.0000 0.9974 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425937 3 0.0000 0.9974 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425938 3 0.0508 0.9887 0.004 0.000 0.984 0.000 0.000 0.012
#> GSM425939 3 0.0000 0.9974 0.000 0.000 1.000 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 disease.state(p) tissue(p) other(p) k
#> SD:kmeans 96 9.06e-04 6.30e-05 2.95e-07 2
#> SD:kmeans 76 5.21e-10 1.54e-10 1.26e-09 3
#> SD:kmeans 79 3.64e-11 2.36e-12 4.37e-08 4
#> SD:kmeans 85 1.52e-17 6.13e-18 1.87e-11 5
#> SD:kmeans 81 5.18e-16 8.57e-20 3.80e-11 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 103 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 0.915 0.900 0.956 0.5044 0.496 0.496
#> 3 3 0.769 0.841 0.926 0.3248 0.693 0.457
#> 4 4 0.740 0.701 0.842 0.1068 0.897 0.707
#> 5 5 0.761 0.750 0.853 0.0703 0.888 0.618
#> 6 6 0.765 0.590 0.787 0.0527 0.903 0.582
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
#> GSM425907 2 0.0000 0.967 0.000 1.000
#> GSM425908 2 0.1843 0.958 0.028 0.972
#> GSM425909 2 0.0938 0.962 0.012 0.988
#> GSM425910 1 0.9815 0.330 0.580 0.420
#> GSM425911 2 0.0000 0.967 0.000 1.000
#> GSM425912 2 0.6343 0.806 0.160 0.840
#> GSM425913 2 0.0000 0.967 0.000 1.000
#> GSM425914 2 0.2603 0.939 0.044 0.956
#> GSM425915 2 0.0000 0.967 0.000 1.000
#> GSM425874 1 0.2423 0.918 0.960 0.040
#> GSM425875 1 0.0000 0.938 1.000 0.000
#> GSM425876 1 0.2043 0.923 0.968 0.032
#> GSM425877 1 0.0000 0.938 1.000 0.000
#> GSM425878 1 0.0000 0.938 1.000 0.000
#> GSM425879 2 0.0000 0.967 0.000 1.000
#> GSM425880 1 0.1843 0.925 0.972 0.028
#> GSM425881 1 0.7528 0.715 0.784 0.216
#> GSM425882 2 0.2043 0.956 0.032 0.968
#> GSM425883 1 0.0000 0.938 1.000 0.000
#> GSM425884 1 0.0000 0.938 1.000 0.000
#> GSM425885 2 0.9850 0.230 0.428 0.572
#> GSM425848 1 0.0000 0.938 1.000 0.000
#> GSM425849 1 0.0000 0.938 1.000 0.000
#> GSM425850 1 0.0000 0.938 1.000 0.000
#> GSM425851 1 0.0000 0.938 1.000 0.000
#> GSM425852 1 0.2043 0.923 0.968 0.032
#> GSM425893 2 0.0000 0.967 0.000 1.000
#> GSM425894 2 0.1843 0.958 0.028 0.972
#> GSM425895 2 0.1843 0.958 0.028 0.972
#> GSM425896 2 0.0000 0.967 0.000 1.000
#> GSM425897 2 0.0000 0.967 0.000 1.000
#> GSM425898 2 0.1843 0.958 0.028 0.972
#> GSM425899 1 0.0000 0.938 1.000 0.000
#> GSM425900 2 0.3733 0.926 0.072 0.928
#> GSM425901 2 0.2603 0.938 0.044 0.956
#> GSM425902 1 0.2603 0.915 0.956 0.044
#> GSM425903 2 0.2603 0.939 0.044 0.956
#> GSM425904 1 0.1843 0.925 0.972 0.028
#> GSM425905 2 0.0000 0.967 0.000 1.000
#> GSM425906 2 0.0000 0.967 0.000 1.000
#> GSM425863 1 0.0000 0.938 1.000 0.000
#> GSM425864 2 0.0000 0.967 0.000 1.000
#> GSM425865 2 0.0000 0.967 0.000 1.000
#> GSM425866 1 0.1843 0.925 0.972 0.028
#> GSM425867 2 0.2778 0.936 0.048 0.952
#> GSM425868 2 0.2778 0.944 0.048 0.952
#> GSM425869 2 0.1843 0.958 0.028 0.972
#> GSM425870 2 0.0000 0.967 0.000 1.000
#> GSM425871 1 0.0000 0.938 1.000 0.000
#> GSM425872 2 0.1843 0.958 0.028 0.972
#> GSM425873 1 0.0000 0.938 1.000 0.000
#> GSM425843 1 0.0000 0.938 1.000 0.000
#> GSM425844 1 0.0000 0.938 1.000 0.000
#> GSM425845 1 0.9815 0.330 0.580 0.420
#> GSM425846 1 0.0000 0.938 1.000 0.000
#> GSM425847 1 0.3114 0.902 0.944 0.056
#> GSM425886 2 0.0000 0.967 0.000 1.000
#> GSM425887 1 0.9944 0.185 0.544 0.456
#> GSM425888 1 0.4939 0.852 0.892 0.108
#> GSM425889 1 0.0000 0.938 1.000 0.000
#> GSM425890 1 0.2603 0.915 0.956 0.044
#> GSM425891 2 0.0000 0.967 0.000 1.000
#> GSM425892 2 0.1843 0.958 0.028 0.972
#> GSM425853 1 0.1184 0.931 0.984 0.016
#> GSM425854 2 0.1843 0.958 0.028 0.972
#> GSM425855 1 0.0000 0.938 1.000 0.000
#> GSM425856 1 0.1843 0.925 0.972 0.028
#> GSM425857 2 0.3274 0.922 0.060 0.940
#> GSM425858 1 0.9922 0.211 0.552 0.448
#> GSM425859 2 0.1843 0.958 0.028 0.972
#> GSM425860 2 0.7299 0.738 0.204 0.796
#> GSM425861 1 0.0000 0.938 1.000 0.000
#> GSM425862 1 0.0000 0.938 1.000 0.000
#> GSM425837 1 0.0000 0.938 1.000 0.000
#> GSM425838 1 0.2778 0.912 0.952 0.048
#> GSM425839 2 0.1843 0.958 0.028 0.972
#> GSM425840 1 0.0000 0.938 1.000 0.000
#> GSM425841 1 0.2603 0.915 0.956 0.044
#> GSM425842 1 0.0000 0.938 1.000 0.000
#> GSM425917 2 0.0000 0.967 0.000 1.000
#> GSM425922 1 0.2603 0.915 0.956 0.044
#> GSM425919 1 0.0000 0.938 1.000 0.000
#> GSM425920 1 0.0000 0.938 1.000 0.000
#> GSM425923 1 0.0000 0.938 1.000 0.000
#> GSM425916 1 0.0000 0.938 1.000 0.000
#> GSM425918 1 0.0000 0.938 1.000 0.000
#> GSM425921 1 0.2603 0.915 0.956 0.044
#> GSM425925 1 0.0000 0.938 1.000 0.000
#> GSM425926 1 0.2043 0.923 0.968 0.032
#> GSM425927 1 0.0000 0.938 1.000 0.000
#> GSM425924 1 0.9732 0.366 0.596 0.404
#> GSM425928 2 0.0000 0.967 0.000 1.000
#> GSM425929 2 0.0000 0.967 0.000 1.000
#> GSM425930 2 0.0000 0.967 0.000 1.000
#> GSM425931 2 0.0000 0.967 0.000 1.000
#> GSM425932 2 0.0000 0.967 0.000 1.000
#> GSM425933 2 0.0000 0.967 0.000 1.000
#> GSM425934 2 0.0000 0.967 0.000 1.000
#> GSM425935 2 0.0000 0.967 0.000 1.000
#> GSM425936 2 0.0000 0.967 0.000 1.000
#> GSM425937 2 0.0000 0.967 0.000 1.000
#> GSM425938 2 0.0000 0.967 0.000 1.000
#> GSM425939 2 0.0000 0.967 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.0000 0.9026 0.000 1.000 0.000
#> GSM425908 2 0.0000 0.9026 0.000 1.000 0.000
#> GSM425909 3 0.0000 0.9325 0.000 0.000 1.000
#> GSM425910 3 0.7605 0.6312 0.252 0.088 0.660
#> GSM425911 2 0.5327 0.6280 0.000 0.728 0.272
#> GSM425912 2 0.5178 0.6679 0.256 0.744 0.000
#> GSM425913 2 0.0000 0.9026 0.000 1.000 0.000
#> GSM425914 2 0.6949 0.6974 0.112 0.732 0.156
#> GSM425915 3 0.0000 0.9325 0.000 0.000 1.000
#> GSM425874 1 0.5138 0.7048 0.748 0.252 0.000
#> GSM425875 1 0.3482 0.7937 0.872 0.000 0.128
#> GSM425876 1 0.3039 0.8588 0.920 0.044 0.036
#> GSM425877 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425878 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425879 2 0.0892 0.8939 0.000 0.980 0.020
#> GSM425880 3 0.2448 0.8931 0.076 0.000 0.924
#> GSM425881 2 0.5216 0.6630 0.260 0.740 0.000
#> GSM425882 2 0.0000 0.9026 0.000 1.000 0.000
#> GSM425883 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425884 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425885 2 0.6291 -0.0536 0.468 0.532 0.000
#> GSM425848 1 0.2878 0.8509 0.904 0.096 0.000
#> GSM425849 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425850 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425851 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425852 3 0.1411 0.9162 0.036 0.000 0.964
#> GSM425893 2 0.5529 0.5917 0.000 0.704 0.296
#> GSM425894 2 0.0000 0.9026 0.000 1.000 0.000
#> GSM425895 2 0.0000 0.9026 0.000 1.000 0.000
#> GSM425896 2 0.0592 0.8969 0.000 0.988 0.012
#> GSM425897 2 0.1163 0.8886 0.000 0.972 0.028
#> GSM425898 2 0.0000 0.9026 0.000 1.000 0.000
#> GSM425899 2 0.1753 0.8679 0.048 0.952 0.000
#> GSM425900 2 0.0424 0.8994 0.008 0.992 0.000
#> GSM425901 3 0.0000 0.9325 0.000 0.000 1.000
#> GSM425902 1 0.5291 0.6836 0.732 0.268 0.000
#> GSM425903 3 0.0000 0.9325 0.000 0.000 1.000
#> GSM425904 3 0.1643 0.9130 0.044 0.000 0.956
#> GSM425905 2 0.0000 0.9026 0.000 1.000 0.000
#> GSM425906 2 0.0237 0.9012 0.004 0.996 0.000
#> GSM425863 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425864 2 0.0237 0.9013 0.000 0.996 0.004
#> GSM425865 2 0.0000 0.9026 0.000 1.000 0.000
#> GSM425866 3 0.5465 0.6569 0.288 0.000 0.712
#> GSM425867 3 0.0000 0.9325 0.000 0.000 1.000
#> GSM425868 2 0.0000 0.9026 0.000 1.000 0.000
#> GSM425869 2 0.0000 0.9026 0.000 1.000 0.000
#> GSM425870 3 0.0000 0.9325 0.000 0.000 1.000
#> GSM425871 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425872 2 0.0000 0.9026 0.000 1.000 0.000
#> GSM425873 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425843 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425844 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425845 3 0.4887 0.7347 0.228 0.000 0.772
#> GSM425846 2 0.0000 0.9026 0.000 1.000 0.000
#> GSM425847 2 0.6307 0.1623 0.488 0.512 0.000
#> GSM425886 3 0.0000 0.9325 0.000 0.000 1.000
#> GSM425887 2 0.5016 0.6864 0.240 0.760 0.000
#> GSM425888 2 0.5254 0.6580 0.264 0.736 0.000
#> GSM425889 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425890 1 0.5098 0.7095 0.752 0.248 0.000
#> GSM425891 2 0.0000 0.9026 0.000 1.000 0.000
#> GSM425892 2 0.0000 0.9026 0.000 1.000 0.000
#> GSM425853 1 0.1031 0.8981 0.976 0.000 0.024
#> GSM425854 2 0.0000 0.9026 0.000 1.000 0.000
#> GSM425855 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425856 3 0.5529 0.6444 0.296 0.000 0.704
#> GSM425857 3 0.2537 0.8719 0.000 0.080 0.920
#> GSM425858 2 0.1753 0.8741 0.048 0.952 0.000
#> GSM425859 2 0.0000 0.9026 0.000 1.000 0.000
#> GSM425860 3 0.7975 0.6336 0.204 0.140 0.656
#> GSM425861 1 0.5988 0.3105 0.632 0.368 0.000
#> GSM425862 1 0.0237 0.9121 0.996 0.004 0.000
#> GSM425837 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425838 1 0.5178 0.6998 0.744 0.256 0.000
#> GSM425839 2 0.0000 0.9026 0.000 1.000 0.000
#> GSM425840 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425841 1 0.5216 0.6944 0.740 0.260 0.000
#> GSM425842 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425917 3 0.2796 0.8716 0.092 0.000 0.908
#> GSM425922 1 0.5058 0.7142 0.756 0.244 0.000
#> GSM425919 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425920 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425923 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425916 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425918 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425921 1 0.5058 0.7142 0.756 0.244 0.000
#> GSM425925 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425926 1 0.5058 0.7142 0.756 0.244 0.000
#> GSM425927 1 0.0000 0.9142 1.000 0.000 0.000
#> GSM425924 3 0.1964 0.9012 0.056 0.000 0.944
#> GSM425928 3 0.0000 0.9325 0.000 0.000 1.000
#> GSM425929 3 0.0000 0.9325 0.000 0.000 1.000
#> GSM425930 3 0.0000 0.9325 0.000 0.000 1.000
#> GSM425931 3 0.0000 0.9325 0.000 0.000 1.000
#> GSM425932 3 0.0000 0.9325 0.000 0.000 1.000
#> GSM425933 3 0.0000 0.9325 0.000 0.000 1.000
#> GSM425934 3 0.0000 0.9325 0.000 0.000 1.000
#> GSM425935 3 0.0000 0.9325 0.000 0.000 1.000
#> GSM425936 3 0.0000 0.9325 0.000 0.000 1.000
#> GSM425937 3 0.0000 0.9325 0.000 0.000 1.000
#> GSM425938 3 0.0000 0.9325 0.000 0.000 1.000
#> GSM425939 3 0.0000 0.9325 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.0188 0.89507 0.004 0.996 0.000 0.000
#> GSM425908 2 0.0188 0.89507 0.004 0.996 0.000 0.000
#> GSM425909 1 0.5163 0.30938 0.516 0.004 0.480 0.000
#> GSM425910 1 0.0188 0.57593 0.996 0.000 0.004 0.000
#> GSM425911 2 0.3149 0.81801 0.088 0.880 0.032 0.000
#> GSM425912 2 0.5570 0.36382 0.440 0.540 0.000 0.020
#> GSM425913 2 0.0336 0.89362 0.008 0.992 0.000 0.000
#> GSM425914 2 0.4961 0.38565 0.448 0.552 0.000 0.000
#> GSM425915 1 0.4998 0.29671 0.512 0.000 0.488 0.000
#> GSM425874 4 0.1022 0.78577 0.000 0.032 0.000 0.968
#> GSM425875 1 0.1584 0.57918 0.952 0.000 0.012 0.036
#> GSM425876 1 0.2053 0.50322 0.924 0.004 0.000 0.072
#> GSM425877 4 0.2647 0.77743 0.120 0.000 0.000 0.880
#> GSM425878 4 0.4948 0.57746 0.440 0.000 0.000 0.560
#> GSM425879 2 0.0592 0.89204 0.016 0.984 0.000 0.000
#> GSM425880 1 0.4718 0.50271 0.708 0.000 0.280 0.012
#> GSM425881 2 0.5716 0.37945 0.420 0.552 0.000 0.028
#> GSM425882 2 0.0188 0.89507 0.004 0.996 0.000 0.000
#> GSM425883 4 0.0469 0.79500 0.012 0.000 0.000 0.988
#> GSM425884 4 0.4972 0.55868 0.456 0.000 0.000 0.544
#> GSM425885 4 0.4137 0.61780 0.012 0.208 0.000 0.780
#> GSM425848 4 0.1174 0.78738 0.020 0.012 0.000 0.968
#> GSM425849 4 0.4843 0.61114 0.396 0.000 0.000 0.604
#> GSM425850 4 0.4994 0.53318 0.480 0.000 0.000 0.520
#> GSM425851 4 0.1022 0.79465 0.032 0.000 0.000 0.968
#> GSM425852 1 0.4877 0.40158 0.592 0.000 0.408 0.000
#> GSM425893 2 0.5722 0.60629 0.136 0.716 0.148 0.000
#> GSM425894 2 0.0000 0.89514 0.000 1.000 0.000 0.000
#> GSM425895 2 0.0000 0.89514 0.000 1.000 0.000 0.000
#> GSM425896 2 0.0376 0.89384 0.004 0.992 0.004 0.000
#> GSM425897 2 0.0336 0.89454 0.008 0.992 0.000 0.000
#> GSM425898 2 0.0000 0.89514 0.000 1.000 0.000 0.000
#> GSM425899 2 0.2282 0.85435 0.024 0.924 0.000 0.052
#> GSM425900 2 0.1209 0.88322 0.032 0.964 0.004 0.000
#> GSM425901 1 0.5163 0.30938 0.516 0.004 0.480 0.000
#> GSM425902 4 0.1661 0.77353 0.004 0.052 0.000 0.944
#> GSM425903 1 0.4907 0.39155 0.580 0.000 0.420 0.000
#> GSM425904 1 0.5038 0.46865 0.652 0.000 0.336 0.012
#> GSM425905 2 0.0000 0.89514 0.000 1.000 0.000 0.000
#> GSM425906 2 0.1109 0.88504 0.028 0.968 0.004 0.000
#> GSM425863 4 0.4697 0.64642 0.356 0.000 0.000 0.644
#> GSM425864 2 0.0188 0.89507 0.004 0.996 0.000 0.000
#> GSM425865 2 0.0188 0.89507 0.004 0.996 0.000 0.000
#> GSM425866 1 0.1284 0.58206 0.964 0.000 0.024 0.012
#> GSM425867 1 0.4992 0.31980 0.524 0.000 0.476 0.000
#> GSM425868 2 0.1867 0.84675 0.000 0.928 0.000 0.072
#> GSM425869 2 0.0000 0.89514 0.000 1.000 0.000 0.000
#> GSM425870 3 0.2408 0.80979 0.104 0.000 0.896 0.000
#> GSM425871 4 0.3444 0.75401 0.184 0.000 0.000 0.816
#> GSM425872 2 0.0000 0.89514 0.000 1.000 0.000 0.000
#> GSM425873 4 0.4992 0.53722 0.476 0.000 0.000 0.524
#> GSM425843 4 0.4967 0.56406 0.452 0.000 0.000 0.548
#> GSM425844 4 0.0921 0.79454 0.028 0.000 0.000 0.972
#> GSM425845 1 0.0817 0.58016 0.976 0.000 0.024 0.000
#> GSM425846 2 0.2334 0.84295 0.088 0.908 0.000 0.004
#> GSM425847 1 0.6915 -0.14899 0.476 0.416 0.000 0.108
#> GSM425886 1 0.5163 0.30938 0.516 0.004 0.480 0.000
#> GSM425887 2 0.5217 0.48209 0.380 0.608 0.000 0.012
#> GSM425888 2 0.5756 0.40947 0.400 0.568 0.000 0.032
#> GSM425889 4 0.0188 0.79364 0.004 0.000 0.000 0.996
#> GSM425890 4 0.0817 0.78876 0.000 0.024 0.000 0.976
#> GSM425891 2 0.0336 0.89362 0.008 0.992 0.000 0.000
#> GSM425892 2 0.0188 0.89507 0.004 0.996 0.000 0.000
#> GSM425853 1 0.1302 0.54744 0.956 0.000 0.000 0.044
#> GSM425854 2 0.0000 0.89514 0.000 1.000 0.000 0.000
#> GSM425855 4 0.2530 0.77874 0.112 0.000 0.000 0.888
#> GSM425856 1 0.1488 0.58233 0.956 0.000 0.032 0.012
#> GSM425857 1 0.6283 0.32842 0.512 0.024 0.444 0.020
#> GSM425858 2 0.2610 0.83916 0.088 0.900 0.000 0.012
#> GSM425859 2 0.0000 0.89514 0.000 1.000 0.000 0.000
#> GSM425860 1 0.5677 0.02224 0.504 0.016 0.476 0.004
#> GSM425861 1 0.7613 -0.00022 0.448 0.340 0.000 0.212
#> GSM425862 4 0.0188 0.79364 0.004 0.000 0.000 0.996
#> GSM425837 4 0.4776 0.63409 0.376 0.000 0.000 0.624
#> GSM425838 4 0.1211 0.78223 0.000 0.040 0.000 0.960
#> GSM425839 2 0.0000 0.89514 0.000 1.000 0.000 0.000
#> GSM425840 4 0.4277 0.70128 0.280 0.000 0.000 0.720
#> GSM425841 4 0.1302 0.77950 0.000 0.044 0.000 0.956
#> GSM425842 4 0.4989 0.54151 0.472 0.000 0.000 0.528
#> GSM425917 3 0.4673 0.52196 0.008 0.000 0.700 0.292
#> GSM425922 4 0.0817 0.78876 0.000 0.024 0.000 0.976
#> GSM425919 4 0.4746 0.64331 0.368 0.000 0.000 0.632
#> GSM425920 4 0.3219 0.76386 0.164 0.000 0.000 0.836
#> GSM425923 4 0.0000 0.79372 0.000 0.000 0.000 1.000
#> GSM425916 4 0.1022 0.79465 0.032 0.000 0.000 0.968
#> GSM425918 4 0.0336 0.79453 0.008 0.000 0.000 0.992
#> GSM425921 4 0.0817 0.78876 0.000 0.024 0.000 0.976
#> GSM425925 4 0.0000 0.79372 0.000 0.000 0.000 1.000
#> GSM425926 4 0.0817 0.78876 0.000 0.024 0.000 0.976
#> GSM425927 4 0.4989 0.54151 0.472 0.000 0.000 0.528
#> GSM425924 3 0.3577 0.71625 0.012 0.000 0.832 0.156
#> GSM425928 3 0.0000 0.93514 0.000 0.000 1.000 0.000
#> GSM425929 3 0.0000 0.93514 0.000 0.000 1.000 0.000
#> GSM425930 3 0.0000 0.93514 0.000 0.000 1.000 0.000
#> GSM425931 3 0.0000 0.93514 0.000 0.000 1.000 0.000
#> GSM425932 3 0.0000 0.93514 0.000 0.000 1.000 0.000
#> GSM425933 3 0.0000 0.93514 0.000 0.000 1.000 0.000
#> GSM425934 3 0.0000 0.93514 0.000 0.000 1.000 0.000
#> GSM425935 3 0.0000 0.93514 0.000 0.000 1.000 0.000
#> GSM425936 3 0.0000 0.93514 0.000 0.000 1.000 0.000
#> GSM425937 3 0.0000 0.93514 0.000 0.000 1.000 0.000
#> GSM425938 3 0.0000 0.93514 0.000 0.000 1.000 0.000
#> GSM425939 3 0.0000 0.93514 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
#> GSM425907 2 0.2802 0.8757 0.100 0.876 0.000 0.008 0.016
#> GSM425908 2 0.3016 0.8746 0.100 0.868 0.000 0.016 0.016
#> GSM425909 5 0.0880 0.9400 0.000 0.000 0.032 0.000 0.968
#> GSM425910 1 0.1638 0.6319 0.932 0.004 0.000 0.000 0.064
#> GSM425911 2 0.5389 0.7292 0.204 0.688 0.016 0.000 0.092
#> GSM425912 1 0.3612 0.4602 0.732 0.268 0.000 0.000 0.000
#> GSM425913 2 0.1357 0.8825 0.048 0.948 0.000 0.000 0.004
#> GSM425914 1 0.5432 0.0611 0.564 0.376 0.004 0.000 0.056
#> GSM425915 5 0.1043 0.9375 0.000 0.000 0.040 0.000 0.960
#> GSM425874 4 0.0609 0.8041 0.000 0.020 0.000 0.980 0.000
#> GSM425875 5 0.0703 0.9381 0.024 0.000 0.000 0.000 0.976
#> GSM425876 1 0.0324 0.6459 0.992 0.000 0.000 0.004 0.004
#> GSM425877 4 0.4382 0.6137 0.288 0.000 0.000 0.688 0.024
#> GSM425878 1 0.4193 0.4052 0.684 0.000 0.000 0.304 0.012
#> GSM425879 2 0.2470 0.8764 0.104 0.884 0.000 0.000 0.012
#> GSM425880 5 0.0798 0.9416 0.016 0.000 0.008 0.000 0.976
#> GSM425881 1 0.3949 0.4857 0.668 0.332 0.000 0.000 0.000
#> GSM425882 2 0.3201 0.8647 0.132 0.844 0.000 0.008 0.016
#> GSM425883 4 0.2358 0.7833 0.104 0.000 0.000 0.888 0.008
#> GSM425884 1 0.4141 0.4947 0.736 0.000 0.000 0.236 0.028
#> GSM425885 4 0.3132 0.6392 0.000 0.172 0.000 0.820 0.008
#> GSM425848 4 0.1662 0.7907 0.004 0.004 0.000 0.936 0.056
#> GSM425849 4 0.4537 0.3542 0.396 0.000 0.000 0.592 0.012
#> GSM425850 1 0.2286 0.6301 0.888 0.000 0.000 0.108 0.004
#> GSM425851 4 0.4290 0.5855 0.304 0.000 0.000 0.680 0.016
#> GSM425852 5 0.1012 0.9427 0.012 0.000 0.020 0.000 0.968
#> GSM425893 2 0.6265 0.5307 0.124 0.564 0.016 0.000 0.296
#> GSM425894 2 0.0703 0.8769 0.000 0.976 0.000 0.024 0.000
#> GSM425895 2 0.0290 0.8788 0.000 0.992 0.000 0.008 0.000
#> GSM425896 2 0.2802 0.8745 0.100 0.876 0.000 0.008 0.016
#> GSM425897 2 0.2967 0.8740 0.104 0.868 0.012 0.000 0.016
#> GSM425898 2 0.0693 0.8771 0.008 0.980 0.000 0.012 0.000
#> GSM425899 2 0.3997 0.7584 0.064 0.812 0.000 0.112 0.012
#> GSM425900 2 0.2179 0.8298 0.100 0.896 0.000 0.004 0.000
#> GSM425901 5 0.0955 0.9402 0.000 0.004 0.028 0.000 0.968
#> GSM425902 4 0.1121 0.7926 0.000 0.044 0.000 0.956 0.000
#> GSM425903 5 0.0955 0.9423 0.004 0.000 0.028 0.000 0.968
#> GSM425904 5 0.0807 0.9424 0.012 0.000 0.012 0.000 0.976
#> GSM425905 2 0.2069 0.8821 0.076 0.912 0.000 0.000 0.012
#> GSM425906 2 0.2377 0.8098 0.128 0.872 0.000 0.000 0.000
#> GSM425863 4 0.4270 0.5322 0.320 0.000 0.000 0.668 0.012
#> GSM425864 2 0.2519 0.8756 0.100 0.884 0.000 0.000 0.016
#> GSM425865 2 0.2802 0.8745 0.100 0.876 0.000 0.008 0.016
#> GSM425866 5 0.0794 0.9365 0.028 0.000 0.000 0.000 0.972
#> GSM425867 5 0.1544 0.9193 0.000 0.000 0.068 0.000 0.932
#> GSM425868 2 0.2911 0.7967 0.004 0.852 0.000 0.136 0.008
#> GSM425869 2 0.0880 0.8744 0.000 0.968 0.000 0.032 0.000
#> GSM425870 3 0.4768 0.7128 0.180 0.012 0.740 0.000 0.068
#> GSM425871 1 0.4434 -0.0194 0.536 0.000 0.000 0.460 0.004
#> GSM425872 2 0.0912 0.8762 0.012 0.972 0.000 0.016 0.000
#> GSM425873 1 0.1768 0.6430 0.924 0.000 0.000 0.072 0.004
#> GSM425843 1 0.4511 0.2712 0.628 0.000 0.000 0.356 0.016
#> GSM425844 4 0.4339 0.5237 0.336 0.000 0.000 0.652 0.012
#> GSM425845 5 0.1410 0.9186 0.060 0.000 0.000 0.000 0.940
#> GSM425846 2 0.3099 0.7947 0.124 0.848 0.000 0.028 0.000
#> GSM425847 1 0.2233 0.6444 0.892 0.104 0.000 0.004 0.000
#> GSM425886 5 0.0955 0.9402 0.000 0.004 0.028 0.000 0.968
#> GSM425887 1 0.4692 0.1358 0.528 0.460 0.000 0.004 0.008
#> GSM425888 1 0.4356 0.4762 0.648 0.340 0.000 0.012 0.000
#> GSM425889 4 0.0451 0.8079 0.008 0.000 0.000 0.988 0.004
#> GSM425890 4 0.0693 0.8073 0.000 0.012 0.000 0.980 0.008
#> GSM425891 2 0.1851 0.8824 0.088 0.912 0.000 0.000 0.000
#> GSM425892 2 0.3059 0.8763 0.096 0.868 0.000 0.020 0.016
#> GSM425853 5 0.5037 0.3188 0.376 0.000 0.000 0.040 0.584
#> GSM425854 2 0.0162 0.8794 0.000 0.996 0.000 0.004 0.000
#> GSM425855 4 0.3659 0.6781 0.220 0.000 0.000 0.768 0.012
#> GSM425856 5 0.0794 0.9365 0.028 0.000 0.000 0.000 0.972
#> GSM425857 5 0.1419 0.9311 0.000 0.012 0.016 0.016 0.956
#> GSM425858 2 0.3561 0.6079 0.260 0.740 0.000 0.000 0.000
#> GSM425859 2 0.0510 0.8780 0.000 0.984 0.000 0.016 0.000
#> GSM425860 1 0.4801 0.4542 0.692 0.028 0.264 0.000 0.016
#> GSM425861 1 0.4384 0.6114 0.728 0.228 0.000 0.044 0.000
#> GSM425862 4 0.0324 0.8080 0.004 0.000 0.000 0.992 0.004
#> GSM425837 4 0.4599 0.4833 0.356 0.000 0.000 0.624 0.020
#> GSM425838 4 0.1041 0.7983 0.000 0.032 0.000 0.964 0.004
#> GSM425839 2 0.0290 0.8788 0.000 0.992 0.000 0.008 0.000
#> GSM425840 4 0.4613 0.4714 0.360 0.000 0.000 0.620 0.020
#> GSM425841 4 0.1043 0.7941 0.000 0.040 0.000 0.960 0.000
#> GSM425842 1 0.2439 0.6246 0.876 0.000 0.000 0.120 0.004
#> GSM425917 3 0.1251 0.9407 0.000 0.000 0.956 0.036 0.008
#> GSM425922 4 0.0404 0.8068 0.000 0.012 0.000 0.988 0.000
#> GSM425919 1 0.5155 0.4097 0.660 0.000 0.036 0.284 0.020
#> GSM425920 1 0.4815 -0.0681 0.524 0.000 0.000 0.456 0.020
#> GSM425923 4 0.1942 0.7934 0.068 0.000 0.000 0.920 0.012
#> GSM425916 4 0.4138 0.6254 0.276 0.000 0.000 0.708 0.016
#> GSM425918 4 0.2522 0.7763 0.108 0.000 0.000 0.880 0.012
#> GSM425921 4 0.0404 0.8068 0.000 0.012 0.000 0.988 0.000
#> GSM425925 4 0.0671 0.8075 0.016 0.000 0.000 0.980 0.004
#> GSM425926 4 0.0404 0.8068 0.000 0.012 0.000 0.988 0.000
#> GSM425927 1 0.2563 0.6233 0.872 0.000 0.000 0.120 0.008
#> GSM425924 3 0.0798 0.9584 0.000 0.000 0.976 0.016 0.008
#> GSM425928 3 0.0000 0.9776 0.000 0.000 1.000 0.000 0.000
#> GSM425929 3 0.0000 0.9776 0.000 0.000 1.000 0.000 0.000
#> GSM425930 3 0.0000 0.9776 0.000 0.000 1.000 0.000 0.000
#> GSM425931 3 0.0000 0.9776 0.000 0.000 1.000 0.000 0.000
#> GSM425932 3 0.0000 0.9776 0.000 0.000 1.000 0.000 0.000
#> GSM425933 3 0.0000 0.9776 0.000 0.000 1.000 0.000 0.000
#> GSM425934 3 0.0000 0.9776 0.000 0.000 1.000 0.000 0.000
#> GSM425935 3 0.0000 0.9776 0.000 0.000 1.000 0.000 0.000
#> GSM425936 3 0.0000 0.9776 0.000 0.000 1.000 0.000 0.000
#> GSM425937 3 0.0000 0.9776 0.000 0.000 1.000 0.000 0.000
#> GSM425938 3 0.0000 0.9776 0.000 0.000 1.000 0.000 0.000
#> GSM425939 3 0.0000 0.9776 0.000 0.000 1.000 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 2 0.0405 0.66836 0.000 0.988 0.000 0.004 0.000 0.008
#> GSM425908 2 0.0405 0.66836 0.000 0.988 0.000 0.004 0.000 0.008
#> GSM425909 5 0.0260 0.94370 0.000 0.000 0.008 0.000 0.992 0.000
#> GSM425910 1 0.6687 0.07901 0.404 0.172 0.000 0.000 0.056 0.368
#> GSM425911 2 0.4311 0.42811 0.020 0.760 0.008 0.000 0.052 0.160
#> GSM425912 6 0.5227 0.32747 0.188 0.200 0.000 0.000 0.000 0.612
#> GSM425913 2 0.3810 0.33234 0.000 0.572 0.000 0.000 0.000 0.428
#> GSM425914 6 0.5749 0.16130 0.092 0.424 0.000 0.000 0.024 0.460
#> GSM425915 5 0.0547 0.93871 0.000 0.000 0.020 0.000 0.980 0.000
#> GSM425874 4 0.0260 0.82427 0.008 0.000 0.000 0.992 0.000 0.000
#> GSM425875 5 0.0551 0.93906 0.004 0.000 0.000 0.004 0.984 0.008
#> GSM425876 1 0.3714 0.46340 0.656 0.000 0.000 0.000 0.004 0.340
#> GSM425877 1 0.4278 0.35407 0.624 0.000 0.000 0.352 0.008 0.016
#> GSM425878 1 0.4024 0.63844 0.776 0.000 0.000 0.084 0.012 0.128
#> GSM425879 2 0.0458 0.66643 0.000 0.984 0.000 0.000 0.000 0.016
#> GSM425880 5 0.0146 0.94377 0.000 0.000 0.004 0.000 0.996 0.000
#> GSM425881 6 0.3231 0.43654 0.200 0.016 0.000 0.000 0.000 0.784
#> GSM425882 2 0.1644 0.62141 0.004 0.920 0.000 0.000 0.000 0.076
#> GSM425883 4 0.4264 0.66438 0.184 0.000 0.000 0.732 0.004 0.080
#> GSM425884 1 0.3080 0.64946 0.848 0.000 0.000 0.040 0.012 0.100
#> GSM425885 4 0.2512 0.72692 0.008 0.116 0.000 0.868 0.000 0.008
#> GSM425848 4 0.1592 0.81477 0.020 0.000 0.000 0.940 0.032 0.008
#> GSM425849 4 0.5467 0.20819 0.320 0.000 0.000 0.556 0.008 0.116
#> GSM425850 1 0.3699 0.46896 0.660 0.000 0.000 0.000 0.004 0.336
#> GSM425851 1 0.3405 0.49856 0.724 0.000 0.000 0.272 0.000 0.004
#> GSM425852 5 0.1010 0.92613 0.036 0.000 0.004 0.000 0.960 0.000
#> GSM425893 2 0.4387 0.39896 0.004 0.732 0.008 0.000 0.188 0.068
#> GSM425894 2 0.4532 0.25096 0.000 0.500 0.000 0.032 0.000 0.468
#> GSM425895 2 0.4336 0.24853 0.000 0.504 0.000 0.020 0.000 0.476
#> GSM425896 2 0.0146 0.66507 0.000 0.996 0.000 0.000 0.000 0.004
#> GSM425897 2 0.0806 0.65559 0.000 0.972 0.008 0.000 0.000 0.020
#> GSM425898 6 0.4405 -0.26475 0.000 0.472 0.000 0.024 0.000 0.504
#> GSM425899 6 0.6057 0.14908 0.020 0.224 0.000 0.200 0.004 0.552
#> GSM425900 6 0.3774 0.12880 0.000 0.328 0.000 0.008 0.000 0.664
#> GSM425901 5 0.0260 0.94370 0.000 0.000 0.008 0.000 0.992 0.000
#> GSM425902 4 0.1053 0.81846 0.012 0.004 0.000 0.964 0.000 0.020
#> GSM425903 5 0.0260 0.94370 0.000 0.000 0.008 0.000 0.992 0.000
#> GSM425904 5 0.0146 0.94377 0.000 0.000 0.004 0.000 0.996 0.000
#> GSM425905 2 0.1075 0.66004 0.000 0.952 0.000 0.000 0.000 0.048
#> GSM425906 6 0.3789 0.14644 0.008 0.332 0.000 0.000 0.000 0.660
#> GSM425863 4 0.5354 0.36753 0.288 0.000 0.000 0.588 0.008 0.116
#> GSM425864 2 0.0000 0.66652 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425865 2 0.0146 0.66724 0.000 0.996 0.000 0.000 0.000 0.004
#> GSM425866 5 0.0291 0.94181 0.004 0.000 0.000 0.000 0.992 0.004
#> GSM425867 5 0.1471 0.90302 0.000 0.000 0.064 0.000 0.932 0.004
#> GSM425868 2 0.5945 0.31050 0.012 0.524 0.000 0.200 0.000 0.264
#> GSM425869 2 0.4788 0.34506 0.000 0.548 0.000 0.056 0.000 0.396
#> GSM425870 3 0.6930 0.21017 0.020 0.336 0.444 0.000 0.052 0.148
#> GSM425871 1 0.4627 0.60718 0.696 0.000 0.000 0.196 0.004 0.104
#> GSM425872 6 0.4449 -0.19532 0.000 0.440 0.000 0.028 0.000 0.532
#> GSM425873 1 0.3652 0.47424 0.672 0.000 0.000 0.000 0.004 0.324
#> GSM425843 1 0.3972 0.63065 0.776 0.000 0.000 0.144 0.012 0.068
#> GSM425844 1 0.3905 0.52943 0.716 0.000 0.000 0.256 0.004 0.024
#> GSM425845 5 0.0935 0.92329 0.004 0.000 0.000 0.000 0.964 0.032
#> GSM425846 6 0.4931 0.18916 0.012 0.276 0.000 0.072 0.000 0.640
#> GSM425847 6 0.4088 -0.04635 0.436 0.004 0.000 0.000 0.004 0.556
#> GSM425886 5 0.0405 0.94308 0.000 0.004 0.008 0.000 0.988 0.000
#> GSM425887 6 0.3852 0.49463 0.116 0.088 0.000 0.000 0.008 0.788
#> GSM425888 6 0.2009 0.49548 0.068 0.024 0.000 0.000 0.000 0.908
#> GSM425889 4 0.1765 0.81656 0.052 0.000 0.000 0.924 0.000 0.024
#> GSM425890 4 0.2146 0.76982 0.116 0.000 0.000 0.880 0.000 0.004
#> GSM425891 2 0.3288 0.51345 0.000 0.724 0.000 0.000 0.000 0.276
#> GSM425892 2 0.0993 0.66614 0.000 0.964 0.000 0.012 0.000 0.024
#> GSM425853 5 0.4947 -0.00362 0.456 0.000 0.000 0.000 0.480 0.064
#> GSM425854 2 0.4039 0.35418 0.000 0.568 0.000 0.008 0.000 0.424
#> GSM425855 4 0.4855 0.41528 0.316 0.000 0.000 0.616 0.008 0.060
#> GSM425856 5 0.0291 0.94181 0.004 0.000 0.000 0.000 0.992 0.004
#> GSM425857 5 0.0862 0.93520 0.000 0.008 0.004 0.016 0.972 0.000
#> GSM425858 6 0.3141 0.35772 0.012 0.200 0.000 0.000 0.000 0.788
#> GSM425859 2 0.4025 0.36813 0.000 0.576 0.000 0.008 0.000 0.416
#> GSM425860 6 0.6438 0.10532 0.272 0.036 0.168 0.000 0.008 0.516
#> GSM425861 6 0.3329 0.40996 0.220 0.008 0.000 0.000 0.004 0.768
#> GSM425862 4 0.1682 0.81815 0.052 0.000 0.000 0.928 0.000 0.020
#> GSM425837 1 0.5157 0.23451 0.548 0.000 0.000 0.384 0.024 0.044
#> GSM425838 4 0.1464 0.81474 0.036 0.016 0.000 0.944 0.000 0.004
#> GSM425839 2 0.3986 0.29510 0.000 0.532 0.000 0.004 0.000 0.464
#> GSM425840 1 0.5207 0.25202 0.528 0.000 0.000 0.396 0.012 0.064
#> GSM425841 4 0.0405 0.82219 0.008 0.000 0.000 0.988 0.000 0.004
#> GSM425842 1 0.3565 0.52037 0.716 0.000 0.000 0.004 0.004 0.276
#> GSM425917 3 0.2882 0.81937 0.120 0.000 0.848 0.028 0.000 0.004
#> GSM425922 4 0.0937 0.81777 0.040 0.000 0.000 0.960 0.000 0.000
#> GSM425919 1 0.2808 0.63918 0.868 0.000 0.008 0.092 0.004 0.028
#> GSM425920 1 0.3166 0.60985 0.816 0.000 0.000 0.156 0.004 0.024
#> GSM425923 4 0.3955 0.21757 0.436 0.000 0.000 0.560 0.000 0.004
#> GSM425916 1 0.3646 0.46384 0.700 0.000 0.000 0.292 0.004 0.004
#> GSM425918 1 0.4083 0.06383 0.532 0.000 0.000 0.460 0.000 0.008
#> GSM425921 4 0.0547 0.82269 0.020 0.000 0.000 0.980 0.000 0.000
#> GSM425925 4 0.1219 0.81843 0.048 0.000 0.000 0.948 0.000 0.004
#> GSM425926 4 0.0260 0.82427 0.008 0.000 0.000 0.992 0.000 0.000
#> GSM425927 1 0.2902 0.57875 0.800 0.000 0.000 0.000 0.004 0.196
#> GSM425924 3 0.2355 0.84568 0.112 0.000 0.876 0.008 0.000 0.004
#> GSM425928 3 0.0000 0.94192 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425929 3 0.0000 0.94192 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425930 3 0.0000 0.94192 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425931 3 0.0000 0.94192 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425932 3 0.0000 0.94192 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425933 3 0.0000 0.94192 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425934 3 0.0000 0.94192 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425935 3 0.0000 0.94192 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425936 3 0.0000 0.94192 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425937 3 0.0000 0.94192 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425938 3 0.0000 0.94192 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425939 3 0.0000 0.94192 0.000 0.000 1.000 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 disease.state(p) tissue(p) other(p) k
#> SD:skmeans 97 7.96e-04 6.10e-05 2.11e-07 2
#> SD:skmeans 100 1.23e-07 5.81e-09 4.48e-08 3
#> SD:skmeans 86 3.05e-14 3.60e-15 1.87e-12 4
#> SD:skmeans 87 1.07e-13 9.29e-15 8.86e-08 5
#> SD:skmeans 62 2.21e-10 1.48e-10 8.94e-06 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 103 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 4.
#>
#> 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 0.731 0.878 0.938 0.4275 0.560 0.560
#> 3 3 0.466 0.509 0.769 0.4536 0.642 0.451
#> 4 4 0.603 0.661 0.845 0.1324 0.707 0.392
#> 5 5 0.597 0.499 0.752 0.0836 0.907 0.694
#> 6 6 0.677 0.575 0.781 0.0422 0.891 0.602
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 4
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
#> GSM425907 1 0.0000 0.959 1.000 0.000
#> GSM425908 1 0.0000 0.959 1.000 0.000
#> GSM425909 2 0.2423 0.874 0.040 0.960
#> GSM425910 1 0.0000 0.959 1.000 0.000
#> GSM425911 1 0.0000 0.959 1.000 0.000
#> GSM425912 1 0.0000 0.959 1.000 0.000
#> GSM425913 1 0.0000 0.959 1.000 0.000
#> GSM425914 1 0.0000 0.959 1.000 0.000
#> GSM425915 2 0.3274 0.873 0.060 0.940
#> GSM425874 1 0.0938 0.956 0.988 0.012
#> GSM425875 1 0.4815 0.873 0.896 0.104
#> GSM425876 1 0.2423 0.931 0.960 0.040
#> GSM425877 2 0.6048 0.824 0.148 0.852
#> GSM425878 1 0.0672 0.957 0.992 0.008
#> GSM425879 1 0.6438 0.770 0.836 0.164
#> GSM425880 2 0.5178 0.844 0.116 0.884
#> GSM425881 1 0.0000 0.959 1.000 0.000
#> GSM425882 1 0.0000 0.959 1.000 0.000
#> GSM425883 1 0.5629 0.847 0.868 0.132
#> GSM425884 2 0.9661 0.477 0.392 0.608
#> GSM425885 1 0.0938 0.956 0.988 0.012
#> GSM425848 1 0.3584 0.914 0.932 0.068
#> GSM425849 1 0.0938 0.956 0.988 0.012
#> GSM425850 1 0.0000 0.959 1.000 0.000
#> GSM425851 1 0.9881 0.227 0.564 0.436
#> GSM425852 2 0.0938 0.876 0.012 0.988
#> GSM425893 1 0.0000 0.959 1.000 0.000
#> GSM425894 1 0.0000 0.959 1.000 0.000
#> GSM425895 1 0.0000 0.959 1.000 0.000
#> GSM425896 1 0.3274 0.912 0.940 0.060
#> GSM425897 1 0.0000 0.959 1.000 0.000
#> GSM425898 1 0.0000 0.959 1.000 0.000
#> GSM425899 1 0.0000 0.959 1.000 0.000
#> GSM425900 1 0.0000 0.959 1.000 0.000
#> GSM425901 2 0.2778 0.872 0.048 0.952
#> GSM425902 1 0.0938 0.956 0.988 0.012
#> GSM425903 2 0.8443 0.717 0.272 0.728
#> GSM425904 2 0.4939 0.848 0.108 0.892
#> GSM425905 1 0.0376 0.957 0.996 0.004
#> GSM425906 1 0.0000 0.959 1.000 0.000
#> GSM425863 1 0.0938 0.956 0.988 0.012
#> GSM425864 1 0.0000 0.959 1.000 0.000
#> GSM425865 1 0.0000 0.959 1.000 0.000
#> GSM425866 1 0.8813 0.507 0.700 0.300
#> GSM425867 2 0.0000 0.874 0.000 1.000
#> GSM425868 1 0.0938 0.956 0.988 0.012
#> GSM425869 1 0.5842 0.807 0.860 0.140
#> GSM425870 2 0.5408 0.840 0.124 0.876
#> GSM425871 1 0.0938 0.956 0.988 0.012
#> GSM425872 1 0.0000 0.959 1.000 0.000
#> GSM425873 1 0.0000 0.959 1.000 0.000
#> GSM425843 1 0.3584 0.914 0.932 0.068
#> GSM425844 1 0.0938 0.956 0.988 0.012
#> GSM425845 1 0.0938 0.953 0.988 0.012
#> GSM425846 1 0.0000 0.959 1.000 0.000
#> GSM425847 1 0.0000 0.959 1.000 0.000
#> GSM425886 2 0.9087 0.583 0.324 0.676
#> GSM425887 1 0.0000 0.959 1.000 0.000
#> GSM425888 1 0.0000 0.959 1.000 0.000
#> GSM425889 2 0.9358 0.562 0.352 0.648
#> GSM425890 1 0.1184 0.955 0.984 0.016
#> GSM425891 1 0.0938 0.953 0.988 0.012
#> GSM425892 1 0.0000 0.959 1.000 0.000
#> GSM425853 1 0.0938 0.956 0.988 0.012
#> GSM425854 1 0.0000 0.959 1.000 0.000
#> GSM425855 2 0.9358 0.580 0.352 0.648
#> GSM425856 1 0.0376 0.958 0.996 0.004
#> GSM425857 1 0.9815 0.267 0.580 0.420
#> GSM425858 1 0.0000 0.959 1.000 0.000
#> GSM425859 1 0.0000 0.959 1.000 0.000
#> GSM425860 2 0.7815 0.760 0.232 0.768
#> GSM425861 1 0.0000 0.959 1.000 0.000
#> GSM425862 1 0.4431 0.889 0.908 0.092
#> GSM425837 1 0.3274 0.925 0.940 0.060
#> GSM425838 1 0.0938 0.956 0.988 0.012
#> GSM425839 1 0.0376 0.957 0.996 0.004
#> GSM425840 2 0.9710 0.479 0.400 0.600
#> GSM425841 1 0.0938 0.956 0.988 0.012
#> GSM425842 1 0.0938 0.956 0.988 0.012
#> GSM425917 2 0.0938 0.879 0.012 0.988
#> GSM425922 1 0.1633 0.952 0.976 0.024
#> GSM425919 2 0.6887 0.803 0.184 0.816
#> GSM425920 2 0.9933 0.313 0.452 0.548
#> GSM425923 1 0.3114 0.926 0.944 0.056
#> GSM425916 2 0.4022 0.861 0.080 0.920
#> GSM425918 1 0.0938 0.956 0.988 0.012
#> GSM425921 1 0.3114 0.928 0.944 0.056
#> GSM425925 1 0.0938 0.956 0.988 0.012
#> GSM425926 1 0.1414 0.953 0.980 0.020
#> GSM425927 1 0.3733 0.898 0.928 0.072
#> GSM425924 2 0.0938 0.879 0.012 0.988
#> GSM425928 2 0.0938 0.879 0.012 0.988
#> GSM425929 2 0.0938 0.879 0.012 0.988
#> GSM425930 2 0.0938 0.879 0.012 0.988
#> GSM425931 2 0.0376 0.876 0.004 0.996
#> GSM425932 2 0.0938 0.879 0.012 0.988
#> GSM425933 2 0.0938 0.879 0.012 0.988
#> GSM425934 2 0.0938 0.879 0.012 0.988
#> GSM425935 2 0.0938 0.879 0.012 0.988
#> GSM425936 2 0.0938 0.879 0.012 0.988
#> GSM425937 2 0.0938 0.879 0.012 0.988
#> GSM425938 2 0.0672 0.878 0.008 0.992
#> GSM425939 2 0.0938 0.879 0.012 0.988
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.6295 0.6822 0.472 0.528 0.000
#> GSM425908 2 0.6295 0.6822 0.472 0.528 0.000
#> GSM425909 1 0.8939 0.5524 0.560 0.264 0.176
#> GSM425910 1 0.0747 0.3822 0.984 0.016 0.000
#> GSM425911 2 0.6299 0.6800 0.476 0.524 0.000
#> GSM425912 1 0.6299 -0.6519 0.524 0.476 0.000
#> GSM425913 2 0.6295 0.6822 0.472 0.528 0.000
#> GSM425914 1 0.2356 0.2645 0.928 0.072 0.000
#> GSM425915 1 0.5541 0.4465 0.740 0.008 0.252
#> GSM425874 2 0.0424 0.3513 0.008 0.992 0.000
#> GSM425875 1 0.6973 0.5971 0.564 0.416 0.020
#> GSM425876 1 0.2066 0.4390 0.940 0.060 0.000
#> GSM425877 1 0.6516 0.5936 0.516 0.480 0.004
#> GSM425878 2 0.5948 0.5966 0.360 0.640 0.000
#> GSM425879 2 0.6295 0.6822 0.472 0.528 0.000
#> GSM425880 1 0.8938 0.5616 0.552 0.284 0.164
#> GSM425881 1 0.6204 -0.5896 0.576 0.424 0.000
#> GSM425882 2 0.6305 0.6792 0.484 0.516 0.000
#> GSM425883 1 0.6302 0.5939 0.520 0.480 0.000
#> GSM425884 1 0.6302 0.5939 0.520 0.480 0.000
#> GSM425885 2 0.4555 0.5223 0.200 0.800 0.000
#> GSM425848 2 0.6204 -0.5311 0.424 0.576 0.000
#> GSM425849 2 0.6307 -0.5917 0.488 0.512 0.000
#> GSM425850 2 0.6299 0.6801 0.476 0.524 0.000
#> GSM425851 2 0.3083 0.3567 0.024 0.916 0.060
#> GSM425852 2 0.9606 -0.4322 0.340 0.448 0.212
#> GSM425893 1 0.6307 -0.6678 0.512 0.488 0.000
#> GSM425894 2 0.6295 0.6822 0.472 0.528 0.000
#> GSM425895 2 0.6305 0.6792 0.484 0.516 0.000
#> GSM425896 2 0.6302 0.6769 0.480 0.520 0.000
#> GSM425897 2 0.6299 0.6800 0.476 0.524 0.000
#> GSM425898 2 0.6302 0.6808 0.480 0.520 0.000
#> GSM425899 2 0.6305 0.6786 0.484 0.516 0.000
#> GSM425900 2 0.6302 0.6808 0.480 0.520 0.000
#> GSM425901 1 0.9243 0.5188 0.528 0.264 0.208
#> GSM425902 2 0.3412 0.4632 0.124 0.876 0.000
#> GSM425903 1 0.4702 0.4869 0.788 0.000 0.212
#> GSM425904 1 0.8984 0.5612 0.524 0.328 0.148
#> GSM425905 2 0.6295 0.6822 0.472 0.528 0.000
#> GSM425906 2 0.6295 0.6822 0.472 0.528 0.000
#> GSM425863 1 0.6302 0.5939 0.520 0.480 0.000
#> GSM425864 2 0.6299 0.6800 0.476 0.524 0.000
#> GSM425865 2 0.6295 0.6822 0.472 0.528 0.000
#> GSM425866 1 0.7032 0.5884 0.676 0.272 0.052
#> GSM425867 1 0.6305 0.0554 0.516 0.000 0.484
#> GSM425868 2 0.5760 0.6003 0.328 0.672 0.000
#> GSM425869 2 0.6295 0.6822 0.472 0.528 0.000
#> GSM425870 1 0.6452 0.4226 0.704 0.032 0.264
#> GSM425871 2 0.3482 0.4666 0.128 0.872 0.000
#> GSM425872 2 0.6305 0.6805 0.484 0.516 0.000
#> GSM425873 1 0.4605 0.5402 0.796 0.204 0.000
#> GSM425843 1 0.6302 0.5939 0.520 0.480 0.000
#> GSM425844 2 0.1860 0.3942 0.052 0.948 0.000
#> GSM425845 1 0.0000 0.3851 1.000 0.000 0.000
#> GSM425846 2 0.6302 0.6808 0.480 0.520 0.000
#> GSM425847 1 0.6079 -0.5362 0.612 0.388 0.000
#> GSM425886 3 0.4068 0.8480 0.120 0.016 0.864
#> GSM425887 1 0.0424 0.3807 0.992 0.008 0.000
#> GSM425888 2 0.6302 0.6808 0.480 0.520 0.000
#> GSM425889 1 0.6302 0.5939 0.520 0.480 0.000
#> GSM425890 2 0.4121 0.4996 0.168 0.832 0.000
#> GSM425891 2 0.6295 0.6822 0.472 0.528 0.000
#> GSM425892 2 0.6295 0.6822 0.472 0.528 0.000
#> GSM425853 1 0.5465 0.5521 0.712 0.288 0.000
#> GSM425854 2 0.6302 0.6808 0.480 0.520 0.000
#> GSM425855 1 0.6302 0.5939 0.520 0.480 0.000
#> GSM425856 1 0.3038 0.4746 0.896 0.104 0.000
#> GSM425857 2 0.5956 0.4741 0.264 0.720 0.016
#> GSM425858 2 0.6305 0.6792 0.484 0.516 0.000
#> GSM425859 2 0.6295 0.6822 0.472 0.528 0.000
#> GSM425860 1 0.4353 0.4939 0.836 0.008 0.156
#> GSM425861 1 0.3412 0.4945 0.876 0.124 0.000
#> GSM425862 2 0.2711 0.2018 0.088 0.912 0.000
#> GSM425837 1 0.6302 0.5939 0.520 0.480 0.000
#> GSM425838 2 0.4178 0.5018 0.172 0.828 0.000
#> GSM425839 2 0.6295 0.6822 0.472 0.528 0.000
#> GSM425840 1 0.6302 0.5939 0.520 0.480 0.000
#> GSM425841 2 0.1411 0.3900 0.036 0.964 0.000
#> GSM425842 1 0.5465 0.5793 0.712 0.288 0.000
#> GSM425917 3 0.0000 0.9739 0.000 0.000 1.000
#> GSM425922 2 0.0000 0.3542 0.000 1.000 0.000
#> GSM425919 1 0.7778 0.4042 0.644 0.092 0.264
#> GSM425920 2 0.5553 -0.0246 0.272 0.724 0.004
#> GSM425923 1 0.6307 0.5891 0.512 0.488 0.000
#> GSM425916 2 0.8068 -0.5921 0.456 0.480 0.064
#> GSM425918 2 0.5678 -0.3719 0.316 0.684 0.000
#> GSM425921 2 0.0592 0.3474 0.012 0.988 0.000
#> GSM425925 1 0.6302 0.5939 0.520 0.480 0.000
#> GSM425926 2 0.0424 0.3513 0.008 0.992 0.000
#> GSM425927 1 0.4629 0.5347 0.808 0.188 0.004
#> GSM425924 3 0.6181 0.7256 0.104 0.116 0.780
#> GSM425928 3 0.0000 0.9739 0.000 0.000 1.000
#> GSM425929 3 0.0000 0.9739 0.000 0.000 1.000
#> GSM425930 3 0.0000 0.9739 0.000 0.000 1.000
#> GSM425931 3 0.0000 0.9739 0.000 0.000 1.000
#> GSM425932 3 0.0000 0.9739 0.000 0.000 1.000
#> GSM425933 3 0.0000 0.9739 0.000 0.000 1.000
#> GSM425934 3 0.0000 0.9739 0.000 0.000 1.000
#> GSM425935 3 0.0000 0.9739 0.000 0.000 1.000
#> GSM425936 3 0.0000 0.9739 0.000 0.000 1.000
#> GSM425937 3 0.0000 0.9739 0.000 0.000 1.000
#> GSM425938 3 0.0000 0.9739 0.000 0.000 1.000
#> GSM425939 3 0.0000 0.9739 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.0000 0.8691 0.000 1.000 0.000 0.000
#> GSM425908 2 0.0336 0.8650 0.000 0.992 0.000 0.008
#> GSM425909 1 0.0000 0.6742 1.000 0.000 0.000 0.000
#> GSM425910 1 0.4967 0.2725 0.548 0.452 0.000 0.000
#> GSM425911 2 0.0000 0.8691 0.000 1.000 0.000 0.000
#> GSM425912 2 0.1211 0.8372 0.040 0.960 0.000 0.000
#> GSM425913 2 0.0000 0.8691 0.000 1.000 0.000 0.000
#> GSM425914 2 0.4948 0.0111 0.440 0.560 0.000 0.000
#> GSM425915 1 0.0000 0.6742 1.000 0.000 0.000 0.000
#> GSM425874 4 0.3801 0.5960 0.000 0.220 0.000 0.780
#> GSM425875 1 0.2469 0.5982 0.892 0.000 0.000 0.108
#> GSM425876 1 0.5657 0.5070 0.644 0.312 0.000 0.044
#> GSM425877 4 0.4632 0.6411 0.308 0.004 0.000 0.688
#> GSM425878 2 0.2542 0.7963 0.012 0.904 0.000 0.084
#> GSM425879 2 0.0000 0.8691 0.000 1.000 0.000 0.000
#> GSM425880 1 0.0000 0.6742 1.000 0.000 0.000 0.000
#> GSM425881 2 0.2125 0.7995 0.076 0.920 0.000 0.004
#> GSM425882 2 0.0188 0.8670 0.000 0.996 0.000 0.004
#> GSM425883 4 0.4999 0.2815 0.492 0.000 0.000 0.508
#> GSM425884 4 0.4972 0.3909 0.456 0.000 0.000 0.544
#> GSM425885 2 0.4406 0.6491 0.028 0.780 0.000 0.192
#> GSM425848 4 0.5499 0.6740 0.216 0.072 0.000 0.712
#> GSM425849 4 0.4748 0.6668 0.268 0.016 0.000 0.716
#> GSM425850 2 0.0000 0.8691 0.000 1.000 0.000 0.000
#> GSM425851 4 0.5321 0.5498 0.000 0.140 0.112 0.748
#> GSM425852 1 0.3479 0.5946 0.840 0.148 0.000 0.012
#> GSM425893 2 0.4713 0.3319 0.360 0.640 0.000 0.000
#> GSM425894 2 0.0000 0.8691 0.000 1.000 0.000 0.000
#> GSM425895 2 0.0188 0.8670 0.000 0.996 0.000 0.004
#> GSM425896 2 0.0000 0.8691 0.000 1.000 0.000 0.000
#> GSM425897 2 0.0000 0.8691 0.000 1.000 0.000 0.000
#> GSM425898 2 0.0000 0.8691 0.000 1.000 0.000 0.000
#> GSM425899 2 0.0336 0.8645 0.008 0.992 0.000 0.000
#> GSM425900 2 0.0000 0.8691 0.000 1.000 0.000 0.000
#> GSM425901 1 0.0188 0.6723 0.996 0.000 0.000 0.004
#> GSM425902 2 0.7338 -0.0706 0.156 0.440 0.000 0.404
#> GSM425903 1 0.0000 0.6742 1.000 0.000 0.000 0.000
#> GSM425904 1 0.0000 0.6742 1.000 0.000 0.000 0.000
#> GSM425905 2 0.0000 0.8691 0.000 1.000 0.000 0.000
#> GSM425906 2 0.0000 0.8691 0.000 1.000 0.000 0.000
#> GSM425863 4 0.4679 0.5868 0.352 0.000 0.000 0.648
#> GSM425864 2 0.0000 0.8691 0.000 1.000 0.000 0.000
#> GSM425865 2 0.0000 0.8691 0.000 1.000 0.000 0.000
#> GSM425866 1 0.0000 0.6742 1.000 0.000 0.000 0.000
#> GSM425867 1 0.3610 0.5870 0.800 0.000 0.200 0.000
#> GSM425868 2 0.1302 0.8380 0.000 0.956 0.000 0.044
#> GSM425869 2 0.0000 0.8691 0.000 1.000 0.000 0.000
#> GSM425870 1 0.5674 0.6079 0.720 0.148 0.132 0.000
#> GSM425871 2 0.4761 0.3219 0.000 0.628 0.000 0.372
#> GSM425872 2 0.0000 0.8691 0.000 1.000 0.000 0.000
#> GSM425873 1 0.7380 0.2260 0.512 0.200 0.000 0.288
#> GSM425843 4 0.4454 0.6383 0.308 0.000 0.000 0.692
#> GSM425844 4 0.3052 0.6348 0.004 0.136 0.000 0.860
#> GSM425845 1 0.2704 0.6576 0.876 0.124 0.000 0.000
#> GSM425846 2 0.0000 0.8691 0.000 1.000 0.000 0.000
#> GSM425847 2 0.2831 0.7394 0.120 0.876 0.000 0.004
#> GSM425886 1 0.4804 0.0981 0.616 0.000 0.384 0.000
#> GSM425887 2 0.5151 -0.0864 0.464 0.532 0.000 0.004
#> GSM425888 2 0.0000 0.8691 0.000 1.000 0.000 0.000
#> GSM425889 4 0.4585 0.6195 0.332 0.000 0.000 0.668
#> GSM425890 4 0.4898 0.1488 0.000 0.416 0.000 0.584
#> GSM425891 2 0.0000 0.8691 0.000 1.000 0.000 0.000
#> GSM425892 2 0.0000 0.8691 0.000 1.000 0.000 0.000
#> GSM425853 1 0.7191 0.3270 0.500 0.352 0.000 0.148
#> GSM425854 2 0.0000 0.8691 0.000 1.000 0.000 0.000
#> GSM425855 4 0.4304 0.6566 0.284 0.000 0.000 0.716
#> GSM425856 1 0.3710 0.5996 0.804 0.192 0.000 0.004
#> GSM425857 1 0.6215 0.3257 0.600 0.328 0.000 0.072
#> GSM425858 2 0.0188 0.8670 0.000 0.996 0.000 0.004
#> GSM425859 2 0.0000 0.8691 0.000 1.000 0.000 0.000
#> GSM425860 2 0.6145 -0.1884 0.460 0.492 0.000 0.048
#> GSM425861 1 0.7688 0.2220 0.456 0.284 0.000 0.260
#> GSM425862 4 0.2216 0.6693 0.000 0.092 0.000 0.908
#> GSM425837 4 0.4643 0.5983 0.344 0.000 0.000 0.656
#> GSM425838 2 0.4898 0.2874 0.000 0.584 0.000 0.416
#> GSM425839 2 0.0000 0.8691 0.000 1.000 0.000 0.000
#> GSM425840 4 0.4277 0.6602 0.280 0.000 0.000 0.720
#> GSM425841 4 0.4454 0.5003 0.000 0.308 0.000 0.692
#> GSM425842 1 0.6780 0.3825 0.604 0.164 0.000 0.232
#> GSM425917 3 0.3486 0.8021 0.000 0.000 0.812 0.188
#> GSM425922 4 0.0592 0.6682 0.000 0.016 0.000 0.984
#> GSM425919 2 0.8437 -0.2490 0.360 0.412 0.192 0.036
#> GSM425920 4 0.3818 0.6547 0.048 0.108 0.000 0.844
#> GSM425923 4 0.1716 0.6868 0.064 0.000 0.000 0.936
#> GSM425916 4 0.1716 0.6868 0.064 0.000 0.000 0.936
#> GSM425918 4 0.2124 0.6858 0.040 0.028 0.000 0.932
#> GSM425921 4 0.0188 0.6665 0.000 0.004 0.000 0.996
#> GSM425925 4 0.3528 0.6850 0.192 0.000 0.000 0.808
#> GSM425926 4 0.3764 0.5985 0.000 0.216 0.000 0.784
#> GSM425927 4 0.7111 0.3446 0.364 0.136 0.000 0.500
#> GSM425924 3 0.5400 0.5166 0.000 0.020 0.608 0.372
#> GSM425928 3 0.0000 0.9569 0.000 0.000 1.000 0.000
#> GSM425929 3 0.0000 0.9569 0.000 0.000 1.000 0.000
#> GSM425930 3 0.0000 0.9569 0.000 0.000 1.000 0.000
#> GSM425931 3 0.0000 0.9569 0.000 0.000 1.000 0.000
#> GSM425932 3 0.0000 0.9569 0.000 0.000 1.000 0.000
#> GSM425933 3 0.0000 0.9569 0.000 0.000 1.000 0.000
#> GSM425934 3 0.0000 0.9569 0.000 0.000 1.000 0.000
#> GSM425935 3 0.0000 0.9569 0.000 0.000 1.000 0.000
#> GSM425936 3 0.0000 0.9569 0.000 0.000 1.000 0.000
#> GSM425937 3 0.0000 0.9569 0.000 0.000 1.000 0.000
#> GSM425938 3 0.0000 0.9569 0.000 0.000 1.000 0.000
#> GSM425939 3 0.0000 0.9569 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
#> GSM425907 2 0.0162 0.8114 0.000 0.996 0.000 0.004 0.000
#> GSM425908 2 0.0609 0.8064 0.000 0.980 0.000 0.020 0.000
#> GSM425909 5 0.1341 0.6589 0.000 0.000 0.000 0.056 0.944
#> GSM425910 2 0.6863 -0.1318 0.032 0.448 0.000 0.132 0.388
#> GSM425911 2 0.0404 0.8082 0.000 0.988 0.000 0.012 0.000
#> GSM425912 2 0.1934 0.7727 0.004 0.928 0.000 0.052 0.016
#> GSM425913 2 0.0000 0.8119 0.000 1.000 0.000 0.000 0.000
#> GSM425914 2 0.7128 -0.1101 0.016 0.400 0.000 0.256 0.328
#> GSM425915 5 0.0000 0.6707 0.000 0.000 0.000 0.000 1.000
#> GSM425874 4 0.5891 -0.0871 0.328 0.120 0.000 0.552 0.000
#> GSM425875 5 0.4054 0.5128 0.020 0.000 0.000 0.248 0.732
#> GSM425876 5 0.7687 0.1477 0.100 0.160 0.000 0.280 0.460
#> GSM425877 1 0.6829 0.2509 0.496 0.016 0.000 0.272 0.216
#> GSM425878 2 0.6369 0.3553 0.196 0.572 0.000 0.220 0.012
#> GSM425879 2 0.0162 0.8112 0.000 0.996 0.000 0.004 0.000
#> GSM425880 5 0.1851 0.6483 0.000 0.000 0.000 0.088 0.912
#> GSM425881 2 0.6286 0.4163 0.092 0.604 0.000 0.260 0.044
#> GSM425882 2 0.4876 0.5527 0.080 0.700 0.000 0.220 0.000
#> GSM425883 4 0.6596 0.2039 0.236 0.000 0.000 0.456 0.308
#> GSM425884 1 0.5917 0.2033 0.564 0.000 0.000 0.132 0.304
#> GSM425885 2 0.5711 0.4169 0.060 0.668 0.000 0.224 0.048
#> GSM425848 1 0.6902 0.0811 0.428 0.032 0.000 0.404 0.136
#> GSM425849 1 0.6714 0.2446 0.520 0.024 0.000 0.300 0.156
#> GSM425850 2 0.3731 0.6522 0.160 0.800 0.000 0.040 0.000
#> GSM425851 1 0.2835 0.4185 0.868 0.112 0.016 0.004 0.000
#> GSM425852 5 0.2843 0.6354 0.048 0.076 0.000 0.000 0.876
#> GSM425893 2 0.6285 0.1217 0.012 0.484 0.000 0.108 0.396
#> GSM425894 2 0.0000 0.8119 0.000 1.000 0.000 0.000 0.000
#> GSM425895 2 0.4982 0.5413 0.088 0.692 0.000 0.220 0.000
#> GSM425896 2 0.0324 0.8105 0.000 0.992 0.000 0.004 0.004
#> GSM425897 2 0.0404 0.8102 0.000 0.988 0.000 0.012 0.000
#> GSM425898 2 0.0000 0.8119 0.000 1.000 0.000 0.000 0.000
#> GSM425899 2 0.0162 0.8110 0.000 0.996 0.000 0.004 0.000
#> GSM425900 2 0.1041 0.7950 0.004 0.964 0.000 0.032 0.000
#> GSM425901 5 0.1478 0.6553 0.000 0.000 0.000 0.064 0.936
#> GSM425902 4 0.4349 0.1738 0.032 0.052 0.000 0.796 0.120
#> GSM425903 5 0.0000 0.6707 0.000 0.000 0.000 0.000 1.000
#> GSM425904 5 0.2179 0.6657 0.000 0.000 0.000 0.112 0.888
#> GSM425905 2 0.0000 0.8119 0.000 1.000 0.000 0.000 0.000
#> GSM425906 2 0.0000 0.8119 0.000 1.000 0.000 0.000 0.000
#> GSM425863 4 0.6303 0.1485 0.268 0.000 0.000 0.528 0.204
#> GSM425864 2 0.0162 0.8114 0.000 0.996 0.000 0.004 0.000
#> GSM425865 2 0.0162 0.8114 0.000 0.996 0.000 0.004 0.000
#> GSM425866 5 0.2448 0.6423 0.020 0.000 0.000 0.088 0.892
#> GSM425867 5 0.4290 0.4792 0.000 0.000 0.304 0.016 0.680
#> GSM425868 2 0.5450 0.4774 0.132 0.652 0.000 0.216 0.000
#> GSM425869 2 0.0000 0.8119 0.000 1.000 0.000 0.000 0.000
#> GSM425870 5 0.6007 0.4639 0.000 0.188 0.164 0.016 0.632
#> GSM425871 4 0.6549 0.1280 0.360 0.204 0.000 0.436 0.000
#> GSM425872 2 0.0000 0.8119 0.000 1.000 0.000 0.000 0.000
#> GSM425873 4 0.8186 0.1324 0.232 0.116 0.000 0.352 0.300
#> GSM425843 1 0.5490 0.3309 0.652 0.000 0.000 0.148 0.200
#> GSM425844 1 0.3389 0.4216 0.836 0.048 0.000 0.116 0.000
#> GSM425845 5 0.5596 0.4530 0.008 0.120 0.000 0.216 0.656
#> GSM425846 2 0.0324 0.8104 0.004 0.992 0.000 0.004 0.000
#> GSM425847 2 0.6363 0.4713 0.124 0.636 0.000 0.180 0.060
#> GSM425886 5 0.4525 0.4664 0.000 0.000 0.220 0.056 0.724
#> GSM425887 4 0.8093 0.0834 0.092 0.288 0.000 0.332 0.288
#> GSM425888 2 0.0162 0.8114 0.004 0.996 0.000 0.000 0.000
#> GSM425889 4 0.6458 0.1858 0.240 0.000 0.000 0.500 0.260
#> GSM425890 1 0.6358 -0.0589 0.492 0.180 0.000 0.328 0.000
#> GSM425891 2 0.0000 0.8119 0.000 1.000 0.000 0.000 0.000
#> GSM425892 2 0.0162 0.8114 0.000 0.996 0.000 0.004 0.000
#> GSM425853 5 0.8292 -0.1947 0.192 0.152 0.000 0.328 0.328
#> GSM425854 2 0.0000 0.8119 0.000 1.000 0.000 0.000 0.000
#> GSM425855 1 0.4703 0.3513 0.632 0.000 0.000 0.340 0.028
#> GSM425856 5 0.6196 0.3670 0.028 0.280 0.000 0.100 0.592
#> GSM425857 5 0.4955 0.4618 0.012 0.164 0.000 0.092 0.732
#> GSM425858 2 0.4810 0.5587 0.084 0.712 0.000 0.204 0.000
#> GSM425859 2 0.0162 0.8114 0.000 0.996 0.000 0.004 0.000
#> GSM425860 2 0.7659 -0.0599 0.072 0.432 0.000 0.196 0.300
#> GSM425861 4 0.8164 0.1609 0.124 0.212 0.000 0.376 0.288
#> GSM425862 4 0.5218 0.1282 0.296 0.072 0.000 0.632 0.000
#> GSM425837 4 0.6406 0.0426 0.328 0.000 0.000 0.484 0.188
#> GSM425838 4 0.5993 0.1023 0.244 0.156 0.000 0.596 0.004
#> GSM425839 2 0.0000 0.8119 0.000 1.000 0.000 0.000 0.000
#> GSM425840 1 0.5887 0.3232 0.596 0.000 0.000 0.240 0.164
#> GSM425841 4 0.6221 -0.0464 0.300 0.172 0.000 0.528 0.000
#> GSM425842 4 0.7299 0.1992 0.244 0.032 0.000 0.436 0.288
#> GSM425917 3 0.3336 0.7242 0.228 0.000 0.772 0.000 0.000
#> GSM425922 1 0.4597 0.2614 0.564 0.012 0.000 0.424 0.000
#> GSM425919 2 0.9489 -0.2469 0.296 0.296 0.156 0.152 0.100
#> GSM425920 1 0.3749 0.4293 0.828 0.108 0.000 0.052 0.012
#> GSM425923 1 0.2471 0.4484 0.864 0.000 0.000 0.136 0.000
#> GSM425916 1 0.1186 0.4746 0.964 0.000 0.020 0.008 0.008
#> GSM425918 1 0.0963 0.4742 0.964 0.000 0.000 0.036 0.000
#> GSM425921 1 0.4305 0.2290 0.512 0.000 0.000 0.488 0.000
#> GSM425925 4 0.4482 -0.2192 0.348 0.000 0.000 0.636 0.016
#> GSM425926 4 0.5820 -0.0717 0.308 0.120 0.000 0.572 0.000
#> GSM425927 1 0.6304 0.3004 0.652 0.072 0.000 0.132 0.144
#> GSM425924 3 0.5375 0.2369 0.468 0.008 0.492 0.028 0.004
#> GSM425928 3 0.0000 0.9444 0.000 0.000 1.000 0.000 0.000
#> GSM425929 3 0.0000 0.9444 0.000 0.000 1.000 0.000 0.000
#> GSM425930 3 0.0000 0.9444 0.000 0.000 1.000 0.000 0.000
#> GSM425931 3 0.0000 0.9444 0.000 0.000 1.000 0.000 0.000
#> GSM425932 3 0.0000 0.9444 0.000 0.000 1.000 0.000 0.000
#> GSM425933 3 0.0000 0.9444 0.000 0.000 1.000 0.000 0.000
#> GSM425934 3 0.0000 0.9444 0.000 0.000 1.000 0.000 0.000
#> GSM425935 3 0.0000 0.9444 0.000 0.000 1.000 0.000 0.000
#> GSM425936 3 0.0000 0.9444 0.000 0.000 1.000 0.000 0.000
#> GSM425937 3 0.0000 0.9444 0.000 0.000 1.000 0.000 0.000
#> GSM425938 3 0.0000 0.9444 0.000 0.000 1.000 0.000 0.000
#> GSM425939 3 0.0000 0.9444 0.000 0.000 1.000 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 2 0.0858 0.83653 0.028 0.968 0.000 0.004 0.000 0.000
#> GSM425908 2 0.1498 0.82878 0.028 0.940 0.000 0.032 0.000 0.000
#> GSM425909 5 0.0000 0.65723 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM425910 1 0.5652 0.28917 0.540 0.368 0.000 0.016 0.028 0.048
#> GSM425911 2 0.1500 0.82593 0.052 0.936 0.000 0.012 0.000 0.000
#> GSM425912 2 0.2669 0.71400 0.156 0.836 0.000 0.008 0.000 0.000
#> GSM425913 2 0.0363 0.83983 0.012 0.988 0.000 0.000 0.000 0.000
#> GSM425914 1 0.4835 0.36537 0.628 0.320 0.000 0.012 0.020 0.020
#> GSM425915 5 0.4204 0.60760 0.272 0.000 0.000 0.016 0.692 0.020
#> GSM425874 4 0.1789 0.85329 0.000 0.032 0.000 0.924 0.000 0.044
#> GSM425875 1 0.5631 -0.26572 0.512 0.000 0.000 0.044 0.388 0.056
#> GSM425876 1 0.5566 0.33553 0.664 0.056 0.000 0.016 0.064 0.200
#> GSM425877 6 0.5260 0.00994 0.440 0.000 0.000 0.096 0.000 0.464
#> GSM425878 2 0.6509 0.09070 0.236 0.452 0.000 0.032 0.000 0.280
#> GSM425879 2 0.1151 0.83442 0.032 0.956 0.000 0.012 0.000 0.000
#> GSM425880 5 0.4620 0.49182 0.384 0.000 0.000 0.016 0.580 0.020
#> GSM425881 2 0.4181 0.19371 0.476 0.512 0.000 0.012 0.000 0.000
#> GSM425882 2 0.4012 0.53026 0.344 0.640 0.000 0.016 0.000 0.000
#> GSM425883 1 0.5311 0.33893 0.700 0.004 0.000 0.112 0.112 0.072
#> GSM425884 1 0.4432 0.09094 0.544 0.000 0.000 0.020 0.004 0.432
#> GSM425885 2 0.5982 0.49526 0.144 0.644 0.000 0.132 0.064 0.016
#> GSM425848 1 0.6943 0.18234 0.528 0.012 0.000 0.176 0.112 0.172
#> GSM425849 1 0.6473 0.23985 0.540 0.080 0.000 0.156 0.000 0.224
#> GSM425850 2 0.5443 0.32575 0.128 0.580 0.000 0.008 0.000 0.284
#> GSM425851 6 0.1471 0.57282 0.000 0.064 0.004 0.000 0.000 0.932
#> GSM425852 5 0.5481 0.57897 0.188 0.088 0.000 0.008 0.668 0.048
#> GSM425893 2 0.6207 0.11786 0.196 0.448 0.000 0.016 0.340 0.000
#> GSM425894 2 0.0363 0.83796 0.012 0.988 0.000 0.000 0.000 0.000
#> GSM425895 2 0.3905 0.52793 0.316 0.668 0.000 0.016 0.000 0.000
#> GSM425896 2 0.1003 0.83590 0.028 0.964 0.000 0.004 0.004 0.000
#> GSM425897 2 0.1225 0.83423 0.036 0.952 0.000 0.012 0.000 0.000
#> GSM425898 2 0.0000 0.83934 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425899 2 0.0547 0.83650 0.020 0.980 0.000 0.000 0.000 0.000
#> GSM425900 2 0.1267 0.81670 0.060 0.940 0.000 0.000 0.000 0.000
#> GSM425901 5 0.0000 0.65723 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM425902 4 0.3138 0.72437 0.144 0.016 0.000 0.828 0.004 0.008
#> GSM425903 5 0.4117 0.60862 0.272 0.000 0.000 0.012 0.696 0.020
#> GSM425904 5 0.1501 0.63691 0.076 0.000 0.000 0.000 0.924 0.000
#> GSM425905 2 0.0858 0.83653 0.028 0.968 0.000 0.004 0.000 0.000
#> GSM425906 2 0.0000 0.83934 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425863 1 0.3974 0.34308 0.772 0.004 0.000 0.116 0.000 0.108
#> GSM425864 2 0.0858 0.83653 0.028 0.968 0.000 0.004 0.000 0.000
#> GSM425865 2 0.0858 0.83653 0.028 0.968 0.000 0.004 0.000 0.000
#> GSM425866 5 0.4959 0.46706 0.388 0.000 0.000 0.016 0.556 0.040
#> GSM425867 5 0.6907 0.30209 0.308 0.000 0.312 0.016 0.344 0.020
#> GSM425868 2 0.3950 0.53604 0.312 0.672 0.000 0.008 0.000 0.008
#> GSM425869 2 0.0146 0.83928 0.004 0.996 0.000 0.000 0.000 0.000
#> GSM425870 5 0.8180 0.14625 0.276 0.208 0.152 0.012 0.332 0.020
#> GSM425871 1 0.6742 -0.16966 0.420 0.104 0.000 0.108 0.000 0.368
#> GSM425872 2 0.0146 0.83967 0.000 0.996 0.000 0.004 0.000 0.000
#> GSM425873 1 0.3840 0.38567 0.784 0.056 0.000 0.012 0.000 0.148
#> GSM425843 6 0.4466 0.15945 0.336 0.000 0.000 0.044 0.000 0.620
#> GSM425844 6 0.3828 0.52648 0.252 0.016 0.000 0.008 0.000 0.724
#> GSM425845 1 0.5920 0.10496 0.584 0.096 0.000 0.016 0.276 0.028
#> GSM425846 2 0.0146 0.84001 0.004 0.996 0.000 0.000 0.000 0.000
#> GSM425847 2 0.5193 0.35485 0.332 0.576 0.000 0.008 0.000 0.084
#> GSM425886 5 0.0000 0.65723 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM425887 1 0.3261 0.43221 0.780 0.204 0.000 0.016 0.000 0.000
#> GSM425888 2 0.0458 0.83684 0.016 0.984 0.000 0.000 0.000 0.000
#> GSM425889 1 0.6848 0.19149 0.512 0.000 0.000 0.184 0.152 0.152
#> GSM425890 1 0.7734 -0.03888 0.264 0.248 0.000 0.248 0.000 0.240
#> GSM425891 2 0.0363 0.83964 0.012 0.988 0.000 0.000 0.000 0.000
#> GSM425892 2 0.0777 0.83748 0.024 0.972 0.000 0.004 0.000 0.000
#> GSM425853 1 0.5075 0.42159 0.732 0.108 0.000 0.032 0.028 0.100
#> GSM425854 2 0.0458 0.83684 0.016 0.984 0.000 0.000 0.000 0.000
#> GSM425855 6 0.5682 0.28127 0.408 0.004 0.000 0.136 0.000 0.452
#> GSM425856 1 0.7140 -0.13821 0.408 0.216 0.000 0.016 0.308 0.052
#> GSM425857 5 0.0000 0.65723 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM425858 2 0.3351 0.57672 0.288 0.712 0.000 0.000 0.000 0.000
#> GSM425859 2 0.0603 0.83645 0.016 0.980 0.000 0.004 0.000 0.000
#> GSM425860 1 0.4669 0.35695 0.608 0.352 0.000 0.016 0.004 0.020
#> GSM425861 1 0.3121 0.44428 0.796 0.192 0.000 0.004 0.000 0.008
#> GSM425862 1 0.6543 0.07600 0.440 0.052 0.000 0.352 0.000 0.156
#> GSM425837 1 0.4680 0.29621 0.684 0.000 0.000 0.132 0.000 0.184
#> GSM425838 4 0.3936 0.79933 0.060 0.020 0.000 0.796 0.004 0.120
#> GSM425839 2 0.0260 0.83878 0.008 0.992 0.000 0.000 0.000 0.000
#> GSM425840 1 0.5160 0.05707 0.564 0.000 0.000 0.104 0.000 0.332
#> GSM425841 4 0.2122 0.81884 0.000 0.076 0.000 0.900 0.000 0.024
#> GSM425842 1 0.3981 0.39888 0.788 0.020 0.000 0.080 0.000 0.112
#> GSM425917 3 0.3371 0.56892 0.000 0.000 0.708 0.000 0.000 0.292
#> GSM425922 4 0.2597 0.80359 0.000 0.000 0.000 0.824 0.000 0.176
#> GSM425919 6 0.6144 0.39523 0.176 0.116 0.084 0.008 0.000 0.616
#> GSM425920 6 0.3752 0.56341 0.116 0.060 0.000 0.020 0.000 0.804
#> GSM425923 6 0.3253 0.52302 0.192 0.000 0.000 0.020 0.000 0.788
#> GSM425916 6 0.0291 0.58592 0.004 0.000 0.000 0.004 0.000 0.992
#> GSM425918 6 0.2377 0.57445 0.124 0.004 0.000 0.004 0.000 0.868
#> GSM425921 4 0.2454 0.81514 0.000 0.000 0.000 0.840 0.000 0.160
#> GSM425925 4 0.3041 0.74642 0.040 0.000 0.000 0.832 0.000 0.128
#> GSM425926 4 0.1341 0.84773 0.000 0.024 0.000 0.948 0.000 0.028
#> GSM425927 6 0.4877 0.29344 0.388 0.040 0.000 0.012 0.000 0.560
#> GSM425924 6 0.5304 0.33156 0.104 0.004 0.336 0.000 0.000 0.556
#> GSM425928 3 0.0000 0.97326 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425929 3 0.0000 0.97326 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425930 3 0.0000 0.97326 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425931 3 0.0000 0.97326 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425932 3 0.0000 0.97326 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425933 3 0.0000 0.97326 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425934 3 0.0000 0.97326 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425935 3 0.0000 0.97326 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425936 3 0.0000 0.97326 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425937 3 0.0000 0.97326 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425938 3 0.0000 0.97326 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425939 3 0.0000 0.97326 0.000 0.000 1.000 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 disease.state(p) tissue(p) other(p) k
#> SD:pam 98 1.67e-07 9.17e-08 5.91e-05 2
#> SD:pam 68 6.61e-12 4.31e-12 3.74e-07 3
#> SD:pam 84 4.27e-15 1.20e-17 8.35e-11 4
#> SD:pam 51 1.10e-10 2.23e-10 2.64e-05 5
#> SD:pam 64 7.85e-12 1.27e-15 4.77e-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", "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 103 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 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 0.203 0.595 0.778 0.4439 0.541 0.541
#> 3 3 0.474 0.802 0.885 0.3478 0.711 0.516
#> 4 4 0.582 0.718 0.842 0.0771 0.664 0.388
#> 5 5 0.752 0.809 0.885 0.2032 0.758 0.436
#> 6 6 0.721 0.626 0.804 0.0402 0.992 0.964
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 5
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
#> GSM425907 2 0.7139 0.8599 0.196 0.804
#> GSM425908 2 0.7139 0.8599 0.196 0.804
#> GSM425909 1 0.9977 0.2711 0.528 0.472
#> GSM425910 1 0.9522 0.0622 0.628 0.372
#> GSM425911 2 0.7139 0.8599 0.196 0.804
#> GSM425912 2 0.9933 0.4922 0.452 0.548
#> GSM425913 2 0.7139 0.8599 0.196 0.804
#> GSM425914 2 0.7883 0.8157 0.236 0.764
#> GSM425915 2 0.9775 0.0614 0.412 0.588
#> GSM425874 1 0.0000 0.7078 1.000 0.000
#> GSM425875 1 0.8327 0.5599 0.736 0.264
#> GSM425876 1 0.9460 0.0884 0.636 0.364
#> GSM425877 1 0.0000 0.7078 1.000 0.000
#> GSM425878 1 0.3879 0.6687 0.924 0.076
#> GSM425879 2 0.7139 0.8599 0.196 0.804
#> GSM425880 1 0.7453 0.6133 0.788 0.212
#> GSM425881 2 0.9896 0.5110 0.440 0.560
#> GSM425882 2 0.7139 0.8599 0.196 0.804
#> GSM425883 1 0.2043 0.6973 0.968 0.032
#> GSM425884 1 0.2603 0.6915 0.956 0.044
#> GSM425885 1 0.4022 0.6823 0.920 0.080
#> GSM425848 1 0.3114 0.6854 0.944 0.056
#> GSM425849 1 0.3431 0.6787 0.936 0.064
#> GSM425850 1 0.8909 0.2533 0.692 0.308
#> GSM425851 1 0.0000 0.7078 1.000 0.000
#> GSM425852 1 0.7528 0.6137 0.784 0.216
#> GSM425893 2 0.7299 0.8332 0.204 0.796
#> GSM425894 2 0.7139 0.8599 0.196 0.804
#> GSM425895 2 0.7139 0.8599 0.196 0.804
#> GSM425896 2 0.6973 0.8503 0.188 0.812
#> GSM425897 2 0.7139 0.8599 0.196 0.804
#> GSM425898 2 0.7139 0.8599 0.196 0.804
#> GSM425899 2 0.9993 0.4182 0.484 0.516
#> GSM425900 2 0.7139 0.8599 0.196 0.804
#> GSM425901 1 0.9970 0.2771 0.532 0.468
#> GSM425902 1 0.0000 0.7078 1.000 0.000
#> GSM425903 2 0.8955 0.4424 0.312 0.688
#> GSM425904 1 0.7299 0.6183 0.796 0.204
#> GSM425905 2 0.7139 0.8599 0.196 0.804
#> GSM425906 2 0.7139 0.8599 0.196 0.804
#> GSM425863 1 0.3274 0.6801 0.940 0.060
#> GSM425864 2 0.7139 0.8599 0.196 0.804
#> GSM425865 2 0.7139 0.8599 0.196 0.804
#> GSM425866 1 0.8861 0.4959 0.696 0.304
#> GSM425867 1 1.0000 0.2416 0.500 0.500
#> GSM425868 2 0.8661 0.7410 0.288 0.712
#> GSM425869 2 0.7139 0.8599 0.196 0.804
#> GSM425870 2 0.8661 0.4811 0.288 0.712
#> GSM425871 1 0.4690 0.6448 0.900 0.100
#> GSM425872 2 0.7139 0.8599 0.196 0.804
#> GSM425873 1 0.9323 0.1397 0.652 0.348
#> GSM425843 1 0.2778 0.6883 0.952 0.048
#> GSM425844 1 0.0000 0.7078 1.000 0.000
#> GSM425845 1 0.9896 0.1197 0.560 0.440
#> GSM425846 2 0.9933 0.4860 0.452 0.548
#> GSM425847 1 0.9754 -0.0896 0.592 0.408
#> GSM425886 1 0.9970 0.2771 0.532 0.468
#> GSM425887 2 0.9933 0.4916 0.452 0.548
#> GSM425888 2 0.9909 0.5033 0.444 0.556
#> GSM425889 1 0.0000 0.7078 1.000 0.000
#> GSM425890 1 0.0000 0.7078 1.000 0.000
#> GSM425891 2 0.7139 0.8599 0.196 0.804
#> GSM425892 2 0.7139 0.8599 0.196 0.804
#> GSM425853 1 0.7745 0.4717 0.772 0.228
#> GSM425854 2 0.7139 0.8599 0.196 0.804
#> GSM425855 1 0.1843 0.6991 0.972 0.028
#> GSM425856 1 0.8909 0.4884 0.692 0.308
#> GSM425857 1 0.9954 0.2860 0.540 0.460
#> GSM425858 2 0.9775 0.5613 0.412 0.588
#> GSM425859 2 0.7139 0.8599 0.196 0.804
#> GSM425860 1 0.9608 0.0321 0.616 0.384
#> GSM425861 1 0.9850 -0.1684 0.572 0.428
#> GSM425862 1 0.0000 0.7078 1.000 0.000
#> GSM425837 1 0.1184 0.7050 0.984 0.016
#> GSM425838 1 0.0000 0.7078 1.000 0.000
#> GSM425839 2 0.7139 0.8599 0.196 0.804
#> GSM425840 1 0.0672 0.7063 0.992 0.008
#> GSM425841 1 0.0000 0.7078 1.000 0.000
#> GSM425842 1 0.7950 0.4284 0.760 0.240
#> GSM425917 1 0.8608 0.4897 0.716 0.284
#> GSM425922 1 0.0000 0.7078 1.000 0.000
#> GSM425919 1 0.0672 0.7063 0.992 0.008
#> GSM425920 1 0.0672 0.7063 0.992 0.008
#> GSM425923 1 0.0000 0.7078 1.000 0.000
#> GSM425916 1 0.0000 0.7078 1.000 0.000
#> GSM425918 1 0.0000 0.7078 1.000 0.000
#> GSM425921 1 0.0000 0.7078 1.000 0.000
#> GSM425925 1 0.0000 0.7078 1.000 0.000
#> GSM425926 1 0.0000 0.7078 1.000 0.000
#> GSM425927 1 0.5408 0.6144 0.876 0.124
#> GSM425924 1 0.5059 0.6653 0.888 0.112
#> GSM425928 1 0.9686 0.4498 0.604 0.396
#> GSM425929 1 0.9933 0.4251 0.548 0.452
#> GSM425930 1 0.9933 0.4251 0.548 0.452
#> GSM425931 1 0.9933 0.4251 0.548 0.452
#> GSM425932 1 0.9933 0.4251 0.548 0.452
#> GSM425933 1 0.9933 0.4251 0.548 0.452
#> GSM425934 1 0.9933 0.4251 0.548 0.452
#> GSM425935 1 0.9358 0.4633 0.648 0.352
#> GSM425936 1 0.9933 0.4251 0.548 0.452
#> GSM425937 1 0.9933 0.4251 0.548 0.452
#> GSM425938 1 0.9732 0.4467 0.596 0.404
#> GSM425939 1 0.9933 0.4251 0.548 0.452
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.0000 0.792 0.000 1.000 0.000
#> GSM425908 2 0.0000 0.792 0.000 1.000 0.000
#> GSM425909 3 0.7902 0.664 0.208 0.132 0.660
#> GSM425910 2 0.7924 0.634 0.304 0.612 0.084
#> GSM425911 2 0.4873 0.803 0.152 0.824 0.024
#> GSM425912 2 0.4452 0.799 0.192 0.808 0.000
#> GSM425913 2 0.0592 0.797 0.012 0.988 0.000
#> GSM425914 2 0.4291 0.809 0.152 0.840 0.008
#> GSM425915 3 0.9014 0.489 0.208 0.232 0.560
#> GSM425874 1 0.1129 0.935 0.976 0.020 0.004
#> GSM425875 1 0.4164 0.799 0.848 0.008 0.144
#> GSM425876 2 0.7287 0.547 0.408 0.560 0.032
#> GSM425877 1 0.0000 0.929 1.000 0.000 0.000
#> GSM425878 1 0.0000 0.929 1.000 0.000 0.000
#> GSM425879 2 0.3038 0.814 0.104 0.896 0.000
#> GSM425880 1 0.4700 0.758 0.812 0.008 0.180
#> GSM425881 2 0.4504 0.797 0.196 0.804 0.000
#> GSM425882 2 0.3686 0.812 0.140 0.860 0.000
#> GSM425883 1 0.0892 0.936 0.980 0.020 0.000
#> GSM425884 1 0.0000 0.929 1.000 0.000 0.000
#> GSM425885 1 0.2400 0.894 0.932 0.064 0.004
#> GSM425848 1 0.0892 0.936 0.980 0.020 0.000
#> GSM425849 1 0.0892 0.936 0.980 0.020 0.000
#> GSM425850 2 0.6286 0.465 0.464 0.536 0.000
#> GSM425851 1 0.1482 0.932 0.968 0.020 0.012
#> GSM425852 1 0.5384 0.746 0.788 0.024 0.188
#> GSM425893 2 0.5119 0.799 0.152 0.816 0.032
#> GSM425894 2 0.0000 0.792 0.000 1.000 0.000
#> GSM425895 2 0.0000 0.792 0.000 1.000 0.000
#> GSM425896 2 0.1289 0.781 0.000 0.968 0.032
#> GSM425897 2 0.0000 0.792 0.000 1.000 0.000
#> GSM425898 2 0.0000 0.792 0.000 1.000 0.000
#> GSM425899 2 0.5988 0.623 0.368 0.632 0.000
#> GSM425900 2 0.3816 0.811 0.148 0.852 0.000
#> GSM425901 3 0.7169 0.701 0.208 0.088 0.704
#> GSM425902 1 0.1129 0.935 0.976 0.020 0.004
#> GSM425903 2 0.8427 0.600 0.208 0.620 0.172
#> GSM425904 1 0.5062 0.753 0.800 0.016 0.184
#> GSM425905 2 0.0000 0.792 0.000 1.000 0.000
#> GSM425906 2 0.3816 0.811 0.148 0.852 0.000
#> GSM425863 1 0.0000 0.929 1.000 0.000 0.000
#> GSM425864 2 0.0000 0.792 0.000 1.000 0.000
#> GSM425865 2 0.0000 0.792 0.000 1.000 0.000
#> GSM425866 1 0.5330 0.767 0.812 0.044 0.144
#> GSM425867 3 0.6341 0.667 0.252 0.032 0.716
#> GSM425868 2 0.3816 0.803 0.148 0.852 0.000
#> GSM425869 2 0.0000 0.792 0.000 1.000 0.000
#> GSM425870 2 0.6567 0.756 0.160 0.752 0.088
#> GSM425871 1 0.0892 0.936 0.980 0.020 0.000
#> GSM425872 2 0.0892 0.799 0.020 0.980 0.000
#> GSM425873 2 0.6825 0.368 0.492 0.496 0.012
#> GSM425843 1 0.0000 0.929 1.000 0.000 0.000
#> GSM425844 1 0.0892 0.936 0.980 0.020 0.000
#> GSM425845 2 0.8776 0.562 0.296 0.560 0.144
#> GSM425846 2 0.5926 0.642 0.356 0.644 0.000
#> GSM425847 2 0.5016 0.777 0.240 0.760 0.000
#> GSM425886 3 0.7782 0.674 0.208 0.124 0.668
#> GSM425887 2 0.4452 0.799 0.192 0.808 0.000
#> GSM425888 2 0.4654 0.794 0.208 0.792 0.000
#> GSM425889 1 0.0892 0.936 0.980 0.020 0.000
#> GSM425890 1 0.1129 0.935 0.976 0.020 0.004
#> GSM425891 2 0.3038 0.814 0.104 0.896 0.000
#> GSM425892 2 0.0000 0.792 0.000 1.000 0.000
#> GSM425853 1 0.3213 0.877 0.912 0.028 0.060
#> GSM425854 2 0.0000 0.792 0.000 1.000 0.000
#> GSM425855 1 0.0000 0.929 1.000 0.000 0.000
#> GSM425856 1 0.7039 0.641 0.728 0.128 0.144
#> GSM425857 3 0.8132 0.211 0.444 0.068 0.488
#> GSM425858 2 0.4452 0.799 0.192 0.808 0.000
#> GSM425859 2 0.0000 0.792 0.000 1.000 0.000
#> GSM425860 2 0.5269 0.788 0.200 0.784 0.016
#> GSM425861 2 0.6192 0.557 0.420 0.580 0.000
#> GSM425862 1 0.0892 0.936 0.980 0.020 0.000
#> GSM425837 1 0.0000 0.929 1.000 0.000 0.000
#> GSM425838 1 0.1129 0.935 0.976 0.020 0.004
#> GSM425839 2 0.0000 0.792 0.000 1.000 0.000
#> GSM425840 1 0.0000 0.929 1.000 0.000 0.000
#> GSM425841 1 0.1129 0.935 0.976 0.020 0.004
#> GSM425842 1 0.3116 0.821 0.892 0.108 0.000
#> GSM425917 1 0.6195 0.598 0.704 0.020 0.276
#> GSM425922 1 0.1129 0.935 0.976 0.020 0.004
#> GSM425919 1 0.0424 0.928 0.992 0.000 0.008
#> GSM425920 1 0.0000 0.929 1.000 0.000 0.000
#> GSM425923 1 0.0892 0.936 0.980 0.020 0.000
#> GSM425916 1 0.1129 0.935 0.976 0.020 0.004
#> GSM425918 1 0.0892 0.936 0.980 0.020 0.000
#> GSM425921 1 0.1129 0.935 0.976 0.020 0.004
#> GSM425925 1 0.0892 0.936 0.980 0.020 0.000
#> GSM425926 1 0.1129 0.935 0.976 0.020 0.004
#> GSM425927 1 0.0237 0.929 0.996 0.004 0.000
#> GSM425924 1 0.4679 0.813 0.832 0.020 0.148
#> GSM425928 3 0.4485 0.782 0.136 0.020 0.844
#> GSM425929 3 0.0000 0.820 0.000 0.000 1.000
#> GSM425930 3 0.0000 0.820 0.000 0.000 1.000
#> GSM425931 3 0.0000 0.820 0.000 0.000 1.000
#> GSM425932 3 0.0000 0.820 0.000 0.000 1.000
#> GSM425933 3 0.0000 0.820 0.000 0.000 1.000
#> GSM425934 3 0.0000 0.820 0.000 0.000 1.000
#> GSM425935 3 0.4934 0.767 0.156 0.024 0.820
#> GSM425936 3 0.0000 0.820 0.000 0.000 1.000
#> GSM425937 3 0.0000 0.820 0.000 0.000 1.000
#> GSM425938 3 0.3832 0.799 0.100 0.020 0.880
#> GSM425939 3 0.0000 0.820 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.0000 0.904 0.000 1.000 0.000 0.000
#> GSM425908 2 0.0000 0.904 0.000 1.000 0.000 0.000
#> GSM425909 1 0.8533 0.598 0.536 0.100 0.164 0.200
#> GSM425910 1 0.5148 0.690 0.736 0.208 0.000 0.056
#> GSM425911 1 0.5000 0.290 0.504 0.496 0.000 0.000
#> GSM425912 1 0.4888 0.463 0.588 0.412 0.000 0.000
#> GSM425913 2 0.0000 0.904 0.000 1.000 0.000 0.000
#> GSM425914 1 0.4907 0.449 0.580 0.420 0.000 0.000
#> GSM425915 1 0.8203 0.599 0.548 0.060 0.192 0.200
#> GSM425874 4 0.3610 0.998 0.200 0.000 0.000 0.800
#> GSM425875 1 0.3610 0.711 0.800 0.000 0.000 0.200
#> GSM425876 1 0.4617 0.699 0.764 0.204 0.000 0.032
#> GSM425877 1 0.0000 0.732 1.000 0.000 0.000 0.000
#> GSM425878 1 0.0000 0.732 1.000 0.000 0.000 0.000
#> GSM425879 2 0.0000 0.904 0.000 1.000 0.000 0.000
#> GSM425880 1 0.3791 0.710 0.796 0.000 0.004 0.200
#> GSM425881 1 0.4830 0.493 0.608 0.392 0.000 0.000
#> GSM425882 2 0.0817 0.878 0.024 0.976 0.000 0.000
#> GSM425883 1 0.0469 0.734 0.988 0.012 0.000 0.000
#> GSM425884 1 0.0000 0.732 1.000 0.000 0.000 0.000
#> GSM425885 1 0.7314 -0.345 0.424 0.152 0.000 0.424
#> GSM425848 1 0.2124 0.703 0.924 0.008 0.000 0.068
#> GSM425849 1 0.0000 0.732 1.000 0.000 0.000 0.000
#> GSM425850 1 0.1302 0.737 0.956 0.044 0.000 0.000
#> GSM425851 1 0.1792 0.699 0.932 0.000 0.000 0.068
#> GSM425852 1 0.4709 0.706 0.768 0.008 0.024 0.200
#> GSM425893 2 0.4967 -0.175 0.452 0.548 0.000 0.000
#> GSM425894 2 0.0000 0.904 0.000 1.000 0.000 0.000
#> GSM425895 2 0.0000 0.904 0.000 1.000 0.000 0.000
#> GSM425896 2 0.0000 0.904 0.000 1.000 0.000 0.000
#> GSM425897 2 0.0000 0.904 0.000 1.000 0.000 0.000
#> GSM425898 2 0.0000 0.904 0.000 1.000 0.000 0.000
#> GSM425899 1 0.4992 0.342 0.524 0.476 0.000 0.000
#> GSM425900 2 0.4985 -0.220 0.468 0.532 0.000 0.000
#> GSM425901 1 0.8912 0.560 0.500 0.132 0.168 0.200
#> GSM425902 4 0.3610 0.998 0.200 0.000 0.000 0.800
#> GSM425903 1 0.7671 0.646 0.608 0.064 0.128 0.200
#> GSM425904 1 0.3933 0.709 0.792 0.000 0.008 0.200
#> GSM425905 2 0.0000 0.904 0.000 1.000 0.000 0.000
#> GSM425906 2 0.4981 -0.207 0.464 0.536 0.000 0.000
#> GSM425863 1 0.0000 0.732 1.000 0.000 0.000 0.000
#> GSM425864 2 0.0000 0.904 0.000 1.000 0.000 0.000
#> GSM425865 2 0.0000 0.904 0.000 1.000 0.000 0.000
#> GSM425866 1 0.3610 0.711 0.800 0.000 0.000 0.200
#> GSM425867 1 0.8000 0.588 0.548 0.040 0.212 0.200
#> GSM425868 2 0.0817 0.879 0.000 0.976 0.000 0.024
#> GSM425869 2 0.0000 0.904 0.000 1.000 0.000 0.000
#> GSM425870 1 0.6938 0.584 0.592 0.260 0.144 0.004
#> GSM425871 1 0.0000 0.732 1.000 0.000 0.000 0.000
#> GSM425872 2 0.0000 0.904 0.000 1.000 0.000 0.000
#> GSM425873 1 0.1978 0.739 0.928 0.068 0.000 0.004
#> GSM425843 1 0.0000 0.732 1.000 0.000 0.000 0.000
#> GSM425844 1 0.1474 0.708 0.948 0.000 0.000 0.052
#> GSM425845 1 0.5218 0.708 0.736 0.064 0.000 0.200
#> GSM425846 1 0.4977 0.375 0.540 0.460 0.000 0.000
#> GSM425847 1 0.4643 0.565 0.656 0.344 0.000 0.000
#> GSM425886 1 0.9378 0.477 0.440 0.188 0.172 0.200
#> GSM425887 1 0.4888 0.463 0.588 0.412 0.000 0.000
#> GSM425888 1 0.4830 0.493 0.608 0.392 0.000 0.000
#> GSM425889 1 0.2281 0.684 0.904 0.000 0.000 0.096
#> GSM425890 4 0.3688 0.985 0.208 0.000 0.000 0.792
#> GSM425891 2 0.0336 0.896 0.008 0.992 0.000 0.000
#> GSM425892 2 0.0000 0.904 0.000 1.000 0.000 0.000
#> GSM425853 1 0.2469 0.731 0.892 0.000 0.000 0.108
#> GSM425854 2 0.0000 0.904 0.000 1.000 0.000 0.000
#> GSM425855 1 0.0000 0.732 1.000 0.000 0.000 0.000
#> GSM425856 1 0.3610 0.711 0.800 0.000 0.000 0.200
#> GSM425857 1 0.9136 0.502 0.456 0.184 0.120 0.240
#> GSM425858 1 0.4961 0.387 0.552 0.448 0.000 0.000
#> GSM425859 2 0.0000 0.904 0.000 1.000 0.000 0.000
#> GSM425860 1 0.4193 0.652 0.732 0.268 0.000 0.000
#> GSM425861 1 0.4746 0.531 0.632 0.368 0.000 0.000
#> GSM425862 1 0.3486 0.607 0.812 0.000 0.000 0.188
#> GSM425837 1 0.0000 0.732 1.000 0.000 0.000 0.000
#> GSM425838 4 0.3610 0.998 0.200 0.000 0.000 0.800
#> GSM425839 2 0.0000 0.904 0.000 1.000 0.000 0.000
#> GSM425840 1 0.0000 0.732 1.000 0.000 0.000 0.000
#> GSM425841 4 0.3610 0.998 0.200 0.000 0.000 0.800
#> GSM425842 1 0.0000 0.732 1.000 0.000 0.000 0.000
#> GSM425917 1 0.7048 0.577 0.592 0.040 0.304 0.064
#> GSM425922 4 0.3610 0.998 0.200 0.000 0.000 0.800
#> GSM425919 1 0.0000 0.732 1.000 0.000 0.000 0.000
#> GSM425920 1 0.0000 0.732 1.000 0.000 0.000 0.000
#> GSM425923 1 0.1792 0.699 0.932 0.000 0.000 0.068
#> GSM425916 1 0.1792 0.699 0.932 0.000 0.000 0.068
#> GSM425918 1 0.1792 0.699 0.932 0.000 0.000 0.068
#> GSM425921 4 0.3610 0.998 0.200 0.000 0.000 0.800
#> GSM425925 1 0.3569 0.598 0.804 0.000 0.000 0.196
#> GSM425926 4 0.3610 0.998 0.200 0.000 0.000 0.800
#> GSM425927 1 0.0000 0.732 1.000 0.000 0.000 0.000
#> GSM425924 1 0.4793 0.687 0.756 0.040 0.204 0.000
#> GSM425928 3 0.0188 0.954 0.000 0.004 0.996 0.000
#> GSM425929 3 0.0000 0.959 0.000 0.000 1.000 0.000
#> GSM425930 3 0.0000 0.959 0.000 0.000 1.000 0.000
#> GSM425931 3 0.0000 0.959 0.000 0.000 1.000 0.000
#> GSM425932 3 0.0000 0.959 0.000 0.000 1.000 0.000
#> GSM425933 3 0.0000 0.959 0.000 0.000 1.000 0.000
#> GSM425934 3 0.0336 0.950 0.008 0.000 0.992 0.000
#> GSM425935 3 0.4868 0.537 0.212 0.040 0.748 0.000
#> GSM425936 3 0.0000 0.959 0.000 0.000 1.000 0.000
#> GSM425937 3 0.0000 0.959 0.000 0.000 1.000 0.000
#> GSM425938 3 0.0000 0.959 0.000 0.000 1.000 0.000
#> GSM425939 3 0.0000 0.959 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
#> GSM425907 2 0.0000 0.9346 0.000 1.000 0.000 0.000 0.000
#> GSM425908 2 0.0000 0.9346 0.000 1.000 0.000 0.000 0.000
#> GSM425909 3 0.6632 0.6208 0.132 0.176 0.616 0.076 0.000
#> GSM425910 1 0.2011 0.8094 0.908 0.088 0.000 0.004 0.000
#> GSM425911 2 0.3821 0.7072 0.216 0.764 0.000 0.020 0.000
#> GSM425912 1 0.3109 0.8376 0.800 0.200 0.000 0.000 0.000
#> GSM425913 2 0.0000 0.9346 0.000 1.000 0.000 0.000 0.000
#> GSM425914 1 0.2625 0.8156 0.876 0.108 0.000 0.016 0.000
#> GSM425915 3 0.4413 0.7223 0.232 0.000 0.724 0.044 0.000
#> GSM425874 4 0.2280 0.8868 0.000 0.000 0.000 0.880 0.120
#> GSM425875 5 0.4069 0.7572 0.136 0.000 0.000 0.076 0.788
#> GSM425876 1 0.3919 0.7560 0.820 0.056 0.000 0.016 0.108
#> GSM425877 5 0.1341 0.8661 0.000 0.000 0.000 0.056 0.944
#> GSM425878 5 0.0000 0.8800 0.000 0.000 0.000 0.000 1.000
#> GSM425879 2 0.1597 0.8956 0.048 0.940 0.000 0.012 0.000
#> GSM425880 5 0.4025 0.7594 0.132 0.000 0.000 0.076 0.792
#> GSM425881 1 0.3242 0.8274 0.784 0.216 0.000 0.000 0.000
#> GSM425882 2 0.0000 0.9346 0.000 1.000 0.000 0.000 0.000
#> GSM425883 5 0.0290 0.8782 0.008 0.000 0.000 0.000 0.992
#> GSM425884 5 0.0000 0.8800 0.000 0.000 0.000 0.000 1.000
#> GSM425885 4 0.3266 0.8723 0.004 0.000 0.000 0.796 0.200
#> GSM425848 5 0.0000 0.8800 0.000 0.000 0.000 0.000 1.000
#> GSM425849 5 0.0000 0.8800 0.000 0.000 0.000 0.000 1.000
#> GSM425850 1 0.3143 0.6392 0.796 0.000 0.000 0.000 0.204
#> GSM425851 5 0.1965 0.8479 0.000 0.000 0.000 0.096 0.904
#> GSM425852 5 0.4025 0.7594 0.132 0.000 0.000 0.076 0.792
#> GSM425893 2 0.2448 0.8556 0.088 0.892 0.000 0.020 0.000
#> GSM425894 2 0.0000 0.9346 0.000 1.000 0.000 0.000 0.000
#> GSM425895 2 0.0000 0.9346 0.000 1.000 0.000 0.000 0.000
#> GSM425896 2 0.2270 0.8628 0.076 0.904 0.000 0.020 0.000
#> GSM425897 2 0.1549 0.8988 0.040 0.944 0.000 0.016 0.000
#> GSM425898 2 0.0000 0.9346 0.000 1.000 0.000 0.000 0.000
#> GSM425899 2 0.0671 0.9199 0.016 0.980 0.000 0.000 0.004
#> GSM425900 1 0.4307 0.3071 0.500 0.500 0.000 0.000 0.000
#> GSM425901 3 0.6501 0.6388 0.132 0.160 0.632 0.076 0.000
#> GSM425902 4 0.3109 0.8746 0.000 0.000 0.000 0.800 0.200
#> GSM425903 1 0.2046 0.6979 0.916 0.000 0.016 0.068 0.000
#> GSM425904 5 0.4025 0.7594 0.132 0.000 0.000 0.076 0.792
#> GSM425905 2 0.0000 0.9346 0.000 1.000 0.000 0.000 0.000
#> GSM425906 2 0.4305 -0.3309 0.488 0.512 0.000 0.000 0.000
#> GSM425863 5 0.0000 0.8800 0.000 0.000 0.000 0.000 1.000
#> GSM425864 2 0.0898 0.9180 0.020 0.972 0.000 0.008 0.000
#> GSM425865 2 0.0000 0.9346 0.000 1.000 0.000 0.000 0.000
#> GSM425866 5 0.4985 0.6540 0.244 0.000 0.000 0.076 0.680
#> GSM425867 3 0.4025 0.7617 0.132 0.000 0.792 0.076 0.000
#> GSM425868 2 0.0000 0.9346 0.000 1.000 0.000 0.000 0.000
#> GSM425869 2 0.0000 0.9346 0.000 1.000 0.000 0.000 0.000
#> GSM425870 1 0.4216 0.7825 0.804 0.104 0.072 0.020 0.000
#> GSM425871 5 0.0000 0.8800 0.000 0.000 0.000 0.000 1.000
#> GSM425872 2 0.0000 0.9346 0.000 1.000 0.000 0.000 0.000
#> GSM425873 1 0.3196 0.6540 0.804 0.004 0.000 0.000 0.192
#> GSM425843 5 0.0290 0.8799 0.000 0.000 0.000 0.008 0.992
#> GSM425844 5 0.0000 0.8800 0.000 0.000 0.000 0.000 1.000
#> GSM425845 1 0.1671 0.7032 0.924 0.000 0.000 0.076 0.000
#> GSM425846 2 0.3612 0.5265 0.268 0.732 0.000 0.000 0.000
#> GSM425847 1 0.3109 0.8376 0.800 0.200 0.000 0.000 0.000
#> GSM425886 3 0.6859 0.5807 0.132 0.208 0.584 0.076 0.000
#> GSM425887 1 0.3109 0.8376 0.800 0.200 0.000 0.000 0.000
#> GSM425888 1 0.3480 0.7987 0.752 0.248 0.000 0.000 0.000
#> GSM425889 5 0.0880 0.8645 0.000 0.000 0.000 0.032 0.968
#> GSM425890 4 0.2179 0.8851 0.000 0.000 0.000 0.888 0.112
#> GSM425891 2 0.0000 0.9346 0.000 1.000 0.000 0.000 0.000
#> GSM425892 2 0.0000 0.9346 0.000 1.000 0.000 0.000 0.000
#> GSM425853 5 0.2359 0.8426 0.060 0.000 0.000 0.036 0.904
#> GSM425854 2 0.0000 0.9346 0.000 1.000 0.000 0.000 0.000
#> GSM425855 5 0.0000 0.8800 0.000 0.000 0.000 0.000 1.000
#> GSM425856 5 0.5290 0.5799 0.300 0.000 0.000 0.076 0.624
#> GSM425857 4 0.7964 0.0618 0.132 0.184 0.240 0.444 0.000
#> GSM425858 1 0.4138 0.6003 0.616 0.384 0.000 0.000 0.000
#> GSM425859 2 0.0000 0.9346 0.000 1.000 0.000 0.000 0.000
#> GSM425860 1 0.2929 0.8385 0.820 0.180 0.000 0.000 0.000
#> GSM425861 1 0.3109 0.8376 0.800 0.200 0.000 0.000 0.000
#> GSM425862 5 0.2424 0.7665 0.000 0.000 0.000 0.132 0.868
#> GSM425837 5 0.0000 0.8800 0.000 0.000 0.000 0.000 1.000
#> GSM425838 4 0.3109 0.8746 0.000 0.000 0.000 0.800 0.200
#> GSM425839 2 0.0000 0.9346 0.000 1.000 0.000 0.000 0.000
#> GSM425840 5 0.0290 0.8799 0.000 0.000 0.000 0.008 0.992
#> GSM425841 4 0.3109 0.8746 0.000 0.000 0.000 0.800 0.200
#> GSM425842 5 0.4201 0.2672 0.408 0.000 0.000 0.000 0.592
#> GSM425917 3 0.2990 0.7829 0.008 0.000 0.868 0.024 0.100
#> GSM425922 4 0.2127 0.8832 0.000 0.000 0.000 0.892 0.108
#> GSM425919 5 0.1965 0.8479 0.000 0.000 0.000 0.096 0.904
#> GSM425920 5 0.1410 0.8641 0.000 0.000 0.000 0.060 0.940
#> GSM425923 5 0.0510 0.8790 0.000 0.000 0.000 0.016 0.984
#> GSM425916 5 0.1965 0.8479 0.000 0.000 0.000 0.096 0.904
#> GSM425918 5 0.0609 0.8781 0.000 0.000 0.000 0.020 0.980
#> GSM425921 4 0.2179 0.8861 0.000 0.000 0.000 0.888 0.112
#> GSM425925 5 0.2179 0.7916 0.000 0.000 0.000 0.112 0.888
#> GSM425926 4 0.2179 0.8861 0.000 0.000 0.000 0.888 0.112
#> GSM425927 5 0.0693 0.8787 0.012 0.000 0.000 0.008 0.980
#> GSM425924 5 0.4735 0.5568 0.008 0.000 0.304 0.024 0.664
#> GSM425928 3 0.0000 0.8904 0.000 0.000 1.000 0.000 0.000
#> GSM425929 3 0.0000 0.8904 0.000 0.000 1.000 0.000 0.000
#> GSM425930 3 0.0000 0.8904 0.000 0.000 1.000 0.000 0.000
#> GSM425931 3 0.0000 0.8904 0.000 0.000 1.000 0.000 0.000
#> GSM425932 3 0.0000 0.8904 0.000 0.000 1.000 0.000 0.000
#> GSM425933 3 0.0000 0.8904 0.000 0.000 1.000 0.000 0.000
#> GSM425934 3 0.0000 0.8904 0.000 0.000 1.000 0.000 0.000
#> GSM425935 3 0.0290 0.8856 0.008 0.000 0.992 0.000 0.000
#> GSM425936 3 0.0000 0.8904 0.000 0.000 1.000 0.000 0.000
#> GSM425937 3 0.0000 0.8904 0.000 0.000 1.000 0.000 0.000
#> GSM425938 3 0.0000 0.8904 0.000 0.000 1.000 0.000 0.000
#> GSM425939 3 0.0000 0.8904 0.000 0.000 1.000 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 2 0.0000 0.8376 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425908 2 0.0000 0.8376 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425909 3 0.6810 0.5570 0.000 0.084 0.484 0.000 0.232 0.200
#> GSM425910 6 0.3797 0.1026 0.000 0.000 0.000 0.000 0.420 0.580
#> GSM425911 5 0.6018 0.1925 0.000 0.256 0.000 0.000 0.420 0.324
#> GSM425912 6 0.4560 0.3720 0.000 0.200 0.000 0.000 0.108 0.692
#> GSM425913 2 0.1701 0.7978 0.000 0.920 0.000 0.000 0.072 0.008
#> GSM425914 6 0.3851 -0.2591 0.000 0.000 0.000 0.000 0.460 0.540
#> GSM425915 3 0.5351 0.5328 0.000 0.000 0.588 0.000 0.176 0.236
#> GSM425874 4 0.1141 0.8204 0.052 0.000 0.000 0.948 0.000 0.000
#> GSM425875 1 0.3619 0.7362 0.744 0.000 0.000 0.000 0.024 0.232
#> GSM425876 6 0.5269 0.2628 0.132 0.004 0.000 0.000 0.260 0.604
#> GSM425877 1 0.3044 0.7967 0.836 0.000 0.000 0.116 0.048 0.000
#> GSM425878 1 0.0806 0.8269 0.972 0.000 0.000 0.000 0.008 0.020
#> GSM425879 2 0.3713 0.6521 0.000 0.744 0.000 0.000 0.224 0.032
#> GSM425880 1 0.3806 0.7368 0.752 0.000 0.000 0.000 0.048 0.200
#> GSM425881 6 0.3925 0.4021 0.000 0.200 0.000 0.000 0.056 0.744
#> GSM425882 2 0.3727 0.6623 0.000 0.784 0.000 0.000 0.088 0.128
#> GSM425883 1 0.0260 0.8292 0.992 0.000 0.000 0.008 0.000 0.000
#> GSM425884 1 0.0632 0.8287 0.976 0.000 0.000 0.000 0.024 0.000
#> GSM425885 4 0.2793 0.7949 0.200 0.000 0.000 0.800 0.000 0.000
#> GSM425848 1 0.1007 0.8258 0.956 0.000 0.000 0.000 0.044 0.000
#> GSM425849 1 0.0993 0.8258 0.964 0.000 0.000 0.000 0.012 0.024
#> GSM425850 6 0.4699 0.2819 0.228 0.000 0.000 0.000 0.104 0.668
#> GSM425851 1 0.4195 0.7300 0.724 0.000 0.000 0.200 0.076 0.000
#> GSM425852 1 0.3512 0.7508 0.772 0.000 0.000 0.000 0.032 0.196
#> GSM425893 2 0.5380 0.1405 0.000 0.500 0.000 0.000 0.384 0.116
#> GSM425894 2 0.0000 0.8376 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425895 2 0.0632 0.8292 0.000 0.976 0.000 0.000 0.024 0.000
#> GSM425896 2 0.2793 0.6255 0.000 0.800 0.000 0.000 0.200 0.000
#> GSM425897 2 0.2378 0.7237 0.000 0.848 0.000 0.000 0.152 0.000
#> GSM425898 2 0.0000 0.8376 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425899 2 0.4556 0.5197 0.000 0.688 0.000 0.000 0.100 0.212
#> GSM425900 6 0.5758 -0.1096 0.000 0.368 0.000 0.000 0.176 0.456
#> GSM425901 3 0.6776 0.5732 0.000 0.096 0.504 0.000 0.200 0.200
#> GSM425902 4 0.2762 0.7979 0.196 0.000 0.000 0.804 0.000 0.000
#> GSM425903 6 0.3923 -0.0724 0.000 0.000 0.004 0.000 0.416 0.580
#> GSM425904 1 0.3867 0.7379 0.748 0.000 0.000 0.000 0.052 0.200
#> GSM425905 2 0.0000 0.8376 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425906 2 0.5872 -0.3604 0.000 0.404 0.000 0.000 0.196 0.400
#> GSM425863 1 0.0622 0.8280 0.980 0.000 0.000 0.000 0.008 0.012
#> GSM425864 2 0.1714 0.7655 0.000 0.908 0.000 0.000 0.092 0.000
#> GSM425865 2 0.0000 0.8376 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425866 1 0.4664 0.5758 0.584 0.000 0.000 0.000 0.052 0.364
#> GSM425867 3 0.6515 0.4110 0.056 0.000 0.508 0.000 0.196 0.240
#> GSM425868 2 0.0000 0.8376 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425869 2 0.0000 0.8376 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425870 5 0.4224 -0.0804 0.000 0.000 0.016 0.000 0.552 0.432
#> GSM425871 1 0.1257 0.8223 0.952 0.000 0.000 0.000 0.028 0.020
#> GSM425872 2 0.0937 0.8223 0.000 0.960 0.000 0.000 0.040 0.000
#> GSM425873 6 0.5246 0.2733 0.212 0.000 0.000 0.000 0.180 0.608
#> GSM425843 1 0.1657 0.8305 0.936 0.000 0.000 0.040 0.012 0.012
#> GSM425844 1 0.0692 0.8300 0.976 0.000 0.000 0.004 0.020 0.000
#> GSM425845 6 0.2969 0.2021 0.000 0.000 0.000 0.000 0.224 0.776
#> GSM425846 2 0.5282 -0.0142 0.000 0.484 0.000 0.000 0.100 0.416
#> GSM425847 6 0.4340 0.4079 0.000 0.200 0.000 0.000 0.088 0.712
#> GSM425886 3 0.6972 0.5452 0.000 0.120 0.480 0.000 0.216 0.184
#> GSM425887 6 0.4293 0.3781 0.000 0.200 0.000 0.000 0.084 0.716
#> GSM425888 6 0.4144 0.3910 0.000 0.200 0.000 0.000 0.072 0.728
#> GSM425889 1 0.1713 0.8189 0.928 0.000 0.000 0.028 0.044 0.000
#> GSM425890 4 0.1075 0.8178 0.048 0.000 0.000 0.952 0.000 0.000
#> GSM425891 2 0.3225 0.7127 0.000 0.828 0.000 0.000 0.080 0.092
#> GSM425892 2 0.0000 0.8376 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425853 1 0.3213 0.7771 0.820 0.000 0.000 0.000 0.048 0.132
#> GSM425854 2 0.0000 0.8376 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425855 1 0.0405 0.8279 0.988 0.000 0.000 0.004 0.008 0.000
#> GSM425856 1 0.4541 0.5888 0.596 0.000 0.000 0.000 0.044 0.360
#> GSM425857 4 0.8799 -0.1396 0.000 0.116 0.212 0.272 0.200 0.200
#> GSM425858 6 0.4530 0.3448 0.000 0.208 0.000 0.000 0.100 0.692
#> GSM425859 2 0.0000 0.8376 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425860 6 0.5193 0.2224 0.000 0.104 0.000 0.000 0.344 0.552
#> GSM425861 6 0.3875 0.4155 0.016 0.196 0.000 0.000 0.028 0.760
#> GSM425862 1 0.2542 0.7854 0.876 0.000 0.000 0.080 0.044 0.000
#> GSM425837 1 0.0146 0.8283 0.996 0.000 0.000 0.004 0.000 0.000
#> GSM425838 4 0.2762 0.7979 0.196 0.000 0.000 0.804 0.000 0.000
#> GSM425839 2 0.0000 0.8376 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425840 1 0.0547 0.8301 0.980 0.000 0.000 0.020 0.000 0.000
#> GSM425841 4 0.2762 0.7979 0.196 0.000 0.000 0.804 0.000 0.000
#> GSM425842 1 0.5575 -0.0771 0.460 0.000 0.000 0.000 0.140 0.400
#> GSM425917 3 0.6091 0.6039 0.100 0.000 0.584 0.084 0.232 0.000
#> GSM425922 4 0.0632 0.7961 0.024 0.000 0.000 0.976 0.000 0.000
#> GSM425919 1 0.2980 0.7790 0.808 0.000 0.000 0.180 0.012 0.000
#> GSM425920 1 0.2100 0.8091 0.884 0.000 0.000 0.112 0.004 0.000
#> GSM425923 1 0.3020 0.8034 0.844 0.000 0.000 0.076 0.080 0.000
#> GSM425916 1 0.4166 0.7325 0.728 0.000 0.000 0.196 0.076 0.000
#> GSM425918 1 0.2744 0.8123 0.864 0.000 0.000 0.072 0.064 0.000
#> GSM425921 4 0.1075 0.8196 0.048 0.000 0.000 0.952 0.000 0.000
#> GSM425925 1 0.2009 0.8061 0.908 0.000 0.000 0.068 0.024 0.000
#> GSM425926 4 0.1075 0.8196 0.048 0.000 0.000 0.952 0.000 0.000
#> GSM425927 1 0.5027 0.6297 0.696 0.000 0.000 0.032 0.112 0.160
#> GSM425924 1 0.6229 0.4313 0.548 0.000 0.272 0.080 0.100 0.000
#> GSM425928 3 0.2178 0.7897 0.000 0.000 0.868 0.000 0.132 0.000
#> GSM425929 3 0.0000 0.8234 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425930 3 0.0000 0.8234 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425931 3 0.0000 0.8234 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425932 3 0.0000 0.8234 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425933 3 0.0000 0.8234 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425934 3 0.0000 0.8234 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425935 3 0.2793 0.7612 0.000 0.000 0.800 0.000 0.200 0.000
#> GSM425936 3 0.0000 0.8234 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425937 3 0.0000 0.8234 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425938 3 0.1714 0.8027 0.000 0.000 0.908 0.000 0.092 0.000
#> GSM425939 3 0.0000 0.8234 0.000 0.000 1.000 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 disease.state(p) tissue(p) other(p) k
#> SD:mclust 66 NA 3.93e-03 5.09e-04 2
#> SD:mclust 99 4.15e-16 5.02e-18 1.37e-13 3
#> SD:mclust 89 3.59e-19 9.26e-19 9.81e-13 4
#> SD:mclust 99 1.44e-12 2.47e-13 1.14e-08 5
#> SD:mclust 78 5.17e-11 6.06e-11 3.44e-09 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 103 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 0.530 0.842 0.921 0.4877 0.520 0.520
#> 3 3 0.557 0.640 0.843 0.3556 0.689 0.471
#> 4 4 0.601 0.700 0.812 0.1277 0.811 0.521
#> 5 5 0.684 0.684 0.828 0.0669 0.904 0.661
#> 6 6 0.694 0.592 0.773 0.0489 0.890 0.550
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
#> GSM425907 2 0.2236 0.919 0.036 0.964
#> GSM425908 1 0.9491 0.510 0.632 0.368
#> GSM425909 2 0.5629 0.840 0.132 0.868
#> GSM425910 2 0.5946 0.842 0.144 0.856
#> GSM425911 2 0.0672 0.929 0.008 0.992
#> GSM425912 2 0.3431 0.906 0.064 0.936
#> GSM425913 2 0.5408 0.853 0.124 0.876
#> GSM425914 2 0.0672 0.929 0.008 0.992
#> GSM425915 2 0.0938 0.930 0.012 0.988
#> GSM425874 1 0.0376 0.898 0.996 0.004
#> GSM425875 1 0.1184 0.892 0.984 0.016
#> GSM425876 1 0.6148 0.786 0.848 0.152
#> GSM425877 1 0.0376 0.897 0.996 0.004
#> GSM425878 1 0.0000 0.898 1.000 0.000
#> GSM425879 2 0.1633 0.923 0.024 0.976
#> GSM425880 1 0.9323 0.441 0.652 0.348
#> GSM425881 1 0.5629 0.823 0.868 0.132
#> GSM425882 1 0.8499 0.675 0.724 0.276
#> GSM425883 1 0.0000 0.898 1.000 0.000
#> GSM425884 1 0.1633 0.888 0.976 0.024
#> GSM425885 1 0.1633 0.892 0.976 0.024
#> GSM425848 1 0.0672 0.898 0.992 0.008
#> GSM425849 1 0.0000 0.898 1.000 0.000
#> GSM425850 1 0.0000 0.898 1.000 0.000
#> GSM425851 1 0.2423 0.879 0.960 0.040
#> GSM425852 2 0.7745 0.721 0.228 0.772
#> GSM425893 2 0.0000 0.929 0.000 1.000
#> GSM425894 1 0.9248 0.568 0.660 0.340
#> GSM425895 1 0.9248 0.568 0.660 0.340
#> GSM425896 2 0.0000 0.929 0.000 1.000
#> GSM425897 2 0.1184 0.926 0.016 0.984
#> GSM425898 1 0.7453 0.754 0.788 0.212
#> GSM425899 1 0.0376 0.898 0.996 0.004
#> GSM425900 1 0.8144 0.704 0.748 0.252
#> GSM425901 2 0.6343 0.808 0.160 0.840
#> GSM425902 1 0.0376 0.898 0.996 0.004
#> GSM425903 2 0.1184 0.929 0.016 0.984
#> GSM425904 1 0.9732 0.289 0.596 0.404
#> GSM425905 2 0.5842 0.835 0.140 0.860
#> GSM425906 2 0.5737 0.845 0.136 0.864
#> GSM425863 1 0.0000 0.898 1.000 0.000
#> GSM425864 2 0.1633 0.923 0.024 0.976
#> GSM425865 2 0.6148 0.820 0.152 0.848
#> GSM425866 1 0.1843 0.887 0.972 0.028
#> GSM425867 2 0.2043 0.922 0.032 0.968
#> GSM425868 1 0.6343 0.805 0.840 0.160
#> GSM425869 1 0.8144 0.709 0.748 0.252
#> GSM425870 2 0.0376 0.929 0.004 0.996
#> GSM425871 1 0.0000 0.898 1.000 0.000
#> GSM425872 1 0.9087 0.596 0.676 0.324
#> GSM425873 1 0.0000 0.898 1.000 0.000
#> GSM425843 1 0.0000 0.898 1.000 0.000
#> GSM425844 1 0.0376 0.898 0.996 0.004
#> GSM425845 1 0.9922 0.134 0.552 0.448
#> GSM425846 1 0.0938 0.896 0.988 0.012
#> GSM425847 1 0.4690 0.848 0.900 0.100
#> GSM425886 2 0.0672 0.931 0.008 0.992
#> GSM425887 1 0.7453 0.752 0.788 0.212
#> GSM425888 1 0.1633 0.891 0.976 0.024
#> GSM425889 1 0.0376 0.898 0.996 0.004
#> GSM425890 1 0.0376 0.898 0.996 0.004
#> GSM425891 2 0.5519 0.850 0.128 0.872
#> GSM425892 2 0.9209 0.454 0.336 0.664
#> GSM425853 1 0.0376 0.897 0.996 0.004
#> GSM425854 1 0.7139 0.771 0.804 0.196
#> GSM425855 1 0.0000 0.898 1.000 0.000
#> GSM425856 1 0.2043 0.885 0.968 0.032
#> GSM425857 2 0.6247 0.815 0.156 0.844
#> GSM425858 1 0.5737 0.820 0.864 0.136
#> GSM425859 1 0.8144 0.708 0.748 0.252
#> GSM425860 2 0.5946 0.843 0.144 0.856
#> GSM425861 1 0.0672 0.896 0.992 0.008
#> GSM425862 1 0.0376 0.898 0.996 0.004
#> GSM425837 1 0.0376 0.897 0.996 0.004
#> GSM425838 1 0.0376 0.898 0.996 0.004
#> GSM425839 1 0.8861 0.632 0.696 0.304
#> GSM425840 1 0.0000 0.898 1.000 0.000
#> GSM425841 1 0.0376 0.898 0.996 0.004
#> GSM425842 1 0.0000 0.898 1.000 0.000
#> GSM425917 2 0.0672 0.931 0.008 0.992
#> GSM425922 1 0.0376 0.898 0.996 0.004
#> GSM425919 1 0.6048 0.785 0.852 0.148
#> GSM425920 1 0.0000 0.898 1.000 0.000
#> GSM425923 1 0.0000 0.898 1.000 0.000
#> GSM425916 1 0.2043 0.884 0.968 0.032
#> GSM425918 1 0.0000 0.898 1.000 0.000
#> GSM425921 1 0.0376 0.898 0.996 0.004
#> GSM425925 1 0.0376 0.898 0.996 0.004
#> GSM425926 1 0.0376 0.898 0.996 0.004
#> GSM425927 1 0.0000 0.898 1.000 0.000
#> GSM425924 2 0.5519 0.847 0.128 0.872
#> GSM425928 2 0.0672 0.931 0.008 0.992
#> GSM425929 2 0.0938 0.930 0.012 0.988
#> GSM425930 2 0.0938 0.930 0.012 0.988
#> GSM425931 2 0.0672 0.931 0.008 0.992
#> GSM425932 2 0.0376 0.929 0.004 0.996
#> GSM425933 2 0.0938 0.930 0.012 0.988
#> GSM425934 2 0.0376 0.929 0.004 0.996
#> GSM425935 2 0.0000 0.929 0.000 1.000
#> GSM425936 2 0.0000 0.929 0.000 1.000
#> GSM425937 2 0.0672 0.931 0.008 0.992
#> GSM425938 2 0.0672 0.931 0.008 0.992
#> GSM425939 2 0.0938 0.930 0.012 0.988
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.1964 0.7395 0.000 0.944 0.056
#> GSM425908 2 0.0424 0.7587 0.000 0.992 0.008
#> GSM425909 3 0.1999 0.8565 0.012 0.036 0.952
#> GSM425910 1 0.8384 0.2415 0.520 0.088 0.392
#> GSM425911 3 0.6267 0.2066 0.000 0.452 0.548
#> GSM425912 1 0.9370 0.0620 0.420 0.412 0.168
#> GSM425913 2 0.3192 0.7005 0.000 0.888 0.112
#> GSM425914 3 0.9111 0.1032 0.140 0.424 0.436
#> GSM425915 3 0.0000 0.8666 0.000 0.000 1.000
#> GSM425874 2 0.6260 0.2213 0.448 0.552 0.000
#> GSM425875 1 0.1753 0.7907 0.952 0.000 0.048
#> GSM425876 1 0.4095 0.7629 0.880 0.056 0.064
#> GSM425877 1 0.0424 0.7964 0.992 0.000 0.008
#> GSM425878 1 0.0747 0.7934 0.984 0.016 0.000
#> GSM425879 2 0.5835 0.3556 0.000 0.660 0.340
#> GSM425880 1 0.5948 0.4467 0.640 0.000 0.360
#> GSM425881 1 0.6192 0.2740 0.580 0.420 0.000
#> GSM425882 2 0.0592 0.7578 0.012 0.988 0.000
#> GSM425883 1 0.0892 0.7952 0.980 0.020 0.000
#> GSM425884 1 0.2261 0.7844 0.932 0.000 0.068
#> GSM425885 2 0.4692 0.6577 0.168 0.820 0.012
#> GSM425848 1 0.5835 0.3834 0.660 0.340 0.000
#> GSM425849 1 0.1529 0.7851 0.960 0.040 0.000
#> GSM425850 1 0.0592 0.7961 0.988 0.012 0.000
#> GSM425851 1 0.2625 0.7754 0.916 0.000 0.084
#> GSM425852 3 0.4702 0.6705 0.212 0.000 0.788
#> GSM425893 3 0.6168 0.3129 0.000 0.412 0.588
#> GSM425894 2 0.0592 0.7579 0.000 0.988 0.012
#> GSM425895 2 0.0237 0.7593 0.004 0.996 0.000
#> GSM425896 2 0.5138 0.5426 0.000 0.748 0.252
#> GSM425897 2 0.5650 0.4182 0.000 0.688 0.312
#> GSM425898 2 0.0237 0.7593 0.004 0.996 0.000
#> GSM425899 1 0.6126 0.2374 0.600 0.400 0.000
#> GSM425900 2 0.5291 0.4895 0.268 0.732 0.000
#> GSM425901 3 0.2845 0.8371 0.012 0.068 0.920
#> GSM425902 2 0.6215 0.2690 0.428 0.572 0.000
#> GSM425903 3 0.3412 0.7818 0.124 0.000 0.876
#> GSM425904 1 0.5948 0.4507 0.640 0.000 0.360
#> GSM425905 2 0.1964 0.7392 0.000 0.944 0.056
#> GSM425906 2 0.7318 0.4423 0.068 0.668 0.264
#> GSM425863 1 0.0237 0.7952 0.996 0.004 0.000
#> GSM425864 2 0.3941 0.6575 0.000 0.844 0.156
#> GSM425865 2 0.1643 0.7453 0.000 0.956 0.044
#> GSM425866 1 0.2066 0.7874 0.940 0.000 0.060
#> GSM425867 3 0.2878 0.8078 0.096 0.000 0.904
#> GSM425868 2 0.0424 0.7590 0.008 0.992 0.000
#> GSM425869 2 0.0237 0.7592 0.000 0.996 0.004
#> GSM425870 3 0.3272 0.8258 0.016 0.080 0.904
#> GSM425871 1 0.1163 0.7904 0.972 0.028 0.000
#> GSM425872 2 0.0661 0.7595 0.004 0.988 0.008
#> GSM425873 1 0.1015 0.7972 0.980 0.008 0.012
#> GSM425843 1 0.0424 0.7964 0.992 0.000 0.008
#> GSM425844 1 0.1753 0.7808 0.952 0.048 0.000
#> GSM425845 1 0.4931 0.6564 0.768 0.000 0.232
#> GSM425846 1 0.6244 0.2125 0.560 0.440 0.000
#> GSM425847 1 0.5450 0.6066 0.760 0.228 0.012
#> GSM425886 3 0.2448 0.8346 0.000 0.076 0.924
#> GSM425887 1 0.6260 0.2124 0.552 0.448 0.000
#> GSM425888 1 0.6180 0.3019 0.584 0.416 0.000
#> GSM425889 1 0.3752 0.7022 0.856 0.144 0.000
#> GSM425890 2 0.6204 0.2773 0.424 0.576 0.000
#> GSM425891 2 0.3879 0.6632 0.000 0.848 0.152
#> GSM425892 2 0.1031 0.7537 0.000 0.976 0.024
#> GSM425853 1 0.1163 0.7949 0.972 0.000 0.028
#> GSM425854 2 0.0424 0.7585 0.008 0.992 0.000
#> GSM425855 1 0.1163 0.7904 0.972 0.028 0.000
#> GSM425856 1 0.2261 0.7844 0.932 0.000 0.068
#> GSM425857 3 0.6879 0.2112 0.016 0.428 0.556
#> GSM425858 2 0.5882 0.3234 0.348 0.652 0.000
#> GSM425859 2 0.0475 0.7595 0.004 0.992 0.004
#> GSM425860 1 0.9061 0.4008 0.548 0.188 0.264
#> GSM425861 1 0.4887 0.6288 0.772 0.228 0.000
#> GSM425862 1 0.4974 0.5828 0.764 0.236 0.000
#> GSM425837 1 0.0424 0.7964 0.992 0.000 0.008
#> GSM425838 2 0.6140 0.3165 0.404 0.596 0.000
#> GSM425839 2 0.0592 0.7579 0.000 0.988 0.012
#> GSM425840 1 0.0237 0.7952 0.996 0.004 0.000
#> GSM425841 2 0.6215 0.2690 0.428 0.572 0.000
#> GSM425842 1 0.1129 0.7950 0.976 0.020 0.004
#> GSM425917 3 0.2200 0.8468 0.004 0.056 0.940
#> GSM425922 2 0.6244 0.2401 0.440 0.560 0.000
#> GSM425919 1 0.4062 0.7261 0.836 0.000 0.164
#> GSM425920 1 0.0424 0.7964 0.992 0.000 0.008
#> GSM425923 1 0.1163 0.7905 0.972 0.028 0.000
#> GSM425916 1 0.1860 0.7896 0.948 0.000 0.052
#> GSM425918 1 0.1163 0.7905 0.972 0.028 0.000
#> GSM425921 2 0.6280 0.1831 0.460 0.540 0.000
#> GSM425925 1 0.3686 0.7069 0.860 0.140 0.000
#> GSM425926 1 0.6309 -0.0903 0.504 0.496 0.000
#> GSM425927 1 0.0592 0.7963 0.988 0.000 0.012
#> GSM425924 3 0.2878 0.8117 0.096 0.000 0.904
#> GSM425928 3 0.1163 0.8607 0.000 0.028 0.972
#> GSM425929 3 0.0237 0.8656 0.004 0.000 0.996
#> GSM425930 3 0.0237 0.8656 0.004 0.000 0.996
#> GSM425931 3 0.0000 0.8666 0.000 0.000 1.000
#> GSM425932 3 0.0237 0.8663 0.000 0.004 0.996
#> GSM425933 3 0.0000 0.8666 0.000 0.000 1.000
#> GSM425934 3 0.0592 0.8653 0.000 0.012 0.988
#> GSM425935 3 0.3038 0.8149 0.000 0.104 0.896
#> GSM425936 3 0.0424 0.8658 0.000 0.008 0.992
#> GSM425937 3 0.0000 0.8666 0.000 0.000 1.000
#> GSM425938 3 0.0747 0.8646 0.000 0.016 0.984
#> GSM425939 3 0.0237 0.8656 0.004 0.000 0.996
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.5069 0.5599 0.000 0.664 0.016 0.320
#> GSM425908 2 0.4916 0.3591 0.000 0.576 0.000 0.424
#> GSM425909 3 0.3616 0.8251 0.036 0.000 0.852 0.112
#> GSM425910 1 0.4425 0.7244 0.828 0.080 0.012 0.080
#> GSM425911 2 0.1388 0.7972 0.028 0.960 0.012 0.000
#> GSM425912 2 0.3975 0.6665 0.240 0.760 0.000 0.000
#> GSM425913 2 0.0188 0.8032 0.000 0.996 0.004 0.000
#> GSM425914 2 0.2593 0.7698 0.104 0.892 0.004 0.000
#> GSM425915 3 0.3937 0.8362 0.024 0.024 0.852 0.100
#> GSM425874 4 0.2611 0.7885 0.096 0.008 0.000 0.896
#> GSM425875 1 0.4426 0.7526 0.772 0.000 0.024 0.204
#> GSM425876 1 0.3099 0.7395 0.876 0.104 0.000 0.020
#> GSM425877 1 0.4267 0.7341 0.788 0.000 0.024 0.188
#> GSM425878 1 0.1867 0.7987 0.928 0.000 0.000 0.072
#> GSM425879 2 0.0672 0.8036 0.000 0.984 0.008 0.008
#> GSM425880 1 0.7414 0.2718 0.480 0.000 0.340 0.180
#> GSM425881 2 0.4431 0.5839 0.304 0.696 0.000 0.000
#> GSM425882 2 0.0817 0.8049 0.000 0.976 0.000 0.024
#> GSM425883 1 0.4164 0.6679 0.736 0.000 0.000 0.264
#> GSM425884 1 0.2125 0.7951 0.920 0.000 0.004 0.076
#> GSM425885 4 0.2125 0.7117 0.004 0.076 0.000 0.920
#> GSM425848 4 0.4290 0.5885 0.212 0.000 0.016 0.772
#> GSM425849 1 0.2704 0.7812 0.876 0.000 0.000 0.124
#> GSM425850 1 0.2124 0.7797 0.932 0.040 0.000 0.028
#> GSM425851 1 0.7685 0.3192 0.456 0.000 0.288 0.256
#> GSM425852 3 0.5277 0.7422 0.132 0.000 0.752 0.116
#> GSM425893 2 0.3312 0.7597 0.008 0.884 0.068 0.040
#> GSM425894 4 0.4730 0.2874 0.000 0.364 0.000 0.636
#> GSM425895 2 0.2216 0.7928 0.000 0.908 0.000 0.092
#> GSM425896 2 0.6403 0.5742 0.000 0.640 0.128 0.232
#> GSM425897 2 0.1488 0.8002 0.000 0.956 0.032 0.012
#> GSM425898 2 0.3975 0.6795 0.000 0.760 0.000 0.240
#> GSM425899 4 0.4225 0.7370 0.184 0.024 0.000 0.792
#> GSM425900 2 0.2345 0.7761 0.100 0.900 0.000 0.000
#> GSM425901 3 0.3821 0.8195 0.040 0.000 0.840 0.120
#> GSM425902 4 0.2676 0.7889 0.092 0.012 0.000 0.896
#> GSM425903 3 0.6638 0.6502 0.224 0.020 0.656 0.100
#> GSM425904 3 0.7564 -0.0293 0.388 0.000 0.420 0.192
#> GSM425905 2 0.1716 0.8003 0.000 0.936 0.000 0.064
#> GSM425906 2 0.1978 0.7877 0.068 0.928 0.004 0.000
#> GSM425863 1 0.2704 0.7825 0.876 0.000 0.000 0.124
#> GSM425864 2 0.2060 0.8007 0.000 0.932 0.016 0.052
#> GSM425865 2 0.1867 0.7993 0.000 0.928 0.000 0.072
#> GSM425866 1 0.3658 0.7647 0.836 0.000 0.020 0.144
#> GSM425867 3 0.3601 0.8304 0.056 0.000 0.860 0.084
#> GSM425868 4 0.4713 0.2971 0.000 0.360 0.000 0.640
#> GSM425869 4 0.4134 0.5140 0.000 0.260 0.000 0.740
#> GSM425870 3 0.6029 0.0220 0.032 0.480 0.484 0.004
#> GSM425871 1 0.1489 0.7944 0.952 0.004 0.000 0.044
#> GSM425872 2 0.3074 0.7626 0.000 0.848 0.000 0.152
#> GSM425873 1 0.1151 0.7876 0.968 0.024 0.000 0.008
#> GSM425843 1 0.1792 0.7931 0.932 0.000 0.000 0.068
#> GSM425844 1 0.4262 0.6868 0.756 0.000 0.008 0.236
#> GSM425845 1 0.3253 0.7535 0.876 0.008 0.016 0.100
#> GSM425846 1 0.7295 0.2843 0.524 0.288 0.000 0.188
#> GSM425847 1 0.3726 0.6505 0.788 0.212 0.000 0.000
#> GSM425886 3 0.3720 0.8372 0.024 0.016 0.860 0.100
#> GSM425887 2 0.4382 0.5949 0.296 0.704 0.000 0.000
#> GSM425888 2 0.5535 0.3018 0.420 0.560 0.000 0.020
#> GSM425889 4 0.4567 0.6009 0.244 0.000 0.016 0.740
#> GSM425890 4 0.2675 0.7848 0.100 0.000 0.008 0.892
#> GSM425891 2 0.0188 0.8032 0.000 0.996 0.004 0.000
#> GSM425892 2 0.4382 0.6081 0.000 0.704 0.000 0.296
#> GSM425853 1 0.2714 0.7845 0.884 0.000 0.004 0.112
#> GSM425854 2 0.2647 0.7808 0.000 0.880 0.000 0.120
#> GSM425855 1 0.3870 0.7301 0.788 0.000 0.004 0.208
#> GSM425856 1 0.3757 0.7651 0.828 0.000 0.020 0.152
#> GSM425857 4 0.5952 0.3842 0.028 0.028 0.276 0.668
#> GSM425858 2 0.3123 0.7430 0.156 0.844 0.000 0.000
#> GSM425859 2 0.4746 0.4845 0.000 0.632 0.000 0.368
#> GSM425860 1 0.4758 0.6775 0.780 0.156 0.064 0.000
#> GSM425861 1 0.4391 0.5923 0.740 0.252 0.000 0.008
#> GSM425862 4 0.4284 0.6389 0.224 0.000 0.012 0.764
#> GSM425837 1 0.3048 0.7918 0.876 0.000 0.016 0.108
#> GSM425838 4 0.2089 0.7500 0.048 0.020 0.000 0.932
#> GSM425839 2 0.2408 0.7878 0.000 0.896 0.000 0.104
#> GSM425840 1 0.3351 0.7685 0.844 0.000 0.008 0.148
#> GSM425841 4 0.2741 0.7885 0.096 0.012 0.000 0.892
#> GSM425842 1 0.0657 0.7914 0.984 0.012 0.000 0.004
#> GSM425917 3 0.2651 0.8136 0.004 0.004 0.896 0.096
#> GSM425922 4 0.2860 0.7871 0.100 0.008 0.004 0.888
#> GSM425919 1 0.4663 0.7531 0.788 0.000 0.148 0.064
#> GSM425920 1 0.3105 0.7814 0.868 0.000 0.012 0.120
#> GSM425923 1 0.5452 0.4652 0.616 0.000 0.024 0.360
#> GSM425916 1 0.5576 0.6885 0.720 0.000 0.096 0.184
#> GSM425918 1 0.5038 0.5929 0.684 0.000 0.020 0.296
#> GSM425921 4 0.2530 0.7869 0.100 0.004 0.000 0.896
#> GSM425925 4 0.5080 0.2042 0.420 0.004 0.000 0.576
#> GSM425926 4 0.2593 0.7861 0.104 0.004 0.000 0.892
#> GSM425927 1 0.1305 0.7945 0.960 0.000 0.004 0.036
#> GSM425924 3 0.1610 0.8559 0.032 0.000 0.952 0.016
#> GSM425928 3 0.0188 0.8718 0.000 0.000 0.996 0.004
#> GSM425929 3 0.0707 0.8732 0.000 0.020 0.980 0.000
#> GSM425930 3 0.0469 0.8743 0.000 0.012 0.988 0.000
#> GSM425931 3 0.0000 0.8730 0.000 0.000 1.000 0.000
#> GSM425932 3 0.0707 0.8732 0.000 0.020 0.980 0.000
#> GSM425933 3 0.0592 0.8739 0.000 0.016 0.984 0.000
#> GSM425934 3 0.1022 0.8688 0.000 0.032 0.968 0.000
#> GSM425935 3 0.1302 0.8620 0.000 0.044 0.956 0.000
#> GSM425936 3 0.0817 0.8719 0.000 0.024 0.976 0.000
#> GSM425937 3 0.0469 0.8743 0.000 0.012 0.988 0.000
#> GSM425938 3 0.0376 0.8744 0.000 0.004 0.992 0.004
#> GSM425939 3 0.0336 0.8742 0.000 0.008 0.992 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM425907 2 0.4885 0.381 0.000 0.572 0.000 0.400 0.028
#> GSM425908 2 0.4803 0.298 0.000 0.536 0.000 0.444 0.020
#> GSM425909 5 0.1549 0.837 0.000 0.000 0.040 0.016 0.944
#> GSM425910 1 0.4428 0.641 0.756 0.084 0.000 0.000 0.160
#> GSM425911 2 0.0613 0.774 0.008 0.984 0.004 0.000 0.004
#> GSM425912 2 0.2690 0.701 0.156 0.844 0.000 0.000 0.000
#> GSM425913 2 0.0162 0.774 0.000 0.996 0.004 0.000 0.000
#> GSM425914 2 0.1270 0.764 0.052 0.948 0.000 0.000 0.000
#> GSM425915 5 0.2690 0.787 0.000 0.000 0.156 0.000 0.844
#> GSM425874 4 0.1329 0.800 0.032 0.004 0.000 0.956 0.008
#> GSM425875 5 0.2127 0.833 0.108 0.000 0.000 0.000 0.892
#> GSM425876 1 0.3002 0.731 0.856 0.116 0.000 0.000 0.028
#> GSM425877 1 0.3938 0.686 0.796 0.000 0.024 0.164 0.016
#> GSM425878 1 0.1430 0.765 0.944 0.000 0.000 0.004 0.052
#> GSM425879 2 0.0162 0.774 0.000 0.996 0.004 0.000 0.000
#> GSM425880 5 0.1740 0.852 0.056 0.000 0.012 0.000 0.932
#> GSM425881 2 0.3395 0.616 0.236 0.764 0.000 0.000 0.000
#> GSM425882 2 0.0579 0.775 0.008 0.984 0.000 0.008 0.000
#> GSM425883 1 0.5530 0.252 0.532 0.004 0.024 0.420 0.020
#> GSM425884 1 0.1502 0.763 0.940 0.000 0.000 0.004 0.056
#> GSM425885 4 0.3841 0.690 0.000 0.032 0.000 0.780 0.188
#> GSM425848 5 0.2915 0.765 0.024 0.000 0.000 0.116 0.860
#> GSM425849 1 0.2228 0.765 0.912 0.000 0.000 0.040 0.048
#> GSM425850 1 0.2338 0.743 0.884 0.112 0.000 0.000 0.004
#> GSM425851 3 0.7225 -0.013 0.328 0.000 0.388 0.264 0.020
#> GSM425852 5 0.2914 0.842 0.052 0.000 0.076 0.000 0.872
#> GSM425893 2 0.5034 0.470 0.000 0.648 0.028 0.016 0.308
#> GSM425894 4 0.4325 0.525 0.000 0.240 0.000 0.724 0.036
#> GSM425895 2 0.1831 0.764 0.000 0.920 0.000 0.076 0.004
#> GSM425896 2 0.7241 0.141 0.000 0.388 0.020 0.280 0.312
#> GSM425897 2 0.0671 0.773 0.000 0.980 0.004 0.016 0.000
#> GSM425898 2 0.4235 0.526 0.000 0.656 0.000 0.336 0.008
#> GSM425899 4 0.3344 0.780 0.104 0.016 0.000 0.852 0.028
#> GSM425900 2 0.0963 0.768 0.036 0.964 0.000 0.000 0.000
#> GSM425901 5 0.1493 0.833 0.000 0.000 0.028 0.024 0.948
#> GSM425902 4 0.1831 0.782 0.000 0.004 0.000 0.920 0.076
#> GSM425903 5 0.2036 0.853 0.056 0.000 0.024 0.000 0.920
#> GSM425904 5 0.1626 0.852 0.044 0.000 0.016 0.000 0.940
#> GSM425905 2 0.1410 0.766 0.000 0.940 0.000 0.060 0.000
#> GSM425906 2 0.0771 0.771 0.020 0.976 0.004 0.000 0.000
#> GSM425863 1 0.3921 0.674 0.784 0.000 0.000 0.172 0.044
#> GSM425864 2 0.2407 0.752 0.000 0.896 0.004 0.088 0.012
#> GSM425865 2 0.1952 0.758 0.000 0.912 0.000 0.084 0.004
#> GSM425866 5 0.2852 0.777 0.172 0.000 0.000 0.000 0.828
#> GSM425867 5 0.4733 0.501 0.028 0.000 0.348 0.000 0.624
#> GSM425868 4 0.3635 0.536 0.000 0.248 0.000 0.748 0.004
#> GSM425869 4 0.3037 0.729 0.000 0.100 0.000 0.860 0.040
#> GSM425870 2 0.4813 0.346 0.004 0.600 0.376 0.000 0.020
#> GSM425871 1 0.1369 0.766 0.956 0.008 0.000 0.028 0.008
#> GSM425872 2 0.3480 0.622 0.000 0.752 0.000 0.248 0.000
#> GSM425873 1 0.2450 0.751 0.896 0.076 0.000 0.000 0.028
#> GSM425843 1 0.1444 0.768 0.948 0.000 0.000 0.012 0.040
#> GSM425844 1 0.4965 0.515 0.664 0.000 0.024 0.292 0.020
#> GSM425845 5 0.4242 0.278 0.428 0.000 0.000 0.000 0.572
#> GSM425846 2 0.6613 0.218 0.336 0.464 0.000 0.196 0.004
#> GSM425847 1 0.3305 0.654 0.776 0.224 0.000 0.000 0.000
#> GSM425886 5 0.2504 0.817 0.000 0.000 0.064 0.040 0.896
#> GSM425887 2 0.3424 0.613 0.240 0.760 0.000 0.000 0.000
#> GSM425888 2 0.4218 0.434 0.332 0.660 0.000 0.008 0.000
#> GSM425889 4 0.5073 0.606 0.212 0.000 0.000 0.688 0.100
#> GSM425890 4 0.2968 0.760 0.092 0.000 0.028 0.872 0.008
#> GSM425891 2 0.0162 0.774 0.000 0.996 0.004 0.000 0.000
#> GSM425892 2 0.4757 0.426 0.000 0.596 0.000 0.380 0.024
#> GSM425853 1 0.3913 0.445 0.676 0.000 0.000 0.000 0.324
#> GSM425854 2 0.1965 0.758 0.000 0.904 0.000 0.096 0.000
#> GSM425855 1 0.3934 0.590 0.716 0.000 0.000 0.276 0.008
#> GSM425856 5 0.1965 0.840 0.096 0.000 0.000 0.000 0.904
#> GSM425857 5 0.2890 0.712 0.000 0.000 0.004 0.160 0.836
#> GSM425858 2 0.1478 0.758 0.064 0.936 0.000 0.000 0.000
#> GSM425859 2 0.4504 0.357 0.000 0.564 0.000 0.428 0.008
#> GSM425860 1 0.3561 0.686 0.796 0.188 0.008 0.000 0.008
#> GSM425861 1 0.4047 0.481 0.676 0.320 0.000 0.000 0.004
#> GSM425862 4 0.5714 0.529 0.116 0.000 0.000 0.592 0.292
#> GSM425837 1 0.2464 0.751 0.888 0.000 0.000 0.016 0.096
#> GSM425838 4 0.3013 0.728 0.000 0.008 0.000 0.832 0.160
#> GSM425839 2 0.1792 0.761 0.000 0.916 0.000 0.084 0.000
#> GSM425840 1 0.2474 0.749 0.896 0.000 0.008 0.084 0.012
#> GSM425841 4 0.1173 0.800 0.020 0.004 0.000 0.964 0.012
#> GSM425842 1 0.1918 0.762 0.928 0.036 0.000 0.000 0.036
#> GSM425917 3 0.4162 0.742 0.048 0.000 0.800 0.132 0.020
#> GSM425922 4 0.2474 0.773 0.084 0.000 0.008 0.896 0.012
#> GSM425919 1 0.5485 0.492 0.640 0.000 0.284 0.056 0.020
#> GSM425920 1 0.3654 0.710 0.836 0.000 0.036 0.108 0.020
#> GSM425923 1 0.5660 0.417 0.588 0.000 0.052 0.340 0.020
#> GSM425916 1 0.6605 0.411 0.552 0.000 0.188 0.240 0.020
#> GSM425918 1 0.5409 0.455 0.616 0.000 0.040 0.324 0.020
#> GSM425921 4 0.1768 0.788 0.072 0.000 0.000 0.924 0.004
#> GSM425925 4 0.4114 0.288 0.376 0.000 0.000 0.624 0.000
#> GSM425926 4 0.1892 0.787 0.080 0.000 0.000 0.916 0.004
#> GSM425927 1 0.0992 0.768 0.968 0.000 0.000 0.008 0.024
#> GSM425924 3 0.3319 0.815 0.064 0.000 0.864 0.052 0.020
#> GSM425928 3 0.0162 0.914 0.000 0.000 0.996 0.004 0.000
#> GSM425929 3 0.0162 0.917 0.000 0.000 0.996 0.000 0.004
#> GSM425930 3 0.0404 0.917 0.000 0.000 0.988 0.000 0.012
#> GSM425931 3 0.0510 0.916 0.000 0.000 0.984 0.000 0.016
#> GSM425932 3 0.0162 0.917 0.000 0.000 0.996 0.000 0.004
#> GSM425933 3 0.0404 0.917 0.000 0.000 0.988 0.000 0.012
#> GSM425934 3 0.0324 0.917 0.000 0.004 0.992 0.000 0.004
#> GSM425935 3 0.0566 0.911 0.000 0.012 0.984 0.000 0.004
#> GSM425936 3 0.0290 0.918 0.000 0.000 0.992 0.000 0.008
#> GSM425937 3 0.0510 0.916 0.000 0.000 0.984 0.000 0.016
#> GSM425938 3 0.0609 0.913 0.000 0.000 0.980 0.000 0.020
#> GSM425939 3 0.0510 0.916 0.000 0.000 0.984 0.000 0.016
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 4 0.4284 -0.01007 0.000 0.440 0.000 0.544 0.012 0.004
#> GSM425908 4 0.4284 0.00868 0.004 0.440 0.000 0.544 0.012 0.000
#> GSM425909 5 0.1320 0.85788 0.000 0.000 0.016 0.036 0.948 0.000
#> GSM425910 1 0.5843 0.54666 0.632 0.112 0.000 0.008 0.196 0.052
#> GSM425911 2 0.1381 0.73939 0.020 0.952 0.004 0.020 0.004 0.000
#> GSM425912 2 0.3911 0.59754 0.172 0.772 0.008 0.004 0.000 0.044
#> GSM425913 2 0.0976 0.73869 0.000 0.968 0.008 0.008 0.000 0.016
#> GSM425914 2 0.2236 0.70591 0.088 0.896 0.004 0.004 0.004 0.004
#> GSM425915 5 0.2051 0.83615 0.000 0.000 0.096 0.004 0.896 0.004
#> GSM425874 6 0.4300 0.14410 0.012 0.000 0.000 0.456 0.004 0.528
#> GSM425875 5 0.3168 0.75674 0.024 0.000 0.000 0.000 0.804 0.172
#> GSM425876 1 0.4121 0.65432 0.792 0.108 0.000 0.004 0.052 0.044
#> GSM425877 1 0.4364 0.65137 0.744 0.000 0.008 0.160 0.004 0.084
#> GSM425878 1 0.3665 0.68984 0.820 0.000 0.000 0.040 0.048 0.092
#> GSM425879 2 0.1584 0.74092 0.008 0.928 0.000 0.064 0.000 0.000
#> GSM425880 5 0.0551 0.86675 0.004 0.000 0.008 0.000 0.984 0.004
#> GSM425881 2 0.4466 0.55247 0.180 0.716 0.000 0.000 0.004 0.100
#> GSM425882 2 0.2350 0.73064 0.020 0.880 0.000 0.100 0.000 0.000
#> GSM425883 6 0.4800 0.51028 0.200 0.000 0.032 0.056 0.004 0.708
#> GSM425884 1 0.2836 0.69702 0.872 0.000 0.000 0.060 0.052 0.016
#> GSM425885 4 0.4178 0.49822 0.000 0.032 0.000 0.776 0.124 0.068
#> GSM425848 5 0.3371 0.74597 0.004 0.008 0.000 0.180 0.796 0.012
#> GSM425849 6 0.3680 0.53553 0.216 0.000 0.000 0.008 0.020 0.756
#> GSM425850 1 0.4696 0.60659 0.728 0.124 0.000 0.004 0.016 0.128
#> GSM425851 1 0.5060 0.45572 0.600 0.000 0.048 0.332 0.004 0.016
#> GSM425852 5 0.1003 0.86657 0.016 0.000 0.020 0.000 0.964 0.000
#> GSM425893 2 0.5876 0.36372 0.012 0.548 0.012 0.120 0.308 0.000
#> GSM425894 6 0.5615 0.18198 0.000 0.116 0.004 0.368 0.004 0.508
#> GSM425895 2 0.3416 0.66918 0.000 0.804 0.000 0.140 0.000 0.056
#> GSM425896 4 0.5947 0.08569 0.000 0.340 0.004 0.460 0.196 0.000
#> GSM425897 2 0.2006 0.72965 0.000 0.892 0.000 0.104 0.004 0.000
#> GSM425898 6 0.5530 0.36631 0.000 0.216 0.000 0.224 0.000 0.560
#> GSM425899 6 0.2488 0.62123 0.004 0.000 0.000 0.124 0.008 0.864
#> GSM425900 6 0.3121 0.60146 0.008 0.192 0.004 0.000 0.000 0.796
#> GSM425901 5 0.1524 0.85043 0.000 0.000 0.008 0.060 0.932 0.000
#> GSM425902 6 0.3690 0.46374 0.000 0.000 0.000 0.288 0.012 0.700
#> GSM425903 5 0.0820 0.86682 0.012 0.000 0.016 0.000 0.972 0.000
#> GSM425904 5 0.0405 0.86642 0.000 0.000 0.008 0.000 0.988 0.004
#> GSM425905 2 0.1765 0.73274 0.000 0.904 0.000 0.096 0.000 0.000
#> GSM425906 2 0.1483 0.72859 0.008 0.944 0.012 0.000 0.000 0.036
#> GSM425863 6 0.1500 0.64773 0.052 0.000 0.000 0.000 0.012 0.936
#> GSM425864 2 0.2964 0.65623 0.000 0.792 0.000 0.204 0.004 0.000
#> GSM425865 2 0.2631 0.68061 0.000 0.820 0.000 0.180 0.000 0.000
#> GSM425866 5 0.1908 0.84266 0.056 0.000 0.000 0.000 0.916 0.028
#> GSM425867 5 0.3667 0.68343 0.012 0.000 0.240 0.000 0.740 0.008
#> GSM425868 4 0.4165 0.36083 0.004 0.292 0.000 0.676 0.000 0.028
#> GSM425869 4 0.4441 0.42715 0.000 0.092 0.000 0.700 0.000 0.208
#> GSM425870 2 0.4505 0.45851 0.028 0.652 0.304 0.000 0.016 0.000
#> GSM425871 1 0.2429 0.69461 0.896 0.008 0.000 0.028 0.004 0.064
#> GSM425872 6 0.4210 0.55585 0.000 0.080 0.008 0.164 0.000 0.748
#> GSM425873 1 0.4663 0.62064 0.744 0.072 0.000 0.004 0.040 0.140
#> GSM425843 1 0.4956 0.66145 0.704 0.000 0.000 0.072 0.048 0.176
#> GSM425844 1 0.3747 0.59018 0.732 0.000 0.004 0.248 0.004 0.012
#> GSM425845 5 0.5091 0.49068 0.220 0.000 0.000 0.004 0.640 0.136
#> GSM425846 6 0.3272 0.64778 0.020 0.092 0.000 0.032 0.008 0.848
#> GSM425847 1 0.5239 0.51460 0.624 0.248 0.000 0.004 0.004 0.120
#> GSM425886 5 0.2350 0.82543 0.000 0.000 0.020 0.100 0.880 0.000
#> GSM425887 2 0.5354 0.41599 0.164 0.624 0.000 0.004 0.004 0.204
#> GSM425888 6 0.4518 0.53798 0.072 0.236 0.004 0.000 0.000 0.688
#> GSM425889 6 0.2630 0.63555 0.004 0.000 0.000 0.092 0.032 0.872
#> GSM425890 4 0.3808 0.25013 0.284 0.000 0.004 0.700 0.000 0.012
#> GSM425891 2 0.0779 0.73923 0.000 0.976 0.008 0.008 0.000 0.008
#> GSM425892 2 0.4169 0.15856 0.000 0.532 0.000 0.456 0.012 0.000
#> GSM425853 1 0.5056 0.18107 0.508 0.000 0.000 0.004 0.424 0.064
#> GSM425854 2 0.2744 0.69452 0.000 0.840 0.000 0.144 0.000 0.016
#> GSM425855 6 0.1768 0.65119 0.040 0.000 0.004 0.020 0.004 0.932
#> GSM425856 5 0.1633 0.85136 0.024 0.000 0.000 0.000 0.932 0.044
#> GSM425857 5 0.3171 0.71159 0.000 0.012 0.000 0.204 0.784 0.000
#> GSM425858 6 0.4527 0.16117 0.024 0.456 0.004 0.000 0.000 0.516
#> GSM425859 2 0.4218 0.25108 0.000 0.556 0.000 0.428 0.000 0.016
#> GSM425860 1 0.7407 0.37873 0.492 0.192 0.096 0.004 0.028 0.188
#> GSM425861 6 0.4994 0.47247 0.208 0.108 0.000 0.004 0.008 0.672
#> GSM425862 6 0.3405 0.61504 0.000 0.000 0.000 0.112 0.076 0.812
#> GSM425837 1 0.6096 0.35967 0.480 0.000 0.000 0.016 0.180 0.324
#> GSM425838 4 0.3145 0.52111 0.068 0.028 0.000 0.860 0.040 0.004
#> GSM425839 2 0.3767 0.65873 0.000 0.788 0.004 0.128 0.000 0.080
#> GSM425840 6 0.4705 -0.09070 0.464 0.000 0.004 0.012 0.016 0.504
#> GSM425841 4 0.4124 0.27238 0.012 0.004 0.000 0.656 0.004 0.324
#> GSM425842 1 0.3861 0.65791 0.808 0.044 0.000 0.004 0.036 0.108
#> GSM425917 3 0.6049 0.30191 0.264 0.000 0.512 0.212 0.004 0.008
#> GSM425922 4 0.5020 0.36884 0.192 0.000 0.012 0.680 0.004 0.112
#> GSM425919 1 0.4086 0.63581 0.776 0.000 0.044 0.152 0.004 0.024
#> GSM425920 1 0.3859 0.64937 0.788 0.000 0.012 0.148 0.004 0.048
#> GSM425923 1 0.4871 0.50137 0.632 0.000 0.020 0.308 0.004 0.036
#> GSM425916 1 0.4368 0.57690 0.704 0.000 0.024 0.248 0.004 0.020
#> GSM425918 1 0.4334 0.54553 0.676 0.000 0.004 0.284 0.004 0.032
#> GSM425921 4 0.5490 0.21110 0.104 0.000 0.008 0.564 0.004 0.320
#> GSM425925 6 0.2068 0.64264 0.008 0.000 0.000 0.080 0.008 0.904
#> GSM425926 4 0.4521 -0.04408 0.024 0.000 0.000 0.524 0.004 0.448
#> GSM425927 1 0.2976 0.68759 0.852 0.000 0.000 0.020 0.020 0.108
#> GSM425924 3 0.5063 0.52482 0.244 0.000 0.644 0.104 0.004 0.004
#> GSM425928 3 0.0363 0.91628 0.000 0.000 0.988 0.012 0.000 0.000
#> GSM425929 3 0.0291 0.92310 0.000 0.004 0.992 0.000 0.004 0.000
#> GSM425930 3 0.0363 0.92209 0.000 0.000 0.988 0.000 0.012 0.000
#> GSM425931 3 0.0458 0.91938 0.000 0.000 0.984 0.000 0.016 0.000
#> GSM425932 3 0.0291 0.92310 0.000 0.004 0.992 0.000 0.004 0.000
#> GSM425933 3 0.0291 0.92310 0.000 0.004 0.992 0.000 0.004 0.000
#> GSM425934 3 0.0260 0.91901 0.000 0.008 0.992 0.000 0.000 0.000
#> GSM425935 3 0.0260 0.91905 0.000 0.008 0.992 0.000 0.000 0.000
#> GSM425936 3 0.0291 0.92310 0.000 0.004 0.992 0.000 0.004 0.000
#> GSM425937 3 0.0363 0.92209 0.000 0.000 0.988 0.000 0.012 0.000
#> GSM425938 3 0.0405 0.92229 0.000 0.000 0.988 0.004 0.008 0.000
#> GSM425939 3 0.0363 0.92209 0.000 0.000 0.988 0.000 0.012 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 disease.state(p) tissue(p) other(p) k
#> SD:NMF 99 1.97e-05 1.50e-05 7.31e-07 2
#> SD:NMF 75 3.36e-08 4.19e-08 3.01e-07 3
#> SD:NMF 90 7.26e-10 2.23e-09 1.03e-07 4
#> SD:NMF 84 2.27e-14 5.88e-14 2.01e-08 5
#> SD:NMF 74 3.90e-13 2.49e-13 1.43e-09 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 103 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 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 0.0934 0.458 0.723 0.4432 0.499 0.499
#> 3 3 0.0979 0.467 0.632 0.3797 0.803 0.638
#> 4 4 0.2758 0.312 0.564 0.1386 0.695 0.370
#> 5 5 0.4609 0.528 0.671 0.0971 0.784 0.386
#> 6 6 0.5853 0.507 0.680 0.0457 0.940 0.746
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
#> GSM425907 2 0.1843 0.6663 0.028 0.972
#> GSM425908 2 0.2778 0.6600 0.048 0.952
#> GSM425909 1 0.9248 0.5591 0.660 0.340
#> GSM425910 2 1.0000 -0.1943 0.496 0.504
#> GSM425911 2 0.5629 0.6440 0.132 0.868
#> GSM425912 2 0.6623 0.5885 0.172 0.828
#> GSM425913 2 0.3114 0.6663 0.056 0.944
#> GSM425914 2 0.9754 0.1821 0.408 0.592
#> GSM425915 1 0.9323 0.5435 0.652 0.348
#> GSM425874 2 0.9998 -0.3147 0.492 0.508
#> GSM425875 1 0.9044 0.5753 0.680 0.320
#> GSM425876 1 0.9815 0.3275 0.580 0.420
#> GSM425877 1 0.7139 0.6050 0.804 0.196
#> GSM425878 1 0.9522 0.5142 0.628 0.372
#> GSM425879 2 0.2043 0.6662 0.032 0.968
#> GSM425880 1 0.9044 0.5753 0.680 0.320
#> GSM425881 2 0.6343 0.5987 0.160 0.840
#> GSM425882 2 0.2236 0.6677 0.036 0.964
#> GSM425883 1 0.9983 0.3688 0.524 0.476
#> GSM425884 1 0.6531 0.5923 0.832 0.168
#> GSM425885 2 0.9286 0.0933 0.344 0.656
#> GSM425848 1 0.9686 0.5030 0.604 0.396
#> GSM425849 1 0.9983 0.3879 0.524 0.476
#> GSM425850 2 0.9998 -0.2192 0.492 0.508
#> GSM425851 1 0.4690 0.5727 0.900 0.100
#> GSM425852 1 0.9044 0.5735 0.680 0.320
#> GSM425893 2 0.5519 0.6400 0.128 0.872
#> GSM425894 2 0.0672 0.6608 0.008 0.992
#> GSM425895 2 0.3584 0.6655 0.068 0.932
#> GSM425896 2 0.4161 0.6582 0.084 0.916
#> GSM425897 2 0.3879 0.6658 0.076 0.924
#> GSM425898 2 0.0938 0.6618 0.012 0.988
#> GSM425899 2 0.8081 0.3597 0.248 0.752
#> GSM425900 2 0.3114 0.6663 0.056 0.944
#> GSM425901 1 0.9209 0.5627 0.664 0.336
#> GSM425902 2 0.9998 -0.3289 0.492 0.508
#> GSM425903 1 0.9323 0.5435 0.652 0.348
#> GSM425904 1 0.9044 0.5753 0.680 0.320
#> GSM425905 2 0.1414 0.6641 0.020 0.980
#> GSM425906 2 0.3879 0.6629 0.076 0.924
#> GSM425863 1 0.9795 0.4730 0.584 0.416
#> GSM425864 2 0.3733 0.6665 0.072 0.928
#> GSM425865 2 0.4022 0.6601 0.080 0.920
#> GSM425866 1 0.9044 0.5753 0.680 0.320
#> GSM425867 1 0.8661 0.5300 0.712 0.288
#> GSM425868 2 0.3584 0.6526 0.068 0.932
#> GSM425869 2 0.0672 0.6623 0.008 0.992
#> GSM425870 2 0.6148 0.6222 0.152 0.848
#> GSM425871 1 0.9983 0.3215 0.524 0.476
#> GSM425872 2 0.2603 0.6677 0.044 0.956
#> GSM425873 1 0.9850 0.3210 0.572 0.428
#> GSM425843 1 0.7528 0.6059 0.784 0.216
#> GSM425844 1 0.9944 0.3598 0.544 0.456
#> GSM425845 1 0.8555 0.5388 0.720 0.280
#> GSM425846 2 0.5737 0.6010 0.136 0.864
#> GSM425847 2 0.8608 0.4175 0.284 0.716
#> GSM425886 1 0.9427 0.5363 0.640 0.360
#> GSM425887 2 0.3733 0.6650 0.072 0.928
#> GSM425888 2 0.6531 0.5931 0.168 0.832
#> GSM425889 1 0.9710 0.4891 0.600 0.400
#> GSM425890 1 0.8144 0.5946 0.748 0.252
#> GSM425891 2 0.3584 0.6677 0.068 0.932
#> GSM425892 2 0.6343 0.5524 0.160 0.840
#> GSM425853 1 0.9087 0.5361 0.676 0.324
#> GSM425854 2 0.1633 0.6673 0.024 0.976
#> GSM425855 1 0.9393 0.5454 0.644 0.356
#> GSM425856 1 0.9044 0.5753 0.680 0.320
#> GSM425857 1 0.9491 0.5337 0.632 0.368
#> GSM425858 2 0.3431 0.6661 0.064 0.936
#> GSM425859 2 0.0672 0.6608 0.008 0.992
#> GSM425860 1 0.9522 0.3861 0.628 0.372
#> GSM425861 2 0.6531 0.5931 0.168 0.832
#> GSM425862 1 0.9732 0.4853 0.596 0.404
#> GSM425837 1 0.3274 0.5650 0.940 0.060
#> GSM425838 2 0.9866 -0.1828 0.432 0.568
#> GSM425839 2 0.0672 0.6608 0.008 0.992
#> GSM425840 1 0.9393 0.5420 0.644 0.356
#> GSM425841 2 0.9993 -0.3141 0.484 0.516
#> GSM425842 1 0.9850 0.3359 0.572 0.428
#> GSM425917 1 1.0000 0.0255 0.504 0.496
#> GSM425922 1 0.9998 0.3157 0.508 0.492
#> GSM425919 1 0.4690 0.5727 0.900 0.100
#> GSM425920 1 0.8861 0.5598 0.696 0.304
#> GSM425923 1 0.5059 0.5843 0.888 0.112
#> GSM425916 1 0.1184 0.5469 0.984 0.016
#> GSM425918 1 0.7815 0.6047 0.768 0.232
#> GSM425921 1 1.0000 0.3013 0.500 0.500
#> GSM425925 1 1.0000 0.3057 0.500 0.500
#> GSM425926 2 0.9993 -0.2951 0.484 0.516
#> GSM425927 1 0.8207 0.5308 0.744 0.256
#> GSM425924 1 1.0000 0.0141 0.500 0.500
#> GSM425928 2 0.9491 0.3240 0.368 0.632
#> GSM425929 2 0.9460 0.3350 0.364 0.636
#> GSM425930 2 0.9460 0.3350 0.364 0.636
#> GSM425931 2 0.9460 0.3350 0.364 0.636
#> GSM425932 2 0.9460 0.3350 0.364 0.636
#> GSM425933 2 0.9460 0.3350 0.364 0.636
#> GSM425934 2 0.9460 0.3350 0.364 0.636
#> GSM425935 2 0.9460 0.3350 0.364 0.636
#> GSM425936 2 0.9460 0.3350 0.364 0.636
#> GSM425937 2 0.9460 0.3350 0.364 0.636
#> GSM425938 2 0.9552 0.3019 0.376 0.624
#> GSM425939 2 0.9460 0.3350 0.364 0.636
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.410 0.59352 0.060 0.880 0.060
#> GSM425908 2 0.421 0.56141 0.088 0.872 0.040
#> GSM425909 3 0.318 0.85433 0.016 0.076 0.908
#> GSM425910 1 0.965 0.18854 0.408 0.384 0.208
#> GSM425911 2 0.645 0.57001 0.052 0.736 0.212
#> GSM425912 2 0.715 0.43991 0.176 0.716 0.108
#> GSM425913 2 0.293 0.59811 0.036 0.924 0.040
#> GSM425914 2 0.953 0.17236 0.300 0.480 0.220
#> GSM425915 3 0.367 0.84127 0.020 0.092 0.888
#> GSM425874 1 0.977 0.47015 0.400 0.368 0.232
#> GSM425875 3 0.343 0.85421 0.032 0.064 0.904
#> GSM425876 1 0.906 0.34467 0.524 0.316 0.160
#> GSM425877 1 0.748 0.46445 0.688 0.108 0.204
#> GSM425878 1 0.946 0.47889 0.500 0.256 0.244
#> GSM425879 2 0.429 0.59798 0.068 0.872 0.060
#> GSM425880 3 0.343 0.85421 0.032 0.064 0.904
#> GSM425881 2 0.632 0.46418 0.160 0.764 0.076
#> GSM425882 2 0.315 0.60262 0.048 0.916 0.036
#> GSM425883 1 0.976 0.51203 0.420 0.344 0.236
#> GSM425884 1 0.721 0.31891 0.668 0.060 0.272
#> GSM425885 2 0.909 -0.19561 0.312 0.524 0.164
#> GSM425848 1 0.956 0.52648 0.484 0.260 0.256
#> GSM425849 1 0.982 0.51621 0.420 0.324 0.256
#> GSM425850 1 0.944 0.37785 0.440 0.380 0.180
#> GSM425851 1 0.671 0.31083 0.716 0.056 0.228
#> GSM425852 3 0.535 0.78868 0.088 0.088 0.824
#> GSM425893 2 0.649 0.56300 0.052 0.732 0.216
#> GSM425894 2 0.260 0.60668 0.016 0.932 0.052
#> GSM425895 2 0.313 0.59559 0.032 0.916 0.052
#> GSM425896 2 0.597 0.58520 0.060 0.780 0.160
#> GSM425897 2 0.563 0.59597 0.044 0.792 0.164
#> GSM425898 2 0.234 0.60665 0.012 0.940 0.048
#> GSM425899 2 0.830 0.06256 0.196 0.632 0.172
#> GSM425900 2 0.293 0.59802 0.036 0.924 0.040
#> GSM425901 3 0.309 0.85394 0.016 0.072 0.912
#> GSM425902 1 0.985 0.48389 0.396 0.352 0.252
#> GSM425903 3 0.367 0.84127 0.020 0.092 0.888
#> GSM425904 3 0.343 0.85421 0.032 0.064 0.904
#> GSM425905 2 0.359 0.58623 0.052 0.900 0.048
#> GSM425906 2 0.419 0.58478 0.056 0.876 0.068
#> GSM425863 1 0.968 0.51892 0.460 0.280 0.260
#> GSM425864 2 0.553 0.59609 0.036 0.792 0.172
#> GSM425865 2 0.523 0.59268 0.068 0.828 0.104
#> GSM425866 3 0.343 0.85421 0.032 0.064 0.904
#> GSM425867 3 0.893 0.26594 0.384 0.128 0.488
#> GSM425868 2 0.445 0.53945 0.100 0.860 0.040
#> GSM425869 2 0.277 0.60323 0.024 0.928 0.048
#> GSM425870 2 0.698 0.55330 0.076 0.712 0.212
#> GSM425871 1 0.945 0.47244 0.452 0.364 0.184
#> GSM425872 2 0.350 0.61605 0.020 0.896 0.084
#> GSM425873 1 0.903 0.33278 0.520 0.328 0.152
#> GSM425843 1 0.752 0.46183 0.688 0.116 0.196
#> GSM425844 1 0.950 0.47865 0.452 0.356 0.192
#> GSM425845 3 0.908 0.25147 0.368 0.144 0.488
#> GSM425846 2 0.611 0.44890 0.116 0.784 0.100
#> GSM425847 2 0.829 0.22981 0.280 0.604 0.116
#> GSM425886 3 0.338 0.84441 0.012 0.092 0.896
#> GSM425887 2 0.325 0.59628 0.036 0.912 0.052
#> GSM425888 2 0.652 0.45323 0.168 0.752 0.080
#> GSM425889 1 0.963 0.51277 0.472 0.264 0.264
#> GSM425890 1 0.861 0.48081 0.600 0.172 0.228
#> GSM425891 2 0.398 0.59864 0.048 0.884 0.068
#> GSM425892 2 0.686 0.39986 0.132 0.740 0.128
#> GSM425853 1 0.939 0.22423 0.496 0.200 0.304
#> GSM425854 2 0.245 0.61200 0.012 0.936 0.052
#> GSM425855 1 0.921 0.52090 0.536 0.240 0.224
#> GSM425856 3 0.343 0.85421 0.032 0.064 0.904
#> GSM425857 3 0.422 0.79600 0.032 0.100 0.868
#> GSM425858 2 0.301 0.59902 0.028 0.920 0.052
#> GSM425859 2 0.234 0.60831 0.012 0.940 0.048
#> GSM425860 1 0.969 0.00652 0.452 0.240 0.308
#> GSM425861 2 0.652 0.45323 0.168 0.752 0.080
#> GSM425862 1 0.965 0.51387 0.468 0.268 0.264
#> GSM425837 1 0.605 0.29574 0.696 0.012 0.292
#> GSM425838 2 0.967 -0.39701 0.344 0.436 0.220
#> GSM425839 2 0.234 0.60831 0.012 0.940 0.048
#> GSM425840 1 0.918 0.52245 0.540 0.240 0.220
#> GSM425841 1 0.983 0.47605 0.388 0.368 0.244
#> GSM425842 1 0.906 0.35599 0.520 0.324 0.156
#> GSM425917 1 0.991 -0.14135 0.368 0.364 0.268
#> GSM425922 1 0.953 0.47936 0.448 0.356 0.196
#> GSM425919 1 0.671 0.31083 0.716 0.056 0.228
#> GSM425920 1 0.869 0.47157 0.596 0.204 0.200
#> GSM425923 1 0.714 0.39927 0.688 0.068 0.244
#> GSM425916 1 0.528 0.32345 0.752 0.004 0.244
#> GSM425918 1 0.844 0.45976 0.612 0.152 0.236
#> GSM425921 1 0.968 0.47064 0.416 0.368 0.216
#> GSM425925 1 0.971 0.47901 0.420 0.356 0.224
#> GSM425926 1 0.962 0.45657 0.416 0.380 0.204
#> GSM425927 1 0.751 0.37212 0.696 0.160 0.144
#> GSM425924 2 0.994 0.12057 0.356 0.364 0.280
#> GSM425928 2 0.964 0.29514 0.224 0.452 0.324
#> GSM425929 2 0.963 0.30361 0.224 0.456 0.320
#> GSM425930 2 0.963 0.30361 0.224 0.456 0.320
#> GSM425931 2 0.963 0.30361 0.224 0.456 0.320
#> GSM425932 2 0.963 0.30361 0.224 0.456 0.320
#> GSM425933 2 0.963 0.30361 0.224 0.456 0.320
#> GSM425934 2 0.963 0.30361 0.224 0.456 0.320
#> GSM425935 2 0.963 0.30361 0.224 0.456 0.320
#> GSM425936 2 0.963 0.30361 0.224 0.456 0.320
#> GSM425937 2 0.963 0.30361 0.224 0.456 0.320
#> GSM425938 2 0.961 0.27486 0.212 0.448 0.340
#> GSM425939 2 0.963 0.30361 0.224 0.456 0.320
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.8362 0.2497 0.316 0.368 0.016 0.300
#> GSM425908 4 0.8380 -0.2978 0.312 0.320 0.016 0.352
#> GSM425909 3 0.4500 0.9520 0.012 0.168 0.796 0.024
#> GSM425910 1 0.8153 0.2522 0.516 0.308 0.076 0.100
#> GSM425911 2 0.7153 0.3446 0.264 0.604 0.028 0.104
#> GSM425912 1 0.8339 0.1149 0.508 0.272 0.056 0.164
#> GSM425913 1 0.8335 -0.1580 0.392 0.368 0.024 0.216
#> GSM425914 1 0.7680 0.0264 0.472 0.404 0.056 0.068
#> GSM425915 3 0.4923 0.9304 0.016 0.208 0.756 0.020
#> GSM425874 4 0.2174 0.5756 0.000 0.020 0.052 0.928
#> GSM425875 3 0.4508 0.9536 0.012 0.152 0.804 0.032
#> GSM425876 1 0.7300 0.2780 0.644 0.188 0.096 0.072
#> GSM425877 1 0.8938 -0.1490 0.392 0.112 0.124 0.372
#> GSM425878 1 0.8972 -0.0788 0.408 0.104 0.140 0.348
#> GSM425879 2 0.8333 0.2616 0.316 0.384 0.016 0.284
#> GSM425880 3 0.4508 0.9536 0.012 0.152 0.804 0.032
#> GSM425881 1 0.8217 0.1007 0.516 0.256 0.044 0.184
#> GSM425882 2 0.8576 0.2328 0.340 0.360 0.028 0.272
#> GSM425883 4 0.6892 0.5288 0.116 0.124 0.072 0.688
#> GSM425884 1 0.9214 0.0684 0.452 0.128 0.216 0.204
#> GSM425885 4 0.6489 0.4113 0.108 0.156 0.036 0.700
#> GSM425848 4 0.7609 0.4731 0.180 0.080 0.116 0.624
#> GSM425849 4 0.6856 0.5039 0.168 0.048 0.108 0.676
#> GSM425850 1 0.8933 0.0425 0.448 0.168 0.092 0.292
#> GSM425851 1 0.9428 0.0738 0.400 0.284 0.156 0.160
#> GSM425852 3 0.5770 0.8643 0.040 0.228 0.708 0.024
#> GSM425893 2 0.6595 0.3849 0.232 0.652 0.016 0.100
#> GSM425894 2 0.8151 0.2422 0.324 0.380 0.008 0.288
#> GSM425895 1 0.8412 -0.1519 0.392 0.344 0.024 0.240
#> GSM425896 2 0.7575 0.3644 0.236 0.556 0.016 0.192
#> GSM425897 2 0.7312 0.3656 0.256 0.580 0.016 0.148
#> GSM425898 2 0.8151 0.2345 0.332 0.376 0.008 0.284
#> GSM425899 4 0.7934 0.2559 0.244 0.136 0.056 0.564
#> GSM425900 1 0.8350 -0.1539 0.392 0.364 0.024 0.220
#> GSM425901 3 0.4455 0.9519 0.012 0.164 0.800 0.024
#> GSM425902 4 0.3687 0.5761 0.012 0.048 0.072 0.868
#> GSM425903 3 0.4923 0.9304 0.016 0.208 0.756 0.020
#> GSM425904 3 0.4508 0.9536 0.012 0.152 0.804 0.032
#> GSM425905 2 0.8384 0.2291 0.328 0.344 0.016 0.312
#> GSM425906 1 0.8349 -0.1168 0.412 0.356 0.028 0.204
#> GSM425863 4 0.6582 0.5399 0.108 0.060 0.124 0.708
#> GSM425864 2 0.7640 0.3519 0.264 0.560 0.028 0.148
#> GSM425865 2 0.8534 0.2321 0.304 0.396 0.028 0.272
#> GSM425866 3 0.4508 0.9536 0.012 0.152 0.804 0.032
#> GSM425867 2 0.8157 -0.1895 0.284 0.424 0.280 0.012
#> GSM425868 4 0.8421 -0.2573 0.284 0.316 0.020 0.380
#> GSM425869 2 0.8266 0.2397 0.320 0.372 0.012 0.296
#> GSM425870 2 0.6382 0.3637 0.260 0.652 0.016 0.072
#> GSM425871 4 0.8055 0.2856 0.368 0.064 0.092 0.476
#> GSM425872 2 0.8320 0.2092 0.336 0.432 0.028 0.204
#> GSM425873 1 0.7288 0.2777 0.644 0.192 0.084 0.080
#> GSM425843 1 0.8991 -0.1092 0.408 0.124 0.120 0.348
#> GSM425844 4 0.8324 0.2865 0.348 0.080 0.100 0.472
#> GSM425845 2 0.8440 -0.2197 0.304 0.372 0.304 0.020
#> GSM425846 4 0.8621 -0.1032 0.344 0.236 0.036 0.384
#> GSM425847 1 0.8253 0.2187 0.544 0.236 0.072 0.148
#> GSM425886 3 0.4692 0.9388 0.012 0.196 0.772 0.020
#> GSM425887 1 0.8398 -0.1512 0.396 0.344 0.024 0.236
#> GSM425888 1 0.8334 0.1168 0.512 0.252 0.052 0.184
#> GSM425889 4 0.6380 0.5390 0.104 0.052 0.124 0.720
#> GSM425890 4 0.8428 0.3184 0.228 0.128 0.104 0.540
#> GSM425891 1 0.8472 -0.1523 0.380 0.376 0.032 0.212
#> GSM425892 4 0.8149 -0.0217 0.276 0.236 0.020 0.468
#> GSM425853 1 0.9459 0.1578 0.400 0.276 0.168 0.156
#> GSM425854 2 0.8483 0.2159 0.352 0.384 0.028 0.236
#> GSM425855 4 0.8656 0.2994 0.304 0.120 0.100 0.476
#> GSM425856 3 0.4508 0.9536 0.012 0.152 0.804 0.032
#> GSM425857 3 0.5585 0.8975 0.012 0.192 0.732 0.064
#> GSM425858 1 0.8420 -0.1608 0.400 0.352 0.028 0.220
#> GSM425859 2 0.8134 0.2497 0.324 0.388 0.008 0.280
#> GSM425860 2 0.7639 -0.1087 0.344 0.516 0.108 0.032
#> GSM425861 1 0.8334 0.1168 0.512 0.252 0.052 0.184
#> GSM425862 4 0.6455 0.5401 0.104 0.056 0.124 0.716
#> GSM425837 1 0.9082 -0.0175 0.436 0.088 0.236 0.240
#> GSM425838 4 0.4318 0.5259 0.088 0.016 0.060 0.836
#> GSM425839 2 0.8134 0.2497 0.324 0.388 0.008 0.280
#> GSM425840 4 0.8708 0.2904 0.308 0.124 0.100 0.468
#> GSM425841 4 0.3037 0.5765 0.000 0.036 0.076 0.888
#> GSM425842 1 0.7755 0.2670 0.612 0.188 0.104 0.096
#> GSM425917 2 0.5981 0.2549 0.088 0.752 0.096 0.064
#> GSM425922 4 0.2099 0.5644 0.012 0.008 0.044 0.936
#> GSM425919 1 0.9428 0.0738 0.400 0.284 0.156 0.160
#> GSM425920 1 0.9676 -0.0861 0.324 0.232 0.140 0.304
#> GSM425923 4 0.9003 0.1641 0.328 0.104 0.148 0.420
#> GSM425916 1 0.9426 -0.0736 0.392 0.148 0.164 0.296
#> GSM425918 4 0.8774 0.2697 0.252 0.136 0.116 0.496
#> GSM425921 4 0.1732 0.5727 0.004 0.008 0.040 0.948
#> GSM425925 4 0.1975 0.5760 0.016 0.000 0.048 0.936
#> GSM425926 4 0.1109 0.5701 0.004 0.000 0.028 0.968
#> GSM425927 1 0.8199 0.1772 0.544 0.260 0.100 0.096
#> GSM425924 2 0.5798 0.2667 0.092 0.764 0.076 0.068
#> GSM425928 2 0.0779 0.4552 0.000 0.980 0.016 0.004
#> GSM425929 2 0.0524 0.4596 0.000 0.988 0.008 0.004
#> GSM425930 2 0.0524 0.4596 0.000 0.988 0.008 0.004
#> GSM425931 2 0.0524 0.4596 0.000 0.988 0.008 0.004
#> GSM425932 2 0.0524 0.4596 0.000 0.988 0.008 0.004
#> GSM425933 2 0.0524 0.4596 0.000 0.988 0.008 0.004
#> GSM425934 2 0.0524 0.4596 0.000 0.988 0.008 0.004
#> GSM425935 2 0.0524 0.4596 0.000 0.988 0.008 0.004
#> GSM425936 2 0.0524 0.4596 0.000 0.988 0.008 0.004
#> GSM425937 2 0.0524 0.4596 0.000 0.988 0.008 0.004
#> GSM425938 2 0.1022 0.4470 0.000 0.968 0.032 0.000
#> GSM425939 2 0.0524 0.4596 0.000 0.988 0.008 0.004
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM425907 2 0.4491 0.67970 0.008 0.780 0.088 0.120 0.004
#> GSM425908 2 0.5021 0.65547 0.032 0.748 0.060 0.156 0.004
#> GSM425909 5 0.0693 0.94422 0.000 0.008 0.012 0.000 0.980
#> GSM425910 1 0.7386 0.42497 0.524 0.232 0.168 0.004 0.072
#> GSM425911 2 0.6984 0.34566 0.088 0.540 0.292 0.004 0.076
#> GSM425912 2 0.5882 0.32232 0.344 0.572 0.068 0.008 0.008
#> GSM425913 2 0.3762 0.70156 0.064 0.852 0.044 0.016 0.024
#> GSM425914 2 0.7937 -0.04337 0.328 0.368 0.232 0.004 0.068
#> GSM425915 5 0.1857 0.91829 0.004 0.008 0.060 0.000 0.928
#> GSM425874 4 0.2735 0.62753 0.000 0.084 0.000 0.880 0.036
#> GSM425875 5 0.0451 0.94582 0.000 0.000 0.004 0.008 0.988
#> GSM425876 1 0.4669 0.49993 0.760 0.152 0.076 0.004 0.008
#> GSM425877 1 0.7100 0.16456 0.512 0.024 0.112 0.324 0.028
#> GSM425878 1 0.7606 0.28112 0.520 0.092 0.048 0.284 0.056
#> GSM425879 2 0.4675 0.67605 0.008 0.772 0.100 0.112 0.008
#> GSM425880 5 0.0451 0.94582 0.000 0.000 0.004 0.008 0.988
#> GSM425881 2 0.5698 0.36320 0.336 0.596 0.044 0.016 0.008
#> GSM425882 2 0.4715 0.71037 0.048 0.796 0.048 0.092 0.016
#> GSM425883 4 0.7144 0.53047 0.096 0.136 0.080 0.632 0.056
#> GSM425884 1 0.7322 0.41185 0.584 0.016 0.136 0.164 0.100
#> GSM425885 4 0.5889 0.37439 0.012 0.332 0.040 0.592 0.024
#> GSM425848 4 0.7692 0.43762 0.220 0.076 0.060 0.556 0.088
#> GSM425849 4 0.6908 0.48066 0.196 0.104 0.008 0.604 0.088
#> GSM425850 1 0.7794 0.35518 0.544 0.184 0.056 0.164 0.052
#> GSM425851 3 0.6105 -0.34240 0.424 0.004 0.464 0.108 0.000
#> GSM425852 5 0.3446 0.82995 0.040 0.020 0.076 0.004 0.860
#> GSM425893 2 0.6691 0.27049 0.040 0.540 0.336 0.016 0.068
#> GSM425894 2 0.2665 0.71656 0.008 0.900 0.036 0.052 0.004
#> GSM425895 2 0.3833 0.70797 0.052 0.852 0.036 0.040 0.020
#> GSM425896 2 0.5959 0.42626 0.008 0.620 0.280 0.072 0.020
#> GSM425897 2 0.5587 0.47775 0.016 0.656 0.268 0.016 0.044
#> GSM425898 2 0.2881 0.71901 0.016 0.892 0.036 0.052 0.004
#> GSM425899 4 0.7539 0.10952 0.088 0.404 0.028 0.420 0.060
#> GSM425900 2 0.3561 0.70328 0.052 0.864 0.044 0.016 0.024
#> GSM425901 5 0.0579 0.94438 0.000 0.008 0.008 0.000 0.984
#> GSM425902 4 0.4227 0.62522 0.012 0.108 0.008 0.808 0.064
#> GSM425903 5 0.1857 0.91829 0.004 0.008 0.060 0.000 0.928
#> GSM425904 5 0.0451 0.94582 0.000 0.000 0.004 0.008 0.988
#> GSM425905 2 0.4019 0.69080 0.004 0.808 0.064 0.120 0.004
#> GSM425906 2 0.4465 0.66714 0.116 0.800 0.048 0.016 0.020
#> GSM425863 4 0.6689 0.55667 0.144 0.076 0.028 0.656 0.096
#> GSM425864 2 0.5879 0.49567 0.028 0.652 0.252 0.016 0.052
#> GSM425865 2 0.5694 0.68061 0.036 0.736 0.080 0.108 0.040
#> GSM425866 5 0.0451 0.94582 0.000 0.000 0.004 0.008 0.988
#> GSM425867 1 0.7620 0.17331 0.328 0.032 0.324 0.004 0.312
#> GSM425868 2 0.5277 0.62950 0.036 0.724 0.048 0.184 0.008
#> GSM425869 2 0.3023 0.71562 0.008 0.880 0.044 0.064 0.004
#> GSM425870 2 0.6716 0.22191 0.080 0.512 0.348 0.000 0.060
#> GSM425871 1 0.8074 0.00145 0.400 0.144 0.032 0.360 0.064
#> GSM425872 2 0.4509 0.70394 0.040 0.812 0.076 0.020 0.052
#> GSM425873 1 0.4256 0.49572 0.788 0.148 0.052 0.004 0.008
#> GSM425843 1 0.6956 0.23561 0.556 0.028 0.104 0.284 0.028
#> GSM425844 1 0.8500 -0.01405 0.364 0.148 0.076 0.360 0.052
#> GSM425845 1 0.7951 0.22790 0.340 0.052 0.276 0.008 0.324
#> GSM425846 2 0.6241 0.52397 0.080 0.648 0.008 0.212 0.052
#> GSM425847 1 0.6300 0.01051 0.492 0.416 0.060 0.012 0.020
#> GSM425886 5 0.1522 0.92831 0.000 0.012 0.044 0.000 0.944
#> GSM425887 2 0.3901 0.70789 0.056 0.848 0.036 0.040 0.020
#> GSM425888 2 0.6006 0.33707 0.344 0.576 0.044 0.020 0.016
#> GSM425889 4 0.6384 0.56714 0.140 0.064 0.028 0.680 0.088
#> GSM425890 4 0.7276 0.23309 0.244 0.032 0.172 0.532 0.020
#> GSM425891 2 0.4273 0.68617 0.084 0.820 0.052 0.012 0.032
#> GSM425892 2 0.6442 0.40367 0.028 0.564 0.044 0.332 0.032
#> GSM425853 1 0.8762 0.42395 0.456 0.076 0.196 0.108 0.164
#> GSM425854 2 0.3183 0.72626 0.024 0.884 0.032 0.044 0.016
#> GSM425855 4 0.8394 0.09559 0.364 0.084 0.096 0.388 0.068
#> GSM425856 5 0.0451 0.94582 0.000 0.000 0.004 0.008 0.988
#> GSM425857 5 0.2607 0.88811 0.000 0.032 0.024 0.040 0.904
#> GSM425858 2 0.4268 0.70760 0.076 0.824 0.048 0.036 0.016
#> GSM425859 2 0.2873 0.71395 0.008 0.892 0.044 0.048 0.008
#> GSM425860 3 0.7707 -0.20398 0.380 0.088 0.412 0.012 0.108
#> GSM425861 2 0.6006 0.33707 0.344 0.576 0.044 0.020 0.016
#> GSM425862 4 0.6442 0.56803 0.140 0.068 0.028 0.676 0.088
#> GSM425837 1 0.7299 0.32310 0.544 0.000 0.164 0.192 0.100
#> GSM425838 4 0.5308 0.53046 0.064 0.176 0.008 0.724 0.028
#> GSM425839 2 0.2873 0.71491 0.008 0.892 0.044 0.048 0.008
#> GSM425840 4 0.8433 0.08023 0.368 0.088 0.096 0.380 0.068
#> GSM425841 4 0.3449 0.62628 0.000 0.088 0.004 0.844 0.064
#> GSM425842 1 0.5079 0.49715 0.752 0.148 0.064 0.016 0.020
#> GSM425917 3 0.5367 0.58181 0.060 0.136 0.736 0.064 0.004
#> GSM425922 4 0.2467 0.60849 0.016 0.052 0.024 0.908 0.000
#> GSM425919 3 0.6105 -0.34240 0.424 0.004 0.464 0.108 0.000
#> GSM425920 1 0.8553 0.21140 0.376 0.068 0.280 0.236 0.040
#> GSM425923 4 0.7088 -0.09409 0.376 0.000 0.232 0.376 0.016
#> GSM425916 1 0.6764 0.22198 0.440 0.000 0.320 0.236 0.004
#> GSM425918 4 0.7687 0.14549 0.264 0.040 0.204 0.472 0.020
#> GSM425921 4 0.2022 0.61900 0.004 0.048 0.004 0.928 0.016
#> GSM425925 4 0.2769 0.62666 0.020 0.064 0.000 0.892 0.024
#> GSM425926 4 0.1857 0.61711 0.008 0.060 0.000 0.928 0.004
#> GSM425927 1 0.5282 0.45873 0.688 0.028 0.232 0.052 0.000
#> GSM425924 3 0.5624 0.59627 0.052 0.136 0.728 0.068 0.016
#> GSM425928 3 0.4787 0.79066 0.000 0.208 0.712 0.000 0.080
#> GSM425929 3 0.4676 0.79591 0.000 0.208 0.720 0.000 0.072
#> GSM425930 3 0.4676 0.79591 0.000 0.208 0.720 0.000 0.072
#> GSM425931 3 0.4676 0.79591 0.000 0.208 0.720 0.000 0.072
#> GSM425932 3 0.4676 0.79591 0.000 0.208 0.720 0.000 0.072
#> GSM425933 3 0.4676 0.79591 0.000 0.208 0.720 0.000 0.072
#> GSM425934 3 0.4676 0.79591 0.000 0.208 0.720 0.000 0.072
#> GSM425935 3 0.4676 0.79591 0.000 0.208 0.720 0.000 0.072
#> GSM425936 3 0.4676 0.79591 0.000 0.208 0.720 0.000 0.072
#> GSM425937 3 0.4676 0.79591 0.000 0.208 0.720 0.000 0.072
#> GSM425938 3 0.5043 0.77452 0.000 0.208 0.692 0.000 0.100
#> GSM425939 3 0.4676 0.79591 0.000 0.208 0.720 0.000 0.072
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 2 0.422 0.6518 0.008 0.796 0.072 0.032 0.004 0.088
#> GSM425908 2 0.468 0.6221 0.012 0.764 0.044 0.064 0.004 0.112
#> GSM425909 5 0.134 0.8859 0.008 0.004 0.040 0.000 0.948 0.000
#> GSM425910 6 0.807 0.2570 0.208 0.140 0.184 0.004 0.048 0.416
#> GSM425911 2 0.618 0.2078 0.008 0.440 0.404 0.000 0.020 0.128
#> GSM425912 2 0.498 0.1537 0.004 0.488 0.036 0.004 0.004 0.464
#> GSM425913 2 0.429 0.6553 0.000 0.776 0.064 0.016 0.016 0.128
#> GSM425914 2 0.817 -0.1322 0.180 0.316 0.236 0.000 0.032 0.236
#> GSM425915 5 0.242 0.8606 0.012 0.008 0.088 0.000 0.888 0.004
#> GSM425874 4 0.225 0.6315 0.000 0.056 0.004 0.908 0.020 0.012
#> GSM425875 5 0.079 0.8871 0.000 0.000 0.032 0.000 0.968 0.000
#> GSM425876 6 0.580 0.4063 0.320 0.096 0.028 0.000 0.004 0.552
#> GSM425877 1 0.715 0.2692 0.468 0.016 0.036 0.260 0.016 0.204
#> GSM425878 6 0.796 0.1931 0.196 0.068 0.016 0.252 0.048 0.420
#> GSM425879 2 0.440 0.6507 0.008 0.780 0.092 0.028 0.004 0.088
#> GSM425880 5 0.079 0.8871 0.000 0.000 0.032 0.000 0.968 0.000
#> GSM425881 2 0.444 0.2387 0.000 0.532 0.004 0.008 0.008 0.448
#> GSM425882 2 0.422 0.6700 0.008 0.796 0.056 0.028 0.008 0.104
#> GSM425883 4 0.686 0.5303 0.056 0.084 0.080 0.628 0.032 0.120
#> GSM425884 1 0.714 0.1316 0.468 0.008 0.032 0.076 0.088 0.328
#> GSM425885 4 0.686 0.3149 0.024 0.344 0.032 0.468 0.012 0.120
#> GSM425848 4 0.766 0.4080 0.140 0.048 0.044 0.528 0.060 0.180
#> GSM425849 4 0.671 0.4430 0.064 0.076 0.004 0.592 0.064 0.200
#> GSM425850 6 0.787 0.4131 0.144 0.112 0.040 0.160 0.036 0.508
#> GSM425851 1 0.471 0.4225 0.688 0.000 0.228 0.016 0.000 0.068
#> GSM425852 5 0.347 0.7881 0.028 0.004 0.120 0.004 0.828 0.016
#> GSM425893 2 0.563 0.1540 0.004 0.456 0.440 0.000 0.012 0.088
#> GSM425894 2 0.228 0.6851 0.000 0.904 0.056 0.016 0.000 0.024
#> GSM425895 2 0.407 0.6630 0.000 0.796 0.044 0.024 0.016 0.120
#> GSM425896 2 0.537 0.3953 0.008 0.600 0.312 0.008 0.008 0.064
#> GSM425897 2 0.506 0.4218 0.004 0.588 0.344 0.004 0.004 0.056
#> GSM425898 2 0.253 0.6866 0.000 0.896 0.052 0.020 0.004 0.028
#> GSM425899 4 0.691 0.1435 0.004 0.372 0.024 0.432 0.044 0.124
#> GSM425900 2 0.399 0.6557 0.000 0.800 0.052 0.016 0.016 0.116
#> GSM425901 5 0.127 0.8860 0.008 0.004 0.036 0.000 0.952 0.000
#> GSM425902 4 0.351 0.6343 0.008 0.084 0.012 0.844 0.036 0.016
#> GSM425903 5 0.242 0.8606 0.012 0.008 0.088 0.000 0.888 0.004
#> GSM425904 5 0.079 0.8871 0.000 0.000 0.032 0.000 0.968 0.000
#> GSM425905 2 0.388 0.6580 0.008 0.820 0.052 0.032 0.004 0.084
#> GSM425906 2 0.478 0.5976 0.000 0.704 0.056 0.012 0.016 0.212
#> GSM425863 4 0.624 0.5722 0.060 0.048 0.028 0.672 0.060 0.132
#> GSM425864 2 0.531 0.4310 0.004 0.572 0.340 0.000 0.012 0.072
#> GSM425865 2 0.549 0.6493 0.004 0.688 0.140 0.064 0.004 0.100
#> GSM425866 5 0.079 0.8871 0.000 0.000 0.032 0.000 0.968 0.000
#> GSM425867 3 0.794 -0.2207 0.248 0.012 0.316 0.004 0.272 0.148
#> GSM425868 2 0.489 0.6103 0.016 0.752 0.040 0.100 0.004 0.088
#> GSM425869 2 0.269 0.6815 0.000 0.884 0.052 0.036 0.000 0.028
#> GSM425870 3 0.586 -0.1197 0.008 0.404 0.464 0.000 0.008 0.116
#> GSM425871 6 0.770 0.1604 0.128 0.072 0.016 0.332 0.040 0.412
#> GSM425872 2 0.492 0.6542 0.000 0.724 0.144 0.016 0.020 0.096
#> GSM425873 6 0.551 0.4298 0.280 0.088 0.024 0.000 0.004 0.604
#> GSM425843 1 0.739 0.2125 0.452 0.016 0.040 0.188 0.028 0.276
#> GSM425844 6 0.801 0.1465 0.156 0.068 0.036 0.324 0.032 0.384
#> GSM425845 5 0.828 -0.1999 0.244 0.032 0.256 0.004 0.300 0.164
#> GSM425846 2 0.601 0.4329 0.000 0.616 0.020 0.216 0.040 0.108
#> GSM425847 6 0.591 0.2323 0.068 0.344 0.020 0.004 0.020 0.544
#> GSM425886 5 0.201 0.8716 0.008 0.008 0.076 0.000 0.908 0.000
#> GSM425887 2 0.421 0.6631 0.004 0.792 0.044 0.024 0.016 0.120
#> GSM425888 2 0.462 0.1845 0.000 0.508 0.004 0.008 0.016 0.464
#> GSM425889 4 0.599 0.5734 0.076 0.028 0.028 0.688 0.056 0.124
#> GSM425890 1 0.602 0.1556 0.452 0.016 0.080 0.432 0.004 0.016
#> GSM425891 2 0.475 0.6232 0.000 0.716 0.076 0.008 0.016 0.184
#> GSM425892 2 0.703 0.4143 0.024 0.540 0.072 0.208 0.008 0.148
#> GSM425853 1 0.896 0.0101 0.312 0.036 0.172 0.068 0.152 0.260
#> GSM425854 2 0.327 0.6888 0.000 0.852 0.060 0.016 0.008 0.064
#> GSM425855 4 0.828 0.0902 0.220 0.044 0.060 0.384 0.040 0.252
#> GSM425856 5 0.079 0.8871 0.000 0.000 0.032 0.000 0.968 0.000
#> GSM425857 5 0.318 0.8367 0.008 0.032 0.040 0.012 0.872 0.036
#> GSM425858 2 0.394 0.6620 0.000 0.796 0.044 0.016 0.012 0.132
#> GSM425859 2 0.233 0.6838 0.000 0.900 0.060 0.012 0.000 0.028
#> GSM425860 3 0.824 -0.1746 0.244 0.068 0.388 0.012 0.080 0.208
#> GSM425861 2 0.462 0.1845 0.000 0.508 0.004 0.008 0.016 0.464
#> GSM425862 4 0.613 0.5730 0.076 0.032 0.032 0.680 0.056 0.124
#> GSM425837 1 0.642 0.3558 0.620 0.000 0.044 0.068 0.108 0.160
#> GSM425838 4 0.728 0.3610 0.088 0.180 0.024 0.516 0.008 0.184
#> GSM425839 2 0.233 0.6847 0.000 0.900 0.060 0.012 0.000 0.028
#> GSM425840 4 0.831 0.0667 0.228 0.044 0.060 0.372 0.040 0.256
#> GSM425841 4 0.276 0.6337 0.000 0.064 0.008 0.880 0.040 0.008
#> GSM425842 6 0.609 0.4288 0.260 0.088 0.028 0.012 0.016 0.596
#> GSM425917 3 0.477 0.5226 0.216 0.060 0.700 0.016 0.000 0.008
#> GSM425922 4 0.320 0.5800 0.052 0.016 0.024 0.864 0.000 0.044
#> GSM425919 1 0.471 0.4225 0.688 0.000 0.228 0.016 0.000 0.068
#> GSM425920 1 0.813 0.2599 0.436 0.028 0.164 0.164 0.024 0.184
#> GSM425923 1 0.504 0.4491 0.680 0.000 0.048 0.224 0.004 0.044
#> GSM425916 1 0.330 0.4625 0.840 0.000 0.080 0.064 0.000 0.016
#> GSM425918 1 0.645 0.2788 0.484 0.016 0.092 0.364 0.004 0.040
#> GSM425921 4 0.194 0.6084 0.008 0.016 0.016 0.932 0.004 0.024
#> GSM425925 4 0.274 0.6204 0.016 0.024 0.004 0.884 0.004 0.068
#> GSM425926 4 0.217 0.6096 0.008 0.024 0.004 0.912 0.000 0.052
#> GSM425927 1 0.607 0.1262 0.508 0.020 0.112 0.012 0.000 0.348
#> GSM425924 3 0.486 0.5608 0.184 0.060 0.720 0.020 0.004 0.012
#> GSM425928 3 0.221 0.8228 0.004 0.100 0.888 0.000 0.008 0.000
#> GSM425929 3 0.196 0.8276 0.000 0.100 0.896 0.000 0.004 0.000
#> GSM425930 3 0.196 0.8276 0.000 0.100 0.896 0.000 0.004 0.000
#> GSM425931 3 0.196 0.8276 0.000 0.100 0.896 0.000 0.004 0.000
#> GSM425932 3 0.196 0.8276 0.000 0.100 0.896 0.000 0.004 0.000
#> GSM425933 3 0.196 0.8276 0.000 0.100 0.896 0.000 0.004 0.000
#> GSM425934 3 0.196 0.8276 0.000 0.100 0.896 0.000 0.004 0.000
#> GSM425935 3 0.196 0.8276 0.000 0.100 0.896 0.000 0.004 0.000
#> GSM425936 3 0.196 0.8276 0.000 0.100 0.896 0.000 0.004 0.000
#> GSM425937 3 0.196 0.8276 0.000 0.100 0.896 0.000 0.004 0.000
#> GSM425938 3 0.265 0.8073 0.004 0.100 0.868 0.000 0.028 0.000
#> GSM425939 3 0.196 0.8276 0.000 0.100 0.896 0.000 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 disease.state(p) tissue(p) other(p) k
#> CV:hclust 64 NA 2.60e-02 7.18e-02 2
#> CV:hclust 47 NA NA 4.01e-01 3
#> CV:hclust 25 NA 1.21e-01 3.86e-01 4
#> CV:hclust 60 1.13e-10 7.55e-12 6.42e-06 5
#> CV:hclust 58 2.65e-10 1.19e-11 5.26e-06 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 103 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 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 0.200 0.630 0.767 0.4620 0.495 0.495
#> 3 3 0.478 0.714 0.833 0.3639 0.771 0.573
#> 4 4 0.666 0.765 0.833 0.1372 0.913 0.762
#> 5 5 0.745 0.670 0.828 0.0892 0.893 0.656
#> 6 6 0.770 0.698 0.822 0.0537 0.904 0.608
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
#> GSM425907 2 0.8386 0.6587 0.268 0.732
#> GSM425908 2 0.9087 0.6399 0.324 0.676
#> GSM425909 2 0.9000 0.4741 0.316 0.684
#> GSM425910 1 0.9209 0.2501 0.664 0.336
#> GSM425911 2 0.8207 0.6614 0.256 0.744
#> GSM425912 2 0.9754 0.5900 0.408 0.592
#> GSM425913 2 0.9044 0.6438 0.320 0.680
#> GSM425914 2 0.9608 0.6163 0.384 0.616
#> GSM425915 2 0.7528 0.5796 0.216 0.784
#> GSM425874 1 0.4939 0.7558 0.892 0.108
#> GSM425875 1 0.5294 0.7131 0.880 0.120
#> GSM425876 1 0.7745 0.5721 0.772 0.228
#> GSM425877 1 0.2043 0.7873 0.968 0.032
#> GSM425878 1 0.0672 0.7959 0.992 0.008
#> GSM425879 2 0.8267 0.6593 0.260 0.740
#> GSM425880 1 0.8813 0.4582 0.700 0.300
#> GSM425881 1 0.9866 0.0531 0.568 0.432
#> GSM425882 2 0.9087 0.6399 0.324 0.676
#> GSM425883 1 0.1414 0.7950 0.980 0.020
#> GSM425884 1 0.2043 0.7873 0.968 0.032
#> GSM425885 1 0.9491 0.1554 0.632 0.368
#> GSM425848 1 0.4298 0.7749 0.912 0.088
#> GSM425849 1 0.4690 0.7600 0.900 0.100
#> GSM425850 1 0.2948 0.7843 0.948 0.052
#> GSM425851 1 0.2043 0.7873 0.968 0.032
#> GSM425852 1 0.8763 0.4623 0.704 0.296
#> GSM425893 2 0.4815 0.6350 0.104 0.896
#> GSM425894 2 0.9044 0.6438 0.320 0.680
#> GSM425895 2 0.9044 0.6438 0.320 0.680
#> GSM425896 2 0.4815 0.6343 0.104 0.896
#> GSM425897 2 0.8443 0.6584 0.272 0.728
#> GSM425898 2 0.9044 0.6438 0.320 0.680
#> GSM425899 1 0.7453 0.6256 0.788 0.212
#> GSM425900 2 0.9129 0.6427 0.328 0.672
#> GSM425901 2 0.9286 0.4222 0.344 0.656
#> GSM425902 1 0.4939 0.7558 0.892 0.108
#> GSM425903 2 0.7528 0.5907 0.216 0.784
#> GSM425904 1 0.8813 0.4582 0.700 0.300
#> GSM425905 2 0.9000 0.6460 0.316 0.684
#> GSM425906 2 0.9087 0.6458 0.324 0.676
#> GSM425863 1 0.1633 0.7944 0.976 0.024
#> GSM425864 2 0.8813 0.6519 0.300 0.700
#> GSM425865 2 0.9087 0.6399 0.324 0.676
#> GSM425866 1 0.6531 0.6529 0.832 0.168
#> GSM425867 2 0.7674 0.5543 0.224 0.776
#> GSM425868 2 0.9775 0.4756 0.412 0.588
#> GSM425869 2 0.9087 0.6399 0.324 0.676
#> GSM425870 2 0.5629 0.6117 0.132 0.868
#> GSM425871 1 0.3733 0.7779 0.928 0.072
#> GSM425872 2 0.9044 0.6438 0.320 0.680
#> GSM425873 1 0.5737 0.7231 0.864 0.136
#> GSM425843 1 0.2043 0.7873 0.968 0.032
#> GSM425844 1 0.0938 0.7959 0.988 0.012
#> GSM425845 1 0.9866 0.1568 0.568 0.432
#> GSM425846 1 0.8763 0.4970 0.704 0.296
#> GSM425847 1 0.8909 0.3821 0.692 0.308
#> GSM425886 2 0.7674 0.5858 0.224 0.776
#> GSM425887 2 0.9775 0.4979 0.412 0.588
#> GSM425888 1 0.9686 0.2011 0.604 0.396
#> GSM425889 1 0.1414 0.7963 0.980 0.020
#> GSM425890 1 0.4815 0.7588 0.896 0.104
#> GSM425891 2 0.9000 0.6460 0.316 0.684
#> GSM425892 2 0.9087 0.6399 0.324 0.676
#> GSM425853 1 0.2778 0.7792 0.952 0.048
#> GSM425854 2 0.9087 0.6399 0.324 0.676
#> GSM425855 1 0.0376 0.7961 0.996 0.004
#> GSM425856 1 0.5408 0.7103 0.876 0.124
#> GSM425857 2 0.9393 0.2965 0.356 0.644
#> GSM425858 2 0.9460 0.5793 0.364 0.636
#> GSM425859 2 0.9044 0.6438 0.320 0.680
#> GSM425860 2 0.9850 0.5395 0.428 0.572
#> GSM425861 1 0.8661 0.5017 0.712 0.288
#> GSM425862 1 0.2948 0.7881 0.948 0.052
#> GSM425837 1 0.2778 0.7792 0.952 0.048
#> GSM425838 1 0.4939 0.7558 0.892 0.108
#> GSM425839 2 0.9044 0.6438 0.320 0.680
#> GSM425840 1 0.1633 0.7907 0.976 0.024
#> GSM425841 1 0.4939 0.7558 0.892 0.108
#> GSM425842 1 0.2778 0.7911 0.952 0.048
#> GSM425917 2 0.9922 0.4858 0.448 0.552
#> GSM425922 1 0.4939 0.7558 0.892 0.108
#> GSM425919 1 0.2043 0.7873 0.968 0.032
#> GSM425920 1 0.2043 0.7873 0.968 0.032
#> GSM425923 1 0.0938 0.7943 0.988 0.012
#> GSM425916 1 0.2043 0.7873 0.968 0.032
#> GSM425918 1 0.1184 0.7932 0.984 0.016
#> GSM425921 1 0.4939 0.7558 0.892 0.108
#> GSM425925 1 0.4690 0.7600 0.900 0.100
#> GSM425926 1 0.4815 0.7572 0.896 0.104
#> GSM425927 1 0.2043 0.7903 0.968 0.032
#> GSM425924 1 0.9044 0.3726 0.680 0.320
#> GSM425928 2 0.8081 0.5763 0.248 0.752
#> GSM425929 2 0.7883 0.5861 0.236 0.764
#> GSM425930 2 0.7815 0.5885 0.232 0.768
#> GSM425931 2 0.8081 0.5763 0.248 0.752
#> GSM425932 2 0.7745 0.5905 0.228 0.772
#> GSM425933 2 0.7883 0.5861 0.236 0.764
#> GSM425934 2 0.6973 0.6032 0.188 0.812
#> GSM425935 2 0.7745 0.5905 0.228 0.772
#> GSM425936 2 0.7815 0.5885 0.232 0.768
#> GSM425937 2 0.8081 0.5763 0.248 0.752
#> GSM425938 2 0.8016 0.5744 0.244 0.756
#> GSM425939 2 0.8081 0.5763 0.248 0.752
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.0592 0.88451 0.012 0.988 0.000
#> GSM425908 2 0.1289 0.89167 0.032 0.968 0.000
#> GSM425909 3 0.8307 0.56671 0.192 0.176 0.632
#> GSM425910 1 0.7424 0.28874 0.572 0.388 0.040
#> GSM425911 2 0.0237 0.87923 0.004 0.996 0.000
#> GSM425912 2 0.5119 0.75806 0.160 0.812 0.028
#> GSM425913 2 0.0592 0.88451 0.012 0.988 0.000
#> GSM425914 2 0.4172 0.80387 0.104 0.868 0.028
#> GSM425915 3 0.6025 0.62348 0.028 0.232 0.740
#> GSM425874 1 0.5111 0.75551 0.808 0.168 0.024
#> GSM425875 1 0.6016 0.57231 0.724 0.020 0.256
#> GSM425876 1 0.7065 0.46855 0.644 0.316 0.040
#> GSM425877 1 0.1267 0.83328 0.972 0.024 0.004
#> GSM425878 1 0.2810 0.83192 0.928 0.036 0.036
#> GSM425879 2 0.0424 0.88243 0.008 0.992 0.000
#> GSM425880 3 0.7049 0.11867 0.452 0.020 0.528
#> GSM425881 2 0.5402 0.75941 0.180 0.792 0.028
#> GSM425882 2 0.1411 0.89054 0.036 0.964 0.000
#> GSM425883 1 0.1399 0.83470 0.968 0.028 0.004
#> GSM425884 1 0.2187 0.82962 0.948 0.024 0.028
#> GSM425885 1 0.7001 0.43904 0.588 0.388 0.024
#> GSM425848 1 0.4045 0.80136 0.872 0.104 0.024
#> GSM425849 1 0.3148 0.83259 0.916 0.048 0.036
#> GSM425850 1 0.2926 0.82656 0.924 0.036 0.040
#> GSM425851 1 0.1620 0.83315 0.964 0.024 0.012
#> GSM425852 3 0.6825 -0.00836 0.492 0.012 0.496
#> GSM425893 2 0.1182 0.85457 0.012 0.976 0.012
#> GSM425894 2 0.1289 0.89167 0.032 0.968 0.000
#> GSM425895 2 0.1289 0.89167 0.032 0.968 0.000
#> GSM425896 2 0.0000 0.87548 0.000 1.000 0.000
#> GSM425897 2 0.0424 0.88243 0.008 0.992 0.000
#> GSM425898 2 0.1289 0.89167 0.032 0.968 0.000
#> GSM425899 1 0.7377 0.26695 0.516 0.452 0.032
#> GSM425900 2 0.2096 0.88370 0.052 0.944 0.004
#> GSM425901 3 0.8309 0.56762 0.188 0.180 0.632
#> GSM425902 1 0.5111 0.75551 0.808 0.168 0.024
#> GSM425903 3 0.7603 0.55031 0.096 0.236 0.668
#> GSM425904 3 0.7049 0.11867 0.452 0.020 0.528
#> GSM425905 2 0.0592 0.88451 0.012 0.988 0.000
#> GSM425906 2 0.1525 0.88178 0.032 0.964 0.004
#> GSM425863 1 0.2152 0.83626 0.948 0.036 0.016
#> GSM425864 2 0.0424 0.88243 0.008 0.992 0.000
#> GSM425865 2 0.1289 0.89167 0.032 0.968 0.000
#> GSM425866 1 0.6416 0.48646 0.676 0.020 0.304
#> GSM425867 3 0.2806 0.69309 0.040 0.032 0.928
#> GSM425868 2 0.2866 0.85700 0.076 0.916 0.008
#> GSM425869 2 0.1525 0.89009 0.032 0.964 0.004
#> GSM425870 2 0.7223 -0.06477 0.028 0.548 0.424
#> GSM425871 1 0.1832 0.83564 0.956 0.036 0.008
#> GSM425872 2 0.1289 0.89167 0.032 0.968 0.000
#> GSM425873 1 0.6482 0.60409 0.716 0.244 0.040
#> GSM425843 1 0.2313 0.82884 0.944 0.024 0.032
#> GSM425844 1 0.1585 0.83424 0.964 0.028 0.008
#> GSM425845 1 0.9767 -0.08545 0.404 0.232 0.364
#> GSM425846 2 0.4742 0.80190 0.104 0.848 0.048
#> GSM425847 2 0.6897 0.60631 0.292 0.668 0.040
#> GSM425886 3 0.7112 0.53560 0.044 0.308 0.648
#> GSM425887 2 0.5060 0.78316 0.156 0.816 0.028
#> GSM425888 2 0.5826 0.73002 0.204 0.764 0.032
#> GSM425889 1 0.2434 0.83110 0.940 0.036 0.024
#> GSM425890 1 0.4551 0.77773 0.840 0.140 0.020
#> GSM425891 2 0.0592 0.88451 0.012 0.988 0.000
#> GSM425892 2 0.1289 0.89167 0.032 0.968 0.000
#> GSM425853 1 0.2383 0.82515 0.940 0.016 0.044
#> GSM425854 2 0.1289 0.89167 0.032 0.968 0.000
#> GSM425855 1 0.1525 0.83601 0.964 0.032 0.004
#> GSM425856 1 0.6294 0.51732 0.692 0.020 0.288
#> GSM425857 3 0.9517 0.30512 0.312 0.212 0.476
#> GSM425858 2 0.3310 0.86340 0.064 0.908 0.028
#> GSM425859 2 0.1289 0.89167 0.032 0.968 0.000
#> GSM425860 2 0.8934 0.37797 0.236 0.568 0.196
#> GSM425861 2 0.6744 0.58758 0.300 0.668 0.032
#> GSM425862 1 0.2550 0.83050 0.936 0.040 0.024
#> GSM425837 1 0.2297 0.82828 0.944 0.020 0.036
#> GSM425838 1 0.5111 0.75551 0.808 0.168 0.024
#> GSM425839 2 0.1289 0.89167 0.032 0.968 0.000
#> GSM425840 1 0.2187 0.83269 0.948 0.028 0.024
#> GSM425841 1 0.5111 0.75551 0.808 0.168 0.024
#> GSM425842 1 0.2681 0.82590 0.932 0.028 0.040
#> GSM425917 3 0.8984 0.21780 0.436 0.128 0.436
#> GSM425922 1 0.4679 0.77393 0.832 0.148 0.020
#> GSM425919 1 0.2313 0.82923 0.944 0.024 0.032
#> GSM425920 1 0.1453 0.83274 0.968 0.024 0.008
#> GSM425923 1 0.1585 0.83419 0.964 0.028 0.008
#> GSM425916 1 0.1453 0.83327 0.968 0.024 0.008
#> GSM425918 1 0.1399 0.83441 0.968 0.028 0.004
#> GSM425921 1 0.4811 0.77243 0.828 0.148 0.024
#> GSM425925 1 0.2492 0.83086 0.936 0.048 0.016
#> GSM425926 1 0.4811 0.77243 0.828 0.148 0.024
#> GSM425927 1 0.2550 0.82685 0.936 0.024 0.040
#> GSM425924 1 0.8501 -0.14537 0.488 0.092 0.420
#> GSM425928 3 0.5526 0.74877 0.036 0.172 0.792
#> GSM425929 3 0.5526 0.74877 0.036 0.172 0.792
#> GSM425930 3 0.5526 0.74877 0.036 0.172 0.792
#> GSM425931 3 0.5526 0.74877 0.036 0.172 0.792
#> GSM425932 3 0.5526 0.74877 0.036 0.172 0.792
#> GSM425933 3 0.5526 0.74877 0.036 0.172 0.792
#> GSM425934 3 0.5402 0.74067 0.028 0.180 0.792
#> GSM425935 3 0.5526 0.74877 0.036 0.172 0.792
#> GSM425936 3 0.5526 0.74877 0.036 0.172 0.792
#> GSM425937 3 0.5526 0.74877 0.036 0.172 0.792
#> GSM425938 3 0.5413 0.74749 0.036 0.164 0.800
#> GSM425939 3 0.5526 0.74877 0.036 0.172 0.792
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.0895 0.8800 0.020 0.976 0.000 0.004
#> GSM425908 2 0.0895 0.8800 0.020 0.976 0.000 0.004
#> GSM425909 1 0.6587 0.8005 0.688 0.076 0.188 0.048
#> GSM425910 4 0.8865 0.0994 0.328 0.292 0.044 0.336
#> GSM425911 2 0.2401 0.8700 0.092 0.904 0.000 0.004
#> GSM425912 2 0.6077 0.7390 0.200 0.708 0.028 0.064
#> GSM425913 2 0.1661 0.8773 0.052 0.944 0.000 0.004
#> GSM425914 2 0.5277 0.7775 0.196 0.748 0.016 0.040
#> GSM425915 1 0.5696 0.7223 0.680 0.052 0.264 0.004
#> GSM425874 4 0.4837 0.7125 0.076 0.120 0.008 0.796
#> GSM425875 1 0.4399 0.7534 0.768 0.000 0.020 0.212
#> GSM425876 4 0.8766 0.2607 0.320 0.248 0.044 0.388
#> GSM425877 4 0.1452 0.7929 0.036 0.000 0.008 0.956
#> GSM425878 4 0.4559 0.7447 0.164 0.004 0.040 0.792
#> GSM425879 2 0.0921 0.8818 0.028 0.972 0.000 0.000
#> GSM425880 1 0.5174 0.8307 0.760 0.000 0.124 0.116
#> GSM425881 2 0.5708 0.7662 0.168 0.744 0.032 0.056
#> GSM425882 2 0.2474 0.8784 0.056 0.920 0.016 0.008
#> GSM425883 4 0.1545 0.7958 0.040 0.000 0.008 0.952
#> GSM425884 4 0.5057 0.7208 0.204 0.004 0.044 0.748
#> GSM425885 4 0.6290 0.5290 0.076 0.272 0.008 0.644
#> GSM425848 4 0.4261 0.7442 0.100 0.060 0.008 0.832
#> GSM425849 4 0.3749 0.7747 0.128 0.000 0.032 0.840
#> GSM425850 4 0.5649 0.6642 0.280 0.004 0.044 0.672
#> GSM425851 4 0.2813 0.7848 0.080 0.000 0.024 0.896
#> GSM425852 1 0.5226 0.8302 0.756 0.000 0.128 0.116
#> GSM425893 2 0.2520 0.8697 0.088 0.904 0.004 0.004
#> GSM425894 2 0.0376 0.8806 0.004 0.992 0.000 0.004
#> GSM425895 2 0.0188 0.8807 0.000 0.996 0.000 0.004
#> GSM425896 2 0.0895 0.8800 0.020 0.976 0.000 0.004
#> GSM425897 2 0.0895 0.8816 0.020 0.976 0.000 0.004
#> GSM425898 2 0.0376 0.8806 0.004 0.992 0.000 0.004
#> GSM425899 2 0.6666 0.2829 0.052 0.584 0.024 0.340
#> GSM425900 2 0.2197 0.8700 0.080 0.916 0.000 0.004
#> GSM425901 1 0.6587 0.8005 0.688 0.076 0.188 0.048
#> GSM425902 4 0.4837 0.7125 0.076 0.120 0.008 0.796
#> GSM425903 1 0.4728 0.7916 0.776 0.020 0.188 0.016
#> GSM425904 1 0.5174 0.8307 0.760 0.000 0.124 0.116
#> GSM425905 2 0.0779 0.8807 0.016 0.980 0.000 0.004
#> GSM425906 2 0.2401 0.8656 0.092 0.904 0.000 0.004
#> GSM425863 4 0.2563 0.7888 0.072 0.000 0.020 0.908
#> GSM425864 2 0.1109 0.8820 0.028 0.968 0.000 0.004
#> GSM425865 2 0.0895 0.8816 0.020 0.976 0.000 0.004
#> GSM425866 1 0.4756 0.7906 0.772 0.000 0.052 0.176
#> GSM425867 1 0.4877 0.6809 0.664 0.000 0.328 0.008
#> GSM425868 2 0.1878 0.8605 0.008 0.944 0.008 0.040
#> GSM425869 2 0.1271 0.8727 0.012 0.968 0.008 0.012
#> GSM425870 2 0.6451 0.6390 0.136 0.656 0.204 0.004
#> GSM425871 4 0.3215 0.7831 0.092 0.000 0.032 0.876
#> GSM425872 2 0.0657 0.8822 0.012 0.984 0.000 0.004
#> GSM425873 4 0.8457 0.3663 0.320 0.184 0.044 0.452
#> GSM425843 4 0.4380 0.7455 0.164 0.004 0.032 0.800
#> GSM425844 4 0.2943 0.7842 0.076 0.000 0.032 0.892
#> GSM425845 1 0.3546 0.7495 0.876 0.012 0.052 0.060
#> GSM425846 2 0.2262 0.8668 0.012 0.932 0.040 0.016
#> GSM425847 2 0.7939 0.5260 0.268 0.544 0.044 0.144
#> GSM425886 1 0.6232 0.7705 0.688 0.088 0.208 0.016
#> GSM425887 2 0.5161 0.7959 0.156 0.776 0.028 0.040
#> GSM425888 2 0.5947 0.7533 0.164 0.732 0.032 0.072
#> GSM425889 4 0.2412 0.7732 0.084 0.000 0.008 0.908
#> GSM425890 4 0.3974 0.7512 0.060 0.068 0.016 0.856
#> GSM425891 2 0.1824 0.8759 0.060 0.936 0.000 0.004
#> GSM425892 2 0.0779 0.8801 0.016 0.980 0.000 0.004
#> GSM425853 4 0.4800 0.7258 0.196 0.000 0.044 0.760
#> GSM425854 2 0.0564 0.8813 0.004 0.988 0.004 0.004
#> GSM425855 4 0.1576 0.7969 0.048 0.000 0.004 0.948
#> GSM425856 1 0.4679 0.7838 0.772 0.000 0.044 0.184
#> GSM425857 1 0.6702 0.7770 0.704 0.092 0.120 0.084
#> GSM425858 2 0.3446 0.8529 0.092 0.872 0.028 0.008
#> GSM425859 2 0.0188 0.8807 0.000 0.996 0.000 0.004
#> GSM425860 2 0.7950 0.4797 0.304 0.520 0.040 0.136
#> GSM425861 2 0.6695 0.6937 0.200 0.672 0.036 0.092
#> GSM425862 4 0.2412 0.7732 0.084 0.000 0.008 0.908
#> GSM425837 4 0.3853 0.7494 0.160 0.000 0.020 0.820
#> GSM425838 4 0.4837 0.7125 0.076 0.120 0.008 0.796
#> GSM425839 2 0.0188 0.8807 0.000 0.996 0.000 0.004
#> GSM425840 4 0.3266 0.7797 0.108 0.000 0.024 0.868
#> GSM425841 4 0.4837 0.7125 0.076 0.120 0.008 0.796
#> GSM425842 4 0.5722 0.6516 0.292 0.004 0.044 0.660
#> GSM425917 3 0.7296 0.2220 0.060 0.040 0.496 0.404
#> GSM425922 4 0.3974 0.7512 0.060 0.068 0.016 0.856
#> GSM425919 4 0.4689 0.7488 0.168 0.004 0.044 0.784
#> GSM425920 4 0.3215 0.7802 0.092 0.000 0.032 0.876
#> GSM425923 4 0.0927 0.7900 0.016 0.000 0.008 0.976
#> GSM425916 4 0.2376 0.7885 0.068 0.000 0.016 0.916
#> GSM425918 4 0.1284 0.7921 0.024 0.000 0.012 0.964
#> GSM425921 4 0.4265 0.7423 0.076 0.068 0.016 0.840
#> GSM425925 4 0.2384 0.7763 0.072 0.004 0.008 0.916
#> GSM425926 4 0.4019 0.7428 0.076 0.068 0.008 0.848
#> GSM425927 4 0.5366 0.6990 0.240 0.004 0.044 0.712
#> GSM425924 3 0.7136 0.0477 0.068 0.024 0.456 0.452
#> GSM425928 3 0.1637 0.8868 0.000 0.060 0.940 0.000
#> GSM425929 3 0.1637 0.8868 0.000 0.060 0.940 0.000
#> GSM425930 3 0.1637 0.8868 0.000 0.060 0.940 0.000
#> GSM425931 3 0.1637 0.8868 0.000 0.060 0.940 0.000
#> GSM425932 3 0.1637 0.8868 0.000 0.060 0.940 0.000
#> GSM425933 3 0.1637 0.8868 0.000 0.060 0.940 0.000
#> GSM425934 3 0.1637 0.8868 0.000 0.060 0.940 0.000
#> GSM425935 3 0.1637 0.8868 0.000 0.060 0.940 0.000
#> GSM425936 3 0.1637 0.8868 0.000 0.060 0.940 0.000
#> GSM425937 3 0.1637 0.8868 0.000 0.060 0.940 0.000
#> GSM425938 3 0.1743 0.8806 0.004 0.056 0.940 0.000
#> GSM425939 3 0.1637 0.8868 0.000 0.060 0.940 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM425907 2 0.2103 0.8545 0.056 0.920 0.004 0.000 0.020
#> GSM425908 2 0.1934 0.8558 0.052 0.928 0.004 0.000 0.016
#> GSM425909 5 0.2824 0.9230 0.000 0.028 0.068 0.016 0.888
#> GSM425910 1 0.1300 0.5864 0.956 0.016 0.000 0.000 0.028
#> GSM425911 2 0.3706 0.7918 0.184 0.792 0.004 0.000 0.020
#> GSM425912 1 0.5047 -0.3747 0.504 0.468 0.004 0.000 0.024
#> GSM425913 2 0.2110 0.8487 0.072 0.912 0.000 0.000 0.016
#> GSM425914 2 0.5103 0.4554 0.444 0.524 0.004 0.000 0.028
#> GSM425915 5 0.3222 0.9012 0.028 0.020 0.088 0.000 0.864
#> GSM425874 4 0.2875 0.7133 0.008 0.052 0.000 0.884 0.056
#> GSM425875 5 0.2464 0.9124 0.032 0.000 0.012 0.048 0.908
#> GSM425876 1 0.1393 0.5903 0.956 0.012 0.000 0.008 0.024
#> GSM425877 4 0.4238 0.6200 0.164 0.000 0.000 0.768 0.068
#> GSM425878 1 0.5126 0.3718 0.636 0.000 0.000 0.300 0.064
#> GSM425879 2 0.1901 0.8559 0.056 0.928 0.004 0.000 0.012
#> GSM425880 5 0.2483 0.9294 0.028 0.000 0.048 0.016 0.908
#> GSM425881 2 0.4897 0.3806 0.460 0.516 0.000 0.000 0.024
#> GSM425882 2 0.1901 0.8592 0.056 0.928 0.004 0.000 0.012
#> GSM425883 4 0.2966 0.6807 0.136 0.000 0.000 0.848 0.016
#> GSM425884 1 0.4777 0.4455 0.680 0.000 0.000 0.268 0.052
#> GSM425885 4 0.3829 0.5710 0.000 0.196 0.000 0.776 0.028
#> GSM425848 4 0.3175 0.7174 0.020 0.044 0.000 0.872 0.064
#> GSM425849 4 0.4114 0.6230 0.164 0.000 0.000 0.776 0.060
#> GSM425850 1 0.2293 0.5802 0.900 0.000 0.000 0.084 0.016
#> GSM425851 4 0.5452 0.0187 0.448 0.000 0.000 0.492 0.060
#> GSM425852 5 0.2625 0.9271 0.040 0.000 0.048 0.012 0.900
#> GSM425893 2 0.3381 0.8115 0.160 0.820 0.004 0.000 0.016
#> GSM425894 2 0.0451 0.8555 0.004 0.988 0.000 0.000 0.008
#> GSM425895 2 0.0324 0.8562 0.004 0.992 0.000 0.000 0.004
#> GSM425896 2 0.2103 0.8545 0.056 0.920 0.004 0.000 0.020
#> GSM425897 2 0.2005 0.8554 0.056 0.924 0.004 0.000 0.016
#> GSM425898 2 0.0324 0.8562 0.004 0.992 0.000 0.000 0.004
#> GSM425899 2 0.6894 0.2778 0.116 0.548 0.000 0.272 0.064
#> GSM425900 2 0.2966 0.8009 0.136 0.848 0.000 0.000 0.016
#> GSM425901 5 0.2824 0.9230 0.000 0.028 0.068 0.016 0.888
#> GSM425902 4 0.2945 0.7110 0.008 0.056 0.000 0.880 0.056
#> GSM425903 5 0.3151 0.9011 0.068 0.004 0.064 0.000 0.864
#> GSM425904 5 0.2483 0.9294 0.028 0.000 0.048 0.016 0.908
#> GSM425905 2 0.1569 0.8591 0.044 0.944 0.004 0.000 0.008
#> GSM425906 2 0.3381 0.7846 0.176 0.808 0.000 0.000 0.016
#> GSM425863 4 0.4289 0.6306 0.176 0.000 0.000 0.760 0.064
#> GSM425864 2 0.2005 0.8554 0.056 0.924 0.004 0.000 0.016
#> GSM425865 2 0.1901 0.8559 0.056 0.928 0.004 0.000 0.012
#> GSM425866 5 0.2499 0.9165 0.036 0.000 0.016 0.040 0.908
#> GSM425867 5 0.3039 0.8723 0.012 0.000 0.152 0.000 0.836
#> GSM425868 2 0.0968 0.8523 0.004 0.972 0.000 0.012 0.012
#> GSM425869 2 0.0566 0.8542 0.000 0.984 0.000 0.004 0.012
#> GSM425870 2 0.6211 0.5098 0.364 0.532 0.076 0.000 0.028
#> GSM425871 1 0.4966 0.1910 0.564 0.000 0.000 0.404 0.032
#> GSM425872 2 0.0807 0.8556 0.012 0.976 0.000 0.000 0.012
#> GSM425873 1 0.1612 0.5918 0.948 0.012 0.000 0.016 0.024
#> GSM425843 1 0.5429 0.2441 0.564 0.000 0.000 0.368 0.068
#> GSM425844 4 0.5161 0.0513 0.444 0.000 0.000 0.516 0.040
#> GSM425845 5 0.2777 0.8729 0.120 0.000 0.016 0.000 0.864
#> GSM425846 2 0.1386 0.8516 0.032 0.952 0.000 0.000 0.016
#> GSM425847 1 0.3193 0.5387 0.840 0.132 0.000 0.000 0.028
#> GSM425886 5 0.2775 0.9165 0.000 0.036 0.068 0.008 0.888
#> GSM425887 2 0.4768 0.5224 0.384 0.592 0.000 0.000 0.024
#> GSM425888 2 0.4752 0.4197 0.412 0.568 0.000 0.000 0.020
#> GSM425889 4 0.2605 0.7211 0.044 0.004 0.000 0.896 0.056
#> GSM425890 4 0.1117 0.7090 0.016 0.000 0.000 0.964 0.020
#> GSM425891 2 0.2233 0.8481 0.080 0.904 0.000 0.000 0.016
#> GSM425892 2 0.1630 0.8586 0.036 0.944 0.004 0.000 0.016
#> GSM425853 1 0.5240 0.4116 0.656 0.000 0.000 0.252 0.092
#> GSM425854 2 0.0451 0.8560 0.004 0.988 0.000 0.000 0.008
#> GSM425855 4 0.4525 0.6050 0.220 0.000 0.000 0.724 0.056
#> GSM425856 5 0.2499 0.9165 0.036 0.000 0.016 0.040 0.908
#> GSM425857 5 0.3092 0.9182 0.000 0.036 0.048 0.036 0.880
#> GSM425858 2 0.3011 0.7979 0.140 0.844 0.000 0.000 0.016
#> GSM425859 2 0.0451 0.8555 0.004 0.988 0.000 0.000 0.008
#> GSM425860 1 0.3400 0.5226 0.828 0.136 0.000 0.000 0.036
#> GSM425861 1 0.4907 -0.2942 0.492 0.484 0.000 0.000 0.024
#> GSM425862 4 0.2536 0.7208 0.044 0.004 0.000 0.900 0.052
#> GSM425837 1 0.5737 -0.0770 0.464 0.000 0.000 0.452 0.084
#> GSM425838 4 0.2838 0.7048 0.008 0.072 0.000 0.884 0.036
#> GSM425839 2 0.0324 0.8562 0.004 0.992 0.000 0.000 0.004
#> GSM425840 4 0.5587 0.1224 0.428 0.000 0.000 0.500 0.072
#> GSM425841 4 0.2875 0.7133 0.008 0.052 0.000 0.884 0.056
#> GSM425842 1 0.1893 0.5892 0.928 0.000 0.000 0.048 0.024
#> GSM425917 3 0.7710 -0.0791 0.236 0.000 0.388 0.316 0.060
#> GSM425922 4 0.1012 0.7099 0.012 0.000 0.000 0.968 0.020
#> GSM425919 1 0.5188 0.3493 0.612 0.000 0.000 0.328 0.060
#> GSM425920 1 0.5450 0.0553 0.496 0.000 0.000 0.444 0.060
#> GSM425923 4 0.3365 0.6479 0.120 0.000 0.000 0.836 0.044
#> GSM425916 4 0.5408 0.1230 0.408 0.000 0.000 0.532 0.060
#> GSM425918 4 0.4337 0.5429 0.204 0.000 0.000 0.744 0.052
#> GSM425921 4 0.0609 0.7191 0.000 0.000 0.000 0.980 0.020
#> GSM425925 4 0.2609 0.7192 0.052 0.004 0.000 0.896 0.048
#> GSM425926 4 0.1717 0.7249 0.008 0.004 0.000 0.936 0.052
#> GSM425927 1 0.4035 0.5346 0.784 0.000 0.000 0.156 0.060
#> GSM425924 4 0.7826 -0.0509 0.308 0.000 0.312 0.320 0.060
#> GSM425928 3 0.0162 0.9427 0.000 0.000 0.996 0.000 0.004
#> GSM425929 3 0.0162 0.9427 0.000 0.000 0.996 0.000 0.004
#> GSM425930 3 0.0162 0.9427 0.000 0.000 0.996 0.000 0.004
#> GSM425931 3 0.0162 0.9427 0.000 0.000 0.996 0.000 0.004
#> GSM425932 3 0.0162 0.9427 0.000 0.000 0.996 0.000 0.004
#> GSM425933 3 0.0162 0.9427 0.000 0.000 0.996 0.000 0.004
#> GSM425934 3 0.0162 0.9427 0.000 0.000 0.996 0.000 0.004
#> GSM425935 3 0.0000 0.9383 0.000 0.000 1.000 0.000 0.000
#> GSM425936 3 0.0162 0.9427 0.000 0.000 0.996 0.000 0.004
#> GSM425937 3 0.0162 0.9427 0.000 0.000 0.996 0.000 0.004
#> GSM425938 3 0.0162 0.9427 0.000 0.000 0.996 0.000 0.004
#> GSM425939 3 0.0162 0.9427 0.000 0.000 0.996 0.000 0.004
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 2 0.2900 0.7819 0.012 0.856 0.000 0.004 0.016 0.112
#> GSM425908 2 0.2900 0.7819 0.012 0.856 0.000 0.004 0.016 0.112
#> GSM425909 5 0.1121 0.9651 0.000 0.004 0.008 0.016 0.964 0.008
#> GSM425910 6 0.4072 0.3670 0.292 0.000 0.004 0.004 0.016 0.684
#> GSM425911 2 0.4473 0.5711 0.012 0.644 0.000 0.004 0.020 0.320
#> GSM425912 6 0.3215 0.5396 0.004 0.240 0.000 0.000 0.000 0.756
#> GSM425913 2 0.2902 0.6851 0.004 0.800 0.000 0.000 0.000 0.196
#> GSM425914 6 0.3509 0.5054 0.000 0.240 0.000 0.000 0.016 0.744
#> GSM425915 5 0.0909 0.9587 0.000 0.000 0.012 0.000 0.968 0.020
#> GSM425874 4 0.0603 0.8418 0.004 0.016 0.000 0.980 0.000 0.000
#> GSM425875 5 0.1857 0.9586 0.012 0.000 0.000 0.028 0.928 0.032
#> GSM425876 6 0.4144 0.3535 0.308 0.000 0.004 0.004 0.016 0.668
#> GSM425877 1 0.4189 0.2116 0.552 0.000 0.000 0.436 0.004 0.008
#> GSM425878 1 0.6564 0.3583 0.388 0.000 0.004 0.288 0.016 0.304
#> GSM425879 2 0.2945 0.7817 0.012 0.852 0.000 0.004 0.016 0.116
#> GSM425880 5 0.1950 0.9616 0.012 0.000 0.008 0.020 0.928 0.032
#> GSM425881 6 0.3756 0.4672 0.004 0.352 0.000 0.000 0.000 0.644
#> GSM425882 2 0.2989 0.7844 0.012 0.848 0.000 0.004 0.016 0.120
#> GSM425883 4 0.3934 0.5307 0.304 0.000 0.000 0.676 0.000 0.020
#> GSM425884 1 0.5723 0.4589 0.576 0.000 0.004 0.116 0.020 0.284
#> GSM425885 4 0.2531 0.7313 0.000 0.128 0.000 0.860 0.008 0.004
#> GSM425848 4 0.1655 0.8387 0.052 0.008 0.000 0.932 0.000 0.008
#> GSM425849 4 0.2803 0.7757 0.084 0.000 0.000 0.864 0.004 0.048
#> GSM425850 6 0.4585 0.2400 0.352 0.000 0.004 0.020 0.012 0.612
#> GSM425851 1 0.2030 0.6319 0.908 0.000 0.000 0.064 0.000 0.028
#> GSM425852 5 0.0984 0.9642 0.012 0.000 0.008 0.012 0.968 0.000
#> GSM425893 2 0.4432 0.6478 0.012 0.688 0.000 0.004 0.032 0.264
#> GSM425894 2 0.0935 0.7852 0.004 0.964 0.000 0.000 0.000 0.032
#> GSM425895 2 0.0790 0.7862 0.000 0.968 0.000 0.000 0.000 0.032
#> GSM425896 2 0.3202 0.7709 0.012 0.832 0.000 0.004 0.020 0.132
#> GSM425897 2 0.3032 0.7780 0.012 0.844 0.000 0.004 0.016 0.124
#> GSM425898 2 0.0935 0.7852 0.004 0.964 0.000 0.000 0.000 0.032
#> GSM425899 2 0.6373 0.0776 0.080 0.456 0.000 0.376 0.000 0.088
#> GSM425900 2 0.3584 0.4977 0.004 0.688 0.000 0.000 0.000 0.308
#> GSM425901 5 0.1121 0.9651 0.000 0.004 0.008 0.016 0.964 0.008
#> GSM425902 4 0.1053 0.8435 0.012 0.020 0.000 0.964 0.000 0.004
#> GSM425903 5 0.0891 0.9582 0.000 0.000 0.008 0.000 0.968 0.024
#> GSM425904 5 0.1950 0.9616 0.012 0.000 0.008 0.020 0.928 0.032
#> GSM425905 2 0.2619 0.7889 0.012 0.876 0.000 0.004 0.012 0.096
#> GSM425906 2 0.3830 0.3543 0.004 0.620 0.000 0.000 0.000 0.376
#> GSM425863 4 0.3039 0.7644 0.088 0.000 0.000 0.848 0.004 0.060
#> GSM425864 2 0.2945 0.7817 0.012 0.852 0.000 0.004 0.016 0.116
#> GSM425865 2 0.2945 0.7822 0.012 0.852 0.000 0.004 0.016 0.116
#> GSM425866 5 0.1857 0.9586 0.012 0.000 0.000 0.028 0.928 0.032
#> GSM425867 5 0.0935 0.9565 0.000 0.000 0.032 0.000 0.964 0.004
#> GSM425868 2 0.0912 0.7931 0.004 0.972 0.000 0.008 0.004 0.012
#> GSM425869 2 0.0653 0.7898 0.004 0.980 0.000 0.012 0.000 0.004
#> GSM425870 6 0.4736 0.4189 0.012 0.252 0.020 0.000 0.032 0.684
#> GSM425871 1 0.4747 0.5318 0.668 0.000 0.004 0.072 0.004 0.252
#> GSM425872 2 0.2402 0.7207 0.004 0.856 0.000 0.000 0.000 0.140
#> GSM425873 6 0.4267 0.3453 0.312 0.000 0.004 0.008 0.016 0.660
#> GSM425843 1 0.5907 0.5281 0.548 0.000 0.000 0.236 0.016 0.200
#> GSM425844 1 0.4016 0.6195 0.768 0.000 0.004 0.108 0.000 0.120
#> GSM425845 5 0.1686 0.9496 0.012 0.000 0.000 0.000 0.924 0.064
#> GSM425846 2 0.2738 0.6916 0.004 0.820 0.000 0.000 0.000 0.176
#> GSM425847 6 0.3678 0.5730 0.128 0.084 0.000 0.000 0.000 0.788
#> GSM425886 5 0.1235 0.9583 0.000 0.008 0.008 0.008 0.960 0.016
#> GSM425887 6 0.3737 0.3963 0.000 0.392 0.000 0.000 0.000 0.608
#> GSM425888 6 0.4010 0.3730 0.008 0.408 0.000 0.000 0.000 0.584
#> GSM425889 4 0.1340 0.8391 0.040 0.000 0.000 0.948 0.004 0.008
#> GSM425890 4 0.3221 0.6001 0.264 0.000 0.000 0.736 0.000 0.000
#> GSM425891 2 0.3052 0.6646 0.004 0.780 0.000 0.000 0.000 0.216
#> GSM425892 2 0.2610 0.7888 0.012 0.880 0.000 0.004 0.016 0.088
#> GSM425853 1 0.6364 0.4008 0.512 0.000 0.004 0.104 0.064 0.316
#> GSM425854 2 0.0865 0.7868 0.000 0.964 0.000 0.000 0.000 0.036
#> GSM425855 4 0.4042 0.3393 0.316 0.000 0.000 0.664 0.004 0.016
#> GSM425856 5 0.1857 0.9586 0.012 0.000 0.000 0.028 0.928 0.032
#> GSM425857 5 0.1235 0.9638 0.000 0.008 0.008 0.016 0.960 0.008
#> GSM425858 2 0.3684 0.4485 0.004 0.664 0.000 0.000 0.000 0.332
#> GSM425859 2 0.0146 0.7906 0.000 0.996 0.000 0.000 0.000 0.004
#> GSM425860 6 0.3414 0.5726 0.092 0.068 0.000 0.000 0.012 0.828
#> GSM425861 6 0.3778 0.5549 0.016 0.288 0.000 0.000 0.000 0.696
#> GSM425862 4 0.1410 0.8377 0.044 0.000 0.000 0.944 0.004 0.008
#> GSM425837 1 0.5828 0.4673 0.524 0.000 0.000 0.308 0.012 0.156
#> GSM425838 4 0.1616 0.8372 0.020 0.028 0.000 0.940 0.000 0.012
#> GSM425839 2 0.0935 0.7852 0.004 0.964 0.000 0.000 0.000 0.032
#> GSM425840 1 0.5600 0.2877 0.464 0.000 0.000 0.424 0.012 0.100
#> GSM425841 4 0.0603 0.8418 0.004 0.016 0.000 0.980 0.000 0.000
#> GSM425842 6 0.4453 0.2985 0.336 0.000 0.004 0.012 0.016 0.632
#> GSM425917 1 0.4976 0.4475 0.656 0.000 0.252 0.072 0.000 0.020
#> GSM425922 4 0.3101 0.6257 0.244 0.000 0.000 0.756 0.000 0.000
#> GSM425919 1 0.1865 0.6248 0.920 0.000 0.000 0.040 0.000 0.040
#> GSM425920 1 0.1984 0.6299 0.912 0.000 0.000 0.056 0.000 0.032
#> GSM425923 1 0.3944 0.1489 0.568 0.000 0.000 0.428 0.000 0.004
#> GSM425916 1 0.2831 0.6233 0.840 0.000 0.000 0.136 0.000 0.024
#> GSM425918 1 0.3578 0.3831 0.660 0.000 0.000 0.340 0.000 0.000
#> GSM425921 4 0.1327 0.8180 0.064 0.000 0.000 0.936 0.000 0.000
#> GSM425925 4 0.0922 0.8425 0.024 0.000 0.000 0.968 0.004 0.004
#> GSM425926 4 0.0260 0.8428 0.008 0.000 0.000 0.992 0.000 0.000
#> GSM425927 1 0.4303 0.3425 0.640 0.000 0.000 0.012 0.016 0.332
#> GSM425924 1 0.4810 0.5166 0.696 0.000 0.204 0.076 0.000 0.024
#> GSM425928 3 0.0436 0.9946 0.004 0.000 0.988 0.000 0.004 0.004
#> GSM425929 3 0.0146 0.9982 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM425930 3 0.0146 0.9982 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM425931 3 0.0146 0.9982 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM425932 3 0.0146 0.9982 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM425933 3 0.0146 0.9982 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM425934 3 0.0146 0.9982 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM425935 3 0.0436 0.9946 0.004 0.000 0.988 0.000 0.004 0.004
#> GSM425936 3 0.0146 0.9982 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM425937 3 0.0146 0.9982 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM425938 3 0.0436 0.9946 0.004 0.000 0.988 0.000 0.004 0.004
#> GSM425939 3 0.0146 0.9982 0.000 0.000 0.996 0.000 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 disease.state(p) tissue(p) other(p) k
#> CV:kmeans 86 1.14e-03 1.73e-05 9.57e-07 2
#> CV:kmeans 89 1.32e-12 4.99e-14 2.60e-11 3
#> CV:kmeans 96 1.13e-20 2.74e-22 1.24e-15 4
#> CV:kmeans 83 4.03e-17 6.09e-18 1.73e-09 5
#> CV:kmeans 79 1.36e-15 2.24e-17 1.17e-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["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 103 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 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 0.624 0.831 0.914 0.5036 0.496 0.496
#> 3 3 0.793 0.846 0.925 0.3263 0.716 0.488
#> 4 4 0.612 0.681 0.790 0.1080 0.924 0.775
#> 5 5 0.645 0.607 0.781 0.0740 0.898 0.652
#> 6 6 0.668 0.521 0.705 0.0466 0.914 0.631
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
#> GSM425907 2 0.0938 0.8928 0.012 0.988
#> GSM425908 2 0.4939 0.8623 0.108 0.892
#> GSM425909 2 0.7950 0.6925 0.240 0.760
#> GSM425910 2 0.9954 0.0887 0.460 0.540
#> GSM425911 2 0.0672 0.8922 0.008 0.992
#> GSM425912 2 0.2236 0.8941 0.036 0.964
#> GSM425913 2 0.2603 0.8886 0.044 0.956
#> GSM425914 2 0.0672 0.8923 0.008 0.992
#> GSM425915 2 0.2236 0.8917 0.036 0.964
#> GSM425874 1 0.1184 0.9212 0.984 0.016
#> GSM425875 1 0.3274 0.8880 0.940 0.060
#> GSM425876 1 0.8909 0.5906 0.692 0.308
#> GSM425877 1 0.0672 0.9187 0.992 0.008
#> GSM425878 1 0.0938 0.9217 0.988 0.012
#> GSM425879 2 0.0672 0.8923 0.008 0.992
#> GSM425880 1 0.4939 0.8466 0.892 0.108
#> GSM425881 2 0.9944 0.2102 0.456 0.544
#> GSM425882 2 0.5737 0.8421 0.136 0.864
#> GSM425883 1 0.1414 0.9200 0.980 0.020
#> GSM425884 1 0.0938 0.9176 0.988 0.012
#> GSM425885 1 0.9170 0.4425 0.668 0.332
#> GSM425848 1 0.0938 0.9217 0.988 0.012
#> GSM425849 1 0.1414 0.9198 0.980 0.020
#> GSM425850 1 0.2423 0.9158 0.960 0.040
#> GSM425851 1 0.0938 0.9179 0.988 0.012
#> GSM425852 1 0.5946 0.8154 0.856 0.144
#> GSM425893 2 0.0376 0.8924 0.004 0.996
#> GSM425894 2 0.4431 0.8719 0.092 0.908
#> GSM425895 2 0.4690 0.8672 0.100 0.900
#> GSM425896 2 0.0672 0.8923 0.008 0.992
#> GSM425897 2 0.0938 0.8928 0.012 0.988
#> GSM425898 2 0.4562 0.8697 0.096 0.904
#> GSM425899 1 0.2603 0.9058 0.956 0.044
#> GSM425900 2 0.4022 0.8773 0.080 0.920
#> GSM425901 2 0.8386 0.6470 0.268 0.732
#> GSM425902 1 0.1184 0.9212 0.984 0.016
#> GSM425903 2 0.1633 0.8918 0.024 0.976
#> GSM425904 1 0.4939 0.8466 0.892 0.108
#> GSM425905 2 0.1414 0.8929 0.020 0.980
#> GSM425906 2 0.2603 0.8887 0.044 0.956
#> GSM425863 1 0.1184 0.9212 0.984 0.016
#> GSM425864 2 0.0672 0.8923 0.008 0.992
#> GSM425865 2 0.3879 0.8786 0.076 0.924
#> GSM425866 1 0.4298 0.8656 0.912 0.088
#> GSM425867 2 0.3114 0.8861 0.056 0.944
#> GSM425868 2 0.9909 0.2732 0.444 0.556
#> GSM425869 2 0.4690 0.8672 0.100 0.900
#> GSM425870 2 0.1184 0.8907 0.016 0.984
#> GSM425871 1 0.2236 0.9107 0.964 0.036
#> GSM425872 2 0.5408 0.8530 0.124 0.876
#> GSM425873 1 0.2603 0.9097 0.956 0.044
#> GSM425843 1 0.0672 0.9187 0.992 0.008
#> GSM425844 1 0.1184 0.9214 0.984 0.016
#> GSM425845 1 0.9954 0.2089 0.540 0.460
#> GSM425846 1 0.4298 0.8777 0.912 0.088
#> GSM425847 1 0.9000 0.5314 0.684 0.316
#> GSM425886 2 0.2423 0.8913 0.040 0.960
#> GSM425887 2 0.8713 0.6347 0.292 0.708
#> GSM425888 1 0.9522 0.3940 0.628 0.372
#> GSM425889 1 0.0938 0.9216 0.988 0.012
#> GSM425890 1 0.1184 0.9212 0.984 0.016
#> GSM425891 2 0.0938 0.8929 0.012 0.988
#> GSM425892 2 0.4431 0.8729 0.092 0.908
#> GSM425853 1 0.2423 0.9016 0.960 0.040
#> GSM425854 2 0.4939 0.8624 0.108 0.892
#> GSM425855 1 0.0672 0.9217 0.992 0.008
#> GSM425856 1 0.3431 0.8845 0.936 0.064
#> GSM425857 2 0.9815 0.2970 0.420 0.580
#> GSM425858 2 0.6712 0.8035 0.176 0.824
#> GSM425859 2 0.4690 0.8672 0.100 0.900
#> GSM425860 2 0.3274 0.8820 0.060 0.940
#> GSM425861 1 0.4690 0.8651 0.900 0.100
#> GSM425862 1 0.1184 0.9212 0.984 0.016
#> GSM425837 1 0.0376 0.9200 0.996 0.004
#> GSM425838 1 0.1184 0.9212 0.984 0.016
#> GSM425839 2 0.4690 0.8672 0.100 0.900
#> GSM425840 1 0.0938 0.9201 0.988 0.012
#> GSM425841 1 0.1184 0.9212 0.984 0.016
#> GSM425842 1 0.2043 0.9154 0.968 0.032
#> GSM425917 2 0.7815 0.7294 0.232 0.768
#> GSM425922 1 0.1184 0.9212 0.984 0.016
#> GSM425919 1 0.0938 0.9179 0.988 0.012
#> GSM425920 1 0.0672 0.9187 0.992 0.008
#> GSM425923 1 0.0376 0.9215 0.996 0.004
#> GSM425916 1 0.0672 0.9187 0.992 0.008
#> GSM425918 1 0.0000 0.9208 1.000 0.000
#> GSM425921 1 0.1184 0.9212 0.984 0.016
#> GSM425925 1 0.1184 0.9212 0.984 0.016
#> GSM425926 1 0.1184 0.9212 0.984 0.016
#> GSM425927 1 0.1184 0.9197 0.984 0.016
#> GSM425924 1 0.9881 0.2508 0.564 0.436
#> GSM425928 2 0.2603 0.8904 0.044 0.956
#> GSM425929 2 0.2603 0.8904 0.044 0.956
#> GSM425930 2 0.2423 0.8913 0.040 0.960
#> GSM425931 2 0.2603 0.8904 0.044 0.956
#> GSM425932 2 0.2236 0.8917 0.036 0.964
#> GSM425933 2 0.2603 0.8904 0.044 0.956
#> GSM425934 2 0.1843 0.8920 0.028 0.972
#> GSM425935 2 0.2043 0.8928 0.032 0.968
#> GSM425936 2 0.2236 0.8917 0.036 0.964
#> GSM425937 2 0.2603 0.8904 0.044 0.956
#> GSM425938 2 0.2603 0.8904 0.044 0.956
#> GSM425939 2 0.2603 0.8904 0.044 0.956
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.0424 0.9359 0.000 0.992 0.008
#> GSM425908 2 0.0237 0.9365 0.004 0.996 0.000
#> GSM425909 3 0.0424 0.9013 0.000 0.008 0.992
#> GSM425910 3 0.9901 0.0985 0.268 0.348 0.384
#> GSM425911 2 0.3340 0.8538 0.000 0.880 0.120
#> GSM425912 2 0.2945 0.8901 0.088 0.908 0.004
#> GSM425913 2 0.0237 0.9371 0.000 0.996 0.004
#> GSM425914 2 0.4423 0.8630 0.048 0.864 0.088
#> GSM425915 3 0.0000 0.9039 0.000 0.000 1.000
#> GSM425874 1 0.3038 0.8738 0.896 0.104 0.000
#> GSM425875 1 0.6267 0.0659 0.548 0.000 0.452
#> GSM425876 1 0.8472 0.2448 0.540 0.360 0.100
#> GSM425877 1 0.0237 0.9148 0.996 0.000 0.004
#> GSM425878 1 0.0000 0.9151 1.000 0.000 0.000
#> GSM425879 2 0.1643 0.9206 0.000 0.956 0.044
#> GSM425880 3 0.3116 0.8462 0.108 0.000 0.892
#> GSM425881 2 0.2590 0.9034 0.072 0.924 0.004
#> GSM425882 2 0.0237 0.9372 0.004 0.996 0.000
#> GSM425883 1 0.3933 0.8435 0.880 0.092 0.028
#> GSM425884 1 0.0000 0.9151 1.000 0.000 0.000
#> GSM425885 1 0.7021 0.2773 0.544 0.436 0.020
#> GSM425848 1 0.1989 0.9034 0.948 0.048 0.004
#> GSM425849 1 0.0424 0.9157 0.992 0.008 0.000
#> GSM425850 1 0.1529 0.9013 0.960 0.040 0.000
#> GSM425851 1 0.1529 0.9010 0.960 0.000 0.040
#> GSM425852 3 0.1860 0.8820 0.052 0.000 0.948
#> GSM425893 2 0.5431 0.6174 0.000 0.716 0.284
#> GSM425894 2 0.0424 0.9359 0.000 0.992 0.008
#> GSM425895 2 0.0000 0.9371 0.000 1.000 0.000
#> GSM425896 2 0.2066 0.9033 0.000 0.940 0.060
#> GSM425897 2 0.0892 0.9326 0.000 0.980 0.020
#> GSM425898 2 0.0000 0.9371 0.000 1.000 0.000
#> GSM425899 2 0.6225 0.1435 0.432 0.568 0.000
#> GSM425900 2 0.0829 0.9358 0.004 0.984 0.012
#> GSM425901 3 0.0424 0.9013 0.000 0.008 0.992
#> GSM425902 1 0.3412 0.8600 0.876 0.124 0.000
#> GSM425903 3 0.0237 0.9026 0.004 0.000 0.996
#> GSM425904 3 0.2796 0.8576 0.092 0.000 0.908
#> GSM425905 2 0.0000 0.9371 0.000 1.000 0.000
#> GSM425906 2 0.1482 0.9305 0.012 0.968 0.020
#> GSM425863 1 0.0000 0.9151 1.000 0.000 0.000
#> GSM425864 2 0.0424 0.9365 0.000 0.992 0.008
#> GSM425865 2 0.0000 0.9371 0.000 1.000 0.000
#> GSM425866 3 0.5956 0.5627 0.324 0.004 0.672
#> GSM425867 3 0.0000 0.9039 0.000 0.000 1.000
#> GSM425868 2 0.0892 0.9288 0.020 0.980 0.000
#> GSM425869 2 0.0000 0.9371 0.000 1.000 0.000
#> GSM425870 3 0.4555 0.7087 0.000 0.200 0.800
#> GSM425871 1 0.0000 0.9151 1.000 0.000 0.000
#> GSM425872 2 0.0237 0.9371 0.000 0.996 0.004
#> GSM425873 1 0.5070 0.6783 0.772 0.224 0.004
#> GSM425843 1 0.0000 0.9151 1.000 0.000 0.000
#> GSM425844 1 0.0592 0.9152 0.988 0.012 0.000
#> GSM425845 3 0.3272 0.8627 0.080 0.016 0.904
#> GSM425846 2 0.0424 0.9367 0.008 0.992 0.000
#> GSM425847 2 0.4555 0.7784 0.200 0.800 0.000
#> GSM425886 3 0.0237 0.9025 0.000 0.004 0.996
#> GSM425887 2 0.2866 0.8989 0.076 0.916 0.008
#> GSM425888 2 0.2772 0.8973 0.080 0.916 0.004
#> GSM425889 1 0.0829 0.9138 0.984 0.004 0.012
#> GSM425890 1 0.2356 0.8929 0.928 0.072 0.000
#> GSM425891 2 0.0829 0.9358 0.004 0.984 0.012
#> GSM425892 2 0.0000 0.9371 0.000 1.000 0.000
#> GSM425853 1 0.1411 0.8997 0.964 0.000 0.036
#> GSM425854 2 0.0000 0.9371 0.000 1.000 0.000
#> GSM425855 1 0.0000 0.9151 1.000 0.000 0.000
#> GSM425856 3 0.6180 0.3450 0.416 0.000 0.584
#> GSM425857 3 0.3967 0.8501 0.044 0.072 0.884
#> GSM425858 2 0.1267 0.9303 0.024 0.972 0.004
#> GSM425859 2 0.0000 0.9371 0.000 1.000 0.000
#> GSM425860 3 0.6495 0.6769 0.060 0.200 0.740
#> GSM425861 2 0.5016 0.7196 0.240 0.760 0.000
#> GSM425862 1 0.1163 0.9114 0.972 0.028 0.000
#> GSM425837 1 0.0000 0.9151 1.000 0.000 0.000
#> GSM425838 1 0.3412 0.8588 0.876 0.124 0.000
#> GSM425839 2 0.0000 0.9371 0.000 1.000 0.000
#> GSM425840 1 0.0000 0.9151 1.000 0.000 0.000
#> GSM425841 1 0.3038 0.8739 0.896 0.104 0.000
#> GSM425842 1 0.0747 0.9115 0.984 0.016 0.000
#> GSM425917 3 0.6193 0.5715 0.292 0.016 0.692
#> GSM425922 1 0.2711 0.8842 0.912 0.088 0.000
#> GSM425919 1 0.2682 0.8682 0.920 0.004 0.076
#> GSM425920 1 0.0000 0.9151 1.000 0.000 0.000
#> GSM425923 1 0.0237 0.9148 0.996 0.000 0.004
#> GSM425916 1 0.0424 0.9141 0.992 0.000 0.008
#> GSM425918 1 0.0000 0.9151 1.000 0.000 0.000
#> GSM425921 1 0.2356 0.8928 0.928 0.072 0.000
#> GSM425925 1 0.0747 0.9149 0.984 0.016 0.000
#> GSM425926 1 0.2796 0.8816 0.908 0.092 0.000
#> GSM425927 1 0.0000 0.9151 1.000 0.000 0.000
#> GSM425924 3 0.4291 0.7623 0.180 0.000 0.820
#> GSM425928 3 0.0000 0.9039 0.000 0.000 1.000
#> GSM425929 3 0.0000 0.9039 0.000 0.000 1.000
#> GSM425930 3 0.0000 0.9039 0.000 0.000 1.000
#> GSM425931 3 0.0000 0.9039 0.000 0.000 1.000
#> GSM425932 3 0.0000 0.9039 0.000 0.000 1.000
#> GSM425933 3 0.0000 0.9039 0.000 0.000 1.000
#> GSM425934 3 0.0000 0.9039 0.000 0.000 1.000
#> GSM425935 3 0.0000 0.9039 0.000 0.000 1.000
#> GSM425936 3 0.0000 0.9039 0.000 0.000 1.000
#> GSM425937 3 0.0000 0.9039 0.000 0.000 1.000
#> GSM425938 3 0.0000 0.9039 0.000 0.000 1.000
#> GSM425939 3 0.0000 0.9039 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.0376 0.8624 0.004 0.992 0.000 0.004
#> GSM425908 2 0.0376 0.8624 0.004 0.992 0.000 0.004
#> GSM425909 1 0.6421 0.4293 0.560 0.020 0.384 0.036
#> GSM425910 1 0.7224 0.3865 0.660 0.156 0.104 0.080
#> GSM425911 2 0.5332 0.7156 0.124 0.748 0.128 0.000
#> GSM425912 2 0.5169 0.7457 0.212 0.744 0.020 0.024
#> GSM425913 2 0.1767 0.8617 0.044 0.944 0.012 0.000
#> GSM425914 2 0.6078 0.6943 0.204 0.692 0.096 0.008
#> GSM425915 3 0.5396 -0.1786 0.464 0.012 0.524 0.000
#> GSM425874 4 0.2926 0.7550 0.048 0.056 0.000 0.896
#> GSM425875 1 0.5471 0.5822 0.724 0.004 0.064 0.208
#> GSM425876 1 0.7577 0.2157 0.600 0.200 0.040 0.160
#> GSM425877 4 0.2593 0.7971 0.104 0.000 0.004 0.892
#> GSM425878 4 0.4564 0.7002 0.328 0.000 0.000 0.672
#> GSM425879 2 0.1256 0.8636 0.028 0.964 0.008 0.000
#> GSM425880 1 0.6214 0.5961 0.676 0.008 0.220 0.096
#> GSM425881 2 0.4123 0.7673 0.220 0.772 0.000 0.008
#> GSM425882 2 0.1022 0.8655 0.032 0.968 0.000 0.000
#> GSM425883 4 0.5561 0.7225 0.128 0.028 0.080 0.764
#> GSM425884 4 0.5137 0.5457 0.452 0.000 0.004 0.544
#> GSM425885 4 0.6253 0.5082 0.088 0.240 0.008 0.664
#> GSM425848 4 0.4137 0.7224 0.140 0.028 0.008 0.824
#> GSM425849 4 0.3908 0.7700 0.212 0.004 0.000 0.784
#> GSM425850 4 0.5851 0.5339 0.456 0.024 0.004 0.516
#> GSM425851 4 0.4465 0.7728 0.144 0.000 0.056 0.800
#> GSM425852 1 0.6290 0.4518 0.568 0.000 0.364 0.068
#> GSM425893 2 0.7414 0.0641 0.340 0.480 0.180 0.000
#> GSM425894 2 0.0707 0.8620 0.000 0.980 0.000 0.020
#> GSM425895 2 0.0469 0.8645 0.012 0.988 0.000 0.000
#> GSM425896 2 0.4285 0.7567 0.068 0.832 0.092 0.008
#> GSM425897 2 0.1297 0.8613 0.016 0.964 0.020 0.000
#> GSM425898 2 0.0524 0.8641 0.004 0.988 0.000 0.008
#> GSM425899 2 0.6882 0.1725 0.108 0.500 0.000 0.392
#> GSM425900 2 0.2876 0.8449 0.092 0.892 0.008 0.008
#> GSM425901 1 0.6828 0.4581 0.564 0.032 0.356 0.048
#> GSM425902 4 0.3611 0.7386 0.060 0.080 0.000 0.860
#> GSM425903 1 0.5311 0.3991 0.596 0.004 0.392 0.008
#> GSM425904 1 0.6478 0.5817 0.644 0.008 0.248 0.100
#> GSM425905 2 0.0469 0.8636 0.012 0.988 0.000 0.000
#> GSM425906 2 0.2983 0.8392 0.108 0.880 0.004 0.008
#> GSM425863 4 0.3528 0.7800 0.192 0.000 0.000 0.808
#> GSM425864 2 0.1109 0.8638 0.028 0.968 0.004 0.000
#> GSM425865 2 0.0592 0.8644 0.016 0.984 0.000 0.000
#> GSM425866 1 0.5459 0.6157 0.748 0.004 0.120 0.128
#> GSM425867 3 0.4643 0.2444 0.344 0.000 0.656 0.000
#> GSM425868 2 0.2593 0.8070 0.004 0.892 0.000 0.104
#> GSM425869 2 0.0817 0.8603 0.000 0.976 0.000 0.024
#> GSM425870 3 0.5171 0.5644 0.112 0.128 0.760 0.000
#> GSM425871 4 0.4252 0.7448 0.252 0.004 0.000 0.744
#> GSM425872 2 0.1771 0.8640 0.036 0.948 0.004 0.012
#> GSM425873 1 0.7650 -0.1183 0.512 0.172 0.012 0.304
#> GSM425843 4 0.4643 0.6745 0.344 0.000 0.000 0.656
#> GSM425844 4 0.4377 0.7723 0.188 0.008 0.016 0.788
#> GSM425845 1 0.4088 0.5774 0.824 0.008 0.144 0.024
#> GSM425846 2 0.3037 0.8456 0.076 0.888 0.000 0.036
#> GSM425847 2 0.7224 0.3255 0.408 0.480 0.012 0.100
#> GSM425886 1 0.6062 0.2807 0.512 0.028 0.452 0.008
#> GSM425887 2 0.4333 0.7736 0.208 0.776 0.008 0.008
#> GSM425888 2 0.4951 0.7377 0.212 0.744 0.000 0.044
#> GSM425889 4 0.2081 0.7798 0.084 0.000 0.000 0.916
#> GSM425890 4 0.2231 0.7776 0.012 0.044 0.012 0.932
#> GSM425891 2 0.1938 0.8606 0.052 0.936 0.012 0.000
#> GSM425892 2 0.0779 0.8616 0.004 0.980 0.000 0.016
#> GSM425853 1 0.4936 0.1005 0.672 0.000 0.012 0.316
#> GSM425854 2 0.0188 0.8631 0.000 0.996 0.000 0.004
#> GSM425855 4 0.2408 0.7991 0.104 0.000 0.000 0.896
#> GSM425856 1 0.5368 0.6114 0.752 0.004 0.096 0.148
#> GSM425857 1 0.8160 0.5169 0.552 0.072 0.240 0.136
#> GSM425858 2 0.2401 0.8477 0.092 0.904 0.000 0.004
#> GSM425859 2 0.0188 0.8625 0.004 0.996 0.000 0.000
#> GSM425860 3 0.5649 0.3667 0.344 0.036 0.620 0.000
#> GSM425861 2 0.7232 0.3975 0.320 0.516 0.000 0.164
#> GSM425862 4 0.1637 0.7819 0.060 0.000 0.000 0.940
#> GSM425837 4 0.4585 0.6839 0.332 0.000 0.000 0.668
#> GSM425838 4 0.3647 0.7289 0.040 0.108 0.000 0.852
#> GSM425839 2 0.0000 0.8628 0.000 1.000 0.000 0.000
#> GSM425840 4 0.3688 0.7718 0.208 0.000 0.000 0.792
#> GSM425841 4 0.3009 0.7572 0.052 0.056 0.000 0.892
#> GSM425842 4 0.5897 0.4969 0.468 0.020 0.008 0.504
#> GSM425917 3 0.4978 0.5850 0.052 0.004 0.764 0.180
#> GSM425922 4 0.1936 0.7799 0.032 0.028 0.000 0.940
#> GSM425919 4 0.7317 0.5003 0.268 0.000 0.204 0.528
#> GSM425920 4 0.4472 0.7545 0.220 0.000 0.020 0.760
#> GSM425923 4 0.2011 0.7963 0.080 0.000 0.000 0.920
#> GSM425916 4 0.3161 0.7894 0.124 0.000 0.012 0.864
#> GSM425918 4 0.2197 0.7953 0.080 0.000 0.004 0.916
#> GSM425921 4 0.1833 0.7749 0.032 0.024 0.000 0.944
#> GSM425925 4 0.2198 0.7938 0.072 0.008 0.000 0.920
#> GSM425926 4 0.2411 0.7658 0.040 0.040 0.000 0.920
#> GSM425927 4 0.4877 0.6180 0.408 0.000 0.000 0.592
#> GSM425924 3 0.5003 0.5943 0.084 0.000 0.768 0.148
#> GSM425928 3 0.0000 0.8421 0.000 0.000 1.000 0.000
#> GSM425929 3 0.0000 0.8421 0.000 0.000 1.000 0.000
#> GSM425930 3 0.0000 0.8421 0.000 0.000 1.000 0.000
#> GSM425931 3 0.0000 0.8421 0.000 0.000 1.000 0.000
#> GSM425932 3 0.0000 0.8421 0.000 0.000 1.000 0.000
#> GSM425933 3 0.0000 0.8421 0.000 0.000 1.000 0.000
#> GSM425934 3 0.0000 0.8421 0.000 0.000 1.000 0.000
#> GSM425935 3 0.0000 0.8421 0.000 0.000 1.000 0.000
#> GSM425936 3 0.0000 0.8421 0.000 0.000 1.000 0.000
#> GSM425937 3 0.0000 0.8421 0.000 0.000 1.000 0.000
#> GSM425938 3 0.0000 0.8421 0.000 0.000 1.000 0.000
#> GSM425939 3 0.0000 0.8421 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
#> GSM425907 2 0.1153 0.7912 0.008 0.964 0.004 0.024 0.000
#> GSM425908 2 0.2263 0.7864 0.020 0.916 0.004 0.056 0.004
#> GSM425909 5 0.2722 0.8311 0.000 0.020 0.108 0.000 0.872
#> GSM425910 1 0.4552 0.5262 0.796 0.020 0.056 0.016 0.112
#> GSM425911 2 0.6383 0.5784 0.180 0.640 0.084 0.000 0.096
#> GSM425912 1 0.4738 -0.1221 0.564 0.420 0.004 0.000 0.012
#> GSM425913 2 0.3129 0.7632 0.156 0.832 0.004 0.008 0.000
#> GSM425914 2 0.6238 0.2930 0.404 0.500 0.052 0.000 0.044
#> GSM425915 5 0.4066 0.6399 0.004 0.000 0.324 0.000 0.672
#> GSM425874 4 0.2264 0.7121 0.004 0.060 0.000 0.912 0.024
#> GSM425875 5 0.2326 0.8052 0.020 0.000 0.020 0.044 0.916
#> GSM425876 1 0.1990 0.5511 0.920 0.008 0.000 0.004 0.068
#> GSM425877 4 0.4455 0.6724 0.188 0.000 0.000 0.744 0.068
#> GSM425878 1 0.6603 -0.0797 0.480 0.012 0.000 0.352 0.156
#> GSM425879 2 0.2353 0.7982 0.028 0.920 0.032 0.008 0.012
#> GSM425880 5 0.2341 0.8296 0.012 0.000 0.056 0.020 0.912
#> GSM425881 1 0.4829 -0.2785 0.500 0.480 0.000 0.000 0.020
#> GSM425882 2 0.3588 0.7711 0.144 0.824 0.004 0.008 0.020
#> GSM425883 4 0.6273 0.6048 0.188 0.040 0.048 0.672 0.052
#> GSM425884 1 0.6567 0.2082 0.524 0.000 0.008 0.236 0.232
#> GSM425885 4 0.5235 0.5076 0.004 0.244 0.004 0.676 0.072
#> GSM425848 4 0.4903 0.5921 0.036 0.012 0.000 0.680 0.272
#> GSM425849 4 0.5702 0.5628 0.268 0.012 0.000 0.628 0.092
#> GSM425850 1 0.4331 0.4862 0.780 0.008 0.000 0.140 0.072
#> GSM425851 4 0.6495 0.3946 0.340 0.000 0.068 0.536 0.056
#> GSM425852 5 0.4746 0.7758 0.048 0.000 0.164 0.032 0.756
#> GSM425893 2 0.7757 0.0780 0.108 0.408 0.140 0.000 0.344
#> GSM425894 2 0.2291 0.7801 0.008 0.908 0.000 0.072 0.012
#> GSM425895 2 0.1974 0.7986 0.036 0.932 0.000 0.016 0.016
#> GSM425896 2 0.4244 0.7266 0.020 0.824 0.052 0.024 0.080
#> GSM425897 2 0.2910 0.7817 0.044 0.884 0.060 0.000 0.012
#> GSM425898 2 0.2300 0.7964 0.040 0.920 0.004 0.024 0.012
#> GSM425899 2 0.8264 -0.1315 0.204 0.344 0.000 0.312 0.140
#> GSM425900 2 0.4340 0.7062 0.224 0.744 0.008 0.008 0.016
#> GSM425901 5 0.2784 0.8322 0.000 0.016 0.108 0.004 0.872
#> GSM425902 4 0.3443 0.7009 0.012 0.076 0.000 0.852 0.060
#> GSM425903 5 0.3321 0.8211 0.032 0.000 0.136 0.000 0.832
#> GSM425904 5 0.2492 0.8332 0.008 0.000 0.072 0.020 0.900
#> GSM425905 2 0.0833 0.7950 0.016 0.976 0.004 0.004 0.000
#> GSM425906 2 0.4387 0.6696 0.272 0.704 0.008 0.000 0.016
#> GSM425863 4 0.5275 0.6335 0.216 0.008 0.000 0.684 0.092
#> GSM425864 2 0.1565 0.7959 0.020 0.952 0.008 0.004 0.016
#> GSM425865 2 0.2551 0.7885 0.104 0.884 0.004 0.004 0.004
#> GSM425866 5 0.2342 0.8233 0.020 0.000 0.040 0.024 0.916
#> GSM425867 5 0.4655 0.3022 0.012 0.000 0.476 0.000 0.512
#> GSM425868 2 0.4804 0.5922 0.048 0.716 0.000 0.224 0.012
#> GSM425869 2 0.2362 0.7733 0.008 0.900 0.000 0.084 0.008
#> GSM425870 3 0.6623 0.4754 0.172 0.140 0.616 0.000 0.072
#> GSM425871 1 0.5830 -0.1294 0.504 0.008 0.000 0.416 0.072
#> GSM425872 2 0.4801 0.7376 0.152 0.764 0.016 0.012 0.056
#> GSM425873 1 0.1885 0.5482 0.932 0.004 0.000 0.020 0.044
#> GSM425843 1 0.6303 -0.0718 0.476 0.000 0.000 0.364 0.160
#> GSM425844 4 0.5206 0.4277 0.384 0.000 0.004 0.572 0.040
#> GSM425845 5 0.3684 0.7823 0.116 0.000 0.056 0.004 0.824
#> GSM425846 2 0.5333 0.6753 0.188 0.708 0.000 0.072 0.032
#> GSM425847 1 0.3606 0.4928 0.808 0.164 0.000 0.004 0.024
#> GSM425886 5 0.3821 0.7647 0.000 0.020 0.216 0.000 0.764
#> GSM425887 2 0.6087 0.3887 0.380 0.532 0.004 0.020 0.064
#> GSM425888 1 0.4997 -0.2029 0.520 0.456 0.000 0.012 0.012
#> GSM425889 4 0.3474 0.7162 0.044 0.004 0.000 0.836 0.116
#> GSM425890 4 0.2418 0.7249 0.044 0.024 0.000 0.912 0.020
#> GSM425891 2 0.3250 0.7591 0.168 0.820 0.008 0.000 0.004
#> GSM425892 2 0.2376 0.7906 0.024 0.916 0.004 0.044 0.012
#> GSM425853 5 0.6125 0.0505 0.380 0.000 0.008 0.104 0.508
#> GSM425854 2 0.1393 0.7972 0.024 0.956 0.000 0.008 0.012
#> GSM425855 4 0.5294 0.6299 0.244 0.004 0.000 0.664 0.088
#> GSM425856 5 0.2444 0.8150 0.024 0.000 0.028 0.036 0.912
#> GSM425857 5 0.3779 0.7827 0.000 0.068 0.032 0.060 0.840
#> GSM425858 2 0.4040 0.6694 0.260 0.724 0.000 0.000 0.016
#> GSM425859 2 0.0693 0.7933 0.000 0.980 0.000 0.012 0.008
#> GSM425860 3 0.6212 0.1248 0.456 0.028 0.460 0.008 0.048
#> GSM425861 1 0.5825 0.2867 0.632 0.264 0.000 0.076 0.028
#> GSM425862 4 0.2813 0.7264 0.032 0.004 0.000 0.880 0.084
#> GSM425837 4 0.6725 0.2942 0.288 0.000 0.000 0.420 0.292
#> GSM425838 4 0.4533 0.6903 0.048 0.100 0.000 0.792 0.060
#> GSM425839 2 0.1243 0.7968 0.028 0.960 0.000 0.008 0.004
#> GSM425840 4 0.5981 0.4218 0.364 0.000 0.004 0.528 0.104
#> GSM425841 4 0.2522 0.7085 0.004 0.076 0.000 0.896 0.024
#> GSM425842 1 0.3033 0.5249 0.864 0.000 0.000 0.084 0.052
#> GSM425917 3 0.4962 0.6607 0.064 0.000 0.740 0.168 0.028
#> GSM425922 4 0.2082 0.7251 0.032 0.024 0.000 0.928 0.016
#> GSM425919 1 0.7505 0.1601 0.488 0.000 0.196 0.240 0.076
#> GSM425920 4 0.5406 0.2162 0.468 0.000 0.000 0.476 0.056
#> GSM425923 4 0.3551 0.7003 0.136 0.000 0.000 0.820 0.044
#> GSM425916 4 0.5226 0.5550 0.284 0.000 0.020 0.656 0.040
#> GSM425918 4 0.4021 0.6812 0.168 0.000 0.000 0.780 0.052
#> GSM425921 4 0.1012 0.7207 0.000 0.020 0.000 0.968 0.012
#> GSM425925 4 0.3468 0.7259 0.092 0.012 0.000 0.848 0.048
#> GSM425926 4 0.1865 0.7212 0.008 0.032 0.000 0.936 0.024
#> GSM425927 1 0.4514 0.4006 0.740 0.000 0.000 0.188 0.072
#> GSM425924 3 0.4980 0.6827 0.088 0.000 0.752 0.128 0.032
#> GSM425928 3 0.0162 0.8870 0.000 0.000 0.996 0.004 0.000
#> GSM425929 3 0.0000 0.8904 0.000 0.000 1.000 0.000 0.000
#> GSM425930 3 0.0000 0.8904 0.000 0.000 1.000 0.000 0.000
#> GSM425931 3 0.0000 0.8904 0.000 0.000 1.000 0.000 0.000
#> GSM425932 3 0.0000 0.8904 0.000 0.000 1.000 0.000 0.000
#> GSM425933 3 0.0000 0.8904 0.000 0.000 1.000 0.000 0.000
#> GSM425934 3 0.0000 0.8904 0.000 0.000 1.000 0.000 0.000
#> GSM425935 3 0.0324 0.8844 0.000 0.004 0.992 0.000 0.004
#> GSM425936 3 0.0000 0.8904 0.000 0.000 1.000 0.000 0.000
#> GSM425937 3 0.0000 0.8904 0.000 0.000 1.000 0.000 0.000
#> GSM425938 3 0.0000 0.8904 0.000 0.000 1.000 0.000 0.000
#> GSM425939 3 0.0000 0.8904 0.000 0.000 1.000 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 2 0.1452 0.6214 0.000 0.948 0.004 0.008 0.008 0.032
#> GSM425908 2 0.2441 0.6211 0.012 0.900 0.000 0.024 0.008 0.056
#> GSM425909 5 0.1799 0.8740 0.008 0.004 0.052 0.000 0.928 0.008
#> GSM425910 6 0.6748 -0.1687 0.396 0.056 0.016 0.000 0.116 0.416
#> GSM425911 2 0.6857 0.1598 0.052 0.528 0.048 0.000 0.108 0.264
#> GSM425912 6 0.4707 0.4767 0.092 0.228 0.000 0.000 0.004 0.676
#> GSM425913 2 0.4700 0.3999 0.012 0.628 0.012 0.020 0.000 0.328
#> GSM425914 6 0.7121 0.2581 0.100 0.364 0.048 0.000 0.060 0.428
#> GSM425915 5 0.3817 0.7532 0.004 0.004 0.220 0.000 0.748 0.024
#> GSM425874 4 0.2572 0.6605 0.016 0.052 0.000 0.896 0.024 0.012
#> GSM425875 5 0.2334 0.8473 0.040 0.000 0.008 0.032 0.908 0.012
#> GSM425876 1 0.4752 0.2538 0.540 0.004 0.000 0.004 0.032 0.420
#> GSM425877 4 0.5027 0.2818 0.412 0.000 0.000 0.532 0.024 0.032
#> GSM425878 1 0.6762 0.3478 0.484 0.008 0.000 0.292 0.064 0.152
#> GSM425879 2 0.2451 0.6228 0.008 0.904 0.028 0.000 0.024 0.036
#> GSM425880 5 0.1251 0.8711 0.008 0.000 0.024 0.000 0.956 0.012
#> GSM425881 6 0.5703 0.4407 0.124 0.276 0.000 0.008 0.012 0.580
#> GSM425882 2 0.4762 0.4428 0.044 0.680 0.000 0.012 0.012 0.252
#> GSM425883 4 0.6869 0.4443 0.192 0.032 0.048 0.584 0.024 0.120
#> GSM425884 1 0.6600 0.4793 0.552 0.000 0.004 0.200 0.104 0.140
#> GSM425885 4 0.5891 0.4616 0.032 0.224 0.000 0.632 0.068 0.044
#> GSM425848 4 0.6305 0.4528 0.164 0.032 0.000 0.584 0.196 0.024
#> GSM425849 4 0.6690 0.2161 0.328 0.020 0.000 0.484 0.052 0.116
#> GSM425850 1 0.5953 0.3596 0.500 0.020 0.000 0.084 0.016 0.380
#> GSM425851 1 0.5680 0.2530 0.556 0.000 0.048 0.348 0.020 0.028
#> GSM425852 5 0.4974 0.7464 0.096 0.000 0.124 0.024 0.732 0.024
#> GSM425893 2 0.7382 0.0508 0.024 0.408 0.068 0.004 0.332 0.164
#> GSM425894 2 0.5396 0.5272 0.028 0.648 0.000 0.084 0.008 0.232
#> GSM425895 2 0.3880 0.6013 0.012 0.760 0.000 0.024 0.004 0.200
#> GSM425896 2 0.3024 0.5995 0.012 0.876 0.012 0.008 0.056 0.036
#> GSM425897 2 0.3967 0.5951 0.020 0.808 0.004 0.020 0.032 0.116
#> GSM425898 2 0.4491 0.5787 0.016 0.708 0.000 0.028 0.012 0.236
#> GSM425899 2 0.8526 -0.0857 0.184 0.260 0.000 0.244 0.064 0.248
#> GSM425900 6 0.4565 -0.0627 0.012 0.460 0.004 0.004 0.004 0.516
#> GSM425901 5 0.1768 0.8737 0.000 0.008 0.044 0.004 0.932 0.012
#> GSM425902 4 0.4630 0.6397 0.056 0.068 0.000 0.780 0.048 0.048
#> GSM425903 5 0.2458 0.8696 0.012 0.008 0.052 0.000 0.900 0.028
#> GSM425904 5 0.1476 0.8724 0.008 0.004 0.028 0.000 0.948 0.012
#> GSM425905 2 0.2019 0.6266 0.000 0.900 0.000 0.012 0.000 0.088
#> GSM425906 6 0.3944 0.0974 0.004 0.428 0.000 0.000 0.000 0.568
#> GSM425863 4 0.5899 0.4243 0.292 0.000 0.000 0.560 0.044 0.104
#> GSM425864 2 0.3202 0.6023 0.012 0.852 0.000 0.008 0.044 0.084
#> GSM425865 2 0.4205 0.5691 0.040 0.776 0.000 0.032 0.008 0.144
#> GSM425866 5 0.1690 0.8686 0.020 0.000 0.020 0.004 0.940 0.016
#> GSM425867 5 0.4604 0.3424 0.008 0.000 0.432 0.000 0.536 0.024
#> GSM425868 2 0.6959 0.3390 0.076 0.508 0.000 0.224 0.016 0.176
#> GSM425869 2 0.4386 0.6038 0.012 0.760 0.000 0.076 0.012 0.140
#> GSM425870 3 0.6982 0.2339 0.032 0.156 0.516 0.000 0.060 0.236
#> GSM425871 1 0.5910 0.4520 0.544 0.000 0.000 0.252 0.016 0.188
#> GSM425872 2 0.6437 0.2563 0.036 0.476 0.008 0.040 0.048 0.392
#> GSM425873 1 0.4640 0.2499 0.532 0.004 0.000 0.004 0.024 0.436
#> GSM425843 1 0.5691 0.4053 0.600 0.000 0.000 0.244 0.032 0.124
#> GSM425844 1 0.5735 0.2254 0.468 0.000 0.000 0.408 0.016 0.108
#> GSM425845 5 0.3374 0.8105 0.048 0.000 0.024 0.000 0.836 0.092
#> GSM425846 2 0.6374 0.2189 0.048 0.472 0.000 0.084 0.016 0.380
#> GSM425847 6 0.4587 0.2191 0.316 0.048 0.000 0.000 0.004 0.632
#> GSM425886 5 0.2890 0.8522 0.004 0.016 0.096 0.000 0.864 0.020
#> GSM425887 6 0.5888 0.4003 0.088 0.244 0.004 0.016 0.032 0.616
#> GSM425888 6 0.4710 0.4379 0.072 0.208 0.000 0.020 0.000 0.700
#> GSM425889 4 0.4798 0.6379 0.160 0.008 0.000 0.732 0.048 0.052
#> GSM425890 4 0.3085 0.6247 0.148 0.004 0.008 0.828 0.000 0.012
#> GSM425891 2 0.5518 0.3126 0.048 0.568 0.004 0.016 0.016 0.348
#> GSM425892 2 0.4490 0.6066 0.024 0.780 0.004 0.076 0.020 0.096
#> GSM425853 1 0.6961 0.2402 0.408 0.000 0.008 0.076 0.364 0.144
#> GSM425854 2 0.3261 0.5965 0.000 0.780 0.000 0.016 0.000 0.204
#> GSM425855 4 0.5737 0.4008 0.300 0.004 0.000 0.572 0.028 0.096
#> GSM425856 5 0.2635 0.8428 0.056 0.000 0.012 0.016 0.892 0.024
#> GSM425857 5 0.2450 0.8440 0.008 0.036 0.008 0.040 0.904 0.004
#> GSM425858 6 0.4072 -0.0299 0.008 0.448 0.000 0.000 0.000 0.544
#> GSM425859 2 0.2730 0.6168 0.000 0.836 0.000 0.012 0.000 0.152
#> GSM425860 6 0.7886 0.0221 0.208 0.048 0.336 0.008 0.060 0.340
#> GSM425861 6 0.5397 0.4427 0.148 0.084 0.000 0.068 0.008 0.692
#> GSM425862 4 0.4444 0.6463 0.176 0.004 0.000 0.744 0.040 0.036
#> GSM425837 1 0.6952 0.0680 0.408 0.000 0.000 0.320 0.196 0.076
#> GSM425838 4 0.5025 0.6056 0.104 0.100 0.000 0.736 0.024 0.036
#> GSM425839 2 0.3748 0.5728 0.016 0.748 0.000 0.012 0.000 0.224
#> GSM425840 1 0.6007 -0.0432 0.464 0.000 0.000 0.404 0.048 0.084
#> GSM425841 4 0.3411 0.6556 0.036 0.064 0.000 0.852 0.024 0.024
#> GSM425842 1 0.4910 0.3908 0.584 0.000 0.000 0.020 0.036 0.360
#> GSM425917 3 0.5336 0.5651 0.152 0.004 0.668 0.156 0.004 0.016
#> GSM425922 4 0.2306 0.6472 0.096 0.004 0.000 0.888 0.004 0.008
#> GSM425919 1 0.6185 0.4736 0.640 0.000 0.100 0.152 0.032 0.076
#> GSM425920 1 0.4819 0.3932 0.648 0.000 0.004 0.276 0.004 0.068
#> GSM425923 4 0.3972 0.4950 0.300 0.000 0.000 0.680 0.004 0.016
#> GSM425916 1 0.4677 0.0153 0.524 0.000 0.008 0.444 0.004 0.020
#> GSM425918 4 0.4144 0.3827 0.360 0.000 0.000 0.620 0.000 0.020
#> GSM425921 4 0.1699 0.6593 0.060 0.004 0.000 0.928 0.004 0.004
#> GSM425925 4 0.4206 0.6147 0.168 0.008 0.000 0.760 0.012 0.052
#> GSM425926 4 0.2295 0.6698 0.048 0.024 0.000 0.908 0.016 0.004
#> GSM425927 1 0.4988 0.5282 0.672 0.000 0.000 0.080 0.024 0.224
#> GSM425924 3 0.4398 0.6631 0.164 0.004 0.740 0.084 0.000 0.008
#> GSM425928 3 0.0291 0.9150 0.004 0.000 0.992 0.004 0.000 0.000
#> GSM425929 3 0.0146 0.9181 0.004 0.000 0.996 0.000 0.000 0.000
#> GSM425930 3 0.0000 0.9191 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425931 3 0.0000 0.9191 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425932 3 0.0000 0.9191 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425933 3 0.0000 0.9191 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425934 3 0.0000 0.9191 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425935 3 0.0653 0.9080 0.004 0.012 0.980 0.004 0.000 0.000
#> GSM425936 3 0.0000 0.9191 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425937 3 0.0146 0.9181 0.004 0.000 0.996 0.000 0.000 0.000
#> GSM425938 3 0.0146 0.9181 0.004 0.000 0.996 0.000 0.000 0.000
#> GSM425939 3 0.0000 0.9191 0.000 0.000 1.000 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 disease.state(p) tissue(p) other(p) k
#> CV:skmeans 95 1.03e-03 6.48e-05 2.49e-07 2
#> CV:skmeans 97 4.70e-08 1.50e-09 1.74e-07 3
#> CV:skmeans 86 3.05e-14 1.78e-15 5.96e-12 4
#> CV:skmeans 78 2.79e-13 1.12e-14 2.59e-07 5
#> CV:skmeans 55 4.07e-09 5.32e-11 6.62e-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["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 103 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 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 0.619 0.838 0.926 0.4211 0.591 0.591
#> 3 3 0.335 0.368 0.681 0.4954 0.640 0.454
#> 4 4 0.418 0.409 0.716 0.1134 0.713 0.391
#> 5 5 0.519 0.454 0.731 0.0775 0.873 0.606
#> 6 6 0.593 0.541 0.747 0.0570 0.886 0.563
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 5
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
#> GSM425907 1 0.0000 0.92493 1.000 0.000
#> GSM425908 1 0.0000 0.92493 1.000 0.000
#> GSM425909 1 0.9998 0.00709 0.508 0.492
#> GSM425910 1 0.7139 0.74979 0.804 0.196
#> GSM425911 1 0.0000 0.92493 1.000 0.000
#> GSM425912 1 0.0000 0.92493 1.000 0.000
#> GSM425913 1 0.5294 0.84145 0.880 0.120
#> GSM425914 1 0.0000 0.92493 1.000 0.000
#> GSM425915 2 0.1843 0.88371 0.028 0.972
#> GSM425874 1 0.0000 0.92493 1.000 0.000
#> GSM425875 1 0.3879 0.88417 0.924 0.076
#> GSM425876 1 0.2043 0.91293 0.968 0.032
#> GSM425877 1 0.8713 0.58643 0.708 0.292
#> GSM425878 1 0.0000 0.92493 1.000 0.000
#> GSM425879 1 0.0376 0.92419 0.996 0.004
#> GSM425880 2 0.8555 0.64986 0.280 0.720
#> GSM425881 1 0.0000 0.92493 1.000 0.000
#> GSM425882 1 0.0000 0.92493 1.000 0.000
#> GSM425883 1 0.2043 0.91347 0.968 0.032
#> GSM425884 1 0.7219 0.75419 0.800 0.200
#> GSM425885 1 0.0000 0.92493 1.000 0.000
#> GSM425848 1 0.5842 0.82729 0.860 0.140
#> GSM425849 1 0.0000 0.92493 1.000 0.000
#> GSM425850 1 0.0000 0.92493 1.000 0.000
#> GSM425851 2 0.9129 0.57270 0.328 0.672
#> GSM425852 2 0.1184 0.88764 0.016 0.984
#> GSM425893 1 0.1184 0.92071 0.984 0.016
#> GSM425894 1 0.0000 0.92493 1.000 0.000
#> GSM425895 1 0.0000 0.92493 1.000 0.000
#> GSM425896 1 0.0938 0.92211 0.988 0.012
#> GSM425897 1 0.0376 0.92419 0.996 0.004
#> GSM425898 1 0.3733 0.88575 0.928 0.072
#> GSM425899 1 0.6623 0.78310 0.828 0.172
#> GSM425900 1 0.8081 0.66529 0.752 0.248
#> GSM425901 1 0.9427 0.43762 0.640 0.360
#> GSM425902 1 0.4161 0.87752 0.916 0.084
#> GSM425903 1 0.9129 0.51538 0.672 0.328
#> GSM425904 2 0.5842 0.80862 0.140 0.860
#> GSM425905 1 0.0000 0.92493 1.000 0.000
#> GSM425906 1 0.2043 0.91235 0.968 0.032
#> GSM425863 1 0.0672 0.92362 0.992 0.008
#> GSM425864 1 0.0000 0.92493 1.000 0.000
#> GSM425865 1 0.0000 0.92493 1.000 0.000
#> GSM425866 1 0.6801 0.78305 0.820 0.180
#> GSM425867 2 0.0000 0.89023 0.000 1.000
#> GSM425868 1 0.0000 0.92493 1.000 0.000
#> GSM425869 1 0.1184 0.92059 0.984 0.016
#> GSM425870 2 0.9580 0.45420 0.380 0.620
#> GSM425871 1 0.0000 0.92493 1.000 0.000
#> GSM425872 1 0.0376 0.92432 0.996 0.004
#> GSM425873 1 0.0376 0.92419 0.996 0.004
#> GSM425843 1 0.6887 0.77266 0.816 0.184
#> GSM425844 1 0.1184 0.92092 0.984 0.016
#> GSM425845 1 0.1184 0.92072 0.984 0.016
#> GSM425846 1 0.0000 0.92493 1.000 0.000
#> GSM425847 1 0.0000 0.92493 1.000 0.000
#> GSM425886 1 0.8909 0.55726 0.692 0.308
#> GSM425887 1 0.0000 0.92493 1.000 0.000
#> GSM425888 1 0.0000 0.92493 1.000 0.000
#> GSM425889 2 0.9460 0.46867 0.364 0.636
#> GSM425890 1 0.0000 0.92493 1.000 0.000
#> GSM425891 1 0.2236 0.91066 0.964 0.036
#> GSM425892 1 0.0000 0.92493 1.000 0.000
#> GSM425853 1 0.0672 0.92364 0.992 0.008
#> GSM425854 1 0.0000 0.92493 1.000 0.000
#> GSM425855 2 0.8763 0.60594 0.296 0.704
#> GSM425856 1 0.2043 0.91308 0.968 0.032
#> GSM425857 2 0.9552 0.47255 0.376 0.624
#> GSM425858 1 0.0000 0.92493 1.000 0.000
#> GSM425859 1 0.0000 0.92493 1.000 0.000
#> GSM425860 2 0.7219 0.75141 0.200 0.800
#> GSM425861 1 0.0000 0.92493 1.000 0.000
#> GSM425862 1 0.0000 0.92493 1.000 0.000
#> GSM425837 1 0.6531 0.79444 0.832 0.168
#> GSM425838 1 0.0000 0.92493 1.000 0.000
#> GSM425839 1 0.0938 0.92201 0.988 0.012
#> GSM425840 2 0.2423 0.87797 0.040 0.960
#> GSM425841 1 0.4298 0.87124 0.912 0.088
#> GSM425842 1 0.1184 0.92027 0.984 0.016
#> GSM425917 2 0.0672 0.88945 0.008 0.992
#> GSM425922 1 0.7299 0.72910 0.796 0.204
#> GSM425919 2 0.2043 0.88234 0.032 0.968
#> GSM425920 2 0.8499 0.65835 0.276 0.724
#> GSM425923 1 0.5178 0.85184 0.884 0.116
#> GSM425916 2 0.1633 0.88379 0.024 0.976
#> GSM425918 1 0.0000 0.92493 1.000 0.000
#> GSM425921 1 0.9970 0.02282 0.532 0.468
#> GSM425925 1 0.0000 0.92493 1.000 0.000
#> GSM425926 1 0.0000 0.92493 1.000 0.000
#> GSM425927 1 0.3584 0.89227 0.932 0.068
#> GSM425924 2 0.0376 0.88997 0.004 0.996
#> GSM425928 2 0.0000 0.89023 0.000 1.000
#> GSM425929 2 0.0000 0.89023 0.000 1.000
#> GSM425930 2 0.0000 0.89023 0.000 1.000
#> GSM425931 2 0.0000 0.89023 0.000 1.000
#> GSM425932 2 0.0000 0.89023 0.000 1.000
#> GSM425933 2 0.0000 0.89023 0.000 1.000
#> GSM425934 2 0.0000 0.89023 0.000 1.000
#> GSM425935 2 0.0000 0.89023 0.000 1.000
#> GSM425936 2 0.0000 0.89023 0.000 1.000
#> GSM425937 2 0.0000 0.89023 0.000 1.000
#> GSM425938 2 0.0000 0.89023 0.000 1.000
#> GSM425939 2 0.0000 0.89023 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.3340 0.6371 0.000 0.880 0.120
#> GSM425908 2 0.6053 0.5920 0.020 0.720 0.260
#> GSM425909 3 0.7493 -0.1418 0.092 0.232 0.676
#> GSM425910 3 0.9858 -0.4427 0.256 0.348 0.396
#> GSM425911 2 0.6045 0.5687 0.000 0.620 0.380
#> GSM425912 2 0.6045 0.5687 0.000 0.620 0.380
#> GSM425913 2 0.1031 0.5956 0.000 0.976 0.024
#> GSM425914 2 0.6045 0.5687 0.000 0.620 0.380
#> GSM425915 3 0.8434 0.4941 0.416 0.088 0.496
#> GSM425874 2 0.5958 0.2783 0.300 0.692 0.008
#> GSM425875 3 0.9789 -0.4862 0.368 0.236 0.396
#> GSM425876 2 0.8943 0.3813 0.128 0.480 0.392
#> GSM425877 1 0.7133 0.5102 0.712 0.096 0.192
#> GSM425878 1 0.9775 0.2688 0.392 0.232 0.376
#> GSM425879 2 0.6314 0.5607 0.004 0.604 0.392
#> GSM425880 1 0.7782 0.3313 0.668 0.124 0.208
#> GSM425881 2 0.6045 0.5687 0.000 0.620 0.380
#> GSM425882 2 0.6205 0.5956 0.008 0.656 0.336
#> GSM425883 2 0.8747 0.4500 0.112 0.492 0.396
#> GSM425884 1 0.8211 0.4567 0.520 0.076 0.404
#> GSM425885 2 0.4409 0.4549 0.172 0.824 0.004
#> GSM425848 1 0.7953 0.4665 0.564 0.068 0.368
#> GSM425849 1 0.8967 0.4169 0.488 0.132 0.380
#> GSM425850 3 0.9969 -0.4580 0.308 0.320 0.372
#> GSM425851 1 0.7841 0.3178 0.536 0.408 0.056
#> GSM425852 1 0.7228 -0.3431 0.600 0.036 0.364
#> GSM425893 2 0.6345 0.5566 0.004 0.596 0.400
#> GSM425894 2 0.5016 0.6329 0.000 0.760 0.240
#> GSM425895 2 0.5678 0.6065 0.000 0.684 0.316
#> GSM425896 2 0.5988 0.5789 0.000 0.632 0.368
#> GSM425897 2 0.5656 0.6123 0.004 0.712 0.284
#> GSM425898 2 0.2584 0.6244 0.008 0.928 0.064
#> GSM425899 2 0.7097 0.5075 0.172 0.720 0.108
#> GSM425900 2 0.8675 0.3917 0.184 0.596 0.220
#> GSM425901 3 0.9642 -0.4756 0.376 0.208 0.416
#> GSM425902 2 0.8720 0.3686 0.252 0.584 0.164
#> GSM425903 3 0.7770 -0.2028 0.080 0.292 0.628
#> GSM425904 1 0.5538 0.2190 0.808 0.060 0.132
#> GSM425905 2 0.1753 0.6254 0.000 0.952 0.048
#> GSM425906 2 0.1860 0.6239 0.000 0.948 0.052
#> GSM425863 1 0.9863 0.1748 0.400 0.340 0.260
#> GSM425864 2 0.3752 0.6364 0.000 0.856 0.144
#> GSM425865 2 0.2448 0.6328 0.000 0.924 0.076
#> GSM425866 1 0.9147 0.3757 0.444 0.144 0.412
#> GSM425867 3 0.6126 0.5855 0.400 0.000 0.600
#> GSM425868 2 0.2448 0.5578 0.076 0.924 0.000
#> GSM425869 2 0.2681 0.5986 0.040 0.932 0.028
#> GSM425870 3 0.9937 0.1664 0.328 0.288 0.384
#> GSM425871 2 0.8730 -0.1457 0.388 0.500 0.112
#> GSM425872 2 0.0237 0.6007 0.000 0.996 0.004
#> GSM425873 2 0.9518 0.2407 0.188 0.420 0.392
#> GSM425843 1 0.9322 0.3680 0.444 0.164 0.392
#> GSM425844 1 0.9229 0.4177 0.488 0.164 0.348
#> GSM425845 2 0.7080 0.5293 0.024 0.564 0.412
#> GSM425846 2 0.2400 0.6276 0.004 0.932 0.064
#> GSM425847 2 0.5016 0.6339 0.000 0.760 0.240
#> GSM425886 3 0.7534 -0.3655 0.048 0.368 0.584
#> GSM425887 2 0.6379 0.5746 0.008 0.624 0.368
#> GSM425888 2 0.3193 0.6293 0.004 0.896 0.100
#> GSM425889 1 0.7246 0.4492 0.664 0.060 0.276
#> GSM425890 2 0.6396 0.2298 0.320 0.664 0.016
#> GSM425891 2 0.2866 0.6266 0.008 0.916 0.076
#> GSM425892 2 0.0000 0.6025 0.000 1.000 0.000
#> GSM425853 2 0.8973 -0.0388 0.364 0.500 0.136
#> GSM425854 2 0.4654 0.6378 0.000 0.792 0.208
#> GSM425855 1 0.8743 0.0504 0.512 0.116 0.372
#> GSM425856 2 0.8084 -0.0660 0.384 0.544 0.072
#> GSM425857 2 0.7923 0.2160 0.120 0.652 0.228
#> GSM425858 2 0.5098 0.6322 0.000 0.752 0.248
#> GSM425859 2 0.3116 0.6380 0.000 0.892 0.108
#> GSM425860 1 0.9649 -0.3986 0.404 0.208 0.388
#> GSM425861 2 0.6298 0.5611 0.004 0.608 0.388
#> GSM425862 1 0.9532 0.3536 0.488 0.268 0.244
#> GSM425837 1 0.9314 0.4218 0.492 0.180 0.328
#> GSM425838 1 0.9721 0.3274 0.452 0.284 0.264
#> GSM425839 2 0.0000 0.6025 0.000 1.000 0.000
#> GSM425840 1 0.5860 -0.0942 0.748 0.024 0.228
#> GSM425841 1 0.7309 0.2577 0.552 0.416 0.032
#> GSM425842 3 0.9888 -0.4420 0.264 0.348 0.388
#> GSM425917 3 0.6432 0.5686 0.428 0.004 0.568
#> GSM425922 2 0.5588 0.3107 0.276 0.720 0.004
#> GSM425919 3 0.7868 0.5334 0.420 0.056 0.524
#> GSM425920 1 0.7603 0.1610 0.688 0.172 0.140
#> GSM425923 1 0.8623 0.4794 0.584 0.144 0.272
#> GSM425916 1 0.3851 0.1171 0.860 0.004 0.136
#> GSM425918 2 0.9305 -0.0517 0.380 0.456 0.164
#> GSM425921 1 0.6215 0.2503 0.572 0.428 0.000
#> GSM425925 1 0.9280 0.3326 0.452 0.160 0.388
#> GSM425926 2 0.6617 0.0859 0.388 0.600 0.012
#> GSM425927 2 0.9752 0.2023 0.236 0.424 0.340
#> GSM425924 3 0.6675 0.5800 0.404 0.012 0.584
#> GSM425928 3 0.6140 0.5876 0.404 0.000 0.596
#> GSM425929 3 0.6140 0.5876 0.404 0.000 0.596
#> GSM425930 3 0.6140 0.5876 0.404 0.000 0.596
#> GSM425931 3 0.6140 0.5876 0.404 0.000 0.596
#> GSM425932 3 0.6140 0.5876 0.404 0.000 0.596
#> GSM425933 3 0.6140 0.5876 0.404 0.000 0.596
#> GSM425934 3 0.6140 0.5876 0.404 0.000 0.596
#> GSM425935 3 0.6140 0.5876 0.404 0.000 0.596
#> GSM425936 3 0.6140 0.5876 0.404 0.000 0.596
#> GSM425937 3 0.6140 0.5876 0.404 0.000 0.596
#> GSM425938 3 0.6140 0.5876 0.404 0.000 0.596
#> GSM425939 3 0.6140 0.5876 0.404 0.000 0.596
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.3626 0.4285 0.184 0.812 0.000 0.004
#> GSM425908 2 0.4741 0.1427 0.328 0.668 0.000 0.004
#> GSM425909 4 0.4997 0.7467 0.104 0.012 0.092 0.792
#> GSM425910 1 0.6538 0.3879 0.640 0.276 0.036 0.048
#> GSM425911 1 0.5503 0.2027 0.516 0.468 0.000 0.016
#> GSM425912 1 0.4994 0.1910 0.520 0.480 0.000 0.000
#> GSM425913 2 0.0895 0.5291 0.004 0.976 0.020 0.000
#> GSM425914 1 0.5161 0.1915 0.520 0.476 0.000 0.004
#> GSM425915 3 0.4836 0.5085 0.000 0.008 0.672 0.320
#> GSM425874 2 0.5807 0.2555 0.364 0.596 0.000 0.040
#> GSM425875 1 0.6100 0.3574 0.624 0.072 0.000 0.304
#> GSM425876 1 0.6688 0.2947 0.536 0.368 0.000 0.096
#> GSM425877 1 0.8354 0.1965 0.544 0.076 0.192 0.188
#> GSM425878 1 0.6723 0.3951 0.600 0.260 0.000 0.140
#> GSM425879 1 0.5163 0.1880 0.516 0.480 0.000 0.004
#> GSM425880 4 0.1624 0.7784 0.028 0.000 0.020 0.952
#> GSM425881 1 0.5161 0.1915 0.520 0.476 0.000 0.004
#> GSM425882 2 0.5151 -0.1137 0.464 0.532 0.000 0.004
#> GSM425883 1 0.5488 0.3134 0.636 0.340 0.012 0.012
#> GSM425884 1 0.6379 0.3974 0.668 0.076 0.020 0.236
#> GSM425885 2 0.4767 0.3569 0.256 0.724 0.000 0.020
#> GSM425848 1 0.5256 0.2880 0.700 0.040 0.000 0.260
#> GSM425849 1 0.5690 0.4095 0.716 0.116 0.000 0.168
#> GSM425850 1 0.6924 0.3551 0.536 0.340 0.000 0.124
#> GSM425851 2 0.9420 0.0152 0.272 0.408 0.168 0.152
#> GSM425852 3 0.5901 0.5775 0.084 0.004 0.692 0.220
#> GSM425893 1 0.7420 0.2565 0.480 0.364 0.004 0.152
#> GSM425894 2 0.4730 0.1811 0.364 0.636 0.000 0.000
#> GSM425895 2 0.4730 0.0993 0.364 0.636 0.000 0.000
#> GSM425896 1 0.6443 0.1848 0.472 0.468 0.004 0.056
#> GSM425897 2 0.5375 -0.0218 0.416 0.572 0.004 0.008
#> GSM425898 2 0.3495 0.4968 0.140 0.844 0.016 0.000
#> GSM425899 2 0.6078 0.4483 0.168 0.724 0.036 0.072
#> GSM425900 2 0.7636 0.0787 0.268 0.500 0.228 0.004
#> GSM425901 4 0.2685 0.7868 0.040 0.004 0.044 0.912
#> GSM425902 1 0.6847 -0.0987 0.500 0.428 0.036 0.036
#> GSM425903 4 0.4932 0.7497 0.128 0.012 0.068 0.792
#> GSM425904 4 0.1256 0.7760 0.028 0.000 0.008 0.964
#> GSM425905 2 0.2944 0.5098 0.128 0.868 0.000 0.004
#> GSM425906 2 0.2714 0.5188 0.112 0.884 0.004 0.000
#> GSM425863 1 0.7049 0.2585 0.548 0.300 0.000 0.152
#> GSM425864 2 0.3870 0.4030 0.208 0.788 0.000 0.004
#> GSM425865 2 0.2266 0.5131 0.084 0.912 0.000 0.004
#> GSM425866 4 0.2530 0.7045 0.112 0.000 0.000 0.888
#> GSM425867 3 0.2149 0.7771 0.000 0.000 0.912 0.088
#> GSM425868 2 0.1661 0.5147 0.052 0.944 0.000 0.004
#> GSM425869 2 0.2944 0.5255 0.128 0.868 0.004 0.000
#> GSM425870 3 0.8403 0.3042 0.128 0.224 0.544 0.104
#> GSM425871 2 0.7113 0.0429 0.276 0.552 0.000 0.172
#> GSM425872 2 0.0524 0.5323 0.000 0.988 0.004 0.008
#> GSM425873 1 0.5632 0.3556 0.624 0.340 0.000 0.036
#> GSM425843 1 0.6907 0.4130 0.644 0.144 0.020 0.192
#> GSM425844 1 0.6475 0.3906 0.644 0.184 0.000 0.172
#> GSM425845 1 0.7423 0.2724 0.476 0.344 0.000 0.180
#> GSM425846 2 0.2255 0.5280 0.068 0.920 0.000 0.012
#> GSM425847 2 0.4643 0.2192 0.344 0.656 0.000 0.000
#> GSM425886 4 0.5297 0.7547 0.108 0.044 0.060 0.788
#> GSM425887 1 0.5168 0.1646 0.504 0.492 0.000 0.004
#> GSM425888 2 0.3583 0.4580 0.180 0.816 0.000 0.004
#> GSM425889 1 0.6983 0.1540 0.616 0.036 0.272 0.076
#> GSM425890 2 0.5673 0.2516 0.372 0.596 0.000 0.032
#> GSM425891 2 0.2412 0.5269 0.084 0.908 0.008 0.000
#> GSM425892 2 0.0188 0.5313 0.000 0.996 0.000 0.004
#> GSM425853 2 0.7146 0.1030 0.228 0.560 0.000 0.212
#> GSM425854 2 0.4661 0.2249 0.348 0.652 0.000 0.000
#> GSM425855 1 0.6461 -0.1448 0.544 0.036 0.400 0.020
#> GSM425856 4 0.7179 0.1314 0.140 0.380 0.000 0.480
#> GSM425857 4 0.5138 0.7185 0.020 0.132 0.064 0.784
#> GSM425858 2 0.4543 0.2456 0.324 0.676 0.000 0.000
#> GSM425859 2 0.2714 0.4926 0.112 0.884 0.000 0.004
#> GSM425860 3 0.4360 0.5557 0.008 0.248 0.744 0.000
#> GSM425861 1 0.5399 0.2052 0.520 0.468 0.000 0.012
#> GSM425862 1 0.6065 0.1656 0.644 0.276 0.000 0.080
#> GSM425837 1 0.7215 0.3735 0.592 0.168 0.012 0.228
#> GSM425838 1 0.5792 0.2081 0.648 0.296 0.000 0.056
#> GSM425839 2 0.0188 0.5313 0.000 0.996 0.000 0.004
#> GSM425840 3 0.6744 0.4504 0.312 0.012 0.592 0.084
#> GSM425841 1 0.7356 -0.0783 0.468 0.368 0.000 0.164
#> GSM425842 1 0.5592 0.3819 0.656 0.300 0.000 0.044
#> GSM425917 3 0.1305 0.8128 0.036 0.004 0.960 0.000
#> GSM425922 2 0.5630 0.2625 0.360 0.608 0.000 0.032
#> GSM425919 3 0.3697 0.7329 0.048 0.100 0.852 0.000
#> GSM425920 3 0.9209 0.2563 0.220 0.164 0.460 0.156
#> GSM425923 1 0.6983 0.2846 0.656 0.128 0.036 0.180
#> GSM425916 3 0.7108 0.3281 0.348 0.000 0.512 0.140
#> GSM425918 2 0.7443 -0.0562 0.392 0.436 0.000 0.172
#> GSM425921 2 0.7113 0.1176 0.448 0.456 0.016 0.080
#> GSM425925 1 0.2300 0.3732 0.924 0.028 0.000 0.048
#> GSM425926 2 0.6265 0.1671 0.444 0.500 0.000 0.056
#> GSM425927 1 0.7524 0.2997 0.496 0.384 0.036 0.084
#> GSM425924 3 0.0707 0.8196 0.000 0.020 0.980 0.000
#> GSM425928 3 0.0000 0.8308 0.000 0.000 1.000 0.000
#> GSM425929 3 0.0000 0.8308 0.000 0.000 1.000 0.000
#> GSM425930 3 0.0000 0.8308 0.000 0.000 1.000 0.000
#> GSM425931 3 0.0000 0.8308 0.000 0.000 1.000 0.000
#> GSM425932 3 0.0000 0.8308 0.000 0.000 1.000 0.000
#> GSM425933 3 0.0000 0.8308 0.000 0.000 1.000 0.000
#> GSM425934 3 0.0000 0.8308 0.000 0.000 1.000 0.000
#> GSM425935 3 0.0000 0.8308 0.000 0.000 1.000 0.000
#> GSM425936 3 0.0000 0.8308 0.000 0.000 1.000 0.000
#> GSM425937 3 0.0000 0.8308 0.000 0.000 1.000 0.000
#> GSM425938 3 0.0000 0.8308 0.000 0.000 1.000 0.000
#> GSM425939 3 0.0000 0.8308 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
#> GSM425907 2 0.3814 0.407700 0.276 0.720 0.000 0.004 0.000
#> GSM425908 2 0.4817 -0.000535 0.404 0.572 0.000 0.024 0.000
#> GSM425909 5 0.0451 0.927938 0.004 0.000 0.008 0.000 0.988
#> GSM425910 1 0.2770 0.494011 0.864 0.124 0.008 0.000 0.004
#> GSM425911 1 0.4726 0.324403 0.580 0.400 0.000 0.000 0.020
#> GSM425912 1 0.4227 0.305026 0.580 0.420 0.000 0.000 0.000
#> GSM425913 2 0.0324 0.620531 0.004 0.992 0.000 0.004 0.000
#> GSM425914 1 0.4210 0.307999 0.588 0.412 0.000 0.000 0.000
#> GSM425915 3 0.4171 0.392910 0.000 0.000 0.604 0.000 0.396
#> GSM425874 4 0.3878 0.617021 0.016 0.236 0.000 0.748 0.000
#> GSM425875 1 0.3387 0.412658 0.852 0.020 0.000 0.028 0.100
#> GSM425876 1 0.5426 0.393469 0.608 0.308 0.000 0.000 0.084
#> GSM425877 4 0.7394 0.233099 0.380 0.020 0.184 0.400 0.016
#> GSM425878 1 0.3827 0.411456 0.816 0.068 0.000 0.112 0.004
#> GSM425879 1 0.4242 0.296989 0.572 0.428 0.000 0.000 0.000
#> GSM425880 5 0.0324 0.929980 0.004 0.000 0.004 0.000 0.992
#> GSM425881 1 0.4192 0.309831 0.596 0.404 0.000 0.000 0.000
#> GSM425882 1 0.4437 0.194981 0.532 0.464 0.000 0.004 0.000
#> GSM425883 1 0.5450 0.401252 0.660 0.252 0.016 0.072 0.000
#> GSM425884 1 0.4468 0.229951 0.748 0.004 0.012 0.208 0.028
#> GSM425885 2 0.4887 0.058800 0.048 0.692 0.000 0.252 0.008
#> GSM425848 1 0.5915 -0.221088 0.484 0.000 0.000 0.412 0.104
#> GSM425849 1 0.2964 0.330848 0.840 0.004 0.000 0.152 0.004
#> GSM425850 1 0.4953 0.464380 0.712 0.196 0.000 0.088 0.004
#> GSM425851 2 0.8433 -0.355098 0.320 0.324 0.116 0.232 0.008
#> GSM425852 3 0.5844 0.529815 0.244 0.000 0.636 0.020 0.100
#> GSM425893 1 0.6371 0.343175 0.516 0.268 0.000 0.000 0.216
#> GSM425894 2 0.4321 0.214316 0.396 0.600 0.000 0.004 0.000
#> GSM425895 2 0.4446 0.123811 0.400 0.592 0.000 0.008 0.000
#> GSM425896 1 0.5657 0.313636 0.544 0.380 0.004 0.000 0.072
#> GSM425897 1 0.4452 0.128806 0.500 0.496 0.000 0.000 0.004
#> GSM425898 2 0.2646 0.605393 0.124 0.868 0.004 0.004 0.000
#> GSM425899 2 0.4836 0.556003 0.076 0.756 0.016 0.148 0.004
#> GSM425900 2 0.6465 0.122051 0.288 0.492 0.220 0.000 0.000
#> GSM425901 5 0.0000 0.930839 0.000 0.000 0.000 0.000 1.000
#> GSM425902 4 0.5786 0.616424 0.148 0.204 0.008 0.640 0.000
#> GSM425903 5 0.0404 0.927237 0.012 0.000 0.000 0.000 0.988
#> GSM425904 5 0.0000 0.930839 0.000 0.000 0.000 0.000 1.000
#> GSM425905 2 0.2280 0.609201 0.120 0.880 0.000 0.000 0.000
#> GSM425906 2 0.1908 0.619029 0.092 0.908 0.000 0.000 0.000
#> GSM425863 1 0.6465 0.210473 0.576 0.220 0.000 0.184 0.020
#> GSM425864 2 0.3752 0.385873 0.292 0.708 0.000 0.000 0.000
#> GSM425865 2 0.2536 0.583263 0.128 0.868 0.000 0.004 0.000
#> GSM425866 5 0.4967 0.521890 0.192 0.000 0.000 0.104 0.704
#> GSM425867 3 0.2179 0.738444 0.000 0.000 0.888 0.000 0.112
#> GSM425868 2 0.1753 0.596579 0.032 0.936 0.000 0.032 0.000
#> GSM425869 2 0.2673 0.621761 0.060 0.892 0.004 0.044 0.000
#> GSM425870 3 0.7569 0.304947 0.140 0.212 0.512 0.000 0.136
#> GSM425871 1 0.6243 -0.049614 0.520 0.348 0.000 0.124 0.008
#> GSM425872 2 0.0740 0.618215 0.004 0.980 0.000 0.008 0.008
#> GSM425873 1 0.3366 0.473339 0.784 0.212 0.000 0.000 0.004
#> GSM425843 1 0.4192 0.249197 0.764 0.012 0.008 0.204 0.012
#> GSM425844 1 0.4929 0.037865 0.648 0.032 0.000 0.312 0.008
#> GSM425845 1 0.6388 0.345893 0.508 0.284 0.000 0.000 0.208
#> GSM425846 2 0.1770 0.626324 0.048 0.936 0.000 0.008 0.008
#> GSM425847 2 0.4074 0.272509 0.364 0.636 0.000 0.000 0.000
#> GSM425886 5 0.0404 0.927448 0.012 0.000 0.000 0.000 0.988
#> GSM425887 1 0.4262 0.272636 0.560 0.440 0.000 0.000 0.000
#> GSM425888 2 0.2719 0.585808 0.144 0.852 0.000 0.000 0.004
#> GSM425889 1 0.6836 -0.207712 0.460 0.008 0.272 0.260 0.000
#> GSM425890 4 0.5542 0.460494 0.072 0.396 0.000 0.532 0.000
#> GSM425891 2 0.1697 0.626997 0.060 0.932 0.008 0.000 0.000
#> GSM425892 2 0.0693 0.614669 0.012 0.980 0.000 0.008 0.000
#> GSM425853 2 0.6795 -0.014564 0.388 0.452 0.000 0.132 0.028
#> GSM425854 2 0.4126 0.250750 0.380 0.620 0.000 0.000 0.000
#> GSM425855 3 0.7193 -0.074844 0.312 0.016 0.376 0.296 0.000
#> GSM425856 2 0.7975 -0.158011 0.320 0.396 0.000 0.124 0.160
#> GSM425857 5 0.0833 0.917715 0.004 0.016 0.000 0.004 0.976
#> GSM425858 2 0.4182 0.292242 0.352 0.644 0.000 0.004 0.000
#> GSM425859 2 0.3171 0.541883 0.176 0.816 0.000 0.008 0.000
#> GSM425860 3 0.3885 0.518878 0.008 0.268 0.724 0.000 0.000
#> GSM425861 1 0.4367 0.309047 0.580 0.416 0.000 0.000 0.004
#> GSM425862 4 0.6646 0.442652 0.356 0.196 0.000 0.444 0.004
#> GSM425837 1 0.5102 0.180082 0.724 0.048 0.004 0.196 0.028
#> GSM425838 4 0.6434 0.517279 0.368 0.180 0.000 0.452 0.000
#> GSM425839 2 0.0290 0.617841 0.000 0.992 0.000 0.008 0.000
#> GSM425840 3 0.5938 0.434676 0.304 0.004 0.584 0.104 0.004
#> GSM425841 4 0.3214 0.610997 0.036 0.120 0.000 0.844 0.000
#> GSM425842 1 0.2127 0.493141 0.892 0.108 0.000 0.000 0.000
#> GSM425917 3 0.2103 0.767068 0.020 0.004 0.920 0.056 0.000
#> GSM425922 4 0.2629 0.609520 0.004 0.136 0.000 0.860 0.000
#> GSM425919 3 0.3387 0.712507 0.028 0.100 0.852 0.020 0.000
#> GSM425920 3 0.8485 -0.018643 0.208 0.136 0.344 0.304 0.008
#> GSM425923 4 0.6191 0.330209 0.360 0.044 0.032 0.552 0.012
#> GSM425916 3 0.6959 -0.019973 0.336 0.000 0.340 0.320 0.004
#> GSM425918 4 0.7005 0.142323 0.232 0.372 0.000 0.384 0.012
#> GSM425921 4 0.2020 0.608441 0.000 0.100 0.000 0.900 0.000
#> GSM425925 4 0.4009 0.498147 0.312 0.004 0.000 0.684 0.000
#> GSM425926 4 0.4302 0.628605 0.048 0.208 0.000 0.744 0.000
#> GSM425927 1 0.6233 0.383139 0.592 0.308 0.032 0.052 0.016
#> GSM425924 3 0.1267 0.784693 0.004 0.024 0.960 0.012 0.000
#> GSM425928 3 0.0000 0.798995 0.000 0.000 1.000 0.000 0.000
#> GSM425929 3 0.0000 0.798995 0.000 0.000 1.000 0.000 0.000
#> GSM425930 3 0.0000 0.798995 0.000 0.000 1.000 0.000 0.000
#> GSM425931 3 0.0000 0.798995 0.000 0.000 1.000 0.000 0.000
#> GSM425932 3 0.0000 0.798995 0.000 0.000 1.000 0.000 0.000
#> GSM425933 3 0.0000 0.798995 0.000 0.000 1.000 0.000 0.000
#> GSM425934 3 0.0000 0.798995 0.000 0.000 1.000 0.000 0.000
#> GSM425935 3 0.0000 0.798995 0.000 0.000 1.000 0.000 0.000
#> GSM425936 3 0.0000 0.798995 0.000 0.000 1.000 0.000 0.000
#> GSM425937 3 0.0000 0.798995 0.000 0.000 1.000 0.000 0.000
#> GSM425938 3 0.0000 0.798995 0.000 0.000 1.000 0.000 0.000
#> GSM425939 3 0.0000 0.798995 0.000 0.000 1.000 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 6 0.4305 0.1356 0.000 0.436 0.000 0.020 0.000 0.544
#> GSM425908 6 0.4067 0.5364 0.000 0.260 0.000 0.040 0.000 0.700
#> GSM425909 5 0.0000 0.9205 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM425910 6 0.3821 0.5348 0.148 0.080 0.000 0.000 0.000 0.772
#> GSM425911 6 0.3109 0.6306 0.000 0.224 0.000 0.000 0.004 0.772
#> GSM425912 6 0.3620 0.5708 0.000 0.352 0.000 0.000 0.000 0.648
#> GSM425913 2 0.0260 0.7304 0.000 0.992 0.000 0.000 0.000 0.008
#> GSM425914 6 0.3221 0.6273 0.000 0.264 0.000 0.000 0.000 0.736
#> GSM425915 3 0.3890 0.4097 0.000 0.000 0.596 0.000 0.400 0.004
#> GSM425874 4 0.0603 0.7287 0.004 0.016 0.000 0.980 0.000 0.000
#> GSM425875 6 0.4668 0.2173 0.236 0.000 0.000 0.012 0.068 0.684
#> GSM425876 6 0.4484 0.6278 0.012 0.252 0.000 0.000 0.048 0.688
#> GSM425877 1 0.6967 0.4307 0.520 0.008 0.132 0.172 0.000 0.168
#> GSM425878 6 0.4666 0.0124 0.388 0.048 0.000 0.000 0.000 0.564
#> GSM425879 6 0.3482 0.5920 0.000 0.316 0.000 0.000 0.000 0.684
#> GSM425880 5 0.0858 0.9084 0.004 0.000 0.000 0.000 0.968 0.028
#> GSM425881 6 0.2854 0.6363 0.000 0.208 0.000 0.000 0.000 0.792
#> GSM425882 6 0.3452 0.5937 0.004 0.256 0.000 0.004 0.000 0.736
#> GSM425883 6 0.3340 0.6128 0.012 0.084 0.004 0.060 0.000 0.840
#> GSM425884 1 0.4323 0.5018 0.600 0.000 0.004 0.020 0.000 0.376
#> GSM425885 2 0.5567 0.3057 0.004 0.600 0.000 0.228 0.008 0.160
#> GSM425848 1 0.6856 0.3292 0.372 0.000 0.000 0.260 0.048 0.320
#> GSM425849 6 0.4957 -0.2435 0.412 0.000 0.000 0.068 0.000 0.520
#> GSM425850 6 0.5767 0.1745 0.376 0.176 0.000 0.000 0.000 0.448
#> GSM425851 1 0.4300 0.4854 0.780 0.132 0.024 0.036 0.000 0.028
#> GSM425852 3 0.5832 0.4426 0.208 0.000 0.620 0.000 0.084 0.088
#> GSM425893 6 0.5237 0.5510 0.000 0.172 0.000 0.000 0.220 0.608
#> GSM425894 2 0.3717 0.1779 0.000 0.616 0.000 0.000 0.000 0.384
#> GSM425895 2 0.3851 -0.0143 0.000 0.540 0.000 0.000 0.000 0.460
#> GSM425896 6 0.3549 0.6210 0.000 0.192 0.000 0.004 0.028 0.776
#> GSM425897 6 0.3608 0.5742 0.000 0.272 0.000 0.012 0.000 0.716
#> GSM425898 2 0.1410 0.7306 0.000 0.944 0.008 0.004 0.000 0.044
#> GSM425899 2 0.3025 0.6794 0.016 0.844 0.000 0.120 0.000 0.020
#> GSM425900 6 0.5903 0.1410 0.000 0.364 0.208 0.000 0.000 0.428
#> GSM425901 5 0.0000 0.9205 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM425902 4 0.3704 0.6761 0.040 0.072 0.000 0.820 0.000 0.068
#> GSM425903 5 0.0146 0.9182 0.000 0.000 0.000 0.000 0.996 0.004
#> GSM425904 5 0.0692 0.9124 0.004 0.000 0.000 0.000 0.976 0.020
#> GSM425905 2 0.2632 0.6893 0.000 0.832 0.000 0.004 0.000 0.164
#> GSM425906 2 0.0937 0.7284 0.000 0.960 0.000 0.000 0.000 0.040
#> GSM425863 1 0.7245 0.2801 0.364 0.196 0.000 0.112 0.000 0.328
#> GSM425864 6 0.4161 0.1187 0.000 0.448 0.000 0.012 0.000 0.540
#> GSM425865 2 0.4049 0.4644 0.000 0.648 0.000 0.020 0.000 0.332
#> GSM425866 5 0.4619 0.2750 0.348 0.000 0.000 0.000 0.600 0.052
#> GSM425867 3 0.1957 0.7692 0.000 0.000 0.888 0.000 0.112 0.000
#> GSM425868 2 0.3494 0.6289 0.004 0.792 0.000 0.036 0.000 0.168
#> GSM425869 2 0.1682 0.7244 0.000 0.928 0.000 0.052 0.000 0.020
#> GSM425870 3 0.6854 0.2771 0.000 0.192 0.504 0.000 0.120 0.184
#> GSM425871 1 0.4943 0.5398 0.704 0.128 0.000 0.028 0.000 0.140
#> GSM425872 2 0.0436 0.7278 0.000 0.988 0.000 0.004 0.004 0.004
#> GSM425873 6 0.4626 0.6187 0.136 0.172 0.000 0.000 0.000 0.692
#> GSM425843 1 0.3833 0.5146 0.648 0.000 0.000 0.008 0.000 0.344
#> GSM425844 1 0.2959 0.5216 0.844 0.008 0.000 0.024 0.000 0.124
#> GSM425845 6 0.5539 0.5281 0.000 0.260 0.000 0.000 0.188 0.552
#> GSM425846 2 0.0858 0.7317 0.000 0.968 0.000 0.004 0.000 0.028
#> GSM425847 2 0.3659 0.1926 0.000 0.636 0.000 0.000 0.000 0.364
#> GSM425886 5 0.0146 0.9182 0.000 0.000 0.000 0.000 0.996 0.004
#> GSM425887 6 0.3747 0.5111 0.000 0.396 0.000 0.000 0.000 0.604
#> GSM425888 2 0.1267 0.7181 0.000 0.940 0.000 0.000 0.000 0.060
#> GSM425889 1 0.7677 0.3161 0.340 0.004 0.216 0.172 0.000 0.268
#> GSM425890 4 0.7196 0.2368 0.208 0.320 0.000 0.372 0.000 0.100
#> GSM425891 2 0.0692 0.7318 0.000 0.976 0.004 0.000 0.000 0.020
#> GSM425892 2 0.2094 0.6962 0.000 0.900 0.000 0.020 0.000 0.080
#> GSM425853 1 0.5513 0.4814 0.548 0.324 0.000 0.000 0.008 0.120
#> GSM425854 2 0.3765 0.0817 0.000 0.596 0.000 0.000 0.000 0.404
#> GSM425855 3 0.7217 -0.0205 0.092 0.000 0.372 0.268 0.000 0.268
#> GSM425856 1 0.6384 0.4698 0.528 0.272 0.000 0.000 0.072 0.128
#> GSM425857 5 0.0000 0.9205 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM425858 2 0.3409 0.3782 0.000 0.700 0.000 0.000 0.000 0.300
#> GSM425859 2 0.4209 0.3602 0.000 0.596 0.000 0.020 0.000 0.384
#> GSM425860 3 0.3586 0.5382 0.000 0.268 0.720 0.000 0.000 0.012
#> GSM425861 6 0.3515 0.5916 0.000 0.324 0.000 0.000 0.000 0.676
#> GSM425862 4 0.6897 0.0564 0.276 0.064 0.000 0.424 0.000 0.236
#> GSM425837 1 0.4720 0.5415 0.640 0.012 0.000 0.048 0.000 0.300
#> GSM425838 4 0.6206 0.2958 0.216 0.056 0.000 0.564 0.000 0.164
#> GSM425839 2 0.1686 0.7123 0.000 0.924 0.000 0.012 0.000 0.064
#> GSM425840 3 0.5964 0.2760 0.300 0.004 0.556 0.040 0.000 0.100
#> GSM425841 4 0.1088 0.7242 0.016 0.024 0.000 0.960 0.000 0.000
#> GSM425842 6 0.3982 0.4437 0.200 0.060 0.000 0.000 0.000 0.740
#> GSM425917 3 0.3538 0.6763 0.216 0.004 0.764 0.012 0.000 0.004
#> GSM425922 4 0.2584 0.6849 0.144 0.004 0.000 0.848 0.000 0.004
#> GSM425919 3 0.4630 0.6554 0.192 0.064 0.720 0.004 0.000 0.020
#> GSM425920 1 0.5345 0.3877 0.688 0.076 0.176 0.048 0.000 0.012
#> GSM425923 1 0.4216 0.2073 0.676 0.004 0.000 0.288 0.000 0.032
#> GSM425916 1 0.5277 0.3947 0.664 0.000 0.212 0.060 0.000 0.064
#> GSM425918 1 0.4907 0.4053 0.668 0.228 0.000 0.092 0.000 0.012
#> GSM425921 4 0.2053 0.7028 0.108 0.000 0.000 0.888 0.000 0.004
#> GSM425925 4 0.2867 0.6763 0.040 0.000 0.000 0.848 0.000 0.112
#> GSM425926 4 0.0862 0.7280 0.008 0.016 0.000 0.972 0.000 0.004
#> GSM425927 1 0.6463 -0.2063 0.380 0.220 0.024 0.000 0.000 0.376
#> GSM425924 3 0.1788 0.7977 0.040 0.028 0.928 0.004 0.000 0.000
#> GSM425928 3 0.0000 0.8276 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425929 3 0.0000 0.8276 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425930 3 0.0000 0.8276 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425931 3 0.0000 0.8276 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425932 3 0.0000 0.8276 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425933 3 0.0000 0.8276 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425934 3 0.0000 0.8276 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425935 3 0.0000 0.8276 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425936 3 0.0000 0.8276 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425937 3 0.0000 0.8276 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425938 3 0.0000 0.8276 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425939 3 0.0000 0.8276 0.000 0.000 1.000 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 disease.state(p) tissue(p) other(p) k
#> CV:pam 97 8.07e-09 5.07e-10 4.14e-07 2
#> CV:pam 52 2.39e-08 1.24e-09 5.65e-05 3
#> CV:pam 38 1.55e-04 5.56e-05 1.20e-02 4
#> CV:pam 48 6.91e-06 5.60e-07 4.31e-04 5
#> CV:pam 66 5.18e-08 9.66e-11 5.33e-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["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 103 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 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 0.293 0.673 0.823 0.3862 0.696 0.696
#> 3 3 0.724 0.787 0.909 0.6391 0.657 0.512
#> 4 4 0.770 0.744 0.880 0.0918 0.943 0.847
#> 5 5 0.752 0.664 0.817 0.1008 0.874 0.627
#> 6 6 0.707 0.567 0.755 0.0413 0.939 0.760
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
#> GSM425907 1 0.9044 0.685 0.680 0.320
#> GSM425908 1 0.9044 0.685 0.680 0.320
#> GSM425909 2 0.9393 0.652 0.356 0.644
#> GSM425910 1 0.2236 0.758 0.964 0.036
#> GSM425911 1 0.9044 0.685 0.680 0.320
#> GSM425912 1 0.9044 0.685 0.680 0.320
#> GSM425913 1 0.9044 0.685 0.680 0.320
#> GSM425914 1 0.9044 0.685 0.680 0.320
#> GSM425915 2 0.6973 0.873 0.188 0.812
#> GSM425874 1 0.0938 0.753 0.988 0.012
#> GSM425875 1 0.9209 0.108 0.664 0.336
#> GSM425876 1 0.2043 0.759 0.968 0.032
#> GSM425877 1 0.0000 0.759 1.000 0.000
#> GSM425878 1 0.0000 0.759 1.000 0.000
#> GSM425879 1 0.9044 0.685 0.680 0.320
#> GSM425880 1 0.9209 0.108 0.664 0.336
#> GSM425881 1 0.9044 0.685 0.680 0.320
#> GSM425882 1 0.9044 0.685 0.680 0.320
#> GSM425883 1 0.1414 0.760 0.980 0.020
#> GSM425884 1 0.0000 0.759 1.000 0.000
#> GSM425885 1 0.1184 0.759 0.984 0.016
#> GSM425848 1 0.0000 0.759 1.000 0.000
#> GSM425849 1 0.0000 0.759 1.000 0.000
#> GSM425850 1 0.1843 0.760 0.972 0.028
#> GSM425851 1 0.0000 0.759 1.000 0.000
#> GSM425852 1 0.9732 -0.167 0.596 0.404
#> GSM425893 1 0.9710 0.593 0.600 0.400
#> GSM425894 1 0.9044 0.685 0.680 0.320
#> GSM425895 1 0.9044 0.685 0.680 0.320
#> GSM425896 1 0.9460 0.641 0.636 0.364
#> GSM425897 1 0.9044 0.685 0.680 0.320
#> GSM425898 1 0.9044 0.685 0.680 0.320
#> GSM425899 1 0.2236 0.759 0.964 0.036
#> GSM425900 1 0.9044 0.685 0.680 0.320
#> GSM425901 2 0.9833 0.535 0.424 0.576
#> GSM425902 1 0.0000 0.759 1.000 0.000
#> GSM425903 2 0.8443 0.770 0.272 0.728
#> GSM425904 1 0.9286 0.077 0.656 0.344
#> GSM425905 1 0.9044 0.685 0.680 0.320
#> GSM425906 1 0.9044 0.685 0.680 0.320
#> GSM425863 1 0.0000 0.759 1.000 0.000
#> GSM425864 1 0.9044 0.685 0.680 0.320
#> GSM425865 1 0.9044 0.685 0.680 0.320
#> GSM425866 1 0.9209 0.108 0.664 0.336
#> GSM425867 2 0.6438 0.892 0.164 0.836
#> GSM425868 1 0.8661 0.698 0.712 0.288
#> GSM425869 1 0.9044 0.685 0.680 0.320
#> GSM425870 2 0.9710 0.330 0.400 0.600
#> GSM425871 1 0.0376 0.760 0.996 0.004
#> GSM425872 1 0.9044 0.685 0.680 0.320
#> GSM425873 1 0.1843 0.760 0.972 0.028
#> GSM425843 1 0.0000 0.759 1.000 0.000
#> GSM425844 1 0.0000 0.759 1.000 0.000
#> GSM425845 1 0.9460 0.109 0.636 0.364
#> GSM425846 1 0.8555 0.700 0.720 0.280
#> GSM425847 1 0.3584 0.755 0.932 0.068
#> GSM425886 2 0.8386 0.783 0.268 0.732
#> GSM425887 1 0.8327 0.699 0.736 0.264
#> GSM425888 1 0.8661 0.698 0.712 0.288
#> GSM425889 1 0.0000 0.759 1.000 0.000
#> GSM425890 1 0.0000 0.759 1.000 0.000
#> GSM425891 1 0.9044 0.685 0.680 0.320
#> GSM425892 1 0.9044 0.685 0.680 0.320
#> GSM425853 1 0.3274 0.705 0.940 0.060
#> GSM425854 1 0.9044 0.685 0.680 0.320
#> GSM425855 1 0.0000 0.759 1.000 0.000
#> GSM425856 1 0.9209 0.108 0.664 0.336
#> GSM425857 1 0.9209 0.108 0.664 0.336
#> GSM425858 1 0.9044 0.685 0.680 0.320
#> GSM425859 1 0.9044 0.685 0.680 0.320
#> GSM425860 1 0.6887 0.700 0.816 0.184
#> GSM425861 1 0.3274 0.757 0.940 0.060
#> GSM425862 1 0.0000 0.759 1.000 0.000
#> GSM425837 1 0.0376 0.757 0.996 0.004
#> GSM425838 1 0.0000 0.759 1.000 0.000
#> GSM425839 1 0.9044 0.685 0.680 0.320
#> GSM425840 1 0.0000 0.759 1.000 0.000
#> GSM425841 1 0.0376 0.758 0.996 0.004
#> GSM425842 1 0.1184 0.760 0.984 0.016
#> GSM425917 1 0.9933 -0.257 0.548 0.452
#> GSM425922 1 0.0376 0.758 0.996 0.004
#> GSM425919 1 0.0672 0.755 0.992 0.008
#> GSM425920 1 0.0000 0.759 1.000 0.000
#> GSM425923 1 0.0000 0.759 1.000 0.000
#> GSM425916 1 0.0000 0.759 1.000 0.000
#> GSM425918 1 0.0000 0.759 1.000 0.000
#> GSM425921 1 0.0672 0.755 0.992 0.008
#> GSM425925 1 0.0672 0.755 0.992 0.008
#> GSM425926 1 0.0938 0.753 0.988 0.012
#> GSM425927 1 0.0376 0.760 0.996 0.004
#> GSM425924 1 0.9850 -0.216 0.572 0.428
#> GSM425928 2 0.5737 0.905 0.136 0.864
#> GSM425929 2 0.5737 0.905 0.136 0.864
#> GSM425930 2 0.5737 0.905 0.136 0.864
#> GSM425931 2 0.5737 0.905 0.136 0.864
#> GSM425932 2 0.5737 0.905 0.136 0.864
#> GSM425933 2 0.5737 0.905 0.136 0.864
#> GSM425934 2 0.5737 0.905 0.136 0.864
#> GSM425935 2 0.6531 0.890 0.168 0.832
#> GSM425936 2 0.5737 0.905 0.136 0.864
#> GSM425937 2 0.5737 0.905 0.136 0.864
#> GSM425938 2 0.5737 0.905 0.136 0.864
#> GSM425939 2 0.5737 0.905 0.136 0.864
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425908 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425909 3 0.7329 0.1306 0.424 0.032 0.544
#> GSM425910 2 0.7339 0.3192 0.392 0.572 0.036
#> GSM425911 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425912 2 0.0424 0.9033 0.008 0.992 0.000
#> GSM425913 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425914 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425915 3 0.3310 0.8530 0.028 0.064 0.908
#> GSM425874 1 0.0237 0.8787 0.996 0.004 0.000
#> GSM425875 1 0.5982 0.5473 0.668 0.004 0.328
#> GSM425876 2 0.7069 0.0850 0.472 0.508 0.020
#> GSM425877 1 0.0424 0.8806 0.992 0.008 0.000
#> GSM425878 1 0.0424 0.8806 0.992 0.008 0.000
#> GSM425879 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425880 1 0.6008 0.5399 0.664 0.004 0.332
#> GSM425881 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425882 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425883 1 0.0592 0.8789 0.988 0.012 0.000
#> GSM425884 1 0.0661 0.8795 0.988 0.008 0.004
#> GSM425885 1 0.4164 0.7441 0.848 0.144 0.008
#> GSM425848 1 0.0424 0.8806 0.992 0.008 0.000
#> GSM425849 1 0.0424 0.8806 0.992 0.008 0.000
#> GSM425850 1 0.4399 0.6939 0.812 0.188 0.000
#> GSM425851 1 0.0829 0.8760 0.984 0.004 0.012
#> GSM425852 1 0.5982 0.5473 0.668 0.004 0.328
#> GSM425893 2 0.4063 0.7938 0.020 0.868 0.112
#> GSM425894 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425895 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425896 2 0.3752 0.8121 0.020 0.884 0.096
#> GSM425897 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425898 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425899 2 0.6309 0.0227 0.496 0.504 0.000
#> GSM425900 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425901 3 0.7049 0.0425 0.452 0.020 0.528
#> GSM425902 1 0.0424 0.8806 0.992 0.008 0.000
#> GSM425903 3 0.6843 0.4340 0.028 0.332 0.640
#> GSM425904 1 0.6008 0.5399 0.664 0.004 0.332
#> GSM425905 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425906 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425863 1 0.0424 0.8806 0.992 0.008 0.000
#> GSM425864 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425865 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425866 1 0.5982 0.5473 0.668 0.004 0.328
#> GSM425867 3 0.1525 0.8855 0.032 0.004 0.964
#> GSM425868 2 0.3116 0.8307 0.108 0.892 0.000
#> GSM425869 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425870 2 0.6796 0.3761 0.020 0.612 0.368
#> GSM425871 1 0.0424 0.8806 0.992 0.008 0.000
#> GSM425872 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425873 1 0.6633 0.1237 0.548 0.444 0.008
#> GSM425843 1 0.0424 0.8806 0.992 0.008 0.000
#> GSM425844 1 0.0424 0.8806 0.992 0.008 0.000
#> GSM425845 1 0.9980 -0.0432 0.364 0.312 0.324
#> GSM425846 2 0.3192 0.8277 0.112 0.888 0.000
#> GSM425847 2 0.4121 0.7696 0.168 0.832 0.000
#> GSM425886 3 0.3112 0.8596 0.028 0.056 0.916
#> GSM425887 2 0.1163 0.8913 0.028 0.972 0.000
#> GSM425888 2 0.0592 0.9007 0.012 0.988 0.000
#> GSM425889 1 0.0424 0.8806 0.992 0.008 0.000
#> GSM425890 1 0.0424 0.8806 0.992 0.008 0.000
#> GSM425891 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425892 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425853 1 0.4755 0.7387 0.808 0.008 0.184
#> GSM425854 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425855 1 0.0424 0.8806 0.992 0.008 0.000
#> GSM425856 1 0.5956 0.5537 0.672 0.004 0.324
#> GSM425857 1 0.6180 0.5343 0.660 0.008 0.332
#> GSM425858 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425859 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425860 2 0.7129 0.6464 0.180 0.716 0.104
#> GSM425861 2 0.4504 0.7418 0.196 0.804 0.000
#> GSM425862 1 0.0424 0.8806 0.992 0.008 0.000
#> GSM425837 1 0.0661 0.8795 0.988 0.008 0.004
#> GSM425838 1 0.0237 0.8787 0.996 0.004 0.000
#> GSM425839 2 0.0000 0.9078 0.000 1.000 0.000
#> GSM425840 1 0.0424 0.8806 0.992 0.008 0.000
#> GSM425841 1 0.0237 0.8787 0.996 0.004 0.000
#> GSM425842 1 0.1163 0.8690 0.972 0.028 0.000
#> GSM425917 1 0.5588 0.6384 0.720 0.004 0.276
#> GSM425922 1 0.0237 0.8787 0.996 0.004 0.000
#> GSM425919 1 0.1647 0.8628 0.960 0.004 0.036
#> GSM425920 1 0.0475 0.8790 0.992 0.004 0.004
#> GSM425923 1 0.0424 0.8806 0.992 0.008 0.000
#> GSM425916 1 0.1525 0.8653 0.964 0.004 0.032
#> GSM425918 1 0.0424 0.8806 0.992 0.008 0.000
#> GSM425921 1 0.0237 0.8787 0.996 0.004 0.000
#> GSM425925 1 0.0424 0.8806 0.992 0.008 0.000
#> GSM425926 1 0.0237 0.8787 0.996 0.004 0.000
#> GSM425927 1 0.0424 0.8806 0.992 0.008 0.000
#> GSM425924 1 0.5443 0.6554 0.736 0.004 0.260
#> GSM425928 3 0.0000 0.9012 0.000 0.000 1.000
#> GSM425929 3 0.0000 0.9012 0.000 0.000 1.000
#> GSM425930 3 0.0000 0.9012 0.000 0.000 1.000
#> GSM425931 3 0.0000 0.9012 0.000 0.000 1.000
#> GSM425932 3 0.0000 0.9012 0.000 0.000 1.000
#> GSM425933 3 0.0000 0.9012 0.000 0.000 1.000
#> GSM425934 3 0.0000 0.9012 0.000 0.000 1.000
#> GSM425935 3 0.0983 0.8924 0.016 0.004 0.980
#> GSM425936 3 0.0000 0.9012 0.000 0.000 1.000
#> GSM425937 3 0.0000 0.9012 0.000 0.000 1.000
#> GSM425938 3 0.0592 0.8964 0.012 0.000 0.988
#> GSM425939 3 0.0000 0.9012 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.0000 0.9427 0.000 1.000 0.000 0.000
#> GSM425908 2 0.0000 0.9427 0.000 1.000 0.000 0.000
#> GSM425909 1 0.8797 -0.0238 0.376 0.048 0.344 0.232
#> GSM425910 1 0.7033 0.4870 0.528 0.336 0.000 0.136
#> GSM425911 2 0.0336 0.9379 0.000 0.992 0.000 0.008
#> GSM425912 2 0.1042 0.9269 0.020 0.972 0.000 0.008
#> GSM425913 2 0.0000 0.9427 0.000 1.000 0.000 0.000
#> GSM425914 2 0.0927 0.9295 0.016 0.976 0.000 0.008
#> GSM425915 3 0.6388 0.4360 0.360 0.056 0.576 0.008
#> GSM425874 4 0.2530 0.7981 0.112 0.000 0.000 0.888
#> GSM425875 4 0.4713 0.4876 0.360 0.000 0.000 0.640
#> GSM425876 1 0.7307 0.5312 0.524 0.284 0.000 0.192
#> GSM425877 4 0.0000 0.8480 0.000 0.000 0.000 1.000
#> GSM425878 4 0.0000 0.8480 0.000 0.000 0.000 1.000
#> GSM425879 2 0.0000 0.9427 0.000 1.000 0.000 0.000
#> GSM425880 4 0.4776 0.4646 0.376 0.000 0.000 0.624
#> GSM425881 2 0.1256 0.9201 0.028 0.964 0.000 0.008
#> GSM425882 2 0.0000 0.9427 0.000 1.000 0.000 0.000
#> GSM425883 4 0.0804 0.8411 0.012 0.008 0.000 0.980
#> GSM425884 4 0.0188 0.8467 0.004 0.000 0.000 0.996
#> GSM425885 4 0.3895 0.6369 0.012 0.184 0.000 0.804
#> GSM425848 4 0.0779 0.8396 0.004 0.016 0.000 0.980
#> GSM425849 4 0.0188 0.8464 0.000 0.004 0.000 0.996
#> GSM425850 4 0.6010 -0.0875 0.472 0.040 0.000 0.488
#> GSM425851 4 0.0000 0.8480 0.000 0.000 0.000 1.000
#> GSM425852 4 0.5040 0.4752 0.364 0.008 0.000 0.628
#> GSM425893 2 0.0672 0.9341 0.008 0.984 0.000 0.008
#> GSM425894 2 0.0000 0.9427 0.000 1.000 0.000 0.000
#> GSM425895 2 0.0000 0.9427 0.000 1.000 0.000 0.000
#> GSM425896 2 0.0000 0.9427 0.000 1.000 0.000 0.000
#> GSM425897 2 0.0000 0.9427 0.000 1.000 0.000 0.000
#> GSM425898 2 0.0000 0.9427 0.000 1.000 0.000 0.000
#> GSM425899 2 0.7164 -0.0499 0.240 0.556 0.000 0.204
#> GSM425900 2 0.0672 0.9349 0.008 0.984 0.000 0.008
#> GSM425901 1 0.8761 0.0782 0.376 0.040 0.276 0.308
#> GSM425902 4 0.2654 0.7986 0.108 0.004 0.000 0.888
#> GSM425903 1 0.7521 -0.0265 0.528 0.140 0.316 0.016
#> GSM425904 4 0.4776 0.4646 0.376 0.000 0.000 0.624
#> GSM425905 2 0.0000 0.9427 0.000 1.000 0.000 0.000
#> GSM425906 2 0.0804 0.9324 0.012 0.980 0.000 0.008
#> GSM425863 4 0.0000 0.8480 0.000 0.000 0.000 1.000
#> GSM425864 2 0.0000 0.9427 0.000 1.000 0.000 0.000
#> GSM425865 2 0.0000 0.9427 0.000 1.000 0.000 0.000
#> GSM425866 4 0.4761 0.4706 0.372 0.000 0.000 0.628
#> GSM425867 3 0.5783 0.5178 0.324 0.032 0.636 0.008
#> GSM425868 2 0.0469 0.9312 0.000 0.988 0.000 0.012
#> GSM425869 2 0.0000 0.9427 0.000 1.000 0.000 0.000
#> GSM425870 2 0.4160 0.6757 0.016 0.808 0.168 0.008
#> GSM425871 4 0.0000 0.8480 0.000 0.000 0.000 1.000
#> GSM425872 2 0.0000 0.9427 0.000 1.000 0.000 0.000
#> GSM425873 1 0.7372 0.5412 0.524 0.236 0.000 0.240
#> GSM425843 4 0.0000 0.8480 0.000 0.000 0.000 1.000
#> GSM425844 4 0.0000 0.8480 0.000 0.000 0.000 1.000
#> GSM425845 1 0.3435 0.3987 0.864 0.036 0.000 0.100
#> GSM425846 2 0.0804 0.9331 0.012 0.980 0.000 0.008
#> GSM425847 1 0.6130 0.2838 0.512 0.440 0.000 0.048
#> GSM425886 3 0.6539 0.4138 0.372 0.044 0.564 0.020
#> GSM425887 2 0.1042 0.9271 0.020 0.972 0.000 0.008
#> GSM425888 2 0.2859 0.8147 0.112 0.880 0.000 0.008
#> GSM425889 4 0.0000 0.8480 0.000 0.000 0.000 1.000
#> GSM425890 4 0.1635 0.8315 0.044 0.008 0.000 0.948
#> GSM425891 2 0.0188 0.9407 0.000 0.996 0.000 0.004
#> GSM425892 2 0.0000 0.9427 0.000 1.000 0.000 0.000
#> GSM425853 4 0.0921 0.8366 0.028 0.000 0.000 0.972
#> GSM425854 2 0.0000 0.9427 0.000 1.000 0.000 0.000
#> GSM425855 4 0.0000 0.8480 0.000 0.000 0.000 1.000
#> GSM425856 4 0.4713 0.4876 0.360 0.000 0.000 0.640
#> GSM425857 4 0.5723 0.4106 0.388 0.032 0.000 0.580
#> GSM425858 2 0.0524 0.9368 0.004 0.988 0.000 0.008
#> GSM425859 2 0.0000 0.9427 0.000 1.000 0.000 0.000
#> GSM425860 1 0.6484 0.3124 0.504 0.432 0.004 0.060
#> GSM425861 2 0.5859 -0.2231 0.472 0.496 0.000 0.032
#> GSM425862 4 0.0000 0.8480 0.000 0.000 0.000 1.000
#> GSM425837 4 0.0000 0.8480 0.000 0.000 0.000 1.000
#> GSM425838 4 0.2530 0.7981 0.112 0.000 0.000 0.888
#> GSM425839 2 0.0000 0.9427 0.000 1.000 0.000 0.000
#> GSM425840 4 0.0000 0.8480 0.000 0.000 0.000 1.000
#> GSM425841 4 0.2530 0.7981 0.112 0.000 0.000 0.888
#> GSM425842 4 0.5628 0.1188 0.420 0.024 0.000 0.556
#> GSM425917 4 0.5453 0.4602 0.000 0.032 0.320 0.648
#> GSM425922 4 0.2530 0.7981 0.112 0.000 0.000 0.888
#> GSM425919 4 0.0000 0.8480 0.000 0.000 0.000 1.000
#> GSM425920 4 0.0000 0.8480 0.000 0.000 0.000 1.000
#> GSM425923 4 0.0000 0.8480 0.000 0.000 0.000 1.000
#> GSM425916 4 0.0000 0.8480 0.000 0.000 0.000 1.000
#> GSM425918 4 0.0000 0.8480 0.000 0.000 0.000 1.000
#> GSM425921 4 0.2530 0.7981 0.112 0.000 0.000 0.888
#> GSM425925 4 0.0937 0.8409 0.012 0.012 0.000 0.976
#> GSM425926 4 0.2530 0.7981 0.112 0.000 0.000 0.888
#> GSM425927 4 0.1042 0.8365 0.020 0.008 0.000 0.972
#> GSM425924 4 0.4764 0.6234 0.000 0.032 0.220 0.748
#> GSM425928 3 0.0188 0.8893 0.000 0.004 0.996 0.000
#> GSM425929 3 0.0000 0.8933 0.000 0.000 1.000 0.000
#> GSM425930 3 0.0000 0.8933 0.000 0.000 1.000 0.000
#> GSM425931 3 0.0000 0.8933 0.000 0.000 1.000 0.000
#> GSM425932 3 0.0000 0.8933 0.000 0.000 1.000 0.000
#> GSM425933 3 0.0000 0.8933 0.000 0.000 1.000 0.000
#> GSM425934 3 0.0000 0.8933 0.000 0.000 1.000 0.000
#> GSM425935 3 0.1356 0.8446 0.000 0.032 0.960 0.008
#> GSM425936 3 0.0000 0.8933 0.000 0.000 1.000 0.000
#> GSM425937 3 0.0000 0.8933 0.000 0.000 1.000 0.000
#> GSM425938 3 0.0000 0.8933 0.000 0.000 1.000 0.000
#> GSM425939 3 0.0000 0.8933 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
#> GSM425907 2 0.0290 0.8526 0.000 0.992 0.000 0.008 0.000
#> GSM425908 2 0.0000 0.8569 0.000 1.000 0.000 0.000 0.000
#> GSM425909 3 0.7370 0.5220 0.360 0.056 0.480 0.040 0.064
#> GSM425910 1 0.5108 0.6350 0.648 0.304 0.000 0.024 0.024
#> GSM425911 2 0.2221 0.7968 0.036 0.912 0.000 0.052 0.000
#> GSM425912 1 0.4287 0.4511 0.540 0.460 0.000 0.000 0.000
#> GSM425913 2 0.0000 0.8569 0.000 1.000 0.000 0.000 0.000
#> GSM425914 2 0.4738 -0.3295 0.464 0.520 0.000 0.016 0.000
#> GSM425915 3 0.4555 0.6432 0.344 0.000 0.636 0.020 0.000
#> GSM425874 4 0.4045 0.9088 0.000 0.000 0.000 0.644 0.356
#> GSM425875 5 0.4327 0.5216 0.360 0.000 0.000 0.008 0.632
#> GSM425876 1 0.5920 0.6349 0.644 0.240 0.000 0.044 0.072
#> GSM425877 5 0.0609 0.7909 0.000 0.000 0.000 0.020 0.980
#> GSM425878 5 0.0162 0.7931 0.004 0.000 0.000 0.000 0.996
#> GSM425879 2 0.0880 0.8348 0.000 0.968 0.000 0.032 0.000
#> GSM425880 5 0.4444 0.5154 0.364 0.000 0.000 0.012 0.624
#> GSM425881 1 0.4307 0.3488 0.500 0.500 0.000 0.000 0.000
#> GSM425882 2 0.0000 0.8569 0.000 1.000 0.000 0.000 0.000
#> GSM425883 5 0.1310 0.7814 0.024 0.000 0.000 0.020 0.956
#> GSM425884 5 0.0404 0.7930 0.012 0.000 0.000 0.000 0.988
#> GSM425885 4 0.5324 0.8461 0.004 0.056 0.000 0.600 0.340
#> GSM425848 5 0.4256 -0.5020 0.000 0.000 0.000 0.436 0.564
#> GSM425849 5 0.0290 0.7901 0.000 0.000 0.000 0.008 0.992
#> GSM425850 1 0.5049 0.0165 0.548 0.012 0.000 0.016 0.424
#> GSM425851 5 0.1908 0.7649 0.000 0.000 0.000 0.092 0.908
#> GSM425852 5 0.4538 0.5256 0.348 0.000 0.004 0.012 0.636
#> GSM425893 2 0.3163 0.6732 0.012 0.824 0.000 0.164 0.000
#> GSM425894 2 0.0000 0.8569 0.000 1.000 0.000 0.000 0.000
#> GSM425895 2 0.0000 0.8569 0.000 1.000 0.000 0.000 0.000
#> GSM425896 2 0.2732 0.6903 0.000 0.840 0.000 0.160 0.000
#> GSM425897 2 0.0609 0.8445 0.000 0.980 0.000 0.020 0.000
#> GSM425898 2 0.0000 0.8569 0.000 1.000 0.000 0.000 0.000
#> GSM425899 2 0.3604 0.6564 0.008 0.836 0.000 0.056 0.100
#> GSM425900 2 0.4045 0.1065 0.356 0.644 0.000 0.000 0.000
#> GSM425901 3 0.7769 0.4358 0.368 0.044 0.408 0.156 0.024
#> GSM425902 4 0.4074 0.9047 0.000 0.000 0.000 0.636 0.364
#> GSM425903 1 0.4339 -0.1188 0.684 0.000 0.296 0.020 0.000
#> GSM425904 5 0.4594 0.5116 0.364 0.000 0.004 0.012 0.620
#> GSM425905 2 0.0000 0.8569 0.000 1.000 0.000 0.000 0.000
#> GSM425906 2 0.4256 -0.2141 0.436 0.564 0.000 0.000 0.000
#> GSM425863 5 0.0290 0.7901 0.000 0.000 0.000 0.008 0.992
#> GSM425864 2 0.0162 0.8549 0.000 0.996 0.000 0.004 0.000
#> GSM425865 2 0.0000 0.8569 0.000 1.000 0.000 0.000 0.000
#> GSM425866 5 0.4430 0.5184 0.360 0.000 0.000 0.012 0.628
#> GSM425867 3 0.4213 0.6713 0.308 0.000 0.680 0.012 0.000
#> GSM425868 2 0.0324 0.8514 0.000 0.992 0.000 0.004 0.004
#> GSM425869 2 0.0000 0.8569 0.000 1.000 0.000 0.000 0.000
#> GSM425870 1 0.8308 0.4154 0.380 0.196 0.252 0.172 0.000
#> GSM425871 5 0.0162 0.7916 0.000 0.000 0.000 0.004 0.996
#> GSM425872 2 0.0000 0.8569 0.000 1.000 0.000 0.000 0.000
#> GSM425873 1 0.5978 0.6123 0.644 0.200 0.000 0.024 0.132
#> GSM425843 5 0.0451 0.7934 0.004 0.000 0.000 0.008 0.988
#> GSM425844 5 0.0290 0.7921 0.000 0.000 0.000 0.008 0.992
#> GSM425845 1 0.1357 0.3908 0.948 0.004 0.000 0.000 0.048
#> GSM425846 2 0.0162 0.8542 0.004 0.996 0.000 0.000 0.000
#> GSM425847 1 0.4875 0.6197 0.632 0.336 0.000 0.024 0.008
#> GSM425886 3 0.5869 0.5928 0.356 0.052 0.564 0.028 0.000
#> GSM425887 2 0.4307 -0.4144 0.500 0.500 0.000 0.000 0.000
#> GSM425888 1 0.4291 0.4425 0.536 0.464 0.000 0.000 0.000
#> GSM425889 5 0.0510 0.7855 0.000 0.000 0.000 0.016 0.984
#> GSM425890 4 0.4074 0.8869 0.000 0.000 0.000 0.636 0.364
#> GSM425891 2 0.0000 0.8569 0.000 1.000 0.000 0.000 0.000
#> GSM425892 2 0.0000 0.8569 0.000 1.000 0.000 0.000 0.000
#> GSM425853 5 0.0703 0.7905 0.024 0.000 0.000 0.000 0.976
#> GSM425854 2 0.0000 0.8569 0.000 1.000 0.000 0.000 0.000
#> GSM425855 5 0.0162 0.7927 0.000 0.000 0.000 0.004 0.996
#> GSM425856 5 0.4211 0.5243 0.360 0.000 0.000 0.004 0.636
#> GSM425857 4 0.4949 0.3248 0.368 0.000 0.028 0.600 0.004
#> GSM425858 2 0.4045 0.1084 0.356 0.644 0.000 0.000 0.000
#> GSM425859 2 0.0000 0.8569 0.000 1.000 0.000 0.000 0.000
#> GSM425860 1 0.5059 0.6234 0.632 0.320 0.000 0.044 0.004
#> GSM425861 1 0.4551 0.5924 0.616 0.368 0.000 0.000 0.016
#> GSM425862 5 0.0290 0.7901 0.000 0.000 0.000 0.008 0.992
#> GSM425837 5 0.0451 0.7930 0.008 0.000 0.000 0.004 0.988
#> GSM425838 4 0.4074 0.9047 0.000 0.000 0.000 0.636 0.364
#> GSM425839 2 0.0000 0.8569 0.000 1.000 0.000 0.000 0.000
#> GSM425840 5 0.0162 0.7927 0.000 0.000 0.000 0.004 0.996
#> GSM425841 4 0.4045 0.9088 0.000 0.000 0.000 0.644 0.356
#> GSM425842 5 0.4708 0.0594 0.436 0.000 0.000 0.016 0.548
#> GSM425917 3 0.6718 0.2113 0.012 0.000 0.468 0.176 0.344
#> GSM425922 4 0.3999 0.9005 0.000 0.000 0.000 0.656 0.344
#> GSM425919 5 0.2624 0.7437 0.012 0.000 0.000 0.116 0.872
#> GSM425920 5 0.1704 0.7762 0.004 0.000 0.000 0.068 0.928
#> GSM425923 5 0.0703 0.7894 0.000 0.000 0.000 0.024 0.976
#> GSM425916 5 0.1908 0.7649 0.000 0.000 0.000 0.092 0.908
#> GSM425918 5 0.0609 0.7909 0.000 0.000 0.000 0.020 0.980
#> GSM425921 4 0.4045 0.9088 0.000 0.000 0.000 0.644 0.356
#> GSM425925 5 0.1357 0.7513 0.004 0.000 0.000 0.048 0.948
#> GSM425926 4 0.4045 0.9088 0.000 0.000 0.000 0.644 0.356
#> GSM425927 5 0.1992 0.7725 0.032 0.000 0.000 0.044 0.924
#> GSM425924 5 0.5948 0.4897 0.012 0.000 0.184 0.172 0.632
#> GSM425928 3 0.0000 0.8398 0.000 0.000 1.000 0.000 0.000
#> GSM425929 3 0.0000 0.8398 0.000 0.000 1.000 0.000 0.000
#> GSM425930 3 0.0000 0.8398 0.000 0.000 1.000 0.000 0.000
#> GSM425931 3 0.0000 0.8398 0.000 0.000 1.000 0.000 0.000
#> GSM425932 3 0.0000 0.8398 0.000 0.000 1.000 0.000 0.000
#> GSM425933 3 0.0000 0.8398 0.000 0.000 1.000 0.000 0.000
#> GSM425934 3 0.0162 0.8380 0.004 0.000 0.996 0.000 0.000
#> GSM425935 3 0.1124 0.8260 0.004 0.000 0.960 0.036 0.000
#> GSM425936 3 0.0000 0.8398 0.000 0.000 1.000 0.000 0.000
#> GSM425937 3 0.0000 0.8398 0.000 0.000 1.000 0.000 0.000
#> GSM425938 3 0.0162 0.8388 0.000 0.000 0.996 0.004 0.000
#> GSM425939 3 0.0000 0.8398 0.000 0.000 1.000 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 2 0.1444 0.7051 0.000 0.928 0.000 0.000 0.072 0.000
#> GSM425908 2 0.0458 0.7230 0.000 0.984 0.000 0.000 0.000 0.016
#> GSM425909 4 0.6799 -0.3689 0.008 0.008 0.268 0.356 0.348 0.012
#> GSM425910 6 0.3816 0.5029 0.012 0.200 0.000 0.000 0.028 0.760
#> GSM425911 2 0.4513 0.4510 0.000 0.528 0.000 0.000 0.440 0.032
#> GSM425912 2 0.6105 -0.0782 0.000 0.360 0.000 0.000 0.288 0.352
#> GSM425913 2 0.2871 0.6610 0.000 0.804 0.000 0.000 0.192 0.004
#> GSM425914 5 0.6109 -0.2807 0.000 0.316 0.000 0.000 0.376 0.308
#> GSM425915 3 0.5728 0.4154 0.000 0.000 0.604 0.248 0.100 0.048
#> GSM425874 4 0.3699 0.7503 0.336 0.000 0.000 0.660 0.000 0.004
#> GSM425875 1 0.4331 0.5368 0.632 0.000 0.000 0.340 0.016 0.012
#> GSM425876 6 0.4078 0.5274 0.068 0.180 0.000 0.000 0.004 0.748
#> GSM425877 1 0.0870 0.8094 0.972 0.000 0.000 0.004 0.012 0.012
#> GSM425878 1 0.0146 0.8110 0.996 0.000 0.000 0.000 0.000 0.004
#> GSM425879 2 0.2006 0.6859 0.000 0.892 0.000 0.000 0.104 0.004
#> GSM425880 1 0.4923 0.5050 0.596 0.000 0.000 0.340 0.052 0.012
#> GSM425881 2 0.6101 -0.0337 0.000 0.372 0.000 0.000 0.288 0.340
#> GSM425882 2 0.2703 0.6731 0.000 0.824 0.000 0.000 0.172 0.004
#> GSM425883 1 0.1082 0.8055 0.956 0.000 0.000 0.004 0.000 0.040
#> GSM425884 1 0.0363 0.8121 0.988 0.000 0.000 0.000 0.000 0.012
#> GSM425885 4 0.4391 0.7283 0.320 0.028 0.000 0.644 0.000 0.008
#> GSM425848 4 0.4384 0.5327 0.460 0.000 0.000 0.520 0.004 0.016
#> GSM425849 1 0.0692 0.8063 0.976 0.000 0.000 0.020 0.000 0.004
#> GSM425850 6 0.3992 0.3171 0.364 0.012 0.000 0.000 0.000 0.624
#> GSM425851 1 0.2670 0.7638 0.872 0.000 0.000 0.004 0.040 0.084
#> GSM425852 1 0.5486 0.4800 0.568 0.000 0.000 0.328 0.076 0.028
#> GSM425893 2 0.4181 0.3936 0.000 0.512 0.000 0.000 0.476 0.012
#> GSM425894 2 0.0790 0.7188 0.000 0.968 0.000 0.000 0.000 0.032
#> GSM425895 2 0.0146 0.7246 0.000 0.996 0.000 0.000 0.000 0.004
#> GSM425896 2 0.3490 0.5110 0.000 0.724 0.000 0.000 0.268 0.008
#> GSM425897 2 0.1858 0.6960 0.000 0.904 0.000 0.000 0.092 0.004
#> GSM425898 2 0.0260 0.7242 0.000 0.992 0.000 0.000 0.000 0.008
#> GSM425899 2 0.6237 0.5110 0.104 0.656 0.000 0.076 0.076 0.088
#> GSM425900 2 0.5943 0.1787 0.000 0.456 0.000 0.000 0.292 0.252
#> GSM425901 4 0.6541 -0.3191 0.004 0.008 0.208 0.420 0.348 0.012
#> GSM425902 4 0.3592 0.7462 0.344 0.000 0.000 0.656 0.000 0.000
#> GSM425903 6 0.7237 -0.1249 0.000 0.000 0.276 0.272 0.092 0.360
#> GSM425904 1 0.5220 0.4811 0.572 0.000 0.000 0.340 0.076 0.012
#> GSM425905 2 0.0146 0.7246 0.000 0.996 0.000 0.000 0.000 0.004
#> GSM425906 2 0.6056 0.0777 0.000 0.412 0.000 0.000 0.296 0.292
#> GSM425863 1 0.0508 0.8093 0.984 0.000 0.000 0.012 0.000 0.004
#> GSM425864 2 0.1444 0.7066 0.000 0.928 0.000 0.000 0.072 0.000
#> GSM425865 2 0.0260 0.7242 0.000 0.992 0.000 0.000 0.000 0.008
#> GSM425866 1 0.4411 0.5326 0.628 0.000 0.000 0.340 0.020 0.012
#> GSM425867 3 0.5226 0.4828 0.020 0.000 0.660 0.244 0.020 0.056
#> GSM425868 2 0.1806 0.6883 0.004 0.908 0.000 0.000 0.000 0.088
#> GSM425869 2 0.0363 0.7237 0.000 0.988 0.000 0.000 0.000 0.012
#> GSM425870 5 0.6112 -0.1551 0.000 0.056 0.120 0.000 0.556 0.268
#> GSM425871 1 0.0146 0.8110 0.996 0.000 0.000 0.000 0.000 0.004
#> GSM425872 2 0.2822 0.6967 0.000 0.852 0.000 0.000 0.108 0.040
#> GSM425873 6 0.4121 0.5172 0.116 0.136 0.000 0.000 0.000 0.748
#> GSM425843 1 0.0520 0.8127 0.984 0.000 0.000 0.000 0.008 0.008
#> GSM425844 1 0.0291 0.8104 0.992 0.000 0.000 0.004 0.004 0.000
#> GSM425845 6 0.4821 0.2596 0.020 0.004 0.000 0.312 0.032 0.632
#> GSM425846 2 0.3916 0.6511 0.000 0.752 0.000 0.000 0.184 0.064
#> GSM425847 6 0.3619 0.4306 0.000 0.316 0.000 0.000 0.004 0.680
#> GSM425886 5 0.7005 -0.1902 0.000 0.012 0.288 0.280 0.384 0.036
#> GSM425887 2 0.6109 -0.0340 0.000 0.356 0.000 0.000 0.292 0.352
#> GSM425888 2 0.6109 -0.0743 0.000 0.356 0.000 0.000 0.292 0.352
#> GSM425889 1 0.1010 0.7940 0.960 0.000 0.000 0.036 0.004 0.000
#> GSM425890 4 0.3898 0.7461 0.336 0.000 0.000 0.652 0.000 0.012
#> GSM425891 2 0.3266 0.6084 0.000 0.728 0.000 0.000 0.272 0.000
#> GSM425892 2 0.0547 0.7222 0.000 0.980 0.000 0.000 0.000 0.020
#> GSM425853 1 0.1176 0.8039 0.956 0.000 0.000 0.020 0.000 0.024
#> GSM425854 2 0.0146 0.7246 0.000 0.996 0.000 0.000 0.000 0.004
#> GSM425855 1 0.0146 0.8118 0.996 0.000 0.000 0.000 0.000 0.004
#> GSM425856 1 0.4331 0.5368 0.632 0.000 0.000 0.340 0.016 0.012
#> GSM425857 4 0.1956 0.2461 0.004 0.000 0.000 0.908 0.080 0.008
#> GSM425858 2 0.5916 0.1967 0.000 0.464 0.000 0.000 0.292 0.244
#> GSM425859 2 0.0146 0.7246 0.000 0.996 0.000 0.000 0.000 0.004
#> GSM425860 6 0.4475 0.4599 0.000 0.200 0.000 0.000 0.100 0.700
#> GSM425861 6 0.5968 0.2153 0.008 0.284 0.000 0.000 0.208 0.500
#> GSM425862 1 0.0777 0.8034 0.972 0.000 0.000 0.024 0.004 0.000
#> GSM425837 1 0.0458 0.8118 0.984 0.000 0.000 0.000 0.000 0.016
#> GSM425838 4 0.3592 0.7462 0.344 0.000 0.000 0.656 0.000 0.000
#> GSM425839 2 0.0146 0.7246 0.000 0.996 0.000 0.000 0.000 0.004
#> GSM425840 1 0.0146 0.8110 0.996 0.000 0.000 0.000 0.000 0.004
#> GSM425841 4 0.3699 0.7503 0.336 0.000 0.000 0.660 0.000 0.004
#> GSM425842 6 0.3890 0.2495 0.400 0.004 0.000 0.000 0.000 0.596
#> GSM425917 5 0.7239 -0.2596 0.056 0.000 0.356 0.020 0.368 0.200
#> GSM425922 4 0.3912 0.7437 0.340 0.000 0.000 0.648 0.000 0.012
#> GSM425919 1 0.2868 0.7548 0.852 0.000 0.000 0.004 0.032 0.112
#> GSM425920 1 0.1442 0.8021 0.944 0.000 0.000 0.004 0.012 0.040
#> GSM425923 1 0.0665 0.8094 0.980 0.000 0.000 0.004 0.008 0.008
#> GSM425916 1 0.2617 0.7658 0.876 0.000 0.000 0.004 0.040 0.080
#> GSM425918 1 0.0862 0.8098 0.972 0.000 0.000 0.004 0.016 0.008
#> GSM425921 4 0.3789 0.7495 0.332 0.000 0.000 0.660 0.000 0.008
#> GSM425925 1 0.0713 0.8002 0.972 0.000 0.000 0.028 0.000 0.000
#> GSM425926 4 0.3699 0.7503 0.336 0.000 0.000 0.660 0.000 0.004
#> GSM425927 1 0.3586 0.5010 0.720 0.000 0.000 0.000 0.012 0.268
#> GSM425924 1 0.7127 0.2920 0.472 0.000 0.120 0.004 0.200 0.204
#> GSM425928 3 0.2793 0.7135 0.000 0.000 0.800 0.000 0.200 0.000
#> GSM425929 3 0.0000 0.8701 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425930 3 0.0000 0.8701 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425931 3 0.0000 0.8701 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425932 3 0.0000 0.8701 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425933 3 0.0000 0.8701 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425934 3 0.0146 0.8677 0.000 0.000 0.996 0.000 0.000 0.004
#> GSM425935 3 0.4613 0.5531 0.000 0.000 0.660 0.000 0.260 0.080
#> GSM425936 3 0.0000 0.8701 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425937 3 0.0000 0.8701 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425938 3 0.1958 0.8037 0.000 0.000 0.896 0.000 0.100 0.004
#> GSM425939 3 0.0000 0.8701 0.000 0.000 1.000 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 disease.state(p) tissue(p) other(p) k
#> CV:mclust 92 9.20e-13 3.91e-13 1.23e-09 2
#> CV:mclust 94 1.85e-16 9.80e-18 6.87e-14 3
#> CV:mclust 82 4.39e-16 2.28e-17 5.58e-12 4
#> CV:mclust 85 2.56e-12 1.42e-12 3.11e-09 5
#> CV:mclust 75 1.99e-15 4.68e-15 2.25e-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["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 103 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 0.495 0.782 0.841 0.4611 0.530 0.530
#> 3 3 0.592 0.723 0.870 0.4205 0.678 0.461
#> 4 4 0.593 0.633 0.812 0.1342 0.808 0.510
#> 5 5 0.678 0.673 0.823 0.0687 0.891 0.614
#> 6 6 0.679 0.547 0.741 0.0505 0.913 0.628
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
#> GSM425907 2 0.9323 0.472 0.348 0.652
#> GSM425908 1 0.4161 0.873 0.916 0.084
#> GSM425909 2 0.5294 0.796 0.120 0.880
#> GSM425910 2 0.9491 0.483 0.368 0.632
#> GSM425911 2 0.3584 0.810 0.068 0.932
#> GSM425912 2 0.9580 0.398 0.380 0.620
#> GSM425913 1 0.9933 0.181 0.548 0.452
#> GSM425914 2 0.7139 0.710 0.196 0.804
#> GSM425915 2 0.2043 0.839 0.032 0.968
#> GSM425874 1 0.0000 0.904 1.000 0.000
#> GSM425875 1 0.3733 0.853 0.928 0.072
#> GSM425876 1 0.6973 0.791 0.812 0.188
#> GSM425877 1 0.0672 0.900 0.992 0.008
#> GSM425878 1 0.0000 0.904 1.000 0.000
#> GSM425879 2 0.6973 0.718 0.188 0.812
#> GSM425880 2 0.9732 0.442 0.404 0.596
#> GSM425881 1 0.5059 0.854 0.888 0.112
#> GSM425882 1 0.6247 0.819 0.844 0.156
#> GSM425883 1 0.0000 0.904 1.000 0.000
#> GSM425884 1 0.1414 0.894 0.980 0.020
#> GSM425885 1 0.0000 0.904 1.000 0.000
#> GSM425848 1 0.0000 0.904 1.000 0.000
#> GSM425849 1 0.0000 0.904 1.000 0.000
#> GSM425850 1 0.1414 0.897 0.980 0.020
#> GSM425851 1 0.3114 0.869 0.944 0.056
#> GSM425852 2 0.6623 0.762 0.172 0.828
#> GSM425893 2 0.0672 0.825 0.008 0.992
#> GSM425894 1 0.6438 0.811 0.836 0.164
#> GSM425895 1 0.7139 0.773 0.804 0.196
#> GSM425896 2 0.3431 0.813 0.064 0.936
#> GSM425897 2 0.9608 0.387 0.384 0.616
#> GSM425898 1 0.5737 0.838 0.864 0.136
#> GSM425899 1 0.0000 0.904 1.000 0.000
#> GSM425900 1 0.8813 0.606 0.700 0.300
#> GSM425901 2 0.5519 0.792 0.128 0.872
#> GSM425902 1 0.0000 0.904 1.000 0.000
#> GSM425903 2 0.2043 0.839 0.032 0.968
#> GSM425904 2 0.9580 0.490 0.380 0.620
#> GSM425905 1 0.9323 0.499 0.652 0.348
#> GSM425906 2 0.9998 0.014 0.492 0.508
#> GSM425863 1 0.0000 0.904 1.000 0.000
#> GSM425864 2 0.9552 0.410 0.376 0.624
#> GSM425865 1 0.9087 0.556 0.676 0.324
#> GSM425866 1 0.3733 0.853 0.928 0.072
#> GSM425867 2 0.2043 0.839 0.032 0.968
#> GSM425868 1 0.2043 0.892 0.968 0.032
#> GSM425869 1 0.3431 0.882 0.936 0.064
#> GSM425870 2 0.0000 0.825 0.000 1.000
#> GSM425871 1 0.0672 0.902 0.992 0.008
#> GSM425872 1 0.3584 0.882 0.932 0.068
#> GSM425873 1 0.2043 0.892 0.968 0.032
#> GSM425843 1 0.0000 0.904 1.000 0.000
#> GSM425844 1 0.0000 0.904 1.000 0.000
#> GSM425845 2 0.8608 0.670 0.284 0.716
#> GSM425846 1 0.2043 0.892 0.968 0.032
#> GSM425847 1 0.6712 0.799 0.824 0.176
#> GSM425886 2 0.2236 0.837 0.036 0.964
#> GSM425887 1 0.6148 0.824 0.848 0.152
#> GSM425888 1 0.5294 0.849 0.880 0.120
#> GSM425889 1 0.0000 0.904 1.000 0.000
#> GSM425890 1 0.0000 0.904 1.000 0.000
#> GSM425891 2 0.9944 0.163 0.456 0.544
#> GSM425892 1 0.8608 0.637 0.716 0.284
#> GSM425853 1 0.1843 0.889 0.972 0.028
#> GSM425854 1 0.5178 0.852 0.884 0.116
#> GSM425855 1 0.0000 0.904 1.000 0.000
#> GSM425856 1 0.2603 0.878 0.956 0.044
#> GSM425857 1 0.9775 0.119 0.588 0.412
#> GSM425858 1 0.5294 0.849 0.880 0.120
#> GSM425859 1 0.5059 0.855 0.888 0.112
#> GSM425860 2 0.3584 0.810 0.068 0.932
#> GSM425861 1 0.2423 0.891 0.960 0.040
#> GSM425862 1 0.0000 0.904 1.000 0.000
#> GSM425837 1 0.0672 0.900 0.992 0.008
#> GSM425838 1 0.0000 0.904 1.000 0.000
#> GSM425839 1 0.5842 0.833 0.860 0.140
#> GSM425840 1 0.0000 0.904 1.000 0.000
#> GSM425841 1 0.0000 0.904 1.000 0.000
#> GSM425842 1 0.0000 0.904 1.000 0.000
#> GSM425917 2 0.7299 0.754 0.204 0.796
#> GSM425922 1 0.0000 0.904 1.000 0.000
#> GSM425919 1 0.9686 0.176 0.604 0.396
#> GSM425920 1 0.0000 0.904 1.000 0.000
#> GSM425923 1 0.0376 0.902 0.996 0.004
#> GSM425916 1 0.4690 0.822 0.900 0.100
#> GSM425918 1 0.0376 0.902 0.996 0.004
#> GSM425921 1 0.0000 0.904 1.000 0.000
#> GSM425925 1 0.0000 0.904 1.000 0.000
#> GSM425926 1 0.0000 0.904 1.000 0.000
#> GSM425927 1 0.0000 0.904 1.000 0.000
#> GSM425924 2 0.4815 0.812 0.104 0.896
#> GSM425928 2 0.2043 0.839 0.032 0.968
#> GSM425929 2 0.2043 0.839 0.032 0.968
#> GSM425930 2 0.2043 0.839 0.032 0.968
#> GSM425931 2 0.2043 0.839 0.032 0.968
#> GSM425932 2 0.2043 0.839 0.032 0.968
#> GSM425933 2 0.2043 0.839 0.032 0.968
#> GSM425934 2 0.0376 0.827 0.004 0.996
#> GSM425935 2 0.1843 0.837 0.028 0.972
#> GSM425936 2 0.2043 0.839 0.032 0.968
#> GSM425937 2 0.2043 0.839 0.032 0.968
#> GSM425938 2 0.2043 0.839 0.032 0.968
#> GSM425939 2 0.2043 0.839 0.032 0.968
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.1647 0.8355 0.004 0.960 0.036
#> GSM425908 2 0.1289 0.8361 0.032 0.968 0.000
#> GSM425909 3 0.2689 0.8351 0.032 0.036 0.932
#> GSM425910 2 0.9651 0.1744 0.392 0.400 0.208
#> GSM425911 2 0.4291 0.7225 0.000 0.820 0.180
#> GSM425912 2 0.6911 0.6790 0.180 0.728 0.092
#> GSM425913 2 0.0747 0.8397 0.000 0.984 0.016
#> GSM425914 2 0.5955 0.7036 0.048 0.772 0.180
#> GSM425915 3 0.0237 0.8522 0.000 0.004 0.996
#> GSM425874 1 0.5291 0.6736 0.732 0.268 0.000
#> GSM425875 1 0.1860 0.8264 0.948 0.000 0.052
#> GSM425876 1 0.6865 0.2034 0.596 0.384 0.020
#> GSM425877 1 0.0237 0.8473 0.996 0.000 0.004
#> GSM425878 1 0.0000 0.8485 1.000 0.000 0.000
#> GSM425879 2 0.2066 0.8240 0.000 0.940 0.060
#> GSM425880 1 0.6309 -0.1774 0.500 0.000 0.500
#> GSM425881 2 0.5138 0.6679 0.252 0.748 0.000
#> GSM425882 2 0.0237 0.8421 0.004 0.996 0.000
#> GSM425883 1 0.1753 0.8446 0.952 0.048 0.000
#> GSM425884 1 0.0592 0.8456 0.988 0.000 0.012
#> GSM425885 1 0.6260 0.3182 0.552 0.448 0.000
#> GSM425848 1 0.3619 0.7996 0.864 0.136 0.000
#> GSM425849 1 0.1289 0.8483 0.968 0.032 0.000
#> GSM425850 1 0.1860 0.8330 0.948 0.052 0.000
#> GSM425851 1 0.2680 0.8174 0.924 0.008 0.068
#> GSM425852 3 0.5098 0.6719 0.248 0.000 0.752
#> GSM425893 2 0.5098 0.6431 0.000 0.752 0.248
#> GSM425894 2 0.0892 0.8401 0.020 0.980 0.000
#> GSM425895 2 0.0237 0.8421 0.004 0.996 0.000
#> GSM425896 2 0.2261 0.8208 0.000 0.932 0.068
#> GSM425897 2 0.1643 0.8316 0.000 0.956 0.044
#> GSM425898 2 0.0237 0.8421 0.004 0.996 0.000
#> GSM425899 1 0.4291 0.7692 0.820 0.180 0.000
#> GSM425900 2 0.1878 0.8369 0.044 0.952 0.004
#> GSM425901 3 0.4628 0.7901 0.056 0.088 0.856
#> GSM425902 1 0.5397 0.6577 0.720 0.280 0.000
#> GSM425903 3 0.1289 0.8430 0.032 0.000 0.968
#> GSM425904 3 0.6274 0.2585 0.456 0.000 0.544
#> GSM425905 2 0.0237 0.8417 0.000 0.996 0.004
#> GSM425906 2 0.3764 0.8096 0.040 0.892 0.068
#> GSM425863 1 0.0237 0.8495 0.996 0.004 0.000
#> GSM425864 2 0.1289 0.8358 0.000 0.968 0.032
#> GSM425865 2 0.0237 0.8417 0.000 0.996 0.004
#> GSM425866 1 0.2165 0.8172 0.936 0.000 0.064
#> GSM425867 3 0.1964 0.8345 0.056 0.000 0.944
#> GSM425868 2 0.5810 0.3903 0.336 0.664 0.000
#> GSM425869 2 0.3412 0.7668 0.124 0.876 0.000
#> GSM425870 3 0.6154 0.1719 0.000 0.408 0.592
#> GSM425871 1 0.1031 0.8495 0.976 0.024 0.000
#> GSM425872 2 0.2165 0.8209 0.064 0.936 0.000
#> GSM425873 1 0.4589 0.7007 0.820 0.172 0.008
#> GSM425843 1 0.0237 0.8473 0.996 0.000 0.004
#> GSM425844 1 0.0892 0.8499 0.980 0.020 0.000
#> GSM425845 3 0.7353 0.2750 0.436 0.032 0.532
#> GSM425846 2 0.6235 0.1152 0.436 0.564 0.000
#> GSM425847 2 0.6373 0.4080 0.408 0.588 0.004
#> GSM425886 3 0.2625 0.8077 0.000 0.084 0.916
#> GSM425887 2 0.4605 0.7253 0.204 0.796 0.000
#> GSM425888 2 0.5650 0.5903 0.312 0.688 0.000
#> GSM425889 1 0.1860 0.8443 0.948 0.052 0.000
#> GSM425890 1 0.4931 0.7157 0.768 0.232 0.000
#> GSM425891 2 0.1529 0.8344 0.000 0.960 0.040
#> GSM425892 2 0.0424 0.8418 0.008 0.992 0.000
#> GSM425853 1 0.1643 0.8313 0.956 0.000 0.044
#> GSM425854 2 0.0237 0.8421 0.004 0.996 0.000
#> GSM425855 1 0.0592 0.8498 0.988 0.012 0.000
#> GSM425856 1 0.1753 0.8288 0.952 0.000 0.048
#> GSM425857 3 0.9978 0.0244 0.336 0.304 0.360
#> GSM425858 2 0.1860 0.8345 0.052 0.948 0.000
#> GSM425859 2 0.0592 0.8416 0.012 0.988 0.000
#> GSM425860 2 0.9447 0.2098 0.188 0.464 0.348
#> GSM425861 1 0.6308 -0.1252 0.508 0.492 0.000
#> GSM425862 1 0.2066 0.8416 0.940 0.060 0.000
#> GSM425837 1 0.0592 0.8455 0.988 0.000 0.012
#> GSM425838 1 0.5706 0.5953 0.680 0.320 0.000
#> GSM425839 2 0.0237 0.8421 0.004 0.996 0.000
#> GSM425840 1 0.0000 0.8485 1.000 0.000 0.000
#> GSM425841 1 0.5216 0.6827 0.740 0.260 0.000
#> GSM425842 1 0.0661 0.8473 0.988 0.008 0.004
#> GSM425917 3 0.5325 0.6484 0.248 0.004 0.748
#> GSM425922 1 0.4887 0.7207 0.772 0.228 0.000
#> GSM425919 1 0.4605 0.6545 0.796 0.000 0.204
#> GSM425920 1 0.0000 0.8485 1.000 0.000 0.000
#> GSM425923 1 0.0424 0.8498 0.992 0.008 0.000
#> GSM425916 1 0.2625 0.8000 0.916 0.000 0.084
#> GSM425918 1 0.0424 0.8498 0.992 0.008 0.000
#> GSM425921 1 0.4291 0.7655 0.820 0.180 0.000
#> GSM425925 1 0.2356 0.8379 0.928 0.072 0.000
#> GSM425926 1 0.4750 0.7349 0.784 0.216 0.000
#> GSM425927 1 0.0475 0.8474 0.992 0.004 0.004
#> GSM425924 3 0.4654 0.7205 0.208 0.000 0.792
#> GSM425928 3 0.0237 0.8524 0.000 0.004 0.996
#> GSM425929 3 0.0000 0.8532 0.000 0.000 1.000
#> GSM425930 3 0.0000 0.8532 0.000 0.000 1.000
#> GSM425931 3 0.0000 0.8532 0.000 0.000 1.000
#> GSM425932 3 0.0237 0.8520 0.000 0.004 0.996
#> GSM425933 3 0.0000 0.8532 0.000 0.000 1.000
#> GSM425934 3 0.0892 0.8446 0.000 0.020 0.980
#> GSM425935 3 0.3038 0.7866 0.000 0.104 0.896
#> GSM425936 3 0.0424 0.8507 0.000 0.008 0.992
#> GSM425937 3 0.0000 0.8532 0.000 0.000 1.000
#> GSM425938 3 0.0000 0.8532 0.000 0.000 1.000
#> GSM425939 3 0.0000 0.8532 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.5137 0.65426 0.000 0.680 0.024 0.296
#> GSM425908 4 0.4817 0.10495 0.000 0.388 0.000 0.612
#> GSM425909 3 0.5539 0.76705 0.224 0.004 0.712 0.060
#> GSM425910 1 0.3933 0.57853 0.796 0.196 0.004 0.004
#> GSM425911 2 0.0672 0.84768 0.008 0.984 0.008 0.000
#> GSM425912 2 0.2868 0.77478 0.136 0.864 0.000 0.000
#> GSM425913 2 0.0376 0.84831 0.004 0.992 0.000 0.004
#> GSM425914 2 0.1305 0.84061 0.036 0.960 0.004 0.000
#> GSM425915 3 0.3610 0.80816 0.200 0.000 0.800 0.000
#> GSM425874 4 0.0376 0.72163 0.004 0.004 0.000 0.992
#> GSM425875 1 0.3047 0.60297 0.872 0.000 0.012 0.116
#> GSM425876 1 0.4053 0.56494 0.768 0.228 0.000 0.004
#> GSM425877 1 0.5236 0.37828 0.560 0.000 0.008 0.432
#> GSM425878 1 0.4382 0.60164 0.704 0.000 0.000 0.296
#> GSM425879 2 0.1388 0.84930 0.000 0.960 0.012 0.028
#> GSM425880 1 0.6259 0.16696 0.616 0.000 0.300 0.084
#> GSM425881 2 0.2814 0.78068 0.132 0.868 0.000 0.000
#> GSM425882 2 0.0779 0.84982 0.004 0.980 0.000 0.016
#> GSM425883 4 0.4781 0.34089 0.336 0.004 0.000 0.660
#> GSM425884 1 0.2714 0.66127 0.884 0.000 0.004 0.112
#> GSM425885 4 0.1722 0.69840 0.008 0.048 0.000 0.944
#> GSM425848 4 0.3484 0.67115 0.144 0.004 0.008 0.844
#> GSM425849 1 0.5143 0.27980 0.540 0.004 0.000 0.456
#> GSM425850 1 0.4996 0.63500 0.752 0.056 0.000 0.192
#> GSM425851 4 0.6005 0.27437 0.324 0.000 0.060 0.616
#> GSM425852 3 0.5812 0.65114 0.328 0.000 0.624 0.048
#> GSM425893 2 0.3009 0.80916 0.056 0.892 0.052 0.000
#> GSM425894 4 0.4855 0.01508 0.000 0.400 0.000 0.600
#> GSM425895 2 0.3123 0.81035 0.000 0.844 0.000 0.156
#> GSM425896 2 0.6897 0.48970 0.000 0.544 0.124 0.332
#> GSM425897 2 0.2546 0.84122 0.000 0.900 0.008 0.092
#> GSM425898 2 0.3311 0.79927 0.000 0.828 0.000 0.172
#> GSM425899 4 0.2882 0.70151 0.084 0.024 0.000 0.892
#> GSM425900 2 0.1022 0.84251 0.032 0.968 0.000 0.000
#> GSM425901 3 0.6713 0.69435 0.232 0.004 0.624 0.140
#> GSM425902 4 0.0672 0.72076 0.008 0.008 0.000 0.984
#> GSM425903 3 0.4999 0.69770 0.328 0.012 0.660 0.000
#> GSM425904 1 0.6727 -0.23654 0.496 0.000 0.412 0.092
#> GSM425905 2 0.1940 0.84540 0.000 0.924 0.000 0.076
#> GSM425906 2 0.1211 0.83929 0.040 0.960 0.000 0.000
#> GSM425863 1 0.4456 0.61072 0.716 0.004 0.000 0.280
#> GSM425864 2 0.1743 0.84836 0.000 0.940 0.004 0.056
#> GSM425865 2 0.1940 0.84599 0.000 0.924 0.000 0.076
#> GSM425866 1 0.1970 0.63124 0.932 0.000 0.008 0.060
#> GSM425867 3 0.3444 0.81674 0.184 0.000 0.816 0.000
#> GSM425868 4 0.2408 0.66422 0.000 0.104 0.000 0.896
#> GSM425869 4 0.3444 0.57563 0.000 0.184 0.000 0.816
#> GSM425870 2 0.5281 0.12775 0.008 0.528 0.464 0.000
#> GSM425871 1 0.4608 0.59085 0.692 0.004 0.000 0.304
#> GSM425872 2 0.2773 0.83216 0.004 0.880 0.000 0.116
#> GSM425873 1 0.4692 0.57631 0.756 0.212 0.000 0.032
#> GSM425843 1 0.3908 0.64854 0.784 0.000 0.004 0.212
#> GSM425844 4 0.4948 -0.00780 0.440 0.000 0.000 0.560
#> GSM425845 1 0.1004 0.62237 0.972 0.024 0.004 0.000
#> GSM425846 2 0.5916 0.57820 0.072 0.656 0.000 0.272
#> GSM425847 1 0.5060 0.27158 0.584 0.412 0.000 0.004
#> GSM425886 3 0.4789 0.78737 0.224 0.004 0.748 0.024
#> GSM425887 2 0.2345 0.80718 0.100 0.900 0.000 0.000
#> GSM425888 2 0.3764 0.68179 0.216 0.784 0.000 0.000
#> GSM425889 4 0.3636 0.61510 0.172 0.000 0.008 0.820
#> GSM425890 4 0.0707 0.72259 0.020 0.000 0.000 0.980
#> GSM425891 2 0.0188 0.84782 0.004 0.996 0.000 0.000
#> GSM425892 2 0.4998 0.29104 0.000 0.512 0.000 0.488
#> GSM425853 1 0.1576 0.64094 0.948 0.000 0.004 0.048
#> GSM425854 2 0.3208 0.81717 0.004 0.848 0.000 0.148
#> GSM425855 1 0.4661 0.53662 0.652 0.000 0.000 0.348
#> GSM425856 1 0.2412 0.62403 0.908 0.000 0.008 0.084
#> GSM425857 4 0.5710 0.48760 0.228 0.008 0.060 0.704
#> GSM425858 2 0.1022 0.84330 0.032 0.968 0.000 0.000
#> GSM425859 2 0.4040 0.72909 0.000 0.752 0.000 0.248
#> GSM425860 1 0.6120 0.15323 0.520 0.432 0.048 0.000
#> GSM425861 1 0.5408 0.03691 0.500 0.488 0.000 0.012
#> GSM425862 4 0.3751 0.60546 0.196 0.000 0.004 0.800
#> GSM425837 1 0.2973 0.65745 0.856 0.000 0.000 0.144
#> GSM425838 4 0.0188 0.72006 0.000 0.004 0.000 0.996
#> GSM425839 2 0.2149 0.84226 0.000 0.912 0.000 0.088
#> GSM425840 1 0.4454 0.59017 0.692 0.000 0.000 0.308
#> GSM425841 4 0.0336 0.72244 0.008 0.000 0.000 0.992
#> GSM425842 1 0.3245 0.66233 0.872 0.028 0.000 0.100
#> GSM425917 3 0.5420 0.43944 0.024 0.000 0.624 0.352
#> GSM425922 4 0.0921 0.72214 0.028 0.000 0.000 0.972
#> GSM425919 1 0.5522 0.63031 0.716 0.000 0.080 0.204
#> GSM425920 1 0.4406 0.59762 0.700 0.000 0.000 0.300
#> GSM425923 4 0.4905 0.24642 0.364 0.000 0.004 0.632
#> GSM425916 1 0.5894 0.36144 0.536 0.000 0.036 0.428
#> GSM425918 4 0.4941 0.00524 0.436 0.000 0.000 0.564
#> GSM425921 4 0.1022 0.71983 0.032 0.000 0.000 0.968
#> GSM425925 4 0.4741 0.37427 0.328 0.004 0.000 0.668
#> GSM425926 4 0.0921 0.72223 0.028 0.000 0.000 0.972
#> GSM425927 1 0.4122 0.63350 0.760 0.000 0.004 0.236
#> GSM425924 3 0.4030 0.76909 0.092 0.000 0.836 0.072
#> GSM425928 3 0.0657 0.87651 0.000 0.004 0.984 0.012
#> GSM425929 3 0.0188 0.87858 0.000 0.004 0.996 0.000
#> GSM425930 3 0.0188 0.87858 0.000 0.004 0.996 0.000
#> GSM425931 3 0.0188 0.87836 0.000 0.004 0.996 0.000
#> GSM425932 3 0.0188 0.87858 0.000 0.004 0.996 0.000
#> GSM425933 3 0.0188 0.87858 0.000 0.004 0.996 0.000
#> GSM425934 3 0.0592 0.87395 0.000 0.016 0.984 0.000
#> GSM425935 3 0.0804 0.87469 0.000 0.012 0.980 0.008
#> GSM425936 3 0.0336 0.87763 0.000 0.008 0.992 0.000
#> GSM425937 3 0.0000 0.87862 0.000 0.000 1.000 0.000
#> GSM425938 3 0.0376 0.87809 0.000 0.004 0.992 0.004
#> GSM425939 3 0.0000 0.87862 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
#> GSM425907 4 0.5099 -0.1894 0.000 0.484 0.012 0.488 0.016
#> GSM425908 4 0.4037 0.4505 0.000 0.288 0.004 0.704 0.004
#> GSM425909 5 0.1992 0.8482 0.000 0.000 0.044 0.032 0.924
#> GSM425910 1 0.4863 0.5619 0.708 0.088 0.000 0.000 0.204
#> GSM425911 2 0.0579 0.8113 0.000 0.984 0.008 0.000 0.008
#> GSM425912 2 0.2674 0.7525 0.140 0.856 0.000 0.000 0.004
#> GSM425913 2 0.0324 0.8116 0.000 0.992 0.000 0.004 0.004
#> GSM425914 2 0.1341 0.8017 0.056 0.944 0.000 0.000 0.000
#> GSM425915 5 0.3730 0.6451 0.000 0.000 0.288 0.000 0.712
#> GSM425874 4 0.1356 0.7335 0.012 0.004 0.000 0.956 0.028
#> GSM425875 5 0.1205 0.8549 0.040 0.000 0.000 0.004 0.956
#> GSM425876 1 0.3116 0.7073 0.860 0.076 0.000 0.000 0.064
#> GSM425877 1 0.4521 0.5365 0.664 0.000 0.012 0.316 0.008
#> GSM425878 1 0.3323 0.7397 0.844 0.000 0.000 0.056 0.100
#> GSM425879 2 0.1168 0.8100 0.000 0.960 0.008 0.032 0.000
#> GSM425880 5 0.1278 0.8627 0.020 0.000 0.016 0.004 0.960
#> GSM425881 2 0.2280 0.7722 0.120 0.880 0.000 0.000 0.000
#> GSM425882 2 0.0000 0.8108 0.000 1.000 0.000 0.000 0.000
#> GSM425883 4 0.4777 0.3175 0.356 0.000 0.016 0.620 0.008
#> GSM425884 1 0.3039 0.7078 0.836 0.000 0.000 0.012 0.152
#> GSM425885 4 0.2654 0.7130 0.000 0.048 0.000 0.888 0.064
#> GSM425848 4 0.4902 0.0582 0.024 0.000 0.000 0.508 0.468
#> GSM425849 1 0.5382 0.5783 0.640 0.000 0.000 0.260 0.100
#> GSM425850 1 0.1753 0.7364 0.936 0.032 0.000 0.000 0.032
#> GSM425851 1 0.5722 0.4713 0.600 0.000 0.088 0.304 0.008
#> GSM425852 5 0.2464 0.8395 0.016 0.000 0.096 0.000 0.888
#> GSM425893 2 0.3912 0.6550 0.000 0.768 0.020 0.004 0.208
#> GSM425894 4 0.4533 0.4747 0.000 0.260 0.004 0.704 0.032
#> GSM425895 2 0.3579 0.6749 0.000 0.756 0.000 0.240 0.004
#> GSM425896 2 0.6939 0.2107 0.000 0.460 0.044 0.376 0.120
#> GSM425897 2 0.2293 0.7969 0.000 0.900 0.016 0.084 0.000
#> GSM425898 2 0.3521 0.6864 0.000 0.764 0.000 0.232 0.004
#> GSM425899 4 0.5138 0.5527 0.252 0.036 0.000 0.684 0.028
#> GSM425900 2 0.0880 0.8083 0.032 0.968 0.000 0.000 0.000
#> GSM425901 5 0.2171 0.8347 0.000 0.000 0.024 0.064 0.912
#> GSM425902 4 0.1697 0.7268 0.000 0.008 0.000 0.932 0.060
#> GSM425903 5 0.2074 0.8556 0.044 0.000 0.036 0.000 0.920
#> GSM425904 5 0.0854 0.8624 0.008 0.000 0.012 0.004 0.976
#> GSM425905 2 0.1478 0.8062 0.000 0.936 0.000 0.064 0.000
#> GSM425906 2 0.1357 0.8035 0.048 0.948 0.000 0.000 0.004
#> GSM425863 1 0.3090 0.7404 0.860 0.000 0.000 0.088 0.052
#> GSM425864 2 0.1704 0.8042 0.000 0.928 0.004 0.068 0.000
#> GSM425865 2 0.1638 0.8057 0.000 0.932 0.004 0.064 0.000
#> GSM425866 5 0.1571 0.8470 0.060 0.000 0.000 0.004 0.936
#> GSM425867 5 0.4848 0.3583 0.024 0.000 0.420 0.000 0.556
#> GSM425868 4 0.2672 0.7016 0.008 0.116 0.004 0.872 0.000
#> GSM425869 4 0.3474 0.6737 0.000 0.116 0.004 0.836 0.044
#> GSM425870 2 0.4620 0.3381 0.000 0.592 0.392 0.000 0.016
#> GSM425871 1 0.2338 0.7214 0.884 0.004 0.000 0.112 0.000
#> GSM425872 2 0.2471 0.7672 0.000 0.864 0.000 0.136 0.000
#> GSM425873 1 0.2863 0.7174 0.876 0.064 0.000 0.000 0.060
#> GSM425843 1 0.2249 0.7359 0.896 0.000 0.000 0.008 0.096
#> GSM425844 1 0.4491 0.4496 0.624 0.000 0.004 0.364 0.008
#> GSM425845 5 0.3266 0.7044 0.200 0.000 0.004 0.000 0.796
#> GSM425846 2 0.4332 0.7181 0.064 0.768 0.000 0.164 0.004
#> GSM425847 1 0.3916 0.5484 0.732 0.256 0.000 0.000 0.012
#> GSM425886 5 0.2871 0.8222 0.000 0.000 0.088 0.040 0.872
#> GSM425887 2 0.2127 0.7790 0.108 0.892 0.000 0.000 0.000
#> GSM425888 2 0.3550 0.6502 0.236 0.760 0.000 0.000 0.004
#> GSM425889 4 0.4054 0.6054 0.204 0.000 0.000 0.760 0.036
#> GSM425890 4 0.3053 0.6841 0.128 0.000 0.012 0.852 0.008
#> GSM425891 2 0.0000 0.8108 0.000 1.000 0.000 0.000 0.000
#> GSM425892 2 0.4705 0.1502 0.000 0.504 0.004 0.484 0.008
#> GSM425853 1 0.4273 0.2233 0.552 0.000 0.000 0.000 0.448
#> GSM425854 2 0.3003 0.7350 0.000 0.812 0.000 0.188 0.000
#> GSM425855 1 0.3527 0.6808 0.792 0.000 0.000 0.192 0.016
#> GSM425856 5 0.1430 0.8514 0.052 0.000 0.000 0.004 0.944
#> GSM425857 5 0.3689 0.6090 0.000 0.000 0.004 0.256 0.740
#> GSM425858 2 0.1121 0.8066 0.044 0.956 0.000 0.000 0.000
#> GSM425859 2 0.4114 0.4651 0.000 0.624 0.000 0.376 0.000
#> GSM425860 1 0.6634 0.2341 0.516 0.352 0.064 0.000 0.068
#> GSM425861 2 0.4740 0.1244 0.468 0.516 0.000 0.000 0.016
#> GSM425862 4 0.4462 0.6096 0.196 0.000 0.000 0.740 0.064
#> GSM425837 1 0.3527 0.6913 0.792 0.000 0.000 0.016 0.192
#> GSM425838 4 0.1124 0.7320 0.000 0.004 0.000 0.960 0.036
#> GSM425839 2 0.1908 0.7977 0.000 0.908 0.000 0.092 0.000
#> GSM425840 1 0.3336 0.7399 0.844 0.000 0.000 0.096 0.060
#> GSM425841 4 0.0898 0.7309 0.020 0.000 0.000 0.972 0.008
#> GSM425842 1 0.1942 0.7360 0.920 0.012 0.000 0.000 0.068
#> GSM425917 3 0.6150 0.4441 0.176 0.000 0.592 0.224 0.008
#> GSM425922 4 0.3129 0.6637 0.156 0.000 0.004 0.832 0.008
#> GSM425919 1 0.3661 0.7059 0.836 0.000 0.056 0.096 0.012
#> GSM425920 1 0.3201 0.7032 0.844 0.000 0.016 0.132 0.008
#> GSM425923 1 0.4865 0.2916 0.552 0.000 0.012 0.428 0.008
#> GSM425916 1 0.5160 0.5695 0.672 0.000 0.064 0.256 0.008
#> GSM425918 1 0.4617 0.5240 0.660 0.000 0.016 0.316 0.008
#> GSM425921 4 0.2722 0.6915 0.120 0.000 0.004 0.868 0.008
#> GSM425925 4 0.4371 0.3284 0.344 0.000 0.000 0.644 0.012
#> GSM425926 4 0.1892 0.7145 0.080 0.000 0.000 0.916 0.004
#> GSM425927 1 0.0955 0.7425 0.968 0.000 0.000 0.004 0.028
#> GSM425924 3 0.5732 0.5067 0.224 0.000 0.640 0.128 0.008
#> GSM425928 3 0.0566 0.9139 0.000 0.000 0.984 0.012 0.004
#> GSM425929 3 0.0162 0.9210 0.000 0.000 0.996 0.000 0.004
#> GSM425930 3 0.0290 0.9208 0.000 0.000 0.992 0.000 0.008
#> GSM425931 3 0.0162 0.9218 0.000 0.000 0.996 0.000 0.004
#> GSM425932 3 0.0000 0.9217 0.000 0.000 1.000 0.000 0.000
#> GSM425933 3 0.0162 0.9218 0.000 0.000 0.996 0.000 0.004
#> GSM425934 3 0.0451 0.9163 0.000 0.008 0.988 0.000 0.004
#> GSM425935 3 0.0727 0.9144 0.000 0.012 0.980 0.004 0.004
#> GSM425936 3 0.0162 0.9210 0.000 0.000 0.996 0.004 0.000
#> GSM425937 3 0.0162 0.9218 0.000 0.000 0.996 0.000 0.004
#> GSM425938 3 0.0290 0.9195 0.000 0.000 0.992 0.000 0.008
#> GSM425939 3 0.0290 0.9208 0.000 0.000 0.992 0.000 0.008
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 4 0.3899 -0.02358 0.000 0.404 0.000 0.592 0.004 0.000
#> GSM425908 4 0.3585 0.47546 0.048 0.172 0.000 0.780 0.000 0.000
#> GSM425909 5 0.0935 0.89622 0.000 0.000 0.004 0.032 0.964 0.000
#> GSM425910 1 0.6515 0.42214 0.560 0.088 0.000 0.004 0.156 0.192
#> GSM425911 2 0.2337 0.71324 0.016 0.908 0.000 0.048 0.016 0.012
#> GSM425912 2 0.2575 0.68567 0.072 0.880 0.000 0.004 0.000 0.044
#> GSM425913 2 0.1251 0.71344 0.008 0.956 0.000 0.012 0.000 0.024
#> GSM425914 2 0.2512 0.69907 0.040 0.896 0.000 0.008 0.008 0.048
#> GSM425915 5 0.1714 0.86939 0.000 0.000 0.092 0.000 0.908 0.000
#> GSM425874 4 0.3903 0.36979 0.012 0.000 0.000 0.680 0.004 0.304
#> GSM425875 5 0.2703 0.78322 0.000 0.000 0.000 0.004 0.824 0.172
#> GSM425876 1 0.5239 0.51624 0.692 0.092 0.000 0.004 0.048 0.164
#> GSM425877 1 0.4862 0.51229 0.664 0.000 0.000 0.172 0.000 0.164
#> GSM425878 1 0.6016 0.45573 0.544 0.000 0.000 0.084 0.064 0.308
#> GSM425879 2 0.2333 0.69919 0.000 0.872 0.004 0.120 0.004 0.000
#> GSM425880 5 0.0405 0.90192 0.008 0.000 0.000 0.000 0.988 0.004
#> GSM425881 2 0.3823 0.60458 0.044 0.760 0.000 0.004 0.000 0.192
#> GSM425882 2 0.2269 0.71151 0.012 0.896 0.000 0.080 0.000 0.012
#> GSM425883 6 0.6075 0.16156 0.312 0.004 0.004 0.208 0.000 0.472
#> GSM425884 1 0.5272 0.56006 0.688 0.000 0.000 0.064 0.096 0.152
#> GSM425885 4 0.1767 0.54564 0.000 0.012 0.000 0.932 0.020 0.036
#> GSM425848 4 0.5384 0.30810 0.044 0.000 0.000 0.580 0.328 0.048
#> GSM425849 6 0.4064 0.53705 0.092 0.000 0.000 0.132 0.008 0.768
#> GSM425850 1 0.3859 0.56524 0.804 0.056 0.000 0.008 0.016 0.116
#> GSM425851 1 0.3894 0.51391 0.740 0.000 0.004 0.220 0.000 0.036
#> GSM425852 5 0.1899 0.89522 0.032 0.000 0.028 0.008 0.928 0.004
#> GSM425893 2 0.5521 0.22651 0.004 0.508 0.004 0.076 0.400 0.008
#> GSM425894 4 0.5415 0.28908 0.000 0.128 0.000 0.564 0.004 0.304
#> GSM425895 2 0.5138 0.45273 0.000 0.604 0.000 0.268 0.000 0.128
#> GSM425896 4 0.5367 0.02980 0.000 0.344 0.000 0.532 0.124 0.000
#> GSM425897 2 0.2700 0.69226 0.000 0.836 0.000 0.156 0.004 0.004
#> GSM425898 2 0.5655 0.26117 0.000 0.504 0.000 0.324 0.000 0.172
#> GSM425899 6 0.4543 0.48192 0.056 0.012 0.000 0.204 0.008 0.720
#> GSM425900 2 0.4320 0.14820 0.008 0.516 0.000 0.008 0.000 0.468
#> GSM425901 5 0.1296 0.89201 0.000 0.000 0.004 0.044 0.948 0.004
#> GSM425902 6 0.4581 0.00933 0.000 0.000 0.000 0.448 0.036 0.516
#> GSM425903 5 0.0951 0.90014 0.020 0.000 0.008 0.000 0.968 0.004
#> GSM425904 5 0.0436 0.90209 0.004 0.000 0.004 0.000 0.988 0.004
#> GSM425905 2 0.2597 0.67378 0.000 0.824 0.000 0.176 0.000 0.000
#> GSM425906 2 0.1296 0.70958 0.012 0.952 0.000 0.004 0.000 0.032
#> GSM425863 6 0.2479 0.55488 0.064 0.000 0.000 0.028 0.016 0.892
#> GSM425864 2 0.2878 0.68370 0.004 0.828 0.000 0.160 0.004 0.004
#> GSM425865 2 0.2340 0.69407 0.000 0.852 0.000 0.148 0.000 0.000
#> GSM425866 5 0.0508 0.90168 0.004 0.000 0.000 0.000 0.984 0.012
#> GSM425867 5 0.4381 0.68231 0.024 0.000 0.236 0.000 0.708 0.032
#> GSM425868 4 0.3847 0.54341 0.064 0.068 0.000 0.812 0.000 0.056
#> GSM425869 4 0.3695 0.48560 0.000 0.044 0.000 0.776 0.004 0.176
#> GSM425870 2 0.3451 0.66303 0.024 0.828 0.124 0.004 0.012 0.008
#> GSM425871 1 0.2189 0.59085 0.904 0.004 0.000 0.032 0.000 0.060
#> GSM425872 6 0.5543 -0.09891 0.008 0.444 0.000 0.088 0.004 0.456
#> GSM425873 1 0.5511 0.43278 0.592 0.068 0.000 0.004 0.032 0.304
#> GSM425843 1 0.5029 0.27596 0.484 0.000 0.000 0.000 0.072 0.444
#> GSM425844 1 0.3745 0.49278 0.732 0.000 0.000 0.240 0.000 0.028
#> GSM425845 5 0.3634 0.77112 0.072 0.004 0.000 0.004 0.808 0.112
#> GSM425846 6 0.5138 0.36510 0.000 0.208 0.000 0.168 0.000 0.624
#> GSM425847 1 0.5938 0.29198 0.520 0.296 0.000 0.004 0.008 0.172
#> GSM425886 5 0.2019 0.86401 0.000 0.000 0.012 0.088 0.900 0.000
#> GSM425887 2 0.4145 0.58680 0.052 0.740 0.000 0.004 0.004 0.200
#> GSM425888 2 0.5395 0.14156 0.100 0.496 0.000 0.004 0.000 0.400
#> GSM425889 6 0.4282 0.47850 0.036 0.000 0.000 0.200 0.028 0.736
#> GSM425890 4 0.4334 0.13083 0.408 0.000 0.000 0.568 0.000 0.024
#> GSM425891 2 0.0692 0.71174 0.000 0.976 0.000 0.004 0.000 0.020
#> GSM425892 2 0.3997 0.23471 0.000 0.508 0.000 0.488 0.004 0.000
#> GSM425853 1 0.5804 0.18091 0.436 0.000 0.000 0.004 0.404 0.156
#> GSM425854 2 0.4697 0.45329 0.000 0.612 0.000 0.324 0.000 0.064
#> GSM425855 6 0.3979 0.39805 0.256 0.000 0.000 0.036 0.000 0.708
#> GSM425856 5 0.1268 0.89446 0.008 0.000 0.000 0.004 0.952 0.036
#> GSM425857 5 0.2703 0.78603 0.000 0.000 0.004 0.172 0.824 0.000
#> GSM425858 2 0.4026 0.41733 0.000 0.636 0.000 0.016 0.000 0.348
#> GSM425859 2 0.4159 0.40647 0.000 0.588 0.000 0.396 0.000 0.016
#> GSM425860 6 0.8265 -0.12407 0.252 0.176 0.216 0.004 0.032 0.320
#> GSM425861 6 0.4204 0.44760 0.088 0.152 0.000 0.000 0.008 0.752
#> GSM425862 6 0.4766 0.46371 0.052 0.000 0.000 0.204 0.040 0.704
#> GSM425837 6 0.5280 0.08138 0.328 0.000 0.000 0.004 0.104 0.564
#> GSM425838 4 0.1845 0.53489 0.072 0.000 0.000 0.916 0.008 0.004
#> GSM425839 2 0.4209 0.62216 0.000 0.736 0.000 0.160 0.000 0.104
#> GSM425840 6 0.4513 0.19435 0.304 0.000 0.000 0.024 0.020 0.652
#> GSM425841 4 0.3778 0.40592 0.020 0.000 0.000 0.708 0.000 0.272
#> GSM425842 1 0.4696 0.51445 0.688 0.032 0.000 0.008 0.024 0.248
#> GSM425917 1 0.6502 0.20798 0.456 0.000 0.316 0.188 0.000 0.040
#> GSM425922 4 0.4747 0.17782 0.376 0.000 0.000 0.568 0.000 0.056
#> GSM425919 1 0.2745 0.59264 0.884 0.000 0.020 0.040 0.004 0.052
#> GSM425920 1 0.2474 0.58398 0.880 0.000 0.000 0.040 0.000 0.080
#> GSM425923 1 0.4595 0.43175 0.668 0.000 0.000 0.248 0.000 0.084
#> GSM425916 1 0.3652 0.52891 0.760 0.000 0.008 0.212 0.000 0.020
#> GSM425918 1 0.3488 0.54381 0.780 0.000 0.000 0.184 0.000 0.036
#> GSM425921 4 0.5711 0.22020 0.180 0.000 0.000 0.492 0.000 0.328
#> GSM425925 6 0.3652 0.49679 0.032 0.000 0.000 0.196 0.004 0.768
#> GSM425926 4 0.4449 0.08070 0.028 0.000 0.000 0.532 0.000 0.440
#> GSM425927 1 0.4313 0.48891 0.664 0.008 0.000 0.004 0.020 0.304
#> GSM425924 1 0.5302 0.12423 0.500 0.000 0.424 0.056 0.000 0.020
#> GSM425928 3 0.0146 0.99485 0.004 0.000 0.996 0.000 0.000 0.000
#> GSM425929 3 0.0000 0.99772 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425930 3 0.0146 0.99451 0.004 0.000 0.996 0.000 0.000 0.000
#> GSM425931 3 0.0000 0.99772 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425932 3 0.0000 0.99772 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425933 3 0.0000 0.99772 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425934 3 0.0000 0.99772 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425935 3 0.0436 0.98906 0.000 0.004 0.988 0.004 0.000 0.004
#> GSM425936 3 0.0146 0.99504 0.000 0.000 0.996 0.000 0.000 0.004
#> GSM425937 3 0.0000 0.99772 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425938 3 0.0000 0.99772 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425939 3 0.0000 0.99772 0.000 0.000 1.000 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 disease.state(p) tissue(p) other(p) k
#> CV:NMF 90 4.08e-07 4.56e-07 2.98e-06 2
#> CV:NMF 90 1.32e-10 2.45e-11 5.10e-10 3
#> CV:NMF 82 1.86e-09 6.08e-09 1.07e-05 4
#> CV:NMF 85 6.23e-16 1.02e-15 1.07e-09 5
#> CV:NMF 58 3.15e-11 3.68e-12 2.82e-06 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 103 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 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 0.0848 0.342 0.664 0.4459 0.639 0.639
#> 3 3 0.1503 0.454 0.619 0.3688 0.621 0.472
#> 4 4 0.3341 0.507 0.684 0.1677 0.824 0.591
#> 5 5 0.5165 0.511 0.675 0.0759 0.962 0.863
#> 6 6 0.5846 0.551 0.704 0.0389 0.939 0.762
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
#> GSM425907 2 0.991 0.3826 0.444 0.556
#> GSM425908 2 0.998 0.3612 0.476 0.524
#> GSM425909 2 0.871 0.3779 0.292 0.708
#> GSM425910 2 0.706 0.4031 0.192 0.808
#> GSM425911 2 0.821 0.4851 0.256 0.744
#> GSM425912 2 0.605 0.4767 0.148 0.852
#> GSM425913 2 0.939 0.4400 0.356 0.644
#> GSM425914 2 0.671 0.4349 0.176 0.824
#> GSM425915 2 0.714 0.4832 0.196 0.804
#> GSM425874 1 0.563 0.4573 0.868 0.132
#> GSM425875 2 0.795 0.2853 0.240 0.760
#> GSM425876 2 0.802 0.3047 0.244 0.756
#> GSM425877 2 1.000 -0.4024 0.488 0.512
#> GSM425878 2 0.981 -0.2354 0.420 0.580
#> GSM425879 2 0.981 0.4014 0.420 0.580
#> GSM425880 2 0.808 0.3017 0.248 0.752
#> GSM425881 2 0.605 0.4913 0.148 0.852
#> GSM425882 2 0.995 0.3747 0.460 0.540
#> GSM425883 1 0.990 0.4584 0.560 0.440
#> GSM425884 2 0.993 -0.3524 0.452 0.548
#> GSM425885 1 0.932 0.0186 0.652 0.348
#> GSM425848 1 0.996 0.4049 0.536 0.464
#> GSM425849 2 1.000 -0.3470 0.492 0.508
#> GSM425850 2 0.932 0.0641 0.348 0.652
#> GSM425851 1 1.000 0.4194 0.504 0.496
#> GSM425852 2 0.767 0.3427 0.224 0.776
#> GSM425893 2 0.943 0.4418 0.360 0.640
#> GSM425894 2 0.987 0.3856 0.432 0.568
#> GSM425895 2 0.929 0.4463 0.344 0.656
#> GSM425896 2 0.973 0.4134 0.404 0.596
#> GSM425897 2 0.958 0.4282 0.380 0.620
#> GSM425898 2 0.973 0.4042 0.404 0.596
#> GSM425899 2 0.991 0.3823 0.444 0.556
#> GSM425900 2 0.929 0.4465 0.344 0.656
#> GSM425901 2 0.886 0.3718 0.304 0.696
#> GSM425902 1 0.563 0.4573 0.868 0.132
#> GSM425903 2 0.584 0.4422 0.140 0.860
#> GSM425904 2 0.808 0.3017 0.248 0.752
#> GSM425905 2 0.988 0.3891 0.436 0.564
#> GSM425906 2 0.866 0.4683 0.288 0.712
#> GSM425863 1 0.990 0.4491 0.560 0.440
#> GSM425864 2 0.971 0.4208 0.400 0.600
#> GSM425865 2 0.991 0.3952 0.444 0.556
#> GSM425866 2 0.795 0.2853 0.240 0.760
#> GSM425867 2 0.680 0.3851 0.180 0.820
#> GSM425868 2 1.000 0.3557 0.488 0.512
#> GSM425869 2 0.992 0.3691 0.448 0.552
#> GSM425870 2 0.563 0.4982 0.132 0.868
#> GSM425871 2 0.990 -0.1933 0.440 0.560
#> GSM425872 2 0.969 0.4116 0.396 0.604
#> GSM425873 2 0.913 0.0441 0.328 0.672
#> GSM425843 2 1.000 -0.4024 0.488 0.512
#> GSM425844 2 0.988 -0.2254 0.436 0.564
#> GSM425845 2 0.689 0.3859 0.184 0.816
#> GSM425846 2 0.993 0.3748 0.452 0.548
#> GSM425847 2 0.625 0.4662 0.156 0.844
#> GSM425886 2 0.760 0.4820 0.220 0.780
#> GSM425887 2 0.929 0.4477 0.344 0.656
#> GSM425888 2 0.605 0.4913 0.148 0.852
#> GSM425889 1 0.955 0.5060 0.624 0.376
#> GSM425890 1 0.971 0.5019 0.600 0.400
#> GSM425891 2 0.943 0.4417 0.360 0.640
#> GSM425892 1 0.998 -0.3203 0.524 0.476
#> GSM425853 2 0.821 0.2589 0.256 0.744
#> GSM425854 2 0.939 0.4427 0.356 0.644
#> GSM425855 1 0.997 0.4066 0.532 0.468
#> GSM425856 2 0.795 0.2853 0.240 0.760
#> GSM425857 2 0.943 0.3517 0.360 0.640
#> GSM425858 2 0.904 0.4583 0.320 0.680
#> GSM425859 2 0.990 0.3766 0.440 0.560
#> GSM425860 2 0.706 0.3880 0.192 0.808
#> GSM425861 2 0.605 0.4913 0.148 0.852
#> GSM425862 1 0.952 0.5057 0.628 0.372
#> GSM425837 1 1.000 0.4252 0.512 0.488
#> GSM425838 1 0.625 0.4044 0.844 0.156
#> GSM425839 2 0.988 0.3766 0.436 0.564
#> GSM425840 1 0.999 0.3850 0.520 0.480
#> GSM425841 1 0.563 0.4573 0.868 0.132
#> GSM425842 2 0.939 -0.0694 0.356 0.644
#> GSM425917 2 0.529 0.4578 0.120 0.880
#> GSM425922 1 0.563 0.4676 0.868 0.132
#> GSM425919 1 1.000 0.4194 0.504 0.496
#> GSM425920 2 0.994 -0.2852 0.456 0.544
#> GSM425923 1 0.990 0.4756 0.560 0.440
#> GSM425916 1 0.988 0.4545 0.564 0.436
#> GSM425918 1 0.991 0.4759 0.556 0.444
#> GSM425921 1 0.563 0.4676 0.868 0.132
#> GSM425925 1 0.529 0.4654 0.880 0.120
#> GSM425926 1 0.552 0.4650 0.872 0.128
#> GSM425927 2 0.980 -0.2273 0.416 0.584
#> GSM425924 2 0.552 0.4568 0.128 0.872
#> GSM425928 2 0.358 0.5042 0.068 0.932
#> GSM425929 2 0.358 0.5042 0.068 0.932
#> GSM425930 2 0.358 0.5042 0.068 0.932
#> GSM425931 2 0.358 0.5042 0.068 0.932
#> GSM425932 2 0.358 0.5042 0.068 0.932
#> GSM425933 2 0.358 0.5042 0.068 0.932
#> GSM425934 2 0.358 0.5042 0.068 0.932
#> GSM425935 2 0.358 0.5042 0.068 0.932
#> GSM425936 2 0.358 0.5042 0.068 0.932
#> GSM425937 2 0.358 0.5042 0.068 0.932
#> GSM425938 2 0.358 0.5042 0.068 0.932
#> GSM425939 2 0.358 0.5042 0.068 0.932
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.249 0.8314 0.016 0.936 0.048
#> GSM425908 2 0.344 0.8172 0.016 0.896 0.088
#> GSM425909 1 0.880 0.3769 0.556 0.300 0.144
#> GSM425910 1 0.749 0.4895 0.664 0.256 0.080
#> GSM425911 2 0.710 0.4450 0.280 0.668 0.052
#> GSM425912 1 0.832 0.3045 0.524 0.392 0.084
#> GSM425913 2 0.429 0.8098 0.092 0.868 0.040
#> GSM425914 1 0.788 0.4528 0.612 0.308 0.080
#> GSM425915 1 0.787 0.3245 0.552 0.388 0.060
#> GSM425874 3 0.540 0.6253 0.004 0.256 0.740
#> GSM425875 1 0.625 0.4826 0.772 0.144 0.084
#> GSM425876 1 0.683 0.4474 0.736 0.168 0.096
#> GSM425877 1 0.721 0.0863 0.604 0.036 0.360
#> GSM425878 1 0.748 0.1997 0.632 0.060 0.308
#> GSM425879 2 0.281 0.8399 0.036 0.928 0.036
#> GSM425880 1 0.699 0.4819 0.724 0.180 0.096
#> GSM425881 1 0.846 0.1990 0.476 0.436 0.088
#> GSM425882 2 0.401 0.8232 0.036 0.880 0.084
#> GSM425883 3 0.862 0.2248 0.424 0.100 0.476
#> GSM425884 1 0.695 0.1490 0.636 0.032 0.332
#> GSM425885 2 0.762 0.1660 0.048 0.560 0.392
#> GSM425848 1 0.841 -0.0672 0.508 0.088 0.404
#> GSM425849 1 0.812 0.0122 0.532 0.072 0.396
#> GSM425850 1 0.851 0.3154 0.604 0.152 0.244
#> GSM425851 1 0.692 -0.0399 0.580 0.020 0.400
#> GSM425852 1 0.691 0.4959 0.724 0.192 0.084
#> GSM425893 2 0.504 0.7682 0.104 0.836 0.060
#> GSM425894 2 0.266 0.8417 0.024 0.932 0.044
#> GSM425895 2 0.550 0.7939 0.124 0.812 0.064
#> GSM425896 2 0.369 0.8135 0.052 0.896 0.052
#> GSM425897 2 0.421 0.7969 0.088 0.872 0.040
#> GSM425898 2 0.338 0.8385 0.048 0.908 0.044
#> GSM425899 2 0.581 0.7865 0.072 0.796 0.132
#> GSM425900 2 0.494 0.8001 0.104 0.840 0.056
#> GSM425901 1 0.899 0.3398 0.528 0.320 0.152
#> GSM425902 3 0.550 0.6283 0.008 0.248 0.744
#> GSM425903 1 0.728 0.5136 0.672 0.260 0.068
#> GSM425904 1 0.699 0.4819 0.724 0.180 0.096
#> GSM425905 2 0.253 0.8347 0.020 0.936 0.044
#> GSM425906 2 0.596 0.6971 0.188 0.768 0.044
#> GSM425863 3 0.858 0.1535 0.452 0.096 0.452
#> GSM425864 2 0.338 0.8248 0.044 0.908 0.048
#> GSM425865 2 0.397 0.8307 0.044 0.884 0.072
#> GSM425866 1 0.625 0.4826 0.772 0.144 0.084
#> GSM425867 1 0.666 0.5122 0.736 0.192 0.072
#> GSM425868 2 0.400 0.8062 0.016 0.868 0.116
#> GSM425869 2 0.341 0.8316 0.020 0.900 0.080
#> GSM425870 1 0.792 0.2379 0.484 0.460 0.056
#> GSM425871 1 0.833 0.1580 0.564 0.096 0.340
#> GSM425872 2 0.380 0.8350 0.056 0.892 0.052
#> GSM425873 1 0.736 0.3651 0.700 0.112 0.188
#> GSM425843 1 0.721 0.0863 0.604 0.036 0.360
#> GSM425844 1 0.818 0.1222 0.564 0.084 0.352
#> GSM425845 1 0.719 0.5061 0.696 0.224 0.080
#> GSM425846 2 0.611 0.7718 0.080 0.780 0.140
#> GSM425847 1 0.831 0.3703 0.556 0.352 0.092
#> GSM425886 1 0.805 0.2141 0.500 0.436 0.064
#> GSM425887 2 0.566 0.7888 0.128 0.804 0.068
#> GSM425888 1 0.845 0.2100 0.480 0.432 0.088
#> GSM425889 3 0.867 0.3385 0.412 0.104 0.484
#> GSM425890 3 0.749 0.3644 0.380 0.044 0.576
#> GSM425891 2 0.460 0.8061 0.108 0.852 0.040
#> GSM425892 2 0.579 0.7326 0.048 0.784 0.168
#> GSM425853 1 0.641 0.4775 0.764 0.144 0.092
#> GSM425854 2 0.521 0.8139 0.108 0.828 0.064
#> GSM425855 1 0.813 -0.0375 0.528 0.072 0.400
#> GSM425856 1 0.625 0.4826 0.772 0.144 0.084
#> GSM425857 1 0.940 0.2198 0.452 0.372 0.176
#> GSM425858 2 0.582 0.7621 0.144 0.792 0.064
#> GSM425859 2 0.270 0.8386 0.016 0.928 0.056
#> GSM425860 1 0.750 0.4937 0.672 0.240 0.088
#> GSM425861 1 0.845 0.2100 0.480 0.432 0.088
#> GSM425862 3 0.866 0.3459 0.408 0.104 0.488
#> GSM425837 1 0.675 -0.0278 0.596 0.016 0.388
#> GSM425838 3 0.687 0.5608 0.040 0.288 0.672
#> GSM425839 2 0.238 0.8400 0.016 0.940 0.044
#> GSM425840 1 0.818 -0.0218 0.532 0.076 0.392
#> GSM425841 3 0.558 0.6250 0.008 0.256 0.736
#> GSM425842 1 0.753 0.3220 0.676 0.096 0.228
#> GSM425917 1 0.850 0.4314 0.576 0.304 0.120
#> GSM425922 3 0.489 0.6368 0.000 0.228 0.772
#> GSM425919 1 0.692 -0.0399 0.580 0.020 0.400
#> GSM425920 1 0.777 0.1376 0.592 0.064 0.344
#> GSM425923 3 0.667 0.2375 0.468 0.008 0.524
#> GSM425916 1 0.652 -0.2190 0.508 0.004 0.488
#> GSM425918 3 0.666 0.2416 0.460 0.008 0.532
#> GSM425921 3 0.489 0.6368 0.000 0.228 0.772
#> GSM425925 3 0.554 0.6362 0.012 0.236 0.752
#> GSM425926 3 0.493 0.6354 0.000 0.232 0.768
#> GSM425927 1 0.756 0.2524 0.644 0.072 0.284
#> GSM425924 1 0.841 0.4329 0.580 0.308 0.112
#> GSM425928 1 0.823 0.3589 0.536 0.384 0.080
#> GSM425929 1 0.823 0.3589 0.536 0.384 0.080
#> GSM425930 1 0.823 0.3589 0.536 0.384 0.080
#> GSM425931 1 0.823 0.3589 0.536 0.384 0.080
#> GSM425932 1 0.823 0.3589 0.536 0.384 0.080
#> GSM425933 1 0.823 0.3589 0.536 0.384 0.080
#> GSM425934 1 0.823 0.3589 0.536 0.384 0.080
#> GSM425935 1 0.823 0.3589 0.536 0.384 0.080
#> GSM425936 1 0.823 0.3589 0.536 0.384 0.080
#> GSM425937 1 0.823 0.3589 0.536 0.384 0.080
#> GSM425938 1 0.823 0.3589 0.536 0.384 0.080
#> GSM425939 1 0.823 0.3589 0.536 0.384 0.080
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.299 0.8049 0.008 0.900 0.056 0.036
#> GSM425908 2 0.326 0.8024 0.012 0.888 0.032 0.068
#> GSM425909 3 0.838 0.4586 0.176 0.168 0.556 0.100
#> GSM425910 1 0.574 0.4747 0.700 0.092 0.208 0.000
#> GSM425911 2 0.789 0.1095 0.184 0.436 0.368 0.012
#> GSM425912 1 0.665 0.3898 0.608 0.280 0.108 0.004
#> GSM425913 2 0.418 0.8004 0.084 0.844 0.056 0.016
#> GSM425914 1 0.640 0.4394 0.648 0.144 0.208 0.000
#> GSM425915 3 0.751 0.4944 0.180 0.200 0.592 0.028
#> GSM425874 4 0.338 0.6823 0.008 0.116 0.012 0.864
#> GSM425875 1 0.734 0.0315 0.468 0.048 0.432 0.052
#> GSM425876 1 0.373 0.5600 0.848 0.044 0.108 0.000
#> GSM425877 1 0.628 0.4164 0.656 0.000 0.128 0.216
#> GSM425878 1 0.501 0.5113 0.776 0.008 0.060 0.156
#> GSM425879 2 0.339 0.8118 0.020 0.884 0.068 0.028
#> GSM425880 3 0.755 0.1205 0.396 0.064 0.488 0.052
#> GSM425881 1 0.678 0.2845 0.568 0.336 0.088 0.008
#> GSM425882 2 0.408 0.8070 0.032 0.856 0.048 0.064
#> GSM425883 1 0.764 0.0960 0.448 0.028 0.104 0.420
#> GSM425884 1 0.550 0.4704 0.728 0.000 0.096 0.176
#> GSM425885 2 0.696 0.0994 0.012 0.476 0.076 0.436
#> GSM425848 1 0.733 0.3412 0.564 0.028 0.100 0.308
#> GSM425849 1 0.556 0.4283 0.676 0.008 0.032 0.284
#> GSM425850 1 0.591 0.5320 0.748 0.060 0.056 0.136
#> GSM425851 3 0.804 -0.1928 0.312 0.008 0.424 0.256
#> GSM425852 3 0.758 0.2159 0.368 0.080 0.508 0.044
#> GSM425893 2 0.571 0.6049 0.032 0.692 0.256 0.020
#> GSM425894 2 0.230 0.8196 0.012 0.932 0.024 0.032
#> GSM425895 2 0.494 0.7876 0.124 0.800 0.044 0.032
#> GSM425896 2 0.461 0.6958 0.004 0.768 0.204 0.024
#> GSM425897 2 0.507 0.6420 0.012 0.720 0.252 0.016
#> GSM425898 2 0.294 0.8170 0.028 0.908 0.032 0.032
#> GSM425899 2 0.548 0.7482 0.056 0.764 0.032 0.148
#> GSM425900 2 0.440 0.7912 0.100 0.832 0.044 0.024
#> GSM425901 3 0.836 0.4759 0.148 0.184 0.560 0.108
#> GSM425902 4 0.349 0.6818 0.008 0.116 0.016 0.860
#> GSM425903 1 0.697 -0.0516 0.456 0.096 0.444 0.004
#> GSM425904 3 0.755 0.1205 0.396 0.064 0.488 0.052
#> GSM425905 2 0.290 0.8069 0.008 0.904 0.056 0.032
#> GSM425906 2 0.545 0.7067 0.184 0.740 0.068 0.008
#> GSM425863 1 0.732 0.2161 0.504 0.028 0.080 0.388
#> GSM425864 2 0.472 0.7620 0.016 0.796 0.152 0.036
#> GSM425865 2 0.423 0.8068 0.032 0.848 0.068 0.052
#> GSM425866 1 0.734 0.0315 0.468 0.048 0.432 0.052
#> GSM425867 1 0.589 0.3814 0.640 0.048 0.308 0.004
#> GSM425868 2 0.404 0.7860 0.012 0.840 0.032 0.116
#> GSM425869 2 0.252 0.8138 0.000 0.912 0.024 0.064
#> GSM425870 3 0.796 0.0066 0.364 0.248 0.384 0.004
#> GSM425871 1 0.586 0.4737 0.712 0.036 0.036 0.216
#> GSM425872 2 0.312 0.8147 0.044 0.900 0.032 0.024
#> GSM425873 1 0.419 0.5589 0.848 0.024 0.068 0.060
#> GSM425843 1 0.628 0.4164 0.656 0.000 0.128 0.216
#> GSM425844 1 0.657 0.4329 0.656 0.024 0.080 0.240
#> GSM425845 1 0.594 0.4327 0.664 0.064 0.268 0.004
#> GSM425846 2 0.568 0.7351 0.064 0.752 0.032 0.152
#> GSM425847 1 0.631 0.4461 0.652 0.244 0.100 0.004
#> GSM425886 3 0.762 0.5040 0.144 0.252 0.572 0.032
#> GSM425887 2 0.491 0.7830 0.128 0.800 0.040 0.032
#> GSM425888 1 0.664 0.2772 0.572 0.344 0.076 0.008
#> GSM425889 4 0.788 0.1021 0.344 0.028 0.140 0.488
#> GSM425890 4 0.785 0.3429 0.204 0.012 0.296 0.488
#> GSM425891 2 0.487 0.7892 0.096 0.804 0.084 0.016
#> GSM425892 2 0.592 0.7197 0.032 0.740 0.084 0.144
#> GSM425853 1 0.703 0.2610 0.560 0.044 0.348 0.048
#> GSM425854 2 0.454 0.8025 0.096 0.828 0.040 0.036
#> GSM425855 1 0.687 0.3824 0.608 0.024 0.080 0.288
#> GSM425856 1 0.734 0.0315 0.468 0.048 0.432 0.052
#> GSM425857 3 0.833 0.4839 0.092 0.236 0.544 0.128
#> GSM425858 2 0.500 0.7672 0.136 0.792 0.044 0.028
#> GSM425859 2 0.193 0.8174 0.000 0.940 0.024 0.036
#> GSM425860 1 0.564 0.4810 0.704 0.064 0.228 0.004
#> GSM425861 1 0.664 0.2772 0.572 0.344 0.076 0.008
#> GSM425862 4 0.787 0.1151 0.340 0.028 0.140 0.492
#> GSM425837 1 0.723 0.2954 0.540 0.000 0.192 0.268
#> GSM425838 4 0.512 0.6093 0.052 0.168 0.012 0.768
#> GSM425839 2 0.202 0.8189 0.004 0.940 0.028 0.028
#> GSM425840 1 0.677 0.3958 0.620 0.024 0.076 0.280
#> GSM425841 4 0.349 0.6815 0.008 0.116 0.016 0.860
#> GSM425842 1 0.433 0.5513 0.836 0.016 0.064 0.084
#> GSM425917 3 0.539 0.6300 0.048 0.120 0.780 0.052
#> GSM425922 4 0.253 0.6901 0.008 0.072 0.008 0.912
#> GSM425919 3 0.804 -0.1928 0.312 0.008 0.424 0.256
#> GSM425920 1 0.700 0.3519 0.612 0.008 0.184 0.196
#> GSM425923 4 0.786 0.2016 0.276 0.000 0.340 0.384
#> GSM425916 3 0.786 -0.3210 0.276 0.000 0.388 0.336
#> GSM425918 4 0.783 0.2170 0.264 0.000 0.340 0.396
#> GSM425921 4 0.253 0.6901 0.008 0.072 0.008 0.912
#> GSM425925 4 0.307 0.6859 0.024 0.076 0.008 0.892
#> GSM425926 4 0.238 0.6898 0.008 0.072 0.004 0.916
#> GSM425927 1 0.519 0.5227 0.776 0.012 0.080 0.132
#> GSM425924 3 0.539 0.6297 0.048 0.120 0.780 0.052
#> GSM425928 3 0.340 0.6980 0.008 0.152 0.840 0.000
#> GSM425929 3 0.340 0.6980 0.008 0.152 0.840 0.000
#> GSM425930 3 0.340 0.6980 0.008 0.152 0.840 0.000
#> GSM425931 3 0.340 0.6980 0.008 0.152 0.840 0.000
#> GSM425932 3 0.340 0.6980 0.008 0.152 0.840 0.000
#> GSM425933 3 0.340 0.6980 0.008 0.152 0.840 0.000
#> GSM425934 3 0.340 0.6980 0.008 0.152 0.840 0.000
#> GSM425935 3 0.340 0.6980 0.008 0.152 0.840 0.000
#> GSM425936 3 0.340 0.6980 0.008 0.152 0.840 0.000
#> GSM425937 3 0.340 0.6980 0.008 0.152 0.840 0.000
#> GSM425938 3 0.340 0.6980 0.008 0.152 0.840 0.000
#> GSM425939 3 0.340 0.6980 0.008 0.152 0.840 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM425907 2 0.391 0.79944 0.004 0.824 0.072 0.008 0.092
#> GSM425908 2 0.440 0.79073 0.004 0.804 0.040 0.048 0.104
#> GSM425909 3 0.757 0.40536 0.088 0.072 0.460 0.024 0.356
#> GSM425910 1 0.512 0.46280 0.712 0.048 0.208 0.000 0.032
#> GSM425911 3 0.741 0.04952 0.176 0.356 0.416 0.000 0.052
#> GSM425912 1 0.585 0.39376 0.628 0.272 0.064 0.000 0.036
#> GSM425913 2 0.333 0.80599 0.076 0.868 0.028 0.008 0.020
#> GSM425914 1 0.582 0.45131 0.660 0.104 0.208 0.000 0.028
#> GSM425915 3 0.753 0.44509 0.128 0.108 0.516 0.004 0.244
#> GSM425874 4 0.284 0.68223 0.004 0.056 0.004 0.888 0.048
#> GSM425875 1 0.714 0.00257 0.384 0.000 0.344 0.016 0.256
#> GSM425876 1 0.313 0.48788 0.872 0.020 0.076 0.000 0.032
#> GSM425877 1 0.668 0.15575 0.584 0.000 0.060 0.116 0.240
#> GSM425878 1 0.533 0.40582 0.720 0.004 0.024 0.088 0.164
#> GSM425879 2 0.374 0.81020 0.008 0.836 0.080 0.004 0.072
#> GSM425880 3 0.718 0.10010 0.316 0.000 0.384 0.016 0.284
#> GSM425881 1 0.589 0.29328 0.584 0.336 0.048 0.004 0.028
#> GSM425882 2 0.512 0.79383 0.024 0.772 0.052 0.048 0.104
#> GSM425883 1 0.775 0.08043 0.416 0.020 0.060 0.372 0.132
#> GSM425884 1 0.570 0.29722 0.672 0.000 0.036 0.080 0.212
#> GSM425885 4 0.731 -0.03375 0.000 0.392 0.072 0.416 0.120
#> GSM425848 1 0.756 0.24391 0.524 0.016 0.064 0.232 0.164
#> GSM425849 1 0.564 0.37888 0.644 0.004 0.000 0.216 0.136
#> GSM425850 1 0.546 0.47208 0.752 0.032 0.048 0.108 0.060
#> GSM425851 5 0.797 0.79261 0.220 0.000 0.284 0.096 0.400
#> GSM425852 3 0.685 0.18411 0.276 0.000 0.420 0.004 0.300
#> GSM425893 2 0.622 0.55237 0.032 0.596 0.288 0.004 0.080
#> GSM425894 2 0.201 0.81950 0.012 0.936 0.016 0.024 0.012
#> GSM425895 2 0.417 0.79232 0.104 0.820 0.020 0.016 0.040
#> GSM425896 2 0.514 0.67462 0.000 0.684 0.228 0.004 0.084
#> GSM425897 2 0.543 0.59082 0.004 0.636 0.288 0.004 0.068
#> GSM425898 2 0.229 0.81544 0.028 0.924 0.012 0.024 0.012
#> GSM425899 2 0.474 0.73107 0.048 0.776 0.016 0.140 0.020
#> GSM425900 2 0.324 0.79057 0.088 0.868 0.012 0.016 0.016
#> GSM425901 3 0.750 0.41864 0.060 0.088 0.460 0.028 0.364
#> GSM425902 4 0.284 0.68342 0.004 0.052 0.004 0.888 0.052
#> GSM425903 1 0.716 -0.00138 0.428 0.052 0.388 0.000 0.132
#> GSM425904 3 0.718 0.10010 0.316 0.000 0.384 0.016 0.284
#> GSM425905 2 0.379 0.80349 0.004 0.832 0.068 0.008 0.088
#> GSM425906 2 0.458 0.70978 0.180 0.760 0.036 0.004 0.020
#> GSM425863 1 0.750 0.18790 0.472 0.020 0.048 0.332 0.128
#> GSM425864 2 0.506 0.74325 0.012 0.728 0.176 0.004 0.080
#> GSM425865 2 0.478 0.79990 0.020 0.788 0.072 0.024 0.096
#> GSM425866 1 0.714 0.00257 0.384 0.000 0.344 0.016 0.256
#> GSM425867 1 0.566 0.36761 0.612 0.012 0.300 0.000 0.076
#> GSM425868 2 0.508 0.76848 0.004 0.756 0.036 0.092 0.112
#> GSM425869 2 0.264 0.81078 0.000 0.900 0.016 0.052 0.032
#> GSM425870 3 0.733 0.00918 0.360 0.192 0.408 0.000 0.040
#> GSM425871 1 0.560 0.40428 0.708 0.024 0.008 0.148 0.112
#> GSM425872 2 0.225 0.81544 0.040 0.920 0.020 0.020 0.000
#> GSM425873 1 0.314 0.47417 0.876 0.004 0.048 0.012 0.060
#> GSM425843 1 0.668 0.15575 0.584 0.000 0.060 0.116 0.240
#> GSM425844 1 0.633 0.31794 0.648 0.012 0.032 0.172 0.136
#> GSM425845 1 0.530 0.43340 0.668 0.012 0.252 0.000 0.068
#> GSM425846 2 0.475 0.71682 0.056 0.768 0.008 0.148 0.020
#> GSM425847 1 0.549 0.41695 0.672 0.240 0.052 0.000 0.036
#> GSM425886 3 0.762 0.45950 0.092 0.144 0.508 0.008 0.248
#> GSM425887 2 0.413 0.78800 0.108 0.820 0.016 0.016 0.040
#> GSM425888 1 0.566 0.27952 0.588 0.348 0.036 0.004 0.024
#> GSM425889 4 0.797 -0.00748 0.280 0.012 0.072 0.436 0.200
#> GSM425890 5 0.815 0.68651 0.132 0.004 0.156 0.320 0.388
#> GSM425891 2 0.404 0.80099 0.088 0.824 0.064 0.004 0.020
#> GSM425892 2 0.643 0.68357 0.004 0.656 0.096 0.108 0.136
#> GSM425853 1 0.702 0.22386 0.476 0.000 0.288 0.024 0.212
#> GSM425854 2 0.409 0.80475 0.084 0.832 0.020 0.024 0.040
#> GSM425855 1 0.712 0.27180 0.564 0.012 0.052 0.228 0.144
#> GSM425856 1 0.714 0.00257 0.384 0.000 0.344 0.016 0.256
#> GSM425857 3 0.759 0.41703 0.028 0.120 0.440 0.044 0.368
#> GSM425858 2 0.416 0.77123 0.124 0.812 0.012 0.020 0.032
#> GSM425859 2 0.198 0.81826 0.004 0.936 0.016 0.024 0.020
#> GSM425860 1 0.490 0.46499 0.716 0.020 0.220 0.000 0.044
#> GSM425861 1 0.566 0.27952 0.588 0.348 0.036 0.004 0.024
#> GSM425862 4 0.796 -0.00102 0.276 0.012 0.072 0.440 0.200
#> GSM425837 1 0.766 -0.03417 0.452 0.000 0.100 0.148 0.300
#> GSM425838 4 0.550 0.52037 0.020 0.064 0.004 0.672 0.240
#> GSM425839 2 0.178 0.81940 0.004 0.944 0.020 0.020 0.012
#> GSM425840 1 0.703 0.28632 0.576 0.012 0.052 0.224 0.136
#> GSM425841 4 0.291 0.68243 0.004 0.056 0.004 0.884 0.052
#> GSM425842 1 0.384 0.45202 0.836 0.004 0.044 0.024 0.092
#> GSM425917 3 0.454 0.52564 0.028 0.036 0.804 0.028 0.104
#> GSM425922 4 0.115 0.67251 0.004 0.008 0.000 0.964 0.024
#> GSM425919 5 0.797 0.79261 0.220 0.000 0.284 0.096 0.400
#> GSM425920 1 0.692 0.00253 0.576 0.004 0.076 0.104 0.240
#> GSM425923 5 0.808 0.82142 0.184 0.000 0.176 0.200 0.440
#> GSM425916 5 0.782 0.82757 0.192 0.000 0.200 0.132 0.476
#> GSM425918 5 0.809 0.81492 0.172 0.000 0.176 0.216 0.436
#> GSM425921 4 0.115 0.67251 0.004 0.008 0.000 0.964 0.024
#> GSM425925 4 0.171 0.67069 0.024 0.012 0.000 0.944 0.020
#> GSM425926 4 0.074 0.67649 0.004 0.008 0.000 0.980 0.008
#> GSM425927 1 0.469 0.39478 0.768 0.000 0.036 0.052 0.144
#> GSM425924 3 0.453 0.52827 0.028 0.040 0.804 0.024 0.104
#> GSM425928 3 0.104 0.67484 0.000 0.040 0.960 0.000 0.000
#> GSM425929 3 0.104 0.67484 0.000 0.040 0.960 0.000 0.000
#> GSM425930 3 0.104 0.67484 0.000 0.040 0.960 0.000 0.000
#> GSM425931 3 0.104 0.67484 0.000 0.040 0.960 0.000 0.000
#> GSM425932 3 0.104 0.67484 0.000 0.040 0.960 0.000 0.000
#> GSM425933 3 0.104 0.67484 0.000 0.040 0.960 0.000 0.000
#> GSM425934 3 0.104 0.67484 0.000 0.040 0.960 0.000 0.000
#> GSM425935 3 0.104 0.67484 0.000 0.040 0.960 0.000 0.000
#> GSM425936 3 0.104 0.67484 0.000 0.040 0.960 0.000 0.000
#> GSM425937 3 0.104 0.67484 0.000 0.040 0.960 0.000 0.000
#> GSM425938 3 0.104 0.67484 0.000 0.040 0.960 0.000 0.000
#> GSM425939 3 0.104 0.67484 0.000 0.040 0.960 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 2 0.440 0.7582 0.004 0.772 0.056 0.004 0.128 0.036
#> GSM425908 2 0.480 0.7513 0.008 0.756 0.020 0.032 0.132 0.052
#> GSM425909 5 0.542 0.6642 0.044 0.048 0.268 0.004 0.632 0.004
#> GSM425910 1 0.414 0.4113 0.752 0.020 0.184 0.000 0.044 0.000
#> GSM425911 3 0.715 0.0544 0.212 0.296 0.416 0.004 0.068 0.004
#> GSM425912 1 0.478 0.4192 0.680 0.256 0.024 0.000 0.020 0.020
#> GSM425913 2 0.319 0.7689 0.100 0.852 0.020 0.004 0.016 0.008
#> GSM425914 1 0.496 0.3902 0.700 0.072 0.184 0.000 0.044 0.000
#> GSM425915 5 0.629 0.5877 0.088 0.076 0.348 0.000 0.488 0.000
#> GSM425874 4 0.322 0.7088 0.004 0.048 0.000 0.856 0.064 0.028
#> GSM425875 5 0.605 0.6308 0.328 0.000 0.184 0.000 0.476 0.012
#> GSM425876 1 0.224 0.5066 0.912 0.008 0.048 0.000 0.016 0.016
#> GSM425877 1 0.599 0.1009 0.484 0.000 0.024 0.044 0.040 0.408
#> GSM425878 1 0.527 0.4122 0.676 0.004 0.008 0.036 0.060 0.216
#> GSM425879 2 0.444 0.7696 0.016 0.780 0.072 0.004 0.104 0.024
#> GSM425880 5 0.595 0.6974 0.260 0.000 0.204 0.000 0.524 0.012
#> GSM425881 1 0.485 0.3430 0.624 0.324 0.012 0.000 0.020 0.020
#> GSM425882 2 0.539 0.7553 0.028 0.728 0.028 0.032 0.128 0.056
#> GSM425883 1 0.769 0.0944 0.356 0.016 0.016 0.348 0.076 0.188
#> GSM425884 1 0.523 0.2868 0.592 0.000 0.020 0.012 0.040 0.336
#> GSM425885 2 0.763 0.0611 0.004 0.364 0.044 0.348 0.184 0.056
#> GSM425848 1 0.764 0.2300 0.452 0.012 0.016 0.196 0.108 0.216
#> GSM425849 1 0.630 0.3907 0.584 0.004 0.000 0.172 0.072 0.168
#> GSM425850 1 0.538 0.4876 0.740 0.028 0.028 0.092 0.048 0.064
#> GSM425851 6 0.532 0.7073 0.108 0.000 0.188 0.012 0.020 0.672
#> GSM425852 5 0.600 0.6896 0.224 0.000 0.248 0.000 0.516 0.012
#> GSM425893 2 0.659 0.5006 0.036 0.528 0.288 0.004 0.120 0.024
#> GSM425894 2 0.162 0.7828 0.016 0.944 0.000 0.020 0.012 0.008
#> GSM425895 2 0.399 0.7557 0.124 0.804 0.012 0.008 0.024 0.028
#> GSM425896 2 0.561 0.6283 0.000 0.624 0.224 0.004 0.120 0.028
#> GSM425897 2 0.597 0.5302 0.008 0.560 0.296 0.004 0.112 0.020
#> GSM425898 2 0.202 0.7792 0.040 0.924 0.004 0.020 0.008 0.004
#> GSM425899 2 0.435 0.6981 0.056 0.772 0.000 0.124 0.044 0.004
#> GSM425900 2 0.282 0.7490 0.112 0.860 0.000 0.012 0.008 0.008
#> GSM425901 5 0.527 0.6316 0.020 0.064 0.276 0.004 0.632 0.004
#> GSM425902 4 0.310 0.7088 0.004 0.040 0.000 0.860 0.076 0.020
#> GSM425903 1 0.682 -0.3524 0.396 0.036 0.284 0.000 0.280 0.004
#> GSM425904 5 0.595 0.6974 0.260 0.000 0.204 0.000 0.524 0.012
#> GSM425905 2 0.454 0.7642 0.012 0.772 0.060 0.004 0.116 0.036
#> GSM425906 2 0.407 0.6573 0.208 0.748 0.016 0.000 0.012 0.016
#> GSM425863 1 0.755 0.1847 0.408 0.016 0.012 0.316 0.084 0.164
#> GSM425864 2 0.564 0.6970 0.020 0.664 0.176 0.008 0.116 0.016
#> GSM425865 2 0.535 0.7586 0.028 0.728 0.068 0.016 0.124 0.036
#> GSM425866 5 0.605 0.6308 0.328 0.000 0.184 0.000 0.476 0.012
#> GSM425867 1 0.528 0.1843 0.616 0.000 0.248 0.000 0.128 0.008
#> GSM425868 2 0.536 0.7373 0.008 0.720 0.020 0.072 0.128 0.052
#> GSM425869 2 0.261 0.7753 0.000 0.888 0.000 0.044 0.048 0.020
#> GSM425870 3 0.681 -0.0883 0.376 0.140 0.408 0.000 0.072 0.004
#> GSM425871 1 0.594 0.4184 0.652 0.024 0.000 0.124 0.052 0.148
#> GSM425872 2 0.174 0.7751 0.052 0.928 0.000 0.016 0.004 0.000
#> GSM425873 1 0.301 0.4916 0.852 0.000 0.024 0.000 0.020 0.104
#> GSM425843 1 0.599 0.1009 0.484 0.000 0.024 0.044 0.040 0.408
#> GSM425844 1 0.633 0.3290 0.592 0.012 0.004 0.136 0.052 0.204
#> GSM425845 1 0.502 0.2965 0.668 0.000 0.212 0.000 0.104 0.016
#> GSM425846 2 0.447 0.6850 0.068 0.764 0.000 0.128 0.032 0.008
#> GSM425847 1 0.434 0.4353 0.724 0.224 0.012 0.000 0.020 0.020
#> GSM425886 5 0.640 0.5176 0.056 0.108 0.360 0.004 0.472 0.000
#> GSM425887 2 0.404 0.7517 0.128 0.800 0.012 0.008 0.024 0.028
#> GSM425888 1 0.472 0.3284 0.620 0.336 0.008 0.000 0.016 0.020
#> GSM425889 4 0.804 0.0201 0.212 0.004 0.020 0.356 0.172 0.236
#> GSM425890 6 0.548 0.6085 0.060 0.004 0.056 0.188 0.012 0.680
#> GSM425891 2 0.388 0.7623 0.108 0.808 0.052 0.000 0.024 0.008
#> GSM425892 2 0.676 0.6556 0.016 0.604 0.088 0.060 0.184 0.048
#> GSM425853 1 0.646 -0.3807 0.440 0.000 0.184 0.008 0.348 0.020
#> GSM425854 2 0.365 0.7675 0.096 0.832 0.004 0.016 0.020 0.032
#> GSM425855 1 0.711 0.2653 0.492 0.008 0.012 0.196 0.064 0.228
#> GSM425856 5 0.605 0.6308 0.328 0.000 0.184 0.000 0.476 0.012
#> GSM425857 5 0.581 0.5549 0.004 0.096 0.272 0.020 0.596 0.012
#> GSM425858 2 0.384 0.7286 0.144 0.800 0.004 0.012 0.016 0.024
#> GSM425859 2 0.159 0.7824 0.004 0.944 0.000 0.016 0.024 0.012
#> GSM425860 1 0.438 0.4009 0.736 0.004 0.192 0.000 0.052 0.016
#> GSM425861 1 0.472 0.3284 0.620 0.336 0.008 0.000 0.016 0.020
#> GSM425862 4 0.804 0.0256 0.208 0.004 0.020 0.356 0.176 0.236
#> GSM425837 6 0.721 -0.0102 0.348 0.000 0.028 0.056 0.164 0.404
#> GSM425838 4 0.708 0.3499 0.032 0.028 0.000 0.400 0.332 0.208
#> GSM425839 2 0.131 0.7822 0.008 0.956 0.000 0.012 0.020 0.004
#> GSM425840 1 0.705 0.2811 0.504 0.008 0.012 0.192 0.064 0.220
#> GSM425841 4 0.322 0.7078 0.004 0.048 0.000 0.856 0.064 0.028
#> GSM425842 1 0.371 0.4668 0.792 0.000 0.028 0.000 0.024 0.156
#> GSM425917 3 0.342 0.6717 0.020 0.000 0.804 0.016 0.000 0.160
#> GSM425922 4 0.194 0.7038 0.000 0.008 0.000 0.916 0.012 0.064
#> GSM425919 6 0.532 0.7073 0.108 0.000 0.188 0.012 0.020 0.672
#> GSM425920 1 0.580 0.0150 0.512 0.004 0.028 0.052 0.012 0.392
#> GSM425923 6 0.488 0.7373 0.084 0.000 0.060 0.076 0.024 0.756
#> GSM425916 6 0.376 0.7398 0.084 0.000 0.076 0.028 0.000 0.812
#> GSM425918 6 0.502 0.7311 0.084 0.000 0.060 0.088 0.024 0.744
#> GSM425921 4 0.214 0.7039 0.004 0.008 0.000 0.908 0.012 0.068
#> GSM425925 4 0.169 0.7050 0.012 0.008 0.000 0.940 0.012 0.028
#> GSM425926 4 0.123 0.7123 0.000 0.008 0.000 0.956 0.008 0.028
#> GSM425927 1 0.372 0.4041 0.732 0.000 0.012 0.008 0.000 0.248
#> GSM425924 3 0.344 0.6764 0.020 0.004 0.808 0.012 0.000 0.156
#> GSM425928 3 0.000 0.8565 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425929 3 0.000 0.8565 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425930 3 0.000 0.8565 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425931 3 0.000 0.8565 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425932 3 0.000 0.8565 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425933 3 0.000 0.8565 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425934 3 0.000 0.8565 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425935 3 0.000 0.8565 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425936 3 0.000 0.8565 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425937 3 0.000 0.8565 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425938 3 0.000 0.8565 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425939 3 0.000 0.8565 0.000 0.000 1.000 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 disease.state(p) tissue(p) other(p) k
#> MAD:hclust 15 2.17e-03 2.17e-03 5.53e-04 2
#> MAD:hclust 39 NA 1.78e-04 1.47e-01 3
#> MAD:hclust 57 3.05e-09 5.03e-11 3.43e-07 4
#> MAD:hclust 56 6.20e-10 3.65e-13 5.00e-09 5
#> MAD:hclust 67 1.11e-10 1.34e-14 3.19e-07 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 103 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 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 0.255 0.687 0.825 0.4866 0.496 0.496
#> 3 3 0.544 0.708 0.842 0.2974 0.833 0.680
#> 4 4 0.657 0.640 0.826 0.1527 0.796 0.518
#> 5 5 0.700 0.674 0.820 0.0768 0.891 0.625
#> 6 6 0.754 0.681 0.802 0.0527 0.921 0.656
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
#> GSM425907 2 0.3114 0.7664 0.056 0.944
#> GSM425908 2 0.5737 0.7476 0.136 0.864
#> GSM425909 2 0.9635 0.5496 0.388 0.612
#> GSM425910 1 0.9909 -0.1567 0.556 0.444
#> GSM425911 2 0.5519 0.7661 0.128 0.872
#> GSM425912 2 0.8608 0.7109 0.284 0.716
#> GSM425913 2 0.3879 0.7661 0.076 0.924
#> GSM425914 2 0.7950 0.7412 0.240 0.760
#> GSM425915 2 0.8144 0.7317 0.252 0.748
#> GSM425874 1 0.7453 0.7368 0.788 0.212
#> GSM425875 1 0.0376 0.8200 0.996 0.004
#> GSM425876 1 0.9129 0.2991 0.672 0.328
#> GSM425877 1 0.0376 0.8236 0.996 0.004
#> GSM425878 1 0.1184 0.8255 0.984 0.016
#> GSM425879 2 0.2948 0.7664 0.052 0.948
#> GSM425880 1 0.3114 0.7762 0.944 0.056
#> GSM425881 2 0.9993 0.0477 0.484 0.516
#> GSM425882 2 0.5737 0.7476 0.136 0.864
#> GSM425883 1 0.4022 0.8178 0.920 0.080
#> GSM425884 1 0.0376 0.8236 0.996 0.004
#> GSM425885 2 0.9996 -0.0130 0.488 0.512
#> GSM425848 1 0.5408 0.7972 0.876 0.124
#> GSM425849 1 0.4690 0.8097 0.900 0.100
#> GSM425850 1 0.2423 0.8252 0.960 0.040
#> GSM425851 1 0.0376 0.8236 0.996 0.004
#> GSM425852 1 0.4690 0.7251 0.900 0.100
#> GSM425893 2 0.4815 0.7660 0.104 0.896
#> GSM425894 2 0.5737 0.7476 0.136 0.864
#> GSM425895 2 0.5737 0.7476 0.136 0.864
#> GSM425896 2 0.2423 0.7638 0.040 0.960
#> GSM425897 2 0.2948 0.7664 0.052 0.948
#> GSM425898 2 0.5737 0.7476 0.136 0.864
#> GSM425899 1 0.9732 0.4336 0.596 0.404
#> GSM425900 2 0.5629 0.7494 0.132 0.868
#> GSM425901 2 0.9815 0.4514 0.420 0.580
#> GSM425902 1 0.7602 0.7307 0.780 0.220
#> GSM425903 2 0.8499 0.7156 0.276 0.724
#> GSM425904 1 0.2948 0.7803 0.948 0.052
#> GSM425905 2 0.3584 0.7667 0.068 0.932
#> GSM425906 2 0.3879 0.7661 0.076 0.924
#> GSM425863 1 0.3733 0.8207 0.928 0.072
#> GSM425864 2 0.2948 0.7664 0.052 0.948
#> GSM425865 2 0.4298 0.7639 0.088 0.912
#> GSM425866 1 0.0672 0.8178 0.992 0.008
#> GSM425867 2 0.9129 0.6348 0.328 0.672
#> GSM425868 2 0.5737 0.7476 0.136 0.864
#> GSM425869 2 0.5737 0.7476 0.136 0.864
#> GSM425870 2 0.6973 0.7324 0.188 0.812
#> GSM425871 1 0.5629 0.7956 0.868 0.132
#> GSM425872 2 0.5737 0.7476 0.136 0.864
#> GSM425873 1 0.1184 0.8242 0.984 0.016
#> GSM425843 1 0.0376 0.8236 0.996 0.004
#> GSM425844 1 0.3584 0.8219 0.932 0.068
#> GSM425845 1 0.9922 -0.1659 0.552 0.448
#> GSM425846 1 0.9896 0.3349 0.560 0.440
#> GSM425847 1 0.9754 0.0639 0.592 0.408
#> GSM425886 2 0.7219 0.7507 0.200 0.800
#> GSM425887 2 0.8909 0.5847 0.308 0.692
#> GSM425888 2 0.9998 -0.0146 0.492 0.508
#> GSM425889 1 0.5408 0.7992 0.876 0.124
#> GSM425890 1 0.7299 0.7452 0.796 0.204
#> GSM425891 2 0.3733 0.7665 0.072 0.928
#> GSM425892 2 0.5737 0.7476 0.136 0.864
#> GSM425853 1 0.0376 0.8200 0.996 0.004
#> GSM425854 2 0.5737 0.7476 0.136 0.864
#> GSM425855 1 0.3584 0.8217 0.932 0.068
#> GSM425856 1 0.0672 0.8178 0.992 0.008
#> GSM425857 2 0.9358 0.4718 0.352 0.648
#> GSM425858 2 0.8267 0.6027 0.260 0.740
#> GSM425859 2 0.5737 0.7476 0.136 0.864
#> GSM425860 2 0.9580 0.6143 0.380 0.620
#> GSM425861 1 0.9209 0.5267 0.664 0.336
#> GSM425862 1 0.5629 0.7946 0.868 0.132
#> GSM425837 1 0.0000 0.8220 1.000 0.000
#> GSM425838 1 0.7602 0.7307 0.780 0.220
#> GSM425839 2 0.5737 0.7476 0.136 0.864
#> GSM425840 1 0.0376 0.8236 0.996 0.004
#> GSM425841 1 0.7602 0.7307 0.780 0.220
#> GSM425842 1 0.0938 0.8246 0.988 0.012
#> GSM425917 2 0.8443 0.7066 0.272 0.728
#> GSM425922 1 0.7602 0.7307 0.780 0.220
#> GSM425919 1 0.0376 0.8236 0.996 0.004
#> GSM425920 1 0.0376 0.8236 0.996 0.004
#> GSM425923 1 0.2778 0.8251 0.952 0.048
#> GSM425916 1 0.0376 0.8236 0.996 0.004
#> GSM425918 1 0.2778 0.8251 0.952 0.048
#> GSM425921 1 0.7602 0.7307 0.780 0.220
#> GSM425925 1 0.6343 0.7739 0.840 0.160
#> GSM425926 1 0.6973 0.7503 0.812 0.188
#> GSM425927 1 0.0376 0.8236 0.996 0.004
#> GSM425924 1 0.9522 0.2437 0.628 0.372
#> GSM425928 2 0.8207 0.7033 0.256 0.744
#> GSM425929 2 0.7883 0.7165 0.236 0.764
#> GSM425930 2 0.7883 0.7165 0.236 0.764
#> GSM425931 2 0.8207 0.7033 0.256 0.744
#> GSM425932 2 0.7883 0.7165 0.236 0.764
#> GSM425933 2 0.7883 0.7165 0.236 0.764
#> GSM425934 2 0.7376 0.7260 0.208 0.792
#> GSM425935 2 0.7376 0.7294 0.208 0.792
#> GSM425936 2 0.7883 0.7165 0.236 0.764
#> GSM425937 2 0.8207 0.7033 0.256 0.744
#> GSM425938 2 0.8207 0.7033 0.256 0.744
#> GSM425939 2 0.8207 0.7033 0.256 0.744
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.0661 0.78343 0.004 0.988 0.008
#> GSM425908 2 0.0848 0.78466 0.008 0.984 0.008
#> GSM425909 2 0.9969 -0.03237 0.320 0.372 0.308
#> GSM425910 1 0.8328 0.06056 0.520 0.396 0.084
#> GSM425911 2 0.0000 0.78328 0.000 1.000 0.000
#> GSM425912 2 0.6487 0.57809 0.268 0.700 0.032
#> GSM425913 2 0.0661 0.78343 0.004 0.988 0.008
#> GSM425914 2 0.5982 0.61318 0.228 0.744 0.028
#> GSM425915 2 0.6925 0.03403 0.016 0.532 0.452
#> GSM425874 1 0.7169 0.66711 0.704 0.208 0.088
#> GSM425875 1 0.2590 0.83113 0.924 0.004 0.072
#> GSM425876 1 0.7980 0.20492 0.572 0.356 0.072
#> GSM425877 1 0.1289 0.84608 0.968 0.000 0.032
#> GSM425878 1 0.1031 0.84229 0.976 0.000 0.024
#> GSM425879 2 0.0424 0.78222 0.000 0.992 0.008
#> GSM425880 1 0.2945 0.82301 0.908 0.004 0.088
#> GSM425881 2 0.6621 0.57495 0.284 0.684 0.032
#> GSM425882 2 0.1015 0.78156 0.008 0.980 0.012
#> GSM425883 1 0.2796 0.83722 0.908 0.000 0.092
#> GSM425884 1 0.1289 0.84051 0.968 0.000 0.032
#> GSM425885 2 0.8524 -0.15632 0.452 0.456 0.092
#> GSM425848 1 0.3587 0.83079 0.892 0.020 0.088
#> GSM425849 1 0.1129 0.84512 0.976 0.004 0.020
#> GSM425850 1 0.2806 0.82397 0.928 0.032 0.040
#> GSM425851 1 0.2448 0.83802 0.924 0.000 0.076
#> GSM425852 1 0.3112 0.81256 0.900 0.004 0.096
#> GSM425893 2 0.0000 0.78328 0.000 1.000 0.000
#> GSM425894 2 0.0848 0.78466 0.008 0.984 0.008
#> GSM425895 2 0.0661 0.78494 0.008 0.988 0.004
#> GSM425896 2 0.0424 0.78222 0.000 0.992 0.008
#> GSM425897 2 0.0424 0.78222 0.000 0.992 0.008
#> GSM425898 2 0.0848 0.78466 0.008 0.984 0.008
#> GSM425899 2 0.4662 0.71425 0.124 0.844 0.032
#> GSM425900 2 0.1170 0.78027 0.008 0.976 0.016
#> GSM425901 2 0.9975 -0.04070 0.332 0.364 0.304
#> GSM425902 1 0.7169 0.66711 0.704 0.208 0.088
#> GSM425903 2 0.9671 0.30907 0.248 0.460 0.292
#> GSM425904 1 0.2945 0.82301 0.908 0.004 0.088
#> GSM425905 2 0.0424 0.78222 0.000 0.992 0.008
#> GSM425906 2 0.0661 0.78268 0.004 0.988 0.008
#> GSM425863 1 0.1163 0.84693 0.972 0.000 0.028
#> GSM425864 2 0.0424 0.78222 0.000 0.992 0.008
#> GSM425865 2 0.0661 0.78343 0.004 0.988 0.008
#> GSM425866 1 0.2772 0.82846 0.916 0.004 0.080
#> GSM425867 3 0.3690 0.76554 0.100 0.016 0.884
#> GSM425868 2 0.1905 0.77437 0.016 0.956 0.028
#> GSM425869 2 0.1015 0.78385 0.008 0.980 0.012
#> GSM425870 2 0.6661 0.13351 0.012 0.588 0.400
#> GSM425871 1 0.2496 0.84208 0.928 0.004 0.068
#> GSM425872 2 0.0848 0.78466 0.008 0.984 0.008
#> GSM425873 1 0.2269 0.83320 0.944 0.016 0.040
#> GSM425843 1 0.1163 0.84132 0.972 0.000 0.028
#> GSM425844 1 0.2261 0.84008 0.932 0.000 0.068
#> GSM425845 1 0.8515 -0.07128 0.476 0.432 0.092
#> GSM425846 2 0.4295 0.72301 0.104 0.864 0.032
#> GSM425847 2 0.7287 0.35040 0.408 0.560 0.032
#> GSM425886 2 0.5591 0.43824 0.000 0.696 0.304
#> GSM425887 2 0.6341 0.60235 0.252 0.716 0.032
#> GSM425888 2 0.6653 0.56954 0.288 0.680 0.032
#> GSM425889 1 0.2945 0.83608 0.908 0.004 0.088
#> GSM425890 1 0.7169 0.66711 0.704 0.208 0.088
#> GSM425891 2 0.0000 0.78328 0.000 1.000 0.000
#> GSM425892 2 0.0848 0.78466 0.008 0.984 0.008
#> GSM425853 1 0.2496 0.82947 0.928 0.004 0.068
#> GSM425854 2 0.0424 0.78454 0.008 0.992 0.000
#> GSM425855 1 0.1411 0.84700 0.964 0.000 0.036
#> GSM425856 1 0.2772 0.82846 0.916 0.004 0.080
#> GSM425857 2 0.9702 0.00531 0.364 0.416 0.220
#> GSM425858 2 0.3530 0.74049 0.068 0.900 0.032
#> GSM425859 2 0.0848 0.78466 0.008 0.984 0.008
#> GSM425860 2 0.7534 0.41387 0.368 0.584 0.048
#> GSM425861 1 0.7493 -0.16612 0.484 0.480 0.036
#> GSM425862 1 0.2945 0.83608 0.908 0.004 0.088
#> GSM425837 1 0.0592 0.84631 0.988 0.000 0.012
#> GSM425838 1 0.7169 0.66711 0.704 0.208 0.088
#> GSM425839 2 0.0848 0.78466 0.008 0.984 0.008
#> GSM425840 1 0.0424 0.84492 0.992 0.000 0.008
#> GSM425841 1 0.7169 0.66711 0.704 0.208 0.088
#> GSM425842 1 0.1950 0.83612 0.952 0.008 0.040
#> GSM425917 3 0.5757 0.84828 0.056 0.152 0.792
#> GSM425922 1 0.7169 0.66711 0.704 0.208 0.088
#> GSM425919 1 0.1163 0.84132 0.972 0.000 0.028
#> GSM425920 1 0.1860 0.84391 0.948 0.000 0.052
#> GSM425923 1 0.2537 0.83705 0.920 0.000 0.080
#> GSM425916 1 0.2448 0.83802 0.924 0.000 0.076
#> GSM425918 1 0.2537 0.83705 0.920 0.000 0.080
#> GSM425921 1 0.7169 0.66711 0.704 0.208 0.088
#> GSM425925 1 0.2945 0.83608 0.908 0.004 0.088
#> GSM425926 1 0.7169 0.66711 0.704 0.208 0.088
#> GSM425927 1 0.1765 0.83748 0.956 0.004 0.040
#> GSM425924 3 0.6318 0.74127 0.172 0.068 0.760
#> GSM425928 3 0.4293 0.95333 0.004 0.164 0.832
#> GSM425929 3 0.4293 0.95333 0.004 0.164 0.832
#> GSM425930 3 0.4293 0.95333 0.004 0.164 0.832
#> GSM425931 3 0.4293 0.95333 0.004 0.164 0.832
#> GSM425932 3 0.4293 0.95333 0.004 0.164 0.832
#> GSM425933 3 0.4293 0.95333 0.004 0.164 0.832
#> GSM425934 3 0.4293 0.95333 0.004 0.164 0.832
#> GSM425935 3 0.4293 0.95333 0.004 0.164 0.832
#> GSM425936 3 0.4293 0.95333 0.004 0.164 0.832
#> GSM425937 3 0.4293 0.95333 0.004 0.164 0.832
#> GSM425938 3 0.4293 0.95333 0.004 0.164 0.832
#> GSM425939 3 0.4293 0.95333 0.004 0.164 0.832
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.1042 0.8831 0.020 0.972 0.000 0.008
#> GSM425908 2 0.1042 0.8831 0.020 0.972 0.000 0.008
#> GSM425909 1 0.8391 0.3416 0.536 0.228 0.156 0.080
#> GSM425910 1 0.0707 0.5748 0.980 0.000 0.000 0.020
#> GSM425911 2 0.3649 0.7535 0.204 0.796 0.000 0.000
#> GSM425912 2 0.5888 0.2431 0.424 0.540 0.000 0.036
#> GSM425913 2 0.1004 0.8857 0.024 0.972 0.000 0.004
#> GSM425914 1 0.5296 -0.2273 0.496 0.496 0.000 0.008
#> GSM425915 1 0.6931 0.3013 0.588 0.228 0.184 0.000
#> GSM425874 4 0.1716 0.7642 0.000 0.064 0.000 0.936
#> GSM425875 1 0.3306 0.5551 0.840 0.000 0.004 0.156
#> GSM425876 1 0.2282 0.5707 0.924 0.024 0.000 0.052
#> GSM425877 4 0.4955 0.4224 0.344 0.000 0.008 0.648
#> GSM425878 1 0.4996 0.0143 0.516 0.000 0.000 0.484
#> GSM425879 2 0.1302 0.8824 0.044 0.956 0.000 0.000
#> GSM425880 1 0.3306 0.5551 0.840 0.000 0.004 0.156
#> GSM425881 2 0.5881 0.2462 0.420 0.544 0.000 0.036
#> GSM425882 2 0.1211 0.8839 0.040 0.960 0.000 0.000
#> GSM425883 4 0.1389 0.7821 0.048 0.000 0.000 0.952
#> GSM425884 1 0.5288 0.0392 0.520 0.000 0.008 0.472
#> GSM425885 4 0.4253 0.5650 0.016 0.208 0.000 0.776
#> GSM425848 4 0.1557 0.7786 0.056 0.000 0.000 0.944
#> GSM425849 4 0.4907 0.2359 0.420 0.000 0.000 0.580
#> GSM425850 1 0.4730 0.2518 0.636 0.000 0.000 0.364
#> GSM425851 4 0.2799 0.7599 0.108 0.000 0.008 0.884
#> GSM425852 1 0.3597 0.5512 0.836 0.000 0.016 0.148
#> GSM425893 2 0.2814 0.8186 0.132 0.868 0.000 0.000
#> GSM425894 2 0.0921 0.8847 0.000 0.972 0.000 0.028
#> GSM425895 2 0.0707 0.8870 0.000 0.980 0.000 0.020
#> GSM425896 2 0.1151 0.8828 0.024 0.968 0.000 0.008
#> GSM425897 2 0.1211 0.8837 0.040 0.960 0.000 0.000
#> GSM425898 2 0.0707 0.8870 0.000 0.980 0.000 0.020
#> GSM425899 2 0.1833 0.8737 0.024 0.944 0.000 0.032
#> GSM425900 2 0.2174 0.8737 0.052 0.928 0.000 0.020
#> GSM425901 1 0.8548 0.3351 0.524 0.228 0.156 0.092
#> GSM425902 4 0.1716 0.7642 0.000 0.064 0.000 0.936
#> GSM425903 1 0.2408 0.5638 0.920 0.036 0.044 0.000
#> GSM425904 1 0.3306 0.5551 0.840 0.000 0.004 0.156
#> GSM425905 2 0.0592 0.8878 0.016 0.984 0.000 0.000
#> GSM425906 2 0.1576 0.8764 0.048 0.948 0.000 0.004
#> GSM425863 4 0.4624 0.3951 0.340 0.000 0.000 0.660
#> GSM425864 2 0.1022 0.8850 0.032 0.968 0.000 0.000
#> GSM425865 2 0.0921 0.8854 0.028 0.972 0.000 0.000
#> GSM425866 1 0.3157 0.5590 0.852 0.000 0.004 0.144
#> GSM425867 1 0.4072 0.4008 0.748 0.000 0.252 0.000
#> GSM425868 2 0.1022 0.8835 0.000 0.968 0.000 0.032
#> GSM425869 2 0.0921 0.8847 0.000 0.972 0.000 0.028
#> GSM425870 2 0.7519 0.1234 0.392 0.424 0.184 0.000
#> GSM425871 4 0.3208 0.7345 0.148 0.000 0.004 0.848
#> GSM425872 2 0.0707 0.8870 0.000 0.980 0.000 0.020
#> GSM425873 1 0.4661 0.2773 0.652 0.000 0.000 0.348
#> GSM425843 1 0.5295 -0.0149 0.504 0.000 0.008 0.488
#> GSM425844 4 0.2859 0.7576 0.112 0.000 0.008 0.880
#> GSM425845 1 0.0992 0.5752 0.976 0.012 0.004 0.008
#> GSM425846 2 0.1174 0.8844 0.012 0.968 0.000 0.020
#> GSM425847 1 0.6114 0.0756 0.524 0.428 0.000 0.048
#> GSM425886 1 0.7910 0.1144 0.448 0.364 0.172 0.016
#> GSM425887 2 0.5062 0.5415 0.300 0.680 0.000 0.020
#> GSM425888 2 0.5764 0.4879 0.304 0.644 0.000 0.052
#> GSM425889 4 0.0469 0.7844 0.012 0.000 0.000 0.988
#> GSM425890 4 0.2156 0.7677 0.008 0.060 0.004 0.928
#> GSM425891 2 0.1109 0.8855 0.028 0.968 0.000 0.004
#> GSM425892 2 0.1042 0.8831 0.020 0.972 0.000 0.008
#> GSM425853 1 0.3074 0.5524 0.848 0.000 0.000 0.152
#> GSM425854 2 0.0707 0.8870 0.000 0.980 0.000 0.020
#> GSM425855 4 0.4483 0.5089 0.284 0.000 0.004 0.712
#> GSM425856 1 0.3306 0.5551 0.840 0.000 0.004 0.156
#> GSM425857 1 0.8276 0.2015 0.428 0.240 0.020 0.312
#> GSM425858 2 0.2563 0.8611 0.072 0.908 0.000 0.020
#> GSM425859 2 0.0817 0.8861 0.000 0.976 0.000 0.024
#> GSM425860 1 0.5256 0.4325 0.700 0.260 0.000 0.040
#> GSM425861 1 0.6395 -0.0350 0.476 0.460 0.000 0.064
#> GSM425862 4 0.0469 0.7844 0.012 0.000 0.000 0.988
#> GSM425837 4 0.5281 0.0914 0.464 0.000 0.008 0.528
#> GSM425838 4 0.2048 0.7673 0.008 0.064 0.000 0.928
#> GSM425839 2 0.0707 0.8870 0.000 0.980 0.000 0.020
#> GSM425840 4 0.5250 0.1778 0.440 0.000 0.008 0.552
#> GSM425841 4 0.1716 0.7642 0.000 0.064 0.000 0.936
#> GSM425842 1 0.4776 0.2425 0.624 0.000 0.000 0.376
#> GSM425917 3 0.3945 0.7399 0.000 0.004 0.780 0.216
#> GSM425922 4 0.1716 0.7642 0.000 0.064 0.000 0.936
#> GSM425919 1 0.5292 0.0103 0.512 0.000 0.008 0.480
#> GSM425920 4 0.3681 0.7020 0.176 0.000 0.008 0.816
#> GSM425923 4 0.1807 0.7811 0.052 0.000 0.008 0.940
#> GSM425916 4 0.2799 0.7599 0.108 0.000 0.008 0.884
#> GSM425918 4 0.1970 0.7792 0.060 0.000 0.008 0.932
#> GSM425921 4 0.1716 0.7642 0.000 0.064 0.000 0.936
#> GSM425925 4 0.0336 0.7838 0.008 0.000 0.000 0.992
#> GSM425926 4 0.1716 0.7642 0.000 0.064 0.000 0.936
#> GSM425927 1 0.4964 0.2336 0.616 0.000 0.004 0.380
#> GSM425924 3 0.4857 0.6900 0.024 0.004 0.740 0.232
#> GSM425928 3 0.0469 0.9585 0.000 0.012 0.988 0.000
#> GSM425929 3 0.0469 0.9585 0.000 0.012 0.988 0.000
#> GSM425930 3 0.0469 0.9585 0.000 0.012 0.988 0.000
#> GSM425931 3 0.0469 0.9585 0.000 0.012 0.988 0.000
#> GSM425932 3 0.0469 0.9585 0.000 0.012 0.988 0.000
#> GSM425933 3 0.0469 0.9585 0.000 0.012 0.988 0.000
#> GSM425934 3 0.0469 0.9585 0.000 0.012 0.988 0.000
#> GSM425935 3 0.0469 0.9585 0.000 0.012 0.988 0.000
#> GSM425936 3 0.0469 0.9585 0.000 0.012 0.988 0.000
#> GSM425937 3 0.0469 0.9585 0.000 0.012 0.988 0.000
#> GSM425938 3 0.0469 0.9585 0.000 0.012 0.988 0.000
#> GSM425939 3 0.0469 0.9585 0.000 0.012 0.988 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM425907 2 0.3188 0.8684 0.028 0.860 0.000 0.012 0.100
#> GSM425908 2 0.3272 0.8673 0.032 0.856 0.000 0.012 0.100
#> GSM425909 5 0.4047 0.7457 0.016 0.088 0.024 0.040 0.832
#> GSM425910 1 0.2068 0.4910 0.904 0.004 0.000 0.000 0.092
#> GSM425911 2 0.5466 0.6825 0.192 0.656 0.000 0.000 0.152
#> GSM425912 1 0.4849 0.2387 0.608 0.360 0.000 0.000 0.032
#> GSM425913 2 0.0798 0.8853 0.008 0.976 0.000 0.000 0.016
#> GSM425914 1 0.6094 -0.0872 0.488 0.384 0.000 0.000 0.128
#> GSM425915 5 0.4228 0.7423 0.128 0.040 0.032 0.000 0.800
#> GSM425874 4 0.1419 0.7771 0.016 0.012 0.000 0.956 0.016
#> GSM425875 5 0.3656 0.7821 0.168 0.000 0.000 0.032 0.800
#> GSM425876 1 0.1205 0.5381 0.956 0.004 0.000 0.000 0.040
#> GSM425877 1 0.6261 0.0790 0.488 0.000 0.000 0.356 0.156
#> GSM425878 1 0.4591 0.5337 0.748 0.000 0.000 0.132 0.120
#> GSM425879 2 0.2959 0.8697 0.036 0.864 0.000 0.000 0.100
#> GSM425880 5 0.3488 0.7905 0.168 0.000 0.000 0.024 0.808
#> GSM425881 1 0.4866 0.2005 0.580 0.396 0.000 0.004 0.020
#> GSM425882 2 0.3012 0.8682 0.036 0.860 0.000 0.000 0.104
#> GSM425883 4 0.4069 0.7062 0.112 0.000 0.000 0.792 0.096
#> GSM425884 1 0.4676 0.5276 0.740 0.000 0.000 0.140 0.120
#> GSM425885 4 0.3319 0.6796 0.008 0.100 0.000 0.852 0.040
#> GSM425848 4 0.2694 0.7640 0.032 0.004 0.000 0.888 0.076
#> GSM425849 1 0.5452 0.3592 0.616 0.000 0.000 0.292 0.092
#> GSM425850 1 0.1124 0.5789 0.960 0.000 0.000 0.036 0.004
#> GSM425851 4 0.6063 0.3743 0.316 0.000 0.000 0.540 0.144
#> GSM425852 5 0.3768 0.7281 0.228 0.000 0.004 0.008 0.760
#> GSM425893 2 0.4179 0.8114 0.072 0.776 0.000 0.000 0.152
#> GSM425894 2 0.0510 0.8843 0.000 0.984 0.000 0.016 0.000
#> GSM425895 2 0.0579 0.8866 0.000 0.984 0.000 0.008 0.008
#> GSM425896 2 0.3376 0.8646 0.032 0.848 0.000 0.012 0.108
#> GSM425897 2 0.3141 0.8648 0.040 0.852 0.000 0.000 0.108
#> GSM425898 2 0.0451 0.8844 0.000 0.988 0.000 0.008 0.004
#> GSM425899 2 0.1471 0.8725 0.004 0.952 0.000 0.024 0.020
#> GSM425900 2 0.1845 0.8570 0.056 0.928 0.000 0.000 0.016
#> GSM425901 5 0.4020 0.7435 0.012 0.088 0.024 0.044 0.832
#> GSM425902 4 0.1524 0.7752 0.016 0.016 0.000 0.952 0.016
#> GSM425903 5 0.3521 0.7469 0.232 0.000 0.004 0.000 0.764
#> GSM425904 5 0.3488 0.7905 0.168 0.000 0.000 0.024 0.808
#> GSM425905 2 0.2344 0.8804 0.032 0.904 0.000 0.000 0.064
#> GSM425906 2 0.2270 0.8460 0.076 0.904 0.000 0.000 0.020
#> GSM425863 4 0.5473 0.1434 0.416 0.000 0.000 0.520 0.064
#> GSM425864 2 0.3064 0.8662 0.036 0.856 0.000 0.000 0.108
#> GSM425865 2 0.3012 0.8682 0.036 0.860 0.000 0.000 0.104
#> GSM425866 5 0.3527 0.7885 0.172 0.000 0.000 0.024 0.804
#> GSM425867 5 0.4555 0.7658 0.224 0.000 0.056 0.000 0.720
#> GSM425868 2 0.1386 0.8855 0.000 0.952 0.000 0.016 0.032
#> GSM425869 2 0.0671 0.8850 0.000 0.980 0.000 0.016 0.004
#> GSM425870 1 0.7591 -0.1153 0.416 0.356 0.088 0.000 0.140
#> GSM425871 1 0.5868 0.0364 0.516 0.000 0.000 0.380 0.104
#> GSM425872 2 0.0579 0.8842 0.000 0.984 0.000 0.008 0.008
#> GSM425873 1 0.1124 0.5763 0.960 0.000 0.000 0.036 0.004
#> GSM425843 1 0.4676 0.5276 0.740 0.000 0.000 0.140 0.120
#> GSM425844 4 0.6046 0.3347 0.344 0.000 0.000 0.524 0.132
#> GSM425845 5 0.3707 0.7387 0.284 0.000 0.000 0.000 0.716
#> GSM425846 2 0.0968 0.8807 0.004 0.972 0.000 0.012 0.012
#> GSM425847 1 0.3727 0.4761 0.768 0.216 0.000 0.000 0.016
#> GSM425886 5 0.4108 0.7025 0.028 0.112 0.028 0.012 0.820
#> GSM425887 2 0.4944 0.4366 0.344 0.620 0.000 0.004 0.032
#> GSM425888 2 0.4803 -0.0365 0.484 0.500 0.000 0.004 0.012
#> GSM425889 4 0.1914 0.7782 0.032 0.004 0.000 0.932 0.032
#> GSM425890 4 0.1764 0.7568 0.008 0.000 0.000 0.928 0.064
#> GSM425891 2 0.1018 0.8865 0.016 0.968 0.000 0.000 0.016
#> GSM425892 2 0.3079 0.8707 0.028 0.868 0.000 0.012 0.092
#> GSM425853 5 0.4561 0.1739 0.488 0.000 0.000 0.008 0.504
#> GSM425854 2 0.0290 0.8852 0.000 0.992 0.000 0.008 0.000
#> GSM425855 4 0.5550 0.1960 0.400 0.000 0.000 0.528 0.072
#> GSM425856 5 0.3488 0.7905 0.168 0.000 0.000 0.024 0.808
#> GSM425857 5 0.3924 0.7221 0.000 0.096 0.008 0.080 0.816
#> GSM425858 2 0.2289 0.8345 0.080 0.904 0.000 0.004 0.012
#> GSM425859 2 0.0807 0.8865 0.000 0.976 0.000 0.012 0.012
#> GSM425860 1 0.3641 0.4772 0.820 0.120 0.000 0.000 0.060
#> GSM425861 1 0.4500 0.4098 0.664 0.316 0.000 0.004 0.016
#> GSM425862 4 0.1914 0.7782 0.032 0.004 0.000 0.932 0.032
#> GSM425837 1 0.5508 0.4055 0.636 0.000 0.000 0.244 0.120
#> GSM425838 4 0.1617 0.7787 0.020 0.012 0.000 0.948 0.020
#> GSM425839 2 0.0290 0.8852 0.000 0.992 0.000 0.008 0.000
#> GSM425840 1 0.5365 0.4279 0.656 0.000 0.000 0.228 0.116
#> GSM425841 4 0.1419 0.7771 0.016 0.012 0.000 0.956 0.016
#> GSM425842 1 0.1648 0.5806 0.940 0.000 0.000 0.040 0.020
#> GSM425917 3 0.4737 0.6714 0.008 0.000 0.732 0.196 0.064
#> GSM425922 4 0.0771 0.7686 0.000 0.004 0.000 0.976 0.020
#> GSM425919 1 0.5344 0.4850 0.672 0.000 0.000 0.168 0.160
#> GSM425920 1 0.6140 0.1246 0.504 0.000 0.000 0.356 0.140
#> GSM425923 4 0.4968 0.6239 0.152 0.000 0.000 0.712 0.136
#> GSM425916 4 0.6006 0.4044 0.300 0.000 0.000 0.556 0.144
#> GSM425918 4 0.5673 0.5012 0.252 0.000 0.000 0.616 0.132
#> GSM425921 4 0.0566 0.7695 0.000 0.004 0.000 0.984 0.012
#> GSM425925 4 0.1547 0.7792 0.032 0.004 0.000 0.948 0.016
#> GSM425926 4 0.1306 0.7779 0.016 0.008 0.000 0.960 0.016
#> GSM425927 1 0.3003 0.5757 0.864 0.000 0.000 0.044 0.092
#> GSM425924 3 0.7168 0.4020 0.164 0.000 0.556 0.192 0.088
#> GSM425928 3 0.0162 0.9414 0.004 0.000 0.996 0.000 0.000
#> GSM425929 3 0.0000 0.9427 0.000 0.000 1.000 0.000 0.000
#> GSM425930 3 0.0000 0.9427 0.000 0.000 1.000 0.000 0.000
#> GSM425931 3 0.0000 0.9427 0.000 0.000 1.000 0.000 0.000
#> GSM425932 3 0.0000 0.9427 0.000 0.000 1.000 0.000 0.000
#> GSM425933 3 0.0000 0.9427 0.000 0.000 1.000 0.000 0.000
#> GSM425934 3 0.0000 0.9427 0.000 0.000 1.000 0.000 0.000
#> GSM425935 3 0.0162 0.9414 0.004 0.000 0.996 0.000 0.000
#> GSM425936 3 0.0000 0.9427 0.000 0.000 1.000 0.000 0.000
#> GSM425937 3 0.0000 0.9427 0.000 0.000 1.000 0.000 0.000
#> GSM425938 3 0.0162 0.9414 0.004 0.000 0.996 0.000 0.000
#> GSM425939 3 0.0000 0.9427 0.000 0.000 1.000 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 2 0.5303 0.7418 0.076 0.692 0.000 0.000 0.112 0.120
#> GSM425908 2 0.5342 0.7401 0.076 0.688 0.000 0.000 0.112 0.124
#> GSM425909 5 0.1816 0.8378 0.012 0.016 0.004 0.028 0.936 0.004
#> GSM425910 6 0.3481 0.5151 0.160 0.000 0.000 0.000 0.048 0.792
#> GSM425911 6 0.6562 -0.2944 0.072 0.392 0.000 0.000 0.120 0.416
#> GSM425912 6 0.2848 0.6347 0.008 0.160 0.000 0.000 0.004 0.828
#> GSM425913 2 0.1606 0.7875 0.004 0.932 0.000 0.000 0.008 0.056
#> GSM425914 6 0.3809 0.5755 0.044 0.104 0.000 0.000 0.044 0.808
#> GSM425915 5 0.2236 0.8363 0.008 0.016 0.016 0.000 0.912 0.048
#> GSM425874 4 0.0363 0.8187 0.000 0.012 0.000 0.988 0.000 0.000
#> GSM425875 5 0.3084 0.8637 0.056 0.000 0.000 0.028 0.860 0.056
#> GSM425876 6 0.3642 0.4739 0.204 0.000 0.000 0.000 0.036 0.760
#> GSM425877 1 0.3980 0.6587 0.784 0.000 0.000 0.136 0.024 0.056
#> GSM425878 1 0.5651 0.4475 0.520 0.000 0.000 0.064 0.040 0.376
#> GSM425879 2 0.5557 0.7312 0.076 0.664 0.000 0.000 0.112 0.148
#> GSM425880 5 0.3023 0.8639 0.056 0.000 0.000 0.028 0.864 0.052
#> GSM425881 6 0.3404 0.6248 0.016 0.224 0.000 0.000 0.000 0.760
#> GSM425882 2 0.5523 0.7336 0.076 0.668 0.000 0.000 0.112 0.144
#> GSM425883 4 0.4926 0.3596 0.336 0.000 0.000 0.584 0.000 0.080
#> GSM425884 1 0.5124 0.5700 0.636 0.000 0.000 0.044 0.044 0.276
#> GSM425885 4 0.2357 0.7831 0.016 0.032 0.000 0.908 0.036 0.008
#> GSM425848 4 0.2565 0.7810 0.072 0.004 0.000 0.888 0.024 0.012
#> GSM425849 1 0.6478 0.3468 0.356 0.000 0.000 0.328 0.016 0.300
#> GSM425850 6 0.3730 0.4298 0.236 0.000 0.000 0.008 0.016 0.740
#> GSM425851 1 0.2416 0.6146 0.844 0.000 0.000 0.156 0.000 0.000
#> GSM425852 5 0.3288 0.8408 0.096 0.000 0.000 0.012 0.836 0.056
#> GSM425893 2 0.5922 0.6950 0.076 0.620 0.000 0.000 0.128 0.176
#> GSM425894 2 0.0551 0.7929 0.000 0.984 0.000 0.008 0.004 0.004
#> GSM425895 2 0.0291 0.7950 0.000 0.992 0.000 0.000 0.004 0.004
#> GSM425896 2 0.5639 0.7232 0.076 0.656 0.000 0.000 0.124 0.144
#> GSM425897 2 0.5731 0.7164 0.076 0.644 0.000 0.000 0.120 0.160
#> GSM425898 2 0.1080 0.7843 0.000 0.960 0.000 0.004 0.004 0.032
#> GSM425899 2 0.2325 0.7529 0.008 0.900 0.000 0.020 0.004 0.068
#> GSM425900 2 0.2234 0.7262 0.000 0.872 0.000 0.000 0.004 0.124
#> GSM425901 5 0.1816 0.8378 0.012 0.016 0.004 0.028 0.936 0.004
#> GSM425902 4 0.0767 0.8181 0.004 0.012 0.000 0.976 0.000 0.008
#> GSM425903 5 0.2165 0.8406 0.008 0.000 0.000 0.000 0.884 0.108
#> GSM425904 5 0.3023 0.8639 0.056 0.000 0.000 0.028 0.864 0.052
#> GSM425905 2 0.4683 0.7582 0.076 0.744 0.000 0.000 0.060 0.120
#> GSM425906 2 0.2662 0.7165 0.004 0.840 0.000 0.000 0.004 0.152
#> GSM425863 4 0.6115 0.0697 0.212 0.000 0.000 0.500 0.016 0.272
#> GSM425864 2 0.5596 0.7285 0.076 0.660 0.000 0.000 0.116 0.148
#> GSM425865 2 0.5489 0.7355 0.076 0.672 0.000 0.000 0.112 0.140
#> GSM425866 5 0.3084 0.8637 0.056 0.000 0.000 0.028 0.860 0.056
#> GSM425867 5 0.2925 0.8512 0.016 0.000 0.024 0.000 0.856 0.104
#> GSM425868 2 0.2276 0.7919 0.020 0.908 0.000 0.004 0.052 0.016
#> GSM425869 2 0.0520 0.7946 0.000 0.984 0.000 0.008 0.008 0.000
#> GSM425870 6 0.5601 0.5058 0.068 0.108 0.044 0.000 0.076 0.704
#> GSM425871 1 0.5787 0.4856 0.480 0.000 0.000 0.196 0.000 0.324
#> GSM425872 2 0.1542 0.7724 0.000 0.936 0.000 0.008 0.004 0.052
#> GSM425873 6 0.3833 0.4318 0.232 0.000 0.000 0.004 0.028 0.736
#> GSM425843 1 0.5373 0.5667 0.612 0.000 0.000 0.064 0.040 0.284
#> GSM425844 1 0.3490 0.6108 0.784 0.000 0.000 0.176 0.000 0.040
#> GSM425845 5 0.2948 0.8017 0.008 0.000 0.000 0.000 0.804 0.188
#> GSM425846 2 0.2202 0.7539 0.008 0.904 0.000 0.012 0.004 0.072
#> GSM425847 6 0.3376 0.6076 0.092 0.092 0.000 0.000 0.000 0.816
#> GSM425886 5 0.1766 0.8175 0.008 0.020 0.004 0.012 0.940 0.016
#> GSM425887 6 0.3955 0.4397 0.008 0.384 0.000 0.000 0.000 0.608
#> GSM425888 6 0.4366 0.3878 0.016 0.440 0.000 0.004 0.000 0.540
#> GSM425889 4 0.1586 0.8128 0.040 0.004 0.000 0.940 0.004 0.012
#> GSM425890 4 0.3717 0.4045 0.384 0.000 0.000 0.616 0.000 0.000
#> GSM425891 2 0.2373 0.7818 0.008 0.880 0.000 0.000 0.008 0.104
#> GSM425892 2 0.5303 0.7425 0.076 0.692 0.000 0.000 0.112 0.120
#> GSM425853 5 0.6173 0.0916 0.308 0.000 0.000 0.012 0.460 0.220
#> GSM425854 2 0.0000 0.7963 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425855 4 0.6227 -0.1055 0.336 0.004 0.000 0.468 0.016 0.176
#> GSM425856 5 0.3084 0.8637 0.056 0.000 0.000 0.028 0.860 0.056
#> GSM425857 5 0.2156 0.8226 0.012 0.020 0.000 0.028 0.920 0.020
#> GSM425858 2 0.2655 0.6996 0.008 0.848 0.000 0.000 0.004 0.140
#> GSM425859 2 0.0260 0.7960 0.000 0.992 0.000 0.000 0.008 0.000
#> GSM425860 6 0.2796 0.5825 0.100 0.020 0.000 0.000 0.016 0.864
#> GSM425861 6 0.3819 0.6178 0.040 0.200 0.000 0.004 0.000 0.756
#> GSM425862 4 0.1586 0.8128 0.040 0.004 0.000 0.940 0.004 0.012
#> GSM425837 1 0.5441 0.6117 0.636 0.000 0.000 0.100 0.036 0.228
#> GSM425838 4 0.1453 0.8123 0.040 0.008 0.000 0.944 0.008 0.000
#> GSM425839 2 0.0291 0.7950 0.000 0.992 0.000 0.000 0.004 0.004
#> GSM425840 1 0.5615 0.5830 0.592 0.000 0.000 0.100 0.032 0.276
#> GSM425841 4 0.0363 0.8187 0.000 0.012 0.000 0.988 0.000 0.000
#> GSM425842 6 0.4237 0.2712 0.308 0.000 0.000 0.004 0.028 0.660
#> GSM425917 3 0.4847 0.1834 0.444 0.000 0.500 0.056 0.000 0.000
#> GSM425922 4 0.1501 0.7891 0.076 0.000 0.000 0.924 0.000 0.000
#> GSM425919 1 0.2955 0.6626 0.860 0.000 0.000 0.036 0.016 0.088
#> GSM425920 1 0.3175 0.6643 0.832 0.000 0.000 0.088 0.000 0.080
#> GSM425923 1 0.3215 0.5084 0.756 0.000 0.000 0.240 0.000 0.004
#> GSM425916 1 0.2491 0.6098 0.836 0.000 0.000 0.164 0.000 0.000
#> GSM425918 1 0.3052 0.5490 0.780 0.000 0.000 0.216 0.000 0.004
#> GSM425921 4 0.1327 0.7970 0.064 0.000 0.000 0.936 0.000 0.000
#> GSM425925 4 0.0912 0.8159 0.012 0.004 0.000 0.972 0.004 0.008
#> GSM425926 4 0.0363 0.8187 0.000 0.012 0.000 0.988 0.000 0.000
#> GSM425927 1 0.4875 0.2749 0.492 0.000 0.000 0.008 0.040 0.460
#> GSM425924 1 0.4791 0.2607 0.612 0.000 0.328 0.052 0.000 0.008
#> GSM425928 3 0.0260 0.9534 0.008 0.000 0.992 0.000 0.000 0.000
#> GSM425929 3 0.0000 0.9569 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425930 3 0.0000 0.9569 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425931 3 0.0000 0.9569 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425932 3 0.0000 0.9569 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425933 3 0.0000 0.9569 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425934 3 0.0000 0.9569 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425935 3 0.0146 0.9553 0.004 0.000 0.996 0.000 0.000 0.000
#> GSM425936 3 0.0000 0.9569 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425937 3 0.0000 0.9569 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425938 3 0.0260 0.9534 0.008 0.000 0.992 0.000 0.000 0.000
#> GSM425939 3 0.0000 0.9569 0.000 0.000 1.000 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 disease.state(p) tissue(p) other(p) k
#> MAD:kmeans 91 1.74e-03 6.86e-05 5.73e-07 2
#> MAD:kmeans 89 1.39e-15 2.08e-16 1.46e-14 3
#> MAD:kmeans 76 1.27e-13 1.22e-15 2.23e-09 4
#> MAD:kmeans 79 9.30e-15 2.99e-16 9.24e-09 5
#> MAD:kmeans 85 7.53e-17 5.71e-19 1.56e-11 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 103 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 0.800 0.868 0.940 0.5044 0.495 0.495
#> 3 3 0.742 0.860 0.934 0.3177 0.741 0.525
#> 4 4 0.698 0.652 0.845 0.1152 0.860 0.619
#> 5 5 0.686 0.697 0.824 0.0714 0.906 0.665
#> 6 6 0.700 0.542 0.737 0.0473 0.917 0.638
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
#> GSM425907 2 0.0000 0.936 0.000 1.000
#> GSM425908 2 0.2423 0.923 0.040 0.960
#> GSM425909 2 0.9000 0.540 0.316 0.684
#> GSM425910 1 0.9881 0.294 0.564 0.436
#> GSM425911 2 0.0000 0.936 0.000 1.000
#> GSM425912 2 0.2778 0.912 0.048 0.952
#> GSM425913 2 0.0000 0.936 0.000 1.000
#> GSM425914 2 0.1414 0.929 0.020 0.980
#> GSM425915 2 0.0376 0.936 0.004 0.996
#> GSM425874 1 0.0938 0.927 0.988 0.012
#> GSM425875 1 0.0376 0.929 0.996 0.004
#> GSM425876 1 0.8144 0.682 0.748 0.252
#> GSM425877 1 0.0000 0.930 1.000 0.000
#> GSM425878 1 0.0000 0.930 1.000 0.000
#> GSM425879 2 0.0000 0.936 0.000 1.000
#> GSM425880 1 0.2423 0.908 0.960 0.040
#> GSM425881 1 0.9491 0.443 0.632 0.368
#> GSM425882 2 0.2423 0.923 0.040 0.960
#> GSM425883 1 0.0000 0.930 1.000 0.000
#> GSM425884 1 0.0000 0.930 1.000 0.000
#> GSM425885 2 0.9815 0.327 0.420 0.580
#> GSM425848 1 0.0376 0.930 0.996 0.004
#> GSM425849 1 0.0376 0.930 0.996 0.004
#> GSM425850 1 0.0376 0.930 0.996 0.004
#> GSM425851 1 0.0000 0.930 1.000 0.000
#> GSM425852 1 0.2603 0.905 0.956 0.044
#> GSM425893 2 0.0000 0.936 0.000 1.000
#> GSM425894 2 0.2423 0.923 0.040 0.960
#> GSM425895 2 0.2423 0.923 0.040 0.960
#> GSM425896 2 0.0000 0.936 0.000 1.000
#> GSM425897 2 0.0000 0.936 0.000 1.000
#> GSM425898 2 0.2423 0.923 0.040 0.960
#> GSM425899 1 0.2778 0.903 0.952 0.048
#> GSM425900 2 0.2043 0.928 0.032 0.968
#> GSM425901 2 0.9358 0.464 0.352 0.648
#> GSM425902 1 0.1414 0.924 0.980 0.020
#> GSM425903 2 0.1633 0.927 0.024 0.976
#> GSM425904 1 0.2423 0.908 0.960 0.040
#> GSM425905 2 0.0000 0.936 0.000 1.000
#> GSM425906 2 0.0000 0.936 0.000 1.000
#> GSM425863 1 0.0376 0.930 0.996 0.004
#> GSM425864 2 0.0000 0.936 0.000 1.000
#> GSM425865 2 0.0000 0.936 0.000 1.000
#> GSM425866 1 0.2423 0.908 0.960 0.040
#> GSM425867 2 0.6623 0.785 0.172 0.828
#> GSM425868 2 0.2948 0.916 0.052 0.948
#> GSM425869 2 0.2423 0.923 0.040 0.960
#> GSM425870 2 0.0376 0.936 0.004 0.996
#> GSM425871 1 0.0376 0.930 0.996 0.004
#> GSM425872 2 0.2423 0.923 0.040 0.960
#> GSM425873 1 0.0000 0.930 1.000 0.000
#> GSM425843 1 0.0000 0.930 1.000 0.000
#> GSM425844 1 0.0000 0.930 1.000 0.000
#> GSM425845 1 0.9710 0.398 0.600 0.400
#> GSM425846 1 0.6531 0.780 0.832 0.168
#> GSM425847 1 0.9358 0.471 0.648 0.352
#> GSM425886 2 0.0376 0.936 0.004 0.996
#> GSM425887 2 0.8763 0.585 0.296 0.704
#> GSM425888 1 0.9393 0.470 0.644 0.356
#> GSM425889 1 0.0376 0.930 0.996 0.004
#> GSM425890 1 0.1633 0.921 0.976 0.024
#> GSM425891 2 0.0000 0.936 0.000 1.000
#> GSM425892 2 0.2043 0.926 0.032 0.968
#> GSM425853 1 0.1414 0.921 0.980 0.020
#> GSM425854 2 0.2423 0.923 0.040 0.960
#> GSM425855 1 0.0376 0.930 0.996 0.004
#> GSM425856 1 0.2423 0.908 0.960 0.040
#> GSM425857 2 0.9323 0.465 0.348 0.652
#> GSM425858 2 0.8608 0.610 0.284 0.716
#> GSM425859 2 0.2423 0.923 0.040 0.960
#> GSM425860 2 0.5178 0.845 0.116 0.884
#> GSM425861 1 0.4431 0.864 0.908 0.092
#> GSM425862 1 0.0376 0.930 0.996 0.004
#> GSM425837 1 0.0000 0.930 1.000 0.000
#> GSM425838 1 0.1414 0.924 0.980 0.020
#> GSM425839 2 0.2423 0.923 0.040 0.960
#> GSM425840 1 0.0000 0.930 1.000 0.000
#> GSM425841 1 0.1414 0.924 0.980 0.020
#> GSM425842 1 0.0000 0.930 1.000 0.000
#> GSM425917 2 0.1184 0.934 0.016 0.984
#> GSM425922 1 0.1414 0.924 0.980 0.020
#> GSM425919 1 0.0000 0.930 1.000 0.000
#> GSM425920 1 0.0000 0.930 1.000 0.000
#> GSM425923 1 0.0000 0.930 1.000 0.000
#> GSM425916 1 0.0000 0.930 1.000 0.000
#> GSM425918 1 0.0000 0.930 1.000 0.000
#> GSM425921 1 0.1414 0.924 0.980 0.020
#> GSM425925 1 0.0376 0.930 0.996 0.004
#> GSM425926 1 0.0376 0.930 0.996 0.004
#> GSM425927 1 0.0000 0.930 1.000 0.000
#> GSM425924 1 0.9209 0.502 0.664 0.336
#> GSM425928 2 0.0376 0.936 0.004 0.996
#> GSM425929 2 0.0376 0.936 0.004 0.996
#> GSM425930 2 0.0376 0.936 0.004 0.996
#> GSM425931 2 0.0376 0.936 0.004 0.996
#> GSM425932 2 0.0376 0.936 0.004 0.996
#> GSM425933 2 0.0376 0.936 0.004 0.996
#> GSM425934 2 0.0376 0.936 0.004 0.996
#> GSM425935 2 0.0376 0.936 0.004 0.996
#> GSM425936 2 0.0376 0.936 0.004 0.996
#> GSM425937 2 0.0376 0.936 0.004 0.996
#> GSM425938 2 0.0376 0.936 0.004 0.996
#> GSM425939 2 0.0376 0.936 0.004 0.996
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.0000 0.927 0.000 1.000 0.000
#> GSM425908 2 0.0000 0.927 0.000 1.000 0.000
#> GSM425909 3 0.0237 0.951 0.004 0.000 0.996
#> GSM425910 3 0.5191 0.838 0.112 0.060 0.828
#> GSM425911 2 0.4974 0.704 0.000 0.764 0.236
#> GSM425912 2 0.4818 0.829 0.108 0.844 0.048
#> GSM425913 2 0.0237 0.926 0.000 0.996 0.004
#> GSM425914 2 0.6335 0.667 0.036 0.724 0.240
#> GSM425915 3 0.0000 0.953 0.000 0.000 1.000
#> GSM425874 1 0.3482 0.840 0.872 0.128 0.000
#> GSM425875 1 0.1289 0.897 0.968 0.000 0.032
#> GSM425876 1 0.8691 -0.081 0.448 0.104 0.448
#> GSM425877 1 0.0000 0.913 1.000 0.000 0.000
#> GSM425878 1 0.0000 0.913 1.000 0.000 0.000
#> GSM425879 2 0.0592 0.923 0.000 0.988 0.012
#> GSM425880 1 0.6204 0.294 0.576 0.000 0.424
#> GSM425881 2 0.3619 0.834 0.136 0.864 0.000
#> GSM425882 2 0.0000 0.927 0.000 1.000 0.000
#> GSM425883 1 0.0661 0.910 0.988 0.008 0.004
#> GSM425884 1 0.0000 0.913 1.000 0.000 0.000
#> GSM425885 2 0.6204 0.188 0.424 0.576 0.000
#> GSM425848 1 0.1031 0.905 0.976 0.024 0.000
#> GSM425849 1 0.0000 0.913 1.000 0.000 0.000
#> GSM425850 1 0.1163 0.900 0.972 0.028 0.000
#> GSM425851 1 0.0892 0.906 0.980 0.000 0.020
#> GSM425852 3 0.4974 0.678 0.236 0.000 0.764
#> GSM425893 2 0.4750 0.730 0.000 0.784 0.216
#> GSM425894 2 0.0000 0.927 0.000 1.000 0.000
#> GSM425895 2 0.0000 0.927 0.000 1.000 0.000
#> GSM425896 2 0.0747 0.920 0.000 0.984 0.016
#> GSM425897 2 0.0747 0.921 0.000 0.984 0.016
#> GSM425898 2 0.0000 0.927 0.000 1.000 0.000
#> GSM425899 2 0.1964 0.891 0.056 0.944 0.000
#> GSM425900 2 0.0424 0.924 0.000 0.992 0.008
#> GSM425901 3 0.0829 0.946 0.012 0.004 0.984
#> GSM425902 1 0.3686 0.830 0.860 0.140 0.000
#> GSM425903 3 0.0237 0.951 0.000 0.004 0.996
#> GSM425904 1 0.6291 0.170 0.532 0.000 0.468
#> GSM425905 2 0.0000 0.927 0.000 1.000 0.000
#> GSM425906 2 0.0592 0.923 0.000 0.988 0.012
#> GSM425863 1 0.0000 0.913 1.000 0.000 0.000
#> GSM425864 2 0.0237 0.926 0.000 0.996 0.004
#> GSM425865 2 0.0000 0.927 0.000 1.000 0.000
#> GSM425866 1 0.5178 0.643 0.744 0.000 0.256
#> GSM425867 3 0.0000 0.953 0.000 0.000 1.000
#> GSM425868 2 0.0000 0.927 0.000 1.000 0.000
#> GSM425869 2 0.0000 0.927 0.000 1.000 0.000
#> GSM425870 3 0.1964 0.915 0.000 0.056 0.944
#> GSM425871 1 0.0000 0.913 1.000 0.000 0.000
#> GSM425872 2 0.0000 0.927 0.000 1.000 0.000
#> GSM425873 1 0.0237 0.912 0.996 0.004 0.000
#> GSM425843 1 0.0000 0.913 1.000 0.000 0.000
#> GSM425844 1 0.0000 0.913 1.000 0.000 0.000
#> GSM425845 3 0.4295 0.864 0.104 0.032 0.864
#> GSM425846 2 0.0000 0.927 0.000 1.000 0.000
#> GSM425847 2 0.4784 0.772 0.200 0.796 0.004
#> GSM425886 3 0.0237 0.951 0.000 0.004 0.996
#> GSM425887 2 0.2945 0.870 0.088 0.908 0.004
#> GSM425888 2 0.3619 0.836 0.136 0.864 0.000
#> GSM425889 1 0.0237 0.912 0.996 0.004 0.000
#> GSM425890 1 0.3412 0.845 0.876 0.124 0.000
#> GSM425891 2 0.0000 0.927 0.000 1.000 0.000
#> GSM425892 2 0.0000 0.927 0.000 1.000 0.000
#> GSM425853 1 0.1643 0.889 0.956 0.000 0.044
#> GSM425854 2 0.0000 0.927 0.000 1.000 0.000
#> GSM425855 1 0.0000 0.913 1.000 0.000 0.000
#> GSM425856 1 0.5497 0.582 0.708 0.000 0.292
#> GSM425857 3 0.5339 0.823 0.080 0.096 0.824
#> GSM425858 2 0.0592 0.922 0.012 0.988 0.000
#> GSM425859 2 0.0000 0.927 0.000 1.000 0.000
#> GSM425860 3 0.5138 0.824 0.052 0.120 0.828
#> GSM425861 2 0.6026 0.478 0.376 0.624 0.000
#> GSM425862 1 0.0592 0.910 0.988 0.012 0.000
#> GSM425837 1 0.0000 0.913 1.000 0.000 0.000
#> GSM425838 1 0.3551 0.837 0.868 0.132 0.000
#> GSM425839 2 0.0000 0.927 0.000 1.000 0.000
#> GSM425840 1 0.0000 0.913 1.000 0.000 0.000
#> GSM425841 1 0.3686 0.830 0.860 0.140 0.000
#> GSM425842 1 0.0000 0.913 1.000 0.000 0.000
#> GSM425917 3 0.4413 0.831 0.124 0.024 0.852
#> GSM425922 1 0.3412 0.844 0.876 0.124 0.000
#> GSM425919 1 0.1163 0.900 0.972 0.000 0.028
#> GSM425920 1 0.0000 0.913 1.000 0.000 0.000
#> GSM425923 1 0.0000 0.913 1.000 0.000 0.000
#> GSM425916 1 0.0000 0.913 1.000 0.000 0.000
#> GSM425918 1 0.0000 0.913 1.000 0.000 0.000
#> GSM425921 1 0.3412 0.844 0.876 0.124 0.000
#> GSM425925 1 0.0237 0.912 0.996 0.004 0.000
#> GSM425926 1 0.3340 0.847 0.880 0.120 0.000
#> GSM425927 1 0.0000 0.913 1.000 0.000 0.000
#> GSM425924 3 0.2066 0.914 0.060 0.000 0.940
#> GSM425928 3 0.0000 0.953 0.000 0.000 1.000
#> GSM425929 3 0.0000 0.953 0.000 0.000 1.000
#> GSM425930 3 0.0000 0.953 0.000 0.000 1.000
#> GSM425931 3 0.0000 0.953 0.000 0.000 1.000
#> GSM425932 3 0.0000 0.953 0.000 0.000 1.000
#> GSM425933 3 0.0000 0.953 0.000 0.000 1.000
#> GSM425934 3 0.0000 0.953 0.000 0.000 1.000
#> GSM425935 3 0.0000 0.953 0.000 0.000 1.000
#> GSM425936 3 0.0000 0.953 0.000 0.000 1.000
#> GSM425937 3 0.0000 0.953 0.000 0.000 1.000
#> GSM425938 3 0.0000 0.953 0.000 0.000 1.000
#> GSM425939 3 0.0000 0.953 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.0000 0.901352 0.000 1.000 0.000 0.000
#> GSM425908 2 0.0188 0.901014 0.000 0.996 0.000 0.004
#> GSM425909 3 0.5854 0.286638 0.460 0.024 0.512 0.004
#> GSM425910 1 0.0524 0.594884 0.988 0.000 0.004 0.008
#> GSM425911 2 0.4916 0.723642 0.184 0.760 0.056 0.000
#> GSM425912 2 0.5507 0.381559 0.416 0.568 0.008 0.008
#> GSM425913 2 0.0524 0.900389 0.008 0.988 0.004 0.000
#> GSM425914 2 0.6060 0.287550 0.440 0.516 0.044 0.000
#> GSM425915 3 0.4907 0.390727 0.420 0.000 0.580 0.000
#> GSM425874 4 0.0817 0.816281 0.000 0.024 0.000 0.976
#> GSM425875 1 0.3443 0.592740 0.848 0.000 0.016 0.136
#> GSM425876 1 0.0469 0.596769 0.988 0.000 0.000 0.012
#> GSM425877 4 0.3764 0.710871 0.216 0.000 0.000 0.784
#> GSM425878 4 0.4961 0.319279 0.448 0.000 0.000 0.552
#> GSM425879 2 0.0657 0.899499 0.012 0.984 0.004 0.000
#> GSM425880 1 0.4636 0.518728 0.792 0.000 0.140 0.068
#> GSM425881 2 0.5150 0.430874 0.396 0.596 0.000 0.008
#> GSM425882 2 0.0707 0.899724 0.020 0.980 0.000 0.000
#> GSM425883 4 0.1762 0.818804 0.048 0.004 0.004 0.944
#> GSM425884 1 0.4992 -0.148987 0.524 0.000 0.000 0.476
#> GSM425885 4 0.3873 0.579456 0.000 0.228 0.000 0.772
#> GSM425848 4 0.1151 0.817968 0.024 0.008 0.000 0.968
#> GSM425849 4 0.4761 0.543420 0.332 0.004 0.000 0.664
#> GSM425850 1 0.5060 0.000863 0.584 0.004 0.000 0.412
#> GSM425851 4 0.2313 0.811546 0.044 0.000 0.032 0.924
#> GSM425852 1 0.5386 0.100890 0.612 0.000 0.368 0.020
#> GSM425893 2 0.5199 0.704390 0.144 0.756 0.100 0.000
#> GSM425894 2 0.0817 0.894279 0.000 0.976 0.000 0.024
#> GSM425895 2 0.0188 0.901014 0.000 0.996 0.000 0.004
#> GSM425896 2 0.0779 0.898030 0.000 0.980 0.016 0.004
#> GSM425897 2 0.0937 0.899039 0.012 0.976 0.012 0.000
#> GSM425898 2 0.0188 0.901014 0.000 0.996 0.000 0.004
#> GSM425899 2 0.4827 0.730413 0.092 0.784 0.000 0.124
#> GSM425900 2 0.1211 0.890842 0.040 0.960 0.000 0.000
#> GSM425901 3 0.6378 0.267942 0.456 0.028 0.496 0.020
#> GSM425902 4 0.1118 0.810188 0.000 0.036 0.000 0.964
#> GSM425903 1 0.4477 0.208695 0.688 0.000 0.312 0.000
#> GSM425904 1 0.5226 0.468223 0.744 0.000 0.180 0.076
#> GSM425905 2 0.0188 0.901192 0.000 0.996 0.004 0.000
#> GSM425906 2 0.1398 0.890062 0.040 0.956 0.004 0.000
#> GSM425863 4 0.4382 0.612538 0.296 0.000 0.000 0.704
#> GSM425864 2 0.0188 0.901192 0.000 0.996 0.004 0.000
#> GSM425865 2 0.0188 0.901192 0.000 0.996 0.004 0.000
#> GSM425866 1 0.2214 0.601064 0.928 0.000 0.028 0.044
#> GSM425867 1 0.4985 -0.201810 0.532 0.000 0.468 0.000
#> GSM425868 2 0.2081 0.850459 0.000 0.916 0.000 0.084
#> GSM425869 2 0.0592 0.897543 0.000 0.984 0.000 0.016
#> GSM425870 3 0.5304 0.609906 0.148 0.104 0.748 0.000
#> GSM425871 4 0.3356 0.758477 0.176 0.000 0.000 0.824
#> GSM425872 2 0.0469 0.899180 0.000 0.988 0.000 0.012
#> GSM425873 1 0.4643 0.205314 0.656 0.000 0.000 0.344
#> GSM425843 4 0.4967 0.305558 0.452 0.000 0.000 0.548
#> GSM425844 4 0.1637 0.816173 0.060 0.000 0.000 0.940
#> GSM425845 1 0.0707 0.589046 0.980 0.000 0.020 0.000
#> GSM425846 2 0.1706 0.887593 0.036 0.948 0.000 0.016
#> GSM425847 1 0.5827 -0.054281 0.536 0.436 0.004 0.024
#> GSM425886 3 0.5731 0.349545 0.428 0.028 0.544 0.000
#> GSM425887 2 0.4053 0.723727 0.228 0.768 0.000 0.004
#> GSM425888 2 0.5050 0.635908 0.268 0.704 0.000 0.028
#> GSM425889 4 0.0188 0.820313 0.000 0.004 0.000 0.996
#> GSM425890 4 0.0779 0.818064 0.000 0.016 0.004 0.980
#> GSM425891 2 0.0657 0.899499 0.012 0.984 0.004 0.000
#> GSM425892 2 0.0188 0.901014 0.000 0.996 0.000 0.004
#> GSM425853 1 0.2542 0.606151 0.904 0.000 0.012 0.084
#> GSM425854 2 0.0000 0.901352 0.000 1.000 0.000 0.000
#> GSM425855 4 0.3123 0.761795 0.156 0.000 0.000 0.844
#> GSM425856 1 0.3168 0.589266 0.884 0.000 0.056 0.060
#> GSM425857 1 0.8711 -0.097805 0.436 0.072 0.336 0.156
#> GSM425858 2 0.2081 0.864663 0.084 0.916 0.000 0.000
#> GSM425859 2 0.0000 0.901352 0.000 1.000 0.000 0.000
#> GSM425860 1 0.6163 0.390527 0.668 0.080 0.244 0.008
#> GSM425861 1 0.7006 -0.047432 0.456 0.428 0.000 0.116
#> GSM425862 4 0.0188 0.820313 0.000 0.004 0.000 0.996
#> GSM425837 4 0.4679 0.524132 0.352 0.000 0.000 0.648
#> GSM425838 4 0.1118 0.810002 0.000 0.036 0.000 0.964
#> GSM425839 2 0.0000 0.901352 0.000 1.000 0.000 0.000
#> GSM425840 4 0.4431 0.605095 0.304 0.000 0.000 0.696
#> GSM425841 4 0.1022 0.812482 0.000 0.032 0.000 0.968
#> GSM425842 1 0.4898 0.002394 0.584 0.000 0.000 0.416
#> GSM425917 3 0.4011 0.609444 0.008 0.000 0.784 0.208
#> GSM425922 4 0.0817 0.816281 0.000 0.024 0.000 0.976
#> GSM425919 4 0.7495 0.219147 0.340 0.000 0.192 0.468
#> GSM425920 4 0.3219 0.765273 0.164 0.000 0.000 0.836
#> GSM425923 4 0.0592 0.822413 0.016 0.000 0.000 0.984
#> GSM425916 4 0.2125 0.811315 0.076 0.000 0.004 0.920
#> GSM425918 4 0.1211 0.820717 0.040 0.000 0.000 0.960
#> GSM425921 4 0.0707 0.817812 0.000 0.020 0.000 0.980
#> GSM425925 4 0.1004 0.823219 0.024 0.004 0.000 0.972
#> GSM425926 4 0.0592 0.818937 0.000 0.016 0.000 0.984
#> GSM425927 1 0.4916 -0.011111 0.576 0.000 0.000 0.424
#> GSM425924 3 0.3367 0.717325 0.028 0.000 0.864 0.108
#> GSM425928 3 0.0000 0.837136 0.000 0.000 1.000 0.000
#> GSM425929 3 0.0000 0.837136 0.000 0.000 1.000 0.000
#> GSM425930 3 0.0000 0.837136 0.000 0.000 1.000 0.000
#> GSM425931 3 0.0000 0.837136 0.000 0.000 1.000 0.000
#> GSM425932 3 0.0000 0.837136 0.000 0.000 1.000 0.000
#> GSM425933 3 0.0000 0.837136 0.000 0.000 1.000 0.000
#> GSM425934 3 0.0000 0.837136 0.000 0.000 1.000 0.000
#> GSM425935 3 0.0000 0.837136 0.000 0.000 1.000 0.000
#> GSM425936 3 0.0000 0.837136 0.000 0.000 1.000 0.000
#> GSM425937 3 0.0000 0.837136 0.000 0.000 1.000 0.000
#> GSM425938 3 0.0000 0.837136 0.000 0.000 1.000 0.000
#> GSM425939 3 0.0000 0.837136 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
#> GSM425907 2 0.1686 0.8449 0.028 0.944 0.000 0.008 0.020
#> GSM425908 2 0.1854 0.8443 0.036 0.936 0.000 0.008 0.020
#> GSM425909 5 0.3014 0.8426 0.004 0.016 0.104 0.008 0.868
#> GSM425910 1 0.3826 0.4721 0.752 0.008 0.004 0.000 0.236
#> GSM425911 2 0.7361 0.3047 0.284 0.496 0.084 0.000 0.136
#> GSM425912 1 0.4229 0.4015 0.704 0.276 0.000 0.000 0.020
#> GSM425913 2 0.2054 0.8459 0.072 0.916 0.000 0.004 0.008
#> GSM425914 1 0.6254 0.3264 0.576 0.276 0.016 0.000 0.132
#> GSM425915 5 0.3727 0.7732 0.016 0.000 0.216 0.000 0.768
#> GSM425874 4 0.1653 0.7539 0.004 0.028 0.000 0.944 0.024
#> GSM425875 5 0.1774 0.8264 0.052 0.000 0.000 0.016 0.932
#> GSM425876 1 0.2170 0.6232 0.904 0.004 0.000 0.004 0.088
#> GSM425877 4 0.5701 0.5679 0.272 0.000 0.000 0.604 0.124
#> GSM425878 1 0.5947 0.1190 0.556 0.000 0.000 0.312 0.132
#> GSM425879 2 0.2606 0.8373 0.056 0.900 0.012 0.000 0.032
#> GSM425880 5 0.1525 0.8418 0.036 0.000 0.012 0.004 0.948
#> GSM425881 1 0.4109 0.3877 0.700 0.288 0.000 0.000 0.012
#> GSM425882 2 0.2669 0.8283 0.104 0.876 0.000 0.000 0.020
#> GSM425883 4 0.3391 0.7451 0.112 0.004 0.008 0.848 0.028
#> GSM425884 1 0.6253 0.1673 0.532 0.000 0.000 0.280 0.188
#> GSM425885 4 0.3807 0.5412 0.000 0.240 0.000 0.748 0.012
#> GSM425848 4 0.4295 0.6750 0.032 0.012 0.000 0.760 0.196
#> GSM425849 4 0.6157 0.3331 0.364 0.000 0.000 0.496 0.140
#> GSM425850 1 0.2863 0.6152 0.876 0.000 0.000 0.064 0.060
#> GSM425851 4 0.4763 0.6955 0.192 0.000 0.024 0.740 0.044
#> GSM425852 5 0.3817 0.8347 0.056 0.000 0.108 0.012 0.824
#> GSM425893 2 0.6719 0.4657 0.104 0.564 0.060 0.000 0.272
#> GSM425894 2 0.2267 0.8401 0.028 0.916 0.000 0.048 0.008
#> GSM425895 2 0.1949 0.8493 0.040 0.932 0.000 0.016 0.012
#> GSM425896 2 0.2539 0.8386 0.036 0.912 0.016 0.008 0.028
#> GSM425897 2 0.3217 0.8275 0.056 0.876 0.040 0.004 0.024
#> GSM425898 2 0.2291 0.8427 0.048 0.916 0.000 0.024 0.012
#> GSM425899 2 0.7365 0.4212 0.136 0.544 0.000 0.136 0.184
#> GSM425900 2 0.3476 0.7849 0.160 0.816 0.000 0.004 0.020
#> GSM425901 5 0.2917 0.8414 0.000 0.012 0.108 0.012 0.868
#> GSM425902 4 0.1996 0.7520 0.004 0.032 0.000 0.928 0.036
#> GSM425903 5 0.3579 0.8208 0.100 0.000 0.072 0.000 0.828
#> GSM425904 5 0.1569 0.8421 0.032 0.000 0.012 0.008 0.948
#> GSM425905 2 0.1331 0.8484 0.040 0.952 0.000 0.000 0.008
#> GSM425906 2 0.3511 0.7772 0.184 0.800 0.000 0.004 0.012
#> GSM425863 4 0.5516 0.5249 0.296 0.000 0.000 0.608 0.096
#> GSM425864 2 0.1907 0.8428 0.044 0.928 0.000 0.000 0.028
#> GSM425865 2 0.1725 0.8451 0.044 0.936 0.000 0.000 0.020
#> GSM425866 5 0.1591 0.8369 0.052 0.000 0.004 0.004 0.940
#> GSM425867 5 0.4329 0.6493 0.016 0.000 0.312 0.000 0.672
#> GSM425868 2 0.2805 0.7986 0.008 0.872 0.000 0.108 0.012
#> GSM425869 2 0.1830 0.8407 0.012 0.932 0.000 0.052 0.004
#> GSM425870 3 0.6355 0.4430 0.264 0.060 0.600 0.000 0.076
#> GSM425871 4 0.5029 0.3641 0.444 0.004 0.000 0.528 0.024
#> GSM425872 2 0.3613 0.8179 0.076 0.848 0.000 0.048 0.028
#> GSM425873 1 0.2409 0.6213 0.900 0.000 0.000 0.032 0.068
#> GSM425843 1 0.6122 -0.0246 0.512 0.000 0.000 0.348 0.140
#> GSM425844 4 0.4167 0.6627 0.252 0.000 0.000 0.724 0.024
#> GSM425845 5 0.3039 0.7524 0.192 0.000 0.000 0.000 0.808
#> GSM425846 2 0.4117 0.7825 0.128 0.804 0.000 0.048 0.020
#> GSM425847 1 0.2519 0.6297 0.884 0.100 0.000 0.000 0.016
#> GSM425886 5 0.3925 0.7957 0.004 0.032 0.180 0.000 0.784
#> GSM425887 2 0.5051 0.2109 0.480 0.492 0.000 0.004 0.024
#> GSM425888 1 0.5270 0.0798 0.556 0.404 0.000 0.024 0.016
#> GSM425889 4 0.1981 0.7646 0.028 0.000 0.000 0.924 0.048
#> GSM425890 4 0.1372 0.7614 0.016 0.024 0.000 0.956 0.004
#> GSM425891 2 0.2179 0.8412 0.100 0.896 0.000 0.000 0.004
#> GSM425892 2 0.1721 0.8475 0.016 0.944 0.000 0.020 0.020
#> GSM425853 5 0.3783 0.6436 0.216 0.000 0.004 0.012 0.768
#> GSM425854 2 0.1267 0.8488 0.024 0.960 0.000 0.012 0.004
#> GSM425855 4 0.4645 0.6785 0.204 0.000 0.000 0.724 0.072
#> GSM425856 5 0.1285 0.8387 0.036 0.000 0.004 0.004 0.956
#> GSM425857 5 0.4741 0.7721 0.000 0.068 0.056 0.096 0.780
#> GSM425858 2 0.4216 0.6813 0.260 0.720 0.000 0.008 0.012
#> GSM425859 2 0.1518 0.8469 0.016 0.952 0.000 0.020 0.012
#> GSM425860 1 0.4649 0.5453 0.768 0.016 0.120 0.000 0.096
#> GSM425861 1 0.4716 0.5781 0.752 0.176 0.000 0.040 0.032
#> GSM425862 4 0.1568 0.7646 0.020 0.000 0.000 0.944 0.036
#> GSM425837 4 0.6352 0.4328 0.308 0.000 0.000 0.504 0.188
#> GSM425838 4 0.1569 0.7547 0.004 0.044 0.000 0.944 0.008
#> GSM425839 2 0.1787 0.8457 0.032 0.940 0.000 0.012 0.016
#> GSM425840 4 0.5932 0.2620 0.440 0.000 0.000 0.456 0.104
#> GSM425841 4 0.1818 0.7498 0.000 0.044 0.000 0.932 0.024
#> GSM425842 1 0.3532 0.5758 0.832 0.000 0.000 0.092 0.076
#> GSM425917 3 0.2193 0.8623 0.000 0.000 0.900 0.092 0.008
#> GSM425922 4 0.0703 0.7568 0.000 0.024 0.000 0.976 0.000
#> GSM425919 1 0.7433 0.0836 0.472 0.000 0.168 0.292 0.068
#> GSM425920 4 0.5044 0.4373 0.408 0.000 0.000 0.556 0.036
#> GSM425923 4 0.3115 0.7464 0.112 0.000 0.000 0.852 0.036
#> GSM425916 4 0.4134 0.7017 0.196 0.000 0.000 0.760 0.044
#> GSM425918 4 0.3051 0.7444 0.120 0.000 0.000 0.852 0.028
#> GSM425921 4 0.0865 0.7570 0.000 0.024 0.000 0.972 0.004
#> GSM425925 4 0.1981 0.7652 0.048 0.000 0.000 0.924 0.028
#> GSM425926 4 0.1173 0.7585 0.004 0.020 0.000 0.964 0.012
#> GSM425927 1 0.4219 0.5326 0.780 0.000 0.000 0.116 0.104
#> GSM425924 3 0.1788 0.8976 0.004 0.000 0.932 0.056 0.008
#> GSM425928 3 0.0000 0.9556 0.000 0.000 1.000 0.000 0.000
#> GSM425929 3 0.0000 0.9556 0.000 0.000 1.000 0.000 0.000
#> GSM425930 3 0.0000 0.9556 0.000 0.000 1.000 0.000 0.000
#> GSM425931 3 0.0000 0.9556 0.000 0.000 1.000 0.000 0.000
#> GSM425932 3 0.0000 0.9556 0.000 0.000 1.000 0.000 0.000
#> GSM425933 3 0.0000 0.9556 0.000 0.000 1.000 0.000 0.000
#> GSM425934 3 0.0000 0.9556 0.000 0.000 1.000 0.000 0.000
#> GSM425935 3 0.0000 0.9556 0.000 0.000 1.000 0.000 0.000
#> GSM425936 3 0.0000 0.9556 0.000 0.000 1.000 0.000 0.000
#> GSM425937 3 0.0000 0.9556 0.000 0.000 1.000 0.000 0.000
#> GSM425938 3 0.0000 0.9556 0.000 0.000 1.000 0.000 0.000
#> GSM425939 3 0.0000 0.9556 0.000 0.000 1.000 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 2 0.0458 0.656826 0.000 0.984 0.000 0.000 0.000 0.016
#> GSM425908 2 0.0806 0.654628 0.000 0.972 0.000 0.008 0.000 0.020
#> GSM425909 5 0.1448 0.877238 0.000 0.016 0.024 0.000 0.948 0.012
#> GSM425910 1 0.6090 0.066840 0.452 0.024 0.000 0.000 0.140 0.384
#> GSM425911 2 0.6456 0.031398 0.064 0.536 0.024 0.000 0.076 0.300
#> GSM425912 6 0.5476 0.298953 0.276 0.136 0.000 0.000 0.008 0.580
#> GSM425913 2 0.3835 0.548239 0.004 0.656 0.000 0.000 0.004 0.336
#> GSM425914 6 0.7427 0.261986 0.172 0.280 0.024 0.000 0.092 0.432
#> GSM425915 5 0.3211 0.841120 0.012 0.008 0.108 0.000 0.844 0.028
#> GSM425874 4 0.1663 0.737942 0.024 0.004 0.000 0.940 0.008 0.024
#> GSM425875 5 0.2495 0.846003 0.052 0.000 0.004 0.036 0.896 0.012
#> GSM425876 1 0.4301 0.216388 0.584 0.000 0.000 0.000 0.024 0.392
#> GSM425877 1 0.4964 0.034807 0.540 0.000 0.000 0.404 0.044 0.012
#> GSM425878 1 0.4870 0.573867 0.724 0.000 0.000 0.140 0.056 0.080
#> GSM425879 2 0.1806 0.641097 0.004 0.908 0.000 0.000 0.000 0.088
#> GSM425880 5 0.0837 0.876672 0.020 0.000 0.004 0.000 0.972 0.004
#> GSM425881 6 0.4971 0.326183 0.300 0.096 0.000 0.000 0.000 0.604
#> GSM425882 2 0.2742 0.572118 0.012 0.852 0.000 0.008 0.000 0.128
#> GSM425883 4 0.4371 0.668328 0.144 0.000 0.012 0.760 0.012 0.072
#> GSM425884 1 0.4098 0.567886 0.784 0.000 0.000 0.104 0.084 0.028
#> GSM425885 4 0.4135 0.566586 0.008 0.200 0.000 0.748 0.012 0.032
#> GSM425848 4 0.4262 0.643823 0.052 0.008 0.000 0.760 0.164 0.016
#> GSM425849 4 0.5951 0.034348 0.412 0.000 0.000 0.464 0.060 0.064
#> GSM425850 1 0.4359 0.363730 0.664 0.000 0.000 0.032 0.008 0.296
#> GSM425851 1 0.5248 -0.106395 0.496 0.000 0.024 0.440 0.004 0.036
#> GSM425852 5 0.3479 0.834382 0.096 0.000 0.052 0.008 0.832 0.012
#> GSM425893 2 0.6022 0.238413 0.016 0.620 0.040 0.000 0.144 0.180
#> GSM425894 2 0.4782 0.485728 0.000 0.568 0.000 0.048 0.004 0.380
#> GSM425895 2 0.4479 0.533727 0.000 0.608 0.000 0.032 0.004 0.356
#> GSM425896 2 0.1092 0.638590 0.000 0.960 0.000 0.000 0.020 0.020
#> GSM425897 2 0.2746 0.583250 0.004 0.868 0.020 0.000 0.008 0.100
#> GSM425898 2 0.4444 0.490608 0.000 0.576 0.000 0.024 0.004 0.396
#> GSM425899 6 0.7766 0.000122 0.056 0.248 0.000 0.148 0.108 0.440
#> GSM425900 6 0.4189 -0.279689 0.008 0.436 0.000 0.004 0.000 0.552
#> GSM425901 5 0.1680 0.876456 0.000 0.020 0.024 0.004 0.940 0.012
#> GSM425902 4 0.2177 0.728743 0.016 0.012 0.000 0.916 0.012 0.044
#> GSM425903 5 0.3152 0.848171 0.040 0.008 0.020 0.000 0.860 0.072
#> GSM425904 5 0.0837 0.876672 0.020 0.000 0.004 0.000 0.972 0.004
#> GSM425905 2 0.1387 0.660558 0.000 0.932 0.000 0.000 0.000 0.068
#> GSM425906 6 0.4096 -0.298729 0.008 0.484 0.000 0.000 0.000 0.508
#> GSM425863 4 0.5461 0.422130 0.252 0.000 0.000 0.624 0.040 0.084
#> GSM425864 2 0.1462 0.637814 0.000 0.936 0.000 0.000 0.008 0.056
#> GSM425865 2 0.1364 0.657624 0.000 0.944 0.000 0.004 0.004 0.048
#> GSM425866 5 0.0837 0.876222 0.020 0.000 0.004 0.000 0.972 0.004
#> GSM425867 5 0.4253 0.708993 0.020 0.000 0.228 0.000 0.720 0.032
#> GSM425868 2 0.5145 0.520103 0.008 0.648 0.000 0.148 0.000 0.196
#> GSM425869 2 0.4170 0.570585 0.000 0.660 0.000 0.032 0.000 0.308
#> GSM425870 3 0.8053 -0.111314 0.068 0.200 0.332 0.000 0.084 0.316
#> GSM425871 1 0.5406 0.226524 0.528 0.000 0.000 0.368 0.008 0.096
#> GSM425872 2 0.5127 0.382366 0.004 0.500 0.004 0.040 0.008 0.444
#> GSM425873 1 0.3802 0.335396 0.676 0.000 0.000 0.000 0.012 0.312
#> GSM425843 1 0.4564 0.557742 0.748 0.000 0.000 0.132 0.076 0.044
#> GSM425844 4 0.4863 0.217308 0.440 0.000 0.000 0.512 0.008 0.040
#> GSM425845 5 0.3608 0.788051 0.068 0.000 0.004 0.000 0.800 0.128
#> GSM425846 6 0.6007 -0.225450 0.048 0.392 0.000 0.056 0.012 0.492
#> GSM425847 6 0.4389 -0.014593 0.468 0.016 0.000 0.000 0.004 0.512
#> GSM425886 5 0.2670 0.862334 0.000 0.044 0.052 0.000 0.884 0.020
#> GSM425887 6 0.5920 0.321228 0.160 0.316 0.000 0.004 0.008 0.512
#> GSM425888 6 0.4995 0.360895 0.148 0.152 0.000 0.016 0.000 0.684
#> GSM425889 4 0.2689 0.727285 0.060 0.004 0.000 0.884 0.040 0.012
#> GSM425890 4 0.2848 0.708834 0.124 0.000 0.004 0.848 0.000 0.024
#> GSM425891 2 0.3738 0.570897 0.004 0.680 0.000 0.000 0.004 0.312
#> GSM425892 2 0.2230 0.658847 0.000 0.892 0.000 0.024 0.000 0.084
#> GSM425853 5 0.4321 0.496368 0.316 0.000 0.000 0.012 0.652 0.020
#> GSM425854 2 0.3672 0.585932 0.000 0.688 0.000 0.008 0.000 0.304
#> GSM425855 4 0.5374 0.467415 0.276 0.000 0.000 0.616 0.036 0.072
#> GSM425856 5 0.1053 0.874867 0.020 0.000 0.000 0.004 0.964 0.012
#> GSM425857 5 0.3114 0.839777 0.000 0.068 0.012 0.052 0.860 0.008
#> GSM425858 6 0.4936 -0.061476 0.048 0.364 0.000 0.012 0.000 0.576
#> GSM425859 2 0.3426 0.598854 0.000 0.720 0.000 0.004 0.000 0.276
#> GSM425860 6 0.6129 -0.011035 0.388 0.016 0.060 0.000 0.048 0.488
#> GSM425861 6 0.5198 0.192546 0.376 0.028 0.000 0.028 0.008 0.560
#> GSM425862 4 0.2445 0.735034 0.060 0.004 0.000 0.896 0.032 0.008
#> GSM425837 1 0.5961 0.319998 0.544 0.000 0.000 0.292 0.132 0.032
#> GSM425838 4 0.2910 0.728657 0.068 0.044 0.000 0.868 0.000 0.020
#> GSM425839 2 0.4058 0.528319 0.000 0.616 0.000 0.008 0.004 0.372
#> GSM425840 1 0.5385 0.356505 0.592 0.000 0.000 0.312 0.052 0.044
#> GSM425841 4 0.2205 0.733425 0.020 0.020 0.000 0.916 0.008 0.036
#> GSM425842 1 0.3404 0.450003 0.760 0.000 0.000 0.000 0.016 0.224
#> GSM425917 3 0.3730 0.762005 0.088 0.000 0.812 0.076 0.000 0.024
#> GSM425922 4 0.1745 0.737380 0.056 0.000 0.000 0.924 0.000 0.020
#> GSM425919 1 0.4881 0.511323 0.740 0.000 0.100 0.112 0.016 0.032
#> GSM425920 1 0.4710 0.344155 0.652 0.000 0.004 0.288 0.008 0.048
#> GSM425923 4 0.3879 0.568163 0.292 0.000 0.000 0.688 0.000 0.020
#> GSM425916 4 0.4536 0.173322 0.476 0.000 0.000 0.496 0.004 0.024
#> GSM425918 4 0.4092 0.474526 0.344 0.000 0.000 0.636 0.000 0.020
#> GSM425921 4 0.1268 0.739088 0.036 0.004 0.000 0.952 0.000 0.008
#> GSM425925 4 0.2798 0.722581 0.108 0.000 0.000 0.860 0.020 0.012
#> GSM425926 4 0.1293 0.739553 0.020 0.004 0.000 0.956 0.004 0.016
#> GSM425927 1 0.3433 0.529663 0.808 0.000 0.000 0.020 0.020 0.152
#> GSM425924 3 0.3575 0.780700 0.092 0.000 0.824 0.056 0.000 0.028
#> GSM425928 3 0.0000 0.928092 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425929 3 0.0000 0.928092 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425930 3 0.0000 0.928092 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425931 3 0.0000 0.928092 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425932 3 0.0000 0.928092 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425933 3 0.0000 0.928092 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425934 3 0.0000 0.928092 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425935 3 0.0000 0.928092 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425936 3 0.0000 0.928092 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425937 3 0.0000 0.928092 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425938 3 0.0000 0.928092 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425939 3 0.0000 0.928092 0.000 0.000 1.000 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 disease.state(p) tissue(p) other(p) k
#> MAD:skmeans 95 1.03e-03 3.96e-05 7.66e-07 2
#> MAD:skmeans 98 5.99e-09 4.25e-10 1.99e-08 3
#> MAD:skmeans 80 3.30e-13 2.34e-14 8.63e-11 4
#> MAD:skmeans 84 2.27e-14 2.37e-15 3.36e-08 5
#> MAD:skmeans 66 4.18e-11 4.68e-12 7.79e-06 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 103 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 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 0.704 0.848 0.928 0.4739 0.525 0.525
#> 3 3 0.431 0.656 0.827 0.3738 0.700 0.486
#> 4 4 0.575 0.690 0.829 0.1124 0.857 0.624
#> 5 5 0.610 0.666 0.794 0.0679 0.943 0.796
#> 6 6 0.655 0.650 0.785 0.0530 0.921 0.674
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
#> GSM425907 1 0.0000 0.9352 1.000 0.000
#> GSM425908 1 0.0376 0.9345 0.996 0.004
#> GSM425909 2 0.3431 0.8909 0.064 0.936
#> GSM425910 1 0.7815 0.6880 0.768 0.232
#> GSM425911 1 0.0938 0.9336 0.988 0.012
#> GSM425912 1 0.0000 0.9352 1.000 0.000
#> GSM425913 1 0.0938 0.9337 0.988 0.012
#> GSM425914 1 0.0000 0.9352 1.000 0.000
#> GSM425915 2 0.2778 0.8955 0.048 0.952
#> GSM425874 1 0.0672 0.9336 0.992 0.008
#> GSM425875 1 0.9970 0.0339 0.532 0.468
#> GSM425876 2 0.9686 0.4313 0.396 0.604
#> GSM425877 2 0.3114 0.8900 0.056 0.944
#> GSM425878 1 0.0938 0.9342 0.988 0.012
#> GSM425879 1 0.3114 0.9109 0.944 0.056
#> GSM425880 2 0.0938 0.9035 0.012 0.988
#> GSM425881 1 0.0376 0.9345 0.996 0.004
#> GSM425882 1 0.0376 0.9345 0.996 0.004
#> GSM425883 2 0.9977 0.2073 0.472 0.528
#> GSM425884 2 0.4431 0.8674 0.092 0.908
#> GSM425885 1 0.0672 0.9352 0.992 0.008
#> GSM425848 1 0.6531 0.8047 0.832 0.168
#> GSM425849 1 0.0672 0.9336 0.992 0.008
#> GSM425850 1 0.0938 0.9352 0.988 0.012
#> GSM425851 1 0.8327 0.6800 0.736 0.264
#> GSM425852 2 0.0672 0.9035 0.008 0.992
#> GSM425893 1 0.1633 0.9291 0.976 0.024
#> GSM425894 1 0.0000 0.9352 1.000 0.000
#> GSM425895 1 0.0000 0.9352 1.000 0.000
#> GSM425896 1 0.0938 0.9338 0.988 0.012
#> GSM425897 1 0.0376 0.9354 0.996 0.004
#> GSM425898 1 0.2236 0.9225 0.964 0.036
#> GSM425899 1 0.3274 0.9085 0.940 0.060
#> GSM425900 1 0.5946 0.8305 0.856 0.144
#> GSM425901 2 0.3431 0.8836 0.064 0.936
#> GSM425902 1 0.3733 0.9013 0.928 0.072
#> GSM425903 2 0.3879 0.8853 0.076 0.924
#> GSM425904 2 0.0376 0.9028 0.004 0.996
#> GSM425905 1 0.0000 0.9352 1.000 0.000
#> GSM425906 1 0.0376 0.9352 0.996 0.004
#> GSM425863 1 0.1184 0.9337 0.984 0.016
#> GSM425864 1 0.0672 0.9350 0.992 0.008
#> GSM425865 1 0.0000 0.9352 1.000 0.000
#> GSM425866 2 0.9963 0.2237 0.464 0.536
#> GSM425867 2 0.0376 0.9028 0.004 0.996
#> GSM425868 1 0.0000 0.9352 1.000 0.000
#> GSM425869 1 0.2778 0.9152 0.952 0.048
#> GSM425870 2 0.3879 0.8858 0.076 0.924
#> GSM425871 1 0.0672 0.9336 0.992 0.008
#> GSM425872 1 0.0000 0.9352 1.000 0.000
#> GSM425873 1 0.3879 0.8990 0.924 0.076
#> GSM425843 2 0.7883 0.7229 0.236 0.764
#> GSM425844 2 0.9833 0.3101 0.424 0.576
#> GSM425845 1 0.9209 0.4762 0.664 0.336
#> GSM425846 1 0.0000 0.9352 1.000 0.000
#> GSM425847 1 0.0000 0.9352 1.000 0.000
#> GSM425886 2 0.5842 0.8376 0.140 0.860
#> GSM425887 1 0.0000 0.9352 1.000 0.000
#> GSM425888 1 0.0376 0.9353 0.996 0.004
#> GSM425889 2 0.5178 0.8506 0.116 0.884
#> GSM425890 1 0.1414 0.9319 0.980 0.020
#> GSM425891 1 0.3879 0.8963 0.924 0.076
#> GSM425892 1 0.0000 0.9352 1.000 0.000
#> GSM425853 1 0.5629 0.8496 0.868 0.132
#> GSM425854 1 0.0000 0.9352 1.000 0.000
#> GSM425855 2 0.2948 0.8943 0.052 0.948
#> GSM425856 1 0.2423 0.9224 0.960 0.040
#> GSM425857 1 0.6343 0.8197 0.840 0.160
#> GSM425858 1 0.0000 0.9352 1.000 0.000
#> GSM425859 1 0.0000 0.9352 1.000 0.000
#> GSM425860 2 0.2948 0.8934 0.052 0.948
#> GSM425861 1 0.0376 0.9345 0.996 0.004
#> GSM425862 1 0.2778 0.9152 0.952 0.048
#> GSM425837 1 0.9491 0.4211 0.632 0.368
#> GSM425838 1 0.1633 0.9302 0.976 0.024
#> GSM425839 1 0.3274 0.9063 0.940 0.060
#> GSM425840 2 0.3584 0.8855 0.068 0.932
#> GSM425841 1 0.0938 0.9348 0.988 0.012
#> GSM425842 1 0.6048 0.8148 0.852 0.148
#> GSM425917 2 0.0376 0.9028 0.004 0.996
#> GSM425922 1 0.2043 0.9294 0.968 0.032
#> GSM425919 2 0.0376 0.9028 0.004 0.996
#> GSM425920 2 0.5842 0.8278 0.140 0.860
#> GSM425923 1 0.9983 0.0318 0.524 0.476
#> GSM425916 2 0.1184 0.9011 0.016 0.984
#> GSM425918 1 0.1414 0.9332 0.980 0.020
#> GSM425921 1 0.2423 0.9247 0.960 0.040
#> GSM425925 1 0.1843 0.9303 0.972 0.028
#> GSM425926 1 0.0938 0.9338 0.988 0.012
#> GSM425927 2 0.9933 0.2573 0.452 0.548
#> GSM425924 2 0.0376 0.9028 0.004 0.996
#> GSM425928 2 0.0672 0.9038 0.008 0.992
#> GSM425929 2 0.0672 0.9038 0.008 0.992
#> GSM425930 2 0.0672 0.9038 0.008 0.992
#> GSM425931 2 0.0376 0.9028 0.004 0.996
#> GSM425932 2 0.0672 0.9038 0.008 0.992
#> GSM425933 2 0.0672 0.9038 0.008 0.992
#> GSM425934 2 0.0672 0.9038 0.008 0.992
#> GSM425935 2 0.0672 0.9038 0.008 0.992
#> GSM425936 2 0.0672 0.9038 0.008 0.992
#> GSM425937 2 0.0672 0.9038 0.008 0.992
#> GSM425938 2 0.0672 0.9038 0.008 0.992
#> GSM425939 2 0.0672 0.9038 0.008 0.992
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.0747 0.8016 0.016 0.984 0.000
#> GSM425908 2 0.1860 0.8005 0.052 0.948 0.000
#> GSM425909 3 0.8055 0.2528 0.440 0.064 0.496
#> GSM425910 2 0.8297 0.4551 0.348 0.560 0.092
#> GSM425911 2 0.1529 0.8032 0.040 0.960 0.000
#> GSM425912 2 0.5591 0.6412 0.304 0.696 0.000
#> GSM425913 2 0.0829 0.8015 0.004 0.984 0.012
#> GSM425914 2 0.5760 0.5962 0.328 0.672 0.000
#> GSM425915 3 0.6283 0.7025 0.064 0.176 0.760
#> GSM425874 1 0.5859 0.5621 0.656 0.344 0.000
#> GSM425875 1 0.7785 0.4920 0.672 0.192 0.136
#> GSM425876 1 0.9544 0.0235 0.464 0.328 0.208
#> GSM425877 1 0.1129 0.7274 0.976 0.004 0.020
#> GSM425878 1 0.5553 0.5359 0.724 0.272 0.004
#> GSM425879 2 0.4139 0.7518 0.016 0.860 0.124
#> GSM425880 1 0.6952 -0.1926 0.504 0.016 0.480
#> GSM425881 2 0.4931 0.7182 0.232 0.768 0.000
#> GSM425882 2 0.1964 0.8013 0.056 0.944 0.000
#> GSM425883 1 0.1585 0.7315 0.964 0.028 0.008
#> GSM425884 1 0.1585 0.7235 0.964 0.008 0.028
#> GSM425885 2 0.3816 0.6540 0.148 0.852 0.000
#> GSM425848 1 0.1031 0.7344 0.976 0.024 0.000
#> GSM425849 1 0.0000 0.7281 1.000 0.000 0.000
#> GSM425850 2 0.6298 0.4298 0.388 0.608 0.004
#> GSM425851 1 0.8840 0.3330 0.456 0.428 0.116
#> GSM425852 3 0.5493 0.6345 0.232 0.012 0.756
#> GSM425893 2 0.6090 0.6529 0.264 0.716 0.020
#> GSM425894 2 0.0000 0.7998 0.000 1.000 0.000
#> GSM425895 2 0.1529 0.8033 0.040 0.960 0.000
#> GSM425896 2 0.1031 0.8053 0.024 0.976 0.000
#> GSM425897 2 0.1163 0.8052 0.028 0.972 0.000
#> GSM425898 2 0.3038 0.7632 0.000 0.896 0.104
#> GSM425899 2 0.4504 0.7326 0.196 0.804 0.000
#> GSM425900 2 0.6388 0.6820 0.064 0.752 0.184
#> GSM425901 3 0.8404 0.1757 0.452 0.084 0.464
#> GSM425902 1 0.6608 0.4424 0.560 0.432 0.008
#> GSM425903 3 0.9423 0.3222 0.320 0.196 0.484
#> GSM425904 1 0.5884 0.4528 0.716 0.012 0.272
#> GSM425905 2 0.1031 0.8036 0.024 0.976 0.000
#> GSM425906 2 0.1031 0.8036 0.024 0.976 0.000
#> GSM425863 1 0.0892 0.7339 0.980 0.020 0.000
#> GSM425864 2 0.0592 0.8035 0.012 0.988 0.000
#> GSM425865 2 0.1031 0.8036 0.024 0.976 0.000
#> GSM425866 1 0.8729 0.3601 0.592 0.204 0.204
#> GSM425867 3 0.2584 0.8183 0.064 0.008 0.928
#> GSM425868 2 0.1031 0.7980 0.024 0.976 0.000
#> GSM425869 2 0.0237 0.7998 0.000 0.996 0.004
#> GSM425870 3 0.7147 0.6691 0.124 0.156 0.720
#> GSM425871 2 0.6309 -0.2295 0.500 0.500 0.000
#> GSM425872 2 0.2878 0.7863 0.096 0.904 0.000
#> GSM425873 1 0.3851 0.6404 0.860 0.136 0.004
#> GSM425843 1 0.0424 0.7289 0.992 0.000 0.008
#> GSM425844 1 0.6974 0.6468 0.728 0.104 0.168
#> GSM425845 2 0.8288 0.4817 0.332 0.572 0.096
#> GSM425846 2 0.3941 0.7619 0.156 0.844 0.000
#> GSM425847 2 0.4750 0.7316 0.216 0.784 0.000
#> GSM425886 3 0.7447 0.6345 0.120 0.184 0.696
#> GSM425887 2 0.5785 0.6060 0.332 0.668 0.000
#> GSM425888 2 0.3941 0.7643 0.156 0.844 0.000
#> GSM425889 1 0.5951 0.6296 0.764 0.040 0.196
#> GSM425890 2 0.6305 -0.2455 0.484 0.516 0.000
#> GSM425891 2 0.1636 0.8050 0.020 0.964 0.016
#> GSM425892 2 0.0000 0.7998 0.000 1.000 0.000
#> GSM425853 1 0.2384 0.7267 0.936 0.056 0.008
#> GSM425854 2 0.0747 0.8016 0.016 0.984 0.000
#> GSM425855 1 0.4645 0.6501 0.816 0.008 0.176
#> GSM425856 2 0.6155 0.5875 0.328 0.664 0.008
#> GSM425857 2 0.6001 0.5860 0.144 0.784 0.072
#> GSM425858 2 0.4121 0.7594 0.168 0.832 0.000
#> GSM425859 2 0.0592 0.7999 0.012 0.988 0.000
#> GSM425860 3 0.6488 0.6836 0.064 0.192 0.744
#> GSM425861 2 0.6180 0.4855 0.416 0.584 0.000
#> GSM425862 1 0.5497 0.6143 0.708 0.292 0.000
#> GSM425837 1 0.0000 0.7281 1.000 0.000 0.000
#> GSM425838 1 0.5529 0.6026 0.704 0.296 0.000
#> GSM425839 2 0.0237 0.7998 0.000 0.996 0.004
#> GSM425840 1 0.3482 0.6875 0.872 0.000 0.128
#> GSM425841 1 0.5905 0.5668 0.648 0.352 0.000
#> GSM425842 1 0.1753 0.7238 0.952 0.048 0.000
#> GSM425917 3 0.0000 0.8500 0.000 0.000 1.000
#> GSM425922 1 0.6168 0.4664 0.588 0.412 0.000
#> GSM425919 3 0.4469 0.7856 0.076 0.060 0.864
#> GSM425920 1 0.6126 0.5531 0.712 0.020 0.268
#> GSM425923 1 0.0424 0.7287 0.992 0.000 0.008
#> GSM425916 1 0.5431 0.5385 0.716 0.000 0.284
#> GSM425918 1 0.3941 0.6924 0.844 0.156 0.000
#> GSM425921 1 0.5859 0.5608 0.656 0.344 0.000
#> GSM425925 1 0.0892 0.7320 0.980 0.020 0.000
#> GSM425926 1 0.5785 0.5760 0.668 0.332 0.000
#> GSM425927 1 0.4636 0.6502 0.848 0.116 0.036
#> GSM425924 3 0.1636 0.8378 0.020 0.016 0.964
#> GSM425928 3 0.0000 0.8500 0.000 0.000 1.000
#> GSM425929 3 0.0000 0.8500 0.000 0.000 1.000
#> GSM425930 3 0.0000 0.8500 0.000 0.000 1.000
#> GSM425931 3 0.0000 0.8500 0.000 0.000 1.000
#> GSM425932 3 0.0000 0.8500 0.000 0.000 1.000
#> GSM425933 3 0.0000 0.8500 0.000 0.000 1.000
#> GSM425934 3 0.0000 0.8500 0.000 0.000 1.000
#> GSM425935 3 0.0000 0.8500 0.000 0.000 1.000
#> GSM425936 3 0.0000 0.8500 0.000 0.000 1.000
#> GSM425937 3 0.0000 0.8500 0.000 0.000 1.000
#> GSM425938 3 0.0000 0.8500 0.000 0.000 1.000
#> GSM425939 3 0.0000 0.8500 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.0000 0.850 0.000 1.000 0.000 0.000
#> GSM425908 2 0.1109 0.852 0.028 0.968 0.000 0.004
#> GSM425909 1 0.2965 0.740 0.892 0.036 0.072 0.000
#> GSM425910 1 0.4632 0.509 0.688 0.308 0.000 0.004
#> GSM425911 2 0.2466 0.831 0.096 0.900 0.000 0.004
#> GSM425912 2 0.3791 0.751 0.200 0.796 0.000 0.004
#> GSM425913 2 0.0524 0.852 0.008 0.988 0.004 0.000
#> GSM425914 2 0.5060 0.354 0.412 0.584 0.000 0.004
#> GSM425915 1 0.6327 0.630 0.652 0.132 0.216 0.000
#> GSM425874 4 0.0469 0.713 0.000 0.012 0.000 0.988
#> GSM425875 1 0.0188 0.720 0.996 0.000 0.000 0.004
#> GSM425876 1 0.5726 0.644 0.728 0.196 0.024 0.052
#> GSM425877 4 0.3668 0.727 0.188 0.000 0.004 0.808
#> GSM425878 4 0.7910 0.249 0.316 0.320 0.000 0.364
#> GSM425879 2 0.2400 0.842 0.028 0.924 0.044 0.004
#> GSM425880 1 0.1302 0.725 0.956 0.000 0.044 0.000
#> GSM425881 2 0.3751 0.759 0.196 0.800 0.000 0.004
#> GSM425882 2 0.1661 0.844 0.052 0.944 0.000 0.004
#> GSM425883 1 0.5832 0.490 0.708 0.040 0.028 0.224
#> GSM425884 4 0.4804 0.602 0.384 0.000 0.000 0.616
#> GSM425885 2 0.3523 0.744 0.032 0.856 0.000 0.112
#> GSM425848 4 0.4008 0.710 0.244 0.000 0.000 0.756
#> GSM425849 4 0.3610 0.730 0.200 0.000 0.000 0.800
#> GSM425850 2 0.6639 0.527 0.160 0.640 0.004 0.196
#> GSM425851 4 0.9171 0.295 0.084 0.268 0.244 0.404
#> GSM425852 1 0.6148 0.468 0.636 0.000 0.280 0.084
#> GSM425893 1 0.4522 0.561 0.680 0.320 0.000 0.000
#> GSM425894 2 0.0376 0.851 0.004 0.992 0.000 0.004
#> GSM425895 2 0.2216 0.829 0.092 0.908 0.000 0.000
#> GSM425896 2 0.1398 0.851 0.040 0.956 0.000 0.004
#> GSM425897 2 0.2197 0.838 0.080 0.916 0.000 0.004
#> GSM425898 2 0.2494 0.832 0.048 0.916 0.036 0.000
#> GSM425899 2 0.4088 0.692 0.232 0.764 0.000 0.004
#> GSM425900 2 0.4245 0.774 0.116 0.820 0.064 0.000
#> GSM425901 1 0.2189 0.728 0.932 0.020 0.044 0.004
#> GSM425902 4 0.7182 -0.124 0.412 0.136 0.000 0.452
#> GSM425903 1 0.2670 0.743 0.908 0.052 0.040 0.000
#> GSM425904 1 0.1637 0.721 0.940 0.000 0.060 0.000
#> GSM425905 2 0.0524 0.853 0.008 0.988 0.000 0.004
#> GSM425906 2 0.0524 0.853 0.008 0.988 0.000 0.004
#> GSM425863 4 0.4175 0.722 0.200 0.016 0.000 0.784
#> GSM425864 2 0.0524 0.853 0.008 0.988 0.000 0.004
#> GSM425865 2 0.0524 0.853 0.008 0.988 0.000 0.004
#> GSM425866 1 0.0188 0.723 0.996 0.000 0.004 0.000
#> GSM425867 3 0.5000 -0.131 0.496 0.000 0.504 0.000
#> GSM425868 2 0.0000 0.850 0.000 1.000 0.000 0.000
#> GSM425869 2 0.2011 0.825 0.000 0.920 0.000 0.080
#> GSM425870 1 0.7325 0.440 0.516 0.152 0.328 0.004
#> GSM425871 2 0.7222 0.119 0.172 0.528 0.000 0.300
#> GSM425872 2 0.2530 0.821 0.112 0.888 0.000 0.000
#> GSM425873 4 0.6160 0.592 0.316 0.072 0.000 0.612
#> GSM425843 4 0.3907 0.715 0.232 0.000 0.000 0.768
#> GSM425844 4 0.5287 0.723 0.144 0.036 0.044 0.776
#> GSM425845 1 0.4576 0.611 0.728 0.260 0.012 0.000
#> GSM425846 2 0.2216 0.830 0.092 0.908 0.000 0.000
#> GSM425847 2 0.3448 0.786 0.168 0.828 0.000 0.004
#> GSM425886 1 0.5820 0.622 0.696 0.100 0.204 0.000
#> GSM425887 2 0.4655 0.597 0.312 0.684 0.000 0.004
#> GSM425888 2 0.2149 0.833 0.088 0.912 0.000 0.000
#> GSM425889 4 0.5296 -0.175 0.492 0.000 0.008 0.500
#> GSM425890 4 0.5150 0.294 0.008 0.396 0.000 0.596
#> GSM425891 2 0.0592 0.853 0.016 0.984 0.000 0.000
#> GSM425892 2 0.0000 0.850 0.000 1.000 0.000 0.000
#> GSM425853 1 0.3539 0.519 0.820 0.004 0.000 0.176
#> GSM425854 2 0.0188 0.852 0.004 0.996 0.000 0.000
#> GSM425855 4 0.4931 0.717 0.132 0.000 0.092 0.776
#> GSM425856 1 0.2081 0.733 0.916 0.084 0.000 0.000
#> GSM425857 1 0.4854 0.564 0.676 0.316 0.004 0.004
#> GSM425858 2 0.2466 0.829 0.096 0.900 0.000 0.004
#> GSM425859 2 0.0000 0.850 0.000 1.000 0.000 0.000
#> GSM425860 2 0.9708 -0.195 0.212 0.348 0.280 0.160
#> GSM425861 2 0.6943 0.421 0.264 0.576 0.000 0.160
#> GSM425862 4 0.3885 0.690 0.092 0.064 0.000 0.844
#> GSM425837 4 0.4431 0.675 0.304 0.000 0.000 0.696
#> GSM425838 4 0.3056 0.719 0.040 0.072 0.000 0.888
#> GSM425839 2 0.0000 0.850 0.000 1.000 0.000 0.000
#> GSM425840 4 0.5397 0.703 0.212 0.000 0.068 0.720
#> GSM425841 4 0.2469 0.704 0.000 0.108 0.000 0.892
#> GSM425842 4 0.6186 0.554 0.352 0.064 0.000 0.584
#> GSM425917 3 0.2011 0.858 0.000 0.000 0.920 0.080
#> GSM425922 4 0.3801 0.577 0.000 0.220 0.000 0.780
#> GSM425919 3 0.7439 0.492 0.096 0.116 0.648 0.140
#> GSM425920 4 0.3652 0.730 0.064 0.008 0.060 0.868
#> GSM425923 4 0.2149 0.738 0.088 0.000 0.000 0.912
#> GSM425916 4 0.5018 0.702 0.144 0.000 0.088 0.768
#> GSM425918 4 0.3372 0.742 0.096 0.036 0.000 0.868
#> GSM425921 4 0.0188 0.712 0.000 0.004 0.000 0.996
#> GSM425925 4 0.1854 0.728 0.048 0.012 0.000 0.940
#> GSM425926 4 0.2334 0.713 0.004 0.088 0.000 0.908
#> GSM425927 4 0.6530 0.640 0.248 0.068 0.028 0.656
#> GSM425924 3 0.3615 0.822 0.016 0.036 0.872 0.076
#> GSM425928 3 0.0000 0.920 0.000 0.000 1.000 0.000
#> GSM425929 3 0.0000 0.920 0.000 0.000 1.000 0.000
#> GSM425930 3 0.0188 0.917 0.004 0.000 0.996 0.000
#> GSM425931 3 0.0000 0.920 0.000 0.000 1.000 0.000
#> GSM425932 3 0.0000 0.920 0.000 0.000 1.000 0.000
#> GSM425933 3 0.0000 0.920 0.000 0.000 1.000 0.000
#> GSM425934 3 0.0000 0.920 0.000 0.000 1.000 0.000
#> GSM425935 3 0.0000 0.920 0.000 0.000 1.000 0.000
#> GSM425936 3 0.0000 0.920 0.000 0.000 1.000 0.000
#> GSM425937 3 0.0000 0.920 0.000 0.000 1.000 0.000
#> GSM425938 3 0.0000 0.920 0.000 0.000 1.000 0.000
#> GSM425939 3 0.0000 0.920 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
#> GSM425907 2 0.0609 0.810 0.000 0.980 0.000 0.020 0.000
#> GSM425908 2 0.1704 0.812 0.004 0.928 0.000 0.068 0.000
#> GSM425909 5 0.0162 0.692 0.000 0.000 0.004 0.000 0.996
#> GSM425910 5 0.7892 0.166 0.100 0.308 0.000 0.184 0.408
#> GSM425911 2 0.4025 0.748 0.024 0.780 0.000 0.184 0.012
#> GSM425912 2 0.6232 0.641 0.052 0.644 0.000 0.184 0.120
#> GSM425913 2 0.0771 0.812 0.000 0.976 0.000 0.004 0.020
#> GSM425914 2 0.7415 0.401 0.076 0.504 0.000 0.184 0.236
#> GSM425915 5 0.4653 0.653 0.012 0.120 0.092 0.004 0.772
#> GSM425874 4 0.3424 0.707 0.240 0.000 0.000 0.760 0.000
#> GSM425875 5 0.2751 0.679 0.056 0.004 0.000 0.052 0.888
#> GSM425876 5 0.8374 0.379 0.132 0.216 0.020 0.184 0.448
#> GSM425877 1 0.4827 0.614 0.724 0.000 0.000 0.160 0.116
#> GSM425878 1 0.7700 0.384 0.496 0.188 0.000 0.188 0.128
#> GSM425879 2 0.2824 0.804 0.000 0.880 0.024 0.088 0.008
#> GSM425880 5 0.0794 0.694 0.028 0.000 0.000 0.000 0.972
#> GSM425881 2 0.6604 0.614 0.076 0.616 0.000 0.188 0.120
#> GSM425882 2 0.3073 0.785 0.024 0.856 0.000 0.116 0.004
#> GSM425883 5 0.5394 0.298 0.384 0.004 0.000 0.052 0.560
#> GSM425884 1 0.3884 0.604 0.708 0.004 0.000 0.000 0.288
#> GSM425885 2 0.4418 0.343 0.000 0.652 0.000 0.332 0.016
#> GSM425848 1 0.3921 0.630 0.800 0.000 0.000 0.128 0.072
#> GSM425849 1 0.3732 0.667 0.820 0.004 0.000 0.120 0.056
#> GSM425850 2 0.7084 0.179 0.368 0.428 0.004 0.180 0.020
#> GSM425851 1 0.7410 0.298 0.520 0.192 0.200 0.088 0.000
#> GSM425852 5 0.5354 0.530 0.140 0.000 0.192 0.000 0.668
#> GSM425893 5 0.6221 0.419 0.024 0.304 0.000 0.100 0.572
#> GSM425894 2 0.1310 0.811 0.000 0.956 0.000 0.020 0.024
#> GSM425895 2 0.3997 0.782 0.024 0.808 0.000 0.136 0.032
#> GSM425896 2 0.2732 0.799 0.008 0.884 0.000 0.088 0.020
#> GSM425897 2 0.2914 0.794 0.016 0.872 0.000 0.100 0.012
#> GSM425898 2 0.3166 0.777 0.000 0.860 0.016 0.020 0.104
#> GSM425899 2 0.4371 0.629 0.012 0.708 0.000 0.012 0.268
#> GSM425900 2 0.4034 0.745 0.004 0.804 0.036 0.012 0.144
#> GSM425901 5 0.0740 0.689 0.004 0.008 0.000 0.008 0.980
#> GSM425902 4 0.4592 0.626 0.012 0.036 0.000 0.728 0.224
#> GSM425903 5 0.0807 0.696 0.012 0.000 0.000 0.012 0.976
#> GSM425904 5 0.0510 0.694 0.016 0.000 0.000 0.000 0.984
#> GSM425905 2 0.0000 0.813 0.000 1.000 0.000 0.000 0.000
#> GSM425906 2 0.0404 0.815 0.000 0.988 0.000 0.012 0.000
#> GSM425863 1 0.3913 0.699 0.824 0.036 0.000 0.032 0.108
#> GSM425864 2 0.0162 0.813 0.000 0.996 0.000 0.004 0.000
#> GSM425865 2 0.0404 0.811 0.000 0.988 0.000 0.012 0.000
#> GSM425866 5 0.1043 0.691 0.040 0.000 0.000 0.000 0.960
#> GSM425867 5 0.4464 0.313 0.008 0.000 0.408 0.000 0.584
#> GSM425868 2 0.0865 0.810 0.004 0.972 0.000 0.024 0.000
#> GSM425869 2 0.2929 0.721 0.000 0.820 0.000 0.180 0.000
#> GSM425870 5 0.8982 0.391 0.036 0.176 0.236 0.184 0.368
#> GSM425871 1 0.6477 0.152 0.464 0.420 0.000 0.080 0.036
#> GSM425872 2 0.3141 0.763 0.000 0.832 0.000 0.016 0.152
#> GSM425873 1 0.5740 0.546 0.656 0.012 0.000 0.184 0.148
#> GSM425843 1 0.1992 0.698 0.924 0.000 0.000 0.032 0.044
#> GSM425844 1 0.3642 0.611 0.760 0.008 0.000 0.232 0.000
#> GSM425845 5 0.4915 0.564 0.048 0.240 0.000 0.012 0.700
#> GSM425846 2 0.3209 0.798 0.008 0.864 0.000 0.068 0.060
#> GSM425847 2 0.5287 0.715 0.032 0.716 0.000 0.176 0.076
#> GSM425886 5 0.4414 0.597 0.000 0.072 0.160 0.004 0.764
#> GSM425887 2 0.6594 0.588 0.040 0.592 0.000 0.196 0.172
#> GSM425888 2 0.3186 0.800 0.008 0.864 0.000 0.080 0.048
#> GSM425889 4 0.5267 0.228 0.048 0.000 0.000 0.524 0.428
#> GSM425890 4 0.5197 0.628 0.116 0.204 0.000 0.680 0.000
#> GSM425891 2 0.0912 0.816 0.000 0.972 0.000 0.016 0.012
#> GSM425892 2 0.0703 0.809 0.000 0.976 0.000 0.024 0.000
#> GSM425853 5 0.3838 0.468 0.280 0.004 0.000 0.000 0.716
#> GSM425854 2 0.1732 0.813 0.000 0.920 0.000 0.080 0.000
#> GSM425855 1 0.4012 0.686 0.820 0.000 0.032 0.044 0.104
#> GSM425856 5 0.2228 0.696 0.040 0.048 0.000 0.000 0.912
#> GSM425857 5 0.3328 0.573 0.000 0.176 0.004 0.008 0.812
#> GSM425858 2 0.3470 0.792 0.016 0.852 0.000 0.080 0.052
#> GSM425859 2 0.0794 0.809 0.000 0.972 0.000 0.028 0.000
#> GSM425860 2 0.9535 0.120 0.184 0.364 0.152 0.156 0.144
#> GSM425861 2 0.7375 0.491 0.104 0.536 0.000 0.184 0.176
#> GSM425862 4 0.5077 0.735 0.108 0.096 0.000 0.752 0.044
#> GSM425837 1 0.3093 0.691 0.824 0.000 0.000 0.008 0.168
#> GSM425838 4 0.3130 0.681 0.048 0.096 0.000 0.856 0.000
#> GSM425839 2 0.0510 0.810 0.000 0.984 0.000 0.016 0.000
#> GSM425840 1 0.3305 0.707 0.860 0.000 0.020 0.032 0.088
#> GSM425841 4 0.4441 0.719 0.236 0.044 0.000 0.720 0.000
#> GSM425842 1 0.7039 0.406 0.552 0.060 0.000 0.188 0.200
#> GSM425917 3 0.3043 0.827 0.080 0.000 0.864 0.056 0.000
#> GSM425922 4 0.3944 0.703 0.052 0.160 0.000 0.788 0.000
#> GSM425919 3 0.7207 0.354 0.240 0.100 0.540 0.000 0.120
#> GSM425920 1 0.2068 0.653 0.904 0.000 0.004 0.092 0.000
#> GSM425923 1 0.3757 0.522 0.772 0.000 0.000 0.208 0.020
#> GSM425916 1 0.3033 0.650 0.876 0.000 0.016 0.076 0.032
#> GSM425918 1 0.2722 0.638 0.872 0.020 0.000 0.108 0.000
#> GSM425921 4 0.3336 0.702 0.228 0.000 0.000 0.772 0.000
#> GSM425925 4 0.4510 0.399 0.432 0.000 0.000 0.560 0.008
#> GSM425926 4 0.4169 0.715 0.240 0.028 0.000 0.732 0.000
#> GSM425927 1 0.2339 0.703 0.892 0.004 0.000 0.004 0.100
#> GSM425924 3 0.5275 0.711 0.156 0.044 0.740 0.048 0.012
#> GSM425928 3 0.0000 0.939 0.000 0.000 1.000 0.000 0.000
#> GSM425929 3 0.0000 0.939 0.000 0.000 1.000 0.000 0.000
#> GSM425930 3 0.0162 0.936 0.000 0.000 0.996 0.000 0.004
#> GSM425931 3 0.0000 0.939 0.000 0.000 1.000 0.000 0.000
#> GSM425932 3 0.0000 0.939 0.000 0.000 1.000 0.000 0.000
#> GSM425933 3 0.0000 0.939 0.000 0.000 1.000 0.000 0.000
#> GSM425934 3 0.0000 0.939 0.000 0.000 1.000 0.000 0.000
#> GSM425935 3 0.0000 0.939 0.000 0.000 1.000 0.000 0.000
#> GSM425936 3 0.0000 0.939 0.000 0.000 1.000 0.000 0.000
#> GSM425937 3 0.0000 0.939 0.000 0.000 1.000 0.000 0.000
#> GSM425938 3 0.0000 0.939 0.000 0.000 1.000 0.000 0.000
#> GSM425939 3 0.0000 0.939 0.000 0.000 1.000 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 2 0.1387 0.77871 0.000 0.932 0.000 0.000 0.000 0.068
#> GSM425908 2 0.3023 0.64577 0.000 0.768 0.000 0.000 0.000 0.232
#> GSM425909 5 0.0458 0.72979 0.000 0.000 0.000 0.000 0.984 0.016
#> GSM425910 6 0.3448 0.62600 0.004 0.108 0.000 0.000 0.072 0.816
#> GSM425911 6 0.3817 0.31533 0.000 0.432 0.000 0.000 0.000 0.568
#> GSM425912 6 0.4277 0.50884 0.000 0.356 0.000 0.000 0.028 0.616
#> GSM425913 2 0.1092 0.79227 0.000 0.960 0.000 0.000 0.020 0.020
#> GSM425914 6 0.3551 0.66178 0.000 0.192 0.000 0.000 0.036 0.772
#> GSM425915 5 0.4780 0.67340 0.000 0.072 0.088 0.000 0.740 0.100
#> GSM425874 4 0.2053 0.77166 0.108 0.004 0.000 0.888 0.000 0.000
#> GSM425875 5 0.3794 0.68282 0.028 0.000 0.000 0.000 0.724 0.248
#> GSM425876 6 0.3469 0.61796 0.012 0.092 0.000 0.000 0.072 0.824
#> GSM425877 1 0.3650 0.73041 0.812 0.000 0.000 0.056 0.020 0.112
#> GSM425878 6 0.4613 0.41872 0.264 0.032 0.000 0.000 0.028 0.676
#> GSM425879 2 0.3533 0.68616 0.000 0.776 0.020 0.000 0.008 0.196
#> GSM425880 5 0.2613 0.74246 0.012 0.000 0.000 0.000 0.848 0.140
#> GSM425881 6 0.3351 0.59433 0.000 0.288 0.000 0.000 0.000 0.712
#> GSM425882 2 0.3851 0.05201 0.000 0.540 0.000 0.000 0.000 0.460
#> GSM425883 5 0.5815 0.38668 0.200 0.000 0.000 0.000 0.472 0.328
#> GSM425884 1 0.4781 0.63011 0.672 0.000 0.000 0.000 0.140 0.188
#> GSM425885 2 0.5421 0.42143 0.008 0.632 0.000 0.264 0.044 0.052
#> GSM425848 1 0.4128 0.68987 0.768 0.000 0.000 0.096 0.124 0.012
#> GSM425849 1 0.4166 0.70699 0.760 0.000 0.000 0.124 0.008 0.108
#> GSM425850 6 0.5330 0.54462 0.208 0.176 0.000 0.000 0.004 0.612
#> GSM425851 1 0.7732 0.32667 0.476 0.156 0.188 0.112 0.000 0.068
#> GSM425852 5 0.4645 0.66414 0.068 0.000 0.152 0.000 0.736 0.044
#> GSM425893 5 0.5855 -0.04011 0.000 0.192 0.000 0.000 0.408 0.400
#> GSM425894 2 0.1418 0.78586 0.000 0.944 0.000 0.000 0.032 0.024
#> GSM425895 2 0.3969 0.49332 0.000 0.668 0.000 0.000 0.020 0.312
#> GSM425896 2 0.3917 0.53361 0.000 0.692 0.000 0.000 0.024 0.284
#> GSM425897 2 0.4109 0.19628 0.000 0.576 0.000 0.000 0.012 0.412
#> GSM425898 2 0.2696 0.74049 0.000 0.856 0.000 0.000 0.116 0.028
#> GSM425899 2 0.4234 0.59054 0.004 0.744 0.000 0.000 0.152 0.100
#> GSM425900 2 0.3443 0.72959 0.000 0.832 0.032 0.000 0.096 0.040
#> GSM425901 5 0.0748 0.72637 0.004 0.004 0.000 0.000 0.976 0.016
#> GSM425902 4 0.2405 0.75450 0.004 0.016 0.000 0.880 0.100 0.000
#> GSM425903 5 0.2631 0.71894 0.000 0.000 0.000 0.000 0.820 0.180
#> GSM425904 5 0.1866 0.73798 0.008 0.000 0.000 0.000 0.908 0.084
#> GSM425905 2 0.0713 0.78917 0.000 0.972 0.000 0.000 0.000 0.028
#> GSM425906 2 0.1124 0.78689 0.000 0.956 0.000 0.000 0.008 0.036
#> GSM425863 1 0.4126 0.74186 0.788 0.008 0.000 0.072 0.020 0.112
#> GSM425864 2 0.1141 0.78572 0.000 0.948 0.000 0.000 0.000 0.052
#> GSM425865 2 0.1765 0.77169 0.000 0.904 0.000 0.000 0.000 0.096
#> GSM425866 5 0.2859 0.73846 0.016 0.000 0.000 0.000 0.828 0.156
#> GSM425867 5 0.5335 0.31725 0.004 0.000 0.412 0.000 0.492 0.092
#> GSM425868 2 0.1387 0.77902 0.000 0.932 0.000 0.000 0.000 0.068
#> GSM425869 2 0.3215 0.62896 0.000 0.756 0.000 0.240 0.000 0.004
#> GSM425870 6 0.6446 0.51199 0.000 0.148 0.120 0.000 0.164 0.568
#> GSM425871 6 0.6011 0.17281 0.296 0.272 0.000 0.000 0.000 0.432
#> GSM425872 2 0.2932 0.70494 0.000 0.820 0.000 0.000 0.164 0.016
#> GSM425873 6 0.3602 0.42041 0.208 0.000 0.000 0.000 0.032 0.760
#> GSM425843 1 0.1204 0.75858 0.944 0.000 0.000 0.000 0.000 0.056
#> GSM425844 1 0.5363 0.32773 0.492 0.000 0.000 0.112 0.000 0.396
#> GSM425845 5 0.5446 0.43298 0.000 0.144 0.000 0.000 0.540 0.316
#> GSM425846 2 0.1958 0.76236 0.000 0.896 0.000 0.000 0.004 0.100
#> GSM425847 2 0.3847 0.37118 0.000 0.644 0.000 0.000 0.008 0.348
#> GSM425886 5 0.3106 0.69713 0.000 0.036 0.056 0.000 0.860 0.048
#> GSM425887 6 0.4098 0.10448 0.000 0.496 0.000 0.000 0.008 0.496
#> GSM425888 2 0.2020 0.76427 0.000 0.896 0.000 0.000 0.008 0.096
#> GSM425889 4 0.5276 -0.00452 0.044 0.004 0.004 0.472 0.464 0.012
#> GSM425890 4 0.5020 0.60864 0.120 0.128 0.000 0.708 0.000 0.044
#> GSM425891 2 0.1297 0.79276 0.000 0.948 0.000 0.000 0.012 0.040
#> GSM425892 2 0.1141 0.78350 0.000 0.948 0.000 0.000 0.000 0.052
#> GSM425853 5 0.5749 0.48079 0.196 0.004 0.000 0.000 0.532 0.268
#> GSM425854 2 0.1462 0.78177 0.000 0.936 0.000 0.000 0.008 0.056
#> GSM425855 1 0.3771 0.74556 0.792 0.000 0.024 0.004 0.024 0.156
#> GSM425856 5 0.3846 0.72912 0.016 0.048 0.000 0.000 0.784 0.152
#> GSM425857 5 0.1716 0.70187 0.004 0.036 0.000 0.000 0.932 0.028
#> GSM425858 2 0.2431 0.74094 0.000 0.860 0.000 0.000 0.008 0.132
#> GSM425859 2 0.1327 0.78427 0.000 0.936 0.000 0.000 0.000 0.064
#> GSM425860 6 0.6266 0.59326 0.044 0.148 0.124 0.000 0.052 0.632
#> GSM425861 6 0.4747 0.36760 0.024 0.412 0.000 0.000 0.016 0.548
#> GSM425862 4 0.3972 0.74725 0.084 0.100 0.000 0.796 0.012 0.008
#> GSM425837 1 0.2795 0.75101 0.856 0.000 0.000 0.000 0.044 0.100
#> GSM425838 4 0.4855 0.68110 0.064 0.104 0.000 0.732 0.000 0.100
#> GSM425839 2 0.0622 0.78909 0.000 0.980 0.000 0.000 0.008 0.012
#> GSM425840 1 0.3018 0.74891 0.816 0.000 0.012 0.000 0.004 0.168
#> GSM425841 4 0.2214 0.77515 0.096 0.016 0.000 0.888 0.000 0.000
#> GSM425842 6 0.3675 0.54196 0.128 0.016 0.000 0.000 0.052 0.804
#> GSM425917 3 0.2956 0.80476 0.064 0.000 0.848 0.088 0.000 0.000
#> GSM425922 4 0.0000 0.76948 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425919 3 0.7719 0.25905 0.232 0.088 0.468 0.000 0.096 0.116
#> GSM425920 1 0.3835 0.71376 0.776 0.000 0.000 0.112 0.000 0.112
#> GSM425923 1 0.3398 0.65824 0.768 0.000 0.000 0.216 0.012 0.004
#> GSM425916 1 0.3521 0.69230 0.812 0.000 0.008 0.120 0.000 0.060
#> GSM425918 1 0.3268 0.69752 0.808 0.020 0.000 0.164 0.000 0.008
#> GSM425921 4 0.0692 0.76273 0.020 0.000 0.000 0.976 0.000 0.004
#> GSM425925 4 0.3565 0.52268 0.304 0.000 0.000 0.692 0.000 0.004
#> GSM425926 4 0.2146 0.76820 0.116 0.004 0.000 0.880 0.000 0.000
#> GSM425927 1 0.3457 0.72438 0.752 0.000 0.000 0.000 0.016 0.232
#> GSM425924 3 0.6308 0.58681 0.096 0.032 0.652 0.076 0.012 0.132
#> GSM425928 3 0.0000 0.92929 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425929 3 0.0000 0.92929 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425930 3 0.0146 0.92609 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM425931 3 0.0000 0.92929 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425932 3 0.0000 0.92929 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425933 3 0.0000 0.92929 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425934 3 0.0000 0.92929 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425935 3 0.0000 0.92929 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425936 3 0.0000 0.92929 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425937 3 0.0000 0.92929 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425938 3 0.0000 0.92929 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425939 3 0.0000 0.92929 0.000 0.000 1.000 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 disease.state(p) tissue(p) other(p) k
#> MAD:pam 94 4.12e-06 1.42e-06 1.45e-03 2
#> MAD:pam 86 4.23e-10 1.42e-11 5.49e-10 3
#> MAD:pam 89 5.11e-16 1.04e-18 4.36e-13 4
#> MAD:pam 84 2.27e-14 9.12e-16 2.33e-09 5
#> MAD:pam 83 1.55e-13 3.27e-15 1.10e-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["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 103 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 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 0.289 0.580 0.810 0.4784 0.535 0.535
#> 3 3 0.991 0.932 0.966 0.2768 0.736 0.555
#> 4 4 0.585 0.787 0.886 0.0298 0.702 0.442
#> 5 5 0.868 0.840 0.931 0.2295 0.799 0.504
#> 6 6 0.776 0.741 0.850 0.0389 0.982 0.921
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
#> GSM425907 2 0.1184 0.8550 0.016 0.984
#> GSM425908 2 0.1184 0.8550 0.016 0.984
#> GSM425909 1 0.9635 0.3751 0.612 0.388
#> GSM425910 1 0.9954 0.1850 0.540 0.460
#> GSM425911 2 0.3431 0.8165 0.064 0.936
#> GSM425912 2 0.9209 0.4215 0.336 0.664
#> GSM425913 2 0.1184 0.8550 0.016 0.984
#> GSM425914 2 0.6623 0.7005 0.172 0.828
#> GSM425915 2 0.7219 0.6174 0.200 0.800
#> GSM425874 1 0.0000 0.6982 1.000 0.000
#> GSM425875 1 0.6712 0.6452 0.824 0.176
#> GSM425876 1 0.9775 0.2912 0.588 0.412
#> GSM425877 1 0.0376 0.6984 0.996 0.004
#> GSM425878 1 0.6801 0.6425 0.820 0.180
#> GSM425879 2 0.1184 0.8550 0.016 0.984
#> GSM425880 1 0.4815 0.6769 0.896 0.104
#> GSM425881 2 0.9044 0.4519 0.320 0.680
#> GSM425882 2 0.1184 0.8550 0.016 0.984
#> GSM425883 1 0.6712 0.6518 0.824 0.176
#> GSM425884 1 0.6712 0.6452 0.824 0.176
#> GSM425885 1 0.8909 0.4655 0.692 0.308
#> GSM425848 1 0.0376 0.6985 0.996 0.004
#> GSM425849 1 0.6623 0.6477 0.828 0.172
#> GSM425850 1 0.8608 0.5183 0.716 0.284
#> GSM425851 1 0.0000 0.6982 1.000 0.000
#> GSM425852 1 0.0672 0.6963 0.992 0.008
#> GSM425893 2 0.3431 0.8164 0.064 0.936
#> GSM425894 2 0.1184 0.8550 0.016 0.984
#> GSM425895 2 0.1184 0.8550 0.016 0.984
#> GSM425896 2 0.1184 0.8550 0.016 0.984
#> GSM425897 2 0.1184 0.8550 0.016 0.984
#> GSM425898 2 0.1184 0.8550 0.016 0.984
#> GSM425899 2 0.9993 -0.0379 0.484 0.516
#> GSM425900 2 0.1184 0.8550 0.016 0.984
#> GSM425901 1 0.9522 0.3809 0.628 0.372
#> GSM425902 1 0.0000 0.6982 1.000 0.000
#> GSM425903 2 0.9393 0.3287 0.356 0.644
#> GSM425904 1 0.0672 0.6983 0.992 0.008
#> GSM425905 2 0.1184 0.8550 0.016 0.984
#> GSM425906 2 0.1184 0.8550 0.016 0.984
#> GSM425863 1 0.6801 0.6425 0.820 0.180
#> GSM425864 2 0.1184 0.8550 0.016 0.984
#> GSM425865 2 0.1184 0.8550 0.016 0.984
#> GSM425866 1 0.6801 0.6425 0.820 0.180
#> GSM425867 1 0.9635 0.4128 0.612 0.388
#> GSM425868 2 0.1414 0.8522 0.020 0.980
#> GSM425869 2 0.1184 0.8550 0.016 0.984
#> GSM425870 2 0.6343 0.6850 0.160 0.840
#> GSM425871 1 0.6801 0.6425 0.820 0.180
#> GSM425872 2 0.1184 0.8550 0.016 0.984
#> GSM425873 1 0.9323 0.3932 0.652 0.348
#> GSM425843 1 0.6801 0.6425 0.820 0.180
#> GSM425844 1 0.0000 0.6982 1.000 0.000
#> GSM425845 1 0.9944 0.1950 0.544 0.456
#> GSM425846 2 0.8861 0.4647 0.304 0.696
#> GSM425847 1 0.9998 0.0848 0.508 0.492
#> GSM425886 2 0.9963 -0.0980 0.464 0.536
#> GSM425887 2 0.9170 0.4299 0.332 0.668
#> GSM425888 2 0.9000 0.4588 0.316 0.684
#> GSM425889 1 0.0000 0.6982 1.000 0.000
#> GSM425890 1 0.0000 0.6982 1.000 0.000
#> GSM425891 2 0.1184 0.8550 0.016 0.984
#> GSM425892 2 0.1184 0.8550 0.016 0.984
#> GSM425853 1 0.6801 0.6425 0.820 0.180
#> GSM425854 2 0.1184 0.8550 0.016 0.984
#> GSM425855 1 0.6623 0.6477 0.828 0.172
#> GSM425856 1 0.6801 0.6425 0.820 0.180
#> GSM425857 1 0.9522 0.3761 0.628 0.372
#> GSM425858 2 0.4939 0.7698 0.108 0.892
#> GSM425859 2 0.1184 0.8550 0.016 0.984
#> GSM425860 1 0.9993 0.1147 0.516 0.484
#> GSM425861 1 0.9983 0.1288 0.524 0.476
#> GSM425862 1 0.0000 0.6982 1.000 0.000
#> GSM425837 1 0.2778 0.6927 0.952 0.048
#> GSM425838 1 0.0000 0.6982 1.000 0.000
#> GSM425839 2 0.1184 0.8550 0.016 0.984
#> GSM425840 1 0.6438 0.6520 0.836 0.164
#> GSM425841 1 0.0000 0.6982 1.000 0.000
#> GSM425842 1 0.7602 0.5994 0.780 0.220
#> GSM425917 1 0.9909 0.2527 0.556 0.444
#> GSM425922 1 0.0000 0.6982 1.000 0.000
#> GSM425919 1 0.1633 0.6967 0.976 0.024
#> GSM425920 1 0.2043 0.6956 0.968 0.032
#> GSM425923 1 0.0000 0.6982 1.000 0.000
#> GSM425916 1 0.0000 0.6982 1.000 0.000
#> GSM425918 1 0.0000 0.6982 1.000 0.000
#> GSM425921 1 0.0000 0.6982 1.000 0.000
#> GSM425925 1 0.0376 0.6985 0.996 0.004
#> GSM425926 1 0.0000 0.6982 1.000 0.000
#> GSM425927 1 0.6801 0.6425 0.820 0.180
#> GSM425924 1 0.8267 0.5246 0.740 0.260
#> GSM425928 1 0.9993 0.1832 0.516 0.484
#> GSM425929 1 0.9998 0.1826 0.508 0.492
#> GSM425930 1 0.9998 0.1826 0.508 0.492
#> GSM425931 1 0.9998 0.1826 0.508 0.492
#> GSM425932 1 0.9998 0.1826 0.508 0.492
#> GSM425933 1 0.9998 0.1826 0.508 0.492
#> GSM425934 1 0.9998 0.1826 0.508 0.492
#> GSM425935 1 0.9988 0.1830 0.520 0.480
#> GSM425936 1 0.9998 0.1826 0.508 0.492
#> GSM425937 1 0.9998 0.1826 0.508 0.492
#> GSM425938 1 0.9993 0.1832 0.516 0.484
#> GSM425939 1 0.9998 0.1826 0.508 0.492
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.0000 0.961 0.000 1.000 0.000
#> GSM425908 2 0.0000 0.961 0.000 1.000 0.000
#> GSM425909 1 0.6843 0.704 0.740 0.116 0.144
#> GSM425910 2 0.1643 0.936 0.044 0.956 0.000
#> GSM425911 2 0.0237 0.961 0.004 0.996 0.000
#> GSM425912 2 0.0892 0.955 0.020 0.980 0.000
#> GSM425913 2 0.0000 0.961 0.000 1.000 0.000
#> GSM425914 2 0.0424 0.960 0.008 0.992 0.000
#> GSM425915 2 0.2866 0.892 0.008 0.916 0.076
#> GSM425874 1 0.1015 0.965 0.980 0.008 0.012
#> GSM425875 1 0.0424 0.971 0.992 0.008 0.000
#> GSM425876 2 0.2165 0.913 0.064 0.936 0.000
#> GSM425877 1 0.0424 0.971 0.992 0.008 0.000
#> GSM425878 1 0.0424 0.971 0.992 0.008 0.000
#> GSM425879 2 0.0000 0.961 0.000 1.000 0.000
#> GSM425880 1 0.0424 0.971 0.992 0.008 0.000
#> GSM425881 2 0.0892 0.955 0.020 0.980 0.000
#> GSM425882 2 0.0000 0.961 0.000 1.000 0.000
#> GSM425883 1 0.0892 0.969 0.980 0.020 0.000
#> GSM425884 1 0.0424 0.971 0.992 0.008 0.000
#> GSM425885 1 0.2569 0.942 0.936 0.032 0.032
#> GSM425848 1 0.0747 0.971 0.984 0.016 0.000
#> GSM425849 1 0.0747 0.971 0.984 0.016 0.000
#> GSM425850 2 0.6079 0.385 0.388 0.612 0.000
#> GSM425851 1 0.0747 0.971 0.984 0.016 0.000
#> GSM425852 1 0.1491 0.964 0.968 0.016 0.016
#> GSM425893 2 0.0237 0.961 0.004 0.996 0.000
#> GSM425894 2 0.0000 0.961 0.000 1.000 0.000
#> GSM425895 2 0.0000 0.961 0.000 1.000 0.000
#> GSM425896 2 0.0000 0.961 0.000 1.000 0.000
#> GSM425897 2 0.0000 0.961 0.000 1.000 0.000
#> GSM425898 2 0.0000 0.961 0.000 1.000 0.000
#> GSM425899 2 0.1031 0.953 0.024 0.976 0.000
#> GSM425900 2 0.0237 0.961 0.004 0.996 0.000
#> GSM425901 1 0.3967 0.893 0.884 0.044 0.072
#> GSM425902 1 0.1182 0.967 0.976 0.012 0.012
#> GSM425903 2 0.1289 0.947 0.032 0.968 0.000
#> GSM425904 1 0.0592 0.971 0.988 0.012 0.000
#> GSM425905 2 0.0000 0.961 0.000 1.000 0.000
#> GSM425906 2 0.0237 0.961 0.004 0.996 0.000
#> GSM425863 1 0.0424 0.971 0.992 0.008 0.000
#> GSM425864 2 0.0000 0.961 0.000 1.000 0.000
#> GSM425865 2 0.0000 0.961 0.000 1.000 0.000
#> GSM425866 1 0.0592 0.970 0.988 0.012 0.000
#> GSM425867 3 0.3502 0.875 0.084 0.020 0.896
#> GSM425868 2 0.0000 0.961 0.000 1.000 0.000
#> GSM425869 2 0.0000 0.961 0.000 1.000 0.000
#> GSM425870 2 0.0424 0.960 0.008 0.992 0.000
#> GSM425871 1 0.0747 0.971 0.984 0.016 0.000
#> GSM425872 2 0.0000 0.961 0.000 1.000 0.000
#> GSM425873 2 0.6252 0.220 0.444 0.556 0.000
#> GSM425843 1 0.0424 0.971 0.992 0.008 0.000
#> GSM425844 1 0.0592 0.971 0.988 0.012 0.000
#> GSM425845 2 0.1529 0.940 0.040 0.960 0.000
#> GSM425846 2 0.0892 0.955 0.020 0.980 0.000
#> GSM425847 2 0.0892 0.955 0.020 0.980 0.000
#> GSM425886 3 0.6448 0.457 0.012 0.352 0.636
#> GSM425887 2 0.0892 0.955 0.020 0.980 0.000
#> GSM425888 2 0.0892 0.955 0.020 0.980 0.000
#> GSM425889 1 0.0747 0.971 0.984 0.016 0.000
#> GSM425890 1 0.1337 0.968 0.972 0.016 0.012
#> GSM425891 2 0.0000 0.961 0.000 1.000 0.000
#> GSM425892 2 0.0000 0.961 0.000 1.000 0.000
#> GSM425853 1 0.0424 0.971 0.992 0.008 0.000
#> GSM425854 2 0.0000 0.961 0.000 1.000 0.000
#> GSM425855 1 0.0424 0.971 0.992 0.008 0.000
#> GSM425856 1 0.1031 0.966 0.976 0.024 0.000
#> GSM425857 1 0.2569 0.942 0.936 0.032 0.032
#> GSM425858 2 0.0892 0.955 0.020 0.980 0.000
#> GSM425859 2 0.0000 0.961 0.000 1.000 0.000
#> GSM425860 2 0.1031 0.953 0.024 0.976 0.000
#> GSM425861 2 0.1529 0.940 0.040 0.960 0.000
#> GSM425862 1 0.0747 0.971 0.984 0.016 0.000
#> GSM425837 1 0.0424 0.971 0.992 0.008 0.000
#> GSM425838 1 0.1015 0.965 0.980 0.008 0.012
#> GSM425839 2 0.0000 0.961 0.000 1.000 0.000
#> GSM425840 1 0.0424 0.971 0.992 0.008 0.000
#> GSM425841 1 0.1015 0.965 0.980 0.008 0.012
#> GSM425842 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425917 1 0.7021 0.219 0.544 0.020 0.436
#> GSM425922 1 0.1015 0.965 0.980 0.008 0.012
#> GSM425919 1 0.0424 0.971 0.992 0.008 0.000
#> GSM425920 1 0.0424 0.971 0.992 0.008 0.000
#> GSM425923 1 0.0747 0.971 0.984 0.016 0.000
#> GSM425916 1 0.0747 0.971 0.984 0.016 0.000
#> GSM425918 1 0.0592 0.971 0.988 0.012 0.000
#> GSM425921 1 0.1015 0.965 0.980 0.008 0.012
#> GSM425925 1 0.0747 0.971 0.984 0.016 0.000
#> GSM425926 1 0.1015 0.965 0.980 0.008 0.012
#> GSM425927 1 0.0592 0.970 0.988 0.012 0.000
#> GSM425924 1 0.2527 0.941 0.936 0.020 0.044
#> GSM425928 3 0.0983 0.952 0.004 0.016 0.980
#> GSM425929 3 0.0237 0.960 0.000 0.004 0.996
#> GSM425930 3 0.0237 0.960 0.000 0.004 0.996
#> GSM425931 3 0.0237 0.960 0.000 0.004 0.996
#> GSM425932 3 0.0237 0.960 0.000 0.004 0.996
#> GSM425933 3 0.0237 0.960 0.000 0.004 0.996
#> GSM425934 3 0.0237 0.960 0.000 0.004 0.996
#> GSM425935 3 0.1129 0.949 0.004 0.020 0.976
#> GSM425936 3 0.0237 0.960 0.000 0.004 0.996
#> GSM425937 3 0.0237 0.960 0.000 0.004 0.996
#> GSM425938 3 0.0983 0.952 0.004 0.016 0.980
#> GSM425939 3 0.0237 0.960 0.000 0.004 0.996
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.0000 0.900 0.000 1.000 0.000 0.000
#> GSM425908 2 0.0000 0.900 0.000 1.000 0.000 0.000
#> GSM425909 1 0.3160 0.816 0.872 0.108 0.020 0.000
#> GSM425910 1 0.4046 0.797 0.828 0.124 0.000 0.048
#> GSM425911 2 0.5163 -0.220 0.480 0.516 0.000 0.004
#> GSM425912 1 0.5320 0.458 0.572 0.416 0.000 0.012
#> GSM425913 2 0.0000 0.900 0.000 1.000 0.000 0.000
#> GSM425914 1 0.5125 0.523 0.604 0.388 0.000 0.008
#> GSM425915 1 0.6197 0.662 0.660 0.268 0.052 0.020
#> GSM425874 4 0.1389 0.974 0.048 0.000 0.000 0.952
#> GSM425875 1 0.0000 0.824 1.000 0.000 0.000 0.000
#> GSM425876 1 0.4046 0.797 0.828 0.124 0.000 0.048
#> GSM425877 1 0.1940 0.813 0.924 0.000 0.000 0.076
#> GSM425878 1 0.0000 0.824 1.000 0.000 0.000 0.000
#> GSM425879 2 0.0000 0.900 0.000 1.000 0.000 0.000
#> GSM425880 1 0.0000 0.824 1.000 0.000 0.000 0.000
#> GSM425881 1 0.5329 0.449 0.568 0.420 0.000 0.012
#> GSM425882 2 0.0000 0.900 0.000 1.000 0.000 0.000
#> GSM425883 1 0.3239 0.826 0.880 0.052 0.000 0.068
#> GSM425884 1 0.0000 0.824 1.000 0.000 0.000 0.000
#> GSM425885 1 0.6750 0.667 0.628 0.168 0.004 0.200
#> GSM425848 1 0.2654 0.802 0.888 0.004 0.000 0.108
#> GSM425849 1 0.1489 0.823 0.952 0.004 0.000 0.044
#> GSM425850 1 0.3354 0.814 0.872 0.084 0.000 0.044
#> GSM425851 1 0.2831 0.797 0.876 0.004 0.000 0.120
#> GSM425852 1 0.0592 0.828 0.984 0.016 0.000 0.000
#> GSM425893 2 0.3837 0.619 0.224 0.776 0.000 0.000
#> GSM425894 2 0.0000 0.900 0.000 1.000 0.000 0.000
#> GSM425895 2 0.0000 0.900 0.000 1.000 0.000 0.000
#> GSM425896 2 0.0188 0.895 0.004 0.996 0.000 0.000
#> GSM425897 2 0.0000 0.900 0.000 1.000 0.000 0.000
#> GSM425898 2 0.0000 0.900 0.000 1.000 0.000 0.000
#> GSM425899 1 0.5756 0.534 0.592 0.372 0.000 0.036
#> GSM425900 2 0.3942 0.598 0.236 0.764 0.000 0.000
#> GSM425901 1 0.3444 0.818 0.868 0.104 0.012 0.016
#> GSM425902 4 0.1389 0.974 0.048 0.000 0.000 0.952
#> GSM425903 1 0.4153 0.792 0.820 0.132 0.000 0.048
#> GSM425904 1 0.0000 0.824 1.000 0.000 0.000 0.000
#> GSM425905 2 0.0000 0.900 0.000 1.000 0.000 0.000
#> GSM425906 2 0.3569 0.673 0.196 0.804 0.000 0.000
#> GSM425863 1 0.1557 0.818 0.944 0.000 0.000 0.056
#> GSM425864 2 0.0000 0.900 0.000 1.000 0.000 0.000
#> GSM425865 2 0.0000 0.900 0.000 1.000 0.000 0.000
#> GSM425866 1 0.0000 0.824 1.000 0.000 0.000 0.000
#> GSM425867 1 0.4188 0.799 0.824 0.112 0.064 0.000
#> GSM425868 2 0.0000 0.900 0.000 1.000 0.000 0.000
#> GSM425869 2 0.0000 0.900 0.000 1.000 0.000 0.000
#> GSM425870 1 0.5598 0.587 0.628 0.344 0.020 0.008
#> GSM425871 1 0.1824 0.819 0.936 0.004 0.000 0.060
#> GSM425872 2 0.0000 0.900 0.000 1.000 0.000 0.000
#> GSM425873 1 0.3674 0.808 0.852 0.104 0.000 0.044
#> GSM425843 1 0.0188 0.824 0.996 0.000 0.000 0.004
#> GSM425844 1 0.2401 0.809 0.904 0.004 0.000 0.092
#> GSM425845 1 0.4046 0.797 0.828 0.124 0.000 0.048
#> GSM425846 1 0.5277 0.355 0.532 0.460 0.000 0.008
#> GSM425847 1 0.5623 0.646 0.660 0.292 0.000 0.048
#> GSM425886 1 0.6444 0.638 0.628 0.272 0.096 0.004
#> GSM425887 1 0.5329 0.448 0.568 0.420 0.000 0.012
#> GSM425888 1 0.5353 0.419 0.556 0.432 0.000 0.012
#> GSM425889 1 0.3494 0.766 0.824 0.004 0.000 0.172
#> GSM425890 4 0.3257 0.815 0.152 0.004 0.000 0.844
#> GSM425891 2 0.0000 0.900 0.000 1.000 0.000 0.000
#> GSM425892 2 0.0000 0.900 0.000 1.000 0.000 0.000
#> GSM425853 1 0.0000 0.824 1.000 0.000 0.000 0.000
#> GSM425854 2 0.0000 0.900 0.000 1.000 0.000 0.000
#> GSM425855 1 0.1637 0.818 0.940 0.000 0.000 0.060
#> GSM425856 1 0.0000 0.824 1.000 0.000 0.000 0.000
#> GSM425857 1 0.5442 0.787 0.756 0.116 0.008 0.120
#> GSM425858 2 0.4994 -0.213 0.480 0.520 0.000 0.000
#> GSM425859 2 0.0000 0.900 0.000 1.000 0.000 0.000
#> GSM425860 1 0.4307 0.784 0.808 0.144 0.000 0.048
#> GSM425861 1 0.5472 0.665 0.676 0.280 0.000 0.044
#> GSM425862 1 0.2999 0.791 0.864 0.004 0.000 0.132
#> GSM425837 1 0.1118 0.822 0.964 0.000 0.000 0.036
#> GSM425838 4 0.1389 0.974 0.048 0.000 0.000 0.952
#> GSM425839 2 0.0000 0.900 0.000 1.000 0.000 0.000
#> GSM425840 1 0.0469 0.824 0.988 0.000 0.000 0.012
#> GSM425841 4 0.1389 0.974 0.048 0.000 0.000 0.952
#> GSM425842 1 0.0469 0.823 0.988 0.000 0.000 0.012
#> GSM425917 1 0.6291 0.757 0.712 0.124 0.136 0.028
#> GSM425922 4 0.1389 0.974 0.048 0.000 0.000 0.952
#> GSM425919 1 0.0188 0.825 0.996 0.000 0.000 0.004
#> GSM425920 1 0.1792 0.816 0.932 0.000 0.000 0.068
#> GSM425923 1 0.2831 0.797 0.876 0.004 0.000 0.120
#> GSM425916 1 0.2831 0.797 0.876 0.004 0.000 0.120
#> GSM425918 1 0.2831 0.797 0.876 0.004 0.000 0.120
#> GSM425921 4 0.1389 0.974 0.048 0.000 0.000 0.952
#> GSM425925 1 0.2831 0.797 0.876 0.004 0.000 0.120
#> GSM425926 4 0.1389 0.974 0.048 0.000 0.000 0.952
#> GSM425927 1 0.0188 0.824 0.996 0.000 0.000 0.004
#> GSM425924 1 0.3601 0.821 0.864 0.100 0.024 0.012
#> GSM425928 3 0.0188 0.926 0.000 0.004 0.996 0.000
#> GSM425929 3 0.0000 0.928 0.000 0.000 1.000 0.000
#> GSM425930 3 0.1042 0.904 0.020 0.008 0.972 0.000
#> GSM425931 3 0.0000 0.928 0.000 0.000 1.000 0.000
#> GSM425932 3 0.0000 0.928 0.000 0.000 1.000 0.000
#> GSM425933 3 0.0000 0.928 0.000 0.000 1.000 0.000
#> GSM425934 3 0.1042 0.904 0.020 0.008 0.972 0.000
#> GSM425935 3 0.6681 0.290 0.292 0.120 0.588 0.000
#> GSM425936 3 0.0000 0.928 0.000 0.000 1.000 0.000
#> GSM425937 3 0.0000 0.928 0.000 0.000 1.000 0.000
#> GSM425938 3 0.0188 0.926 0.000 0.004 0.996 0.000
#> GSM425939 3 0.0000 0.928 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
#> GSM425907 2 0.0000 0.964 0.000 1.000 0.000 0.000 0.000
#> GSM425908 2 0.0000 0.964 0.000 1.000 0.000 0.000 0.000
#> GSM425909 5 0.7550 -0.162 0.056 0.196 0.352 0.000 0.396
#> GSM425910 1 0.0000 0.814 1.000 0.000 0.000 0.000 0.000
#> GSM425911 2 0.4171 0.368 0.396 0.604 0.000 0.000 0.000
#> GSM425912 1 0.0000 0.814 1.000 0.000 0.000 0.000 0.000
#> GSM425913 2 0.0000 0.964 0.000 1.000 0.000 0.000 0.000
#> GSM425914 1 0.0000 0.814 1.000 0.000 0.000 0.000 0.000
#> GSM425915 1 0.4452 -0.189 0.500 0.004 0.496 0.000 0.000
#> GSM425874 4 0.0000 0.967 0.000 0.000 0.000 1.000 0.000
#> GSM425875 5 0.0000 0.920 0.000 0.000 0.000 0.000 1.000
#> GSM425876 1 0.0000 0.814 1.000 0.000 0.000 0.000 0.000
#> GSM425877 5 0.0000 0.920 0.000 0.000 0.000 0.000 1.000
#> GSM425878 5 0.0000 0.920 0.000 0.000 0.000 0.000 1.000
#> GSM425879 2 0.0162 0.962 0.004 0.996 0.000 0.000 0.000
#> GSM425880 5 0.0290 0.918 0.008 0.000 0.000 0.000 0.992
#> GSM425881 1 0.3177 0.693 0.792 0.208 0.000 0.000 0.000
#> GSM425882 2 0.0000 0.964 0.000 1.000 0.000 0.000 0.000
#> GSM425883 5 0.1106 0.908 0.024 0.000 0.000 0.012 0.964
#> GSM425884 5 0.0000 0.920 0.000 0.000 0.000 0.000 1.000
#> GSM425885 4 0.1121 0.923 0.044 0.000 0.000 0.956 0.000
#> GSM425848 5 0.0510 0.915 0.000 0.000 0.000 0.016 0.984
#> GSM425849 5 0.0000 0.920 0.000 0.000 0.000 0.000 1.000
#> GSM425850 1 0.4088 0.406 0.632 0.000 0.000 0.000 0.368
#> GSM425851 5 0.2377 0.836 0.000 0.000 0.000 0.128 0.872
#> GSM425852 5 0.1043 0.897 0.040 0.000 0.000 0.000 0.960
#> GSM425893 2 0.3039 0.760 0.192 0.808 0.000 0.000 0.000
#> GSM425894 2 0.0000 0.964 0.000 1.000 0.000 0.000 0.000
#> GSM425895 2 0.0000 0.964 0.000 1.000 0.000 0.000 0.000
#> GSM425896 2 0.0162 0.962 0.004 0.996 0.000 0.000 0.000
#> GSM425897 2 0.0162 0.962 0.004 0.996 0.000 0.000 0.000
#> GSM425898 2 0.0000 0.964 0.000 1.000 0.000 0.000 0.000
#> GSM425899 2 0.1914 0.900 0.060 0.924 0.000 0.000 0.016
#> GSM425900 2 0.0000 0.964 0.000 1.000 0.000 0.000 0.000
#> GSM425901 3 0.7410 0.216 0.052 0.176 0.412 0.000 0.360
#> GSM425902 4 0.0000 0.967 0.000 0.000 0.000 1.000 0.000
#> GSM425903 1 0.0000 0.814 1.000 0.000 0.000 0.000 0.000
#> GSM425904 5 0.0290 0.918 0.008 0.000 0.000 0.000 0.992
#> GSM425905 2 0.0000 0.964 0.000 1.000 0.000 0.000 0.000
#> GSM425906 2 0.0404 0.957 0.012 0.988 0.000 0.000 0.000
#> GSM425863 5 0.0000 0.920 0.000 0.000 0.000 0.000 1.000
#> GSM425864 2 0.0000 0.964 0.000 1.000 0.000 0.000 0.000
#> GSM425865 2 0.0000 0.964 0.000 1.000 0.000 0.000 0.000
#> GSM425866 5 0.0404 0.916 0.012 0.000 0.000 0.000 0.988
#> GSM425867 3 0.4356 0.480 0.340 0.000 0.648 0.000 0.012
#> GSM425868 2 0.0000 0.964 0.000 1.000 0.000 0.000 0.000
#> GSM425869 2 0.0000 0.964 0.000 1.000 0.000 0.000 0.000
#> GSM425870 1 0.0324 0.811 0.992 0.004 0.004 0.000 0.000
#> GSM425871 5 0.0000 0.920 0.000 0.000 0.000 0.000 1.000
#> GSM425872 2 0.0000 0.964 0.000 1.000 0.000 0.000 0.000
#> GSM425873 1 0.2561 0.713 0.856 0.000 0.000 0.000 0.144
#> GSM425843 5 0.0000 0.920 0.000 0.000 0.000 0.000 1.000
#> GSM425844 5 0.0162 0.919 0.000 0.000 0.000 0.004 0.996
#> GSM425845 1 0.0000 0.814 1.000 0.000 0.000 0.000 0.000
#> GSM425846 2 0.1341 0.916 0.056 0.944 0.000 0.000 0.000
#> GSM425847 1 0.0000 0.814 1.000 0.000 0.000 0.000 0.000
#> GSM425886 3 0.5528 0.532 0.140 0.216 0.644 0.000 0.000
#> GSM425887 1 0.3774 0.598 0.704 0.296 0.000 0.000 0.000
#> GSM425888 1 0.4074 0.477 0.636 0.364 0.000 0.000 0.000
#> GSM425889 5 0.3424 0.702 0.000 0.000 0.000 0.240 0.760
#> GSM425890 4 0.0162 0.964 0.004 0.000 0.000 0.996 0.000
#> GSM425891 2 0.0290 0.959 0.008 0.992 0.000 0.000 0.000
#> GSM425892 2 0.0000 0.964 0.000 1.000 0.000 0.000 0.000
#> GSM425853 5 0.0000 0.920 0.000 0.000 0.000 0.000 1.000
#> GSM425854 2 0.0000 0.964 0.000 1.000 0.000 0.000 0.000
#> GSM425855 5 0.0000 0.920 0.000 0.000 0.000 0.000 1.000
#> GSM425856 5 0.0404 0.916 0.012 0.000 0.000 0.000 0.988
#> GSM425857 4 0.3821 0.738 0.052 0.000 0.000 0.800 0.148
#> GSM425858 2 0.2377 0.833 0.128 0.872 0.000 0.000 0.000
#> GSM425859 2 0.0000 0.964 0.000 1.000 0.000 0.000 0.000
#> GSM425860 1 0.0000 0.814 1.000 0.000 0.000 0.000 0.000
#> GSM425861 1 0.4714 0.671 0.724 0.192 0.000 0.000 0.084
#> GSM425862 5 0.3876 0.577 0.000 0.000 0.000 0.316 0.684
#> GSM425837 5 0.0000 0.920 0.000 0.000 0.000 0.000 1.000
#> GSM425838 4 0.0000 0.967 0.000 0.000 0.000 1.000 0.000
#> GSM425839 2 0.0000 0.964 0.000 1.000 0.000 0.000 0.000
#> GSM425840 5 0.0000 0.920 0.000 0.000 0.000 0.000 1.000
#> GSM425841 4 0.0000 0.967 0.000 0.000 0.000 1.000 0.000
#> GSM425842 5 0.3661 0.579 0.276 0.000 0.000 0.000 0.724
#> GSM425917 3 0.3749 0.788 0.056 0.000 0.844 0.056 0.044
#> GSM425922 4 0.0000 0.967 0.000 0.000 0.000 1.000 0.000
#> GSM425919 5 0.0162 0.919 0.000 0.000 0.000 0.004 0.996
#> GSM425920 5 0.0000 0.920 0.000 0.000 0.000 0.000 1.000
#> GSM425923 5 0.2690 0.808 0.000 0.000 0.000 0.156 0.844
#> GSM425916 5 0.1732 0.875 0.000 0.000 0.000 0.080 0.920
#> GSM425918 5 0.1608 0.881 0.000 0.000 0.000 0.072 0.928
#> GSM425921 4 0.0000 0.967 0.000 0.000 0.000 1.000 0.000
#> GSM425925 5 0.2648 0.812 0.000 0.000 0.000 0.152 0.848
#> GSM425926 4 0.0000 0.967 0.000 0.000 0.000 1.000 0.000
#> GSM425927 5 0.0794 0.907 0.028 0.000 0.000 0.000 0.972
#> GSM425924 5 0.3978 0.749 0.052 0.000 0.148 0.004 0.796
#> GSM425928 3 0.0000 0.896 0.000 0.000 1.000 0.000 0.000
#> GSM425929 3 0.0000 0.896 0.000 0.000 1.000 0.000 0.000
#> GSM425930 3 0.0000 0.896 0.000 0.000 1.000 0.000 0.000
#> GSM425931 3 0.0000 0.896 0.000 0.000 1.000 0.000 0.000
#> GSM425932 3 0.0000 0.896 0.000 0.000 1.000 0.000 0.000
#> GSM425933 3 0.0000 0.896 0.000 0.000 1.000 0.000 0.000
#> GSM425934 3 0.0000 0.896 0.000 0.000 1.000 0.000 0.000
#> GSM425935 3 0.0404 0.888 0.012 0.000 0.988 0.000 0.000
#> GSM425936 3 0.0000 0.896 0.000 0.000 1.000 0.000 0.000
#> GSM425937 3 0.0000 0.896 0.000 0.000 1.000 0.000 0.000
#> GSM425938 3 0.0000 0.896 0.000 0.000 1.000 0.000 0.000
#> GSM425939 3 0.0000 0.896 0.000 0.000 1.000 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 2 0.1444 0.847 0.000 0.928 0.000 0.000 0.072 0.000
#> GSM425908 2 0.1327 0.844 0.000 0.936 0.000 0.000 0.064 0.000
#> GSM425909 5 0.7115 0.682 0.200 0.092 0.196 0.000 0.496 0.016
#> GSM425910 6 0.0363 0.708 0.000 0.000 0.000 0.000 0.012 0.988
#> GSM425911 2 0.5822 0.375 0.000 0.492 0.000 0.000 0.232 0.276
#> GSM425912 6 0.2838 0.701 0.000 0.004 0.000 0.000 0.188 0.808
#> GSM425913 2 0.1765 0.854 0.000 0.904 0.000 0.000 0.096 0.000
#> GSM425914 6 0.2562 0.704 0.000 0.000 0.000 0.000 0.172 0.828
#> GSM425915 6 0.6351 -0.035 0.000 0.024 0.264 0.000 0.240 0.472
#> GSM425874 4 0.0000 0.941 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425875 1 0.1863 0.836 0.896 0.000 0.000 0.000 0.104 0.000
#> GSM425876 6 0.0458 0.707 0.000 0.000 0.000 0.000 0.016 0.984
#> GSM425877 1 0.0713 0.861 0.972 0.000 0.000 0.000 0.028 0.000
#> GSM425878 1 0.0713 0.861 0.972 0.000 0.000 0.000 0.028 0.000
#> GSM425879 2 0.2362 0.841 0.000 0.860 0.000 0.000 0.136 0.004
#> GSM425880 1 0.1957 0.836 0.888 0.000 0.000 0.000 0.112 0.000
#> GSM425881 6 0.5100 0.601 0.000 0.128 0.000 0.000 0.260 0.612
#> GSM425882 2 0.2883 0.805 0.000 0.788 0.000 0.000 0.212 0.000
#> GSM425883 1 0.1262 0.860 0.956 0.000 0.000 0.016 0.020 0.008
#> GSM425884 1 0.1814 0.839 0.900 0.000 0.000 0.000 0.100 0.000
#> GSM425885 4 0.0912 0.917 0.004 0.012 0.000 0.972 0.004 0.008
#> GSM425848 1 0.2747 0.809 0.860 0.000 0.000 0.044 0.096 0.000
#> GSM425849 1 0.0260 0.861 0.992 0.000 0.000 0.000 0.008 0.000
#> GSM425850 6 0.5077 0.121 0.404 0.000 0.000 0.000 0.080 0.516
#> GSM425851 1 0.3770 0.738 0.776 0.000 0.000 0.076 0.148 0.000
#> GSM425852 1 0.3012 0.804 0.796 0.000 0.000 0.000 0.196 0.008
#> GSM425893 2 0.5303 0.597 0.000 0.596 0.000 0.000 0.232 0.172
#> GSM425894 2 0.1141 0.848 0.000 0.948 0.000 0.000 0.052 0.000
#> GSM425895 2 0.0458 0.859 0.000 0.984 0.000 0.000 0.016 0.000
#> GSM425896 2 0.2001 0.854 0.000 0.900 0.004 0.000 0.092 0.004
#> GSM425897 2 0.2006 0.850 0.000 0.892 0.000 0.000 0.104 0.004
#> GSM425898 2 0.0363 0.859 0.000 0.988 0.000 0.000 0.012 0.000
#> GSM425899 2 0.3965 0.758 0.008 0.720 0.000 0.000 0.248 0.024
#> GSM425900 2 0.3541 0.767 0.000 0.728 0.000 0.000 0.260 0.012
#> GSM425901 5 0.6959 0.685 0.184 0.076 0.204 0.004 0.520 0.012
#> GSM425902 4 0.0000 0.941 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425903 6 0.0692 0.711 0.000 0.000 0.004 0.000 0.020 0.976
#> GSM425904 1 0.2838 0.812 0.808 0.000 0.000 0.000 0.188 0.004
#> GSM425905 2 0.1267 0.859 0.000 0.940 0.000 0.000 0.060 0.000
#> GSM425906 2 0.3432 0.793 0.000 0.764 0.000 0.000 0.216 0.020
#> GSM425863 1 0.0146 0.862 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM425864 2 0.1556 0.857 0.000 0.920 0.000 0.000 0.080 0.000
#> GSM425865 2 0.0260 0.857 0.000 0.992 0.000 0.000 0.008 0.000
#> GSM425866 1 0.2006 0.835 0.892 0.000 0.000 0.000 0.104 0.004
#> GSM425867 3 0.6386 -0.063 0.060 0.000 0.416 0.000 0.112 0.412
#> GSM425868 2 0.1327 0.844 0.000 0.936 0.000 0.000 0.064 0.000
#> GSM425869 2 0.1327 0.844 0.000 0.936 0.000 0.000 0.064 0.000
#> GSM425870 6 0.2163 0.713 0.000 0.008 0.004 0.000 0.096 0.892
#> GSM425871 1 0.0146 0.862 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM425872 2 0.0865 0.860 0.000 0.964 0.000 0.000 0.036 0.000
#> GSM425873 6 0.3796 0.534 0.140 0.000 0.000 0.000 0.084 0.776
#> GSM425843 1 0.0632 0.862 0.976 0.000 0.000 0.000 0.024 0.000
#> GSM425844 1 0.1765 0.830 0.904 0.000 0.000 0.000 0.096 0.000
#> GSM425845 6 0.0260 0.708 0.000 0.000 0.000 0.000 0.008 0.992
#> GSM425846 2 0.3929 0.738 0.000 0.700 0.000 0.000 0.272 0.028
#> GSM425847 6 0.2278 0.718 0.000 0.004 0.000 0.000 0.128 0.868
#> GSM425886 5 0.6528 0.168 0.000 0.116 0.380 0.000 0.432 0.072
#> GSM425887 6 0.5718 0.514 0.000 0.204 0.000 0.000 0.284 0.512
#> GSM425888 6 0.5788 0.481 0.000 0.224 0.000 0.000 0.276 0.500
#> GSM425889 1 0.4932 0.566 0.644 0.000 0.000 0.228 0.128 0.000
#> GSM425890 4 0.0000 0.941 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425891 2 0.2964 0.810 0.000 0.792 0.000 0.000 0.204 0.004
#> GSM425892 2 0.1141 0.848 0.000 0.948 0.000 0.000 0.052 0.000
#> GSM425853 1 0.1863 0.836 0.896 0.000 0.000 0.000 0.104 0.000
#> GSM425854 2 0.0547 0.856 0.000 0.980 0.000 0.000 0.020 0.000
#> GSM425855 1 0.0146 0.862 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM425856 1 0.1863 0.836 0.896 0.000 0.000 0.000 0.104 0.000
#> GSM425857 4 0.6193 0.166 0.148 0.000 0.020 0.504 0.320 0.008
#> GSM425858 2 0.4692 0.665 0.000 0.644 0.000 0.000 0.276 0.080
#> GSM425859 2 0.1327 0.844 0.000 0.936 0.000 0.000 0.064 0.000
#> GSM425860 6 0.0146 0.710 0.000 0.000 0.000 0.000 0.004 0.996
#> GSM425861 6 0.6789 0.513 0.136 0.116 0.000 0.000 0.252 0.496
#> GSM425862 1 0.4851 0.502 0.632 0.000 0.000 0.272 0.096 0.000
#> GSM425837 1 0.0260 0.862 0.992 0.000 0.000 0.000 0.008 0.000
#> GSM425838 4 0.0000 0.941 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425839 2 0.1007 0.850 0.000 0.956 0.000 0.000 0.044 0.000
#> GSM425840 1 0.0146 0.862 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM425841 4 0.0000 0.941 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425842 1 0.4855 0.438 0.640 0.000 0.000 0.000 0.104 0.256
#> GSM425917 3 0.5119 -0.189 0.020 0.000 0.476 0.020 0.472 0.012
#> GSM425922 4 0.0000 0.941 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425919 1 0.1668 0.860 0.928 0.000 0.000 0.004 0.060 0.008
#> GSM425920 1 0.0000 0.862 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425923 1 0.3893 0.727 0.768 0.000 0.000 0.092 0.140 0.000
#> GSM425916 1 0.3473 0.769 0.804 0.000 0.000 0.048 0.144 0.004
#> GSM425918 1 0.2972 0.790 0.836 0.000 0.000 0.036 0.128 0.000
#> GSM425921 4 0.0000 0.941 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425925 1 0.2006 0.820 0.904 0.000 0.000 0.080 0.016 0.000
#> GSM425926 4 0.0000 0.941 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425927 1 0.2842 0.803 0.852 0.000 0.000 0.000 0.104 0.044
#> GSM425924 5 0.5877 0.555 0.316 0.000 0.160 0.000 0.512 0.012
#> GSM425928 3 0.1267 0.796 0.000 0.000 0.940 0.000 0.060 0.000
#> GSM425929 3 0.0000 0.839 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425930 3 0.0000 0.839 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425931 3 0.0000 0.839 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425932 3 0.0000 0.839 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425933 3 0.0000 0.839 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425934 3 0.0000 0.839 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425935 3 0.3619 0.380 0.000 0.000 0.680 0.000 0.316 0.004
#> GSM425936 3 0.0000 0.839 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425937 3 0.0000 0.839 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425938 3 0.1444 0.784 0.000 0.000 0.928 0.000 0.072 0.000
#> GSM425939 3 0.0000 0.839 0.000 0.000 1.000 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 disease.state(p) tissue(p) other(p) k
#> MAD:mclust 70 NA 6.83e-03 1.87e-04 2
#> MAD:mclust 99 2.42e-20 1.26e-21 3.30e-16 3
#> MAD:mclust 95 1.85e-20 3.77e-20 4.27e-14 4
#> MAD:mclust 96 1.49e-16 7.09e-17 1.00e-11 5
#> MAD:mclust 93 1.57e-18 1.66e-18 4.09e-16 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 103 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 0.564 0.805 0.906 0.4869 0.516 0.516
#> 3 3 0.469 0.606 0.816 0.3538 0.688 0.475
#> 4 4 0.691 0.762 0.877 0.1362 0.803 0.510
#> 5 5 0.627 0.601 0.727 0.0640 0.911 0.673
#> 6 6 0.659 0.555 0.735 0.0469 0.899 0.576
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
#> GSM425907 2 0.3733 0.8734 0.072 0.928
#> GSM425908 1 0.8813 0.6267 0.700 0.300
#> GSM425909 2 0.8555 0.6288 0.280 0.720
#> GSM425910 2 0.5946 0.8074 0.144 0.856
#> GSM425911 2 0.1184 0.8992 0.016 0.984
#> GSM425912 2 0.2043 0.8954 0.032 0.968
#> GSM425913 2 0.4022 0.8678 0.080 0.920
#> GSM425914 2 0.1414 0.8987 0.020 0.980
#> GSM425915 2 0.0376 0.9004 0.004 0.996
#> GSM425874 1 0.0000 0.8915 1.000 0.000
#> GSM425875 1 0.0938 0.8877 0.988 0.012
#> GSM425876 1 1.0000 -0.0423 0.500 0.500
#> GSM425877 1 0.0938 0.8877 0.988 0.012
#> GSM425878 1 0.0376 0.8907 0.996 0.004
#> GSM425879 2 0.1843 0.8966 0.028 0.972
#> GSM425880 1 0.4815 0.8256 0.896 0.104
#> GSM425881 1 0.5946 0.8039 0.856 0.144
#> GSM425882 1 0.9710 0.4218 0.600 0.400
#> GSM425883 1 0.0376 0.8905 0.996 0.004
#> GSM425884 1 0.2236 0.8751 0.964 0.036
#> GSM425885 1 0.0376 0.8905 0.996 0.004
#> GSM425848 1 0.0000 0.8915 1.000 0.000
#> GSM425849 1 0.0000 0.8915 1.000 0.000
#> GSM425850 1 0.0000 0.8915 1.000 0.000
#> GSM425851 1 0.2423 0.8730 0.960 0.040
#> GSM425852 2 0.9460 0.4703 0.364 0.636
#> GSM425893 2 0.0938 0.8997 0.012 0.988
#> GSM425894 1 0.8955 0.6065 0.688 0.312
#> GSM425895 1 0.9087 0.5858 0.676 0.324
#> GSM425896 2 0.1184 0.8997 0.016 0.984
#> GSM425897 2 0.1633 0.8979 0.024 0.976
#> GSM425898 1 0.8144 0.6941 0.748 0.252
#> GSM425899 1 0.0000 0.8915 1.000 0.000
#> GSM425900 2 0.9993 -0.0666 0.484 0.516
#> GSM425901 2 0.9248 0.5259 0.340 0.660
#> GSM425902 1 0.0000 0.8915 1.000 0.000
#> GSM425903 2 0.2043 0.8940 0.032 0.968
#> GSM425904 1 0.4562 0.8325 0.904 0.096
#> GSM425905 2 0.5178 0.8335 0.116 0.884
#> GSM425906 2 0.2043 0.8954 0.032 0.968
#> GSM425863 1 0.0000 0.8915 1.000 0.000
#> GSM425864 2 0.2236 0.8940 0.036 0.964
#> GSM425865 2 0.6343 0.7820 0.160 0.840
#> GSM425866 1 0.0938 0.8886 0.988 0.012
#> GSM425867 2 0.5059 0.8316 0.112 0.888
#> GSM425868 1 0.5842 0.8076 0.860 0.140
#> GSM425869 1 0.7674 0.7276 0.776 0.224
#> GSM425870 2 0.0000 0.8993 0.000 1.000
#> GSM425871 1 0.0000 0.8915 1.000 0.000
#> GSM425872 1 0.9286 0.5483 0.656 0.344
#> GSM425873 1 0.0938 0.8886 0.988 0.012
#> GSM425843 1 0.0000 0.8915 1.000 0.000
#> GSM425844 1 0.0000 0.8915 1.000 0.000
#> GSM425845 2 0.9993 0.1326 0.484 0.516
#> GSM425846 1 0.1184 0.8853 0.984 0.016
#> GSM425847 1 0.9795 0.3874 0.584 0.416
#> GSM425886 2 0.0376 0.9004 0.004 0.996
#> GSM425887 1 0.8713 0.6411 0.708 0.292
#> GSM425888 1 0.6531 0.7833 0.832 0.168
#> GSM425889 1 0.0000 0.8915 1.000 0.000
#> GSM425890 1 0.0376 0.8907 0.996 0.004
#> GSM425891 2 0.2603 0.8906 0.044 0.956
#> GSM425892 2 0.8443 0.5963 0.272 0.728
#> GSM425853 1 0.1843 0.8812 0.972 0.028
#> GSM425854 1 0.7528 0.7360 0.784 0.216
#> GSM425855 1 0.0000 0.8915 1.000 0.000
#> GSM425856 1 0.1184 0.8869 0.984 0.016
#> GSM425857 1 0.8555 0.6011 0.720 0.280
#> GSM425858 1 0.6623 0.7801 0.828 0.172
#> GSM425859 1 0.7815 0.7182 0.768 0.232
#> GSM425860 2 0.4298 0.8720 0.088 0.912
#> GSM425861 1 0.2043 0.8785 0.968 0.032
#> GSM425862 1 0.0000 0.8915 1.000 0.000
#> GSM425837 1 0.0938 0.8877 0.988 0.012
#> GSM425838 1 0.0000 0.8915 1.000 0.000
#> GSM425839 1 0.9608 0.4615 0.616 0.384
#> GSM425840 1 0.0000 0.8915 1.000 0.000
#> GSM425841 1 0.0000 0.8915 1.000 0.000
#> GSM425842 1 0.0672 0.8897 0.992 0.008
#> GSM425917 2 0.1184 0.9005 0.016 0.984
#> GSM425922 1 0.0000 0.8915 1.000 0.000
#> GSM425919 1 0.8016 0.6493 0.756 0.244
#> GSM425920 1 0.0000 0.8915 1.000 0.000
#> GSM425923 1 0.0672 0.8893 0.992 0.008
#> GSM425916 1 0.2043 0.8766 0.968 0.032
#> GSM425918 1 0.0376 0.8907 0.996 0.004
#> GSM425921 1 0.0000 0.8915 1.000 0.000
#> GSM425925 1 0.0000 0.8915 1.000 0.000
#> GSM425926 1 0.0000 0.8915 1.000 0.000
#> GSM425927 1 0.0672 0.8900 0.992 0.008
#> GSM425924 2 0.5294 0.8304 0.120 0.880
#> GSM425928 2 0.1184 0.9003 0.016 0.984
#> GSM425929 2 0.0938 0.9007 0.012 0.988
#> GSM425930 2 0.1184 0.9005 0.016 0.984
#> GSM425931 2 0.1414 0.8992 0.020 0.980
#> GSM425932 2 0.0376 0.9004 0.004 0.996
#> GSM425933 2 0.0672 0.9008 0.008 0.992
#> GSM425934 2 0.0000 0.8993 0.000 1.000
#> GSM425935 2 0.0000 0.8993 0.000 1.000
#> GSM425936 2 0.0000 0.8993 0.000 1.000
#> GSM425937 2 0.1414 0.8992 0.020 0.980
#> GSM425938 2 0.1184 0.9003 0.016 0.984
#> GSM425939 2 0.1414 0.8992 0.020 0.980
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.2878 0.7218 0.000 0.904 0.096
#> GSM425908 2 0.0475 0.7438 0.004 0.992 0.004
#> GSM425909 3 0.5932 0.7326 0.164 0.056 0.780
#> GSM425910 1 0.7591 0.1405 0.544 0.044 0.412
#> GSM425911 2 0.6302 0.2043 0.000 0.520 0.480
#> GSM425912 2 0.9664 0.2394 0.296 0.460 0.244
#> GSM425913 2 0.4235 0.6781 0.000 0.824 0.176
#> GSM425914 2 0.9021 0.1238 0.132 0.452 0.416
#> GSM425915 3 0.0829 0.8684 0.012 0.004 0.984
#> GSM425874 1 0.6286 0.2946 0.536 0.464 0.000
#> GSM425875 1 0.0592 0.7548 0.988 0.000 0.012
#> GSM425876 1 0.6519 0.6283 0.760 0.108 0.132
#> GSM425877 1 0.0747 0.7545 0.984 0.000 0.016
#> GSM425878 1 0.0237 0.7548 0.996 0.004 0.000
#> GSM425879 2 0.5621 0.5485 0.000 0.692 0.308
#> GSM425880 1 0.5216 0.5439 0.740 0.000 0.260
#> GSM425881 1 0.6260 0.1215 0.552 0.448 0.000
#> GSM425882 2 0.0661 0.7437 0.004 0.988 0.008
#> GSM425883 1 0.2711 0.7382 0.912 0.088 0.000
#> GSM425884 1 0.3551 0.6917 0.868 0.000 0.132
#> GSM425885 2 0.5431 0.3659 0.284 0.716 0.000
#> GSM425848 1 0.5216 0.6018 0.740 0.260 0.000
#> GSM425849 1 0.2165 0.7455 0.936 0.064 0.000
#> GSM425850 1 0.0747 0.7530 0.984 0.016 0.000
#> GSM425851 1 0.6810 0.6162 0.720 0.068 0.212
#> GSM425852 3 0.6095 0.3629 0.392 0.000 0.608
#> GSM425893 2 0.6307 0.1849 0.000 0.512 0.488
#> GSM425894 2 0.0237 0.7430 0.004 0.996 0.000
#> GSM425895 2 0.0829 0.7415 0.012 0.984 0.004
#> GSM425896 2 0.4887 0.6424 0.000 0.772 0.228
#> GSM425897 2 0.5254 0.6020 0.000 0.736 0.264
#> GSM425898 2 0.0892 0.7354 0.020 0.980 0.000
#> GSM425899 1 0.6111 0.4228 0.604 0.396 0.000
#> GSM425900 2 0.5178 0.6425 0.164 0.808 0.028
#> GSM425901 3 0.7500 0.6145 0.140 0.164 0.696
#> GSM425902 1 0.6305 0.2513 0.516 0.484 0.000
#> GSM425903 3 0.5244 0.6606 0.240 0.004 0.756
#> GSM425904 1 0.4842 0.5945 0.776 0.000 0.224
#> GSM425905 2 0.2796 0.7233 0.000 0.908 0.092
#> GSM425906 2 0.6081 0.4902 0.004 0.652 0.344
#> GSM425863 1 0.0892 0.7525 0.980 0.020 0.000
#> GSM425864 2 0.4702 0.6521 0.000 0.788 0.212
#> GSM425865 2 0.2165 0.7325 0.000 0.936 0.064
#> GSM425866 1 0.1163 0.7516 0.972 0.000 0.028
#> GSM425867 3 0.4750 0.6997 0.216 0.000 0.784
#> GSM425868 2 0.2165 0.7024 0.064 0.936 0.000
#> GSM425869 2 0.0592 0.7404 0.012 0.988 0.000
#> GSM425870 3 0.5269 0.6274 0.016 0.200 0.784
#> GSM425871 1 0.2356 0.7432 0.928 0.072 0.000
#> GSM425872 2 0.0592 0.7403 0.012 0.988 0.000
#> GSM425873 1 0.0747 0.7543 0.984 0.000 0.016
#> GSM425843 1 0.0424 0.7546 0.992 0.000 0.008
#> GSM425844 1 0.3116 0.7263 0.892 0.108 0.000
#> GSM425845 1 0.5285 0.5683 0.752 0.004 0.244
#> GSM425846 2 0.6154 0.0607 0.408 0.592 0.000
#> GSM425847 1 0.7128 0.3459 0.620 0.344 0.036
#> GSM425886 3 0.2796 0.8153 0.000 0.092 0.908
#> GSM425887 2 0.6286 0.1108 0.464 0.536 0.000
#> GSM425888 1 0.6274 0.1050 0.544 0.456 0.000
#> GSM425889 1 0.4346 0.6768 0.816 0.184 0.000
#> GSM425890 1 0.6305 0.2471 0.516 0.484 0.000
#> GSM425891 2 0.5291 0.5982 0.000 0.732 0.268
#> GSM425892 2 0.1529 0.7381 0.000 0.960 0.040
#> GSM425853 1 0.1860 0.7444 0.948 0.000 0.052
#> GSM425854 2 0.0592 0.7395 0.012 0.988 0.000
#> GSM425855 1 0.1411 0.7514 0.964 0.036 0.000
#> GSM425856 1 0.1031 0.7529 0.976 0.000 0.024
#> GSM425857 2 0.9077 0.1728 0.152 0.508 0.340
#> GSM425858 2 0.5327 0.4884 0.272 0.728 0.000
#> GSM425859 2 0.0237 0.7430 0.004 0.996 0.000
#> GSM425860 1 0.9282 0.0315 0.468 0.164 0.368
#> GSM425861 1 0.4654 0.6148 0.792 0.208 0.000
#> GSM425862 1 0.4887 0.6393 0.772 0.228 0.000
#> GSM425837 1 0.0747 0.7541 0.984 0.000 0.016
#> GSM425838 2 0.6305 -0.2059 0.484 0.516 0.000
#> GSM425839 2 0.0237 0.7430 0.004 0.996 0.000
#> GSM425840 1 0.0000 0.7545 1.000 0.000 0.000
#> GSM425841 1 0.6307 0.2419 0.512 0.488 0.000
#> GSM425842 1 0.0592 0.7546 0.988 0.000 0.012
#> GSM425917 3 0.3193 0.8115 0.004 0.100 0.896
#> GSM425922 1 0.6305 0.2511 0.516 0.484 0.000
#> GSM425919 1 0.5968 0.3545 0.636 0.000 0.364
#> GSM425920 1 0.0237 0.7546 0.996 0.000 0.004
#> GSM425923 1 0.2774 0.7447 0.920 0.072 0.008
#> GSM425916 1 0.4750 0.6023 0.784 0.000 0.216
#> GSM425918 1 0.2165 0.7455 0.936 0.064 0.000
#> GSM425921 1 0.6280 0.3035 0.540 0.460 0.000
#> GSM425925 1 0.4178 0.6878 0.828 0.172 0.000
#> GSM425926 1 0.6168 0.3937 0.588 0.412 0.000
#> GSM425927 1 0.0592 0.7546 0.988 0.000 0.012
#> GSM425924 3 0.3412 0.8021 0.124 0.000 0.876
#> GSM425928 3 0.1751 0.8655 0.012 0.028 0.960
#> GSM425929 3 0.0424 0.8688 0.008 0.000 0.992
#> GSM425930 3 0.0592 0.8681 0.012 0.000 0.988
#> GSM425931 3 0.1015 0.8694 0.012 0.008 0.980
#> GSM425932 3 0.0424 0.8666 0.000 0.008 0.992
#> GSM425933 3 0.0475 0.8688 0.004 0.004 0.992
#> GSM425934 3 0.1411 0.8542 0.000 0.036 0.964
#> GSM425935 3 0.3267 0.7865 0.000 0.116 0.884
#> GSM425936 3 0.1031 0.8622 0.000 0.024 0.976
#> GSM425937 3 0.0661 0.8692 0.008 0.004 0.988
#> GSM425938 3 0.1031 0.8625 0.000 0.024 0.976
#> GSM425939 3 0.0892 0.8653 0.020 0.000 0.980
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.4222 0.6602 0.000 0.728 0.000 0.272
#> GSM425908 2 0.4977 0.2776 0.000 0.540 0.000 0.460
#> GSM425909 3 0.3005 0.8993 0.048 0.008 0.900 0.044
#> GSM425910 1 0.1356 0.8662 0.960 0.032 0.008 0.000
#> GSM425911 2 0.0927 0.8162 0.016 0.976 0.008 0.000
#> GSM425912 2 0.4456 0.6081 0.280 0.716 0.004 0.000
#> GSM425913 2 0.0592 0.8199 0.000 0.984 0.000 0.016
#> GSM425914 2 0.2654 0.7744 0.108 0.888 0.004 0.000
#> GSM425915 3 0.0376 0.9490 0.004 0.004 0.992 0.000
#> GSM425874 4 0.0188 0.8032 0.004 0.000 0.000 0.996
#> GSM425875 1 0.1978 0.8757 0.928 0.000 0.004 0.068
#> GSM425876 1 0.1305 0.8655 0.960 0.036 0.004 0.000
#> GSM425877 1 0.3870 0.7495 0.788 0.000 0.004 0.208
#> GSM425878 1 0.1716 0.8772 0.936 0.000 0.000 0.064
#> GSM425879 2 0.0000 0.8190 0.000 1.000 0.000 0.000
#> GSM425880 1 0.3900 0.8317 0.844 0.000 0.084 0.072
#> GSM425881 2 0.4866 0.3878 0.404 0.596 0.000 0.000
#> GSM425882 2 0.0657 0.8209 0.004 0.984 0.000 0.012
#> GSM425883 4 0.4643 0.4583 0.344 0.000 0.000 0.656
#> GSM425884 1 0.0707 0.8844 0.980 0.000 0.000 0.020
#> GSM425885 4 0.1302 0.7741 0.000 0.044 0.000 0.956
#> GSM425848 4 0.2704 0.7700 0.124 0.000 0.000 0.876
#> GSM425849 1 0.2704 0.8407 0.876 0.000 0.000 0.124
#> GSM425850 1 0.0469 0.8772 0.988 0.012 0.000 0.000
#> GSM425851 4 0.6500 0.2769 0.080 0.000 0.376 0.544
#> GSM425852 3 0.4524 0.7155 0.204 0.000 0.768 0.028
#> GSM425893 2 0.0779 0.8170 0.004 0.980 0.016 0.000
#> GSM425894 4 0.4585 0.3480 0.000 0.332 0.000 0.668
#> GSM425895 2 0.2345 0.7982 0.000 0.900 0.000 0.100
#> GSM425896 2 0.6068 0.6344 0.000 0.676 0.116 0.208
#> GSM425897 2 0.0921 0.8192 0.000 0.972 0.000 0.028
#> GSM425898 2 0.3873 0.7066 0.000 0.772 0.000 0.228
#> GSM425899 4 0.3999 0.7642 0.140 0.036 0.000 0.824
#> GSM425900 2 0.1022 0.8131 0.032 0.968 0.000 0.000
#> GSM425901 3 0.3850 0.7756 0.004 0.004 0.804 0.188
#> GSM425902 4 0.0000 0.8025 0.000 0.000 0.000 1.000
#> GSM425903 1 0.4524 0.7035 0.768 0.028 0.204 0.000
#> GSM425904 1 0.5783 0.6823 0.708 0.000 0.172 0.120
#> GSM425905 2 0.0817 0.8195 0.000 0.976 0.000 0.024
#> GSM425906 2 0.0921 0.8143 0.028 0.972 0.000 0.000
#> GSM425863 1 0.1867 0.8742 0.928 0.000 0.000 0.072
#> GSM425864 2 0.0921 0.8192 0.000 0.972 0.000 0.028
#> GSM425865 2 0.1637 0.8126 0.000 0.940 0.000 0.060
#> GSM425866 1 0.0707 0.8846 0.980 0.000 0.000 0.020
#> GSM425867 3 0.2345 0.8733 0.100 0.000 0.900 0.000
#> GSM425868 4 0.3528 0.6221 0.000 0.192 0.000 0.808
#> GSM425869 4 0.3123 0.6687 0.000 0.156 0.000 0.844
#> GSM425870 2 0.5856 0.2555 0.036 0.556 0.408 0.000
#> GSM425871 1 0.1474 0.8820 0.948 0.000 0.000 0.052
#> GSM425872 2 0.4164 0.6673 0.000 0.736 0.000 0.264
#> GSM425873 1 0.0336 0.8786 0.992 0.008 0.000 0.000
#> GSM425843 1 0.0707 0.8844 0.980 0.000 0.000 0.020
#> GSM425844 4 0.4898 0.3070 0.416 0.000 0.000 0.584
#> GSM425845 1 0.0895 0.8733 0.976 0.020 0.004 0.000
#> GSM425846 4 0.6926 0.0834 0.112 0.392 0.000 0.496
#> GSM425847 1 0.2831 0.7981 0.876 0.120 0.004 0.000
#> GSM425886 3 0.1059 0.9414 0.000 0.012 0.972 0.016
#> GSM425887 2 0.4134 0.6452 0.260 0.740 0.000 0.000
#> GSM425888 2 0.4776 0.4540 0.376 0.624 0.000 0.000
#> GSM425889 4 0.1716 0.7978 0.064 0.000 0.000 0.936
#> GSM425890 4 0.0000 0.8025 0.000 0.000 0.000 1.000
#> GSM425891 2 0.0000 0.8190 0.000 1.000 0.000 0.000
#> GSM425892 2 0.4454 0.6102 0.000 0.692 0.000 0.308
#> GSM425853 1 0.1356 0.8850 0.960 0.000 0.008 0.032
#> GSM425854 2 0.2216 0.8021 0.000 0.908 0.000 0.092
#> GSM425855 1 0.4040 0.6892 0.752 0.000 0.000 0.248
#> GSM425856 1 0.1209 0.8851 0.964 0.000 0.004 0.032
#> GSM425857 4 0.2861 0.7530 0.000 0.016 0.096 0.888
#> GSM425858 2 0.1867 0.7991 0.072 0.928 0.000 0.000
#> GSM425859 2 0.4304 0.6436 0.000 0.716 0.000 0.284
#> GSM425860 1 0.2060 0.8509 0.932 0.052 0.016 0.000
#> GSM425861 1 0.3123 0.7581 0.844 0.156 0.000 0.000
#> GSM425862 4 0.1792 0.7966 0.068 0.000 0.000 0.932
#> GSM425837 1 0.2149 0.8656 0.912 0.000 0.000 0.088
#> GSM425838 4 0.0000 0.8025 0.000 0.000 0.000 1.000
#> GSM425839 2 0.2081 0.8059 0.000 0.916 0.000 0.084
#> GSM425840 1 0.2011 0.8698 0.920 0.000 0.000 0.080
#> GSM425841 4 0.0000 0.8025 0.000 0.000 0.000 1.000
#> GSM425842 1 0.0000 0.8807 1.000 0.000 0.000 0.000
#> GSM425917 3 0.3306 0.8204 0.000 0.004 0.840 0.156
#> GSM425922 4 0.0000 0.8025 0.000 0.000 0.000 1.000
#> GSM425919 1 0.4139 0.7938 0.816 0.000 0.144 0.040
#> GSM425920 1 0.2216 0.8645 0.908 0.000 0.000 0.092
#> GSM425923 4 0.3583 0.7096 0.180 0.000 0.004 0.816
#> GSM425916 1 0.7882 -0.0398 0.368 0.000 0.284 0.348
#> GSM425918 4 0.4564 0.4988 0.328 0.000 0.000 0.672
#> GSM425921 4 0.0469 0.8036 0.012 0.000 0.000 0.988
#> GSM425925 4 0.4713 0.4378 0.360 0.000 0.000 0.640
#> GSM425926 4 0.0707 0.8036 0.020 0.000 0.000 0.980
#> GSM425927 1 0.0188 0.8817 0.996 0.000 0.000 0.004
#> GSM425924 3 0.1109 0.9386 0.004 0.000 0.968 0.028
#> GSM425928 3 0.0336 0.9500 0.000 0.000 0.992 0.008
#> GSM425929 3 0.0000 0.9509 0.000 0.000 1.000 0.000
#> GSM425930 3 0.0000 0.9509 0.000 0.000 1.000 0.000
#> GSM425931 3 0.0336 0.9500 0.000 0.000 0.992 0.008
#> GSM425932 3 0.0000 0.9509 0.000 0.000 1.000 0.000
#> GSM425933 3 0.0000 0.9509 0.000 0.000 1.000 0.000
#> GSM425934 3 0.0188 0.9496 0.000 0.004 0.996 0.000
#> GSM425935 3 0.0804 0.9463 0.000 0.012 0.980 0.008
#> GSM425936 3 0.0188 0.9504 0.000 0.000 0.996 0.004
#> GSM425937 3 0.0000 0.9509 0.000 0.000 1.000 0.000
#> GSM425938 3 0.0336 0.9500 0.000 0.000 0.992 0.008
#> GSM425939 3 0.0000 0.9509 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
#> GSM425907 2 0.6284 0.4004 0.000 0.508 0.000 0.320 0.172
#> GSM425908 2 0.6370 0.2333 0.000 0.432 0.000 0.404 0.164
#> GSM425909 5 0.2277 0.6765 0.016 0.000 0.052 0.016 0.916
#> GSM425910 1 0.4468 0.4709 0.716 0.044 0.000 0.000 0.240
#> GSM425911 2 0.0609 0.7631 0.000 0.980 0.000 0.000 0.020
#> GSM425912 2 0.3534 0.5432 0.256 0.744 0.000 0.000 0.000
#> GSM425913 2 0.0510 0.7685 0.000 0.984 0.000 0.016 0.000
#> GSM425914 2 0.3445 0.6759 0.140 0.824 0.000 0.000 0.036
#> GSM425915 5 0.4905 0.4935 0.040 0.000 0.336 0.000 0.624
#> GSM425874 4 0.2848 0.6345 0.028 0.000 0.000 0.868 0.104
#> GSM425875 5 0.3689 0.6293 0.256 0.000 0.004 0.000 0.740
#> GSM425876 1 0.3682 0.6487 0.820 0.108 0.000 0.000 0.072
#> GSM425877 1 0.4389 0.3149 0.624 0.000 0.004 0.368 0.004
#> GSM425878 1 0.1701 0.7242 0.936 0.000 0.000 0.016 0.048
#> GSM425879 2 0.1243 0.7702 0.000 0.960 0.004 0.028 0.008
#> GSM425880 5 0.3696 0.6647 0.212 0.000 0.016 0.000 0.772
#> GSM425881 2 0.3932 0.4189 0.328 0.672 0.000 0.000 0.000
#> GSM425882 2 0.0404 0.7684 0.000 0.988 0.000 0.012 0.000
#> GSM425883 4 0.4165 0.4500 0.320 0.000 0.000 0.672 0.008
#> GSM425884 1 0.1701 0.7266 0.936 0.000 0.000 0.016 0.048
#> GSM425885 4 0.4419 0.4604 0.000 0.020 0.000 0.668 0.312
#> GSM425848 5 0.3053 0.5114 0.008 0.000 0.000 0.164 0.828
#> GSM425849 1 0.3281 0.7083 0.848 0.000 0.000 0.092 0.060
#> GSM425850 1 0.2616 0.7142 0.880 0.100 0.000 0.020 0.000
#> GSM425851 4 0.6543 0.2794 0.192 0.000 0.316 0.488 0.004
#> GSM425852 5 0.5361 0.6449 0.144 0.000 0.188 0.000 0.668
#> GSM425893 2 0.4547 0.5654 0.000 0.712 0.024 0.012 0.252
#> GSM425894 4 0.6219 0.2382 0.000 0.240 0.000 0.548 0.212
#> GSM425895 2 0.4349 0.6974 0.000 0.756 0.000 0.176 0.068
#> GSM425896 5 0.7308 -0.0666 0.000 0.276 0.032 0.256 0.436
#> GSM425897 2 0.2238 0.7688 0.000 0.912 0.020 0.064 0.004
#> GSM425898 2 0.4788 0.6516 0.000 0.696 0.000 0.240 0.064
#> GSM425899 4 0.6599 0.5334 0.156 0.032 0.000 0.572 0.240
#> GSM425900 2 0.0451 0.7645 0.004 0.988 0.000 0.000 0.008
#> GSM425901 5 0.2149 0.6416 0.000 0.000 0.036 0.048 0.916
#> GSM425902 4 0.3790 0.5297 0.000 0.004 0.000 0.724 0.272
#> GSM425903 5 0.4599 0.6144 0.272 0.000 0.040 0.000 0.688
#> GSM425904 5 0.3456 0.6760 0.184 0.000 0.016 0.000 0.800
#> GSM425905 2 0.1331 0.7710 0.000 0.952 0.000 0.040 0.008
#> GSM425906 2 0.0290 0.7625 0.008 0.992 0.000 0.000 0.000
#> GSM425863 1 0.3051 0.6853 0.852 0.000 0.000 0.120 0.028
#> GSM425864 2 0.2853 0.7623 0.000 0.880 0.004 0.076 0.040
#> GSM425865 2 0.2561 0.7610 0.000 0.884 0.000 0.096 0.020
#> GSM425866 5 0.4088 0.4629 0.368 0.000 0.000 0.000 0.632
#> GSM425867 5 0.6233 0.3535 0.144 0.000 0.396 0.000 0.460
#> GSM425868 4 0.4971 0.4806 0.000 0.144 0.000 0.712 0.144
#> GSM425869 4 0.5222 0.4838 0.000 0.124 0.000 0.680 0.196
#> GSM425870 2 0.4951 0.2238 0.012 0.556 0.420 0.000 0.012
#> GSM425871 1 0.3628 0.5916 0.772 0.012 0.000 0.216 0.000
#> GSM425872 2 0.4313 0.6802 0.000 0.732 0.000 0.228 0.040
#> GSM425873 1 0.2141 0.7172 0.916 0.064 0.000 0.004 0.016
#> GSM425843 1 0.1579 0.7329 0.944 0.000 0.000 0.024 0.032
#> GSM425844 4 0.4410 0.2104 0.440 0.000 0.000 0.556 0.004
#> GSM425845 1 0.4015 0.2838 0.652 0.000 0.000 0.000 0.348
#> GSM425846 2 0.7564 0.2895 0.128 0.472 0.000 0.292 0.108
#> GSM425847 1 0.4046 0.5585 0.696 0.296 0.000 0.008 0.000
#> GSM425886 5 0.3575 0.6374 0.000 0.000 0.120 0.056 0.824
#> GSM425887 2 0.2891 0.6598 0.176 0.824 0.000 0.000 0.000
#> GSM425888 2 0.4653 0.4037 0.324 0.652 0.000 0.016 0.008
#> GSM425889 4 0.5382 0.5942 0.120 0.000 0.000 0.656 0.224
#> GSM425890 4 0.2588 0.6462 0.100 0.000 0.008 0.884 0.008
#> GSM425891 2 0.0162 0.7657 0.000 0.996 0.000 0.004 0.000
#> GSM425892 2 0.5655 0.5403 0.000 0.600 0.000 0.288 0.112
#> GSM425853 1 0.4242 0.0630 0.572 0.000 0.000 0.000 0.428
#> GSM425854 2 0.3289 0.7488 0.000 0.844 0.000 0.108 0.048
#> GSM425855 1 0.4288 0.3973 0.664 0.000 0.000 0.324 0.012
#> GSM425856 5 0.3700 0.6466 0.240 0.000 0.008 0.000 0.752
#> GSM425857 5 0.3783 0.3740 0.000 0.000 0.008 0.252 0.740
#> GSM425858 2 0.1638 0.7459 0.064 0.932 0.000 0.000 0.004
#> GSM425859 2 0.5523 0.5217 0.000 0.592 0.000 0.320 0.088
#> GSM425860 1 0.4116 0.6046 0.756 0.212 0.004 0.000 0.028
#> GSM425861 1 0.4454 0.6005 0.708 0.260 0.000 0.028 0.004
#> GSM425862 4 0.4968 0.6385 0.136 0.000 0.000 0.712 0.152
#> GSM425837 1 0.2813 0.7111 0.876 0.000 0.000 0.040 0.084
#> GSM425838 4 0.3662 0.5357 0.000 0.004 0.000 0.744 0.252
#> GSM425839 2 0.3262 0.7467 0.000 0.840 0.000 0.124 0.036
#> GSM425840 1 0.2462 0.6912 0.880 0.000 0.000 0.112 0.008
#> GSM425841 4 0.2921 0.6025 0.004 0.004 0.000 0.844 0.148
#> GSM425842 1 0.1741 0.7208 0.936 0.024 0.000 0.000 0.040
#> GSM425917 3 0.5100 0.5100 0.056 0.000 0.652 0.288 0.004
#> GSM425922 4 0.2488 0.6331 0.124 0.000 0.004 0.872 0.000
#> GSM425919 1 0.6662 0.1718 0.480 0.000 0.276 0.240 0.004
#> GSM425920 1 0.4335 0.4075 0.664 0.000 0.008 0.324 0.004
#> GSM425923 4 0.4346 0.4585 0.304 0.000 0.012 0.680 0.004
#> GSM425916 4 0.6724 0.2364 0.296 0.000 0.240 0.460 0.004
#> GSM425918 4 0.4824 0.3269 0.380 0.000 0.020 0.596 0.004
#> GSM425921 4 0.2629 0.6478 0.104 0.000 0.004 0.880 0.012
#> GSM425925 4 0.4547 0.3227 0.400 0.000 0.000 0.588 0.012
#> GSM425926 4 0.3307 0.6554 0.104 0.000 0.000 0.844 0.052
#> GSM425927 1 0.1430 0.7215 0.944 0.000 0.000 0.052 0.004
#> GSM425924 3 0.5183 0.5900 0.104 0.000 0.692 0.200 0.004
#> GSM425928 3 0.0404 0.9265 0.000 0.000 0.988 0.012 0.000
#> GSM425929 3 0.0000 0.9321 0.000 0.000 1.000 0.000 0.000
#> GSM425930 3 0.0290 0.9288 0.000 0.000 0.992 0.000 0.008
#> GSM425931 3 0.0162 0.9314 0.000 0.000 0.996 0.000 0.004
#> GSM425932 3 0.0000 0.9321 0.000 0.000 1.000 0.000 0.000
#> GSM425933 3 0.0000 0.9321 0.000 0.000 1.000 0.000 0.000
#> GSM425934 3 0.0404 0.9263 0.000 0.012 0.988 0.000 0.000
#> GSM425935 3 0.0566 0.9249 0.000 0.004 0.984 0.012 0.000
#> GSM425936 3 0.0162 0.9310 0.000 0.004 0.996 0.000 0.000
#> GSM425937 3 0.0162 0.9314 0.000 0.000 0.996 0.000 0.004
#> GSM425938 3 0.0290 0.9285 0.000 0.000 0.992 0.000 0.008
#> GSM425939 3 0.0162 0.9314 0.000 0.000 0.996 0.000 0.004
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 2 0.6883 0.29166 0.000 0.432 0.004 0.336 0.152 0.076
#> GSM425908 4 0.6381 -0.00522 0.000 0.304 0.000 0.508 0.120 0.068
#> GSM425909 5 0.1490 0.74902 0.004 0.000 0.024 0.016 0.948 0.008
#> GSM425910 1 0.3421 0.54403 0.780 0.012 0.000 0.004 0.200 0.004
#> GSM425911 2 0.3844 0.71203 0.048 0.800 0.004 0.012 0.132 0.004
#> GSM425912 2 0.3432 0.59996 0.216 0.764 0.000 0.000 0.000 0.020
#> GSM425913 2 0.1296 0.71479 0.000 0.948 0.004 0.004 0.000 0.044
#> GSM425914 2 0.3168 0.65757 0.192 0.792 0.000 0.000 0.016 0.000
#> GSM425915 5 0.3803 0.65086 0.020 0.000 0.252 0.000 0.724 0.004
#> GSM425874 6 0.4559 0.27875 0.000 0.012 0.000 0.364 0.024 0.600
#> GSM425875 5 0.5279 0.56552 0.200 0.000 0.000 0.000 0.604 0.196
#> GSM425876 1 0.2421 0.70285 0.900 0.052 0.000 0.012 0.032 0.004
#> GSM425877 1 0.5204 0.32444 0.560 0.000 0.004 0.356 0.004 0.076
#> GSM425878 1 0.2355 0.69159 0.876 0.000 0.000 0.112 0.008 0.004
#> GSM425879 2 0.2150 0.73726 0.000 0.912 0.004 0.044 0.036 0.004
#> GSM425880 5 0.3018 0.74645 0.168 0.000 0.004 0.000 0.816 0.012
#> GSM425881 2 0.4718 0.43197 0.316 0.616 0.000 0.000 0.000 0.068
#> GSM425882 2 0.3172 0.73400 0.032 0.852 0.000 0.080 0.036 0.000
#> GSM425883 6 0.5458 0.06066 0.096 0.000 0.008 0.400 0.000 0.496
#> GSM425884 1 0.3043 0.67433 0.832 0.000 0.000 0.140 0.020 0.008
#> GSM425885 4 0.6070 0.25860 0.000 0.032 0.000 0.552 0.236 0.180
#> GSM425848 5 0.4296 0.47531 0.012 0.000 0.000 0.252 0.700 0.036
#> GSM425849 6 0.4701 0.04573 0.480 0.000 0.000 0.008 0.028 0.484
#> GSM425850 1 0.2295 0.71025 0.904 0.028 0.000 0.052 0.000 0.016
#> GSM425851 4 0.4988 0.41806 0.212 0.000 0.096 0.676 0.004 0.012
#> GSM425852 5 0.3864 0.72025 0.208 0.000 0.048 0.000 0.744 0.000
#> GSM425893 2 0.4811 0.61210 0.020 0.672 0.004 0.048 0.256 0.000
#> GSM425894 6 0.5583 0.46140 0.000 0.188 0.000 0.128 0.044 0.640
#> GSM425895 2 0.4488 0.59120 0.000 0.704 0.000 0.052 0.016 0.228
#> GSM425896 2 0.6771 0.19948 0.000 0.340 0.000 0.308 0.316 0.036
#> GSM425897 2 0.2393 0.73586 0.000 0.892 0.000 0.064 0.040 0.004
#> GSM425898 6 0.4249 0.39573 0.000 0.328 0.000 0.032 0.000 0.640
#> GSM425899 6 0.1642 0.62488 0.028 0.000 0.000 0.004 0.032 0.936
#> GSM425900 6 0.3983 0.58612 0.056 0.208 0.000 0.000 0.000 0.736
#> GSM425901 5 0.1679 0.73758 0.000 0.000 0.016 0.036 0.936 0.012
#> GSM425902 6 0.3317 0.57432 0.000 0.004 0.000 0.088 0.080 0.828
#> GSM425903 5 0.3314 0.71598 0.224 0.000 0.012 0.000 0.764 0.000
#> GSM425904 5 0.2933 0.76016 0.120 0.000 0.012 0.000 0.848 0.020
#> GSM425905 2 0.1452 0.73299 0.000 0.948 0.000 0.020 0.012 0.020
#> GSM425906 2 0.1781 0.70728 0.008 0.924 0.008 0.000 0.000 0.060
#> GSM425863 6 0.3915 0.54509 0.236 0.000 0.000 0.016 0.016 0.732
#> GSM425864 2 0.3175 0.72003 0.000 0.832 0.000 0.088 0.080 0.000
#> GSM425865 2 0.2812 0.72636 0.000 0.856 0.000 0.096 0.048 0.000
#> GSM425866 5 0.3719 0.67779 0.248 0.000 0.000 0.000 0.728 0.024
#> GSM425867 5 0.5682 0.50561 0.180 0.000 0.316 0.000 0.504 0.000
#> GSM425868 4 0.6017 0.20843 0.000 0.224 0.000 0.592 0.116 0.068
#> GSM425869 6 0.5917 0.35210 0.000 0.080 0.000 0.248 0.080 0.592
#> GSM425870 2 0.3931 0.63448 0.048 0.768 0.172 0.000 0.012 0.000
#> GSM425871 1 0.3816 0.47137 0.688 0.000 0.000 0.296 0.000 0.016
#> GSM425872 6 0.2760 0.61645 0.000 0.116 0.000 0.024 0.004 0.856
#> GSM425873 1 0.0870 0.71312 0.972 0.012 0.000 0.012 0.000 0.004
#> GSM425843 1 0.2432 0.70267 0.892 0.000 0.000 0.020 0.016 0.072
#> GSM425844 4 0.4213 0.29277 0.340 0.000 0.004 0.636 0.000 0.020
#> GSM425845 1 0.4445 0.05432 0.572 0.000 0.000 0.000 0.396 0.032
#> GSM425846 6 0.2617 0.63165 0.032 0.080 0.000 0.004 0.004 0.880
#> GSM425847 1 0.4071 0.48126 0.672 0.304 0.000 0.004 0.000 0.020
#> GSM425886 5 0.2058 0.72380 0.000 0.000 0.036 0.056 0.908 0.000
#> GSM425887 2 0.3786 0.61690 0.168 0.768 0.000 0.000 0.000 0.064
#> GSM425888 6 0.5366 0.42193 0.144 0.292 0.000 0.000 0.000 0.564
#> GSM425889 6 0.3221 0.60198 0.024 0.000 0.000 0.048 0.080 0.848
#> GSM425890 4 0.2159 0.54313 0.072 0.000 0.000 0.904 0.012 0.012
#> GSM425891 2 0.1080 0.71647 0.004 0.960 0.004 0.000 0.000 0.032
#> GSM425892 2 0.5982 0.37885 0.000 0.496 0.000 0.340 0.144 0.020
#> GSM425853 1 0.3817 0.03526 0.568 0.000 0.000 0.000 0.432 0.000
#> GSM425854 2 0.3854 0.65895 0.000 0.780 0.000 0.044 0.016 0.160
#> GSM425855 6 0.3652 0.57703 0.188 0.000 0.000 0.044 0.000 0.768
#> GSM425856 5 0.3409 0.74955 0.144 0.000 0.004 0.000 0.808 0.044
#> GSM425857 5 0.3804 0.52587 0.000 0.012 0.004 0.212 0.756 0.016
#> GSM425858 6 0.5034 0.11062 0.072 0.456 0.000 0.000 0.000 0.472
#> GSM425859 2 0.6346 0.51677 0.000 0.552 0.000 0.220 0.068 0.160
#> GSM425860 1 0.3944 0.62013 0.796 0.124 0.008 0.000 0.016 0.056
#> GSM425861 6 0.5886 0.23180 0.352 0.180 0.000 0.000 0.004 0.464
#> GSM425862 6 0.5069 0.48325 0.024 0.000 0.000 0.208 0.096 0.672
#> GSM425837 1 0.4878 0.65329 0.732 0.000 0.000 0.076 0.092 0.100
#> GSM425838 4 0.4334 0.42102 0.000 0.028 0.000 0.752 0.160 0.060
#> GSM425839 2 0.4425 0.46988 0.000 0.660 0.000 0.036 0.008 0.296
#> GSM425840 1 0.3395 0.67527 0.824 0.000 0.000 0.048 0.012 0.116
#> GSM425841 4 0.5128 0.00680 0.000 0.012 0.000 0.524 0.056 0.408
#> GSM425842 1 0.1219 0.71148 0.948 0.000 0.000 0.048 0.004 0.000
#> GSM425917 3 0.4933 0.32556 0.036 0.000 0.568 0.380 0.004 0.012
#> GSM425922 4 0.3079 0.51379 0.056 0.000 0.004 0.844 0.000 0.096
#> GSM425919 1 0.6708 0.06887 0.404 0.000 0.208 0.348 0.004 0.036
#> GSM425920 1 0.5555 0.25513 0.528 0.000 0.016 0.372 0.004 0.080
#> GSM425923 4 0.4271 0.43615 0.236 0.000 0.012 0.716 0.004 0.032
#> GSM425916 4 0.5036 0.32028 0.304 0.000 0.048 0.624 0.004 0.020
#> GSM425918 4 0.4637 0.36256 0.292 0.000 0.012 0.656 0.004 0.036
#> GSM425921 4 0.4296 0.20991 0.016 0.000 0.004 0.628 0.004 0.348
#> GSM425925 6 0.2724 0.60461 0.052 0.000 0.000 0.084 0.000 0.864
#> GSM425926 6 0.4009 0.33756 0.000 0.004 0.000 0.356 0.008 0.632
#> GSM425927 1 0.2213 0.70692 0.904 0.000 0.000 0.048 0.004 0.044
#> GSM425924 3 0.5500 0.29761 0.100 0.000 0.552 0.336 0.004 0.008
#> GSM425928 3 0.0632 0.90345 0.000 0.000 0.976 0.024 0.000 0.000
#> GSM425929 3 0.0146 0.91835 0.000 0.004 0.996 0.000 0.000 0.000
#> GSM425930 3 0.0000 0.91880 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425931 3 0.0000 0.91880 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425932 3 0.0146 0.91835 0.000 0.004 0.996 0.000 0.000 0.000
#> GSM425933 3 0.0146 0.91835 0.000 0.004 0.996 0.000 0.000 0.000
#> GSM425934 3 0.0260 0.91525 0.000 0.008 0.992 0.000 0.000 0.000
#> GSM425935 3 0.0291 0.91767 0.000 0.004 0.992 0.004 0.000 0.000
#> GSM425936 3 0.0146 0.91835 0.000 0.004 0.996 0.000 0.000 0.000
#> GSM425937 3 0.0000 0.91880 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425938 3 0.0146 0.91695 0.000 0.000 0.996 0.004 0.000 0.000
#> GSM425939 3 0.0000 0.91880 0.000 0.000 1.000 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 disease.state(p) tissue(p) other(p) k
#> MAD:NMF 96 2.05e-05 1.57e-05 3.00e-07 2
#> MAD:NMF 77 5.87e-09 1.01e-08 5.73e-08 3
#> MAD:NMF 91 1.26e-10 2.48e-10 4.65e-07 4
#> MAD:NMF 74 1.49e-12 9.01e-13 3.83e-08 5
#> MAD:NMF 66 6.95e-13 1.08e-12 1.76e-07 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 103 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 0.835 0.890 0.947 0.4192 0.600 0.600
#> 3 3 0.610 0.839 0.873 0.4880 0.721 0.540
#> 4 4 0.718 0.719 0.834 0.1378 0.954 0.862
#> 5 5 0.756 0.726 0.812 0.0557 0.920 0.737
#> 6 6 0.789 0.743 0.876 0.0232 0.981 0.923
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
#> GSM425907 2 0.000 0.9641 0.000 1.000
#> GSM425908 2 0.000 0.9641 0.000 1.000
#> GSM425909 2 0.163 0.9565 0.024 0.976
#> GSM425910 1 0.000 0.9344 1.000 0.000
#> GSM425911 1 0.224 0.9235 0.964 0.036
#> GSM425912 1 0.000 0.9344 1.000 0.000
#> GSM425913 1 0.891 0.6273 0.692 0.308
#> GSM425914 1 0.000 0.9344 1.000 0.000
#> GSM425915 1 0.000 0.9344 1.000 0.000
#> GSM425874 2 0.000 0.9641 0.000 1.000
#> GSM425875 1 0.000 0.9344 1.000 0.000
#> GSM425876 1 0.000 0.9344 1.000 0.000
#> GSM425877 1 0.000 0.9344 1.000 0.000
#> GSM425878 1 0.000 0.9344 1.000 0.000
#> GSM425879 1 0.358 0.9069 0.932 0.068
#> GSM425880 1 0.000 0.9344 1.000 0.000
#> GSM425881 1 0.000 0.9344 1.000 0.000
#> GSM425882 1 0.358 0.9069 0.932 0.068
#> GSM425883 1 0.000 0.9344 1.000 0.000
#> GSM425884 1 0.000 0.9344 1.000 0.000
#> GSM425885 2 0.000 0.9641 0.000 1.000
#> GSM425848 1 0.482 0.8811 0.896 0.104
#> GSM425849 1 0.000 0.9344 1.000 0.000
#> GSM425850 1 0.000 0.9344 1.000 0.000
#> GSM425851 1 0.494 0.8755 0.892 0.108
#> GSM425852 1 0.224 0.9235 0.964 0.036
#> GSM425893 1 0.358 0.9069 0.932 0.068
#> GSM425894 2 0.118 0.9618 0.016 0.984
#> GSM425895 1 0.358 0.9069 0.932 0.068
#> GSM425896 2 0.000 0.9641 0.000 1.000
#> GSM425897 1 1.000 0.1478 0.508 0.492
#> GSM425898 2 0.722 0.7221 0.200 0.800
#> GSM425899 1 0.358 0.9069 0.932 0.068
#> GSM425900 1 0.000 0.9344 1.000 0.000
#> GSM425901 2 0.163 0.9565 0.024 0.976
#> GSM425902 2 0.163 0.9565 0.024 0.976
#> GSM425903 1 0.000 0.9344 1.000 0.000
#> GSM425904 1 0.000 0.9344 1.000 0.000
#> GSM425905 2 0.118 0.9618 0.016 0.984
#> GSM425906 1 0.000 0.9344 1.000 0.000
#> GSM425863 1 0.000 0.9344 1.000 0.000
#> GSM425864 2 0.118 0.9618 0.016 0.984
#> GSM425865 2 0.118 0.9618 0.016 0.984
#> GSM425866 1 0.000 0.9344 1.000 0.000
#> GSM425867 1 0.000 0.9344 1.000 0.000
#> GSM425868 2 0.000 0.9641 0.000 1.000
#> GSM425869 2 0.000 0.9641 0.000 1.000
#> GSM425870 1 0.000 0.9344 1.000 0.000
#> GSM425871 1 0.278 0.9180 0.952 0.048
#> GSM425872 1 0.358 0.9069 0.932 0.068
#> GSM425873 1 0.000 0.9344 1.000 0.000
#> GSM425843 1 0.000 0.9344 1.000 0.000
#> GSM425844 1 0.891 0.6273 0.692 0.308
#> GSM425845 1 0.000 0.9344 1.000 0.000
#> GSM425846 1 0.278 0.9180 0.952 0.048
#> GSM425847 1 0.000 0.9344 1.000 0.000
#> GSM425886 2 0.163 0.9565 0.024 0.976
#> GSM425887 1 0.000 0.9344 1.000 0.000
#> GSM425888 1 0.000 0.9344 1.000 0.000
#> GSM425889 1 0.000 0.9344 1.000 0.000
#> GSM425890 2 0.000 0.9641 0.000 1.000
#> GSM425891 1 0.358 0.9069 0.932 0.068
#> GSM425892 2 0.118 0.9618 0.016 0.984
#> GSM425853 1 0.000 0.9344 1.000 0.000
#> GSM425854 1 0.482 0.8811 0.896 0.104
#> GSM425855 1 0.000 0.9344 1.000 0.000
#> GSM425856 1 0.204 0.9251 0.968 0.032
#> GSM425857 2 0.000 0.9641 0.000 1.000
#> GSM425858 1 0.000 0.9344 1.000 0.000
#> GSM425859 2 0.000 0.9641 0.000 1.000
#> GSM425860 1 0.000 0.9344 1.000 0.000
#> GSM425861 1 0.000 0.9344 1.000 0.000
#> GSM425862 1 0.358 0.9069 0.932 0.068
#> GSM425837 1 0.000 0.9344 1.000 0.000
#> GSM425838 2 0.000 0.9641 0.000 1.000
#> GSM425839 2 0.118 0.9618 0.016 0.984
#> GSM425840 1 0.000 0.9344 1.000 0.000
#> GSM425841 2 0.000 0.9641 0.000 1.000
#> GSM425842 1 0.000 0.9344 1.000 0.000
#> GSM425917 1 0.891 0.6273 0.692 0.308
#> GSM425922 2 0.000 0.9641 0.000 1.000
#> GSM425919 1 0.000 0.9344 1.000 0.000
#> GSM425920 1 0.000 0.9344 1.000 0.000
#> GSM425923 1 0.184 0.9270 0.972 0.028
#> GSM425916 1 0.000 0.9344 1.000 0.000
#> GSM425918 1 0.184 0.9270 0.972 0.028
#> GSM425921 2 0.000 0.9641 0.000 1.000
#> GSM425925 1 0.278 0.9180 0.952 0.048
#> GSM425926 2 0.118 0.9618 0.016 0.984
#> GSM425927 1 0.000 0.9344 1.000 0.000
#> GSM425924 1 0.891 0.6273 0.692 0.308
#> GSM425928 2 0.000 0.9641 0.000 1.000
#> GSM425929 1 0.184 0.9241 0.972 0.028
#> GSM425930 1 0.184 0.9241 0.972 0.028
#> GSM425931 1 0.909 0.5993 0.676 0.324
#> GSM425932 1 0.184 0.9241 0.972 0.028
#> GSM425933 1 0.881 0.6397 0.700 0.300
#> GSM425934 1 0.184 0.9241 0.972 0.028
#> GSM425935 2 0.993 0.0351 0.452 0.548
#> GSM425936 1 0.909 0.5993 0.676 0.324
#> GSM425937 1 0.909 0.5993 0.676 0.324
#> GSM425938 1 0.909 0.5993 0.676 0.324
#> GSM425939 1 0.184 0.9241 0.972 0.028
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.0000 0.892 0.000 1.000 0.000
#> GSM425908 2 0.0000 0.892 0.000 1.000 0.000
#> GSM425909 2 0.4887 0.877 0.000 0.772 0.228
#> GSM425910 1 0.0000 0.953 1.000 0.000 0.000
#> GSM425911 3 0.5706 0.783 0.320 0.000 0.680
#> GSM425912 1 0.0000 0.953 1.000 0.000 0.000
#> GSM425913 3 0.1315 0.690 0.020 0.008 0.972
#> GSM425914 1 0.0000 0.953 1.000 0.000 0.000
#> GSM425915 1 0.4605 0.683 0.796 0.000 0.204
#> GSM425874 2 0.0000 0.892 0.000 1.000 0.000
#> GSM425875 1 0.0000 0.953 1.000 0.000 0.000
#> GSM425876 1 0.0000 0.953 1.000 0.000 0.000
#> GSM425877 1 0.0237 0.951 0.996 0.000 0.004
#> GSM425878 1 0.0424 0.949 0.992 0.000 0.008
#> GSM425879 3 0.5327 0.811 0.272 0.000 0.728
#> GSM425880 1 0.2165 0.905 0.936 0.000 0.064
#> GSM425881 1 0.0000 0.953 1.000 0.000 0.000
#> GSM425882 3 0.5327 0.811 0.272 0.000 0.728
#> GSM425883 3 0.6154 0.662 0.408 0.000 0.592
#> GSM425884 1 0.0000 0.953 1.000 0.000 0.000
#> GSM425885 2 0.0000 0.892 0.000 1.000 0.000
#> GSM425848 3 0.5681 0.806 0.236 0.016 0.748
#> GSM425849 1 0.0424 0.949 0.992 0.000 0.008
#> GSM425850 1 0.4121 0.752 0.832 0.000 0.168
#> GSM425851 3 0.4931 0.805 0.232 0.000 0.768
#> GSM425852 3 0.5706 0.783 0.320 0.000 0.680
#> GSM425893 3 0.5327 0.811 0.272 0.000 0.728
#> GSM425894 2 0.4750 0.884 0.000 0.784 0.216
#> GSM425895 3 0.5327 0.811 0.272 0.000 0.728
#> GSM425896 2 0.0000 0.892 0.000 1.000 0.000
#> GSM425897 3 0.4178 0.425 0.000 0.172 0.828
#> GSM425898 2 0.6584 0.631 0.012 0.608 0.380
#> GSM425899 3 0.5327 0.811 0.272 0.000 0.728
#> GSM425900 1 0.4002 0.766 0.840 0.000 0.160
#> GSM425901 2 0.4887 0.877 0.000 0.772 0.228
#> GSM425902 2 0.4887 0.877 0.000 0.772 0.228
#> GSM425903 1 0.0000 0.953 1.000 0.000 0.000
#> GSM425904 1 0.2165 0.905 0.936 0.000 0.064
#> GSM425905 2 0.4750 0.884 0.000 0.784 0.216
#> GSM425906 1 0.4121 0.752 0.832 0.000 0.168
#> GSM425863 1 0.0000 0.953 1.000 0.000 0.000
#> GSM425864 2 0.4750 0.884 0.000 0.784 0.216
#> GSM425865 2 0.4750 0.884 0.000 0.784 0.216
#> GSM425866 1 0.1411 0.929 0.964 0.000 0.036
#> GSM425867 1 0.0000 0.953 1.000 0.000 0.000
#> GSM425868 2 0.2959 0.895 0.000 0.900 0.100
#> GSM425869 2 0.0000 0.892 0.000 1.000 0.000
#> GSM425870 1 0.0000 0.953 1.000 0.000 0.000
#> GSM425871 3 0.5591 0.796 0.304 0.000 0.696
#> GSM425872 3 0.5327 0.811 0.272 0.000 0.728
#> GSM425873 1 0.0000 0.953 1.000 0.000 0.000
#> GSM425843 1 0.0000 0.953 1.000 0.000 0.000
#> GSM425844 3 0.1315 0.690 0.020 0.008 0.972
#> GSM425845 1 0.0000 0.953 1.000 0.000 0.000
#> GSM425846 3 0.5591 0.796 0.304 0.000 0.696
#> GSM425847 1 0.0000 0.953 1.000 0.000 0.000
#> GSM425886 2 0.4887 0.877 0.000 0.772 0.228
#> GSM425887 1 0.1753 0.920 0.952 0.000 0.048
#> GSM425888 1 0.0000 0.953 1.000 0.000 0.000
#> GSM425889 1 0.3482 0.817 0.872 0.000 0.128
#> GSM425890 2 0.0000 0.892 0.000 1.000 0.000
#> GSM425891 3 0.5327 0.811 0.272 0.000 0.728
#> GSM425892 2 0.4750 0.884 0.000 0.784 0.216
#> GSM425853 1 0.1411 0.929 0.964 0.000 0.036
#> GSM425854 3 0.5681 0.806 0.236 0.016 0.748
#> GSM425855 1 0.0424 0.949 0.992 0.000 0.008
#> GSM425856 3 0.5835 0.764 0.340 0.000 0.660
#> GSM425857 2 0.0000 0.892 0.000 1.000 0.000
#> GSM425858 1 0.0000 0.953 1.000 0.000 0.000
#> GSM425859 2 0.3879 0.893 0.000 0.848 0.152
#> GSM425860 1 0.0000 0.953 1.000 0.000 0.000
#> GSM425861 1 0.0000 0.953 1.000 0.000 0.000
#> GSM425862 3 0.5327 0.811 0.272 0.000 0.728
#> GSM425837 1 0.0000 0.953 1.000 0.000 0.000
#> GSM425838 2 0.0000 0.892 0.000 1.000 0.000
#> GSM425839 2 0.4750 0.884 0.000 0.784 0.216
#> GSM425840 1 0.0424 0.949 0.992 0.000 0.008
#> GSM425841 2 0.0000 0.892 0.000 1.000 0.000
#> GSM425842 1 0.0000 0.953 1.000 0.000 0.000
#> GSM425917 3 0.1315 0.690 0.020 0.008 0.972
#> GSM425922 2 0.0000 0.892 0.000 1.000 0.000
#> GSM425919 1 0.0000 0.953 1.000 0.000 0.000
#> GSM425920 1 0.4399 0.712 0.812 0.000 0.188
#> GSM425923 3 0.5835 0.763 0.340 0.000 0.660
#> GSM425916 3 0.6168 0.654 0.412 0.000 0.588
#> GSM425918 3 0.5835 0.763 0.340 0.000 0.660
#> GSM425921 2 0.0000 0.892 0.000 1.000 0.000
#> GSM425925 3 0.5591 0.796 0.304 0.000 0.696
#> GSM425926 2 0.4750 0.884 0.000 0.784 0.216
#> GSM425927 1 0.0000 0.953 1.000 0.000 0.000
#> GSM425924 3 0.1315 0.690 0.020 0.008 0.972
#> GSM425928 2 0.3412 0.895 0.000 0.876 0.124
#> GSM425929 3 0.5859 0.738 0.344 0.000 0.656
#> GSM425930 3 0.5859 0.738 0.344 0.000 0.656
#> GSM425931 3 0.0237 0.669 0.000 0.004 0.996
#> GSM425932 3 0.5859 0.738 0.344 0.000 0.656
#> GSM425933 3 0.0892 0.694 0.020 0.000 0.980
#> GSM425934 3 0.5859 0.738 0.344 0.000 0.656
#> GSM425935 3 0.4974 0.283 0.000 0.236 0.764
#> GSM425936 3 0.0237 0.669 0.000 0.004 0.996
#> GSM425937 3 0.0237 0.669 0.000 0.004 0.996
#> GSM425938 3 0.0237 0.669 0.000 0.004 0.996
#> GSM425939 3 0.5859 0.738 0.344 0.000 0.656
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.0000 0.744 0.000 1.000 0.000 0.000
#> GSM425908 2 0.0817 0.749 0.000 0.976 0.024 0.000
#> GSM425909 2 0.5360 0.700 0.000 0.552 0.436 0.012
#> GSM425910 1 0.0000 0.924 1.000 0.000 0.000 0.000
#> GSM425911 4 0.2216 0.763 0.092 0.000 0.000 0.908
#> GSM425912 1 0.0000 0.924 1.000 0.000 0.000 0.000
#> GSM425913 4 0.4543 0.190 0.000 0.000 0.324 0.676
#> GSM425914 1 0.0000 0.924 1.000 0.000 0.000 0.000
#> GSM425915 1 0.4830 0.362 0.608 0.000 0.000 0.392
#> GSM425874 2 0.0817 0.749 0.000 0.976 0.024 0.000
#> GSM425875 1 0.0000 0.924 1.000 0.000 0.000 0.000
#> GSM425876 1 0.0000 0.924 1.000 0.000 0.000 0.000
#> GSM425877 1 0.0469 0.919 0.988 0.000 0.000 0.012
#> GSM425878 1 0.0592 0.918 0.984 0.000 0.000 0.016
#> GSM425879 4 0.1807 0.769 0.052 0.000 0.008 0.940
#> GSM425880 1 0.2011 0.874 0.920 0.000 0.000 0.080
#> GSM425881 1 0.0000 0.924 1.000 0.000 0.000 0.000
#> GSM425882 4 0.1807 0.769 0.052 0.000 0.008 0.940
#> GSM425883 4 0.3852 0.682 0.180 0.000 0.012 0.808
#> GSM425884 1 0.0000 0.924 1.000 0.000 0.000 0.000
#> GSM425885 2 0.0000 0.744 0.000 1.000 0.000 0.000
#> GSM425848 4 0.2224 0.739 0.032 0.000 0.040 0.928
#> GSM425849 1 0.0592 0.918 0.984 0.000 0.000 0.016
#> GSM425850 1 0.4624 0.487 0.660 0.000 0.000 0.340
#> GSM425851 4 0.5549 0.480 0.048 0.000 0.280 0.672
#> GSM425852 4 0.2216 0.763 0.092 0.000 0.000 0.908
#> GSM425893 4 0.1807 0.769 0.052 0.000 0.008 0.940
#> GSM425894 2 0.5229 0.710 0.000 0.564 0.428 0.008
#> GSM425895 4 0.1807 0.769 0.052 0.000 0.008 0.940
#> GSM425896 2 0.0817 0.749 0.000 0.976 0.024 0.000
#> GSM425897 3 0.1637 0.554 0.000 0.000 0.940 0.060
#> GSM425898 3 0.7564 -0.445 0.000 0.388 0.420 0.192
#> GSM425899 4 0.1807 0.769 0.052 0.000 0.008 0.940
#> GSM425900 1 0.4643 0.479 0.656 0.000 0.000 0.344
#> GSM425901 2 0.5360 0.700 0.000 0.552 0.436 0.012
#> GSM425902 2 0.5360 0.700 0.000 0.552 0.436 0.012
#> GSM425903 1 0.0000 0.924 1.000 0.000 0.000 0.000
#> GSM425904 1 0.2011 0.874 0.920 0.000 0.000 0.080
#> GSM425905 2 0.5229 0.710 0.000 0.564 0.428 0.008
#> GSM425906 1 0.4697 0.452 0.644 0.000 0.000 0.356
#> GSM425863 1 0.0000 0.924 1.000 0.000 0.000 0.000
#> GSM425864 2 0.5229 0.710 0.000 0.564 0.428 0.008
#> GSM425865 2 0.5229 0.710 0.000 0.564 0.428 0.008
#> GSM425866 1 0.1557 0.892 0.944 0.000 0.000 0.056
#> GSM425867 1 0.0000 0.924 1.000 0.000 0.000 0.000
#> GSM425868 2 0.3942 0.744 0.000 0.764 0.236 0.000
#> GSM425869 2 0.0000 0.744 0.000 1.000 0.000 0.000
#> GSM425870 1 0.0000 0.924 1.000 0.000 0.000 0.000
#> GSM425871 4 0.1940 0.769 0.076 0.000 0.000 0.924
#> GSM425872 4 0.1807 0.769 0.052 0.000 0.008 0.940
#> GSM425873 1 0.0000 0.924 1.000 0.000 0.000 0.000
#> GSM425843 1 0.0000 0.924 1.000 0.000 0.000 0.000
#> GSM425844 4 0.4543 0.190 0.000 0.000 0.324 0.676
#> GSM425845 1 0.0000 0.924 1.000 0.000 0.000 0.000
#> GSM425846 4 0.1940 0.769 0.076 0.000 0.000 0.924
#> GSM425847 1 0.0000 0.924 1.000 0.000 0.000 0.000
#> GSM425886 2 0.5360 0.700 0.000 0.552 0.436 0.012
#> GSM425887 1 0.1792 0.884 0.932 0.000 0.000 0.068
#> GSM425888 1 0.0000 0.924 1.000 0.000 0.000 0.000
#> GSM425889 1 0.4134 0.637 0.740 0.000 0.000 0.260
#> GSM425890 2 0.0000 0.744 0.000 1.000 0.000 0.000
#> GSM425891 4 0.1807 0.769 0.052 0.000 0.008 0.940
#> GSM425892 2 0.5229 0.710 0.000 0.564 0.428 0.008
#> GSM425853 1 0.1474 0.895 0.948 0.000 0.000 0.052
#> GSM425854 4 0.2224 0.739 0.032 0.000 0.040 0.928
#> GSM425855 1 0.0592 0.918 0.984 0.000 0.000 0.016
#> GSM425856 4 0.2589 0.749 0.116 0.000 0.000 0.884
#> GSM425857 2 0.0000 0.744 0.000 1.000 0.000 0.000
#> GSM425858 1 0.0000 0.924 1.000 0.000 0.000 0.000
#> GSM425859 2 0.4522 0.733 0.000 0.680 0.320 0.000
#> GSM425860 1 0.0000 0.924 1.000 0.000 0.000 0.000
#> GSM425861 1 0.0000 0.924 1.000 0.000 0.000 0.000
#> GSM425862 4 0.1807 0.769 0.052 0.000 0.008 0.940
#> GSM425837 1 0.0000 0.924 1.000 0.000 0.000 0.000
#> GSM425838 2 0.0000 0.744 0.000 1.000 0.000 0.000
#> GSM425839 2 0.5229 0.710 0.000 0.564 0.428 0.008
#> GSM425840 1 0.0592 0.918 0.984 0.000 0.000 0.016
#> GSM425841 2 0.1118 0.750 0.000 0.964 0.036 0.000
#> GSM425842 1 0.0000 0.924 1.000 0.000 0.000 0.000
#> GSM425917 4 0.4543 0.190 0.000 0.000 0.324 0.676
#> GSM425922 2 0.0000 0.744 0.000 1.000 0.000 0.000
#> GSM425919 1 0.0000 0.924 1.000 0.000 0.000 0.000
#> GSM425920 1 0.4843 0.347 0.604 0.000 0.000 0.396
#> GSM425923 4 0.3166 0.745 0.116 0.000 0.016 0.868
#> GSM425916 4 0.3895 0.677 0.184 0.000 0.012 0.804
#> GSM425918 4 0.3166 0.745 0.116 0.000 0.016 0.868
#> GSM425921 2 0.0000 0.744 0.000 1.000 0.000 0.000
#> GSM425925 4 0.1940 0.769 0.076 0.000 0.000 0.924
#> GSM425926 2 0.5229 0.710 0.000 0.564 0.428 0.008
#> GSM425927 1 0.0000 0.924 1.000 0.000 0.000 0.000
#> GSM425924 4 0.4543 0.190 0.000 0.000 0.324 0.676
#> GSM425928 2 0.4164 0.741 0.000 0.736 0.264 0.000
#> GSM425929 4 0.6570 0.376 0.116 0.000 0.280 0.604
#> GSM425930 4 0.6570 0.376 0.116 0.000 0.280 0.604
#> GSM425931 3 0.4661 0.674 0.000 0.000 0.652 0.348
#> GSM425932 4 0.6570 0.376 0.116 0.000 0.280 0.604
#> GSM425933 3 0.4761 0.624 0.000 0.000 0.628 0.372
#> GSM425934 4 0.6570 0.376 0.116 0.000 0.280 0.604
#> GSM425935 3 0.4646 0.525 0.000 0.084 0.796 0.120
#> GSM425936 3 0.4661 0.674 0.000 0.000 0.652 0.348
#> GSM425937 3 0.4661 0.674 0.000 0.000 0.652 0.348
#> GSM425938 3 0.4661 0.674 0.000 0.000 0.652 0.348
#> GSM425939 4 0.6570 0.376 0.116 0.000 0.280 0.604
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM425907 4 0.3913 0.9613 0.000 0.000 0.000 0.676 0.324
#> GSM425908 4 0.4138 0.9180 0.000 0.000 0.000 0.616 0.384
#> GSM425909 5 0.0404 0.8631 0.000 0.000 0.012 0.000 0.988
#> GSM425910 1 0.0000 0.8953 1.000 0.000 0.000 0.000 0.000
#> GSM425911 2 0.0579 0.8395 0.000 0.984 0.008 0.000 0.008
#> GSM425912 1 0.0000 0.8953 1.000 0.000 0.000 0.000 0.000
#> GSM425913 3 0.4883 0.2812 0.000 0.464 0.516 0.004 0.016
#> GSM425914 1 0.0000 0.8953 1.000 0.000 0.000 0.000 0.000
#> GSM425915 1 0.5283 0.2902 0.508 0.444 0.048 0.000 0.000
#> GSM425874 4 0.4138 0.9180 0.000 0.000 0.000 0.616 0.384
#> GSM425875 1 0.0000 0.8953 1.000 0.000 0.000 0.000 0.000
#> GSM425876 1 0.0000 0.8953 1.000 0.000 0.000 0.000 0.000
#> GSM425877 1 0.1568 0.8778 0.944 0.020 0.036 0.000 0.000
#> GSM425878 1 0.1907 0.8715 0.928 0.028 0.044 0.000 0.000
#> GSM425879 2 0.1830 0.8485 0.000 0.924 0.068 0.000 0.008
#> GSM425880 1 0.3339 0.8208 0.840 0.112 0.048 0.000 0.000
#> GSM425881 1 0.0000 0.8953 1.000 0.000 0.000 0.000 0.000
#> GSM425882 2 0.1764 0.8521 0.000 0.928 0.064 0.000 0.008
#> GSM425883 2 0.2804 0.7219 0.044 0.884 0.068 0.004 0.000
#> GSM425884 1 0.0000 0.8953 1.000 0.000 0.000 0.000 0.000
#> GSM425885 4 0.3913 0.9613 0.000 0.000 0.000 0.676 0.324
#> GSM425848 2 0.2632 0.8191 0.000 0.888 0.072 0.000 0.040
#> GSM425849 1 0.1907 0.8715 0.928 0.028 0.044 0.000 0.000
#> GSM425850 1 0.5154 0.4543 0.580 0.372 0.048 0.000 0.000
#> GSM425851 2 0.4276 0.2470 0.000 0.616 0.380 0.000 0.004
#> GSM425852 2 0.0579 0.8395 0.000 0.984 0.008 0.000 0.008
#> GSM425893 2 0.1764 0.8521 0.000 0.928 0.064 0.000 0.008
#> GSM425894 5 0.0000 0.8679 0.000 0.000 0.000 0.000 1.000
#> GSM425895 2 0.1764 0.8521 0.000 0.928 0.064 0.000 0.008
#> GSM425896 4 0.4138 0.9180 0.000 0.000 0.000 0.616 0.384
#> GSM425897 3 0.7158 0.1079 0.000 0.016 0.392 0.320 0.272
#> GSM425898 5 0.3318 0.5915 0.000 0.180 0.012 0.000 0.808
#> GSM425899 2 0.1830 0.8485 0.000 0.924 0.068 0.000 0.008
#> GSM425900 1 0.5176 0.4375 0.572 0.380 0.048 0.000 0.000
#> GSM425901 5 0.0404 0.8631 0.000 0.000 0.012 0.000 0.988
#> GSM425902 5 0.0404 0.8631 0.000 0.000 0.012 0.000 0.988
#> GSM425903 1 0.0000 0.8953 1.000 0.000 0.000 0.000 0.000
#> GSM425904 1 0.3339 0.8208 0.840 0.112 0.048 0.000 0.000
#> GSM425905 5 0.0000 0.8679 0.000 0.000 0.000 0.000 1.000
#> GSM425906 1 0.5204 0.4104 0.560 0.392 0.048 0.000 0.000
#> GSM425863 1 0.0000 0.8953 1.000 0.000 0.000 0.000 0.000
#> GSM425864 5 0.0000 0.8679 0.000 0.000 0.000 0.000 1.000
#> GSM425865 5 0.0000 0.8679 0.000 0.000 0.000 0.000 1.000
#> GSM425866 1 0.3019 0.8348 0.864 0.088 0.048 0.000 0.000
#> GSM425867 1 0.0000 0.8953 1.000 0.000 0.000 0.000 0.000
#> GSM425868 5 0.4138 -0.2301 0.000 0.000 0.000 0.384 0.616
#> GSM425869 4 0.3913 0.9613 0.000 0.000 0.000 0.676 0.324
#> GSM425870 1 0.0000 0.8953 1.000 0.000 0.000 0.000 0.000
#> GSM425871 2 0.0693 0.8502 0.000 0.980 0.012 0.000 0.008
#> GSM425872 2 0.1764 0.8521 0.000 0.928 0.064 0.000 0.008
#> GSM425873 1 0.0000 0.8953 1.000 0.000 0.000 0.000 0.000
#> GSM425843 1 0.0000 0.8953 1.000 0.000 0.000 0.000 0.000
#> GSM425844 3 0.4883 0.2812 0.000 0.464 0.516 0.004 0.016
#> GSM425845 1 0.0000 0.8953 1.000 0.000 0.000 0.000 0.000
#> GSM425846 2 0.0693 0.8502 0.000 0.980 0.012 0.000 0.008
#> GSM425847 1 0.0000 0.8953 1.000 0.000 0.000 0.000 0.000
#> GSM425886 5 0.0404 0.8631 0.000 0.000 0.012 0.000 0.988
#> GSM425887 1 0.3184 0.8284 0.852 0.100 0.048 0.000 0.000
#> GSM425888 1 0.0000 0.8953 1.000 0.000 0.000 0.000 0.000
#> GSM425889 1 0.4863 0.5874 0.656 0.296 0.048 0.000 0.000
#> GSM425890 4 0.3913 0.9613 0.000 0.000 0.000 0.676 0.324
#> GSM425891 2 0.1764 0.8521 0.000 0.928 0.064 0.000 0.008
#> GSM425892 5 0.0000 0.8679 0.000 0.000 0.000 0.000 1.000
#> GSM425853 1 0.2903 0.8395 0.872 0.080 0.048 0.000 0.000
#> GSM425854 2 0.2632 0.8191 0.000 0.888 0.072 0.000 0.040
#> GSM425855 1 0.1830 0.8732 0.932 0.028 0.040 0.000 0.000
#> GSM425856 2 0.1299 0.8216 0.020 0.960 0.012 0.000 0.008
#> GSM425857 4 0.3913 0.9613 0.000 0.000 0.000 0.676 0.324
#> GSM425858 1 0.0162 0.8942 0.996 0.000 0.004 0.000 0.000
#> GSM425859 5 0.2377 0.6850 0.000 0.000 0.000 0.128 0.872
#> GSM425860 1 0.0000 0.8953 1.000 0.000 0.000 0.000 0.000
#> GSM425861 1 0.0000 0.8953 1.000 0.000 0.000 0.000 0.000
#> GSM425862 2 0.1764 0.8521 0.000 0.928 0.064 0.000 0.008
#> GSM425837 1 0.0000 0.8953 1.000 0.000 0.000 0.000 0.000
#> GSM425838 4 0.3913 0.9613 0.000 0.000 0.000 0.676 0.324
#> GSM425839 5 0.0000 0.8679 0.000 0.000 0.000 0.000 1.000
#> GSM425840 1 0.1907 0.8715 0.928 0.028 0.044 0.000 0.000
#> GSM425841 4 0.4171 0.8992 0.000 0.000 0.000 0.604 0.396
#> GSM425842 1 0.0000 0.8953 1.000 0.000 0.000 0.000 0.000
#> GSM425917 3 0.4883 0.2812 0.000 0.464 0.516 0.004 0.016
#> GSM425922 4 0.3913 0.9613 0.000 0.000 0.000 0.676 0.324
#> GSM425919 1 0.0000 0.8953 1.000 0.000 0.000 0.000 0.000
#> GSM425920 1 0.5271 0.3068 0.520 0.432 0.048 0.000 0.000
#> GSM425923 2 0.2228 0.8027 0.004 0.900 0.092 0.004 0.000
#> GSM425916 2 0.2878 0.7158 0.048 0.880 0.068 0.004 0.000
#> GSM425918 2 0.2228 0.8027 0.004 0.900 0.092 0.004 0.000
#> GSM425921 4 0.3913 0.9613 0.000 0.000 0.000 0.676 0.324
#> GSM425925 2 0.0693 0.8502 0.000 0.980 0.012 0.000 0.008
#> GSM425926 5 0.0000 0.8679 0.000 0.000 0.000 0.000 1.000
#> GSM425927 1 0.0000 0.8953 1.000 0.000 0.000 0.000 0.000
#> GSM425924 3 0.4883 0.2812 0.000 0.464 0.516 0.004 0.016
#> GSM425928 5 0.4030 -0.0739 0.000 0.000 0.000 0.352 0.648
#> GSM425929 3 0.5178 0.1068 0.040 0.480 0.480 0.000 0.000
#> GSM425930 2 0.5178 -0.2043 0.040 0.480 0.480 0.000 0.000
#> GSM425931 3 0.2864 0.5883 0.000 0.112 0.864 0.000 0.024
#> GSM425932 3 0.5178 0.1068 0.040 0.480 0.480 0.000 0.000
#> GSM425933 3 0.2471 0.5785 0.000 0.136 0.864 0.000 0.000
#> GSM425934 3 0.5178 0.1068 0.040 0.480 0.480 0.000 0.000
#> GSM425935 3 0.4530 0.1761 0.000 0.008 0.612 0.004 0.376
#> GSM425936 3 0.2864 0.5883 0.000 0.112 0.864 0.000 0.024
#> GSM425937 3 0.2864 0.5883 0.000 0.112 0.864 0.000 0.024
#> GSM425938 3 0.2951 0.5877 0.000 0.112 0.860 0.000 0.028
#> GSM425939 3 0.5178 0.1068 0.040 0.480 0.480 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 4 0.0000 9.07e-01 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425908 4 0.1327 8.88e-01 0.000 0.000 0.000 0.936 0.064 0.000
#> GSM425909 5 0.0146 9.49e-01 0.000 0.000 0.004 0.000 0.996 0.000
#> GSM425910 1 0.0000 8.87e-01 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425911 2 0.0951 8.43e-01 0.000 0.968 0.020 0.000 0.008 0.004
#> GSM425912 1 0.0000 8.87e-01 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425913 3 0.4694 3.51e-01 0.000 0.376 0.572 0.000 0.000 0.052
#> GSM425914 1 0.0000 8.87e-01 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425915 1 0.5294 3.03e-01 0.508 0.416 0.056 0.000 0.000 0.020
#> GSM425874 4 0.1327 8.88e-01 0.000 0.000 0.000 0.936 0.064 0.000
#> GSM425875 1 0.0000 8.87e-01 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425876 1 0.0000 8.87e-01 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425877 1 0.1511 8.69e-01 0.944 0.012 0.032 0.000 0.000 0.012
#> GSM425878 1 0.1820 8.62e-01 0.928 0.012 0.044 0.000 0.000 0.016
#> GSM425879 2 0.1500 8.63e-01 0.000 0.936 0.052 0.000 0.012 0.000
#> GSM425880 1 0.3281 8.10e-01 0.840 0.088 0.056 0.000 0.000 0.016
#> GSM425881 1 0.0000 8.87e-01 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425882 2 0.1434 8.66e-01 0.000 0.940 0.048 0.000 0.012 0.000
#> GSM425883 2 0.4133 6.68e-01 0.044 0.788 0.092 0.000 0.000 0.076
#> GSM425884 1 0.0000 8.87e-01 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425885 4 0.0000 9.07e-01 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425848 2 0.2197 8.35e-01 0.000 0.900 0.056 0.000 0.044 0.000
#> GSM425849 1 0.1820 8.62e-01 0.928 0.012 0.044 0.000 0.000 0.016
#> GSM425850 1 0.5150 4.63e-01 0.580 0.344 0.056 0.000 0.000 0.020
#> GSM425851 2 0.3911 2.35e-01 0.000 0.624 0.368 0.000 0.008 0.000
#> GSM425852 2 0.0951 8.43e-01 0.000 0.968 0.020 0.000 0.008 0.004
#> GSM425893 2 0.1434 8.66e-01 0.000 0.940 0.048 0.000 0.012 0.000
#> GSM425894 5 0.0260 9.53e-01 0.000 0.000 0.000 0.008 0.992 0.000
#> GSM425895 2 0.1434 8.66e-01 0.000 0.940 0.048 0.000 0.012 0.000
#> GSM425896 4 0.1327 8.88e-01 0.000 0.000 0.000 0.936 0.064 0.000
#> GSM425897 6 0.1501 0.00e+00 0.000 0.000 0.076 0.000 0.000 0.924
#> GSM425898 5 0.2772 6.73e-01 0.000 0.180 0.004 0.000 0.816 0.000
#> GSM425899 2 0.1500 8.63e-01 0.000 0.936 0.052 0.000 0.012 0.000
#> GSM425900 1 0.5172 4.47e-01 0.572 0.352 0.056 0.000 0.000 0.020
#> GSM425901 5 0.0146 9.49e-01 0.000 0.000 0.004 0.000 0.996 0.000
#> GSM425902 5 0.0146 9.49e-01 0.000 0.000 0.004 0.000 0.996 0.000
#> GSM425903 1 0.0000 8.87e-01 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425904 1 0.3281 8.10e-01 0.840 0.088 0.056 0.000 0.000 0.016
#> GSM425905 5 0.0260 9.53e-01 0.000 0.000 0.000 0.008 0.992 0.000
#> GSM425906 1 0.5203 4.20e-01 0.560 0.364 0.056 0.000 0.000 0.020
#> GSM425863 1 0.0000 8.87e-01 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425864 5 0.0260 9.53e-01 0.000 0.000 0.000 0.008 0.992 0.000
#> GSM425865 5 0.0260 9.53e-01 0.000 0.000 0.000 0.008 0.992 0.000
#> GSM425866 1 0.2952 8.24e-01 0.864 0.068 0.052 0.000 0.000 0.016
#> GSM425867 1 0.0000 8.87e-01 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425868 4 0.3371 5.99e-01 0.000 0.000 0.000 0.708 0.292 0.000
#> GSM425869 4 0.0000 9.07e-01 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425870 1 0.0000 8.87e-01 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425871 2 0.0260 8.58e-01 0.000 0.992 0.000 0.000 0.008 0.000
#> GSM425872 2 0.1434 8.66e-01 0.000 0.940 0.048 0.000 0.012 0.000
#> GSM425873 1 0.0000 8.87e-01 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425843 1 0.0000 8.87e-01 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425844 3 0.4694 3.51e-01 0.000 0.376 0.572 0.000 0.000 0.052
#> GSM425845 1 0.0000 8.87e-01 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425846 2 0.0260 8.58e-01 0.000 0.992 0.000 0.000 0.008 0.000
#> GSM425847 1 0.0000 8.87e-01 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425886 5 0.0146 9.49e-01 0.000 0.000 0.004 0.000 0.996 0.000
#> GSM425887 1 0.3125 8.17e-01 0.852 0.076 0.056 0.000 0.000 0.016
#> GSM425888 1 0.0000 8.87e-01 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425889 1 0.4851 5.84e-01 0.656 0.268 0.056 0.000 0.000 0.020
#> GSM425890 4 0.0000 9.07e-01 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425891 2 0.1434 8.66e-01 0.000 0.940 0.048 0.000 0.012 0.000
#> GSM425892 5 0.0260 9.53e-01 0.000 0.000 0.000 0.008 0.992 0.000
#> GSM425853 1 0.2836 8.28e-01 0.872 0.060 0.052 0.000 0.000 0.016
#> GSM425854 2 0.2197 8.35e-01 0.000 0.900 0.056 0.000 0.044 0.000
#> GSM425855 1 0.1750 8.64e-01 0.932 0.012 0.040 0.000 0.000 0.016
#> GSM425856 2 0.1579 8.24e-01 0.020 0.944 0.024 0.000 0.008 0.004
#> GSM425857 4 0.0000 9.07e-01 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425858 1 0.0146 8.86e-01 0.996 0.000 0.004 0.000 0.000 0.000
#> GSM425859 5 0.2454 7.58e-01 0.000 0.000 0.000 0.160 0.840 0.000
#> GSM425860 1 0.0000 8.87e-01 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425861 1 0.0000 8.87e-01 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425862 2 0.1434 8.66e-01 0.000 0.940 0.048 0.000 0.012 0.000
#> GSM425837 1 0.0000 8.87e-01 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425838 4 0.0000 9.07e-01 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425839 5 0.0260 9.53e-01 0.000 0.000 0.000 0.008 0.992 0.000
#> GSM425840 1 0.1820 8.62e-01 0.928 0.012 0.044 0.000 0.000 0.016
#> GSM425841 4 0.1501 8.78e-01 0.000 0.000 0.000 0.924 0.076 0.000
#> GSM425842 1 0.0000 8.87e-01 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425917 3 0.4694 3.51e-01 0.000 0.376 0.572 0.000 0.000 0.052
#> GSM425922 4 0.0000 9.07e-01 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425919 1 0.0000 8.87e-01 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425920 1 0.5279 3.20e-01 0.520 0.404 0.056 0.000 0.000 0.020
#> GSM425923 2 0.3909 7.01e-01 0.004 0.772 0.148 0.000 0.000 0.076
#> GSM425916 2 0.4196 6.62e-01 0.048 0.784 0.092 0.000 0.000 0.076
#> GSM425918 2 0.3909 7.01e-01 0.004 0.772 0.148 0.000 0.000 0.076
#> GSM425921 4 0.0000 9.07e-01 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425925 2 0.0260 8.58e-01 0.000 0.992 0.000 0.000 0.008 0.000
#> GSM425926 5 0.0260 9.53e-01 0.000 0.000 0.000 0.008 0.992 0.000
#> GSM425927 1 0.0000 8.87e-01 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425924 3 0.4694 3.51e-01 0.000 0.376 0.572 0.000 0.000 0.052
#> GSM425928 4 0.3515 5.49e-01 0.000 0.000 0.000 0.676 0.324 0.000
#> GSM425929 3 0.5108 2.51e-01 0.040 0.444 0.496 0.000 0.000 0.020
#> GSM425930 3 0.5108 2.51e-01 0.040 0.444 0.496 0.000 0.000 0.020
#> GSM425931 3 0.2384 4.15e-01 0.000 0.084 0.884 0.000 0.032 0.000
#> GSM425932 3 0.5108 2.51e-01 0.040 0.444 0.496 0.000 0.000 0.020
#> GSM425933 3 0.2165 4.20e-01 0.000 0.108 0.884 0.000 0.008 0.000
#> GSM425934 3 0.5108 2.51e-01 0.040 0.444 0.496 0.000 0.000 0.020
#> GSM425935 3 0.4138 -7.82e-06 0.000 0.004 0.616 0.012 0.368 0.000
#> GSM425936 3 0.2384 4.15e-01 0.000 0.084 0.884 0.000 0.032 0.000
#> GSM425937 3 0.2384 4.15e-01 0.000 0.084 0.884 0.000 0.032 0.000
#> GSM425938 3 0.2457 4.13e-01 0.000 0.084 0.880 0.000 0.036 0.000
#> GSM425939 3 0.5108 2.51e-01 0.040 0.444 0.496 0.000 0.000 0.020
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 disease.state(p) tissue(p) other(p) k
#> ATC:hclust 101 2.98e-01 3.55e-01 3.52e-01 2
#> ATC:hclust 101 1.60e-04 3.58e-04 5.69e-02 3
#> ATC:hclust 87 1.79e-13 3.95e-12 2.20e-06 4
#> ATC:hclust 84 2.47e-17 1.73e-15 1.00e-08 5
#> ATC:hclust 81 1.83e-01 2.56e-01 6.02e-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["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 103 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 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 0.836 0.949 0.974 0.4937 0.499 0.499
#> 3 3 1.000 0.994 0.997 0.3383 0.706 0.481
#> 4 4 0.661 0.564 0.778 0.1165 0.819 0.533
#> 5 5 0.693 0.509 0.732 0.0590 0.894 0.640
#> 6 6 0.755 0.686 0.772 0.0465 0.846 0.443
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
#> GSM425907 2 0.0000 0.947 0.000 1.000
#> GSM425908 2 0.0000 0.947 0.000 1.000
#> GSM425909 2 0.0000 0.947 0.000 1.000
#> GSM425910 1 0.0000 0.994 1.000 0.000
#> GSM425911 1 0.0000 0.994 1.000 0.000
#> GSM425912 1 0.0000 0.994 1.000 0.000
#> GSM425913 2 0.0000 0.947 0.000 1.000
#> GSM425914 1 0.0000 0.994 1.000 0.000
#> GSM425915 1 0.0000 0.994 1.000 0.000
#> GSM425874 2 0.0000 0.947 0.000 1.000
#> GSM425875 1 0.0000 0.994 1.000 0.000
#> GSM425876 1 0.0000 0.994 1.000 0.000
#> GSM425877 1 0.0000 0.994 1.000 0.000
#> GSM425878 1 0.0000 0.994 1.000 0.000
#> GSM425879 2 0.7950 0.741 0.240 0.760
#> GSM425880 1 0.0000 0.994 1.000 0.000
#> GSM425881 1 0.0000 0.994 1.000 0.000
#> GSM425882 2 0.7950 0.741 0.240 0.760
#> GSM425883 1 0.0000 0.994 1.000 0.000
#> GSM425884 1 0.0000 0.994 1.000 0.000
#> GSM425885 2 0.0000 0.947 0.000 1.000
#> GSM425848 2 0.0000 0.947 0.000 1.000
#> GSM425849 1 0.0000 0.994 1.000 0.000
#> GSM425850 1 0.0000 0.994 1.000 0.000
#> GSM425851 2 0.7950 0.741 0.240 0.760
#> GSM425852 1 0.0000 0.994 1.000 0.000
#> GSM425893 2 0.7950 0.741 0.240 0.760
#> GSM425894 2 0.0000 0.947 0.000 1.000
#> GSM425895 2 0.7950 0.741 0.240 0.760
#> GSM425896 2 0.0000 0.947 0.000 1.000
#> GSM425897 2 0.0000 0.947 0.000 1.000
#> GSM425898 2 0.0000 0.947 0.000 1.000
#> GSM425899 1 0.0000 0.994 1.000 0.000
#> GSM425900 1 0.0000 0.994 1.000 0.000
#> GSM425901 2 0.0000 0.947 0.000 1.000
#> GSM425902 2 0.0000 0.947 0.000 1.000
#> GSM425903 1 0.0000 0.994 1.000 0.000
#> GSM425904 1 0.0000 0.994 1.000 0.000
#> GSM425905 2 0.0000 0.947 0.000 1.000
#> GSM425906 1 0.0000 0.994 1.000 0.000
#> GSM425863 1 0.0000 0.994 1.000 0.000
#> GSM425864 2 0.0000 0.947 0.000 1.000
#> GSM425865 2 0.0000 0.947 0.000 1.000
#> GSM425866 1 0.0000 0.994 1.000 0.000
#> GSM425867 1 0.0000 0.994 1.000 0.000
#> GSM425868 2 0.0000 0.947 0.000 1.000
#> GSM425869 2 0.0000 0.947 0.000 1.000
#> GSM425870 1 0.0000 0.994 1.000 0.000
#> GSM425871 1 0.0000 0.994 1.000 0.000
#> GSM425872 2 0.7950 0.741 0.240 0.760
#> GSM425873 1 0.0000 0.994 1.000 0.000
#> GSM425843 1 0.0000 0.994 1.000 0.000
#> GSM425844 2 0.6343 0.823 0.160 0.840
#> GSM425845 1 0.0000 0.994 1.000 0.000
#> GSM425846 1 0.0000 0.994 1.000 0.000
#> GSM425847 1 0.0000 0.994 1.000 0.000
#> GSM425886 2 0.0000 0.947 0.000 1.000
#> GSM425887 1 0.0000 0.994 1.000 0.000
#> GSM425888 1 0.0000 0.994 1.000 0.000
#> GSM425889 1 0.0000 0.994 1.000 0.000
#> GSM425890 2 0.0000 0.947 0.000 1.000
#> GSM425891 2 0.7950 0.741 0.240 0.760
#> GSM425892 2 0.0000 0.947 0.000 1.000
#> GSM425853 1 0.0000 0.994 1.000 0.000
#> GSM425854 2 0.0000 0.947 0.000 1.000
#> GSM425855 1 0.0000 0.994 1.000 0.000
#> GSM425856 1 0.0000 0.994 1.000 0.000
#> GSM425857 2 0.0000 0.947 0.000 1.000
#> GSM425858 1 0.0000 0.994 1.000 0.000
#> GSM425859 2 0.0000 0.947 0.000 1.000
#> GSM425860 1 0.0000 0.994 1.000 0.000
#> GSM425861 1 0.0000 0.994 1.000 0.000
#> GSM425862 2 0.7950 0.741 0.240 0.760
#> GSM425837 1 0.0000 0.994 1.000 0.000
#> GSM425838 2 0.0000 0.947 0.000 1.000
#> GSM425839 2 0.0000 0.947 0.000 1.000
#> GSM425840 1 0.0000 0.994 1.000 0.000
#> GSM425841 2 0.0000 0.947 0.000 1.000
#> GSM425842 1 0.0000 0.994 1.000 0.000
#> GSM425917 2 0.0000 0.947 0.000 1.000
#> GSM425922 2 0.0000 0.947 0.000 1.000
#> GSM425919 1 0.0000 0.994 1.000 0.000
#> GSM425920 1 0.0000 0.994 1.000 0.000
#> GSM425923 1 0.0000 0.994 1.000 0.000
#> GSM425916 1 0.0000 0.994 1.000 0.000
#> GSM425918 1 0.4562 0.884 0.904 0.096
#> GSM425921 2 0.0000 0.947 0.000 1.000
#> GSM425925 1 0.0000 0.994 1.000 0.000
#> GSM425926 2 0.0000 0.947 0.000 1.000
#> GSM425927 1 0.0000 0.994 1.000 0.000
#> GSM425924 2 0.8327 0.705 0.264 0.736
#> GSM425928 2 0.0000 0.947 0.000 1.000
#> GSM425929 1 0.0000 0.994 1.000 0.000
#> GSM425930 1 0.0000 0.994 1.000 0.000
#> GSM425931 2 0.0000 0.947 0.000 1.000
#> GSM425932 1 0.0000 0.994 1.000 0.000
#> GSM425933 1 0.7376 0.712 0.792 0.208
#> GSM425934 1 0.0000 0.994 1.000 0.000
#> GSM425935 2 0.0000 0.947 0.000 1.000
#> GSM425936 2 0.0000 0.947 0.000 1.000
#> GSM425937 2 0.0938 0.939 0.012 0.988
#> GSM425938 2 0.0000 0.947 0.000 1.000
#> GSM425939 1 0.0000 0.994 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.0000 1.000 0.000 1 0.000
#> GSM425908 2 0.0000 1.000 0.000 1 0.000
#> GSM425909 3 0.0000 0.993 0.000 0 1.000
#> GSM425910 1 0.0000 0.999 1.000 0 0.000
#> GSM425911 3 0.0000 0.993 0.000 0 1.000
#> GSM425912 1 0.0000 0.999 1.000 0 0.000
#> GSM425913 3 0.0000 0.993 0.000 0 1.000
#> GSM425914 1 0.0000 0.999 1.000 0 0.000
#> GSM425915 3 0.0592 0.984 0.012 0 0.988
#> GSM425874 2 0.0000 1.000 0.000 1 0.000
#> GSM425875 1 0.0000 0.999 1.000 0 0.000
#> GSM425876 1 0.0000 0.999 1.000 0 0.000
#> GSM425877 1 0.0000 0.999 1.000 0 0.000
#> GSM425878 1 0.0000 0.999 1.000 0 0.000
#> GSM425879 3 0.0000 0.993 0.000 0 1.000
#> GSM425880 1 0.0000 0.999 1.000 0 0.000
#> GSM425881 1 0.0000 0.999 1.000 0 0.000
#> GSM425882 3 0.0000 0.993 0.000 0 1.000
#> GSM425883 1 0.0000 0.999 1.000 0 0.000
#> GSM425884 1 0.0000 0.999 1.000 0 0.000
#> GSM425885 2 0.0000 1.000 0.000 1 0.000
#> GSM425848 3 0.0000 0.993 0.000 0 1.000
#> GSM425849 1 0.0000 0.999 1.000 0 0.000
#> GSM425850 1 0.0000 0.999 1.000 0 0.000
#> GSM425851 3 0.0000 0.993 0.000 0 1.000
#> GSM425852 3 0.0000 0.993 0.000 0 1.000
#> GSM425893 3 0.0000 0.993 0.000 0 1.000
#> GSM425894 2 0.0000 1.000 0.000 1 0.000
#> GSM425895 3 0.0000 0.993 0.000 0 1.000
#> GSM425896 2 0.0000 1.000 0.000 1 0.000
#> GSM425897 3 0.0000 0.993 0.000 0 1.000
#> GSM425898 3 0.0000 0.993 0.000 0 1.000
#> GSM425899 3 0.0000 0.993 0.000 0 1.000
#> GSM425900 1 0.0000 0.999 1.000 0 0.000
#> GSM425901 2 0.0000 1.000 0.000 1 0.000
#> GSM425902 2 0.0000 1.000 0.000 1 0.000
#> GSM425903 1 0.0000 0.999 1.000 0 0.000
#> GSM425904 1 0.0747 0.983 0.984 0 0.016
#> GSM425905 2 0.0000 1.000 0.000 1 0.000
#> GSM425906 1 0.0000 0.999 1.000 0 0.000
#> GSM425863 1 0.0000 0.999 1.000 0 0.000
#> GSM425864 2 0.0000 1.000 0.000 1 0.000
#> GSM425865 2 0.0000 1.000 0.000 1 0.000
#> GSM425866 1 0.0000 0.999 1.000 0 0.000
#> GSM425867 1 0.0000 0.999 1.000 0 0.000
#> GSM425868 2 0.0000 1.000 0.000 1 0.000
#> GSM425869 2 0.0000 1.000 0.000 1 0.000
#> GSM425870 1 0.0000 0.999 1.000 0 0.000
#> GSM425871 3 0.0000 0.993 0.000 0 1.000
#> GSM425872 3 0.0000 0.993 0.000 0 1.000
#> GSM425873 1 0.0000 0.999 1.000 0 0.000
#> GSM425843 1 0.0000 0.999 1.000 0 0.000
#> GSM425844 3 0.0000 0.993 0.000 0 1.000
#> GSM425845 1 0.0000 0.999 1.000 0 0.000
#> GSM425846 3 0.0000 0.993 0.000 0 1.000
#> GSM425847 1 0.0000 0.999 1.000 0 0.000
#> GSM425886 3 0.0000 0.993 0.000 0 1.000
#> GSM425887 1 0.0000 0.999 1.000 0 0.000
#> GSM425888 1 0.0000 0.999 1.000 0 0.000
#> GSM425889 1 0.0747 0.983 0.984 0 0.016
#> GSM425890 2 0.0000 1.000 0.000 1 0.000
#> GSM425891 3 0.0000 0.993 0.000 0 1.000
#> GSM425892 2 0.0000 1.000 0.000 1 0.000
#> GSM425853 1 0.0000 0.999 1.000 0 0.000
#> GSM425854 3 0.0000 0.993 0.000 0 1.000
#> GSM425855 1 0.0000 0.999 1.000 0 0.000
#> GSM425856 3 0.1643 0.953 0.044 0 0.956
#> GSM425857 2 0.0000 1.000 0.000 1 0.000
#> GSM425858 1 0.0000 0.999 1.000 0 0.000
#> GSM425859 2 0.0000 1.000 0.000 1 0.000
#> GSM425860 1 0.0000 0.999 1.000 0 0.000
#> GSM425861 1 0.0000 0.999 1.000 0 0.000
#> GSM425862 3 0.0000 0.993 0.000 0 1.000
#> GSM425837 1 0.0000 0.999 1.000 0 0.000
#> GSM425838 2 0.0000 1.000 0.000 1 0.000
#> GSM425839 2 0.0000 1.000 0.000 1 0.000
#> GSM425840 1 0.0000 0.999 1.000 0 0.000
#> GSM425841 2 0.0000 1.000 0.000 1 0.000
#> GSM425842 1 0.0000 0.999 1.000 0 0.000
#> GSM425917 3 0.0000 0.993 0.000 0 1.000
#> GSM425922 2 0.0000 1.000 0.000 1 0.000
#> GSM425919 1 0.0000 0.999 1.000 0 0.000
#> GSM425920 1 0.0747 0.983 0.984 0 0.016
#> GSM425923 3 0.0000 0.993 0.000 0 1.000
#> GSM425916 1 0.0000 0.999 1.000 0 0.000
#> GSM425918 3 0.0000 0.993 0.000 0 1.000
#> GSM425921 2 0.0000 1.000 0.000 1 0.000
#> GSM425925 3 0.1643 0.953 0.044 0 0.956
#> GSM425926 2 0.0000 1.000 0.000 1 0.000
#> GSM425927 1 0.0000 0.999 1.000 0 0.000
#> GSM425924 3 0.0000 0.993 0.000 0 1.000
#> GSM425928 2 0.0000 1.000 0.000 1 0.000
#> GSM425929 3 0.1964 0.942 0.056 0 0.944
#> GSM425930 3 0.0592 0.984 0.012 0 0.988
#> GSM425931 3 0.0000 0.993 0.000 0 1.000
#> GSM425932 3 0.0592 0.984 0.012 0 0.988
#> GSM425933 3 0.0000 0.993 0.000 0 1.000
#> GSM425934 3 0.1964 0.942 0.056 0 0.944
#> GSM425935 2 0.0000 1.000 0.000 1 0.000
#> GSM425936 3 0.0000 0.993 0.000 0 1.000
#> GSM425937 3 0.0000 0.993 0.000 0 1.000
#> GSM425938 3 0.0000 0.993 0.000 0 1.000
#> GSM425939 3 0.0592 0.984 0.012 0 0.988
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.0000 0.8959 0.000 1.000 0.000 0.000
#> GSM425908 2 0.0000 0.8959 0.000 1.000 0.000 0.000
#> GSM425909 3 0.4382 0.6919 0.000 0.000 0.704 0.296
#> GSM425910 1 0.0000 0.9191 1.000 0.000 0.000 0.000
#> GSM425911 4 0.2408 0.3359 0.000 0.000 0.104 0.896
#> GSM425912 1 0.0000 0.9191 1.000 0.000 0.000 0.000
#> GSM425913 3 0.3311 0.6887 0.000 0.000 0.828 0.172
#> GSM425914 1 0.0000 0.9191 1.000 0.000 0.000 0.000
#> GSM425915 4 0.0000 0.4345 0.000 0.000 0.000 1.000
#> GSM425874 2 0.0000 0.8959 0.000 1.000 0.000 0.000
#> GSM425875 1 0.3764 0.7086 0.784 0.000 0.000 0.216
#> GSM425876 1 0.0000 0.9191 1.000 0.000 0.000 0.000
#> GSM425877 1 0.0188 0.9161 0.996 0.000 0.000 0.004
#> GSM425878 1 0.4040 0.6637 0.752 0.000 0.000 0.248
#> GSM425879 4 0.4985 -0.4829 0.000 0.000 0.468 0.532
#> GSM425880 4 0.4761 0.2181 0.372 0.000 0.000 0.628
#> GSM425881 1 0.0000 0.9191 1.000 0.000 0.000 0.000
#> GSM425882 4 0.4985 -0.4829 0.000 0.000 0.468 0.532
#> GSM425883 4 0.6341 0.4289 0.212 0.000 0.136 0.652
#> GSM425884 1 0.0000 0.9191 1.000 0.000 0.000 0.000
#> GSM425885 2 0.0000 0.8959 0.000 1.000 0.000 0.000
#> GSM425848 3 0.4679 0.6661 0.000 0.000 0.648 0.352
#> GSM425849 1 0.4304 0.6054 0.716 0.000 0.000 0.284
#> GSM425850 4 0.5000 -0.1502 0.500 0.000 0.000 0.500
#> GSM425851 4 0.4989 -0.4879 0.000 0.000 0.472 0.528
#> GSM425852 4 0.0000 0.4345 0.000 0.000 0.000 1.000
#> GSM425893 4 0.4998 -0.5139 0.000 0.000 0.488 0.512
#> GSM425894 2 0.3873 0.8156 0.000 0.772 0.228 0.000
#> GSM425895 4 0.4992 -0.4982 0.000 0.000 0.476 0.524
#> GSM425896 2 0.0000 0.8959 0.000 1.000 0.000 0.000
#> GSM425897 3 0.2345 0.6604 0.000 0.000 0.900 0.100
#> GSM425898 3 0.4382 0.6919 0.000 0.000 0.704 0.296
#> GSM425899 4 0.2469 0.3297 0.000 0.000 0.108 0.892
#> GSM425900 4 0.5000 -0.1379 0.496 0.000 0.000 0.504
#> GSM425901 2 0.4761 0.6353 0.000 0.628 0.372 0.000
#> GSM425902 2 0.4624 0.6896 0.000 0.660 0.340 0.000
#> GSM425903 1 0.0000 0.9191 1.000 0.000 0.000 0.000
#> GSM425904 4 0.3688 0.4730 0.208 0.000 0.000 0.792
#> GSM425905 2 0.3688 0.8268 0.000 0.792 0.208 0.000
#> GSM425906 1 0.4996 0.1480 0.516 0.000 0.000 0.484
#> GSM425863 1 0.0000 0.9191 1.000 0.000 0.000 0.000
#> GSM425864 2 0.3907 0.8130 0.000 0.768 0.232 0.000
#> GSM425865 2 0.4624 0.6896 0.000 0.660 0.340 0.000
#> GSM425866 1 0.4981 0.2071 0.536 0.000 0.000 0.464
#> GSM425867 1 0.0000 0.9191 1.000 0.000 0.000 0.000
#> GSM425868 2 0.0000 0.8959 0.000 1.000 0.000 0.000
#> GSM425869 2 0.0000 0.8959 0.000 1.000 0.000 0.000
#> GSM425870 1 0.0000 0.9191 1.000 0.000 0.000 0.000
#> GSM425871 4 0.1474 0.4013 0.000 0.000 0.052 0.948
#> GSM425872 4 0.4998 -0.5139 0.000 0.000 0.488 0.512
#> GSM425873 1 0.0000 0.9191 1.000 0.000 0.000 0.000
#> GSM425843 1 0.0000 0.9191 1.000 0.000 0.000 0.000
#> GSM425844 3 0.4746 0.5609 0.000 0.000 0.632 0.368
#> GSM425845 1 0.0000 0.9191 1.000 0.000 0.000 0.000
#> GSM425846 4 0.2408 0.3427 0.000 0.000 0.104 0.896
#> GSM425847 1 0.0000 0.9191 1.000 0.000 0.000 0.000
#> GSM425886 3 0.4831 0.6869 0.000 0.016 0.704 0.280
#> GSM425887 4 0.4843 0.1669 0.396 0.000 0.000 0.604
#> GSM425888 1 0.0000 0.9191 1.000 0.000 0.000 0.000
#> GSM425889 4 0.3649 0.4735 0.204 0.000 0.000 0.796
#> GSM425890 2 0.0469 0.8914 0.000 0.988 0.012 0.000
#> GSM425891 4 0.4985 -0.4829 0.000 0.000 0.468 0.532
#> GSM425892 2 0.3688 0.8268 0.000 0.792 0.208 0.000
#> GSM425853 4 0.4999 -0.1257 0.492 0.000 0.000 0.508
#> GSM425854 3 0.4679 0.6661 0.000 0.000 0.648 0.352
#> GSM425855 1 0.0000 0.9191 1.000 0.000 0.000 0.000
#> GSM425856 4 0.0921 0.4485 0.028 0.000 0.000 0.972
#> GSM425857 2 0.0000 0.8959 0.000 1.000 0.000 0.000
#> GSM425858 1 0.3528 0.7373 0.808 0.000 0.000 0.192
#> GSM425859 2 0.0000 0.8959 0.000 1.000 0.000 0.000
#> GSM425860 1 0.0000 0.9191 1.000 0.000 0.000 0.000
#> GSM425861 1 0.0000 0.9191 1.000 0.000 0.000 0.000
#> GSM425862 4 0.4985 -0.4829 0.000 0.000 0.468 0.532
#> GSM425837 1 0.0000 0.9191 1.000 0.000 0.000 0.000
#> GSM425838 2 0.0000 0.8959 0.000 1.000 0.000 0.000
#> GSM425839 2 0.4072 0.7959 0.000 0.748 0.252 0.000
#> GSM425840 4 0.5000 -0.1502 0.500 0.000 0.000 0.500
#> GSM425841 2 0.0000 0.8959 0.000 1.000 0.000 0.000
#> GSM425842 1 0.0000 0.9191 1.000 0.000 0.000 0.000
#> GSM425917 3 0.3123 0.6831 0.000 0.000 0.844 0.156
#> GSM425922 2 0.0469 0.8914 0.000 0.988 0.012 0.000
#> GSM425919 1 0.0000 0.9191 1.000 0.000 0.000 0.000
#> GSM425920 4 0.4072 0.4537 0.252 0.000 0.000 0.748
#> GSM425923 4 0.3688 0.3814 0.000 0.000 0.208 0.792
#> GSM425916 4 0.6815 0.3027 0.284 0.000 0.136 0.580
#> GSM425918 3 0.4713 0.5300 0.000 0.000 0.640 0.360
#> GSM425921 2 0.0469 0.8914 0.000 0.988 0.012 0.000
#> GSM425925 4 0.1256 0.4480 0.028 0.000 0.008 0.964
#> GSM425926 2 0.3726 0.8245 0.000 0.788 0.212 0.000
#> GSM425927 1 0.0000 0.9191 1.000 0.000 0.000 0.000
#> GSM425924 3 0.4454 0.5874 0.000 0.000 0.692 0.308
#> GSM425928 2 0.1792 0.8797 0.000 0.932 0.068 0.000
#> GSM425929 4 0.4372 0.2965 0.004 0.000 0.268 0.728
#> GSM425930 4 0.4193 0.2929 0.000 0.000 0.268 0.732
#> GSM425931 3 0.4040 0.7057 0.000 0.000 0.752 0.248
#> GSM425932 4 0.4193 0.2929 0.000 0.000 0.268 0.732
#> GSM425933 3 0.4790 0.5551 0.000 0.000 0.620 0.380
#> GSM425934 4 0.4372 0.2965 0.004 0.000 0.268 0.728
#> GSM425935 3 0.4730 0.0473 0.000 0.364 0.636 0.000
#> GSM425936 3 0.3975 0.7078 0.000 0.000 0.760 0.240
#> GSM425937 3 0.4331 0.6785 0.000 0.000 0.712 0.288
#> GSM425938 3 0.4072 0.7123 0.000 0.000 0.748 0.252
#> GSM425939 4 0.4193 0.2929 0.000 0.000 0.268 0.732
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM425907 4 0.0671 0.76930 0.000 0.000 0.004 0.980 0.016
#> GSM425908 4 0.0451 0.77309 0.000 0.000 0.008 0.988 0.004
#> GSM425909 2 0.3752 0.15957 0.000 0.708 0.292 0.000 0.000
#> GSM425910 1 0.0703 0.88952 0.976 0.000 0.024 0.000 0.000
#> GSM425911 2 0.3999 0.22396 0.000 0.656 0.000 0.000 0.344
#> GSM425912 1 0.0290 0.89697 0.992 0.000 0.008 0.000 0.000
#> GSM425913 3 0.5818 0.29924 0.000 0.444 0.464 0.000 0.092
#> GSM425914 1 0.1082 0.88282 0.964 0.000 0.028 0.000 0.008
#> GSM425915 5 0.3816 0.52148 0.000 0.304 0.000 0.000 0.696
#> GSM425874 4 0.0162 0.77237 0.000 0.000 0.000 0.996 0.004
#> GSM425875 1 0.4924 0.18219 0.552 0.000 0.028 0.000 0.420
#> GSM425876 1 0.0290 0.89697 0.992 0.000 0.008 0.000 0.000
#> GSM425877 1 0.3193 0.75356 0.840 0.000 0.028 0.000 0.132
#> GSM425878 1 0.4948 0.12833 0.536 0.000 0.028 0.000 0.436
#> GSM425879 2 0.0703 0.48254 0.000 0.976 0.000 0.000 0.024
#> GSM425880 5 0.5870 0.61154 0.140 0.176 0.024 0.000 0.660
#> GSM425881 1 0.0290 0.89697 0.992 0.000 0.008 0.000 0.000
#> GSM425882 2 0.0703 0.48254 0.000 0.976 0.000 0.000 0.024
#> GSM425883 5 0.6549 0.46240 0.072 0.080 0.260 0.000 0.588
#> GSM425884 1 0.0290 0.89697 0.992 0.000 0.008 0.000 0.000
#> GSM425885 4 0.0671 0.76930 0.000 0.000 0.004 0.980 0.016
#> GSM425848 2 0.2471 0.35719 0.000 0.864 0.136 0.000 0.000
#> GSM425849 1 0.4961 0.08382 0.524 0.000 0.028 0.000 0.448
#> GSM425850 5 0.4456 0.49531 0.320 0.000 0.020 0.000 0.660
#> GSM425851 2 0.0703 0.48254 0.000 0.976 0.000 0.000 0.024
#> GSM425852 5 0.3913 0.50525 0.000 0.324 0.000 0.000 0.676
#> GSM425893 2 0.0703 0.48254 0.000 0.976 0.000 0.000 0.024
#> GSM425894 4 0.5484 0.57569 0.000 0.080 0.336 0.584 0.000
#> GSM425895 2 0.0703 0.48254 0.000 0.976 0.000 0.000 0.024
#> GSM425896 4 0.0451 0.77309 0.000 0.000 0.008 0.988 0.004
#> GSM425897 3 0.5313 0.34447 0.000 0.388 0.556 0.000 0.056
#> GSM425898 2 0.3661 0.18086 0.000 0.724 0.276 0.000 0.000
#> GSM425899 2 0.4030 0.20760 0.000 0.648 0.000 0.000 0.352
#> GSM425900 5 0.4456 0.49531 0.320 0.000 0.020 0.000 0.660
#> GSM425901 4 0.6538 0.35366 0.000 0.208 0.340 0.452 0.000
#> GSM425902 4 0.6469 0.38850 0.000 0.196 0.336 0.468 0.000
#> GSM425903 1 0.0703 0.88952 0.976 0.000 0.024 0.000 0.000
#> GSM425904 5 0.4941 0.58521 0.064 0.240 0.004 0.000 0.692
#> GSM425905 4 0.5300 0.59355 0.000 0.068 0.328 0.604 0.000
#> GSM425906 5 0.4630 0.52711 0.300 0.008 0.020 0.000 0.672
#> GSM425863 1 0.0000 0.89610 1.000 0.000 0.000 0.000 0.000
#> GSM425864 4 0.5671 0.55649 0.000 0.096 0.336 0.568 0.000
#> GSM425865 4 0.6469 0.38850 0.000 0.196 0.336 0.468 0.000
#> GSM425866 5 0.4703 0.44322 0.340 0.000 0.028 0.000 0.632
#> GSM425867 1 0.0290 0.89697 0.992 0.000 0.008 0.000 0.000
#> GSM425868 4 0.1300 0.77153 0.000 0.000 0.016 0.956 0.028
#> GSM425869 4 0.0771 0.76922 0.000 0.000 0.004 0.976 0.020
#> GSM425870 1 0.0703 0.88952 0.976 0.000 0.024 0.000 0.000
#> GSM425871 2 0.4278 -0.08230 0.000 0.548 0.000 0.000 0.452
#> GSM425872 2 0.0703 0.48254 0.000 0.976 0.000 0.000 0.024
#> GSM425873 1 0.0290 0.89697 0.992 0.000 0.008 0.000 0.000
#> GSM425843 1 0.0290 0.89697 0.992 0.000 0.008 0.000 0.000
#> GSM425844 2 0.5759 -0.32379 0.000 0.520 0.388 0.000 0.092
#> GSM425845 1 0.0162 0.89538 0.996 0.000 0.004 0.000 0.000
#> GSM425846 2 0.4114 0.15089 0.000 0.624 0.000 0.000 0.376
#> GSM425847 1 0.0290 0.89697 0.992 0.000 0.008 0.000 0.000
#> GSM425886 2 0.4624 0.05146 0.000 0.636 0.340 0.024 0.000
#> GSM425887 5 0.5243 0.62598 0.208 0.104 0.004 0.000 0.684
#> GSM425888 1 0.0290 0.89697 0.992 0.000 0.008 0.000 0.000
#> GSM425889 5 0.4879 0.59307 0.076 0.228 0.000 0.000 0.696
#> GSM425890 4 0.1981 0.75359 0.000 0.000 0.028 0.924 0.048
#> GSM425891 2 0.0703 0.48254 0.000 0.976 0.000 0.000 0.024
#> GSM425892 4 0.5300 0.59355 0.000 0.068 0.328 0.604 0.000
#> GSM425853 5 0.5130 0.53237 0.292 0.028 0.024 0.000 0.656
#> GSM425854 2 0.2329 0.36450 0.000 0.876 0.124 0.000 0.000
#> GSM425855 1 0.1300 0.87715 0.956 0.000 0.028 0.000 0.016
#> GSM425856 5 0.3876 0.51365 0.000 0.316 0.000 0.000 0.684
#> GSM425857 4 0.0671 0.76930 0.000 0.000 0.004 0.980 0.016
#> GSM425858 1 0.4866 0.26204 0.580 0.000 0.028 0.000 0.392
#> GSM425859 4 0.0955 0.77215 0.000 0.000 0.028 0.968 0.004
#> GSM425860 1 0.0290 0.89697 0.992 0.000 0.008 0.000 0.000
#> GSM425861 1 0.0703 0.88952 0.976 0.000 0.024 0.000 0.000
#> GSM425862 2 0.0703 0.48254 0.000 0.976 0.000 0.000 0.024
#> GSM425837 1 0.0000 0.89610 1.000 0.000 0.000 0.000 0.000
#> GSM425838 4 0.0290 0.77239 0.000 0.000 0.000 0.992 0.008
#> GSM425839 4 0.6186 0.47419 0.000 0.152 0.336 0.512 0.000
#> GSM425840 5 0.4540 0.49136 0.320 0.000 0.024 0.000 0.656
#> GSM425841 4 0.0955 0.77215 0.000 0.000 0.028 0.968 0.004
#> GSM425842 1 0.0290 0.89697 0.992 0.000 0.008 0.000 0.000
#> GSM425917 3 0.5883 0.37778 0.000 0.388 0.508 0.000 0.104
#> GSM425922 4 0.1981 0.75359 0.000 0.000 0.028 0.924 0.048
#> GSM425919 1 0.0290 0.89450 0.992 0.000 0.008 0.000 0.000
#> GSM425920 5 0.5241 0.62495 0.152 0.148 0.004 0.000 0.696
#> GSM425923 5 0.6726 -0.10157 0.000 0.252 0.360 0.000 0.388
#> GSM425916 5 0.6505 0.47705 0.112 0.044 0.260 0.000 0.584
#> GSM425918 2 0.6095 -0.35374 0.000 0.460 0.416 0.000 0.124
#> GSM425921 4 0.1981 0.75359 0.000 0.000 0.028 0.924 0.048
#> GSM425925 5 0.4074 0.45688 0.000 0.364 0.000 0.000 0.636
#> GSM425926 4 0.5456 0.58268 0.000 0.080 0.328 0.592 0.000
#> GSM425927 1 0.0290 0.89697 0.992 0.000 0.008 0.000 0.000
#> GSM425924 2 0.5927 -0.39422 0.000 0.468 0.428 0.000 0.104
#> GSM425928 4 0.3339 0.73620 0.000 0.000 0.112 0.840 0.048
#> GSM425929 5 0.6141 0.23981 0.000 0.196 0.244 0.000 0.560
#> GSM425930 5 0.6141 0.23981 0.000 0.196 0.244 0.000 0.560
#> GSM425931 2 0.6418 -0.03426 0.000 0.472 0.344 0.000 0.184
#> GSM425932 5 0.6141 0.23981 0.000 0.196 0.244 0.000 0.560
#> GSM425933 2 0.6690 0.04446 0.000 0.432 0.300 0.000 0.268
#> GSM425934 5 0.6141 0.23981 0.000 0.196 0.244 0.000 0.560
#> GSM425935 3 0.7478 -0.10411 0.000 0.256 0.428 0.272 0.044
#> GSM425936 2 0.6418 -0.03426 0.000 0.472 0.344 0.000 0.184
#> GSM425937 2 0.6372 0.00544 0.000 0.492 0.324 0.000 0.184
#> GSM425938 2 0.6062 -0.03625 0.000 0.564 0.268 0.000 0.168
#> GSM425939 5 0.6141 0.23981 0.000 0.196 0.244 0.000 0.560
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 4 0.3795 0.9400 0.000 0.000 0.004 0.632 0.000 0.364
#> GSM425908 4 0.3899 0.9332 0.000 0.000 0.004 0.592 0.000 0.404
#> GSM425909 6 0.6938 0.0951 0.000 0.152 0.064 0.236 0.028 0.520
#> GSM425910 1 0.1818 0.9221 0.920 0.004 0.004 0.068 0.004 0.000
#> GSM425911 5 0.7057 -0.2891 0.000 0.292 0.064 0.236 0.404 0.004
#> GSM425912 1 0.0291 0.9448 0.992 0.000 0.004 0.004 0.000 0.000
#> GSM425913 2 0.2714 0.3495 0.000 0.848 0.136 0.004 0.012 0.000
#> GSM425914 1 0.2594 0.8951 0.884 0.004 0.004 0.068 0.040 0.000
#> GSM425915 5 0.0508 0.7037 0.000 0.004 0.012 0.000 0.984 0.000
#> GSM425874 4 0.3872 0.9381 0.000 0.000 0.004 0.604 0.000 0.392
#> GSM425875 5 0.4452 0.6100 0.220 0.004 0.004 0.064 0.708 0.000
#> GSM425876 1 0.0291 0.9448 0.992 0.000 0.004 0.004 0.000 0.000
#> GSM425877 1 0.5150 0.2555 0.552 0.004 0.004 0.068 0.372 0.000
#> GSM425878 5 0.4426 0.6137 0.216 0.004 0.004 0.064 0.712 0.000
#> GSM425879 2 0.8399 0.6222 0.000 0.372 0.144 0.236 0.132 0.116
#> GSM425880 5 0.0806 0.7127 0.008 0.000 0.000 0.020 0.972 0.000
#> GSM425881 1 0.0291 0.9448 0.992 0.000 0.004 0.004 0.000 0.000
#> GSM425882 2 0.8399 0.6222 0.000 0.372 0.144 0.236 0.132 0.116
#> GSM425883 5 0.4785 0.2917 0.004 0.452 0.032 0.004 0.508 0.000
#> GSM425884 1 0.0291 0.9448 0.992 0.000 0.004 0.004 0.000 0.000
#> GSM425885 4 0.3795 0.9400 0.000 0.000 0.004 0.632 0.000 0.364
#> GSM425848 2 0.8262 0.5115 0.000 0.352 0.084 0.236 0.096 0.232
#> GSM425849 5 0.4399 0.6171 0.212 0.004 0.004 0.064 0.716 0.000
#> GSM425850 5 0.2149 0.7025 0.104 0.000 0.004 0.004 0.888 0.000
#> GSM425851 2 0.8375 0.6223 0.000 0.376 0.144 0.236 0.128 0.116
#> GSM425852 5 0.0458 0.7018 0.000 0.000 0.016 0.000 0.984 0.000
#> GSM425893 2 0.8375 0.6223 0.000 0.376 0.144 0.236 0.128 0.116
#> GSM425894 6 0.0260 0.7164 0.000 0.000 0.000 0.008 0.000 0.992
#> GSM425895 2 0.8406 0.6155 0.000 0.372 0.136 0.236 0.128 0.128
#> GSM425896 4 0.3899 0.9332 0.000 0.000 0.004 0.592 0.000 0.404
#> GSM425897 2 0.5890 0.2153 0.000 0.588 0.128 0.044 0.000 0.240
#> GSM425898 6 0.6992 0.0754 0.000 0.160 0.064 0.236 0.028 0.512
#> GSM425899 5 0.7022 -0.2880 0.000 0.296 0.060 0.236 0.404 0.004
#> GSM425900 5 0.2604 0.7004 0.096 0.004 0.000 0.028 0.872 0.000
#> GSM425901 6 0.1409 0.7404 0.000 0.032 0.008 0.012 0.000 0.948
#> GSM425902 6 0.1409 0.7404 0.000 0.032 0.008 0.012 0.000 0.948
#> GSM425903 1 0.2125 0.9147 0.908 0.004 0.004 0.068 0.016 0.000
#> GSM425904 5 0.0405 0.7070 0.004 0.000 0.008 0.000 0.988 0.000
#> GSM425905 6 0.0363 0.7098 0.000 0.000 0.000 0.012 0.000 0.988
#> GSM425906 5 0.3018 0.6978 0.100 0.008 0.008 0.028 0.856 0.000
#> GSM425863 1 0.0363 0.9438 0.988 0.000 0.000 0.012 0.000 0.000
#> GSM425864 6 0.0405 0.7181 0.000 0.004 0.000 0.008 0.000 0.988
#> GSM425865 6 0.1151 0.7394 0.000 0.032 0.012 0.000 0.000 0.956
#> GSM425866 5 0.3355 0.6746 0.132 0.004 0.000 0.048 0.816 0.000
#> GSM425867 1 0.0291 0.9448 0.992 0.000 0.004 0.004 0.000 0.000
#> GSM425868 4 0.4936 0.9224 0.000 0.028 0.024 0.552 0.000 0.396
#> GSM425869 4 0.3911 0.9398 0.000 0.000 0.008 0.624 0.000 0.368
#> GSM425870 1 0.1818 0.9221 0.920 0.004 0.004 0.068 0.004 0.000
#> GSM425871 5 0.6488 -0.1535 0.000 0.280 0.036 0.216 0.468 0.000
#> GSM425872 2 0.8377 0.6200 0.000 0.376 0.144 0.236 0.124 0.120
#> GSM425873 1 0.0291 0.9448 0.992 0.000 0.004 0.004 0.000 0.000
#> GSM425843 1 0.0291 0.9448 0.992 0.000 0.004 0.004 0.000 0.000
#> GSM425844 2 0.2290 0.3813 0.000 0.892 0.084 0.004 0.020 0.000
#> GSM425845 1 0.1082 0.9367 0.956 0.000 0.004 0.040 0.000 0.000
#> GSM425846 5 0.6800 -0.2534 0.000 0.292 0.052 0.236 0.420 0.000
#> GSM425847 1 0.0291 0.9448 0.992 0.000 0.004 0.004 0.000 0.000
#> GSM425886 6 0.5793 0.3213 0.000 0.084 0.040 0.236 0.016 0.624
#> GSM425887 5 0.1049 0.7145 0.032 0.000 0.008 0.000 0.960 0.000
#> GSM425888 1 0.0000 0.9447 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425889 5 0.0665 0.7086 0.008 0.004 0.008 0.000 0.980 0.000
#> GSM425890 4 0.4889 0.9148 0.000 0.028 0.028 0.596 0.000 0.348
#> GSM425891 2 0.8399 0.6222 0.000 0.372 0.144 0.236 0.132 0.116
#> GSM425892 6 0.0363 0.7098 0.000 0.000 0.000 0.012 0.000 0.988
#> GSM425853 5 0.1500 0.7152 0.052 0.000 0.000 0.012 0.936 0.000
#> GSM425854 2 0.8231 0.5273 0.000 0.364 0.084 0.236 0.096 0.220
#> GSM425855 1 0.2973 0.8705 0.860 0.004 0.004 0.068 0.064 0.000
#> GSM425856 5 0.0260 0.7047 0.000 0.000 0.008 0.000 0.992 0.000
#> GSM425857 4 0.3795 0.9400 0.000 0.000 0.004 0.632 0.000 0.364
#> GSM425858 5 0.4628 0.5826 0.240 0.004 0.004 0.068 0.684 0.000
#> GSM425859 4 0.3955 0.9076 0.000 0.000 0.004 0.560 0.000 0.436
#> GSM425860 1 0.0291 0.9445 0.992 0.000 0.004 0.004 0.000 0.000
#> GSM425861 1 0.1818 0.9221 0.920 0.004 0.004 0.068 0.004 0.000
#> GSM425862 2 0.8399 0.6222 0.000 0.372 0.144 0.236 0.132 0.116
#> GSM425837 1 0.0547 0.9423 0.980 0.000 0.000 0.020 0.000 0.000
#> GSM425838 4 0.3862 0.9390 0.000 0.000 0.004 0.608 0.000 0.388
#> GSM425839 6 0.0508 0.7313 0.000 0.012 0.004 0.000 0.000 0.984
#> GSM425840 5 0.3126 0.6909 0.104 0.004 0.004 0.044 0.844 0.000
#> GSM425841 4 0.3950 0.9118 0.000 0.000 0.004 0.564 0.000 0.432
#> GSM425842 1 0.0291 0.9448 0.992 0.000 0.004 0.004 0.000 0.000
#> GSM425917 2 0.3100 0.3152 0.000 0.836 0.128 0.012 0.000 0.024
#> GSM425922 4 0.4956 0.9143 0.000 0.028 0.032 0.592 0.000 0.348
#> GSM425919 1 0.1152 0.9350 0.952 0.000 0.000 0.044 0.004 0.000
#> GSM425920 5 0.1138 0.7117 0.024 0.004 0.012 0.000 0.960 0.000
#> GSM425923 2 0.4108 0.2223 0.000 0.744 0.092 0.000 0.164 0.000
#> GSM425916 5 0.4992 0.3160 0.020 0.444 0.024 0.004 0.508 0.000
#> GSM425918 2 0.2494 0.3517 0.000 0.864 0.120 0.000 0.016 0.000
#> GSM425921 4 0.4956 0.9143 0.000 0.028 0.032 0.592 0.000 0.348
#> GSM425925 5 0.1777 0.6802 0.000 0.044 0.024 0.004 0.928 0.000
#> GSM425926 6 0.0260 0.7164 0.000 0.000 0.000 0.008 0.000 0.992
#> GSM425927 1 0.0291 0.9448 0.992 0.000 0.004 0.004 0.000 0.000
#> GSM425924 2 0.2723 0.3454 0.000 0.852 0.128 0.004 0.016 0.000
#> GSM425928 4 0.5105 0.8481 0.000 0.028 0.032 0.520 0.000 0.420
#> GSM425929 3 0.2980 0.8100 0.000 0.008 0.800 0.000 0.192 0.000
#> GSM425930 3 0.2980 0.8100 0.000 0.008 0.800 0.000 0.192 0.000
#> GSM425931 3 0.3148 0.7401 0.000 0.092 0.840 0.000 0.004 0.064
#> GSM425932 3 0.2948 0.8102 0.000 0.008 0.804 0.000 0.188 0.000
#> GSM425933 3 0.1863 0.7786 0.000 0.044 0.920 0.000 0.036 0.000
#> GSM425934 3 0.2980 0.8100 0.000 0.008 0.800 0.000 0.192 0.000
#> GSM425935 6 0.3542 0.6435 0.000 0.052 0.160 0.000 0.000 0.788
#> GSM425936 3 0.3148 0.7401 0.000 0.092 0.840 0.000 0.004 0.064
#> GSM425937 3 0.2763 0.7519 0.000 0.088 0.868 0.000 0.008 0.036
#> GSM425938 3 0.4610 0.5764 0.000 0.152 0.724 0.008 0.004 0.112
#> GSM425939 3 0.2980 0.8100 0.000 0.008 0.800 0.000 0.192 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 disease.state(p) tissue(p) other(p) k
#> ATC:kmeans 103 9.88e-01 9.19e-01 7.95e-01 2
#> ATC:kmeans 103 1.15e-03 6.16e-03 1.82e-01 3
#> ATC:kmeans 67 1.44e-03 3.95e-03 1.02e-01 4
#> ATC:kmeans 53 4.31e-01 6.96e-01 6.20e-01 5
#> ATC:kmeans 86 7.22e-14 1.51e-11 2.30e-06 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 103 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 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 0.997 0.998 0.5040 0.496 0.496
#> 3 3 0.971 0.945 0.975 0.1946 0.889 0.780
#> 4 4 0.878 0.902 0.951 0.0747 0.951 0.877
#> 5 5 0.900 0.883 0.953 0.0869 0.931 0.809
#> 6 6 0.875 0.861 0.932 0.0442 0.958 0.859
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 3
There is also optional best \(k\) = 2 3 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
#> GSM425907 2 0.0000 0.997 0.000 1.000
#> GSM425908 2 0.0000 0.997 0.000 1.000
#> GSM425909 2 0.0000 0.997 0.000 1.000
#> GSM425910 1 0.0000 1.000 1.000 0.000
#> GSM425911 1 0.0000 1.000 1.000 0.000
#> GSM425912 1 0.0000 1.000 1.000 0.000
#> GSM425913 2 0.0000 0.997 0.000 1.000
#> GSM425914 1 0.0000 1.000 1.000 0.000
#> GSM425915 1 0.0000 1.000 1.000 0.000
#> GSM425874 2 0.0000 0.997 0.000 1.000
#> GSM425875 1 0.0000 1.000 1.000 0.000
#> GSM425876 1 0.0000 1.000 1.000 0.000
#> GSM425877 1 0.0000 1.000 1.000 0.000
#> GSM425878 1 0.0000 1.000 1.000 0.000
#> GSM425879 2 0.0000 0.997 0.000 1.000
#> GSM425880 1 0.0000 1.000 1.000 0.000
#> GSM425881 1 0.0000 1.000 1.000 0.000
#> GSM425882 2 0.0000 0.997 0.000 1.000
#> GSM425883 1 0.0000 1.000 1.000 0.000
#> GSM425884 1 0.0000 1.000 1.000 0.000
#> GSM425885 2 0.0000 0.997 0.000 1.000
#> GSM425848 2 0.0000 0.997 0.000 1.000
#> GSM425849 1 0.0000 1.000 1.000 0.000
#> GSM425850 1 0.0000 1.000 1.000 0.000
#> GSM425851 2 0.0000 0.997 0.000 1.000
#> GSM425852 1 0.0000 1.000 1.000 0.000
#> GSM425893 2 0.0000 0.997 0.000 1.000
#> GSM425894 2 0.0000 0.997 0.000 1.000
#> GSM425895 2 0.0000 0.997 0.000 1.000
#> GSM425896 2 0.0000 0.997 0.000 1.000
#> GSM425897 2 0.0000 0.997 0.000 1.000
#> GSM425898 2 0.0000 0.997 0.000 1.000
#> GSM425899 1 0.0376 0.996 0.996 0.004
#> GSM425900 1 0.0000 1.000 1.000 0.000
#> GSM425901 2 0.0000 0.997 0.000 1.000
#> GSM425902 2 0.0000 0.997 0.000 1.000
#> GSM425903 1 0.0000 1.000 1.000 0.000
#> GSM425904 1 0.0000 1.000 1.000 0.000
#> GSM425905 2 0.0000 0.997 0.000 1.000
#> GSM425906 1 0.0000 1.000 1.000 0.000
#> GSM425863 1 0.0000 1.000 1.000 0.000
#> GSM425864 2 0.0000 0.997 0.000 1.000
#> GSM425865 2 0.0000 0.997 0.000 1.000
#> GSM425866 1 0.0000 1.000 1.000 0.000
#> GSM425867 1 0.0000 1.000 1.000 0.000
#> GSM425868 2 0.0000 0.997 0.000 1.000
#> GSM425869 2 0.0000 0.997 0.000 1.000
#> GSM425870 1 0.0000 1.000 1.000 0.000
#> GSM425871 1 0.0000 1.000 1.000 0.000
#> GSM425872 2 0.0000 0.997 0.000 1.000
#> GSM425873 1 0.0000 1.000 1.000 0.000
#> GSM425843 1 0.0000 1.000 1.000 0.000
#> GSM425844 2 0.0000 0.997 0.000 1.000
#> GSM425845 1 0.0000 1.000 1.000 0.000
#> GSM425846 1 0.0000 1.000 1.000 0.000
#> GSM425847 1 0.0000 1.000 1.000 0.000
#> GSM425886 2 0.0000 0.997 0.000 1.000
#> GSM425887 1 0.0000 1.000 1.000 0.000
#> GSM425888 1 0.0000 1.000 1.000 0.000
#> GSM425889 1 0.0000 1.000 1.000 0.000
#> GSM425890 2 0.0000 0.997 0.000 1.000
#> GSM425891 2 0.0000 0.997 0.000 1.000
#> GSM425892 2 0.0000 0.997 0.000 1.000
#> GSM425853 1 0.0000 1.000 1.000 0.000
#> GSM425854 2 0.0000 0.997 0.000 1.000
#> GSM425855 1 0.0000 1.000 1.000 0.000
#> GSM425856 1 0.0000 1.000 1.000 0.000
#> GSM425857 2 0.0000 0.997 0.000 1.000
#> GSM425858 1 0.0000 1.000 1.000 0.000
#> GSM425859 2 0.0000 0.997 0.000 1.000
#> GSM425860 1 0.0000 1.000 1.000 0.000
#> GSM425861 1 0.0000 1.000 1.000 0.000
#> GSM425862 2 0.0000 0.997 0.000 1.000
#> GSM425837 1 0.0000 1.000 1.000 0.000
#> GSM425838 2 0.0000 0.997 0.000 1.000
#> GSM425839 2 0.0000 0.997 0.000 1.000
#> GSM425840 1 0.0000 1.000 1.000 0.000
#> GSM425841 2 0.0000 0.997 0.000 1.000
#> GSM425842 1 0.0000 1.000 1.000 0.000
#> GSM425917 2 0.0000 0.997 0.000 1.000
#> GSM425922 2 0.0000 0.997 0.000 1.000
#> GSM425919 1 0.0000 1.000 1.000 0.000
#> GSM425920 1 0.0000 1.000 1.000 0.000
#> GSM425923 1 0.0000 1.000 1.000 0.000
#> GSM425916 1 0.0000 1.000 1.000 0.000
#> GSM425918 2 0.6247 0.815 0.156 0.844
#> GSM425921 2 0.0000 0.997 0.000 1.000
#> GSM425925 1 0.0000 1.000 1.000 0.000
#> GSM425926 2 0.0000 0.997 0.000 1.000
#> GSM425927 1 0.0000 1.000 1.000 0.000
#> GSM425924 2 0.0000 0.997 0.000 1.000
#> GSM425928 2 0.0000 0.997 0.000 1.000
#> GSM425929 1 0.0000 1.000 1.000 0.000
#> GSM425930 1 0.0000 1.000 1.000 0.000
#> GSM425931 2 0.0000 0.997 0.000 1.000
#> GSM425932 1 0.0000 1.000 1.000 0.000
#> GSM425933 2 0.0000 0.997 0.000 1.000
#> GSM425934 1 0.0000 1.000 1.000 0.000
#> GSM425935 2 0.0000 0.997 0.000 1.000
#> GSM425936 2 0.0000 0.997 0.000 1.000
#> GSM425937 2 0.0000 0.997 0.000 1.000
#> GSM425938 2 0.0000 0.997 0.000 1.000
#> GSM425939 1 0.0000 1.000 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425908 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425909 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425910 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425911 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425912 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425913 2 0.5650 0.561 0.000 0.688 0.312
#> GSM425914 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425915 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425874 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425875 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425876 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425877 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425878 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425879 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425880 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425881 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425882 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425883 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425884 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425885 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425848 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425849 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425850 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425851 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425852 1 0.0237 0.992 0.996 0.000 0.004
#> GSM425893 2 0.1411 0.938 0.000 0.964 0.036
#> GSM425894 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425895 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425896 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425897 2 0.1529 0.934 0.000 0.960 0.040
#> GSM425898 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425899 1 0.3482 0.818 0.872 0.128 0.000
#> GSM425900 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425901 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425902 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425903 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425904 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425905 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425906 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425863 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425864 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425865 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425866 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425867 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425868 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425869 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425870 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425871 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425872 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425873 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425843 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425844 2 0.4750 0.725 0.000 0.784 0.216
#> GSM425845 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425846 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425847 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425886 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425887 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425888 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425889 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425890 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425891 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425892 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425853 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425854 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425855 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425856 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425857 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425858 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425859 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425860 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425861 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425862 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425837 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425838 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425839 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425840 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425841 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425842 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425917 2 0.5650 0.561 0.000 0.688 0.312
#> GSM425922 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425919 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425920 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425923 3 0.6062 0.403 0.384 0.000 0.616
#> GSM425916 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425918 3 0.1643 0.891 0.000 0.044 0.956
#> GSM425921 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425925 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425926 2 0.0000 0.965 0.000 1.000 0.000
#> GSM425927 1 0.0000 0.996 1.000 0.000 0.000
#> GSM425924 3 0.1643 0.891 0.000 0.044 0.956
#> GSM425928 2 0.1411 0.938 0.000 0.964 0.036
#> GSM425929 3 0.1529 0.909 0.040 0.000 0.960
#> GSM425930 3 0.1529 0.909 0.040 0.000 0.960
#> GSM425931 3 0.4002 0.784 0.000 0.160 0.840
#> GSM425932 3 0.1529 0.909 0.040 0.000 0.960
#> GSM425933 3 0.0000 0.900 0.000 0.000 1.000
#> GSM425934 3 0.1529 0.909 0.040 0.000 0.960
#> GSM425935 2 0.0747 0.953 0.000 0.984 0.016
#> GSM425936 3 0.3941 0.789 0.000 0.156 0.844
#> GSM425937 3 0.0000 0.900 0.000 0.000 1.000
#> GSM425938 2 0.6260 0.216 0.000 0.552 0.448
#> GSM425939 3 0.1529 0.909 0.040 0.000 0.960
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425908 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425909 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425910 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425911 1 0.4050 0.771 0.808 0.000 0.024 0.168
#> GSM425912 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425913 4 0.3448 0.717 0.000 0.168 0.004 0.828
#> GSM425914 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425915 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425874 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425875 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425876 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425877 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425878 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425879 2 0.3355 0.828 0.000 0.836 0.004 0.160
#> GSM425880 1 0.0188 0.971 0.996 0.000 0.000 0.004
#> GSM425881 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425882 2 0.3402 0.824 0.000 0.832 0.004 0.164
#> GSM425883 4 0.4543 0.535 0.324 0.000 0.000 0.676
#> GSM425884 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425885 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425848 2 0.3355 0.828 0.000 0.836 0.004 0.160
#> GSM425849 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425850 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425851 2 0.2408 0.879 0.000 0.896 0.000 0.104
#> GSM425852 1 0.3577 0.792 0.832 0.000 0.156 0.012
#> GSM425893 2 0.0524 0.944 0.000 0.988 0.004 0.008
#> GSM425894 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425895 2 0.2401 0.887 0.000 0.904 0.004 0.092
#> GSM425896 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425897 2 0.4088 0.660 0.000 0.764 0.004 0.232
#> GSM425898 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425899 1 0.5891 0.631 0.724 0.088 0.016 0.172
#> GSM425900 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425901 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425902 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425903 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425904 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425905 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425906 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425863 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425864 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425865 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425866 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425867 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425868 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425869 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425870 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425871 1 0.3547 0.812 0.840 0.000 0.016 0.144
#> GSM425872 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425873 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425843 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425844 4 0.3448 0.717 0.000 0.168 0.004 0.828
#> GSM425845 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425846 1 0.3925 0.770 0.808 0.000 0.016 0.176
#> GSM425847 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425886 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425887 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425888 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425889 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425890 2 0.0336 0.945 0.000 0.992 0.000 0.008
#> GSM425891 2 0.3355 0.828 0.000 0.836 0.004 0.160
#> GSM425892 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425853 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425854 2 0.3355 0.828 0.000 0.836 0.004 0.160
#> GSM425855 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425856 1 0.0937 0.954 0.976 0.000 0.012 0.012
#> GSM425857 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425858 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425859 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425860 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425861 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425862 2 0.2149 0.893 0.000 0.912 0.000 0.088
#> GSM425837 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425838 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425839 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425840 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425841 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425842 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425917 4 0.3494 0.713 0.000 0.172 0.004 0.824
#> GSM425922 2 0.0336 0.945 0.000 0.992 0.000 0.008
#> GSM425919 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425920 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425923 4 0.3907 0.656 0.140 0.000 0.032 0.828
#> GSM425916 4 0.4522 0.539 0.320 0.000 0.000 0.680
#> GSM425918 4 0.4168 0.696 0.000 0.080 0.092 0.828
#> GSM425921 2 0.0336 0.945 0.000 0.992 0.000 0.008
#> GSM425925 1 0.1297 0.944 0.964 0.000 0.016 0.020
#> GSM425926 2 0.0000 0.949 0.000 1.000 0.000 0.000
#> GSM425927 1 0.0000 0.974 1.000 0.000 0.000 0.000
#> GSM425924 4 0.4168 0.695 0.000 0.080 0.092 0.828
#> GSM425928 2 0.0524 0.943 0.000 0.988 0.004 0.008
#> GSM425929 3 0.0707 0.908 0.020 0.000 0.980 0.000
#> GSM425930 3 0.0707 0.908 0.020 0.000 0.980 0.000
#> GSM425931 3 0.3528 0.685 0.000 0.192 0.808 0.000
#> GSM425932 3 0.0707 0.908 0.020 0.000 0.980 0.000
#> GSM425933 3 0.0657 0.897 0.000 0.004 0.984 0.012
#> GSM425934 3 0.0707 0.908 0.020 0.000 0.980 0.000
#> GSM425935 2 0.0188 0.947 0.000 0.996 0.004 0.000
#> GSM425936 3 0.3808 0.705 0.000 0.176 0.812 0.012
#> GSM425937 3 0.0657 0.897 0.000 0.004 0.984 0.012
#> GSM425938 2 0.5339 0.301 0.000 0.600 0.384 0.016
#> GSM425939 3 0.0707 0.908 0.020 0.000 0.980 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM425907 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425908 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425909 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425910 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425911 5 0.0794 0.66048 0.028 0.000 0.000 0.000 0.972
#> GSM425912 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425913 4 0.0324 0.87961 0.000 0.004 0.000 0.992 0.004
#> GSM425914 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425915 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425874 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425875 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425876 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425877 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425878 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425879 5 0.2690 0.74282 0.000 0.156 0.000 0.000 0.844
#> GSM425880 1 0.1043 0.94076 0.960 0.000 0.000 0.000 0.040
#> GSM425881 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425882 5 0.3210 0.73284 0.000 0.212 0.000 0.000 0.788
#> GSM425883 4 0.3461 0.65142 0.224 0.000 0.000 0.772 0.004
#> GSM425884 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425885 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425848 5 0.3586 0.67364 0.000 0.264 0.000 0.000 0.736
#> GSM425849 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425850 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425851 2 0.3885 0.56798 0.000 0.724 0.000 0.008 0.268
#> GSM425852 1 0.5915 0.38889 0.584 0.000 0.264 0.000 0.152
#> GSM425893 2 0.1357 0.90497 0.000 0.948 0.004 0.000 0.048
#> GSM425894 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425895 2 0.4287 0.00355 0.000 0.540 0.000 0.000 0.460
#> GSM425896 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425897 2 0.2583 0.81227 0.000 0.864 0.000 0.132 0.004
#> GSM425898 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425899 5 0.0162 0.67192 0.004 0.000 0.000 0.000 0.996
#> GSM425900 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425901 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425902 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425903 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425904 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425905 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425906 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425863 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425864 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425865 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425866 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425867 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425868 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425869 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425870 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425871 5 0.4367 0.15612 0.416 0.000 0.000 0.004 0.580
#> GSM425872 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425873 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425843 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425844 4 0.0000 0.88158 0.000 0.000 0.000 1.000 0.000
#> GSM425845 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425846 5 0.0162 0.67192 0.004 0.000 0.000 0.000 0.996
#> GSM425847 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425886 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425887 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425888 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425889 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425890 2 0.0404 0.93917 0.000 0.988 0.000 0.012 0.000
#> GSM425891 5 0.3039 0.74318 0.000 0.192 0.000 0.000 0.808
#> GSM425892 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425853 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425854 5 0.3143 0.73872 0.000 0.204 0.000 0.000 0.796
#> GSM425855 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425856 1 0.2732 0.80860 0.840 0.000 0.000 0.000 0.160
#> GSM425857 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425858 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425859 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425860 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425861 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425862 2 0.3983 0.41497 0.000 0.660 0.000 0.000 0.340
#> GSM425837 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425838 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425839 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425840 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425841 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425842 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425917 4 0.0324 0.87961 0.000 0.004 0.000 0.992 0.004
#> GSM425922 2 0.0404 0.93917 0.000 0.988 0.000 0.012 0.000
#> GSM425919 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425920 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425923 4 0.0162 0.88003 0.000 0.000 0.000 0.996 0.004
#> GSM425916 4 0.3491 0.64561 0.228 0.000 0.000 0.768 0.004
#> GSM425918 4 0.0000 0.88158 0.000 0.000 0.000 1.000 0.000
#> GSM425921 2 0.0404 0.93917 0.000 0.988 0.000 0.012 0.000
#> GSM425925 1 0.3730 0.61481 0.712 0.000 0.000 0.000 0.288
#> GSM425926 2 0.0000 0.94702 0.000 1.000 0.000 0.000 0.000
#> GSM425927 1 0.0000 0.97742 1.000 0.000 0.000 0.000 0.000
#> GSM425924 4 0.0162 0.88113 0.000 0.000 0.000 0.996 0.004
#> GSM425928 2 0.0566 0.93635 0.000 0.984 0.000 0.012 0.004
#> GSM425929 3 0.0162 0.92003 0.004 0.000 0.996 0.000 0.000
#> GSM425930 3 0.0162 0.92003 0.004 0.000 0.996 0.000 0.000
#> GSM425931 3 0.3123 0.71052 0.000 0.184 0.812 0.000 0.004
#> GSM425932 3 0.0000 0.91915 0.000 0.000 1.000 0.000 0.000
#> GSM425933 3 0.0000 0.91915 0.000 0.000 1.000 0.000 0.000
#> GSM425934 3 0.0162 0.92003 0.004 0.000 0.996 0.000 0.000
#> GSM425935 2 0.0162 0.94438 0.000 0.996 0.000 0.000 0.004
#> GSM425936 3 0.3086 0.71732 0.000 0.180 0.816 0.000 0.004
#> GSM425937 3 0.0162 0.91800 0.000 0.000 0.996 0.000 0.004
#> GSM425938 2 0.3706 0.65839 0.000 0.756 0.236 0.004 0.004
#> GSM425939 3 0.0162 0.92003 0.004 0.000 0.996 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 2 0.0000 0.935 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425908 2 0.0000 0.935 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425909 2 0.0000 0.935 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425910 1 0.0000 0.988 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425911 5 0.2814 0.399 0.008 0.000 0.000 0.172 0.820 0.000
#> GSM425912 1 0.0000 0.988 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425913 6 0.1421 0.855 0.000 0.000 0.000 0.028 0.028 0.944
#> GSM425914 1 0.0000 0.988 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425915 1 0.1267 0.923 0.940 0.000 0.000 0.000 0.060 0.000
#> GSM425874 2 0.0000 0.935 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425875 1 0.0000 0.988 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425876 1 0.0000 0.988 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425877 1 0.0146 0.987 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM425878 1 0.0260 0.984 0.992 0.000 0.000 0.000 0.008 0.000
#> GSM425879 4 0.2201 0.728 0.000 0.052 0.000 0.900 0.048 0.000
#> GSM425880 1 0.2378 0.797 0.848 0.000 0.000 0.000 0.152 0.000
#> GSM425881 1 0.0146 0.987 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM425882 4 0.2672 0.712 0.000 0.052 0.000 0.868 0.080 0.000
#> GSM425883 6 0.2762 0.615 0.196 0.000 0.000 0.000 0.000 0.804
#> GSM425884 1 0.0146 0.987 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM425885 2 0.0000 0.935 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425848 4 0.2003 0.749 0.000 0.116 0.000 0.884 0.000 0.000
#> GSM425849 1 0.0146 0.987 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM425850 1 0.0000 0.988 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425851 2 0.5794 -0.259 0.000 0.460 0.000 0.392 0.140 0.008
#> GSM425852 5 0.5084 0.542 0.264 0.000 0.124 0.000 0.612 0.000
#> GSM425893 2 0.4530 0.579 0.000 0.692 0.000 0.208 0.100 0.000
#> GSM425894 2 0.0000 0.935 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425895 4 0.3330 0.606 0.000 0.284 0.000 0.716 0.000 0.000
#> GSM425896 2 0.0000 0.935 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425897 2 0.2969 0.818 0.000 0.860 0.000 0.032 0.020 0.088
#> GSM425898 2 0.0260 0.930 0.000 0.992 0.000 0.008 0.000 0.000
#> GSM425899 4 0.3464 0.362 0.000 0.000 0.000 0.688 0.312 0.000
#> GSM425900 1 0.0000 0.988 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425901 2 0.0000 0.935 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425902 2 0.0000 0.935 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425903 1 0.0000 0.988 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425904 1 0.1663 0.887 0.912 0.000 0.000 0.000 0.088 0.000
#> GSM425905 2 0.0000 0.935 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425906 1 0.0000 0.988 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425863 1 0.0000 0.988 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425864 2 0.0000 0.935 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425865 2 0.0000 0.935 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425866 1 0.0000 0.988 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425867 1 0.0000 0.988 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425868 2 0.0458 0.926 0.000 0.984 0.000 0.016 0.000 0.000
#> GSM425869 2 0.0000 0.935 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425870 1 0.0000 0.988 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425871 5 0.4877 0.544 0.124 0.000 0.000 0.188 0.680 0.008
#> GSM425872 2 0.3602 0.739 0.000 0.792 0.000 0.136 0.072 0.000
#> GSM425873 1 0.0000 0.988 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425843 1 0.0146 0.987 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM425844 6 0.0000 0.865 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM425845 1 0.0146 0.987 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM425846 5 0.3659 0.238 0.000 0.000 0.000 0.364 0.636 0.000
#> GSM425847 1 0.0000 0.988 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425886 2 0.0000 0.935 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425887 1 0.0146 0.987 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM425888 1 0.0000 0.988 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425889 1 0.0000 0.988 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425890 2 0.0717 0.921 0.000 0.976 0.000 0.016 0.008 0.000
#> GSM425891 4 0.3321 0.726 0.000 0.080 0.000 0.820 0.100 0.000
#> GSM425892 2 0.0000 0.935 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425853 1 0.0458 0.976 0.984 0.000 0.000 0.000 0.016 0.000
#> GSM425854 4 0.2039 0.751 0.000 0.076 0.000 0.904 0.020 0.000
#> GSM425855 1 0.0000 0.988 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425856 5 0.3531 0.556 0.328 0.000 0.000 0.000 0.672 0.000
#> GSM425857 2 0.0000 0.935 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425858 1 0.0146 0.987 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM425859 2 0.0000 0.935 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425860 1 0.0000 0.988 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425861 1 0.0146 0.987 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM425862 4 0.5104 0.538 0.000 0.304 0.000 0.588 0.108 0.000
#> GSM425837 1 0.0146 0.987 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM425838 2 0.0000 0.935 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425839 2 0.0000 0.935 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425840 1 0.0146 0.987 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM425841 2 0.0000 0.935 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425842 1 0.0000 0.988 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425917 6 0.1421 0.855 0.000 0.000 0.000 0.028 0.028 0.944
#> GSM425922 2 0.0717 0.921 0.000 0.976 0.000 0.016 0.008 0.000
#> GSM425919 1 0.0000 0.988 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425920 1 0.0000 0.988 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425923 6 0.0000 0.865 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM425916 6 0.2854 0.590 0.208 0.000 0.000 0.000 0.000 0.792
#> GSM425918 6 0.0000 0.865 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM425921 2 0.0717 0.921 0.000 0.976 0.000 0.016 0.008 0.000
#> GSM425925 5 0.4473 0.601 0.252 0.000 0.000 0.072 0.676 0.000
#> GSM425926 2 0.0000 0.935 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425927 1 0.0146 0.987 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM425924 6 0.0909 0.862 0.000 0.000 0.000 0.012 0.020 0.968
#> GSM425928 2 0.1498 0.896 0.000 0.940 0.000 0.032 0.028 0.000
#> GSM425929 3 0.0000 0.912 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425930 3 0.0000 0.912 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425931 3 0.4503 0.744 0.000 0.116 0.756 0.044 0.084 0.000
#> GSM425932 3 0.0000 0.912 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425933 3 0.0146 0.911 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM425934 3 0.0000 0.912 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425935 2 0.2846 0.816 0.000 0.856 0.000 0.060 0.084 0.000
#> GSM425936 3 0.4470 0.755 0.000 0.104 0.760 0.044 0.092 0.000
#> GSM425937 3 0.2595 0.851 0.000 0.000 0.872 0.044 0.084 0.000
#> GSM425938 2 0.5887 0.401 0.000 0.588 0.256 0.060 0.096 0.000
#> GSM425939 3 0.0000 0.912 0.000 0.000 1.000 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 disease.state(p) tissue(p) other(p) k
#> ATC:skmeans 103 6.27e-01 7.00e-01 8.46e-01 2
#> ATC:skmeans 101 9.80e-15 6.60e-14 3.83e-09 3
#> ATC:skmeans 102 9.96e-18 5.60e-20 4.64e-11 4
#> ATC:skmeans 99 4.35e-15 7.05e-17 8.12e-08 5
#> ATC:skmeans 98 1.22e-15 4.09e-17 3.28e-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["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 103 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 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 0.960 0.949 0.977 0.4521 0.541 0.541
#> 3 3 0.986 0.955 0.982 0.4340 0.760 0.576
#> 4 4 0.830 0.686 0.848 0.1156 0.934 0.815
#> 5 5 0.838 0.858 0.922 0.0638 0.928 0.762
#> 6 6 0.838 0.739 0.871 0.0592 0.947 0.778
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
#> GSM425907 2 0.000 0.952 0.000 1.000
#> GSM425908 2 0.000 0.952 0.000 1.000
#> GSM425909 2 0.224 0.932 0.036 0.964
#> GSM425910 1 0.000 0.988 1.000 0.000
#> GSM425911 1 0.000 0.988 1.000 0.000
#> GSM425912 1 0.000 0.988 1.000 0.000
#> GSM425913 1 0.925 0.455 0.660 0.340
#> GSM425914 1 0.000 0.988 1.000 0.000
#> GSM425915 1 0.000 0.988 1.000 0.000
#> GSM425874 2 0.000 0.952 0.000 1.000
#> GSM425875 1 0.000 0.988 1.000 0.000
#> GSM425876 1 0.000 0.988 1.000 0.000
#> GSM425877 1 0.000 0.988 1.000 0.000
#> GSM425878 1 0.000 0.988 1.000 0.000
#> GSM425879 1 0.141 0.974 0.980 0.020
#> GSM425880 1 0.000 0.988 1.000 0.000
#> GSM425881 1 0.000 0.988 1.000 0.000
#> GSM425882 1 0.163 0.970 0.976 0.024
#> GSM425883 1 0.000 0.988 1.000 0.000
#> GSM425884 1 0.000 0.988 1.000 0.000
#> GSM425885 2 0.000 0.952 0.000 1.000
#> GSM425848 2 0.886 0.603 0.304 0.696
#> GSM425849 1 0.000 0.988 1.000 0.000
#> GSM425850 1 0.000 0.988 1.000 0.000
#> GSM425851 1 0.653 0.790 0.832 0.168
#> GSM425852 1 0.000 0.988 1.000 0.000
#> GSM425893 1 0.163 0.970 0.976 0.024
#> GSM425894 2 0.000 0.952 0.000 1.000
#> GSM425895 1 0.141 0.974 0.980 0.020
#> GSM425896 2 0.000 0.952 0.000 1.000
#> GSM425897 2 0.327 0.914 0.060 0.940
#> GSM425898 2 0.224 0.932 0.036 0.964
#> GSM425899 1 0.000 0.988 1.000 0.000
#> GSM425900 1 0.000 0.988 1.000 0.000
#> GSM425901 2 0.000 0.952 0.000 1.000
#> GSM425902 2 0.000 0.952 0.000 1.000
#> GSM425903 1 0.000 0.988 1.000 0.000
#> GSM425904 1 0.000 0.988 1.000 0.000
#> GSM425905 2 0.000 0.952 0.000 1.000
#> GSM425906 1 0.000 0.988 1.000 0.000
#> GSM425863 1 0.000 0.988 1.000 0.000
#> GSM425864 2 0.000 0.952 0.000 1.000
#> GSM425865 2 0.000 0.952 0.000 1.000
#> GSM425866 1 0.000 0.988 1.000 0.000
#> GSM425867 1 0.000 0.988 1.000 0.000
#> GSM425868 2 0.000 0.952 0.000 1.000
#> GSM425869 2 0.000 0.952 0.000 1.000
#> GSM425870 1 0.000 0.988 1.000 0.000
#> GSM425871 1 0.000 0.988 1.000 0.000
#> GSM425872 1 0.163 0.970 0.976 0.024
#> GSM425873 1 0.000 0.988 1.000 0.000
#> GSM425843 1 0.000 0.988 1.000 0.000
#> GSM425844 1 0.141 0.974 0.980 0.020
#> GSM425845 1 0.000 0.988 1.000 0.000
#> GSM425846 1 0.000 0.988 1.000 0.000
#> GSM425847 1 0.000 0.988 1.000 0.000
#> GSM425886 2 0.000 0.952 0.000 1.000
#> GSM425887 1 0.000 0.988 1.000 0.000
#> GSM425888 1 0.000 0.988 1.000 0.000
#> GSM425889 1 0.000 0.988 1.000 0.000
#> GSM425890 2 0.000 0.952 0.000 1.000
#> GSM425891 1 0.141 0.974 0.980 0.020
#> GSM425892 2 0.000 0.952 0.000 1.000
#> GSM425853 1 0.000 0.988 1.000 0.000
#> GSM425854 2 0.680 0.792 0.180 0.820
#> GSM425855 1 0.000 0.988 1.000 0.000
#> GSM425856 1 0.000 0.988 1.000 0.000
#> GSM425857 2 0.000 0.952 0.000 1.000
#> GSM425858 1 0.000 0.988 1.000 0.000
#> GSM425859 2 0.000 0.952 0.000 1.000
#> GSM425860 1 0.000 0.988 1.000 0.000
#> GSM425861 1 0.000 0.988 1.000 0.000
#> GSM425862 1 0.141 0.974 0.980 0.020
#> GSM425837 1 0.000 0.988 1.000 0.000
#> GSM425838 2 0.000 0.952 0.000 1.000
#> GSM425839 2 0.000 0.952 0.000 1.000
#> GSM425840 1 0.000 0.988 1.000 0.000
#> GSM425841 2 0.000 0.952 0.000 1.000
#> GSM425842 1 0.000 0.988 1.000 0.000
#> GSM425917 2 0.224 0.932 0.036 0.964
#> GSM425922 2 0.000 0.952 0.000 1.000
#> GSM425919 1 0.000 0.988 1.000 0.000
#> GSM425920 1 0.000 0.988 1.000 0.000
#> GSM425923 1 0.000 0.988 1.000 0.000
#> GSM425916 1 0.000 0.988 1.000 0.000
#> GSM425918 1 0.000 0.988 1.000 0.000
#> GSM425921 2 0.000 0.952 0.000 1.000
#> GSM425925 1 0.000 0.988 1.000 0.000
#> GSM425926 2 0.000 0.952 0.000 1.000
#> GSM425927 1 0.000 0.988 1.000 0.000
#> GSM425924 1 0.141 0.974 0.980 0.020
#> GSM425928 2 0.000 0.952 0.000 1.000
#> GSM425929 1 0.000 0.988 1.000 0.000
#> GSM425930 1 0.000 0.988 1.000 0.000
#> GSM425931 2 0.833 0.672 0.264 0.736
#> GSM425932 1 0.000 0.988 1.000 0.000
#> GSM425933 1 0.141 0.974 0.980 0.020
#> GSM425934 1 0.000 0.988 1.000 0.000
#> GSM425935 2 0.000 0.952 0.000 1.000
#> GSM425936 2 0.644 0.813 0.164 0.836
#> GSM425937 2 0.994 0.214 0.456 0.544
#> GSM425938 2 0.552 0.853 0.128 0.872
#> GSM425939 1 0.000 0.988 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425908 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425909 2 0.1529 0.9346 0.000 0.960 0.040
#> GSM425910 1 0.0000 0.9918 1.000 0.000 0.000
#> GSM425911 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425912 1 0.0000 0.9918 1.000 0.000 0.000
#> GSM425913 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425914 1 0.0000 0.9918 1.000 0.000 0.000
#> GSM425915 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425874 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425875 3 0.0424 0.9765 0.008 0.000 0.992
#> GSM425876 1 0.0000 0.9918 1.000 0.000 0.000
#> GSM425877 1 0.0000 0.9918 1.000 0.000 0.000
#> GSM425878 3 0.0237 0.9798 0.004 0.000 0.996
#> GSM425879 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425880 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425881 1 0.0000 0.9918 1.000 0.000 0.000
#> GSM425882 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425883 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425884 1 0.0000 0.9918 1.000 0.000 0.000
#> GSM425885 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425848 3 0.6291 0.0651 0.000 0.468 0.532
#> GSM425849 3 0.1529 0.9471 0.040 0.000 0.960
#> GSM425850 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425851 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425852 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425893 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425894 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425895 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425896 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425897 2 0.2959 0.8771 0.000 0.900 0.100
#> GSM425898 2 0.1529 0.9346 0.000 0.960 0.040
#> GSM425899 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425900 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425901 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425902 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425903 1 0.3879 0.8153 0.848 0.000 0.152
#> GSM425904 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425905 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425906 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425863 1 0.0000 0.9918 1.000 0.000 0.000
#> GSM425864 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425865 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425866 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425867 1 0.0000 0.9918 1.000 0.000 0.000
#> GSM425868 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425869 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425870 1 0.0000 0.9918 1.000 0.000 0.000
#> GSM425871 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425872 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425873 1 0.0000 0.9918 1.000 0.000 0.000
#> GSM425843 1 0.0000 0.9918 1.000 0.000 0.000
#> GSM425844 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425845 1 0.0000 0.9918 1.000 0.000 0.000
#> GSM425846 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425847 1 0.0000 0.9918 1.000 0.000 0.000
#> GSM425886 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425887 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425888 1 0.0000 0.9918 1.000 0.000 0.000
#> GSM425889 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425890 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425891 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425892 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425853 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425854 2 0.3192 0.8645 0.000 0.888 0.112
#> GSM425855 1 0.0000 0.9918 1.000 0.000 0.000
#> GSM425856 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425857 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425858 1 0.0592 0.9798 0.988 0.000 0.012
#> GSM425859 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425860 1 0.0000 0.9918 1.000 0.000 0.000
#> GSM425861 1 0.0000 0.9918 1.000 0.000 0.000
#> GSM425862 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425837 1 0.0000 0.9918 1.000 0.000 0.000
#> GSM425838 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425839 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425840 3 0.1289 0.9550 0.032 0.000 0.968
#> GSM425841 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425842 1 0.0000 0.9918 1.000 0.000 0.000
#> GSM425917 2 0.1529 0.9346 0.000 0.960 0.040
#> GSM425922 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425919 1 0.0000 0.9918 1.000 0.000 0.000
#> GSM425920 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425923 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425916 3 0.1163 0.9587 0.028 0.000 0.972
#> GSM425918 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425921 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425925 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425926 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425927 1 0.0000 0.9918 1.000 0.000 0.000
#> GSM425924 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425928 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425929 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425930 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425931 3 0.3752 0.8197 0.000 0.144 0.856
#> GSM425932 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425933 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425934 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425935 2 0.0000 0.9645 0.000 1.000 0.000
#> GSM425936 2 0.5859 0.4999 0.000 0.656 0.344
#> GSM425937 3 0.0000 0.9829 0.000 0.000 1.000
#> GSM425938 2 0.5560 0.5945 0.000 0.700 0.300
#> GSM425939 3 0.0000 0.9829 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.4994 0.6083 0.000 0.520 0.480 0.000
#> GSM425908 2 0.4994 0.6083 0.000 0.520 0.480 0.000
#> GSM425909 2 0.4004 0.3142 0.000 0.812 0.164 0.024
#> GSM425910 1 0.0000 0.9908 1.000 0.000 0.000 0.000
#> GSM425911 4 0.0000 0.8979 0.000 0.000 0.000 1.000
#> GSM425912 1 0.0000 0.9908 1.000 0.000 0.000 0.000
#> GSM425913 4 0.7273 -0.2098 0.000 0.400 0.148 0.452
#> GSM425914 1 0.0000 0.9908 1.000 0.000 0.000 0.000
#> GSM425915 4 0.0000 0.8979 0.000 0.000 0.000 1.000
#> GSM425874 2 0.4994 0.6083 0.000 0.520 0.480 0.000
#> GSM425875 4 0.0336 0.8919 0.008 0.000 0.000 0.992
#> GSM425876 1 0.0000 0.9908 1.000 0.000 0.000 0.000
#> GSM425877 1 0.0000 0.9908 1.000 0.000 0.000 0.000
#> GSM425878 4 0.0188 0.8952 0.004 0.000 0.000 0.996
#> GSM425879 4 0.0188 0.8960 0.000 0.004 0.000 0.996
#> GSM425880 4 0.0000 0.8979 0.000 0.000 0.000 1.000
#> GSM425881 1 0.0000 0.9908 1.000 0.000 0.000 0.000
#> GSM425882 4 0.0188 0.8960 0.000 0.004 0.000 0.996
#> GSM425883 4 0.0000 0.8979 0.000 0.000 0.000 1.000
#> GSM425884 1 0.0000 0.9908 1.000 0.000 0.000 0.000
#> GSM425885 2 0.4994 0.6083 0.000 0.520 0.480 0.000
#> GSM425848 2 0.4933 -0.1488 0.000 0.568 0.000 0.432
#> GSM425849 4 0.1211 0.8577 0.040 0.000 0.000 0.960
#> GSM425850 4 0.0000 0.8979 0.000 0.000 0.000 1.000
#> GSM425851 4 0.4801 0.5602 0.000 0.188 0.048 0.764
#> GSM425852 4 0.0000 0.8979 0.000 0.000 0.000 1.000
#> GSM425893 4 0.4431 0.3967 0.000 0.304 0.000 0.696
#> GSM425894 2 0.0188 0.5413 0.000 0.996 0.004 0.000
#> GSM425895 4 0.4961 0.0432 0.000 0.448 0.000 0.552
#> GSM425896 2 0.4994 0.6083 0.000 0.520 0.480 0.000
#> GSM425897 2 0.5172 0.0612 0.000 0.704 0.260 0.036
#> GSM425898 2 0.3486 0.2846 0.000 0.812 0.000 0.188
#> GSM425899 4 0.0000 0.8979 0.000 0.000 0.000 1.000
#> GSM425900 4 0.0000 0.8979 0.000 0.000 0.000 1.000
#> GSM425901 2 0.0000 0.5395 0.000 1.000 0.000 0.000
#> GSM425902 2 0.0000 0.5395 0.000 1.000 0.000 0.000
#> GSM425903 1 0.3074 0.7790 0.848 0.000 0.000 0.152
#> GSM425904 4 0.0000 0.8979 0.000 0.000 0.000 1.000
#> GSM425905 2 0.0000 0.5395 0.000 1.000 0.000 0.000
#> GSM425906 4 0.0000 0.8979 0.000 0.000 0.000 1.000
#> GSM425863 1 0.0000 0.9908 1.000 0.000 0.000 0.000
#> GSM425864 2 0.0188 0.5413 0.000 0.996 0.004 0.000
#> GSM425865 2 0.0000 0.5395 0.000 1.000 0.000 0.000
#> GSM425866 4 0.0000 0.8979 0.000 0.000 0.000 1.000
#> GSM425867 1 0.0000 0.9908 1.000 0.000 0.000 0.000
#> GSM425868 2 0.4977 0.6061 0.000 0.540 0.460 0.000
#> GSM425869 2 0.4994 0.6083 0.000 0.520 0.480 0.000
#> GSM425870 1 0.0000 0.9908 1.000 0.000 0.000 0.000
#> GSM425871 4 0.0000 0.8979 0.000 0.000 0.000 1.000
#> GSM425872 4 0.0188 0.8960 0.000 0.004 0.000 0.996
#> GSM425873 1 0.0000 0.9908 1.000 0.000 0.000 0.000
#> GSM425843 1 0.0000 0.9908 1.000 0.000 0.000 0.000
#> GSM425844 4 0.0188 0.8960 0.000 0.004 0.000 0.996
#> GSM425845 1 0.0000 0.9908 1.000 0.000 0.000 0.000
#> GSM425846 4 0.0000 0.8979 0.000 0.000 0.000 1.000
#> GSM425847 1 0.0000 0.9908 1.000 0.000 0.000 0.000
#> GSM425886 2 0.3486 0.3061 0.000 0.812 0.188 0.000
#> GSM425887 4 0.0000 0.8979 0.000 0.000 0.000 1.000
#> GSM425888 1 0.0000 0.9908 1.000 0.000 0.000 0.000
#> GSM425889 4 0.0000 0.8979 0.000 0.000 0.000 1.000
#> GSM425890 2 0.4994 0.6083 0.000 0.520 0.480 0.000
#> GSM425891 4 0.0188 0.8960 0.000 0.004 0.000 0.996
#> GSM425892 2 0.0188 0.5413 0.000 0.996 0.004 0.000
#> GSM425853 4 0.0000 0.8979 0.000 0.000 0.000 1.000
#> GSM425854 2 0.3486 0.2846 0.000 0.812 0.000 0.188
#> GSM425855 1 0.0000 0.9908 1.000 0.000 0.000 0.000
#> GSM425856 4 0.0000 0.8979 0.000 0.000 0.000 1.000
#> GSM425857 2 0.4994 0.6083 0.000 0.520 0.480 0.000
#> GSM425858 1 0.0469 0.9767 0.988 0.000 0.000 0.012
#> GSM425859 2 0.4994 0.6083 0.000 0.520 0.480 0.000
#> GSM425860 1 0.0000 0.9908 1.000 0.000 0.000 0.000
#> GSM425861 1 0.0000 0.9908 1.000 0.000 0.000 0.000
#> GSM425862 4 0.0469 0.8888 0.000 0.012 0.000 0.988
#> GSM425837 1 0.0000 0.9908 1.000 0.000 0.000 0.000
#> GSM425838 2 0.4994 0.6083 0.000 0.520 0.480 0.000
#> GSM425839 2 0.0000 0.5395 0.000 1.000 0.000 0.000
#> GSM425840 4 0.1022 0.8671 0.032 0.000 0.000 0.968
#> GSM425841 2 0.4994 0.6083 0.000 0.520 0.480 0.000
#> GSM425842 1 0.0000 0.9908 1.000 0.000 0.000 0.000
#> GSM425917 2 0.4992 -0.4507 0.000 0.524 0.476 0.000
#> GSM425922 2 0.4994 0.6083 0.000 0.520 0.480 0.000
#> GSM425919 1 0.0000 0.9908 1.000 0.000 0.000 0.000
#> GSM425920 4 0.0000 0.8979 0.000 0.000 0.000 1.000
#> GSM425923 4 0.0000 0.8979 0.000 0.000 0.000 1.000
#> GSM425916 4 0.0921 0.8713 0.028 0.000 0.000 0.972
#> GSM425918 4 0.0000 0.8979 0.000 0.000 0.000 1.000
#> GSM425921 2 0.4994 0.6083 0.000 0.520 0.480 0.000
#> GSM425925 4 0.0000 0.8979 0.000 0.000 0.000 1.000
#> GSM425926 2 0.0188 0.5413 0.000 0.996 0.004 0.000
#> GSM425927 1 0.0000 0.9908 1.000 0.000 0.000 0.000
#> GSM425924 4 0.0188 0.8960 0.000 0.004 0.000 0.996
#> GSM425928 2 0.2921 0.3915 0.000 0.860 0.140 0.000
#> GSM425929 4 0.4898 0.0184 0.000 0.000 0.416 0.584
#> GSM425930 4 0.4564 0.3268 0.000 0.000 0.328 0.672
#> GSM425931 3 0.5161 0.4489 0.000 0.476 0.520 0.004
#> GSM425932 3 0.4994 0.2423 0.000 0.000 0.520 0.480
#> GSM425933 3 0.4994 0.2423 0.000 0.000 0.520 0.480
#> GSM425934 4 0.4898 0.0184 0.000 0.000 0.416 0.584
#> GSM425935 2 0.4998 -0.4765 0.000 0.512 0.488 0.000
#> GSM425936 3 0.4994 0.4440 0.000 0.480 0.520 0.000
#> GSM425937 3 0.5682 0.4578 0.000 0.456 0.520 0.024
#> GSM425938 3 0.4994 0.4440 0.000 0.480 0.520 0.000
#> GSM425939 3 0.4994 0.2423 0.000 0.000 0.520 0.480
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM425907 4 0.0000 0.979 0.000 0.000 0.000 1.000 0.000
#> GSM425908 4 0.0162 0.978 0.000 0.004 0.000 0.996 0.000
#> GSM425909 2 0.3224 0.743 0.000 0.824 0.016 0.000 0.160
#> GSM425910 1 0.0000 0.990 1.000 0.000 0.000 0.000 0.000
#> GSM425911 5 0.0671 0.826 0.000 0.004 0.016 0.000 0.980
#> GSM425912 1 0.0000 0.990 1.000 0.000 0.000 0.000 0.000
#> GSM425913 5 0.4360 0.546 0.000 0.064 0.184 0.000 0.752
#> GSM425914 1 0.0000 0.990 1.000 0.000 0.000 0.000 0.000
#> GSM425915 5 0.2732 0.874 0.000 0.000 0.160 0.000 0.840
#> GSM425874 4 0.0404 0.975 0.000 0.012 0.000 0.988 0.000
#> GSM425875 5 0.3013 0.871 0.008 0.000 0.160 0.000 0.832
#> GSM425876 1 0.0000 0.990 1.000 0.000 0.000 0.000 0.000
#> GSM425877 1 0.0000 0.990 1.000 0.000 0.000 0.000 0.000
#> GSM425878 5 0.2890 0.872 0.004 0.000 0.160 0.000 0.836
#> GSM425879 5 0.0671 0.826 0.000 0.004 0.016 0.000 0.980
#> GSM425880 5 0.2732 0.874 0.000 0.000 0.160 0.000 0.840
#> GSM425881 1 0.0000 0.990 1.000 0.000 0.000 0.000 0.000
#> GSM425882 5 0.0898 0.822 0.000 0.008 0.020 0.000 0.972
#> GSM425883 5 0.2732 0.874 0.000 0.000 0.160 0.000 0.840
#> GSM425884 1 0.0000 0.990 1.000 0.000 0.000 0.000 0.000
#> GSM425885 4 0.0000 0.979 0.000 0.000 0.000 1.000 0.000
#> GSM425848 2 0.4682 0.322 0.000 0.564 0.016 0.000 0.420
#> GSM425849 5 0.3731 0.843 0.040 0.000 0.160 0.000 0.800
#> GSM425850 5 0.2732 0.874 0.000 0.000 0.160 0.000 0.840
#> GSM425851 5 0.3246 0.631 0.000 0.008 0.184 0.000 0.808
#> GSM425852 5 0.2890 0.874 0.000 0.004 0.160 0.000 0.836
#> GSM425893 5 0.2914 0.729 0.000 0.052 0.076 0.000 0.872
#> GSM425894 2 0.0162 0.870 0.000 0.996 0.000 0.004 0.000
#> GSM425895 5 0.2777 0.708 0.000 0.120 0.016 0.000 0.864
#> GSM425896 4 0.0290 0.977 0.000 0.008 0.000 0.992 0.000
#> GSM425897 2 0.0510 0.861 0.000 0.984 0.000 0.000 0.016
#> GSM425898 2 0.3224 0.743 0.000 0.824 0.016 0.000 0.160
#> GSM425899 5 0.0671 0.826 0.000 0.004 0.016 0.000 0.980
#> GSM425900 5 0.2732 0.874 0.000 0.000 0.160 0.000 0.840
#> GSM425901 2 0.0162 0.870 0.000 0.996 0.000 0.004 0.000
#> GSM425902 2 0.0162 0.870 0.000 0.996 0.000 0.004 0.000
#> GSM425903 1 0.2648 0.765 0.848 0.000 0.000 0.000 0.152
#> GSM425904 5 0.2732 0.874 0.000 0.000 0.160 0.000 0.840
#> GSM425905 2 0.0162 0.870 0.000 0.996 0.000 0.004 0.000
#> GSM425906 5 0.2732 0.874 0.000 0.000 0.160 0.000 0.840
#> GSM425863 1 0.0000 0.990 1.000 0.000 0.000 0.000 0.000
#> GSM425864 2 0.0162 0.870 0.000 0.996 0.000 0.004 0.000
#> GSM425865 2 0.0162 0.870 0.000 0.996 0.000 0.004 0.000
#> GSM425866 5 0.2732 0.874 0.000 0.000 0.160 0.000 0.840
#> GSM425867 1 0.0000 0.990 1.000 0.000 0.000 0.000 0.000
#> GSM425868 2 0.2813 0.733 0.000 0.832 0.000 0.168 0.000
#> GSM425869 4 0.0000 0.979 0.000 0.000 0.000 1.000 0.000
#> GSM425870 1 0.0000 0.990 1.000 0.000 0.000 0.000 0.000
#> GSM425871 5 0.0771 0.829 0.000 0.004 0.020 0.000 0.976
#> GSM425872 5 0.1251 0.811 0.000 0.008 0.036 0.000 0.956
#> GSM425873 1 0.0000 0.990 1.000 0.000 0.000 0.000 0.000
#> GSM425843 1 0.0000 0.990 1.000 0.000 0.000 0.000 0.000
#> GSM425844 5 0.0671 0.826 0.000 0.004 0.016 0.000 0.980
#> GSM425845 1 0.0000 0.990 1.000 0.000 0.000 0.000 0.000
#> GSM425846 5 0.0510 0.828 0.000 0.000 0.016 0.000 0.984
#> GSM425847 1 0.0000 0.990 1.000 0.000 0.000 0.000 0.000
#> GSM425886 2 0.0000 0.868 0.000 1.000 0.000 0.000 0.000
#> GSM425887 5 0.2732 0.874 0.000 0.000 0.160 0.000 0.840
#> GSM425888 1 0.0000 0.990 1.000 0.000 0.000 0.000 0.000
#> GSM425889 5 0.2732 0.874 0.000 0.000 0.160 0.000 0.840
#> GSM425890 4 0.0703 0.964 0.000 0.024 0.000 0.976 0.000
#> GSM425891 5 0.0671 0.826 0.000 0.004 0.016 0.000 0.980
#> GSM425892 2 0.0162 0.870 0.000 0.996 0.000 0.004 0.000
#> GSM425853 5 0.2732 0.874 0.000 0.000 0.160 0.000 0.840
#> GSM425854 2 0.3381 0.728 0.000 0.808 0.016 0.000 0.176
#> GSM425855 1 0.0162 0.986 0.996 0.000 0.000 0.000 0.004
#> GSM425856 5 0.2732 0.874 0.000 0.000 0.160 0.000 0.840
#> GSM425857 4 0.0000 0.979 0.000 0.000 0.000 1.000 0.000
#> GSM425858 1 0.0510 0.972 0.984 0.000 0.000 0.000 0.016
#> GSM425859 4 0.1792 0.915 0.000 0.084 0.000 0.916 0.000
#> GSM425860 1 0.0000 0.990 1.000 0.000 0.000 0.000 0.000
#> GSM425861 1 0.0000 0.990 1.000 0.000 0.000 0.000 0.000
#> GSM425862 5 0.1205 0.810 0.000 0.004 0.040 0.000 0.956
#> GSM425837 1 0.0000 0.990 1.000 0.000 0.000 0.000 0.000
#> GSM425838 4 0.0000 0.979 0.000 0.000 0.000 1.000 0.000
#> GSM425839 2 0.0162 0.870 0.000 0.996 0.000 0.004 0.000
#> GSM425840 5 0.3577 0.851 0.032 0.000 0.160 0.000 0.808
#> GSM425841 4 0.1908 0.908 0.000 0.092 0.000 0.908 0.000
#> GSM425842 1 0.0000 0.990 1.000 0.000 0.000 0.000 0.000
#> GSM425917 2 0.4897 0.162 0.000 0.516 0.460 0.000 0.024
#> GSM425922 4 0.0000 0.979 0.000 0.000 0.000 1.000 0.000
#> GSM425919 1 0.0000 0.990 1.000 0.000 0.000 0.000 0.000
#> GSM425920 5 0.2732 0.874 0.000 0.000 0.160 0.000 0.840
#> GSM425923 5 0.2732 0.874 0.000 0.000 0.160 0.000 0.840
#> GSM425916 5 0.3495 0.854 0.028 0.000 0.160 0.000 0.812
#> GSM425918 5 0.0880 0.846 0.000 0.000 0.032 0.000 0.968
#> GSM425921 4 0.0000 0.979 0.000 0.000 0.000 1.000 0.000
#> GSM425925 5 0.2732 0.874 0.000 0.000 0.160 0.000 0.840
#> GSM425926 2 0.0162 0.870 0.000 0.996 0.000 0.004 0.000
#> GSM425927 1 0.0000 0.990 1.000 0.000 0.000 0.000 0.000
#> GSM425924 5 0.1478 0.832 0.000 0.000 0.064 0.000 0.936
#> GSM425928 2 0.0324 0.868 0.000 0.992 0.004 0.004 0.000
#> GSM425929 3 0.3003 0.723 0.000 0.000 0.812 0.000 0.188
#> GSM425930 3 0.3561 0.608 0.000 0.000 0.740 0.000 0.260
#> GSM425931 3 0.2732 0.706 0.000 0.000 0.840 0.000 0.160
#> GSM425932 3 0.0510 0.766 0.000 0.000 0.984 0.000 0.016
#> GSM425933 3 0.0510 0.766 0.000 0.000 0.984 0.000 0.016
#> GSM425934 3 0.3003 0.723 0.000 0.000 0.812 0.000 0.188
#> GSM425935 2 0.3949 0.546 0.000 0.696 0.300 0.004 0.000
#> GSM425936 3 0.3284 0.626 0.000 0.148 0.828 0.000 0.024
#> GSM425937 3 0.2732 0.706 0.000 0.000 0.840 0.000 0.160
#> GSM425938 3 0.2848 0.706 0.000 0.004 0.840 0.000 0.156
#> GSM425939 3 0.2561 0.758 0.000 0.000 0.856 0.000 0.144
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 4 0.0000 0.940 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425908 4 0.0146 0.938 0.000 0.004 0.000 0.996 0.000 0.000
#> GSM425909 2 0.0146 0.367 0.000 0.996 0.000 0.000 0.000 0.004
#> GSM425910 1 0.0632 0.924 0.976 0.000 0.000 0.000 0.024 0.000
#> GSM425911 5 0.3804 0.622 0.000 0.424 0.000 0.000 0.576 0.000
#> GSM425912 1 0.0000 0.937 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425913 6 0.4950 0.492 0.000 0.344 0.080 0.000 0.000 0.576
#> GSM425914 1 0.2697 0.764 0.812 0.000 0.000 0.000 0.188 0.000
#> GSM425915 5 0.0000 0.747 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM425874 4 0.0405 0.934 0.000 0.008 0.000 0.988 0.000 0.004
#> GSM425875 5 0.0146 0.746 0.004 0.000 0.000 0.000 0.996 0.000
#> GSM425876 1 0.0000 0.937 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425877 1 0.2048 0.839 0.880 0.000 0.000 0.000 0.120 0.000
#> GSM425878 5 0.0146 0.744 0.004 0.000 0.000 0.000 0.996 0.000
#> GSM425879 5 0.3804 0.622 0.000 0.424 0.000 0.000 0.576 0.000
#> GSM425880 5 0.0000 0.747 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM425881 1 0.0000 0.937 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425882 5 0.3804 0.622 0.000 0.424 0.000 0.000 0.576 0.000
#> GSM425883 6 0.3847 0.364 0.000 0.000 0.000 0.000 0.456 0.544
#> GSM425884 1 0.0000 0.937 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425885 4 0.0000 0.940 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425848 2 0.2003 0.166 0.000 0.884 0.000 0.000 0.116 0.000
#> GSM425849 5 0.0937 0.709 0.040 0.000 0.000 0.000 0.960 0.000
#> GSM425850 5 0.0000 0.747 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM425851 5 0.3804 0.622 0.000 0.424 0.000 0.000 0.576 0.000
#> GSM425852 5 0.3563 0.653 0.000 0.336 0.000 0.000 0.664 0.000
#> GSM425893 5 0.4552 0.608 0.000 0.388 0.040 0.000 0.572 0.000
#> GSM425894 2 0.3804 0.809 0.000 0.576 0.000 0.000 0.000 0.424
#> GSM425895 5 0.3817 0.613 0.000 0.432 0.000 0.000 0.568 0.000
#> GSM425896 4 0.0260 0.936 0.000 0.008 0.000 0.992 0.000 0.000
#> GSM425897 6 0.4057 -0.648 0.000 0.436 0.008 0.000 0.000 0.556
#> GSM425898 2 0.0146 0.367 0.000 0.996 0.000 0.000 0.000 0.004
#> GSM425899 5 0.3804 0.622 0.000 0.424 0.000 0.000 0.576 0.000
#> GSM425900 5 0.0000 0.747 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM425901 2 0.3804 0.809 0.000 0.576 0.000 0.000 0.000 0.424
#> GSM425902 2 0.3804 0.809 0.000 0.576 0.000 0.000 0.000 0.424
#> GSM425903 1 0.2697 0.736 0.812 0.000 0.000 0.000 0.188 0.000
#> GSM425904 5 0.0000 0.747 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM425905 2 0.3804 0.809 0.000 0.576 0.000 0.000 0.000 0.424
#> GSM425906 5 0.0363 0.743 0.012 0.000 0.000 0.000 0.988 0.000
#> GSM425863 1 0.0000 0.937 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425864 2 0.3804 0.809 0.000 0.576 0.000 0.000 0.000 0.424
#> GSM425865 2 0.3804 0.809 0.000 0.576 0.000 0.000 0.000 0.424
#> GSM425866 5 0.0000 0.747 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM425867 1 0.0000 0.937 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425868 2 0.4788 0.761 0.000 0.548 0.000 0.056 0.000 0.396
#> GSM425869 4 0.0000 0.940 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425870 1 0.0260 0.934 0.992 0.000 0.000 0.000 0.008 0.000
#> GSM425871 5 0.3547 0.660 0.000 0.332 0.000 0.000 0.668 0.000
#> GSM425872 5 0.3804 0.622 0.000 0.424 0.000 0.000 0.576 0.000
#> GSM425873 1 0.0000 0.937 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425843 1 0.0000 0.937 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425844 6 0.3804 0.479 0.000 0.424 0.000 0.000 0.000 0.576
#> GSM425845 1 0.0000 0.937 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425846 5 0.3266 0.679 0.000 0.272 0.000 0.000 0.728 0.000
#> GSM425847 1 0.0000 0.937 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425886 2 0.4109 0.801 0.000 0.576 0.012 0.000 0.000 0.412
#> GSM425887 5 0.0000 0.747 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM425888 1 0.0000 0.937 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425889 5 0.0000 0.747 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM425890 4 0.0146 0.938 0.000 0.004 0.000 0.996 0.000 0.000
#> GSM425891 5 0.3804 0.622 0.000 0.424 0.000 0.000 0.576 0.000
#> GSM425892 2 0.3804 0.809 0.000 0.576 0.000 0.000 0.000 0.424
#> GSM425853 5 0.0000 0.747 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM425854 2 0.0632 0.328 0.000 0.976 0.000 0.000 0.024 0.000
#> GSM425855 1 0.3499 0.578 0.680 0.000 0.000 0.000 0.320 0.000
#> GSM425856 5 0.0632 0.744 0.000 0.024 0.000 0.000 0.976 0.000
#> GSM425857 4 0.0000 0.940 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425858 1 0.3607 0.531 0.652 0.000 0.000 0.000 0.348 0.000
#> GSM425859 4 0.3555 0.643 0.000 0.008 0.000 0.712 0.000 0.280
#> GSM425860 1 0.0000 0.937 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425861 1 0.0363 0.932 0.988 0.000 0.000 0.000 0.012 0.000
#> GSM425862 5 0.3804 0.622 0.000 0.424 0.000 0.000 0.576 0.000
#> GSM425837 1 0.0146 0.935 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM425838 4 0.0000 0.940 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425839 2 0.3804 0.809 0.000 0.576 0.000 0.000 0.000 0.424
#> GSM425840 5 0.0790 0.718 0.032 0.000 0.000 0.000 0.968 0.000
#> GSM425841 4 0.3797 0.612 0.000 0.016 0.000 0.692 0.000 0.292
#> GSM425842 1 0.0000 0.937 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425917 6 0.4295 0.468 0.000 0.160 0.112 0.000 0.000 0.728
#> GSM425922 4 0.0000 0.940 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425919 1 0.0363 0.932 0.988 0.000 0.000 0.000 0.012 0.000
#> GSM425920 5 0.0000 0.747 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM425923 6 0.5160 0.467 0.000 0.108 0.000 0.000 0.320 0.572
#> GSM425916 6 0.3847 0.364 0.000 0.000 0.000 0.000 0.456 0.544
#> GSM425918 6 0.5192 0.527 0.000 0.308 0.000 0.000 0.116 0.576
#> GSM425921 4 0.0000 0.940 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425925 5 0.1863 0.726 0.000 0.104 0.000 0.000 0.896 0.000
#> GSM425926 2 0.3804 0.809 0.000 0.576 0.000 0.000 0.000 0.424
#> GSM425927 1 0.0000 0.937 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425924 6 0.5753 0.339 0.000 0.124 0.272 0.000 0.028 0.576
#> GSM425928 2 0.3847 0.783 0.000 0.544 0.000 0.000 0.000 0.456
#> GSM425929 3 0.1556 0.913 0.000 0.000 0.920 0.000 0.080 0.000
#> GSM425930 3 0.1814 0.890 0.000 0.000 0.900 0.000 0.100 0.000
#> GSM425931 3 0.0000 0.944 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425932 3 0.0000 0.944 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425933 3 0.0000 0.944 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425934 3 0.1556 0.913 0.000 0.000 0.920 0.000 0.080 0.000
#> GSM425935 6 0.6050 -0.509 0.000 0.312 0.276 0.000 0.000 0.412
#> GSM425936 3 0.0000 0.944 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425937 3 0.0000 0.944 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425938 3 0.0000 0.944 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425939 3 0.1501 0.916 0.000 0.000 0.924 0.000 0.076 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 disease.state(p) tissue(p) other(p) k
#> ATC:pam 101 6.44e-01 7.28e-01 7.85e-01 2
#> ATC:pam 101 7.40e-02 1.96e-01 4.52e-01 3
#> ATC:pam 81 NA 5.92e-01 7.25e-01 4
#> ATC:pam 101 2.30e-17 3.45e-15 1.29e-08 5
#> ATC:pam 90 4.16e-16 1.65e-15 1.83e-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["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 103 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 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 0.991 0.995 0.3972 0.600 0.600
#> 3 3 0.979 0.933 0.956 0.3868 0.772 0.643
#> 4 4 0.839 0.897 0.956 0.1579 0.856 0.696
#> 5 5 0.889 0.876 0.950 0.1664 0.827 0.558
#> 6 6 0.850 0.849 0.924 0.0576 0.932 0.744
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
#> GSM425907 2 0.4022 0.924 0.080 0.920
#> GSM425908 1 0.0938 0.989 0.988 0.012
#> GSM425909 1 0.0000 0.999 1.000 0.000
#> GSM425910 1 0.0000 0.999 1.000 0.000
#> GSM425911 1 0.0000 0.999 1.000 0.000
#> GSM425912 1 0.0000 0.999 1.000 0.000
#> GSM425913 2 0.0000 0.984 0.000 1.000
#> GSM425914 1 0.0000 0.999 1.000 0.000
#> GSM425915 1 0.0000 0.999 1.000 0.000
#> GSM425874 1 0.0938 0.989 0.988 0.012
#> GSM425875 1 0.0000 0.999 1.000 0.000
#> GSM425876 1 0.0000 0.999 1.000 0.000
#> GSM425877 1 0.0000 0.999 1.000 0.000
#> GSM425878 1 0.0000 0.999 1.000 0.000
#> GSM425879 1 0.0000 0.999 1.000 0.000
#> GSM425880 1 0.0000 0.999 1.000 0.000
#> GSM425881 1 0.0000 0.999 1.000 0.000
#> GSM425882 1 0.0000 0.999 1.000 0.000
#> GSM425883 2 0.0000 0.984 0.000 1.000
#> GSM425884 1 0.0000 0.999 1.000 0.000
#> GSM425885 2 0.4161 0.920 0.084 0.916
#> GSM425848 1 0.0000 0.999 1.000 0.000
#> GSM425849 1 0.0000 0.999 1.000 0.000
#> GSM425850 1 0.0000 0.999 1.000 0.000
#> GSM425851 1 0.0000 0.999 1.000 0.000
#> GSM425852 1 0.0000 0.999 1.000 0.000
#> GSM425893 1 0.0000 0.999 1.000 0.000
#> GSM425894 1 0.0000 0.999 1.000 0.000
#> GSM425895 1 0.0000 0.999 1.000 0.000
#> GSM425896 1 0.0938 0.989 0.988 0.012
#> GSM425897 2 0.0000 0.984 0.000 1.000
#> GSM425898 1 0.0000 0.999 1.000 0.000
#> GSM425899 1 0.0000 0.999 1.000 0.000
#> GSM425900 1 0.0000 0.999 1.000 0.000
#> GSM425901 1 0.0000 0.999 1.000 0.000
#> GSM425902 1 0.0000 0.999 1.000 0.000
#> GSM425903 1 0.0000 0.999 1.000 0.000
#> GSM425904 1 0.0000 0.999 1.000 0.000
#> GSM425905 1 0.0672 0.992 0.992 0.008
#> GSM425906 1 0.0000 0.999 1.000 0.000
#> GSM425863 1 0.0000 0.999 1.000 0.000
#> GSM425864 1 0.0000 0.999 1.000 0.000
#> GSM425865 1 0.0000 0.999 1.000 0.000
#> GSM425866 1 0.0000 0.999 1.000 0.000
#> GSM425867 1 0.0000 0.999 1.000 0.000
#> GSM425868 2 0.3431 0.939 0.064 0.936
#> GSM425869 1 0.0938 0.989 0.988 0.012
#> GSM425870 1 0.0000 0.999 1.000 0.000
#> GSM425871 1 0.0000 0.999 1.000 0.000
#> GSM425872 1 0.0000 0.999 1.000 0.000
#> GSM425873 1 0.0000 0.999 1.000 0.000
#> GSM425843 1 0.0000 0.999 1.000 0.000
#> GSM425844 2 0.0000 0.984 0.000 1.000
#> GSM425845 1 0.0000 0.999 1.000 0.000
#> GSM425846 1 0.0000 0.999 1.000 0.000
#> GSM425847 1 0.0000 0.999 1.000 0.000
#> GSM425886 1 0.0000 0.999 1.000 0.000
#> GSM425887 1 0.0000 0.999 1.000 0.000
#> GSM425888 1 0.0000 0.999 1.000 0.000
#> GSM425889 1 0.0000 0.999 1.000 0.000
#> GSM425890 2 0.0000 0.984 0.000 1.000
#> GSM425891 1 0.0000 0.999 1.000 0.000
#> GSM425892 1 0.0000 0.999 1.000 0.000
#> GSM425853 1 0.0000 0.999 1.000 0.000
#> GSM425854 1 0.0000 0.999 1.000 0.000
#> GSM425855 1 0.0000 0.999 1.000 0.000
#> GSM425856 1 0.0000 0.999 1.000 0.000
#> GSM425857 2 0.4022 0.924 0.080 0.920
#> GSM425858 1 0.0000 0.999 1.000 0.000
#> GSM425859 1 0.0938 0.989 0.988 0.012
#> GSM425860 1 0.0000 0.999 1.000 0.000
#> GSM425861 1 0.0000 0.999 1.000 0.000
#> GSM425862 1 0.0000 0.999 1.000 0.000
#> GSM425837 1 0.0000 0.999 1.000 0.000
#> GSM425838 1 0.0938 0.989 0.988 0.012
#> GSM425839 1 0.0000 0.999 1.000 0.000
#> GSM425840 1 0.0000 0.999 1.000 0.000
#> GSM425841 1 0.0938 0.989 0.988 0.012
#> GSM425842 1 0.0000 0.999 1.000 0.000
#> GSM425917 2 0.0000 0.984 0.000 1.000
#> GSM425922 2 0.0000 0.984 0.000 1.000
#> GSM425919 1 0.0000 0.999 1.000 0.000
#> GSM425920 1 0.0000 0.999 1.000 0.000
#> GSM425923 2 0.0000 0.984 0.000 1.000
#> GSM425916 2 0.0000 0.984 0.000 1.000
#> GSM425918 2 0.0000 0.984 0.000 1.000
#> GSM425921 2 0.0000 0.984 0.000 1.000
#> GSM425925 1 0.0000 0.999 1.000 0.000
#> GSM425926 1 0.0938 0.989 0.988 0.012
#> GSM425927 1 0.0000 0.999 1.000 0.000
#> GSM425924 2 0.0000 0.984 0.000 1.000
#> GSM425928 2 0.0000 0.984 0.000 1.000
#> GSM425929 2 0.0938 0.983 0.012 0.988
#> GSM425930 2 0.0938 0.983 0.012 0.988
#> GSM425931 2 0.0938 0.983 0.012 0.988
#> GSM425932 2 0.0938 0.983 0.012 0.988
#> GSM425933 2 0.0938 0.983 0.012 0.988
#> GSM425934 2 0.0938 0.983 0.012 0.988
#> GSM425935 2 0.0938 0.983 0.012 0.988
#> GSM425936 2 0.0938 0.983 0.012 0.988
#> GSM425937 2 0.0938 0.983 0.012 0.988
#> GSM425938 2 0.0938 0.983 0.012 0.988
#> GSM425939 2 0.0938 0.983 0.012 0.988
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.1289 0.888 0.032 0.968 0.000
#> GSM425908 2 0.1643 0.888 0.044 0.956 0.000
#> GSM425909 1 0.1753 0.960 0.952 0.048 0.000
#> GSM425910 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425911 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425912 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425913 3 0.0000 1.000 0.000 0.000 1.000
#> GSM425914 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425915 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425874 2 0.1643 0.888 0.044 0.956 0.000
#> GSM425875 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425876 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425877 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425878 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425879 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425880 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425881 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425882 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425883 3 0.0000 1.000 0.000 0.000 1.000
#> GSM425884 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425885 2 0.1289 0.888 0.032 0.968 0.000
#> GSM425848 1 0.1289 0.969 0.968 0.032 0.000
#> GSM425849 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425850 1 0.0424 0.970 0.992 0.008 0.000
#> GSM425851 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425852 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425893 1 0.1482 0.968 0.968 0.020 0.012
#> GSM425894 2 0.5178 0.630 0.256 0.744 0.000
#> GSM425895 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425896 2 0.3412 0.805 0.124 0.876 0.000
#> GSM425897 3 0.0000 1.000 0.000 0.000 1.000
#> GSM425898 1 0.1529 0.965 0.960 0.040 0.000
#> GSM425899 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425900 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425901 1 0.2261 0.944 0.932 0.068 0.000
#> GSM425902 1 0.1753 0.960 0.952 0.048 0.000
#> GSM425903 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425904 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425905 2 0.1860 0.882 0.052 0.948 0.000
#> GSM425906 1 0.1964 0.945 0.944 0.000 0.056
#> GSM425863 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425864 2 0.1643 0.888 0.044 0.956 0.000
#> GSM425865 2 0.1643 0.888 0.044 0.956 0.000
#> GSM425866 1 0.0592 0.970 0.988 0.012 0.000
#> GSM425867 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425868 2 0.2537 0.875 0.000 0.920 0.080
#> GSM425869 2 0.1643 0.888 0.044 0.956 0.000
#> GSM425870 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425871 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425872 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425873 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425843 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425844 3 0.0000 1.000 0.000 0.000 1.000
#> GSM425845 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425846 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425847 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425886 1 0.2959 0.910 0.900 0.100 0.000
#> GSM425887 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425888 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425889 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425890 3 0.0000 1.000 0.000 0.000 1.000
#> GSM425891 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425892 2 0.6260 0.226 0.448 0.552 0.000
#> GSM425853 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425854 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425855 1 0.0424 0.970 0.992 0.008 0.000
#> GSM425856 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425857 2 0.1289 0.888 0.032 0.968 0.000
#> GSM425858 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425859 2 0.1643 0.888 0.044 0.956 0.000
#> GSM425860 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425861 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425862 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425837 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425838 2 0.1643 0.888 0.044 0.956 0.000
#> GSM425839 2 0.5706 0.539 0.320 0.680 0.000
#> GSM425840 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425841 2 0.1643 0.888 0.044 0.956 0.000
#> GSM425842 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425917 3 0.0000 1.000 0.000 0.000 1.000
#> GSM425922 3 0.0000 1.000 0.000 0.000 1.000
#> GSM425919 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425920 1 0.1964 0.945 0.944 0.000 0.056
#> GSM425923 3 0.0000 1.000 0.000 0.000 1.000
#> GSM425916 3 0.0000 1.000 0.000 0.000 1.000
#> GSM425918 3 0.0000 1.000 0.000 0.000 1.000
#> GSM425921 3 0.0000 1.000 0.000 0.000 1.000
#> GSM425925 1 0.1163 0.971 0.972 0.028 0.000
#> GSM425926 1 0.2959 0.910 0.900 0.100 0.000
#> GSM425927 1 0.1163 0.963 0.972 0.028 0.000
#> GSM425924 3 0.0000 1.000 0.000 0.000 1.000
#> GSM425928 3 0.0000 1.000 0.000 0.000 1.000
#> GSM425929 2 0.2448 0.876 0.000 0.924 0.076
#> GSM425930 2 0.2448 0.876 0.000 0.924 0.076
#> GSM425931 2 0.2448 0.876 0.000 0.924 0.076
#> GSM425932 2 0.2448 0.876 0.000 0.924 0.076
#> GSM425933 2 0.2448 0.876 0.000 0.924 0.076
#> GSM425934 2 0.2448 0.876 0.000 0.924 0.076
#> GSM425935 2 0.2448 0.876 0.000 0.924 0.076
#> GSM425936 2 0.2448 0.876 0.000 0.924 0.076
#> GSM425937 2 0.2448 0.876 0.000 0.924 0.076
#> GSM425938 2 0.2448 0.876 0.000 0.924 0.076
#> GSM425939 2 0.2448 0.876 0.000 0.924 0.076
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.0000 0.854 0.000 1.000 0 0
#> GSM425908 2 0.0000 0.854 0.000 1.000 0 0
#> GSM425909 2 0.3942 0.773 0.236 0.764 0 0
#> GSM425910 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425911 1 0.0336 0.946 0.992 0.008 0 0
#> GSM425912 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425913 4 0.0000 1.000 0.000 0.000 0 1
#> GSM425914 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425915 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425874 2 0.0000 0.854 0.000 1.000 0 0
#> GSM425875 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425876 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425877 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425878 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425879 1 0.4776 0.312 0.624 0.376 0 0
#> GSM425880 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425881 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425882 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425883 4 0.0000 1.000 0.000 0.000 0 1
#> GSM425884 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425885 2 0.0000 0.854 0.000 1.000 0 0
#> GSM425848 2 0.4277 0.719 0.280 0.720 0 0
#> GSM425849 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425850 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425851 1 0.0921 0.927 0.972 0.028 0 0
#> GSM425852 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425893 1 0.0921 0.927 0.972 0.028 0 0
#> GSM425894 2 0.3024 0.851 0.148 0.852 0 0
#> GSM425895 1 0.4999 -0.126 0.508 0.492 0 0
#> GSM425896 2 0.1302 0.856 0.044 0.956 0 0
#> GSM425897 4 0.0000 1.000 0.000 0.000 0 1
#> GSM425898 2 0.3569 0.817 0.196 0.804 0 0
#> GSM425899 1 0.2704 0.816 0.876 0.124 0 0
#> GSM425900 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425901 2 0.3311 0.838 0.172 0.828 0 0
#> GSM425902 2 0.3219 0.843 0.164 0.836 0 0
#> GSM425903 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425904 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425905 2 0.0188 0.854 0.004 0.996 0 0
#> GSM425906 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425863 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425864 2 0.3123 0.848 0.156 0.844 0 0
#> GSM425865 2 0.3123 0.848 0.156 0.844 0 0
#> GSM425866 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425867 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425868 2 0.0000 0.854 0.000 1.000 0 0
#> GSM425869 2 0.0000 0.854 0.000 1.000 0 0
#> GSM425870 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425871 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425872 1 0.4624 0.414 0.660 0.340 0 0
#> GSM425873 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425843 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425844 4 0.0000 1.000 0.000 0.000 0 1
#> GSM425845 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425846 1 0.0188 0.949 0.996 0.004 0 0
#> GSM425847 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425886 2 0.3486 0.824 0.188 0.812 0 0
#> GSM425887 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425888 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425889 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425890 4 0.0000 1.000 0.000 0.000 0 1
#> GSM425891 1 0.4998 -0.110 0.512 0.488 0 0
#> GSM425892 2 0.3123 0.848 0.156 0.844 0 0
#> GSM425853 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425854 2 0.4304 0.712 0.284 0.716 0 0
#> GSM425855 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425856 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425857 2 0.0000 0.854 0.000 1.000 0 0
#> GSM425858 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425859 2 0.0000 0.854 0.000 1.000 0 0
#> GSM425860 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425861 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425862 1 0.4222 0.572 0.728 0.272 0 0
#> GSM425837 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425838 2 0.0000 0.854 0.000 1.000 0 0
#> GSM425839 2 0.3024 0.851 0.148 0.852 0 0
#> GSM425840 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425841 2 0.0000 0.854 0.000 1.000 0 0
#> GSM425842 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425917 4 0.0000 1.000 0.000 0.000 0 1
#> GSM425922 4 0.0000 1.000 0.000 0.000 0 1
#> GSM425919 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425920 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425923 4 0.0000 1.000 0.000 0.000 0 1
#> GSM425916 4 0.0000 1.000 0.000 0.000 0 1
#> GSM425918 4 0.0000 1.000 0.000 0.000 0 1
#> GSM425921 4 0.0000 1.000 0.000 0.000 0 1
#> GSM425925 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425926 2 0.0000 0.854 0.000 1.000 0 0
#> GSM425927 1 0.0000 0.953 1.000 0.000 0 0
#> GSM425924 4 0.0000 1.000 0.000 0.000 0 1
#> GSM425928 4 0.0000 1.000 0.000 0.000 0 1
#> GSM425929 3 0.0000 1.000 0.000 0.000 1 0
#> GSM425930 3 0.0000 1.000 0.000 0.000 1 0
#> GSM425931 3 0.0000 1.000 0.000 0.000 1 0
#> GSM425932 3 0.0000 1.000 0.000 0.000 1 0
#> GSM425933 3 0.0000 1.000 0.000 0.000 1 0
#> GSM425934 3 0.0000 1.000 0.000 0.000 1 0
#> GSM425935 3 0.0000 1.000 0.000 0.000 1 0
#> GSM425936 3 0.0000 1.000 0.000 0.000 1 0
#> GSM425937 3 0.0000 1.000 0.000 0.000 1 0
#> GSM425938 3 0.0000 1.000 0.000 0.000 1 0
#> GSM425939 3 0.0000 1.000 0.000 0.000 1 0
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM425907 5 0.0162 0.9958 0.000 0.004 0 0 0.996
#> GSM425908 5 0.0290 0.9970 0.000 0.008 0 0 0.992
#> GSM425909 2 0.0000 0.8795 0.000 1.000 0 0 0.000
#> GSM425910 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425911 2 0.0290 0.8767 0.008 0.992 0 0 0.000
#> GSM425912 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425913 4 0.0000 1.0000 0.000 0.000 0 1 0.000
#> GSM425914 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425915 1 0.0162 0.9257 0.996 0.004 0 0 0.000
#> GSM425874 5 0.0290 0.9970 0.000 0.008 0 0 0.992
#> GSM425875 1 0.3452 0.6485 0.756 0.244 0 0 0.000
#> GSM425876 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425877 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425878 1 0.4238 0.3950 0.628 0.368 0 0 0.004
#> GSM425879 2 0.0000 0.8795 0.000 1.000 0 0 0.000
#> GSM425880 2 0.3266 0.7255 0.200 0.796 0 0 0.004
#> GSM425881 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425882 2 0.3796 0.5764 0.300 0.700 0 0 0.000
#> GSM425883 4 0.0000 1.0000 0.000 0.000 0 1 0.000
#> GSM425884 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425885 5 0.0162 0.9958 0.000 0.004 0 0 0.996
#> GSM425848 2 0.0162 0.8783 0.000 0.996 0 0 0.004
#> GSM425849 1 0.4443 0.0685 0.524 0.472 0 0 0.004
#> GSM425850 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425851 1 0.4300 0.0792 0.524 0.476 0 0 0.000
#> GSM425852 2 0.4161 0.3539 0.392 0.608 0 0 0.000
#> GSM425893 2 0.3508 0.6417 0.252 0.748 0 0 0.000
#> GSM425894 2 0.0000 0.8795 0.000 1.000 0 0 0.000
#> GSM425895 2 0.0000 0.8795 0.000 1.000 0 0 0.000
#> GSM425896 2 0.3612 0.5833 0.000 0.732 0 0 0.268
#> GSM425897 4 0.0000 1.0000 0.000 0.000 0 1 0.000
#> GSM425898 2 0.0000 0.8795 0.000 1.000 0 0 0.000
#> GSM425899 2 0.0290 0.8767 0.008 0.992 0 0 0.000
#> GSM425900 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425901 2 0.0000 0.8795 0.000 1.000 0 0 0.000
#> GSM425902 2 0.0000 0.8795 0.000 1.000 0 0 0.000
#> GSM425903 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425904 1 0.2732 0.7713 0.840 0.160 0 0 0.000
#> GSM425905 2 0.3452 0.6231 0.000 0.756 0 0 0.244
#> GSM425906 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425863 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425864 2 0.0000 0.8795 0.000 1.000 0 0 0.000
#> GSM425865 2 0.0000 0.8795 0.000 1.000 0 0 0.000
#> GSM425866 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425867 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425868 5 0.0162 0.9958 0.000 0.004 0 0 0.996
#> GSM425869 5 0.0290 0.9970 0.000 0.008 0 0 0.992
#> GSM425870 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425871 1 0.4101 0.3929 0.628 0.372 0 0 0.000
#> GSM425872 2 0.0162 0.8785 0.004 0.996 0 0 0.000
#> GSM425873 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425843 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425844 4 0.0000 1.0000 0.000 0.000 0 1 0.000
#> GSM425845 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425846 2 0.2488 0.7921 0.124 0.872 0 0 0.004
#> GSM425847 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425886 2 0.0000 0.8795 0.000 1.000 0 0 0.000
#> GSM425887 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425888 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425889 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425890 4 0.0000 1.0000 0.000 0.000 0 1 0.000
#> GSM425891 2 0.0000 0.8795 0.000 1.000 0 0 0.000
#> GSM425892 2 0.0000 0.8795 0.000 1.000 0 0 0.000
#> GSM425853 1 0.4074 0.4145 0.636 0.364 0 0 0.000
#> GSM425854 2 0.0162 0.8783 0.000 0.996 0 0 0.004
#> GSM425855 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425856 2 0.3895 0.5350 0.320 0.680 0 0 0.000
#> GSM425857 5 0.0162 0.9958 0.000 0.004 0 0 0.996
#> GSM425858 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425859 5 0.0290 0.9970 0.000 0.008 0 0 0.992
#> GSM425860 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425861 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425862 2 0.0162 0.8785 0.004 0.996 0 0 0.000
#> GSM425837 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425838 5 0.0290 0.9970 0.000 0.008 0 0 0.992
#> GSM425839 2 0.0000 0.8795 0.000 1.000 0 0 0.000
#> GSM425840 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425841 5 0.0290 0.9970 0.000 0.008 0 0 0.992
#> GSM425842 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425917 4 0.0000 1.0000 0.000 0.000 0 1 0.000
#> GSM425922 4 0.0000 1.0000 0.000 0.000 0 1 0.000
#> GSM425919 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425920 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425923 4 0.0000 1.0000 0.000 0.000 0 1 0.000
#> GSM425916 4 0.0000 1.0000 0.000 0.000 0 1 0.000
#> GSM425918 4 0.0000 1.0000 0.000 0.000 0 1 0.000
#> GSM425921 4 0.0000 1.0000 0.000 0.000 0 1 0.000
#> GSM425925 2 0.4359 0.2962 0.412 0.584 0 0 0.004
#> GSM425926 5 0.0404 0.9882 0.000 0.012 0 0 0.988
#> GSM425927 1 0.0000 0.9291 1.000 0.000 0 0 0.000
#> GSM425924 4 0.0000 1.0000 0.000 0.000 0 1 0.000
#> GSM425928 4 0.0000 1.0000 0.000 0.000 0 1 0.000
#> GSM425929 3 0.0000 1.0000 0.000 0.000 1 0 0.000
#> GSM425930 3 0.0000 1.0000 0.000 0.000 1 0 0.000
#> GSM425931 3 0.0000 1.0000 0.000 0.000 1 0 0.000
#> GSM425932 3 0.0000 1.0000 0.000 0.000 1 0 0.000
#> GSM425933 3 0.0000 1.0000 0.000 0.000 1 0 0.000
#> GSM425934 3 0.0000 1.0000 0.000 0.000 1 0 0.000
#> GSM425935 3 0.0000 1.0000 0.000 0.000 1 0 0.000
#> GSM425936 3 0.0000 1.0000 0.000 0.000 1 0 0.000
#> GSM425937 3 0.0000 1.0000 0.000 0.000 1 0 0.000
#> GSM425938 3 0.0000 1.0000 0.000 0.000 1 0 0.000
#> GSM425939 3 0.0000 1.0000 0.000 0.000 1 0 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 4 0.0000 0.943 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425908 4 0.1267 0.958 0.000 0.060 0.000 0.940 0.000 0.000
#> GSM425909 2 0.0972 0.817 0.000 0.964 0.000 0.008 0.028 0.000
#> GSM425910 1 0.1753 0.900 0.912 0.004 0.000 0.000 0.084 0.000
#> GSM425911 2 0.2553 0.766 0.008 0.848 0.000 0.000 0.144 0.000
#> GSM425912 1 0.0000 0.926 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425913 6 0.0146 0.996 0.000 0.000 0.000 0.004 0.000 0.996
#> GSM425914 1 0.2234 0.873 0.872 0.004 0.000 0.000 0.124 0.000
#> GSM425915 1 0.2887 0.848 0.844 0.036 0.000 0.000 0.120 0.000
#> GSM425874 4 0.1267 0.958 0.000 0.060 0.000 0.940 0.000 0.000
#> GSM425875 1 0.2871 0.794 0.804 0.004 0.000 0.000 0.192 0.000
#> GSM425876 1 0.0000 0.926 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425877 1 0.1531 0.907 0.928 0.004 0.000 0.000 0.068 0.000
#> GSM425878 5 0.2871 0.733 0.192 0.004 0.000 0.000 0.804 0.000
#> GSM425879 2 0.2320 0.776 0.004 0.864 0.000 0.000 0.132 0.000
#> GSM425880 5 0.2882 0.736 0.180 0.008 0.000 0.000 0.812 0.000
#> GSM425881 1 0.0000 0.926 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425882 2 0.5552 0.030 0.404 0.460 0.000 0.000 0.136 0.000
#> GSM425883 6 0.0000 0.998 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM425884 1 0.0000 0.926 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425885 4 0.0000 0.943 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425848 5 0.3772 0.398 0.004 0.320 0.000 0.004 0.672 0.000
#> GSM425849 5 0.2805 0.736 0.184 0.004 0.000 0.000 0.812 0.000
#> GSM425850 1 0.1806 0.898 0.908 0.004 0.000 0.000 0.088 0.000
#> GSM425851 2 0.3701 0.691 0.100 0.788 0.000 0.000 0.112 0.000
#> GSM425852 2 0.5046 0.407 0.224 0.632 0.000 0.000 0.144 0.000
#> GSM425893 2 0.2723 0.773 0.020 0.856 0.000 0.004 0.120 0.000
#> GSM425894 2 0.0146 0.820 0.000 0.996 0.000 0.004 0.000 0.000
#> GSM425895 2 0.1556 0.805 0.000 0.920 0.000 0.000 0.080 0.000
#> GSM425896 2 0.3515 0.435 0.000 0.676 0.000 0.324 0.000 0.000
#> GSM425897 6 0.0146 0.996 0.000 0.000 0.000 0.004 0.000 0.996
#> GSM425898 2 0.0291 0.820 0.000 0.992 0.000 0.004 0.004 0.000
#> GSM425899 2 0.3996 0.144 0.004 0.512 0.000 0.000 0.484 0.000
#> GSM425900 1 0.2191 0.876 0.876 0.004 0.000 0.000 0.120 0.000
#> GSM425901 2 0.0146 0.820 0.000 0.996 0.000 0.004 0.000 0.000
#> GSM425902 2 0.0146 0.820 0.000 0.996 0.000 0.004 0.000 0.000
#> GSM425903 1 0.2320 0.866 0.864 0.004 0.000 0.000 0.132 0.000
#> GSM425904 1 0.3370 0.797 0.804 0.048 0.000 0.000 0.148 0.000
#> GSM425905 2 0.3464 0.451 0.000 0.688 0.000 0.312 0.000 0.000
#> GSM425906 1 0.0146 0.926 0.996 0.004 0.000 0.000 0.000 0.000
#> GSM425863 1 0.0000 0.926 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425864 2 0.0146 0.820 0.000 0.996 0.000 0.004 0.000 0.000
#> GSM425865 2 0.0146 0.820 0.000 0.996 0.000 0.004 0.000 0.000
#> GSM425866 1 0.2100 0.882 0.884 0.004 0.000 0.000 0.112 0.000
#> GSM425867 1 0.0146 0.926 0.996 0.004 0.000 0.000 0.000 0.000
#> GSM425868 4 0.0000 0.943 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425869 4 0.1267 0.958 0.000 0.060 0.000 0.940 0.000 0.000
#> GSM425870 1 0.0146 0.926 0.996 0.004 0.000 0.000 0.000 0.000
#> GSM425871 5 0.2219 0.684 0.136 0.000 0.000 0.000 0.864 0.000
#> GSM425872 2 0.2288 0.786 0.004 0.876 0.000 0.004 0.116 0.000
#> GSM425873 1 0.0000 0.926 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425843 1 0.0000 0.926 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425844 6 0.0000 0.998 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM425845 1 0.0000 0.926 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425846 5 0.0000 0.658 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM425847 1 0.0000 0.926 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425886 2 0.0291 0.820 0.000 0.992 0.000 0.004 0.004 0.000
#> GSM425887 1 0.1958 0.891 0.896 0.004 0.000 0.000 0.100 0.000
#> GSM425888 1 0.0000 0.926 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425889 1 0.2053 0.885 0.888 0.004 0.000 0.000 0.108 0.000
#> GSM425890 6 0.0146 0.997 0.000 0.000 0.000 0.004 0.000 0.996
#> GSM425891 2 0.1349 0.810 0.004 0.940 0.000 0.000 0.056 0.000
#> GSM425892 2 0.0146 0.820 0.000 0.996 0.000 0.004 0.000 0.000
#> GSM425853 5 0.3961 0.301 0.440 0.004 0.000 0.000 0.556 0.000
#> GSM425854 5 0.3109 0.526 0.000 0.224 0.000 0.004 0.772 0.000
#> GSM425855 1 0.2402 0.858 0.856 0.004 0.000 0.000 0.140 0.000
#> GSM425856 5 0.4282 0.357 0.420 0.020 0.000 0.000 0.560 0.000
#> GSM425857 4 0.0000 0.943 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM425858 1 0.1610 0.902 0.916 0.000 0.000 0.000 0.084 0.000
#> GSM425859 4 0.1267 0.958 0.000 0.060 0.000 0.940 0.000 0.000
#> GSM425860 1 0.0000 0.926 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425861 1 0.0260 0.921 0.992 0.000 0.000 0.000 0.008 0.000
#> GSM425862 2 0.2219 0.776 0.000 0.864 0.000 0.000 0.136 0.000
#> GSM425837 1 0.0000 0.926 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425838 4 0.1267 0.958 0.000 0.060 0.000 0.940 0.000 0.000
#> GSM425839 2 0.0146 0.820 0.000 0.996 0.000 0.004 0.000 0.000
#> GSM425840 1 0.2442 0.853 0.852 0.004 0.000 0.000 0.144 0.000
#> GSM425841 4 0.1267 0.958 0.000 0.060 0.000 0.940 0.000 0.000
#> GSM425842 1 0.0000 0.926 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425917 6 0.0260 0.995 0.000 0.000 0.000 0.008 0.000 0.992
#> GSM425922 6 0.0146 0.997 0.000 0.000 0.000 0.004 0.000 0.996
#> GSM425919 1 0.0000 0.926 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425920 1 0.0291 0.925 0.992 0.004 0.000 0.004 0.000 0.000
#> GSM425923 6 0.0000 0.998 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM425916 6 0.0000 0.998 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM425918 6 0.0000 0.998 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM425921 6 0.0146 0.997 0.000 0.000 0.000 0.004 0.000 0.996
#> GSM425925 5 0.0000 0.658 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM425926 4 0.3752 0.809 0.000 0.064 0.000 0.772 0.164 0.000
#> GSM425927 1 0.0000 0.926 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM425924 6 0.0000 0.998 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM425928 6 0.0000 0.998 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM425929 3 0.0000 0.999 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425930 3 0.0000 0.999 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425931 3 0.0000 0.999 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425932 3 0.0000 0.999 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425933 3 0.0000 0.999 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425934 3 0.0000 0.999 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425935 3 0.0000 0.999 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425936 3 0.0146 0.997 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM425937 3 0.0000 0.999 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM425938 3 0.0146 0.997 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM425939 3 0.0000 0.999 0.000 0.000 1.000 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 disease.state(p) tissue(p) other(p) k
#> ATC:mclust 103 1.30e-08 3.82e-11 1.52e-06 2
#> ATC:mclust 102 2.62e-07 2.37e-11 3.96e-05 3
#> ATC:mclust 99 1.86e-19 1.61e-22 9.29e-12 4
#> ATC:mclust 96 4.34e-18 2.56e-21 3.37e-10 5
#> ATC:mclust 95 3.42e-17 2.96e-19 7.66e-09 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 103 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 0.999 0.970 0.986 0.4671 0.535 0.535
#> 3 3 0.701 0.852 0.916 0.3143 0.777 0.611
#> 4 4 0.784 0.803 0.886 0.1114 0.870 0.687
#> 5 5 0.789 0.785 0.892 0.1031 0.868 0.613
#> 6 6 0.768 0.671 0.850 0.0355 0.973 0.890
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
#> GSM425907 2 0.0000 0.987 0.000 1.000
#> GSM425908 2 0.0000 0.987 0.000 1.000
#> GSM425909 2 0.0000 0.987 0.000 1.000
#> GSM425910 1 0.0000 0.985 1.000 0.000
#> GSM425911 1 0.0000 0.985 1.000 0.000
#> GSM425912 1 0.0000 0.985 1.000 0.000
#> GSM425913 2 0.2778 0.944 0.048 0.952
#> GSM425914 1 0.0000 0.985 1.000 0.000
#> GSM425915 1 0.0000 0.985 1.000 0.000
#> GSM425874 2 0.0000 0.987 0.000 1.000
#> GSM425875 1 0.0000 0.985 1.000 0.000
#> GSM425876 1 0.0000 0.985 1.000 0.000
#> GSM425877 1 0.0000 0.985 1.000 0.000
#> GSM425878 1 0.0000 0.985 1.000 0.000
#> GSM425879 1 0.0376 0.982 0.996 0.004
#> GSM425880 1 0.0000 0.985 1.000 0.000
#> GSM425881 1 0.0000 0.985 1.000 0.000
#> GSM425882 1 0.0376 0.982 0.996 0.004
#> GSM425883 1 0.0000 0.985 1.000 0.000
#> GSM425884 1 0.0000 0.985 1.000 0.000
#> GSM425885 2 0.0000 0.987 0.000 1.000
#> GSM425848 2 0.2236 0.955 0.036 0.964
#> GSM425849 1 0.0000 0.985 1.000 0.000
#> GSM425850 1 0.0000 0.985 1.000 0.000
#> GSM425851 1 0.7815 0.713 0.768 0.232
#> GSM425852 1 0.0000 0.985 1.000 0.000
#> GSM425893 1 0.3879 0.916 0.924 0.076
#> GSM425894 2 0.0000 0.987 0.000 1.000
#> GSM425895 1 0.7139 0.769 0.804 0.196
#> GSM425896 2 0.0000 0.987 0.000 1.000
#> GSM425897 2 0.0000 0.987 0.000 1.000
#> GSM425898 2 0.0000 0.987 0.000 1.000
#> GSM425899 1 0.0000 0.985 1.000 0.000
#> GSM425900 1 0.0000 0.985 1.000 0.000
#> GSM425901 2 0.0000 0.987 0.000 1.000
#> GSM425902 2 0.0000 0.987 0.000 1.000
#> GSM425903 1 0.0000 0.985 1.000 0.000
#> GSM425904 1 0.0000 0.985 1.000 0.000
#> GSM425905 2 0.0000 0.987 0.000 1.000
#> GSM425906 1 0.0000 0.985 1.000 0.000
#> GSM425863 1 0.0000 0.985 1.000 0.000
#> GSM425864 2 0.0000 0.987 0.000 1.000
#> GSM425865 2 0.0000 0.987 0.000 1.000
#> GSM425866 1 0.0000 0.985 1.000 0.000
#> GSM425867 1 0.0000 0.985 1.000 0.000
#> GSM425868 2 0.0000 0.987 0.000 1.000
#> GSM425869 2 0.0000 0.987 0.000 1.000
#> GSM425870 1 0.0000 0.985 1.000 0.000
#> GSM425871 1 0.0000 0.985 1.000 0.000
#> GSM425872 1 0.5178 0.873 0.884 0.116
#> GSM425873 1 0.0000 0.985 1.000 0.000
#> GSM425843 1 0.0000 0.985 1.000 0.000
#> GSM425844 1 0.7219 0.763 0.800 0.200
#> GSM425845 1 0.0000 0.985 1.000 0.000
#> GSM425846 1 0.0000 0.985 1.000 0.000
#> GSM425847 1 0.0000 0.985 1.000 0.000
#> GSM425886 2 0.0000 0.987 0.000 1.000
#> GSM425887 1 0.0000 0.985 1.000 0.000
#> GSM425888 1 0.0000 0.985 1.000 0.000
#> GSM425889 1 0.0000 0.985 1.000 0.000
#> GSM425890 2 0.0000 0.987 0.000 1.000
#> GSM425891 1 0.2423 0.951 0.960 0.040
#> GSM425892 2 0.0000 0.987 0.000 1.000
#> GSM425853 1 0.0000 0.985 1.000 0.000
#> GSM425854 2 0.2948 0.939 0.052 0.948
#> GSM425855 1 0.0000 0.985 1.000 0.000
#> GSM425856 1 0.0000 0.985 1.000 0.000
#> GSM425857 2 0.0000 0.987 0.000 1.000
#> GSM425858 1 0.0000 0.985 1.000 0.000
#> GSM425859 2 0.0000 0.987 0.000 1.000
#> GSM425860 1 0.0000 0.985 1.000 0.000
#> GSM425861 1 0.0000 0.985 1.000 0.000
#> GSM425862 1 0.3733 0.920 0.928 0.072
#> GSM425837 1 0.0000 0.985 1.000 0.000
#> GSM425838 2 0.0000 0.987 0.000 1.000
#> GSM425839 2 0.0000 0.987 0.000 1.000
#> GSM425840 1 0.0000 0.985 1.000 0.000
#> GSM425841 2 0.0000 0.987 0.000 1.000
#> GSM425842 1 0.0000 0.985 1.000 0.000
#> GSM425917 2 0.0000 0.987 0.000 1.000
#> GSM425922 2 0.0000 0.987 0.000 1.000
#> GSM425919 1 0.0000 0.985 1.000 0.000
#> GSM425920 1 0.0000 0.985 1.000 0.000
#> GSM425923 1 0.0000 0.985 1.000 0.000
#> GSM425916 1 0.0000 0.985 1.000 0.000
#> GSM425918 1 0.0000 0.985 1.000 0.000
#> GSM425921 2 0.0000 0.987 0.000 1.000
#> GSM425925 1 0.0000 0.985 1.000 0.000
#> GSM425926 2 0.0000 0.987 0.000 1.000
#> GSM425927 1 0.0000 0.985 1.000 0.000
#> GSM425924 1 0.0938 0.976 0.988 0.012
#> GSM425928 2 0.0000 0.987 0.000 1.000
#> GSM425929 1 0.0000 0.985 1.000 0.000
#> GSM425930 1 0.0000 0.985 1.000 0.000
#> GSM425931 2 0.0000 0.987 0.000 1.000
#> GSM425932 1 0.0000 0.985 1.000 0.000
#> GSM425933 1 0.0000 0.985 1.000 0.000
#> GSM425934 1 0.0000 0.985 1.000 0.000
#> GSM425935 2 0.0000 0.987 0.000 1.000
#> GSM425936 2 0.0000 0.987 0.000 1.000
#> GSM425937 2 0.9087 0.511 0.324 0.676
#> GSM425938 2 0.0000 0.987 0.000 1.000
#> GSM425939 1 0.0000 0.985 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM425907 2 0.0000 0.908 0.000 1.000 0.000
#> GSM425908 2 0.0000 0.908 0.000 1.000 0.000
#> GSM425909 2 0.2711 0.866 0.000 0.912 0.088
#> GSM425910 1 0.0237 0.929 0.996 0.000 0.004
#> GSM425911 1 0.3038 0.870 0.896 0.000 0.104
#> GSM425912 1 0.0424 0.929 0.992 0.000 0.008
#> GSM425913 3 0.3851 0.854 0.004 0.136 0.860
#> GSM425914 1 0.0000 0.929 1.000 0.000 0.000
#> GSM425915 1 0.0424 0.929 0.992 0.000 0.008
#> GSM425874 2 0.0424 0.907 0.000 0.992 0.008
#> GSM425875 1 0.0424 0.926 0.992 0.000 0.008
#> GSM425876 1 0.0424 0.929 0.992 0.000 0.008
#> GSM425877 1 0.0237 0.929 0.996 0.000 0.004
#> GSM425878 1 0.0747 0.923 0.984 0.000 0.016
#> GSM425879 1 0.6949 0.699 0.732 0.156 0.112
#> GSM425880 1 0.3551 0.847 0.868 0.000 0.132
#> GSM425881 1 0.0000 0.929 1.000 0.000 0.000
#> GSM425882 1 0.3532 0.836 0.884 0.108 0.008
#> GSM425883 1 0.3192 0.842 0.888 0.000 0.112
#> GSM425884 1 0.0424 0.929 0.992 0.000 0.008
#> GSM425885 2 0.0237 0.907 0.000 0.996 0.004
#> GSM425848 2 0.5136 0.802 0.044 0.824 0.132
#> GSM425849 1 0.2165 0.896 0.936 0.000 0.064
#> GSM425850 1 0.0237 0.929 0.996 0.000 0.004
#> GSM425851 2 0.4473 0.739 0.164 0.828 0.008
#> GSM425852 1 0.1411 0.913 0.964 0.000 0.036
#> GSM425893 1 0.8792 -0.049 0.456 0.432 0.112
#> GSM425894 2 0.0000 0.908 0.000 1.000 0.000
#> GSM425895 2 0.8071 0.314 0.380 0.548 0.072
#> GSM425896 2 0.0000 0.908 0.000 1.000 0.000
#> GSM425897 3 0.5926 0.553 0.000 0.356 0.644
#> GSM425898 2 0.3965 0.830 0.008 0.860 0.132
#> GSM425899 1 0.3965 0.841 0.860 0.008 0.132
#> GSM425900 1 0.0237 0.929 0.996 0.000 0.004
#> GSM425901 2 0.0237 0.908 0.000 0.996 0.004
#> GSM425902 2 0.2261 0.879 0.000 0.932 0.068
#> GSM425903 1 0.0237 0.929 0.996 0.000 0.004
#> GSM425904 1 0.0000 0.929 1.000 0.000 0.000
#> GSM425905 2 0.0747 0.904 0.000 0.984 0.016
#> GSM425906 1 0.5016 0.653 0.760 0.000 0.240
#> GSM425863 1 0.0424 0.929 0.992 0.000 0.008
#> GSM425864 2 0.0000 0.908 0.000 1.000 0.000
#> GSM425865 2 0.0000 0.908 0.000 1.000 0.000
#> GSM425866 1 0.0000 0.929 1.000 0.000 0.000
#> GSM425867 1 0.0424 0.929 0.992 0.000 0.008
#> GSM425868 2 0.0592 0.902 0.000 0.988 0.012
#> GSM425869 2 0.0000 0.908 0.000 1.000 0.000
#> GSM425870 1 0.0424 0.929 0.992 0.000 0.008
#> GSM425871 1 0.3340 0.857 0.880 0.000 0.120
#> GSM425872 2 0.6189 0.438 0.364 0.632 0.004
#> GSM425873 1 0.0424 0.929 0.992 0.000 0.008
#> GSM425843 1 0.0237 0.929 0.996 0.000 0.004
#> GSM425844 2 0.7065 0.527 0.276 0.672 0.052
#> GSM425845 1 0.0237 0.928 0.996 0.000 0.004
#> GSM425846 1 0.3965 0.841 0.860 0.008 0.132
#> GSM425847 1 0.0424 0.929 0.992 0.000 0.008
#> GSM425886 2 0.0000 0.908 0.000 1.000 0.000
#> GSM425887 1 0.0237 0.928 0.996 0.000 0.004
#> GSM425888 1 0.0237 0.929 0.996 0.000 0.004
#> GSM425889 1 0.0237 0.929 0.996 0.000 0.004
#> GSM425890 2 0.1289 0.892 0.000 0.968 0.032
#> GSM425891 1 0.8352 0.354 0.568 0.332 0.100
#> GSM425892 2 0.0237 0.908 0.000 0.996 0.004
#> GSM425853 1 0.2959 0.873 0.900 0.000 0.100
#> GSM425854 2 0.5538 0.787 0.060 0.808 0.132
#> GSM425855 1 0.0000 0.929 1.000 0.000 0.000
#> GSM425856 1 0.2448 0.889 0.924 0.000 0.076
#> GSM425857 2 0.0000 0.908 0.000 1.000 0.000
#> GSM425858 1 0.0237 0.928 0.996 0.000 0.004
#> GSM425859 2 0.1289 0.897 0.000 0.968 0.032
#> GSM425860 1 0.0237 0.929 0.996 0.000 0.004
#> GSM425861 1 0.0000 0.929 1.000 0.000 0.000
#> GSM425862 1 0.5835 0.472 0.660 0.340 0.000
#> GSM425837 1 0.0424 0.929 0.992 0.000 0.008
#> GSM425838 2 0.0000 0.908 0.000 1.000 0.000
#> GSM425839 2 0.0000 0.908 0.000 1.000 0.000
#> GSM425840 1 0.0000 0.929 1.000 0.000 0.000
#> GSM425841 2 0.0000 0.908 0.000 1.000 0.000
#> GSM425842 1 0.0424 0.929 0.992 0.000 0.008
#> GSM425917 3 0.3686 0.850 0.000 0.140 0.860
#> GSM425922 2 0.1163 0.895 0.000 0.972 0.028
#> GSM425919 1 0.0424 0.929 0.992 0.000 0.008
#> GSM425920 1 0.2066 0.893 0.940 0.000 0.060
#> GSM425923 3 0.5058 0.755 0.244 0.000 0.756
#> GSM425916 1 0.1163 0.918 0.972 0.000 0.028
#> GSM425918 3 0.4233 0.854 0.160 0.004 0.836
#> GSM425921 2 0.1163 0.895 0.000 0.972 0.028
#> GSM425925 1 0.3551 0.847 0.868 0.000 0.132
#> GSM425926 2 0.3784 0.833 0.004 0.864 0.132
#> GSM425927 1 0.0237 0.929 0.996 0.000 0.004
#> GSM425924 3 0.4270 0.868 0.116 0.024 0.860
#> GSM425928 3 0.4654 0.790 0.000 0.208 0.792
#> GSM425929 3 0.3879 0.861 0.152 0.000 0.848
#> GSM425930 3 0.3941 0.859 0.156 0.000 0.844
#> GSM425931 3 0.3752 0.851 0.000 0.144 0.856
#> GSM425932 3 0.3686 0.865 0.140 0.000 0.860
#> GSM425933 3 0.3686 0.865 0.140 0.000 0.860
#> GSM425934 3 0.3879 0.861 0.152 0.000 0.848
#> GSM425935 3 0.3879 0.845 0.000 0.152 0.848
#> GSM425936 3 0.3752 0.850 0.000 0.144 0.856
#> GSM425937 3 0.3965 0.857 0.008 0.132 0.860
#> GSM425938 3 0.3851 0.855 0.004 0.136 0.860
#> GSM425939 3 0.3879 0.862 0.152 0.000 0.848
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM425907 2 0.4720 0.709 0.000 0.672 0.004 0.324
#> GSM425908 2 0.4401 0.752 0.000 0.724 0.004 0.272
#> GSM425909 2 0.0376 0.758 0.000 0.992 0.004 0.004
#> GSM425910 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425911 1 0.5318 0.488 0.624 0.360 0.004 0.012
#> GSM425912 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425913 4 0.0844 0.777 0.004 0.004 0.012 0.980
#> GSM425914 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425915 1 0.3445 0.825 0.864 0.012 0.112 0.012
#> GSM425874 2 0.4456 0.747 0.000 0.716 0.004 0.280
#> GSM425875 1 0.0657 0.944 0.984 0.012 0.000 0.004
#> GSM425876 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425877 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425878 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425879 2 0.5175 0.343 0.328 0.656 0.004 0.012
#> GSM425880 1 0.1690 0.921 0.952 0.032 0.008 0.008
#> GSM425881 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425882 1 0.1677 0.906 0.948 0.040 0.000 0.012
#> GSM425883 4 0.4950 0.513 0.376 0.000 0.004 0.620
#> GSM425884 1 0.0336 0.948 0.992 0.000 0.000 0.008
#> GSM425885 2 0.4837 0.682 0.000 0.648 0.004 0.348
#> GSM425848 2 0.0992 0.751 0.012 0.976 0.008 0.004
#> GSM425849 1 0.0188 0.951 0.996 0.000 0.004 0.000
#> GSM425850 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425851 2 0.7955 0.347 0.304 0.448 0.008 0.240
#> GSM425852 3 0.7341 0.142 0.428 0.100 0.456 0.016
#> GSM425893 2 0.7384 0.132 0.104 0.452 0.428 0.016
#> GSM425894 2 0.3257 0.789 0.000 0.844 0.004 0.152
#> GSM425895 2 0.2839 0.679 0.108 0.884 0.004 0.004
#> GSM425896 2 0.4088 0.770 0.000 0.764 0.004 0.232
#> GSM425897 4 0.0804 0.775 0.000 0.012 0.008 0.980
#> GSM425898 2 0.0336 0.758 0.000 0.992 0.008 0.000
#> GSM425899 1 0.5229 0.528 0.648 0.336 0.008 0.008
#> GSM425900 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425901 2 0.1042 0.770 0.000 0.972 0.008 0.020
#> GSM425902 2 0.0188 0.763 0.000 0.996 0.000 0.004
#> GSM425903 1 0.0376 0.949 0.992 0.004 0.000 0.004
#> GSM425904 1 0.0992 0.939 0.976 0.012 0.004 0.008
#> GSM425905 2 0.3105 0.790 0.000 0.856 0.004 0.140
#> GSM425906 3 0.4008 0.592 0.244 0.000 0.756 0.000
#> GSM425863 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425864 2 0.2480 0.787 0.000 0.904 0.008 0.088
#> GSM425865 2 0.4220 0.765 0.000 0.748 0.004 0.248
#> GSM425866 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425867 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425868 2 0.5168 0.443 0.000 0.504 0.004 0.492
#> GSM425869 2 0.4401 0.752 0.000 0.724 0.004 0.272
#> GSM425870 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425871 1 0.0524 0.946 0.988 0.004 0.008 0.000
#> GSM425872 2 0.5140 0.674 0.056 0.780 0.144 0.020
#> GSM425873 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425843 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425844 4 0.1639 0.779 0.036 0.008 0.004 0.952
#> GSM425845 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425846 1 0.4548 0.686 0.752 0.232 0.008 0.008
#> GSM425847 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425886 2 0.1297 0.756 0.000 0.964 0.020 0.016
#> GSM425887 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425888 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425889 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425890 4 0.1022 0.765 0.000 0.032 0.000 0.968
#> GSM425891 2 0.3636 0.594 0.172 0.820 0.000 0.008
#> GSM425892 2 0.2714 0.790 0.000 0.884 0.004 0.112
#> GSM425853 1 0.0672 0.945 0.984 0.008 0.008 0.000
#> GSM425854 2 0.2010 0.772 0.012 0.940 0.008 0.040
#> GSM425855 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425856 1 0.1909 0.910 0.940 0.048 0.008 0.004
#> GSM425857 2 0.4800 0.692 0.000 0.656 0.004 0.340
#> GSM425858 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425859 2 0.3831 0.780 0.000 0.792 0.004 0.204
#> GSM425860 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425861 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425862 1 0.6151 0.216 0.540 0.420 0.024 0.016
#> GSM425837 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425838 2 0.4483 0.745 0.000 0.712 0.004 0.284
#> GSM425839 2 0.2401 0.788 0.000 0.904 0.004 0.092
#> GSM425840 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425841 2 0.4304 0.746 0.000 0.716 0.000 0.284
#> GSM425842 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425917 4 0.0804 0.776 0.000 0.008 0.012 0.980
#> GSM425922 4 0.2053 0.724 0.000 0.072 0.004 0.924
#> GSM425919 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425920 1 0.0469 0.945 0.988 0.000 0.012 0.000
#> GSM425923 4 0.4978 0.564 0.324 0.000 0.012 0.664
#> GSM425916 4 0.4790 0.506 0.380 0.000 0.000 0.620
#> GSM425918 4 0.4098 0.675 0.204 0.000 0.012 0.784
#> GSM425921 4 0.2266 0.707 0.000 0.084 0.004 0.912
#> GSM425925 1 0.1042 0.937 0.972 0.020 0.008 0.000
#> GSM425926 2 0.3545 0.788 0.000 0.828 0.008 0.164
#> GSM425927 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM425924 4 0.2676 0.759 0.092 0.000 0.012 0.896
#> GSM425928 4 0.1624 0.766 0.000 0.020 0.028 0.952
#> GSM425929 3 0.0469 0.900 0.012 0.000 0.988 0.000
#> GSM425930 3 0.0657 0.899 0.012 0.000 0.984 0.004
#> GSM425931 3 0.0336 0.896 0.000 0.008 0.992 0.000
#> GSM425932 3 0.0469 0.900 0.012 0.000 0.988 0.000
#> GSM425933 3 0.0469 0.900 0.012 0.000 0.988 0.000
#> GSM425934 3 0.0469 0.900 0.012 0.000 0.988 0.000
#> GSM425935 3 0.0524 0.893 0.000 0.008 0.988 0.004
#> GSM425936 3 0.0336 0.896 0.000 0.008 0.992 0.000
#> GSM425937 3 0.0336 0.896 0.000 0.008 0.992 0.000
#> GSM425938 3 0.0336 0.896 0.000 0.008 0.992 0.000
#> GSM425939 3 0.0469 0.900 0.012 0.000 0.988 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM425907 2 0.0290 0.813 0.000 0.992 0.000 0.008 0.000
#> GSM425908 2 0.0671 0.812 0.000 0.980 0.000 0.004 0.016
#> GSM425909 5 0.2732 0.713 0.000 0.160 0.000 0.000 0.840
#> GSM425910 1 0.0000 0.969 1.000 0.000 0.000 0.000 0.000
#> GSM425911 5 0.3037 0.702 0.100 0.032 0.004 0.000 0.864
#> GSM425912 1 0.0000 0.969 1.000 0.000 0.000 0.000 0.000
#> GSM425913 4 0.0290 0.877 0.000 0.008 0.000 0.992 0.000
#> GSM425914 1 0.0162 0.968 0.996 0.000 0.000 0.000 0.004
#> GSM425915 3 0.4787 0.430 0.364 0.000 0.608 0.000 0.028
#> GSM425874 2 0.0324 0.813 0.000 0.992 0.000 0.004 0.004
#> GSM425875 1 0.0000 0.969 1.000 0.000 0.000 0.000 0.000
#> GSM425876 1 0.0162 0.968 0.996 0.000 0.000 0.000 0.004
#> GSM425877 1 0.0162 0.968 0.996 0.000 0.000 0.000 0.004
#> GSM425878 1 0.0290 0.968 0.992 0.000 0.000 0.000 0.008
#> GSM425879 5 0.1469 0.706 0.016 0.036 0.000 0.000 0.948
#> GSM425880 1 0.1121 0.941 0.956 0.000 0.000 0.000 0.044
#> GSM425881 1 0.0000 0.969 1.000 0.000 0.000 0.000 0.000
#> GSM425882 1 0.4638 0.702 0.760 0.124 0.000 0.008 0.108
#> GSM425883 4 0.0865 0.866 0.024 0.000 0.000 0.972 0.004
#> GSM425884 1 0.0290 0.967 0.992 0.000 0.000 0.000 0.008
#> GSM425885 2 0.0566 0.811 0.000 0.984 0.000 0.012 0.004
#> GSM425848 5 0.3752 0.658 0.000 0.292 0.000 0.000 0.708
#> GSM425849 1 0.0162 0.968 0.996 0.000 0.000 0.000 0.004
#> GSM425850 1 0.0912 0.960 0.972 0.000 0.000 0.012 0.016
#> GSM425851 2 0.3002 0.728 0.092 0.872 0.004 0.028 0.004
#> GSM425852 3 0.5115 0.600 0.168 0.000 0.696 0.000 0.136
#> GSM425893 2 0.7060 0.410 0.120 0.572 0.200 0.000 0.108
#> GSM425894 2 0.2471 0.705 0.000 0.864 0.000 0.000 0.136
#> GSM425895 2 0.4752 0.529 0.184 0.724 0.000 0.000 0.092
#> GSM425896 2 0.0404 0.811 0.000 0.988 0.000 0.000 0.012
#> GSM425897 4 0.1701 0.862 0.000 0.016 0.000 0.936 0.048
#> GSM425898 5 0.2127 0.713 0.000 0.108 0.000 0.000 0.892
#> GSM425899 5 0.3929 0.642 0.208 0.028 0.000 0.000 0.764
#> GSM425900 1 0.0290 0.968 0.992 0.000 0.000 0.000 0.008
#> GSM425901 5 0.3430 0.697 0.000 0.220 0.004 0.000 0.776
#> GSM425902 5 0.4182 0.511 0.000 0.400 0.000 0.000 0.600
#> GSM425903 1 0.0290 0.967 0.992 0.000 0.000 0.000 0.008
#> GSM425904 1 0.0880 0.954 0.968 0.000 0.000 0.000 0.032
#> GSM425905 2 0.3766 0.559 0.000 0.728 0.000 0.004 0.268
#> GSM425906 3 0.3424 0.641 0.240 0.000 0.760 0.000 0.000
#> GSM425863 1 0.0000 0.969 1.000 0.000 0.000 0.000 0.000
#> GSM425864 5 0.4455 0.493 0.000 0.404 0.008 0.000 0.588
#> GSM425865 2 0.1768 0.770 0.000 0.924 0.004 0.000 0.072
#> GSM425866 1 0.0880 0.952 0.968 0.000 0.000 0.000 0.032
#> GSM425867 1 0.0000 0.969 1.000 0.000 0.000 0.000 0.000
#> GSM425868 2 0.1502 0.786 0.000 0.940 0.000 0.056 0.004
#> GSM425869 2 0.0000 0.813 0.000 1.000 0.000 0.000 0.000
#> GSM425870 1 0.1082 0.951 0.964 0.000 0.008 0.000 0.028
#> GSM425871 5 0.4159 0.608 0.156 0.000 0.000 0.068 0.776
#> GSM425872 5 0.4919 0.428 0.012 0.028 0.304 0.000 0.656
#> GSM425873 1 0.0162 0.968 0.996 0.000 0.000 0.000 0.004
#> GSM425843 1 0.0000 0.969 1.000 0.000 0.000 0.000 0.000
#> GSM425844 4 0.0162 0.877 0.000 0.000 0.000 0.996 0.004
#> GSM425845 1 0.0162 0.968 0.996 0.000 0.000 0.000 0.004
#> GSM425846 5 0.1644 0.701 0.048 0.004 0.000 0.008 0.940
#> GSM425847 1 0.0162 0.968 0.996 0.000 0.000 0.000 0.004
#> GSM425886 5 0.6190 0.354 0.000 0.420 0.136 0.000 0.444
#> GSM425887 1 0.0794 0.955 0.972 0.000 0.000 0.000 0.028
#> GSM425888 1 0.0290 0.968 0.992 0.000 0.000 0.000 0.008
#> GSM425889 1 0.0404 0.966 0.988 0.000 0.000 0.000 0.012
#> GSM425890 4 0.2966 0.745 0.000 0.184 0.000 0.816 0.000
#> GSM425891 5 0.4736 0.698 0.072 0.216 0.000 0.000 0.712
#> GSM425892 2 0.0703 0.805 0.000 0.976 0.000 0.000 0.024
#> GSM425853 1 0.4235 0.171 0.576 0.000 0.000 0.000 0.424
#> GSM425854 5 0.3395 0.681 0.000 0.236 0.000 0.000 0.764
#> GSM425855 1 0.0290 0.967 0.992 0.000 0.000 0.000 0.008
#> GSM425856 5 0.3715 0.597 0.260 0.004 0.000 0.000 0.736
#> GSM425857 2 0.0404 0.812 0.000 0.988 0.000 0.012 0.000
#> GSM425858 1 0.0290 0.968 0.992 0.000 0.000 0.000 0.008
#> GSM425859 2 0.3487 0.595 0.000 0.780 0.000 0.008 0.212
#> GSM425860 1 0.0000 0.969 1.000 0.000 0.000 0.000 0.000
#> GSM425861 1 0.1106 0.953 0.964 0.000 0.000 0.024 0.012
#> GSM425862 2 0.4977 0.187 0.444 0.532 0.008 0.000 0.016
#> GSM425837 1 0.0579 0.964 0.984 0.000 0.000 0.008 0.008
#> GSM425838 2 0.0000 0.813 0.000 1.000 0.000 0.000 0.000
#> GSM425839 5 0.3913 0.630 0.000 0.324 0.000 0.000 0.676
#> GSM425840 1 0.0404 0.967 0.988 0.000 0.000 0.000 0.012
#> GSM425841 2 0.0579 0.813 0.000 0.984 0.000 0.008 0.008
#> GSM425842 1 0.0000 0.969 1.000 0.000 0.000 0.000 0.000
#> GSM425917 4 0.0290 0.877 0.000 0.008 0.000 0.992 0.000
#> GSM425922 4 0.4440 0.187 0.000 0.468 0.000 0.528 0.004
#> GSM425919 1 0.0162 0.968 0.996 0.000 0.000 0.000 0.004
#> GSM425920 1 0.2630 0.882 0.892 0.000 0.080 0.016 0.012
#> GSM425923 4 0.0451 0.875 0.008 0.000 0.000 0.988 0.004
#> GSM425916 4 0.1168 0.856 0.032 0.000 0.000 0.960 0.008
#> GSM425918 4 0.0162 0.877 0.004 0.000 0.000 0.996 0.000
#> GSM425921 2 0.4443 -0.112 0.000 0.524 0.000 0.472 0.004
#> GSM425925 5 0.4375 0.267 0.420 0.000 0.000 0.004 0.576
#> GSM425926 5 0.4313 0.548 0.000 0.356 0.000 0.008 0.636
#> GSM425927 1 0.0162 0.968 0.996 0.000 0.000 0.000 0.004
#> GSM425924 4 0.0000 0.877 0.000 0.000 0.000 1.000 0.000
#> GSM425928 4 0.4425 0.401 0.000 0.392 0.008 0.600 0.000
#> GSM425929 3 0.0000 0.901 0.000 0.000 1.000 0.000 0.000
#> GSM425930 3 0.0000 0.901 0.000 0.000 1.000 0.000 0.000
#> GSM425931 3 0.0000 0.901 0.000 0.000 1.000 0.000 0.000
#> GSM425932 3 0.0000 0.901 0.000 0.000 1.000 0.000 0.000
#> GSM425933 3 0.0000 0.901 0.000 0.000 1.000 0.000 0.000
#> GSM425934 3 0.0000 0.901 0.000 0.000 1.000 0.000 0.000
#> GSM425935 3 0.0404 0.894 0.000 0.012 0.988 0.000 0.000
#> GSM425936 3 0.0162 0.899 0.000 0.000 0.996 0.004 0.000
#> GSM425937 3 0.0000 0.901 0.000 0.000 1.000 0.000 0.000
#> GSM425938 3 0.0290 0.897 0.000 0.000 0.992 0.008 0.000
#> GSM425939 3 0.0000 0.901 0.000 0.000 1.000 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM425907 2 0.0146 0.7826 0.000 0.996 0.000 0.000 0.000 0.004
#> GSM425908 2 0.0914 0.7814 0.000 0.968 0.000 0.000 0.016 0.016
#> GSM425909 5 0.3156 0.4769 0.000 0.072 0.020 0.000 0.852 0.056
#> GSM425910 1 0.0964 0.9292 0.968 0.000 0.000 0.004 0.012 0.016
#> GSM425911 5 0.3078 0.4544 0.032 0.024 0.012 0.000 0.868 0.064
#> GSM425912 1 0.0922 0.9336 0.968 0.000 0.000 0.004 0.004 0.024
#> GSM425913 4 0.0551 0.8426 0.000 0.008 0.004 0.984 0.000 0.004
#> GSM425914 1 0.1390 0.9245 0.948 0.000 0.000 0.004 0.016 0.032
#> GSM425915 3 0.5857 0.3593 0.252 0.000 0.592 0.000 0.100 0.056
#> GSM425874 2 0.0603 0.7830 0.000 0.980 0.000 0.000 0.004 0.016
#> GSM425875 1 0.1168 0.9267 0.956 0.000 0.000 0.000 0.016 0.028
#> GSM425876 1 0.0748 0.9331 0.976 0.000 0.000 0.004 0.004 0.016
#> GSM425877 1 0.0713 0.9327 0.972 0.000 0.000 0.000 0.000 0.028
#> GSM425878 1 0.1151 0.9317 0.956 0.000 0.000 0.000 0.012 0.032
#> GSM425879 5 0.2909 0.3930 0.000 0.012 0.004 0.000 0.828 0.156
#> GSM425880 1 0.3293 0.7870 0.812 0.000 0.000 0.000 0.140 0.048
#> GSM425881 1 0.0405 0.9323 0.988 0.000 0.000 0.000 0.004 0.008
#> GSM425882 1 0.7236 -0.3135 0.356 0.264 0.008 0.000 0.064 0.308
#> GSM425883 4 0.0520 0.8444 0.008 0.000 0.000 0.984 0.000 0.008
#> GSM425884 1 0.1411 0.9181 0.936 0.000 0.000 0.004 0.000 0.060
#> GSM425885 2 0.0922 0.7763 0.000 0.968 0.000 0.004 0.004 0.024
#> GSM425848 5 0.3630 0.4966 0.004 0.176 0.000 0.000 0.780 0.040
#> GSM425849 1 0.1010 0.9272 0.960 0.000 0.000 0.000 0.004 0.036
#> GSM425850 1 0.1755 0.9254 0.932 0.000 0.000 0.008 0.032 0.028
#> GSM425851 2 0.6665 0.4593 0.112 0.632 0.068 0.068 0.012 0.108
#> GSM425852 3 0.6065 0.3562 0.108 0.000 0.576 0.000 0.248 0.068
#> GSM425893 2 0.7558 -0.0548 0.056 0.408 0.144 0.000 0.068 0.324
#> GSM425894 2 0.3383 0.5283 0.000 0.728 0.000 0.000 0.268 0.004
#> GSM425895 2 0.3656 0.6612 0.108 0.808 0.000 0.000 0.072 0.012
#> GSM425896 2 0.0692 0.7793 0.000 0.976 0.000 0.000 0.020 0.004
#> GSM425897 4 0.4441 0.0949 0.000 0.004 0.004 0.508 0.012 0.472
#> GSM425898 5 0.4039 0.3671 0.000 0.060 0.000 0.000 0.732 0.208
#> GSM425899 5 0.2961 0.4367 0.080 0.012 0.000 0.000 0.860 0.048
#> GSM425900 1 0.1408 0.9230 0.944 0.000 0.000 0.000 0.036 0.020
#> GSM425901 5 0.3568 0.4911 0.000 0.128 0.040 0.000 0.812 0.020
#> GSM425902 5 0.4602 0.3142 0.000 0.384 0.000 0.000 0.572 0.044
#> GSM425903 1 0.1719 0.9143 0.924 0.000 0.000 0.000 0.016 0.060
#> GSM425904 1 0.2803 0.8716 0.864 0.000 0.004 0.000 0.048 0.084
#> GSM425905 2 0.4699 0.5111 0.000 0.668 0.000 0.000 0.104 0.228
#> GSM425906 3 0.5100 0.2299 0.368 0.000 0.552 0.000 0.004 0.076
#> GSM425863 1 0.1007 0.9307 0.956 0.000 0.000 0.000 0.000 0.044
#> GSM425864 2 0.4114 0.0586 0.000 0.532 0.004 0.000 0.460 0.004
#> GSM425865 2 0.1082 0.7734 0.000 0.956 0.000 0.000 0.040 0.004
#> GSM425866 1 0.1909 0.9108 0.920 0.000 0.000 0.004 0.052 0.024
#> GSM425867 1 0.1074 0.9276 0.960 0.000 0.000 0.000 0.012 0.028
#> GSM425868 2 0.1515 0.7739 0.000 0.944 0.000 0.028 0.008 0.020
#> GSM425869 2 0.0260 0.7825 0.000 0.992 0.000 0.000 0.000 0.008
#> GSM425870 1 0.2376 0.8895 0.884 0.000 0.008 0.000 0.012 0.096
#> GSM425871 6 0.6008 0.0000 0.044 0.004 0.000 0.100 0.296 0.556
#> GSM425872 5 0.6486 -0.2443 0.008 0.012 0.240 0.000 0.424 0.316
#> GSM425873 1 0.0508 0.9315 0.984 0.000 0.000 0.004 0.000 0.012
#> GSM425843 1 0.0622 0.9308 0.980 0.000 0.000 0.000 0.008 0.012
#> GSM425844 4 0.0748 0.8434 0.004 0.000 0.000 0.976 0.004 0.016
#> GSM425845 1 0.0622 0.9333 0.980 0.000 0.000 0.000 0.012 0.008
#> GSM425846 5 0.3650 0.2498 0.008 0.000 0.000 0.004 0.716 0.272
#> GSM425847 1 0.0551 0.9326 0.984 0.000 0.000 0.004 0.004 0.008
#> GSM425886 5 0.6351 0.1927 0.000 0.344 0.212 0.000 0.424 0.020
#> GSM425887 1 0.2662 0.8526 0.856 0.000 0.000 0.000 0.024 0.120
#> GSM425888 1 0.1204 0.9221 0.944 0.000 0.000 0.000 0.000 0.056
#> GSM425889 1 0.2009 0.9055 0.904 0.000 0.004 0.000 0.008 0.084
#> GSM425890 4 0.3104 0.6577 0.000 0.184 0.000 0.800 0.000 0.016
#> GSM425891 5 0.4095 0.4832 0.088 0.152 0.000 0.000 0.756 0.004
#> GSM425892 2 0.1285 0.7673 0.000 0.944 0.000 0.000 0.052 0.004
#> GSM425853 5 0.4591 0.0192 0.452 0.000 0.000 0.004 0.516 0.028
#> GSM425854 5 0.4878 0.4123 0.008 0.164 0.000 0.000 0.684 0.144
#> GSM425855 1 0.0972 0.9322 0.964 0.000 0.000 0.000 0.008 0.028
#> GSM425856 5 0.3697 0.3692 0.140 0.000 0.004 0.004 0.796 0.056
#> GSM425857 2 0.0291 0.7816 0.000 0.992 0.000 0.004 0.000 0.004
#> GSM425858 1 0.1003 0.9302 0.964 0.000 0.000 0.004 0.004 0.028
#> GSM425859 2 0.2333 0.7364 0.000 0.884 0.000 0.000 0.092 0.024
#> GSM425860 1 0.0767 0.9324 0.976 0.000 0.000 0.004 0.012 0.008
#> GSM425861 1 0.1082 0.9265 0.956 0.000 0.000 0.004 0.000 0.040
#> GSM425862 2 0.4834 0.2767 0.348 0.604 0.024 0.000 0.016 0.008
#> GSM425837 1 0.0922 0.9326 0.968 0.000 0.000 0.004 0.004 0.024
#> GSM425838 2 0.0000 0.7825 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM425839 5 0.3906 0.4648 0.000 0.216 0.008 0.000 0.744 0.032
#> GSM425840 1 0.1644 0.9075 0.920 0.000 0.000 0.000 0.004 0.076
#> GSM425841 2 0.0603 0.7829 0.000 0.980 0.000 0.000 0.004 0.016
#> GSM425842 1 0.0777 0.9331 0.972 0.000 0.000 0.000 0.004 0.024
#> GSM425917 4 0.0291 0.8444 0.000 0.004 0.000 0.992 0.000 0.004
#> GSM425922 2 0.4403 -0.0122 0.000 0.508 0.000 0.468 0.000 0.024
#> GSM425919 1 0.0858 0.9290 0.968 0.000 0.000 0.004 0.000 0.028
#> GSM425920 1 0.4162 0.7233 0.760 0.000 0.128 0.008 0.000 0.104
#> GSM425923 4 0.0405 0.8450 0.008 0.000 0.000 0.988 0.000 0.004
#> GSM425916 4 0.0909 0.8373 0.012 0.000 0.000 0.968 0.000 0.020
#> GSM425918 4 0.0291 0.8456 0.004 0.000 0.000 0.992 0.000 0.004
#> GSM425921 2 0.4273 0.2649 0.000 0.596 0.000 0.380 0.000 0.024
#> GSM425925 5 0.5442 0.0473 0.204 0.000 0.000 0.000 0.576 0.220
#> GSM425926 5 0.5312 0.2692 0.000 0.364 0.000 0.000 0.524 0.112
#> GSM425927 1 0.0692 0.9304 0.976 0.000 0.000 0.004 0.000 0.020
#> GSM425924 4 0.0547 0.8397 0.000 0.000 0.000 0.980 0.000 0.020
#> GSM425928 4 0.4810 0.3874 0.000 0.352 0.016 0.596 0.000 0.036
#> GSM425929 3 0.0692 0.8423 0.000 0.000 0.976 0.004 0.000 0.020
#> GSM425930 3 0.0458 0.8457 0.000 0.000 0.984 0.000 0.000 0.016
#> GSM425931 3 0.0363 0.8465 0.000 0.000 0.988 0.000 0.000 0.012
#> GSM425932 3 0.0146 0.8470 0.000 0.000 0.996 0.000 0.000 0.004
#> GSM425933 3 0.0260 0.8467 0.000 0.000 0.992 0.000 0.000 0.008
#> GSM425934 3 0.0363 0.8465 0.000 0.000 0.988 0.000 0.000 0.012
#> GSM425935 3 0.2030 0.7752 0.000 0.064 0.908 0.000 0.000 0.028
#> GSM425936 3 0.0692 0.8449 0.000 0.000 0.976 0.004 0.000 0.020
#> GSM425937 3 0.0547 0.8443 0.000 0.000 0.980 0.000 0.000 0.020
#> GSM425938 3 0.0692 0.8449 0.000 0.000 0.976 0.004 0.000 0.020
#> GSM425939 3 0.0260 0.8466 0.000 0.000 0.992 0.000 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 disease.state(p) tissue(p) other(p) k
#> ATC:NMF 103 4.46e-01 5.56e-01 7.07e-01 2
#> ATC:NMF 98 6.35e-14 8.69e-14 8.14e-08 3
#> ATC:NMF 96 4.60e-17 5.43e-20 3.74e-10 4
#> ATC:NMF 92 1.27e-15 2.21e-17 1.99e-07 5
#> ATC:NMF 72 1.59e-15 9.18e-18 5.34e-09 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