Date: 2019-12-25 21:41:08 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 27425 rows and 116 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] 27425 116
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 | ||
|---|---|---|---|---|---|---|
| SD:skmeans | 2 | 1.000 | 0.976 | 0.990 | ** | |
| MAD:skmeans | 2 | 1.000 | 0.976 | 0.990 | ** | |
| ATC:kmeans | 2 | 1.000 | 0.995 | 0.998 | ** | |
| ATC:mclust | 2 | 1.000 | 0.988 | 0.995 | ** | |
| ATC:NMF | 2 | 1.000 | 0.963 | 0.985 | ** | |
| ATC:pam | 4 | 0.979 | 0.947 | 0.977 | ** | 2 |
| CV:skmeans | 2 | 0.947 | 0.947 | 0.979 | * | |
| CV:NMF | 2 | 0.945 | 0.948 | 0.976 | * | |
| CV:mclust | 2 | 0.945 | 0.934 | 0.973 | * | |
| ATC:skmeans | 4 | 0.918 | 0.889 | 0.939 | * | 2 |
| SD:NMF | 2 | 0.912 | 0.940 | 0.974 | * | |
| SD:kmeans | 2 | 0.861 | 0.930 | 0.967 | ||
| MAD:NMF | 2 | 0.844 | 0.919 | 0.965 | ||
| MAD:kmeans | 2 | 0.838 | 0.910 | 0.951 | ||
| MAD:mclust | 6 | 0.832 | 0.787 | 0.894 | ||
| CV:kmeans | 2 | 0.821 | 0.908 | 0.927 | ||
| SD:mclust | 2 | 0.702 | 0.930 | 0.926 | ||
| SD:pam | 2 | 0.615 | 0.873 | 0.935 | ||
| MAD:hclust | 2 | 0.576 | 0.824 | 0.915 | ||
| CV:hclust | 4 | 0.544 | 0.779 | 0.865 | ||
| CV:pam | 4 | 0.538 | 0.681 | 0.853 | ||
| MAD:pam | 2 | 0.528 | 0.741 | 0.895 | ||
| SD:hclust | 4 | 0.473 | 0.703 | 0.789 | ||
| ATC:hclust | 2 | 0.354 | 0.697 | 0.867 |
**: 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 0.912 0.940 0.974 0.501 0.498 0.498
#> CV:NMF 2 0.945 0.948 0.976 0.501 0.499 0.499
#> MAD:NMF 2 0.844 0.919 0.965 0.499 0.499 0.499
#> ATC:NMF 2 1.000 0.963 0.985 0.504 0.496 0.496
#> SD:skmeans 2 1.000 0.976 0.990 0.504 0.496 0.496
#> CV:skmeans 2 0.947 0.947 0.979 0.505 0.496 0.496
#> MAD:skmeans 2 1.000 0.976 0.990 0.504 0.496 0.496
#> ATC:skmeans 2 1.000 0.998 0.999 0.504 0.496 0.496
#> SD:mclust 2 0.702 0.930 0.926 0.465 0.521 0.521
#> CV:mclust 2 0.945 0.934 0.973 0.124 0.886 0.886
#> MAD:mclust 2 0.466 0.800 0.867 0.460 0.529 0.529
#> ATC:mclust 2 1.000 0.988 0.995 0.502 0.498 0.498
#> SD:kmeans 2 0.861 0.930 0.967 0.497 0.497 0.497
#> CV:kmeans 2 0.821 0.908 0.927 0.465 0.498 0.498
#> MAD:kmeans 2 0.838 0.910 0.951 0.487 0.517 0.517
#> ATC:kmeans 2 1.000 0.995 0.998 0.504 0.496 0.496
#> SD:pam 2 0.615 0.873 0.935 0.495 0.503 0.503
#> CV:pam 2 0.510 0.627 0.843 0.490 0.503 0.503
#> MAD:pam 2 0.528 0.741 0.895 0.497 0.497 0.497
#> ATC:pam 2 1.000 0.979 0.992 0.501 0.499 0.499
#> SD:hclust 2 0.208 0.725 0.810 0.417 0.544 0.544
#> CV:hclust 2 0.537 0.904 0.903 0.148 0.933 0.933
#> MAD:hclust 2 0.576 0.824 0.915 0.454 0.544 0.544
#> ATC:hclust 2 0.354 0.697 0.867 0.448 0.505 0.505
get_stats(res_list, k = 3)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 3 0.670 0.801 0.910 0.305 0.767 0.566
#> CV:NMF 3 0.684 0.822 0.906 0.304 0.769 0.569
#> MAD:NMF 3 0.677 0.775 0.902 0.307 0.752 0.547
#> ATC:NMF 3 0.541 0.706 0.818 0.269 0.867 0.736
#> SD:skmeans 3 0.750 0.863 0.914 0.306 0.748 0.534
#> CV:skmeans 3 0.720 0.841 0.905 0.297 0.755 0.545
#> MAD:skmeans 3 0.754 0.855 0.920 0.307 0.728 0.505
#> ATC:skmeans 3 0.831 0.905 0.945 0.217 0.894 0.788
#> SD:mclust 3 0.416 0.573 0.723 0.320 0.766 0.579
#> CV:mclust 3 0.207 0.593 0.808 2.440 0.637 0.607
#> MAD:mclust 3 0.358 0.511 0.720 0.293 0.795 0.629
#> ATC:mclust 3 0.766 0.799 0.895 0.171 0.965 0.930
#> SD:kmeans 3 0.575 0.600 0.829 0.320 0.732 0.511
#> CV:kmeans 3 0.517 0.598 0.733 0.385 0.718 0.491
#> MAD:kmeans 3 0.592 0.728 0.843 0.348 0.760 0.559
#> ATC:kmeans 3 0.720 0.834 0.910 0.319 0.741 0.523
#> SD:pam 3 0.496 0.413 0.602 0.323 0.777 0.586
#> CV:pam 3 0.386 0.649 0.808 0.145 0.873 0.770
#> MAD:pam 3 0.445 0.562 0.771 0.326 0.737 0.521
#> ATC:pam 3 0.873 0.932 0.964 0.305 0.770 0.571
#> SD:hclust 3 0.354 0.457 0.754 0.418 0.731 0.546
#> CV:hclust 3 0.438 0.651 0.851 2.369 0.531 0.497
#> MAD:hclust 3 0.414 0.605 0.767 0.375 0.770 0.586
#> ATC:hclust 3 0.511 0.676 0.840 0.418 0.635 0.414
get_stats(res_list, k = 4)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 4 0.745 0.814 0.910 0.1123 0.852 0.613
#> CV:NMF 4 0.607 0.579 0.794 0.1012 0.802 0.519
#> MAD:NMF 4 0.690 0.752 0.873 0.1163 0.859 0.628
#> ATC:NMF 4 0.642 0.710 0.831 0.0992 0.843 0.618
#> SD:skmeans 4 0.698 0.745 0.819 0.1246 0.851 0.592
#> CV:skmeans 4 0.589 0.596 0.778 0.1233 0.900 0.720
#> MAD:skmeans 4 0.749 0.851 0.894 0.1309 0.845 0.578
#> ATC:skmeans 4 0.918 0.889 0.939 0.1130 0.922 0.805
#> SD:mclust 4 0.629 0.692 0.816 0.1475 0.824 0.574
#> CV:mclust 4 0.423 0.586 0.803 0.4388 0.669 0.482
#> MAD:mclust 4 0.394 0.424 0.680 0.1696 0.766 0.477
#> ATC:mclust 4 0.571 0.421 0.744 0.1791 0.866 0.718
#> SD:kmeans 4 0.552 0.607 0.724 0.1207 0.830 0.550
#> CV:kmeans 4 0.622 0.728 0.844 0.0947 0.933 0.809
#> MAD:kmeans 4 0.576 0.621 0.785 0.1268 0.862 0.616
#> ATC:kmeans 4 0.747 0.856 0.899 0.1227 0.795 0.475
#> SD:pam 4 0.639 0.607 0.788 0.1343 0.746 0.403
#> CV:pam 4 0.538 0.681 0.853 0.2045 0.780 0.566
#> MAD:pam 4 0.685 0.639 0.816 0.1227 0.854 0.617
#> ATC:pam 4 0.979 0.947 0.977 0.1105 0.911 0.749
#> SD:hclust 4 0.473 0.703 0.789 0.1561 0.777 0.505
#> CV:hclust 4 0.544 0.779 0.865 0.3603 0.720 0.469
#> MAD:hclust 4 0.490 0.598 0.770 0.1080 0.879 0.684
#> ATC:hclust 4 0.624 0.669 0.810 0.1490 0.838 0.587
get_stats(res_list, k = 5)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 5 0.609 0.587 0.769 0.0671 0.909 0.701
#> CV:NMF 5 0.672 0.608 0.794 0.0559 0.877 0.621
#> MAD:NMF 5 0.593 0.599 0.780 0.0746 0.877 0.601
#> ATC:NMF 5 0.561 0.609 0.757 0.0747 0.903 0.690
#> SD:skmeans 5 0.725 0.722 0.834 0.0612 0.906 0.652
#> CV:skmeans 5 0.614 0.603 0.747 0.0606 0.929 0.756
#> MAD:skmeans 5 0.777 0.750 0.871 0.0565 0.917 0.694
#> ATC:skmeans 5 0.790 0.667 0.833 0.0799 0.989 0.966
#> SD:mclust 5 0.712 0.582 0.809 0.1003 0.860 0.561
#> CV:mclust 5 0.615 0.746 0.812 0.1817 0.936 0.822
#> MAD:mclust 5 0.693 0.720 0.844 0.0870 0.858 0.571
#> ATC:mclust 5 0.593 0.436 0.681 0.0813 0.814 0.545
#> SD:kmeans 5 0.585 0.460 0.633 0.0673 0.903 0.648
#> CV:kmeans 5 0.566 0.514 0.712 0.0746 0.955 0.859
#> MAD:kmeans 5 0.642 0.587 0.739 0.0653 0.862 0.528
#> ATC:kmeans 5 0.724 0.588 0.760 0.0595 0.946 0.793
#> SD:pam 5 0.621 0.586 0.767 0.0308 0.917 0.703
#> CV:pam 5 0.575 0.621 0.807 0.1106 0.897 0.698
#> MAD:pam 5 0.665 0.679 0.818 0.0658 0.857 0.544
#> ATC:pam 5 0.878 0.843 0.929 0.0725 0.951 0.825
#> SD:hclust 5 0.492 0.576 0.719 0.0594 0.959 0.870
#> CV:hclust 5 0.574 0.732 0.787 0.0923 0.932 0.786
#> MAD:hclust 5 0.520 0.624 0.727 0.0617 0.921 0.753
#> ATC:hclust 5 0.712 0.645 0.819 0.0551 0.942 0.789
get_stats(res_list, k = 6)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 6 0.618 0.492 0.712 0.0427 0.920 0.688
#> CV:NMF 6 0.623 0.532 0.727 0.0482 0.909 0.670
#> MAD:NMF 6 0.594 0.448 0.607 0.0415 0.951 0.791
#> ATC:NMF 6 0.609 0.567 0.751 0.0523 0.898 0.630
#> SD:skmeans 6 0.755 0.703 0.803 0.0378 0.932 0.696
#> CV:skmeans 6 0.650 0.522 0.709 0.0417 0.907 0.645
#> MAD:skmeans 6 0.886 0.801 0.892 0.0370 0.931 0.703
#> ATC:skmeans 6 0.747 0.476 0.763 0.0540 0.908 0.716
#> SD:mclust 6 0.843 0.775 0.904 0.0472 0.897 0.580
#> CV:mclust 6 0.811 0.852 0.916 0.0962 0.836 0.518
#> MAD:mclust 6 0.832 0.787 0.894 0.0701 0.884 0.560
#> ATC:mclust 6 0.615 0.611 0.740 0.0544 0.833 0.493
#> SD:kmeans 6 0.664 0.545 0.683 0.0439 0.867 0.471
#> CV:kmeans 6 0.672 0.568 0.712 0.0620 0.839 0.495
#> MAD:kmeans 6 0.692 0.583 0.730 0.0457 0.929 0.672
#> ATC:kmeans 6 0.737 0.717 0.789 0.0361 0.920 0.679
#> SD:pam 6 0.712 0.513 0.770 0.0551 0.837 0.466
#> CV:pam 6 0.604 0.567 0.756 0.0691 0.909 0.674
#> MAD:pam 6 0.736 0.681 0.824 0.0327 0.956 0.800
#> ATC:pam 6 0.836 0.718 0.865 0.0340 0.970 0.873
#> SD:hclust 6 0.498 0.600 0.680 0.0589 0.958 0.855
#> CV:hclust 6 0.595 0.683 0.727 0.0576 0.955 0.826
#> MAD:hclust 6 0.530 0.583 0.639 0.0617 0.950 0.809
#> ATC:hclust 6 0.760 0.619 0.768 0.0340 0.903 0.636
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) k
#> SD:NMF 113 0.02720 2
#> CV:NMF 115 0.05801 2
#> MAD:NMF 114 0.04030 2
#> ATC:NMF 115 0.00706 2
#> SD:skmeans 114 0.02080 2
#> CV:skmeans 113 0.02024 2
#> MAD:skmeans 115 0.01478 2
#> ATC:skmeans 116 0.00835 2
#> SD:mclust 115 0.06107 2
#> CV:mclust 113 0.06713 2
#> MAD:mclust 113 0.08641 2
#> ATC:mclust 115 0.02352 2
#> SD:kmeans 115 0.02576 2
#> CV:kmeans 112 0.07133 2
#> MAD:kmeans 114 0.05645 2
#> ATC:kmeans 116 0.00835 2
#> SD:pam 114 0.05460 2
#> CV:pam 82 0.00815 2
#> MAD:pam 101 0.14111 2
#> ATC:pam 114 0.00782 2
#> SD:hclust 102 0.16156 2
#> CV:hclust 116 0.01242 2
#> MAD:hclust 110 0.15104 2
#> ATC:hclust 97 0.01505 2
test_to_known_factors(res_list, k = 3)
#> n disease.state(p) k
#> SD:NMF 107 0.02848 3
#> CV:NMF 110 0.00673 3
#> MAD:NMF 101 0.04363 3
#> ATC:NMF 104 0.15393 3
#> SD:skmeans 112 0.10850 3
#> CV:skmeans 109 0.01386 3
#> MAD:skmeans 108 0.05864 3
#> ATC:skmeans 112 0.00141 3
#> SD:mclust 61 0.44765 3
#> CV:mclust 100 0.00019 3
#> MAD:mclust 65 0.54267 3
#> ATC:mclust 100 0.05748 3
#> SD:kmeans 84 0.08498 3
#> CV:kmeans 85 0.00212 3
#> MAD:kmeans 111 0.03210 3
#> ATC:kmeans 109 0.03614 3
#> SD:pam 61 0.14258 3
#> CV:pam 93 0.00180 3
#> MAD:pam 88 0.00557 3
#> ATC:pam 115 0.01264 3
#> SD:hclust 78 0.19843 3
#> CV:hclust 86 0.01132 3
#> MAD:hclust 80 0.04549 3
#> ATC:hclust 91 0.22009 3
test_to_known_factors(res_list, k = 4)
#> n disease.state(p) k
#> SD:NMF 107 3.38e-01 4
#> CV:NMF 83 2.51e-01 4
#> MAD:NMF 106 3.87e-01 4
#> ATC:NMF 102 4.07e-01 4
#> SD:skmeans 105 4.11e-02 4
#> CV:skmeans 87 1.60e-04 4
#> MAD:skmeans 112 8.91e-03 4
#> ATC:skmeans 111 2.04e-02 4
#> SD:mclust 102 1.40e-01 4
#> CV:mclust 77 2.82e-08 4
#> MAD:mclust 46 1.37e-01 4
#> ATC:mclust 77 1.17e-01 4
#> SD:kmeans 82 1.56e-03 4
#> CV:kmeans 110 6.10e-05 4
#> MAD:kmeans 92 1.35e-03 4
#> ATC:kmeans 114 5.67e-02 4
#> SD:pam 87 6.39e-02 4
#> CV:pam 95 4.25e-07 4
#> MAD:pam 102 8.82e-03 4
#> ATC:pam 114 3.16e-02 4
#> SD:hclust 110 2.16e-03 4
#> CV:hclust 104 1.03e-04 4
#> MAD:hclust 82 1.55e-03 4
#> ATC:hclust 90 3.44e-01 4
test_to_known_factors(res_list, k = 5)
#> n disease.state(p) k
#> SD:NMF 82 1.36e-01 5
#> CV:NMF 81 1.63e-03 5
#> MAD:NMF 87 2.18e-01 5
#> ATC:NMF 90 1.15e-01 5
#> SD:skmeans 97 8.63e-02 5
#> CV:skmeans 87 4.17e-07 5
#> MAD:skmeans 99 1.01e-01 5
#> ATC:skmeans 93 2.05e-01 5
#> SD:mclust 69 1.72e-01 5
#> CV:mclust 110 2.31e-10 5
#> MAD:mclust 107 9.34e-02 5
#> ATC:mclust 59 1.12e-01 5
#> SD:kmeans 65 2.34e-05 5
#> CV:kmeans 91 2.40e-06 5
#> MAD:kmeans 78 4.51e-04 5
#> ATC:kmeans 82 1.07e-01 5
#> SD:pam 87 4.10e-03 5
#> CV:pam 92 4.46e-08 5
#> MAD:pam 97 2.30e-05 5
#> ATC:pam 109 6.15e-02 5
#> SD:hclust 78 1.06e-02 5
#> CV:hclust 104 6.66e-06 5
#> MAD:hclust 88 1.89e-03 5
#> ATC:hclust 73 4.13e-01 5
test_to_known_factors(res_list, k = 6)
#> n disease.state(p) k
#> SD:NMF 68 1.17e-02 6
#> CV:NMF 69 3.11e-05 6
#> MAD:NMF 50 3.27e-01 6
#> ATC:NMF 85 2.30e-02 6
#> SD:skmeans 95 7.15e-03 6
#> CV:skmeans 80 1.89e-07 6
#> MAD:skmeans 108 5.83e-03 6
#> ATC:skmeans 58 1.51e-01 6
#> SD:mclust 99 8.71e-04 6
#> CV:mclust 113 4.66e-08 6
#> MAD:mclust 105 4.44e-04 6
#> ATC:mclust 98 4.64e-02 6
#> SD:kmeans 68 2.71e-05 6
#> CV:kmeans 81 2.82e-06 6
#> MAD:kmeans 78 1.52e-04 6
#> ATC:kmeans 103 6.00e-02 6
#> SD:pam 69 1.23e-04 6
#> CV:pam 83 2.80e-08 6
#> MAD:pam 99 2.37e-05 6
#> ATC:pam 96 6.75e-03 6
#> SD:hclust 88 5.68e-03 6
#> CV:hclust 103 8.91e-08 6
#> MAD:hclust 83 7.13e-05 6
#> ATC:hclust 83 3.16e-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 27425 rows and 116 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 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 0.208 0.725 0.810 0.4171 0.544 0.544
#> 3 3 0.354 0.457 0.754 0.4177 0.731 0.546
#> 4 4 0.473 0.703 0.789 0.1561 0.777 0.505
#> 5 5 0.492 0.576 0.719 0.0594 0.959 0.870
#> 6 6 0.498 0.600 0.680 0.0589 0.958 0.855
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
#> GSM613638 2 0.9552 0.4942 0.376 0.624
#> GSM613639 1 0.9866 0.2376 0.568 0.432
#> GSM613640 2 0.9954 0.2429 0.460 0.540
#> GSM613641 1 0.4690 0.9077 0.900 0.100
#> GSM613642 2 0.5519 0.7822 0.128 0.872
#> GSM613643 2 0.9998 0.1090 0.492 0.508
#> GSM613644 2 0.9993 0.1454 0.484 0.516
#> GSM613645 1 0.8386 0.6848 0.732 0.268
#> GSM613646 2 0.8499 0.6756 0.276 0.724
#> GSM613647 2 0.8267 0.6676 0.260 0.740
#> GSM613648 2 0.7453 0.7172 0.212 0.788
#> GSM613649 2 0.0376 0.7822 0.004 0.996
#> GSM613650 2 0.9775 0.4415 0.412 0.588
#> GSM613651 1 0.9988 0.0191 0.520 0.480
#> GSM613652 1 0.4690 0.9077 0.900 0.100
#> GSM613653 2 0.9661 0.4937 0.392 0.608
#> GSM613654 1 0.4690 0.9077 0.900 0.100
#> GSM613655 1 0.4690 0.9077 0.900 0.100
#> GSM613656 1 0.4690 0.9077 0.900 0.100
#> GSM613657 2 0.0376 0.7822 0.004 0.996
#> GSM613658 1 0.4690 0.9077 0.900 0.100
#> GSM613659 2 0.8016 0.7108 0.244 0.756
#> GSM613660 2 0.2603 0.7949 0.044 0.956
#> GSM613661 1 0.4690 0.9077 0.900 0.100
#> GSM613662 2 0.2778 0.7947 0.048 0.952
#> GSM613663 1 0.4690 0.9077 0.900 0.100
#> GSM613664 2 0.2948 0.7952 0.052 0.948
#> GSM613665 2 0.2778 0.7947 0.048 0.952
#> GSM613666 1 0.4690 0.9077 0.900 0.100
#> GSM613667 1 0.8386 0.6848 0.732 0.268
#> GSM613668 1 0.4690 0.9077 0.900 0.100
#> GSM613669 1 0.4690 0.9077 0.900 0.100
#> GSM613670 2 0.2778 0.7947 0.048 0.952
#> GSM613671 1 0.4690 0.9077 0.900 0.100
#> GSM613672 1 0.4690 0.9077 0.900 0.100
#> GSM613673 1 0.5059 0.9014 0.888 0.112
#> GSM613674 2 0.2778 0.7947 0.048 0.952
#> GSM613675 2 0.3584 0.7931 0.068 0.932
#> GSM613676 2 0.2778 0.7947 0.048 0.952
#> GSM613677 2 0.7674 0.7369 0.224 0.776
#> GSM613678 2 0.8327 0.7012 0.264 0.736
#> GSM613679 2 0.2778 0.7947 0.048 0.952
#> GSM613680 1 0.4690 0.9077 0.900 0.100
#> GSM613681 1 0.4815 0.9060 0.896 0.104
#> GSM613682 1 0.6712 0.8391 0.824 0.176
#> GSM613683 1 0.4690 0.9077 0.900 0.100
#> GSM613684 2 0.2603 0.7946 0.044 0.956
#> GSM613685 2 0.2778 0.7947 0.048 0.952
#> GSM613686 1 0.7602 0.7782 0.780 0.220
#> GSM613687 1 0.4815 0.9060 0.896 0.104
#> GSM613688 2 0.2778 0.7957 0.048 0.952
#> GSM613689 2 0.7745 0.7073 0.228 0.772
#> GSM613690 2 0.5946 0.7623 0.144 0.856
#> GSM613691 2 0.6343 0.7661 0.160 0.840
#> GSM613692 1 0.9393 0.5060 0.644 0.356
#> GSM613693 2 0.2603 0.7946 0.044 0.956
#> GSM613694 2 0.7883 0.7001 0.236 0.764
#> GSM613695 2 0.8081 0.6814 0.248 0.752
#> GSM613696 2 0.7602 0.7325 0.220 0.780
#> GSM613697 1 0.9988 0.0191 0.520 0.480
#> GSM613698 2 0.9170 0.5815 0.332 0.668
#> GSM613699 2 0.7745 0.7073 0.228 0.772
#> GSM613700 2 0.2778 0.7947 0.048 0.952
#> GSM613701 2 0.9608 0.5048 0.384 0.616
#> GSM613702 2 0.9552 0.5224 0.376 0.624
#> GSM613703 1 0.4939 0.9038 0.892 0.108
#> GSM613704 2 0.2778 0.7947 0.048 0.952
#> GSM613705 2 0.9522 0.5001 0.372 0.628
#> GSM613706 2 0.9608 0.5048 0.384 0.616
#> GSM613707 2 0.2778 0.7947 0.048 0.952
#> GSM613708 1 0.7299 0.8171 0.796 0.204
#> GSM613709 1 0.4690 0.9077 0.900 0.100
#> GSM613710 2 0.2603 0.7949 0.044 0.956
#> GSM613711 2 0.0376 0.7822 0.004 0.996
#> GSM613712 2 0.9686 0.4092 0.396 0.604
#> GSM613713 2 0.2603 0.7946 0.044 0.956
#> GSM613714 2 0.8081 0.6814 0.248 0.752
#> GSM613715 2 0.5629 0.7669 0.132 0.868
#> GSM613716 2 0.7376 0.7217 0.208 0.792
#> GSM613717 2 0.0376 0.7822 0.004 0.996
#> GSM613718 2 0.0376 0.7822 0.004 0.996
#> GSM613719 2 0.9661 0.4937 0.392 0.608
#> GSM613720 2 0.2423 0.7928 0.040 0.960
#> GSM613721 2 0.4298 0.7921 0.088 0.912
#> GSM613722 2 0.3584 0.7947 0.068 0.932
#> GSM613723 1 0.4690 0.9077 0.900 0.100
#> GSM613724 1 0.4690 0.9077 0.900 0.100
#> GSM613725 2 0.2778 0.7947 0.048 0.952
#> GSM613726 1 0.9393 0.4625 0.644 0.356
#> GSM613727 1 0.4690 0.9077 0.900 0.100
#> GSM613728 2 0.7056 0.7541 0.192 0.808
#> GSM613729 1 0.4939 0.9038 0.892 0.108
#> GSM613730 2 0.7883 0.7244 0.236 0.764
#> GSM613731 2 0.9998 0.1090 0.492 0.508
#> GSM613732 2 0.0376 0.7822 0.004 0.996
#> GSM613733 2 0.0376 0.7822 0.004 0.996
#> GSM613734 1 0.4690 0.9077 0.900 0.100
#> GSM613735 1 0.4690 0.9077 0.900 0.100
#> GSM613736 2 0.0376 0.7831 0.004 0.996
#> GSM613737 2 0.8499 0.6486 0.276 0.724
#> GSM613738 1 0.5946 0.8783 0.856 0.144
#> GSM613739 1 0.5946 0.8783 0.856 0.144
#> GSM613740 2 0.0376 0.7822 0.004 0.996
#> GSM613741 2 0.9661 0.4937 0.392 0.608
#> GSM613742 1 0.5946 0.8783 0.856 0.144
#> GSM613743 2 0.0376 0.7831 0.004 0.996
#> GSM613744 2 0.0376 0.7822 0.004 0.996
#> GSM613745 2 0.8499 0.6756 0.276 0.724
#> GSM613746 2 0.2778 0.7947 0.048 0.952
#> GSM613747 1 0.4690 0.9077 0.900 0.100
#> GSM613748 2 0.7883 0.7244 0.236 0.764
#> GSM613749 2 0.9608 0.5061 0.384 0.616
#> GSM613750 2 0.4690 0.6926 0.100 0.900
#> GSM613751 2 0.4690 0.6926 0.100 0.900
#> GSM613752 2 0.4690 0.6926 0.100 0.900
#> GSM613753 2 0.4690 0.6926 0.100 0.900
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM613638 3 0.9776 0.4080 0.380 0.232 0.388
#> GSM613639 1 0.8571 0.1877 0.588 0.140 0.272
#> GSM613640 1 0.9354 -0.1840 0.472 0.176 0.352
#> GSM613641 1 0.0237 0.7750 0.996 0.004 0.000
#> GSM613642 2 0.6306 0.4576 0.052 0.748 0.200
#> GSM613643 1 0.9207 -0.0757 0.508 0.172 0.320
#> GSM613644 1 0.9118 -0.1027 0.496 0.152 0.352
#> GSM613645 1 0.6000 0.5709 0.760 0.040 0.200
#> GSM613646 2 0.9589 -0.3096 0.200 0.424 0.376
#> GSM613647 3 0.9007 0.6297 0.268 0.180 0.552
#> GSM613648 3 0.9578 0.5887 0.248 0.272 0.480
#> GSM613649 2 0.5254 0.5137 0.000 0.736 0.264
#> GSM613650 1 0.9916 -0.3856 0.396 0.288 0.316
#> GSM613651 1 0.8346 0.0405 0.548 0.092 0.360
#> GSM613652 1 0.0000 0.7746 1.000 0.000 0.000
#> GSM613653 1 0.9950 -0.4184 0.372 0.288 0.340
#> GSM613654 1 0.0000 0.7746 1.000 0.000 0.000
#> GSM613655 1 0.0000 0.7746 1.000 0.000 0.000
#> GSM613656 1 0.0000 0.7746 1.000 0.000 0.000
#> GSM613657 2 0.5138 0.5198 0.000 0.748 0.252
#> GSM613658 1 0.0237 0.7750 0.996 0.004 0.000
#> GSM613659 2 0.9243 -0.1696 0.168 0.492 0.340
#> GSM613660 2 0.0237 0.6604 0.000 0.996 0.004
#> GSM613661 1 0.0475 0.7747 0.992 0.004 0.004
#> GSM613662 2 0.0424 0.6587 0.000 0.992 0.008
#> GSM613663 1 0.0237 0.7747 0.996 0.000 0.004
#> GSM613664 2 0.0892 0.6589 0.000 0.980 0.020
#> GSM613665 2 0.0592 0.6606 0.000 0.988 0.012
#> GSM613666 1 0.0237 0.7750 0.996 0.004 0.000
#> GSM613667 1 0.5660 0.5807 0.772 0.028 0.200
#> GSM613668 1 0.0000 0.7746 1.000 0.000 0.000
#> GSM613669 1 0.0237 0.7750 0.996 0.004 0.000
#> GSM613670 2 0.0424 0.6587 0.000 0.992 0.008
#> GSM613671 1 0.0237 0.7750 0.996 0.004 0.000
#> GSM613672 1 0.0237 0.7747 0.996 0.000 0.004
#> GSM613673 1 0.1315 0.7693 0.972 0.008 0.020
#> GSM613674 2 0.0000 0.6595 0.000 1.000 0.000
#> GSM613675 2 0.1315 0.6527 0.020 0.972 0.008
#> GSM613676 2 0.0592 0.6606 0.000 0.988 0.012
#> GSM613677 2 0.9046 -0.1201 0.152 0.516 0.332
#> GSM613678 2 0.9207 -0.1383 0.172 0.508 0.320
#> GSM613679 2 0.0237 0.6605 0.000 0.996 0.004
#> GSM613680 1 0.0237 0.7747 0.996 0.000 0.004
#> GSM613681 1 0.0983 0.7711 0.980 0.016 0.004
#> GSM613682 1 0.2860 0.7187 0.912 0.084 0.004
#> GSM613683 1 0.0237 0.7747 0.996 0.000 0.004
#> GSM613684 2 0.0892 0.6600 0.000 0.980 0.020
#> GSM613685 2 0.0000 0.6595 0.000 1.000 0.000
#> GSM613686 1 0.5053 0.6113 0.812 0.164 0.024
#> GSM613687 1 0.0983 0.7711 0.980 0.016 0.004
#> GSM613688 2 0.1031 0.6588 0.000 0.976 0.024
#> GSM613689 3 0.9122 0.5623 0.184 0.280 0.536
#> GSM613690 3 0.8858 0.4494 0.136 0.332 0.532
#> GSM613691 2 0.7984 0.2517 0.132 0.652 0.216
#> GSM613692 1 0.7263 0.4149 0.692 0.084 0.224
#> GSM613693 2 0.0747 0.6606 0.000 0.984 0.016
#> GSM613694 3 0.9061 0.5762 0.188 0.264 0.548
#> GSM613695 3 0.9045 0.6304 0.256 0.192 0.552
#> GSM613696 2 0.9098 -0.1500 0.148 0.492 0.360
#> GSM613697 1 0.8346 0.0405 0.548 0.092 0.360
#> GSM613698 3 0.9273 0.4957 0.364 0.164 0.472
#> GSM613699 3 0.9122 0.5623 0.184 0.280 0.536
#> GSM613700 2 0.0000 0.6595 0.000 1.000 0.000
#> GSM613701 2 0.9941 -0.3529 0.340 0.376 0.284
#> GSM613702 2 0.9961 -0.3615 0.332 0.372 0.296
#> GSM613703 1 0.1636 0.7654 0.964 0.020 0.016
#> GSM613704 2 0.0237 0.6578 0.000 0.996 0.004
#> GSM613705 3 0.9669 0.4125 0.380 0.212 0.408
#> GSM613706 2 0.9941 -0.3529 0.340 0.376 0.284
#> GSM613707 2 0.0747 0.6599 0.000 0.984 0.016
#> GSM613708 1 0.4609 0.6677 0.856 0.092 0.052
#> GSM613709 1 0.0237 0.7750 0.996 0.004 0.000
#> GSM613710 2 0.0237 0.6604 0.000 0.996 0.004
#> GSM613711 2 0.5016 0.5304 0.000 0.760 0.240
#> GSM613712 3 0.9221 0.3932 0.404 0.152 0.444
#> GSM613713 2 0.0237 0.6604 0.000 0.996 0.004
#> GSM613714 3 0.9055 0.6292 0.252 0.196 0.552
#> GSM613715 3 0.8841 0.4346 0.132 0.340 0.528
#> GSM613716 3 0.9783 0.5526 0.256 0.312 0.432
#> GSM613717 2 0.5058 0.5269 0.000 0.756 0.244
#> GSM613718 2 0.5178 0.5156 0.000 0.744 0.256
#> GSM613719 1 0.9950 -0.4184 0.372 0.288 0.340
#> GSM613720 2 0.3116 0.6167 0.000 0.892 0.108
#> GSM613721 2 0.5047 0.5376 0.036 0.824 0.140
#> GSM613722 2 0.3112 0.6002 0.004 0.900 0.096
#> GSM613723 1 0.0000 0.7746 1.000 0.000 0.000
#> GSM613724 1 0.0475 0.7747 0.992 0.004 0.004
#> GSM613725 2 0.0000 0.6595 0.000 1.000 0.000
#> GSM613726 1 0.7548 0.4164 0.684 0.112 0.204
#> GSM613727 1 0.0000 0.7746 1.000 0.000 0.000
#> GSM613728 2 0.7666 0.2696 0.148 0.684 0.168
#> GSM613729 1 0.1636 0.7654 0.964 0.020 0.016
#> GSM613730 2 0.8995 -0.0836 0.152 0.528 0.320
#> GSM613731 1 0.9207 -0.0757 0.508 0.172 0.320
#> GSM613732 2 0.5138 0.5198 0.000 0.748 0.252
#> GSM613733 2 0.4750 0.5442 0.000 0.784 0.216
#> GSM613734 1 0.0000 0.7746 1.000 0.000 0.000
#> GSM613735 1 0.0000 0.7746 1.000 0.000 0.000
#> GSM613736 2 0.4931 0.5373 0.000 0.768 0.232
#> GSM613737 3 0.9066 0.6282 0.284 0.176 0.540
#> GSM613738 1 0.2165 0.7458 0.936 0.000 0.064
#> GSM613739 1 0.2165 0.7458 0.936 0.000 0.064
#> GSM613740 2 0.5098 0.5299 0.000 0.752 0.248
#> GSM613741 1 0.9950 -0.4184 0.372 0.288 0.340
#> GSM613742 1 0.2165 0.7458 0.936 0.000 0.064
#> GSM613743 2 0.4931 0.5373 0.000 0.768 0.232
#> GSM613744 2 0.5216 0.5183 0.000 0.740 0.260
#> GSM613745 2 0.9589 -0.3096 0.200 0.424 0.376
#> GSM613746 2 0.0237 0.6578 0.000 0.996 0.004
#> GSM613747 1 0.0000 0.7746 1.000 0.000 0.000
#> GSM613748 2 0.9108 -0.1023 0.164 0.520 0.316
#> GSM613749 2 0.9972 -0.3673 0.336 0.364 0.300
#> GSM613750 3 0.4504 0.2279 0.000 0.196 0.804
#> GSM613751 3 0.4504 0.2279 0.000 0.196 0.804
#> GSM613752 3 0.4504 0.2279 0.000 0.196 0.804
#> GSM613753 3 0.4504 0.2279 0.000 0.196 0.804
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 3 0.6012 0.6915 0.232 0.056 0.692 0.020
#> GSM613639 3 0.5229 0.3597 0.428 0.008 0.564 0.000
#> GSM613640 3 0.4980 0.6030 0.304 0.016 0.680 0.000
#> GSM613641 1 0.0895 0.8952 0.976 0.000 0.020 0.004
#> GSM613642 2 0.5754 0.3997 0.004 0.572 0.400 0.024
#> GSM613643 3 0.5057 0.5535 0.340 0.012 0.648 0.000
#> GSM613644 3 0.4897 0.5611 0.332 0.008 0.660 0.000
#> GSM613645 1 0.4343 0.5841 0.732 0.000 0.264 0.004
#> GSM613646 3 0.3731 0.6627 0.036 0.120 0.844 0.000
#> GSM613647 3 0.4992 0.6606 0.100 0.008 0.788 0.104
#> GSM613648 3 0.6528 0.6288 0.088 0.080 0.716 0.116
#> GSM613649 2 0.7031 0.5786 0.000 0.520 0.348 0.132
#> GSM613650 3 0.4644 0.6824 0.208 0.024 0.764 0.004
#> GSM613651 3 0.5220 0.5219 0.352 0.000 0.632 0.016
#> GSM613652 1 0.0804 0.8936 0.980 0.000 0.008 0.012
#> GSM613653 3 0.4406 0.6928 0.184 0.024 0.788 0.004
#> GSM613654 1 0.0804 0.8936 0.980 0.000 0.008 0.012
#> GSM613655 1 0.0469 0.8932 0.988 0.000 0.000 0.012
#> GSM613656 1 0.0804 0.8936 0.980 0.000 0.008 0.012
#> GSM613657 2 0.6993 0.5924 0.000 0.532 0.336 0.132
#> GSM613658 1 0.0804 0.8959 0.980 0.000 0.008 0.012
#> GSM613659 3 0.4446 0.6137 0.028 0.196 0.776 0.000
#> GSM613660 2 0.2593 0.7668 0.000 0.904 0.080 0.016
#> GSM613661 1 0.0817 0.8946 0.976 0.000 0.024 0.000
#> GSM613662 2 0.3390 0.7468 0.000 0.852 0.132 0.016
#> GSM613663 1 0.0188 0.8962 0.996 0.000 0.004 0.000
#> GSM613664 2 0.3249 0.7558 0.000 0.852 0.140 0.008
#> GSM613665 2 0.2741 0.7706 0.000 0.892 0.096 0.012
#> GSM613666 1 0.0895 0.8952 0.976 0.000 0.020 0.004
#> GSM613667 1 0.4103 0.5973 0.744 0.000 0.256 0.000
#> GSM613668 1 0.0469 0.8932 0.988 0.000 0.000 0.012
#> GSM613669 1 0.0895 0.8952 0.976 0.000 0.020 0.004
#> GSM613670 2 0.3390 0.7468 0.000 0.852 0.132 0.016
#> GSM613671 1 0.0895 0.8952 0.976 0.000 0.020 0.004
#> GSM613672 1 0.0188 0.8962 0.996 0.000 0.004 0.000
#> GSM613673 1 0.1042 0.8928 0.972 0.008 0.020 0.000
#> GSM613674 2 0.0657 0.7429 0.000 0.984 0.004 0.012
#> GSM613675 2 0.4276 0.7470 0.004 0.788 0.192 0.016
#> GSM613676 2 0.2741 0.7706 0.000 0.892 0.096 0.012
#> GSM613677 3 0.5849 0.5070 0.020 0.276 0.672 0.032
#> GSM613678 3 0.4979 0.5929 0.032 0.224 0.740 0.004
#> GSM613679 2 0.1452 0.7584 0.000 0.956 0.036 0.008
#> GSM613680 1 0.0188 0.8962 0.996 0.000 0.004 0.000
#> GSM613681 1 0.1004 0.8932 0.972 0.000 0.024 0.004
#> GSM613682 1 0.3354 0.8092 0.872 0.044 0.084 0.000
#> GSM613683 1 0.0188 0.8962 0.996 0.000 0.004 0.000
#> GSM613684 2 0.2741 0.7695 0.000 0.892 0.096 0.012
#> GSM613685 2 0.0657 0.7429 0.000 0.984 0.004 0.012
#> GSM613686 1 0.5321 0.6719 0.756 0.096 0.144 0.004
#> GSM613687 1 0.1004 0.8932 0.972 0.000 0.024 0.004
#> GSM613688 2 0.3032 0.7700 0.000 0.868 0.124 0.008
#> GSM613689 3 0.4958 0.6378 0.032 0.056 0.804 0.108
#> GSM613690 3 0.6235 0.5616 0.032 0.124 0.720 0.124
#> GSM613691 3 0.5786 0.1409 0.028 0.380 0.588 0.004
#> GSM613692 1 0.5294 -0.1199 0.508 0.000 0.484 0.008
#> GSM613693 2 0.3108 0.7715 0.000 0.872 0.112 0.016
#> GSM613694 3 0.4808 0.6425 0.036 0.044 0.812 0.108
#> GSM613695 3 0.5054 0.6571 0.092 0.012 0.788 0.108
#> GSM613696 3 0.4939 0.5676 0.040 0.220 0.740 0.000
#> GSM613697 3 0.5220 0.5219 0.352 0.000 0.632 0.016
#> GSM613698 3 0.5673 0.6810 0.200 0.008 0.720 0.072
#> GSM613699 3 0.4958 0.6378 0.032 0.056 0.804 0.108
#> GSM613700 2 0.1488 0.7553 0.000 0.956 0.032 0.012
#> GSM613701 3 0.7120 0.6151 0.208 0.204 0.584 0.004
#> GSM613702 3 0.6964 0.6270 0.200 0.192 0.604 0.004
#> GSM613703 1 0.1902 0.8770 0.932 0.000 0.064 0.004
#> GSM613704 2 0.3335 0.7476 0.000 0.856 0.128 0.016
#> GSM613705 3 0.5763 0.6956 0.200 0.052 0.724 0.024
#> GSM613706 3 0.7058 0.6194 0.208 0.196 0.592 0.004
#> GSM613707 2 0.1584 0.7562 0.000 0.952 0.036 0.012
#> GSM613708 1 0.4456 0.5767 0.716 0.004 0.280 0.000
#> GSM613709 1 0.0895 0.8952 0.976 0.000 0.020 0.004
#> GSM613710 2 0.2593 0.7668 0.000 0.904 0.080 0.016
#> GSM613711 2 0.6835 0.6252 0.000 0.560 0.316 0.124
#> GSM613712 3 0.5187 0.6826 0.212 0.008 0.740 0.040
#> GSM613713 2 0.2546 0.7712 0.000 0.900 0.092 0.008
#> GSM613714 3 0.4992 0.6564 0.088 0.012 0.792 0.108
#> GSM613715 3 0.6243 0.5468 0.028 0.132 0.716 0.124
#> GSM613716 3 0.6834 0.6290 0.096 0.112 0.696 0.096
#> GSM613717 2 0.6894 0.6167 0.000 0.552 0.320 0.128
#> GSM613718 2 0.6993 0.5935 0.000 0.532 0.336 0.132
#> GSM613719 3 0.4406 0.6928 0.184 0.024 0.788 0.004
#> GSM613720 2 0.5272 0.7297 0.000 0.744 0.172 0.084
#> GSM613721 2 0.4820 0.5569 0.000 0.692 0.296 0.012
#> GSM613722 2 0.3539 0.7019 0.000 0.820 0.176 0.004
#> GSM613723 1 0.0804 0.8936 0.980 0.000 0.008 0.012
#> GSM613724 1 0.0817 0.8946 0.976 0.000 0.024 0.000
#> GSM613725 2 0.1488 0.7553 0.000 0.956 0.032 0.012
#> GSM613726 1 0.5203 0.0994 0.576 0.008 0.416 0.000
#> GSM613727 1 0.0469 0.8932 0.988 0.000 0.000 0.012
#> GSM613728 3 0.5754 0.1207 0.016 0.428 0.548 0.008
#> GSM613729 1 0.1902 0.8770 0.932 0.000 0.064 0.004
#> GSM613730 3 0.4927 0.5398 0.016 0.268 0.712 0.004
#> GSM613731 3 0.5057 0.5535 0.340 0.012 0.648 0.000
#> GSM613732 2 0.6993 0.5924 0.000 0.532 0.336 0.132
#> GSM613733 2 0.6538 0.6521 0.000 0.600 0.292 0.108
#> GSM613734 1 0.0804 0.8936 0.980 0.000 0.008 0.012
#> GSM613735 1 0.0804 0.8936 0.980 0.000 0.008 0.012
#> GSM613736 2 0.6627 0.6404 0.000 0.588 0.300 0.112
#> GSM613737 3 0.5274 0.6571 0.120 0.008 0.768 0.104
#> GSM613738 1 0.3257 0.7786 0.844 0.000 0.152 0.004
#> GSM613739 1 0.3257 0.7786 0.844 0.000 0.152 0.004
#> GSM613740 2 0.6852 0.6205 0.000 0.556 0.320 0.124
#> GSM613741 3 0.4406 0.6928 0.184 0.024 0.788 0.004
#> GSM613742 1 0.3257 0.7786 0.844 0.000 0.152 0.004
#> GSM613743 2 0.6765 0.6350 0.000 0.576 0.300 0.124
#> GSM613744 2 0.7019 0.5850 0.000 0.524 0.344 0.132
#> GSM613745 3 0.3731 0.6627 0.036 0.120 0.844 0.000
#> GSM613746 2 0.3616 0.7602 0.000 0.852 0.112 0.036
#> GSM613747 1 0.0804 0.8936 0.980 0.000 0.008 0.012
#> GSM613748 3 0.5142 0.5553 0.028 0.256 0.712 0.004
#> GSM613749 3 0.6928 0.6307 0.204 0.184 0.608 0.004
#> GSM613750 4 0.1661 1.0000 0.000 0.004 0.052 0.944
#> GSM613751 4 0.1661 1.0000 0.000 0.004 0.052 0.944
#> GSM613752 4 0.1661 1.0000 0.000 0.004 0.052 0.944
#> GSM613753 4 0.1661 1.0000 0.000 0.004 0.052 0.944
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM613638 4 0.5860 0.6574 0.208 0.064 0.028 0.680 0.020
#> GSM613639 4 0.4819 0.3867 0.404 0.008 0.012 0.576 0.000
#> GSM613640 4 0.4516 0.6118 0.276 0.016 0.012 0.696 0.000
#> GSM613641 1 0.1168 0.8925 0.960 0.000 0.008 0.032 0.000
#> GSM613642 2 0.6324 0.0385 0.004 0.544 0.092 0.340 0.020
#> GSM613643 4 0.4502 0.5653 0.312 0.012 0.008 0.668 0.000
#> GSM613644 4 0.4483 0.5719 0.308 0.008 0.012 0.672 0.000
#> GSM613645 1 0.3885 0.5758 0.724 0.000 0.008 0.268 0.000
#> GSM613646 4 0.4462 0.6181 0.028 0.088 0.092 0.792 0.000
#> GSM613647 4 0.3671 0.6423 0.060 0.000 0.024 0.844 0.072
#> GSM613648 4 0.5142 0.5867 0.048 0.068 0.028 0.776 0.080
#> GSM613649 2 0.7930 0.3955 0.000 0.392 0.180 0.324 0.104
#> GSM613650 4 0.4837 0.6469 0.176 0.004 0.092 0.728 0.000
#> GSM613651 4 0.5036 0.5583 0.304 0.000 0.040 0.648 0.008
#> GSM613652 1 0.1630 0.8845 0.944 0.000 0.004 0.036 0.016
#> GSM613653 4 0.4612 0.6557 0.152 0.004 0.092 0.752 0.000
#> GSM613654 1 0.1630 0.8845 0.944 0.000 0.004 0.036 0.016
#> GSM613655 1 0.0854 0.8905 0.976 0.000 0.008 0.004 0.012
#> GSM613656 1 0.1630 0.8845 0.944 0.000 0.004 0.036 0.016
#> GSM613657 2 0.7933 0.4021 0.000 0.400 0.184 0.312 0.104
#> GSM613658 1 0.1299 0.8937 0.960 0.000 0.012 0.020 0.008
#> GSM613659 4 0.5257 0.5713 0.020 0.160 0.104 0.716 0.000
#> GSM613660 2 0.2227 0.3370 0.000 0.916 0.032 0.048 0.004
#> GSM613661 1 0.0703 0.8950 0.976 0.000 0.000 0.024 0.000
#> GSM613662 3 0.4925 0.6585 0.000 0.324 0.632 0.044 0.000
#> GSM613663 1 0.0162 0.8950 0.996 0.000 0.000 0.004 0.000
#> GSM613664 2 0.5386 -0.2925 0.000 0.544 0.396 0.060 0.000
#> GSM613665 2 0.4742 0.1712 0.000 0.716 0.220 0.060 0.004
#> GSM613666 1 0.1168 0.8925 0.960 0.000 0.008 0.032 0.000
#> GSM613667 1 0.3662 0.5970 0.744 0.000 0.004 0.252 0.000
#> GSM613668 1 0.0854 0.8905 0.976 0.000 0.008 0.004 0.012
#> GSM613669 1 0.1168 0.8925 0.960 0.000 0.008 0.032 0.000
#> GSM613670 3 0.4925 0.6585 0.000 0.324 0.632 0.044 0.000
#> GSM613671 1 0.1168 0.8925 0.960 0.000 0.008 0.032 0.000
#> GSM613672 1 0.0162 0.8950 0.996 0.000 0.000 0.004 0.000
#> GSM613673 1 0.0898 0.8943 0.972 0.008 0.000 0.020 0.000
#> GSM613674 2 0.2561 0.1985 0.000 0.856 0.144 0.000 0.000
#> GSM613675 3 0.6035 0.5582 0.004 0.316 0.556 0.124 0.000
#> GSM613676 2 0.4742 0.1712 0.000 0.716 0.220 0.060 0.004
#> GSM613677 4 0.6510 0.4724 0.012 0.224 0.124 0.612 0.028
#> GSM613678 4 0.5689 0.5346 0.024 0.184 0.116 0.676 0.000
#> GSM613679 2 0.3194 0.2181 0.000 0.832 0.148 0.020 0.000
#> GSM613680 1 0.0162 0.8950 0.996 0.000 0.000 0.004 0.000
#> GSM613681 1 0.1041 0.8935 0.964 0.000 0.004 0.032 0.000
#> GSM613682 1 0.3331 0.8179 0.864 0.032 0.032 0.072 0.000
#> GSM613683 1 0.0162 0.8950 0.996 0.000 0.000 0.004 0.000
#> GSM613684 2 0.4908 0.0287 0.000 0.636 0.320 0.044 0.000
#> GSM613685 2 0.2561 0.1985 0.000 0.856 0.144 0.000 0.000
#> GSM613686 1 0.5225 0.6786 0.740 0.072 0.056 0.132 0.000
#> GSM613687 1 0.1041 0.8935 0.964 0.000 0.004 0.032 0.000
#> GSM613688 2 0.5274 -0.1383 0.000 0.572 0.372 0.056 0.000
#> GSM613689 4 0.4458 0.5917 0.012 0.052 0.048 0.812 0.076
#> GSM613690 4 0.5428 0.5069 0.008 0.064 0.092 0.744 0.092
#> GSM613691 4 0.6591 0.2423 0.020 0.172 0.260 0.548 0.000
#> GSM613692 4 0.5254 0.1774 0.460 0.000 0.036 0.500 0.004
#> GSM613693 2 0.5309 0.1127 0.000 0.604 0.336 0.056 0.004
#> GSM613694 4 0.4268 0.6037 0.016 0.036 0.048 0.824 0.076
#> GSM613695 4 0.3755 0.6362 0.052 0.004 0.024 0.844 0.076
#> GSM613696 4 0.5612 0.5450 0.032 0.120 0.152 0.696 0.000
#> GSM613697 4 0.5036 0.5583 0.304 0.000 0.040 0.648 0.008
#> GSM613698 4 0.4962 0.6614 0.156 0.000 0.048 0.748 0.048
#> GSM613699 4 0.4458 0.5917 0.012 0.052 0.048 0.812 0.076
#> GSM613700 2 0.0451 0.3047 0.000 0.988 0.004 0.008 0.000
#> GSM613701 4 0.6983 0.5073 0.200 0.188 0.056 0.556 0.000
#> GSM613702 4 0.6816 0.5239 0.192 0.172 0.056 0.580 0.000
#> GSM613703 1 0.2124 0.8754 0.916 0.000 0.028 0.056 0.000
#> GSM613704 3 0.4857 0.6563 0.000 0.324 0.636 0.040 0.000
#> GSM613705 4 0.5854 0.6631 0.172 0.068 0.040 0.700 0.020
#> GSM613706 4 0.6869 0.5158 0.200 0.180 0.052 0.568 0.000
#> GSM613707 2 0.4339 0.0189 0.000 0.684 0.296 0.020 0.000
#> GSM613708 1 0.4296 0.5512 0.692 0.008 0.008 0.292 0.000
#> GSM613709 1 0.1168 0.8925 0.960 0.000 0.008 0.032 0.000
#> GSM613710 2 0.2227 0.3370 0.000 0.916 0.032 0.048 0.004
#> GSM613711 2 0.7802 0.4137 0.000 0.432 0.180 0.292 0.096
#> GSM613712 4 0.4906 0.6627 0.172 0.004 0.044 0.748 0.032
#> GSM613713 2 0.4452 0.2057 0.000 0.696 0.272 0.032 0.000
#> GSM613714 4 0.3685 0.6341 0.048 0.004 0.024 0.848 0.076
#> GSM613715 4 0.5598 0.4915 0.008 0.072 0.096 0.732 0.092
#> GSM613716 4 0.5991 0.5874 0.060 0.052 0.096 0.724 0.068
#> GSM613717 2 0.7848 0.4121 0.000 0.424 0.180 0.296 0.100
#> GSM613718 2 0.7933 0.4015 0.000 0.400 0.184 0.312 0.104
#> GSM613719 4 0.4612 0.6557 0.152 0.004 0.092 0.752 0.000
#> GSM613720 3 0.4608 0.4112 0.000 0.076 0.784 0.104 0.036
#> GSM613721 3 0.6696 0.2440 0.000 0.372 0.388 0.240 0.000
#> GSM613722 2 0.3980 0.1696 0.000 0.796 0.076 0.128 0.000
#> GSM613723 1 0.1630 0.8845 0.944 0.000 0.004 0.036 0.016
#> GSM613724 1 0.0703 0.8950 0.976 0.000 0.000 0.024 0.000
#> GSM613725 2 0.0451 0.3047 0.000 0.988 0.004 0.008 0.000
#> GSM613726 1 0.4481 0.0867 0.576 0.008 0.000 0.416 0.000
#> GSM613727 1 0.0854 0.8905 0.976 0.000 0.008 0.004 0.012
#> GSM613728 4 0.6803 0.1787 0.016 0.296 0.196 0.492 0.000
#> GSM613729 1 0.2124 0.8754 0.916 0.000 0.028 0.056 0.000
#> GSM613730 4 0.5561 0.4968 0.016 0.244 0.084 0.656 0.000
#> GSM613731 4 0.4502 0.5653 0.312 0.012 0.008 0.668 0.000
#> GSM613732 2 0.7933 0.4021 0.000 0.400 0.184 0.312 0.104
#> GSM613733 2 0.7451 0.4109 0.000 0.492 0.164 0.264 0.080
#> GSM613734 1 0.1630 0.8845 0.944 0.000 0.004 0.036 0.016
#> GSM613735 1 0.1630 0.8845 0.944 0.000 0.004 0.036 0.016
#> GSM613736 2 0.7497 0.4135 0.000 0.480 0.156 0.280 0.084
#> GSM613737 4 0.4227 0.6378 0.080 0.000 0.036 0.812 0.072
#> GSM613738 1 0.3716 0.7486 0.800 0.000 0.020 0.172 0.008
#> GSM613739 1 0.3716 0.7486 0.800 0.000 0.020 0.172 0.008
#> GSM613740 2 0.7753 0.4162 0.000 0.436 0.168 0.300 0.096
#> GSM613741 4 0.4612 0.6557 0.152 0.004 0.092 0.752 0.000
#> GSM613742 1 0.3716 0.7486 0.800 0.000 0.020 0.172 0.008
#> GSM613743 2 0.7674 0.4177 0.000 0.460 0.164 0.280 0.096
#> GSM613744 2 0.7944 0.3978 0.000 0.392 0.184 0.320 0.104
#> GSM613745 4 0.4462 0.6181 0.028 0.088 0.092 0.792 0.000
#> GSM613746 3 0.2077 0.5221 0.000 0.084 0.908 0.008 0.000
#> GSM613747 1 0.1630 0.8845 0.944 0.000 0.004 0.036 0.016
#> GSM613748 4 0.5710 0.5116 0.024 0.232 0.088 0.656 0.000
#> GSM613749 4 0.6781 0.5285 0.196 0.164 0.056 0.584 0.000
#> GSM613750 5 0.0510 1.0000 0.000 0.000 0.000 0.016 0.984
#> GSM613751 5 0.0510 1.0000 0.000 0.000 0.000 0.016 0.984
#> GSM613752 5 0.0510 1.0000 0.000 0.000 0.000 0.016 0.984
#> GSM613753 5 0.0510 1.0000 0.000 0.000 0.000 0.016 0.984
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM613638 4 0.5532 0.6297 0.140 0.024 0.108 0.688 0.000 0.040
#> GSM613639 4 0.5471 0.4101 0.300 0.008 0.032 0.608 0.004 0.048
#> GSM613640 4 0.4610 0.5864 0.200 0.012 0.036 0.728 0.004 0.020
#> GSM613641 1 0.2856 0.7761 0.856 0.000 0.000 0.068 0.000 0.076
#> GSM613642 2 0.7034 0.2015 0.004 0.348 0.280 0.328 0.008 0.032
#> GSM613643 4 0.4541 0.5466 0.236 0.012 0.036 0.704 0.000 0.012
#> GSM613644 4 0.4907 0.5495 0.232 0.012 0.032 0.692 0.004 0.028
#> GSM613645 1 0.4766 0.5167 0.656 0.008 0.000 0.276 0.004 0.056
#> GSM613646 4 0.4661 0.6079 0.008 0.064 0.132 0.756 0.004 0.036
#> GSM613647 4 0.4741 0.5391 0.016 0.000 0.252 0.672 0.000 0.060
#> GSM613648 4 0.5248 0.4534 0.012 0.020 0.324 0.600 0.000 0.044
#> GSM613649 3 0.2113 0.9276 0.000 0.008 0.896 0.092 0.000 0.004
#> GSM613650 4 0.4224 0.6205 0.076 0.004 0.048 0.796 0.004 0.072
#> GSM613651 4 0.5399 0.5386 0.192 0.000 0.040 0.656 0.000 0.112
#> GSM613652 1 0.4358 0.7074 0.712 0.000 0.000 0.092 0.000 0.196
#> GSM613653 4 0.4002 0.6272 0.060 0.008 0.048 0.816 0.004 0.064
#> GSM613654 1 0.4358 0.7074 0.712 0.000 0.000 0.092 0.000 0.196
#> GSM613655 1 0.2553 0.7604 0.848 0.000 0.000 0.008 0.000 0.144
#> GSM613656 1 0.4358 0.7074 0.712 0.000 0.000 0.092 0.000 0.196
#> GSM613657 3 0.1897 0.9359 0.000 0.004 0.908 0.084 0.000 0.004
#> GSM613658 1 0.2979 0.7791 0.840 0.000 0.000 0.044 0.000 0.116
#> GSM613659 4 0.5242 0.5794 0.004 0.136 0.120 0.700 0.004 0.036
#> GSM613660 2 0.4621 0.4254 0.000 0.528 0.444 0.012 0.008 0.008
#> GSM613661 1 0.2542 0.7855 0.876 0.000 0.000 0.044 0.000 0.080
#> GSM613662 2 0.6359 -0.0973 0.000 0.548 0.136 0.076 0.000 0.240
#> GSM613663 1 0.1168 0.7887 0.956 0.000 0.000 0.016 0.000 0.028
#> GSM613664 2 0.6020 0.3721 0.000 0.616 0.188 0.072 0.004 0.120
#> GSM613665 2 0.5162 0.5524 0.000 0.600 0.320 0.052 0.000 0.028
#> GSM613666 1 0.2856 0.7761 0.856 0.000 0.000 0.068 0.000 0.076
#> GSM613667 1 0.4642 0.5414 0.680 0.008 0.000 0.252 0.004 0.056
#> GSM613668 1 0.2553 0.7604 0.848 0.000 0.000 0.008 0.000 0.144
#> GSM613669 1 0.2688 0.7778 0.868 0.000 0.000 0.068 0.000 0.064
#> GSM613670 2 0.6359 -0.0973 0.000 0.548 0.136 0.076 0.000 0.240
#> GSM613671 1 0.2856 0.7761 0.856 0.000 0.000 0.068 0.000 0.076
#> GSM613672 1 0.1391 0.7899 0.944 0.000 0.000 0.016 0.000 0.040
#> GSM613673 1 0.1906 0.7919 0.924 0.008 0.000 0.032 0.000 0.036
#> GSM613674 2 0.3840 0.5528 0.000 0.740 0.228 0.000 0.008 0.024
#> GSM613675 2 0.6833 -0.0254 0.000 0.516 0.160 0.160 0.000 0.164
#> GSM613676 2 0.5162 0.5524 0.000 0.600 0.320 0.052 0.000 0.028
#> GSM613677 4 0.6043 0.4992 0.004 0.168 0.172 0.604 0.000 0.052
#> GSM613678 4 0.5345 0.5463 0.008 0.172 0.080 0.692 0.004 0.044
#> GSM613679 2 0.4164 0.5788 0.000 0.688 0.280 0.016 0.000 0.016
#> GSM613680 1 0.1480 0.7904 0.940 0.000 0.000 0.020 0.000 0.040
#> GSM613681 1 0.2389 0.7835 0.888 0.000 0.000 0.052 0.000 0.060
#> GSM613682 1 0.3648 0.7364 0.808 0.024 0.000 0.128 0.000 0.040
#> GSM613683 1 0.1480 0.7907 0.940 0.000 0.000 0.020 0.000 0.040
#> GSM613684 2 0.5085 0.4614 0.000 0.680 0.192 0.012 0.008 0.108
#> GSM613685 2 0.3840 0.5528 0.000 0.740 0.228 0.000 0.008 0.024
#> GSM613686 1 0.5924 0.5763 0.628 0.064 0.004 0.204 0.004 0.096
#> GSM613687 1 0.2389 0.7811 0.888 0.000 0.000 0.052 0.000 0.060
#> GSM613688 2 0.5546 0.4196 0.000 0.628 0.232 0.028 0.004 0.108
#> GSM613689 4 0.5149 0.4575 0.000 0.012 0.336 0.588 0.004 0.060
#> GSM613690 4 0.4947 0.3364 0.004 0.012 0.424 0.528 0.000 0.032
#> GSM613691 4 0.6809 0.3066 0.004 0.200 0.176 0.520 0.000 0.100
#> GSM613692 4 0.6016 0.2281 0.320 0.000 0.032 0.520 0.000 0.128
#> GSM613693 2 0.6148 0.4698 0.000 0.480 0.336 0.024 0.000 0.160
#> GSM613694 4 0.5076 0.4729 0.000 0.012 0.324 0.596 0.000 0.068
#> GSM613695 4 0.4643 0.5302 0.012 0.000 0.260 0.672 0.000 0.056
#> GSM613696 4 0.5619 0.5558 0.012 0.100 0.148 0.676 0.000 0.064
#> GSM613697 4 0.5399 0.5386 0.192 0.000 0.040 0.656 0.000 0.112
#> GSM613698 4 0.5195 0.5996 0.072 0.004 0.148 0.704 0.000 0.072
#> GSM613699 4 0.5149 0.4575 0.000 0.012 0.336 0.588 0.004 0.060
#> GSM613700 2 0.4300 0.5448 0.000 0.636 0.340 0.008 0.008 0.008
#> GSM613701 4 0.6253 0.5117 0.168 0.160 0.032 0.612 0.008 0.020
#> GSM613702 4 0.6272 0.5211 0.160 0.152 0.024 0.620 0.008 0.036
#> GSM613703 1 0.4301 0.7234 0.748 0.004 0.000 0.100 0.004 0.144
#> GSM613704 2 0.6377 -0.1013 0.000 0.544 0.136 0.076 0.000 0.244
#> GSM613705 4 0.5644 0.6197 0.108 0.036 0.100 0.696 0.000 0.060
#> GSM613706 4 0.6162 0.5215 0.168 0.152 0.032 0.620 0.004 0.024
#> GSM613707 2 0.4367 0.4777 0.000 0.752 0.148 0.008 0.008 0.084
#> GSM613708 1 0.5502 0.4204 0.568 0.004 0.028 0.336 0.000 0.064
#> GSM613709 1 0.2688 0.7778 0.868 0.000 0.000 0.068 0.000 0.064
#> GSM613710 2 0.4621 0.4254 0.000 0.528 0.444 0.012 0.008 0.008
#> GSM613711 3 0.1983 0.9324 0.000 0.020 0.908 0.072 0.000 0.000
#> GSM613712 4 0.5356 0.6077 0.104 0.000 0.124 0.688 0.000 0.084
#> GSM613713 2 0.5826 0.4753 0.000 0.492 0.376 0.008 0.008 0.116
#> GSM613714 4 0.4664 0.5281 0.012 0.000 0.264 0.668 0.000 0.056
#> GSM613715 4 0.5101 0.3004 0.004 0.016 0.436 0.508 0.000 0.036
#> GSM613716 4 0.5944 0.4839 0.012 0.064 0.264 0.596 0.000 0.064
#> GSM613717 3 0.1802 0.9365 0.000 0.012 0.916 0.072 0.000 0.000
#> GSM613718 3 0.1806 0.9358 0.000 0.004 0.908 0.088 0.000 0.000
#> GSM613719 4 0.4002 0.6272 0.060 0.008 0.048 0.816 0.004 0.064
#> GSM613720 6 0.6727 0.7298 0.000 0.300 0.224 0.048 0.000 0.428
#> GSM613721 2 0.7204 0.1070 0.000 0.468 0.148 0.200 0.004 0.180
#> GSM613722 2 0.5989 0.5064 0.000 0.568 0.272 0.124 0.008 0.028
#> GSM613723 1 0.4358 0.7074 0.712 0.000 0.000 0.092 0.000 0.196
#> GSM613724 1 0.2376 0.7878 0.888 0.000 0.000 0.044 0.000 0.068
#> GSM613725 2 0.4300 0.5448 0.000 0.636 0.340 0.008 0.008 0.008
#> GSM613726 1 0.5059 0.0936 0.528 0.008 0.016 0.420 0.000 0.028
#> GSM613727 1 0.2473 0.7620 0.856 0.000 0.000 0.008 0.000 0.136
#> GSM613728 4 0.6817 0.2604 0.004 0.288 0.172 0.468 0.000 0.068
#> GSM613729 1 0.4301 0.7234 0.748 0.004 0.000 0.100 0.004 0.144
#> GSM613730 4 0.5873 0.5100 0.004 0.184 0.148 0.624 0.004 0.036
#> GSM613731 4 0.4541 0.5466 0.236 0.012 0.036 0.704 0.000 0.012
#> GSM613732 3 0.1897 0.9359 0.000 0.004 0.908 0.084 0.000 0.004
#> GSM613733 3 0.2822 0.8737 0.000 0.068 0.868 0.056 0.008 0.000
#> GSM613734 1 0.4358 0.7074 0.712 0.000 0.000 0.092 0.000 0.196
#> GSM613735 1 0.3967 0.7293 0.760 0.000 0.000 0.092 0.000 0.148
#> GSM613736 3 0.3649 0.8417 0.000 0.112 0.800 0.084 0.000 0.004
#> GSM613737 4 0.5259 0.5216 0.024 0.000 0.256 0.632 0.000 0.088
#> GSM613738 1 0.5461 0.5885 0.592 0.000 0.004 0.208 0.000 0.196
#> GSM613739 1 0.5461 0.5885 0.592 0.000 0.004 0.208 0.000 0.196
#> GSM613740 3 0.2493 0.9276 0.000 0.036 0.884 0.076 0.000 0.004
#> GSM613741 4 0.4002 0.6272 0.060 0.008 0.048 0.816 0.004 0.064
#> GSM613742 1 0.5461 0.5885 0.592 0.000 0.004 0.208 0.000 0.196
#> GSM613743 3 0.2803 0.9094 0.000 0.048 0.864 0.084 0.000 0.004
#> GSM613744 3 0.2062 0.9311 0.000 0.008 0.900 0.088 0.000 0.004
#> GSM613745 4 0.4661 0.6079 0.008 0.064 0.132 0.756 0.004 0.036
#> GSM613746 6 0.5611 0.7280 0.000 0.308 0.152 0.004 0.000 0.536
#> GSM613747 1 0.4358 0.7074 0.712 0.000 0.000 0.092 0.000 0.196
#> GSM613748 4 0.5966 0.5217 0.012 0.164 0.148 0.636 0.008 0.032
#> GSM613749 4 0.5990 0.5281 0.164 0.152 0.020 0.632 0.004 0.028
#> GSM613750 5 0.0458 1.0000 0.000 0.000 0.016 0.000 0.984 0.000
#> GSM613751 5 0.0458 1.0000 0.000 0.000 0.016 0.000 0.984 0.000
#> GSM613752 5 0.0458 1.0000 0.000 0.000 0.016 0.000 0.984 0.000
#> GSM613753 5 0.0458 1.0000 0.000 0.000 0.016 0.000 0.984 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) k
#> SD:hclust 102 0.16156 2
#> SD:hclust 78 0.19843 3
#> SD:hclust 110 0.00216 4
#> SD:hclust 78 0.01058 5
#> SD:hclust 88 0.00568 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 27425 rows and 116 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 0.861 0.930 0.967 0.4971 0.497 0.497
#> 3 3 0.575 0.600 0.829 0.3199 0.732 0.511
#> 4 4 0.552 0.607 0.724 0.1207 0.830 0.550
#> 5 5 0.585 0.460 0.633 0.0673 0.903 0.648
#> 6 6 0.664 0.545 0.683 0.0439 0.867 0.471
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
#> GSM613638 2 0.8608 0.580 0.284 0.716
#> GSM613639 1 0.0376 0.951 0.996 0.004
#> GSM613640 2 0.1843 0.954 0.028 0.972
#> GSM613641 1 0.0376 0.951 0.996 0.004
#> GSM613642 2 0.0000 0.980 0.000 1.000
#> GSM613643 1 0.0376 0.951 0.996 0.004
#> GSM613644 1 0.0376 0.951 0.996 0.004
#> GSM613645 1 0.0376 0.951 0.996 0.004
#> GSM613646 1 0.8909 0.614 0.692 0.308
#> GSM613647 1 0.8713 0.644 0.708 0.292
#> GSM613648 2 0.0000 0.980 0.000 1.000
#> GSM613649 2 0.0000 0.980 0.000 1.000
#> GSM613650 1 0.0672 0.948 0.992 0.008
#> GSM613651 1 0.0672 0.948 0.992 0.008
#> GSM613652 1 0.0376 0.951 0.996 0.004
#> GSM613653 1 0.7745 0.737 0.772 0.228
#> GSM613654 1 0.0376 0.951 0.996 0.004
#> GSM613655 1 0.0376 0.951 0.996 0.004
#> GSM613656 1 0.0376 0.951 0.996 0.004
#> GSM613657 2 0.0000 0.980 0.000 1.000
#> GSM613658 1 0.0376 0.951 0.996 0.004
#> GSM613659 2 0.0000 0.980 0.000 1.000
#> GSM613660 2 0.0000 0.980 0.000 1.000
#> GSM613661 1 0.0376 0.951 0.996 0.004
#> GSM613662 2 0.0000 0.980 0.000 1.000
#> GSM613663 1 0.0376 0.951 0.996 0.004
#> GSM613664 2 0.0000 0.980 0.000 1.000
#> GSM613665 2 0.0000 0.980 0.000 1.000
#> GSM613666 1 0.0376 0.951 0.996 0.004
#> GSM613667 1 0.0376 0.951 0.996 0.004
#> GSM613668 1 0.0376 0.951 0.996 0.004
#> GSM613669 1 0.0376 0.951 0.996 0.004
#> GSM613670 2 0.0000 0.980 0.000 1.000
#> GSM613671 1 0.0376 0.951 0.996 0.004
#> GSM613672 1 0.0376 0.951 0.996 0.004
#> GSM613673 1 0.0376 0.951 0.996 0.004
#> GSM613674 2 0.0000 0.980 0.000 1.000
#> GSM613675 2 0.0000 0.980 0.000 1.000
#> GSM613676 2 0.0000 0.980 0.000 1.000
#> GSM613677 2 0.0000 0.980 0.000 1.000
#> GSM613678 1 0.7139 0.778 0.804 0.196
#> GSM613679 2 0.0000 0.980 0.000 1.000
#> GSM613680 1 0.0376 0.951 0.996 0.004
#> GSM613681 1 0.0376 0.951 0.996 0.004
#> GSM613682 1 0.0376 0.951 0.996 0.004
#> GSM613683 1 0.0376 0.951 0.996 0.004
#> GSM613684 2 0.0000 0.980 0.000 1.000
#> GSM613685 2 0.0000 0.980 0.000 1.000
#> GSM613686 1 0.0376 0.951 0.996 0.004
#> GSM613687 1 0.0376 0.951 0.996 0.004
#> GSM613688 2 0.0000 0.980 0.000 1.000
#> GSM613689 2 0.0000 0.980 0.000 1.000
#> GSM613690 2 0.0000 0.980 0.000 1.000
#> GSM613691 2 0.0000 0.980 0.000 1.000
#> GSM613692 1 0.0376 0.951 0.996 0.004
#> GSM613693 2 0.0000 0.980 0.000 1.000
#> GSM613694 1 0.8443 0.675 0.728 0.272
#> GSM613695 2 0.0000 0.980 0.000 1.000
#> GSM613696 2 0.0000 0.980 0.000 1.000
#> GSM613697 1 0.0672 0.948 0.992 0.008
#> GSM613698 1 0.8909 0.613 0.692 0.308
#> GSM613699 2 0.2948 0.929 0.052 0.948
#> GSM613700 2 0.0000 0.980 0.000 1.000
#> GSM613701 2 0.0672 0.973 0.008 0.992
#> GSM613702 2 0.0000 0.980 0.000 1.000
#> GSM613703 1 0.0376 0.951 0.996 0.004
#> GSM613704 2 0.0000 0.980 0.000 1.000
#> GSM613705 2 0.4815 0.870 0.104 0.896
#> GSM613706 1 0.8443 0.675 0.728 0.272
#> GSM613707 2 0.0000 0.980 0.000 1.000
#> GSM613708 1 0.0376 0.951 0.996 0.004
#> GSM613709 1 0.0376 0.951 0.996 0.004
#> GSM613710 2 0.0000 0.980 0.000 1.000
#> GSM613711 2 0.0000 0.980 0.000 1.000
#> GSM613712 2 0.7950 0.665 0.240 0.760
#> GSM613713 2 0.0000 0.980 0.000 1.000
#> GSM613714 2 0.0000 0.980 0.000 1.000
#> GSM613715 2 0.0000 0.980 0.000 1.000
#> GSM613716 2 0.0000 0.980 0.000 1.000
#> GSM613717 2 0.0000 0.980 0.000 1.000
#> GSM613718 2 0.0000 0.980 0.000 1.000
#> GSM613719 1 0.6801 0.794 0.820 0.180
#> GSM613720 2 0.0000 0.980 0.000 1.000
#> GSM613721 2 0.0000 0.980 0.000 1.000
#> GSM613722 2 0.0000 0.980 0.000 1.000
#> GSM613723 1 0.0376 0.951 0.996 0.004
#> GSM613724 1 0.0376 0.951 0.996 0.004
#> GSM613725 2 0.0000 0.980 0.000 1.000
#> GSM613726 1 0.0376 0.951 0.996 0.004
#> GSM613727 1 0.0376 0.951 0.996 0.004
#> GSM613728 2 0.0000 0.980 0.000 1.000
#> GSM613729 1 0.0376 0.951 0.996 0.004
#> GSM613730 2 0.0000 0.980 0.000 1.000
#> GSM613731 1 0.0376 0.951 0.996 0.004
#> GSM613732 2 0.0000 0.980 0.000 1.000
#> GSM613733 2 0.0000 0.980 0.000 1.000
#> GSM613734 1 0.0376 0.951 0.996 0.004
#> GSM613735 1 0.0376 0.951 0.996 0.004
#> GSM613736 2 0.0000 0.980 0.000 1.000
#> GSM613737 1 0.8608 0.655 0.716 0.284
#> GSM613738 1 0.0376 0.951 0.996 0.004
#> GSM613739 1 0.0376 0.951 0.996 0.004
#> GSM613740 2 0.0000 0.980 0.000 1.000
#> GSM613741 1 0.7745 0.737 0.772 0.228
#> GSM613742 1 0.0376 0.951 0.996 0.004
#> GSM613743 2 0.0000 0.980 0.000 1.000
#> GSM613744 2 0.0000 0.980 0.000 1.000
#> GSM613745 2 0.9580 0.322 0.380 0.620
#> GSM613746 2 0.0000 0.980 0.000 1.000
#> GSM613747 1 0.0376 0.951 0.996 0.004
#> GSM613748 2 0.0000 0.980 0.000 1.000
#> GSM613749 1 0.0376 0.951 0.996 0.004
#> GSM613750 2 0.0376 0.976 0.004 0.996
#> GSM613751 2 0.0376 0.976 0.004 0.996
#> GSM613752 2 0.0376 0.976 0.004 0.996
#> GSM613753 2 0.0376 0.976 0.004 0.996
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM613638 3 0.3276 0.7385 0.024 0.068 0.908
#> GSM613639 1 0.5905 0.4872 0.648 0.000 0.352
#> GSM613640 3 0.3445 0.7331 0.016 0.088 0.896
#> GSM613641 1 0.0000 0.9031 1.000 0.000 0.000
#> GSM613642 2 0.4233 0.5531 0.004 0.836 0.160
#> GSM613643 1 0.6252 0.3334 0.556 0.000 0.444
#> GSM613644 3 0.6302 -0.1457 0.480 0.000 0.520
#> GSM613645 1 0.5810 0.5160 0.664 0.000 0.336
#> GSM613646 3 0.7252 0.5855 0.100 0.196 0.704
#> GSM613647 3 0.2947 0.7246 0.060 0.020 0.920
#> GSM613648 3 0.5591 0.4704 0.000 0.304 0.696
#> GSM613649 3 0.6235 0.1586 0.000 0.436 0.564
#> GSM613650 3 0.4842 0.5802 0.224 0.000 0.776
#> GSM613651 3 0.2711 0.7047 0.088 0.000 0.912
#> GSM613652 1 0.2625 0.8709 0.916 0.000 0.084
#> GSM613653 3 0.7542 0.5713 0.120 0.192 0.688
#> GSM613654 1 0.2625 0.8709 0.916 0.000 0.084
#> GSM613655 1 0.0000 0.9031 1.000 0.000 0.000
#> GSM613656 1 0.2625 0.8709 0.916 0.000 0.084
#> GSM613657 2 0.6274 0.1041 0.000 0.544 0.456
#> GSM613658 1 0.0000 0.9031 1.000 0.000 0.000
#> GSM613659 2 0.6282 0.2510 0.004 0.612 0.384
#> GSM613660 2 0.0475 0.6763 0.004 0.992 0.004
#> GSM613661 1 0.4121 0.7660 0.832 0.000 0.168
#> GSM613662 2 0.0475 0.6787 0.004 0.992 0.004
#> GSM613663 1 0.0000 0.9031 1.000 0.000 0.000
#> GSM613664 2 0.0475 0.6787 0.004 0.992 0.004
#> GSM613665 2 0.0475 0.6787 0.004 0.992 0.004
#> GSM613666 1 0.0000 0.9031 1.000 0.000 0.000
#> GSM613667 1 0.5810 0.5160 0.664 0.000 0.336
#> GSM613668 1 0.0000 0.9031 1.000 0.000 0.000
#> GSM613669 1 0.0000 0.9031 1.000 0.000 0.000
#> GSM613670 2 0.6696 0.2991 0.020 0.632 0.348
#> GSM613671 1 0.0000 0.9031 1.000 0.000 0.000
#> GSM613672 1 0.0000 0.9031 1.000 0.000 0.000
#> GSM613673 1 0.0000 0.9031 1.000 0.000 0.000
#> GSM613674 2 0.0237 0.6780 0.004 0.996 0.000
#> GSM613675 2 0.0475 0.6787 0.004 0.992 0.004
#> GSM613676 2 0.0237 0.6780 0.004 0.996 0.000
#> GSM613677 3 0.5138 0.5923 0.000 0.252 0.748
#> GSM613678 2 0.8784 0.0868 0.116 0.496 0.388
#> GSM613679 2 0.0475 0.6787 0.004 0.992 0.004
#> GSM613680 1 0.0000 0.9031 1.000 0.000 0.000
#> GSM613681 1 0.0000 0.9031 1.000 0.000 0.000
#> GSM613682 1 0.0000 0.9031 1.000 0.000 0.000
#> GSM613683 1 0.0000 0.9031 1.000 0.000 0.000
#> GSM613684 2 0.0237 0.6780 0.004 0.996 0.000
#> GSM613685 2 0.0237 0.6780 0.004 0.996 0.000
#> GSM613686 1 0.3038 0.8325 0.896 0.000 0.104
#> GSM613687 1 0.0000 0.9031 1.000 0.000 0.000
#> GSM613688 2 0.0475 0.6787 0.004 0.992 0.004
#> GSM613689 3 0.5678 0.4658 0.000 0.316 0.684
#> GSM613690 3 0.3816 0.6919 0.000 0.148 0.852
#> GSM613691 2 0.5623 0.4073 0.004 0.716 0.280
#> GSM613692 1 0.2796 0.8667 0.908 0.000 0.092
#> GSM613693 2 0.0592 0.6758 0.000 0.988 0.012
#> GSM613694 3 0.3155 0.7363 0.040 0.044 0.916
#> GSM613695 3 0.2448 0.7321 0.000 0.076 0.924
#> GSM613696 3 0.4121 0.6768 0.000 0.168 0.832
#> GSM613697 3 0.2711 0.7047 0.088 0.000 0.912
#> GSM613698 3 0.3155 0.7363 0.040 0.044 0.916
#> GSM613699 3 0.3116 0.7226 0.000 0.108 0.892
#> GSM613700 2 0.0475 0.6787 0.004 0.992 0.004
#> GSM613701 2 0.6081 0.3209 0.004 0.652 0.344
#> GSM613702 2 0.6617 0.2337 0.012 0.600 0.388
#> GSM613703 1 0.0000 0.9031 1.000 0.000 0.000
#> GSM613704 2 0.0475 0.6787 0.004 0.992 0.004
#> GSM613705 3 0.2947 0.7382 0.020 0.060 0.920
#> GSM613706 3 0.9335 0.1159 0.168 0.376 0.456
#> GSM613707 2 0.0237 0.6780 0.004 0.996 0.000
#> GSM613708 1 0.0000 0.9031 1.000 0.000 0.000
#> GSM613709 1 0.0000 0.9031 1.000 0.000 0.000
#> GSM613710 2 0.0661 0.6749 0.004 0.988 0.008
#> GSM613711 2 0.6244 0.1416 0.000 0.560 0.440
#> GSM613712 3 0.3083 0.7383 0.024 0.060 0.916
#> GSM613713 2 0.0747 0.6710 0.000 0.984 0.016
#> GSM613714 3 0.3267 0.7213 0.000 0.116 0.884
#> GSM613715 3 0.4178 0.6730 0.000 0.172 0.828
#> GSM613716 3 0.3752 0.7047 0.000 0.144 0.856
#> GSM613717 2 0.6244 0.1416 0.000 0.560 0.440
#> GSM613718 2 0.6280 0.0942 0.000 0.540 0.460
#> GSM613719 3 0.3155 0.7363 0.040 0.044 0.916
#> GSM613720 2 0.6168 0.1855 0.000 0.588 0.412
#> GSM613721 2 0.5956 0.3516 0.004 0.672 0.324
#> GSM613722 2 0.0475 0.6787 0.004 0.992 0.004
#> GSM613723 1 0.2625 0.8709 0.916 0.000 0.084
#> GSM613724 1 0.0000 0.9031 1.000 0.000 0.000
#> GSM613725 2 0.0237 0.6780 0.004 0.996 0.000
#> GSM613726 1 0.5810 0.5160 0.664 0.000 0.336
#> GSM613727 1 0.0000 0.9031 1.000 0.000 0.000
#> GSM613728 2 0.0475 0.6787 0.004 0.992 0.004
#> GSM613729 1 0.0000 0.9031 1.000 0.000 0.000
#> GSM613730 2 0.6468 0.1332 0.004 0.552 0.444
#> GSM613731 1 0.6079 0.4139 0.612 0.000 0.388
#> GSM613732 2 0.6280 0.0942 0.000 0.540 0.460
#> GSM613733 2 0.6180 0.1862 0.000 0.584 0.416
#> GSM613734 1 0.1031 0.8951 0.976 0.000 0.024
#> GSM613735 1 0.2537 0.8727 0.920 0.000 0.080
#> GSM613736 2 0.6244 0.1416 0.000 0.560 0.440
#> GSM613737 3 0.3042 0.7359 0.040 0.040 0.920
#> GSM613738 1 0.2796 0.8667 0.908 0.000 0.092
#> GSM613739 1 0.2796 0.8667 0.908 0.000 0.092
#> GSM613740 2 0.6280 0.0942 0.000 0.540 0.460
#> GSM613741 3 0.7542 0.5713 0.120 0.192 0.688
#> GSM613742 1 0.2959 0.8609 0.900 0.000 0.100
#> GSM613743 2 0.6244 0.1416 0.000 0.560 0.440
#> GSM613744 2 0.6280 0.0942 0.000 0.540 0.460
#> GSM613745 3 0.5987 0.6212 0.036 0.208 0.756
#> GSM613746 2 0.0475 0.6787 0.004 0.992 0.004
#> GSM613747 1 0.1031 0.8951 0.976 0.000 0.024
#> GSM613748 2 0.6779 0.1223 0.012 0.544 0.444
#> GSM613749 2 0.9806 -0.0067 0.244 0.408 0.348
#> GSM613750 3 0.6180 0.0755 0.000 0.416 0.584
#> GSM613751 3 0.6291 -0.0545 0.000 0.468 0.532
#> GSM613752 3 0.6291 -0.0545 0.000 0.468 0.532
#> GSM613753 3 0.2261 0.6884 0.000 0.068 0.932
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 4 0.4543 0.5067 0.000 0.000 0.324 0.676
#> GSM613639 1 0.5558 0.1488 0.528 0.012 0.004 0.456
#> GSM613640 4 0.5988 0.5719 0.040 0.032 0.232 0.696
#> GSM613641 1 0.0524 0.8044 0.988 0.004 0.000 0.008
#> GSM613642 2 0.6110 0.6164 0.000 0.680 0.144 0.176
#> GSM613643 4 0.5792 0.3940 0.296 0.000 0.056 0.648
#> GSM613644 4 0.5463 0.4828 0.256 0.000 0.052 0.692
#> GSM613645 1 0.5670 0.2651 0.572 0.020 0.004 0.404
#> GSM613646 4 0.6279 0.5848 0.048 0.136 0.092 0.724
#> GSM613647 4 0.4761 0.4895 0.004 0.000 0.332 0.664
#> GSM613648 3 0.5723 0.5303 0.000 0.072 0.684 0.244
#> GSM613649 3 0.6397 0.6800 0.000 0.184 0.652 0.164
#> GSM613650 4 0.4483 0.5849 0.088 0.000 0.104 0.808
#> GSM613651 4 0.4820 0.4637 0.012 0.000 0.296 0.692
#> GSM613652 1 0.5968 0.6770 0.672 0.000 0.092 0.236
#> GSM613653 4 0.6296 0.5842 0.052 0.136 0.088 0.724
#> GSM613654 1 0.5998 0.6739 0.668 0.000 0.092 0.240
#> GSM613655 1 0.1888 0.7998 0.940 0.000 0.044 0.016
#> GSM613656 1 0.5968 0.6770 0.672 0.000 0.092 0.236
#> GSM613657 3 0.5090 0.7630 0.000 0.228 0.728 0.044
#> GSM613658 1 0.1985 0.8006 0.940 0.004 0.040 0.016
#> GSM613659 4 0.5511 0.0305 0.000 0.484 0.016 0.500
#> GSM613660 2 0.4017 0.7803 0.000 0.828 0.128 0.044
#> GSM613661 1 0.4809 0.4775 0.684 0.004 0.004 0.308
#> GSM613662 2 0.3529 0.7359 0.000 0.836 0.012 0.152
#> GSM613663 1 0.0895 0.8021 0.976 0.000 0.004 0.020
#> GSM613664 2 0.2737 0.7581 0.000 0.888 0.008 0.104
#> GSM613665 2 0.3108 0.7965 0.000 0.872 0.112 0.016
#> GSM613666 1 0.0524 0.8044 0.988 0.004 0.000 0.008
#> GSM613667 1 0.5334 0.2945 0.588 0.008 0.004 0.400
#> GSM613668 1 0.0921 0.8047 0.972 0.000 0.028 0.000
#> GSM613669 1 0.0524 0.8044 0.988 0.004 0.000 0.008
#> GSM613670 2 0.4980 0.5039 0.000 0.680 0.016 0.304
#> GSM613671 1 0.0524 0.8044 0.988 0.004 0.000 0.008
#> GSM613672 1 0.0921 0.8047 0.972 0.000 0.028 0.000
#> GSM613673 1 0.0817 0.8023 0.976 0.000 0.000 0.024
#> GSM613674 2 0.2589 0.7900 0.000 0.884 0.116 0.000
#> GSM613675 2 0.2805 0.7724 0.000 0.888 0.012 0.100
#> GSM613676 2 0.3280 0.7926 0.000 0.860 0.124 0.016
#> GSM613677 4 0.7483 0.3080 0.000 0.184 0.360 0.456
#> GSM613678 4 0.7019 0.3084 0.108 0.332 0.008 0.552
#> GSM613679 2 0.3048 0.7968 0.000 0.876 0.108 0.016
#> GSM613680 1 0.0336 0.8052 0.992 0.000 0.008 0.000
#> GSM613681 1 0.0779 0.8029 0.980 0.004 0.000 0.016
#> GSM613682 1 0.0707 0.8030 0.980 0.000 0.000 0.020
#> GSM613683 1 0.1888 0.7995 0.940 0.000 0.044 0.016
#> GSM613684 2 0.2530 0.7924 0.000 0.888 0.112 0.000
#> GSM613685 2 0.2589 0.7900 0.000 0.884 0.116 0.000
#> GSM613686 1 0.5305 0.4359 0.648 0.016 0.004 0.332
#> GSM613687 1 0.0817 0.8019 0.976 0.000 0.000 0.024
#> GSM613688 2 0.2111 0.7860 0.000 0.932 0.024 0.044
#> GSM613689 3 0.5008 0.5219 0.000 0.040 0.732 0.228
#> GSM613690 3 0.4936 0.3809 0.000 0.012 0.672 0.316
#> GSM613691 2 0.5141 0.5498 0.000 0.700 0.032 0.268
#> GSM613692 1 0.6259 0.6241 0.616 0.000 0.084 0.300
#> GSM613693 2 0.4274 0.7520 0.000 0.820 0.108 0.072
#> GSM613694 4 0.4406 0.5270 0.000 0.000 0.300 0.700
#> GSM613695 3 0.4916 0.0191 0.000 0.000 0.576 0.424
#> GSM613696 4 0.6668 0.3397 0.000 0.092 0.380 0.528
#> GSM613697 4 0.4891 0.4491 0.012 0.000 0.308 0.680
#> GSM613698 4 0.4872 0.4545 0.000 0.004 0.356 0.640
#> GSM613699 4 0.5132 0.3270 0.000 0.004 0.448 0.548
#> GSM613700 2 0.3634 0.7949 0.000 0.856 0.096 0.048
#> GSM613701 2 0.5650 0.1127 0.000 0.544 0.024 0.432
#> GSM613702 4 0.5570 0.1140 0.000 0.440 0.020 0.540
#> GSM613703 1 0.3350 0.7350 0.864 0.016 0.004 0.116
#> GSM613704 2 0.2546 0.7748 0.000 0.900 0.008 0.092
#> GSM613705 4 0.4624 0.4888 0.000 0.000 0.340 0.660
#> GSM613706 4 0.7508 0.5650 0.120 0.164 0.080 0.636
#> GSM613707 2 0.2589 0.7900 0.000 0.884 0.116 0.000
#> GSM613708 1 0.1209 0.7969 0.964 0.000 0.004 0.032
#> GSM613709 1 0.0524 0.8044 0.988 0.004 0.000 0.008
#> GSM613710 2 0.4224 0.7653 0.000 0.812 0.144 0.044
#> GSM613711 3 0.5219 0.7526 0.000 0.244 0.712 0.044
#> GSM613712 4 0.4830 0.4174 0.000 0.000 0.392 0.608
#> GSM613713 2 0.5130 0.3746 0.000 0.652 0.332 0.016
#> GSM613714 3 0.4761 0.3197 0.000 0.004 0.664 0.332
#> GSM613715 3 0.5297 0.4186 0.000 0.032 0.676 0.292
#> GSM613716 4 0.7130 0.2156 0.000 0.132 0.396 0.472
#> GSM613717 3 0.5156 0.7581 0.000 0.236 0.720 0.044
#> GSM613718 3 0.5056 0.7647 0.000 0.224 0.732 0.044
#> GSM613719 4 0.3494 0.5729 0.000 0.004 0.172 0.824
#> GSM613720 3 0.6969 0.4321 0.000 0.436 0.452 0.112
#> GSM613721 2 0.4898 0.5556 0.000 0.716 0.024 0.260
#> GSM613722 2 0.3734 0.7911 0.000 0.848 0.108 0.044
#> GSM613723 1 0.5998 0.6739 0.668 0.000 0.092 0.240
#> GSM613724 1 0.1798 0.8003 0.944 0.000 0.040 0.016
#> GSM613725 2 0.3962 0.7834 0.000 0.832 0.124 0.044
#> GSM613726 1 0.6049 0.2342 0.564 0.008 0.032 0.396
#> GSM613727 1 0.1209 0.8047 0.964 0.004 0.032 0.000
#> GSM613728 2 0.2796 0.7845 0.000 0.892 0.016 0.092
#> GSM613729 1 0.0967 0.8021 0.976 0.004 0.004 0.016
#> GSM613730 4 0.6352 0.3391 0.012 0.356 0.048 0.584
#> GSM613731 4 0.6368 0.2194 0.400 0.004 0.056 0.540
#> GSM613732 3 0.5213 0.7638 0.000 0.224 0.724 0.052
#> GSM613733 3 0.6078 0.6244 0.000 0.312 0.620 0.068
#> GSM613734 1 0.5003 0.7323 0.768 0.000 0.084 0.148
#> GSM613735 1 0.5968 0.6770 0.672 0.000 0.092 0.236
#> GSM613736 3 0.5188 0.7569 0.000 0.240 0.716 0.044
#> GSM613737 4 0.4746 0.4506 0.000 0.000 0.368 0.632
#> GSM613738 1 0.6217 0.6318 0.624 0.000 0.084 0.292
#> GSM613739 1 0.6307 0.6283 0.620 0.000 0.092 0.288
#> GSM613740 3 0.5056 0.7647 0.000 0.224 0.732 0.044
#> GSM613741 4 0.6390 0.5813 0.052 0.144 0.088 0.716
#> GSM613742 1 0.6338 0.6015 0.600 0.000 0.084 0.316
#> GSM613743 3 0.5156 0.7581 0.000 0.236 0.720 0.044
#> GSM613744 3 0.5056 0.7647 0.000 0.224 0.732 0.044
#> GSM613745 4 0.6609 0.5739 0.048 0.160 0.096 0.696
#> GSM613746 2 0.2845 0.7727 0.000 0.896 0.028 0.076
#> GSM613747 1 0.5003 0.7323 0.768 0.000 0.084 0.148
#> GSM613748 4 0.6617 0.4286 0.016 0.300 0.072 0.612
#> GSM613749 4 0.7190 0.3371 0.192 0.260 0.000 0.548
#> GSM613750 3 0.3910 0.7212 0.000 0.156 0.820 0.024
#> GSM613751 3 0.3900 0.7247 0.000 0.164 0.816 0.020
#> GSM613752 3 0.3991 0.7245 0.000 0.172 0.808 0.020
#> GSM613753 3 0.3810 0.4907 0.000 0.008 0.804 0.188
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM613638 4 0.4667 0.6159 0.020 0.008 0.104 0.784 0.084
#> GSM613639 1 0.5904 0.2351 0.532 0.008 0.000 0.376 0.084
#> GSM613640 4 0.4205 0.6179 0.036 0.060 0.048 0.832 0.024
#> GSM613641 1 0.4557 0.3791 0.516 0.008 0.000 0.000 0.476
#> GSM613642 2 0.6392 0.4608 0.088 0.548 0.036 0.328 0.000
#> GSM613643 4 0.5039 0.5817 0.184 0.000 0.000 0.700 0.116
#> GSM613644 4 0.5222 0.6017 0.196 0.000 0.000 0.680 0.124
#> GSM613645 1 0.6003 0.3761 0.572 0.008 0.000 0.308 0.112
#> GSM613646 4 0.6609 0.5077 0.188 0.160 0.024 0.612 0.016
#> GSM613647 4 0.4896 0.6044 0.004 0.004 0.096 0.736 0.160
#> GSM613648 3 0.4763 0.4126 0.004 0.020 0.616 0.360 0.000
#> GSM613649 3 0.3849 0.6180 0.000 0.016 0.752 0.232 0.000
#> GSM613650 4 0.5756 0.6341 0.140 0.012 0.024 0.700 0.124
#> GSM613651 4 0.5697 0.4968 0.008 0.000 0.072 0.568 0.352
#> GSM613652 5 0.0703 0.5915 0.000 0.000 0.000 0.024 0.976
#> GSM613653 4 0.6682 0.4957 0.180 0.176 0.020 0.604 0.020
#> GSM613654 5 0.0794 0.5911 0.000 0.000 0.000 0.028 0.972
#> GSM613655 5 0.4440 -0.2882 0.468 0.004 0.000 0.000 0.528
#> GSM613656 5 0.0703 0.5915 0.000 0.000 0.000 0.024 0.976
#> GSM613657 3 0.1041 0.7831 0.000 0.004 0.964 0.032 0.000
#> GSM613658 5 0.4555 -0.3049 0.472 0.008 0.000 0.000 0.520
#> GSM613659 2 0.6328 0.0718 0.156 0.516 0.004 0.324 0.000
#> GSM613660 2 0.6794 0.6306 0.108 0.592 0.212 0.088 0.000
#> GSM613661 1 0.5788 0.3848 0.580 0.000 0.000 0.300 0.120
#> GSM613662 2 0.3787 0.6305 0.048 0.836 0.028 0.088 0.000
#> GSM613663 1 0.4278 0.4171 0.548 0.000 0.000 0.000 0.452
#> GSM613664 2 0.3005 0.6535 0.052 0.888 0.016 0.036 0.008
#> GSM613665 2 0.6292 0.6520 0.076 0.632 0.216 0.076 0.000
#> GSM613666 1 0.4557 0.3791 0.516 0.008 0.000 0.000 0.476
#> GSM613667 1 0.5971 0.3803 0.580 0.008 0.000 0.300 0.112
#> GSM613668 5 0.4449 -0.3359 0.484 0.004 0.000 0.000 0.512
#> GSM613669 1 0.4557 0.3791 0.516 0.008 0.000 0.000 0.476
#> GSM613670 2 0.4732 0.5318 0.108 0.744 0.004 0.144 0.000
#> GSM613671 1 0.4557 0.3791 0.516 0.008 0.000 0.000 0.476
#> GSM613672 5 0.4305 -0.3403 0.488 0.000 0.000 0.000 0.512
#> GSM613673 1 0.4861 0.4282 0.548 0.000 0.000 0.024 0.428
#> GSM613674 2 0.6292 0.6427 0.124 0.640 0.196 0.032 0.008
#> GSM613675 2 0.4028 0.6384 0.044 0.824 0.044 0.088 0.000
#> GSM613676 2 0.6370 0.6448 0.076 0.620 0.228 0.076 0.000
#> GSM613677 4 0.5724 0.4612 0.024 0.108 0.200 0.668 0.000
#> GSM613678 4 0.6681 0.2310 0.248 0.328 0.000 0.424 0.000
#> GSM613679 2 0.6026 0.6529 0.096 0.660 0.192 0.052 0.000
#> GSM613680 1 0.4449 0.3596 0.512 0.004 0.000 0.000 0.484
#> GSM613681 1 0.4700 0.3865 0.516 0.008 0.000 0.004 0.472
#> GSM613682 1 0.4528 0.4264 0.548 0.000 0.000 0.008 0.444
#> GSM613683 5 0.4294 -0.2829 0.468 0.000 0.000 0.000 0.532
#> GSM613684 2 0.4797 0.6568 0.080 0.736 0.176 0.000 0.008
#> GSM613685 2 0.6292 0.6427 0.124 0.640 0.196 0.032 0.008
#> GSM613686 1 0.5494 0.4093 0.668 0.004 0.000 0.172 0.156
#> GSM613687 1 0.4528 0.4264 0.548 0.000 0.000 0.008 0.444
#> GSM613688 2 0.2155 0.6682 0.036 0.928 0.012 0.016 0.008
#> GSM613689 3 0.5021 0.3823 0.024 0.008 0.588 0.380 0.000
#> GSM613690 3 0.4553 0.3858 0.008 0.004 0.604 0.384 0.000
#> GSM613691 2 0.5279 0.5397 0.108 0.724 0.028 0.140 0.000
#> GSM613692 5 0.1892 0.5627 0.004 0.000 0.000 0.080 0.916
#> GSM613693 2 0.6438 0.6099 0.068 0.648 0.180 0.096 0.008
#> GSM613694 4 0.4312 0.6133 0.000 0.000 0.104 0.772 0.124
#> GSM613695 4 0.4886 0.1240 0.004 0.004 0.420 0.560 0.012
#> GSM613696 4 0.6375 0.5269 0.064 0.120 0.148 0.660 0.008
#> GSM613697 4 0.5760 0.4721 0.008 0.000 0.072 0.544 0.376
#> GSM613698 4 0.5540 0.5604 0.008 0.000 0.120 0.664 0.208
#> GSM613699 4 0.4167 0.4948 0.000 0.000 0.252 0.724 0.024
#> GSM613700 2 0.6698 0.6373 0.104 0.604 0.204 0.088 0.000
#> GSM613701 2 0.6132 0.2451 0.124 0.524 0.004 0.348 0.000
#> GSM613702 4 0.6218 0.1731 0.148 0.364 0.000 0.488 0.000
#> GSM613703 1 0.5014 0.4207 0.628 0.008 0.000 0.032 0.332
#> GSM613704 2 0.4083 0.6358 0.044 0.820 0.044 0.092 0.000
#> GSM613705 4 0.4746 0.6085 0.020 0.004 0.116 0.772 0.088
#> GSM613706 4 0.4300 0.5985 0.088 0.108 0.000 0.792 0.012
#> GSM613707 2 0.6292 0.6427 0.124 0.640 0.196 0.032 0.008
#> GSM613708 1 0.4713 0.4277 0.544 0.000 0.000 0.016 0.440
#> GSM613709 1 0.4557 0.3791 0.516 0.008 0.000 0.000 0.476
#> GSM613710 2 0.6844 0.6175 0.108 0.580 0.228 0.084 0.000
#> GSM613711 3 0.1153 0.7802 0.004 0.008 0.964 0.024 0.000
#> GSM613712 4 0.5227 0.5567 0.004 0.000 0.168 0.696 0.132
#> GSM613713 3 0.6424 -0.1933 0.120 0.384 0.484 0.004 0.008
#> GSM613714 4 0.4596 -0.1453 0.004 0.004 0.496 0.496 0.000
#> GSM613715 3 0.5013 0.4183 0.008 0.028 0.612 0.352 0.000
#> GSM613716 4 0.7769 0.2270 0.084 0.340 0.180 0.396 0.000
#> GSM613717 3 0.1243 0.7810 0.004 0.008 0.960 0.028 0.000
#> GSM613718 3 0.1041 0.7831 0.000 0.004 0.964 0.032 0.000
#> GSM613719 4 0.6141 0.6364 0.132 0.012 0.052 0.684 0.120
#> GSM613720 2 0.7431 -0.0081 0.060 0.404 0.376 0.160 0.000
#> GSM613721 2 0.5258 0.5558 0.116 0.732 0.016 0.128 0.008
#> GSM613722 2 0.6698 0.6373 0.104 0.604 0.204 0.088 0.000
#> GSM613723 5 0.0794 0.5911 0.000 0.000 0.000 0.028 0.972
#> GSM613724 5 0.4440 -0.2882 0.468 0.004 0.000 0.000 0.528
#> GSM613725 2 0.6810 0.6314 0.112 0.592 0.208 0.088 0.000
#> GSM613726 1 0.5762 0.3323 0.548 0.000 0.000 0.352 0.100
#> GSM613727 5 0.4561 -0.3541 0.488 0.008 0.000 0.000 0.504
#> GSM613728 2 0.4191 0.6620 0.036 0.808 0.044 0.112 0.000
#> GSM613729 1 0.4989 0.4040 0.520 0.008 0.000 0.016 0.456
#> GSM613730 4 0.5920 0.4121 0.148 0.272 0.000 0.580 0.000
#> GSM613731 4 0.4990 0.3739 0.324 0.000 0.000 0.628 0.048
#> GSM613732 3 0.1041 0.7831 0.000 0.004 0.964 0.032 0.000
#> GSM613733 3 0.4534 0.6066 0.064 0.072 0.796 0.068 0.000
#> GSM613734 5 0.1851 0.5294 0.088 0.000 0.000 0.000 0.912
#> GSM613735 5 0.0703 0.5915 0.000 0.000 0.000 0.024 0.976
#> GSM613736 3 0.1908 0.7697 0.016 0.024 0.936 0.024 0.000
#> GSM613737 4 0.5426 0.5615 0.004 0.000 0.132 0.672 0.192
#> GSM613738 5 0.1892 0.5627 0.004 0.000 0.000 0.080 0.916
#> GSM613739 5 0.1892 0.5627 0.004 0.000 0.000 0.080 0.916
#> GSM613740 3 0.1026 0.7824 0.004 0.004 0.968 0.024 0.000
#> GSM613741 4 0.6712 0.4912 0.180 0.180 0.020 0.600 0.020
#> GSM613742 5 0.2179 0.5389 0.004 0.000 0.000 0.100 0.896
#> GSM613743 3 0.1153 0.7802 0.004 0.008 0.964 0.024 0.000
#> GSM613744 3 0.1041 0.7831 0.000 0.004 0.964 0.032 0.000
#> GSM613745 4 0.6859 0.4437 0.156 0.232 0.024 0.572 0.016
#> GSM613746 2 0.5082 0.6146 0.068 0.768 0.060 0.096 0.008
#> GSM613747 5 0.1851 0.5294 0.088 0.000 0.000 0.000 0.912
#> GSM613748 4 0.4610 0.5614 0.112 0.128 0.004 0.756 0.000
#> GSM613749 1 0.6133 -0.1197 0.496 0.136 0.000 0.368 0.000
#> GSM613750 3 0.4062 0.7031 0.152 0.000 0.796 0.036 0.016
#> GSM613751 3 0.3632 0.7055 0.152 0.000 0.816 0.016 0.016
#> GSM613752 3 0.3632 0.7055 0.152 0.000 0.816 0.016 0.016
#> GSM613753 3 0.5788 0.6110 0.156 0.004 0.672 0.152 0.016
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM613638 4 0.5542 0.5130 0.000 0.032 0.092 0.688 0.152 0.036
#> GSM613639 4 0.5729 0.2928 0.340 0.000 0.000 0.544 0.048 0.068
#> GSM613640 4 0.4449 0.5269 0.000 0.088 0.048 0.776 0.080 0.008
#> GSM613641 1 0.1096 0.8793 0.964 0.000 0.008 0.004 0.004 0.020
#> GSM613642 2 0.5085 0.4431 0.000 0.688 0.052 0.204 0.052 0.004
#> GSM613643 4 0.3847 0.5470 0.092 0.004 0.004 0.800 0.096 0.004
#> GSM613644 4 0.3865 0.5366 0.072 0.000 0.000 0.808 0.080 0.040
#> GSM613645 4 0.5777 0.1889 0.392 0.000 0.000 0.496 0.044 0.068
#> GSM613646 4 0.5431 0.1296 0.004 0.000 0.016 0.512 0.064 0.404
#> GSM613647 4 0.6071 0.4339 0.000 0.000 0.092 0.544 0.300 0.064
#> GSM613648 3 0.5761 0.4919 0.000 0.004 0.628 0.220 0.080 0.068
#> GSM613649 3 0.5720 0.6043 0.000 0.052 0.684 0.148 0.048 0.068
#> GSM613650 4 0.5655 0.4651 0.004 0.000 0.024 0.624 0.160 0.188
#> GSM613651 5 0.6047 -0.2083 0.000 0.000 0.076 0.380 0.484 0.060
#> GSM613652 5 0.3309 0.8055 0.280 0.000 0.000 0.000 0.720 0.000
#> GSM613653 6 0.5534 -0.0315 0.004 0.000 0.016 0.416 0.072 0.492
#> GSM613654 5 0.3405 0.8079 0.272 0.000 0.000 0.004 0.724 0.000
#> GSM613655 1 0.1820 0.8553 0.924 0.000 0.012 0.000 0.056 0.008
#> GSM613656 5 0.3309 0.8055 0.280 0.000 0.000 0.000 0.720 0.000
#> GSM613657 3 0.2402 0.7197 0.000 0.140 0.856 0.004 0.000 0.000
#> GSM613658 1 0.1476 0.8700 0.948 0.000 0.008 0.004 0.028 0.012
#> GSM613659 6 0.5203 0.3260 0.000 0.104 0.000 0.348 0.000 0.548
#> GSM613660 2 0.1320 0.7145 0.000 0.948 0.016 0.036 0.000 0.000
#> GSM613661 1 0.5119 -0.0141 0.480 0.000 0.000 0.456 0.052 0.012
#> GSM613662 6 0.4495 0.4364 0.000 0.340 0.016 0.020 0.000 0.624
#> GSM613663 1 0.1553 0.8709 0.944 0.000 0.004 0.032 0.012 0.008
#> GSM613664 6 0.4546 0.0662 0.000 0.444 0.000 0.008 0.020 0.528
#> GSM613665 2 0.2956 0.6889 0.000 0.856 0.028 0.016 0.000 0.100
#> GSM613666 1 0.1096 0.8793 0.964 0.000 0.008 0.004 0.004 0.020
#> GSM613667 4 0.5782 0.1790 0.396 0.000 0.000 0.492 0.044 0.068
#> GSM613668 1 0.1226 0.8691 0.952 0.000 0.004 0.000 0.040 0.004
#> GSM613669 1 0.1096 0.8793 0.964 0.000 0.008 0.004 0.004 0.020
#> GSM613670 6 0.4158 0.5075 0.000 0.244 0.000 0.052 0.000 0.704
#> GSM613671 1 0.1096 0.8793 0.964 0.000 0.008 0.004 0.004 0.020
#> GSM613672 1 0.1734 0.8656 0.932 0.000 0.004 0.008 0.048 0.008
#> GSM613673 1 0.2382 0.8472 0.896 0.000 0.004 0.072 0.020 0.008
#> GSM613674 2 0.3233 0.6666 0.000 0.828 0.000 0.016 0.024 0.132
#> GSM613675 6 0.4583 0.4257 0.000 0.344 0.016 0.024 0.000 0.616
#> GSM613676 2 0.2973 0.6946 0.000 0.860 0.040 0.016 0.000 0.084
#> GSM613677 4 0.6806 0.3818 0.000 0.084 0.200 0.576 0.076 0.064
#> GSM613678 4 0.6426 0.2019 0.056 0.060 0.000 0.544 0.040 0.300
#> GSM613679 2 0.1686 0.7113 0.000 0.932 0.004 0.004 0.008 0.052
#> GSM613680 1 0.1080 0.8741 0.960 0.000 0.004 0.000 0.032 0.004
#> GSM613681 1 0.0405 0.8819 0.988 0.000 0.000 0.004 0.000 0.008
#> GSM613682 1 0.1836 0.8637 0.928 0.000 0.004 0.048 0.012 0.008
#> GSM613683 1 0.1732 0.8483 0.920 0.000 0.004 0.000 0.072 0.004
#> GSM613684 2 0.4839 0.4465 0.000 0.640 0.012 0.016 0.028 0.304
#> GSM613685 2 0.3233 0.6666 0.000 0.828 0.000 0.016 0.024 0.132
#> GSM613686 1 0.4696 0.5806 0.704 0.000 0.000 0.212 0.048 0.036
#> GSM613687 1 0.1836 0.8637 0.928 0.000 0.004 0.048 0.012 0.008
#> GSM613688 2 0.4928 -0.0260 0.000 0.480 0.008 0.008 0.028 0.476
#> GSM613689 3 0.6654 0.3878 0.000 0.048 0.540 0.280 0.076 0.056
#> GSM613690 3 0.5889 0.4376 0.000 0.000 0.592 0.248 0.100 0.060
#> GSM613691 6 0.3886 0.5543 0.000 0.164 0.008 0.056 0.000 0.772
#> GSM613692 5 0.3642 0.8053 0.236 0.000 0.000 0.008 0.744 0.012
#> GSM613693 6 0.4900 0.4118 0.000 0.260 0.076 0.000 0.012 0.652
#> GSM613694 4 0.6105 0.4759 0.000 0.000 0.084 0.588 0.220 0.108
#> GSM613695 3 0.6510 0.1245 0.000 0.000 0.432 0.376 0.132 0.060
#> GSM613696 6 0.6948 -0.1460 0.000 0.000 0.152 0.304 0.104 0.440
#> GSM613697 5 0.5962 -0.1091 0.000 0.000 0.076 0.336 0.528 0.060
#> GSM613698 4 0.6828 0.3470 0.000 0.000 0.116 0.436 0.336 0.112
#> GSM613699 4 0.6667 0.3319 0.000 0.000 0.216 0.528 0.128 0.128
#> GSM613700 2 0.1320 0.7140 0.000 0.948 0.016 0.036 0.000 0.000
#> GSM613701 2 0.5245 0.0211 0.004 0.480 0.000 0.444 0.004 0.068
#> GSM613702 4 0.5729 0.3118 0.000 0.252 0.012 0.588 0.008 0.140
#> GSM613703 1 0.4169 0.7261 0.788 0.000 0.008 0.120 0.044 0.040
#> GSM613704 6 0.4345 0.4215 0.000 0.344 0.016 0.012 0.000 0.628
#> GSM613705 4 0.5918 0.4903 0.000 0.032 0.116 0.656 0.152 0.044
#> GSM613706 4 0.4206 0.5068 0.008 0.152 0.028 0.772 0.040 0.000
#> GSM613707 2 0.3233 0.6666 0.000 0.828 0.000 0.016 0.024 0.132
#> GSM613708 1 0.2620 0.8155 0.868 0.000 0.000 0.108 0.012 0.012
#> GSM613709 1 0.1096 0.8793 0.964 0.000 0.008 0.004 0.004 0.020
#> GSM613710 2 0.1644 0.7075 0.000 0.932 0.028 0.040 0.000 0.000
#> GSM613711 3 0.2442 0.7173 0.000 0.144 0.852 0.004 0.000 0.000
#> GSM613712 4 0.6876 0.3607 0.000 0.000 0.148 0.464 0.284 0.104
#> GSM613713 2 0.5688 0.4768 0.000 0.632 0.220 0.016 0.024 0.108
#> GSM613714 3 0.6244 0.2683 0.000 0.000 0.496 0.340 0.104 0.060
#> GSM613715 3 0.5530 0.5048 0.000 0.000 0.644 0.212 0.076 0.068
#> GSM613716 6 0.5194 0.3861 0.000 0.000 0.124 0.136 0.048 0.692
#> GSM613717 3 0.3196 0.7142 0.000 0.156 0.816 0.020 0.000 0.008
#> GSM613718 3 0.2431 0.7229 0.000 0.132 0.860 0.008 0.000 0.000
#> GSM613719 4 0.6404 0.4332 0.000 0.000 0.052 0.524 0.188 0.236
#> GSM613720 6 0.5396 0.4673 0.000 0.100 0.180 0.032 0.012 0.676
#> GSM613721 6 0.3513 0.5389 0.000 0.176 0.004 0.020 0.008 0.792
#> GSM613722 2 0.1464 0.7125 0.000 0.944 0.016 0.036 0.000 0.004
#> GSM613723 5 0.3405 0.8079 0.272 0.000 0.000 0.004 0.724 0.000
#> GSM613724 1 0.1429 0.8608 0.940 0.000 0.004 0.000 0.052 0.004
#> GSM613725 2 0.1124 0.7148 0.000 0.956 0.008 0.036 0.000 0.000
#> GSM613726 4 0.5216 0.2320 0.376 0.000 0.004 0.556 0.040 0.024
#> GSM613727 1 0.1672 0.8729 0.940 0.000 0.012 0.004 0.028 0.016
#> GSM613728 2 0.4708 0.2367 0.000 0.612 0.016 0.032 0.000 0.340
#> GSM613729 1 0.1406 0.8766 0.952 0.000 0.008 0.016 0.004 0.020
#> GSM613730 4 0.5959 0.3472 0.000 0.140 0.012 0.620 0.040 0.188
#> GSM613731 4 0.4101 0.5130 0.192 0.004 0.004 0.752 0.044 0.004
#> GSM613732 3 0.2431 0.7229 0.000 0.132 0.860 0.008 0.000 0.000
#> GSM613733 3 0.3993 0.4188 0.000 0.400 0.592 0.008 0.000 0.000
#> GSM613734 5 0.3634 0.7056 0.356 0.000 0.000 0.000 0.644 0.000
#> GSM613735 5 0.3330 0.8018 0.284 0.000 0.000 0.000 0.716 0.000
#> GSM613736 3 0.2809 0.7048 0.000 0.168 0.824 0.004 0.004 0.000
#> GSM613737 4 0.6833 0.3600 0.000 0.000 0.128 0.456 0.308 0.108
#> GSM613738 5 0.3642 0.8053 0.236 0.000 0.000 0.008 0.744 0.012
#> GSM613739 5 0.3642 0.8059 0.236 0.000 0.000 0.008 0.744 0.012
#> GSM613740 3 0.2389 0.7226 0.000 0.128 0.864 0.008 0.000 0.000
#> GSM613741 6 0.5516 0.0133 0.004 0.000 0.016 0.400 0.072 0.508
#> GSM613742 5 0.3693 0.7926 0.216 0.000 0.000 0.016 0.756 0.012
#> GSM613743 3 0.2442 0.7173 0.000 0.144 0.852 0.004 0.000 0.000
#> GSM613744 3 0.2431 0.7229 0.000 0.132 0.860 0.008 0.000 0.000
#> GSM613745 4 0.5464 0.0307 0.004 0.000 0.016 0.472 0.064 0.444
#> GSM613746 6 0.3780 0.4883 0.000 0.248 0.020 0.000 0.004 0.728
#> GSM613747 5 0.3634 0.7056 0.356 0.000 0.000 0.000 0.644 0.000
#> GSM613748 4 0.4780 0.4714 0.000 0.164 0.024 0.732 0.016 0.064
#> GSM613749 4 0.6730 0.3734 0.264 0.044 0.000 0.536 0.044 0.112
#> GSM613750 3 0.4961 0.6166 0.000 0.052 0.756 0.048 0.064 0.080
#> GSM613751 3 0.5197 0.6134 0.000 0.064 0.740 0.052 0.068 0.076
#> GSM613752 3 0.5133 0.6131 0.000 0.064 0.744 0.048 0.064 0.080
#> GSM613753 3 0.4794 0.6115 0.000 0.008 0.752 0.076 0.084 0.080
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n disease.state(p) k
#> SD:kmeans 115 2.58e-02 2
#> SD:kmeans 84 8.50e-02 3
#> SD:kmeans 82 1.56e-03 4
#> SD:kmeans 65 2.34e-05 5
#> SD:kmeans 68 2.71e-05 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["SD", "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 27425 rows and 116 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 1.000 0.976 0.990 0.5045 0.496 0.496
#> 3 3 0.750 0.863 0.914 0.3062 0.748 0.534
#> 4 4 0.698 0.745 0.819 0.1246 0.851 0.592
#> 5 5 0.725 0.722 0.834 0.0612 0.906 0.652
#> 6 6 0.755 0.703 0.803 0.0378 0.932 0.696
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
#> GSM613638 2 0.9635 0.384 0.388 0.612
#> GSM613639 1 0.0000 0.996 1.000 0.000
#> GSM613640 2 0.0672 0.978 0.008 0.992
#> GSM613641 1 0.0000 0.996 1.000 0.000
#> GSM613642 2 0.0000 0.984 0.000 1.000
#> GSM613643 1 0.0000 0.996 1.000 0.000
#> GSM613644 1 0.0000 0.996 1.000 0.000
#> GSM613645 1 0.0000 0.996 1.000 0.000
#> GSM613646 1 0.0376 0.992 0.996 0.004
#> GSM613647 1 0.0376 0.992 0.996 0.004
#> GSM613648 2 0.0000 0.984 0.000 1.000
#> GSM613649 2 0.0000 0.984 0.000 1.000
#> GSM613650 1 0.0000 0.996 1.000 0.000
#> GSM613651 1 0.0000 0.996 1.000 0.000
#> GSM613652 1 0.0000 0.996 1.000 0.000
#> GSM613653 1 0.0376 0.992 0.996 0.004
#> GSM613654 1 0.0000 0.996 1.000 0.000
#> GSM613655 1 0.0000 0.996 1.000 0.000
#> GSM613656 1 0.0000 0.996 1.000 0.000
#> GSM613657 2 0.0000 0.984 0.000 1.000
#> GSM613658 1 0.0000 0.996 1.000 0.000
#> GSM613659 2 0.0000 0.984 0.000 1.000
#> GSM613660 2 0.0000 0.984 0.000 1.000
#> GSM613661 1 0.0000 0.996 1.000 0.000
#> GSM613662 2 0.0000 0.984 0.000 1.000
#> GSM613663 1 0.0000 0.996 1.000 0.000
#> GSM613664 2 0.0000 0.984 0.000 1.000
#> GSM613665 2 0.0000 0.984 0.000 1.000
#> GSM613666 1 0.0000 0.996 1.000 0.000
#> GSM613667 1 0.0000 0.996 1.000 0.000
#> GSM613668 1 0.0000 0.996 1.000 0.000
#> GSM613669 1 0.0000 0.996 1.000 0.000
#> GSM613670 2 0.0376 0.981 0.004 0.996
#> GSM613671 1 0.0000 0.996 1.000 0.000
#> GSM613672 1 0.0000 0.996 1.000 0.000
#> GSM613673 1 0.0000 0.996 1.000 0.000
#> GSM613674 2 0.0000 0.984 0.000 1.000
#> GSM613675 2 0.0000 0.984 0.000 1.000
#> GSM613676 2 0.0000 0.984 0.000 1.000
#> GSM613677 2 0.0000 0.984 0.000 1.000
#> GSM613678 1 0.0000 0.996 1.000 0.000
#> GSM613679 2 0.0000 0.984 0.000 1.000
#> GSM613680 1 0.0000 0.996 1.000 0.000
#> GSM613681 1 0.0000 0.996 1.000 0.000
#> GSM613682 1 0.0000 0.996 1.000 0.000
#> GSM613683 1 0.0000 0.996 1.000 0.000
#> GSM613684 2 0.0000 0.984 0.000 1.000
#> GSM613685 2 0.0000 0.984 0.000 1.000
#> GSM613686 1 0.0000 0.996 1.000 0.000
#> GSM613687 1 0.0000 0.996 1.000 0.000
#> GSM613688 2 0.0000 0.984 0.000 1.000
#> GSM613689 2 0.0000 0.984 0.000 1.000
#> GSM613690 2 0.0000 0.984 0.000 1.000
#> GSM613691 2 0.0000 0.984 0.000 1.000
#> GSM613692 1 0.0000 0.996 1.000 0.000
#> GSM613693 2 0.0000 0.984 0.000 1.000
#> GSM613694 1 0.0000 0.996 1.000 0.000
#> GSM613695 2 0.0000 0.984 0.000 1.000
#> GSM613696 2 0.0000 0.984 0.000 1.000
#> GSM613697 1 0.0000 0.996 1.000 0.000
#> GSM613698 1 0.0000 0.996 1.000 0.000
#> GSM613699 2 0.2043 0.955 0.032 0.968
#> GSM613700 2 0.0000 0.984 0.000 1.000
#> GSM613701 2 0.0000 0.984 0.000 1.000
#> GSM613702 2 0.0000 0.984 0.000 1.000
#> GSM613703 1 0.0000 0.996 1.000 0.000
#> GSM613704 2 0.0000 0.984 0.000 1.000
#> GSM613705 2 0.5737 0.838 0.136 0.864
#> GSM613706 1 0.0000 0.996 1.000 0.000
#> GSM613707 2 0.0000 0.984 0.000 1.000
#> GSM613708 1 0.0000 0.996 1.000 0.000
#> GSM613709 1 0.0000 0.996 1.000 0.000
#> GSM613710 2 0.0000 0.984 0.000 1.000
#> GSM613711 2 0.0000 0.984 0.000 1.000
#> GSM613712 2 0.9248 0.498 0.340 0.660
#> GSM613713 2 0.0000 0.984 0.000 1.000
#> GSM613714 2 0.0000 0.984 0.000 1.000
#> GSM613715 2 0.0000 0.984 0.000 1.000
#> GSM613716 2 0.0000 0.984 0.000 1.000
#> GSM613717 2 0.0000 0.984 0.000 1.000
#> GSM613718 2 0.0000 0.984 0.000 1.000
#> GSM613719 1 0.0000 0.996 1.000 0.000
#> GSM613720 2 0.0000 0.984 0.000 1.000
#> GSM613721 2 0.0000 0.984 0.000 1.000
#> GSM613722 2 0.0000 0.984 0.000 1.000
#> GSM613723 1 0.0000 0.996 1.000 0.000
#> GSM613724 1 0.0000 0.996 1.000 0.000
#> GSM613725 2 0.0000 0.984 0.000 1.000
#> GSM613726 1 0.0000 0.996 1.000 0.000
#> GSM613727 1 0.0000 0.996 1.000 0.000
#> GSM613728 2 0.0000 0.984 0.000 1.000
#> GSM613729 1 0.0000 0.996 1.000 0.000
#> GSM613730 2 0.0000 0.984 0.000 1.000
#> GSM613731 1 0.0000 0.996 1.000 0.000
#> GSM613732 2 0.0000 0.984 0.000 1.000
#> GSM613733 2 0.0000 0.984 0.000 1.000
#> GSM613734 1 0.0000 0.996 1.000 0.000
#> GSM613735 1 0.0000 0.996 1.000 0.000
#> GSM613736 2 0.0000 0.984 0.000 1.000
#> GSM613737 1 0.0000 0.996 1.000 0.000
#> GSM613738 1 0.0000 0.996 1.000 0.000
#> GSM613739 1 0.0000 0.996 1.000 0.000
#> GSM613740 2 0.0000 0.984 0.000 1.000
#> GSM613741 1 0.0376 0.992 0.996 0.004
#> GSM613742 1 0.0000 0.996 1.000 0.000
#> GSM613743 2 0.0000 0.984 0.000 1.000
#> GSM613744 2 0.0000 0.984 0.000 1.000
#> GSM613745 1 0.7674 0.707 0.776 0.224
#> GSM613746 2 0.0000 0.984 0.000 1.000
#> GSM613747 1 0.0000 0.996 1.000 0.000
#> GSM613748 2 0.0000 0.984 0.000 1.000
#> GSM613749 1 0.0000 0.996 1.000 0.000
#> GSM613750 2 0.0000 0.984 0.000 1.000
#> GSM613751 2 0.0000 0.984 0.000 1.000
#> GSM613752 2 0.0000 0.984 0.000 1.000
#> GSM613753 2 0.0000 0.984 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM613638 3 0.4291 0.769 0.180 0.000 0.820
#> GSM613639 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613640 3 0.0747 0.881 0.016 0.000 0.984
#> GSM613641 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613642 2 0.4654 0.853 0.000 0.792 0.208
#> GSM613643 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613644 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613645 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613646 1 0.7484 0.176 0.504 0.460 0.036
#> GSM613647 3 0.3482 0.810 0.128 0.000 0.872
#> GSM613648 3 0.1031 0.888 0.000 0.024 0.976
#> GSM613649 3 0.1031 0.888 0.000 0.024 0.976
#> GSM613650 1 0.0747 0.952 0.984 0.000 0.016
#> GSM613651 3 0.5810 0.549 0.336 0.000 0.664
#> GSM613652 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613653 1 0.6769 0.402 0.592 0.392 0.016
#> GSM613654 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613655 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613656 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613657 3 0.1031 0.888 0.000 0.024 0.976
#> GSM613658 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613659 2 0.0000 0.845 0.000 1.000 0.000
#> GSM613660 2 0.4399 0.869 0.000 0.812 0.188
#> GSM613661 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613662 2 0.0000 0.845 0.000 1.000 0.000
#> GSM613663 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613664 2 0.0000 0.845 0.000 1.000 0.000
#> GSM613665 2 0.4399 0.869 0.000 0.812 0.188
#> GSM613666 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613667 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613668 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613669 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613670 2 0.0000 0.845 0.000 1.000 0.000
#> GSM613671 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613672 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613673 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613674 2 0.4399 0.869 0.000 0.812 0.188
#> GSM613675 2 0.0000 0.845 0.000 1.000 0.000
#> GSM613676 2 0.4399 0.869 0.000 0.812 0.188
#> GSM613677 3 0.3340 0.790 0.000 0.120 0.880
#> GSM613678 2 0.1031 0.827 0.024 0.976 0.000
#> GSM613679 2 0.4399 0.869 0.000 0.812 0.188
#> GSM613680 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613681 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613682 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613683 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613684 2 0.4399 0.869 0.000 0.812 0.188
#> GSM613685 2 0.4399 0.869 0.000 0.812 0.188
#> GSM613686 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613687 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613688 2 0.4178 0.871 0.000 0.828 0.172
#> GSM613689 3 0.0000 0.885 0.000 0.000 1.000
#> GSM613690 3 0.0000 0.885 0.000 0.000 1.000
#> GSM613691 2 0.0000 0.845 0.000 1.000 0.000
#> GSM613692 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613693 2 0.4399 0.869 0.000 0.812 0.188
#> GSM613694 3 0.4504 0.755 0.196 0.000 0.804
#> GSM613695 3 0.0000 0.885 0.000 0.000 1.000
#> GSM613696 3 0.4842 0.753 0.000 0.224 0.776
#> GSM613697 3 0.4750 0.736 0.216 0.000 0.784
#> GSM613698 3 0.5497 0.782 0.064 0.124 0.812
#> GSM613699 3 0.0747 0.880 0.016 0.000 0.984
#> GSM613700 2 0.4399 0.869 0.000 0.812 0.188
#> GSM613701 2 0.4121 0.870 0.000 0.832 0.168
#> GSM613702 2 0.1860 0.857 0.000 0.948 0.052
#> GSM613703 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613704 2 0.0000 0.845 0.000 1.000 0.000
#> GSM613705 3 0.0000 0.885 0.000 0.000 1.000
#> GSM613706 1 0.4413 0.813 0.852 0.124 0.024
#> GSM613707 2 0.4399 0.869 0.000 0.812 0.188
#> GSM613708 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613709 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613710 2 0.4654 0.853 0.000 0.792 0.208
#> GSM613711 3 0.1031 0.888 0.000 0.024 0.976
#> GSM613712 3 0.4235 0.773 0.176 0.000 0.824
#> GSM613713 2 0.5363 0.772 0.000 0.724 0.276
#> GSM613714 3 0.0000 0.885 0.000 0.000 1.000
#> GSM613715 3 0.1031 0.888 0.000 0.024 0.976
#> GSM613716 3 0.5327 0.708 0.000 0.272 0.728
#> GSM613717 3 0.1031 0.888 0.000 0.024 0.976
#> GSM613718 3 0.1031 0.888 0.000 0.024 0.976
#> GSM613719 3 0.8694 0.545 0.268 0.152 0.580
#> GSM613720 3 0.6008 0.539 0.000 0.372 0.628
#> GSM613721 2 0.0000 0.845 0.000 1.000 0.000
#> GSM613722 2 0.4452 0.867 0.000 0.808 0.192
#> GSM613723 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613724 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613725 2 0.4399 0.869 0.000 0.812 0.188
#> GSM613726 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613727 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613728 2 0.2165 0.859 0.000 0.936 0.064
#> GSM613729 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613730 2 0.0000 0.845 0.000 1.000 0.000
#> GSM613731 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613732 3 0.1031 0.888 0.000 0.024 0.976
#> GSM613733 3 0.1411 0.879 0.000 0.036 0.964
#> GSM613734 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613735 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613736 3 0.1163 0.886 0.000 0.028 0.972
#> GSM613737 3 0.4399 0.761 0.188 0.000 0.812
#> GSM613738 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613739 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613740 3 0.1031 0.888 0.000 0.024 0.976
#> GSM613741 1 0.6783 0.393 0.588 0.396 0.016
#> GSM613742 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613743 3 0.1031 0.888 0.000 0.024 0.976
#> GSM613744 3 0.1031 0.888 0.000 0.024 0.976
#> GSM613745 2 0.7187 0.539 0.232 0.692 0.076
#> GSM613746 2 0.0000 0.845 0.000 1.000 0.000
#> GSM613747 1 0.0000 0.967 1.000 0.000 0.000
#> GSM613748 2 0.4399 0.868 0.000 0.812 0.188
#> GSM613749 2 0.6280 0.145 0.460 0.540 0.000
#> GSM613750 3 0.0892 0.887 0.000 0.020 0.980
#> GSM613751 3 0.1031 0.888 0.000 0.024 0.976
#> GSM613752 3 0.1031 0.888 0.000 0.024 0.976
#> GSM613753 3 0.0000 0.885 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 3 0.5511 0.323 0.016 0.000 0.500 0.484
#> GSM613639 1 0.0524 0.951 0.988 0.008 0.000 0.004
#> GSM613640 3 0.7851 0.365 0.144 0.024 0.480 0.352
#> GSM613641 1 0.0000 0.959 1.000 0.000 0.000 0.000
#> GSM613642 2 0.4584 0.751 0.000 0.696 0.300 0.004
#> GSM613643 1 0.3649 0.656 0.796 0.000 0.000 0.204
#> GSM613644 1 0.3791 0.658 0.796 0.004 0.000 0.200
#> GSM613645 1 0.0657 0.947 0.984 0.012 0.000 0.004
#> GSM613646 4 0.8531 0.387 0.196 0.296 0.048 0.460
#> GSM613647 4 0.2647 0.571 0.000 0.000 0.120 0.880
#> GSM613648 3 0.1557 0.823 0.000 0.000 0.944 0.056
#> GSM613649 3 0.1118 0.826 0.000 0.000 0.964 0.036
#> GSM613650 4 0.5182 0.634 0.356 0.008 0.004 0.632
#> GSM613651 4 0.3107 0.611 0.036 0.000 0.080 0.884
#> GSM613652 4 0.4624 0.658 0.340 0.000 0.000 0.660
#> GSM613653 4 0.8026 0.426 0.180 0.288 0.028 0.504
#> GSM613654 4 0.4624 0.658 0.340 0.000 0.000 0.660
#> GSM613655 1 0.0336 0.958 0.992 0.000 0.000 0.008
#> GSM613656 4 0.4624 0.658 0.340 0.000 0.000 0.660
#> GSM613657 3 0.0000 0.826 0.000 0.000 1.000 0.000
#> GSM613658 1 0.0336 0.958 0.992 0.000 0.000 0.008
#> GSM613659 2 0.2281 0.710 0.000 0.904 0.000 0.096
#> GSM613660 2 0.4428 0.775 0.000 0.720 0.276 0.004
#> GSM613661 1 0.0000 0.959 1.000 0.000 0.000 0.000
#> GSM613662 2 0.2741 0.719 0.000 0.892 0.012 0.096
#> GSM613663 1 0.0188 0.959 0.996 0.000 0.000 0.004
#> GSM613664 2 0.2101 0.733 0.000 0.928 0.012 0.060
#> GSM613665 2 0.4313 0.786 0.000 0.736 0.260 0.004
#> GSM613666 1 0.0000 0.959 1.000 0.000 0.000 0.000
#> GSM613667 1 0.0524 0.951 0.988 0.008 0.000 0.004
#> GSM613668 1 0.0336 0.958 0.992 0.000 0.000 0.008
#> GSM613669 1 0.0000 0.959 1.000 0.000 0.000 0.000
#> GSM613670 2 0.2345 0.708 0.000 0.900 0.000 0.100
#> GSM613671 1 0.0000 0.959 1.000 0.000 0.000 0.000
#> GSM613672 1 0.0469 0.956 0.988 0.000 0.000 0.012
#> GSM613673 1 0.0336 0.958 0.992 0.000 0.000 0.008
#> GSM613674 2 0.4103 0.788 0.000 0.744 0.256 0.000
#> GSM613675 2 0.2861 0.722 0.000 0.888 0.016 0.096
#> GSM613676 2 0.4428 0.775 0.000 0.720 0.276 0.004
#> GSM613677 3 0.2714 0.717 0.000 0.112 0.884 0.004
#> GSM613678 2 0.6743 0.122 0.392 0.512 0.000 0.096
#> GSM613679 2 0.4283 0.787 0.000 0.740 0.256 0.004
#> GSM613680 1 0.0336 0.958 0.992 0.000 0.000 0.008
#> GSM613681 1 0.0000 0.959 1.000 0.000 0.000 0.000
#> GSM613682 1 0.0336 0.958 0.992 0.000 0.000 0.008
#> GSM613683 1 0.0469 0.956 0.988 0.000 0.000 0.012
#> GSM613684 2 0.4103 0.788 0.000 0.744 0.256 0.000
#> GSM613685 2 0.4103 0.788 0.000 0.744 0.256 0.000
#> GSM613686 1 0.0188 0.957 0.996 0.000 0.000 0.004
#> GSM613687 1 0.0188 0.959 0.996 0.000 0.000 0.004
#> GSM613688 2 0.3975 0.790 0.000 0.760 0.240 0.000
#> GSM613689 3 0.1004 0.826 0.000 0.004 0.972 0.024
#> GSM613690 3 0.3024 0.781 0.000 0.000 0.852 0.148
#> GSM613691 2 0.3205 0.707 0.000 0.872 0.024 0.104
#> GSM613692 4 0.4624 0.658 0.340 0.000 0.000 0.660
#> GSM613693 2 0.6611 0.430 0.000 0.460 0.460 0.080
#> GSM613694 4 0.3047 0.582 0.012 0.000 0.116 0.872
#> GSM613695 3 0.3975 0.710 0.000 0.000 0.760 0.240
#> GSM613696 3 0.5833 0.596 0.000 0.212 0.692 0.096
#> GSM613697 4 0.2924 0.592 0.016 0.000 0.100 0.884
#> GSM613698 4 0.2647 0.568 0.000 0.000 0.120 0.880
#> GSM613699 3 0.4188 0.703 0.000 0.004 0.752 0.244
#> GSM613700 2 0.4313 0.786 0.000 0.736 0.260 0.004
#> GSM613701 2 0.4715 0.786 0.016 0.740 0.240 0.004
#> GSM613702 2 0.2928 0.775 0.000 0.880 0.108 0.012
#> GSM613703 1 0.0524 0.951 0.988 0.004 0.000 0.008
#> GSM613704 2 0.2861 0.722 0.000 0.888 0.016 0.096
#> GSM613705 3 0.4972 0.411 0.000 0.000 0.544 0.456
#> GSM613706 1 0.6035 0.519 0.692 0.108 0.004 0.196
#> GSM613707 2 0.4103 0.788 0.000 0.744 0.256 0.000
#> GSM613708 1 0.0336 0.958 0.992 0.000 0.000 0.008
#> GSM613709 1 0.0000 0.959 1.000 0.000 0.000 0.000
#> GSM613710 2 0.4584 0.751 0.000 0.696 0.300 0.004
#> GSM613711 3 0.0921 0.811 0.000 0.028 0.972 0.000
#> GSM613712 4 0.4252 0.362 0.004 0.000 0.252 0.744
#> GSM613713 3 0.4122 0.511 0.000 0.236 0.760 0.004
#> GSM613714 3 0.3764 0.729 0.000 0.000 0.784 0.216
#> GSM613715 3 0.1557 0.823 0.000 0.000 0.944 0.056
#> GSM613716 3 0.6269 0.528 0.000 0.272 0.632 0.096
#> GSM613717 3 0.0921 0.811 0.000 0.028 0.972 0.000
#> GSM613718 3 0.0000 0.826 0.000 0.000 1.000 0.000
#> GSM613719 4 0.4917 0.586 0.024 0.176 0.024 0.776
#> GSM613720 3 0.5798 0.584 0.000 0.208 0.696 0.096
#> GSM613721 2 0.3550 0.705 0.000 0.860 0.044 0.096
#> GSM613722 2 0.4428 0.775 0.000 0.720 0.276 0.004
#> GSM613723 4 0.4624 0.658 0.340 0.000 0.000 0.660
#> GSM613724 1 0.0336 0.958 0.992 0.000 0.000 0.008
#> GSM613725 2 0.4401 0.777 0.000 0.724 0.272 0.004
#> GSM613726 1 0.0000 0.959 1.000 0.000 0.000 0.000
#> GSM613727 1 0.0336 0.958 0.992 0.000 0.000 0.008
#> GSM613728 2 0.3161 0.778 0.000 0.864 0.124 0.012
#> GSM613729 1 0.0000 0.959 1.000 0.000 0.000 0.000
#> GSM613730 2 0.2255 0.729 0.000 0.920 0.012 0.068
#> GSM613731 1 0.0921 0.943 0.972 0.000 0.000 0.028
#> GSM613732 3 0.0000 0.826 0.000 0.000 1.000 0.000
#> GSM613733 3 0.1824 0.781 0.000 0.060 0.936 0.004
#> GSM613734 4 0.4967 0.470 0.452 0.000 0.000 0.548
#> GSM613735 4 0.4643 0.654 0.344 0.000 0.000 0.656
#> GSM613736 3 0.1118 0.808 0.000 0.036 0.964 0.000
#> GSM613737 4 0.2999 0.562 0.004 0.000 0.132 0.864
#> GSM613738 4 0.4624 0.658 0.340 0.000 0.000 0.660
#> GSM613739 4 0.4624 0.658 0.340 0.000 0.000 0.660
#> GSM613740 3 0.0000 0.826 0.000 0.000 1.000 0.000
#> GSM613741 4 0.8026 0.426 0.180 0.288 0.028 0.504
#> GSM613742 4 0.4624 0.658 0.340 0.000 0.000 0.660
#> GSM613743 3 0.0921 0.811 0.000 0.028 0.972 0.000
#> GSM613744 3 0.0000 0.826 0.000 0.000 1.000 0.000
#> GSM613745 4 0.8256 0.356 0.088 0.320 0.092 0.500
#> GSM613746 2 0.3307 0.710 0.000 0.868 0.028 0.104
#> GSM613747 4 0.4941 0.515 0.436 0.000 0.000 0.564
#> GSM613748 2 0.4442 0.779 0.004 0.752 0.236 0.008
#> GSM613749 1 0.1677 0.904 0.948 0.040 0.000 0.012
#> GSM613750 3 0.1474 0.824 0.000 0.000 0.948 0.052
#> GSM613751 3 0.0000 0.826 0.000 0.000 1.000 0.000
#> GSM613752 3 0.0000 0.826 0.000 0.000 1.000 0.000
#> GSM613753 3 0.3764 0.730 0.000 0.000 0.784 0.216
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM613638 5 0.7502 0.2388 0.000 0.144 0.260 0.100 0.496
#> GSM613639 1 0.1544 0.8950 0.932 0.000 0.000 0.068 0.000
#> GSM613640 2 0.8733 0.0477 0.028 0.340 0.264 0.104 0.264
#> GSM613641 1 0.0000 0.9384 1.000 0.000 0.000 0.000 0.000
#> GSM613642 2 0.3106 0.7493 0.000 0.844 0.132 0.024 0.000
#> GSM613643 1 0.6564 0.3428 0.588 0.056 0.000 0.104 0.252
#> GSM613644 1 0.7466 0.0308 0.464 0.068 0.004 0.140 0.324
#> GSM613645 1 0.1768 0.8880 0.924 0.004 0.000 0.072 0.000
#> GSM613646 4 0.3258 0.6382 0.028 0.016 0.016 0.876 0.064
#> GSM613647 5 0.2721 0.6592 0.000 0.036 0.016 0.052 0.896
#> GSM613648 3 0.0566 0.9182 0.000 0.004 0.984 0.000 0.012
#> GSM613649 3 0.0162 0.9217 0.000 0.004 0.996 0.000 0.000
#> GSM613650 5 0.6269 0.5385 0.188 0.000 0.000 0.284 0.528
#> GSM613651 5 0.0324 0.6936 0.004 0.004 0.000 0.000 0.992
#> GSM613652 5 0.3395 0.7577 0.236 0.000 0.000 0.000 0.764
#> GSM613653 4 0.2707 0.6263 0.024 0.000 0.000 0.876 0.100
#> GSM613654 5 0.3395 0.7577 0.236 0.000 0.000 0.000 0.764
#> GSM613655 1 0.0290 0.9386 0.992 0.000 0.000 0.000 0.008
#> GSM613656 5 0.3395 0.7577 0.236 0.000 0.000 0.000 0.764
#> GSM613657 3 0.0290 0.9229 0.000 0.008 0.992 0.000 0.000
#> GSM613658 1 0.0162 0.9387 0.996 0.000 0.000 0.000 0.004
#> GSM613659 4 0.4171 0.4677 0.000 0.396 0.000 0.604 0.000
#> GSM613660 2 0.2852 0.7410 0.000 0.828 0.172 0.000 0.000
#> GSM613661 1 0.0162 0.9371 0.996 0.000 0.000 0.004 0.000
#> GSM613662 4 0.4649 0.4578 0.000 0.404 0.016 0.580 0.000
#> GSM613663 1 0.0162 0.9387 0.996 0.000 0.000 0.000 0.004
#> GSM613664 2 0.4235 -0.1039 0.000 0.576 0.000 0.424 0.000
#> GSM613665 2 0.3656 0.7379 0.000 0.800 0.168 0.032 0.000
#> GSM613666 1 0.0000 0.9384 1.000 0.000 0.000 0.000 0.000
#> GSM613667 1 0.1768 0.8880 0.924 0.004 0.000 0.072 0.000
#> GSM613668 1 0.0290 0.9386 0.992 0.000 0.000 0.000 0.008
#> GSM613669 1 0.0000 0.9384 1.000 0.000 0.000 0.000 0.000
#> GSM613670 4 0.4101 0.4995 0.000 0.372 0.000 0.628 0.000
#> GSM613671 1 0.0162 0.9371 0.996 0.000 0.000 0.004 0.000
#> GSM613672 1 0.0290 0.9386 0.992 0.000 0.000 0.000 0.008
#> GSM613673 1 0.0290 0.9386 0.992 0.000 0.000 0.000 0.008
#> GSM613674 2 0.3849 0.7297 0.000 0.808 0.112 0.080 0.000
#> GSM613675 4 0.4674 0.4371 0.000 0.416 0.016 0.568 0.000
#> GSM613676 2 0.3929 0.7179 0.000 0.764 0.208 0.028 0.000
#> GSM613677 3 0.4914 0.5507 0.000 0.204 0.704 0.092 0.000
#> GSM613678 4 0.6545 0.3086 0.284 0.240 0.000 0.476 0.000
#> GSM613679 2 0.3389 0.7454 0.000 0.836 0.116 0.048 0.000
#> GSM613680 1 0.0290 0.9386 0.992 0.000 0.000 0.000 0.008
#> GSM613681 1 0.0000 0.9384 1.000 0.000 0.000 0.000 0.000
#> GSM613682 1 0.0290 0.9386 0.992 0.000 0.000 0.000 0.008
#> GSM613683 1 0.0290 0.9386 0.992 0.000 0.000 0.000 0.008
#> GSM613684 2 0.5086 0.6208 0.000 0.700 0.156 0.144 0.000
#> GSM613685 2 0.3849 0.7297 0.000 0.808 0.112 0.080 0.000
#> GSM613686 1 0.0794 0.9224 0.972 0.000 0.000 0.028 0.000
#> GSM613687 1 0.0290 0.9386 0.992 0.000 0.000 0.000 0.008
#> GSM613688 2 0.4541 0.6105 0.000 0.744 0.084 0.172 0.000
#> GSM613689 3 0.1800 0.8981 0.000 0.048 0.932 0.000 0.020
#> GSM613690 3 0.1357 0.8948 0.000 0.004 0.948 0.000 0.048
#> GSM613691 4 0.3550 0.6482 0.000 0.184 0.020 0.796 0.000
#> GSM613692 5 0.3395 0.7577 0.236 0.000 0.000 0.000 0.764
#> GSM613693 4 0.6499 0.2909 0.000 0.192 0.368 0.440 0.000
#> GSM613694 5 0.3024 0.6657 0.008 0.012 0.064 0.032 0.884
#> GSM613695 3 0.3319 0.7920 0.000 0.020 0.820 0.000 0.160
#> GSM613696 4 0.6010 0.4660 0.000 0.096 0.304 0.584 0.016
#> GSM613697 5 0.0451 0.6960 0.008 0.004 0.000 0.000 0.988
#> GSM613698 5 0.1471 0.6894 0.000 0.004 0.020 0.024 0.952
#> GSM613699 3 0.4196 0.7486 0.000 0.016 0.768 0.024 0.192
#> GSM613700 2 0.2377 0.7536 0.000 0.872 0.128 0.000 0.000
#> GSM613701 2 0.1026 0.7053 0.000 0.968 0.024 0.004 0.004
#> GSM613702 2 0.2351 0.6661 0.000 0.896 0.016 0.088 0.000
#> GSM613703 1 0.1410 0.9018 0.940 0.000 0.000 0.060 0.000
#> GSM613704 4 0.4640 0.4648 0.000 0.400 0.016 0.584 0.000
#> GSM613705 5 0.7634 0.0785 0.000 0.140 0.312 0.100 0.448
#> GSM613706 2 0.7704 0.2319 0.220 0.500 0.004 0.104 0.172
#> GSM613707 2 0.3906 0.7269 0.000 0.804 0.112 0.084 0.000
#> GSM613708 1 0.0290 0.9386 0.992 0.000 0.000 0.000 0.008
#> GSM613709 1 0.0000 0.9384 1.000 0.000 0.000 0.000 0.000
#> GSM613710 2 0.3476 0.7327 0.000 0.804 0.176 0.020 0.000
#> GSM613711 3 0.0290 0.9229 0.000 0.008 0.992 0.000 0.000
#> GSM613712 5 0.1717 0.6775 0.000 0.008 0.052 0.004 0.936
#> GSM613713 3 0.4485 0.4923 0.000 0.292 0.680 0.028 0.000
#> GSM613714 3 0.2660 0.8356 0.000 0.008 0.864 0.000 0.128
#> GSM613715 3 0.0671 0.9163 0.000 0.004 0.980 0.000 0.016
#> GSM613716 4 0.4413 0.5851 0.000 0.044 0.232 0.724 0.000
#> GSM613717 3 0.0290 0.9229 0.000 0.008 0.992 0.000 0.000
#> GSM613718 3 0.0162 0.9235 0.000 0.004 0.996 0.000 0.000
#> GSM613719 5 0.4533 0.2637 0.008 0.000 0.000 0.448 0.544
#> GSM613720 4 0.5084 0.5030 0.000 0.052 0.332 0.616 0.000
#> GSM613721 4 0.3305 0.6304 0.000 0.224 0.000 0.776 0.000
#> GSM613722 2 0.2424 0.7533 0.000 0.868 0.132 0.000 0.000
#> GSM613723 5 0.3395 0.7577 0.236 0.000 0.000 0.000 0.764
#> GSM613724 1 0.0290 0.9386 0.992 0.000 0.000 0.000 0.008
#> GSM613725 2 0.2377 0.7536 0.000 0.872 0.128 0.000 0.000
#> GSM613726 1 0.0693 0.9331 0.980 0.012 0.000 0.000 0.008
#> GSM613727 1 0.0290 0.9386 0.992 0.000 0.000 0.000 0.008
#> GSM613728 2 0.4152 0.6165 0.000 0.772 0.060 0.168 0.000
#> GSM613729 1 0.0290 0.9358 0.992 0.000 0.000 0.008 0.000
#> GSM613730 2 0.4171 0.3051 0.000 0.604 0.000 0.396 0.000
#> GSM613731 1 0.4519 0.7408 0.792 0.056 0.000 0.104 0.048
#> GSM613732 3 0.0162 0.9235 0.000 0.004 0.996 0.000 0.000
#> GSM613733 3 0.1341 0.8901 0.000 0.056 0.944 0.000 0.000
#> GSM613734 5 0.4088 0.5834 0.368 0.000 0.000 0.000 0.632
#> GSM613735 5 0.3424 0.7540 0.240 0.000 0.000 0.000 0.760
#> GSM613736 3 0.0963 0.9091 0.000 0.036 0.964 0.000 0.000
#> GSM613737 5 0.1990 0.6701 0.000 0.004 0.068 0.008 0.920
#> GSM613738 5 0.3395 0.7577 0.236 0.000 0.000 0.000 0.764
#> GSM613739 5 0.3395 0.7577 0.236 0.000 0.000 0.000 0.764
#> GSM613740 3 0.0290 0.9229 0.000 0.008 0.992 0.000 0.000
#> GSM613741 4 0.2653 0.6288 0.024 0.000 0.000 0.880 0.096
#> GSM613742 5 0.3395 0.7577 0.236 0.000 0.000 0.000 0.764
#> GSM613743 3 0.0290 0.9229 0.000 0.008 0.992 0.000 0.000
#> GSM613744 3 0.0162 0.9235 0.000 0.004 0.996 0.000 0.000
#> GSM613745 4 0.3145 0.6383 0.008 0.016 0.024 0.876 0.076
#> GSM613746 4 0.3596 0.6433 0.000 0.200 0.016 0.784 0.000
#> GSM613747 5 0.4219 0.4896 0.416 0.000 0.000 0.000 0.584
#> GSM613748 2 0.4622 0.5947 0.000 0.764 0.088 0.136 0.012
#> GSM613749 1 0.2370 0.8725 0.904 0.040 0.000 0.056 0.000
#> GSM613750 3 0.0566 0.9209 0.000 0.004 0.984 0.000 0.012
#> GSM613751 3 0.0162 0.9235 0.000 0.004 0.996 0.000 0.000
#> GSM613752 3 0.0162 0.9235 0.000 0.004 0.996 0.000 0.000
#> GSM613753 3 0.2124 0.8588 0.000 0.004 0.900 0.000 0.096
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM613638 4 0.3526 0.688 0.000 0.004 0.028 0.792 0.172 0.004
#> GSM613639 1 0.2679 0.852 0.876 0.004 0.000 0.024 0.008 0.088
#> GSM613640 4 0.3034 0.687 0.000 0.032 0.048 0.864 0.056 0.000
#> GSM613641 1 0.0000 0.948 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613642 2 0.4569 0.604 0.000 0.700 0.096 0.200 0.000 0.004
#> GSM613643 4 0.5202 0.566 0.196 0.000 0.000 0.616 0.188 0.000
#> GSM613644 4 0.5172 0.583 0.148 0.000 0.000 0.644 0.200 0.008
#> GSM613645 1 0.2594 0.860 0.880 0.004 0.000 0.028 0.004 0.084
#> GSM613646 6 0.2136 0.566 0.012 0.000 0.000 0.064 0.016 0.908
#> GSM613647 5 0.4425 0.219 0.000 0.004 0.020 0.364 0.608 0.004
#> GSM613648 3 0.0767 0.900 0.000 0.004 0.976 0.012 0.008 0.000
#> GSM613649 3 0.0520 0.905 0.000 0.008 0.984 0.008 0.000 0.000
#> GSM613650 6 0.6194 0.221 0.092 0.004 0.000 0.068 0.284 0.552
#> GSM613651 5 0.1299 0.749 0.000 0.004 0.004 0.036 0.952 0.004
#> GSM613652 5 0.2219 0.839 0.136 0.000 0.000 0.000 0.864 0.000
#> GSM613653 6 0.2849 0.556 0.028 0.004 0.000 0.068 0.024 0.876
#> GSM613654 5 0.2219 0.839 0.136 0.000 0.000 0.000 0.864 0.000
#> GSM613655 1 0.1082 0.944 0.956 0.000 0.000 0.004 0.040 0.000
#> GSM613656 5 0.2219 0.839 0.136 0.000 0.000 0.000 0.864 0.000
#> GSM613657 3 0.0692 0.907 0.000 0.020 0.976 0.004 0.000 0.000
#> GSM613658 1 0.0713 0.948 0.972 0.000 0.000 0.000 0.028 0.000
#> GSM613659 2 0.4768 0.163 0.000 0.532 0.000 0.052 0.000 0.416
#> GSM613660 2 0.4782 0.615 0.000 0.700 0.120 0.168 0.000 0.012
#> GSM613661 1 0.0291 0.945 0.992 0.004 0.000 0.004 0.000 0.000
#> GSM613662 2 0.4723 0.190 0.000 0.548 0.004 0.040 0.000 0.408
#> GSM613663 1 0.0508 0.949 0.984 0.000 0.000 0.004 0.012 0.000
#> GSM613664 2 0.3420 0.461 0.000 0.748 0.000 0.012 0.000 0.240
#> GSM613665 2 0.2462 0.677 0.000 0.876 0.096 0.028 0.000 0.000
#> GSM613666 1 0.0260 0.949 0.992 0.000 0.000 0.000 0.008 0.000
#> GSM613667 1 0.2432 0.871 0.892 0.004 0.000 0.028 0.004 0.072
#> GSM613668 1 0.1082 0.944 0.956 0.000 0.000 0.004 0.040 0.000
#> GSM613669 1 0.0000 0.948 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613670 2 0.4726 0.154 0.000 0.528 0.000 0.048 0.000 0.424
#> GSM613671 1 0.0146 0.947 0.996 0.000 0.000 0.004 0.000 0.000
#> GSM613672 1 0.1152 0.942 0.952 0.000 0.000 0.004 0.044 0.000
#> GSM613673 1 0.1082 0.944 0.956 0.000 0.000 0.004 0.040 0.000
#> GSM613674 2 0.1674 0.676 0.000 0.924 0.068 0.004 0.000 0.004
#> GSM613675 2 0.4716 0.197 0.000 0.552 0.004 0.040 0.000 0.404
#> GSM613676 2 0.2709 0.663 0.000 0.848 0.132 0.020 0.000 0.000
#> GSM613677 3 0.4986 0.193 0.000 0.036 0.540 0.408 0.004 0.012
#> GSM613678 6 0.7030 0.124 0.316 0.308 0.000 0.060 0.000 0.316
#> GSM613679 2 0.2006 0.678 0.000 0.904 0.080 0.016 0.000 0.000
#> GSM613680 1 0.1082 0.944 0.956 0.000 0.000 0.004 0.040 0.000
#> GSM613681 1 0.0000 0.948 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613682 1 0.1082 0.944 0.956 0.000 0.000 0.004 0.040 0.000
#> GSM613683 1 0.1219 0.939 0.948 0.000 0.000 0.004 0.048 0.000
#> GSM613684 2 0.3214 0.637 0.000 0.840 0.084 0.008 0.000 0.068
#> GSM613685 2 0.1674 0.676 0.000 0.924 0.068 0.004 0.000 0.004
#> GSM613686 1 0.1723 0.904 0.932 0.004 0.000 0.012 0.004 0.048
#> GSM613687 1 0.0777 0.948 0.972 0.000 0.000 0.004 0.024 0.000
#> GSM613688 2 0.2547 0.630 0.000 0.880 0.036 0.004 0.000 0.080
#> GSM613689 3 0.2081 0.888 0.000 0.036 0.916 0.036 0.012 0.000
#> GSM613690 3 0.1313 0.881 0.000 0.004 0.952 0.016 0.028 0.000
#> GSM613691 6 0.4350 0.404 0.000 0.280 0.008 0.036 0.000 0.676
#> GSM613692 5 0.2219 0.839 0.136 0.000 0.000 0.000 0.864 0.000
#> GSM613693 2 0.6297 0.016 0.000 0.428 0.264 0.012 0.000 0.296
#> GSM613694 5 0.5064 0.563 0.004 0.012 0.036 0.068 0.720 0.160
#> GSM613695 3 0.2968 0.818 0.000 0.008 0.864 0.064 0.060 0.004
#> GSM613696 6 0.6544 0.394 0.000 0.200 0.268 0.008 0.032 0.492
#> GSM613697 5 0.1371 0.749 0.000 0.004 0.004 0.040 0.948 0.004
#> GSM613698 5 0.2298 0.745 0.000 0.008 0.024 0.032 0.912 0.024
#> GSM613699 3 0.5493 0.608 0.000 0.012 0.688 0.056 0.132 0.112
#> GSM613700 2 0.4498 0.622 0.000 0.720 0.080 0.188 0.000 0.012
#> GSM613701 2 0.3767 0.539 0.000 0.708 0.004 0.276 0.000 0.012
#> GSM613702 2 0.4392 0.478 0.000 0.628 0.000 0.332 0.000 0.040
#> GSM613703 1 0.2200 0.877 0.900 0.004 0.000 0.012 0.004 0.080
#> GSM613704 2 0.4723 0.190 0.000 0.548 0.004 0.040 0.000 0.408
#> GSM613705 4 0.3868 0.679 0.000 0.004 0.060 0.780 0.152 0.004
#> GSM613706 4 0.3658 0.683 0.012 0.088 0.000 0.824 0.064 0.012
#> GSM613707 2 0.1643 0.674 0.000 0.924 0.068 0.000 0.000 0.008
#> GSM613708 1 0.0458 0.949 0.984 0.000 0.000 0.000 0.016 0.000
#> GSM613709 1 0.0000 0.948 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613710 2 0.4901 0.604 0.000 0.688 0.136 0.164 0.000 0.012
#> GSM613711 3 0.0632 0.905 0.000 0.024 0.976 0.000 0.000 0.000
#> GSM613712 5 0.2290 0.726 0.000 0.004 0.044 0.044 0.904 0.004
#> GSM613713 3 0.4098 0.187 0.000 0.444 0.548 0.004 0.000 0.004
#> GSM613714 3 0.2145 0.867 0.000 0.008 0.912 0.056 0.020 0.004
#> GSM613715 3 0.0717 0.897 0.000 0.000 0.976 0.016 0.008 0.000
#> GSM613716 6 0.5755 0.443 0.000 0.108 0.292 0.032 0.000 0.568
#> GSM613717 3 0.0632 0.905 0.000 0.024 0.976 0.000 0.000 0.000
#> GSM613718 3 0.0692 0.907 0.000 0.020 0.976 0.004 0.000 0.000
#> GSM613719 6 0.5457 0.295 0.020 0.008 0.004 0.068 0.284 0.616
#> GSM613720 6 0.6212 0.361 0.000 0.164 0.324 0.028 0.000 0.484
#> GSM613721 6 0.3707 0.412 0.000 0.312 0.000 0.008 0.000 0.680
#> GSM613722 2 0.4516 0.623 0.000 0.724 0.092 0.172 0.000 0.012
#> GSM613723 5 0.2219 0.839 0.136 0.000 0.000 0.000 0.864 0.000
#> GSM613724 1 0.1285 0.937 0.944 0.000 0.000 0.004 0.052 0.000
#> GSM613725 2 0.4454 0.624 0.000 0.728 0.084 0.176 0.000 0.012
#> GSM613726 1 0.1485 0.936 0.944 0.000 0.000 0.028 0.024 0.004
#> GSM613727 1 0.1082 0.944 0.956 0.000 0.000 0.004 0.040 0.000
#> GSM613728 2 0.3700 0.604 0.000 0.800 0.008 0.076 0.000 0.116
#> GSM613729 1 0.0520 0.943 0.984 0.000 0.000 0.008 0.000 0.008
#> GSM613730 4 0.5627 0.307 0.000 0.156 0.004 0.568 0.004 0.268
#> GSM613731 4 0.4766 0.520 0.316 0.000 0.000 0.612 0.072 0.000
#> GSM613732 3 0.0692 0.907 0.000 0.020 0.976 0.004 0.000 0.000
#> GSM613733 3 0.1970 0.850 0.000 0.092 0.900 0.008 0.000 0.000
#> GSM613734 5 0.3189 0.723 0.236 0.000 0.000 0.004 0.760 0.000
#> GSM613735 5 0.2219 0.839 0.136 0.000 0.000 0.000 0.864 0.000
#> GSM613736 3 0.1152 0.895 0.000 0.044 0.952 0.004 0.000 0.000
#> GSM613737 5 0.2732 0.718 0.000 0.008 0.032 0.048 0.888 0.024
#> GSM613738 5 0.2219 0.839 0.136 0.000 0.000 0.000 0.864 0.000
#> GSM613739 5 0.2178 0.838 0.132 0.000 0.000 0.000 0.868 0.000
#> GSM613740 3 0.0547 0.906 0.000 0.020 0.980 0.000 0.000 0.000
#> GSM613741 6 0.2463 0.563 0.020 0.000 0.000 0.068 0.020 0.892
#> GSM613742 5 0.2219 0.839 0.136 0.000 0.000 0.000 0.864 0.000
#> GSM613743 3 0.0858 0.904 0.000 0.028 0.968 0.004 0.000 0.000
#> GSM613744 3 0.0603 0.907 0.000 0.016 0.980 0.004 0.000 0.000
#> GSM613745 6 0.2325 0.568 0.008 0.004 0.000 0.068 0.020 0.900
#> GSM613746 6 0.4467 0.263 0.000 0.376 0.004 0.028 0.000 0.592
#> GSM613747 5 0.3508 0.644 0.292 0.000 0.000 0.004 0.704 0.000
#> GSM613748 4 0.3172 0.607 0.000 0.152 0.012 0.820 0.000 0.016
#> GSM613749 1 0.2908 0.863 0.872 0.016 0.000 0.064 0.004 0.044
#> GSM613750 3 0.0767 0.905 0.000 0.008 0.976 0.012 0.004 0.000
#> GSM613751 3 0.0717 0.906 0.000 0.016 0.976 0.008 0.000 0.000
#> GSM613752 3 0.0717 0.906 0.000 0.016 0.976 0.008 0.000 0.000
#> GSM613753 3 0.1977 0.861 0.000 0.008 0.920 0.032 0.040 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) k
#> SD:skmeans 114 0.02080 2
#> SD:skmeans 112 0.10850 3
#> SD:skmeans 105 0.04110 4
#> SD:skmeans 97 0.08634 5
#> SD:skmeans 95 0.00715 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 27425 rows and 116 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 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 0.615 0.873 0.935 0.4950 0.503 0.503
#> 3 3 0.496 0.413 0.602 0.3226 0.777 0.586
#> 4 4 0.639 0.607 0.788 0.1343 0.746 0.403
#> 5 5 0.621 0.586 0.767 0.0308 0.917 0.703
#> 6 6 0.712 0.513 0.770 0.0551 0.837 0.466
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
#> GSM613638 1 0.6438 0.8180 0.836 0.164
#> GSM613639 1 0.0000 0.9304 1.000 0.000
#> GSM613640 1 0.3879 0.8919 0.924 0.076
#> GSM613641 1 0.0000 0.9304 1.000 0.000
#> GSM613642 2 0.6801 0.7947 0.180 0.820
#> GSM613643 1 0.0000 0.9304 1.000 0.000
#> GSM613644 1 0.0000 0.9304 1.000 0.000
#> GSM613645 1 0.0000 0.9304 1.000 0.000
#> GSM613646 1 0.2948 0.9046 0.948 0.052
#> GSM613647 1 0.8144 0.7089 0.748 0.252
#> GSM613648 2 0.1414 0.9200 0.020 0.980
#> GSM613649 2 0.0000 0.9245 0.000 1.000
#> GSM613650 1 0.4298 0.8812 0.912 0.088
#> GSM613651 1 0.6623 0.8103 0.828 0.172
#> GSM613652 1 0.0000 0.9304 1.000 0.000
#> GSM613653 1 0.8608 0.6566 0.716 0.284
#> GSM613654 1 0.0000 0.9304 1.000 0.000
#> GSM613655 1 0.0000 0.9304 1.000 0.000
#> GSM613656 1 0.0000 0.9304 1.000 0.000
#> GSM613657 2 0.0000 0.9245 0.000 1.000
#> GSM613658 1 0.0000 0.9304 1.000 0.000
#> GSM613659 1 0.5629 0.8511 0.868 0.132
#> GSM613660 2 0.3431 0.8980 0.064 0.936
#> GSM613661 1 0.0000 0.9304 1.000 0.000
#> GSM613662 2 0.7139 0.7958 0.196 0.804
#> GSM613663 1 0.0000 0.9304 1.000 0.000
#> GSM613664 1 0.9988 0.0141 0.520 0.480
#> GSM613665 2 0.0000 0.9245 0.000 1.000
#> GSM613666 1 0.0000 0.9304 1.000 0.000
#> GSM613667 1 0.0000 0.9304 1.000 0.000
#> GSM613668 1 0.0000 0.9304 1.000 0.000
#> GSM613669 1 0.0000 0.9304 1.000 0.000
#> GSM613670 1 0.8861 0.6004 0.696 0.304
#> GSM613671 1 0.0000 0.9304 1.000 0.000
#> GSM613672 1 0.0000 0.9304 1.000 0.000
#> GSM613673 1 0.0000 0.9304 1.000 0.000
#> GSM613674 2 0.4562 0.8777 0.096 0.904
#> GSM613675 2 0.1633 0.9198 0.024 0.976
#> GSM613676 2 0.0000 0.9245 0.000 1.000
#> GSM613677 2 0.5737 0.8436 0.136 0.864
#> GSM613678 1 0.0376 0.9286 0.996 0.004
#> GSM613679 2 0.6531 0.8142 0.168 0.832
#> GSM613680 1 0.0000 0.9304 1.000 0.000
#> GSM613681 1 0.0000 0.9304 1.000 0.000
#> GSM613682 1 0.0000 0.9304 1.000 0.000
#> GSM613683 1 0.0000 0.9304 1.000 0.000
#> GSM613684 2 0.0376 0.9238 0.004 0.996
#> GSM613685 2 0.6343 0.8218 0.160 0.840
#> GSM613686 1 0.0000 0.9304 1.000 0.000
#> GSM613687 1 0.0000 0.9304 1.000 0.000
#> GSM613688 2 0.8327 0.6924 0.264 0.736
#> GSM613689 2 0.3584 0.8991 0.068 0.932
#> GSM613690 2 0.4022 0.8919 0.080 0.920
#> GSM613691 2 0.0000 0.9245 0.000 1.000
#> GSM613692 1 0.6438 0.8180 0.836 0.164
#> GSM613693 2 0.0000 0.9245 0.000 1.000
#> GSM613694 1 0.1414 0.9204 0.980 0.020
#> GSM613695 2 0.3879 0.8947 0.076 0.924
#> GSM613696 2 0.4815 0.8736 0.104 0.896
#> GSM613697 1 0.6623 0.8103 0.828 0.172
#> GSM613698 2 0.8016 0.7037 0.244 0.756
#> GSM613699 2 0.8081 0.6959 0.248 0.752
#> GSM613700 2 0.6801 0.8046 0.180 0.820
#> GSM613701 1 0.0938 0.9249 0.988 0.012
#> GSM613702 1 0.7056 0.7426 0.808 0.192
#> GSM613703 1 0.0000 0.9304 1.000 0.000
#> GSM613704 2 0.0938 0.9222 0.012 0.988
#> GSM613705 1 0.5737 0.8420 0.864 0.136
#> GSM613706 1 0.0000 0.9304 1.000 0.000
#> GSM613707 2 0.4022 0.8876 0.080 0.920
#> GSM613708 1 0.0000 0.9304 1.000 0.000
#> GSM613709 1 0.0000 0.9304 1.000 0.000
#> GSM613710 2 0.0000 0.9245 0.000 1.000
#> GSM613711 2 0.0000 0.9245 0.000 1.000
#> GSM613712 1 0.9833 0.3244 0.576 0.424
#> GSM613713 2 0.0000 0.9245 0.000 1.000
#> GSM613714 2 0.2778 0.9098 0.048 0.952
#> GSM613715 2 0.1184 0.9212 0.016 0.984
#> GSM613716 2 0.0000 0.9245 0.000 1.000
#> GSM613717 2 0.0000 0.9245 0.000 1.000
#> GSM613718 2 0.0000 0.9245 0.000 1.000
#> GSM613719 1 0.6801 0.8017 0.820 0.180
#> GSM613720 2 0.0000 0.9245 0.000 1.000
#> GSM613721 2 0.5294 0.8591 0.120 0.880
#> GSM613722 2 0.8267 0.7219 0.260 0.740
#> GSM613723 1 0.0000 0.9304 1.000 0.000
#> GSM613724 1 0.0000 0.9304 1.000 0.000
#> GSM613725 2 0.6531 0.8140 0.168 0.832
#> GSM613726 1 0.0000 0.9304 1.000 0.000
#> GSM613727 1 0.0000 0.9304 1.000 0.000
#> GSM613728 2 0.4298 0.8853 0.088 0.912
#> GSM613729 1 0.0000 0.9304 1.000 0.000
#> GSM613730 1 0.5178 0.8445 0.884 0.116
#> GSM613731 1 0.0000 0.9304 1.000 0.000
#> GSM613732 2 0.0000 0.9245 0.000 1.000
#> GSM613733 2 0.0000 0.9245 0.000 1.000
#> GSM613734 1 0.0000 0.9304 1.000 0.000
#> GSM613735 1 0.0000 0.9304 1.000 0.000
#> GSM613736 2 0.0000 0.9245 0.000 1.000
#> GSM613737 2 0.8661 0.6151 0.288 0.712
#> GSM613738 1 0.4298 0.8811 0.912 0.088
#> GSM613739 1 0.6438 0.8180 0.836 0.164
#> GSM613740 2 0.0000 0.9245 0.000 1.000
#> GSM613741 1 0.4431 0.8791 0.908 0.092
#> GSM613742 1 0.5629 0.8481 0.868 0.132
#> GSM613743 2 0.0000 0.9245 0.000 1.000
#> GSM613744 2 0.0000 0.9245 0.000 1.000
#> GSM613745 1 0.4161 0.8832 0.916 0.084
#> GSM613746 2 0.0000 0.9245 0.000 1.000
#> GSM613747 1 0.0000 0.9304 1.000 0.000
#> GSM613748 1 0.4431 0.8674 0.908 0.092
#> GSM613749 1 0.0000 0.9304 1.000 0.000
#> GSM613750 2 0.0000 0.9245 0.000 1.000
#> GSM613751 2 0.0000 0.9245 0.000 1.000
#> GSM613752 2 0.0000 0.9245 0.000 1.000
#> GSM613753 2 0.3274 0.9037 0.060 0.940
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM613638 1 0.9380 0.3511 0.512 0.256 0.232
#> GSM613639 1 0.5988 0.0791 0.632 0.368 0.000
#> GSM613640 1 0.9604 0.3432 0.476 0.256 0.268
#> GSM613641 2 0.5882 0.6735 0.348 0.652 0.000
#> GSM613642 1 0.9926 -0.3699 0.376 0.348 0.276
#> GSM613643 1 0.5138 0.3143 0.748 0.252 0.000
#> GSM613644 1 0.5803 0.3339 0.736 0.248 0.016
#> GSM613645 1 0.5621 0.2385 0.692 0.308 0.000
#> GSM613646 1 0.5529 0.3490 0.704 0.296 0.000
#> GSM613647 1 0.5882 0.1937 0.652 0.000 0.348
#> GSM613648 3 0.3412 0.6475 0.124 0.000 0.876
#> GSM613649 3 0.0000 0.7046 0.000 0.000 1.000
#> GSM613650 1 0.5650 0.2321 0.688 0.312 0.000
#> GSM613651 1 0.6275 0.1991 0.644 0.008 0.348
#> GSM613652 1 0.6180 -0.2216 0.584 0.416 0.000
#> GSM613653 3 0.9664 -0.1749 0.296 0.244 0.460
#> GSM613654 1 0.6180 -0.2216 0.584 0.416 0.000
#> GSM613655 2 0.5882 0.6735 0.348 0.652 0.000
#> GSM613656 1 0.6180 -0.2216 0.584 0.416 0.000
#> GSM613657 3 0.0000 0.7046 0.000 0.000 1.000
#> GSM613658 2 0.5882 0.6735 0.348 0.652 0.000
#> GSM613659 2 0.6180 -0.2336 0.416 0.584 0.000
#> GSM613660 3 0.7867 0.6861 0.068 0.348 0.584
#> GSM613661 2 0.5882 0.6735 0.348 0.652 0.000
#> GSM613662 3 0.6192 0.6551 0.000 0.420 0.580
#> GSM613663 2 0.6111 0.5753 0.396 0.604 0.000
#> GSM613664 2 0.6565 -0.4596 0.008 0.576 0.416
#> GSM613665 3 0.5882 0.7047 0.000 0.348 0.652
#> GSM613666 2 0.5882 0.6735 0.348 0.652 0.000
#> GSM613667 1 0.5785 0.1930 0.668 0.332 0.000
#> GSM613668 2 0.5882 0.6735 0.348 0.652 0.000
#> GSM613669 2 0.5882 0.6735 0.348 0.652 0.000
#> GSM613670 2 0.8760 -0.1495 0.240 0.584 0.176
#> GSM613671 2 0.5882 0.6735 0.348 0.652 0.000
#> GSM613672 2 0.5905 0.6670 0.352 0.648 0.000
#> GSM613673 1 0.5948 0.1262 0.640 0.360 0.000
#> GSM613674 3 0.5882 0.7047 0.000 0.348 0.652
#> GSM613675 3 0.7992 0.6886 0.080 0.328 0.592
#> GSM613676 3 0.5882 0.7047 0.000 0.348 0.652
#> GSM613677 3 0.3686 0.6309 0.140 0.000 0.860
#> GSM613678 1 0.5529 0.3490 0.704 0.296 0.000
#> GSM613679 3 0.5882 0.7047 0.000 0.348 0.652
#> GSM613680 2 0.5882 0.6735 0.348 0.652 0.000
#> GSM613681 2 0.5882 0.6735 0.348 0.652 0.000
#> GSM613682 1 0.5926 0.1536 0.644 0.356 0.000
#> GSM613683 2 0.5882 0.6735 0.348 0.652 0.000
#> GSM613684 3 0.5882 0.7047 0.000 0.348 0.652
#> GSM613685 3 0.5882 0.7047 0.000 0.348 0.652
#> GSM613686 1 0.6008 0.1798 0.628 0.372 0.000
#> GSM613687 2 0.5905 0.6668 0.352 0.648 0.000
#> GSM613688 2 0.8984 -0.4901 0.136 0.496 0.368
#> GSM613689 3 0.5977 0.4789 0.252 0.020 0.728
#> GSM613690 3 0.5016 0.4943 0.240 0.000 0.760
#> GSM613691 3 0.6506 0.7170 0.044 0.236 0.720
#> GSM613692 1 0.9336 -0.0318 0.420 0.416 0.164
#> GSM613693 3 0.5760 0.7078 0.000 0.328 0.672
#> GSM613694 1 0.5465 0.3490 0.712 0.288 0.000
#> GSM613695 3 0.6280 0.1419 0.460 0.000 0.540
#> GSM613696 3 0.9806 0.5385 0.244 0.348 0.408
#> GSM613697 1 0.5882 0.1937 0.652 0.000 0.348
#> GSM613698 1 0.5882 0.1937 0.652 0.000 0.348
#> GSM613699 3 0.9914 0.3862 0.348 0.272 0.380
#> GSM613700 3 0.8091 0.6803 0.080 0.348 0.572
#> GSM613701 2 0.6192 -0.2355 0.420 0.580 0.000
#> GSM613702 1 0.6224 0.3397 0.688 0.296 0.016
#> GSM613703 2 0.5882 0.6735 0.348 0.652 0.000
#> GSM613704 3 0.5882 0.7047 0.000 0.348 0.652
#> GSM613705 3 0.8976 -0.1285 0.416 0.128 0.456
#> GSM613706 1 0.5529 0.3490 0.704 0.296 0.000
#> GSM613707 3 0.5882 0.7047 0.000 0.348 0.652
#> GSM613708 2 0.5882 0.6735 0.348 0.652 0.000
#> GSM613709 2 0.5882 0.6735 0.348 0.652 0.000
#> GSM613710 3 0.7787 0.6876 0.064 0.348 0.588
#> GSM613711 3 0.0000 0.7046 0.000 0.000 1.000
#> GSM613712 1 0.5882 0.1937 0.652 0.000 0.348
#> GSM613713 3 0.5882 0.7047 0.000 0.348 0.652
#> GSM613714 3 0.5678 0.4070 0.316 0.000 0.684
#> GSM613715 3 0.2625 0.6716 0.084 0.000 0.916
#> GSM613716 3 0.1529 0.6904 0.040 0.000 0.960
#> GSM613717 3 0.0000 0.7046 0.000 0.000 1.000
#> GSM613718 3 0.0000 0.7046 0.000 0.000 1.000
#> GSM613719 1 0.6566 0.2036 0.636 0.016 0.348
#> GSM613720 3 0.0000 0.7046 0.000 0.000 1.000
#> GSM613721 3 0.9723 0.5514 0.228 0.348 0.424
#> GSM613722 3 0.9379 0.6070 0.180 0.348 0.472
#> GSM613723 1 0.6180 -0.2216 0.584 0.416 0.000
#> GSM613724 2 0.5882 0.6735 0.348 0.652 0.000
#> GSM613725 3 0.5882 0.7047 0.000 0.348 0.652
#> GSM613726 1 0.5397 0.3203 0.720 0.280 0.000
#> GSM613727 2 0.5882 0.6735 0.348 0.652 0.000
#> GSM613728 3 0.8091 0.6803 0.080 0.348 0.572
#> GSM613729 2 0.5882 0.6735 0.348 0.652 0.000
#> GSM613730 1 0.6432 0.2841 0.568 0.428 0.004
#> GSM613731 1 0.5138 0.3143 0.748 0.252 0.000
#> GSM613732 3 0.0747 0.7010 0.016 0.000 0.984
#> GSM613733 3 0.0000 0.7046 0.000 0.000 1.000
#> GSM613734 1 0.6180 -0.2216 0.584 0.416 0.000
#> GSM613735 1 0.6180 -0.2216 0.584 0.416 0.000
#> GSM613736 3 0.7230 0.7041 0.040 0.344 0.616
#> GSM613737 1 0.5882 0.1937 0.652 0.000 0.348
#> GSM613738 1 0.6398 -0.2169 0.580 0.416 0.004
#> GSM613739 1 0.8657 0.1756 0.592 0.244 0.164
#> GSM613740 3 0.0747 0.7010 0.016 0.000 0.984
#> GSM613741 1 0.8295 0.2974 0.548 0.364 0.088
#> GSM613742 1 0.5042 0.2678 0.836 0.104 0.060
#> GSM613743 3 0.0747 0.7010 0.016 0.000 0.984
#> GSM613744 3 0.0747 0.7010 0.016 0.000 0.984
#> GSM613745 1 0.6016 0.3489 0.724 0.256 0.020
#> GSM613746 3 0.5760 0.7078 0.000 0.328 0.672
#> GSM613747 1 0.6180 -0.2216 0.584 0.416 0.000
#> GSM613748 1 0.6596 0.3596 0.704 0.256 0.040
#> GSM613749 1 0.5254 0.3357 0.736 0.264 0.000
#> GSM613750 3 0.1289 0.6945 0.032 0.000 0.968
#> GSM613751 3 0.0000 0.7046 0.000 0.000 1.000
#> GSM613752 3 0.0747 0.7010 0.016 0.000 0.984
#> GSM613753 3 0.6291 0.1403 0.468 0.000 0.532
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 4 0.6347 0.2021 0.068 0.000 0.384 0.548
#> GSM613639 1 0.4222 0.0900 0.728 0.000 0.000 0.272
#> GSM613640 4 0.6985 0.3857 0.140 0.000 0.312 0.548
#> GSM613641 1 0.0000 0.6702 1.000 0.000 0.000 0.000
#> GSM613642 2 0.4446 0.7467 0.000 0.776 0.028 0.196
#> GSM613643 4 0.4967 0.5811 0.452 0.000 0.000 0.548
#> GSM613644 4 0.4967 0.5811 0.452 0.000 0.000 0.548
#> GSM613645 4 0.4985 0.5668 0.468 0.000 0.000 0.532
#> GSM613646 1 0.7351 -0.5299 0.452 0.072 0.032 0.444
#> GSM613647 4 0.2760 0.4157 0.000 0.000 0.128 0.872
#> GSM613648 3 0.1929 0.8507 0.000 0.036 0.940 0.024
#> GSM613649 3 0.1637 0.8534 0.000 0.060 0.940 0.000
#> GSM613650 1 0.5292 -0.5282 0.512 0.000 0.008 0.480
#> GSM613651 4 0.3539 0.2710 0.004 0.000 0.176 0.820
#> GSM613652 1 0.4967 0.4377 0.548 0.000 0.000 0.452
#> GSM613653 3 0.6573 0.6192 0.048 0.080 0.692 0.180
#> GSM613654 1 0.4967 0.4377 0.548 0.000 0.000 0.452
#> GSM613655 1 0.1389 0.6462 0.952 0.000 0.000 0.048
#> GSM613656 1 0.4967 0.4377 0.548 0.000 0.000 0.452
#> GSM613657 3 0.1022 0.8692 0.000 0.032 0.968 0.000
#> GSM613658 1 0.0592 0.6637 0.984 0.000 0.000 0.016
#> GSM613659 2 0.4199 0.7696 0.000 0.804 0.032 0.164
#> GSM613660 2 0.2943 0.8619 0.000 0.892 0.076 0.032
#> GSM613661 1 0.0000 0.6702 1.000 0.000 0.000 0.000
#> GSM613662 2 0.1022 0.8548 0.000 0.968 0.032 0.000
#> GSM613663 1 0.2408 0.5218 0.896 0.000 0.000 0.104
#> GSM613664 2 0.0000 0.8629 0.000 1.000 0.000 0.000
#> GSM613665 2 0.3837 0.7604 0.000 0.776 0.224 0.000
#> GSM613666 1 0.0000 0.6702 1.000 0.000 0.000 0.000
#> GSM613667 4 0.4998 0.5418 0.488 0.000 0.000 0.512
#> GSM613668 1 0.0000 0.6702 1.000 0.000 0.000 0.000
#> GSM613669 1 0.0000 0.6702 1.000 0.000 0.000 0.000
#> GSM613670 2 0.1022 0.8548 0.000 0.968 0.032 0.000
#> GSM613671 1 0.0000 0.6702 1.000 0.000 0.000 0.000
#> GSM613672 1 0.0188 0.6665 0.996 0.000 0.000 0.004
#> GSM613673 1 0.4992 -0.5118 0.524 0.000 0.000 0.476
#> GSM613674 2 0.1867 0.8660 0.000 0.928 0.072 0.000
#> GSM613675 2 0.1022 0.8548 0.000 0.968 0.032 0.000
#> GSM613676 2 0.3942 0.7533 0.000 0.764 0.236 0.000
#> GSM613677 3 0.3245 0.8476 0.000 0.100 0.872 0.028
#> GSM613678 4 0.6709 0.5147 0.452 0.088 0.000 0.460
#> GSM613679 2 0.1867 0.8660 0.000 0.928 0.072 0.000
#> GSM613680 1 0.0188 0.6667 0.996 0.000 0.000 0.004
#> GSM613681 1 0.0000 0.6702 1.000 0.000 0.000 0.000
#> GSM613682 4 0.4998 0.5418 0.488 0.000 0.000 0.512
#> GSM613683 1 0.0000 0.6702 1.000 0.000 0.000 0.000
#> GSM613684 2 0.2281 0.8626 0.000 0.904 0.096 0.000
#> GSM613685 2 0.1867 0.8660 0.000 0.928 0.072 0.000
#> GSM613686 4 0.4998 0.5418 0.488 0.000 0.000 0.512
#> GSM613687 1 0.0188 0.6663 0.996 0.000 0.000 0.004
#> GSM613688 2 0.1792 0.8532 0.000 0.932 0.068 0.000
#> GSM613689 3 0.2760 0.7950 0.000 0.000 0.872 0.128
#> GSM613690 3 0.0657 0.8624 0.000 0.004 0.984 0.012
#> GSM613691 2 0.4372 0.6631 0.000 0.728 0.268 0.004
#> GSM613692 1 0.4967 0.4377 0.548 0.000 0.000 0.452
#> GSM613693 2 0.2530 0.8569 0.000 0.888 0.112 0.000
#> GSM613694 4 0.4967 0.5811 0.452 0.000 0.000 0.548
#> GSM613695 3 0.4713 0.4687 0.000 0.000 0.640 0.360
#> GSM613696 2 0.3948 0.8044 0.000 0.840 0.064 0.096
#> GSM613697 4 0.4477 0.0822 0.000 0.000 0.312 0.688
#> GSM613698 4 0.5313 -0.0519 0.000 0.016 0.376 0.608
#> GSM613699 2 0.7505 0.3365 0.000 0.476 0.324 0.200
#> GSM613700 2 0.2943 0.8619 0.000 0.892 0.076 0.032
#> GSM613701 2 0.4053 0.7105 0.004 0.768 0.000 0.228
#> GSM613702 4 0.6788 0.5357 0.452 0.036 0.032 0.480
#> GSM613703 1 0.0000 0.6702 1.000 0.000 0.000 0.000
#> GSM613704 2 0.0000 0.8629 0.000 1.000 0.000 0.000
#> GSM613705 4 0.4998 -0.1333 0.000 0.000 0.488 0.512
#> GSM613706 4 0.4967 0.5811 0.452 0.000 0.000 0.548
#> GSM613707 2 0.1716 0.8674 0.000 0.936 0.064 0.000
#> GSM613708 1 0.0000 0.6702 1.000 0.000 0.000 0.000
#> GSM613709 1 0.0000 0.6702 1.000 0.000 0.000 0.000
#> GSM613710 2 0.4535 0.7395 0.000 0.744 0.240 0.016
#> GSM613711 3 0.2530 0.8307 0.000 0.112 0.888 0.000
#> GSM613712 3 0.4781 0.4977 0.000 0.004 0.660 0.336
#> GSM613713 2 0.3074 0.8476 0.000 0.848 0.152 0.000
#> GSM613714 3 0.4730 0.4596 0.000 0.000 0.636 0.364
#> GSM613715 3 0.2053 0.8283 0.000 0.072 0.924 0.004
#> GSM613716 3 0.4072 0.6685 0.000 0.252 0.748 0.000
#> GSM613717 3 0.1389 0.8661 0.000 0.048 0.952 0.000
#> GSM613718 3 0.1022 0.8692 0.000 0.032 0.968 0.000
#> GSM613719 3 0.5716 0.5813 0.000 0.068 0.680 0.252
#> GSM613720 3 0.2868 0.8117 0.000 0.136 0.864 0.000
#> GSM613721 2 0.2867 0.8423 0.000 0.884 0.104 0.012
#> GSM613722 2 0.2281 0.8617 0.000 0.904 0.096 0.000
#> GSM613723 1 0.4967 0.4377 0.548 0.000 0.000 0.452
#> GSM613724 1 0.0000 0.6702 1.000 0.000 0.000 0.000
#> GSM613725 2 0.2647 0.8586 0.000 0.880 0.120 0.000
#> GSM613726 4 0.4967 0.5811 0.452 0.000 0.000 0.548
#> GSM613727 1 0.0000 0.6702 1.000 0.000 0.000 0.000
#> GSM613728 2 0.0469 0.8610 0.000 0.988 0.012 0.000
#> GSM613729 1 0.0000 0.6702 1.000 0.000 0.000 0.000
#> GSM613730 4 0.7648 0.5004 0.368 0.164 0.008 0.460
#> GSM613731 4 0.4967 0.5811 0.452 0.000 0.000 0.548
#> GSM613732 3 0.1022 0.8692 0.000 0.032 0.968 0.000
#> GSM613733 3 0.2760 0.8194 0.000 0.128 0.872 0.000
#> GSM613734 1 0.4967 0.4377 0.548 0.000 0.000 0.452
#> GSM613735 1 0.4967 0.4377 0.548 0.000 0.000 0.452
#> GSM613736 2 0.4819 0.6577 0.000 0.652 0.344 0.004
#> GSM613737 4 0.1302 0.4049 0.000 0.000 0.044 0.956
#> GSM613738 1 0.4967 0.4377 0.548 0.000 0.000 0.452
#> GSM613739 4 0.3942 0.0357 0.236 0.000 0.000 0.764
#> GSM613740 3 0.1022 0.8692 0.000 0.032 0.968 0.000
#> GSM613741 4 0.8715 0.4428 0.300 0.244 0.044 0.412
#> GSM613742 4 0.1118 0.3632 0.036 0.000 0.000 0.964
#> GSM613743 3 0.1022 0.8692 0.000 0.032 0.968 0.000
#> GSM613744 3 0.1022 0.8692 0.000 0.032 0.968 0.000
#> GSM613745 1 0.7496 -0.5132 0.460 0.084 0.032 0.424
#> GSM613746 2 0.1389 0.8553 0.000 0.952 0.048 0.000
#> GSM613747 1 0.4967 0.4377 0.548 0.000 0.000 0.452
#> GSM613748 4 0.4967 0.5811 0.452 0.000 0.000 0.548
#> GSM613749 4 0.4981 0.5713 0.464 0.000 0.000 0.536
#> GSM613750 3 0.1022 0.8692 0.000 0.032 0.968 0.000
#> GSM613751 3 0.1637 0.8642 0.000 0.060 0.940 0.000
#> GSM613752 3 0.1211 0.8673 0.000 0.040 0.960 0.000
#> GSM613753 3 0.0000 0.8635 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
#> GSM613638 4 0.5368 0.2082 0.000 0.000 0.332 0.596 0.072
#> GSM613639 4 0.5159 0.1263 0.284 0.000 0.000 0.644 0.072
#> GSM613640 4 0.4873 0.4307 0.000 0.000 0.244 0.688 0.068
#> GSM613641 1 0.4278 0.6698 0.548 0.000 0.000 0.452 0.000
#> GSM613642 2 0.4015 0.6925 0.000 0.768 0.012 0.204 0.016
#> GSM613643 4 0.1544 0.6759 0.000 0.000 0.000 0.932 0.068
#> GSM613644 4 0.1544 0.6759 0.000 0.000 0.000 0.932 0.068
#> GSM613645 4 0.1845 0.6382 0.016 0.000 0.000 0.928 0.056
#> GSM613646 4 0.4069 0.5485 0.000 0.096 0.000 0.792 0.112
#> GSM613647 4 0.6752 0.3730 0.296 0.000 0.088 0.548 0.068
#> GSM613648 3 0.3001 0.6647 0.000 0.052 0.884 0.032 0.032
#> GSM613649 3 0.0566 0.6778 0.000 0.012 0.984 0.000 0.004
#> GSM613650 4 0.3340 0.6057 0.076 0.000 0.016 0.860 0.048
#> GSM613651 4 0.6182 0.2503 0.440 0.000 0.104 0.448 0.008
#> GSM613652 1 0.0000 0.4985 1.000 0.000 0.000 0.000 0.000
#> GSM613653 3 0.8604 0.3478 0.100 0.176 0.492 0.116 0.116
#> GSM613654 1 0.0000 0.4985 1.000 0.000 0.000 0.000 0.000
#> GSM613655 1 0.4219 0.6597 0.584 0.000 0.000 0.416 0.000
#> GSM613656 1 0.0000 0.4985 1.000 0.000 0.000 0.000 0.000
#> GSM613657 3 0.0000 0.6800 0.000 0.000 1.000 0.000 0.000
#> GSM613658 1 0.4256 0.6692 0.564 0.000 0.000 0.436 0.000
#> GSM613659 2 0.3966 0.7296 0.000 0.796 0.000 0.132 0.072
#> GSM613660 2 0.5884 0.5855 0.000 0.620 0.268 0.020 0.092
#> GSM613661 1 0.4415 0.6694 0.552 0.000 0.000 0.444 0.004
#> GSM613662 2 0.0609 0.7971 0.000 0.980 0.000 0.000 0.020
#> GSM613663 4 0.4268 -0.4920 0.444 0.000 0.000 0.556 0.000
#> GSM613664 2 0.1952 0.7985 0.000 0.912 0.004 0.000 0.084
#> GSM613665 2 0.4418 0.5952 0.000 0.652 0.332 0.000 0.016
#> GSM613666 1 0.4278 0.6698 0.548 0.000 0.000 0.452 0.000
#> GSM613667 4 0.1195 0.6405 0.028 0.000 0.000 0.960 0.012
#> GSM613668 1 0.4278 0.6698 0.548 0.000 0.000 0.452 0.000
#> GSM613669 1 0.4273 0.6714 0.552 0.000 0.000 0.448 0.000
#> GSM613670 2 0.2020 0.7693 0.000 0.900 0.000 0.000 0.100
#> GSM613671 1 0.4278 0.6698 0.548 0.000 0.000 0.452 0.000
#> GSM613672 1 0.4283 0.6654 0.544 0.000 0.000 0.456 0.000
#> GSM613673 4 0.1671 0.5935 0.076 0.000 0.000 0.924 0.000
#> GSM613674 2 0.2124 0.7966 0.000 0.900 0.004 0.000 0.096
#> GSM613675 2 0.0609 0.7971 0.000 0.980 0.000 0.000 0.020
#> GSM613676 2 0.4288 0.6094 0.000 0.664 0.324 0.000 0.012
#> GSM613677 3 0.5896 0.5302 0.000 0.148 0.688 0.092 0.072
#> GSM613678 4 0.2068 0.6168 0.000 0.092 0.000 0.904 0.004
#> GSM613679 2 0.2597 0.7985 0.000 0.884 0.024 0.000 0.092
#> GSM613680 1 0.4283 0.6658 0.544 0.000 0.000 0.456 0.000
#> GSM613681 1 0.4278 0.6698 0.548 0.000 0.000 0.452 0.000
#> GSM613682 4 0.1043 0.6322 0.040 0.000 0.000 0.960 0.000
#> GSM613683 1 0.4273 0.6714 0.552 0.000 0.000 0.448 0.000
#> GSM613684 2 0.2654 0.7967 0.000 0.884 0.032 0.000 0.084
#> GSM613685 2 0.2124 0.7966 0.000 0.900 0.004 0.000 0.096
#> GSM613686 4 0.1568 0.6324 0.036 0.000 0.000 0.944 0.020
#> GSM613687 1 0.4283 0.6651 0.544 0.000 0.000 0.456 0.000
#> GSM613688 2 0.3154 0.7967 0.000 0.860 0.024 0.012 0.104
#> GSM613689 3 0.3278 0.5868 0.000 0.000 0.824 0.156 0.020
#> GSM613690 3 0.3270 0.6416 0.000 0.036 0.864 0.080 0.020
#> GSM613691 2 0.4998 0.6537 0.000 0.716 0.172 0.004 0.108
#> GSM613692 1 0.0000 0.4985 1.000 0.000 0.000 0.000 0.000
#> GSM613693 2 0.3942 0.6777 0.000 0.728 0.260 0.000 0.012
#> GSM613694 4 0.0898 0.6621 0.000 0.000 0.008 0.972 0.020
#> GSM613695 3 0.5752 0.2282 0.000 0.000 0.500 0.412 0.088
#> GSM613696 2 0.3664 0.7465 0.000 0.840 0.024 0.096 0.040
#> GSM613697 4 0.7115 0.1579 0.368 0.000 0.200 0.408 0.024
#> GSM613698 1 0.8113 -0.3435 0.360 0.036 0.216 0.352 0.036
#> GSM613699 2 0.6551 0.4818 0.000 0.564 0.204 0.212 0.020
#> GSM613700 2 0.5880 0.6017 0.000 0.632 0.252 0.024 0.092
#> GSM613701 2 0.3877 0.6810 0.000 0.764 0.000 0.212 0.024
#> GSM613702 4 0.2616 0.6705 0.000 0.036 0.000 0.888 0.076
#> GSM613703 1 0.4803 0.6527 0.536 0.000 0.000 0.444 0.020
#> GSM613704 2 0.0671 0.7986 0.000 0.980 0.004 0.000 0.016
#> GSM613705 4 0.5499 0.0135 0.000 0.000 0.400 0.532 0.068
#> GSM613706 4 0.1544 0.6759 0.000 0.000 0.000 0.932 0.068
#> GSM613707 2 0.2351 0.7974 0.000 0.896 0.016 0.000 0.088
#> GSM613708 1 0.4273 0.6714 0.552 0.000 0.000 0.448 0.000
#> GSM613709 1 0.4273 0.6714 0.552 0.000 0.000 0.448 0.000
#> GSM613710 2 0.5887 0.5232 0.000 0.580 0.320 0.012 0.088
#> GSM613711 3 0.1106 0.6626 0.000 0.024 0.964 0.000 0.012
#> GSM613712 3 0.6354 0.2251 0.024 0.004 0.492 0.404 0.076
#> GSM613713 2 0.4049 0.7630 0.000 0.792 0.124 0.000 0.084
#> GSM613714 3 0.4734 0.5297 0.000 0.000 0.724 0.188 0.088
#> GSM613715 3 0.2361 0.6433 0.000 0.096 0.892 0.000 0.012
#> GSM613716 3 0.5804 0.3855 0.000 0.304 0.576 0.000 0.120
#> GSM613717 3 0.0162 0.6798 0.000 0.000 0.996 0.000 0.004
#> GSM613718 3 0.0000 0.6800 0.000 0.000 1.000 0.000 0.000
#> GSM613719 3 0.8185 0.3641 0.060 0.080 0.496 0.244 0.120
#> GSM613720 3 0.3224 0.5932 0.000 0.160 0.824 0.000 0.016
#> GSM613721 2 0.2795 0.7691 0.000 0.872 0.028 0.000 0.100
#> GSM613722 2 0.3151 0.7712 0.000 0.836 0.144 0.000 0.020
#> GSM613723 1 0.0000 0.4985 1.000 0.000 0.000 0.000 0.000
#> GSM613724 1 0.4273 0.6714 0.552 0.000 0.000 0.448 0.000
#> GSM613725 2 0.4748 0.7459 0.000 0.728 0.172 0.000 0.100
#> GSM613726 4 0.1608 0.6759 0.000 0.000 0.000 0.928 0.072
#> GSM613727 1 0.4273 0.6714 0.552 0.000 0.000 0.448 0.000
#> GSM613728 2 0.1774 0.7949 0.000 0.932 0.052 0.000 0.016
#> GSM613729 1 0.4420 0.6689 0.548 0.000 0.000 0.448 0.004
#> GSM613730 4 0.4795 0.6098 0.000 0.100 0.008 0.744 0.148
#> GSM613731 4 0.1544 0.6759 0.000 0.000 0.000 0.932 0.068
#> GSM613732 3 0.0000 0.6800 0.000 0.000 1.000 0.000 0.000
#> GSM613733 3 0.1661 0.6571 0.000 0.036 0.940 0.000 0.024
#> GSM613734 1 0.0000 0.4985 1.000 0.000 0.000 0.000 0.000
#> GSM613735 1 0.0000 0.4985 1.000 0.000 0.000 0.000 0.000
#> GSM613736 3 0.4648 -0.3413 0.000 0.464 0.524 0.000 0.012
#> GSM613737 4 0.5793 0.3271 0.412 0.000 0.044 0.520 0.024
#> GSM613738 1 0.0000 0.4985 1.000 0.000 0.000 0.000 0.000
#> GSM613739 1 0.3816 -0.0217 0.696 0.000 0.000 0.304 0.000
#> GSM613740 3 0.0000 0.6800 0.000 0.000 1.000 0.000 0.000
#> GSM613741 4 0.5952 0.4563 0.004 0.264 0.008 0.612 0.112
#> GSM613742 4 0.4306 0.3293 0.492 0.000 0.000 0.508 0.000
#> GSM613743 3 0.0000 0.6800 0.000 0.000 1.000 0.000 0.000
#> GSM613744 3 0.0000 0.6800 0.000 0.000 1.000 0.000 0.000
#> GSM613745 4 0.4455 0.5421 0.012 0.096 0.000 0.780 0.112
#> GSM613746 2 0.0671 0.7974 0.000 0.980 0.004 0.000 0.016
#> GSM613747 1 0.0000 0.4985 1.000 0.000 0.000 0.000 0.000
#> GSM613748 4 0.1830 0.6749 0.000 0.000 0.008 0.924 0.068
#> GSM613749 4 0.1018 0.6486 0.016 0.000 0.000 0.968 0.016
#> GSM613750 5 0.3730 0.9635 0.000 0.000 0.288 0.000 0.712
#> GSM613751 5 0.4425 0.9292 0.000 0.040 0.244 0.000 0.716
#> GSM613752 5 0.3861 0.9646 0.000 0.004 0.284 0.000 0.712
#> GSM613753 5 0.3636 0.9590 0.000 0.000 0.272 0.000 0.728
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM613638 4 0.0146 0.7313 0.000 0.000 0.000 0.996 0.004 0.000
#> GSM613639 4 0.4052 0.3684 0.260 0.000 0.000 0.708 0.020 0.012
#> GSM613640 4 0.0000 0.7326 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613641 1 0.0547 0.6356 0.980 0.000 0.000 0.000 0.000 0.020
#> GSM613642 2 0.2664 0.6670 0.000 0.816 0.000 0.184 0.000 0.000
#> GSM613643 4 0.0000 0.7326 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613644 4 0.0000 0.7326 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613645 1 0.4941 0.1920 0.492 0.000 0.000 0.444 0.064 0.000
#> GSM613646 1 0.5078 0.0736 0.488 0.000 0.000 0.056 0.448 0.008
#> GSM613647 4 0.0000 0.7326 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613648 3 0.3960 0.6115 0.000 0.000 0.760 0.180 0.052 0.008
#> GSM613649 3 0.0458 0.7666 0.000 0.016 0.984 0.000 0.000 0.000
#> GSM613650 1 0.6336 -0.0167 0.412 0.000 0.000 0.296 0.280 0.012
#> GSM613651 5 0.4466 0.2480 0.000 0.000 0.020 0.476 0.500 0.004
#> GSM613652 1 0.3868 0.1773 0.508 0.000 0.000 0.000 0.492 0.000
#> GSM613653 5 0.7155 -0.0136 0.100 0.288 0.140 0.004 0.460 0.008
#> GSM613654 1 0.3868 0.1773 0.508 0.000 0.000 0.000 0.492 0.000
#> GSM613655 1 0.1267 0.6060 0.940 0.000 0.000 0.000 0.060 0.000
#> GSM613656 1 0.3868 0.1773 0.508 0.000 0.000 0.000 0.492 0.000
#> GSM613657 3 0.0000 0.7673 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613658 1 0.0363 0.6341 0.988 0.000 0.000 0.000 0.012 0.000
#> GSM613659 2 0.4004 0.7164 0.000 0.780 0.000 0.108 0.100 0.012
#> GSM613660 4 0.6810 0.1318 0.000 0.068 0.328 0.492 0.056 0.056
#> GSM613661 1 0.0436 0.6353 0.988 0.000 0.000 0.004 0.004 0.004
#> GSM613662 2 0.3588 0.7600 0.000 0.788 0.000 0.000 0.152 0.060
#> GSM613663 1 0.1918 0.5888 0.904 0.000 0.000 0.088 0.000 0.008
#> GSM613664 2 0.0520 0.7738 0.000 0.984 0.000 0.000 0.008 0.008
#> GSM613665 3 0.5865 -0.0399 0.000 0.420 0.464 0.000 0.056 0.060
#> GSM613666 1 0.0547 0.6356 0.980 0.000 0.000 0.000 0.000 0.020
#> GSM613667 1 0.4653 0.1813 0.488 0.000 0.000 0.480 0.020 0.012
#> GSM613668 1 0.0260 0.6364 0.992 0.000 0.000 0.000 0.000 0.008
#> GSM613669 1 0.0508 0.6365 0.984 0.000 0.000 0.000 0.004 0.012
#> GSM613670 2 0.3745 0.7357 0.000 0.732 0.000 0.000 0.240 0.028
#> GSM613671 1 0.0363 0.6366 0.988 0.000 0.000 0.000 0.000 0.012
#> GSM613672 1 0.0405 0.6364 0.988 0.000 0.000 0.004 0.000 0.008
#> GSM613673 1 0.4072 0.2423 0.544 0.000 0.000 0.448 0.000 0.008
#> GSM613674 2 0.0146 0.7704 0.000 0.996 0.000 0.000 0.000 0.004
#> GSM613675 2 0.3513 0.7631 0.000 0.796 0.000 0.000 0.144 0.060
#> GSM613676 3 0.5643 0.0698 0.000 0.396 0.504 0.000 0.056 0.044
#> GSM613677 4 0.5898 0.3565 0.000 0.072 0.312 0.552 0.064 0.000
#> GSM613678 1 0.5541 0.1700 0.484 0.080 0.000 0.420 0.012 0.004
#> GSM613679 2 0.2732 0.7620 0.000 0.880 0.020 0.000 0.056 0.044
#> GSM613680 1 0.0405 0.6365 0.988 0.000 0.000 0.004 0.000 0.008
#> GSM613681 1 0.0363 0.6366 0.988 0.000 0.000 0.000 0.000 0.012
#> GSM613682 1 0.4095 0.2054 0.512 0.000 0.000 0.480 0.000 0.008
#> GSM613683 1 0.0146 0.6357 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM613684 2 0.0632 0.7682 0.000 0.976 0.024 0.000 0.000 0.000
#> GSM613685 2 0.0405 0.7715 0.000 0.988 0.000 0.000 0.008 0.004
#> GSM613686 1 0.5089 0.2078 0.496 0.000 0.000 0.444 0.044 0.016
#> GSM613687 1 0.0405 0.6363 0.988 0.000 0.000 0.004 0.000 0.008
#> GSM613688 2 0.1321 0.7668 0.000 0.952 0.020 0.004 0.024 0.000
#> GSM613689 3 0.4158 0.4879 0.000 0.000 0.704 0.052 0.244 0.000
#> GSM613690 3 0.5327 0.3170 0.000 0.000 0.588 0.164 0.248 0.000
#> GSM613691 2 0.6239 0.4573 0.000 0.500 0.292 0.004 0.184 0.020
#> GSM613692 1 0.3868 0.1773 0.508 0.000 0.000 0.000 0.492 0.000
#> GSM613693 2 0.5910 0.0712 0.000 0.448 0.432 0.000 0.068 0.052
#> GSM613694 1 0.6045 0.0900 0.488 0.000 0.000 0.260 0.244 0.008
#> GSM613695 4 0.5055 0.3465 0.000 0.000 0.132 0.624 0.244 0.000
#> GSM613696 2 0.5477 0.4229 0.000 0.560 0.008 0.100 0.328 0.004
#> GSM613697 5 0.4176 0.4886 0.000 0.000 0.068 0.212 0.720 0.000
#> GSM613698 5 0.3857 0.4859 0.000 0.000 0.072 0.148 0.776 0.004
#> GSM613699 2 0.7590 -0.0464 0.000 0.348 0.208 0.200 0.244 0.000
#> GSM613700 4 0.6936 0.1139 0.000 0.080 0.328 0.480 0.056 0.056
#> GSM613701 2 0.4230 0.5953 0.004 0.728 0.000 0.200 0.068 0.000
#> GSM613702 4 0.1196 0.7077 0.000 0.000 0.000 0.952 0.040 0.008
#> GSM613703 1 0.1745 0.6140 0.924 0.000 0.000 0.000 0.056 0.020
#> GSM613704 2 0.3588 0.7600 0.000 0.788 0.000 0.000 0.152 0.060
#> GSM613705 4 0.0713 0.7196 0.000 0.000 0.028 0.972 0.000 0.000
#> GSM613706 4 0.0000 0.7326 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613707 2 0.0260 0.7709 0.000 0.992 0.008 0.000 0.000 0.000
#> GSM613708 1 0.0363 0.6360 0.988 0.000 0.000 0.000 0.012 0.000
#> GSM613709 1 0.0508 0.6365 0.984 0.000 0.000 0.000 0.004 0.012
#> GSM613710 3 0.6765 0.0812 0.000 0.064 0.432 0.400 0.056 0.048
#> GSM613711 3 0.1493 0.7459 0.000 0.004 0.936 0.000 0.056 0.004
#> GSM613712 4 0.5240 0.2894 0.000 0.000 0.136 0.588 0.276 0.000
#> GSM613713 2 0.1444 0.7531 0.000 0.928 0.072 0.000 0.000 0.000
#> GSM613714 4 0.4508 0.2580 0.000 0.000 0.396 0.568 0.036 0.000
#> GSM613715 3 0.2118 0.7058 0.000 0.000 0.888 0.008 0.104 0.000
#> GSM613716 5 0.7148 -0.0201 0.000 0.224 0.296 0.052 0.412 0.016
#> GSM613717 3 0.0146 0.7675 0.000 0.004 0.996 0.000 0.000 0.000
#> GSM613718 3 0.0000 0.7673 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613719 5 0.4435 0.3802 0.032 0.000 0.136 0.060 0.764 0.008
#> GSM613720 3 0.4025 0.6773 0.000 0.060 0.796 0.000 0.096 0.048
#> GSM613721 2 0.3309 0.7449 0.000 0.800 0.024 0.000 0.172 0.004
#> GSM613722 2 0.3037 0.7297 0.000 0.820 0.160 0.000 0.004 0.016
#> GSM613723 1 0.3868 0.1773 0.508 0.000 0.000 0.000 0.492 0.000
#> GSM613724 1 0.0146 0.6357 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM613725 2 0.4651 0.3977 0.000 0.636 0.304 0.000 0.056 0.004
#> GSM613726 4 0.0508 0.7217 0.000 0.000 0.000 0.984 0.012 0.004
#> GSM613727 1 0.0508 0.6365 0.984 0.000 0.000 0.000 0.004 0.012
#> GSM613728 2 0.4792 0.7343 0.000 0.728 0.064 0.000 0.148 0.060
#> GSM613729 1 0.0622 0.6361 0.980 0.000 0.000 0.000 0.008 0.012
#> GSM613730 4 0.2653 0.6128 0.000 0.000 0.000 0.844 0.144 0.012
#> GSM613731 4 0.0000 0.7326 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613732 3 0.0000 0.7673 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613733 3 0.2002 0.7413 0.000 0.020 0.916 0.000 0.056 0.008
#> GSM613734 1 0.3868 0.1773 0.508 0.000 0.000 0.000 0.492 0.000
#> GSM613735 1 0.3868 0.1773 0.508 0.000 0.000 0.000 0.492 0.000
#> GSM613736 3 0.3214 0.6782 0.000 0.080 0.836 0.080 0.004 0.000
#> GSM613737 5 0.3405 0.4687 0.000 0.000 0.004 0.272 0.724 0.000
#> GSM613738 1 0.3868 0.1773 0.508 0.000 0.000 0.000 0.492 0.000
#> GSM613739 5 0.5818 0.2580 0.228 0.000 0.000 0.280 0.492 0.000
#> GSM613740 3 0.0363 0.7642 0.000 0.000 0.988 0.000 0.012 0.000
#> GSM613741 5 0.6874 0.1454 0.324 0.152 0.004 0.056 0.456 0.008
#> GSM613742 5 0.4609 0.3130 0.024 0.000 0.000 0.436 0.532 0.008
#> GSM613743 3 0.0000 0.7673 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613744 3 0.0713 0.7549 0.000 0.000 0.972 0.000 0.028 0.000
#> GSM613745 1 0.5081 0.0611 0.480 0.000 0.000 0.056 0.456 0.008
#> GSM613746 2 0.2997 0.7697 0.000 0.844 0.000 0.000 0.096 0.060
#> GSM613747 1 0.3867 0.1811 0.512 0.000 0.000 0.000 0.488 0.000
#> GSM613748 4 0.0000 0.7326 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613749 1 0.4653 0.1813 0.488 0.000 0.000 0.480 0.020 0.012
#> GSM613750 6 0.1714 0.9772 0.000 0.000 0.092 0.000 0.000 0.908
#> GSM613751 6 0.1349 0.9461 0.000 0.004 0.056 0.000 0.000 0.940
#> GSM613752 6 0.1663 0.9775 0.000 0.000 0.088 0.000 0.000 0.912
#> GSM613753 6 0.1806 0.9765 0.000 0.000 0.088 0.000 0.004 0.908
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) k
#> SD:pam 114 0.054603 2
#> SD:pam 61 0.142578 3
#> SD:pam 87 0.063930 4
#> SD:pam 87 0.004098 5
#> SD:pam 69 0.000123 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 27425 rows and 116 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'SD' method.
#> Subgroups are detected by 'mclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.702 0.930 0.926 0.4646 0.521 0.521
#> 3 3 0.416 0.573 0.723 0.3204 0.766 0.579
#> 4 4 0.629 0.692 0.816 0.1475 0.824 0.574
#> 5 5 0.712 0.582 0.809 0.1003 0.860 0.561
#> 6 6 0.843 0.775 0.904 0.0472 0.897 0.580
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
#> GSM613638 2 0.7376 0.834 0.208 0.792
#> GSM613639 1 0.4022 0.982 0.920 0.080
#> GSM613640 2 0.5059 0.892 0.112 0.888
#> GSM613641 1 0.4022 0.982 0.920 0.080
#> GSM613642 2 0.4815 0.897 0.104 0.896
#> GSM613643 1 0.2778 0.973 0.952 0.048
#> GSM613644 1 0.2603 0.971 0.956 0.044
#> GSM613645 1 0.4022 0.982 0.920 0.080
#> GSM613646 2 0.5408 0.883 0.124 0.876
#> GSM613647 2 0.6048 0.891 0.148 0.852
#> GSM613648 2 0.3431 0.918 0.064 0.936
#> GSM613649 2 0.3114 0.922 0.056 0.944
#> GSM613650 1 0.3431 0.959 0.936 0.064
#> GSM613651 1 0.4298 0.935 0.912 0.088
#> GSM613652 1 0.2603 0.971 0.956 0.044
#> GSM613653 2 0.6973 0.814 0.188 0.812
#> GSM613654 1 0.2603 0.971 0.956 0.044
#> GSM613655 1 0.4022 0.982 0.920 0.080
#> GSM613656 1 0.2603 0.971 0.956 0.044
#> GSM613657 2 0.3274 0.912 0.060 0.940
#> GSM613658 1 0.3114 0.975 0.944 0.056
#> GSM613659 2 0.5059 0.892 0.112 0.888
#> GSM613660 2 0.1184 0.929 0.016 0.984
#> GSM613661 1 0.4022 0.982 0.920 0.080
#> GSM613662 2 0.1414 0.928 0.020 0.980
#> GSM613663 1 0.4022 0.982 0.920 0.080
#> GSM613664 2 0.0672 0.930 0.008 0.992
#> GSM613665 2 0.0672 0.930 0.008 0.992
#> GSM613666 1 0.4022 0.982 0.920 0.080
#> GSM613667 1 0.4022 0.982 0.920 0.080
#> GSM613668 1 0.4022 0.982 0.920 0.080
#> GSM613669 1 0.4022 0.982 0.920 0.080
#> GSM613670 2 0.2423 0.928 0.040 0.960
#> GSM613671 1 0.4022 0.982 0.920 0.080
#> GSM613672 1 0.4022 0.982 0.920 0.080
#> GSM613673 1 0.4022 0.982 0.920 0.080
#> GSM613674 2 0.0672 0.926 0.008 0.992
#> GSM613675 2 0.1414 0.928 0.020 0.980
#> GSM613676 2 0.0000 0.929 0.000 1.000
#> GSM613677 2 0.1633 0.929 0.024 0.976
#> GSM613678 2 0.6623 0.835 0.172 0.828
#> GSM613679 2 0.1184 0.929 0.016 0.984
#> GSM613680 1 0.4022 0.982 0.920 0.080
#> GSM613681 1 0.4022 0.982 0.920 0.080
#> GSM613682 1 0.4022 0.982 0.920 0.080
#> GSM613683 1 0.4022 0.982 0.920 0.080
#> GSM613684 2 0.0672 0.930 0.008 0.992
#> GSM613685 2 0.0672 0.926 0.008 0.992
#> GSM613686 1 0.4022 0.982 0.920 0.080
#> GSM613687 1 0.4022 0.982 0.920 0.080
#> GSM613688 2 0.1184 0.929 0.016 0.984
#> GSM613689 2 0.2778 0.926 0.048 0.952
#> GSM613690 2 0.2603 0.925 0.044 0.956
#> GSM613691 2 0.0672 0.930 0.008 0.992
#> GSM613692 1 0.2603 0.971 0.956 0.044
#> GSM613693 2 0.0672 0.930 0.008 0.992
#> GSM613694 2 0.7139 0.848 0.196 0.804
#> GSM613695 2 0.6048 0.891 0.148 0.852
#> GSM613696 2 0.5408 0.893 0.124 0.876
#> GSM613697 1 0.3274 0.962 0.940 0.060
#> GSM613698 2 0.6048 0.891 0.148 0.852
#> GSM613699 2 0.6048 0.891 0.148 0.852
#> GSM613700 2 0.1184 0.929 0.016 0.984
#> GSM613701 2 0.5059 0.892 0.112 0.888
#> GSM613702 2 0.5059 0.892 0.112 0.888
#> GSM613703 1 0.4022 0.982 0.920 0.080
#> GSM613704 2 0.1414 0.928 0.020 0.980
#> GSM613705 2 0.6048 0.891 0.148 0.852
#> GSM613706 2 0.5408 0.883 0.124 0.876
#> GSM613707 2 0.0376 0.928 0.004 0.996
#> GSM613708 1 0.4022 0.982 0.920 0.080
#> GSM613709 1 0.4022 0.982 0.920 0.080
#> GSM613710 2 0.1184 0.929 0.016 0.984
#> GSM613711 2 0.3274 0.912 0.060 0.940
#> GSM613712 2 0.6343 0.883 0.160 0.840
#> GSM613713 2 0.0672 0.930 0.008 0.992
#> GSM613714 2 0.3584 0.925 0.068 0.932
#> GSM613715 2 0.2603 0.925 0.044 0.956
#> GSM613716 2 0.2603 0.925 0.044 0.956
#> GSM613717 2 0.0938 0.925 0.012 0.988
#> GSM613718 2 0.3274 0.912 0.060 0.940
#> GSM613719 2 0.9896 0.354 0.440 0.560
#> GSM613720 2 0.2603 0.925 0.044 0.956
#> GSM613721 2 0.4939 0.895 0.108 0.892
#> GSM613722 2 0.0672 0.930 0.008 0.992
#> GSM613723 1 0.2603 0.971 0.956 0.044
#> GSM613724 1 0.2603 0.971 0.956 0.044
#> GSM613725 2 0.1184 0.929 0.016 0.984
#> GSM613726 1 0.4022 0.982 0.920 0.080
#> GSM613727 1 0.4022 0.982 0.920 0.080
#> GSM613728 2 0.0672 0.930 0.008 0.992
#> GSM613729 1 0.4022 0.982 0.920 0.080
#> GSM613730 2 0.5059 0.892 0.112 0.888
#> GSM613731 1 0.4022 0.982 0.920 0.080
#> GSM613732 2 0.3274 0.912 0.060 0.940
#> GSM613733 2 0.0672 0.930 0.008 0.992
#> GSM613734 1 0.2603 0.971 0.956 0.044
#> GSM613735 1 0.2603 0.971 0.956 0.044
#> GSM613736 2 0.2603 0.925 0.044 0.956
#> GSM613737 2 0.7056 0.853 0.192 0.808
#> GSM613738 1 0.2603 0.971 0.956 0.044
#> GSM613739 1 0.2603 0.971 0.956 0.044
#> GSM613740 2 0.3274 0.912 0.060 0.940
#> GSM613741 2 0.6623 0.834 0.172 0.828
#> GSM613742 1 0.2603 0.971 0.956 0.044
#> GSM613743 2 0.3274 0.912 0.060 0.940
#> GSM613744 2 0.3274 0.912 0.060 0.940
#> GSM613745 2 0.5059 0.892 0.112 0.888
#> GSM613746 2 0.1414 0.928 0.020 0.980
#> GSM613747 1 0.2603 0.971 0.956 0.044
#> GSM613748 2 0.5059 0.892 0.112 0.888
#> GSM613749 1 0.4431 0.973 0.908 0.092
#> GSM613750 2 0.2236 0.923 0.036 0.964
#> GSM613751 2 0.3274 0.912 0.060 0.940
#> GSM613752 2 0.3114 0.922 0.056 0.944
#> GSM613753 2 0.2603 0.925 0.044 0.956
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM613638 3 0.0592 0.4642 0.012 0.000 0.988
#> GSM613639 1 0.5327 0.6742 0.728 0.000 0.272
#> GSM613640 3 0.5633 0.3618 0.208 0.024 0.768
#> GSM613641 1 0.0000 0.9043 1.000 0.000 0.000
#> GSM613642 2 0.6518 0.5738 0.004 0.512 0.484
#> GSM613643 1 0.6095 0.4565 0.608 0.000 0.392
#> GSM613644 3 0.6225 0.1008 0.432 0.000 0.568
#> GSM613645 1 0.4346 0.7787 0.816 0.000 0.184
#> GSM613646 3 0.7083 0.2293 0.380 0.028 0.592
#> GSM613647 3 0.0747 0.4645 0.016 0.000 0.984
#> GSM613648 3 0.5480 0.3053 0.004 0.264 0.732
#> GSM613649 3 0.6008 0.2877 0.004 0.332 0.664
#> GSM613650 3 0.6302 -0.0769 0.480 0.000 0.520
#> GSM613651 3 0.4796 0.3879 0.220 0.000 0.780
#> GSM613652 1 0.3482 0.8692 0.872 0.128 0.000
#> GSM613653 3 0.6896 0.2018 0.392 0.020 0.588
#> GSM613654 1 0.3482 0.8692 0.872 0.128 0.000
#> GSM613655 1 0.0000 0.9043 1.000 0.000 0.000
#> GSM613656 1 0.3482 0.8692 0.872 0.128 0.000
#> GSM613657 3 0.6225 0.2965 0.000 0.432 0.568
#> GSM613658 1 0.0000 0.9043 1.000 0.000 0.000
#> GSM613659 3 0.6410 -0.3590 0.004 0.420 0.576
#> GSM613660 2 0.5465 0.8973 0.000 0.712 0.288
#> GSM613661 1 0.4062 0.7975 0.836 0.000 0.164
#> GSM613662 2 0.5785 0.9000 0.004 0.696 0.300
#> GSM613663 1 0.0000 0.9043 1.000 0.000 0.000
#> GSM613664 2 0.5785 0.9000 0.004 0.696 0.300
#> GSM613665 2 0.5929 0.8989 0.004 0.676 0.320
#> GSM613666 1 0.0000 0.9043 1.000 0.000 0.000
#> GSM613667 1 0.4235 0.7859 0.824 0.000 0.176
#> GSM613668 1 0.0000 0.9043 1.000 0.000 0.000
#> GSM613669 1 0.0000 0.9043 1.000 0.000 0.000
#> GSM613670 2 0.6520 0.4971 0.004 0.508 0.488
#> GSM613671 1 0.0000 0.9043 1.000 0.000 0.000
#> GSM613672 1 0.0000 0.9043 1.000 0.000 0.000
#> GSM613673 1 0.0000 0.9043 1.000 0.000 0.000
#> GSM613674 2 0.5465 0.8973 0.000 0.712 0.288
#> GSM613675 2 0.5785 0.9000 0.004 0.696 0.300
#> GSM613676 2 0.5929 0.8989 0.004 0.676 0.320
#> GSM613677 3 0.5785 0.2446 0.004 0.300 0.696
#> GSM613678 3 0.7099 -0.2561 0.028 0.384 0.588
#> GSM613679 2 0.5465 0.8973 0.000 0.712 0.288
#> GSM613680 1 0.0000 0.9043 1.000 0.000 0.000
#> GSM613681 1 0.0000 0.9043 1.000 0.000 0.000
#> GSM613682 1 0.0000 0.9043 1.000 0.000 0.000
#> GSM613683 1 0.0000 0.9043 1.000 0.000 0.000
#> GSM613684 2 0.5929 0.8989 0.004 0.676 0.320
#> GSM613685 2 0.5465 0.8973 0.000 0.712 0.288
#> GSM613686 1 0.4178 0.7900 0.828 0.000 0.172
#> GSM613687 1 0.0000 0.9043 1.000 0.000 0.000
#> GSM613688 2 0.5929 0.8989 0.004 0.676 0.320
#> GSM613689 3 0.4629 0.3742 0.004 0.188 0.808
#> GSM613690 3 0.4409 0.3860 0.004 0.172 0.824
#> GSM613691 2 0.5815 0.8969 0.004 0.692 0.304
#> GSM613692 1 0.3482 0.7961 0.872 0.000 0.128
#> GSM613693 2 0.6126 0.8365 0.004 0.644 0.352
#> GSM613694 3 0.4931 0.3715 0.232 0.000 0.768
#> GSM613695 3 0.0661 0.4614 0.004 0.008 0.988
#> GSM613696 3 0.1129 0.4566 0.004 0.020 0.976
#> GSM613697 3 0.3116 0.4409 0.108 0.000 0.892
#> GSM613698 3 0.1129 0.4596 0.004 0.020 0.976
#> GSM613699 3 0.0237 0.4634 0.004 0.000 0.996
#> GSM613700 2 0.5465 0.8973 0.000 0.712 0.288
#> GSM613701 3 0.6410 -0.3486 0.004 0.420 0.576
#> GSM613702 3 0.6509 -0.4836 0.004 0.472 0.524
#> GSM613703 1 0.3193 0.8289 0.896 0.004 0.100
#> GSM613704 2 0.5785 0.9000 0.004 0.696 0.300
#> GSM613705 3 0.0475 0.4628 0.004 0.004 0.992
#> GSM613706 3 0.6330 0.2070 0.396 0.004 0.600
#> GSM613707 2 0.5529 0.9011 0.000 0.704 0.296
#> GSM613708 1 0.0000 0.9043 1.000 0.000 0.000
#> GSM613709 1 0.0000 0.9043 1.000 0.000 0.000
#> GSM613710 2 0.5465 0.8973 0.000 0.712 0.288
#> GSM613711 3 0.6215 0.2985 0.000 0.428 0.572
#> GSM613712 3 0.0237 0.4634 0.004 0.000 0.996
#> GSM613713 3 0.6330 -0.0492 0.004 0.396 0.600
#> GSM613714 3 0.5404 0.3179 0.004 0.256 0.740
#> GSM613715 3 0.5480 0.3053 0.004 0.264 0.732
#> GSM613716 3 0.5158 0.3557 0.004 0.232 0.764
#> GSM613717 3 0.6215 0.2985 0.000 0.428 0.572
#> GSM613718 3 0.6215 0.2985 0.000 0.428 0.572
#> GSM613719 3 0.5503 0.3798 0.208 0.020 0.772
#> GSM613720 3 0.5873 0.2638 0.004 0.312 0.684
#> GSM613721 3 0.6495 -0.4001 0.004 0.460 0.536
#> GSM613722 2 0.5560 0.9021 0.000 0.700 0.300
#> GSM613723 1 0.3482 0.8692 0.872 0.128 0.000
#> GSM613724 1 0.0000 0.9043 1.000 0.000 0.000
#> GSM613725 2 0.5465 0.8973 0.000 0.712 0.288
#> GSM613726 1 0.4346 0.7787 0.816 0.000 0.184
#> GSM613727 1 0.0000 0.9043 1.000 0.000 0.000
#> GSM613728 2 0.5929 0.8989 0.004 0.676 0.320
#> GSM613729 1 0.0000 0.9043 1.000 0.000 0.000
#> GSM613730 2 0.6521 0.5390 0.004 0.500 0.496
#> GSM613731 1 0.6095 0.4565 0.608 0.000 0.392
#> GSM613732 3 0.6215 0.2985 0.000 0.428 0.572
#> GSM613733 3 0.6126 0.1325 0.004 0.352 0.644
#> GSM613734 1 0.3482 0.8692 0.872 0.128 0.000
#> GSM613735 1 0.3482 0.8692 0.872 0.128 0.000
#> GSM613736 3 0.5690 0.2681 0.004 0.288 0.708
#> GSM613737 3 0.0237 0.4634 0.004 0.000 0.996
#> GSM613738 1 0.3482 0.7961 0.872 0.000 0.128
#> GSM613739 1 0.3482 0.8692 0.872 0.128 0.000
#> GSM613740 3 0.6215 0.2985 0.000 0.428 0.572
#> GSM613741 3 0.6896 0.2018 0.392 0.020 0.588
#> GSM613742 1 0.3619 0.7914 0.864 0.000 0.136
#> GSM613743 3 0.6215 0.2985 0.000 0.428 0.572
#> GSM613744 3 0.6215 0.2985 0.000 0.428 0.572
#> GSM613745 3 0.5889 0.3473 0.096 0.108 0.796
#> GSM613746 2 0.5785 0.9000 0.004 0.696 0.300
#> GSM613747 1 0.3482 0.8692 0.872 0.128 0.000
#> GSM613748 3 0.6298 -0.2795 0.004 0.388 0.608
#> GSM613749 3 0.7912 0.1499 0.404 0.060 0.536
#> GSM613750 3 0.5480 0.3053 0.004 0.264 0.732
#> GSM613751 3 0.6192 0.3060 0.000 0.420 0.580
#> GSM613752 3 0.5529 0.2727 0.000 0.296 0.704
#> GSM613753 3 0.0829 0.4603 0.004 0.012 0.984
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 3 0.7313 0.45739 0.188 0.084 0.644 0.084
#> GSM613639 1 0.5555 0.72606 0.740 0.004 0.140 0.116
#> GSM613640 3 0.9076 0.05572 0.216 0.276 0.424 0.084
#> GSM613641 1 0.0000 0.89791 1.000 0.000 0.000 0.000
#> GSM613642 2 0.6286 0.57518 0.012 0.668 0.236 0.084
#> GSM613643 1 0.5053 0.75253 0.772 0.004 0.148 0.076
#> GSM613644 1 0.5276 0.73493 0.756 0.004 0.156 0.084
#> GSM613645 1 0.4163 0.80698 0.828 0.000 0.076 0.096
#> GSM613646 1 0.6838 0.54807 0.612 0.004 0.152 0.232
#> GSM613647 3 0.5409 0.52792 0.168 0.004 0.744 0.084
#> GSM613648 3 0.3730 0.70770 0.004 0.144 0.836 0.016
#> GSM613649 3 0.3289 0.70695 0.004 0.140 0.852 0.004
#> GSM613650 1 0.5339 0.73441 0.752 0.004 0.156 0.088
#> GSM613651 3 0.6791 0.16535 0.392 0.000 0.508 0.100
#> GSM613652 1 0.1114 0.89272 0.972 0.004 0.008 0.016
#> GSM613653 4 0.4144 0.68512 0.028 0.004 0.152 0.816
#> GSM613654 1 0.1114 0.89272 0.972 0.004 0.008 0.016
#> GSM613655 1 0.0000 0.89791 1.000 0.000 0.000 0.000
#> GSM613656 1 0.1114 0.89272 0.972 0.004 0.008 0.016
#> GSM613657 3 0.3024 0.70083 0.000 0.148 0.852 0.000
#> GSM613658 1 0.0188 0.89747 0.996 0.000 0.000 0.004
#> GSM613659 4 0.5110 0.65775 0.008 0.056 0.172 0.764
#> GSM613660 2 0.0188 0.81226 0.000 0.996 0.004 0.000
#> GSM613661 1 0.3398 0.83636 0.872 0.000 0.060 0.068
#> GSM613662 4 0.2457 0.75933 0.004 0.076 0.008 0.912
#> GSM613663 1 0.0000 0.89791 1.000 0.000 0.000 0.000
#> GSM613664 4 0.2412 0.76000 0.008 0.084 0.000 0.908
#> GSM613665 2 0.1617 0.80213 0.008 0.956 0.012 0.024
#> GSM613666 1 0.0000 0.89791 1.000 0.000 0.000 0.000
#> GSM613667 1 0.3164 0.84217 0.884 0.000 0.064 0.052
#> GSM613668 1 0.0000 0.89791 1.000 0.000 0.000 0.000
#> GSM613669 1 0.0000 0.89791 1.000 0.000 0.000 0.000
#> GSM613670 4 0.2125 0.76023 0.004 0.076 0.000 0.920
#> GSM613671 1 0.0188 0.89718 0.996 0.000 0.000 0.004
#> GSM613672 1 0.0000 0.89791 1.000 0.000 0.000 0.000
#> GSM613673 1 0.0000 0.89791 1.000 0.000 0.000 0.000
#> GSM613674 2 0.0188 0.81226 0.000 0.996 0.004 0.000
#> GSM613675 4 0.2473 0.76056 0.000 0.080 0.012 0.908
#> GSM613676 2 0.3651 0.73575 0.008 0.844 0.136 0.012
#> GSM613677 3 0.4087 0.68663 0.008 0.080 0.844 0.068
#> GSM613678 1 0.6407 0.62747 0.664 0.004 0.148 0.184
#> GSM613679 2 0.0188 0.81226 0.000 0.996 0.004 0.000
#> GSM613680 1 0.0000 0.89791 1.000 0.000 0.000 0.000
#> GSM613681 1 0.0000 0.89791 1.000 0.000 0.000 0.000
#> GSM613682 1 0.0000 0.89791 1.000 0.000 0.000 0.000
#> GSM613683 1 0.0000 0.89791 1.000 0.000 0.000 0.000
#> GSM613684 2 0.5803 0.38323 0.008 0.632 0.328 0.032
#> GSM613685 2 0.0188 0.81226 0.000 0.996 0.004 0.000
#> GSM613686 1 0.2926 0.84977 0.896 0.000 0.056 0.048
#> GSM613687 1 0.0000 0.89791 1.000 0.000 0.000 0.000
#> GSM613688 2 0.6056 0.51908 0.012 0.676 0.064 0.248
#> GSM613689 3 0.6525 0.43533 0.008 0.384 0.548 0.060
#> GSM613690 3 0.2039 0.69680 0.008 0.036 0.940 0.016
#> GSM613691 4 0.2402 0.76174 0.000 0.076 0.012 0.912
#> GSM613692 1 0.1042 0.89330 0.972 0.000 0.008 0.020
#> GSM613693 3 0.7923 0.21414 0.008 0.216 0.436 0.340
#> GSM613694 3 0.6946 0.02607 0.436 0.008 0.472 0.084
#> GSM613695 3 0.2597 0.65447 0.008 0.004 0.904 0.084
#> GSM613696 3 0.4034 0.57570 0.008 0.004 0.796 0.192
#> GSM613697 3 0.6393 0.37722 0.284 0.000 0.616 0.100
#> GSM613698 3 0.4153 0.56224 0.008 0.004 0.784 0.204
#> GSM613699 3 0.2960 0.65101 0.020 0.004 0.892 0.084
#> GSM613700 2 0.0188 0.81226 0.000 0.996 0.004 0.000
#> GSM613701 2 0.5779 0.61487 0.016 0.736 0.156 0.092
#> GSM613702 2 0.5747 0.61612 0.016 0.740 0.148 0.096
#> GSM613703 1 0.4905 0.34681 0.632 0.004 0.000 0.364
#> GSM613704 4 0.2342 0.75844 0.000 0.080 0.008 0.912
#> GSM613705 3 0.5369 0.58721 0.016 0.132 0.768 0.084
#> GSM613706 1 0.8827 0.15540 0.440 0.320 0.156 0.084
#> GSM613707 2 0.0188 0.81226 0.000 0.996 0.004 0.000
#> GSM613708 1 0.0188 0.89747 0.996 0.000 0.000 0.004
#> GSM613709 1 0.0000 0.89791 1.000 0.000 0.000 0.000
#> GSM613710 2 0.0188 0.81226 0.000 0.996 0.004 0.000
#> GSM613711 3 0.3074 0.69841 0.000 0.152 0.848 0.000
#> GSM613712 3 0.2795 0.65228 0.012 0.004 0.896 0.088
#> GSM613713 3 0.5012 0.57866 0.008 0.320 0.668 0.004
#> GSM613714 3 0.5401 0.62719 0.008 0.260 0.700 0.032
#> GSM613715 3 0.3873 0.70807 0.008 0.144 0.832 0.016
#> GSM613716 3 0.5591 -0.00677 0.008 0.008 0.500 0.484
#> GSM613717 3 0.3123 0.69966 0.000 0.156 0.844 0.000
#> GSM613718 3 0.3024 0.70083 0.000 0.148 0.852 0.000
#> GSM613719 3 0.6917 -0.08480 0.092 0.004 0.468 0.436
#> GSM613720 4 0.7710 -0.14300 0.008 0.168 0.404 0.420
#> GSM613721 4 0.3607 0.70736 0.008 0.016 0.124 0.852
#> GSM613722 2 0.0712 0.81013 0.004 0.984 0.004 0.008
#> GSM613723 1 0.1114 0.89272 0.972 0.004 0.008 0.016
#> GSM613724 1 0.0188 0.89747 0.996 0.000 0.000 0.004
#> GSM613725 2 0.0188 0.81226 0.000 0.996 0.004 0.000
#> GSM613726 1 0.4155 0.80049 0.828 0.000 0.100 0.072
#> GSM613727 1 0.0000 0.89791 1.000 0.000 0.000 0.000
#> GSM613728 2 0.3006 0.76231 0.008 0.888 0.012 0.092
#> GSM613729 1 0.0188 0.89718 0.996 0.000 0.000 0.004
#> GSM613730 2 0.6792 0.55259 0.012 0.644 0.180 0.164
#> GSM613731 1 0.5136 0.74494 0.768 0.004 0.144 0.084
#> GSM613732 3 0.2973 0.70284 0.000 0.144 0.856 0.000
#> GSM613733 2 0.4571 0.58143 0.008 0.736 0.252 0.004
#> GSM613734 1 0.1114 0.89272 0.972 0.004 0.008 0.016
#> GSM613735 1 0.1082 0.89275 0.972 0.004 0.004 0.020
#> GSM613736 3 0.4092 0.69434 0.008 0.184 0.800 0.008
#> GSM613737 3 0.2597 0.65447 0.008 0.004 0.904 0.084
#> GSM613738 1 0.1042 0.89330 0.972 0.000 0.008 0.020
#> GSM613739 1 0.1114 0.89272 0.972 0.004 0.008 0.016
#> GSM613740 3 0.2973 0.70284 0.000 0.144 0.856 0.000
#> GSM613741 4 0.3780 0.69459 0.016 0.004 0.148 0.832
#> GSM613742 1 0.3156 0.85529 0.884 0.000 0.048 0.068
#> GSM613743 3 0.3074 0.70189 0.000 0.152 0.848 0.000
#> GSM613744 3 0.2973 0.70284 0.000 0.144 0.856 0.000
#> GSM613745 4 0.6443 0.03289 0.056 0.004 0.468 0.472
#> GSM613746 4 0.2473 0.76056 0.000 0.080 0.012 0.908
#> GSM613747 1 0.1114 0.89272 0.972 0.004 0.008 0.016
#> GSM613748 2 0.6923 0.56702 0.064 0.672 0.180 0.084
#> GSM613749 1 0.5136 0.74494 0.768 0.004 0.144 0.084
#> GSM613750 3 0.3873 0.70807 0.008 0.144 0.832 0.016
#> GSM613751 3 0.2921 0.70423 0.000 0.140 0.860 0.000
#> GSM613752 3 0.2973 0.70284 0.000 0.144 0.856 0.000
#> GSM613753 3 0.1516 0.68838 0.008 0.016 0.960 0.016
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM613638 3 0.4944 0.4141 0.012 0.000 0.560 0.012 0.416
#> GSM613639 1 0.4436 0.4356 0.596 0.000 0.000 0.008 0.396
#> GSM613640 5 0.6697 -0.1963 0.000 0.240 0.376 0.000 0.384
#> GSM613641 1 0.0000 0.7898 1.000 0.000 0.000 0.000 0.000
#> GSM613642 2 0.5058 0.4551 0.000 0.576 0.040 0.000 0.384
#> GSM613643 1 0.4659 0.2596 0.500 0.000 0.000 0.012 0.488
#> GSM613644 5 0.5115 0.3082 0.224 0.000 0.068 0.012 0.696
#> GSM613645 1 0.4074 0.4771 0.636 0.000 0.000 0.000 0.364
#> GSM613646 4 0.6518 0.2676 0.192 0.000 0.000 0.412 0.396
#> GSM613647 5 0.4270 0.1276 0.012 0.000 0.320 0.000 0.668
#> GSM613648 3 0.0703 0.8108 0.000 0.000 0.976 0.000 0.024
#> GSM613649 3 0.0404 0.8090 0.000 0.000 0.988 0.000 0.012
#> GSM613650 5 0.4347 0.2288 0.264 0.000 0.012 0.012 0.712
#> GSM613651 5 0.0404 0.3832 0.000 0.000 0.012 0.000 0.988
#> GSM613652 5 0.4734 0.4661 0.372 0.000 0.000 0.024 0.604
#> GSM613653 4 0.4138 0.5268 0.000 0.000 0.000 0.616 0.384
#> GSM613654 5 0.4734 0.4661 0.372 0.000 0.000 0.024 0.604
#> GSM613655 1 0.0000 0.7898 1.000 0.000 0.000 0.000 0.000
#> GSM613656 5 0.4734 0.4661 0.372 0.000 0.000 0.024 0.604
#> GSM613657 3 0.0000 0.8087 0.000 0.000 1.000 0.000 0.000
#> GSM613658 1 0.0807 0.7800 0.976 0.000 0.000 0.012 0.012
#> GSM613659 4 0.4871 0.5174 0.012 0.000 0.012 0.592 0.384
#> GSM613660 2 0.0000 0.7507 0.000 1.000 0.000 0.000 0.000
#> GSM613661 1 0.4030 0.4979 0.648 0.000 0.000 0.000 0.352
#> GSM613662 4 0.1106 0.7133 0.000 0.012 0.000 0.964 0.024
#> GSM613663 1 0.0000 0.7898 1.000 0.000 0.000 0.000 0.000
#> GSM613664 4 0.1106 0.7133 0.000 0.012 0.000 0.964 0.024
#> GSM613665 2 0.0693 0.7429 0.000 0.980 0.012 0.008 0.000
#> GSM613666 1 0.0404 0.7865 0.988 0.000 0.000 0.000 0.012
#> GSM613667 1 0.3534 0.5848 0.744 0.000 0.000 0.000 0.256
#> GSM613668 1 0.0000 0.7898 1.000 0.000 0.000 0.000 0.000
#> GSM613669 1 0.0404 0.7865 0.988 0.000 0.000 0.000 0.012
#> GSM613670 4 0.1106 0.7133 0.000 0.012 0.000 0.964 0.024
#> GSM613671 1 0.0404 0.7865 0.988 0.000 0.000 0.000 0.012
#> GSM613672 1 0.0000 0.7898 1.000 0.000 0.000 0.000 0.000
#> GSM613673 1 0.0000 0.7898 1.000 0.000 0.000 0.000 0.000
#> GSM613674 2 0.0000 0.7507 0.000 1.000 0.000 0.000 0.000
#> GSM613675 4 0.1106 0.7133 0.000 0.012 0.000 0.964 0.024
#> GSM613676 2 0.1965 0.7225 0.000 0.924 0.052 0.000 0.024
#> GSM613677 3 0.4323 0.5385 0.000 0.000 0.656 0.012 0.332
#> GSM613678 1 0.5086 0.3995 0.564 0.000 0.000 0.040 0.396
#> GSM613679 2 0.0000 0.7507 0.000 1.000 0.000 0.000 0.000
#> GSM613680 1 0.0000 0.7898 1.000 0.000 0.000 0.000 0.000
#> GSM613681 1 0.0000 0.7898 1.000 0.000 0.000 0.000 0.000
#> GSM613682 1 0.0000 0.7898 1.000 0.000 0.000 0.000 0.000
#> GSM613683 1 0.0000 0.7898 1.000 0.000 0.000 0.000 0.000
#> GSM613684 2 0.5714 0.4261 0.000 0.636 0.072 0.268 0.024
#> GSM613685 2 0.0000 0.7507 0.000 1.000 0.000 0.000 0.000
#> GSM613686 1 0.2773 0.6676 0.836 0.000 0.000 0.000 0.164
#> GSM613687 1 0.0000 0.7898 1.000 0.000 0.000 0.000 0.000
#> GSM613688 4 0.5797 0.1633 0.000 0.352 0.012 0.564 0.072
#> GSM613689 3 0.3318 0.6972 0.000 0.012 0.808 0.000 0.180
#> GSM613690 3 0.0880 0.8093 0.000 0.000 0.968 0.000 0.032
#> GSM613691 4 0.1106 0.7133 0.000 0.012 0.000 0.964 0.024
#> GSM613692 5 0.4138 0.4463 0.384 0.000 0.000 0.000 0.616
#> GSM613693 4 0.1741 0.6999 0.000 0.000 0.040 0.936 0.024
#> GSM613694 5 0.4976 -0.1879 0.012 0.000 0.436 0.012 0.540
#> GSM613695 3 0.4138 0.4832 0.000 0.000 0.616 0.000 0.384
#> GSM613696 3 0.5518 0.4066 0.000 0.000 0.544 0.072 0.384
#> GSM613697 5 0.0404 0.3832 0.000 0.000 0.012 0.000 0.988
#> GSM613698 5 0.4135 0.0704 0.000 0.000 0.340 0.004 0.656
#> GSM613699 3 0.4505 0.4739 0.000 0.000 0.604 0.012 0.384
#> GSM613700 2 0.0000 0.7507 0.000 1.000 0.000 0.000 0.000
#> GSM613701 2 0.4505 0.4770 0.012 0.604 0.000 0.000 0.384
#> GSM613702 2 0.4505 0.4770 0.012 0.604 0.000 0.000 0.384
#> GSM613703 1 0.3940 0.5086 0.756 0.000 0.000 0.220 0.024
#> GSM613704 4 0.1106 0.7133 0.000 0.012 0.000 0.964 0.024
#> GSM613705 3 0.4936 0.4267 0.000 0.012 0.564 0.012 0.412
#> GSM613706 2 0.6189 0.3372 0.140 0.476 0.000 0.000 0.384
#> GSM613707 2 0.0000 0.7507 0.000 1.000 0.000 0.000 0.000
#> GSM613708 1 0.0566 0.7852 0.984 0.000 0.000 0.004 0.012
#> GSM613709 1 0.0404 0.7865 0.988 0.000 0.000 0.000 0.012
#> GSM613710 2 0.0000 0.7507 0.000 1.000 0.000 0.000 0.000
#> GSM613711 3 0.0000 0.8087 0.000 0.000 1.000 0.000 0.000
#> GSM613712 3 0.4219 0.4471 0.000 0.000 0.584 0.000 0.416
#> GSM613713 3 0.4692 0.5768 0.000 0.276 0.688 0.012 0.024
#> GSM613714 3 0.1364 0.8041 0.000 0.012 0.952 0.000 0.036
#> GSM613715 3 0.0963 0.8079 0.000 0.000 0.964 0.000 0.036
#> GSM613716 3 0.5977 0.3875 0.000 0.000 0.540 0.332 0.128
#> GSM613717 3 0.0290 0.8110 0.000 0.000 0.992 0.000 0.008
#> GSM613718 3 0.0000 0.8087 0.000 0.000 1.000 0.000 0.000
#> GSM613719 5 0.4254 0.2743 0.000 0.000 0.220 0.040 0.740
#> GSM613720 4 0.5109 -0.0385 0.000 0.000 0.460 0.504 0.036
#> GSM613721 4 0.3003 0.6613 0.000 0.000 0.000 0.812 0.188
#> GSM613722 2 0.0000 0.7507 0.000 1.000 0.000 0.000 0.000
#> GSM613723 5 0.4734 0.4661 0.372 0.000 0.000 0.024 0.604
#> GSM613724 1 0.0404 0.7820 0.988 0.000 0.000 0.012 0.000
#> GSM613725 2 0.0000 0.7507 0.000 1.000 0.000 0.000 0.000
#> GSM613726 1 0.4074 0.4732 0.636 0.000 0.000 0.000 0.364
#> GSM613727 1 0.0000 0.7898 1.000 0.000 0.000 0.000 0.000
#> GSM613728 2 0.4015 0.6043 0.000 0.768 0.012 0.204 0.016
#> GSM613729 1 0.0404 0.7865 0.988 0.000 0.000 0.000 0.012
#> GSM613730 2 0.6750 0.4555 0.012 0.556 0.012 0.192 0.228
#> GSM613731 1 0.4138 0.4469 0.616 0.000 0.000 0.000 0.384
#> GSM613732 3 0.0000 0.8087 0.000 0.000 1.000 0.000 0.000
#> GSM613733 2 0.4897 0.1327 0.000 0.516 0.460 0.000 0.024
#> GSM613734 5 0.5028 0.4237 0.400 0.000 0.000 0.036 0.564
#> GSM613735 5 0.4696 0.4661 0.360 0.000 0.000 0.024 0.616
#> GSM613736 3 0.0510 0.8119 0.000 0.000 0.984 0.000 0.016
#> GSM613737 5 0.4242 -0.1552 0.000 0.000 0.428 0.000 0.572
#> GSM613738 5 0.4074 0.4649 0.364 0.000 0.000 0.000 0.636
#> GSM613739 5 0.4696 0.4661 0.360 0.000 0.000 0.024 0.616
#> GSM613740 3 0.0000 0.8087 0.000 0.000 1.000 0.000 0.000
#> GSM613741 4 0.4138 0.5268 0.000 0.000 0.000 0.616 0.384
#> GSM613742 5 0.1043 0.4082 0.040 0.000 0.000 0.000 0.960
#> GSM613743 3 0.0000 0.8087 0.000 0.000 1.000 0.000 0.000
#> GSM613744 3 0.0000 0.8087 0.000 0.000 1.000 0.000 0.000
#> GSM613745 4 0.4321 0.5160 0.000 0.000 0.004 0.600 0.396
#> GSM613746 4 0.0703 0.7119 0.000 0.000 0.000 0.976 0.024
#> GSM613747 5 0.4969 0.4580 0.376 0.000 0.000 0.036 0.588
#> GSM613748 2 0.5068 0.4602 0.032 0.580 0.004 0.000 0.384
#> GSM613749 1 0.4138 0.4469 0.616 0.000 0.000 0.000 0.384
#> GSM613750 3 0.0703 0.8108 0.000 0.000 0.976 0.000 0.024
#> GSM613751 3 0.0000 0.8087 0.000 0.000 1.000 0.000 0.000
#> GSM613752 3 0.0510 0.8119 0.000 0.000 0.984 0.000 0.016
#> GSM613753 3 0.0703 0.8108 0.000 0.000 0.976 0.000 0.024
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM613638 4 0.0000 0.8782 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613639 1 0.4774 0.4639 0.600 0.000 0.000 0.332 0.068 0.000
#> GSM613640 4 0.0000 0.8782 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613641 1 0.0000 0.8807 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613642 4 0.3857 0.0305 0.000 0.468 0.000 0.532 0.000 0.000
#> GSM613643 4 0.0000 0.8782 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613644 4 0.1007 0.8596 0.000 0.000 0.000 0.956 0.044 0.000
#> GSM613645 1 0.3626 0.7240 0.788 0.000 0.000 0.144 0.068 0.000
#> GSM613646 4 0.1387 0.8464 0.000 0.000 0.000 0.932 0.068 0.000
#> GSM613647 4 0.0000 0.8782 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613648 3 0.0000 0.9594 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613649 3 0.0000 0.9594 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613650 4 0.1387 0.8464 0.000 0.000 0.000 0.932 0.068 0.000
#> GSM613651 4 0.0000 0.8782 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613652 5 0.1387 0.9664 0.068 0.000 0.000 0.000 0.932 0.000
#> GSM613653 6 0.4823 0.3954 0.000 0.000 0.000 0.348 0.068 0.584
#> GSM613654 5 0.1387 0.9664 0.068 0.000 0.000 0.000 0.932 0.000
#> GSM613655 1 0.0713 0.8613 0.972 0.000 0.000 0.000 0.028 0.000
#> GSM613656 5 0.1387 0.9664 0.068 0.000 0.000 0.000 0.932 0.000
#> GSM613657 3 0.0000 0.9594 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613658 1 0.0000 0.8807 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613659 6 0.4118 0.4317 0.000 0.000 0.000 0.352 0.020 0.628
#> GSM613660 2 0.0000 0.8169 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613661 1 0.4507 0.5786 0.664 0.000 0.000 0.268 0.068 0.000
#> GSM613662 6 0.0000 0.7846 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM613663 1 0.0000 0.8807 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613664 6 0.0000 0.7846 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM613665 2 0.0000 0.8169 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613666 1 0.0000 0.8807 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613667 1 0.3206 0.7614 0.828 0.000 0.000 0.104 0.068 0.000
#> GSM613668 1 0.0000 0.8807 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613669 1 0.0000 0.8807 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613670 6 0.0000 0.7846 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM613671 1 0.0000 0.8807 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613672 1 0.0000 0.8807 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613673 1 0.0000 0.8807 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613674 2 0.0000 0.8169 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613675 6 0.0000 0.7846 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM613676 2 0.0632 0.8032 0.000 0.976 0.024 0.000 0.000 0.000
#> GSM613677 4 0.0632 0.8657 0.000 0.000 0.024 0.976 0.000 0.000
#> GSM613678 1 0.5183 0.2563 0.516 0.000 0.000 0.408 0.068 0.008
#> GSM613679 2 0.0000 0.8169 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613680 1 0.0000 0.8807 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613681 1 0.0000 0.8807 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613682 1 0.0000 0.8807 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613683 1 0.0000 0.8807 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613684 2 0.4310 0.2543 0.000 0.580 0.024 0.000 0.000 0.396
#> GSM613685 2 0.0000 0.8169 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613686 1 0.1387 0.8383 0.932 0.000 0.000 0.000 0.068 0.000
#> GSM613687 1 0.0000 0.8807 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613688 6 0.3630 0.5403 0.000 0.212 0.000 0.032 0.000 0.756
#> GSM613689 3 0.3515 0.5014 0.000 0.000 0.676 0.324 0.000 0.000
#> GSM613690 3 0.0146 0.9560 0.000 0.000 0.996 0.004 0.000 0.000
#> GSM613691 6 0.0000 0.7846 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM613692 4 0.3470 0.6510 0.200 0.000 0.000 0.772 0.028 0.000
#> GSM613693 6 0.0146 0.7826 0.000 0.000 0.004 0.000 0.000 0.996
#> GSM613694 4 0.0000 0.8782 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613695 4 0.0000 0.8782 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613696 4 0.0000 0.8782 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613697 4 0.0000 0.8782 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613698 4 0.0000 0.8782 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613699 4 0.0000 0.8782 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613700 2 0.0000 0.8169 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613701 2 0.3756 0.3174 0.000 0.600 0.000 0.400 0.000 0.000
#> GSM613702 2 0.3756 0.3174 0.000 0.600 0.000 0.400 0.000 0.000
#> GSM613703 1 0.1387 0.8383 0.932 0.000 0.000 0.000 0.068 0.000
#> GSM613704 6 0.0000 0.7846 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM613705 4 0.0000 0.8782 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613706 4 0.2454 0.7331 0.000 0.160 0.000 0.840 0.000 0.000
#> GSM613707 2 0.0000 0.8169 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613708 1 0.0000 0.8807 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613709 1 0.0000 0.8807 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613710 2 0.0000 0.8169 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613711 3 0.0000 0.9594 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613712 4 0.0000 0.8782 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613713 3 0.3266 0.6328 0.000 0.272 0.728 0.000 0.000 0.000
#> GSM613714 4 0.3515 0.4615 0.000 0.000 0.324 0.676 0.000 0.000
#> GSM613715 3 0.0000 0.9594 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613716 4 0.3765 0.2369 0.000 0.000 0.000 0.596 0.000 0.404
#> GSM613717 3 0.0000 0.9594 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613718 3 0.0000 0.9594 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613719 4 0.1387 0.8464 0.000 0.000 0.000 0.932 0.068 0.000
#> GSM613720 6 0.3828 0.1367 0.000 0.000 0.440 0.000 0.000 0.560
#> GSM613721 6 0.3453 0.6778 0.000 0.000 0.000 0.132 0.064 0.804
#> GSM613722 2 0.0000 0.8169 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613723 5 0.1387 0.9664 0.068 0.000 0.000 0.000 0.932 0.000
#> GSM613724 1 0.0000 0.8807 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613725 2 0.0000 0.8169 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613726 1 0.4738 0.4608 0.600 0.000 0.000 0.336 0.064 0.000
#> GSM613727 1 0.0000 0.8807 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613728 2 0.2854 0.6472 0.000 0.792 0.000 0.000 0.000 0.208
#> GSM613729 1 0.0000 0.8807 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613730 2 0.5887 0.1143 0.000 0.408 0.000 0.392 0.000 0.200
#> GSM613731 4 0.3727 0.2593 0.388 0.000 0.000 0.612 0.000 0.000
#> GSM613732 3 0.0000 0.9594 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613733 2 0.3747 0.3217 0.000 0.604 0.396 0.000 0.000 0.000
#> GSM613734 5 0.1387 0.9664 0.068 0.000 0.000 0.000 0.932 0.000
#> GSM613735 5 0.1387 0.9664 0.068 0.000 0.000 0.000 0.932 0.000
#> GSM613736 3 0.0000 0.9594 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613737 4 0.0000 0.8782 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613738 5 0.4024 0.7186 0.264 0.000 0.000 0.036 0.700 0.000
#> GSM613739 5 0.1387 0.9664 0.068 0.000 0.000 0.000 0.932 0.000
#> GSM613740 3 0.0000 0.9594 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613741 6 0.4760 0.4363 0.000 0.000 0.000 0.328 0.068 0.604
#> GSM613742 4 0.1387 0.8299 0.068 0.000 0.000 0.932 0.000 0.000
#> GSM613743 3 0.0000 0.9594 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613744 3 0.0000 0.9594 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613745 4 0.1387 0.8464 0.000 0.000 0.000 0.932 0.068 0.000
#> GSM613746 6 0.0000 0.7846 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM613747 5 0.1387 0.9664 0.068 0.000 0.000 0.000 0.932 0.000
#> GSM613748 4 0.2941 0.6472 0.000 0.220 0.000 0.780 0.000 0.000
#> GSM613749 1 0.4774 0.4639 0.600 0.000 0.000 0.332 0.068 0.000
#> GSM613750 3 0.0000 0.9594 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613751 3 0.0000 0.9594 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613752 3 0.0000 0.9594 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613753 3 0.0547 0.9402 0.000 0.000 0.980 0.020 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) k
#> SD:mclust 115 0.061075 2
#> SD:mclust 61 0.447646 3
#> SD:mclust 102 0.140369 4
#> SD:mclust 69 0.172469 5
#> SD:mclust 99 0.000871 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 27425 rows and 116 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 0.912 0.940 0.974 0.5012 0.498 0.498
#> 3 3 0.670 0.801 0.910 0.3049 0.767 0.566
#> 4 4 0.745 0.814 0.910 0.1123 0.852 0.613
#> 5 5 0.609 0.587 0.769 0.0671 0.909 0.701
#> 6 6 0.618 0.492 0.712 0.0427 0.920 0.688
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
#> GSM613638 2 0.8081 0.684 0.248 0.752
#> GSM613639 1 0.0000 0.979 1.000 0.000
#> GSM613640 2 0.7139 0.764 0.196 0.804
#> GSM613641 1 0.0000 0.979 1.000 0.000
#> GSM613642 2 0.0000 0.967 0.000 1.000
#> GSM613643 1 0.0000 0.979 1.000 0.000
#> GSM613644 1 0.0000 0.979 1.000 0.000
#> GSM613645 1 0.0000 0.979 1.000 0.000
#> GSM613646 1 0.5178 0.862 0.884 0.116
#> GSM613647 1 0.8267 0.641 0.740 0.260
#> GSM613648 2 0.0000 0.967 0.000 1.000
#> GSM613649 2 0.0000 0.967 0.000 1.000
#> GSM613650 1 0.0000 0.979 1.000 0.000
#> GSM613651 1 0.0000 0.979 1.000 0.000
#> GSM613652 1 0.0000 0.979 1.000 0.000
#> GSM613653 1 0.2423 0.945 0.960 0.040
#> GSM613654 1 0.0000 0.979 1.000 0.000
#> GSM613655 1 0.0000 0.979 1.000 0.000
#> GSM613656 1 0.0000 0.979 1.000 0.000
#> GSM613657 2 0.0000 0.967 0.000 1.000
#> GSM613658 1 0.0000 0.979 1.000 0.000
#> GSM613659 2 0.0000 0.967 0.000 1.000
#> GSM613660 2 0.0000 0.967 0.000 1.000
#> GSM613661 1 0.0000 0.979 1.000 0.000
#> GSM613662 2 0.0000 0.967 0.000 1.000
#> GSM613663 1 0.0000 0.979 1.000 0.000
#> GSM613664 2 0.0000 0.967 0.000 1.000
#> GSM613665 2 0.0000 0.967 0.000 1.000
#> GSM613666 1 0.0000 0.979 1.000 0.000
#> GSM613667 1 0.0000 0.979 1.000 0.000
#> GSM613668 1 0.0000 0.979 1.000 0.000
#> GSM613669 1 0.0000 0.979 1.000 0.000
#> GSM613670 2 0.2236 0.938 0.036 0.964
#> GSM613671 1 0.0000 0.979 1.000 0.000
#> GSM613672 1 0.0000 0.979 1.000 0.000
#> GSM613673 1 0.0000 0.979 1.000 0.000
#> GSM613674 2 0.0000 0.967 0.000 1.000
#> GSM613675 2 0.0000 0.967 0.000 1.000
#> GSM613676 2 0.0000 0.967 0.000 1.000
#> GSM613677 2 0.0000 0.967 0.000 1.000
#> GSM613678 1 0.0672 0.973 0.992 0.008
#> GSM613679 2 0.0000 0.967 0.000 1.000
#> GSM613680 1 0.0000 0.979 1.000 0.000
#> GSM613681 1 0.0000 0.979 1.000 0.000
#> GSM613682 1 0.0000 0.979 1.000 0.000
#> GSM613683 1 0.0000 0.979 1.000 0.000
#> GSM613684 2 0.0000 0.967 0.000 1.000
#> GSM613685 2 0.0000 0.967 0.000 1.000
#> GSM613686 1 0.0000 0.979 1.000 0.000
#> GSM613687 1 0.0000 0.979 1.000 0.000
#> GSM613688 2 0.0000 0.967 0.000 1.000
#> GSM613689 2 0.0000 0.967 0.000 1.000
#> GSM613690 2 0.0000 0.967 0.000 1.000
#> GSM613691 2 0.0000 0.967 0.000 1.000
#> GSM613692 1 0.0000 0.979 1.000 0.000
#> GSM613693 2 0.0000 0.967 0.000 1.000
#> GSM613694 1 0.5519 0.847 0.872 0.128
#> GSM613695 2 0.0000 0.967 0.000 1.000
#> GSM613696 2 0.1414 0.952 0.020 0.980
#> GSM613697 1 0.0000 0.979 1.000 0.000
#> GSM613698 2 0.9775 0.323 0.412 0.588
#> GSM613699 2 0.6887 0.778 0.184 0.816
#> GSM613700 2 0.0000 0.967 0.000 1.000
#> GSM613701 2 0.2043 0.941 0.032 0.968
#> GSM613702 2 0.0672 0.961 0.008 0.992
#> GSM613703 1 0.0000 0.979 1.000 0.000
#> GSM613704 2 0.0000 0.967 0.000 1.000
#> GSM613705 2 0.7528 0.734 0.216 0.784
#> GSM613706 1 0.1414 0.963 0.980 0.020
#> GSM613707 2 0.0000 0.967 0.000 1.000
#> GSM613708 1 0.0000 0.979 1.000 0.000
#> GSM613709 1 0.0000 0.979 1.000 0.000
#> GSM613710 2 0.0000 0.967 0.000 1.000
#> GSM613711 2 0.0000 0.967 0.000 1.000
#> GSM613712 2 0.7745 0.716 0.228 0.772
#> GSM613713 2 0.0000 0.967 0.000 1.000
#> GSM613714 2 0.0000 0.967 0.000 1.000
#> GSM613715 2 0.0000 0.967 0.000 1.000
#> GSM613716 2 0.0000 0.967 0.000 1.000
#> GSM613717 2 0.0000 0.967 0.000 1.000
#> GSM613718 2 0.0000 0.967 0.000 1.000
#> GSM613719 1 0.1633 0.960 0.976 0.024
#> GSM613720 2 0.0000 0.967 0.000 1.000
#> GSM613721 2 0.0000 0.967 0.000 1.000
#> GSM613722 2 0.0000 0.967 0.000 1.000
#> GSM613723 1 0.0000 0.979 1.000 0.000
#> GSM613724 1 0.0000 0.979 1.000 0.000
#> GSM613725 2 0.0000 0.967 0.000 1.000
#> GSM613726 1 0.0000 0.979 1.000 0.000
#> GSM613727 1 0.0000 0.979 1.000 0.000
#> GSM613728 2 0.0000 0.967 0.000 1.000
#> GSM613729 1 0.0000 0.979 1.000 0.000
#> GSM613730 2 0.0000 0.967 0.000 1.000
#> GSM613731 1 0.0000 0.979 1.000 0.000
#> GSM613732 2 0.0000 0.967 0.000 1.000
#> GSM613733 2 0.0000 0.967 0.000 1.000
#> GSM613734 1 0.0000 0.979 1.000 0.000
#> GSM613735 1 0.0000 0.979 1.000 0.000
#> GSM613736 2 0.0000 0.967 0.000 1.000
#> GSM613737 1 0.9795 0.261 0.584 0.416
#> GSM613738 1 0.0000 0.979 1.000 0.000
#> GSM613739 1 0.0000 0.979 1.000 0.000
#> GSM613740 2 0.0000 0.967 0.000 1.000
#> GSM613741 1 0.2948 0.933 0.948 0.052
#> GSM613742 1 0.0000 0.979 1.000 0.000
#> GSM613743 2 0.0000 0.967 0.000 1.000
#> GSM613744 2 0.0000 0.967 0.000 1.000
#> GSM613745 2 0.9358 0.481 0.352 0.648
#> GSM613746 2 0.0000 0.967 0.000 1.000
#> GSM613747 1 0.0000 0.979 1.000 0.000
#> GSM613748 2 0.0000 0.967 0.000 1.000
#> GSM613749 1 0.0000 0.979 1.000 0.000
#> GSM613750 2 0.0000 0.967 0.000 1.000
#> GSM613751 2 0.0000 0.967 0.000 1.000
#> GSM613752 2 0.0000 0.967 0.000 1.000
#> GSM613753 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
#> GSM613638 3 0.4796 0.7092 0.220 0.000 0.780
#> GSM613639 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613640 3 0.3752 0.7676 0.144 0.000 0.856
#> GSM613641 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613642 3 0.6295 -0.1593 0.000 0.472 0.528
#> GSM613643 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613644 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613645 1 0.4002 0.8098 0.840 0.160 0.000
#> GSM613646 1 0.5581 0.7579 0.788 0.176 0.036
#> GSM613647 3 0.5560 0.6077 0.300 0.000 0.700
#> GSM613648 3 0.0000 0.8369 0.000 0.000 1.000
#> GSM613649 3 0.0000 0.8369 0.000 0.000 1.000
#> GSM613650 1 0.1031 0.9309 0.976 0.000 0.024
#> GSM613651 3 0.6252 0.2992 0.444 0.000 0.556
#> GSM613652 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613653 1 0.3850 0.8633 0.884 0.088 0.028
#> GSM613654 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613655 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613656 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613657 3 0.0000 0.8369 0.000 0.000 1.000
#> GSM613658 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613659 2 0.0000 0.8806 0.000 1.000 0.000
#> GSM613660 3 0.6192 0.0442 0.000 0.420 0.580
#> GSM613661 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613662 2 0.0000 0.8806 0.000 1.000 0.000
#> GSM613663 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613664 2 0.0000 0.8806 0.000 1.000 0.000
#> GSM613665 2 0.4399 0.8147 0.000 0.812 0.188
#> GSM613666 1 0.0592 0.9419 0.988 0.012 0.000
#> GSM613667 1 0.0424 0.9446 0.992 0.008 0.000
#> GSM613668 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613669 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613670 2 0.0000 0.8806 0.000 1.000 0.000
#> GSM613671 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613672 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613673 1 0.0237 0.9468 0.996 0.004 0.000
#> GSM613674 2 0.3412 0.8526 0.000 0.876 0.124
#> GSM613675 2 0.0237 0.8806 0.000 0.996 0.004
#> GSM613676 3 0.6180 0.0698 0.000 0.416 0.584
#> GSM613677 3 0.0000 0.8369 0.000 0.000 1.000
#> GSM613678 2 0.0000 0.8806 0.000 1.000 0.000
#> GSM613679 2 0.4235 0.8242 0.000 0.824 0.176
#> GSM613680 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613681 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613682 1 0.5327 0.6136 0.728 0.272 0.000
#> GSM613683 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613684 2 0.5706 0.6449 0.000 0.680 0.320
#> GSM613685 2 0.4062 0.8315 0.000 0.836 0.164
#> GSM613686 2 0.4796 0.7016 0.220 0.780 0.000
#> GSM613687 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613688 2 0.2165 0.8728 0.000 0.936 0.064
#> GSM613689 3 0.0000 0.8369 0.000 0.000 1.000
#> GSM613690 3 0.0000 0.8369 0.000 0.000 1.000
#> GSM613691 2 0.0892 0.8769 0.000 0.980 0.020
#> GSM613692 1 0.0237 0.9465 0.996 0.000 0.004
#> GSM613693 3 0.2711 0.7816 0.000 0.088 0.912
#> GSM613694 3 0.6154 0.3959 0.408 0.000 0.592
#> GSM613695 3 0.0000 0.8369 0.000 0.000 1.000
#> GSM613696 3 0.4033 0.7690 0.136 0.008 0.856
#> GSM613697 3 0.6140 0.4046 0.404 0.000 0.596
#> GSM613698 3 0.5138 0.6784 0.252 0.000 0.748
#> GSM613699 3 0.3816 0.7633 0.148 0.000 0.852
#> GSM613700 2 0.4452 0.8124 0.000 0.808 0.192
#> GSM613701 2 0.4128 0.8002 0.132 0.856 0.012
#> GSM613702 2 0.0237 0.8801 0.004 0.996 0.000
#> GSM613703 1 0.4796 0.7325 0.780 0.220 0.000
#> GSM613704 2 0.0000 0.8806 0.000 1.000 0.000
#> GSM613705 3 0.4121 0.7491 0.168 0.000 0.832
#> GSM613706 1 0.4931 0.6810 0.768 0.232 0.000
#> GSM613707 2 0.3340 0.8545 0.000 0.880 0.120
#> GSM613708 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613709 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613710 3 0.4974 0.5454 0.000 0.236 0.764
#> GSM613711 3 0.0000 0.8369 0.000 0.000 1.000
#> GSM613712 3 0.4504 0.7279 0.196 0.000 0.804
#> GSM613713 3 0.0424 0.8320 0.000 0.008 0.992
#> GSM613714 3 0.0000 0.8369 0.000 0.000 1.000
#> GSM613715 3 0.0000 0.8369 0.000 0.000 1.000
#> GSM613716 3 0.3482 0.7626 0.000 0.128 0.872
#> GSM613717 3 0.0000 0.8369 0.000 0.000 1.000
#> GSM613718 3 0.0000 0.8369 0.000 0.000 1.000
#> GSM613719 1 0.6299 -0.0665 0.524 0.000 0.476
#> GSM613720 3 0.0747 0.8294 0.000 0.016 0.984
#> GSM613721 2 0.0424 0.8799 0.000 0.992 0.008
#> GSM613722 2 0.4796 0.7864 0.000 0.780 0.220
#> GSM613723 1 0.0237 0.9465 0.996 0.000 0.004
#> GSM613724 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613725 2 0.5760 0.6385 0.000 0.672 0.328
#> GSM613726 1 0.0237 0.9468 0.996 0.004 0.000
#> GSM613727 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613728 2 0.0000 0.8806 0.000 1.000 0.000
#> GSM613729 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613730 2 0.0000 0.8806 0.000 1.000 0.000
#> GSM613731 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613732 3 0.0000 0.8369 0.000 0.000 1.000
#> GSM613733 3 0.0237 0.8345 0.000 0.004 0.996
#> GSM613734 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613735 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613736 3 0.0000 0.8369 0.000 0.000 1.000
#> GSM613737 3 0.5254 0.6621 0.264 0.000 0.736
#> GSM613738 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613739 1 0.0237 0.9465 0.996 0.000 0.004
#> GSM613740 3 0.0000 0.8369 0.000 0.000 1.000
#> GSM613741 1 0.6737 0.4060 0.600 0.384 0.016
#> GSM613742 1 0.1163 0.9271 0.972 0.000 0.028
#> GSM613743 3 0.0000 0.8369 0.000 0.000 1.000
#> GSM613744 3 0.0000 0.8369 0.000 0.000 1.000
#> GSM613745 3 0.8627 0.2723 0.104 0.392 0.504
#> GSM613746 2 0.1529 0.8680 0.000 0.960 0.040
#> GSM613747 1 0.0000 0.9489 1.000 0.000 0.000
#> GSM613748 2 0.6975 0.5496 0.028 0.616 0.356
#> GSM613749 2 0.3752 0.7879 0.144 0.856 0.000
#> GSM613750 3 0.0000 0.8369 0.000 0.000 1.000
#> GSM613751 3 0.0000 0.8369 0.000 0.000 1.000
#> GSM613752 3 0.0000 0.8369 0.000 0.000 1.000
#> GSM613753 3 0.0000 0.8369 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 3 0.7082 0.440 0.308 0.152 0.540 0.000
#> GSM613639 1 0.4746 0.480 0.632 0.000 0.000 0.368
#> GSM613640 2 0.7773 0.226 0.288 0.432 0.280 0.000
#> GSM613641 1 0.0000 0.936 1.000 0.000 0.000 0.000
#> GSM613642 2 0.2281 0.839 0.000 0.904 0.096 0.000
#> GSM613643 1 0.0000 0.936 1.000 0.000 0.000 0.000
#> GSM613644 1 0.0188 0.934 0.996 0.000 0.004 0.000
#> GSM613645 1 0.4353 0.687 0.756 0.012 0.000 0.232
#> GSM613646 4 0.0524 0.915 0.004 0.000 0.008 0.988
#> GSM613647 3 0.1716 0.841 0.064 0.000 0.936 0.000
#> GSM613648 3 0.0000 0.860 0.000 0.000 1.000 0.000
#> GSM613649 3 0.0707 0.854 0.000 0.000 0.980 0.020
#> GSM613650 1 0.4040 0.640 0.752 0.000 0.248 0.000
#> GSM613651 3 0.4122 0.702 0.236 0.000 0.760 0.004
#> GSM613652 1 0.0000 0.936 1.000 0.000 0.000 0.000
#> GSM613653 4 0.0336 0.916 0.000 0.000 0.008 0.992
#> GSM613654 1 0.0000 0.936 1.000 0.000 0.000 0.000
#> GSM613655 1 0.0000 0.936 1.000 0.000 0.000 0.000
#> GSM613656 1 0.0000 0.936 1.000 0.000 0.000 0.000
#> GSM613657 3 0.0469 0.858 0.000 0.012 0.988 0.000
#> GSM613658 1 0.0000 0.936 1.000 0.000 0.000 0.000
#> GSM613659 4 0.1211 0.901 0.000 0.040 0.000 0.960
#> GSM613660 2 0.1474 0.861 0.000 0.948 0.052 0.000
#> GSM613661 1 0.0000 0.936 1.000 0.000 0.000 0.000
#> GSM613662 4 0.0707 0.911 0.000 0.020 0.000 0.980
#> GSM613663 1 0.0000 0.936 1.000 0.000 0.000 0.000
#> GSM613664 4 0.3975 0.686 0.000 0.240 0.000 0.760
#> GSM613665 2 0.0707 0.872 0.000 0.980 0.020 0.000
#> GSM613666 1 0.4535 0.627 0.704 0.004 0.000 0.292
#> GSM613667 1 0.0188 0.934 0.996 0.004 0.000 0.000
#> GSM613668 1 0.0000 0.936 1.000 0.000 0.000 0.000
#> GSM613669 1 0.0336 0.932 0.992 0.000 0.000 0.008
#> GSM613670 4 0.0707 0.911 0.000 0.020 0.000 0.980
#> GSM613671 1 0.3764 0.740 0.784 0.000 0.000 0.216
#> GSM613672 1 0.0000 0.936 1.000 0.000 0.000 0.000
#> GSM613673 1 0.0707 0.924 0.980 0.020 0.000 0.000
#> GSM613674 2 0.0336 0.872 0.000 0.992 0.000 0.008
#> GSM613675 4 0.0188 0.916 0.000 0.000 0.004 0.996
#> GSM613676 2 0.2921 0.801 0.000 0.860 0.140 0.000
#> GSM613677 3 0.0188 0.860 0.000 0.004 0.996 0.000
#> GSM613678 4 0.3801 0.702 0.000 0.220 0.000 0.780
#> GSM613679 2 0.0524 0.873 0.000 0.988 0.004 0.008
#> GSM613680 1 0.0000 0.936 1.000 0.000 0.000 0.000
#> GSM613681 1 0.0000 0.936 1.000 0.000 0.000 0.000
#> GSM613682 1 0.3142 0.814 0.860 0.132 0.000 0.008
#> GSM613683 1 0.0000 0.936 1.000 0.000 0.000 0.000
#> GSM613684 2 0.2002 0.859 0.000 0.936 0.020 0.044
#> GSM613685 2 0.0376 0.873 0.000 0.992 0.004 0.004
#> GSM613686 1 0.6327 0.576 0.652 0.132 0.000 0.216
#> GSM613687 1 0.0000 0.936 1.000 0.000 0.000 0.000
#> GSM613688 2 0.3751 0.697 0.000 0.800 0.004 0.196
#> GSM613689 3 0.4304 0.570 0.000 0.284 0.716 0.000
#> GSM613690 3 0.0336 0.858 0.000 0.000 0.992 0.008
#> GSM613691 4 0.0188 0.916 0.000 0.000 0.004 0.996
#> GSM613692 1 0.3790 0.766 0.820 0.000 0.164 0.016
#> GSM613693 4 0.5873 0.148 0.000 0.036 0.416 0.548
#> GSM613694 3 0.4985 0.205 0.468 0.000 0.532 0.000
#> GSM613695 3 0.0000 0.860 0.000 0.000 1.000 0.000
#> GSM613696 3 0.5613 0.703 0.120 0.000 0.724 0.156
#> GSM613697 3 0.3024 0.788 0.148 0.000 0.852 0.000
#> GSM613698 3 0.3693 0.806 0.072 0.000 0.856 0.072
#> GSM613699 3 0.3498 0.777 0.160 0.000 0.832 0.008
#> GSM613700 2 0.0000 0.873 0.000 1.000 0.000 0.000
#> GSM613701 2 0.0188 0.873 0.000 0.996 0.000 0.004
#> GSM613702 2 0.0188 0.873 0.000 0.996 0.000 0.004
#> GSM613703 4 0.1209 0.895 0.032 0.004 0.000 0.964
#> GSM613704 4 0.0707 0.911 0.000 0.020 0.000 0.980
#> GSM613705 3 0.4057 0.776 0.152 0.032 0.816 0.000
#> GSM613706 2 0.3625 0.741 0.160 0.828 0.012 0.000
#> GSM613707 2 0.0336 0.872 0.000 0.992 0.000 0.008
#> GSM613708 1 0.0000 0.936 1.000 0.000 0.000 0.000
#> GSM613709 1 0.0000 0.936 1.000 0.000 0.000 0.000
#> GSM613710 2 0.2149 0.842 0.000 0.912 0.088 0.000
#> GSM613711 3 0.1022 0.852 0.000 0.032 0.968 0.000
#> GSM613712 3 0.3099 0.814 0.104 0.000 0.876 0.020
#> GSM613713 3 0.5060 0.278 0.000 0.412 0.584 0.004
#> GSM613714 3 0.0817 0.855 0.000 0.024 0.976 0.000
#> GSM613715 3 0.0469 0.857 0.000 0.000 0.988 0.012
#> GSM613716 3 0.4661 0.492 0.000 0.000 0.652 0.348
#> GSM613717 3 0.0592 0.858 0.000 0.016 0.984 0.000
#> GSM613718 3 0.0188 0.860 0.000 0.004 0.996 0.000
#> GSM613719 3 0.6187 0.646 0.144 0.000 0.672 0.184
#> GSM613720 3 0.4804 0.410 0.000 0.000 0.616 0.384
#> GSM613721 4 0.0376 0.916 0.000 0.004 0.004 0.992
#> GSM613722 2 0.0188 0.873 0.000 0.996 0.004 0.000
#> GSM613723 1 0.0188 0.934 0.996 0.000 0.004 0.000
#> GSM613724 1 0.0000 0.936 1.000 0.000 0.000 0.000
#> GSM613725 2 0.0469 0.873 0.000 0.988 0.012 0.000
#> GSM613726 1 0.0336 0.932 0.992 0.008 0.000 0.000
#> GSM613727 1 0.0000 0.936 1.000 0.000 0.000 0.000
#> GSM613728 2 0.1118 0.861 0.000 0.964 0.000 0.036
#> GSM613729 1 0.0592 0.927 0.984 0.000 0.000 0.016
#> GSM613730 2 0.4535 0.549 0.000 0.704 0.004 0.292
#> GSM613731 1 0.0000 0.936 1.000 0.000 0.000 0.000
#> GSM613732 3 0.0524 0.860 0.000 0.008 0.988 0.004
#> GSM613733 2 0.4746 0.443 0.000 0.632 0.368 0.000
#> GSM613734 1 0.0000 0.936 1.000 0.000 0.000 0.000
#> GSM613735 1 0.0000 0.936 1.000 0.000 0.000 0.000
#> GSM613736 3 0.2921 0.774 0.000 0.140 0.860 0.000
#> GSM613737 3 0.2342 0.831 0.080 0.000 0.912 0.008
#> GSM613738 1 0.1042 0.920 0.972 0.000 0.020 0.008
#> GSM613739 1 0.1557 0.895 0.944 0.000 0.056 0.000
#> GSM613740 3 0.0188 0.859 0.000 0.000 0.996 0.004
#> GSM613741 4 0.0336 0.916 0.000 0.000 0.008 0.992
#> GSM613742 1 0.4468 0.659 0.752 0.000 0.232 0.016
#> GSM613743 3 0.0707 0.856 0.000 0.020 0.980 0.000
#> GSM613744 3 0.0188 0.860 0.000 0.004 0.996 0.000
#> GSM613745 4 0.0921 0.901 0.000 0.000 0.028 0.972
#> GSM613746 4 0.0336 0.916 0.000 0.000 0.008 0.992
#> GSM613747 1 0.0000 0.936 1.000 0.000 0.000 0.000
#> GSM613748 2 0.2596 0.834 0.068 0.908 0.024 0.000
#> GSM613749 2 0.4491 0.719 0.140 0.800 0.000 0.060
#> GSM613750 3 0.0000 0.860 0.000 0.000 1.000 0.000
#> GSM613751 3 0.0188 0.860 0.000 0.004 0.996 0.000
#> GSM613752 3 0.0188 0.860 0.000 0.004 0.996 0.000
#> GSM613753 3 0.0000 0.860 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
#> GSM613638 5 0.6004 0.4310 0.256 0.168 0.000 0.000 0.576
#> GSM613639 4 0.3370 0.5604 0.144 0.004 0.016 0.832 0.004
#> GSM613640 5 0.7674 0.1949 0.028 0.316 0.100 0.072 0.484
#> GSM613641 1 0.1041 0.8672 0.964 0.004 0.000 0.032 0.000
#> GSM613642 2 0.3774 0.6100 0.000 0.804 0.008 0.028 0.160
#> GSM613643 1 0.5976 0.6323 0.676 0.056 0.004 0.080 0.184
#> GSM613644 5 0.8183 0.2346 0.140 0.012 0.128 0.300 0.420
#> GSM613645 4 0.3887 0.5415 0.148 0.040 0.008 0.804 0.000
#> GSM613646 4 0.5732 0.3318 0.072 0.000 0.428 0.496 0.004
#> GSM613647 5 0.3285 0.7197 0.048 0.004 0.076 0.008 0.864
#> GSM613648 5 0.3081 0.7035 0.000 0.000 0.156 0.012 0.832
#> GSM613649 5 0.2230 0.7206 0.000 0.000 0.116 0.000 0.884
#> GSM613650 1 0.4552 0.6862 0.760 0.000 0.040 0.024 0.176
#> GSM613651 5 0.4404 0.5582 0.252 0.000 0.036 0.000 0.712
#> GSM613652 1 0.0162 0.8684 0.996 0.000 0.004 0.000 0.000
#> GSM613653 4 0.4928 0.3677 0.012 0.000 0.408 0.568 0.012
#> GSM613654 1 0.0162 0.8684 0.996 0.000 0.004 0.000 0.000
#> GSM613655 1 0.0000 0.8688 1.000 0.000 0.000 0.000 0.000
#> GSM613656 1 0.0162 0.8684 0.996 0.000 0.004 0.000 0.000
#> GSM613657 5 0.1579 0.7274 0.000 0.032 0.024 0.000 0.944
#> GSM613658 1 0.0609 0.8693 0.980 0.000 0.000 0.020 0.000
#> GSM613659 4 0.2674 0.5914 0.000 0.012 0.120 0.868 0.000
#> GSM613660 2 0.2660 0.6290 0.000 0.864 0.000 0.008 0.128
#> GSM613661 1 0.4430 0.3238 0.540 0.004 0.000 0.456 0.000
#> GSM613662 4 0.2561 0.5998 0.000 0.000 0.144 0.856 0.000
#> GSM613663 1 0.1831 0.8538 0.920 0.004 0.000 0.076 0.000
#> GSM613664 2 0.6641 -0.1638 0.000 0.408 0.368 0.224 0.000
#> GSM613665 2 0.3112 0.6363 0.000 0.856 0.000 0.100 0.044
#> GSM613666 1 0.3966 0.7215 0.756 0.008 0.012 0.224 0.000
#> GSM613667 4 0.5344 0.1581 0.372 0.032 0.016 0.580 0.000
#> GSM613668 1 0.0290 0.8695 0.992 0.008 0.000 0.000 0.000
#> GSM613669 1 0.3715 0.7029 0.736 0.004 0.000 0.260 0.000
#> GSM613670 4 0.2020 0.6104 0.000 0.000 0.100 0.900 0.000
#> GSM613671 1 0.4434 0.2955 0.536 0.004 0.000 0.460 0.000
#> GSM613672 1 0.1205 0.8664 0.956 0.004 0.000 0.040 0.000
#> GSM613673 1 0.1211 0.8662 0.960 0.016 0.000 0.024 0.000
#> GSM613674 2 0.4625 0.3803 0.000 0.652 0.324 0.020 0.004
#> GSM613675 4 0.3031 0.6005 0.000 0.004 0.128 0.852 0.016
#> GSM613676 2 0.4404 0.5120 0.000 0.704 0.000 0.032 0.264
#> GSM613677 5 0.2910 0.7114 0.000 0.060 0.044 0.012 0.884
#> GSM613678 4 0.2824 0.5614 0.000 0.096 0.032 0.872 0.000
#> GSM613679 2 0.1670 0.6328 0.000 0.936 0.052 0.012 0.000
#> GSM613680 1 0.0992 0.8679 0.968 0.008 0.000 0.024 0.000
#> GSM613681 1 0.2249 0.8455 0.896 0.008 0.000 0.096 0.000
#> GSM613682 1 0.3740 0.7294 0.784 0.196 0.008 0.012 0.000
#> GSM613683 1 0.0162 0.8696 0.996 0.000 0.000 0.004 0.000
#> GSM613684 2 0.5408 0.1353 0.000 0.516 0.440 0.020 0.024
#> GSM613685 2 0.4518 0.3907 0.000 0.660 0.320 0.016 0.004
#> GSM613686 4 0.4580 0.4967 0.200 0.052 0.008 0.740 0.000
#> GSM613687 1 0.1408 0.8642 0.948 0.008 0.000 0.044 0.000
#> GSM613688 2 0.5789 0.2141 0.000 0.552 0.356 0.088 0.004
#> GSM613689 5 0.5799 0.3182 0.000 0.324 0.112 0.000 0.564
#> GSM613690 5 0.0963 0.7282 0.000 0.000 0.036 0.000 0.964
#> GSM613691 4 0.4225 0.4305 0.000 0.000 0.364 0.632 0.004
#> GSM613692 1 0.3888 0.7492 0.800 0.000 0.136 0.000 0.064
#> GSM613693 3 0.5422 0.5174 0.000 0.100 0.728 0.116 0.056
#> GSM613694 1 0.3912 0.7576 0.828 0.028 0.092 0.000 0.052
#> GSM613695 5 0.2555 0.7273 0.016 0.008 0.072 0.004 0.900
#> GSM613696 3 0.5919 0.4545 0.092 0.040 0.692 0.012 0.164
#> GSM613697 5 0.3891 0.6427 0.172 0.000 0.028 0.008 0.792
#> GSM613698 5 0.5602 0.4538 0.060 0.000 0.316 0.016 0.608
#> GSM613699 5 0.7101 0.3953 0.248 0.040 0.204 0.000 0.508
#> GSM613700 2 0.1300 0.6478 0.000 0.956 0.000 0.028 0.016
#> GSM613701 2 0.1901 0.6331 0.012 0.928 0.056 0.004 0.000
#> GSM613702 2 0.4217 0.5212 0.000 0.704 0.012 0.280 0.004
#> GSM613703 4 0.3124 0.6043 0.016 0.004 0.136 0.844 0.000
#> GSM613704 4 0.4227 0.4934 0.000 0.016 0.292 0.692 0.000
#> GSM613705 5 0.4099 0.6970 0.060 0.076 0.028 0.008 0.828
#> GSM613706 2 0.5184 0.5288 0.164 0.736 0.004 0.056 0.040
#> GSM613707 2 0.4735 0.3417 0.000 0.624 0.352 0.020 0.004
#> GSM613708 1 0.2230 0.8387 0.884 0.000 0.000 0.116 0.000
#> GSM613709 1 0.2439 0.8334 0.876 0.004 0.000 0.120 0.000
#> GSM613710 2 0.2741 0.6269 0.000 0.860 0.004 0.004 0.132
#> GSM613711 5 0.2376 0.7212 0.000 0.044 0.052 0.000 0.904
#> GSM613712 5 0.4676 0.6188 0.140 0.000 0.120 0.000 0.740
#> GSM613713 3 0.5557 -0.1766 0.000 0.460 0.472 0.000 0.068
#> GSM613714 5 0.2992 0.7180 0.000 0.064 0.068 0.000 0.868
#> GSM613715 5 0.1792 0.7235 0.000 0.000 0.084 0.000 0.916
#> GSM613716 5 0.5858 0.0733 0.000 0.000 0.452 0.096 0.452
#> GSM613717 5 0.3119 0.7137 0.000 0.068 0.072 0.000 0.860
#> GSM613718 5 0.0703 0.7300 0.000 0.000 0.024 0.000 0.976
#> GSM613719 5 0.7417 0.0400 0.124 0.000 0.384 0.080 0.412
#> GSM613720 3 0.6203 0.0699 0.000 0.000 0.464 0.140 0.396
#> GSM613721 3 0.5116 0.4420 0.000 0.120 0.692 0.188 0.000
#> GSM613722 2 0.2316 0.6508 0.000 0.916 0.012 0.036 0.036
#> GSM613723 1 0.0162 0.8684 0.996 0.000 0.004 0.000 0.000
#> GSM613724 1 0.0703 0.8692 0.976 0.000 0.000 0.024 0.000
#> GSM613725 2 0.1502 0.6310 0.000 0.940 0.056 0.000 0.004
#> GSM613726 1 0.4159 0.7629 0.776 0.068 0.000 0.156 0.000
#> GSM613727 1 0.0671 0.8692 0.980 0.004 0.000 0.016 0.000
#> GSM613728 2 0.3741 0.5476 0.000 0.732 0.000 0.264 0.004
#> GSM613729 1 0.3814 0.6699 0.720 0.004 0.000 0.276 0.000
#> GSM613730 4 0.5773 0.1088 0.004 0.368 0.056 0.560 0.012
#> GSM613731 1 0.6156 0.5068 0.592 0.180 0.000 0.220 0.008
#> GSM613732 5 0.1845 0.7298 0.000 0.016 0.056 0.000 0.928
#> GSM613733 2 0.5036 0.2557 0.000 0.560 0.036 0.000 0.404
#> GSM613734 1 0.0162 0.8684 0.996 0.000 0.004 0.000 0.000
#> GSM613735 1 0.0324 0.8688 0.992 0.000 0.004 0.004 0.000
#> GSM613736 5 0.6707 0.1858 0.000 0.340 0.192 0.008 0.460
#> GSM613737 5 0.4975 0.5887 0.220 0.000 0.076 0.004 0.700
#> GSM613738 1 0.1444 0.8557 0.948 0.000 0.040 0.000 0.012
#> GSM613739 1 0.2069 0.8311 0.912 0.000 0.012 0.000 0.076
#> GSM613740 5 0.4210 0.6406 0.000 0.036 0.224 0.000 0.740
#> GSM613741 4 0.4686 0.3754 0.004 0.000 0.396 0.588 0.012
#> GSM613742 1 0.3159 0.7961 0.856 0.000 0.056 0.000 0.088
#> GSM613743 5 0.4545 0.6150 0.000 0.116 0.132 0.000 0.752
#> GSM613744 5 0.1082 0.7305 0.000 0.008 0.028 0.000 0.964
#> GSM613745 4 0.5188 0.3490 0.000 0.000 0.416 0.540 0.044
#> GSM613746 3 0.4443 0.2232 0.000 0.008 0.680 0.300 0.012
#> GSM613747 1 0.0162 0.8684 0.996 0.000 0.004 0.000 0.000
#> GSM613748 2 0.6531 0.3116 0.004 0.524 0.052 0.360 0.060
#> GSM613749 2 0.5598 0.4561 0.176 0.656 0.004 0.164 0.000
#> GSM613750 5 0.2439 0.7119 0.000 0.004 0.120 0.000 0.876
#> GSM613751 5 0.2574 0.7103 0.000 0.012 0.112 0.000 0.876
#> GSM613752 5 0.3048 0.6860 0.000 0.004 0.176 0.000 0.820
#> GSM613753 5 0.2377 0.7115 0.000 0.000 0.128 0.000 0.872
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM613638 3 0.7042 0.132177 0.252 0.240 0.424 0.084 0.000 0.000
#> GSM613639 6 0.1666 0.580926 0.036 0.008 0.000 0.020 0.000 0.936
#> GSM613640 2 0.6849 0.338245 0.012 0.516 0.156 0.236 0.000 0.080
#> GSM613641 1 0.1858 0.804590 0.904 0.004 0.000 0.000 0.000 0.092
#> GSM613642 2 0.6261 0.467899 0.000 0.576 0.272 0.036 0.060 0.056
#> GSM613643 1 0.5006 0.701948 0.748 0.060 0.064 0.032 0.000 0.096
#> GSM613644 3 0.7325 -0.022776 0.076 0.016 0.384 0.332 0.000 0.192
#> GSM613645 6 0.5030 0.541871 0.064 0.072 0.000 0.120 0.012 0.732
#> GSM613646 4 0.6794 -0.188204 0.052 0.000 0.020 0.452 0.124 0.352
#> GSM613647 3 0.4749 0.429660 0.088 0.004 0.684 0.220 0.000 0.004
#> GSM613648 4 0.4773 -0.078639 0.000 0.048 0.376 0.572 0.000 0.004
#> GSM613649 3 0.3789 0.485771 0.000 0.040 0.760 0.196 0.004 0.000
#> GSM613650 1 0.7129 -0.008598 0.396 0.000 0.028 0.336 0.036 0.204
#> GSM613651 3 0.3053 0.477820 0.144 0.000 0.828 0.024 0.000 0.004
#> GSM613652 1 0.0713 0.815604 0.972 0.000 0.000 0.028 0.000 0.000
#> GSM613653 6 0.5824 0.417105 0.012 0.000 0.028 0.124 0.220 0.616
#> GSM613654 1 0.0713 0.815604 0.972 0.000 0.000 0.028 0.000 0.000
#> GSM613655 1 0.0146 0.820224 0.996 0.000 0.000 0.000 0.000 0.004
#> GSM613656 1 0.0458 0.817960 0.984 0.000 0.000 0.016 0.000 0.000
#> GSM613657 3 0.5755 0.328372 0.000 0.176 0.516 0.304 0.004 0.000
#> GSM613658 1 0.1141 0.815605 0.948 0.000 0.000 0.000 0.000 0.052
#> GSM613659 6 0.5819 0.406185 0.000 0.064 0.000 0.380 0.052 0.504
#> GSM613660 2 0.2255 0.641445 0.000 0.892 0.016 0.088 0.004 0.000
#> GSM613661 6 0.4709 -0.238496 0.480 0.012 0.004 0.016 0.000 0.488
#> GSM613662 6 0.3671 0.574753 0.000 0.024 0.000 0.068 0.092 0.816
#> GSM613663 1 0.1753 0.808360 0.912 0.004 0.000 0.000 0.000 0.084
#> GSM613664 5 0.3759 0.684513 0.000 0.216 0.000 0.008 0.752 0.024
#> GSM613665 2 0.3739 0.621268 0.000 0.832 0.016 0.044 0.044 0.064
#> GSM613666 1 0.2692 0.778860 0.840 0.000 0.000 0.000 0.012 0.148
#> GSM613667 6 0.6491 0.388859 0.260 0.080 0.000 0.120 0.004 0.536
#> GSM613668 1 0.0146 0.820224 0.996 0.000 0.000 0.000 0.000 0.004
#> GSM613669 1 0.3563 0.568296 0.664 0.000 0.000 0.000 0.000 0.336
#> GSM613670 6 0.2860 0.576727 0.000 0.012 0.000 0.068 0.052 0.868
#> GSM613671 1 0.4089 0.490022 0.616 0.004 0.000 0.004 0.004 0.372
#> GSM613672 1 0.0767 0.820815 0.976 0.004 0.000 0.012 0.000 0.008
#> GSM613673 1 0.2316 0.797979 0.900 0.064 0.000 0.028 0.004 0.004
#> GSM613674 5 0.3547 0.603365 0.000 0.332 0.000 0.000 0.668 0.000
#> GSM613675 6 0.6978 0.379458 0.000 0.072 0.192 0.168 0.032 0.536
#> GSM613676 2 0.4679 0.601723 0.000 0.736 0.168 0.040 0.008 0.048
#> GSM613677 3 0.3167 0.544934 0.000 0.080 0.852 0.040 0.000 0.028
#> GSM613678 6 0.5699 0.344505 0.000 0.252 0.000 0.156 0.016 0.576
#> GSM613679 2 0.4211 0.405348 0.000 0.720 0.000 0.024 0.232 0.024
#> GSM613680 1 0.1036 0.819367 0.964 0.004 0.000 0.024 0.000 0.008
#> GSM613681 1 0.2362 0.788073 0.860 0.004 0.000 0.000 0.000 0.136
#> GSM613682 1 0.4103 0.671148 0.764 0.092 0.000 0.000 0.136 0.008
#> GSM613683 1 0.0000 0.819619 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613684 5 0.3345 0.689540 0.000 0.204 0.000 0.020 0.776 0.000
#> GSM613685 5 0.3782 0.564674 0.000 0.360 0.000 0.004 0.636 0.000
#> GSM613686 6 0.5264 0.492215 0.172 0.072 0.000 0.048 0.012 0.696
#> GSM613687 1 0.1542 0.817624 0.936 0.004 0.000 0.008 0.000 0.052
#> GSM613688 5 0.3905 0.660023 0.000 0.260 0.004 0.004 0.716 0.016
#> GSM613689 2 0.6386 -0.103651 0.004 0.432 0.208 0.340 0.016 0.000
#> GSM613690 3 0.1950 0.587396 0.000 0.024 0.912 0.064 0.000 0.000
#> GSM613691 6 0.4849 0.465725 0.000 0.000 0.000 0.148 0.188 0.664
#> GSM613692 1 0.5091 0.233099 0.516 0.000 0.424 0.040 0.020 0.000
#> GSM613693 5 0.2511 0.649996 0.000 0.024 0.024 0.044 0.900 0.008
#> GSM613694 1 0.4622 0.420186 0.624 0.024 0.020 0.332 0.000 0.000
#> GSM613695 3 0.4477 0.401431 0.036 0.008 0.648 0.308 0.000 0.000
#> GSM613696 5 0.4245 0.580869 0.044 0.012 0.060 0.064 0.808 0.012
#> GSM613697 3 0.2510 0.544874 0.080 0.000 0.884 0.028 0.000 0.008
#> GSM613698 3 0.5452 0.275652 0.060 0.000 0.648 0.216 0.076 0.000
#> GSM613699 4 0.7601 0.195949 0.288 0.108 0.108 0.440 0.056 0.000
#> GSM613700 2 0.0972 0.635420 0.000 0.964 0.000 0.008 0.028 0.000
#> GSM613701 2 0.3252 0.561021 0.032 0.832 0.000 0.008 0.124 0.004
#> GSM613702 2 0.5183 0.550876 0.004 0.680 0.004 0.152 0.012 0.148
#> GSM613703 6 0.3679 0.552655 0.036 0.000 0.000 0.060 0.084 0.820
#> GSM613704 6 0.4915 0.483621 0.000 0.004 0.004 0.116 0.200 0.676
#> GSM613705 3 0.5310 0.429618 0.016 0.208 0.672 0.080 0.000 0.024
#> GSM613706 2 0.3974 0.579728 0.116 0.772 0.004 0.108 0.000 0.000
#> GSM613707 5 0.3563 0.596725 0.000 0.336 0.000 0.000 0.664 0.000
#> GSM613708 1 0.2219 0.790286 0.864 0.000 0.000 0.000 0.000 0.136
#> GSM613709 1 0.2996 0.713768 0.772 0.000 0.000 0.000 0.000 0.228
#> GSM613710 2 0.2507 0.636403 0.000 0.884 0.040 0.072 0.004 0.000
#> GSM613711 3 0.6100 0.261813 0.000 0.184 0.484 0.316 0.016 0.000
#> GSM613712 3 0.2780 0.515889 0.092 0.000 0.868 0.016 0.024 0.000
#> GSM613713 5 0.3502 0.692267 0.000 0.192 0.008 0.020 0.780 0.000
#> GSM613714 4 0.6133 0.103191 0.012 0.248 0.256 0.484 0.000 0.000
#> GSM613715 3 0.2494 0.585405 0.000 0.016 0.864 0.120 0.000 0.000
#> GSM613716 4 0.7366 0.120084 0.000 0.000 0.336 0.344 0.156 0.164
#> GSM613717 4 0.6109 0.045023 0.000 0.248 0.316 0.432 0.004 0.000
#> GSM613718 3 0.4245 0.516222 0.000 0.044 0.696 0.256 0.004 0.000
#> GSM613719 4 0.8444 0.074488 0.080 0.000 0.156 0.304 0.168 0.292
#> GSM613720 5 0.7234 -0.124142 0.000 0.000 0.336 0.148 0.372 0.144
#> GSM613721 5 0.1647 0.641625 0.000 0.004 0.008 0.016 0.940 0.032
#> GSM613722 2 0.2364 0.633891 0.000 0.908 0.016 0.016 0.044 0.016
#> GSM613723 1 0.0547 0.817238 0.980 0.000 0.000 0.020 0.000 0.000
#> GSM613724 1 0.1387 0.811611 0.932 0.000 0.000 0.000 0.000 0.068
#> GSM613725 2 0.2883 0.601319 0.000 0.860 0.008 0.040 0.092 0.000
#> GSM613726 1 0.3139 0.767734 0.816 0.032 0.000 0.000 0.000 0.152
#> GSM613727 1 0.1349 0.814187 0.940 0.004 0.000 0.000 0.000 0.056
#> GSM613728 2 0.5290 0.410196 0.000 0.596 0.000 0.128 0.004 0.272
#> GSM613729 1 0.4116 0.380448 0.572 0.000 0.000 0.012 0.000 0.416
#> GSM613730 6 0.5560 0.288923 0.000 0.236 0.008 0.172 0.000 0.584
#> GSM613731 1 0.6050 0.418302 0.572 0.232 0.004 0.032 0.000 0.160
#> GSM613732 3 0.2701 0.590332 0.000 0.028 0.864 0.104 0.004 0.000
#> GSM613733 2 0.5753 0.191905 0.000 0.556 0.168 0.264 0.012 0.000
#> GSM613734 1 0.0458 0.817960 0.984 0.000 0.000 0.016 0.000 0.000
#> GSM613735 1 0.0951 0.820755 0.968 0.000 0.004 0.008 0.000 0.020
#> GSM613736 4 0.6458 0.163226 0.000 0.256 0.076 0.528 0.140 0.000
#> GSM613737 4 0.6383 0.049952 0.272 0.012 0.240 0.468 0.008 0.000
#> GSM613738 1 0.3248 0.739796 0.828 0.000 0.116 0.052 0.004 0.000
#> GSM613739 1 0.4151 0.551715 0.684 0.000 0.276 0.040 0.000 0.000
#> GSM613740 3 0.6243 0.259716 0.000 0.092 0.492 0.348 0.068 0.000
#> GSM613741 6 0.4985 0.433597 0.000 0.000 0.004 0.112 0.240 0.644
#> GSM613742 1 0.5162 0.566078 0.672 0.000 0.204 0.088 0.036 0.000
#> GSM613743 4 0.6564 -0.000694 0.000 0.264 0.292 0.416 0.028 0.000
#> GSM613744 3 0.4385 0.520618 0.000 0.060 0.696 0.240 0.004 0.000
#> GSM613745 4 0.5989 -0.223975 0.000 0.000 0.016 0.464 0.148 0.372
#> GSM613746 5 0.4438 0.417895 0.000 0.000 0.024 0.076 0.744 0.156
#> GSM613747 1 0.0547 0.817533 0.980 0.000 0.000 0.020 0.000 0.000
#> GSM613748 2 0.4929 0.546254 0.000 0.684 0.016 0.108 0.000 0.192
#> GSM613749 2 0.6967 0.173633 0.260 0.480 0.000 0.040 0.028 0.192
#> GSM613750 3 0.3872 0.531342 0.000 0.004 0.712 0.264 0.020 0.000
#> GSM613751 3 0.4337 0.521736 0.000 0.012 0.684 0.272 0.032 0.000
#> GSM613752 3 0.4390 0.511916 0.000 0.004 0.676 0.272 0.048 0.000
#> GSM613753 3 0.3767 0.536681 0.000 0.004 0.708 0.276 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) k
#> SD:NMF 113 0.0272 2
#> SD:NMF 107 0.0285 3
#> SD:NMF 107 0.3383 4
#> SD:NMF 82 0.1357 5
#> SD:NMF 68 0.0117 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 27425 rows and 116 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 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 0.537 0.904 0.903 0.1478 0.933 0.933
#> 3 3 0.438 0.651 0.851 2.3689 0.531 0.497
#> 4 4 0.544 0.779 0.865 0.3603 0.720 0.469
#> 5 5 0.574 0.732 0.787 0.0923 0.932 0.786
#> 6 6 0.595 0.683 0.727 0.0576 0.955 0.826
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
#> GSM613638 1 0.2948 0.914 0.948 0.052
#> GSM613639 1 0.4939 0.897 0.892 0.108
#> GSM613640 1 0.1414 0.917 0.980 0.020
#> GSM613641 1 0.5737 0.884 0.864 0.136
#> GSM613642 1 0.1633 0.916 0.976 0.024
#> GSM613643 1 0.4022 0.907 0.920 0.080
#> GSM613644 1 0.2778 0.916 0.952 0.048
#> GSM613645 1 0.1633 0.917 0.976 0.024
#> GSM613646 1 0.0938 0.917 0.988 0.012
#> GSM613647 1 0.1184 0.916 0.984 0.016
#> GSM613648 1 0.2603 0.909 0.956 0.044
#> GSM613649 1 0.3584 0.899 0.932 0.068
#> GSM613650 1 0.3114 0.914 0.944 0.056
#> GSM613651 1 0.3114 0.913 0.944 0.056
#> GSM613652 1 0.5737 0.884 0.864 0.136
#> GSM613653 1 0.2778 0.916 0.952 0.048
#> GSM613654 1 0.5737 0.884 0.864 0.136
#> GSM613655 1 0.5737 0.884 0.864 0.136
#> GSM613656 1 0.5737 0.884 0.864 0.136
#> GSM613657 1 0.3584 0.899 0.932 0.068
#> GSM613658 1 0.5737 0.884 0.864 0.136
#> GSM613659 1 0.0672 0.916 0.992 0.008
#> GSM613660 1 0.3584 0.899 0.932 0.068
#> GSM613661 1 0.5178 0.893 0.884 0.116
#> GSM613662 1 0.3431 0.901 0.936 0.064
#> GSM613663 1 0.5737 0.884 0.864 0.136
#> GSM613664 1 0.3274 0.903 0.940 0.060
#> GSM613665 1 0.3584 0.899 0.932 0.068
#> GSM613666 1 0.5737 0.884 0.864 0.136
#> GSM613667 1 0.1633 0.917 0.976 0.024
#> GSM613668 1 0.5737 0.884 0.864 0.136
#> GSM613669 1 0.5737 0.884 0.864 0.136
#> GSM613670 1 0.3584 0.899 0.932 0.068
#> GSM613671 1 0.5737 0.884 0.864 0.136
#> GSM613672 1 0.5737 0.884 0.864 0.136
#> GSM613673 1 0.5519 0.888 0.872 0.128
#> GSM613674 1 0.3584 0.899 0.932 0.068
#> GSM613675 1 0.3584 0.899 0.932 0.068
#> GSM613676 1 0.3584 0.899 0.932 0.068
#> GSM613677 1 0.2948 0.906 0.948 0.052
#> GSM613678 1 0.0672 0.916 0.992 0.008
#> GSM613679 1 0.3584 0.899 0.932 0.068
#> GSM613680 1 0.5737 0.884 0.864 0.136
#> GSM613681 1 0.5737 0.884 0.864 0.136
#> GSM613682 1 0.5737 0.884 0.864 0.136
#> GSM613683 1 0.5737 0.884 0.864 0.136
#> GSM613684 1 0.3431 0.901 0.936 0.064
#> GSM613685 1 0.3584 0.899 0.932 0.068
#> GSM613686 1 0.5408 0.890 0.876 0.124
#> GSM613687 1 0.5737 0.884 0.864 0.136
#> GSM613688 1 0.2043 0.913 0.968 0.032
#> GSM613689 1 0.2423 0.910 0.960 0.040
#> GSM613690 1 0.2043 0.912 0.968 0.032
#> GSM613691 1 0.3274 0.903 0.940 0.060
#> GSM613692 1 0.4690 0.900 0.900 0.100
#> GSM613693 1 0.3584 0.899 0.932 0.068
#> GSM613694 1 0.2603 0.915 0.956 0.044
#> GSM613695 1 0.1414 0.917 0.980 0.020
#> GSM613696 1 0.0000 0.916 1.000 0.000
#> GSM613697 1 0.3114 0.913 0.944 0.056
#> GSM613698 1 0.2423 0.917 0.960 0.040
#> GSM613699 1 0.2236 0.917 0.964 0.036
#> GSM613700 1 0.3274 0.903 0.940 0.060
#> GSM613701 1 0.2236 0.917 0.964 0.036
#> GSM613702 1 0.1414 0.914 0.980 0.020
#> GSM613703 1 0.5737 0.884 0.864 0.136
#> GSM613704 1 0.3584 0.899 0.932 0.068
#> GSM613705 1 0.3114 0.913 0.944 0.056
#> GSM613706 1 0.2236 0.917 0.964 0.036
#> GSM613707 1 0.3584 0.899 0.932 0.068
#> GSM613708 1 0.5519 0.888 0.872 0.128
#> GSM613709 1 0.5737 0.884 0.864 0.136
#> GSM613710 1 0.3584 0.899 0.932 0.068
#> GSM613711 1 0.3584 0.899 0.932 0.068
#> GSM613712 1 0.3114 0.913 0.944 0.056
#> GSM613713 1 0.3584 0.899 0.932 0.068
#> GSM613714 1 0.1184 0.915 0.984 0.016
#> GSM613715 1 0.2603 0.909 0.956 0.044
#> GSM613716 1 0.1633 0.914 0.976 0.024
#> GSM613717 1 0.3584 0.899 0.932 0.068
#> GSM613718 1 0.3584 0.899 0.932 0.068
#> GSM613719 1 0.1633 0.918 0.976 0.024
#> GSM613720 1 0.3584 0.899 0.932 0.068
#> GSM613721 1 0.1414 0.915 0.980 0.020
#> GSM613722 1 0.3274 0.903 0.940 0.060
#> GSM613723 1 0.5737 0.884 0.864 0.136
#> GSM613724 1 0.5737 0.884 0.864 0.136
#> GSM613725 1 0.3274 0.903 0.940 0.060
#> GSM613726 1 0.4022 0.907 0.920 0.080
#> GSM613727 1 0.5737 0.884 0.864 0.136
#> GSM613728 1 0.3274 0.903 0.940 0.060
#> GSM613729 1 0.5737 0.884 0.864 0.136
#> GSM613730 1 0.2778 0.908 0.952 0.048
#> GSM613731 1 0.4022 0.907 0.920 0.080
#> GSM613732 1 0.3584 0.899 0.932 0.068
#> GSM613733 1 0.3584 0.899 0.932 0.068
#> GSM613734 1 0.5737 0.884 0.864 0.136
#> GSM613735 1 0.5737 0.884 0.864 0.136
#> GSM613736 1 0.3584 0.899 0.932 0.068
#> GSM613737 1 0.3114 0.913 0.944 0.056
#> GSM613738 1 0.5737 0.884 0.864 0.136
#> GSM613739 1 0.5737 0.884 0.864 0.136
#> GSM613740 1 0.3274 0.903 0.940 0.060
#> GSM613741 1 0.1633 0.918 0.976 0.024
#> GSM613742 1 0.5737 0.884 0.864 0.136
#> GSM613743 1 0.3584 0.899 0.932 0.068
#> GSM613744 1 0.3584 0.899 0.932 0.068
#> GSM613745 1 0.0376 0.916 0.996 0.004
#> GSM613746 1 0.3584 0.899 0.932 0.068
#> GSM613747 1 0.5737 0.884 0.864 0.136
#> GSM613748 1 0.1414 0.914 0.980 0.020
#> GSM613749 1 0.2236 0.917 0.964 0.036
#> GSM613750 2 0.5737 1.000 0.136 0.864
#> GSM613751 2 0.5737 1.000 0.136 0.864
#> GSM613752 2 0.5737 1.000 0.136 0.864
#> GSM613753 2 0.5737 1.000 0.136 0.864
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM613638 2 0.6825 -0.177 0.492 0.496 0.012
#> GSM613639 1 0.5775 0.625 0.728 0.260 0.012
#> GSM613640 1 0.6819 0.235 0.512 0.476 0.012
#> GSM613641 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613642 2 0.6082 0.499 0.296 0.692 0.012
#> GSM613643 1 0.6357 0.545 0.652 0.336 0.012
#> GSM613644 1 0.6600 0.474 0.604 0.384 0.012
#> GSM613645 1 0.6632 0.458 0.596 0.392 0.012
#> GSM613646 1 0.6745 0.375 0.560 0.428 0.012
#> GSM613647 1 0.6822 0.218 0.508 0.480 0.012
#> GSM613648 2 0.2955 0.783 0.080 0.912 0.008
#> GSM613649 2 0.1129 0.825 0.020 0.976 0.004
#> GSM613650 1 0.6566 0.486 0.612 0.376 0.012
#> GSM613651 1 0.6647 0.450 0.592 0.396 0.012
#> GSM613652 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613653 1 0.6600 0.471 0.604 0.384 0.012
#> GSM613654 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613655 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613656 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613657 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613658 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613659 2 0.5360 0.637 0.220 0.768 0.012
#> GSM613660 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613661 1 0.3293 0.732 0.900 0.088 0.012
#> GSM613662 2 0.0424 0.829 0.000 0.992 0.008
#> GSM613663 1 0.0475 0.748 0.992 0.004 0.004
#> GSM613664 2 0.0661 0.829 0.004 0.988 0.008
#> GSM613665 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613666 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613667 1 0.5072 0.672 0.792 0.196 0.012
#> GSM613668 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613669 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613670 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613671 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613672 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613673 1 0.0424 0.748 0.992 0.008 0.000
#> GSM613674 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613675 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613676 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613677 2 0.1129 0.823 0.020 0.976 0.004
#> GSM613678 2 0.5315 0.643 0.216 0.772 0.012
#> GSM613679 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613680 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613681 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613682 1 0.0237 0.748 0.996 0.004 0.000
#> GSM613683 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613684 2 0.0000 0.829 0.000 1.000 0.000
#> GSM613685 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613686 1 0.1315 0.747 0.972 0.020 0.008
#> GSM613687 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613688 2 0.4293 0.713 0.164 0.832 0.004
#> GSM613689 2 0.6822 -0.146 0.480 0.508 0.012
#> GSM613690 1 0.6825 0.180 0.496 0.492 0.012
#> GSM613691 2 0.4413 0.716 0.160 0.832 0.008
#> GSM613692 1 0.4504 0.678 0.804 0.196 0.000
#> GSM613693 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613694 1 0.6566 0.487 0.612 0.376 0.012
#> GSM613695 1 0.6763 0.357 0.552 0.436 0.012
#> GSM613696 2 0.5536 0.614 0.236 0.752 0.012
#> GSM613697 1 0.6427 0.528 0.640 0.348 0.012
#> GSM613698 1 0.6647 0.451 0.592 0.396 0.012
#> GSM613699 1 0.6754 0.366 0.556 0.432 0.012
#> GSM613700 2 0.0237 0.828 0.000 0.996 0.004
#> GSM613701 2 0.6584 0.287 0.380 0.608 0.012
#> GSM613702 2 0.6282 0.437 0.324 0.664 0.012
#> GSM613703 1 0.1182 0.747 0.976 0.012 0.012
#> GSM613704 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613705 1 0.6661 0.442 0.588 0.400 0.012
#> GSM613706 2 0.6735 0.123 0.424 0.564 0.012
#> GSM613707 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613708 1 0.4755 0.684 0.808 0.184 0.008
#> GSM613709 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613710 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613711 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613712 2 0.6825 -0.159 0.488 0.500 0.012
#> GSM613713 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613714 2 0.6713 0.140 0.416 0.572 0.012
#> GSM613715 2 0.4589 0.700 0.172 0.820 0.008
#> GSM613716 2 0.5220 0.653 0.208 0.780 0.012
#> GSM613717 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613718 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613719 1 0.6688 0.422 0.580 0.408 0.012
#> GSM613720 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613721 2 0.6548 0.299 0.372 0.616 0.012
#> GSM613722 2 0.0237 0.828 0.000 0.996 0.004
#> GSM613723 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613724 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613725 2 0.0237 0.828 0.000 0.996 0.004
#> GSM613726 1 0.5919 0.611 0.712 0.276 0.012
#> GSM613727 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613728 2 0.6102 0.456 0.320 0.672 0.008
#> GSM613729 1 0.0424 0.747 0.992 0.000 0.008
#> GSM613730 2 0.6008 0.424 0.332 0.664 0.004
#> GSM613731 1 0.6357 0.545 0.652 0.336 0.012
#> GSM613732 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613733 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613734 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613735 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613736 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613737 1 0.6448 0.524 0.636 0.352 0.012
#> GSM613738 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613739 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613740 2 0.0237 0.828 0.000 0.996 0.004
#> GSM613741 1 0.6771 0.342 0.548 0.440 0.012
#> GSM613742 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613743 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613744 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613745 1 0.6816 0.245 0.516 0.472 0.012
#> GSM613746 2 0.0237 0.830 0.000 0.996 0.004
#> GSM613747 1 0.0000 0.747 1.000 0.000 0.000
#> GSM613748 2 0.6448 0.361 0.352 0.636 0.012
#> GSM613749 1 0.6771 0.321 0.548 0.440 0.012
#> GSM613750 3 0.0592 1.000 0.000 0.012 0.988
#> GSM613751 3 0.0592 1.000 0.000 0.012 0.988
#> GSM613752 3 0.0592 1.000 0.000 0.012 0.988
#> GSM613753 3 0.0592 1.000 0.000 0.012 0.988
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 3 0.4261 0.76074 0.068 0.112 0.820 0
#> GSM613639 3 0.4428 0.65315 0.276 0.004 0.720 0
#> GSM613640 3 0.2589 0.77049 0.044 0.044 0.912 0
#> GSM613641 1 0.0921 0.93761 0.972 0.000 0.028 0
#> GSM613642 3 0.4584 0.53180 0.004 0.300 0.696 0
#> GSM613643 3 0.3636 0.75162 0.172 0.008 0.820 0
#> GSM613644 3 0.2859 0.77401 0.112 0.008 0.880 0
#> GSM613645 3 0.3249 0.77182 0.140 0.008 0.852 0
#> GSM613646 3 0.2611 0.77354 0.096 0.008 0.896 0
#> GSM613647 3 0.2411 0.76814 0.040 0.040 0.920 0
#> GSM613648 3 0.5000 -0.16867 0.000 0.500 0.500 0
#> GSM613649 2 0.4222 0.68332 0.000 0.728 0.272 0
#> GSM613650 3 0.2973 0.76666 0.144 0.000 0.856 0
#> GSM613651 3 0.2675 0.77234 0.100 0.008 0.892 0
#> GSM613652 1 0.0921 0.94459 0.972 0.000 0.028 0
#> GSM613653 3 0.2868 0.76884 0.136 0.000 0.864 0
#> GSM613654 1 0.0921 0.94459 0.972 0.000 0.028 0
#> GSM613655 1 0.0469 0.94437 0.988 0.000 0.012 0
#> GSM613656 1 0.0921 0.94459 0.972 0.000 0.028 0
#> GSM613657 2 0.2469 0.86478 0.000 0.892 0.108 0
#> GSM613658 1 0.0469 0.94437 0.988 0.000 0.012 0
#> GSM613659 2 0.5288 -0.01491 0.008 0.520 0.472 0
#> GSM613660 2 0.1867 0.87147 0.000 0.928 0.072 0
#> GSM613661 1 0.3764 0.71958 0.784 0.000 0.216 0
#> GSM613662 2 0.1211 0.86830 0.000 0.960 0.040 0
#> GSM613663 1 0.1557 0.92892 0.944 0.000 0.056 0
#> GSM613664 2 0.1637 0.86172 0.000 0.940 0.060 0
#> GSM613665 2 0.0469 0.86631 0.000 0.988 0.012 0
#> GSM613666 1 0.0817 0.93756 0.976 0.000 0.024 0
#> GSM613667 1 0.4632 0.54335 0.688 0.004 0.308 0
#> GSM613668 1 0.0469 0.94437 0.988 0.000 0.012 0
#> GSM613669 1 0.0469 0.93791 0.988 0.000 0.012 0
#> GSM613670 2 0.1118 0.86882 0.000 0.964 0.036 0
#> GSM613671 1 0.0592 0.93848 0.984 0.000 0.016 0
#> GSM613672 1 0.0469 0.94437 0.988 0.000 0.012 0
#> GSM613673 1 0.0817 0.94521 0.976 0.000 0.024 0
#> GSM613674 2 0.0469 0.85690 0.000 0.988 0.012 0
#> GSM613675 2 0.1022 0.87051 0.000 0.968 0.032 0
#> GSM613676 2 0.0592 0.86810 0.000 0.984 0.016 0
#> GSM613677 2 0.3444 0.75858 0.000 0.816 0.184 0
#> GSM613678 2 0.5285 0.00393 0.008 0.524 0.468 0
#> GSM613679 2 0.0592 0.86785 0.000 0.984 0.016 0
#> GSM613680 1 0.0469 0.94437 0.988 0.000 0.012 0
#> GSM613681 1 0.0817 0.94580 0.976 0.000 0.024 0
#> GSM613682 1 0.0921 0.94469 0.972 0.000 0.028 0
#> GSM613683 1 0.0469 0.94437 0.988 0.000 0.012 0
#> GSM613684 2 0.0707 0.86002 0.000 0.980 0.020 0
#> GSM613685 2 0.0469 0.85690 0.000 0.988 0.012 0
#> GSM613686 1 0.2149 0.89535 0.912 0.000 0.088 0
#> GSM613687 1 0.0921 0.94526 0.972 0.000 0.028 0
#> GSM613688 2 0.5220 0.18554 0.008 0.568 0.424 0
#> GSM613689 3 0.4898 0.74505 0.072 0.156 0.772 0
#> GSM613690 3 0.5031 0.75321 0.092 0.140 0.768 0
#> GSM613691 2 0.4897 0.48495 0.008 0.660 0.332 0
#> GSM613692 3 0.4817 0.47095 0.388 0.000 0.612 0
#> GSM613693 2 0.0707 0.86989 0.000 0.980 0.020 0
#> GSM613694 3 0.3257 0.76462 0.152 0.004 0.844 0
#> GSM613695 3 0.3587 0.77970 0.104 0.040 0.856 0
#> GSM613696 3 0.5150 0.30851 0.008 0.396 0.596 0
#> GSM613697 3 0.3356 0.75142 0.176 0.000 0.824 0
#> GSM613698 3 0.3812 0.77545 0.140 0.028 0.832 0
#> GSM613699 3 0.3587 0.78151 0.104 0.040 0.856 0
#> GSM613700 2 0.2281 0.87008 0.000 0.904 0.096 0
#> GSM613701 3 0.5458 0.67476 0.060 0.236 0.704 0
#> GSM613702 3 0.4927 0.62742 0.024 0.264 0.712 0
#> GSM613703 1 0.2814 0.84948 0.868 0.000 0.132 0
#> GSM613704 2 0.0817 0.86935 0.000 0.976 0.024 0
#> GSM613705 3 0.2741 0.77348 0.096 0.012 0.892 0
#> GSM613706 3 0.5392 0.71844 0.072 0.204 0.724 0
#> GSM613707 2 0.0469 0.85690 0.000 0.988 0.012 0
#> GSM613708 3 0.5088 0.36421 0.424 0.004 0.572 0
#> GSM613709 1 0.0817 0.93808 0.976 0.000 0.024 0
#> GSM613710 2 0.1867 0.87147 0.000 0.928 0.072 0
#> GSM613711 2 0.2973 0.84887 0.000 0.856 0.144 0
#> GSM613712 3 0.4261 0.75789 0.068 0.112 0.820 0
#> GSM613713 2 0.0817 0.86394 0.000 0.976 0.024 0
#> GSM613714 3 0.3335 0.74515 0.020 0.120 0.860 0
#> GSM613715 3 0.5050 0.20794 0.004 0.408 0.588 0
#> GSM613716 3 0.4872 0.34758 0.004 0.356 0.640 0
#> GSM613717 2 0.3074 0.84377 0.000 0.848 0.152 0
#> GSM613718 2 0.2973 0.84887 0.000 0.856 0.144 0
#> GSM613719 3 0.2530 0.77175 0.112 0.000 0.888 0
#> GSM613720 2 0.1118 0.87035 0.000 0.964 0.036 0
#> GSM613721 3 0.4468 0.68237 0.016 0.232 0.752 0
#> GSM613722 2 0.2345 0.86904 0.000 0.900 0.100 0
#> GSM613723 1 0.0921 0.94459 0.972 0.000 0.028 0
#> GSM613724 1 0.0817 0.94466 0.976 0.000 0.024 0
#> GSM613725 2 0.2408 0.86824 0.000 0.896 0.104 0
#> GSM613726 3 0.5310 0.43429 0.412 0.012 0.576 0
#> GSM613727 1 0.0469 0.93791 0.988 0.000 0.012 0
#> GSM613728 3 0.5482 0.44005 0.024 0.368 0.608 0
#> GSM613729 1 0.1637 0.91848 0.940 0.000 0.060 0
#> GSM613730 3 0.4955 0.61453 0.024 0.268 0.708 0
#> GSM613731 3 0.3636 0.75162 0.172 0.008 0.820 0
#> GSM613732 2 0.2973 0.84887 0.000 0.856 0.144 0
#> GSM613733 2 0.2011 0.87099 0.000 0.920 0.080 0
#> GSM613734 1 0.0921 0.94459 0.972 0.000 0.028 0
#> GSM613735 1 0.0921 0.94459 0.972 0.000 0.028 0
#> GSM613736 2 0.2973 0.84887 0.000 0.856 0.144 0
#> GSM613737 3 0.3539 0.75431 0.176 0.004 0.820 0
#> GSM613738 1 0.2469 0.88493 0.892 0.000 0.108 0
#> GSM613739 1 0.2469 0.88493 0.892 0.000 0.108 0
#> GSM613740 2 0.3219 0.83713 0.000 0.836 0.164 0
#> GSM613741 3 0.3367 0.77887 0.108 0.028 0.864 0
#> GSM613742 1 0.2469 0.88493 0.892 0.000 0.108 0
#> GSM613743 2 0.2973 0.84887 0.000 0.856 0.144 0
#> GSM613744 2 0.2973 0.84887 0.000 0.856 0.144 0
#> GSM613745 3 0.3107 0.77713 0.080 0.036 0.884 0
#> GSM613746 2 0.0469 0.85690 0.000 0.988 0.012 0
#> GSM613747 1 0.0921 0.94459 0.972 0.000 0.028 0
#> GSM613748 3 0.4464 0.67971 0.024 0.208 0.768 0
#> GSM613749 3 0.6221 0.67321 0.256 0.100 0.644 0
#> GSM613750 4 0.0000 1.00000 0.000 0.000 0.000 1
#> GSM613751 4 0.0000 1.00000 0.000 0.000 0.000 1
#> GSM613752 4 0.0000 1.00000 0.000 0.000 0.000 1
#> GSM613753 4 0.0000 1.00000 0.000 0.000 0.000 1
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM613638 4 0.4338 0.73567 0.036 0.012 0.192 0.760 0
#> GSM613639 4 0.4522 0.69184 0.192 0.004 0.060 0.744 0
#> GSM613640 4 0.3078 0.76626 0.016 0.004 0.132 0.848 0
#> GSM613641 1 0.1918 0.87744 0.928 0.000 0.036 0.036 0
#> GSM613642 4 0.5697 0.55940 0.000 0.116 0.288 0.596 0
#> GSM613643 4 0.3715 0.75912 0.108 0.004 0.064 0.824 0
#> GSM613644 4 0.3087 0.77661 0.064 0.004 0.064 0.868 0
#> GSM613645 4 0.2913 0.77325 0.080 0.004 0.040 0.876 0
#> GSM613646 4 0.2395 0.77413 0.040 0.012 0.036 0.912 0
#> GSM613647 4 0.3078 0.76539 0.016 0.004 0.132 0.848 0
#> GSM613648 3 0.5723 0.14650 0.000 0.088 0.520 0.392 0
#> GSM613649 3 0.5876 0.64826 0.000 0.204 0.604 0.192 0
#> GSM613650 4 0.2872 0.76820 0.048 0.008 0.060 0.884 0
#> GSM613651 4 0.3237 0.77522 0.048 0.000 0.104 0.848 0
#> GSM613652 1 0.2992 0.88122 0.868 0.000 0.064 0.068 0
#> GSM613653 4 0.2864 0.76956 0.044 0.008 0.064 0.884 0
#> GSM613654 1 0.2992 0.88122 0.868 0.000 0.064 0.068 0
#> GSM613655 1 0.1211 0.89660 0.960 0.000 0.016 0.024 0
#> GSM613656 1 0.2992 0.88122 0.868 0.000 0.064 0.068 0
#> GSM613657 3 0.4378 0.82615 0.000 0.248 0.716 0.036 0
#> GSM613658 1 0.1310 0.89670 0.956 0.000 0.020 0.024 0
#> GSM613659 4 0.6361 -0.04861 0.004 0.424 0.140 0.432 0
#> GSM613660 3 0.4025 0.77017 0.000 0.292 0.700 0.008 0
#> GSM613661 1 0.4342 0.68939 0.728 0.000 0.040 0.232 0
#> GSM613662 2 0.2953 0.72620 0.000 0.844 0.144 0.012 0
#> GSM613663 1 0.2300 0.88460 0.904 0.000 0.024 0.072 0
#> GSM613664 2 0.3319 0.71985 0.000 0.820 0.160 0.020 0
#> GSM613665 2 0.2966 0.70874 0.000 0.816 0.184 0.000 0
#> GSM613666 1 0.1918 0.87297 0.928 0.000 0.036 0.036 0
#> GSM613667 1 0.4565 0.56069 0.664 0.000 0.028 0.308 0
#> GSM613668 1 0.1211 0.89660 0.960 0.000 0.016 0.024 0
#> GSM613669 1 0.1106 0.88280 0.964 0.000 0.012 0.024 0
#> GSM613670 2 0.2818 0.72683 0.000 0.856 0.132 0.012 0
#> GSM613671 1 0.1750 0.87476 0.936 0.000 0.036 0.028 0
#> GSM613672 1 0.1106 0.89715 0.964 0.000 0.012 0.024 0
#> GSM613673 1 0.1484 0.89847 0.944 0.000 0.008 0.048 0
#> GSM613674 2 0.2074 0.70337 0.000 0.896 0.104 0.000 0
#> GSM613675 2 0.2843 0.72714 0.000 0.848 0.144 0.008 0
#> GSM613676 2 0.3109 0.69282 0.000 0.800 0.200 0.000 0
#> GSM613677 2 0.5699 0.53031 0.000 0.608 0.264 0.128 0
#> GSM613678 2 0.6361 -0.00774 0.004 0.428 0.140 0.428 0
#> GSM613679 2 0.2929 0.71031 0.000 0.820 0.180 0.000 0
#> GSM613680 1 0.0955 0.89763 0.968 0.000 0.004 0.028 0
#> GSM613681 1 0.1205 0.89937 0.956 0.000 0.004 0.040 0
#> GSM613682 1 0.1408 0.89880 0.948 0.000 0.008 0.044 0
#> GSM613683 1 0.1106 0.89715 0.964 0.000 0.012 0.024 0
#> GSM613684 2 0.2124 0.70719 0.000 0.900 0.096 0.004 0
#> GSM613685 2 0.2074 0.70337 0.000 0.896 0.104 0.000 0
#> GSM613686 1 0.3427 0.82633 0.844 0.004 0.056 0.096 0
#> GSM613687 1 0.1408 0.89870 0.948 0.000 0.008 0.044 0
#> GSM613688 2 0.6458 0.15614 0.004 0.464 0.160 0.372 0
#> GSM613689 4 0.4500 0.72160 0.020 0.040 0.180 0.760 0
#> GSM613690 4 0.4410 0.72727 0.028 0.032 0.168 0.772 0
#> GSM613691 2 0.6069 0.33049 0.004 0.564 0.136 0.296 0
#> GSM613692 4 0.4967 0.54372 0.280 0.000 0.060 0.660 0
#> GSM613693 2 0.3048 0.71270 0.000 0.820 0.176 0.004 0
#> GSM613694 4 0.2853 0.76730 0.072 0.000 0.052 0.876 0
#> GSM613695 4 0.2824 0.76835 0.032 0.000 0.096 0.872 0
#> GSM613696 4 0.6335 0.33045 0.004 0.284 0.176 0.536 0
#> GSM613697 4 0.2914 0.75415 0.076 0.000 0.052 0.872 0
#> GSM613698 4 0.3043 0.76900 0.056 0.000 0.080 0.864 0
#> GSM613699 4 0.3265 0.77794 0.040 0.012 0.088 0.860 0
#> GSM613700 3 0.4014 0.76810 0.000 0.256 0.728 0.016 0
#> GSM613701 4 0.5457 0.67219 0.032 0.060 0.228 0.680 0
#> GSM613702 4 0.5207 0.63523 0.008 0.064 0.264 0.664 0
#> GSM613703 1 0.3937 0.78934 0.804 0.004 0.060 0.132 0
#> GSM613704 2 0.2488 0.72623 0.000 0.872 0.124 0.004 0
#> GSM613705 4 0.3234 0.77597 0.048 0.004 0.092 0.856 0
#> GSM613706 4 0.5002 0.71354 0.036 0.044 0.192 0.728 0
#> GSM613707 2 0.2074 0.70210 0.000 0.896 0.104 0.000 0
#> GSM613708 4 0.5388 0.41564 0.360 0.004 0.056 0.580 0
#> GSM613709 1 0.1568 0.88385 0.944 0.000 0.020 0.036 0
#> GSM613710 3 0.4025 0.77017 0.000 0.292 0.700 0.008 0
#> GSM613711 3 0.4737 0.84526 0.000 0.224 0.708 0.068 0
#> GSM613712 4 0.4512 0.72993 0.040 0.012 0.204 0.744 0
#> GSM613713 2 0.4025 0.46350 0.000 0.700 0.292 0.008 0
#> GSM613714 4 0.3491 0.71450 0.000 0.004 0.228 0.768 0
#> GSM613715 4 0.5352 0.16669 0.000 0.052 0.468 0.480 0
#> GSM613716 4 0.5261 0.29660 0.000 0.048 0.424 0.528 0
#> GSM613717 3 0.4850 0.83918 0.000 0.224 0.700 0.076 0
#> GSM613718 3 0.4737 0.84526 0.000 0.224 0.708 0.068 0
#> GSM613719 4 0.2513 0.77387 0.040 0.008 0.048 0.904 0
#> GSM613720 2 0.3795 0.60559 0.000 0.780 0.192 0.028 0
#> GSM613721 4 0.4725 0.65594 0.000 0.200 0.080 0.720 0
#> GSM613722 3 0.4080 0.76723 0.000 0.252 0.728 0.020 0
#> GSM613723 1 0.2992 0.88122 0.868 0.000 0.064 0.068 0
#> GSM613724 1 0.2928 0.88174 0.872 0.000 0.064 0.064 0
#> GSM613725 3 0.4054 0.77052 0.000 0.248 0.732 0.020 0
#> GSM613726 4 0.5514 0.44433 0.364 0.008 0.056 0.572 0
#> GSM613727 1 0.1493 0.88174 0.948 0.000 0.028 0.024 0
#> GSM613728 4 0.6183 0.48213 0.008 0.272 0.148 0.572 0
#> GSM613729 1 0.2859 0.84705 0.876 0.000 0.056 0.068 0
#> GSM613730 4 0.5677 0.63178 0.008 0.156 0.180 0.656 0
#> GSM613731 4 0.3715 0.75912 0.108 0.004 0.064 0.824 0
#> GSM613732 3 0.4649 0.84582 0.000 0.220 0.716 0.064 0
#> GSM613733 3 0.3890 0.80629 0.000 0.252 0.736 0.012 0
#> GSM613734 1 0.2992 0.88122 0.868 0.000 0.064 0.068 0
#> GSM613735 1 0.2992 0.88122 0.868 0.000 0.064 0.068 0
#> GSM613736 3 0.4762 0.83947 0.000 0.236 0.700 0.064 0
#> GSM613737 4 0.3043 0.75982 0.080 0.000 0.056 0.864 0
#> GSM613738 1 0.3904 0.82081 0.792 0.000 0.052 0.156 0
#> GSM613739 1 0.3904 0.82081 0.792 0.000 0.052 0.156 0
#> GSM613740 3 0.4547 0.82980 0.000 0.192 0.736 0.072 0
#> GSM613741 4 0.3189 0.77540 0.032 0.020 0.080 0.868 0
#> GSM613742 1 0.3904 0.82081 0.792 0.000 0.052 0.156 0
#> GSM613743 3 0.4678 0.84595 0.000 0.224 0.712 0.064 0
#> GSM613744 3 0.4678 0.84595 0.000 0.224 0.712 0.064 0
#> GSM613745 4 0.2882 0.77209 0.024 0.028 0.060 0.888 0
#> GSM613746 2 0.1671 0.67742 0.000 0.924 0.076 0.000 0
#> GSM613747 1 0.2992 0.88122 0.868 0.000 0.064 0.068 0
#> GSM613748 4 0.5092 0.68474 0.008 0.092 0.192 0.708 0
#> GSM613749 4 0.6239 0.63034 0.228 0.044 0.104 0.624 0
#> GSM613750 5 0.0000 1.00000 0.000 0.000 0.000 0.000 1
#> GSM613751 5 0.0000 1.00000 0.000 0.000 0.000 0.000 1
#> GSM613752 5 0.0000 1.00000 0.000 0.000 0.000 0.000 1
#> GSM613753 5 0.0000 1.00000 0.000 0.000 0.000 0.000 1
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM613638 4 0.481 0.7250 0.012 0.040 0.152 0.736 0.060 0
#> GSM613639 4 0.496 0.7027 0.128 0.020 0.008 0.712 0.132 0
#> GSM613640 4 0.358 0.7586 0.004 0.028 0.072 0.832 0.064 0
#> GSM613641 1 0.349 0.6791 0.784 0.004 0.000 0.028 0.184 0
#> GSM613642 4 0.623 0.5537 0.000 0.168 0.216 0.560 0.056 0
#> GSM613643 4 0.425 0.7551 0.076 0.032 0.020 0.796 0.076 0
#> GSM613644 4 0.326 0.7703 0.036 0.024 0.012 0.856 0.072 0
#> GSM613645 4 0.299 0.7641 0.044 0.016 0.000 0.860 0.080 0
#> GSM613646 4 0.251 0.7615 0.024 0.024 0.000 0.892 0.060 0
#> GSM613647 4 0.370 0.7572 0.008 0.032 0.068 0.828 0.064 0
#> GSM613648 3 0.523 0.1407 0.000 0.044 0.540 0.388 0.028 0
#> GSM613649 3 0.322 0.6784 0.000 0.020 0.792 0.188 0.000 0
#> GSM613650 4 0.335 0.7598 0.040 0.020 0.000 0.832 0.108 0
#> GSM613651 4 0.415 0.7653 0.020 0.036 0.044 0.800 0.100 0
#> GSM613652 5 0.451 0.9114 0.436 0.000 0.000 0.032 0.532 0
#> GSM613653 4 0.324 0.7602 0.036 0.020 0.000 0.840 0.104 0
#> GSM613654 5 0.451 0.9114 0.436 0.000 0.000 0.032 0.532 0
#> GSM613655 1 0.262 0.5420 0.856 0.000 0.000 0.020 0.124 0
#> GSM613656 5 0.451 0.9114 0.436 0.000 0.000 0.032 0.532 0
#> GSM613657 3 0.183 0.8342 0.000 0.028 0.928 0.036 0.008 0
#> GSM613658 1 0.262 0.5262 0.856 0.000 0.000 0.020 0.124 0
#> GSM613659 2 0.595 0.0931 0.000 0.452 0.068 0.424 0.056 0
#> GSM613660 3 0.233 0.7718 0.000 0.092 0.884 0.000 0.024 0
#> GSM613661 1 0.479 0.4440 0.692 0.016 0.000 0.204 0.088 0
#> GSM613662 2 0.403 0.7011 0.000 0.736 0.220 0.012 0.032 0
#> GSM613663 1 0.241 0.6704 0.892 0.004 0.000 0.052 0.052 0
#> GSM613664 2 0.442 0.7010 0.000 0.720 0.212 0.024 0.044 0
#> GSM613665 2 0.391 0.6622 0.000 0.660 0.328 0.004 0.008 0
#> GSM613666 1 0.344 0.6802 0.784 0.004 0.000 0.024 0.188 0
#> GSM613667 1 0.452 0.3939 0.660 0.016 0.000 0.292 0.032 0
#> GSM613668 1 0.258 0.5498 0.860 0.000 0.000 0.020 0.120 0
#> GSM613669 1 0.295 0.6848 0.824 0.004 0.000 0.012 0.160 0
#> GSM613670 2 0.407 0.7024 0.000 0.732 0.224 0.016 0.028 0
#> GSM613671 1 0.328 0.6804 0.792 0.004 0.000 0.016 0.188 0
#> GSM613672 1 0.209 0.6079 0.900 0.000 0.000 0.020 0.080 0
#> GSM613673 1 0.206 0.6522 0.908 0.000 0.000 0.036 0.056 0
#> GSM613674 2 0.389 0.6703 0.000 0.752 0.188 0.000 0.060 0
#> GSM613675 2 0.380 0.7018 0.000 0.768 0.188 0.012 0.032 0
#> GSM613676 2 0.384 0.6524 0.000 0.656 0.336 0.004 0.004 0
#> GSM613677 2 0.543 0.5688 0.000 0.616 0.248 0.116 0.020 0
#> GSM613678 2 0.595 0.1086 0.000 0.456 0.068 0.420 0.056 0
#> GSM613679 2 0.376 0.6693 0.000 0.676 0.316 0.004 0.004 0
#> GSM613680 1 0.181 0.6270 0.920 0.000 0.000 0.020 0.060 0
#> GSM613681 1 0.157 0.6728 0.940 0.004 0.000 0.028 0.028 0
#> GSM613682 1 0.200 0.6638 0.912 0.000 0.000 0.040 0.048 0
#> GSM613683 1 0.209 0.6062 0.900 0.000 0.000 0.020 0.080 0
#> GSM613684 2 0.397 0.6745 0.000 0.756 0.180 0.004 0.060 0
#> GSM613685 2 0.389 0.6703 0.000 0.752 0.188 0.000 0.060 0
#> GSM613686 1 0.433 0.6264 0.700 0.004 0.000 0.056 0.240 0
#> GSM613687 1 0.155 0.6742 0.940 0.004 0.000 0.036 0.020 0
#> GSM613688 2 0.608 0.2125 0.000 0.476 0.108 0.376 0.040 0
#> GSM613689 4 0.537 0.7157 0.020 0.060 0.156 0.700 0.064 0
#> GSM613690 4 0.534 0.7184 0.028 0.044 0.128 0.712 0.088 0
#> GSM613691 2 0.608 0.4161 0.000 0.516 0.168 0.292 0.024 0
#> GSM613692 4 0.566 0.5270 0.168 0.020 0.000 0.600 0.212 0
#> GSM613693 2 0.381 0.6750 0.000 0.684 0.304 0.008 0.004 0
#> GSM613694 4 0.364 0.7622 0.048 0.008 0.020 0.824 0.100 0
#> GSM613695 4 0.399 0.7577 0.024 0.028 0.044 0.812 0.092 0
#> GSM613696 4 0.591 0.2422 0.000 0.328 0.120 0.524 0.028 0
#> GSM613697 4 0.401 0.7495 0.044 0.036 0.000 0.784 0.136 0
#> GSM613698 4 0.420 0.7611 0.040 0.024 0.028 0.792 0.116 0
#> GSM613699 4 0.406 0.7686 0.024 0.024 0.060 0.808 0.084 0
#> GSM613700 3 0.296 0.7624 0.000 0.124 0.844 0.008 0.024 0
#> GSM613701 4 0.567 0.6647 0.012 0.056 0.192 0.656 0.084 0
#> GSM613702 4 0.575 0.6341 0.008 0.076 0.208 0.640 0.068 0
#> GSM613703 1 0.508 0.5821 0.652 0.016 0.000 0.096 0.236 0
#> GSM613704 2 0.378 0.7004 0.000 0.744 0.224 0.004 0.028 0
#> GSM613705 4 0.386 0.7651 0.016 0.040 0.036 0.820 0.088 0
#> GSM613706 4 0.519 0.7025 0.012 0.052 0.156 0.708 0.072 0
#> GSM613707 2 0.395 0.6684 0.000 0.744 0.196 0.000 0.060 0
#> GSM613708 4 0.561 0.4436 0.300 0.020 0.000 0.568 0.112 0
#> GSM613709 1 0.332 0.6843 0.804 0.004 0.000 0.028 0.164 0
#> GSM613710 3 0.233 0.7718 0.000 0.092 0.884 0.000 0.024 0
#> GSM613711 3 0.147 0.8477 0.000 0.004 0.932 0.064 0.000 0
#> GSM613712 4 0.506 0.7175 0.016 0.040 0.164 0.716 0.064 0
#> GSM613713 2 0.497 0.3599 0.000 0.512 0.432 0.008 0.048 0
#> GSM613714 4 0.438 0.7089 0.000 0.028 0.172 0.744 0.056 0
#> GSM613715 4 0.538 0.1547 0.000 0.056 0.440 0.480 0.024 0
#> GSM613716 4 0.528 0.2945 0.000 0.052 0.392 0.532 0.024 0
#> GSM613717 3 0.170 0.8431 0.000 0.008 0.920 0.072 0.000 0
#> GSM613718 3 0.147 0.8477 0.000 0.004 0.932 0.064 0.000 0
#> GSM613719 4 0.284 0.7642 0.032 0.024 0.000 0.872 0.072 0
#> GSM613720 2 0.549 0.5687 0.000 0.584 0.304 0.028 0.084 0
#> GSM613721 4 0.468 0.6582 0.000 0.176 0.044 0.724 0.056 0
#> GSM613722 3 0.304 0.7592 0.000 0.132 0.836 0.008 0.024 0
#> GSM613723 5 0.451 0.9114 0.436 0.000 0.000 0.032 0.532 0
#> GSM613724 5 0.453 0.8838 0.460 0.000 0.000 0.032 0.508 0
#> GSM613725 3 0.300 0.7619 0.000 0.128 0.840 0.008 0.024 0
#> GSM613726 4 0.626 0.4687 0.248 0.032 0.004 0.536 0.180 0
#> GSM613727 1 0.323 0.6547 0.776 0.000 0.000 0.012 0.212 0
#> GSM613728 4 0.627 0.5042 0.004 0.180 0.204 0.564 0.048 0
#> GSM613729 1 0.418 0.6464 0.720 0.008 0.000 0.044 0.228 0
#> GSM613730 4 0.579 0.6284 0.004 0.128 0.160 0.644 0.064 0
#> GSM613731 4 0.425 0.7551 0.076 0.032 0.020 0.796 0.076 0
#> GSM613732 3 0.152 0.8485 0.000 0.008 0.932 0.060 0.000 0
#> GSM613733 3 0.151 0.8160 0.000 0.032 0.944 0.012 0.012 0
#> GSM613734 5 0.451 0.9096 0.440 0.000 0.000 0.032 0.528 0
#> GSM613735 5 0.452 0.9031 0.452 0.000 0.000 0.032 0.516 0
#> GSM613736 3 0.219 0.8367 0.000 0.040 0.900 0.060 0.000 0
#> GSM613737 4 0.386 0.7551 0.044 0.016 0.016 0.808 0.116 0
#> GSM613738 5 0.552 0.7792 0.440 0.008 0.000 0.100 0.452 0
#> GSM613739 5 0.552 0.7792 0.440 0.008 0.000 0.100 0.452 0
#> GSM613740 3 0.215 0.8346 0.000 0.024 0.904 0.068 0.004 0
#> GSM613741 4 0.351 0.7602 0.028 0.032 0.004 0.828 0.108 0
#> GSM613742 5 0.552 0.7792 0.440 0.008 0.000 0.100 0.452 0
#> GSM613743 3 0.141 0.8484 0.000 0.004 0.936 0.060 0.000 0
#> GSM613744 3 0.141 0.8484 0.000 0.004 0.936 0.060 0.000 0
#> GSM613745 4 0.307 0.7527 0.016 0.040 0.008 0.864 0.072 0
#> GSM613746 2 0.423 0.6357 0.000 0.732 0.168 0.000 0.100 0
#> GSM613747 5 0.451 0.9096 0.440 0.000 0.000 0.032 0.528 0
#> GSM613748 4 0.529 0.6733 0.004 0.100 0.128 0.700 0.068 0
#> GSM613749 4 0.655 0.6153 0.148 0.044 0.056 0.600 0.152 0
#> GSM613750 6 0.000 1.0000 0.000 0.000 0.000 0.000 0.000 1
#> GSM613751 6 0.000 1.0000 0.000 0.000 0.000 0.000 0.000 1
#> GSM613752 6 0.000 1.0000 0.000 0.000 0.000 0.000 0.000 1
#> GSM613753 6 0.000 1.0000 0.000 0.000 0.000 0.000 0.000 1
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) k
#> CV:hclust 116 1.24e-02 2
#> CV:hclust 86 1.13e-02 3
#> CV:hclust 104 1.03e-04 4
#> CV:hclust 104 6.66e-06 5
#> CV:hclust 103 8.91e-08 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["CV", "kmeans"]
# you can also extract it by
# res = res_list["CV:kmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 27425 rows and 116 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'CV' method.
#> Subgroups are detected by 'kmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.821 0.908 0.927 0.4652 0.498 0.498
#> 3 3 0.517 0.598 0.733 0.3851 0.718 0.491
#> 4 4 0.622 0.728 0.844 0.0947 0.933 0.809
#> 5 5 0.566 0.514 0.712 0.0746 0.955 0.859
#> 6 6 0.672 0.568 0.712 0.0620 0.839 0.495
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
#> GSM613638 1 1.000 -0.146 0.508 0.492
#> GSM613639 1 0.000 0.961 1.000 0.000
#> GSM613640 2 0.506 0.927 0.112 0.888
#> GSM613641 1 0.000 0.961 1.000 0.000
#> GSM613642 2 0.402 0.956 0.080 0.920
#> GSM613643 1 0.000 0.961 1.000 0.000
#> GSM613644 1 0.184 0.937 0.972 0.028
#> GSM613645 1 0.000 0.961 1.000 0.000
#> GSM613646 1 0.936 0.386 0.648 0.352
#> GSM613647 2 0.961 0.504 0.384 0.616
#> GSM613648 2 0.402 0.956 0.080 0.920
#> GSM613649 2 0.402 0.956 0.080 0.920
#> GSM613650 1 0.000 0.961 1.000 0.000
#> GSM613651 1 0.000 0.961 1.000 0.000
#> GSM613652 1 0.000 0.961 1.000 0.000
#> GSM613653 1 0.584 0.821 0.860 0.140
#> GSM613654 1 0.000 0.961 1.000 0.000
#> GSM613655 1 0.000 0.961 1.000 0.000
#> GSM613656 1 0.000 0.961 1.000 0.000
#> GSM613657 2 0.402 0.956 0.080 0.920
#> GSM613658 1 0.000 0.961 1.000 0.000
#> GSM613659 2 0.402 0.956 0.080 0.920
#> GSM613660 2 0.402 0.956 0.080 0.920
#> GSM613661 1 0.000 0.961 1.000 0.000
#> GSM613662 2 0.402 0.956 0.080 0.920
#> GSM613663 1 0.000 0.961 1.000 0.000
#> GSM613664 2 0.402 0.956 0.080 0.920
#> GSM613665 2 0.402 0.956 0.080 0.920
#> GSM613666 1 0.000 0.961 1.000 0.000
#> GSM613667 1 0.000 0.961 1.000 0.000
#> GSM613668 1 0.000 0.961 1.000 0.000
#> GSM613669 1 0.000 0.961 1.000 0.000
#> GSM613670 2 0.402 0.956 0.080 0.920
#> GSM613671 1 0.000 0.961 1.000 0.000
#> GSM613672 1 0.000 0.961 1.000 0.000
#> GSM613673 1 0.000 0.961 1.000 0.000
#> GSM613674 2 0.402 0.956 0.080 0.920
#> GSM613675 2 0.402 0.956 0.080 0.920
#> GSM613676 2 0.402 0.956 0.080 0.920
#> GSM613677 2 0.402 0.956 0.080 0.920
#> GSM613678 1 0.563 0.833 0.868 0.132
#> GSM613679 2 0.402 0.956 0.080 0.920
#> GSM613680 1 0.000 0.961 1.000 0.000
#> GSM613681 1 0.000 0.961 1.000 0.000
#> GSM613682 1 0.000 0.961 1.000 0.000
#> GSM613683 1 0.000 0.961 1.000 0.000
#> GSM613684 2 0.402 0.956 0.080 0.920
#> GSM613685 2 0.402 0.956 0.080 0.920
#> GSM613686 1 0.000 0.961 1.000 0.000
#> GSM613687 1 0.000 0.961 1.000 0.000
#> GSM613688 2 0.402 0.956 0.080 0.920
#> GSM613689 2 0.402 0.956 0.080 0.920
#> GSM613690 2 0.402 0.956 0.080 0.920
#> GSM613691 2 0.402 0.956 0.080 0.920
#> GSM613692 1 0.000 0.961 1.000 0.000
#> GSM613693 2 0.402 0.956 0.080 0.920
#> GSM613694 1 0.595 0.816 0.856 0.144
#> GSM613695 2 0.402 0.956 0.080 0.920
#> GSM613696 2 0.402 0.956 0.080 0.920
#> GSM613697 1 0.000 0.961 1.000 0.000
#> GSM613698 2 0.992 0.331 0.448 0.552
#> GSM613699 2 0.821 0.749 0.256 0.744
#> GSM613700 2 0.402 0.956 0.080 0.920
#> GSM613701 2 0.821 0.749 0.256 0.744
#> GSM613702 2 0.402 0.956 0.080 0.920
#> GSM613703 1 0.000 0.961 1.000 0.000
#> GSM613704 2 0.402 0.956 0.080 0.920
#> GSM613705 2 0.985 0.390 0.428 0.572
#> GSM613706 1 0.456 0.872 0.904 0.096
#> GSM613707 2 0.402 0.956 0.080 0.920
#> GSM613708 1 0.000 0.961 1.000 0.000
#> GSM613709 1 0.000 0.961 1.000 0.000
#> GSM613710 2 0.402 0.956 0.080 0.920
#> GSM613711 2 0.402 0.956 0.080 0.920
#> GSM613712 2 0.952 0.531 0.372 0.628
#> GSM613713 2 0.402 0.956 0.080 0.920
#> GSM613714 2 0.402 0.956 0.080 0.920
#> GSM613715 2 0.402 0.956 0.080 0.920
#> GSM613716 2 0.402 0.956 0.080 0.920
#> GSM613717 2 0.402 0.956 0.080 0.920
#> GSM613718 2 0.402 0.956 0.080 0.920
#> GSM613719 1 0.584 0.821 0.860 0.140
#> GSM613720 2 0.402 0.956 0.080 0.920
#> GSM613721 2 0.402 0.956 0.080 0.920
#> GSM613722 2 0.402 0.956 0.080 0.920
#> GSM613723 1 0.000 0.961 1.000 0.000
#> GSM613724 1 0.000 0.961 1.000 0.000
#> GSM613725 2 0.402 0.956 0.080 0.920
#> GSM613726 1 0.000 0.961 1.000 0.000
#> GSM613727 1 0.000 0.961 1.000 0.000
#> GSM613728 2 0.402 0.956 0.080 0.920
#> GSM613729 1 0.000 0.961 1.000 0.000
#> GSM613730 2 0.402 0.956 0.080 0.920
#> GSM613731 1 0.000 0.961 1.000 0.000
#> GSM613732 2 0.402 0.956 0.080 0.920
#> GSM613733 2 0.402 0.956 0.080 0.920
#> GSM613734 1 0.000 0.961 1.000 0.000
#> GSM613735 1 0.000 0.961 1.000 0.000
#> GSM613736 2 0.402 0.956 0.080 0.920
#> GSM613737 1 0.595 0.816 0.856 0.144
#> GSM613738 1 0.000 0.961 1.000 0.000
#> GSM613739 1 0.000 0.961 1.000 0.000
#> GSM613740 2 0.402 0.956 0.080 0.920
#> GSM613741 1 0.584 0.821 0.860 0.140
#> GSM613742 1 0.000 0.961 1.000 0.000
#> GSM613743 2 0.402 0.956 0.080 0.920
#> GSM613744 2 0.402 0.956 0.080 0.920
#> GSM613745 2 0.932 0.577 0.348 0.652
#> GSM613746 2 0.402 0.956 0.080 0.920
#> GSM613747 1 0.000 0.961 1.000 0.000
#> GSM613748 2 0.402 0.956 0.080 0.920
#> GSM613749 1 0.000 0.961 1.000 0.000
#> GSM613750 2 0.000 0.882 0.000 1.000
#> GSM613751 2 0.000 0.882 0.000 1.000
#> GSM613752 2 0.000 0.882 0.000 1.000
#> GSM613753 2 0.000 0.882 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM613638 3 0.5042 0.5884 0.060 0.104 0.836
#> GSM613639 3 0.6309 0.1015 0.496 0.000 0.504
#> GSM613640 3 0.4692 0.5491 0.012 0.168 0.820
#> GSM613641 1 0.0000 0.9306 1.000 0.000 0.000
#> GSM613642 3 0.6267 0.0219 0.000 0.452 0.548
#> GSM613643 3 0.6260 0.1978 0.448 0.000 0.552
#> GSM613644 3 0.4784 0.5854 0.200 0.004 0.796
#> GSM613645 1 0.6309 -0.1307 0.504 0.000 0.496
#> GSM613646 3 0.8464 0.5823 0.128 0.280 0.592
#> GSM613647 3 0.5085 0.5930 0.072 0.092 0.836
#> GSM613648 3 0.6180 -0.0647 0.000 0.416 0.584
#> GSM613649 2 0.6095 0.5371 0.000 0.608 0.392
#> GSM613650 3 0.6026 0.3678 0.376 0.000 0.624
#> GSM613651 3 0.4750 0.5824 0.216 0.000 0.784
#> GSM613652 1 0.1163 0.9222 0.972 0.000 0.028
#> GSM613653 3 0.8953 0.5794 0.180 0.260 0.560
#> GSM613654 1 0.1163 0.9222 0.972 0.000 0.028
#> GSM613655 1 0.0000 0.9306 1.000 0.000 0.000
#> GSM613656 1 0.1031 0.9242 0.976 0.000 0.024
#> GSM613657 2 0.5529 0.6263 0.000 0.704 0.296
#> GSM613658 1 0.0000 0.9306 1.000 0.000 0.000
#> GSM613659 2 0.6309 -0.4113 0.000 0.500 0.500
#> GSM613660 2 0.0000 0.7015 0.000 1.000 0.000
#> GSM613661 1 0.4291 0.7146 0.820 0.000 0.180
#> GSM613662 2 0.2261 0.6727 0.000 0.932 0.068
#> GSM613663 1 0.0000 0.9306 1.000 0.000 0.000
#> GSM613664 2 0.2261 0.6727 0.000 0.932 0.068
#> GSM613665 2 0.0747 0.6983 0.000 0.984 0.016
#> GSM613666 1 0.0000 0.9306 1.000 0.000 0.000
#> GSM613667 1 0.6192 0.1476 0.580 0.000 0.420
#> GSM613668 1 0.0000 0.9306 1.000 0.000 0.000
#> GSM613669 1 0.0000 0.9306 1.000 0.000 0.000
#> GSM613670 2 0.6955 -0.4112 0.016 0.496 0.488
#> GSM613671 1 0.0000 0.9306 1.000 0.000 0.000
#> GSM613672 1 0.0000 0.9306 1.000 0.000 0.000
#> GSM613673 1 0.0000 0.9306 1.000 0.000 0.000
#> GSM613674 2 0.0000 0.7015 0.000 1.000 0.000
#> GSM613675 2 0.1643 0.6886 0.000 0.956 0.044
#> GSM613676 2 0.0000 0.7015 0.000 1.000 0.000
#> GSM613677 2 0.5291 0.4044 0.000 0.732 0.268
#> GSM613678 3 0.8474 0.4869 0.092 0.404 0.504
#> GSM613679 2 0.1753 0.6858 0.000 0.952 0.048
#> GSM613680 1 0.0000 0.9306 1.000 0.000 0.000
#> GSM613681 1 0.0000 0.9306 1.000 0.000 0.000
#> GSM613682 1 0.0000 0.9306 1.000 0.000 0.000
#> GSM613683 1 0.0000 0.9306 1.000 0.000 0.000
#> GSM613684 2 0.0892 0.7023 0.000 0.980 0.020
#> GSM613685 2 0.0000 0.7015 0.000 1.000 0.000
#> GSM613686 1 0.4121 0.7333 0.832 0.000 0.168
#> GSM613687 1 0.0000 0.9306 1.000 0.000 0.000
#> GSM613688 2 0.2796 0.6463 0.000 0.908 0.092
#> GSM613689 3 0.6111 0.1401 0.000 0.396 0.604
#> GSM613690 3 0.6302 -0.2492 0.000 0.480 0.520
#> GSM613691 2 0.5363 0.2503 0.000 0.724 0.276
#> GSM613692 1 0.1163 0.9222 0.972 0.000 0.028
#> GSM613693 2 0.0000 0.7015 0.000 1.000 0.000
#> GSM613694 3 0.7676 0.6060 0.216 0.112 0.672
#> GSM613695 3 0.4702 0.4844 0.000 0.212 0.788
#> GSM613696 3 0.6305 0.3999 0.000 0.484 0.516
#> GSM613697 3 0.5905 0.3963 0.352 0.000 0.648
#> GSM613698 3 0.5060 0.5901 0.064 0.100 0.836
#> GSM613699 3 0.6470 0.5126 0.012 0.356 0.632
#> GSM613700 2 0.2625 0.6609 0.000 0.916 0.084
#> GSM613701 3 0.6950 0.4131 0.016 0.476 0.508
#> GSM613702 3 0.6680 0.4003 0.008 0.484 0.508
#> GSM613703 1 0.0424 0.9263 0.992 0.000 0.008
#> GSM613704 2 0.2261 0.6727 0.000 0.932 0.068
#> GSM613705 3 0.5067 0.5842 0.052 0.116 0.832
#> GSM613706 3 0.9231 0.5668 0.216 0.252 0.532
#> GSM613707 2 0.0000 0.7015 0.000 1.000 0.000
#> GSM613708 1 0.0592 0.9283 0.988 0.000 0.012
#> GSM613709 1 0.0000 0.9306 1.000 0.000 0.000
#> GSM613710 2 0.4555 0.6669 0.000 0.800 0.200
#> GSM613711 2 0.5560 0.6230 0.000 0.700 0.300
#> GSM613712 3 0.4994 0.5840 0.052 0.112 0.836
#> GSM613713 2 0.4842 0.6580 0.000 0.776 0.224
#> GSM613714 3 0.4291 0.5184 0.000 0.180 0.820
#> GSM613715 3 0.6204 -0.0733 0.000 0.424 0.576
#> GSM613716 3 0.5431 0.3653 0.000 0.284 0.716
#> GSM613717 2 0.5529 0.6288 0.000 0.704 0.296
#> GSM613718 2 0.5678 0.6082 0.000 0.684 0.316
#> GSM613719 3 0.6543 0.6086 0.176 0.076 0.748
#> GSM613720 2 0.5529 0.6288 0.000 0.704 0.296
#> GSM613721 3 0.6309 0.3868 0.000 0.496 0.504
#> GSM613722 2 0.2356 0.6725 0.000 0.928 0.072
#> GSM613723 1 0.1163 0.9222 0.972 0.000 0.028
#> GSM613724 1 0.0592 0.9283 0.988 0.000 0.012
#> GSM613725 2 0.1643 0.6898 0.000 0.956 0.044
#> GSM613726 1 0.6235 0.0907 0.564 0.000 0.436
#> GSM613727 1 0.0000 0.9306 1.000 0.000 0.000
#> GSM613728 2 0.2356 0.6725 0.000 0.928 0.072
#> GSM613729 1 0.0000 0.9306 1.000 0.000 0.000
#> GSM613730 3 0.6274 0.4278 0.000 0.456 0.544
#> GSM613731 3 0.6309 0.0798 0.496 0.000 0.504
#> GSM613732 2 0.5621 0.6171 0.000 0.692 0.308
#> GSM613733 2 0.4931 0.6581 0.000 0.768 0.232
#> GSM613734 1 0.0747 0.9270 0.984 0.000 0.016
#> GSM613735 1 0.1031 0.9242 0.976 0.000 0.024
#> GSM613736 2 0.5560 0.6236 0.000 0.700 0.300
#> GSM613737 3 0.5481 0.6014 0.108 0.076 0.816
#> GSM613738 1 0.1163 0.9222 0.972 0.000 0.028
#> GSM613739 1 0.1163 0.9222 0.972 0.000 0.028
#> GSM613740 2 0.5560 0.6236 0.000 0.700 0.300
#> GSM613741 3 0.8994 0.5779 0.184 0.260 0.556
#> GSM613742 1 0.1163 0.9222 0.972 0.000 0.028
#> GSM613743 2 0.5529 0.6263 0.000 0.704 0.296
#> GSM613744 2 0.5591 0.6198 0.000 0.696 0.304
#> GSM613745 3 0.8238 0.5749 0.104 0.300 0.596
#> GSM613746 2 0.0237 0.7011 0.000 0.996 0.004
#> GSM613747 1 0.0747 0.9270 0.984 0.000 0.016
#> GSM613748 3 0.6267 0.4333 0.000 0.452 0.548
#> GSM613749 3 0.9299 0.4612 0.324 0.180 0.496
#> GSM613750 2 0.6305 0.4636 0.000 0.516 0.484
#> GSM613751 2 0.6305 0.4636 0.000 0.516 0.484
#> GSM613752 2 0.6305 0.4636 0.000 0.516 0.484
#> GSM613753 3 0.6305 -0.4516 0.000 0.484 0.516
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 3 0.1209 0.781 0.000 0.004 0.964 0.032
#> GSM613639 3 0.4687 0.612 0.224 0.004 0.752 0.020
#> GSM613640 3 0.1004 0.786 0.000 0.004 0.972 0.024
#> GSM613641 1 0.0657 0.891 0.984 0.000 0.012 0.004
#> GSM613642 3 0.5279 0.620 0.000 0.232 0.716 0.052
#> GSM613643 3 0.2002 0.777 0.044 0.000 0.936 0.020
#> GSM613644 3 0.0817 0.784 0.000 0.000 0.976 0.024
#> GSM613645 3 0.5076 0.581 0.260 0.004 0.712 0.024
#> GSM613646 3 0.2828 0.784 0.020 0.032 0.912 0.036
#> GSM613647 3 0.1398 0.780 0.000 0.004 0.956 0.040
#> GSM613648 3 0.5473 0.574 0.000 0.192 0.724 0.084
#> GSM613649 2 0.6831 0.261 0.000 0.480 0.420 0.100
#> GSM613650 3 0.1356 0.783 0.032 0.000 0.960 0.008
#> GSM613651 3 0.2124 0.768 0.008 0.000 0.924 0.068
#> GSM613652 1 0.4465 0.840 0.800 0.000 0.056 0.144
#> GSM613653 3 0.2531 0.784 0.020 0.032 0.924 0.024
#> GSM613654 1 0.4541 0.837 0.796 0.000 0.060 0.144
#> GSM613655 1 0.1211 0.892 0.960 0.000 0.000 0.040
#> GSM613656 1 0.3495 0.860 0.844 0.000 0.016 0.140
#> GSM613657 2 0.6262 0.574 0.000 0.660 0.208 0.132
#> GSM613658 1 0.1389 0.890 0.952 0.000 0.000 0.048
#> GSM613659 3 0.6330 0.321 0.000 0.448 0.492 0.060
#> GSM613660 2 0.0817 0.739 0.000 0.976 0.000 0.024
#> GSM613661 1 0.3725 0.726 0.812 0.000 0.180 0.008
#> GSM613662 2 0.2399 0.718 0.000 0.920 0.032 0.048
#> GSM613663 1 0.1151 0.886 0.968 0.000 0.024 0.008
#> GSM613664 2 0.2670 0.710 0.000 0.908 0.040 0.052
#> GSM613665 2 0.0336 0.742 0.000 0.992 0.008 0.000
#> GSM613666 1 0.0657 0.891 0.984 0.000 0.012 0.004
#> GSM613667 1 0.5791 0.144 0.556 0.004 0.416 0.024
#> GSM613668 1 0.0921 0.892 0.972 0.000 0.000 0.028
#> GSM613669 1 0.0657 0.891 0.984 0.000 0.012 0.004
#> GSM613670 2 0.5520 0.423 0.000 0.696 0.244 0.060
#> GSM613671 1 0.0657 0.891 0.984 0.000 0.012 0.004
#> GSM613672 1 0.0921 0.892 0.972 0.000 0.000 0.028
#> GSM613673 1 0.1151 0.886 0.968 0.000 0.024 0.008
#> GSM613674 2 0.1118 0.736 0.000 0.964 0.000 0.036
#> GSM613675 2 0.1733 0.733 0.000 0.948 0.024 0.028
#> GSM613676 2 0.0817 0.738 0.000 0.976 0.000 0.024
#> GSM613677 3 0.5982 0.170 0.000 0.436 0.524 0.040
#> GSM613678 3 0.6956 0.552 0.048 0.296 0.604 0.052
#> GSM613679 2 0.0895 0.741 0.000 0.976 0.020 0.004
#> GSM613680 1 0.0336 0.891 0.992 0.000 0.000 0.008
#> GSM613681 1 0.0657 0.891 0.984 0.000 0.012 0.004
#> GSM613682 1 0.1042 0.888 0.972 0.000 0.020 0.008
#> GSM613683 1 0.1302 0.890 0.956 0.000 0.000 0.044
#> GSM613684 2 0.1118 0.736 0.000 0.964 0.000 0.036
#> GSM613685 2 0.1118 0.736 0.000 0.964 0.000 0.036
#> GSM613686 1 0.4277 0.715 0.800 0.004 0.172 0.024
#> GSM613687 1 0.1042 0.888 0.972 0.000 0.020 0.008
#> GSM613688 2 0.3004 0.699 0.000 0.892 0.060 0.048
#> GSM613689 3 0.5332 0.622 0.000 0.184 0.736 0.080
#> GSM613690 3 0.5859 0.548 0.000 0.156 0.704 0.140
#> GSM613691 2 0.4514 0.575 0.000 0.796 0.148 0.056
#> GSM613692 1 0.4541 0.837 0.796 0.000 0.060 0.144
#> GSM613693 2 0.0469 0.739 0.000 0.988 0.000 0.012
#> GSM613694 3 0.0895 0.786 0.020 0.000 0.976 0.004
#> GSM613695 3 0.2610 0.760 0.000 0.012 0.900 0.088
#> GSM613696 3 0.4204 0.720 0.000 0.192 0.788 0.020
#> GSM613697 3 0.3441 0.731 0.024 0.000 0.856 0.120
#> GSM613698 3 0.1489 0.780 0.000 0.004 0.952 0.044
#> GSM613699 3 0.1151 0.789 0.000 0.024 0.968 0.008
#> GSM613700 2 0.2335 0.728 0.000 0.920 0.060 0.020
#> GSM613701 3 0.5038 0.603 0.000 0.296 0.684 0.020
#> GSM613702 3 0.5366 0.616 0.000 0.276 0.684 0.040
#> GSM613703 1 0.1863 0.873 0.944 0.004 0.040 0.012
#> GSM613704 2 0.1936 0.729 0.000 0.940 0.032 0.028
#> GSM613705 3 0.1109 0.783 0.000 0.004 0.968 0.028
#> GSM613706 3 0.1786 0.783 0.036 0.008 0.948 0.008
#> GSM613707 2 0.1118 0.736 0.000 0.964 0.000 0.036
#> GSM613708 1 0.2466 0.861 0.900 0.000 0.096 0.004
#> GSM613709 1 0.0469 0.891 0.988 0.000 0.012 0.000
#> GSM613710 2 0.3731 0.690 0.000 0.844 0.036 0.120
#> GSM613711 2 0.6341 0.565 0.000 0.652 0.212 0.136
#> GSM613712 3 0.1209 0.781 0.000 0.004 0.964 0.032
#> GSM613713 2 0.4227 0.675 0.000 0.820 0.060 0.120
#> GSM613714 3 0.2329 0.763 0.000 0.012 0.916 0.072
#> GSM613715 3 0.5664 0.572 0.000 0.156 0.720 0.124
#> GSM613716 3 0.4469 0.698 0.000 0.112 0.808 0.080
#> GSM613717 2 0.6167 0.578 0.000 0.668 0.208 0.124
#> GSM613718 2 0.6465 0.540 0.000 0.636 0.228 0.136
#> GSM613719 3 0.1042 0.786 0.020 0.000 0.972 0.008
#> GSM613720 2 0.6031 0.584 0.000 0.676 0.216 0.108
#> GSM613721 3 0.5678 0.573 0.000 0.316 0.640 0.044
#> GSM613722 2 0.2002 0.737 0.000 0.936 0.044 0.020
#> GSM613723 1 0.4465 0.840 0.800 0.000 0.056 0.144
#> GSM613724 1 0.3052 0.865 0.860 0.000 0.004 0.136
#> GSM613725 2 0.1936 0.744 0.000 0.940 0.032 0.028
#> GSM613726 3 0.5751 0.196 0.448 0.004 0.528 0.020
#> GSM613727 1 0.1118 0.892 0.964 0.000 0.000 0.036
#> GSM613728 2 0.2214 0.734 0.000 0.928 0.044 0.028
#> GSM613729 1 0.0657 0.891 0.984 0.000 0.012 0.004
#> GSM613730 3 0.5030 0.704 0.000 0.188 0.752 0.060
#> GSM613731 3 0.4614 0.609 0.228 0.004 0.752 0.016
#> GSM613732 2 0.6341 0.565 0.000 0.652 0.212 0.136
#> GSM613733 2 0.5923 0.607 0.000 0.696 0.176 0.128
#> GSM613734 1 0.3052 0.865 0.860 0.000 0.004 0.136
#> GSM613735 1 0.3495 0.860 0.844 0.000 0.016 0.140
#> GSM613736 2 0.6262 0.578 0.000 0.660 0.208 0.132
#> GSM613737 3 0.0817 0.786 0.000 0.000 0.976 0.024
#> GSM613738 1 0.4491 0.838 0.800 0.000 0.060 0.140
#> GSM613739 1 0.4590 0.834 0.792 0.000 0.060 0.148
#> GSM613740 2 0.6341 0.565 0.000 0.652 0.212 0.136
#> GSM613741 3 0.3296 0.778 0.024 0.048 0.892 0.036
#> GSM613742 1 0.4686 0.835 0.788 0.000 0.068 0.144
#> GSM613743 2 0.6262 0.574 0.000 0.660 0.208 0.132
#> GSM613744 2 0.6373 0.559 0.000 0.648 0.216 0.136
#> GSM613745 3 0.3617 0.777 0.020 0.048 0.876 0.056
#> GSM613746 2 0.0817 0.736 0.000 0.976 0.000 0.024
#> GSM613747 1 0.3052 0.865 0.860 0.000 0.004 0.136
#> GSM613748 3 0.3821 0.756 0.000 0.120 0.840 0.040
#> GSM613749 3 0.6667 0.536 0.276 0.060 0.632 0.032
#> GSM613750 4 0.4462 0.975 0.000 0.164 0.044 0.792
#> GSM613751 4 0.4462 0.975 0.000 0.164 0.044 0.792
#> GSM613752 4 0.4423 0.970 0.000 0.168 0.040 0.792
#> GSM613753 4 0.4410 0.934 0.000 0.128 0.064 0.808
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM613638 4 0.2843 0.7071 0.000 0.000 0.008 0.848 0.144
#> GSM613639 4 0.4816 0.6040 0.168 0.000 0.004 0.732 0.096
#> GSM613640 4 0.1608 0.7255 0.000 0.000 0.000 0.928 0.072
#> GSM613641 1 0.0162 0.6079 0.996 0.000 0.004 0.000 0.000
#> GSM613642 4 0.5982 0.5357 0.000 0.092 0.028 0.624 0.256
#> GSM613643 4 0.2835 0.7127 0.016 0.000 0.004 0.868 0.112
#> GSM613644 4 0.2660 0.7141 0.000 0.000 0.008 0.864 0.128
#> GSM613645 4 0.5666 0.5200 0.240 0.000 0.008 0.640 0.112
#> GSM613646 4 0.3561 0.7037 0.012 0.012 0.016 0.840 0.120
#> GSM613647 4 0.2886 0.7066 0.000 0.000 0.008 0.844 0.148
#> GSM613648 4 0.7161 0.3001 0.000 0.180 0.044 0.492 0.284
#> GSM613649 2 0.7966 0.2632 0.000 0.336 0.076 0.300 0.288
#> GSM613650 4 0.2783 0.7121 0.012 0.000 0.004 0.868 0.116
#> GSM613651 4 0.2848 0.7045 0.000 0.000 0.004 0.840 0.156
#> GSM613652 1 0.5296 -0.9703 0.480 0.000 0.000 0.048 0.472
#> GSM613653 4 0.3513 0.7013 0.012 0.016 0.012 0.844 0.116
#> GSM613654 5 0.5353 0.9849 0.472 0.000 0.000 0.052 0.476
#> GSM613655 1 0.2136 0.5402 0.904 0.000 0.008 0.000 0.088
#> GSM613656 1 0.4815 -0.8322 0.524 0.000 0.000 0.020 0.456
#> GSM613657 2 0.7156 0.5307 0.000 0.528 0.104 0.096 0.272
#> GSM613658 1 0.2304 0.5213 0.892 0.000 0.008 0.000 0.100
#> GSM613659 2 0.6620 0.1334 0.000 0.536 0.020 0.280 0.164
#> GSM613660 2 0.1981 0.6523 0.000 0.920 0.016 0.000 0.064
#> GSM613661 1 0.4766 0.3396 0.708 0.000 0.000 0.220 0.072
#> GSM613662 2 0.3414 0.5832 0.000 0.844 0.020 0.020 0.116
#> GSM613663 1 0.0693 0.6035 0.980 0.000 0.000 0.008 0.012
#> GSM613664 2 0.3997 0.5564 0.000 0.800 0.020 0.028 0.152
#> GSM613665 2 0.0162 0.6484 0.000 0.996 0.000 0.000 0.004
#> GSM613666 1 0.0162 0.6079 0.996 0.000 0.004 0.000 0.000
#> GSM613667 1 0.5855 0.1595 0.552 0.000 0.004 0.348 0.096
#> GSM613668 1 0.1952 0.5460 0.912 0.000 0.004 0.000 0.084
#> GSM613669 1 0.0162 0.6079 0.996 0.000 0.004 0.000 0.000
#> GSM613670 2 0.5722 0.4091 0.000 0.672 0.020 0.144 0.164
#> GSM613671 1 0.0162 0.6079 0.996 0.000 0.004 0.000 0.000
#> GSM613672 1 0.1952 0.5460 0.912 0.000 0.004 0.000 0.084
#> GSM613673 1 0.0854 0.6045 0.976 0.000 0.004 0.008 0.012
#> GSM613674 2 0.1830 0.6412 0.000 0.932 0.028 0.000 0.040
#> GSM613675 2 0.2289 0.6180 0.000 0.904 0.012 0.004 0.080
#> GSM613676 2 0.1386 0.6502 0.000 0.952 0.016 0.000 0.032
#> GSM613677 2 0.6754 -0.0317 0.000 0.420 0.012 0.396 0.172
#> GSM613678 4 0.8294 0.3284 0.128 0.300 0.016 0.412 0.144
#> GSM613679 2 0.0955 0.6426 0.000 0.968 0.000 0.004 0.028
#> GSM613680 1 0.0865 0.5931 0.972 0.000 0.004 0.000 0.024
#> GSM613681 1 0.0000 0.6074 1.000 0.000 0.000 0.000 0.000
#> GSM613682 1 0.0854 0.6045 0.976 0.000 0.004 0.008 0.012
#> GSM613683 1 0.2179 0.5221 0.896 0.000 0.004 0.000 0.100
#> GSM613684 2 0.2209 0.6427 0.000 0.912 0.032 0.000 0.056
#> GSM613685 2 0.1830 0.6412 0.000 0.932 0.028 0.000 0.040
#> GSM613686 1 0.5177 0.3291 0.688 0.004 0.000 0.212 0.096
#> GSM613687 1 0.0693 0.6035 0.980 0.000 0.000 0.008 0.012
#> GSM613688 2 0.3675 0.5887 0.000 0.828 0.016 0.032 0.124
#> GSM613689 4 0.6919 0.3688 0.000 0.128 0.052 0.528 0.292
#> GSM613690 4 0.6706 0.4478 0.000 0.076 0.084 0.568 0.272
#> GSM613691 2 0.4774 0.5056 0.000 0.756 0.020 0.076 0.148
#> GSM613692 5 0.5296 0.9810 0.472 0.000 0.000 0.048 0.480
#> GSM613693 2 0.1571 0.6444 0.000 0.936 0.004 0.000 0.060
#> GSM613694 4 0.1357 0.7285 0.000 0.000 0.004 0.948 0.048
#> GSM613695 4 0.4665 0.6133 0.000 0.000 0.048 0.692 0.260
#> GSM613696 4 0.5359 0.4619 0.000 0.316 0.000 0.608 0.076
#> GSM613697 4 0.4375 0.5163 0.004 0.000 0.004 0.628 0.364
#> GSM613698 4 0.2886 0.7073 0.000 0.000 0.008 0.844 0.148
#> GSM613699 4 0.1717 0.7283 0.000 0.008 0.004 0.936 0.052
#> GSM613700 2 0.3277 0.6443 0.000 0.856 0.004 0.068 0.072
#> GSM613701 4 0.4778 0.6543 0.012 0.136 0.004 0.760 0.088
#> GSM613702 4 0.5356 0.6474 0.012 0.128 0.012 0.724 0.124
#> GSM613703 1 0.4612 0.3934 0.752 0.000 0.004 0.152 0.092
#> GSM613704 2 0.2507 0.6159 0.000 0.900 0.012 0.016 0.072
#> GSM613705 4 0.2536 0.7134 0.000 0.000 0.004 0.868 0.128
#> GSM613706 4 0.1892 0.7224 0.012 0.008 0.004 0.936 0.040
#> GSM613707 2 0.1981 0.6419 0.000 0.924 0.028 0.000 0.048
#> GSM613708 1 0.4170 0.3387 0.780 0.000 0.000 0.140 0.080
#> GSM613709 1 0.0162 0.6079 0.996 0.000 0.004 0.000 0.000
#> GSM613710 2 0.6287 0.5582 0.000 0.600 0.096 0.040 0.264
#> GSM613711 2 0.7492 0.5112 0.000 0.492 0.104 0.132 0.272
#> GSM613712 4 0.2843 0.7060 0.000 0.000 0.008 0.848 0.144
#> GSM613713 2 0.6585 0.5510 0.000 0.576 0.104 0.052 0.268
#> GSM613714 4 0.5200 0.5700 0.000 0.024 0.040 0.672 0.264
#> GSM613715 4 0.7229 0.3566 0.000 0.124 0.080 0.508 0.288
#> GSM613716 4 0.6559 0.5189 0.000 0.092 0.052 0.564 0.292
#> GSM613717 2 0.7284 0.5213 0.000 0.512 0.084 0.132 0.272
#> GSM613718 2 0.7637 0.4931 0.000 0.472 0.108 0.144 0.276
#> GSM613719 4 0.2517 0.7154 0.004 0.000 0.008 0.884 0.104
#> GSM613720 2 0.7406 0.5014 0.000 0.472 0.076 0.144 0.308
#> GSM613721 4 0.6061 0.5619 0.000 0.200 0.016 0.624 0.160
#> GSM613722 2 0.3081 0.6476 0.000 0.868 0.004 0.056 0.072
#> GSM613723 1 0.5296 -0.9703 0.480 0.000 0.000 0.048 0.472
#> GSM613724 1 0.4499 -0.6157 0.584 0.000 0.004 0.004 0.408
#> GSM613725 2 0.3857 0.6402 0.000 0.832 0.028 0.052 0.088
#> GSM613726 4 0.5665 0.2755 0.384 0.000 0.004 0.540 0.072
#> GSM613727 1 0.2077 0.5453 0.908 0.000 0.008 0.000 0.084
#> GSM613728 2 0.4256 0.6235 0.000 0.796 0.016 0.068 0.120
#> GSM613729 1 0.0727 0.6056 0.980 0.000 0.004 0.004 0.012
#> GSM613730 4 0.5926 0.6222 0.008 0.116 0.024 0.672 0.180
#> GSM613731 4 0.3780 0.6500 0.132 0.000 0.000 0.808 0.060
#> GSM613732 2 0.7524 0.5093 0.000 0.488 0.104 0.136 0.272
#> GSM613733 2 0.7096 0.5342 0.000 0.536 0.104 0.092 0.268
#> GSM613734 1 0.4499 -0.6157 0.584 0.000 0.004 0.004 0.408
#> GSM613735 1 0.5039 -0.8742 0.512 0.000 0.000 0.032 0.456
#> GSM613736 2 0.7526 0.5133 0.000 0.476 0.104 0.128 0.292
#> GSM613737 4 0.2124 0.7216 0.000 0.000 0.004 0.900 0.096
#> GSM613738 5 0.5352 0.9846 0.468 0.000 0.000 0.052 0.480
#> GSM613739 5 0.5353 0.9849 0.472 0.000 0.000 0.052 0.476
#> GSM613740 2 0.7473 0.5148 0.000 0.492 0.104 0.128 0.276
#> GSM613741 4 0.4034 0.6919 0.012 0.024 0.016 0.812 0.136
#> GSM613742 5 0.5405 0.9681 0.460 0.000 0.000 0.056 0.484
#> GSM613743 2 0.7459 0.5149 0.000 0.496 0.104 0.128 0.272
#> GSM613744 2 0.7524 0.5093 0.000 0.488 0.104 0.136 0.272
#> GSM613745 4 0.4231 0.6887 0.008 0.024 0.020 0.792 0.156
#> GSM613746 2 0.2407 0.6210 0.000 0.896 0.012 0.004 0.088
#> GSM613747 1 0.4499 -0.6157 0.584 0.000 0.004 0.004 0.408
#> GSM613748 4 0.3675 0.7138 0.008 0.044 0.008 0.840 0.100
#> GSM613749 4 0.6717 0.4891 0.240 0.040 0.008 0.588 0.124
#> GSM613750 3 0.0865 0.9909 0.000 0.024 0.972 0.004 0.000
#> GSM613751 3 0.1372 0.9885 0.000 0.024 0.956 0.004 0.016
#> GSM613752 3 0.0865 0.9909 0.000 0.024 0.972 0.004 0.000
#> GSM613753 3 0.1074 0.9793 0.000 0.012 0.968 0.016 0.004
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM613638 4 0.5105 0.4742 0.000 0.000 0.432 0.488 0.080 0.000
#> GSM613639 4 0.3341 0.6773 0.088 0.000 0.060 0.836 0.016 0.000
#> GSM613640 4 0.4456 0.5026 0.000 0.000 0.448 0.524 0.028 0.000
#> GSM613641 1 0.1026 0.7784 0.968 0.000 0.012 0.004 0.008 0.008
#> GSM613642 3 0.5063 0.1882 0.000 0.048 0.704 0.172 0.072 0.004
#> GSM613643 4 0.5077 0.5005 0.000 0.000 0.404 0.516 0.080 0.000
#> GSM613644 4 0.5054 0.4887 0.000 0.000 0.420 0.504 0.076 0.000
#> GSM613645 4 0.2558 0.6113 0.156 0.000 0.000 0.840 0.004 0.000
#> GSM613646 4 0.0713 0.6843 0.000 0.000 0.028 0.972 0.000 0.000
#> GSM613647 3 0.5073 -0.4598 0.000 0.000 0.476 0.448 0.076 0.000
#> GSM613648 3 0.4784 0.4829 0.000 0.088 0.748 0.080 0.080 0.004
#> GSM613649 3 0.5915 0.4731 0.000 0.212 0.612 0.040 0.128 0.008
#> GSM613650 4 0.2623 0.6917 0.000 0.000 0.132 0.852 0.016 0.000
#> GSM613651 4 0.5387 0.4488 0.000 0.000 0.424 0.464 0.112 0.000
#> GSM613652 5 0.4435 0.9279 0.364 0.000 0.004 0.028 0.604 0.000
#> GSM613653 4 0.0692 0.6825 0.000 0.000 0.020 0.976 0.004 0.000
#> GSM613654 5 0.4490 0.9254 0.360 0.000 0.004 0.032 0.604 0.000
#> GSM613655 1 0.2149 0.6902 0.888 0.000 0.004 0.000 0.104 0.004
#> GSM613656 5 0.4033 0.9096 0.404 0.000 0.004 0.004 0.588 0.000
#> GSM613657 3 0.5529 0.4457 0.000 0.344 0.536 0.004 0.112 0.004
#> GSM613658 1 0.2326 0.7011 0.888 0.000 0.012 0.000 0.092 0.008
#> GSM613659 2 0.6208 0.5220 0.000 0.540 0.060 0.280 0.120 0.000
#> GSM613660 2 0.3666 0.5814 0.000 0.812 0.080 0.016 0.092 0.000
#> GSM613661 1 0.3827 0.5105 0.680 0.000 0.004 0.308 0.008 0.000
#> GSM613662 2 0.5124 0.6368 0.000 0.680 0.028 0.176 0.116 0.000
#> GSM613663 1 0.1049 0.7764 0.960 0.000 0.000 0.032 0.008 0.000
#> GSM613664 2 0.5245 0.6361 0.000 0.668 0.028 0.172 0.132 0.000
#> GSM613665 2 0.1353 0.6900 0.000 0.952 0.012 0.012 0.024 0.000
#> GSM613666 1 0.0551 0.7806 0.984 0.000 0.008 0.004 0.000 0.004
#> GSM613667 1 0.3966 0.3024 0.552 0.000 0.000 0.444 0.004 0.000
#> GSM613668 1 0.1663 0.7075 0.912 0.000 0.000 0.000 0.088 0.000
#> GSM613669 1 0.0912 0.7794 0.972 0.000 0.012 0.004 0.004 0.008
#> GSM613670 2 0.5843 0.5626 0.000 0.588 0.044 0.252 0.116 0.000
#> GSM613671 1 0.0912 0.7794 0.972 0.000 0.012 0.004 0.004 0.008
#> GSM613672 1 0.1663 0.7075 0.912 0.000 0.000 0.000 0.088 0.000
#> GSM613673 1 0.1151 0.7767 0.956 0.000 0.000 0.032 0.012 0.000
#> GSM613674 2 0.2113 0.6760 0.000 0.896 0.008 0.000 0.092 0.004
#> GSM613675 2 0.4081 0.6906 0.000 0.784 0.032 0.064 0.120 0.000
#> GSM613676 2 0.1341 0.6751 0.000 0.948 0.028 0.000 0.024 0.000
#> GSM613677 3 0.5719 -0.1153 0.000 0.416 0.480 0.052 0.052 0.000
#> GSM613678 4 0.5237 -0.1956 0.016 0.428 0.028 0.512 0.016 0.000
#> GSM613679 2 0.1340 0.6941 0.000 0.948 0.004 0.008 0.040 0.000
#> GSM613680 1 0.0363 0.7731 0.988 0.000 0.000 0.000 0.012 0.000
#> GSM613681 1 0.0146 0.7793 0.996 0.000 0.000 0.004 0.000 0.000
#> GSM613682 1 0.1049 0.7764 0.960 0.000 0.000 0.032 0.008 0.000
#> GSM613683 1 0.1714 0.7015 0.908 0.000 0.000 0.000 0.092 0.000
#> GSM613684 2 0.1946 0.6843 0.000 0.912 0.012 0.000 0.072 0.004
#> GSM613685 2 0.2113 0.6760 0.000 0.896 0.008 0.000 0.092 0.004
#> GSM613686 1 0.3615 0.5301 0.700 0.000 0.000 0.292 0.008 0.000
#> GSM613687 1 0.1049 0.7764 0.960 0.000 0.000 0.032 0.008 0.000
#> GSM613688 2 0.5117 0.6674 0.000 0.704 0.056 0.112 0.128 0.000
#> GSM613689 3 0.3768 0.4119 0.000 0.048 0.816 0.080 0.056 0.000
#> GSM613690 3 0.2734 0.3298 0.000 0.008 0.864 0.104 0.024 0.000
#> GSM613691 2 0.5841 0.5848 0.000 0.604 0.048 0.220 0.128 0.000
#> GSM613692 5 0.4523 0.9108 0.372 0.000 0.004 0.032 0.592 0.000
#> GSM613693 2 0.2883 0.6993 0.000 0.864 0.032 0.016 0.088 0.000
#> GSM613694 4 0.4344 0.5989 0.000 0.000 0.356 0.612 0.032 0.000
#> GSM613695 3 0.3307 0.2325 0.000 0.000 0.808 0.148 0.044 0.000
#> GSM613696 2 0.6417 0.0508 0.000 0.420 0.320 0.240 0.020 0.000
#> GSM613697 3 0.6289 -0.2062 0.016 0.000 0.420 0.212 0.352 0.000
#> GSM613698 3 0.5112 -0.4082 0.000 0.000 0.516 0.400 0.084 0.000
#> GSM613699 4 0.4292 0.5751 0.000 0.000 0.388 0.588 0.024 0.000
#> GSM613700 2 0.5157 0.5634 0.000 0.700 0.060 0.100 0.140 0.000
#> GSM613701 4 0.4025 0.6873 0.000 0.040 0.124 0.788 0.048 0.000
#> GSM613702 4 0.3177 0.6692 0.000 0.024 0.072 0.852 0.052 0.000
#> GSM613703 1 0.4346 0.5205 0.664 0.000 0.012 0.304 0.012 0.008
#> GSM613704 2 0.4455 0.6849 0.000 0.752 0.028 0.096 0.124 0.000
#> GSM613705 4 0.5071 0.4662 0.000 0.000 0.444 0.480 0.076 0.000
#> GSM613706 4 0.3642 0.6803 0.000 0.000 0.204 0.760 0.036 0.000
#> GSM613707 2 0.2113 0.6760 0.000 0.896 0.008 0.000 0.092 0.004
#> GSM613708 1 0.4687 0.3328 0.668 0.000 0.008 0.256 0.068 0.000
#> GSM613709 1 0.1026 0.7784 0.968 0.000 0.012 0.004 0.008 0.008
#> GSM613710 2 0.6230 -0.3357 0.000 0.408 0.408 0.016 0.164 0.004
#> GSM613711 3 0.5853 0.4476 0.000 0.344 0.520 0.012 0.116 0.008
#> GSM613712 3 0.5115 -0.4691 0.000 0.000 0.464 0.456 0.080 0.000
#> GSM613713 3 0.6278 0.3305 0.000 0.376 0.432 0.008 0.172 0.012
#> GSM613714 3 0.2686 0.3080 0.000 0.004 0.848 0.140 0.004 0.004
#> GSM613715 3 0.3553 0.3968 0.000 0.032 0.832 0.088 0.044 0.004
#> GSM613716 3 0.6047 -0.0682 0.000 0.028 0.460 0.388 0.124 0.000
#> GSM613717 3 0.5819 0.4485 0.000 0.344 0.524 0.012 0.112 0.008
#> GSM613718 3 0.5870 0.4575 0.000 0.332 0.532 0.016 0.112 0.008
#> GSM613719 4 0.2312 0.6941 0.000 0.000 0.112 0.876 0.012 0.000
#> GSM613720 3 0.6947 0.2927 0.000 0.208 0.484 0.088 0.216 0.004
#> GSM613721 4 0.4501 0.5521 0.000 0.100 0.032 0.760 0.104 0.004
#> GSM613722 2 0.5248 0.5477 0.000 0.696 0.076 0.096 0.132 0.000
#> GSM613723 5 0.4435 0.9279 0.364 0.000 0.004 0.028 0.604 0.000
#> GSM613724 5 0.3971 0.8476 0.448 0.000 0.000 0.000 0.548 0.004
#> GSM613725 2 0.5060 0.5441 0.000 0.712 0.072 0.084 0.132 0.000
#> GSM613726 4 0.4616 0.5966 0.176 0.000 0.056 0.728 0.040 0.000
#> GSM613727 1 0.2376 0.6992 0.884 0.000 0.012 0.000 0.096 0.008
#> GSM613728 2 0.6369 0.6116 0.000 0.564 0.084 0.160 0.192 0.000
#> GSM613729 1 0.1812 0.7738 0.932 0.000 0.012 0.040 0.008 0.008
#> GSM613730 4 0.4072 0.5913 0.000 0.024 0.088 0.784 0.104 0.000
#> GSM613731 4 0.4354 0.6794 0.032 0.000 0.200 0.732 0.036 0.000
#> GSM613732 3 0.5588 0.4566 0.000 0.328 0.548 0.004 0.112 0.008
#> GSM613733 3 0.5794 0.4032 0.000 0.360 0.500 0.008 0.128 0.004
#> GSM613734 5 0.3971 0.8476 0.448 0.000 0.000 0.000 0.548 0.004
#> GSM613735 5 0.4343 0.9203 0.384 0.000 0.000 0.020 0.592 0.004
#> GSM613736 3 0.5940 0.4235 0.000 0.340 0.512 0.012 0.128 0.008
#> GSM613737 4 0.4504 0.5426 0.000 0.000 0.432 0.536 0.032 0.000
#> GSM613738 5 0.4543 0.9209 0.380 0.000 0.004 0.032 0.584 0.000
#> GSM613739 5 0.4490 0.9254 0.360 0.000 0.004 0.032 0.604 0.000
#> GSM613740 3 0.5809 0.4429 0.000 0.340 0.528 0.012 0.112 0.008
#> GSM613741 4 0.1464 0.6716 0.000 0.004 0.036 0.944 0.016 0.000
#> GSM613742 5 0.4638 0.9093 0.368 0.000 0.004 0.040 0.588 0.000
#> GSM613743 3 0.5819 0.4408 0.000 0.344 0.524 0.012 0.112 0.008
#> GSM613744 3 0.5588 0.4566 0.000 0.328 0.548 0.004 0.112 0.008
#> GSM613745 4 0.2760 0.6411 0.000 0.004 0.076 0.868 0.052 0.000
#> GSM613746 2 0.4736 0.6864 0.000 0.728 0.028 0.080 0.160 0.004
#> GSM613747 5 0.3971 0.8476 0.448 0.000 0.000 0.000 0.548 0.004
#> GSM613748 4 0.4055 0.6810 0.000 0.016 0.184 0.756 0.044 0.000
#> GSM613749 4 0.3106 0.6344 0.064 0.008 0.020 0.864 0.044 0.000
#> GSM613750 6 0.0363 1.0000 0.000 0.000 0.012 0.000 0.000 0.988
#> GSM613751 6 0.0363 1.0000 0.000 0.000 0.012 0.000 0.000 0.988
#> GSM613752 6 0.0363 1.0000 0.000 0.000 0.012 0.000 0.000 0.988
#> GSM613753 6 0.0363 1.0000 0.000 0.000 0.012 0.000 0.000 0.988
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) k
#> CV:kmeans 112 7.13e-02 2
#> CV:kmeans 85 2.12e-03 3
#> CV:kmeans 110 6.10e-05 4
#> CV:kmeans 91 2.40e-06 5
#> CV:kmeans 81 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["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 27425 rows and 116 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'CV' method.
#> Subgroups are detected by 'skmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.947 0.947 0.979 0.5046 0.496 0.496
#> 3 3 0.720 0.841 0.905 0.2968 0.755 0.545
#> 4 4 0.589 0.596 0.778 0.1233 0.900 0.720
#> 5 5 0.614 0.603 0.747 0.0606 0.929 0.756
#> 6 6 0.650 0.522 0.709 0.0417 0.907 0.645
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
#> GSM613638 1 0.904 0.5286 0.680 0.320
#> GSM613639 1 0.000 0.9724 1.000 0.000
#> GSM613640 2 0.163 0.9604 0.024 0.976
#> GSM613641 1 0.000 0.9724 1.000 0.000
#> GSM613642 2 0.000 0.9836 0.000 1.000
#> GSM613643 1 0.000 0.9724 1.000 0.000
#> GSM613644 1 0.000 0.9724 1.000 0.000
#> GSM613645 1 0.000 0.9724 1.000 0.000
#> GSM613646 1 0.163 0.9517 0.976 0.024
#> GSM613647 1 0.760 0.7150 0.780 0.220
#> GSM613648 2 0.000 0.9836 0.000 1.000
#> GSM613649 2 0.000 0.9836 0.000 1.000
#> GSM613650 1 0.000 0.9724 1.000 0.000
#> GSM613651 1 0.000 0.9724 1.000 0.000
#> GSM613652 1 0.000 0.9724 1.000 0.000
#> GSM613653 1 0.000 0.9724 1.000 0.000
#> GSM613654 1 0.000 0.9724 1.000 0.000
#> GSM613655 1 0.000 0.9724 1.000 0.000
#> GSM613656 1 0.000 0.9724 1.000 0.000
#> GSM613657 2 0.000 0.9836 0.000 1.000
#> GSM613658 1 0.000 0.9724 1.000 0.000
#> GSM613659 2 0.000 0.9836 0.000 1.000
#> GSM613660 2 0.000 0.9836 0.000 1.000
#> GSM613661 1 0.000 0.9724 1.000 0.000
#> GSM613662 2 0.000 0.9836 0.000 1.000
#> GSM613663 1 0.000 0.9724 1.000 0.000
#> GSM613664 2 0.000 0.9836 0.000 1.000
#> GSM613665 2 0.000 0.9836 0.000 1.000
#> GSM613666 1 0.000 0.9724 1.000 0.000
#> GSM613667 1 0.000 0.9724 1.000 0.000
#> GSM613668 1 0.000 0.9724 1.000 0.000
#> GSM613669 1 0.000 0.9724 1.000 0.000
#> GSM613670 2 0.000 0.9836 0.000 1.000
#> GSM613671 1 0.000 0.9724 1.000 0.000
#> GSM613672 1 0.000 0.9724 1.000 0.000
#> GSM613673 1 0.000 0.9724 1.000 0.000
#> GSM613674 2 0.000 0.9836 0.000 1.000
#> GSM613675 2 0.000 0.9836 0.000 1.000
#> GSM613676 2 0.000 0.9836 0.000 1.000
#> GSM613677 2 0.000 0.9836 0.000 1.000
#> GSM613678 1 0.141 0.9553 0.980 0.020
#> GSM613679 2 0.000 0.9836 0.000 1.000
#> GSM613680 1 0.000 0.9724 1.000 0.000
#> GSM613681 1 0.000 0.9724 1.000 0.000
#> GSM613682 1 0.000 0.9724 1.000 0.000
#> GSM613683 1 0.000 0.9724 1.000 0.000
#> GSM613684 2 0.000 0.9836 0.000 1.000
#> GSM613685 2 0.000 0.9836 0.000 1.000
#> GSM613686 1 0.000 0.9724 1.000 0.000
#> GSM613687 1 0.000 0.9724 1.000 0.000
#> GSM613688 2 0.000 0.9836 0.000 1.000
#> GSM613689 2 0.000 0.9836 0.000 1.000
#> GSM613690 2 0.000 0.9836 0.000 1.000
#> GSM613691 2 0.000 0.9836 0.000 1.000
#> GSM613692 1 0.000 0.9724 1.000 0.000
#> GSM613693 2 0.000 0.9836 0.000 1.000
#> GSM613694 1 0.000 0.9724 1.000 0.000
#> GSM613695 2 0.000 0.9836 0.000 1.000
#> GSM613696 2 0.000 0.9836 0.000 1.000
#> GSM613697 1 0.000 0.9724 1.000 0.000
#> GSM613698 1 0.552 0.8413 0.872 0.128
#> GSM613699 2 0.722 0.7413 0.200 0.800
#> GSM613700 2 0.000 0.9836 0.000 1.000
#> GSM613701 2 0.722 0.7413 0.200 0.800
#> GSM613702 2 0.000 0.9836 0.000 1.000
#> GSM613703 1 0.000 0.9724 1.000 0.000
#> GSM613704 2 0.000 0.9836 0.000 1.000
#> GSM613705 1 0.952 0.4078 0.628 0.372
#> GSM613706 1 0.000 0.9724 1.000 0.000
#> GSM613707 2 0.000 0.9836 0.000 1.000
#> GSM613708 1 0.000 0.9724 1.000 0.000
#> GSM613709 1 0.000 0.9724 1.000 0.000
#> GSM613710 2 0.000 0.9836 0.000 1.000
#> GSM613711 2 0.000 0.9836 0.000 1.000
#> GSM613712 2 0.997 0.0975 0.468 0.532
#> GSM613713 2 0.000 0.9836 0.000 1.000
#> GSM613714 2 0.000 0.9836 0.000 1.000
#> GSM613715 2 0.000 0.9836 0.000 1.000
#> GSM613716 2 0.000 0.9836 0.000 1.000
#> GSM613717 2 0.000 0.9836 0.000 1.000
#> GSM613718 2 0.000 0.9836 0.000 1.000
#> GSM613719 1 0.000 0.9724 1.000 0.000
#> GSM613720 2 0.000 0.9836 0.000 1.000
#> GSM613721 2 0.000 0.9836 0.000 1.000
#> GSM613722 2 0.000 0.9836 0.000 1.000
#> GSM613723 1 0.000 0.9724 1.000 0.000
#> GSM613724 1 0.000 0.9724 1.000 0.000
#> GSM613725 2 0.000 0.9836 0.000 1.000
#> GSM613726 1 0.000 0.9724 1.000 0.000
#> GSM613727 1 0.000 0.9724 1.000 0.000
#> GSM613728 2 0.000 0.9836 0.000 1.000
#> GSM613729 1 0.000 0.9724 1.000 0.000
#> GSM613730 2 0.000 0.9836 0.000 1.000
#> GSM613731 1 0.000 0.9724 1.000 0.000
#> GSM613732 2 0.000 0.9836 0.000 1.000
#> GSM613733 2 0.000 0.9836 0.000 1.000
#> GSM613734 1 0.000 0.9724 1.000 0.000
#> GSM613735 1 0.000 0.9724 1.000 0.000
#> GSM613736 2 0.000 0.9836 0.000 1.000
#> GSM613737 1 0.000 0.9724 1.000 0.000
#> GSM613738 1 0.000 0.9724 1.000 0.000
#> GSM613739 1 0.000 0.9724 1.000 0.000
#> GSM613740 2 0.000 0.9836 0.000 1.000
#> GSM613741 1 0.000 0.9724 1.000 0.000
#> GSM613742 1 0.000 0.9724 1.000 0.000
#> GSM613743 2 0.000 0.9836 0.000 1.000
#> GSM613744 2 0.000 0.9836 0.000 1.000
#> GSM613745 1 0.988 0.2413 0.564 0.436
#> GSM613746 2 0.000 0.9836 0.000 1.000
#> GSM613747 1 0.000 0.9724 1.000 0.000
#> GSM613748 2 0.000 0.9836 0.000 1.000
#> GSM613749 1 0.000 0.9724 1.000 0.000
#> GSM613750 2 0.000 0.9836 0.000 1.000
#> GSM613751 2 0.000 0.9836 0.000 1.000
#> GSM613752 2 0.000 0.9836 0.000 1.000
#> GSM613753 2 0.000 0.9836 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM613638 3 0.4504 0.7103 0.196 0.000 0.804
#> GSM613639 1 0.1411 0.9270 0.964 0.036 0.000
#> GSM613640 3 0.1411 0.8545 0.000 0.036 0.964
#> GSM613641 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613642 3 0.1529 0.8676 0.000 0.040 0.960
#> GSM613643 1 0.1289 0.9285 0.968 0.000 0.032
#> GSM613644 3 0.7905 0.2847 0.376 0.064 0.560
#> GSM613645 1 0.2261 0.9026 0.932 0.068 0.000
#> GSM613646 2 0.4934 0.6957 0.156 0.820 0.024
#> GSM613647 3 0.2200 0.8407 0.004 0.056 0.940
#> GSM613648 3 0.2066 0.8746 0.000 0.060 0.940
#> GSM613649 3 0.2165 0.8741 0.000 0.064 0.936
#> GSM613650 1 0.0983 0.9396 0.980 0.016 0.004
#> GSM613651 1 0.6307 0.0290 0.512 0.000 0.488
#> GSM613652 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613653 1 0.6274 0.2550 0.544 0.456 0.000
#> GSM613654 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613655 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613656 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613657 3 0.2537 0.8683 0.000 0.080 0.920
#> GSM613658 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613659 2 0.1031 0.8619 0.000 0.976 0.024
#> GSM613660 2 0.4346 0.8601 0.000 0.816 0.184
#> GSM613661 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613662 2 0.2261 0.8823 0.000 0.932 0.068
#> GSM613663 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613664 2 0.2261 0.8823 0.000 0.932 0.068
#> GSM613665 2 0.4121 0.8706 0.000 0.832 0.168
#> GSM613666 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613667 1 0.2261 0.9026 0.932 0.068 0.000
#> GSM613668 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613669 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613670 2 0.0237 0.8480 0.000 0.996 0.004
#> GSM613671 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613672 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613673 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613674 2 0.4121 0.8706 0.000 0.832 0.168
#> GSM613675 2 0.2261 0.8823 0.000 0.932 0.068
#> GSM613676 2 0.4750 0.8273 0.000 0.784 0.216
#> GSM613677 3 0.5810 0.4561 0.000 0.336 0.664
#> GSM613678 2 0.2165 0.7979 0.064 0.936 0.000
#> GSM613679 2 0.4121 0.8706 0.000 0.832 0.168
#> GSM613680 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613681 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613682 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613683 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613684 2 0.4796 0.8192 0.000 0.780 0.220
#> GSM613685 2 0.4121 0.8706 0.000 0.832 0.168
#> GSM613686 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613687 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613688 2 0.4121 0.8706 0.000 0.832 0.168
#> GSM613689 3 0.2448 0.8702 0.000 0.076 0.924
#> GSM613690 3 0.0424 0.8727 0.000 0.008 0.992
#> GSM613691 2 0.2261 0.8823 0.000 0.932 0.068
#> GSM613692 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613693 2 0.4178 0.8682 0.000 0.828 0.172
#> GSM613694 1 0.2096 0.9059 0.944 0.004 0.052
#> GSM613695 3 0.0000 0.8701 0.000 0.000 1.000
#> GSM613696 2 0.3116 0.8807 0.000 0.892 0.108
#> GSM613697 1 0.5706 0.5225 0.680 0.000 0.320
#> GSM613698 3 0.5585 0.7515 0.092 0.096 0.812
#> GSM613699 3 0.9342 0.3207 0.180 0.336 0.484
#> GSM613700 2 0.4121 0.8704 0.000 0.832 0.168
#> GSM613701 2 0.4233 0.7560 0.160 0.836 0.004
#> GSM613702 2 0.1860 0.8771 0.000 0.948 0.052
#> GSM613703 1 0.1031 0.9355 0.976 0.024 0.000
#> GSM613704 2 0.2261 0.8823 0.000 0.932 0.068
#> GSM613705 3 0.2261 0.8265 0.068 0.000 0.932
#> GSM613706 1 0.0848 0.9421 0.984 0.008 0.008
#> GSM613707 2 0.4121 0.8706 0.000 0.832 0.168
#> GSM613708 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613709 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613710 3 0.3551 0.8231 0.000 0.132 0.868
#> GSM613711 3 0.2261 0.8732 0.000 0.068 0.932
#> GSM613712 3 0.4291 0.7258 0.180 0.000 0.820
#> GSM613713 3 0.3192 0.8461 0.000 0.112 0.888
#> GSM613714 3 0.0000 0.8701 0.000 0.000 1.000
#> GSM613715 3 0.0424 0.8727 0.000 0.008 0.992
#> GSM613716 3 0.4399 0.8014 0.000 0.188 0.812
#> GSM613717 3 0.2537 0.8683 0.000 0.080 0.920
#> GSM613718 3 0.2066 0.8746 0.000 0.060 0.940
#> GSM613719 1 0.7458 0.5776 0.672 0.084 0.244
#> GSM613720 3 0.4346 0.8042 0.000 0.184 0.816
#> GSM613721 2 0.1643 0.8730 0.000 0.956 0.044
#> GSM613722 2 0.4346 0.8601 0.000 0.816 0.184
#> GSM613723 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613724 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613725 2 0.4346 0.8601 0.000 0.816 0.184
#> GSM613726 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613727 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613728 2 0.2261 0.8823 0.000 0.932 0.068
#> GSM613729 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613730 2 0.1753 0.8752 0.000 0.952 0.048
#> GSM613731 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613732 3 0.2261 0.8732 0.000 0.068 0.932
#> GSM613733 3 0.3192 0.8440 0.000 0.112 0.888
#> GSM613734 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613735 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613736 3 0.2625 0.8670 0.000 0.084 0.916
#> GSM613737 3 0.5098 0.6539 0.248 0.000 0.752
#> GSM613738 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613739 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613740 3 0.2448 0.8703 0.000 0.076 0.924
#> GSM613741 2 0.6305 -0.0992 0.484 0.516 0.000
#> GSM613742 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613743 3 0.2537 0.8683 0.000 0.080 0.920
#> GSM613744 3 0.2261 0.8732 0.000 0.068 0.932
#> GSM613745 2 0.3482 0.7455 0.128 0.872 0.000
#> GSM613746 2 0.2261 0.8823 0.000 0.932 0.068
#> GSM613747 1 0.0000 0.9502 1.000 0.000 0.000
#> GSM613748 2 0.3340 0.8734 0.000 0.880 0.120
#> GSM613749 1 0.6095 0.3337 0.608 0.392 0.000
#> GSM613750 3 0.0424 0.8727 0.000 0.008 0.992
#> GSM613751 3 0.0424 0.8727 0.000 0.008 0.992
#> GSM613752 3 0.0424 0.8727 0.000 0.008 0.992
#> GSM613753 3 0.0000 0.8701 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 4 0.4877 0.6769 0.044 0.000 0.204 0.752
#> GSM613639 1 0.5880 0.4749 0.680 0.088 0.000 0.232
#> GSM613640 4 0.4584 0.4903 0.000 0.004 0.300 0.696
#> GSM613641 1 0.0524 0.7514 0.988 0.004 0.000 0.008
#> GSM613642 3 0.4829 0.7259 0.000 0.068 0.776 0.156
#> GSM613643 4 0.4730 0.2468 0.364 0.000 0.000 0.636
#> GSM613644 4 0.4519 0.6820 0.084 0.036 0.048 0.832
#> GSM613645 1 0.6187 0.4670 0.672 0.144 0.000 0.184
#> GSM613646 2 0.7778 0.1187 0.252 0.512 0.012 0.224
#> GSM613647 4 0.3311 0.6813 0.000 0.000 0.172 0.828
#> GSM613648 3 0.1767 0.8046 0.000 0.012 0.944 0.044
#> GSM613649 3 0.0804 0.8125 0.000 0.012 0.980 0.008
#> GSM613650 4 0.6313 0.1705 0.340 0.064 0.004 0.592
#> GSM613651 4 0.4467 0.6272 0.172 0.000 0.040 0.788
#> GSM613652 1 0.4955 0.2813 0.556 0.000 0.000 0.444
#> GSM613653 2 0.7869 -0.0362 0.348 0.420 0.004 0.228
#> GSM613654 1 0.4972 0.2528 0.544 0.000 0.000 0.456
#> GSM613655 1 0.0817 0.7540 0.976 0.000 0.000 0.024
#> GSM613656 1 0.4907 0.3292 0.580 0.000 0.000 0.420
#> GSM613657 3 0.0469 0.8119 0.000 0.012 0.988 0.000
#> GSM613658 1 0.0817 0.7540 0.976 0.000 0.000 0.024
#> GSM613659 2 0.2345 0.7193 0.000 0.900 0.100 0.000
#> GSM613660 2 0.4761 0.6542 0.000 0.664 0.332 0.004
#> GSM613661 1 0.0188 0.7533 0.996 0.004 0.000 0.000
#> GSM613662 2 0.2973 0.7274 0.000 0.856 0.144 0.000
#> GSM613663 1 0.0000 0.7539 1.000 0.000 0.000 0.000
#> GSM613664 2 0.2760 0.7262 0.000 0.872 0.128 0.000
#> GSM613665 2 0.4720 0.6619 0.000 0.672 0.324 0.004
#> GSM613666 1 0.0188 0.7533 0.996 0.004 0.000 0.000
#> GSM613667 1 0.4740 0.5986 0.788 0.132 0.000 0.080
#> GSM613668 1 0.0817 0.7540 0.976 0.000 0.000 0.024
#> GSM613669 1 0.0188 0.7533 0.996 0.004 0.000 0.000
#> GSM613670 2 0.1004 0.6891 0.000 0.972 0.024 0.004
#> GSM613671 1 0.0188 0.7533 0.996 0.004 0.000 0.000
#> GSM613672 1 0.0817 0.7540 0.976 0.000 0.000 0.024
#> GSM613673 1 0.0817 0.7540 0.976 0.000 0.000 0.024
#> GSM613674 2 0.4741 0.6593 0.000 0.668 0.328 0.004
#> GSM613675 2 0.3123 0.7265 0.000 0.844 0.156 0.000
#> GSM613676 3 0.5165 -0.3184 0.000 0.484 0.512 0.004
#> GSM613677 3 0.4655 0.2780 0.000 0.312 0.684 0.004
#> GSM613678 2 0.2773 0.6101 0.072 0.900 0.000 0.028
#> GSM613679 2 0.4720 0.6619 0.000 0.672 0.324 0.004
#> GSM613680 1 0.0817 0.7540 0.976 0.000 0.000 0.024
#> GSM613681 1 0.0188 0.7533 0.996 0.004 0.000 0.000
#> GSM613682 1 0.0817 0.7540 0.976 0.000 0.000 0.024
#> GSM613683 1 0.1211 0.7489 0.960 0.000 0.000 0.040
#> GSM613684 3 0.4977 -0.2479 0.000 0.460 0.540 0.000
#> GSM613685 2 0.4741 0.6593 0.000 0.668 0.328 0.004
#> GSM613686 1 0.3071 0.6876 0.888 0.044 0.000 0.068
#> GSM613687 1 0.0336 0.7546 0.992 0.000 0.000 0.008
#> GSM613688 2 0.4655 0.6714 0.000 0.684 0.312 0.004
#> GSM613689 3 0.1209 0.8084 0.000 0.004 0.964 0.032
#> GSM613690 3 0.3311 0.7142 0.000 0.000 0.828 0.172
#> GSM613691 2 0.2973 0.7274 0.000 0.856 0.144 0.000
#> GSM613692 1 0.4941 0.2976 0.564 0.000 0.000 0.436
#> GSM613693 2 0.4989 0.3974 0.000 0.528 0.472 0.000
#> GSM613694 1 0.7305 0.0824 0.496 0.020 0.092 0.392
#> GSM613695 3 0.4406 0.5198 0.000 0.000 0.700 0.300
#> GSM613696 2 0.5607 0.2386 0.000 0.492 0.488 0.020
#> GSM613697 4 0.5152 0.4050 0.316 0.000 0.020 0.664
#> GSM613698 4 0.5662 0.6496 0.024 0.032 0.236 0.708
#> GSM613699 3 0.8076 0.4025 0.076 0.224 0.568 0.132
#> GSM613700 2 0.4770 0.6858 0.000 0.700 0.288 0.012
#> GSM613701 2 0.5136 0.6015 0.064 0.788 0.024 0.124
#> GSM613702 2 0.4542 0.6819 0.000 0.804 0.088 0.108
#> GSM613703 1 0.4992 0.5829 0.772 0.096 0.000 0.132
#> GSM613704 2 0.3157 0.7275 0.000 0.852 0.144 0.004
#> GSM613705 4 0.4164 0.5825 0.000 0.000 0.264 0.736
#> GSM613706 1 0.6597 0.2182 0.540 0.088 0.000 0.372
#> GSM613707 2 0.5004 0.5615 0.000 0.604 0.392 0.004
#> GSM613708 1 0.3448 0.6807 0.828 0.004 0.000 0.168
#> GSM613709 1 0.0376 0.7526 0.992 0.004 0.000 0.004
#> GSM613710 3 0.2654 0.7215 0.000 0.108 0.888 0.004
#> GSM613711 3 0.0524 0.8136 0.000 0.008 0.988 0.004
#> GSM613712 4 0.4599 0.6251 0.016 0.000 0.248 0.736
#> GSM613713 3 0.0817 0.8057 0.000 0.024 0.976 0.000
#> GSM613714 3 0.3764 0.6714 0.000 0.000 0.784 0.216
#> GSM613715 3 0.3400 0.7170 0.000 0.000 0.820 0.180
#> GSM613716 3 0.5111 0.6306 0.000 0.204 0.740 0.056
#> GSM613717 3 0.0804 0.8121 0.000 0.012 0.980 0.008
#> GSM613718 3 0.0336 0.8137 0.000 0.008 0.992 0.000
#> GSM613719 4 0.6225 0.4889 0.112 0.196 0.008 0.684
#> GSM613720 3 0.3196 0.7267 0.000 0.136 0.856 0.008
#> GSM613721 2 0.2908 0.6894 0.000 0.896 0.064 0.040
#> GSM613722 2 0.4877 0.6610 0.000 0.664 0.328 0.008
#> GSM613723 1 0.4941 0.2979 0.564 0.000 0.000 0.436
#> GSM613724 1 0.3074 0.6873 0.848 0.000 0.000 0.152
#> GSM613725 2 0.4857 0.6634 0.000 0.668 0.324 0.008
#> GSM613726 1 0.1576 0.7313 0.948 0.004 0.000 0.048
#> GSM613727 1 0.0336 0.7546 0.992 0.000 0.000 0.008
#> GSM613728 2 0.3448 0.7257 0.000 0.828 0.168 0.004
#> GSM613729 1 0.1398 0.7354 0.956 0.004 0.000 0.040
#> GSM613730 2 0.5555 0.6655 0.004 0.732 0.176 0.088
#> GSM613731 1 0.3801 0.6621 0.780 0.000 0.000 0.220
#> GSM613732 3 0.0336 0.8137 0.000 0.008 0.992 0.000
#> GSM613733 3 0.0779 0.8092 0.000 0.016 0.980 0.004
#> GSM613734 1 0.3610 0.6464 0.800 0.000 0.000 0.200
#> GSM613735 1 0.4925 0.3147 0.572 0.000 0.000 0.428
#> GSM613736 3 0.0469 0.8126 0.000 0.012 0.988 0.000
#> GSM613737 4 0.5954 0.6759 0.112 0.008 0.168 0.712
#> GSM613738 1 0.4933 0.3067 0.568 0.000 0.000 0.432
#> GSM613739 1 0.4941 0.2979 0.564 0.000 0.000 0.436
#> GSM613740 3 0.0336 0.8137 0.000 0.008 0.992 0.000
#> GSM613741 2 0.7401 0.0988 0.320 0.512 0.004 0.164
#> GSM613742 1 0.4933 0.3067 0.568 0.000 0.000 0.432
#> GSM613743 3 0.0336 0.8137 0.000 0.008 0.992 0.000
#> GSM613744 3 0.0336 0.8137 0.000 0.008 0.992 0.000
#> GSM613745 2 0.7741 0.2432 0.084 0.596 0.092 0.228
#> GSM613746 2 0.2973 0.7274 0.000 0.856 0.144 0.000
#> GSM613747 1 0.3486 0.6576 0.812 0.000 0.000 0.188
#> GSM613748 2 0.6049 0.6176 0.000 0.652 0.264 0.084
#> GSM613749 1 0.6845 0.3151 0.564 0.308 0.000 0.128
#> GSM613750 3 0.3266 0.7183 0.000 0.000 0.832 0.168
#> GSM613751 3 0.3266 0.7183 0.000 0.000 0.832 0.168
#> GSM613752 3 0.3266 0.7183 0.000 0.000 0.832 0.168
#> GSM613753 3 0.3444 0.6995 0.000 0.000 0.816 0.184
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM613638 5 0.5380 0.6569 0.024 0.000 0.104 0.164 0.708
#> GSM613639 4 0.5026 0.5175 0.372 0.000 0.000 0.588 0.040
#> GSM613640 5 0.6100 0.4235 0.000 0.004 0.136 0.304 0.556
#> GSM613641 1 0.0963 0.7037 0.964 0.000 0.000 0.036 0.000
#> GSM613642 3 0.6658 0.5714 0.000 0.108 0.612 0.088 0.192
#> GSM613643 5 0.5572 0.5265 0.192 0.000 0.000 0.164 0.644
#> GSM613644 5 0.4847 0.6254 0.040 0.000 0.016 0.236 0.708
#> GSM613645 4 0.4717 0.4950 0.396 0.000 0.000 0.584 0.020
#> GSM613646 4 0.3406 0.5909 0.032 0.084 0.004 0.860 0.020
#> GSM613647 5 0.5104 0.6477 0.000 0.000 0.116 0.192 0.692
#> GSM613648 3 0.3894 0.8134 0.000 0.080 0.832 0.056 0.032
#> GSM613649 3 0.3095 0.8256 0.000 0.092 0.868 0.024 0.016
#> GSM613650 4 0.5532 0.4251 0.156 0.000 0.000 0.648 0.196
#> GSM613651 5 0.4480 0.5961 0.128 0.000 0.012 0.084 0.776
#> GSM613652 1 0.4658 0.3341 0.504 0.000 0.000 0.012 0.484
#> GSM613653 4 0.4144 0.6165 0.068 0.084 0.000 0.816 0.032
#> GSM613654 1 0.4747 0.3255 0.500 0.000 0.000 0.016 0.484
#> GSM613655 1 0.0000 0.7176 1.000 0.000 0.000 0.000 0.000
#> GSM613656 1 0.4283 0.3968 0.544 0.000 0.000 0.000 0.456
#> GSM613657 3 0.1965 0.8250 0.000 0.096 0.904 0.000 0.000
#> GSM613658 1 0.0162 0.7175 0.996 0.000 0.000 0.000 0.004
#> GSM613659 2 0.1626 0.7174 0.000 0.940 0.016 0.044 0.000
#> GSM613660 2 0.4143 0.7195 0.000 0.764 0.196 0.036 0.004
#> GSM613661 1 0.0771 0.7079 0.976 0.000 0.000 0.020 0.004
#> GSM613662 2 0.0807 0.7355 0.000 0.976 0.012 0.012 0.000
#> GSM613663 1 0.0404 0.7142 0.988 0.000 0.000 0.012 0.000
#> GSM613664 2 0.0613 0.7358 0.000 0.984 0.004 0.008 0.004
#> GSM613665 2 0.2886 0.7462 0.000 0.844 0.148 0.008 0.000
#> GSM613666 1 0.0510 0.7125 0.984 0.000 0.000 0.016 0.000
#> GSM613667 1 0.3730 0.2818 0.712 0.000 0.000 0.288 0.000
#> GSM613668 1 0.0000 0.7176 1.000 0.000 0.000 0.000 0.000
#> GSM613669 1 0.0510 0.7125 0.984 0.000 0.000 0.016 0.000
#> GSM613670 2 0.2424 0.6560 0.000 0.868 0.000 0.132 0.000
#> GSM613671 1 0.0510 0.7125 0.984 0.000 0.000 0.016 0.000
#> GSM613672 1 0.0000 0.7176 1.000 0.000 0.000 0.000 0.000
#> GSM613673 1 0.0000 0.7176 1.000 0.000 0.000 0.000 0.000
#> GSM613674 2 0.2865 0.7472 0.000 0.856 0.132 0.008 0.004
#> GSM613675 2 0.0992 0.7399 0.000 0.968 0.024 0.008 0.000
#> GSM613676 2 0.3480 0.6824 0.000 0.752 0.248 0.000 0.000
#> GSM613677 2 0.4886 0.1789 0.000 0.512 0.468 0.004 0.016
#> GSM613678 2 0.5867 0.2696 0.180 0.604 0.000 0.216 0.000
#> GSM613679 2 0.2865 0.7494 0.000 0.856 0.132 0.008 0.004
#> GSM613680 1 0.0000 0.7176 1.000 0.000 0.000 0.000 0.000
#> GSM613681 1 0.0510 0.7125 0.984 0.000 0.000 0.016 0.000
#> GSM613682 1 0.0000 0.7176 1.000 0.000 0.000 0.000 0.000
#> GSM613683 1 0.0609 0.7153 0.980 0.000 0.000 0.000 0.020
#> GSM613684 2 0.4299 0.5880 0.000 0.672 0.316 0.004 0.008
#> GSM613685 2 0.2865 0.7472 0.000 0.856 0.132 0.008 0.004
#> GSM613686 1 0.2674 0.5725 0.856 0.000 0.000 0.140 0.004
#> GSM613687 1 0.0290 0.7155 0.992 0.000 0.000 0.008 0.000
#> GSM613688 2 0.2179 0.7540 0.000 0.896 0.100 0.000 0.004
#> GSM613689 3 0.2674 0.8206 0.000 0.060 0.896 0.012 0.032
#> GSM613690 3 0.3369 0.7667 0.000 0.024 0.856 0.028 0.092
#> GSM613691 2 0.1386 0.7332 0.000 0.952 0.016 0.032 0.000
#> GSM613692 1 0.4304 0.3476 0.516 0.000 0.000 0.000 0.484
#> GSM613693 2 0.3336 0.6818 0.000 0.772 0.228 0.000 0.000
#> GSM613694 1 0.7506 0.1230 0.452 0.000 0.060 0.200 0.288
#> GSM613695 3 0.4576 0.5567 0.000 0.000 0.692 0.040 0.268
#> GSM613696 2 0.4572 0.6400 0.000 0.708 0.256 0.024 0.012
#> GSM613697 5 0.3934 0.4282 0.236 0.000 0.012 0.004 0.748
#> GSM613698 5 0.5254 0.5546 0.012 0.000 0.220 0.080 0.688
#> GSM613699 3 0.8898 0.1867 0.080 0.180 0.448 0.152 0.140
#> GSM613700 2 0.6005 0.6792 0.000 0.660 0.148 0.156 0.036
#> GSM613701 2 0.7454 0.2341 0.036 0.452 0.020 0.352 0.140
#> GSM613702 2 0.6305 0.2111 0.000 0.476 0.040 0.424 0.060
#> GSM613703 1 0.4547 -0.0651 0.588 0.000 0.000 0.400 0.012
#> GSM613704 2 0.1626 0.7317 0.000 0.940 0.016 0.044 0.000
#> GSM613705 5 0.5197 0.6082 0.000 0.000 0.116 0.204 0.680
#> GSM613706 4 0.6762 0.2987 0.160 0.020 0.008 0.552 0.260
#> GSM613707 2 0.3170 0.7327 0.000 0.828 0.160 0.008 0.004
#> GSM613708 1 0.4317 0.6115 0.764 0.000 0.000 0.076 0.160
#> GSM613709 1 0.0880 0.7082 0.968 0.000 0.000 0.032 0.000
#> GSM613710 3 0.4635 0.6598 0.000 0.220 0.728 0.040 0.012
#> GSM613711 3 0.2237 0.8294 0.000 0.084 0.904 0.004 0.008
#> GSM613712 5 0.5952 0.6335 0.032 0.000 0.192 0.120 0.656
#> GSM613713 3 0.2719 0.8079 0.000 0.144 0.852 0.000 0.004
#> GSM613714 3 0.4605 0.7352 0.000 0.028 0.780 0.080 0.112
#> GSM613715 3 0.4747 0.7523 0.000 0.044 0.776 0.072 0.108
#> GSM613716 3 0.6211 0.6494 0.000 0.196 0.644 0.104 0.056
#> GSM613717 3 0.3023 0.8240 0.000 0.096 0.868 0.028 0.008
#> GSM613718 3 0.2052 0.8310 0.000 0.080 0.912 0.004 0.004
#> GSM613719 4 0.4579 0.4572 0.032 0.012 0.004 0.740 0.212
#> GSM613720 3 0.4570 0.7254 0.000 0.236 0.720 0.036 0.008
#> GSM613721 2 0.4789 0.4673 0.000 0.668 0.036 0.292 0.004
#> GSM613722 2 0.6207 0.6655 0.000 0.636 0.180 0.148 0.036
#> GSM613723 1 0.4306 0.3460 0.508 0.000 0.000 0.000 0.492
#> GSM613724 1 0.3684 0.6053 0.720 0.000 0.000 0.000 0.280
#> GSM613725 2 0.6207 0.6655 0.000 0.636 0.180 0.148 0.036
#> GSM613726 1 0.3944 0.5290 0.768 0.000 0.000 0.200 0.032
#> GSM613727 1 0.0404 0.7166 0.988 0.000 0.000 0.000 0.012
#> GSM613728 2 0.4939 0.6765 0.000 0.740 0.092 0.152 0.016
#> GSM613729 1 0.2293 0.6583 0.900 0.000 0.000 0.084 0.016
#> GSM613730 2 0.6374 0.1884 0.000 0.460 0.076 0.432 0.032
#> GSM613731 1 0.6200 0.3650 0.568 0.000 0.004 0.180 0.248
#> GSM613732 3 0.1892 0.8295 0.000 0.080 0.916 0.004 0.000
#> GSM613733 3 0.3246 0.8004 0.000 0.120 0.848 0.024 0.008
#> GSM613734 1 0.3876 0.5742 0.684 0.000 0.000 0.000 0.316
#> GSM613735 1 0.4300 0.3737 0.524 0.000 0.000 0.000 0.476
#> GSM613736 3 0.2389 0.8258 0.000 0.116 0.880 0.004 0.000
#> GSM613737 5 0.7005 0.3929 0.100 0.000 0.160 0.156 0.584
#> GSM613738 1 0.4450 0.3490 0.508 0.000 0.000 0.004 0.488
#> GSM613739 1 0.4306 0.3460 0.508 0.000 0.000 0.000 0.492
#> GSM613740 3 0.1892 0.8303 0.000 0.080 0.916 0.004 0.000
#> GSM613741 4 0.5711 0.5956 0.072 0.116 0.000 0.708 0.104
#> GSM613742 1 0.4451 0.3412 0.504 0.000 0.000 0.004 0.492
#> GSM613743 3 0.2011 0.8276 0.000 0.088 0.908 0.004 0.000
#> GSM613744 3 0.1952 0.8284 0.000 0.084 0.912 0.004 0.000
#> GSM613745 4 0.5765 0.5489 0.020 0.144 0.020 0.704 0.112
#> GSM613746 2 0.1485 0.7353 0.000 0.948 0.020 0.032 0.000
#> GSM613747 1 0.3796 0.5894 0.700 0.000 0.000 0.000 0.300
#> GSM613748 2 0.7762 0.2204 0.000 0.380 0.176 0.360 0.084
#> GSM613749 4 0.5943 0.4833 0.376 0.040 0.000 0.544 0.040
#> GSM613750 3 0.3729 0.7101 0.000 0.012 0.824 0.040 0.124
#> GSM613751 3 0.3729 0.7101 0.000 0.012 0.824 0.040 0.124
#> GSM613752 3 0.3783 0.7144 0.000 0.016 0.824 0.040 0.120
#> GSM613753 3 0.3895 0.6978 0.000 0.012 0.812 0.044 0.132
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM613638 5 0.5568 -0.053274 0.000 0.000 0.048 0.420 0.488 0.044
#> GSM613639 6 0.4818 0.523151 0.336 0.000 0.000 0.052 0.008 0.604
#> GSM613640 4 0.6007 0.323311 0.000 0.000 0.080 0.588 0.240 0.092
#> GSM613641 1 0.1444 0.805169 0.928 0.000 0.000 0.000 0.000 0.072
#> GSM613642 3 0.6791 0.173043 0.000 0.056 0.428 0.388 0.104 0.024
#> GSM613643 5 0.5707 0.325279 0.084 0.000 0.000 0.280 0.588 0.048
#> GSM613644 5 0.6072 0.090462 0.020 0.004 0.008 0.384 0.484 0.100
#> GSM613645 6 0.4601 0.454565 0.376 0.004 0.000 0.028 0.004 0.588
#> GSM613646 6 0.2635 0.591606 0.004 0.080 0.004 0.020 0.008 0.884
#> GSM613647 5 0.5643 -0.020285 0.000 0.000 0.036 0.412 0.488 0.064
#> GSM613648 3 0.3405 0.716933 0.000 0.032 0.844 0.084 0.008 0.032
#> GSM613649 3 0.2471 0.732638 0.000 0.032 0.900 0.044 0.004 0.020
#> GSM613650 6 0.5153 0.552932 0.128 0.000 0.000 0.068 0.100 0.704
#> GSM613651 5 0.3886 0.423182 0.056 0.000 0.000 0.164 0.772 0.008
#> GSM613652 5 0.3861 0.604915 0.316 0.000 0.000 0.008 0.672 0.004
#> GSM613653 6 0.2833 0.626173 0.048 0.048 0.000 0.028 0.000 0.876
#> GSM613654 5 0.3861 0.604915 0.316 0.000 0.000 0.008 0.672 0.004
#> GSM613655 1 0.0790 0.819028 0.968 0.000 0.000 0.000 0.032 0.000
#> GSM613656 5 0.3607 0.580604 0.348 0.000 0.000 0.000 0.652 0.000
#> GSM613657 3 0.1124 0.741254 0.000 0.036 0.956 0.008 0.000 0.000
#> GSM613658 1 0.1444 0.788457 0.928 0.000 0.000 0.000 0.072 0.000
#> GSM613659 2 0.2020 0.628166 0.000 0.920 0.020 0.020 0.000 0.040
#> GSM613660 2 0.4854 0.544215 0.000 0.636 0.264 0.100 0.000 0.000
#> GSM613661 1 0.0858 0.819003 0.968 0.000 0.000 0.004 0.000 0.028
#> GSM613662 2 0.1672 0.656695 0.000 0.932 0.048 0.004 0.000 0.016
#> GSM613663 1 0.0146 0.824491 0.996 0.000 0.000 0.000 0.000 0.004
#> GSM613664 2 0.1434 0.655938 0.000 0.948 0.028 0.012 0.000 0.012
#> GSM613665 2 0.3602 0.648546 0.000 0.760 0.208 0.032 0.000 0.000
#> GSM613666 1 0.0363 0.824212 0.988 0.000 0.000 0.000 0.000 0.012
#> GSM613667 1 0.3411 0.498058 0.756 0.004 0.000 0.008 0.000 0.232
#> GSM613668 1 0.0865 0.816972 0.964 0.000 0.000 0.000 0.036 0.000
#> GSM613669 1 0.0713 0.820312 0.972 0.000 0.000 0.000 0.000 0.028
#> GSM613670 2 0.2357 0.591971 0.000 0.872 0.000 0.012 0.000 0.116
#> GSM613671 1 0.0713 0.820312 0.972 0.000 0.000 0.000 0.000 0.028
#> GSM613672 1 0.0937 0.815061 0.960 0.000 0.000 0.000 0.040 0.000
#> GSM613673 1 0.0713 0.820460 0.972 0.000 0.000 0.000 0.028 0.000
#> GSM613674 2 0.3730 0.657356 0.000 0.772 0.168 0.060 0.000 0.000
#> GSM613675 2 0.1655 0.659222 0.000 0.932 0.052 0.008 0.000 0.008
#> GSM613676 2 0.3917 0.607764 0.000 0.692 0.284 0.024 0.000 0.000
#> GSM613677 3 0.5162 -0.207772 0.000 0.468 0.476 0.032 0.012 0.012
#> GSM613678 2 0.5163 0.316498 0.200 0.652 0.000 0.012 0.000 0.136
#> GSM613679 2 0.3744 0.653236 0.000 0.764 0.184 0.052 0.000 0.000
#> GSM613680 1 0.0713 0.820460 0.972 0.000 0.000 0.000 0.028 0.000
#> GSM613681 1 0.0547 0.822901 0.980 0.000 0.000 0.000 0.000 0.020
#> GSM613682 1 0.0713 0.820460 0.972 0.000 0.000 0.000 0.028 0.000
#> GSM613683 1 0.1814 0.757528 0.900 0.000 0.000 0.000 0.100 0.000
#> GSM613684 2 0.4966 0.532879 0.000 0.652 0.256 0.076 0.000 0.016
#> GSM613685 2 0.3763 0.655951 0.000 0.768 0.172 0.060 0.000 0.000
#> GSM613686 1 0.2257 0.722632 0.876 0.000 0.000 0.008 0.000 0.116
#> GSM613687 1 0.0458 0.823198 0.984 0.000 0.000 0.000 0.016 0.000
#> GSM613688 2 0.3275 0.667314 0.000 0.820 0.140 0.032 0.000 0.008
#> GSM613689 3 0.3123 0.708718 0.000 0.032 0.840 0.116 0.012 0.000
#> GSM613690 3 0.4042 0.675608 0.000 0.000 0.784 0.120 0.072 0.024
#> GSM613691 2 0.2257 0.651985 0.000 0.904 0.048 0.008 0.000 0.040
#> GSM613692 5 0.3938 0.600654 0.324 0.000 0.000 0.016 0.660 0.000
#> GSM613693 2 0.3965 0.626198 0.000 0.720 0.248 0.024 0.000 0.008
#> GSM613694 5 0.7604 0.229736 0.368 0.004 0.056 0.064 0.376 0.132
#> GSM613695 3 0.5630 0.529858 0.000 0.000 0.592 0.232 0.160 0.016
#> GSM613696 2 0.5956 0.519448 0.000 0.652 0.152 0.120 0.032 0.044
#> GSM613697 5 0.3062 0.574080 0.144 0.000 0.000 0.032 0.824 0.000
#> GSM613698 5 0.6131 0.209306 0.004 0.004 0.140 0.160 0.620 0.072
#> GSM613699 3 0.8880 0.100071 0.036 0.180 0.392 0.144 0.136 0.112
#> GSM613700 2 0.7205 -0.055557 0.000 0.356 0.208 0.336 0.000 0.100
#> GSM613701 4 0.7483 0.395054 0.028 0.244 0.016 0.448 0.044 0.220
#> GSM613702 4 0.7061 0.327470 0.000 0.320 0.064 0.388 0.004 0.224
#> GSM613703 1 0.3999 -0.234053 0.500 0.000 0.000 0.004 0.000 0.496
#> GSM613704 2 0.2772 0.639315 0.000 0.876 0.048 0.016 0.000 0.060
#> GSM613705 4 0.6049 0.226316 0.000 0.000 0.072 0.508 0.352 0.068
#> GSM613706 4 0.6456 0.237637 0.092 0.000 0.004 0.556 0.116 0.232
#> GSM613707 2 0.4032 0.646783 0.000 0.740 0.192 0.068 0.000 0.000
#> GSM613708 1 0.5265 0.352882 0.636 0.000 0.000 0.028 0.252 0.084
#> GSM613709 1 0.1531 0.808487 0.928 0.000 0.000 0.000 0.004 0.068
#> GSM613710 3 0.4364 0.559423 0.000 0.112 0.732 0.152 0.004 0.000
#> GSM613711 3 0.1053 0.744660 0.000 0.020 0.964 0.012 0.004 0.000
#> GSM613712 5 0.6535 -0.000357 0.016 0.000 0.120 0.324 0.496 0.044
#> GSM613713 3 0.2511 0.728672 0.000 0.064 0.880 0.056 0.000 0.000
#> GSM613714 3 0.5033 0.586410 0.000 0.016 0.692 0.208 0.064 0.020
#> GSM613715 3 0.4868 0.659520 0.000 0.012 0.724 0.172 0.052 0.040
#> GSM613716 3 0.6621 0.475312 0.000 0.220 0.568 0.108 0.024 0.080
#> GSM613717 3 0.2265 0.731967 0.000 0.040 0.908 0.040 0.004 0.008
#> GSM613718 3 0.0820 0.745217 0.000 0.016 0.972 0.012 0.000 0.000
#> GSM613719 6 0.3566 0.602354 0.040 0.004 0.008 0.044 0.060 0.844
#> GSM613720 3 0.4786 0.578818 0.000 0.236 0.684 0.016 0.004 0.060
#> GSM613721 2 0.4918 0.155264 0.000 0.536 0.004 0.044 0.004 0.412
#> GSM613722 2 0.6985 -0.038476 0.000 0.352 0.236 0.348 0.000 0.064
#> GSM613723 5 0.3636 0.601742 0.320 0.000 0.000 0.000 0.676 0.004
#> GSM613724 1 0.4107 -0.164320 0.540 0.000 0.000 0.004 0.452 0.004
#> GSM613725 4 0.6966 -0.124196 0.000 0.352 0.228 0.356 0.000 0.064
#> GSM613726 1 0.5211 0.531042 0.684 0.000 0.000 0.152 0.040 0.124
#> GSM613727 1 0.1410 0.816080 0.944 0.000 0.000 0.004 0.044 0.008
#> GSM613728 2 0.6185 0.228365 0.000 0.564 0.116 0.248 0.000 0.072
#> GSM613729 1 0.2443 0.779383 0.880 0.000 0.000 0.004 0.020 0.096
#> GSM613730 2 0.7583 -0.314156 0.000 0.332 0.100 0.304 0.012 0.252
#> GSM613731 1 0.7012 -0.167247 0.392 0.000 0.000 0.212 0.320 0.076
#> GSM613732 3 0.0717 0.744384 0.000 0.016 0.976 0.008 0.000 0.000
#> GSM613733 3 0.2672 0.697812 0.000 0.052 0.868 0.080 0.000 0.000
#> GSM613734 5 0.4098 0.381500 0.444 0.000 0.000 0.004 0.548 0.004
#> GSM613735 5 0.3820 0.588250 0.332 0.000 0.000 0.004 0.660 0.004
#> GSM613736 3 0.2263 0.734969 0.000 0.048 0.896 0.056 0.000 0.000
#> GSM613737 5 0.5735 0.387653 0.048 0.000 0.092 0.080 0.696 0.084
#> GSM613738 5 0.3878 0.599183 0.320 0.000 0.000 0.004 0.668 0.008
#> GSM613739 5 0.3636 0.601742 0.320 0.000 0.000 0.000 0.676 0.004
#> GSM613740 3 0.1480 0.743356 0.000 0.020 0.940 0.040 0.000 0.000
#> GSM613741 6 0.4334 0.586471 0.020 0.080 0.000 0.068 0.040 0.792
#> GSM613742 5 0.3878 0.599183 0.320 0.000 0.000 0.004 0.668 0.008
#> GSM613743 3 0.1341 0.742031 0.000 0.024 0.948 0.028 0.000 0.000
#> GSM613744 3 0.0603 0.744063 0.000 0.016 0.980 0.004 0.000 0.000
#> GSM613745 6 0.4901 0.498905 0.000 0.148 0.004 0.080 0.044 0.724
#> GSM613746 2 0.2152 0.650102 0.000 0.912 0.036 0.012 0.000 0.040
#> GSM613747 5 0.4128 0.263369 0.488 0.000 0.000 0.004 0.504 0.004
#> GSM613748 4 0.7477 0.403927 0.000 0.204 0.128 0.480 0.032 0.156
#> GSM613749 6 0.6725 0.304954 0.348 0.012 0.000 0.232 0.020 0.388
#> GSM613750 3 0.5858 0.585316 0.000 0.024 0.640 0.208 0.080 0.048
#> GSM613751 3 0.5858 0.585316 0.000 0.024 0.640 0.208 0.080 0.048
#> GSM613752 3 0.5858 0.585316 0.000 0.024 0.640 0.208 0.080 0.048
#> GSM613753 3 0.5903 0.581072 0.000 0.024 0.636 0.208 0.084 0.048
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) k
#> CV:skmeans 113 2.02e-02 2
#> CV:skmeans 109 1.39e-02 3
#> CV:skmeans 87 1.60e-04 4
#> CV:skmeans 87 4.17e-07 5
#> CV:skmeans 80 1.89e-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["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 27425 rows and 116 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 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 0.510 0.627 0.843 0.4900 0.503 0.503
#> 3 3 0.386 0.649 0.808 0.1448 0.873 0.770
#> 4 4 0.538 0.681 0.853 0.2045 0.780 0.566
#> 5 5 0.575 0.621 0.807 0.1106 0.897 0.698
#> 6 6 0.604 0.567 0.756 0.0691 0.909 0.674
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
#> GSM613638 1 0.2043 0.3976 0.968 0.032
#> GSM613639 1 0.9661 0.8082 0.608 0.392
#> GSM613640 1 0.2236 0.3910 0.964 0.036
#> GSM613641 1 0.9552 0.8224 0.624 0.376
#> GSM613642 1 0.5059 0.2288 0.888 0.112
#> GSM613643 1 0.2043 0.3976 0.968 0.032
#> GSM613644 1 0.2043 0.3976 0.968 0.032
#> GSM613645 1 0.9608 0.8129 0.616 0.384
#> GSM613646 1 0.7376 -0.0842 0.792 0.208
#> GSM613647 1 0.2423 0.3839 0.960 0.040
#> GSM613648 2 0.9580 0.7632 0.380 0.620
#> GSM613649 2 0.9552 0.7644 0.376 0.624
#> GSM613650 1 0.7745 0.6513 0.772 0.228
#> GSM613651 1 0.2043 0.3976 0.968 0.032
#> GSM613652 1 0.9460 0.8192 0.636 0.364
#> GSM613653 1 0.9732 0.8121 0.596 0.404
#> GSM613654 1 0.9460 0.8192 0.636 0.364
#> GSM613655 1 0.9552 0.8224 0.624 0.376
#> GSM613656 1 0.9608 0.8200 0.616 0.384
#> GSM613657 2 0.9552 0.7644 0.376 0.624
#> GSM613658 1 0.9552 0.8224 0.624 0.376
#> GSM613659 2 0.3114 0.4288 0.056 0.944
#> GSM613660 2 0.9552 0.7644 0.376 0.624
#> GSM613661 1 0.9635 0.8198 0.612 0.388
#> GSM613662 2 0.3733 0.4078 0.072 0.928
#> GSM613663 1 0.9552 0.8224 0.624 0.376
#> GSM613664 2 0.3114 0.4288 0.056 0.944
#> GSM613665 2 0.0000 0.4963 0.000 1.000
#> GSM613666 1 0.9552 0.8224 0.624 0.376
#> GSM613667 1 0.9686 0.8165 0.604 0.396
#> GSM613668 1 0.9608 0.8200 0.616 0.384
#> GSM613669 1 0.9552 0.8224 0.624 0.376
#> GSM613670 2 0.4431 0.3678 0.092 0.908
#> GSM613671 1 0.9552 0.8224 0.624 0.376
#> GSM613672 1 0.9552 0.8224 0.624 0.376
#> GSM613673 1 0.9608 0.8200 0.616 0.384
#> GSM613674 2 0.6531 0.6501 0.168 0.832
#> GSM613675 2 0.2603 0.4597 0.044 0.956
#> GSM613676 2 0.0376 0.4998 0.004 0.996
#> GSM613677 1 0.9996 0.7317 0.512 0.488
#> GSM613678 1 0.9795 0.8061 0.584 0.416
#> GSM613679 2 0.6973 0.6630 0.188 0.812
#> GSM613680 1 0.9552 0.8224 0.624 0.376
#> GSM613681 1 0.9552 0.8224 0.624 0.376
#> GSM613682 1 0.9608 0.8200 0.616 0.384
#> GSM613683 1 0.9552 0.8224 0.624 0.376
#> GSM613684 2 0.9552 0.7644 0.376 0.624
#> GSM613685 2 0.9460 0.7606 0.364 0.636
#> GSM613686 1 0.9552 0.8224 0.624 0.376
#> GSM613687 1 0.9580 0.8214 0.620 0.380
#> GSM613688 2 0.3879 0.3932 0.076 0.924
#> GSM613689 2 0.9944 0.6947 0.456 0.544
#> GSM613690 2 0.9358 -0.4732 0.352 0.648
#> GSM613691 2 0.3431 0.4160 0.064 0.936
#> GSM613692 1 0.9608 0.8200 0.616 0.384
#> GSM613693 2 0.9522 0.7635 0.372 0.628
#> GSM613694 1 0.2948 0.4036 0.948 0.052
#> GSM613695 1 0.6623 0.0836 0.828 0.172
#> GSM613696 1 0.9866 0.7966 0.568 0.432
#> GSM613697 1 0.9795 0.8080 0.584 0.416
#> GSM613698 1 0.9795 0.8080 0.584 0.416
#> GSM613699 1 0.9833 0.8030 0.576 0.424
#> GSM613700 2 0.9795 0.7467 0.416 0.584
#> GSM613701 1 0.9686 0.8055 0.604 0.396
#> GSM613702 2 0.9909 0.7292 0.444 0.556
#> GSM613703 1 0.9552 0.8224 0.624 0.376
#> GSM613704 2 0.2778 0.4725 0.048 0.952
#> GSM613705 1 0.2043 0.3976 0.968 0.032
#> GSM613706 1 0.8713 0.7205 0.708 0.292
#> GSM613707 2 0.9608 0.7616 0.384 0.616
#> GSM613708 1 0.9552 0.8224 0.624 0.376
#> GSM613709 1 0.9552 0.8224 0.624 0.376
#> GSM613710 2 0.9580 0.7632 0.380 0.620
#> GSM613711 2 0.9552 0.7644 0.376 0.624
#> GSM613712 1 0.2043 0.3976 0.968 0.032
#> GSM613713 2 0.9552 0.7644 0.376 0.624
#> GSM613714 2 0.9552 0.7644 0.376 0.624
#> GSM613715 2 0.9922 0.7165 0.448 0.552
#> GSM613716 2 0.9608 0.7616 0.384 0.616
#> GSM613717 2 0.9552 0.7644 0.376 0.624
#> GSM613718 2 0.9552 0.7644 0.376 0.624
#> GSM613719 1 0.4298 0.4739 0.912 0.088
#> GSM613720 2 0.9608 0.7616 0.384 0.616
#> GSM613721 1 1.0000 -0.6697 0.504 0.496
#> GSM613722 2 0.3431 0.4216 0.064 0.936
#> GSM613723 1 0.9608 0.8200 0.616 0.384
#> GSM613724 1 0.9552 0.8224 0.624 0.376
#> GSM613725 2 0.9552 0.7644 0.376 0.624
#> GSM613726 1 0.9661 0.8184 0.608 0.392
#> GSM613727 1 0.9552 0.8224 0.624 0.376
#> GSM613728 2 0.9358 0.7532 0.352 0.648
#> GSM613729 1 0.9552 0.8224 0.624 0.376
#> GSM613730 2 0.4298 0.4157 0.088 0.912
#> GSM613731 1 0.9686 0.8055 0.604 0.396
#> GSM613732 2 0.9552 0.7644 0.376 0.624
#> GSM613733 2 0.9552 0.7644 0.376 0.624
#> GSM613734 1 0.9552 0.8224 0.624 0.376
#> GSM613735 1 0.9552 0.8224 0.624 0.376
#> GSM613736 2 0.9552 0.7644 0.376 0.624
#> GSM613737 1 0.7815 -0.1305 0.768 0.232
#> GSM613738 1 0.9552 0.8224 0.624 0.376
#> GSM613739 1 0.9522 0.8218 0.628 0.372
#> GSM613740 2 0.9552 0.7644 0.376 0.624
#> GSM613741 2 0.8661 -0.2519 0.288 0.712
#> GSM613742 1 0.9686 0.8181 0.604 0.396
#> GSM613743 2 0.9552 0.7644 0.376 0.624
#> GSM613744 2 0.9552 0.7644 0.376 0.624
#> GSM613745 2 0.5294 0.4106 0.120 0.880
#> GSM613746 2 0.0000 0.4963 0.000 1.000
#> GSM613747 1 0.9552 0.8224 0.624 0.376
#> GSM613748 2 0.6973 0.1620 0.188 0.812
#> GSM613749 2 0.9881 -0.6092 0.436 0.564
#> GSM613750 2 0.9552 0.7644 0.376 0.624
#> GSM613751 2 0.9552 0.7644 0.376 0.624
#> GSM613752 2 0.9552 0.7644 0.376 0.624
#> GSM613753 1 0.8443 -0.2321 0.728 0.272
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM613638 1 0.9098 0.460 0.540 0.276 0.184
#> GSM613639 1 0.5285 0.742 0.824 0.064 0.112
#> GSM613640 1 0.9122 0.453 0.536 0.280 0.184
#> GSM613641 1 0.1289 0.787 0.968 0.000 0.032
#> GSM613642 1 0.9113 0.437 0.528 0.300 0.172
#> GSM613643 1 0.9098 0.460 0.540 0.276 0.184
#> GSM613644 1 0.9098 0.460 0.540 0.276 0.184
#> GSM613645 1 0.5883 0.722 0.796 0.092 0.112
#> GSM613646 2 0.8966 0.359 0.256 0.560 0.184
#> GSM613647 1 0.9089 0.446 0.536 0.288 0.176
#> GSM613648 2 0.5173 0.611 0.036 0.816 0.148
#> GSM613649 2 0.0747 0.693 0.000 0.984 0.016
#> GSM613650 1 0.7348 0.645 0.704 0.176 0.120
#> GSM613651 1 0.8889 0.478 0.560 0.276 0.164
#> GSM613652 1 0.5263 0.750 0.828 0.088 0.084
#> GSM613653 1 0.4235 0.735 0.824 0.000 0.176
#> GSM613654 1 0.5426 0.745 0.820 0.092 0.088
#> GSM613655 1 0.2625 0.778 0.916 0.000 0.084
#> GSM613656 1 0.2860 0.777 0.912 0.004 0.084
#> GSM613657 2 0.0000 0.691 0.000 1.000 0.000
#> GSM613658 1 0.2625 0.778 0.916 0.000 0.084
#> GSM613659 2 0.9054 0.362 0.404 0.460 0.136
#> GSM613660 2 0.0237 0.692 0.000 0.996 0.004
#> GSM613661 1 0.0892 0.784 0.980 0.000 0.020
#> GSM613662 2 0.6247 0.470 0.376 0.620 0.004
#> GSM613663 1 0.1529 0.785 0.960 0.000 0.040
#> GSM613664 2 0.7032 0.478 0.368 0.604 0.028
#> GSM613665 2 0.5363 0.518 0.276 0.724 0.000
#> GSM613666 1 0.2625 0.778 0.916 0.000 0.084
#> GSM613667 1 0.1411 0.781 0.964 0.000 0.036
#> GSM613668 1 0.2860 0.777 0.912 0.004 0.084
#> GSM613669 1 0.2625 0.778 0.916 0.000 0.084
#> GSM613670 2 0.7508 0.434 0.416 0.544 0.040
#> GSM613671 1 0.2448 0.780 0.924 0.000 0.076
#> GSM613672 1 0.2625 0.778 0.916 0.000 0.084
#> GSM613673 1 0.2772 0.785 0.916 0.004 0.080
#> GSM613674 2 0.4452 0.590 0.192 0.808 0.000
#> GSM613675 2 0.5763 0.549 0.276 0.716 0.008
#> GSM613676 2 0.4605 0.588 0.204 0.796 0.000
#> GSM613677 1 0.6662 0.708 0.752 0.120 0.128
#> GSM613678 1 0.4748 0.741 0.832 0.024 0.144
#> GSM613679 2 0.3213 0.664 0.092 0.900 0.008
#> GSM613680 1 0.2625 0.778 0.916 0.000 0.084
#> GSM613681 1 0.2537 0.779 0.920 0.000 0.080
#> GSM613682 1 0.3030 0.779 0.904 0.004 0.092
#> GSM613683 1 0.2625 0.778 0.916 0.000 0.084
#> GSM613684 2 0.1267 0.692 0.004 0.972 0.024
#> GSM613685 2 0.2165 0.662 0.064 0.936 0.000
#> GSM613686 1 0.0592 0.785 0.988 0.000 0.012
#> GSM613687 1 0.2200 0.784 0.940 0.004 0.056
#> GSM613688 2 0.8509 0.416 0.392 0.512 0.096
#> GSM613689 2 0.8508 0.434 0.232 0.608 0.160
#> GSM613690 1 0.6902 0.704 0.736 0.116 0.148
#> GSM613691 2 0.7228 0.483 0.364 0.600 0.036
#> GSM613692 1 0.2860 0.777 0.912 0.004 0.084
#> GSM613693 2 0.0592 0.690 0.012 0.988 0.000
#> GSM613694 1 0.7495 0.617 0.692 0.188 0.120
#> GSM613695 1 0.9374 0.344 0.464 0.360 0.176
#> GSM613696 1 0.4802 0.737 0.824 0.020 0.156
#> GSM613697 1 0.3573 0.759 0.876 0.004 0.120
#> GSM613698 1 0.4521 0.733 0.816 0.004 0.180
#> GSM613699 1 0.4802 0.737 0.824 0.020 0.156
#> GSM613700 2 0.4094 0.650 0.028 0.872 0.100
#> GSM613701 1 0.6911 0.679 0.728 0.092 0.180
#> GSM613702 2 0.7108 0.550 0.100 0.716 0.184
#> GSM613703 1 0.0424 0.785 0.992 0.000 0.008
#> GSM613704 2 0.5109 0.603 0.212 0.780 0.008
#> GSM613705 1 0.9098 0.460 0.540 0.276 0.184
#> GSM613706 1 0.7917 0.622 0.664 0.152 0.184
#> GSM613707 2 0.0237 0.692 0.004 0.996 0.000
#> GSM613708 1 0.0592 0.785 0.988 0.000 0.012
#> GSM613709 1 0.0892 0.786 0.980 0.000 0.020
#> GSM613710 2 0.0747 0.693 0.000 0.984 0.016
#> GSM613711 2 0.0592 0.692 0.000 0.988 0.012
#> GSM613712 1 0.9018 0.468 0.548 0.276 0.176
#> GSM613713 2 0.0000 0.691 0.000 1.000 0.000
#> GSM613714 2 0.6297 0.568 0.060 0.756 0.184
#> GSM613715 2 0.7797 0.433 0.188 0.672 0.140
#> GSM613716 2 0.3780 0.668 0.044 0.892 0.064
#> GSM613717 2 0.0747 0.693 0.000 0.984 0.016
#> GSM613718 2 0.1031 0.690 0.000 0.976 0.024
#> GSM613719 1 0.8321 0.549 0.620 0.240 0.140
#> GSM613720 2 0.0475 0.693 0.004 0.992 0.004
#> GSM613721 2 0.6168 0.594 0.096 0.780 0.124
#> GSM613722 2 0.6047 0.507 0.312 0.680 0.008
#> GSM613723 1 0.2945 0.778 0.908 0.004 0.088
#> GSM613724 1 0.2625 0.778 0.916 0.000 0.084
#> GSM613725 2 0.1031 0.691 0.000 0.976 0.024
#> GSM613726 1 0.3412 0.759 0.876 0.000 0.124
#> GSM613727 1 0.2625 0.778 0.916 0.000 0.084
#> GSM613728 2 0.0829 0.695 0.012 0.984 0.004
#> GSM613729 1 0.0424 0.785 0.992 0.000 0.008
#> GSM613730 2 0.7416 0.560 0.276 0.656 0.068
#> GSM613731 1 0.6962 0.676 0.724 0.092 0.184
#> GSM613732 2 0.0000 0.691 0.000 1.000 0.000
#> GSM613733 2 0.0592 0.692 0.000 0.988 0.012
#> GSM613734 1 0.2625 0.778 0.916 0.000 0.084
#> GSM613735 1 0.2625 0.778 0.916 0.000 0.084
#> GSM613736 2 0.1163 0.692 0.000 0.972 0.028
#> GSM613737 2 0.9098 0.336 0.276 0.540 0.184
#> GSM613738 1 0.1643 0.788 0.956 0.000 0.044
#> GSM613739 1 0.3637 0.781 0.892 0.024 0.084
#> GSM613740 2 0.0000 0.691 0.000 1.000 0.000
#> GSM613741 1 0.7674 -0.332 0.484 0.472 0.044
#> GSM613742 1 0.2945 0.784 0.908 0.004 0.088
#> GSM613743 2 0.0000 0.691 0.000 1.000 0.000
#> GSM613744 2 0.0592 0.692 0.000 0.988 0.012
#> GSM613745 2 0.8082 0.528 0.296 0.608 0.096
#> GSM613746 2 0.5363 0.518 0.276 0.724 0.000
#> GSM613747 1 0.2625 0.778 0.916 0.000 0.084
#> GSM613748 2 0.9250 0.450 0.304 0.512 0.184
#> GSM613749 1 0.8869 0.206 0.560 0.280 0.160
#> GSM613750 3 0.5138 0.883 0.000 0.252 0.748
#> GSM613751 3 0.5291 0.884 0.000 0.268 0.732
#> GSM613752 3 0.5291 0.884 0.000 0.268 0.732
#> GSM613753 3 0.3713 0.713 0.032 0.076 0.892
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 3 0.0000 0.76155 0.000 0.000 1.000 0
#> GSM613639 1 0.4543 0.63509 0.676 0.000 0.324 0
#> GSM613640 3 0.0000 0.76155 0.000 0.000 1.000 0
#> GSM613641 1 0.2011 0.84778 0.920 0.000 0.080 0
#> GSM613642 3 0.0336 0.76245 0.000 0.008 0.992 0
#> GSM613643 3 0.1302 0.74718 0.044 0.000 0.956 0
#> GSM613644 3 0.0000 0.76155 0.000 0.000 1.000 0
#> GSM613645 3 0.4817 0.20058 0.388 0.000 0.612 0
#> GSM613646 3 0.1356 0.76118 0.008 0.032 0.960 0
#> GSM613647 3 0.0336 0.76135 0.008 0.000 0.992 0
#> GSM613648 3 0.2647 0.71112 0.000 0.120 0.880 0
#> GSM613649 3 0.4948 0.14628 0.000 0.440 0.560 0
#> GSM613650 3 0.4955 -0.03632 0.444 0.000 0.556 0
#> GSM613651 3 0.1302 0.75300 0.044 0.000 0.956 0
#> GSM613652 1 0.3528 0.69526 0.808 0.000 0.192 0
#> GSM613653 1 0.4250 0.70477 0.724 0.000 0.276 0
#> GSM613654 1 0.4697 0.35641 0.644 0.000 0.356 0
#> GSM613655 1 0.0000 0.85081 1.000 0.000 0.000 0
#> GSM613656 1 0.0000 0.85081 1.000 0.000 0.000 0
#> GSM613657 2 0.4164 0.52626 0.000 0.736 0.264 0
#> GSM613658 1 0.0000 0.85081 1.000 0.000 0.000 0
#> GSM613659 2 0.7122 0.24588 0.144 0.516 0.340 0
#> GSM613660 2 0.0000 0.78078 0.000 1.000 0.000 0
#> GSM613661 1 0.2589 0.83560 0.884 0.000 0.116 0
#> GSM613662 2 0.3577 0.66518 0.156 0.832 0.012 0
#> GSM613663 1 0.1474 0.85411 0.948 0.000 0.052 0
#> GSM613664 2 0.1398 0.76960 0.004 0.956 0.040 0
#> GSM613665 2 0.0000 0.78078 0.000 1.000 0.000 0
#> GSM613666 1 0.0336 0.85305 0.992 0.000 0.008 0
#> GSM613667 1 0.2973 0.81891 0.856 0.000 0.144 0
#> GSM613668 1 0.0336 0.85119 0.992 0.008 0.000 0
#> GSM613669 1 0.0336 0.85305 0.992 0.000 0.008 0
#> GSM613670 2 0.5293 0.62126 0.152 0.748 0.100 0
#> GSM613671 1 0.0707 0.85503 0.980 0.000 0.020 0
#> GSM613672 1 0.0336 0.85305 0.992 0.000 0.008 0
#> GSM613673 1 0.1256 0.85610 0.964 0.008 0.028 0
#> GSM613674 2 0.0000 0.78078 0.000 1.000 0.000 0
#> GSM613675 2 0.0524 0.78008 0.004 0.988 0.008 0
#> GSM613676 2 0.0188 0.78154 0.000 0.996 0.004 0
#> GSM613677 1 0.5678 0.68346 0.716 0.112 0.172 0
#> GSM613678 1 0.4391 0.72667 0.740 0.008 0.252 0
#> GSM613679 2 0.0000 0.78078 0.000 1.000 0.000 0
#> GSM613680 1 0.0336 0.85305 0.992 0.000 0.008 0
#> GSM613681 1 0.0469 0.85399 0.988 0.000 0.012 0
#> GSM613682 1 0.0804 0.85267 0.980 0.012 0.008 0
#> GSM613683 1 0.0000 0.85081 1.000 0.000 0.000 0
#> GSM613684 2 0.0817 0.77951 0.000 0.976 0.024 0
#> GSM613685 2 0.0000 0.78078 0.000 1.000 0.000 0
#> GSM613686 1 0.2530 0.83686 0.888 0.000 0.112 0
#> GSM613687 1 0.1256 0.85611 0.964 0.008 0.028 0
#> GSM613688 2 0.5222 0.63968 0.112 0.756 0.132 0
#> GSM613689 3 0.6957 0.34742 0.164 0.260 0.576 0
#> GSM613690 1 0.6668 0.29777 0.528 0.092 0.380 0
#> GSM613691 2 0.6974 0.14392 0.396 0.488 0.116 0
#> GSM613692 1 0.0000 0.85081 1.000 0.000 0.000 0
#> GSM613693 2 0.0000 0.78078 0.000 1.000 0.000 0
#> GSM613694 1 0.5250 0.37128 0.552 0.008 0.440 0
#> GSM613695 3 0.0817 0.75940 0.000 0.024 0.976 0
#> GSM613696 1 0.4690 0.70992 0.724 0.016 0.260 0
#> GSM613697 1 0.4011 0.76520 0.784 0.008 0.208 0
#> GSM613698 1 0.4647 0.68113 0.704 0.008 0.288 0
#> GSM613699 1 0.4635 0.70276 0.720 0.012 0.268 0
#> GSM613700 2 0.2868 0.72367 0.000 0.864 0.136 0
#> GSM613701 3 0.4331 0.46244 0.288 0.000 0.712 0
#> GSM613702 3 0.1474 0.75535 0.000 0.052 0.948 0
#> GSM613703 1 0.2408 0.83986 0.896 0.000 0.104 0
#> GSM613704 2 0.0336 0.78019 0.000 0.992 0.008 0
#> GSM613705 3 0.0000 0.76155 0.000 0.000 1.000 0
#> GSM613706 3 0.3105 0.66892 0.140 0.004 0.856 0
#> GSM613707 2 0.0817 0.78109 0.000 0.976 0.024 0
#> GSM613708 1 0.2760 0.83574 0.872 0.000 0.128 0
#> GSM613709 1 0.2216 0.84383 0.908 0.000 0.092 0
#> GSM613710 3 0.4994 0.01676 0.000 0.480 0.520 0
#> GSM613711 2 0.5000 0.00883 0.000 0.504 0.496 0
#> GSM613712 3 0.0817 0.75959 0.024 0.000 0.976 0
#> GSM613713 2 0.3311 0.70195 0.000 0.828 0.172 0
#> GSM613714 3 0.1211 0.75527 0.000 0.040 0.960 0
#> GSM613715 3 0.1867 0.73814 0.000 0.072 0.928 0
#> GSM613716 3 0.3610 0.61684 0.000 0.200 0.800 0
#> GSM613717 3 0.4955 0.13182 0.000 0.444 0.556 0
#> GSM613718 3 0.4713 0.34273 0.000 0.360 0.640 0
#> GSM613719 1 0.4972 0.36137 0.544 0.000 0.456 0
#> GSM613720 2 0.3942 0.64237 0.000 0.764 0.236 0
#> GSM613721 2 0.6362 0.32721 0.072 0.560 0.368 0
#> GSM613722 2 0.0707 0.78160 0.000 0.980 0.020 0
#> GSM613723 1 0.1302 0.84073 0.956 0.000 0.044 0
#> GSM613724 1 0.0000 0.85081 1.000 0.000 0.000 0
#> GSM613725 2 0.0921 0.77939 0.000 0.972 0.028 0
#> GSM613726 1 0.3801 0.76562 0.780 0.000 0.220 0
#> GSM613727 1 0.0188 0.85070 0.996 0.000 0.004 0
#> GSM613728 2 0.0469 0.78025 0.000 0.988 0.012 0
#> GSM613729 1 0.2469 0.84001 0.892 0.000 0.108 0
#> GSM613730 2 0.7184 0.24964 0.160 0.524 0.316 0
#> GSM613731 3 0.3311 0.63298 0.172 0.000 0.828 0
#> GSM613732 2 0.3356 0.70027 0.000 0.824 0.176 0
#> GSM613733 2 0.0336 0.78160 0.000 0.992 0.008 0
#> GSM613734 1 0.0188 0.85070 0.996 0.000 0.004 0
#> GSM613735 1 0.0188 0.85070 0.996 0.000 0.004 0
#> GSM613736 2 0.4790 0.42448 0.000 0.620 0.380 0
#> GSM613737 3 0.1557 0.74794 0.000 0.056 0.944 0
#> GSM613738 1 0.2469 0.84044 0.892 0.000 0.108 0
#> GSM613739 1 0.2149 0.82416 0.912 0.000 0.088 0
#> GSM613740 2 0.2469 0.74821 0.000 0.892 0.108 0
#> GSM613741 2 0.7279 -0.00631 0.408 0.444 0.148 0
#> GSM613742 1 0.1716 0.84440 0.936 0.000 0.064 0
#> GSM613743 2 0.3528 0.68405 0.000 0.808 0.192 0
#> GSM613744 2 0.2281 0.75617 0.000 0.904 0.096 0
#> GSM613745 2 0.7381 0.19394 0.180 0.492 0.328 0
#> GSM613746 2 0.0000 0.78078 0.000 1.000 0.000 0
#> GSM613747 1 0.0188 0.85070 0.996 0.000 0.004 0
#> GSM613748 3 0.5339 0.63394 0.156 0.100 0.744 0
#> GSM613749 1 0.7806 0.11957 0.392 0.356 0.252 0
#> GSM613750 4 0.0000 1.00000 0.000 0.000 0.000 1
#> GSM613751 4 0.0000 1.00000 0.000 0.000 0.000 1
#> GSM613752 4 0.0000 1.00000 0.000 0.000 0.000 1
#> GSM613753 4 0.0000 1.00000 0.000 0.000 0.000 1
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM613638 3 0.2438 0.72056 0.040 0.000 0.900 0 0.060
#> GSM613639 1 0.2230 0.67294 0.884 0.000 0.116 0 0.000
#> GSM613640 3 0.2592 0.72247 0.052 0.000 0.892 0 0.056
#> GSM613641 1 0.3109 0.66274 0.800 0.000 0.000 0 0.200
#> GSM613642 3 0.2644 0.71051 0.008 0.036 0.896 0 0.060
#> GSM613643 3 0.3102 0.71022 0.084 0.000 0.860 0 0.056
#> GSM613644 3 0.2661 0.72198 0.056 0.000 0.888 0 0.056
#> GSM613645 1 0.5174 0.16674 0.604 0.000 0.340 0 0.056
#> GSM613646 3 0.4734 0.62980 0.228 0.020 0.720 0 0.032
#> GSM613647 3 0.2592 0.72247 0.052 0.000 0.892 0 0.056
#> GSM613648 3 0.1124 0.69492 0.000 0.036 0.960 0 0.004
#> GSM613649 3 0.4264 0.25152 0.000 0.376 0.620 0 0.004
#> GSM613650 1 0.4558 0.30420 0.652 0.000 0.324 0 0.024
#> GSM613651 3 0.6388 0.44228 0.244 0.000 0.516 0 0.240
#> GSM613652 5 0.0912 0.82920 0.016 0.000 0.012 0 0.972
#> GSM613653 1 0.0671 0.72640 0.980 0.000 0.016 0 0.004
#> GSM613654 5 0.0912 0.82920 0.016 0.000 0.012 0 0.972
#> GSM613655 1 0.4060 0.50759 0.640 0.000 0.000 0 0.360
#> GSM613656 5 0.2329 0.80697 0.124 0.000 0.000 0 0.876
#> GSM613657 2 0.4235 0.44927 0.000 0.656 0.336 0 0.008
#> GSM613658 1 0.4030 0.51924 0.648 0.000 0.000 0 0.352
#> GSM613659 2 0.6581 0.18125 0.140 0.488 0.356 0 0.016
#> GSM613660 2 0.0290 0.77646 0.000 0.992 0.008 0 0.000
#> GSM613661 1 0.0162 0.72906 0.996 0.000 0.004 0 0.000
#> GSM613662 2 0.3210 0.67363 0.152 0.832 0.008 0 0.008
#> GSM613663 1 0.1197 0.73063 0.952 0.000 0.000 0 0.048
#> GSM613664 2 0.1106 0.76983 0.000 0.964 0.024 0 0.012
#> GSM613665 2 0.0703 0.77524 0.000 0.976 0.024 0 0.000
#> GSM613666 1 0.3452 0.65388 0.756 0.000 0.000 0 0.244
#> GSM613667 1 0.0162 0.73007 0.996 0.000 0.000 0 0.004
#> GSM613668 1 0.3741 0.63723 0.732 0.000 0.004 0 0.264
#> GSM613669 1 0.3242 0.67220 0.784 0.000 0.000 0 0.216
#> GSM613670 2 0.4467 0.60095 0.240 0.724 0.024 0 0.012
#> GSM613671 1 0.2773 0.70241 0.836 0.000 0.000 0 0.164
#> GSM613672 1 0.3534 0.64599 0.744 0.000 0.000 0 0.256
#> GSM613673 1 0.3630 0.68716 0.780 0.000 0.016 0 0.204
#> GSM613674 2 0.0693 0.77349 0.000 0.980 0.008 0 0.012
#> GSM613675 2 0.0162 0.77633 0.000 0.996 0.004 0 0.000
#> GSM613676 2 0.0404 0.77789 0.000 0.988 0.012 0 0.000
#> GSM613677 1 0.4424 0.63469 0.728 0.048 0.224 0 0.000
#> GSM613678 1 0.0865 0.72836 0.972 0.000 0.024 0 0.004
#> GSM613679 2 0.0324 0.77668 0.000 0.992 0.004 0 0.004
#> GSM613680 1 0.3534 0.64626 0.744 0.000 0.000 0 0.256
#> GSM613681 1 0.3366 0.66358 0.768 0.000 0.000 0 0.232
#> GSM613682 1 0.4082 0.65813 0.740 0.008 0.012 0 0.240
#> GSM613683 1 0.3857 0.57951 0.688 0.000 0.000 0 0.312
#> GSM613684 2 0.1579 0.77041 0.000 0.944 0.032 0 0.024
#> GSM613685 2 0.0693 0.77349 0.000 0.980 0.008 0 0.012
#> GSM613686 1 0.0162 0.73007 0.996 0.000 0.000 0 0.004
#> GSM613687 1 0.2439 0.71676 0.876 0.000 0.004 0 0.120
#> GSM613688 2 0.5104 0.61635 0.112 0.728 0.144 0 0.016
#> GSM613689 3 0.5850 0.45548 0.140 0.184 0.656 0 0.020
#> GSM613690 1 0.5349 0.26592 0.516 0.036 0.440 0 0.008
#> GSM613691 2 0.5793 -0.00364 0.456 0.464 0.076 0 0.004
#> GSM613692 5 0.3003 0.75343 0.188 0.000 0.000 0 0.812
#> GSM613693 2 0.0963 0.77420 0.000 0.964 0.036 0 0.000
#> GSM613694 1 0.4283 0.39987 0.644 0.000 0.348 0 0.008
#> GSM613695 3 0.2036 0.71397 0.000 0.024 0.920 0 0.056
#> GSM613696 1 0.3663 0.69572 0.840 0.060 0.084 0 0.016
#> GSM613697 1 0.4836 0.20674 0.612 0.000 0.032 0 0.356
#> GSM613698 1 0.4683 0.56715 0.732 0.000 0.092 0 0.176
#> GSM613699 1 0.4253 0.65930 0.756 0.032 0.204 0 0.008
#> GSM613700 2 0.3010 0.70413 0.000 0.824 0.172 0 0.004
#> GSM613701 3 0.4430 0.12556 0.456 0.000 0.540 0 0.004
#> GSM613702 3 0.2599 0.72391 0.044 0.028 0.904 0 0.024
#> GSM613703 1 0.0000 0.72939 1.000 0.000 0.000 0 0.000
#> GSM613704 2 0.0703 0.77524 0.000 0.976 0.024 0 0.000
#> GSM613705 3 0.2592 0.72247 0.052 0.000 0.892 0 0.056
#> GSM613706 3 0.4434 0.60635 0.208 0.000 0.736 0 0.056
#> GSM613707 2 0.1469 0.77690 0.000 0.948 0.036 0 0.016
#> GSM613708 1 0.1444 0.72108 0.948 0.000 0.012 0 0.040
#> GSM613709 1 0.0510 0.73193 0.984 0.000 0.000 0 0.016
#> GSM613710 3 0.4367 0.14702 0.000 0.416 0.580 0 0.004
#> GSM613711 3 0.4582 0.12834 0.000 0.416 0.572 0 0.012
#> GSM613712 3 0.3779 0.69314 0.144 0.000 0.804 0 0.052
#> GSM613713 2 0.4167 0.63234 0.000 0.724 0.252 0 0.024
#> GSM613714 3 0.0865 0.71237 0.000 0.004 0.972 0 0.024
#> GSM613715 3 0.1412 0.69486 0.004 0.036 0.952 0 0.008
#> GSM613716 3 0.2833 0.64083 0.004 0.140 0.852 0 0.004
#> GSM613717 3 0.4392 0.23795 0.000 0.380 0.612 0 0.008
#> GSM613718 3 0.4063 0.43860 0.000 0.280 0.708 0 0.012
#> GSM613719 1 0.3452 0.53170 0.756 0.000 0.244 0 0.000
#> GSM613720 2 0.4165 0.54829 0.000 0.672 0.320 0 0.008
#> GSM613721 2 0.6791 0.42474 0.240 0.552 0.172 0 0.036
#> GSM613722 2 0.1310 0.77447 0.000 0.956 0.024 0 0.020
#> GSM613723 5 0.0912 0.82813 0.012 0.000 0.016 0 0.972
#> GSM613724 1 0.3876 0.56607 0.684 0.000 0.000 0 0.316
#> GSM613725 2 0.1800 0.77576 0.000 0.932 0.048 0 0.020
#> GSM613726 1 0.0960 0.72642 0.972 0.004 0.016 0 0.008
#> GSM613727 5 0.4291 -0.09144 0.464 0.000 0.000 0 0.536
#> GSM613728 2 0.1444 0.77154 0.000 0.948 0.040 0 0.012
#> GSM613729 1 0.0290 0.72975 0.992 0.000 0.000 0 0.008
#> GSM613730 2 0.6862 0.13991 0.276 0.452 0.264 0 0.008
#> GSM613731 3 0.4793 0.55494 0.236 0.004 0.704 0 0.056
#> GSM613732 2 0.4206 0.59933 0.000 0.696 0.288 0 0.016
#> GSM613733 2 0.1942 0.76478 0.000 0.920 0.068 0 0.012
#> GSM613734 5 0.1671 0.83726 0.076 0.000 0.000 0 0.924
#> GSM613735 5 0.1792 0.83421 0.084 0.000 0.000 0 0.916
#> GSM613736 2 0.4979 0.19302 0.000 0.492 0.480 0 0.028
#> GSM613737 3 0.5389 0.31218 0.036 0.012 0.552 0 0.400
#> GSM613738 5 0.2921 0.71139 0.124 0.000 0.020 0 0.856
#> GSM613739 5 0.1310 0.82396 0.024 0.000 0.020 0 0.956
#> GSM613740 2 0.3462 0.68602 0.000 0.792 0.196 0 0.012
#> GSM613741 1 0.4749 0.29899 0.628 0.348 0.008 0 0.016
#> GSM613742 5 0.1830 0.81663 0.040 0.000 0.028 0 0.932
#> GSM613743 2 0.3942 0.62029 0.000 0.728 0.260 0 0.012
#> GSM613744 2 0.3530 0.69039 0.000 0.784 0.204 0 0.012
#> GSM613745 2 0.7207 0.17008 0.344 0.428 0.196 0 0.032
#> GSM613746 2 0.0898 0.77458 0.000 0.972 0.008 0 0.020
#> GSM613747 5 0.1732 0.83650 0.080 0.000 0.000 0 0.920
#> GSM613748 3 0.5527 0.54240 0.228 0.076 0.672 0 0.024
#> GSM613749 1 0.5051 0.36792 0.640 0.316 0.032 0 0.012
#> GSM613750 4 0.0000 1.00000 0.000 0.000 0.000 1 0.000
#> GSM613751 4 0.0000 1.00000 0.000 0.000 0.000 1 0.000
#> GSM613752 4 0.0000 1.00000 0.000 0.000 0.000 1 0.000
#> GSM613753 4 0.0000 1.00000 0.000 0.000 0.000 1 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM613638 4 0.2416 0.6527 0.000 0.000 0.156 0.844 0.000 0
#> GSM613639 1 0.3819 0.4887 0.672 0.000 0.012 0.316 0.000 0
#> GSM613640 4 0.2531 0.6647 0.012 0.000 0.132 0.856 0.000 0
#> GSM613641 1 0.5352 0.5332 0.620 0.000 0.008 0.168 0.204 0
#> GSM613642 4 0.4017 0.6271 0.012 0.056 0.168 0.764 0.000 0
#> GSM613643 4 0.0692 0.6730 0.004 0.000 0.020 0.976 0.000 0
#> GSM613644 4 0.0632 0.6664 0.024 0.000 0.000 0.976 0.000 0
#> GSM613645 4 0.4093 0.2171 0.404 0.000 0.012 0.584 0.000 0
#> GSM613646 4 0.3946 0.5222 0.228 0.000 0.016 0.736 0.020 0
#> GSM613647 4 0.3134 0.6470 0.024 0.000 0.168 0.808 0.000 0
#> GSM613648 4 0.3198 0.5754 0.000 0.000 0.260 0.740 0.000 0
#> GSM613649 3 0.5350 0.3790 0.000 0.140 0.564 0.296 0.000 0
#> GSM613650 1 0.4084 0.3197 0.588 0.000 0.012 0.400 0.000 0
#> GSM613651 4 0.4909 0.4794 0.236 0.000 0.012 0.664 0.088 0
#> GSM613652 5 0.0632 0.8748 0.000 0.000 0.000 0.024 0.976 0
#> GSM613653 1 0.4114 0.6005 0.732 0.000 0.072 0.196 0.000 0
#> GSM613654 5 0.0632 0.8748 0.000 0.000 0.000 0.024 0.976 0
#> GSM613655 1 0.3769 0.4466 0.640 0.000 0.004 0.000 0.356 0
#> GSM613656 5 0.1765 0.8283 0.096 0.000 0.000 0.000 0.904 0
#> GSM613657 3 0.4153 0.2681 0.000 0.340 0.636 0.024 0.000 0
#> GSM613658 1 0.3975 0.3946 0.600 0.000 0.008 0.000 0.392 0
#> GSM613659 2 0.5781 0.3005 0.016 0.568 0.092 0.308 0.016 0
#> GSM613660 2 0.3073 0.6752 0.000 0.824 0.152 0.016 0.008 0
#> GSM613661 1 0.0914 0.6750 0.968 0.000 0.016 0.016 0.000 0
#> GSM613662 2 0.1863 0.7174 0.044 0.920 0.036 0.000 0.000 0
#> GSM613663 1 0.1141 0.6716 0.948 0.000 0.000 0.000 0.052 0
#> GSM613664 2 0.0146 0.7177 0.000 0.996 0.000 0.004 0.000 0
#> GSM613665 2 0.2553 0.6904 0.000 0.848 0.144 0.000 0.008 0
#> GSM613666 1 0.3323 0.5909 0.752 0.000 0.008 0.000 0.240 0
#> GSM613667 1 0.0260 0.6752 0.992 0.000 0.008 0.000 0.000 0
#> GSM613668 1 0.3445 0.5750 0.732 0.000 0.008 0.000 0.260 0
#> GSM613669 1 0.3190 0.6047 0.772 0.000 0.008 0.000 0.220 0
#> GSM613670 2 0.3355 0.6535 0.076 0.836 0.016 0.072 0.000 0
#> GSM613671 1 0.2743 0.6391 0.828 0.000 0.008 0.000 0.164 0
#> GSM613672 1 0.3314 0.5817 0.740 0.000 0.004 0.000 0.256 0
#> GSM613673 1 0.3359 0.6191 0.784 0.000 0.012 0.008 0.196 0
#> GSM613674 2 0.0865 0.7214 0.000 0.964 0.036 0.000 0.000 0
#> GSM613675 2 0.1757 0.7148 0.000 0.916 0.076 0.000 0.008 0
#> GSM613676 2 0.2416 0.6788 0.000 0.844 0.156 0.000 0.000 0
#> GSM613677 1 0.5081 0.4912 0.636 0.040 0.044 0.280 0.000 0
#> GSM613678 1 0.1086 0.6770 0.964 0.012 0.012 0.012 0.000 0
#> GSM613679 2 0.2003 0.6986 0.000 0.884 0.116 0.000 0.000 0
#> GSM613680 1 0.3398 0.5832 0.740 0.000 0.008 0.000 0.252 0
#> GSM613681 1 0.3271 0.5975 0.760 0.000 0.008 0.000 0.232 0
#> GSM613682 1 0.4171 0.5815 0.716 0.040 0.008 0.000 0.236 0
#> GSM613683 1 0.3672 0.5204 0.688 0.000 0.008 0.000 0.304 0
#> GSM613684 2 0.3168 0.6175 0.000 0.792 0.192 0.000 0.016 0
#> GSM613685 2 0.0713 0.7206 0.000 0.972 0.028 0.000 0.000 0
#> GSM613686 1 0.0000 0.6754 1.000 0.000 0.000 0.000 0.000 0
#> GSM613687 1 0.2400 0.6564 0.872 0.000 0.008 0.004 0.116 0
#> GSM613688 2 0.3448 0.6397 0.000 0.828 0.092 0.064 0.016 0
#> GSM613689 3 0.5684 0.3047 0.004 0.124 0.580 0.276 0.016 0
#> GSM613690 3 0.6674 0.1517 0.304 0.016 0.432 0.232 0.016 0
#> GSM613691 2 0.6272 0.1649 0.372 0.464 0.132 0.016 0.016 0
#> GSM613692 5 0.2219 0.7821 0.136 0.000 0.000 0.000 0.864 0
#> GSM613693 2 0.2562 0.6788 0.000 0.828 0.172 0.000 0.000 0
#> GSM613694 1 0.5969 0.3518 0.560 0.008 0.260 0.156 0.016 0
#> GSM613695 4 0.3665 0.5774 0.000 0.000 0.252 0.728 0.020 0
#> GSM613696 1 0.6754 0.1590 0.472 0.336 0.108 0.068 0.016 0
#> GSM613697 1 0.5069 0.2884 0.588 0.000 0.040 0.028 0.344 0
#> GSM613698 1 0.5597 0.5142 0.652 0.000 0.104 0.068 0.176 0
#> GSM613699 1 0.6657 0.4533 0.564 0.120 0.096 0.204 0.016 0
#> GSM613700 2 0.5640 0.1874 0.000 0.516 0.128 0.348 0.008 0
#> GSM613701 4 0.3099 0.5698 0.176 0.000 0.008 0.808 0.008 0
#> GSM613702 4 0.0405 0.6671 0.004 0.000 0.000 0.988 0.008 0
#> GSM613703 1 0.2912 0.6312 0.816 0.000 0.012 0.172 0.000 0
#> GSM613704 2 0.4523 0.5918 0.000 0.724 0.144 0.124 0.008 0
#> GSM613705 4 0.3053 0.6465 0.020 0.000 0.168 0.812 0.000 0
#> GSM613706 4 0.0603 0.6662 0.000 0.000 0.004 0.980 0.016 0
#> GSM613707 2 0.1267 0.7126 0.000 0.940 0.060 0.000 0.000 0
#> GSM613708 1 0.3510 0.6257 0.772 0.000 0.016 0.204 0.008 0
#> GSM613709 1 0.3442 0.6373 0.796 0.000 0.016 0.172 0.016 0
#> GSM613710 3 0.5945 0.2011 0.000 0.220 0.420 0.360 0.000 0
#> GSM613711 3 0.3588 0.5454 0.000 0.044 0.776 0.180 0.000 0
#> GSM613712 4 0.2383 0.6345 0.096 0.000 0.024 0.880 0.000 0
#> GSM613713 3 0.3867 0.1696 0.000 0.488 0.512 0.000 0.000 0
#> GSM613714 4 0.2664 0.6318 0.000 0.000 0.184 0.816 0.000 0
#> GSM613715 4 0.3547 0.4819 0.000 0.000 0.332 0.668 0.000 0
#> GSM613716 4 0.5303 0.4172 0.000 0.136 0.260 0.600 0.004 0
#> GSM613717 3 0.5675 0.1102 0.000 0.156 0.444 0.400 0.000 0
#> GSM613718 3 0.3202 0.5453 0.000 0.024 0.800 0.176 0.000 0
#> GSM613719 1 0.5126 0.5015 0.636 0.000 0.100 0.252 0.012 0
#> GSM613720 3 0.4419 0.3442 0.000 0.384 0.584 0.032 0.000 0
#> GSM613721 2 0.7857 0.1181 0.192 0.384 0.188 0.216 0.020 0
#> GSM613722 2 0.2553 0.6855 0.000 0.848 0.144 0.000 0.008 0
#> GSM613723 5 0.0632 0.8748 0.000 0.000 0.000 0.024 0.976 0
#> GSM613724 1 0.3937 0.3663 0.572 0.000 0.004 0.000 0.424 0
#> GSM613725 2 0.4015 0.4064 0.000 0.656 0.328 0.008 0.008 0
#> GSM613726 1 0.2230 0.6689 0.892 0.000 0.024 0.084 0.000 0
#> GSM613727 5 0.4032 0.1166 0.420 0.000 0.008 0.000 0.572 0
#> GSM613728 2 0.3706 0.6311 0.000 0.780 0.172 0.040 0.008 0
#> GSM613729 1 0.3252 0.6468 0.828 0.000 0.012 0.128 0.032 0
#> GSM613730 4 0.6887 0.2417 0.144 0.216 0.112 0.520 0.008 0
#> GSM613731 4 0.2805 0.6040 0.160 0.000 0.000 0.828 0.012 0
#> GSM613732 3 0.0713 0.6032 0.000 0.028 0.972 0.000 0.000 0
#> GSM613733 3 0.3615 0.3475 0.000 0.292 0.700 0.000 0.008 0
#> GSM613734 5 0.0632 0.8782 0.024 0.000 0.000 0.000 0.976 0
#> GSM613735 5 0.0632 0.8782 0.024 0.000 0.000 0.000 0.976 0
#> GSM613736 3 0.3493 0.5430 0.000 0.228 0.756 0.008 0.008 0
#> GSM613737 4 0.6154 0.2424 0.020 0.000 0.168 0.460 0.352 0
#> GSM613738 5 0.2726 0.7465 0.112 0.000 0.000 0.032 0.856 0
#> GSM613739 5 0.1151 0.8691 0.012 0.000 0.000 0.032 0.956 0
#> GSM613740 3 0.2431 0.5886 0.000 0.132 0.860 0.000 0.008 0
#> GSM613741 1 0.6628 0.4746 0.588 0.092 0.116 0.176 0.028 0
#> GSM613742 5 0.1794 0.8611 0.036 0.000 0.000 0.040 0.924 0
#> GSM613743 3 0.2389 0.5909 0.000 0.128 0.864 0.000 0.008 0
#> GSM613744 3 0.1745 0.5886 0.000 0.068 0.920 0.000 0.012 0
#> GSM613745 4 0.7778 -0.0197 0.124 0.208 0.220 0.416 0.032 0
#> GSM613746 2 0.2948 0.6312 0.000 0.804 0.188 0.000 0.008 0
#> GSM613747 5 0.0777 0.8772 0.024 0.000 0.004 0.000 0.972 0
#> GSM613748 4 0.3447 0.5941 0.156 0.008 0.020 0.808 0.008 0
#> GSM613749 1 0.6202 0.5011 0.608 0.076 0.108 0.196 0.012 0
#> GSM613750 6 0.0000 1.0000 0.000 0.000 0.000 0.000 0.000 1
#> GSM613751 6 0.0000 1.0000 0.000 0.000 0.000 0.000 0.000 1
#> GSM613752 6 0.0000 1.0000 0.000 0.000 0.000 0.000 0.000 1
#> GSM613753 6 0.0000 1.0000 0.000 0.000 0.000 0.000 0.000 1
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) k
#> CV:pam 82 8.15e-03 2
#> CV:pam 93 1.80e-03 3
#> CV:pam 95 4.25e-07 4
#> CV:pam 92 4.46e-08 5
#> CV:pam 83 2.80e-08 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["CV", "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 27425 rows and 116 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 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 0.945 0.934 0.973 0.1239 0.886 0.886
#> 3 3 0.207 0.593 0.808 2.4405 0.637 0.607
#> 4 4 0.423 0.586 0.803 0.4388 0.669 0.482
#> 5 5 0.615 0.746 0.812 0.1817 0.936 0.822
#> 6 6 0.811 0.852 0.916 0.0962 0.836 0.518
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
#> GSM613638 1 0.0000 0.9787 1.000 0.000
#> GSM613639 1 0.0000 0.9787 1.000 0.000
#> GSM613640 1 0.0000 0.9787 1.000 0.000
#> GSM613641 1 0.0000 0.9787 1.000 0.000
#> GSM613642 1 0.0000 0.9787 1.000 0.000
#> GSM613643 1 0.0000 0.9787 1.000 0.000
#> GSM613644 1 0.0000 0.9787 1.000 0.000
#> GSM613645 1 0.0000 0.9787 1.000 0.000
#> GSM613646 1 0.0000 0.9787 1.000 0.000
#> GSM613647 1 0.0000 0.9787 1.000 0.000
#> GSM613648 1 0.0000 0.9787 1.000 0.000
#> GSM613649 1 0.0000 0.9787 1.000 0.000
#> GSM613650 1 0.0000 0.9787 1.000 0.000
#> GSM613651 1 0.0000 0.9787 1.000 0.000
#> GSM613652 1 0.0000 0.9787 1.000 0.000
#> GSM613653 1 0.0000 0.9787 1.000 0.000
#> GSM613654 1 0.0000 0.9787 1.000 0.000
#> GSM613655 1 0.0000 0.9787 1.000 0.000
#> GSM613656 1 0.0000 0.9787 1.000 0.000
#> GSM613657 1 0.0938 0.9687 0.988 0.012
#> GSM613658 1 0.0000 0.9787 1.000 0.000
#> GSM613659 1 0.0000 0.9787 1.000 0.000
#> GSM613660 1 0.0672 0.9723 0.992 0.008
#> GSM613661 1 0.0000 0.9787 1.000 0.000
#> GSM613662 1 0.8267 0.5482 0.740 0.260
#> GSM613663 1 0.0000 0.9787 1.000 0.000
#> GSM613664 1 0.9732 0.0528 0.596 0.404
#> GSM613665 1 0.0000 0.9787 1.000 0.000
#> GSM613666 1 0.0000 0.9787 1.000 0.000
#> GSM613667 1 0.0000 0.9787 1.000 0.000
#> GSM613668 1 0.0000 0.9787 1.000 0.000
#> GSM613669 1 0.0000 0.9787 1.000 0.000
#> GSM613670 1 0.0000 0.9787 1.000 0.000
#> GSM613671 1 0.0000 0.9787 1.000 0.000
#> GSM613672 1 0.0000 0.9787 1.000 0.000
#> GSM613673 1 0.0000 0.9787 1.000 0.000
#> GSM613674 2 0.9881 0.4250 0.436 0.564
#> GSM613675 1 0.7950 0.6059 0.760 0.240
#> GSM613676 1 0.3114 0.9189 0.944 0.056
#> GSM613677 1 0.0000 0.9787 1.000 0.000
#> GSM613678 1 0.0000 0.9787 1.000 0.000
#> GSM613679 1 0.1633 0.9583 0.976 0.024
#> GSM613680 1 0.0000 0.9787 1.000 0.000
#> GSM613681 1 0.0000 0.9787 1.000 0.000
#> GSM613682 1 0.0000 0.9787 1.000 0.000
#> GSM613683 1 0.0000 0.9787 1.000 0.000
#> GSM613684 2 0.9044 0.6087 0.320 0.680
#> GSM613685 2 0.9933 0.3820 0.452 0.548
#> GSM613686 1 0.0000 0.9787 1.000 0.000
#> GSM613687 1 0.0000 0.9787 1.000 0.000
#> GSM613688 1 0.0000 0.9787 1.000 0.000
#> GSM613689 1 0.0000 0.9787 1.000 0.000
#> GSM613690 1 0.0000 0.9787 1.000 0.000
#> GSM613691 1 0.0000 0.9787 1.000 0.000
#> GSM613692 1 0.0000 0.9787 1.000 0.000
#> GSM613693 1 0.4298 0.8775 0.912 0.088
#> GSM613694 1 0.0000 0.9787 1.000 0.000
#> GSM613695 1 0.0000 0.9787 1.000 0.000
#> GSM613696 1 0.0000 0.9787 1.000 0.000
#> GSM613697 1 0.0000 0.9787 1.000 0.000
#> GSM613698 1 0.0000 0.9787 1.000 0.000
#> GSM613699 1 0.0000 0.9787 1.000 0.000
#> GSM613700 1 0.7528 0.6751 0.784 0.216
#> GSM613701 1 0.0000 0.9787 1.000 0.000
#> GSM613702 1 0.0000 0.9787 1.000 0.000
#> GSM613703 1 0.0000 0.9787 1.000 0.000
#> GSM613704 1 0.1414 0.9603 0.980 0.020
#> GSM613705 1 0.0000 0.9787 1.000 0.000
#> GSM613706 1 0.0000 0.9787 1.000 0.000
#> GSM613707 1 0.5737 0.8081 0.864 0.136
#> GSM613708 1 0.0000 0.9787 1.000 0.000
#> GSM613709 1 0.0000 0.9787 1.000 0.000
#> GSM613710 1 0.1184 0.9650 0.984 0.016
#> GSM613711 1 0.0672 0.9722 0.992 0.008
#> GSM613712 1 0.0000 0.9787 1.000 0.000
#> GSM613713 1 0.0376 0.9755 0.996 0.004
#> GSM613714 1 0.0000 0.9787 1.000 0.000
#> GSM613715 1 0.0000 0.9787 1.000 0.000
#> GSM613716 1 0.0000 0.9787 1.000 0.000
#> GSM613717 1 0.0000 0.9787 1.000 0.000
#> GSM613718 1 0.1843 0.9534 0.972 0.028
#> GSM613719 1 0.0000 0.9787 1.000 0.000
#> GSM613720 1 0.0000 0.9787 1.000 0.000
#> GSM613721 1 0.0000 0.9787 1.000 0.000
#> GSM613722 1 0.2043 0.9493 0.968 0.032
#> GSM613723 1 0.0000 0.9787 1.000 0.000
#> GSM613724 1 0.0000 0.9787 1.000 0.000
#> GSM613725 1 0.2778 0.9311 0.952 0.048
#> GSM613726 1 0.0000 0.9787 1.000 0.000
#> GSM613727 1 0.0000 0.9787 1.000 0.000
#> GSM613728 1 0.0000 0.9787 1.000 0.000
#> GSM613729 1 0.0000 0.9787 1.000 0.000
#> GSM613730 1 0.0000 0.9787 1.000 0.000
#> GSM613731 1 0.0000 0.9787 1.000 0.000
#> GSM613732 1 0.1843 0.9535 0.972 0.028
#> GSM613733 1 0.0938 0.9687 0.988 0.012
#> GSM613734 1 0.0000 0.9787 1.000 0.000
#> GSM613735 1 0.0000 0.9787 1.000 0.000
#> GSM613736 1 0.0000 0.9787 1.000 0.000
#> GSM613737 1 0.0000 0.9787 1.000 0.000
#> GSM613738 1 0.0000 0.9787 1.000 0.000
#> GSM613739 1 0.0000 0.9787 1.000 0.000
#> GSM613740 1 0.2236 0.9450 0.964 0.036
#> GSM613741 1 0.0000 0.9787 1.000 0.000
#> GSM613742 1 0.0000 0.9787 1.000 0.000
#> GSM613743 1 0.0938 0.9688 0.988 0.012
#> GSM613744 1 0.0000 0.9787 1.000 0.000
#> GSM613745 1 0.0000 0.9787 1.000 0.000
#> GSM613746 1 0.7056 0.7124 0.808 0.192
#> GSM613747 1 0.0000 0.9787 1.000 0.000
#> GSM613748 1 0.0000 0.9787 1.000 0.000
#> GSM613749 1 0.0000 0.9787 1.000 0.000
#> GSM613750 2 0.0000 0.7909 0.000 1.000
#> GSM613751 2 0.0000 0.7909 0.000 1.000
#> GSM613752 2 0.0000 0.7909 0.000 1.000
#> GSM613753 2 0.0000 0.7909 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM613638 3 0.2711 0.706 0.088 0 0.912
#> GSM613639 3 0.6260 0.243 0.448 0 0.552
#> GSM613640 3 0.0592 0.728 0.012 0 0.988
#> GSM613641 1 0.5529 0.644 0.704 0 0.296
#> GSM613642 3 0.0424 0.727 0.008 0 0.992
#> GSM613643 3 0.4235 0.653 0.176 0 0.824
#> GSM613644 3 0.4291 0.666 0.180 0 0.820
#> GSM613645 3 0.6286 0.178 0.464 0 0.536
#> GSM613646 3 0.4842 0.684 0.224 0 0.776
#> GSM613647 3 0.1643 0.730 0.044 0 0.956
#> GSM613648 3 0.0000 0.724 0.000 0 1.000
#> GSM613649 3 0.0000 0.724 0.000 0 1.000
#> GSM613650 3 0.5497 0.505 0.292 0 0.708
#> GSM613651 3 0.2878 0.701 0.096 0 0.904
#> GSM613652 3 0.6260 -0.122 0.448 0 0.552
#> GSM613653 3 0.5650 0.605 0.312 0 0.688
#> GSM613654 3 0.6260 -0.122 0.448 0 0.552
#> GSM613655 1 0.4291 0.729 0.820 0 0.180
#> GSM613656 1 0.6286 0.339 0.536 0 0.464
#> GSM613657 3 0.0000 0.724 0.000 0 1.000
#> GSM613658 1 0.5733 0.538 0.676 0 0.324
#> GSM613659 3 0.5948 0.555 0.360 0 0.640
#> GSM613660 3 0.4750 0.631 0.216 0 0.784
#> GSM613661 1 0.5291 0.649 0.732 0 0.268
#> GSM613662 3 0.5988 0.550 0.368 0 0.632
#> GSM613663 1 0.1411 0.654 0.964 0 0.036
#> GSM613664 3 0.5988 0.550 0.368 0 0.632
#> GSM613665 3 0.4887 0.623 0.228 0 0.772
#> GSM613666 1 0.0424 0.627 0.992 0 0.008
#> GSM613667 1 0.3879 0.732 0.848 0 0.152
#> GSM613668 1 0.1411 0.654 0.964 0 0.036
#> GSM613669 1 0.3879 0.732 0.848 0 0.152
#> GSM613670 3 0.5948 0.555 0.360 0 0.640
#> GSM613671 1 0.1163 0.659 0.972 0 0.028
#> GSM613672 1 0.4121 0.732 0.832 0 0.168
#> GSM613673 1 0.1529 0.653 0.960 0 0.040
#> GSM613674 3 0.4974 0.623 0.236 0 0.764
#> GSM613675 3 0.5988 0.550 0.368 0 0.632
#> GSM613676 3 0.4654 0.637 0.208 0 0.792
#> GSM613677 3 0.4291 0.667 0.180 0 0.820
#> GSM613678 3 0.5948 0.555 0.360 0 0.640
#> GSM613679 3 0.4887 0.623 0.228 0 0.772
#> GSM613680 1 0.1411 0.654 0.964 0 0.036
#> GSM613681 1 0.0424 0.627 0.992 0 0.008
#> GSM613682 1 0.5785 0.531 0.668 0 0.332
#> GSM613683 1 0.5835 0.524 0.660 0 0.340
#> GSM613684 3 0.5497 0.612 0.292 0 0.708
#> GSM613685 3 0.4931 0.623 0.232 0 0.768
#> GSM613686 1 0.3879 0.732 0.848 0 0.152
#> GSM613687 1 0.1411 0.654 0.964 0 0.036
#> GSM613688 3 0.5835 0.573 0.340 0 0.660
#> GSM613689 3 0.0424 0.727 0.008 0 0.992
#> GSM613690 3 0.0424 0.727 0.008 0 0.992
#> GSM613691 3 0.5926 0.561 0.356 0 0.644
#> GSM613692 1 0.6225 0.408 0.568 0 0.432
#> GSM613693 3 0.5760 0.591 0.328 0 0.672
#> GSM613694 3 0.3551 0.698 0.132 0 0.868
#> GSM613695 3 0.0424 0.727 0.008 0 0.992
#> GSM613696 3 0.5621 0.604 0.308 0 0.692
#> GSM613697 3 0.3752 0.663 0.144 0 0.856
#> GSM613698 3 0.3192 0.715 0.112 0 0.888
#> GSM613699 3 0.2537 0.736 0.080 0 0.920
#> GSM613700 3 0.3038 0.714 0.104 0 0.896
#> GSM613701 3 0.4504 0.699 0.196 0 0.804
#> GSM613702 3 0.3551 0.722 0.132 0 0.868
#> GSM613703 1 0.4931 0.699 0.768 0 0.232
#> GSM613704 3 0.5216 0.664 0.260 0 0.740
#> GSM613705 3 0.0592 0.727 0.012 0 0.988
#> GSM613706 3 0.4002 0.709 0.160 0 0.840
#> GSM613707 3 0.5016 0.624 0.240 0 0.760
#> GSM613708 1 0.6286 0.273 0.536 0 0.464
#> GSM613709 1 0.5363 0.659 0.724 0 0.276
#> GSM613710 3 0.0000 0.724 0.000 0 1.000
#> GSM613711 3 0.0000 0.724 0.000 0 1.000
#> GSM613712 3 0.3267 0.713 0.116 0 0.884
#> GSM613713 3 0.0000 0.724 0.000 0 1.000
#> GSM613714 3 0.0424 0.727 0.008 0 0.992
#> GSM613715 3 0.0592 0.728 0.012 0 0.988
#> GSM613716 3 0.3941 0.705 0.156 0 0.844
#> GSM613717 3 0.0000 0.724 0.000 0 1.000
#> GSM613718 3 0.0000 0.724 0.000 0 1.000
#> GSM613719 3 0.4750 0.651 0.216 0 0.784
#> GSM613720 3 0.3879 0.706 0.152 0 0.848
#> GSM613721 3 0.5138 0.665 0.252 0 0.748
#> GSM613722 3 0.2959 0.716 0.100 0 0.900
#> GSM613723 3 0.6260 -0.122 0.448 0 0.552
#> GSM613724 1 0.6309 0.246 0.504 0 0.496
#> GSM613725 3 0.3038 0.714 0.104 0 0.896
#> GSM613726 3 0.6252 0.175 0.444 0 0.556
#> GSM613727 1 0.5529 0.653 0.704 0 0.296
#> GSM613728 3 0.4842 0.688 0.224 0 0.776
#> GSM613729 1 0.5363 0.659 0.724 0 0.276
#> GSM613730 3 0.4931 0.679 0.232 0 0.768
#> GSM613731 3 0.3941 0.689 0.156 0 0.844
#> GSM613732 3 0.0000 0.724 0.000 0 1.000
#> GSM613733 3 0.0000 0.724 0.000 0 1.000
#> GSM613734 3 0.6260 -0.122 0.448 0 0.552
#> GSM613735 3 0.6274 -0.142 0.456 0 0.544
#> GSM613736 3 0.0237 0.726 0.004 0 0.996
#> GSM613737 3 0.2537 0.707 0.080 0 0.920
#> GSM613738 3 0.6274 -0.142 0.456 0 0.544
#> GSM613739 3 0.6260 -0.122 0.448 0 0.552
#> GSM613740 3 0.0000 0.724 0.000 0 1.000
#> GSM613741 3 0.5363 0.647 0.276 0 0.724
#> GSM613742 3 0.6267 -0.132 0.452 0 0.548
#> GSM613743 3 0.0000 0.724 0.000 0 1.000
#> GSM613744 3 0.0000 0.724 0.000 0 1.000
#> GSM613745 3 0.4452 0.698 0.192 0 0.808
#> GSM613746 3 0.5835 0.590 0.340 0 0.660
#> GSM613747 3 0.6280 -0.151 0.460 0 0.540
#> GSM613748 3 0.2878 0.732 0.096 0 0.904
#> GSM613749 3 0.5465 0.617 0.288 0 0.712
#> GSM613750 2 0.0000 1.000 0.000 1 0.000
#> GSM613751 2 0.0000 1.000 0.000 1 0.000
#> GSM613752 2 0.0000 1.000 0.000 1 0.000
#> GSM613753 2 0.0000 1.000 0.000 1 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 3 0.3219 0.6553 0.164 0.000 0.836 0
#> GSM613639 3 0.7414 0.1406 0.320 0.188 0.492 0
#> GSM613640 3 0.0000 0.7864 0.000 0.000 1.000 0
#> GSM613641 1 0.6570 0.4624 0.580 0.100 0.320 0
#> GSM613642 3 0.0188 0.7863 0.000 0.004 0.996 0
#> GSM613643 3 0.4643 0.2937 0.344 0.000 0.656 0
#> GSM613644 3 0.4624 0.3085 0.340 0.000 0.660 0
#> GSM613645 1 0.7566 0.1935 0.416 0.192 0.392 0
#> GSM613646 3 0.6646 0.4806 0.172 0.204 0.624 0
#> GSM613647 3 0.0592 0.7825 0.016 0.000 0.984 0
#> GSM613648 3 0.0336 0.7861 0.000 0.008 0.992 0
#> GSM613649 3 0.0592 0.7846 0.000 0.016 0.984 0
#> GSM613650 3 0.6141 0.2862 0.300 0.076 0.624 0
#> GSM613651 3 0.3356 0.6402 0.176 0.000 0.824 0
#> GSM613652 1 0.5388 0.4084 0.532 0.012 0.456 0
#> GSM613653 3 0.7433 0.2051 0.288 0.208 0.504 0
#> GSM613654 1 0.5388 0.4084 0.532 0.012 0.456 0
#> GSM613655 1 0.0188 0.5549 0.996 0.004 0.000 0
#> GSM613656 1 0.5388 0.4084 0.532 0.012 0.456 0
#> GSM613657 3 0.0592 0.7846 0.000 0.016 0.984 0
#> GSM613658 1 0.1022 0.5414 0.968 0.032 0.000 0
#> GSM613659 2 0.0921 0.6836 0.000 0.972 0.028 0
#> GSM613660 2 0.4830 0.5117 0.000 0.608 0.392 0
#> GSM613661 1 0.0524 0.5580 0.988 0.004 0.008 0
#> GSM613662 2 0.2021 0.6829 0.040 0.936 0.024 0
#> GSM613663 1 0.0188 0.5549 0.996 0.004 0.000 0
#> GSM613664 2 0.2197 0.6801 0.048 0.928 0.024 0
#> GSM613665 2 0.4964 0.6575 0.032 0.724 0.244 0
#> GSM613666 1 0.3400 0.4639 0.820 0.180 0.000 0
#> GSM613667 1 0.3978 0.4593 0.796 0.192 0.012 0
#> GSM613668 1 0.0188 0.5549 0.996 0.004 0.000 0
#> GSM613669 1 0.3400 0.4638 0.820 0.180 0.000 0
#> GSM613670 2 0.3548 0.6696 0.068 0.864 0.068 0
#> GSM613671 1 0.3528 0.4532 0.808 0.192 0.000 0
#> GSM613672 1 0.0524 0.5604 0.988 0.004 0.008 0
#> GSM613673 1 0.0376 0.5548 0.992 0.004 0.004 0
#> GSM613674 2 0.3311 0.6935 0.000 0.828 0.172 0
#> GSM613675 2 0.0817 0.6846 0.000 0.976 0.024 0
#> GSM613676 2 0.3837 0.6579 0.000 0.776 0.224 0
#> GSM613677 3 0.2053 0.7574 0.004 0.072 0.924 0
#> GSM613678 2 0.4562 0.5365 0.208 0.764 0.028 0
#> GSM613679 2 0.6357 0.5089 0.068 0.544 0.388 0
#> GSM613680 1 0.0188 0.5549 0.996 0.004 0.000 0
#> GSM613681 1 0.2921 0.4915 0.860 0.140 0.000 0
#> GSM613682 1 0.0707 0.5455 0.980 0.020 0.000 0
#> GSM613683 1 0.0469 0.5546 0.988 0.012 0.000 0
#> GSM613684 2 0.2760 0.7070 0.000 0.872 0.128 0
#> GSM613685 2 0.3837 0.6579 0.000 0.776 0.224 0
#> GSM613686 1 0.3710 0.4521 0.804 0.192 0.004 0
#> GSM613687 1 0.0188 0.5549 0.996 0.004 0.000 0
#> GSM613688 2 0.1940 0.7049 0.000 0.924 0.076 0
#> GSM613689 3 0.0000 0.7864 0.000 0.000 1.000 0
#> GSM613690 3 0.0188 0.7863 0.000 0.004 0.996 0
#> GSM613691 2 0.5810 0.4671 0.064 0.660 0.276 0
#> GSM613692 1 0.5277 0.4005 0.532 0.008 0.460 0
#> GSM613693 2 0.0817 0.6846 0.000 0.976 0.024 0
#> GSM613694 3 0.0707 0.7818 0.020 0.000 0.980 0
#> GSM613695 3 0.0000 0.7864 0.000 0.000 1.000 0
#> GSM613696 2 0.4663 0.6507 0.012 0.716 0.272 0
#> GSM613697 3 0.5097 -0.0839 0.428 0.004 0.568 0
#> GSM613698 3 0.4193 0.4870 0.268 0.000 0.732 0
#> GSM613699 3 0.1661 0.7673 0.052 0.004 0.944 0
#> GSM613700 3 0.3761 0.7122 0.068 0.080 0.852 0
#> GSM613701 3 0.3052 0.7044 0.136 0.004 0.860 0
#> GSM613702 3 0.3052 0.7044 0.136 0.004 0.860 0
#> GSM613703 1 0.7318 0.4274 0.524 0.196 0.280 0
#> GSM613704 2 0.6452 -0.2198 0.068 0.468 0.464 0
#> GSM613705 3 0.0000 0.7864 0.000 0.000 1.000 0
#> GSM613706 3 0.3052 0.7044 0.136 0.004 0.860 0
#> GSM613707 2 0.3123 0.7006 0.000 0.844 0.156 0
#> GSM613708 1 0.5143 0.4827 0.628 0.012 0.360 0
#> GSM613709 1 0.6052 0.4858 0.616 0.064 0.320 0
#> GSM613710 3 0.0592 0.7846 0.000 0.016 0.984 0
#> GSM613711 3 0.0592 0.7846 0.000 0.016 0.984 0
#> GSM613712 3 0.3688 0.5960 0.208 0.000 0.792 0
#> GSM613713 3 0.0921 0.7841 0.000 0.028 0.972 0
#> GSM613714 3 0.0000 0.7864 0.000 0.000 1.000 0
#> GSM613715 3 0.0188 0.7863 0.000 0.004 0.996 0
#> GSM613716 3 0.4072 0.6274 0.000 0.252 0.748 0
#> GSM613717 3 0.0592 0.7846 0.000 0.016 0.984 0
#> GSM613718 3 0.0592 0.7846 0.000 0.016 0.984 0
#> GSM613719 3 0.5940 0.5229 0.120 0.188 0.692 0
#> GSM613720 3 0.4605 0.5418 0.000 0.336 0.664 0
#> GSM613721 3 0.6737 0.2622 0.092 0.420 0.488 0
#> GSM613722 3 0.3761 0.7122 0.068 0.080 0.852 0
#> GSM613723 1 0.5388 0.4084 0.532 0.012 0.456 0
#> GSM613724 1 0.5388 0.4084 0.532 0.012 0.456 0
#> GSM613725 3 0.3761 0.7122 0.068 0.080 0.852 0
#> GSM613726 1 0.4889 0.4600 0.636 0.004 0.360 0
#> GSM613727 1 0.4699 0.5078 0.676 0.004 0.320 0
#> GSM613728 3 0.5901 0.5542 0.068 0.280 0.652 0
#> GSM613729 1 0.7414 0.3823 0.492 0.188 0.320 0
#> GSM613730 3 0.6194 0.5425 0.132 0.200 0.668 0
#> GSM613731 3 0.3400 0.6937 0.180 0.000 0.820 0
#> GSM613732 3 0.0336 0.7861 0.000 0.008 0.992 0
#> GSM613733 3 0.0592 0.7846 0.000 0.016 0.984 0
#> GSM613734 1 0.5388 0.4084 0.532 0.012 0.456 0
#> GSM613735 1 0.5388 0.4084 0.532 0.012 0.456 0
#> GSM613736 3 0.0336 0.7867 0.000 0.008 0.992 0
#> GSM613737 3 0.0000 0.7864 0.000 0.000 1.000 0
#> GSM613738 1 0.5388 0.4084 0.532 0.012 0.456 0
#> GSM613739 1 0.5388 0.4084 0.532 0.012 0.456 0
#> GSM613740 3 0.0188 0.7863 0.000 0.004 0.996 0
#> GSM613741 3 0.7519 0.2284 0.256 0.248 0.496 0
#> GSM613742 1 0.5388 0.4084 0.532 0.012 0.456 0
#> GSM613743 3 0.0592 0.7846 0.000 0.016 0.984 0
#> GSM613744 3 0.0592 0.7846 0.000 0.016 0.984 0
#> GSM613745 3 0.6317 0.4959 0.096 0.280 0.624 0
#> GSM613746 2 0.2704 0.6688 0.000 0.876 0.124 0
#> GSM613747 1 0.5372 0.4185 0.544 0.012 0.444 0
#> GSM613748 3 0.2125 0.7537 0.076 0.004 0.920 0
#> GSM613749 3 0.7386 0.1488 0.320 0.184 0.496 0
#> GSM613750 4 0.0000 1.0000 0.000 0.000 0.000 1
#> GSM613751 4 0.0000 1.0000 0.000 0.000 0.000 1
#> GSM613752 4 0.0000 1.0000 0.000 0.000 0.000 1
#> GSM613753 4 0.0000 1.0000 0.000 0.000 0.000 1
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM613638 3 0.2179 0.7268 0.004 0.000 0.896 0 0.100
#> GSM613639 3 0.4787 0.5190 0.324 0.036 0.640 0 0.000
#> GSM613640 3 0.0290 0.7630 0.000 0.000 0.992 0 0.008
#> GSM613641 1 0.0671 0.8634 0.980 0.004 0.000 0 0.016
#> GSM613642 3 0.1430 0.7627 0.000 0.052 0.944 0 0.004
#> GSM613643 3 0.2798 0.7002 0.008 0.000 0.852 0 0.140
#> GSM613644 3 0.3748 0.7127 0.056 0.020 0.836 0 0.088
#> GSM613645 1 0.5911 0.0395 0.488 0.104 0.408 0 0.000
#> GSM613646 3 0.4822 0.6349 0.076 0.220 0.704 0 0.000
#> GSM613647 3 0.0324 0.7631 0.004 0.000 0.992 0 0.004
#> GSM613648 3 0.3661 0.7341 0.000 0.000 0.724 0 0.276
#> GSM613649 3 0.3661 0.7341 0.000 0.000 0.724 0 0.276
#> GSM613650 3 0.4219 0.6219 0.264 0.016 0.716 0 0.004
#> GSM613651 3 0.3421 0.6442 0.008 0.000 0.788 0 0.204
#> GSM613652 5 0.3730 0.9155 0.288 0.000 0.000 0 0.712
#> GSM613653 3 0.5544 0.5796 0.168 0.184 0.648 0 0.000
#> GSM613654 5 0.3730 0.9155 0.288 0.000 0.000 0 0.712
#> GSM613655 1 0.1410 0.8590 0.940 0.000 0.000 0 0.060
#> GSM613656 5 0.3730 0.9155 0.288 0.000 0.000 0 0.712
#> GSM613657 3 0.3684 0.7339 0.000 0.000 0.720 0 0.280
#> GSM613658 1 0.1121 0.8680 0.956 0.000 0.000 0 0.044
#> GSM613659 2 0.0162 0.8069 0.000 0.996 0.004 0 0.000
#> GSM613660 2 0.5808 0.5519 0.000 0.608 0.232 0 0.160
#> GSM613661 1 0.1251 0.8474 0.956 0.000 0.036 0 0.008
#> GSM613662 2 0.0000 0.8072 0.000 1.000 0.000 0 0.000
#> GSM613663 1 0.1043 0.8687 0.960 0.000 0.000 0 0.040
#> GSM613664 2 0.0000 0.8072 0.000 1.000 0.000 0 0.000
#> GSM613665 2 0.4478 0.7403 0.000 0.756 0.100 0 0.144
#> GSM613666 1 0.0162 0.8649 0.996 0.004 0.000 0 0.000
#> GSM613667 1 0.2645 0.7703 0.888 0.068 0.044 0 0.000
#> GSM613668 1 0.1270 0.8648 0.948 0.000 0.000 0 0.052
#> GSM613669 1 0.0162 0.8649 0.996 0.004 0.000 0 0.000
#> GSM613670 2 0.1792 0.7570 0.000 0.916 0.084 0 0.000
#> GSM613671 1 0.0162 0.8649 0.996 0.004 0.000 0 0.000
#> GSM613672 1 0.2471 0.7725 0.864 0.000 0.000 0 0.136
#> GSM613673 1 0.3535 0.7706 0.832 0.000 0.080 0 0.088
#> GSM613674 2 0.3359 0.7984 0.000 0.844 0.072 0 0.084
#> GSM613675 2 0.0000 0.8072 0.000 1.000 0.000 0 0.000
#> GSM613676 2 0.3967 0.7675 0.000 0.800 0.108 0 0.092
#> GSM613677 3 0.3810 0.7393 0.000 0.100 0.812 0 0.088
#> GSM613678 2 0.3151 0.6877 0.020 0.836 0.144 0 0.000
#> GSM613679 2 0.4630 0.7263 0.000 0.744 0.116 0 0.140
#> GSM613680 1 0.1197 0.8665 0.952 0.000 0.000 0 0.048
#> GSM613681 1 0.0162 0.8649 0.996 0.004 0.000 0 0.000
#> GSM613682 1 0.1270 0.8648 0.948 0.000 0.000 0 0.052
#> GSM613683 1 0.1908 0.8316 0.908 0.000 0.000 0 0.092
#> GSM613684 2 0.2654 0.8144 0.000 0.888 0.064 0 0.048
#> GSM613685 2 0.4020 0.7657 0.000 0.796 0.108 0 0.096
#> GSM613686 1 0.1877 0.8083 0.924 0.064 0.012 0 0.000
#> GSM613687 1 0.1270 0.8648 0.948 0.000 0.000 0 0.052
#> GSM613688 2 0.1800 0.8215 0.000 0.932 0.048 0 0.020
#> GSM613689 3 0.1836 0.7658 0.000 0.036 0.932 0 0.032
#> GSM613690 3 0.2473 0.7637 0.000 0.032 0.896 0 0.072
#> GSM613691 2 0.0000 0.8072 0.000 1.000 0.000 0 0.000
#> GSM613692 1 0.3210 0.6183 0.788 0.000 0.000 0 0.212
#> GSM613693 2 0.1205 0.8167 0.000 0.956 0.004 0 0.040
#> GSM613694 3 0.0798 0.7602 0.008 0.000 0.976 0 0.016
#> GSM613695 3 0.0955 0.7639 0.000 0.028 0.968 0 0.004
#> GSM613696 2 0.5258 0.5970 0.064 0.636 0.296 0 0.004
#> GSM613697 5 0.3934 0.4534 0.008 0.000 0.276 0 0.716
#> GSM613698 3 0.2937 0.7371 0.040 0.016 0.884 0 0.060
#> GSM613699 3 0.0324 0.7632 0.004 0.000 0.992 0 0.004
#> GSM613700 3 0.5774 0.6215 0.000 0.156 0.612 0 0.232
#> GSM613701 3 0.2624 0.7131 0.012 0.116 0.872 0 0.000
#> GSM613702 3 0.2074 0.7632 0.000 0.036 0.920 0 0.044
#> GSM613703 1 0.2127 0.7724 0.892 0.108 0.000 0 0.000
#> GSM613704 2 0.2707 0.7520 0.000 0.876 0.024 0 0.100
#> GSM613705 3 0.0404 0.7631 0.000 0.000 0.988 0 0.012
#> GSM613706 3 0.0404 0.7631 0.000 0.000 0.988 0 0.012
#> GSM613707 2 0.3297 0.8005 0.000 0.848 0.068 0 0.084
#> GSM613708 1 0.2561 0.7337 0.856 0.000 0.000 0 0.144
#> GSM613709 1 0.0671 0.8634 0.980 0.004 0.000 0 0.016
#> GSM613710 3 0.3684 0.7339 0.000 0.000 0.720 0 0.280
#> GSM613711 3 0.3661 0.7341 0.000 0.000 0.724 0 0.276
#> GSM613712 3 0.2124 0.7290 0.004 0.000 0.900 0 0.096
#> GSM613713 3 0.3661 0.7341 0.000 0.000 0.724 0 0.276
#> GSM613714 3 0.3366 0.7451 0.000 0.000 0.768 0 0.232
#> GSM613715 3 0.3790 0.7342 0.000 0.004 0.724 0 0.272
#> GSM613716 3 0.5112 0.6730 0.000 0.256 0.664 0 0.080
#> GSM613717 3 0.3661 0.7341 0.000 0.000 0.724 0 0.276
#> GSM613718 3 0.3661 0.7341 0.000 0.000 0.724 0 0.276
#> GSM613719 3 0.4219 0.7062 0.116 0.104 0.780 0 0.000
#> GSM613720 3 0.6072 0.5973 0.000 0.292 0.552 0 0.156
#> GSM613721 3 0.4307 0.2304 0.000 0.500 0.500 0 0.000
#> GSM613722 3 0.5750 0.6241 0.000 0.156 0.616 0 0.228
#> GSM613723 5 0.3730 0.9155 0.288 0.000 0.000 0 0.712
#> GSM613724 5 0.3913 0.8735 0.324 0.000 0.000 0 0.676
#> GSM613725 3 0.5831 0.6108 0.000 0.160 0.604 0 0.236
#> GSM613726 3 0.5304 0.2495 0.384 0.000 0.560 0 0.056
#> GSM613727 1 0.1341 0.8637 0.944 0.000 0.000 0 0.056
#> GSM613728 3 0.6219 0.3682 0.000 0.424 0.436 0 0.140
#> GSM613729 1 0.0566 0.8643 0.984 0.004 0.000 0 0.012
#> GSM613730 3 0.3336 0.6781 0.000 0.228 0.772 0 0.000
#> GSM613731 3 0.1628 0.7459 0.008 0.000 0.936 0 0.056
#> GSM613732 3 0.3661 0.7341 0.000 0.000 0.724 0 0.276
#> GSM613733 3 0.3684 0.7339 0.000 0.000 0.720 0 0.280
#> GSM613734 5 0.3730 0.9155 0.288 0.000 0.000 0 0.712
#> GSM613735 5 0.3752 0.9133 0.292 0.000 0.000 0 0.708
#> GSM613736 3 0.3885 0.7332 0.000 0.008 0.724 0 0.268
#> GSM613737 3 0.0451 0.7629 0.004 0.000 0.988 0 0.008
#> GSM613738 5 0.4088 0.8934 0.304 0.000 0.008 0 0.688
#> GSM613739 5 0.3730 0.9155 0.288 0.000 0.000 0 0.712
#> GSM613740 3 0.3790 0.7342 0.000 0.004 0.724 0 0.272
#> GSM613741 3 0.5555 0.5679 0.140 0.220 0.640 0 0.000
#> GSM613742 5 0.5136 0.7303 0.180 0.000 0.128 0 0.692
#> GSM613743 3 0.3661 0.7341 0.000 0.000 0.724 0 0.276
#> GSM613744 3 0.3661 0.7341 0.000 0.000 0.724 0 0.276
#> GSM613745 3 0.5423 0.5818 0.124 0.224 0.652 0 0.000
#> GSM613746 2 0.0510 0.8057 0.000 0.984 0.000 0 0.016
#> GSM613747 5 0.3774 0.9100 0.296 0.000 0.000 0 0.704
#> GSM613748 3 0.0404 0.7651 0.000 0.000 0.988 0 0.012
#> GSM613749 3 0.4900 0.1228 0.464 0.024 0.512 0 0.000
#> GSM613750 4 0.0000 1.0000 0.000 0.000 0.000 1 0.000
#> GSM613751 4 0.0000 1.0000 0.000 0.000 0.000 1 0.000
#> GSM613752 4 0.0000 1.0000 0.000 0.000 0.000 1 0.000
#> GSM613753 4 0.0000 1.0000 0.000 0.000 0.000 1 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM613638 4 0.0405 0.885 0.000 0.000 0.004 0.988 0.008 0
#> GSM613639 4 0.3052 0.771 0.216 0.000 0.000 0.780 0.004 0
#> GSM613640 4 0.0260 0.886 0.000 0.000 0.008 0.992 0.000 0
#> GSM613641 1 0.0547 0.890 0.980 0.000 0.000 0.000 0.020 0
#> GSM613642 4 0.0363 0.885 0.000 0.000 0.012 0.988 0.000 0
#> GSM613643 4 0.0363 0.884 0.000 0.000 0.000 0.988 0.012 0
#> GSM613644 4 0.0520 0.884 0.008 0.000 0.000 0.984 0.008 0
#> GSM613645 4 0.3240 0.741 0.244 0.000 0.000 0.752 0.004 0
#> GSM613646 4 0.3343 0.787 0.024 0.176 0.000 0.796 0.004 0
#> GSM613647 4 0.0363 0.885 0.000 0.000 0.012 0.988 0.000 0
#> GSM613648 3 0.0000 0.956 0.000 0.000 1.000 0.000 0.000 0
#> GSM613649 3 0.0000 0.956 0.000 0.000 1.000 0.000 0.000 0
#> GSM613650 4 0.2902 0.788 0.196 0.000 0.000 0.800 0.004 0
#> GSM613651 4 0.0363 0.884 0.000 0.000 0.000 0.988 0.012 0
#> GSM613652 5 0.0146 0.980 0.004 0.000 0.000 0.000 0.996 0
#> GSM613653 4 0.3311 0.775 0.204 0.012 0.000 0.780 0.004 0
#> GSM613654 5 0.0146 0.980 0.004 0.000 0.000 0.000 0.996 0
#> GSM613655 1 0.2730 0.809 0.808 0.000 0.000 0.000 0.192 0
#> GSM613656 5 0.0146 0.980 0.004 0.000 0.000 0.000 0.996 0
#> GSM613657 3 0.0000 0.956 0.000 0.000 1.000 0.000 0.000 0
#> GSM613658 1 0.2664 0.814 0.816 0.000 0.000 0.000 0.184 0
#> GSM613659 2 0.0260 0.834 0.000 0.992 0.000 0.008 0.000 0
#> GSM613660 2 0.3728 0.652 0.000 0.652 0.344 0.004 0.000 0
#> GSM613661 1 0.0146 0.880 0.996 0.000 0.000 0.000 0.004 0
#> GSM613662 2 0.0146 0.839 0.000 0.996 0.000 0.004 0.000 0
#> GSM613663 1 0.0713 0.890 0.972 0.000 0.000 0.000 0.028 0
#> GSM613664 2 0.0146 0.839 0.000 0.996 0.000 0.004 0.000 0
#> GSM613665 2 0.2762 0.816 0.000 0.804 0.196 0.000 0.000 0
#> GSM613666 1 0.0547 0.890 0.980 0.000 0.000 0.000 0.020 0
#> GSM613667 1 0.0405 0.871 0.988 0.000 0.000 0.008 0.004 0
#> GSM613668 1 0.2631 0.820 0.820 0.000 0.000 0.000 0.180 0
#> GSM613669 1 0.0547 0.890 0.980 0.000 0.000 0.000 0.020 0
#> GSM613670 2 0.0146 0.839 0.000 0.996 0.000 0.004 0.000 0
#> GSM613671 1 0.0547 0.890 0.980 0.000 0.000 0.000 0.020 0
#> GSM613672 1 0.2793 0.801 0.800 0.000 0.000 0.000 0.200 0
#> GSM613673 1 0.3202 0.726 0.800 0.000 0.000 0.176 0.024 0
#> GSM613674 2 0.2527 0.829 0.000 0.832 0.168 0.000 0.000 0
#> GSM613675 2 0.0146 0.839 0.000 0.996 0.000 0.004 0.000 0
#> GSM613676 2 0.2912 0.806 0.000 0.784 0.216 0.000 0.000 0
#> GSM613677 4 0.3806 0.705 0.000 0.048 0.200 0.752 0.000 0
#> GSM613678 2 0.3755 0.490 0.020 0.732 0.000 0.244 0.004 0
#> GSM613679 2 0.3043 0.812 0.000 0.792 0.200 0.008 0.000 0
#> GSM613680 1 0.2135 0.852 0.872 0.000 0.000 0.000 0.128 0
#> GSM613681 1 0.0547 0.890 0.980 0.000 0.000 0.000 0.020 0
#> GSM613682 1 0.1151 0.887 0.956 0.000 0.000 0.012 0.032 0
#> GSM613683 1 0.2762 0.805 0.804 0.000 0.000 0.000 0.196 0
#> GSM613684 2 0.1863 0.842 0.000 0.896 0.104 0.000 0.000 0
#> GSM613685 2 0.2762 0.816 0.000 0.804 0.196 0.000 0.000 0
#> GSM613686 1 0.0146 0.875 0.996 0.000 0.000 0.000 0.004 0
#> GSM613687 1 0.1141 0.885 0.948 0.000 0.000 0.000 0.052 0
#> GSM613688 2 0.0632 0.844 0.000 0.976 0.024 0.000 0.000 0
#> GSM613689 4 0.0260 0.886 0.000 0.000 0.008 0.992 0.000 0
#> GSM613690 4 0.2416 0.771 0.000 0.000 0.156 0.844 0.000 0
#> GSM613691 2 0.0000 0.838 0.000 1.000 0.000 0.000 0.000 0
#> GSM613692 5 0.2258 0.875 0.060 0.000 0.000 0.044 0.896 0
#> GSM613693 2 0.0937 0.845 0.000 0.960 0.040 0.000 0.000 0
#> GSM613694 4 0.0405 0.886 0.000 0.000 0.008 0.988 0.004 0
#> GSM613695 4 0.0363 0.885 0.000 0.000 0.012 0.988 0.000 0
#> GSM613696 4 0.1674 0.851 0.004 0.068 0.004 0.924 0.000 0
#> GSM613697 4 0.0363 0.884 0.000 0.000 0.000 0.988 0.012 0
#> GSM613698 4 0.0405 0.886 0.000 0.000 0.008 0.988 0.004 0
#> GSM613699 4 0.0405 0.886 0.000 0.000 0.008 0.988 0.004 0
#> GSM613700 2 0.3323 0.783 0.000 0.752 0.240 0.008 0.000 0
#> GSM613701 4 0.3011 0.706 0.000 0.192 0.004 0.800 0.004 0
#> GSM613702 4 0.0632 0.881 0.000 0.000 0.024 0.976 0.000 0
#> GSM613703 1 0.0436 0.874 0.988 0.004 0.000 0.004 0.004 0
#> GSM613704 2 0.0146 0.839 0.000 0.996 0.000 0.004 0.000 0
#> GSM613705 4 0.0260 0.886 0.000 0.000 0.008 0.992 0.000 0
#> GSM613706 4 0.0146 0.885 0.000 0.000 0.004 0.996 0.000 0
#> GSM613707 2 0.2378 0.833 0.000 0.848 0.152 0.000 0.000 0
#> GSM613708 1 0.4167 0.289 0.612 0.000 0.000 0.368 0.020 0
#> GSM613709 1 0.0547 0.890 0.980 0.000 0.000 0.000 0.020 0
#> GSM613710 3 0.0146 0.952 0.000 0.000 0.996 0.004 0.000 0
#> GSM613711 3 0.0000 0.956 0.000 0.000 1.000 0.000 0.000 0
#> GSM613712 4 0.0405 0.886 0.000 0.000 0.008 0.988 0.004 0
#> GSM613713 3 0.0000 0.956 0.000 0.000 1.000 0.000 0.000 0
#> GSM613714 3 0.2996 0.612 0.000 0.000 0.772 0.228 0.000 0
#> GSM613715 3 0.0146 0.953 0.000 0.004 0.996 0.000 0.000 0
#> GSM613716 4 0.5827 0.305 0.000 0.208 0.316 0.476 0.000 0
#> GSM613717 3 0.0000 0.956 0.000 0.000 1.000 0.000 0.000 0
#> GSM613718 3 0.0000 0.956 0.000 0.000 1.000 0.000 0.000 0
#> GSM613719 4 0.3043 0.786 0.196 0.004 0.000 0.796 0.004 0
#> GSM613720 3 0.3221 0.603 0.000 0.264 0.736 0.000 0.000 0
#> GSM613721 4 0.3833 0.696 0.016 0.272 0.000 0.708 0.004 0
#> GSM613722 2 0.3323 0.783 0.000 0.752 0.240 0.008 0.000 0
#> GSM613723 5 0.0146 0.980 0.004 0.000 0.000 0.000 0.996 0
#> GSM613724 5 0.0865 0.952 0.036 0.000 0.000 0.000 0.964 0
#> GSM613725 2 0.3555 0.741 0.000 0.712 0.280 0.008 0.000 0
#> GSM613726 4 0.0405 0.884 0.008 0.000 0.000 0.988 0.004 0
#> GSM613727 1 0.2664 0.816 0.816 0.000 0.000 0.000 0.184 0
#> GSM613728 2 0.0405 0.840 0.000 0.988 0.008 0.004 0.000 0
#> GSM613729 1 0.0547 0.890 0.980 0.000 0.000 0.000 0.020 0
#> GSM613730 4 0.3052 0.766 0.000 0.216 0.004 0.780 0.000 0
#> GSM613731 4 0.0405 0.886 0.000 0.000 0.008 0.988 0.004 0
#> GSM613732 3 0.0000 0.956 0.000 0.000 1.000 0.000 0.000 0
#> GSM613733 3 0.0146 0.952 0.000 0.000 0.996 0.004 0.000 0
#> GSM613734 5 0.0146 0.980 0.004 0.000 0.000 0.000 0.996 0
#> GSM613735 5 0.0260 0.976 0.008 0.000 0.000 0.000 0.992 0
#> GSM613736 3 0.0260 0.949 0.000 0.008 0.992 0.000 0.000 0
#> GSM613737 4 0.0405 0.886 0.000 0.000 0.008 0.988 0.004 0
#> GSM613738 5 0.0632 0.966 0.024 0.000 0.000 0.000 0.976 0
#> GSM613739 5 0.0146 0.980 0.004 0.000 0.000 0.000 0.996 0
#> GSM613740 3 0.0146 0.953 0.000 0.004 0.996 0.000 0.000 0
#> GSM613741 4 0.3628 0.772 0.036 0.184 0.000 0.776 0.004 0
#> GSM613742 4 0.3388 0.763 0.036 0.000 0.000 0.792 0.172 0
#> GSM613743 3 0.0000 0.956 0.000 0.000 1.000 0.000 0.000 0
#> GSM613744 3 0.0000 0.956 0.000 0.000 1.000 0.000 0.000 0
#> GSM613745 4 0.3409 0.781 0.024 0.184 0.000 0.788 0.004 0
#> GSM613746 2 0.0146 0.839 0.000 0.996 0.000 0.004 0.000 0
#> GSM613747 5 0.0146 0.980 0.004 0.000 0.000 0.000 0.996 0
#> GSM613748 4 0.0363 0.885 0.000 0.000 0.012 0.988 0.000 0
#> GSM613749 4 0.2980 0.789 0.192 0.000 0.000 0.800 0.008 0
#> GSM613750 6 0.0000 1.000 0.000 0.000 0.000 0.000 0.000 1
#> GSM613751 6 0.0000 1.000 0.000 0.000 0.000 0.000 0.000 1
#> GSM613752 6 0.0000 1.000 0.000 0.000 0.000 0.000 0.000 1
#> GSM613753 6 0.0000 1.000 0.000 0.000 0.000 0.000 0.000 1
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) k
#> CV:mclust 113 6.71e-02 2
#> CV:mclust 100 1.90e-04 3
#> CV:mclust 77 2.82e-08 4
#> CV:mclust 110 2.31e-10 5
#> CV:mclust 113 4.66e-08 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["CV", "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 27425 rows and 116 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 0.945 0.948 0.976 0.5014 0.499 0.499
#> 3 3 0.684 0.822 0.906 0.3041 0.769 0.569
#> 4 4 0.607 0.579 0.794 0.1012 0.802 0.519
#> 5 5 0.672 0.608 0.794 0.0559 0.877 0.621
#> 6 6 0.623 0.532 0.727 0.0482 0.909 0.670
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
#> GSM613638 2 0.9248 0.536 0.340 0.660
#> GSM613639 1 0.0000 0.993 1.000 0.000
#> GSM613640 2 0.4562 0.879 0.096 0.904
#> GSM613641 1 0.0000 0.993 1.000 0.000
#> GSM613642 2 0.0000 0.959 0.000 1.000
#> GSM613643 1 0.0000 0.993 1.000 0.000
#> GSM613644 1 0.1184 0.980 0.984 0.016
#> GSM613645 1 0.0000 0.993 1.000 0.000
#> GSM613646 1 0.4161 0.906 0.916 0.084
#> GSM613647 2 0.7453 0.750 0.212 0.788
#> GSM613648 2 0.0000 0.959 0.000 1.000
#> GSM613649 2 0.0000 0.959 0.000 1.000
#> GSM613650 1 0.0000 0.993 1.000 0.000
#> GSM613651 1 0.0672 0.987 0.992 0.008
#> GSM613652 1 0.0000 0.993 1.000 0.000
#> GSM613653 1 0.0376 0.990 0.996 0.004
#> GSM613654 1 0.0000 0.993 1.000 0.000
#> GSM613655 1 0.0000 0.993 1.000 0.000
#> GSM613656 1 0.0000 0.993 1.000 0.000
#> GSM613657 2 0.0000 0.959 0.000 1.000
#> GSM613658 1 0.0000 0.993 1.000 0.000
#> GSM613659 2 0.0000 0.959 0.000 1.000
#> GSM613660 2 0.0000 0.959 0.000 1.000
#> GSM613661 1 0.0000 0.993 1.000 0.000
#> GSM613662 2 0.0000 0.959 0.000 1.000
#> GSM613663 1 0.0000 0.993 1.000 0.000
#> GSM613664 2 0.0000 0.959 0.000 1.000
#> GSM613665 2 0.0000 0.959 0.000 1.000
#> GSM613666 1 0.0000 0.993 1.000 0.000
#> GSM613667 1 0.0000 0.993 1.000 0.000
#> GSM613668 1 0.0000 0.993 1.000 0.000
#> GSM613669 1 0.0000 0.993 1.000 0.000
#> GSM613670 2 0.0376 0.957 0.004 0.996
#> GSM613671 1 0.0000 0.993 1.000 0.000
#> GSM613672 1 0.0000 0.993 1.000 0.000
#> GSM613673 1 0.0000 0.993 1.000 0.000
#> GSM613674 2 0.0000 0.959 0.000 1.000
#> GSM613675 2 0.0000 0.959 0.000 1.000
#> GSM613676 2 0.0000 0.959 0.000 1.000
#> GSM613677 2 0.0000 0.959 0.000 1.000
#> GSM613678 1 0.0672 0.987 0.992 0.008
#> GSM613679 2 0.0000 0.959 0.000 1.000
#> GSM613680 1 0.0000 0.993 1.000 0.000
#> GSM613681 1 0.0000 0.993 1.000 0.000
#> GSM613682 1 0.0000 0.993 1.000 0.000
#> GSM613683 1 0.0000 0.993 1.000 0.000
#> GSM613684 2 0.0000 0.959 0.000 1.000
#> GSM613685 2 0.0000 0.959 0.000 1.000
#> GSM613686 1 0.0000 0.993 1.000 0.000
#> GSM613687 1 0.0000 0.993 1.000 0.000
#> GSM613688 2 0.0000 0.959 0.000 1.000
#> GSM613689 2 0.0000 0.959 0.000 1.000
#> GSM613690 2 0.0000 0.959 0.000 1.000
#> GSM613691 2 0.0000 0.959 0.000 1.000
#> GSM613692 1 0.0000 0.993 1.000 0.000
#> GSM613693 2 0.0000 0.959 0.000 1.000
#> GSM613694 1 0.3431 0.929 0.936 0.064
#> GSM613695 2 0.0000 0.959 0.000 1.000
#> GSM613696 2 0.3733 0.901 0.072 0.928
#> GSM613697 1 0.0000 0.993 1.000 0.000
#> GSM613698 2 0.9775 0.364 0.412 0.588
#> GSM613699 2 0.8327 0.676 0.264 0.736
#> GSM613700 2 0.0000 0.959 0.000 1.000
#> GSM613701 2 0.7883 0.718 0.236 0.764
#> GSM613702 2 0.0000 0.959 0.000 1.000
#> GSM613703 1 0.0000 0.993 1.000 0.000
#> GSM613704 2 0.0000 0.959 0.000 1.000
#> GSM613705 2 0.8144 0.695 0.252 0.748
#> GSM613706 1 0.0376 0.990 0.996 0.004
#> GSM613707 2 0.0000 0.959 0.000 1.000
#> GSM613708 1 0.0000 0.993 1.000 0.000
#> GSM613709 1 0.0000 0.993 1.000 0.000
#> GSM613710 2 0.0000 0.959 0.000 1.000
#> GSM613711 2 0.0000 0.959 0.000 1.000
#> GSM613712 2 0.8443 0.663 0.272 0.728
#> GSM613713 2 0.0000 0.959 0.000 1.000
#> GSM613714 2 0.0000 0.959 0.000 1.000
#> GSM613715 2 0.0000 0.959 0.000 1.000
#> GSM613716 2 0.0000 0.959 0.000 1.000
#> GSM613717 2 0.0000 0.959 0.000 1.000
#> GSM613718 2 0.0000 0.959 0.000 1.000
#> GSM613719 1 0.0672 0.987 0.992 0.008
#> GSM613720 2 0.0000 0.959 0.000 1.000
#> GSM613721 2 0.0000 0.959 0.000 1.000
#> GSM613722 2 0.0000 0.959 0.000 1.000
#> GSM613723 1 0.0000 0.993 1.000 0.000
#> GSM613724 1 0.0000 0.993 1.000 0.000
#> GSM613725 2 0.0000 0.959 0.000 1.000
#> GSM613726 1 0.0000 0.993 1.000 0.000
#> GSM613727 1 0.0000 0.993 1.000 0.000
#> GSM613728 2 0.0000 0.959 0.000 1.000
#> GSM613729 1 0.0000 0.993 1.000 0.000
#> GSM613730 2 0.0000 0.959 0.000 1.000
#> GSM613731 1 0.0000 0.993 1.000 0.000
#> GSM613732 2 0.0000 0.959 0.000 1.000
#> GSM613733 2 0.0000 0.959 0.000 1.000
#> GSM613734 1 0.0000 0.993 1.000 0.000
#> GSM613735 1 0.0000 0.993 1.000 0.000
#> GSM613736 2 0.0000 0.959 0.000 1.000
#> GSM613737 1 0.5519 0.848 0.872 0.128
#> GSM613738 1 0.0000 0.993 1.000 0.000
#> GSM613739 1 0.0000 0.993 1.000 0.000
#> GSM613740 2 0.0000 0.959 0.000 1.000
#> GSM613741 1 0.0672 0.987 0.992 0.008
#> GSM613742 1 0.0000 0.993 1.000 0.000
#> GSM613743 2 0.0000 0.959 0.000 1.000
#> GSM613744 2 0.0000 0.959 0.000 1.000
#> GSM613745 2 0.8813 0.615 0.300 0.700
#> GSM613746 2 0.0000 0.959 0.000 1.000
#> GSM613747 1 0.0000 0.993 1.000 0.000
#> GSM613748 2 0.0376 0.957 0.004 0.996
#> GSM613749 1 0.0000 0.993 1.000 0.000
#> GSM613750 2 0.0000 0.959 0.000 1.000
#> GSM613751 2 0.0000 0.959 0.000 1.000
#> GSM613752 2 0.0000 0.959 0.000 1.000
#> GSM613753 2 0.0000 0.959 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM613638 3 0.4002 0.766 0.160 0.000 0.840
#> GSM613639 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613640 3 0.1860 0.850 0.052 0.000 0.948
#> GSM613641 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613642 3 0.2796 0.817 0.000 0.092 0.908
#> GSM613643 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613644 1 0.5016 0.646 0.760 0.000 0.240
#> GSM613645 1 0.4504 0.762 0.804 0.196 0.000
#> GSM613646 1 0.5591 0.631 0.696 0.304 0.000
#> GSM613647 3 0.3752 0.777 0.144 0.000 0.856
#> GSM613648 3 0.0424 0.871 0.000 0.008 0.992
#> GSM613649 3 0.0747 0.869 0.000 0.016 0.984
#> GSM613650 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613651 3 0.6111 0.388 0.396 0.000 0.604
#> GSM613652 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613653 1 0.5560 0.634 0.700 0.300 0.000
#> GSM613654 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613655 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613656 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613657 3 0.1411 0.861 0.000 0.036 0.964
#> GSM613658 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613659 2 0.0000 0.851 0.000 1.000 0.000
#> GSM613660 2 0.5327 0.762 0.000 0.728 0.272
#> GSM613661 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613662 2 0.0000 0.851 0.000 1.000 0.000
#> GSM613663 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613664 2 0.0000 0.851 0.000 1.000 0.000
#> GSM613665 2 0.4346 0.842 0.000 0.816 0.184
#> GSM613666 1 0.0592 0.925 0.988 0.012 0.000
#> GSM613667 1 0.3116 0.851 0.892 0.108 0.000
#> GSM613668 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613669 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613670 2 0.0000 0.851 0.000 1.000 0.000
#> GSM613671 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613672 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613673 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613674 2 0.4002 0.852 0.000 0.840 0.160
#> GSM613675 2 0.0000 0.851 0.000 1.000 0.000
#> GSM613676 2 0.5363 0.757 0.000 0.724 0.276
#> GSM613677 3 0.5178 0.568 0.000 0.256 0.744
#> GSM613678 2 0.0424 0.846 0.008 0.992 0.000
#> GSM613679 2 0.4121 0.849 0.000 0.832 0.168
#> GSM613680 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613681 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613682 1 0.0747 0.923 0.984 0.016 0.000
#> GSM613683 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613684 2 0.5178 0.780 0.000 0.744 0.256
#> GSM613685 2 0.4062 0.850 0.000 0.836 0.164
#> GSM613686 1 0.6079 0.371 0.612 0.388 0.000
#> GSM613687 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613688 2 0.3879 0.853 0.000 0.848 0.152
#> GSM613689 3 0.1031 0.866 0.000 0.024 0.976
#> GSM613690 3 0.0000 0.872 0.000 0.000 1.000
#> GSM613691 2 0.0000 0.851 0.000 1.000 0.000
#> GSM613692 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613693 2 0.4504 0.833 0.000 0.804 0.196
#> GSM613694 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613695 3 0.0000 0.872 0.000 0.000 1.000
#> GSM613696 2 0.6349 0.759 0.140 0.768 0.092
#> GSM613697 3 0.6260 0.241 0.448 0.000 0.552
#> GSM613698 3 0.4931 0.695 0.232 0.000 0.768
#> GSM613699 1 0.8283 0.137 0.536 0.084 0.380
#> GSM613700 2 0.4178 0.847 0.000 0.828 0.172
#> GSM613701 2 0.4555 0.720 0.200 0.800 0.000
#> GSM613702 2 0.4110 0.853 0.004 0.844 0.152
#> GSM613703 1 0.4346 0.777 0.816 0.184 0.000
#> GSM613704 2 0.0000 0.851 0.000 1.000 0.000
#> GSM613705 3 0.2959 0.814 0.100 0.000 0.900
#> GSM613706 1 0.1860 0.893 0.948 0.052 0.000
#> GSM613707 2 0.4452 0.837 0.000 0.808 0.192
#> GSM613708 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613709 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613710 3 0.4750 0.647 0.000 0.216 0.784
#> GSM613711 3 0.1163 0.865 0.000 0.028 0.972
#> GSM613712 3 0.4346 0.740 0.184 0.000 0.816
#> GSM613713 3 0.3816 0.759 0.000 0.148 0.852
#> GSM613714 3 0.0000 0.872 0.000 0.000 1.000
#> GSM613715 3 0.0000 0.872 0.000 0.000 1.000
#> GSM613716 3 0.4654 0.732 0.000 0.208 0.792
#> GSM613717 3 0.2959 0.815 0.000 0.100 0.900
#> GSM613718 3 0.0000 0.872 0.000 0.000 1.000
#> GSM613719 1 0.1411 0.905 0.964 0.000 0.036
#> GSM613720 3 0.4504 0.760 0.000 0.196 0.804
#> GSM613721 2 0.0000 0.851 0.000 1.000 0.000
#> GSM613722 2 0.4555 0.832 0.000 0.800 0.200
#> GSM613723 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613724 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613725 2 0.4842 0.815 0.000 0.776 0.224
#> GSM613726 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613727 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613728 2 0.0000 0.851 0.000 1.000 0.000
#> GSM613729 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613730 2 0.1031 0.848 0.000 0.976 0.024
#> GSM613731 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613732 3 0.0000 0.872 0.000 0.000 1.000
#> GSM613733 3 0.2878 0.817 0.000 0.096 0.904
#> GSM613734 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613735 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613736 3 0.1163 0.867 0.000 0.028 0.972
#> GSM613737 3 0.5178 0.669 0.256 0.000 0.744
#> GSM613738 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613739 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613740 3 0.0892 0.868 0.000 0.020 0.980
#> GSM613741 1 0.6204 0.398 0.576 0.424 0.000
#> GSM613742 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613743 3 0.1289 0.864 0.000 0.032 0.968
#> GSM613744 3 0.0000 0.872 0.000 0.000 1.000
#> GSM613745 1 0.8795 0.110 0.444 0.444 0.112
#> GSM613746 2 0.0424 0.851 0.000 0.992 0.008
#> GSM613747 1 0.0000 0.932 1.000 0.000 0.000
#> GSM613748 2 0.7186 0.622 0.040 0.624 0.336
#> GSM613749 2 0.5678 0.532 0.316 0.684 0.000
#> GSM613750 3 0.0000 0.872 0.000 0.000 1.000
#> GSM613751 3 0.0000 0.872 0.000 0.000 1.000
#> GSM613752 3 0.0000 0.872 0.000 0.000 1.000
#> GSM613753 3 0.0000 0.872 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 3 0.7273 0.230493 0.408 0.128 0.460 0.004
#> GSM613639 1 0.3942 0.659389 0.764 0.000 0.000 0.236
#> GSM613640 2 0.8555 0.074620 0.268 0.480 0.196 0.056
#> GSM613641 1 0.0469 0.872649 0.988 0.000 0.000 0.012
#> GSM613642 2 0.3625 0.585187 0.000 0.828 0.160 0.012
#> GSM613643 1 0.0524 0.873792 0.988 0.004 0.000 0.008
#> GSM613644 1 0.6179 0.045803 0.504 0.012 0.456 0.028
#> GSM613645 1 0.4998 0.012208 0.512 0.000 0.000 0.488
#> GSM613646 4 0.6437 0.496384 0.168 0.184 0.000 0.648
#> GSM613647 3 0.4036 0.707621 0.032 0.116 0.840 0.012
#> GSM613648 3 0.6334 0.482274 0.000 0.328 0.592 0.080
#> GSM613649 3 0.6668 0.417992 0.000 0.380 0.528 0.092
#> GSM613650 1 0.4746 0.704739 0.792 0.064 0.004 0.140
#> GSM613651 1 0.6614 -0.079015 0.484 0.052 0.452 0.012
#> GSM613652 1 0.0376 0.874944 0.992 0.004 0.000 0.004
#> GSM613653 4 0.6170 0.516751 0.192 0.136 0.000 0.672
#> GSM613654 1 0.0524 0.873792 0.988 0.004 0.000 0.008
#> GSM613655 1 0.0000 0.875029 1.000 0.000 0.000 0.000
#> GSM613656 1 0.0000 0.875029 1.000 0.000 0.000 0.000
#> GSM613657 2 0.3726 0.505478 0.000 0.788 0.212 0.000
#> GSM613658 1 0.0188 0.874318 0.996 0.000 0.000 0.004
#> GSM613659 4 0.3813 0.642891 0.000 0.148 0.024 0.828
#> GSM613660 2 0.2647 0.619659 0.000 0.880 0.000 0.120
#> GSM613661 1 0.0000 0.875029 1.000 0.000 0.000 0.000
#> GSM613662 4 0.2704 0.659060 0.000 0.124 0.000 0.876
#> GSM613663 1 0.0188 0.874318 0.996 0.000 0.000 0.004
#> GSM613664 4 0.3649 0.593626 0.000 0.204 0.000 0.796
#> GSM613665 2 0.3873 0.542343 0.000 0.772 0.000 0.228
#> GSM613666 1 0.3764 0.672128 0.784 0.000 0.000 0.216
#> GSM613667 1 0.2647 0.776300 0.880 0.000 0.000 0.120
#> GSM613668 1 0.0376 0.874612 0.992 0.004 0.000 0.004
#> GSM613669 1 0.0336 0.873419 0.992 0.000 0.000 0.008
#> GSM613670 4 0.2281 0.667878 0.000 0.096 0.000 0.904
#> GSM613671 1 0.1022 0.861473 0.968 0.000 0.000 0.032
#> GSM613672 1 0.0188 0.875165 0.996 0.004 0.000 0.000
#> GSM613673 1 0.0804 0.869008 0.980 0.012 0.000 0.008
#> GSM613674 2 0.4661 0.380104 0.000 0.652 0.000 0.348
#> GSM613675 4 0.3606 0.649469 0.000 0.140 0.020 0.840
#> GSM613676 2 0.4599 0.516393 0.000 0.736 0.016 0.248
#> GSM613677 3 0.6007 0.089702 0.000 0.408 0.548 0.044
#> GSM613678 4 0.3208 0.644872 0.000 0.148 0.004 0.848
#> GSM613679 2 0.4103 0.514521 0.000 0.744 0.000 0.256
#> GSM613680 1 0.0188 0.875165 0.996 0.004 0.000 0.000
#> GSM613681 1 0.0336 0.873419 0.992 0.000 0.000 0.008
#> GSM613682 1 0.5203 0.571214 0.720 0.048 0.000 0.232
#> GSM613683 1 0.0188 0.875165 0.996 0.004 0.000 0.000
#> GSM613684 2 0.6585 0.285806 0.000 0.584 0.104 0.312
#> GSM613685 2 0.4564 0.414572 0.000 0.672 0.000 0.328
#> GSM613686 1 0.6607 -0.019373 0.476 0.080 0.000 0.444
#> GSM613687 1 0.0188 0.874318 0.996 0.000 0.000 0.004
#> GSM613688 2 0.4925 0.206347 0.000 0.572 0.000 0.428
#> GSM613689 2 0.2814 0.599651 0.000 0.868 0.132 0.000
#> GSM613690 3 0.1302 0.712817 0.000 0.044 0.956 0.000
#> GSM613691 4 0.1557 0.674595 0.000 0.056 0.000 0.944
#> GSM613692 1 0.0817 0.865187 0.976 0.000 0.024 0.000
#> GSM613693 4 0.5500 0.000381 0.000 0.464 0.016 0.520
#> GSM613694 1 0.0188 0.874926 0.996 0.004 0.000 0.000
#> GSM613695 3 0.1109 0.713686 0.004 0.028 0.968 0.000
#> GSM613696 4 0.8675 0.307002 0.192 0.228 0.080 0.500
#> GSM613697 3 0.5297 0.158797 0.444 0.004 0.548 0.004
#> GSM613698 3 0.2400 0.700408 0.032 0.012 0.928 0.028
#> GSM613699 1 0.6106 0.362719 0.592 0.348 0.060 0.000
#> GSM613700 2 0.2011 0.637490 0.000 0.920 0.000 0.080
#> GSM613701 2 0.3706 0.606835 0.040 0.848 0.000 0.112
#> GSM613702 2 0.3130 0.632407 0.012 0.892 0.024 0.072
#> GSM613703 4 0.4277 0.517877 0.280 0.000 0.000 0.720
#> GSM613704 4 0.2737 0.661078 0.000 0.104 0.008 0.888
#> GSM613705 2 0.8154 -0.101265 0.240 0.444 0.300 0.016
#> GSM613706 2 0.4844 0.354673 0.300 0.688 0.000 0.012
#> GSM613707 2 0.3907 0.538566 0.000 0.768 0.000 0.232
#> GSM613708 1 0.0469 0.872682 0.988 0.000 0.000 0.012
#> GSM613709 1 0.0469 0.872649 0.988 0.000 0.000 0.012
#> GSM613710 2 0.2125 0.629574 0.000 0.920 0.076 0.004
#> GSM613711 2 0.5345 -0.078029 0.000 0.560 0.428 0.012
#> GSM613712 3 0.4543 0.687485 0.080 0.080 0.824 0.016
#> GSM613713 2 0.3447 0.583301 0.000 0.852 0.128 0.020
#> GSM613714 2 0.5742 0.099813 0.000 0.596 0.368 0.036
#> GSM613715 3 0.4832 0.672833 0.000 0.176 0.768 0.056
#> GSM613716 3 0.7218 0.117585 0.000 0.140 0.444 0.416
#> GSM613717 2 0.4969 0.497832 0.000 0.772 0.140 0.088
#> GSM613718 3 0.4284 0.653978 0.000 0.224 0.764 0.012
#> GSM613719 1 0.9143 -0.158994 0.372 0.104 0.164 0.360
#> GSM613720 4 0.7534 -0.103629 0.000 0.188 0.380 0.432
#> GSM613721 4 0.2530 0.645350 0.000 0.112 0.000 0.888
#> GSM613722 2 0.2125 0.638925 0.000 0.920 0.004 0.076
#> GSM613723 1 0.0188 0.875165 0.996 0.004 0.000 0.000
#> GSM613724 1 0.0000 0.875029 1.000 0.000 0.000 0.000
#> GSM613725 2 0.2197 0.637453 0.000 0.916 0.004 0.080
#> GSM613726 1 0.0188 0.875165 0.996 0.004 0.000 0.000
#> GSM613727 1 0.0000 0.875029 1.000 0.000 0.000 0.000
#> GSM613728 2 0.4343 0.469815 0.000 0.732 0.004 0.264
#> GSM613729 1 0.0469 0.872213 0.988 0.000 0.000 0.012
#> GSM613730 4 0.4985 0.185921 0.000 0.468 0.000 0.532
#> GSM613731 1 0.0376 0.874664 0.992 0.004 0.000 0.004
#> GSM613732 3 0.2408 0.710256 0.000 0.104 0.896 0.000
#> GSM613733 2 0.3160 0.595369 0.000 0.872 0.108 0.020
#> GSM613734 1 0.0188 0.875165 0.996 0.004 0.000 0.000
#> GSM613735 1 0.0000 0.875029 1.000 0.000 0.000 0.000
#> GSM613736 2 0.4855 0.265945 0.000 0.644 0.352 0.004
#> GSM613737 1 0.8705 -0.075003 0.456 0.164 0.308 0.072
#> GSM613738 1 0.0188 0.875165 0.996 0.004 0.000 0.000
#> GSM613739 1 0.0376 0.874664 0.992 0.004 0.000 0.004
#> GSM613740 3 0.4978 0.454252 0.000 0.384 0.612 0.004
#> GSM613741 4 0.4677 0.592908 0.176 0.048 0.000 0.776
#> GSM613742 1 0.0376 0.874664 0.992 0.004 0.000 0.004
#> GSM613743 2 0.4837 0.243651 0.000 0.648 0.348 0.004
#> GSM613744 3 0.5137 0.331357 0.000 0.452 0.544 0.004
#> GSM613745 4 0.6637 0.535569 0.160 0.116 0.036 0.688
#> GSM613746 4 0.1256 0.672421 0.000 0.028 0.008 0.964
#> GSM613747 1 0.0188 0.875165 0.996 0.004 0.000 0.000
#> GSM613748 2 0.2861 0.635516 0.032 0.908 0.048 0.012
#> GSM613749 1 0.5515 0.590752 0.732 0.116 0.000 0.152
#> GSM613750 3 0.0921 0.713997 0.000 0.028 0.972 0.000
#> GSM613751 3 0.0921 0.713997 0.000 0.028 0.972 0.000
#> GSM613752 3 0.0921 0.713997 0.000 0.028 0.972 0.000
#> GSM613753 3 0.0921 0.713997 0.000 0.028 0.972 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM613638 1 0.7098 0.0423 0.444 0.000 0.292 0.020 0.244
#> GSM613639 4 0.3918 0.5446 0.232 0.008 0.008 0.752 0.000
#> GSM613640 3 0.6304 0.4875 0.092 0.100 0.700 0.056 0.052
#> GSM613641 1 0.1331 0.8733 0.952 0.000 0.008 0.040 0.000
#> GSM613642 3 0.3194 0.5842 0.000 0.148 0.832 0.000 0.020
#> GSM613643 1 0.2316 0.8524 0.916 0.000 0.036 0.036 0.012
#> GSM613644 1 0.9074 -0.0339 0.400 0.092 0.104 0.164 0.240
#> GSM613645 4 0.4002 0.6388 0.152 0.044 0.008 0.796 0.000
#> GSM613646 4 0.1596 0.7162 0.012 0.000 0.028 0.948 0.012
#> GSM613647 5 0.5869 0.5954 0.016 0.000 0.256 0.104 0.624
#> GSM613648 3 0.7555 0.2147 0.000 0.180 0.516 0.184 0.120
#> GSM613649 3 0.6749 0.1186 0.000 0.020 0.528 0.208 0.244
#> GSM613650 4 0.6189 0.3508 0.304 0.000 0.084 0.580 0.032
#> GSM613651 1 0.6992 0.2975 0.544 0.000 0.168 0.052 0.236
#> GSM613652 1 0.0162 0.8841 0.996 0.000 0.000 0.004 0.000
#> GSM613653 4 0.1364 0.7247 0.036 0.012 0.000 0.952 0.000
#> GSM613654 1 0.0510 0.8837 0.984 0.000 0.000 0.016 0.000
#> GSM613655 1 0.0000 0.8839 1.000 0.000 0.000 0.000 0.000
#> GSM613656 1 0.0000 0.8839 1.000 0.000 0.000 0.000 0.000
#> GSM613657 3 0.1836 0.6434 0.000 0.032 0.932 0.000 0.036
#> GSM613658 1 0.0162 0.8842 0.996 0.000 0.000 0.004 0.000
#> GSM613659 2 0.3790 0.2962 0.000 0.724 0.000 0.272 0.004
#> GSM613660 3 0.4182 0.1960 0.000 0.352 0.644 0.000 0.004
#> GSM613661 1 0.0798 0.8817 0.976 0.016 0.000 0.008 0.000
#> GSM613662 4 0.4302 0.1604 0.000 0.480 0.000 0.520 0.000
#> GSM613663 1 0.0324 0.8842 0.992 0.004 0.000 0.004 0.000
#> GSM613664 2 0.3957 0.3867 0.000 0.712 0.008 0.280 0.000
#> GSM613665 2 0.4283 0.3834 0.000 0.544 0.456 0.000 0.000
#> GSM613666 1 0.3921 0.7234 0.784 0.172 0.000 0.044 0.000
#> GSM613667 1 0.2798 0.8367 0.888 0.044 0.008 0.060 0.000
#> GSM613668 1 0.0162 0.8841 0.996 0.004 0.000 0.000 0.000
#> GSM613669 1 0.0693 0.8829 0.980 0.008 0.000 0.012 0.000
#> GSM613670 4 0.3913 0.4922 0.000 0.324 0.000 0.676 0.000
#> GSM613671 1 0.2790 0.8231 0.880 0.052 0.000 0.068 0.000
#> GSM613672 1 0.0000 0.8839 1.000 0.000 0.000 0.000 0.000
#> GSM613673 1 0.0510 0.8828 0.984 0.016 0.000 0.000 0.000
#> GSM613674 2 0.3895 0.5542 0.000 0.680 0.320 0.000 0.000
#> GSM613675 2 0.4088 0.0522 0.000 0.632 0.000 0.368 0.000
#> GSM613676 2 0.4808 0.4579 0.000 0.576 0.400 0.000 0.024
#> GSM613677 5 0.6745 -0.0352 0.000 0.188 0.400 0.008 0.404
#> GSM613678 2 0.3966 0.2330 0.000 0.664 0.000 0.336 0.000
#> GSM613679 2 0.4291 0.3645 0.000 0.536 0.464 0.000 0.000
#> GSM613680 1 0.0162 0.8841 0.996 0.004 0.000 0.000 0.000
#> GSM613681 1 0.0451 0.8838 0.988 0.008 0.000 0.004 0.000
#> GSM613682 1 0.4101 0.5265 0.664 0.332 0.000 0.004 0.000
#> GSM613683 1 0.0162 0.8841 0.996 0.004 0.000 0.000 0.000
#> GSM613684 2 0.6120 0.4995 0.000 0.564 0.196 0.000 0.240
#> GSM613685 2 0.4030 0.5298 0.000 0.648 0.352 0.000 0.000
#> GSM613686 1 0.5866 0.1737 0.488 0.424 0.004 0.084 0.000
#> GSM613687 1 0.0324 0.8842 0.992 0.004 0.000 0.004 0.000
#> GSM613688 2 0.3909 0.5987 0.000 0.760 0.216 0.024 0.000
#> GSM613689 3 0.2763 0.5782 0.000 0.148 0.848 0.000 0.004
#> GSM613690 5 0.1597 0.7667 0.000 0.000 0.048 0.012 0.940
#> GSM613691 4 0.3109 0.6491 0.000 0.200 0.000 0.800 0.000
#> GSM613692 1 0.2911 0.7940 0.852 0.008 0.000 0.004 0.136
#> GSM613693 2 0.4955 0.5968 0.000 0.724 0.204 0.036 0.036
#> GSM613694 1 0.0162 0.8844 0.996 0.000 0.004 0.000 0.000
#> GSM613695 5 0.3443 0.7524 0.008 0.032 0.100 0.008 0.852
#> GSM613696 2 0.6268 0.2907 0.216 0.616 0.004 0.020 0.144
#> GSM613697 1 0.4446 0.3607 0.592 0.000 0.000 0.008 0.400
#> GSM613698 5 0.3779 0.7388 0.020 0.012 0.028 0.100 0.840
#> GSM613699 1 0.4839 0.6370 0.720 0.024 0.220 0.000 0.036
#> GSM613700 3 0.3424 0.4631 0.000 0.240 0.760 0.000 0.000
#> GSM613701 3 0.3835 0.4201 0.008 0.260 0.732 0.000 0.000
#> GSM613702 3 0.3599 0.6216 0.016 0.140 0.824 0.020 0.000
#> GSM613703 4 0.3031 0.6996 0.016 0.128 0.004 0.852 0.000
#> GSM613704 4 0.3081 0.6866 0.000 0.156 0.012 0.832 0.000
#> GSM613705 3 0.5864 0.3941 0.188 0.000 0.668 0.036 0.108
#> GSM613706 3 0.4527 0.4194 0.260 0.040 0.700 0.000 0.000
#> GSM613707 2 0.4430 0.3701 0.000 0.540 0.456 0.000 0.004
#> GSM613708 1 0.1205 0.8764 0.956 0.000 0.004 0.040 0.000
#> GSM613709 1 0.1331 0.8733 0.952 0.000 0.008 0.040 0.000
#> GSM613710 3 0.2233 0.6101 0.000 0.104 0.892 0.000 0.004
#> GSM613711 3 0.3064 0.6237 0.000 0.000 0.856 0.036 0.108
#> GSM613712 5 0.5438 0.6824 0.076 0.000 0.124 0.072 0.728
#> GSM613713 3 0.3768 0.5925 0.000 0.156 0.808 0.020 0.016
#> GSM613714 3 0.3427 0.6060 0.000 0.000 0.836 0.056 0.108
#> GSM613715 5 0.6138 0.5313 0.000 0.000 0.272 0.176 0.552
#> GSM613716 4 0.4688 0.6190 0.000 0.068 0.056 0.784 0.092
#> GSM613717 3 0.2798 0.6401 0.000 0.008 0.888 0.060 0.044
#> GSM613718 5 0.5240 0.4584 0.000 0.000 0.360 0.056 0.584
#> GSM613719 4 0.4712 0.6126 0.076 0.000 0.076 0.784 0.064
#> GSM613720 4 0.4507 0.6140 0.000 0.028 0.048 0.776 0.148
#> GSM613721 4 0.2464 0.7129 0.000 0.096 0.016 0.888 0.000
#> GSM613722 3 0.3715 0.4345 0.000 0.260 0.736 0.004 0.000
#> GSM613723 1 0.0000 0.8839 1.000 0.000 0.000 0.000 0.000
#> GSM613724 1 0.0162 0.8841 0.996 0.000 0.000 0.004 0.000
#> GSM613725 3 0.3814 0.4071 0.000 0.276 0.720 0.004 0.000
#> GSM613726 1 0.0579 0.8831 0.984 0.000 0.008 0.008 0.000
#> GSM613727 1 0.0451 0.8837 0.988 0.000 0.004 0.008 0.000
#> GSM613728 3 0.6024 0.2328 0.000 0.148 0.556 0.296 0.000
#> GSM613729 1 0.1430 0.8697 0.944 0.000 0.004 0.052 0.000
#> GSM613730 4 0.4800 0.0292 0.000 0.004 0.476 0.508 0.012
#> GSM613731 1 0.1356 0.8765 0.956 0.004 0.012 0.028 0.000
#> GSM613732 5 0.2881 0.7558 0.000 0.008 0.092 0.024 0.876
#> GSM613733 3 0.1168 0.6391 0.000 0.032 0.960 0.008 0.000
#> GSM613734 1 0.0000 0.8839 1.000 0.000 0.000 0.000 0.000
#> GSM613735 1 0.0404 0.8839 0.988 0.000 0.000 0.012 0.000
#> GSM613736 3 0.4183 0.5647 0.000 0.020 0.776 0.024 0.180
#> GSM613737 1 0.7365 0.0971 0.456 0.004 0.356 0.104 0.080
#> GSM613738 1 0.1124 0.8768 0.960 0.000 0.004 0.036 0.000
#> GSM613739 1 0.0451 0.8839 0.988 0.000 0.004 0.008 0.000
#> GSM613740 3 0.5430 -0.1175 0.000 0.008 0.484 0.040 0.468
#> GSM613741 4 0.1484 0.7219 0.008 0.048 0.000 0.944 0.000
#> GSM613742 1 0.1202 0.8764 0.960 0.004 0.004 0.032 0.000
#> GSM613743 3 0.2864 0.6324 0.000 0.000 0.864 0.024 0.112
#> GSM613744 3 0.4326 0.4160 0.000 0.000 0.708 0.028 0.264
#> GSM613745 4 0.1918 0.7148 0.004 0.048 0.012 0.932 0.004
#> GSM613746 4 0.3171 0.6800 0.000 0.176 0.000 0.816 0.008
#> GSM613747 1 0.0162 0.8841 0.996 0.000 0.000 0.004 0.000
#> GSM613748 3 0.3944 0.5910 0.004 0.224 0.756 0.016 0.000
#> GSM613749 1 0.3343 0.8214 0.864 0.068 0.028 0.040 0.000
#> GSM613750 5 0.1444 0.7471 0.000 0.040 0.000 0.012 0.948
#> GSM613751 5 0.1597 0.7420 0.000 0.048 0.000 0.012 0.940
#> GSM613752 5 0.1597 0.7420 0.000 0.048 0.000 0.012 0.940
#> GSM613753 5 0.1444 0.7471 0.000 0.040 0.000 0.012 0.948
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM613638 4 0.5486 0.3363 0.344 0.000 0.052 0.560 0.044 0.000
#> GSM613639 6 0.4826 0.6187 0.072 0.064 0.000 0.120 0.004 0.740
#> GSM613640 4 0.4240 0.4339 0.020 0.000 0.288 0.680 0.004 0.008
#> GSM613641 1 0.2757 0.8312 0.884 0.024 0.000 0.036 0.004 0.052
#> GSM613642 3 0.4492 0.2956 0.000 0.016 0.624 0.344 0.008 0.008
#> GSM613643 1 0.4346 0.1979 0.524 0.004 0.004 0.460 0.000 0.008
#> GSM613644 4 0.5065 0.4405 0.100 0.040 0.000 0.744 0.048 0.068
#> GSM613645 6 0.5199 0.5869 0.064 0.100 0.000 0.124 0.004 0.708
#> GSM613646 6 0.3046 0.6801 0.000 0.012 0.000 0.188 0.000 0.800
#> GSM613647 4 0.3929 0.5156 0.016 0.004 0.028 0.780 0.168 0.004
#> GSM613648 4 0.2989 0.5471 0.000 0.004 0.120 0.848 0.012 0.016
#> GSM613649 4 0.4986 0.5020 0.000 0.004 0.248 0.668 0.048 0.032
#> GSM613650 6 0.5717 0.4330 0.156 0.016 0.000 0.256 0.000 0.572
#> GSM613651 4 0.5124 0.3482 0.324 0.000 0.012 0.592 0.072 0.000
#> GSM613652 1 0.1074 0.8522 0.960 0.012 0.000 0.028 0.000 0.000
#> GSM613653 6 0.1296 0.6897 0.004 0.004 0.000 0.044 0.000 0.948
#> GSM613654 1 0.1391 0.8516 0.944 0.016 0.000 0.040 0.000 0.000
#> GSM613655 1 0.0146 0.8497 0.996 0.000 0.000 0.004 0.000 0.000
#> GSM613656 1 0.0405 0.8498 0.988 0.004 0.000 0.008 0.000 0.000
#> GSM613657 3 0.3930 0.2455 0.000 0.004 0.628 0.364 0.004 0.000
#> GSM613658 1 0.0551 0.8499 0.984 0.008 0.000 0.004 0.000 0.004
#> GSM613659 2 0.6157 0.4586 0.004 0.624 0.052 0.196 0.020 0.104
#> GSM613660 3 0.2480 0.5540 0.000 0.104 0.872 0.024 0.000 0.000
#> GSM613661 1 0.3896 0.7741 0.808 0.100 0.000 0.036 0.004 0.052
#> GSM613662 2 0.4602 0.0792 0.000 0.528 0.008 0.016 0.004 0.444
#> GSM613663 1 0.1364 0.8492 0.952 0.020 0.000 0.012 0.000 0.016
#> GSM613664 2 0.4763 0.5669 0.000 0.700 0.164 0.004 0.004 0.128
#> GSM613665 3 0.3934 0.0679 0.000 0.376 0.616 0.008 0.000 0.000
#> GSM613666 1 0.3580 0.7126 0.772 0.196 0.000 0.004 0.000 0.028
#> GSM613667 1 0.7554 -0.0636 0.372 0.280 0.004 0.116 0.004 0.224
#> GSM613668 1 0.0405 0.8493 0.988 0.008 0.000 0.004 0.000 0.000
#> GSM613669 1 0.2189 0.8401 0.916 0.028 0.000 0.024 0.004 0.028
#> GSM613670 6 0.4289 0.3336 0.000 0.340 0.000 0.024 0.004 0.632
#> GSM613671 1 0.3582 0.7899 0.820 0.064 0.000 0.020 0.000 0.096
#> GSM613672 1 0.0622 0.8504 0.980 0.008 0.000 0.012 0.000 0.000
#> GSM613673 1 0.2126 0.8348 0.904 0.072 0.004 0.020 0.000 0.000
#> GSM613674 2 0.4578 0.3470 0.000 0.568 0.396 0.000 0.032 0.004
#> GSM613675 2 0.5693 0.3770 0.000 0.616 0.024 0.120 0.008 0.232
#> GSM613676 2 0.5206 0.2546 0.000 0.492 0.436 0.012 0.060 0.000
#> GSM613677 4 0.6783 0.3399 0.000 0.108 0.288 0.476 0.128 0.000
#> GSM613678 2 0.6267 0.4488 0.012 0.612 0.056 0.116 0.008 0.196
#> GSM613679 3 0.3727 0.0491 0.000 0.388 0.612 0.000 0.000 0.000
#> GSM613680 1 0.1176 0.8521 0.956 0.024 0.000 0.020 0.000 0.000
#> GSM613681 1 0.1699 0.8481 0.936 0.032 0.000 0.016 0.000 0.016
#> GSM613682 1 0.4538 0.4194 0.612 0.340 0.048 0.000 0.000 0.000
#> GSM613683 1 0.0405 0.8493 0.988 0.008 0.000 0.004 0.000 0.000
#> GSM613684 2 0.5425 0.4242 0.000 0.560 0.156 0.000 0.284 0.000
#> GSM613685 2 0.4772 0.2268 0.000 0.504 0.452 0.000 0.040 0.004
#> GSM613686 2 0.7178 0.1354 0.348 0.392 0.028 0.032 0.004 0.196
#> GSM613687 1 0.1458 0.8499 0.948 0.020 0.000 0.016 0.000 0.016
#> GSM613688 2 0.4194 0.5104 0.000 0.692 0.272 0.000 0.024 0.012
#> GSM613689 3 0.1693 0.6077 0.000 0.020 0.932 0.044 0.004 0.000
#> GSM613690 4 0.5398 0.2142 0.004 0.016 0.060 0.504 0.416 0.000
#> GSM613691 6 0.3352 0.5808 0.000 0.208 0.000 0.008 0.008 0.776
#> GSM613692 1 0.4198 0.7222 0.768 0.020 0.000 0.084 0.128 0.000
#> GSM613693 2 0.5584 0.5175 0.000 0.656 0.200 0.008 0.080 0.056
#> GSM613694 1 0.2288 0.8421 0.896 0.028 0.000 0.072 0.000 0.004
#> GSM613695 4 0.4624 0.3028 0.012 0.032 0.004 0.648 0.304 0.000
#> GSM613696 2 0.6836 0.4242 0.176 0.588 0.064 0.024 0.128 0.020
#> GSM613697 1 0.5894 -0.0512 0.464 0.008 0.000 0.368 0.160 0.000
#> GSM613698 4 0.6200 0.1631 0.020 0.076 0.000 0.536 0.324 0.044
#> GSM613699 1 0.5397 0.6745 0.708 0.040 0.128 0.100 0.020 0.004
#> GSM613700 3 0.1934 0.5963 0.000 0.044 0.916 0.040 0.000 0.000
#> GSM613701 3 0.4258 0.5124 0.088 0.068 0.792 0.044 0.004 0.004
#> GSM613702 3 0.6609 0.3732 0.048 0.080 0.536 0.296 0.004 0.036
#> GSM613703 6 0.2271 0.6670 0.004 0.056 0.000 0.032 0.004 0.904
#> GSM613704 6 0.2214 0.6625 0.000 0.092 0.012 0.004 0.000 0.892
#> GSM613705 4 0.4799 0.3834 0.040 0.000 0.356 0.592 0.012 0.000
#> GSM613706 3 0.5553 0.3849 0.160 0.020 0.632 0.184 0.000 0.004
#> GSM613707 3 0.4591 -0.0588 0.000 0.408 0.552 0.000 0.040 0.000
#> GSM613708 1 0.3793 0.7909 0.812 0.020 0.000 0.080 0.004 0.084
#> GSM613709 1 0.2675 0.8311 0.888 0.020 0.000 0.036 0.004 0.052
#> GSM613710 3 0.2454 0.5618 0.000 0.000 0.840 0.160 0.000 0.000
#> GSM613711 4 0.4722 0.1453 0.000 0.000 0.468 0.492 0.036 0.004
#> GSM613712 4 0.5271 0.3483 0.084 0.000 0.000 0.576 0.328 0.012
#> GSM613713 3 0.5285 0.4899 0.000 0.172 0.688 0.092 0.040 0.008
#> GSM613714 4 0.4069 0.3329 0.000 0.004 0.376 0.612 0.008 0.000
#> GSM613715 4 0.4645 0.4949 0.000 0.000 0.044 0.712 0.204 0.040
#> GSM613716 4 0.5603 -0.2400 0.000 0.032 0.000 0.452 0.064 0.452
#> GSM613717 3 0.4128 -0.1137 0.000 0.000 0.500 0.492 0.004 0.004
#> GSM613718 4 0.5116 0.5197 0.000 0.000 0.168 0.644 0.184 0.004
#> GSM613719 6 0.3720 0.6588 0.000 0.020 0.000 0.208 0.012 0.760
#> GSM613720 6 0.6193 0.5432 0.000 0.104 0.004 0.168 0.116 0.608
#> GSM613721 6 0.4855 0.5664 0.000 0.212 0.020 0.020 0.044 0.704
#> GSM613722 3 0.1124 0.5878 0.000 0.036 0.956 0.008 0.000 0.000
#> GSM613723 1 0.1579 0.8493 0.944 0.020 0.000 0.024 0.008 0.004
#> GSM613724 1 0.1269 0.8512 0.956 0.020 0.000 0.012 0.000 0.012
#> GSM613725 3 0.1700 0.5580 0.000 0.080 0.916 0.000 0.004 0.000
#> GSM613726 1 0.2653 0.8430 0.896 0.024 0.024 0.020 0.000 0.036
#> GSM613727 1 0.1053 0.8513 0.964 0.020 0.000 0.012 0.000 0.004
#> GSM613728 3 0.6472 0.2298 0.000 0.084 0.548 0.024 0.064 0.280
#> GSM613729 1 0.3399 0.7924 0.816 0.020 0.000 0.024 0.000 0.140
#> GSM613730 6 0.7299 0.1267 0.004 0.048 0.348 0.128 0.048 0.424
#> GSM613731 1 0.2736 0.8369 0.888 0.048 0.012 0.036 0.000 0.016
#> GSM613732 5 0.4319 0.6275 0.000 0.020 0.060 0.160 0.756 0.004
#> GSM613733 3 0.2959 0.5789 0.000 0.008 0.844 0.124 0.024 0.000
#> GSM613734 1 0.1148 0.8498 0.960 0.016 0.000 0.020 0.000 0.004
#> GSM613735 1 0.1129 0.8512 0.964 0.012 0.000 0.012 0.004 0.008
#> GSM613736 3 0.7494 0.2215 0.000 0.144 0.436 0.156 0.248 0.016
#> GSM613737 1 0.7665 0.3549 0.516 0.052 0.064 0.228 0.092 0.048
#> GSM613738 1 0.3436 0.8160 0.852 0.032 0.000 0.060 0.028 0.028
#> GSM613739 1 0.1921 0.8484 0.928 0.024 0.000 0.032 0.012 0.004
#> GSM613740 5 0.7070 0.1593 0.000 0.068 0.304 0.096 0.484 0.048
#> GSM613741 6 0.3910 0.6699 0.004 0.052 0.020 0.040 0.056 0.828
#> GSM613742 1 0.4755 0.7676 0.784 0.052 0.016 0.064 0.048 0.036
#> GSM613743 3 0.6205 0.3710 0.000 0.024 0.560 0.184 0.220 0.012
#> GSM613744 3 0.6259 0.1762 0.000 0.020 0.508 0.312 0.148 0.012
#> GSM613745 6 0.6244 0.6110 0.004 0.100 0.024 0.160 0.076 0.636
#> GSM613746 6 0.5208 0.5151 0.000 0.264 0.012 0.008 0.080 0.636
#> GSM613747 1 0.1434 0.8490 0.948 0.024 0.000 0.020 0.000 0.008
#> GSM613748 3 0.5108 0.5140 0.004 0.068 0.696 0.196 0.008 0.028
#> GSM613749 1 0.7195 0.4361 0.540 0.076 0.236 0.028 0.028 0.092
#> GSM613750 5 0.2100 0.7839 0.000 0.004 0.000 0.112 0.884 0.000
#> GSM613751 5 0.2361 0.7837 0.000 0.028 0.000 0.088 0.884 0.000
#> GSM613752 5 0.2094 0.7851 0.000 0.020 0.000 0.080 0.900 0.000
#> GSM613753 5 0.2212 0.7827 0.000 0.008 0.000 0.112 0.880 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) k
#> CV:NMF 115 5.80e-02 2
#> CV:NMF 110 6.73e-03 3
#> CV:NMF 83 2.51e-01 4
#> CV:NMF 81 1.63e-03 5
#> CV:NMF 69 3.11e-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["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 27425 rows and 116 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'MAD' method.
#> Subgroups are detected by 'hclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.576 0.824 0.915 0.4539 0.544 0.544
#> 3 3 0.414 0.605 0.767 0.3753 0.770 0.586
#> 4 4 0.490 0.598 0.770 0.1080 0.879 0.684
#> 5 5 0.520 0.624 0.727 0.0617 0.921 0.753
#> 6 6 0.530 0.583 0.639 0.0617 0.950 0.809
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
#> GSM613638 2 0.6623 0.8241 0.172 0.828
#> GSM613639 1 0.9775 0.2519 0.588 0.412
#> GSM613640 2 0.9170 0.5760 0.332 0.668
#> GSM613641 1 0.0000 0.8994 1.000 0.000
#> GSM613642 2 0.2778 0.8999 0.048 0.952
#> GSM613643 1 0.9998 -0.0361 0.508 0.492
#> GSM613644 2 0.9881 0.3132 0.436 0.564
#> GSM613645 1 0.7883 0.6710 0.764 0.236
#> GSM613646 2 0.4562 0.8824 0.096 0.904
#> GSM613647 2 0.6343 0.8383 0.160 0.840
#> GSM613648 2 0.5737 0.8555 0.136 0.864
#> GSM613649 2 0.0376 0.9063 0.004 0.996
#> GSM613650 2 0.7376 0.7920 0.208 0.792
#> GSM613651 2 0.9460 0.5253 0.364 0.636
#> GSM613652 1 0.0000 0.8994 1.000 0.000
#> GSM613653 2 0.7376 0.7920 0.208 0.792
#> GSM613654 1 0.0000 0.8994 1.000 0.000
#> GSM613655 1 0.0000 0.8994 1.000 0.000
#> GSM613656 1 0.0000 0.8994 1.000 0.000
#> GSM613657 2 0.0000 0.9067 0.000 1.000
#> GSM613658 1 0.0000 0.8994 1.000 0.000
#> GSM613659 2 0.4298 0.8865 0.088 0.912
#> GSM613660 2 0.0000 0.9067 0.000 1.000
#> GSM613661 1 0.1184 0.8946 0.984 0.016
#> GSM613662 2 0.0000 0.9067 0.000 1.000
#> GSM613663 1 0.0376 0.8988 0.996 0.004
#> GSM613664 2 0.0000 0.9067 0.000 1.000
#> GSM613665 2 0.0000 0.9067 0.000 1.000
#> GSM613666 1 0.0000 0.8994 1.000 0.000
#> GSM613667 1 0.7299 0.7119 0.796 0.204
#> GSM613668 1 0.0000 0.8994 1.000 0.000
#> GSM613669 1 0.0000 0.8994 1.000 0.000
#> GSM613670 2 0.0000 0.9067 0.000 1.000
#> GSM613671 1 0.0000 0.8994 1.000 0.000
#> GSM613672 1 0.0376 0.8988 0.996 0.004
#> GSM613673 1 0.0376 0.8988 0.996 0.004
#> GSM613674 2 0.0000 0.9067 0.000 1.000
#> GSM613675 2 0.0376 0.9059 0.004 0.996
#> GSM613676 2 0.0000 0.9067 0.000 1.000
#> GSM613677 2 0.3114 0.8986 0.056 0.944
#> GSM613678 2 0.3879 0.8917 0.076 0.924
#> GSM613679 2 0.0000 0.9067 0.000 1.000
#> GSM613680 1 0.0376 0.8988 0.996 0.004
#> GSM613681 1 0.1633 0.8906 0.976 0.024
#> GSM613682 1 0.4022 0.8547 0.920 0.080
#> GSM613683 1 0.0376 0.8988 0.996 0.004
#> GSM613684 2 0.0000 0.9067 0.000 1.000
#> GSM613685 2 0.0000 0.9067 0.000 1.000
#> GSM613686 1 0.7528 0.7186 0.784 0.216
#> GSM613687 1 0.1633 0.8906 0.976 0.024
#> GSM613688 2 0.0000 0.9067 0.000 1.000
#> GSM613689 2 0.4562 0.8824 0.096 0.904
#> GSM613690 2 0.3733 0.8936 0.072 0.928
#> GSM613691 2 0.3733 0.8928 0.072 0.928
#> GSM613692 1 1.0000 -0.1240 0.500 0.500
#> GSM613693 2 0.0000 0.9067 0.000 1.000
#> GSM613694 2 0.5059 0.8744 0.112 0.888
#> GSM613695 2 0.5946 0.8502 0.144 0.856
#> GSM613696 2 0.4161 0.8883 0.084 0.916
#> GSM613697 2 0.9460 0.5253 0.364 0.636
#> GSM613698 2 0.7950 0.7492 0.240 0.760
#> GSM613699 2 0.4690 0.8807 0.100 0.900
#> GSM613700 2 0.0000 0.9067 0.000 1.000
#> GSM613701 2 0.8861 0.6025 0.304 0.696
#> GSM613702 2 0.8555 0.6465 0.280 0.720
#> GSM613703 1 0.0376 0.8988 0.996 0.004
#> GSM613704 2 0.0000 0.9067 0.000 1.000
#> GSM613705 2 0.6148 0.8430 0.152 0.848
#> GSM613706 2 0.8861 0.6079 0.304 0.696
#> GSM613707 2 0.0000 0.9067 0.000 1.000
#> GSM613708 1 0.7815 0.6751 0.768 0.232
#> GSM613709 1 0.0000 0.8994 1.000 0.000
#> GSM613710 2 0.0000 0.9067 0.000 1.000
#> GSM613711 2 0.0000 0.9067 0.000 1.000
#> GSM613712 2 0.7056 0.8108 0.192 0.808
#> GSM613713 2 0.0000 0.9067 0.000 1.000
#> GSM613714 2 0.5946 0.8502 0.144 0.856
#> GSM613715 2 0.3431 0.8959 0.064 0.936
#> GSM613716 2 0.5842 0.8533 0.140 0.860
#> GSM613717 2 0.0000 0.9067 0.000 1.000
#> GSM613718 2 0.0000 0.9067 0.000 1.000
#> GSM613719 2 0.7376 0.7920 0.208 0.792
#> GSM613720 2 0.0000 0.9067 0.000 1.000
#> GSM613721 2 0.1633 0.9036 0.024 0.976
#> GSM613722 2 0.0000 0.9067 0.000 1.000
#> GSM613723 1 0.0000 0.8994 1.000 0.000
#> GSM613724 1 0.0376 0.8988 0.996 0.004
#> GSM613725 2 0.0000 0.9067 0.000 1.000
#> GSM613726 1 0.8386 0.6062 0.732 0.268
#> GSM613727 1 0.0000 0.8994 1.000 0.000
#> GSM613728 2 0.1843 0.9033 0.028 0.972
#> GSM613729 1 0.0376 0.8988 0.996 0.004
#> GSM613730 2 0.2778 0.8989 0.048 0.952
#> GSM613731 1 0.9998 -0.0361 0.508 0.492
#> GSM613732 2 0.0000 0.9067 0.000 1.000
#> GSM613733 2 0.0000 0.9067 0.000 1.000
#> GSM613734 1 0.0000 0.8994 1.000 0.000
#> GSM613735 1 0.0000 0.8994 1.000 0.000
#> GSM613736 2 0.0000 0.9067 0.000 1.000
#> GSM613737 2 0.6623 0.8285 0.172 0.828
#> GSM613738 1 0.3431 0.8635 0.936 0.064
#> GSM613739 1 0.3431 0.8635 0.936 0.064
#> GSM613740 2 0.0000 0.9067 0.000 1.000
#> GSM613741 2 0.7376 0.7920 0.208 0.792
#> GSM613742 1 0.3431 0.8635 0.936 0.064
#> GSM613743 2 0.0000 0.9067 0.000 1.000
#> GSM613744 2 0.0000 0.9067 0.000 1.000
#> GSM613745 2 0.4562 0.8824 0.096 0.904
#> GSM613746 2 0.0000 0.9067 0.000 1.000
#> GSM613747 1 0.0000 0.8994 1.000 0.000
#> GSM613748 2 0.3879 0.8902 0.076 0.924
#> GSM613749 2 0.9460 0.4628 0.364 0.636
#> GSM613750 2 0.0000 0.9067 0.000 1.000
#> GSM613751 2 0.0000 0.9067 0.000 1.000
#> GSM613752 2 0.0000 0.9067 0.000 1.000
#> GSM613753 2 0.0000 0.9067 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM613638 3 0.9075 0.331 0.140 0.388 0.472
#> GSM613639 1 0.8926 0.198 0.568 0.192 0.240
#> GSM613640 3 0.9849 0.372 0.300 0.280 0.420
#> GSM613641 1 0.0000 0.881 1.000 0.000 0.000
#> GSM613642 2 0.6217 0.493 0.024 0.712 0.264
#> GSM613643 1 0.9563 -0.026 0.480 0.236 0.284
#> GSM613644 1 0.9602 -0.313 0.404 0.200 0.396
#> GSM613645 1 0.6662 0.616 0.736 0.072 0.192
#> GSM613646 3 0.7332 0.612 0.064 0.276 0.660
#> GSM613647 3 0.6526 0.713 0.128 0.112 0.760
#> GSM613648 3 0.7677 0.671 0.120 0.204 0.676
#> GSM613649 2 0.6111 0.418 0.000 0.604 0.396
#> GSM613650 3 0.7875 0.701 0.176 0.156 0.668
#> GSM613651 3 0.7622 0.561 0.332 0.060 0.608
#> GSM613652 1 0.0000 0.881 1.000 0.000 0.000
#> GSM613653 3 0.7927 0.700 0.176 0.160 0.664
#> GSM613654 1 0.0000 0.881 1.000 0.000 0.000
#> GSM613655 1 0.0000 0.881 1.000 0.000 0.000
#> GSM613656 1 0.0000 0.881 1.000 0.000 0.000
#> GSM613657 2 0.5968 0.467 0.000 0.636 0.364
#> GSM613658 1 0.0000 0.881 1.000 0.000 0.000
#> GSM613659 2 0.7770 0.113 0.056 0.560 0.384
#> GSM613660 2 0.0424 0.697 0.000 0.992 0.008
#> GSM613661 1 0.1399 0.871 0.968 0.004 0.028
#> GSM613662 2 0.0000 0.696 0.000 1.000 0.000
#> GSM613663 1 0.0829 0.878 0.984 0.004 0.012
#> GSM613664 2 0.0424 0.697 0.000 0.992 0.008
#> GSM613665 2 0.0747 0.699 0.000 0.984 0.016
#> GSM613666 1 0.0000 0.881 1.000 0.000 0.000
#> GSM613667 1 0.5901 0.655 0.768 0.040 0.192
#> GSM613668 1 0.0000 0.881 1.000 0.000 0.000
#> GSM613669 1 0.0000 0.881 1.000 0.000 0.000
#> GSM613670 2 0.0000 0.696 0.000 1.000 0.000
#> GSM613671 1 0.0000 0.881 1.000 0.000 0.000
#> GSM613672 1 0.0661 0.880 0.988 0.004 0.008
#> GSM613673 1 0.0983 0.877 0.980 0.004 0.016
#> GSM613674 2 0.0000 0.696 0.000 1.000 0.000
#> GSM613675 2 0.1525 0.696 0.004 0.964 0.032
#> GSM613676 2 0.0747 0.699 0.000 0.984 0.016
#> GSM613677 2 0.6630 0.425 0.028 0.672 0.300
#> GSM613678 2 0.7368 0.229 0.044 0.604 0.352
#> GSM613679 2 0.0237 0.697 0.000 0.996 0.004
#> GSM613680 1 0.0661 0.880 0.988 0.004 0.008
#> GSM613681 1 0.1620 0.870 0.964 0.024 0.012
#> GSM613682 1 0.3272 0.820 0.904 0.080 0.016
#> GSM613683 1 0.0661 0.880 0.988 0.004 0.008
#> GSM613684 2 0.1753 0.694 0.000 0.952 0.048
#> GSM613685 2 0.0000 0.696 0.000 1.000 0.000
#> GSM613686 1 0.5708 0.661 0.768 0.204 0.028
#> GSM613687 1 0.1620 0.870 0.964 0.024 0.012
#> GSM613688 2 0.1753 0.694 0.000 0.952 0.048
#> GSM613689 3 0.6576 0.682 0.068 0.192 0.740
#> GSM613690 3 0.7442 0.371 0.044 0.368 0.588
#> GSM613691 3 0.7492 0.528 0.052 0.340 0.608
#> GSM613692 3 0.7672 0.247 0.468 0.044 0.488
#> GSM613693 2 0.2261 0.687 0.000 0.932 0.068
#> GSM613694 3 0.6407 0.699 0.080 0.160 0.760
#> GSM613695 3 0.7082 0.710 0.120 0.156 0.724
#> GSM613696 3 0.7250 0.601 0.056 0.288 0.656
#> GSM613697 3 0.7622 0.561 0.332 0.060 0.608
#> GSM613698 3 0.7525 0.689 0.208 0.108 0.684
#> GSM613699 3 0.6562 0.688 0.072 0.184 0.744
#> GSM613700 2 0.0000 0.696 0.000 1.000 0.000
#> GSM613701 2 0.9830 -0.128 0.272 0.424 0.304
#> GSM613702 2 0.9804 -0.155 0.248 0.416 0.336
#> GSM613703 1 0.0237 0.881 0.996 0.004 0.000
#> GSM613704 2 0.0000 0.696 0.000 1.000 0.000
#> GSM613705 3 0.8871 0.301 0.120 0.408 0.472
#> GSM613706 2 0.9880 -0.177 0.272 0.404 0.324
#> GSM613707 2 0.0747 0.698 0.000 0.984 0.016
#> GSM613708 1 0.6587 0.635 0.752 0.156 0.092
#> GSM613709 1 0.0000 0.881 1.000 0.000 0.000
#> GSM613710 2 0.0424 0.697 0.000 0.992 0.008
#> GSM613711 2 0.5948 0.470 0.000 0.640 0.360
#> GSM613712 3 0.7265 0.710 0.160 0.128 0.712
#> GSM613713 2 0.5016 0.585 0.000 0.760 0.240
#> GSM613714 3 0.7082 0.710 0.120 0.156 0.724
#> GSM613715 3 0.7487 0.263 0.040 0.408 0.552
#> GSM613716 3 0.6960 0.714 0.116 0.152 0.732
#> GSM613717 2 0.5968 0.467 0.000 0.636 0.364
#> GSM613718 2 0.5968 0.467 0.000 0.636 0.364
#> GSM613719 3 0.7927 0.700 0.176 0.160 0.664
#> GSM613720 2 0.2711 0.679 0.000 0.912 0.088
#> GSM613721 2 0.6045 0.312 0.000 0.620 0.380
#> GSM613722 2 0.1031 0.691 0.000 0.976 0.024
#> GSM613723 1 0.0000 0.881 1.000 0.000 0.000
#> GSM613724 1 0.0829 0.878 0.984 0.004 0.012
#> GSM613725 2 0.0000 0.696 0.000 1.000 0.000
#> GSM613726 1 0.7372 0.554 0.704 0.128 0.168
#> GSM613727 1 0.0000 0.881 1.000 0.000 0.000
#> GSM613728 2 0.4840 0.603 0.016 0.816 0.168
#> GSM613729 1 0.0237 0.881 0.996 0.004 0.000
#> GSM613730 2 0.6062 0.448 0.016 0.708 0.276
#> GSM613731 1 0.9563 -0.026 0.480 0.236 0.284
#> GSM613732 2 0.5968 0.467 0.000 0.636 0.364
#> GSM613733 2 0.5905 0.481 0.000 0.648 0.352
#> GSM613734 1 0.0000 0.881 1.000 0.000 0.000
#> GSM613735 1 0.0000 0.881 1.000 0.000 0.000
#> GSM613736 2 0.5905 0.468 0.000 0.648 0.352
#> GSM613737 3 0.6644 0.713 0.140 0.108 0.752
#> GSM613738 1 0.2537 0.831 0.920 0.000 0.080
#> GSM613739 1 0.2537 0.831 0.920 0.000 0.080
#> GSM613740 2 0.5905 0.479 0.000 0.648 0.352
#> GSM613741 3 0.7927 0.700 0.176 0.160 0.664
#> GSM613742 1 0.2537 0.831 0.920 0.000 0.080
#> GSM613743 2 0.5810 0.499 0.000 0.664 0.336
#> GSM613744 2 0.5968 0.467 0.000 0.636 0.364
#> GSM613745 3 0.7332 0.612 0.064 0.276 0.660
#> GSM613746 2 0.1860 0.692 0.000 0.948 0.052
#> GSM613747 1 0.0000 0.881 1.000 0.000 0.000
#> GSM613748 2 0.7406 0.228 0.044 0.596 0.360
#> GSM613749 2 0.9895 -0.137 0.332 0.396 0.272
#> GSM613750 3 0.4178 0.422 0.000 0.172 0.828
#> GSM613751 3 0.4178 0.422 0.000 0.172 0.828
#> GSM613752 3 0.4178 0.422 0.000 0.172 0.828
#> GSM613753 3 0.4178 0.422 0.000 0.172 0.828
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 3 0.8068 0.4608 0.120 0.276 0.540 0.064
#> GSM613639 1 0.7176 0.1403 0.536 0.108 0.344 0.012
#> GSM613640 3 0.7386 0.5069 0.268 0.160 0.560 0.012
#> GSM613641 1 0.0000 0.8891 1.000 0.000 0.000 0.000
#> GSM613642 2 0.6385 0.3531 0.008 0.628 0.288 0.076
#> GSM613643 1 0.7607 -0.1184 0.448 0.140 0.400 0.012
#> GSM613644 3 0.7252 0.3454 0.372 0.108 0.508 0.012
#> GSM613645 1 0.5094 0.5942 0.724 0.024 0.244 0.008
#> GSM613646 3 0.3689 0.5933 0.036 0.068 0.872 0.024
#> GSM613647 3 0.3463 0.5838 0.096 0.000 0.864 0.040
#> GSM613648 3 0.5666 0.5372 0.088 0.064 0.772 0.076
#> GSM613649 3 0.7789 -0.3673 0.000 0.352 0.400 0.248
#> GSM613650 3 0.3822 0.6102 0.140 0.016 0.836 0.008
#> GSM613651 3 0.5792 0.4875 0.296 0.000 0.648 0.056
#> GSM613652 1 0.0336 0.8876 0.992 0.000 0.008 0.000
#> GSM613653 3 0.3949 0.6107 0.140 0.016 0.832 0.012
#> GSM613654 1 0.0336 0.8876 0.992 0.000 0.008 0.000
#> GSM613655 1 0.0000 0.8891 1.000 0.000 0.000 0.000
#> GSM613656 1 0.0336 0.8876 0.992 0.000 0.008 0.000
#> GSM613657 2 0.7786 0.3661 0.000 0.388 0.368 0.244
#> GSM613658 1 0.0000 0.8891 1.000 0.000 0.000 0.000
#> GSM613659 3 0.6637 0.3353 0.032 0.344 0.584 0.040
#> GSM613660 2 0.1297 0.6859 0.000 0.964 0.020 0.016
#> GSM613661 1 0.1209 0.8782 0.964 0.004 0.032 0.000
#> GSM613662 2 0.2131 0.6781 0.000 0.932 0.032 0.036
#> GSM613663 1 0.0779 0.8865 0.980 0.004 0.016 0.000
#> GSM613664 2 0.1510 0.6792 0.000 0.956 0.028 0.016
#> GSM613665 2 0.2111 0.6891 0.000 0.932 0.044 0.024
#> GSM613666 1 0.0000 0.8891 1.000 0.000 0.000 0.000
#> GSM613667 1 0.4408 0.6321 0.756 0.008 0.232 0.004
#> GSM613668 1 0.0000 0.8891 1.000 0.000 0.000 0.000
#> GSM613669 1 0.0000 0.8891 1.000 0.000 0.000 0.000
#> GSM613670 2 0.2131 0.6781 0.000 0.932 0.032 0.036
#> GSM613671 1 0.0000 0.8891 1.000 0.000 0.000 0.000
#> GSM613672 1 0.0657 0.8876 0.984 0.004 0.012 0.000
#> GSM613673 1 0.0895 0.8848 0.976 0.004 0.020 0.000
#> GSM613674 2 0.0592 0.6770 0.000 0.984 0.000 0.016
#> GSM613675 2 0.3308 0.6605 0.000 0.872 0.092 0.036
#> GSM613676 2 0.2111 0.6891 0.000 0.932 0.044 0.024
#> GSM613677 2 0.7130 0.2075 0.016 0.556 0.328 0.100
#> GSM613678 3 0.6380 0.1730 0.020 0.460 0.492 0.028
#> GSM613679 2 0.0927 0.6827 0.000 0.976 0.008 0.016
#> GSM613680 1 0.0657 0.8876 0.984 0.004 0.012 0.000
#> GSM613681 1 0.1484 0.8787 0.960 0.016 0.020 0.004
#> GSM613682 1 0.3130 0.8244 0.892 0.072 0.024 0.012
#> GSM613683 1 0.0657 0.8876 0.984 0.004 0.012 0.000
#> GSM613684 2 0.4636 0.6568 0.000 0.792 0.140 0.068
#> GSM613685 2 0.0592 0.6770 0.000 0.984 0.000 0.016
#> GSM613686 1 0.5347 0.6726 0.756 0.176 0.048 0.020
#> GSM613687 1 0.1484 0.8787 0.960 0.016 0.020 0.004
#> GSM613688 2 0.4387 0.6610 0.000 0.804 0.144 0.052
#> GSM613689 3 0.3280 0.5602 0.040 0.020 0.892 0.048
#> GSM613690 3 0.6338 0.4182 0.028 0.124 0.708 0.140
#> GSM613691 3 0.4596 0.5433 0.028 0.140 0.808 0.024
#> GSM613692 3 0.6187 0.2361 0.432 0.000 0.516 0.052
#> GSM613693 2 0.5883 0.6244 0.000 0.700 0.172 0.128
#> GSM613694 3 0.2494 0.5710 0.048 0.000 0.916 0.036
#> GSM613695 3 0.4504 0.5719 0.088 0.020 0.828 0.064
#> GSM613696 3 0.3771 0.5815 0.032 0.084 0.864 0.020
#> GSM613697 3 0.5792 0.4875 0.296 0.000 0.648 0.056
#> GSM613698 3 0.4292 0.5898 0.180 0.008 0.796 0.016
#> GSM613699 3 0.3135 0.5642 0.044 0.012 0.896 0.048
#> GSM613700 2 0.0592 0.6785 0.000 0.984 0.000 0.016
#> GSM613701 3 0.8323 0.3564 0.244 0.328 0.408 0.020
#> GSM613702 3 0.8203 0.3791 0.220 0.320 0.440 0.020
#> GSM613703 1 0.0336 0.8888 0.992 0.000 0.008 0.000
#> GSM613704 2 0.2131 0.6781 0.000 0.932 0.032 0.036
#> GSM613705 3 0.8023 0.4269 0.100 0.304 0.528 0.068
#> GSM613706 3 0.8274 0.3927 0.244 0.304 0.432 0.020
#> GSM613707 2 0.2021 0.6842 0.000 0.936 0.024 0.040
#> GSM613708 1 0.5575 0.6280 0.736 0.104 0.156 0.004
#> GSM613709 1 0.0000 0.8891 1.000 0.000 0.000 0.000
#> GSM613710 2 0.1297 0.6859 0.000 0.964 0.020 0.016
#> GSM613711 2 0.7772 0.3707 0.000 0.392 0.368 0.240
#> GSM613712 3 0.5437 0.5703 0.124 0.020 0.768 0.088
#> GSM613713 2 0.7317 0.5079 0.000 0.528 0.268 0.204
#> GSM613714 3 0.4504 0.5719 0.088 0.020 0.828 0.064
#> GSM613715 3 0.6610 0.3731 0.024 0.160 0.680 0.136
#> GSM613716 3 0.4326 0.5890 0.088 0.036 0.840 0.036
#> GSM613717 2 0.7786 0.3661 0.000 0.388 0.368 0.244
#> GSM613718 2 0.7786 0.3661 0.000 0.388 0.368 0.244
#> GSM613719 3 0.3949 0.6107 0.140 0.016 0.832 0.012
#> GSM613720 2 0.6714 0.5662 0.000 0.612 0.228 0.160
#> GSM613721 3 0.6520 0.0648 0.000 0.384 0.536 0.080
#> GSM613722 2 0.1724 0.6790 0.000 0.948 0.032 0.020
#> GSM613723 1 0.0336 0.8876 0.992 0.000 0.008 0.000
#> GSM613724 1 0.0779 0.8865 0.980 0.004 0.016 0.000
#> GSM613725 2 0.0592 0.6785 0.000 0.984 0.000 0.016
#> GSM613726 1 0.6252 0.5123 0.676 0.088 0.224 0.012
#> GSM613727 1 0.0000 0.8891 1.000 0.000 0.000 0.000
#> GSM613728 2 0.5433 0.4329 0.004 0.688 0.272 0.036
#> GSM613729 1 0.0336 0.8888 0.992 0.000 0.008 0.000
#> GSM613730 2 0.5810 0.1423 0.004 0.580 0.388 0.028
#> GSM613731 1 0.7607 -0.1184 0.448 0.140 0.400 0.012
#> GSM613732 2 0.7786 0.3661 0.000 0.388 0.368 0.244
#> GSM613733 2 0.7740 0.3813 0.000 0.404 0.364 0.232
#> GSM613734 1 0.0336 0.8876 0.992 0.000 0.008 0.000
#> GSM613735 1 0.0469 0.8870 0.988 0.000 0.012 0.000
#> GSM613736 3 0.7684 -0.3982 0.000 0.388 0.396 0.216
#> GSM613737 3 0.3557 0.5856 0.108 0.000 0.856 0.036
#> GSM613738 1 0.2216 0.8329 0.908 0.000 0.092 0.000
#> GSM613739 1 0.2216 0.8329 0.908 0.000 0.092 0.000
#> GSM613740 2 0.7758 0.3796 0.000 0.396 0.368 0.236
#> GSM613741 3 0.3949 0.6107 0.140 0.016 0.832 0.012
#> GSM613742 1 0.2216 0.8329 0.908 0.000 0.092 0.000
#> GSM613743 2 0.7733 0.4015 0.000 0.412 0.356 0.232
#> GSM613744 2 0.7799 0.3599 0.000 0.384 0.368 0.248
#> GSM613745 3 0.3689 0.5933 0.036 0.068 0.872 0.024
#> GSM613746 2 0.6433 0.5851 0.000 0.648 0.188 0.164
#> GSM613747 1 0.0336 0.8876 0.992 0.000 0.008 0.000
#> GSM613748 3 0.6636 0.1466 0.032 0.468 0.472 0.028
#> GSM613749 3 0.8446 0.3234 0.304 0.308 0.368 0.020
#> GSM613750 4 0.3486 1.0000 0.000 0.000 0.188 0.812
#> GSM613751 4 0.3486 1.0000 0.000 0.000 0.188 0.812
#> GSM613752 4 0.3486 1.0000 0.000 0.000 0.188 0.812
#> GSM613753 4 0.3486 1.0000 0.000 0.000 0.188 0.812
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM613638 4 0.7443 0.4109 0.052 0.200 0.124 0.576 0.048
#> GSM613639 1 0.6537 -0.0359 0.448 0.096 0.016 0.432 0.008
#> GSM613640 4 0.6669 0.4959 0.196 0.128 0.052 0.616 0.008
#> GSM613641 1 0.0162 0.8814 0.996 0.000 0.000 0.000 0.004
#> GSM613642 2 0.7580 0.4113 0.004 0.452 0.212 0.280 0.052
#> GSM613643 4 0.7050 0.2073 0.388 0.124 0.032 0.448 0.008
#> GSM613644 4 0.6010 0.4443 0.288 0.096 0.008 0.600 0.008
#> GSM613645 1 0.4468 0.5885 0.696 0.024 0.000 0.276 0.004
#> GSM613646 4 0.3997 0.5908 0.012 0.056 0.092 0.828 0.012
#> GSM613647 4 0.2629 0.6012 0.004 0.000 0.104 0.880 0.012
#> GSM613648 4 0.3832 0.5300 0.000 0.016 0.172 0.796 0.016
#> GSM613649 3 0.4803 0.7492 0.000 0.064 0.712 0.220 0.004
#> GSM613650 4 0.1686 0.6266 0.020 0.008 0.028 0.944 0.000
#> GSM613651 4 0.4799 0.5468 0.164 0.000 0.028 0.752 0.056
#> GSM613652 1 0.2074 0.8671 0.896 0.000 0.000 0.104 0.000
#> GSM613653 4 0.1799 0.6267 0.020 0.012 0.028 0.940 0.000
#> GSM613654 1 0.2074 0.8671 0.896 0.000 0.000 0.104 0.000
#> GSM613655 1 0.0162 0.8814 0.996 0.000 0.000 0.000 0.004
#> GSM613656 1 0.2074 0.8671 0.896 0.000 0.000 0.104 0.000
#> GSM613657 3 0.4681 0.7916 0.000 0.084 0.728 0.188 0.000
#> GSM613658 1 0.0162 0.8814 0.996 0.000 0.000 0.000 0.004
#> GSM613659 4 0.6656 0.2903 0.016 0.304 0.124 0.544 0.012
#> GSM613660 2 0.4439 0.6624 0.000 0.728 0.236 0.012 0.024
#> GSM613661 1 0.1948 0.8785 0.928 0.004 0.008 0.056 0.004
#> GSM613662 2 0.5125 0.5579 0.000 0.748 0.096 0.044 0.112
#> GSM613663 1 0.1285 0.8856 0.956 0.004 0.000 0.036 0.004
#> GSM613664 2 0.3880 0.6668 0.000 0.824 0.112 0.036 0.028
#> GSM613665 2 0.4309 0.6789 0.000 0.792 0.136 0.044 0.028
#> GSM613666 1 0.0162 0.8814 0.996 0.000 0.000 0.000 0.004
#> GSM613667 1 0.3989 0.6326 0.728 0.008 0.000 0.260 0.004
#> GSM613668 1 0.0324 0.8817 0.992 0.000 0.000 0.004 0.004
#> GSM613669 1 0.0162 0.8814 0.996 0.000 0.000 0.000 0.004
#> GSM613670 2 0.5125 0.5579 0.000 0.748 0.096 0.044 0.112
#> GSM613671 1 0.0162 0.8814 0.996 0.000 0.000 0.000 0.004
#> GSM613672 1 0.1124 0.8860 0.960 0.004 0.000 0.036 0.000
#> GSM613673 1 0.1365 0.8848 0.952 0.004 0.000 0.040 0.004
#> GSM613674 2 0.3805 0.6815 0.000 0.784 0.184 0.000 0.032
#> GSM613675 2 0.5478 0.5914 0.000 0.728 0.084 0.108 0.080
#> GSM613676 2 0.4309 0.6789 0.000 0.792 0.136 0.044 0.028
#> GSM613677 2 0.7480 0.2840 0.004 0.404 0.212 0.344 0.036
#> GSM613678 4 0.6198 0.0568 0.020 0.420 0.068 0.488 0.004
#> GSM613679 2 0.3751 0.6825 0.000 0.772 0.212 0.004 0.012
#> GSM613680 1 0.1041 0.8862 0.964 0.004 0.000 0.032 0.000
#> GSM613681 1 0.1862 0.8821 0.932 0.016 0.000 0.048 0.004
#> GSM613682 1 0.2728 0.8399 0.888 0.068 0.000 0.040 0.004
#> GSM613683 1 0.1041 0.8862 0.964 0.004 0.000 0.032 0.000
#> GSM613684 2 0.5690 0.3853 0.000 0.592 0.336 0.032 0.040
#> GSM613685 2 0.3805 0.6815 0.000 0.784 0.184 0.000 0.032
#> GSM613686 1 0.4873 0.6928 0.744 0.168 0.012 0.072 0.004
#> GSM613687 1 0.1862 0.8821 0.932 0.016 0.000 0.048 0.004
#> GSM613688 2 0.5868 0.4271 0.000 0.600 0.312 0.048 0.040
#> GSM613689 4 0.3559 0.5623 0.000 0.008 0.176 0.804 0.012
#> GSM613690 4 0.5041 0.2008 0.000 0.020 0.380 0.588 0.012
#> GSM613691 4 0.4909 0.5232 0.004 0.100 0.144 0.744 0.008
#> GSM613692 4 0.5698 0.3636 0.308 0.000 0.028 0.612 0.052
#> GSM613693 3 0.6334 -0.0438 0.000 0.372 0.520 0.040 0.068
#> GSM613694 4 0.3170 0.5808 0.004 0.000 0.160 0.828 0.008
#> GSM613695 4 0.3022 0.5807 0.000 0.004 0.136 0.848 0.012
#> GSM613696 4 0.4168 0.5745 0.004 0.056 0.124 0.804 0.012
#> GSM613697 4 0.4799 0.5468 0.164 0.000 0.028 0.752 0.056
#> GSM613698 4 0.2654 0.6203 0.056 0.000 0.040 0.896 0.008
#> GSM613699 4 0.3399 0.5690 0.000 0.004 0.172 0.812 0.012
#> GSM613700 2 0.4029 0.6688 0.000 0.744 0.232 0.000 0.024
#> GSM613701 4 0.7710 0.2547 0.236 0.292 0.052 0.416 0.004
#> GSM613702 4 0.7574 0.2849 0.220 0.284 0.048 0.444 0.004
#> GSM613703 1 0.0740 0.8810 0.980 0.000 0.008 0.008 0.004
#> GSM613704 2 0.5125 0.5579 0.000 0.748 0.096 0.044 0.112
#> GSM613705 4 0.7350 0.3799 0.036 0.208 0.136 0.572 0.048
#> GSM613706 4 0.7561 0.3139 0.216 0.268 0.052 0.460 0.004
#> GSM613707 2 0.3976 0.6420 0.000 0.760 0.216 0.004 0.020
#> GSM613708 1 0.5759 0.5729 0.652 0.088 0.012 0.240 0.008
#> GSM613709 1 0.0162 0.8814 0.996 0.000 0.000 0.000 0.004
#> GSM613710 2 0.4439 0.6624 0.000 0.728 0.236 0.012 0.024
#> GSM613711 3 0.4734 0.7915 0.000 0.088 0.724 0.188 0.000
#> GSM613712 4 0.4431 0.5918 0.024 0.004 0.128 0.792 0.052
#> GSM613713 3 0.6225 0.5548 0.000 0.216 0.628 0.116 0.040
#> GSM613714 4 0.3022 0.5807 0.000 0.004 0.136 0.848 0.012
#> GSM613715 4 0.5184 0.0774 0.000 0.036 0.404 0.556 0.004
#> GSM613716 4 0.2957 0.5928 0.000 0.012 0.120 0.860 0.008
#> GSM613717 3 0.4681 0.7916 0.000 0.084 0.728 0.188 0.000
#> GSM613718 3 0.4681 0.7916 0.000 0.084 0.728 0.188 0.000
#> GSM613719 4 0.1799 0.6267 0.020 0.012 0.028 0.940 0.000
#> GSM613720 3 0.7204 0.0872 0.000 0.268 0.484 0.040 0.208
#> GSM613721 4 0.7661 0.1013 0.000 0.220 0.320 0.400 0.060
#> GSM613722 2 0.4839 0.6728 0.000 0.720 0.220 0.036 0.024
#> GSM613723 1 0.2074 0.8671 0.896 0.000 0.000 0.104 0.000
#> GSM613724 1 0.1282 0.8853 0.952 0.004 0.000 0.044 0.000
#> GSM613725 2 0.4029 0.6688 0.000 0.744 0.232 0.000 0.024
#> GSM613726 1 0.5843 0.4862 0.636 0.068 0.020 0.268 0.008
#> GSM613727 1 0.0162 0.8814 0.996 0.000 0.000 0.000 0.004
#> GSM613728 2 0.5987 0.4817 0.004 0.612 0.092 0.276 0.016
#> GSM613729 1 0.0740 0.8810 0.980 0.000 0.008 0.008 0.004
#> GSM613730 2 0.6119 0.2466 0.004 0.512 0.100 0.380 0.004
#> GSM613731 4 0.7050 0.2073 0.388 0.124 0.032 0.448 0.008
#> GSM613732 3 0.4681 0.7916 0.000 0.084 0.728 0.188 0.000
#> GSM613733 3 0.4990 0.7883 0.000 0.096 0.712 0.188 0.004
#> GSM613734 1 0.2074 0.8671 0.896 0.000 0.000 0.104 0.000
#> GSM613735 1 0.2127 0.8651 0.892 0.000 0.000 0.108 0.000
#> GSM613736 3 0.5504 0.7495 0.000 0.092 0.672 0.220 0.016
#> GSM613737 4 0.2805 0.6016 0.012 0.000 0.108 0.872 0.008
#> GSM613738 1 0.3438 0.8044 0.808 0.000 0.020 0.172 0.000
#> GSM613739 1 0.3438 0.8044 0.808 0.000 0.020 0.172 0.000
#> GSM613740 3 0.5059 0.7893 0.000 0.092 0.712 0.188 0.008
#> GSM613741 4 0.1799 0.6267 0.020 0.012 0.028 0.940 0.000
#> GSM613742 1 0.3438 0.8044 0.808 0.000 0.020 0.172 0.000
#> GSM613743 3 0.5292 0.7717 0.000 0.108 0.700 0.180 0.012
#> GSM613744 3 0.4627 0.7882 0.000 0.080 0.732 0.188 0.000
#> GSM613745 4 0.3997 0.5908 0.012 0.056 0.092 0.828 0.012
#> GSM613746 3 0.6692 0.0563 0.000 0.292 0.488 0.008 0.212
#> GSM613747 1 0.2074 0.8671 0.896 0.000 0.000 0.104 0.000
#> GSM613748 4 0.6568 0.0260 0.024 0.404 0.096 0.472 0.004
#> GSM613749 4 0.7618 0.2310 0.296 0.280 0.036 0.384 0.004
#> GSM613750 5 0.3579 1.0000 0.000 0.000 0.240 0.004 0.756
#> GSM613751 5 0.3579 1.0000 0.000 0.000 0.240 0.004 0.756
#> GSM613752 5 0.3579 1.0000 0.000 0.000 0.240 0.004 0.756
#> GSM613753 5 0.3579 1.0000 0.000 0.000 0.240 0.004 0.756
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM613638 4 0.766 0.3766 0.040 0.184 0.124 0.524 0.096 0.032
#> GSM613639 4 0.728 0.1064 0.364 0.084 0.012 0.384 0.152 0.004
#> GSM613640 4 0.706 0.4532 0.172 0.120 0.060 0.568 0.076 0.004
#> GSM613641 1 0.107 0.7966 0.952 0.000 0.000 0.000 0.048 0.000
#> GSM613642 2 0.787 0.3890 0.016 0.392 0.256 0.244 0.048 0.044
#> GSM613643 4 0.754 0.1988 0.356 0.108 0.040 0.396 0.096 0.004
#> GSM613644 4 0.670 0.4036 0.232 0.088 0.012 0.552 0.112 0.004
#> GSM613645 1 0.420 0.4959 0.704 0.020 0.000 0.256 0.020 0.000
#> GSM613646 4 0.358 0.5685 0.012 0.044 0.092 0.832 0.020 0.000
#> GSM613647 4 0.323 0.5665 0.004 0.000 0.104 0.832 0.060 0.000
#> GSM613648 4 0.401 0.4932 0.000 0.004 0.192 0.756 0.040 0.008
#> GSM613649 3 0.307 0.7467 0.000 0.004 0.792 0.200 0.000 0.004
#> GSM613650 4 0.193 0.5987 0.004 0.004 0.028 0.924 0.040 0.000
#> GSM613651 4 0.497 0.4915 0.044 0.000 0.004 0.672 0.244 0.036
#> GSM613652 5 0.501 0.9318 0.368 0.000 0.000 0.080 0.552 0.000
#> GSM613653 4 0.204 0.5987 0.004 0.008 0.028 0.920 0.040 0.000
#> GSM613654 5 0.501 0.9318 0.368 0.000 0.000 0.080 0.552 0.000
#> GSM613655 1 0.226 0.7255 0.860 0.000 0.000 0.000 0.140 0.000
#> GSM613656 5 0.501 0.9318 0.368 0.000 0.000 0.080 0.552 0.000
#> GSM613657 3 0.274 0.7834 0.000 0.008 0.828 0.164 0.000 0.000
#> GSM613658 1 0.234 0.7027 0.852 0.000 0.000 0.000 0.148 0.000
#> GSM613659 4 0.636 0.2734 0.016 0.292 0.124 0.532 0.036 0.000
#> GSM613660 2 0.551 0.5996 0.000 0.588 0.308 0.008 0.076 0.020
#> GSM613661 1 0.224 0.7765 0.896 0.000 0.000 0.036 0.068 0.000
#> GSM613662 2 0.568 0.5052 0.000 0.700 0.072 0.052 0.072 0.104
#> GSM613663 1 0.148 0.7998 0.940 0.000 0.000 0.020 0.040 0.000
#> GSM613664 2 0.453 0.6175 0.000 0.764 0.136 0.044 0.036 0.020
#> GSM613665 2 0.472 0.6294 0.000 0.732 0.180 0.032 0.036 0.020
#> GSM613666 1 0.107 0.7966 0.952 0.000 0.000 0.000 0.048 0.000
#> GSM613667 1 0.381 0.5317 0.732 0.004 0.000 0.240 0.024 0.000
#> GSM613668 1 0.205 0.7510 0.880 0.000 0.000 0.000 0.120 0.000
#> GSM613669 1 0.107 0.7966 0.952 0.000 0.000 0.000 0.048 0.000
#> GSM613670 2 0.568 0.5052 0.000 0.700 0.072 0.052 0.072 0.104
#> GSM613671 1 0.107 0.7966 0.952 0.000 0.000 0.000 0.048 0.000
#> GSM613672 1 0.155 0.7940 0.936 0.000 0.000 0.020 0.044 0.000
#> GSM613673 1 0.149 0.8004 0.940 0.000 0.000 0.024 0.036 0.000
#> GSM613674 2 0.512 0.6204 0.000 0.644 0.252 0.000 0.084 0.020
#> GSM613675 2 0.610 0.5335 0.004 0.660 0.136 0.092 0.032 0.076
#> GSM613676 2 0.472 0.6294 0.000 0.732 0.180 0.032 0.036 0.020
#> GSM613677 2 0.774 0.2650 0.012 0.356 0.256 0.292 0.060 0.024
#> GSM613678 4 0.631 0.0528 0.024 0.396 0.072 0.468 0.040 0.000
#> GSM613679 2 0.480 0.6259 0.000 0.652 0.272 0.004 0.068 0.004
#> GSM613680 1 0.117 0.8025 0.956 0.000 0.000 0.016 0.028 0.000
#> GSM613681 1 0.178 0.7980 0.932 0.012 0.000 0.032 0.024 0.000
#> GSM613682 1 0.283 0.7493 0.876 0.056 0.000 0.032 0.036 0.000
#> GSM613683 1 0.125 0.8013 0.952 0.000 0.000 0.016 0.032 0.000
#> GSM613684 2 0.594 0.3774 0.000 0.520 0.372 0.036 0.044 0.028
#> GSM613685 2 0.512 0.6204 0.000 0.644 0.252 0.000 0.084 0.020
#> GSM613686 1 0.490 0.5531 0.720 0.148 0.000 0.064 0.068 0.000
#> GSM613687 1 0.178 0.7980 0.932 0.012 0.000 0.032 0.024 0.000
#> GSM613688 2 0.580 0.4144 0.000 0.548 0.348 0.052 0.032 0.020
#> GSM613689 4 0.404 0.5271 0.000 0.004 0.172 0.760 0.060 0.004
#> GSM613690 4 0.491 0.1624 0.000 0.008 0.396 0.556 0.032 0.008
#> GSM613691 4 0.445 0.5129 0.004 0.076 0.160 0.744 0.016 0.000
#> GSM613692 4 0.566 0.2337 0.076 0.000 0.000 0.544 0.344 0.036
#> GSM613693 3 0.631 -0.0522 0.000 0.324 0.532 0.044 0.068 0.032
#> GSM613694 4 0.380 0.5457 0.004 0.000 0.148 0.780 0.068 0.000
#> GSM613695 4 0.347 0.5434 0.000 0.000 0.144 0.804 0.048 0.004
#> GSM613696 4 0.398 0.5551 0.008 0.044 0.124 0.800 0.020 0.004
#> GSM613697 4 0.497 0.4915 0.044 0.000 0.004 0.672 0.244 0.036
#> GSM613698 4 0.310 0.5868 0.004 0.000 0.048 0.840 0.108 0.000
#> GSM613699 4 0.411 0.5344 0.004 0.004 0.164 0.764 0.060 0.004
#> GSM613700 2 0.528 0.6067 0.000 0.604 0.296 0.000 0.080 0.020
#> GSM613701 4 0.743 0.2264 0.248 0.276 0.032 0.392 0.052 0.000
#> GSM613702 4 0.722 0.2563 0.232 0.268 0.032 0.428 0.040 0.000
#> GSM613703 1 0.181 0.7866 0.912 0.000 0.000 0.008 0.080 0.000
#> GSM613704 2 0.568 0.5052 0.000 0.700 0.072 0.052 0.072 0.104
#> GSM613705 4 0.764 0.3473 0.024 0.188 0.148 0.512 0.092 0.036
#> GSM613706 4 0.728 0.2853 0.232 0.252 0.032 0.436 0.048 0.000
#> GSM613707 2 0.492 0.5982 0.000 0.660 0.260 0.004 0.060 0.016
#> GSM613708 1 0.657 0.2348 0.556 0.076 0.004 0.212 0.148 0.004
#> GSM613709 1 0.107 0.7966 0.952 0.000 0.000 0.000 0.048 0.000
#> GSM613710 2 0.551 0.5996 0.000 0.588 0.308 0.008 0.076 0.020
#> GSM613711 3 0.284 0.7827 0.000 0.012 0.824 0.164 0.000 0.000
#> GSM613712 4 0.500 0.5569 0.012 0.004 0.100 0.736 0.112 0.036
#> GSM613713 3 0.488 0.5463 0.000 0.136 0.732 0.092 0.016 0.024
#> GSM613714 4 0.347 0.5434 0.000 0.000 0.144 0.804 0.048 0.004
#> GSM613715 4 0.490 0.0272 0.000 0.012 0.440 0.516 0.028 0.004
#> GSM613716 4 0.335 0.5589 0.000 0.012 0.124 0.828 0.032 0.004
#> GSM613717 3 0.274 0.7834 0.000 0.008 0.828 0.164 0.000 0.000
#> GSM613718 3 0.278 0.7827 0.000 0.008 0.824 0.168 0.000 0.000
#> GSM613719 4 0.204 0.5987 0.004 0.008 0.028 0.920 0.040 0.000
#> GSM613720 3 0.809 -0.0629 0.000 0.280 0.352 0.044 0.148 0.176
#> GSM613721 4 0.748 0.1313 0.000 0.212 0.280 0.408 0.072 0.028
#> GSM613722 2 0.595 0.6136 0.000 0.592 0.268 0.032 0.088 0.020
#> GSM613723 5 0.501 0.9318 0.368 0.000 0.000 0.080 0.552 0.000
#> GSM613724 1 0.134 0.8008 0.948 0.000 0.000 0.028 0.024 0.000
#> GSM613725 2 0.528 0.6067 0.000 0.604 0.296 0.000 0.080 0.020
#> GSM613726 1 0.617 0.3806 0.600 0.064 0.008 0.228 0.096 0.004
#> GSM613727 1 0.222 0.7296 0.864 0.000 0.000 0.000 0.136 0.000
#> GSM613728 2 0.652 0.4353 0.008 0.552 0.144 0.248 0.032 0.016
#> GSM613729 1 0.181 0.7866 0.912 0.000 0.000 0.008 0.080 0.000
#> GSM613730 2 0.649 0.2407 0.008 0.456 0.144 0.356 0.036 0.000
#> GSM613731 4 0.754 0.1988 0.356 0.108 0.040 0.396 0.096 0.004
#> GSM613732 3 0.278 0.7827 0.000 0.008 0.824 0.168 0.000 0.000
#> GSM613733 3 0.316 0.7778 0.000 0.020 0.812 0.164 0.000 0.004
#> GSM613734 5 0.501 0.9318 0.368 0.000 0.000 0.080 0.552 0.000
#> GSM613735 5 0.506 0.9252 0.372 0.000 0.000 0.084 0.544 0.000
#> GSM613736 3 0.404 0.7391 0.000 0.032 0.760 0.188 0.008 0.012
#> GSM613737 4 0.347 0.5625 0.004 0.000 0.096 0.816 0.084 0.000
#> GSM613738 5 0.519 0.8544 0.288 0.000 0.000 0.124 0.588 0.000
#> GSM613739 5 0.519 0.8544 0.288 0.000 0.000 0.124 0.588 0.000
#> GSM613740 3 0.330 0.7805 0.000 0.020 0.804 0.168 0.000 0.008
#> GSM613741 4 0.204 0.5987 0.004 0.008 0.028 0.920 0.040 0.000
#> GSM613742 5 0.519 0.8544 0.288 0.000 0.000 0.124 0.588 0.000
#> GSM613743 3 0.353 0.7587 0.000 0.032 0.804 0.152 0.004 0.008
#> GSM613744 3 0.267 0.7798 0.000 0.004 0.828 0.168 0.000 0.000
#> GSM613745 4 0.358 0.5685 0.012 0.044 0.092 0.832 0.020 0.000
#> GSM613746 3 0.770 -0.0881 0.000 0.296 0.356 0.012 0.160 0.176
#> GSM613747 5 0.501 0.9318 0.368 0.000 0.000 0.080 0.552 0.000
#> GSM613748 4 0.672 0.0130 0.036 0.380 0.112 0.440 0.032 0.000
#> GSM613749 4 0.722 0.2132 0.308 0.264 0.016 0.364 0.048 0.000
#> GSM613750 6 0.279 1.0000 0.000 0.000 0.200 0.000 0.000 0.800
#> GSM613751 6 0.279 1.0000 0.000 0.000 0.200 0.000 0.000 0.800
#> GSM613752 6 0.279 1.0000 0.000 0.000 0.200 0.000 0.000 0.800
#> GSM613753 6 0.279 1.0000 0.000 0.000 0.200 0.000 0.000 0.800
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) k
#> MAD:hclust 110 1.51e-01 2
#> MAD:hclust 80 4.55e-02 3
#> MAD:hclust 82 1.55e-03 4
#> MAD:hclust 88 1.89e-03 5
#> MAD:hclust 83 7.13e-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["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 27425 rows and 116 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'MAD' method.
#> Subgroups are detected by 'kmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.838 0.910 0.951 0.4872 0.517 0.517
#> 3 3 0.592 0.728 0.843 0.3483 0.760 0.559
#> 4 4 0.576 0.621 0.785 0.1268 0.862 0.616
#> 5 5 0.642 0.587 0.739 0.0653 0.862 0.528
#> 6 6 0.692 0.583 0.730 0.0457 0.929 0.672
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
#> GSM613638 2 0.574 0.835 0.136 0.864
#> GSM613639 1 0.000 0.963 1.000 0.000
#> GSM613640 2 0.343 0.924 0.064 0.936
#> GSM613641 1 0.000 0.963 1.000 0.000
#> GSM613642 2 0.327 0.926 0.060 0.940
#> GSM613643 1 0.000 0.963 1.000 0.000
#> GSM613644 1 0.000 0.963 1.000 0.000
#> GSM613645 1 0.000 0.963 1.000 0.000
#> GSM613646 2 0.753 0.735 0.216 0.784
#> GSM613647 2 0.738 0.746 0.208 0.792
#> GSM613648 2 0.000 0.934 0.000 1.000
#> GSM613649 2 0.000 0.934 0.000 1.000
#> GSM613650 1 0.760 0.753 0.780 0.220
#> GSM613651 1 0.753 0.759 0.784 0.216
#> GSM613652 1 0.343 0.926 0.936 0.064
#> GSM613653 2 0.844 0.646 0.272 0.728
#> GSM613654 1 0.343 0.926 0.936 0.064
#> GSM613655 1 0.000 0.963 1.000 0.000
#> GSM613656 1 0.343 0.926 0.936 0.064
#> GSM613657 2 0.000 0.934 0.000 1.000
#> GSM613658 1 0.000 0.963 1.000 0.000
#> GSM613659 2 0.343 0.924 0.064 0.936
#> GSM613660 2 0.327 0.926 0.060 0.940
#> GSM613661 1 0.000 0.963 1.000 0.000
#> GSM613662 2 0.343 0.924 0.064 0.936
#> GSM613663 1 0.000 0.963 1.000 0.000
#> GSM613664 2 0.343 0.924 0.064 0.936
#> GSM613665 2 0.343 0.924 0.064 0.936
#> GSM613666 1 0.000 0.963 1.000 0.000
#> GSM613667 1 0.000 0.963 1.000 0.000
#> GSM613668 1 0.000 0.963 1.000 0.000
#> GSM613669 1 0.000 0.963 1.000 0.000
#> GSM613670 2 0.343 0.924 0.064 0.936
#> GSM613671 1 0.000 0.963 1.000 0.000
#> GSM613672 1 0.000 0.963 1.000 0.000
#> GSM613673 1 0.000 0.963 1.000 0.000
#> GSM613674 2 0.343 0.924 0.064 0.936
#> GSM613675 2 0.343 0.924 0.064 0.936
#> GSM613676 2 0.204 0.931 0.032 0.968
#> GSM613677 2 0.204 0.931 0.032 0.968
#> GSM613678 1 0.895 0.484 0.688 0.312
#> GSM613679 2 0.343 0.924 0.064 0.936
#> GSM613680 1 0.000 0.963 1.000 0.000
#> GSM613681 1 0.000 0.963 1.000 0.000
#> GSM613682 1 0.000 0.963 1.000 0.000
#> GSM613683 1 0.000 0.963 1.000 0.000
#> GSM613684 2 0.000 0.934 0.000 1.000
#> GSM613685 2 0.343 0.924 0.064 0.936
#> GSM613686 1 0.000 0.963 1.000 0.000
#> GSM613687 1 0.000 0.963 1.000 0.000
#> GSM613688 2 0.343 0.924 0.064 0.936
#> GSM613689 2 0.000 0.934 0.000 1.000
#> GSM613690 2 0.000 0.934 0.000 1.000
#> GSM613691 2 0.000 0.934 0.000 1.000
#> GSM613692 1 0.343 0.926 0.936 0.064
#> GSM613693 2 0.000 0.934 0.000 1.000
#> GSM613694 2 0.808 0.687 0.248 0.752
#> GSM613695 2 0.000 0.934 0.000 1.000
#> GSM613696 2 0.000 0.934 0.000 1.000
#> GSM613697 1 0.753 0.759 0.784 0.216
#> GSM613698 2 0.671 0.788 0.176 0.824
#> GSM613699 2 0.000 0.934 0.000 1.000
#> GSM613700 2 0.343 0.924 0.064 0.936
#> GSM613701 2 0.343 0.924 0.064 0.936
#> GSM613702 2 0.343 0.924 0.064 0.936
#> GSM613703 1 0.000 0.963 1.000 0.000
#> GSM613704 2 0.343 0.924 0.064 0.936
#> GSM613705 2 0.000 0.934 0.000 1.000
#> GSM613706 2 0.886 0.663 0.304 0.696
#> GSM613707 2 0.327 0.926 0.060 0.940
#> GSM613708 1 0.000 0.963 1.000 0.000
#> GSM613709 1 0.000 0.963 1.000 0.000
#> GSM613710 2 0.327 0.926 0.060 0.940
#> GSM613711 2 0.000 0.934 0.000 1.000
#> GSM613712 2 0.482 0.866 0.104 0.896
#> GSM613713 2 0.000 0.934 0.000 1.000
#> GSM613714 2 0.000 0.934 0.000 1.000
#> GSM613715 2 0.000 0.934 0.000 1.000
#> GSM613716 2 0.000 0.934 0.000 1.000
#> GSM613717 2 0.000 0.934 0.000 1.000
#> GSM613718 2 0.000 0.934 0.000 1.000
#> GSM613719 2 0.932 0.488 0.348 0.652
#> GSM613720 2 0.000 0.934 0.000 1.000
#> GSM613721 2 0.000 0.934 0.000 1.000
#> GSM613722 2 0.343 0.924 0.064 0.936
#> GSM613723 1 0.343 0.926 0.936 0.064
#> GSM613724 1 0.000 0.963 1.000 0.000
#> GSM613725 2 0.343 0.924 0.064 0.936
#> GSM613726 1 0.000 0.963 1.000 0.000
#> GSM613727 1 0.000 0.963 1.000 0.000
#> GSM613728 2 0.343 0.924 0.064 0.936
#> GSM613729 1 0.000 0.963 1.000 0.000
#> GSM613730 2 0.343 0.924 0.064 0.936
#> GSM613731 1 0.000 0.963 1.000 0.000
#> GSM613732 2 0.000 0.934 0.000 1.000
#> GSM613733 2 0.000 0.934 0.000 1.000
#> GSM613734 1 0.000 0.963 1.000 0.000
#> GSM613735 1 0.343 0.926 0.936 0.064
#> GSM613736 2 0.000 0.934 0.000 1.000
#> GSM613737 2 0.767 0.724 0.224 0.776
#> GSM613738 1 0.343 0.926 0.936 0.064
#> GSM613739 1 0.343 0.926 0.936 0.064
#> GSM613740 2 0.000 0.934 0.000 1.000
#> GSM613741 2 0.844 0.646 0.272 0.728
#> GSM613742 1 0.343 0.926 0.936 0.064
#> GSM613743 2 0.000 0.934 0.000 1.000
#> GSM613744 2 0.000 0.934 0.000 1.000
#> GSM613745 2 0.443 0.876 0.092 0.908
#> GSM613746 2 0.000 0.934 0.000 1.000
#> GSM613747 1 0.000 0.963 1.000 0.000
#> GSM613748 2 0.343 0.924 0.064 0.936
#> GSM613749 1 0.000 0.963 1.000 0.000
#> GSM613750 2 0.000 0.934 0.000 1.000
#> GSM613751 2 0.000 0.934 0.000 1.000
#> GSM613752 2 0.000 0.934 0.000 1.000
#> GSM613753 2 0.000 0.934 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM613638 3 0.3377 0.705 0.012 0.092 0.896
#> GSM613639 1 0.5216 0.704 0.740 0.000 0.260
#> GSM613640 2 0.6309 0.147 0.000 0.504 0.496
#> GSM613641 1 0.0000 0.923 1.000 0.000 0.000
#> GSM613642 2 0.4235 0.694 0.000 0.824 0.176
#> GSM613643 1 0.5465 0.679 0.712 0.000 0.288
#> GSM613644 1 0.5733 0.644 0.676 0.000 0.324
#> GSM613645 1 0.4654 0.768 0.792 0.000 0.208
#> GSM613646 3 0.5775 0.557 0.012 0.260 0.728
#> GSM613647 3 0.2339 0.695 0.012 0.048 0.940
#> GSM613648 3 0.5785 0.663 0.000 0.332 0.668
#> GSM613649 3 0.6111 0.632 0.000 0.396 0.604
#> GSM613650 3 0.4978 0.493 0.216 0.004 0.780
#> GSM613651 3 0.2261 0.651 0.068 0.000 0.932
#> GSM613652 1 0.3116 0.887 0.892 0.000 0.108
#> GSM613653 3 0.5843 0.556 0.016 0.252 0.732
#> GSM613654 1 0.3116 0.887 0.892 0.000 0.108
#> GSM613655 1 0.0000 0.923 1.000 0.000 0.000
#> GSM613656 1 0.3116 0.887 0.892 0.000 0.108
#> GSM613657 3 0.6235 0.608 0.000 0.436 0.564
#> GSM613658 1 0.0000 0.923 1.000 0.000 0.000
#> GSM613659 2 0.5291 0.622 0.000 0.732 0.268
#> GSM613660 2 0.0000 0.796 0.000 1.000 0.000
#> GSM613661 1 0.2066 0.896 0.940 0.000 0.060
#> GSM613662 2 0.0237 0.796 0.000 0.996 0.004
#> GSM613663 1 0.0000 0.923 1.000 0.000 0.000
#> GSM613664 2 0.0237 0.796 0.000 0.996 0.004
#> GSM613665 2 0.0000 0.796 0.000 1.000 0.000
#> GSM613666 1 0.0000 0.923 1.000 0.000 0.000
#> GSM613667 1 0.4654 0.768 0.792 0.000 0.208
#> GSM613668 1 0.0000 0.923 1.000 0.000 0.000
#> GSM613669 1 0.0000 0.923 1.000 0.000 0.000
#> GSM613670 2 0.5618 0.626 0.008 0.732 0.260
#> GSM613671 1 0.0000 0.923 1.000 0.000 0.000
#> GSM613672 1 0.0000 0.923 1.000 0.000 0.000
#> GSM613673 1 0.0000 0.923 1.000 0.000 0.000
#> GSM613674 2 0.0000 0.796 0.000 1.000 0.000
#> GSM613675 2 0.0000 0.796 0.000 1.000 0.000
#> GSM613676 2 0.0000 0.796 0.000 1.000 0.000
#> GSM613677 2 0.4346 0.678 0.000 0.816 0.184
#> GSM613678 2 0.8379 0.503 0.128 0.604 0.268
#> GSM613679 2 0.0000 0.796 0.000 1.000 0.000
#> GSM613680 1 0.0000 0.923 1.000 0.000 0.000
#> GSM613681 1 0.0000 0.923 1.000 0.000 0.000
#> GSM613682 1 0.0000 0.923 1.000 0.000 0.000
#> GSM613683 1 0.0000 0.923 1.000 0.000 0.000
#> GSM613684 2 0.0000 0.796 0.000 1.000 0.000
#> GSM613685 2 0.0000 0.796 0.000 1.000 0.000
#> GSM613686 1 0.1031 0.915 0.976 0.000 0.024
#> GSM613687 1 0.0000 0.923 1.000 0.000 0.000
#> GSM613688 2 0.0592 0.793 0.000 0.988 0.012
#> GSM613689 3 0.4504 0.695 0.000 0.196 0.804
#> GSM613690 3 0.3340 0.712 0.000 0.120 0.880
#> GSM613691 2 0.3038 0.748 0.000 0.896 0.104
#> GSM613692 1 0.3340 0.879 0.880 0.000 0.120
#> GSM613693 2 0.6062 -0.238 0.000 0.616 0.384
#> GSM613694 3 0.2339 0.695 0.012 0.048 0.940
#> GSM613695 3 0.2448 0.704 0.000 0.076 0.924
#> GSM613696 3 0.3551 0.703 0.000 0.132 0.868
#> GSM613697 3 0.2261 0.651 0.068 0.000 0.932
#> GSM613698 3 0.2339 0.695 0.012 0.048 0.940
#> GSM613699 3 0.3340 0.705 0.000 0.120 0.880
#> GSM613700 2 0.0000 0.796 0.000 1.000 0.000
#> GSM613701 2 0.5216 0.629 0.000 0.740 0.260
#> GSM613702 2 0.5291 0.622 0.000 0.732 0.268
#> GSM613703 1 0.0000 0.923 1.000 0.000 0.000
#> GSM613704 2 0.0000 0.796 0.000 1.000 0.000
#> GSM613705 3 0.2261 0.701 0.000 0.068 0.932
#> GSM613706 2 0.7959 0.514 0.092 0.620 0.288
#> GSM613707 2 0.0000 0.796 0.000 1.000 0.000
#> GSM613708 1 0.0000 0.923 1.000 0.000 0.000
#> GSM613709 1 0.0000 0.923 1.000 0.000 0.000
#> GSM613710 2 0.0237 0.793 0.000 0.996 0.004
#> GSM613711 3 0.6252 0.599 0.000 0.444 0.556
#> GSM613712 3 0.2280 0.696 0.008 0.052 0.940
#> GSM613713 3 0.6286 0.569 0.000 0.464 0.536
#> GSM613714 3 0.3619 0.707 0.000 0.136 0.864
#> GSM613715 3 0.5465 0.679 0.000 0.288 0.712
#> GSM613716 3 0.3941 0.704 0.000 0.156 0.844
#> GSM613717 3 0.6252 0.599 0.000 0.444 0.556
#> GSM613718 3 0.6235 0.608 0.000 0.436 0.564
#> GSM613719 3 0.2636 0.691 0.020 0.048 0.932
#> GSM613720 3 0.6252 0.600 0.000 0.444 0.556
#> GSM613721 3 0.6299 0.050 0.000 0.476 0.524
#> GSM613722 2 0.0000 0.796 0.000 1.000 0.000
#> GSM613723 1 0.3116 0.887 0.892 0.000 0.108
#> GSM613724 1 0.0000 0.923 1.000 0.000 0.000
#> GSM613725 2 0.0000 0.796 0.000 1.000 0.000
#> GSM613726 1 0.4796 0.754 0.780 0.000 0.220
#> GSM613727 1 0.0000 0.923 1.000 0.000 0.000
#> GSM613728 2 0.0000 0.796 0.000 1.000 0.000
#> GSM613729 1 0.0000 0.923 1.000 0.000 0.000
#> GSM613730 2 0.5291 0.622 0.000 0.732 0.268
#> GSM613731 1 0.5291 0.696 0.732 0.000 0.268
#> GSM613732 3 0.6235 0.608 0.000 0.436 0.564
#> GSM613733 3 0.6286 0.569 0.000 0.464 0.536
#> GSM613734 1 0.1964 0.907 0.944 0.000 0.056
#> GSM613735 1 0.3038 0.889 0.896 0.000 0.104
#> GSM613736 3 0.6244 0.603 0.000 0.440 0.560
#> GSM613737 3 0.2339 0.695 0.012 0.048 0.940
#> GSM613738 1 0.3340 0.879 0.880 0.000 0.120
#> GSM613739 1 0.3340 0.879 0.880 0.000 0.120
#> GSM613740 3 0.6235 0.608 0.000 0.436 0.564
#> GSM613741 3 0.5843 0.556 0.016 0.252 0.732
#> GSM613742 1 0.3551 0.873 0.868 0.000 0.132
#> GSM613743 3 0.6244 0.603 0.000 0.440 0.560
#> GSM613744 3 0.6235 0.608 0.000 0.436 0.564
#> GSM613745 3 0.5656 0.556 0.008 0.264 0.728
#> GSM613746 2 0.2625 0.694 0.000 0.916 0.084
#> GSM613747 1 0.1964 0.907 0.944 0.000 0.056
#> GSM613748 2 0.5291 0.622 0.000 0.732 0.268
#> GSM613749 2 0.8994 0.449 0.184 0.556 0.260
#> GSM613750 3 0.5859 0.615 0.000 0.344 0.656
#> GSM613751 3 0.6026 0.595 0.000 0.376 0.624
#> GSM613752 3 0.6026 0.595 0.000 0.376 0.624
#> GSM613753 3 0.1163 0.682 0.000 0.028 0.972
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 4 0.5291 0.5867 0.000 0.024 0.324 0.652
#> GSM613639 1 0.5112 0.3491 0.608 0.000 0.008 0.384
#> GSM613640 4 0.7870 0.4342 0.028 0.220 0.208 0.544
#> GSM613641 1 0.0000 0.7914 1.000 0.000 0.000 0.000
#> GSM613642 2 0.4235 0.7509 0.000 0.824 0.092 0.084
#> GSM613643 4 0.6000 0.2504 0.356 0.000 0.052 0.592
#> GSM613644 4 0.5754 0.3302 0.316 0.000 0.048 0.636
#> GSM613645 1 0.4720 0.4633 0.672 0.004 0.000 0.324
#> GSM613646 4 0.6495 0.5682 0.020 0.092 0.220 0.668
#> GSM613647 4 0.4790 0.5588 0.000 0.000 0.380 0.620
#> GSM613648 3 0.2376 0.8001 0.000 0.068 0.916 0.016
#> GSM613649 3 0.3390 0.8254 0.000 0.132 0.852 0.016
#> GSM613650 4 0.4986 0.6182 0.044 0.000 0.216 0.740
#> GSM613651 4 0.4560 0.5701 0.004 0.000 0.296 0.700
#> GSM613652 1 0.5407 0.1884 0.504 0.000 0.012 0.484
#> GSM613653 4 0.6527 0.5690 0.020 0.092 0.224 0.664
#> GSM613654 1 0.5407 0.1884 0.504 0.000 0.012 0.484
#> GSM613655 1 0.0469 0.7879 0.988 0.000 0.000 0.012
#> GSM613656 1 0.5407 0.1884 0.504 0.000 0.012 0.484
#> GSM613657 3 0.2921 0.8281 0.000 0.140 0.860 0.000
#> GSM613658 1 0.0469 0.7879 0.988 0.000 0.000 0.012
#> GSM613659 2 0.5954 0.5543 0.000 0.604 0.052 0.344
#> GSM613660 2 0.1820 0.8121 0.000 0.944 0.036 0.020
#> GSM613661 1 0.4277 0.5312 0.720 0.000 0.000 0.280
#> GSM613662 2 0.2125 0.8000 0.000 0.920 0.004 0.076
#> GSM613663 1 0.0336 0.7897 0.992 0.000 0.000 0.008
#> GSM613664 2 0.1716 0.8036 0.000 0.936 0.000 0.064
#> GSM613665 2 0.1584 0.8124 0.000 0.952 0.036 0.012
#> GSM613666 1 0.0000 0.7914 1.000 0.000 0.000 0.000
#> GSM613667 1 0.4543 0.4684 0.676 0.000 0.000 0.324
#> GSM613668 1 0.0188 0.7908 0.996 0.000 0.000 0.004
#> GSM613669 1 0.0000 0.7914 1.000 0.000 0.000 0.000
#> GSM613670 2 0.4589 0.7306 0.000 0.784 0.048 0.168
#> GSM613671 1 0.0000 0.7914 1.000 0.000 0.000 0.000
#> GSM613672 1 0.0188 0.7908 0.996 0.000 0.000 0.004
#> GSM613673 1 0.0469 0.7886 0.988 0.000 0.000 0.012
#> GSM613674 2 0.1118 0.8118 0.000 0.964 0.036 0.000
#> GSM613675 2 0.1576 0.8053 0.000 0.948 0.004 0.048
#> GSM613676 2 0.1677 0.8114 0.000 0.948 0.040 0.012
#> GSM613677 2 0.6475 0.6209 0.000 0.644 0.172 0.184
#> GSM613678 2 0.7054 0.4592 0.048 0.532 0.040 0.380
#> GSM613679 2 0.1452 0.8119 0.000 0.956 0.036 0.008
#> GSM613680 1 0.0000 0.7914 1.000 0.000 0.000 0.000
#> GSM613681 1 0.0000 0.7914 1.000 0.000 0.000 0.000
#> GSM613682 1 0.0469 0.7886 0.988 0.000 0.000 0.012
#> GSM613683 1 0.0469 0.7879 0.988 0.000 0.000 0.012
#> GSM613684 2 0.1305 0.8116 0.000 0.960 0.036 0.004
#> GSM613685 2 0.1118 0.8118 0.000 0.964 0.036 0.000
#> GSM613686 1 0.3837 0.6083 0.776 0.000 0.000 0.224
#> GSM613687 1 0.0469 0.7886 0.988 0.000 0.000 0.012
#> GSM613688 2 0.1520 0.8091 0.000 0.956 0.024 0.020
#> GSM613689 3 0.1767 0.7483 0.000 0.012 0.944 0.044
#> GSM613690 3 0.1824 0.7329 0.000 0.004 0.936 0.060
#> GSM613691 2 0.5160 0.7230 0.000 0.760 0.104 0.136
#> GSM613692 4 0.5643 -0.0357 0.428 0.000 0.024 0.548
#> GSM613693 3 0.5812 0.6015 0.000 0.328 0.624 0.048
#> GSM613694 4 0.4790 0.5588 0.000 0.000 0.380 0.620
#> GSM613695 3 0.3528 0.5409 0.000 0.000 0.808 0.192
#> GSM613696 3 0.5057 0.1786 0.000 0.012 0.648 0.340
#> GSM613697 4 0.4560 0.5443 0.004 0.000 0.296 0.700
#> GSM613698 4 0.5050 0.5206 0.000 0.004 0.408 0.588
#> GSM613699 3 0.5039 -0.1130 0.000 0.004 0.592 0.404
#> GSM613700 2 0.1820 0.8121 0.000 0.944 0.036 0.020
#> GSM613701 2 0.5672 0.6192 0.000 0.668 0.056 0.276
#> GSM613702 2 0.5903 0.5618 0.000 0.616 0.052 0.332
#> GSM613703 1 0.2081 0.7472 0.916 0.000 0.000 0.084
#> GSM613704 2 0.1743 0.8029 0.000 0.940 0.004 0.056
#> GSM613705 4 0.4585 0.5923 0.000 0.000 0.332 0.668
#> GSM613706 2 0.8257 0.2149 0.080 0.436 0.088 0.396
#> GSM613707 2 0.1118 0.8118 0.000 0.964 0.036 0.000
#> GSM613708 1 0.1302 0.7714 0.956 0.000 0.000 0.044
#> GSM613709 1 0.0000 0.7914 1.000 0.000 0.000 0.000
#> GSM613710 2 0.1913 0.8108 0.000 0.940 0.040 0.020
#> GSM613711 3 0.2973 0.8272 0.000 0.144 0.856 0.000
#> GSM613712 4 0.4907 0.5097 0.000 0.000 0.420 0.580
#> GSM613713 3 0.4008 0.7518 0.000 0.244 0.756 0.000
#> GSM613714 3 0.1902 0.7285 0.000 0.004 0.932 0.064
#> GSM613715 3 0.2036 0.7601 0.000 0.032 0.936 0.032
#> GSM613716 3 0.5472 0.3905 0.000 0.044 0.676 0.280
#> GSM613717 3 0.2973 0.8272 0.000 0.144 0.856 0.000
#> GSM613718 3 0.3142 0.8288 0.000 0.132 0.860 0.008
#> GSM613719 4 0.4608 0.5836 0.000 0.004 0.304 0.692
#> GSM613720 3 0.4839 0.7838 0.000 0.200 0.756 0.044
#> GSM613721 2 0.7269 0.3917 0.000 0.524 0.180 0.296
#> GSM613722 2 0.1820 0.8121 0.000 0.944 0.036 0.020
#> GSM613723 1 0.5407 0.1884 0.504 0.000 0.012 0.484
#> GSM613724 1 0.0469 0.7879 0.988 0.000 0.000 0.012
#> GSM613725 2 0.1820 0.8121 0.000 0.944 0.036 0.020
#> GSM613726 1 0.5038 0.4299 0.652 0.000 0.012 0.336
#> GSM613727 1 0.0188 0.7908 0.996 0.000 0.000 0.004
#> GSM613728 2 0.1004 0.8128 0.000 0.972 0.004 0.024
#> GSM613729 1 0.0188 0.7907 0.996 0.000 0.000 0.004
#> GSM613730 2 0.5847 0.5836 0.000 0.628 0.052 0.320
#> GSM613731 1 0.6101 0.2396 0.560 0.000 0.052 0.388
#> GSM613732 3 0.3142 0.8288 0.000 0.132 0.860 0.008
#> GSM613733 3 0.4319 0.7559 0.000 0.228 0.760 0.012
#> GSM613734 1 0.4744 0.5420 0.704 0.000 0.012 0.284
#> GSM613735 1 0.5402 0.2144 0.516 0.000 0.012 0.472
#> GSM613736 3 0.2921 0.8281 0.000 0.140 0.860 0.000
#> GSM613737 4 0.4898 0.5125 0.000 0.000 0.416 0.584
#> GSM613738 4 0.5643 -0.0357 0.428 0.000 0.024 0.548
#> GSM613739 4 0.5650 -0.0434 0.432 0.000 0.024 0.544
#> GSM613740 3 0.3142 0.8288 0.000 0.132 0.860 0.008
#> GSM613741 4 0.6551 0.5678 0.020 0.096 0.220 0.664
#> GSM613742 4 0.5933 0.0220 0.408 0.000 0.040 0.552
#> GSM613743 3 0.2973 0.8272 0.000 0.144 0.856 0.000
#> GSM613744 3 0.3142 0.8288 0.000 0.132 0.860 0.008
#> GSM613745 4 0.6606 0.5651 0.020 0.100 0.220 0.660
#> GSM613746 2 0.3392 0.7557 0.000 0.872 0.072 0.056
#> GSM613747 1 0.4770 0.5369 0.700 0.000 0.012 0.288
#> GSM613748 2 0.5985 0.5400 0.000 0.596 0.052 0.352
#> GSM613749 4 0.8465 -0.1575 0.232 0.348 0.028 0.392
#> GSM613750 3 0.3533 0.7950 0.000 0.080 0.864 0.056
#> GSM613751 3 0.4094 0.7984 0.000 0.116 0.828 0.056
#> GSM613752 3 0.4094 0.7984 0.000 0.116 0.828 0.056
#> GSM613753 3 0.2281 0.7266 0.000 0.000 0.904 0.096
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM613638 4 0.5916 0.472503 0.000 0.060 0.080 0.672 0.188
#> GSM613639 4 0.4841 0.162091 0.416 0.024 0.000 0.560 0.000
#> GSM613640 4 0.5619 0.530212 0.004 0.148 0.036 0.708 0.104
#> GSM613641 1 0.0451 0.869342 0.988 0.000 0.000 0.004 0.008
#> GSM613642 2 0.5274 0.638034 0.000 0.724 0.036 0.160 0.080
#> GSM613643 4 0.5436 0.461520 0.212 0.008 0.000 0.672 0.108
#> GSM613644 4 0.5038 0.493073 0.168 0.016 0.000 0.728 0.088
#> GSM613645 1 0.4829 0.031776 0.500 0.020 0.000 0.480 0.000
#> GSM613646 4 0.5407 0.510563 0.000 0.064 0.076 0.728 0.132
#> GSM613647 5 0.6257 -0.068944 0.000 0.000 0.148 0.392 0.460
#> GSM613648 3 0.3441 0.768681 0.000 0.008 0.848 0.088 0.056
#> GSM613649 3 0.2321 0.807990 0.000 0.024 0.916 0.044 0.016
#> GSM613650 4 0.5518 0.384432 0.004 0.004 0.088 0.648 0.256
#> GSM613651 5 0.5240 0.262283 0.000 0.000 0.092 0.252 0.656
#> GSM613652 5 0.4060 0.605940 0.360 0.000 0.000 0.000 0.640
#> GSM613653 4 0.5690 0.502354 0.000 0.076 0.084 0.708 0.132
#> GSM613654 5 0.4045 0.609542 0.356 0.000 0.000 0.000 0.644
#> GSM613655 1 0.0609 0.864706 0.980 0.000 0.000 0.000 0.020
#> GSM613656 5 0.4060 0.605940 0.360 0.000 0.000 0.000 0.640
#> GSM613657 3 0.0566 0.823537 0.000 0.012 0.984 0.000 0.004
#> GSM613658 1 0.0898 0.864508 0.972 0.000 0.000 0.008 0.020
#> GSM613659 4 0.5569 0.176580 0.000 0.364 0.000 0.556 0.080
#> GSM613660 2 0.4374 0.763375 0.000 0.792 0.112 0.076 0.020
#> GSM613661 1 0.4473 0.270043 0.580 0.008 0.000 0.412 0.000
#> GSM613662 2 0.4568 0.682358 0.000 0.768 0.012 0.136 0.084
#> GSM613663 1 0.0566 0.865462 0.984 0.004 0.000 0.012 0.000
#> GSM613664 2 0.4249 0.699414 0.000 0.792 0.008 0.100 0.100
#> GSM613665 2 0.3059 0.786317 0.000 0.860 0.108 0.028 0.004
#> GSM613666 1 0.0579 0.868986 0.984 0.000 0.000 0.008 0.008
#> GSM613667 1 0.4807 0.127412 0.532 0.020 0.000 0.448 0.000
#> GSM613668 1 0.0609 0.864706 0.980 0.000 0.000 0.000 0.020
#> GSM613669 1 0.0579 0.868986 0.984 0.000 0.000 0.008 0.008
#> GSM613670 2 0.5040 0.570654 0.000 0.680 0.000 0.236 0.084
#> GSM613671 1 0.0579 0.868986 0.984 0.000 0.000 0.008 0.008
#> GSM613672 1 0.0898 0.865063 0.972 0.008 0.000 0.000 0.020
#> GSM613673 1 0.1408 0.844730 0.948 0.008 0.000 0.044 0.000
#> GSM613674 2 0.3350 0.780205 0.000 0.844 0.112 0.004 0.040
#> GSM613675 2 0.4750 0.690836 0.000 0.764 0.024 0.132 0.080
#> GSM613676 2 0.3160 0.785208 0.000 0.852 0.116 0.028 0.004
#> GSM613677 4 0.6882 0.267336 0.000 0.320 0.048 0.512 0.120
#> GSM613678 4 0.5447 0.420270 0.084 0.280 0.000 0.632 0.004
#> GSM613679 2 0.2968 0.784332 0.000 0.864 0.112 0.012 0.012
#> GSM613680 1 0.0404 0.868102 0.988 0.000 0.000 0.000 0.012
#> GSM613681 1 0.0451 0.869443 0.988 0.000 0.000 0.008 0.004
#> GSM613682 1 0.0898 0.860768 0.972 0.008 0.000 0.020 0.000
#> GSM613683 1 0.0609 0.864706 0.980 0.000 0.000 0.000 0.020
#> GSM613684 2 0.3830 0.778116 0.000 0.824 0.116 0.020 0.040
#> GSM613685 2 0.3350 0.780205 0.000 0.844 0.112 0.004 0.040
#> GSM613686 1 0.4193 0.494881 0.684 0.012 0.000 0.304 0.000
#> GSM613687 1 0.0898 0.860768 0.972 0.008 0.000 0.020 0.000
#> GSM613688 2 0.2713 0.742990 0.000 0.888 0.004 0.036 0.072
#> GSM613689 3 0.3912 0.733210 0.000 0.000 0.804 0.088 0.108
#> GSM613690 3 0.4270 0.709824 0.000 0.000 0.776 0.112 0.112
#> GSM613691 2 0.6034 0.421562 0.000 0.588 0.020 0.300 0.092
#> GSM613692 5 0.4477 0.644165 0.288 0.000 0.008 0.016 0.688
#> GSM613693 3 0.7410 0.251238 0.000 0.248 0.512 0.144 0.096
#> GSM613694 4 0.6248 0.166573 0.000 0.000 0.148 0.468 0.384
#> GSM613695 3 0.5604 0.496402 0.000 0.000 0.628 0.240 0.132
#> GSM613696 4 0.6886 0.064938 0.000 0.020 0.344 0.460 0.176
#> GSM613697 5 0.5053 0.305454 0.000 0.000 0.096 0.216 0.688
#> GSM613698 5 0.6372 0.052255 0.000 0.000 0.184 0.324 0.492
#> GSM613699 3 0.6413 0.027685 0.000 0.000 0.432 0.396 0.172
#> GSM613700 2 0.4179 0.765068 0.000 0.800 0.112 0.076 0.012
#> GSM613701 2 0.4826 0.004089 0.000 0.508 0.000 0.472 0.020
#> GSM613702 4 0.4276 0.313187 0.000 0.380 0.000 0.616 0.004
#> GSM613703 1 0.2011 0.808691 0.908 0.000 0.000 0.088 0.004
#> GSM613704 2 0.4726 0.689146 0.000 0.768 0.024 0.120 0.088
#> GSM613705 4 0.6185 0.404510 0.000 0.032 0.116 0.620 0.232
#> GSM613706 4 0.5496 0.521504 0.036 0.192 0.000 0.696 0.076
#> GSM613707 2 0.3350 0.780205 0.000 0.844 0.112 0.004 0.040
#> GSM613708 1 0.1697 0.836919 0.932 0.008 0.000 0.060 0.000
#> GSM613709 1 0.0451 0.869342 0.988 0.000 0.000 0.004 0.008
#> GSM613710 2 0.4583 0.754491 0.000 0.776 0.120 0.084 0.020
#> GSM613711 3 0.0771 0.822617 0.000 0.020 0.976 0.000 0.004
#> GSM613712 5 0.6552 -0.025479 0.000 0.000 0.208 0.348 0.444
#> GSM613713 3 0.3927 0.694822 0.000 0.164 0.792 0.004 0.040
#> GSM613714 3 0.4743 0.665665 0.000 0.000 0.732 0.156 0.112
#> GSM613715 3 0.3907 0.748891 0.000 0.012 0.820 0.100 0.068
#> GSM613716 4 0.7779 -0.019356 0.000 0.100 0.364 0.384 0.152
#> GSM613717 3 0.0771 0.822617 0.000 0.020 0.976 0.000 0.004
#> GSM613718 3 0.0404 0.823777 0.000 0.012 0.988 0.000 0.000
#> GSM613719 4 0.6151 0.224397 0.000 0.004 0.124 0.516 0.356
#> GSM613720 3 0.6419 0.565333 0.000 0.124 0.644 0.148 0.084
#> GSM613721 4 0.6903 -0.000414 0.000 0.400 0.040 0.440 0.120
#> GSM613722 2 0.4179 0.765068 0.000 0.800 0.112 0.076 0.012
#> GSM613723 5 0.4045 0.609542 0.356 0.000 0.000 0.000 0.644
#> GSM613724 1 0.0609 0.864706 0.980 0.000 0.000 0.000 0.020
#> GSM613725 2 0.4374 0.763375 0.000 0.792 0.112 0.076 0.020
#> GSM613726 4 0.4905 0.028765 0.464 0.012 0.000 0.516 0.008
#> GSM613727 1 0.0609 0.864706 0.980 0.000 0.000 0.000 0.020
#> GSM613728 2 0.3656 0.744597 0.000 0.844 0.024 0.080 0.052
#> GSM613729 1 0.0510 0.867180 0.984 0.000 0.000 0.016 0.000
#> GSM613730 4 0.5168 0.297602 0.000 0.356 0.000 0.592 0.052
#> GSM613731 4 0.5158 0.386055 0.316 0.008 0.000 0.632 0.044
#> GSM613732 3 0.0404 0.823777 0.000 0.012 0.988 0.000 0.000
#> GSM613733 3 0.2678 0.766458 0.000 0.100 0.880 0.016 0.004
#> GSM613734 5 0.4291 0.424680 0.464 0.000 0.000 0.000 0.536
#> GSM613735 5 0.4074 0.600483 0.364 0.000 0.000 0.000 0.636
#> GSM613736 3 0.0771 0.822617 0.000 0.020 0.976 0.000 0.004
#> GSM613737 5 0.6455 0.034161 0.000 0.000 0.200 0.320 0.480
#> GSM613738 5 0.4477 0.644165 0.288 0.000 0.008 0.016 0.688
#> GSM613739 5 0.4477 0.644165 0.288 0.000 0.008 0.016 0.688
#> GSM613740 3 0.0404 0.823777 0.000 0.012 0.988 0.000 0.000
#> GSM613741 4 0.5839 0.499495 0.000 0.084 0.084 0.696 0.136
#> GSM613742 5 0.4702 0.642483 0.256 0.000 0.008 0.036 0.700
#> GSM613743 3 0.0771 0.822617 0.000 0.020 0.976 0.000 0.004
#> GSM613744 3 0.0404 0.823777 0.000 0.012 0.988 0.000 0.000
#> GSM613745 4 0.5863 0.501224 0.000 0.088 0.076 0.692 0.144
#> GSM613746 2 0.5873 0.621205 0.000 0.676 0.044 0.172 0.108
#> GSM613747 5 0.4287 0.434209 0.460 0.000 0.000 0.000 0.540
#> GSM613748 4 0.4193 0.409834 0.000 0.304 0.000 0.684 0.012
#> GSM613749 4 0.5490 0.346673 0.324 0.084 0.000 0.592 0.000
#> GSM613750 3 0.3248 0.775454 0.000 0.004 0.856 0.052 0.088
#> GSM613751 3 0.3257 0.775098 0.000 0.008 0.860 0.052 0.080
#> GSM613752 3 0.3197 0.775183 0.000 0.008 0.864 0.052 0.076
#> GSM613753 3 0.4674 0.731025 0.000 0.004 0.748 0.100 0.148
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM613638 4 0.4182 0.4755 0.000 0.016 0.072 0.784 0.116 0.012
#> GSM613639 4 0.5110 0.3693 0.324 0.004 0.000 0.592 0.004 0.076
#> GSM613640 4 0.4038 0.5087 0.000 0.056 0.060 0.804 0.076 0.004
#> GSM613641 1 0.1390 0.8872 0.948 0.000 0.000 0.016 0.004 0.032
#> GSM613642 2 0.4972 0.5040 0.000 0.656 0.024 0.256 0.064 0.000
#> GSM613643 4 0.3858 0.5503 0.164 0.004 0.000 0.776 0.052 0.004
#> GSM613644 4 0.3825 0.5439 0.112 0.004 0.000 0.808 0.028 0.048
#> GSM613645 4 0.5101 0.1259 0.424 0.004 0.000 0.504 0.000 0.068
#> GSM613646 6 0.4646 0.3477 0.000 0.000 0.008 0.356 0.036 0.600
#> GSM613647 4 0.6394 -0.0433 0.000 0.000 0.088 0.420 0.412 0.080
#> GSM613648 3 0.3771 0.7490 0.000 0.012 0.828 0.060 0.040 0.060
#> GSM613649 3 0.3469 0.7811 0.000 0.028 0.852 0.044 0.032 0.044
#> GSM613650 4 0.6064 -0.1796 0.000 0.000 0.008 0.428 0.192 0.372
#> GSM613651 5 0.4678 0.4375 0.000 0.000 0.056 0.184 0.720 0.040
#> GSM613652 5 0.2730 0.7063 0.192 0.000 0.000 0.000 0.808 0.000
#> GSM613653 6 0.4390 0.4521 0.000 0.000 0.004 0.272 0.048 0.676
#> GSM613654 5 0.2730 0.7063 0.192 0.000 0.000 0.000 0.808 0.000
#> GSM613655 1 0.0914 0.8836 0.968 0.000 0.000 0.000 0.016 0.016
#> GSM613656 5 0.2730 0.7063 0.192 0.000 0.000 0.000 0.808 0.000
#> GSM613657 3 0.1563 0.8277 0.000 0.056 0.932 0.000 0.000 0.012
#> GSM613658 1 0.1605 0.8851 0.940 0.000 0.000 0.012 0.016 0.032
#> GSM613659 4 0.5856 -0.0353 0.000 0.192 0.000 0.404 0.000 0.404
#> GSM613660 2 0.3057 0.7316 0.000 0.844 0.024 0.120 0.004 0.008
#> GSM613661 1 0.4731 0.0296 0.488 0.004 0.000 0.476 0.004 0.028
#> GSM613662 2 0.4594 0.2797 0.000 0.504 0.004 0.020 0.004 0.468
#> GSM613663 1 0.1226 0.8788 0.952 0.004 0.000 0.040 0.000 0.004
#> GSM613664 2 0.4161 0.5067 0.000 0.612 0.000 0.008 0.008 0.372
#> GSM613665 2 0.2095 0.7590 0.000 0.916 0.016 0.028 0.000 0.040
#> GSM613666 1 0.1391 0.8862 0.944 0.000 0.000 0.016 0.000 0.040
#> GSM613667 1 0.5120 -0.0645 0.468 0.004 0.000 0.460 0.000 0.068
#> GSM613668 1 0.0603 0.8852 0.980 0.000 0.000 0.000 0.016 0.004
#> GSM613669 1 0.1536 0.8856 0.940 0.000 0.000 0.016 0.004 0.040
#> GSM613670 6 0.4574 -0.2245 0.000 0.440 0.000 0.036 0.000 0.524
#> GSM613671 1 0.1536 0.8856 0.940 0.000 0.000 0.016 0.004 0.040
#> GSM613672 1 0.1109 0.8845 0.964 0.004 0.000 0.016 0.012 0.004
#> GSM613673 1 0.1788 0.8543 0.916 0.004 0.000 0.076 0.000 0.004
#> GSM613674 2 0.2017 0.7469 0.000 0.920 0.020 0.004 0.008 0.048
#> GSM613675 2 0.4724 0.2935 0.000 0.508 0.004 0.028 0.004 0.456
#> GSM613676 2 0.2122 0.7593 0.000 0.916 0.024 0.028 0.000 0.032
#> GSM613677 4 0.5596 0.4618 0.000 0.112 0.060 0.704 0.048 0.076
#> GSM613678 4 0.5850 0.4668 0.076 0.120 0.000 0.628 0.000 0.176
#> GSM613679 2 0.1053 0.7573 0.000 0.964 0.020 0.012 0.000 0.004
#> GSM613680 1 0.0405 0.8884 0.988 0.000 0.000 0.008 0.000 0.004
#> GSM613681 1 0.0622 0.8908 0.980 0.000 0.000 0.012 0.000 0.008
#> GSM613682 1 0.1429 0.8727 0.940 0.004 0.000 0.052 0.000 0.004
#> GSM613683 1 0.0653 0.8857 0.980 0.000 0.000 0.004 0.012 0.004
#> GSM613684 2 0.2605 0.7323 0.000 0.876 0.020 0.000 0.012 0.092
#> GSM613685 2 0.2017 0.7469 0.000 0.920 0.020 0.004 0.008 0.048
#> GSM613686 1 0.3945 0.6823 0.748 0.004 0.000 0.200 0.000 0.048
#> GSM613687 1 0.1429 0.8727 0.940 0.004 0.000 0.052 0.000 0.004
#> GSM613688 2 0.3879 0.6315 0.000 0.724 0.004 0.012 0.008 0.252
#> GSM613689 3 0.4535 0.6582 0.000 0.000 0.748 0.104 0.116 0.032
#> GSM613690 3 0.5361 0.5855 0.000 0.000 0.676 0.144 0.128 0.052
#> GSM613691 6 0.3702 0.4297 0.000 0.164 0.008 0.044 0.000 0.784
#> GSM613692 5 0.2706 0.7038 0.160 0.000 0.000 0.000 0.832 0.008
#> GSM613693 6 0.5984 0.2637 0.000 0.204 0.296 0.000 0.008 0.492
#> GSM613694 5 0.7243 -0.1538 0.000 0.000 0.088 0.312 0.324 0.276
#> GSM613695 3 0.5919 0.4766 0.000 0.000 0.608 0.200 0.132 0.060
#> GSM613696 6 0.7102 0.3654 0.000 0.004 0.168 0.204 0.140 0.484
#> GSM613697 5 0.4451 0.4595 0.000 0.000 0.056 0.164 0.744 0.036
#> GSM613698 5 0.7078 0.0991 0.000 0.000 0.112 0.220 0.452 0.216
#> GSM613699 6 0.7552 0.1997 0.000 0.000 0.296 0.256 0.148 0.300
#> GSM613700 2 0.2636 0.7366 0.000 0.860 0.016 0.120 0.004 0.000
#> GSM613701 4 0.5228 0.0792 0.000 0.424 0.000 0.504 0.016 0.056
#> GSM613702 4 0.4821 0.4799 0.000 0.168 0.000 0.696 0.012 0.124
#> GSM613703 1 0.3103 0.8096 0.836 0.000 0.000 0.100 0.000 0.064
#> GSM613704 2 0.4524 0.2829 0.000 0.492 0.004 0.016 0.004 0.484
#> GSM613705 4 0.4890 0.4030 0.000 0.008 0.100 0.716 0.156 0.020
#> GSM613706 4 0.4135 0.5291 0.008 0.116 0.012 0.788 0.072 0.004
#> GSM613707 2 0.2017 0.7469 0.000 0.920 0.020 0.004 0.008 0.048
#> GSM613708 1 0.2597 0.8277 0.868 0.004 0.000 0.112 0.004 0.012
#> GSM613709 1 0.1390 0.8872 0.948 0.000 0.000 0.016 0.004 0.032
#> GSM613710 2 0.3281 0.7216 0.000 0.832 0.036 0.120 0.004 0.008
#> GSM613711 3 0.1563 0.8277 0.000 0.056 0.932 0.000 0.000 0.012
#> GSM613712 5 0.7304 0.0424 0.000 0.000 0.136 0.252 0.408 0.204
#> GSM613713 3 0.4436 0.6638 0.000 0.220 0.712 0.000 0.016 0.052
#> GSM613714 3 0.5867 0.5252 0.000 0.000 0.624 0.172 0.136 0.068
#> GSM613715 3 0.3811 0.7329 0.000 0.004 0.820 0.068 0.056 0.052
#> GSM613716 6 0.4659 0.5305 0.000 0.008 0.112 0.080 0.044 0.756
#> GSM613717 3 0.1707 0.8271 0.000 0.056 0.928 0.000 0.004 0.012
#> GSM613718 3 0.1493 0.8281 0.000 0.056 0.936 0.000 0.004 0.004
#> GSM613719 6 0.6810 0.2192 0.000 0.000 0.048 0.292 0.256 0.404
#> GSM613720 6 0.5389 0.3295 0.000 0.048 0.324 0.016 0.020 0.592
#> GSM613721 6 0.4879 0.5093 0.000 0.120 0.008 0.116 0.028 0.728
#> GSM613722 2 0.2544 0.7362 0.000 0.864 0.012 0.120 0.004 0.000
#> GSM613723 5 0.2730 0.7063 0.192 0.000 0.000 0.000 0.808 0.000
#> GSM613724 1 0.0603 0.8852 0.980 0.000 0.000 0.000 0.016 0.004
#> GSM613725 2 0.2865 0.7349 0.000 0.852 0.020 0.120 0.004 0.004
#> GSM613726 4 0.4157 0.3619 0.360 0.004 0.000 0.624 0.004 0.008
#> GSM613727 1 0.1168 0.8839 0.956 0.000 0.000 0.000 0.016 0.028
#> GSM613728 2 0.4968 0.6395 0.000 0.668 0.004 0.116 0.004 0.208
#> GSM613729 1 0.1461 0.8854 0.940 0.000 0.000 0.016 0.000 0.044
#> GSM613730 4 0.4662 0.4602 0.000 0.140 0.000 0.688 0.000 0.172
#> GSM613731 4 0.4016 0.5447 0.208 0.004 0.000 0.744 0.040 0.004
#> GSM613732 3 0.1462 0.8280 0.000 0.056 0.936 0.000 0.008 0.000
#> GSM613733 3 0.2785 0.7802 0.000 0.128 0.852 0.008 0.004 0.008
#> GSM613734 5 0.3266 0.6406 0.272 0.000 0.000 0.000 0.728 0.000
#> GSM613735 5 0.2730 0.7063 0.192 0.000 0.000 0.000 0.808 0.000
#> GSM613736 3 0.1707 0.8271 0.000 0.056 0.928 0.000 0.004 0.012
#> GSM613737 5 0.7046 0.0911 0.000 0.000 0.104 0.220 0.452 0.224
#> GSM613738 5 0.2706 0.7038 0.160 0.000 0.000 0.000 0.832 0.008
#> GSM613739 5 0.2558 0.7041 0.156 0.000 0.000 0.000 0.840 0.004
#> GSM613740 3 0.1493 0.8277 0.000 0.056 0.936 0.000 0.004 0.004
#> GSM613741 6 0.4349 0.4559 0.000 0.000 0.004 0.264 0.048 0.684
#> GSM613742 5 0.2704 0.6916 0.140 0.000 0.000 0.000 0.844 0.016
#> GSM613743 3 0.1707 0.8271 0.000 0.056 0.928 0.000 0.004 0.012
#> GSM613744 3 0.1462 0.8280 0.000 0.056 0.936 0.000 0.008 0.000
#> GSM613745 6 0.4391 0.4050 0.000 0.000 0.008 0.320 0.028 0.644
#> GSM613746 6 0.4303 0.1307 0.000 0.316 0.012 0.008 0.008 0.656
#> GSM613747 5 0.3266 0.6406 0.272 0.000 0.000 0.000 0.728 0.000
#> GSM613748 4 0.4283 0.5245 0.000 0.148 0.008 0.768 0.024 0.052
#> GSM613749 4 0.5581 0.4796 0.244 0.032 0.000 0.612 0.000 0.112
#> GSM613750 3 0.3788 0.7535 0.000 0.016 0.824 0.056 0.024 0.080
#> GSM613751 3 0.4095 0.7554 0.000 0.036 0.808 0.056 0.020 0.080
#> GSM613752 3 0.4095 0.7554 0.000 0.036 0.808 0.056 0.020 0.080
#> GSM613753 3 0.4495 0.7142 0.000 0.000 0.764 0.076 0.076 0.084
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n disease.state(p) k
#> MAD:kmeans 114 0.056452 2
#> MAD:kmeans 111 0.032102 3
#> MAD:kmeans 92 0.001352 4
#> MAD:kmeans 78 0.000451 5
#> MAD:kmeans 78 0.000152 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 27425 rows and 116 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 1.000 0.976 0.990 0.5043 0.496 0.496
#> 3 3 0.754 0.855 0.920 0.3066 0.728 0.505
#> 4 4 0.749 0.851 0.894 0.1309 0.845 0.578
#> 5 5 0.777 0.750 0.871 0.0565 0.917 0.694
#> 6 6 0.886 0.801 0.892 0.0370 0.931 0.703
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
#> GSM613638 2 0.9815 0.289 0.420 0.580
#> GSM613639 1 0.0000 0.992 1.000 0.000
#> GSM613640 2 0.1843 0.964 0.028 0.972
#> GSM613641 1 0.0000 0.992 1.000 0.000
#> GSM613642 2 0.0000 0.987 0.000 1.000
#> GSM613643 1 0.0000 0.992 1.000 0.000
#> GSM613644 1 0.0000 0.992 1.000 0.000
#> GSM613645 1 0.0000 0.992 1.000 0.000
#> GSM613646 1 0.2043 0.965 0.968 0.032
#> GSM613647 1 0.0000 0.992 1.000 0.000
#> GSM613648 2 0.0000 0.987 0.000 1.000
#> GSM613649 2 0.0000 0.987 0.000 1.000
#> GSM613650 1 0.0000 0.992 1.000 0.000
#> GSM613651 1 0.0000 0.992 1.000 0.000
#> GSM613652 1 0.0000 0.992 1.000 0.000
#> GSM613653 1 0.1633 0.972 0.976 0.024
#> GSM613654 1 0.0000 0.992 1.000 0.000
#> GSM613655 1 0.0000 0.992 1.000 0.000
#> GSM613656 1 0.0000 0.992 1.000 0.000
#> GSM613657 2 0.0000 0.987 0.000 1.000
#> GSM613658 1 0.0000 0.992 1.000 0.000
#> GSM613659 2 0.0000 0.987 0.000 1.000
#> GSM613660 2 0.0000 0.987 0.000 1.000
#> GSM613661 1 0.0000 0.992 1.000 0.000
#> GSM613662 2 0.0000 0.987 0.000 1.000
#> GSM613663 1 0.0000 0.992 1.000 0.000
#> GSM613664 2 0.0000 0.987 0.000 1.000
#> GSM613665 2 0.0000 0.987 0.000 1.000
#> GSM613666 1 0.0000 0.992 1.000 0.000
#> GSM613667 1 0.0000 0.992 1.000 0.000
#> GSM613668 1 0.0000 0.992 1.000 0.000
#> GSM613669 1 0.0000 0.992 1.000 0.000
#> GSM613670 2 0.1843 0.962 0.028 0.972
#> GSM613671 1 0.0000 0.992 1.000 0.000
#> GSM613672 1 0.0000 0.992 1.000 0.000
#> GSM613673 1 0.0000 0.992 1.000 0.000
#> GSM613674 2 0.0000 0.987 0.000 1.000
#> GSM613675 2 0.0000 0.987 0.000 1.000
#> GSM613676 2 0.0000 0.987 0.000 1.000
#> GSM613677 2 0.0000 0.987 0.000 1.000
#> GSM613678 1 0.0000 0.992 1.000 0.000
#> GSM613679 2 0.0000 0.987 0.000 1.000
#> GSM613680 1 0.0000 0.992 1.000 0.000
#> GSM613681 1 0.0000 0.992 1.000 0.000
#> GSM613682 1 0.0000 0.992 1.000 0.000
#> GSM613683 1 0.0000 0.992 1.000 0.000
#> GSM613684 2 0.0000 0.987 0.000 1.000
#> GSM613685 2 0.0000 0.987 0.000 1.000
#> GSM613686 1 0.0000 0.992 1.000 0.000
#> GSM613687 1 0.0000 0.992 1.000 0.000
#> GSM613688 2 0.0000 0.987 0.000 1.000
#> GSM613689 2 0.0000 0.987 0.000 1.000
#> GSM613690 2 0.0000 0.987 0.000 1.000
#> GSM613691 2 0.0000 0.987 0.000 1.000
#> GSM613692 1 0.0000 0.992 1.000 0.000
#> GSM613693 2 0.0000 0.987 0.000 1.000
#> GSM613694 1 0.0376 0.989 0.996 0.004
#> GSM613695 2 0.0000 0.987 0.000 1.000
#> GSM613696 2 0.0000 0.987 0.000 1.000
#> GSM613697 1 0.0000 0.992 1.000 0.000
#> GSM613698 1 0.4161 0.911 0.916 0.084
#> GSM613699 2 0.0000 0.987 0.000 1.000
#> GSM613700 2 0.0000 0.987 0.000 1.000
#> GSM613701 2 0.0000 0.987 0.000 1.000
#> GSM613702 2 0.1414 0.970 0.020 0.980
#> GSM613703 1 0.0000 0.992 1.000 0.000
#> GSM613704 2 0.0000 0.987 0.000 1.000
#> GSM613705 2 0.1843 0.964 0.028 0.972
#> GSM613706 1 0.0000 0.992 1.000 0.000
#> GSM613707 2 0.0000 0.987 0.000 1.000
#> GSM613708 1 0.0000 0.992 1.000 0.000
#> GSM613709 1 0.0000 0.992 1.000 0.000
#> GSM613710 2 0.0000 0.987 0.000 1.000
#> GSM613711 2 0.0000 0.987 0.000 1.000
#> GSM613712 2 0.7376 0.735 0.208 0.792
#> GSM613713 2 0.0000 0.987 0.000 1.000
#> GSM613714 2 0.0000 0.987 0.000 1.000
#> GSM613715 2 0.0000 0.987 0.000 1.000
#> GSM613716 2 0.0000 0.987 0.000 1.000
#> GSM613717 2 0.0000 0.987 0.000 1.000
#> GSM613718 2 0.0000 0.987 0.000 1.000
#> GSM613719 1 0.1414 0.976 0.980 0.020
#> GSM613720 2 0.0000 0.987 0.000 1.000
#> GSM613721 2 0.0000 0.987 0.000 1.000
#> GSM613722 2 0.0000 0.987 0.000 1.000
#> GSM613723 1 0.0000 0.992 1.000 0.000
#> GSM613724 1 0.0000 0.992 1.000 0.000
#> GSM613725 2 0.0000 0.987 0.000 1.000
#> GSM613726 1 0.0000 0.992 1.000 0.000
#> GSM613727 1 0.0000 0.992 1.000 0.000
#> GSM613728 2 0.0000 0.987 0.000 1.000
#> GSM613729 1 0.0000 0.992 1.000 0.000
#> GSM613730 2 0.0000 0.987 0.000 1.000
#> GSM613731 1 0.0000 0.992 1.000 0.000
#> GSM613732 2 0.0000 0.987 0.000 1.000
#> GSM613733 2 0.0000 0.987 0.000 1.000
#> GSM613734 1 0.0000 0.992 1.000 0.000
#> GSM613735 1 0.0000 0.992 1.000 0.000
#> GSM613736 2 0.0000 0.987 0.000 1.000
#> GSM613737 1 0.2043 0.965 0.968 0.032
#> GSM613738 1 0.0000 0.992 1.000 0.000
#> GSM613739 1 0.0000 0.992 1.000 0.000
#> GSM613740 2 0.0000 0.987 0.000 1.000
#> GSM613741 1 0.1633 0.972 0.976 0.024
#> GSM613742 1 0.0000 0.992 1.000 0.000
#> GSM613743 2 0.0000 0.987 0.000 1.000
#> GSM613744 2 0.0000 0.987 0.000 1.000
#> GSM613745 1 0.7883 0.695 0.764 0.236
#> GSM613746 2 0.0000 0.987 0.000 1.000
#> GSM613747 1 0.0000 0.992 1.000 0.000
#> GSM613748 2 0.1414 0.970 0.020 0.980
#> GSM613749 1 0.0000 0.992 1.000 0.000
#> GSM613750 2 0.0000 0.987 0.000 1.000
#> GSM613751 2 0.0000 0.987 0.000 1.000
#> GSM613752 2 0.0000 0.987 0.000 1.000
#> GSM613753 2 0.0000 0.987 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM613638 3 0.4351 0.75387 0.168 0.004 0.828
#> GSM613639 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613640 2 0.6824 0.46004 0.016 0.576 0.408
#> GSM613641 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613642 2 0.2537 0.89463 0.000 0.920 0.080
#> GSM613643 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613644 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613645 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613646 3 0.8547 0.33985 0.364 0.104 0.532
#> GSM613647 3 0.1289 0.85783 0.032 0.000 0.968
#> GSM613648 3 0.3192 0.88102 0.000 0.112 0.888
#> GSM613649 3 0.3192 0.88102 0.000 0.112 0.888
#> GSM613650 1 0.6026 0.34686 0.624 0.000 0.376
#> GSM613651 3 0.3116 0.81127 0.108 0.000 0.892
#> GSM613652 1 0.0592 0.95731 0.988 0.000 0.012
#> GSM613653 1 0.8391 0.00846 0.484 0.084 0.432
#> GSM613654 1 0.0592 0.95731 0.988 0.000 0.012
#> GSM613655 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613656 1 0.0592 0.95731 0.988 0.000 0.012
#> GSM613657 3 0.3192 0.88102 0.000 0.112 0.888
#> GSM613658 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613659 2 0.0000 0.88644 0.000 1.000 0.000
#> GSM613660 2 0.2448 0.89715 0.000 0.924 0.076
#> GSM613661 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613662 2 0.0000 0.88644 0.000 1.000 0.000
#> GSM613663 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613664 2 0.0000 0.88644 0.000 1.000 0.000
#> GSM613665 2 0.2356 0.89840 0.000 0.928 0.072
#> GSM613666 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613667 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613668 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613669 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613670 2 0.0000 0.88644 0.000 1.000 0.000
#> GSM613671 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613672 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613673 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613674 2 0.2356 0.89840 0.000 0.928 0.072
#> GSM613675 2 0.0000 0.88644 0.000 1.000 0.000
#> GSM613676 2 0.2448 0.89715 0.000 0.924 0.076
#> GSM613677 2 0.3038 0.87581 0.000 0.896 0.104
#> GSM613678 2 0.3192 0.78395 0.112 0.888 0.000
#> GSM613679 2 0.2356 0.89840 0.000 0.928 0.072
#> GSM613680 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613681 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613682 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613683 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613684 2 0.2356 0.89840 0.000 0.928 0.072
#> GSM613685 2 0.2356 0.89840 0.000 0.928 0.072
#> GSM613686 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613687 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613688 2 0.2165 0.89860 0.000 0.936 0.064
#> GSM613689 3 0.0747 0.87228 0.000 0.016 0.984
#> GSM613690 3 0.0747 0.87228 0.000 0.016 0.984
#> GSM613691 2 0.0424 0.88476 0.000 0.992 0.008
#> GSM613692 1 0.0592 0.95731 0.988 0.000 0.012
#> GSM613693 3 0.5859 0.54993 0.000 0.344 0.656
#> GSM613694 3 0.2796 0.82285 0.092 0.000 0.908
#> GSM613695 3 0.0000 0.86828 0.000 0.000 1.000
#> GSM613696 3 0.2711 0.88194 0.000 0.088 0.912
#> GSM613697 3 0.3038 0.81444 0.104 0.000 0.896
#> GSM613698 3 0.2636 0.84556 0.020 0.048 0.932
#> GSM613699 3 0.0000 0.86828 0.000 0.000 1.000
#> GSM613700 2 0.2448 0.89715 0.000 0.924 0.076
#> GSM613701 2 0.1964 0.89804 0.000 0.944 0.056
#> GSM613702 2 0.0424 0.88914 0.000 0.992 0.008
#> GSM613703 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613704 2 0.0000 0.88644 0.000 1.000 0.000
#> GSM613705 3 0.0000 0.86828 0.000 0.000 1.000
#> GSM613706 2 0.8362 0.37954 0.348 0.556 0.096
#> GSM613707 2 0.2356 0.89840 0.000 0.928 0.072
#> GSM613708 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613709 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613710 2 0.2448 0.89715 0.000 0.924 0.076
#> GSM613711 3 0.3192 0.88102 0.000 0.112 0.888
#> GSM613712 3 0.2537 0.83086 0.080 0.000 0.920
#> GSM613713 3 0.3412 0.87261 0.000 0.124 0.876
#> GSM613714 3 0.0592 0.87138 0.000 0.012 0.988
#> GSM613715 3 0.3192 0.88102 0.000 0.112 0.888
#> GSM613716 3 0.4555 0.84001 0.000 0.200 0.800
#> GSM613717 3 0.3192 0.88102 0.000 0.112 0.888
#> GSM613718 3 0.3192 0.88102 0.000 0.112 0.888
#> GSM613719 3 0.5901 0.73927 0.192 0.040 0.768
#> GSM613720 3 0.4452 0.84502 0.000 0.192 0.808
#> GSM613721 2 0.6026 0.17590 0.000 0.624 0.376
#> GSM613722 2 0.2448 0.89715 0.000 0.924 0.076
#> GSM613723 1 0.0592 0.95731 0.988 0.000 0.012
#> GSM613724 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613725 2 0.2448 0.89715 0.000 0.924 0.076
#> GSM613726 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613727 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613728 2 0.0424 0.88914 0.000 0.992 0.008
#> GSM613729 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613730 2 0.0000 0.88644 0.000 1.000 0.000
#> GSM613731 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613732 3 0.3192 0.88102 0.000 0.112 0.888
#> GSM613733 3 0.3192 0.88102 0.000 0.112 0.888
#> GSM613734 1 0.0000 0.96305 1.000 0.000 0.000
#> GSM613735 1 0.0592 0.95731 0.988 0.000 0.012
#> GSM613736 3 0.3192 0.88102 0.000 0.112 0.888
#> GSM613737 3 0.2165 0.83997 0.064 0.000 0.936
#> GSM613738 1 0.0592 0.95731 0.988 0.000 0.012
#> GSM613739 1 0.0592 0.95731 0.988 0.000 0.012
#> GSM613740 3 0.3192 0.88102 0.000 0.112 0.888
#> GSM613741 1 0.8382 0.03912 0.492 0.084 0.424
#> GSM613742 1 0.0592 0.95731 0.988 0.000 0.012
#> GSM613743 3 0.3192 0.88102 0.000 0.112 0.888
#> GSM613744 3 0.3192 0.88102 0.000 0.112 0.888
#> GSM613745 3 0.8765 0.58453 0.168 0.252 0.580
#> GSM613746 2 0.4291 0.68834 0.000 0.820 0.180
#> GSM613747 1 0.0237 0.96122 0.996 0.000 0.004
#> GSM613748 2 0.1753 0.89716 0.000 0.952 0.048
#> GSM613749 2 0.6111 0.35503 0.396 0.604 0.000
#> GSM613750 3 0.1289 0.87593 0.000 0.032 0.968
#> GSM613751 3 0.3192 0.88102 0.000 0.112 0.888
#> GSM613752 3 0.3192 0.88102 0.000 0.112 0.888
#> GSM613753 3 0.0000 0.86828 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 3 0.6605 0.3934 0.068 0.008 0.556 0.368
#> GSM613639 1 0.0000 0.9875 1.000 0.000 0.000 0.000
#> GSM613640 3 0.9464 0.1208 0.336 0.204 0.340 0.120
#> GSM613641 1 0.0000 0.9875 1.000 0.000 0.000 0.000
#> GSM613642 2 0.3444 0.8524 0.000 0.816 0.184 0.000
#> GSM613643 1 0.0188 0.9866 0.996 0.000 0.000 0.004
#> GSM613644 1 0.0672 0.9795 0.984 0.008 0.000 0.008
#> GSM613645 1 0.0336 0.9813 0.992 0.008 0.000 0.000
#> GSM613646 4 0.7240 0.5965 0.032 0.184 0.156 0.628
#> GSM613647 4 0.1792 0.7993 0.000 0.000 0.068 0.932
#> GSM613648 3 0.0000 0.9064 0.000 0.000 1.000 0.000
#> GSM613649 3 0.0000 0.9064 0.000 0.000 1.000 0.000
#> GSM613650 4 0.3266 0.8462 0.168 0.000 0.000 0.832
#> GSM613651 4 0.2111 0.8165 0.024 0.000 0.044 0.932
#> GSM613652 4 0.3486 0.8465 0.188 0.000 0.000 0.812
#> GSM613653 4 0.5545 0.6999 0.008 0.180 0.076 0.736
#> GSM613654 4 0.3486 0.8465 0.188 0.000 0.000 0.812
#> GSM613655 1 0.0188 0.9866 0.996 0.000 0.000 0.004
#> GSM613656 4 0.3486 0.8465 0.188 0.000 0.000 0.812
#> GSM613657 3 0.0000 0.9064 0.000 0.000 1.000 0.000
#> GSM613658 1 0.0188 0.9866 0.996 0.000 0.000 0.004
#> GSM613659 2 0.1118 0.8144 0.000 0.964 0.000 0.036
#> GSM613660 2 0.3400 0.8551 0.000 0.820 0.180 0.000
#> GSM613661 1 0.0000 0.9875 1.000 0.000 0.000 0.000
#> GSM613662 2 0.1452 0.8194 0.000 0.956 0.008 0.036
#> GSM613663 1 0.0000 0.9875 1.000 0.000 0.000 0.000
#> GSM613664 2 0.1256 0.8225 0.000 0.964 0.008 0.028
#> GSM613665 2 0.3400 0.8551 0.000 0.820 0.180 0.000
#> GSM613666 1 0.0000 0.9875 1.000 0.000 0.000 0.000
#> GSM613667 1 0.0336 0.9813 0.992 0.008 0.000 0.000
#> GSM613668 1 0.0188 0.9866 0.996 0.000 0.000 0.004
#> GSM613669 1 0.0000 0.9875 1.000 0.000 0.000 0.000
#> GSM613670 2 0.1118 0.8144 0.000 0.964 0.000 0.036
#> GSM613671 1 0.0000 0.9875 1.000 0.000 0.000 0.000
#> GSM613672 1 0.0188 0.9866 0.996 0.000 0.000 0.004
#> GSM613673 1 0.0188 0.9866 0.996 0.000 0.000 0.004
#> GSM613674 2 0.3400 0.8551 0.000 0.820 0.180 0.000
#> GSM613675 2 0.1584 0.8218 0.000 0.952 0.012 0.036
#> GSM613676 2 0.3400 0.8551 0.000 0.820 0.180 0.000
#> GSM613677 2 0.4907 0.4830 0.000 0.580 0.420 0.000
#> GSM613678 2 0.5928 0.0104 0.456 0.508 0.000 0.036
#> GSM613679 2 0.3400 0.8551 0.000 0.820 0.180 0.000
#> GSM613680 1 0.0188 0.9866 0.996 0.000 0.000 0.004
#> GSM613681 1 0.0000 0.9875 1.000 0.000 0.000 0.000
#> GSM613682 1 0.0000 0.9875 1.000 0.000 0.000 0.000
#> GSM613683 1 0.0188 0.9866 0.996 0.000 0.000 0.004
#> GSM613684 2 0.3400 0.8551 0.000 0.820 0.180 0.000
#> GSM613685 2 0.3400 0.8551 0.000 0.820 0.180 0.000
#> GSM613686 1 0.0000 0.9875 1.000 0.000 0.000 0.000
#> GSM613687 1 0.0000 0.9875 1.000 0.000 0.000 0.000
#> GSM613688 2 0.3266 0.8559 0.000 0.832 0.168 0.000
#> GSM613689 3 0.1637 0.8816 0.000 0.000 0.940 0.060
#> GSM613690 3 0.1211 0.8921 0.000 0.000 0.960 0.040
#> GSM613691 2 0.4227 0.7387 0.000 0.820 0.120 0.060
#> GSM613692 4 0.3486 0.8465 0.188 0.000 0.000 0.812
#> GSM613693 3 0.1510 0.8809 0.000 0.016 0.956 0.028
#> GSM613694 4 0.1975 0.8120 0.016 0.000 0.048 0.936
#> GSM613695 3 0.2704 0.8380 0.000 0.000 0.876 0.124
#> GSM613696 3 0.2224 0.8722 0.000 0.032 0.928 0.040
#> GSM613697 4 0.2111 0.8165 0.024 0.000 0.044 0.932
#> GSM613698 4 0.1474 0.8036 0.000 0.000 0.052 0.948
#> GSM613699 3 0.3486 0.7723 0.000 0.000 0.812 0.188
#> GSM613700 2 0.3400 0.8551 0.000 0.820 0.180 0.000
#> GSM613701 2 0.3542 0.8504 0.028 0.852 0.120 0.000
#> GSM613702 2 0.0336 0.8287 0.000 0.992 0.008 0.000
#> GSM613703 1 0.0000 0.9875 1.000 0.000 0.000 0.000
#> GSM613704 2 0.1584 0.8218 0.000 0.952 0.012 0.036
#> GSM613705 3 0.5007 0.5233 0.000 0.008 0.636 0.356
#> GSM613706 1 0.5396 0.6823 0.740 0.104 0.000 0.156
#> GSM613707 2 0.3400 0.8551 0.000 0.820 0.180 0.000
#> GSM613708 1 0.0188 0.9866 0.996 0.000 0.000 0.004
#> GSM613709 1 0.0000 0.9875 1.000 0.000 0.000 0.000
#> GSM613710 2 0.3444 0.8524 0.000 0.816 0.184 0.000
#> GSM613711 3 0.0000 0.9064 0.000 0.000 1.000 0.000
#> GSM613712 4 0.3249 0.7343 0.008 0.000 0.140 0.852
#> GSM613713 3 0.0469 0.8996 0.000 0.012 0.988 0.000
#> GSM613714 3 0.2647 0.8403 0.000 0.000 0.880 0.120
#> GSM613715 3 0.0000 0.9064 0.000 0.000 1.000 0.000
#> GSM613716 3 0.4937 0.7110 0.000 0.172 0.764 0.064
#> GSM613717 3 0.0000 0.9064 0.000 0.000 1.000 0.000
#> GSM613718 3 0.0000 0.9064 0.000 0.000 1.000 0.000
#> GSM613719 4 0.2731 0.8205 0.032 0.048 0.008 0.912
#> GSM613720 3 0.2578 0.8555 0.000 0.036 0.912 0.052
#> GSM613721 2 0.5007 0.6715 0.000 0.760 0.172 0.068
#> GSM613722 2 0.3400 0.8551 0.000 0.820 0.180 0.000
#> GSM613723 4 0.3486 0.8465 0.188 0.000 0.000 0.812
#> GSM613724 1 0.0188 0.9866 0.996 0.000 0.000 0.004
#> GSM613725 2 0.3400 0.8551 0.000 0.820 0.180 0.000
#> GSM613726 1 0.0000 0.9875 1.000 0.000 0.000 0.000
#> GSM613727 1 0.0000 0.9875 1.000 0.000 0.000 0.000
#> GSM613728 2 0.1767 0.8404 0.000 0.944 0.044 0.012
#> GSM613729 1 0.0000 0.9875 1.000 0.000 0.000 0.000
#> GSM613730 2 0.0707 0.8203 0.000 0.980 0.000 0.020
#> GSM613731 1 0.0188 0.9866 0.996 0.000 0.000 0.004
#> GSM613732 3 0.0000 0.9064 0.000 0.000 1.000 0.000
#> GSM613733 3 0.0469 0.8988 0.000 0.012 0.988 0.000
#> GSM613734 4 0.4477 0.6948 0.312 0.000 0.000 0.688
#> GSM613735 4 0.3486 0.8465 0.188 0.000 0.000 0.812
#> GSM613736 3 0.0000 0.9064 0.000 0.000 1.000 0.000
#> GSM613737 4 0.1716 0.7995 0.000 0.000 0.064 0.936
#> GSM613738 4 0.3486 0.8465 0.188 0.000 0.000 0.812
#> GSM613739 4 0.3486 0.8465 0.188 0.000 0.000 0.812
#> GSM613740 3 0.0000 0.9064 0.000 0.000 1.000 0.000
#> GSM613741 4 0.5479 0.7027 0.008 0.180 0.072 0.740
#> GSM613742 4 0.3486 0.8465 0.188 0.000 0.000 0.812
#> GSM613743 3 0.0000 0.9064 0.000 0.000 1.000 0.000
#> GSM613744 3 0.0000 0.9064 0.000 0.000 1.000 0.000
#> GSM613745 4 0.6774 0.5913 0.008 0.196 0.160 0.636
#> GSM613746 2 0.4638 0.7092 0.000 0.788 0.152 0.060
#> GSM613747 4 0.3649 0.8327 0.204 0.000 0.000 0.796
#> GSM613748 2 0.1557 0.8455 0.000 0.944 0.056 0.000
#> GSM613749 1 0.1004 0.9604 0.972 0.024 0.000 0.004
#> GSM613750 3 0.0188 0.9053 0.000 0.000 0.996 0.004
#> GSM613751 3 0.0000 0.9064 0.000 0.000 1.000 0.000
#> GSM613752 3 0.0000 0.9064 0.000 0.000 1.000 0.000
#> GSM613753 3 0.2647 0.8403 0.000 0.000 0.880 0.120
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM613638 5 0.7875 0.2411 0.000 0.168 0.268 0.120 0.444
#> GSM613639 1 0.0609 0.9433 0.980 0.000 0.000 0.020 0.000
#> GSM613640 2 0.7375 0.4240 0.036 0.604 0.128 0.120 0.112
#> GSM613641 1 0.0000 0.9544 1.000 0.000 0.000 0.000 0.000
#> GSM613642 2 0.3275 0.7572 0.000 0.860 0.064 0.068 0.008
#> GSM613643 1 0.4088 0.7914 0.812 0.040 0.000 0.116 0.032
#> GSM613644 1 0.4758 0.7526 0.772 0.056 0.000 0.124 0.048
#> GSM613645 1 0.0865 0.9380 0.972 0.004 0.000 0.024 0.000
#> GSM613646 4 0.2548 0.6879 0.000 0.004 0.004 0.876 0.116
#> GSM613647 5 0.2436 0.7423 0.000 0.020 0.036 0.032 0.912
#> GSM613648 3 0.0000 0.9270 0.000 0.000 1.000 0.000 0.000
#> GSM613649 3 0.0162 0.9284 0.000 0.004 0.996 0.000 0.000
#> GSM613650 5 0.5659 0.5357 0.100 0.000 0.000 0.320 0.580
#> GSM613651 5 0.0404 0.7774 0.012 0.000 0.000 0.000 0.988
#> GSM613652 5 0.2732 0.8211 0.160 0.000 0.000 0.000 0.840
#> GSM613653 4 0.2377 0.6784 0.000 0.000 0.000 0.872 0.128
#> GSM613654 5 0.2732 0.8211 0.160 0.000 0.000 0.000 0.840
#> GSM613655 1 0.0000 0.9544 1.000 0.000 0.000 0.000 0.000
#> GSM613656 5 0.2732 0.8211 0.160 0.000 0.000 0.000 0.840
#> GSM613657 3 0.0162 0.9284 0.000 0.004 0.996 0.000 0.000
#> GSM613658 1 0.0000 0.9544 1.000 0.000 0.000 0.000 0.000
#> GSM613659 4 0.4307 -0.0110 0.000 0.496 0.000 0.504 0.000
#> GSM613660 2 0.1671 0.7864 0.000 0.924 0.076 0.000 0.000
#> GSM613661 1 0.0000 0.9544 1.000 0.000 0.000 0.000 0.000
#> GSM613662 2 0.4446 -0.0127 0.000 0.520 0.004 0.476 0.000
#> GSM613663 1 0.0000 0.9544 1.000 0.000 0.000 0.000 0.000
#> GSM613664 2 0.4367 0.1651 0.000 0.580 0.004 0.416 0.000
#> GSM613665 2 0.2172 0.7870 0.000 0.908 0.076 0.016 0.000
#> GSM613666 1 0.0000 0.9544 1.000 0.000 0.000 0.000 0.000
#> GSM613667 1 0.0865 0.9380 0.972 0.004 0.000 0.024 0.000
#> GSM613668 1 0.0000 0.9544 1.000 0.000 0.000 0.000 0.000
#> GSM613669 1 0.0000 0.9544 1.000 0.000 0.000 0.000 0.000
#> GSM613670 4 0.4300 0.0576 0.000 0.476 0.000 0.524 0.000
#> GSM613671 1 0.0000 0.9544 1.000 0.000 0.000 0.000 0.000
#> GSM613672 1 0.0000 0.9544 1.000 0.000 0.000 0.000 0.000
#> GSM613673 1 0.0000 0.9544 1.000 0.000 0.000 0.000 0.000
#> GSM613674 2 0.2409 0.7840 0.000 0.900 0.068 0.032 0.000
#> GSM613675 2 0.4425 0.0732 0.000 0.544 0.004 0.452 0.000
#> GSM613676 2 0.2069 0.7874 0.000 0.912 0.076 0.012 0.000
#> GSM613677 2 0.5615 0.4619 0.000 0.584 0.320 0.096 0.000
#> GSM613678 1 0.6750 -0.1644 0.408 0.300 0.000 0.292 0.000
#> GSM613679 2 0.2046 0.7874 0.000 0.916 0.068 0.016 0.000
#> GSM613680 1 0.0000 0.9544 1.000 0.000 0.000 0.000 0.000
#> GSM613681 1 0.0000 0.9544 1.000 0.000 0.000 0.000 0.000
#> GSM613682 1 0.0000 0.9544 1.000 0.000 0.000 0.000 0.000
#> GSM613683 1 0.0000 0.9544 1.000 0.000 0.000 0.000 0.000
#> GSM613684 2 0.2903 0.7710 0.000 0.872 0.080 0.048 0.000
#> GSM613685 2 0.2409 0.7840 0.000 0.900 0.068 0.032 0.000
#> GSM613686 1 0.0510 0.9457 0.984 0.000 0.000 0.016 0.000
#> GSM613687 1 0.0000 0.9544 1.000 0.000 0.000 0.000 0.000
#> GSM613688 2 0.2580 0.7781 0.000 0.892 0.064 0.044 0.000
#> GSM613689 3 0.1571 0.8903 0.000 0.004 0.936 0.000 0.060
#> GSM613690 3 0.0703 0.9125 0.000 0.000 0.976 0.000 0.024
#> GSM613691 4 0.3318 0.6570 0.000 0.180 0.012 0.808 0.000
#> GSM613692 5 0.2690 0.8214 0.156 0.000 0.000 0.000 0.844
#> GSM613693 3 0.5037 0.3367 0.000 0.048 0.616 0.336 0.000
#> GSM613694 5 0.2569 0.7325 0.000 0.000 0.040 0.068 0.892
#> GSM613695 3 0.2445 0.8456 0.000 0.004 0.884 0.004 0.108
#> GSM613696 3 0.5367 0.0720 0.000 0.008 0.488 0.468 0.036
#> GSM613697 5 0.0404 0.7774 0.012 0.000 0.000 0.000 0.988
#> GSM613698 5 0.1740 0.7638 0.000 0.000 0.012 0.056 0.932
#> GSM613699 3 0.4686 0.6957 0.000 0.000 0.736 0.104 0.160
#> GSM613700 2 0.1544 0.7877 0.000 0.932 0.068 0.000 0.000
#> GSM613701 2 0.0451 0.7607 0.000 0.988 0.004 0.000 0.008
#> GSM613702 2 0.1608 0.7456 0.000 0.928 0.000 0.072 0.000
#> GSM613703 1 0.0609 0.9433 0.980 0.000 0.000 0.020 0.000
#> GSM613704 2 0.4446 -0.0127 0.000 0.520 0.004 0.476 0.000
#> GSM613705 5 0.7132 0.3290 0.000 0.080 0.272 0.120 0.528
#> GSM613706 2 0.7489 0.2748 0.236 0.512 0.000 0.120 0.132
#> GSM613707 2 0.2409 0.7840 0.000 0.900 0.068 0.032 0.000
#> GSM613708 1 0.0000 0.9544 1.000 0.000 0.000 0.000 0.000
#> GSM613709 1 0.0000 0.9544 1.000 0.000 0.000 0.000 0.000
#> GSM613710 2 0.2974 0.7662 0.000 0.868 0.080 0.052 0.000
#> GSM613711 3 0.0162 0.9284 0.000 0.004 0.996 0.000 0.000
#> GSM613712 5 0.0671 0.7681 0.000 0.000 0.016 0.004 0.980
#> GSM613713 3 0.1041 0.9036 0.000 0.032 0.964 0.004 0.000
#> GSM613714 3 0.2068 0.8629 0.000 0.000 0.904 0.004 0.092
#> GSM613715 3 0.0000 0.9270 0.000 0.000 1.000 0.000 0.000
#> GSM613716 4 0.4127 0.4735 0.000 0.008 0.312 0.680 0.000
#> GSM613717 3 0.0162 0.9284 0.000 0.004 0.996 0.000 0.000
#> GSM613718 3 0.0162 0.9284 0.000 0.004 0.996 0.000 0.000
#> GSM613719 5 0.4425 0.2721 0.004 0.000 0.000 0.452 0.544
#> GSM613720 4 0.4738 0.1019 0.000 0.016 0.464 0.520 0.000
#> GSM613721 4 0.2843 0.6783 0.000 0.144 0.008 0.848 0.000
#> GSM613722 2 0.1544 0.7877 0.000 0.932 0.068 0.000 0.000
#> GSM613723 5 0.2732 0.8211 0.160 0.000 0.000 0.000 0.840
#> GSM613724 1 0.0000 0.9544 1.000 0.000 0.000 0.000 0.000
#> GSM613725 2 0.1544 0.7877 0.000 0.932 0.068 0.000 0.000
#> GSM613726 1 0.0324 0.9500 0.992 0.004 0.000 0.000 0.004
#> GSM613727 1 0.0000 0.9544 1.000 0.000 0.000 0.000 0.000
#> GSM613728 2 0.2351 0.7449 0.000 0.896 0.016 0.088 0.000
#> GSM613729 1 0.0000 0.9544 1.000 0.000 0.000 0.000 0.000
#> GSM613730 2 0.3336 0.6693 0.000 0.772 0.000 0.228 0.000
#> GSM613731 1 0.3830 0.8033 0.824 0.040 0.000 0.116 0.020
#> GSM613732 3 0.0162 0.9284 0.000 0.004 0.996 0.000 0.000
#> GSM613733 3 0.0162 0.9284 0.000 0.004 0.996 0.000 0.000
#> GSM613734 5 0.3003 0.7980 0.188 0.000 0.000 0.000 0.812
#> GSM613735 5 0.2732 0.8211 0.160 0.000 0.000 0.000 0.840
#> GSM613736 3 0.0162 0.9284 0.000 0.004 0.996 0.000 0.000
#> GSM613737 5 0.1386 0.7643 0.000 0.000 0.032 0.016 0.952
#> GSM613738 5 0.2732 0.8211 0.160 0.000 0.000 0.000 0.840
#> GSM613739 5 0.2690 0.8214 0.156 0.000 0.000 0.000 0.844
#> GSM613740 3 0.0162 0.9284 0.000 0.004 0.996 0.000 0.000
#> GSM613741 4 0.2329 0.6829 0.000 0.000 0.000 0.876 0.124
#> GSM613742 5 0.2690 0.8212 0.156 0.000 0.000 0.000 0.844
#> GSM613743 3 0.0162 0.9284 0.000 0.004 0.996 0.000 0.000
#> GSM613744 3 0.0162 0.9284 0.000 0.004 0.996 0.000 0.000
#> GSM613745 4 0.2733 0.6931 0.000 0.012 0.004 0.872 0.112
#> GSM613746 4 0.3476 0.6598 0.000 0.176 0.020 0.804 0.000
#> GSM613747 5 0.2813 0.8150 0.168 0.000 0.000 0.000 0.832
#> GSM613748 2 0.2660 0.6845 0.000 0.864 0.000 0.128 0.008
#> GSM613749 1 0.1493 0.9213 0.948 0.024 0.000 0.028 0.000
#> GSM613750 3 0.0000 0.9270 0.000 0.000 1.000 0.000 0.000
#> GSM613751 3 0.0162 0.9284 0.000 0.004 0.996 0.000 0.000
#> GSM613752 3 0.0162 0.9284 0.000 0.004 0.996 0.000 0.000
#> GSM613753 3 0.1544 0.8811 0.000 0.000 0.932 0.000 0.068
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM613638 4 0.2231 0.7109 0.004 0.000 0.028 0.900 0.068 0.000
#> GSM613639 1 0.0951 0.9648 0.968 0.000 0.000 0.008 0.004 0.020
#> GSM613640 4 0.1334 0.7250 0.000 0.032 0.000 0.948 0.020 0.000
#> GSM613641 1 0.0000 0.9856 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613642 2 0.3990 0.5759 0.000 0.688 0.028 0.284 0.000 0.000
#> GSM613643 4 0.3719 0.6250 0.248 0.000 0.000 0.728 0.024 0.000
#> GSM613644 4 0.3607 0.6522 0.204 0.000 0.000 0.768 0.016 0.012
#> GSM613645 1 0.1321 0.9482 0.952 0.000 0.000 0.020 0.004 0.024
#> GSM613646 6 0.0520 0.7486 0.000 0.000 0.000 0.008 0.008 0.984
#> GSM613647 5 0.4240 0.5221 0.000 0.004 0.012 0.304 0.668 0.012
#> GSM613648 3 0.0405 0.9148 0.000 0.004 0.988 0.008 0.000 0.000
#> GSM613649 3 0.0260 0.9178 0.000 0.008 0.992 0.000 0.000 0.000
#> GSM613650 6 0.4317 0.4019 0.028 0.000 0.000 0.004 0.328 0.640
#> GSM613651 5 0.0547 0.8782 0.000 0.000 0.000 0.020 0.980 0.000
#> GSM613652 5 0.1444 0.9194 0.072 0.000 0.000 0.000 0.928 0.000
#> GSM613653 6 0.0862 0.7487 0.000 0.008 0.000 0.004 0.016 0.972
#> GSM613654 5 0.1444 0.9194 0.072 0.000 0.000 0.000 0.928 0.000
#> GSM613655 1 0.0260 0.9841 0.992 0.000 0.000 0.000 0.008 0.000
#> GSM613656 5 0.1444 0.9194 0.072 0.000 0.000 0.000 0.928 0.000
#> GSM613657 3 0.0260 0.9178 0.000 0.008 0.992 0.000 0.000 0.000
#> GSM613658 1 0.0260 0.9841 0.992 0.000 0.000 0.000 0.008 0.000
#> GSM613659 2 0.4344 0.5076 0.000 0.652 0.000 0.044 0.000 0.304
#> GSM613660 2 0.2999 0.7538 0.000 0.836 0.040 0.124 0.000 0.000
#> GSM613661 1 0.0000 0.9856 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613662 2 0.4066 0.5630 0.000 0.692 0.000 0.036 0.000 0.272
#> GSM613663 1 0.0000 0.9856 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613664 2 0.2909 0.7062 0.000 0.836 0.000 0.028 0.000 0.136
#> GSM613665 2 0.1480 0.7878 0.000 0.940 0.040 0.020 0.000 0.000
#> GSM613666 1 0.0000 0.9856 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613667 1 0.1321 0.9482 0.952 0.000 0.000 0.020 0.004 0.024
#> GSM613668 1 0.0260 0.9841 0.992 0.000 0.000 0.000 0.008 0.000
#> GSM613669 1 0.0000 0.9856 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613670 2 0.4332 0.4934 0.000 0.644 0.000 0.040 0.000 0.316
#> GSM613671 1 0.0000 0.9856 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613672 1 0.0363 0.9815 0.988 0.000 0.000 0.000 0.012 0.000
#> GSM613673 1 0.0260 0.9841 0.992 0.000 0.000 0.000 0.008 0.000
#> GSM613674 2 0.1196 0.7873 0.000 0.952 0.040 0.008 0.000 0.000
#> GSM613675 2 0.3865 0.5925 0.000 0.720 0.000 0.032 0.000 0.248
#> GSM613676 2 0.1564 0.7878 0.000 0.936 0.040 0.024 0.000 0.000
#> GSM613677 4 0.5607 0.3712 0.000 0.284 0.184 0.532 0.000 0.000
#> GSM613678 2 0.6820 0.1138 0.336 0.412 0.000 0.064 0.000 0.188
#> GSM613679 2 0.1564 0.7865 0.000 0.936 0.040 0.024 0.000 0.000
#> GSM613680 1 0.0260 0.9841 0.992 0.000 0.000 0.000 0.008 0.000
#> GSM613681 1 0.0000 0.9856 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613682 1 0.0146 0.9850 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM613683 1 0.0363 0.9815 0.988 0.000 0.000 0.000 0.012 0.000
#> GSM613684 2 0.1500 0.7813 0.000 0.936 0.052 0.012 0.000 0.000
#> GSM613685 2 0.1196 0.7873 0.000 0.952 0.040 0.008 0.000 0.000
#> GSM613686 1 0.0508 0.9762 0.984 0.000 0.000 0.004 0.000 0.012
#> GSM613687 1 0.0000 0.9856 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613688 2 0.0914 0.7816 0.000 0.968 0.016 0.016 0.000 0.000
#> GSM613689 3 0.1245 0.8921 0.000 0.000 0.952 0.032 0.016 0.000
#> GSM613690 3 0.0508 0.9108 0.000 0.000 0.984 0.012 0.004 0.000
#> GSM613691 6 0.3731 0.5872 0.000 0.240 0.004 0.020 0.000 0.736
#> GSM613692 5 0.1444 0.9194 0.072 0.000 0.000 0.000 0.928 0.000
#> GSM613693 3 0.5038 0.5228 0.000 0.176 0.664 0.008 0.000 0.152
#> GSM613694 5 0.4508 0.6455 0.000 0.004 0.036 0.044 0.740 0.176
#> GSM613695 3 0.2053 0.8691 0.000 0.004 0.916 0.052 0.024 0.004
#> GSM613696 3 0.4703 0.0983 0.000 0.016 0.508 0.004 0.012 0.460
#> GSM613697 5 0.0547 0.8782 0.000 0.000 0.000 0.020 0.980 0.000
#> GSM613698 5 0.1498 0.8700 0.000 0.004 0.012 0.012 0.948 0.024
#> GSM613699 3 0.4865 0.6465 0.000 0.004 0.720 0.044 0.064 0.168
#> GSM613700 2 0.3023 0.7472 0.000 0.828 0.032 0.140 0.000 0.000
#> GSM613701 2 0.3136 0.6868 0.000 0.768 0.000 0.228 0.000 0.004
#> GSM613702 2 0.3445 0.6630 0.000 0.732 0.000 0.260 0.000 0.008
#> GSM613703 1 0.0653 0.9734 0.980 0.000 0.000 0.004 0.004 0.012
#> GSM613704 2 0.3978 0.5719 0.000 0.700 0.000 0.032 0.000 0.268
#> GSM613705 4 0.2309 0.7050 0.000 0.000 0.028 0.888 0.084 0.000
#> GSM613706 4 0.1821 0.7267 0.008 0.040 0.000 0.928 0.024 0.000
#> GSM613707 2 0.1196 0.7873 0.000 0.952 0.040 0.008 0.000 0.000
#> GSM613708 1 0.0000 0.9856 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613709 1 0.0000 0.9856 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613710 2 0.3542 0.7191 0.000 0.788 0.052 0.160 0.000 0.000
#> GSM613711 3 0.0260 0.9178 0.000 0.008 0.992 0.000 0.000 0.000
#> GSM613712 5 0.1594 0.8596 0.000 0.000 0.016 0.052 0.932 0.000
#> GSM613713 3 0.1444 0.8717 0.000 0.072 0.928 0.000 0.000 0.000
#> GSM613714 3 0.1852 0.8770 0.000 0.004 0.928 0.040 0.024 0.004
#> GSM613715 3 0.0508 0.9143 0.000 0.004 0.984 0.012 0.000 0.000
#> GSM613716 6 0.4946 0.2699 0.000 0.052 0.384 0.008 0.000 0.556
#> GSM613717 3 0.0260 0.9178 0.000 0.008 0.992 0.000 0.000 0.000
#> GSM613718 3 0.0260 0.9178 0.000 0.008 0.992 0.000 0.000 0.000
#> GSM613719 6 0.3672 0.5182 0.000 0.004 0.000 0.008 0.276 0.712
#> GSM613720 3 0.4970 0.2450 0.000 0.064 0.560 0.004 0.000 0.372
#> GSM613721 6 0.1387 0.7347 0.000 0.068 0.000 0.000 0.000 0.932
#> GSM613722 2 0.2983 0.7472 0.000 0.832 0.032 0.136 0.000 0.000
#> GSM613723 5 0.1444 0.9194 0.072 0.000 0.000 0.000 0.928 0.000
#> GSM613724 1 0.0260 0.9841 0.992 0.000 0.000 0.000 0.008 0.000
#> GSM613725 2 0.3023 0.7472 0.000 0.828 0.032 0.140 0.000 0.000
#> GSM613726 1 0.0603 0.9768 0.980 0.000 0.000 0.016 0.004 0.000
#> GSM613727 1 0.0260 0.9841 0.992 0.000 0.000 0.000 0.008 0.000
#> GSM613728 2 0.2129 0.7725 0.000 0.904 0.000 0.056 0.000 0.040
#> GSM613729 1 0.0146 0.9842 0.996 0.000 0.000 0.000 0.000 0.004
#> GSM613730 4 0.5228 0.3162 0.000 0.308 0.000 0.572 0.000 0.120
#> GSM613731 4 0.3564 0.6134 0.264 0.000 0.000 0.724 0.012 0.000
#> GSM613732 3 0.0260 0.9178 0.000 0.008 0.992 0.000 0.000 0.000
#> GSM613733 3 0.0405 0.9162 0.000 0.008 0.988 0.004 0.000 0.000
#> GSM613734 5 0.1765 0.8971 0.096 0.000 0.000 0.000 0.904 0.000
#> GSM613735 5 0.1444 0.9194 0.072 0.000 0.000 0.000 0.928 0.000
#> GSM613736 3 0.0260 0.9178 0.000 0.008 0.992 0.000 0.000 0.000
#> GSM613737 5 0.1570 0.8646 0.000 0.004 0.008 0.028 0.944 0.016
#> GSM613738 5 0.1444 0.9194 0.072 0.000 0.000 0.000 0.928 0.000
#> GSM613739 5 0.1444 0.9194 0.072 0.000 0.000 0.000 0.928 0.000
#> GSM613740 3 0.0260 0.9178 0.000 0.008 0.992 0.000 0.000 0.000
#> GSM613741 6 0.0665 0.7500 0.000 0.008 0.000 0.004 0.008 0.980
#> GSM613742 5 0.1444 0.9194 0.072 0.000 0.000 0.000 0.928 0.000
#> GSM613743 3 0.0260 0.9178 0.000 0.008 0.992 0.000 0.000 0.000
#> GSM613744 3 0.0260 0.9178 0.000 0.008 0.992 0.000 0.000 0.000
#> GSM613745 6 0.0551 0.7488 0.000 0.004 0.000 0.008 0.004 0.984
#> GSM613746 6 0.4006 0.5665 0.000 0.252 0.012 0.020 0.000 0.716
#> GSM613747 5 0.1663 0.9055 0.088 0.000 0.000 0.000 0.912 0.000
#> GSM613748 4 0.2333 0.6915 0.000 0.120 0.004 0.872 0.000 0.004
#> GSM613749 1 0.1856 0.9195 0.920 0.000 0.000 0.048 0.000 0.032
#> GSM613750 3 0.0551 0.9164 0.000 0.008 0.984 0.004 0.004 0.000
#> GSM613751 3 0.0405 0.9172 0.000 0.008 0.988 0.004 0.000 0.000
#> GSM613752 3 0.0405 0.9172 0.000 0.008 0.988 0.004 0.000 0.000
#> GSM613753 3 0.1282 0.8944 0.000 0.004 0.956 0.024 0.012 0.004
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n disease.state(p) k
#> MAD:skmeans 115 0.01478 2
#> MAD:skmeans 108 0.05864 3
#> MAD:skmeans 112 0.00891 4
#> MAD:skmeans 99 0.10080 5
#> MAD:skmeans 108 0.00583 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 27425 rows and 116 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 0.528 0.741 0.895 0.4968 0.497 0.497
#> 3 3 0.445 0.562 0.771 0.3264 0.737 0.521
#> 4 4 0.685 0.639 0.816 0.1227 0.854 0.617
#> 5 5 0.665 0.679 0.818 0.0658 0.857 0.544
#> 6 6 0.736 0.681 0.824 0.0327 0.956 0.800
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
#> GSM613638 1 0.9866 0.20261 0.568 0.432
#> GSM613639 1 0.0000 0.88105 1.000 0.000
#> GSM613640 1 0.8081 0.60757 0.752 0.248
#> GSM613641 1 0.0000 0.88105 1.000 0.000
#> GSM613642 2 0.6712 0.75413 0.176 0.824
#> GSM613643 1 0.0000 0.88105 1.000 0.000
#> GSM613644 1 0.3584 0.83129 0.932 0.068
#> GSM613645 1 0.0000 0.88105 1.000 0.000
#> GSM613646 1 0.9044 0.51189 0.680 0.320
#> GSM613647 2 0.9954 0.14037 0.460 0.540
#> GSM613648 2 0.0000 0.86083 0.000 1.000
#> GSM613649 2 0.0000 0.86083 0.000 1.000
#> GSM613650 1 0.8267 0.59812 0.740 0.260
#> GSM613651 2 0.9996 0.05248 0.488 0.512
#> GSM613652 1 0.0000 0.88105 1.000 0.000
#> GSM613653 2 0.8207 0.65049 0.256 0.744
#> GSM613654 1 0.0000 0.88105 1.000 0.000
#> GSM613655 1 0.0000 0.88105 1.000 0.000
#> GSM613656 1 0.0000 0.88105 1.000 0.000
#> GSM613657 2 0.0000 0.86083 0.000 1.000
#> GSM613658 1 0.0000 0.88105 1.000 0.000
#> GSM613659 1 0.5178 0.79645 0.884 0.116
#> GSM613660 2 0.0672 0.85913 0.008 0.992
#> GSM613661 1 0.0000 0.88105 1.000 0.000
#> GSM613662 2 0.7453 0.70314 0.212 0.788
#> GSM613663 1 0.0000 0.88105 1.000 0.000
#> GSM613664 1 0.8386 0.58785 0.732 0.268
#> GSM613665 2 0.0000 0.86083 0.000 1.000
#> GSM613666 1 0.0000 0.88105 1.000 0.000
#> GSM613667 1 0.0000 0.88105 1.000 0.000
#> GSM613668 1 0.0000 0.88105 1.000 0.000
#> GSM613669 1 0.0000 0.88105 1.000 0.000
#> GSM613670 1 0.9286 0.48567 0.656 0.344
#> GSM613671 1 0.0000 0.88105 1.000 0.000
#> GSM613672 1 0.0000 0.88105 1.000 0.000
#> GSM613673 1 0.0000 0.88105 1.000 0.000
#> GSM613674 2 0.8813 0.52542 0.300 0.700
#> GSM613675 2 0.2778 0.84451 0.048 0.952
#> GSM613676 2 0.0000 0.86083 0.000 1.000
#> GSM613677 2 0.4298 0.82252 0.088 0.912
#> GSM613678 1 0.0000 0.88105 1.000 0.000
#> GSM613679 2 0.9996 0.04842 0.488 0.512
#> GSM613680 1 0.0000 0.88105 1.000 0.000
#> GSM613681 1 0.0000 0.88105 1.000 0.000
#> GSM613682 1 0.0000 0.88105 1.000 0.000
#> GSM613683 1 0.0000 0.88105 1.000 0.000
#> GSM613684 2 0.0000 0.86083 0.000 1.000
#> GSM613685 2 0.9815 0.25130 0.420 0.580
#> GSM613686 1 0.0000 0.88105 1.000 0.000
#> GSM613687 1 0.0000 0.88105 1.000 0.000
#> GSM613688 2 0.8909 0.54737 0.308 0.692
#> GSM613689 2 0.3733 0.83515 0.072 0.928
#> GSM613690 2 0.3733 0.83515 0.072 0.928
#> GSM613691 2 0.0000 0.86083 0.000 1.000
#> GSM613692 1 0.9954 0.11358 0.540 0.460
#> GSM613693 2 0.0000 0.86083 0.000 1.000
#> GSM613694 1 0.2236 0.85684 0.964 0.036
#> GSM613695 2 0.4161 0.82878 0.084 0.916
#> GSM613696 2 0.4562 0.82080 0.096 0.904
#> GSM613697 2 0.9427 0.44657 0.360 0.640
#> GSM613698 2 0.7883 0.68163 0.236 0.764
#> GSM613699 2 0.6801 0.75085 0.180 0.820
#> GSM613700 1 0.9996 -0.00112 0.512 0.488
#> GSM613701 1 0.0000 0.88105 1.000 0.000
#> GSM613702 1 0.2948 0.84438 0.948 0.052
#> GSM613703 1 0.0000 0.88105 1.000 0.000
#> GSM613704 2 0.1184 0.85659 0.016 0.984
#> GSM613705 1 0.9754 0.26888 0.592 0.408
#> GSM613706 1 0.0000 0.88105 1.000 0.000
#> GSM613707 2 0.5629 0.76610 0.132 0.868
#> GSM613708 1 0.0000 0.88105 1.000 0.000
#> GSM613709 1 0.0000 0.88105 1.000 0.000
#> GSM613710 2 0.0376 0.86000 0.004 0.996
#> GSM613711 2 0.0000 0.86083 0.000 1.000
#> GSM613712 2 0.8386 0.63216 0.268 0.732
#> GSM613713 2 0.0000 0.86083 0.000 1.000
#> GSM613714 2 0.4022 0.83157 0.080 0.920
#> GSM613715 2 0.0000 0.86083 0.000 1.000
#> GSM613716 2 0.0000 0.86083 0.000 1.000
#> GSM613717 2 0.0000 0.86083 0.000 1.000
#> GSM613718 2 0.0000 0.86083 0.000 1.000
#> GSM613719 2 0.9998 0.03669 0.492 0.508
#> GSM613720 2 0.0000 0.86083 0.000 1.000
#> GSM613721 2 0.5059 0.81012 0.112 0.888
#> GSM613722 2 0.9996 0.08745 0.488 0.512
#> GSM613723 1 0.0000 0.88105 1.000 0.000
#> GSM613724 1 0.0000 0.88105 1.000 0.000
#> GSM613725 1 1.0000 -0.02813 0.504 0.496
#> GSM613726 1 0.0000 0.88105 1.000 0.000
#> GSM613727 1 0.0000 0.88105 1.000 0.000
#> GSM613728 2 0.5737 0.76415 0.136 0.864
#> GSM613729 1 0.0000 0.88105 1.000 0.000
#> GSM613730 1 0.6148 0.74497 0.848 0.152
#> GSM613731 1 0.0000 0.88105 1.000 0.000
#> GSM613732 2 0.0000 0.86083 0.000 1.000
#> GSM613733 2 0.0000 0.86083 0.000 1.000
#> GSM613734 1 0.0000 0.88105 1.000 0.000
#> GSM613735 1 0.0000 0.88105 1.000 0.000
#> GSM613736 2 0.0000 0.86083 0.000 1.000
#> GSM613737 2 0.5629 0.79417 0.132 0.868
#> GSM613738 1 0.8386 0.58628 0.732 0.268
#> GSM613739 1 0.9933 0.14183 0.548 0.452
#> GSM613740 2 0.0000 0.86083 0.000 1.000
#> GSM613741 1 0.8499 0.57390 0.724 0.276
#> GSM613742 1 0.9661 0.32433 0.608 0.392
#> GSM613743 2 0.0000 0.86083 0.000 1.000
#> GSM613744 2 0.0000 0.86083 0.000 1.000
#> GSM613745 1 0.8386 0.58788 0.732 0.268
#> GSM613746 2 0.0000 0.86083 0.000 1.000
#> GSM613747 1 0.0000 0.88105 1.000 0.000
#> GSM613748 1 0.3114 0.84387 0.944 0.056
#> GSM613749 1 0.0000 0.88105 1.000 0.000
#> GSM613750 2 0.0000 0.86083 0.000 1.000
#> GSM613751 2 0.0000 0.86083 0.000 1.000
#> GSM613752 2 0.0000 0.86083 0.000 1.000
#> GSM613753 2 0.3733 0.83515 0.072 0.928
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM613638 3 0.8889 -0.24106 0.428 0.120 0.452
#> GSM613639 1 0.7588 0.65487 0.684 0.120 0.196
#> GSM613640 3 0.7677 0.35210 0.204 0.120 0.676
#> GSM613641 1 0.0000 0.79098 1.000 0.000 0.000
#> GSM613642 2 0.5414 0.48741 0.016 0.772 0.212
#> GSM613643 1 0.7804 0.63927 0.664 0.120 0.216
#> GSM613644 1 0.7804 0.63927 0.664 0.120 0.216
#> GSM613645 1 0.4654 0.72054 0.792 0.000 0.208
#> GSM613646 1 0.9770 0.21335 0.400 0.368 0.232
#> GSM613647 3 0.3340 0.48853 0.000 0.120 0.880
#> GSM613648 2 0.6308 -0.51286 0.000 0.508 0.492
#> GSM613649 3 0.6111 0.56252 0.000 0.396 0.604
#> GSM613650 1 0.6723 0.68317 0.724 0.064 0.212
#> GSM613651 3 0.3607 0.48892 0.008 0.112 0.880
#> GSM613652 1 0.4291 0.69068 0.820 0.000 0.180
#> GSM613653 3 0.5659 0.54941 0.052 0.152 0.796
#> GSM613654 1 0.4291 0.69068 0.820 0.000 0.180
#> GSM613655 1 0.0000 0.79098 1.000 0.000 0.000
#> GSM613656 1 0.4291 0.69068 0.820 0.000 0.180
#> GSM613657 3 0.6111 0.56252 0.000 0.396 0.604
#> GSM613658 1 0.0000 0.79098 1.000 0.000 0.000
#> GSM613659 2 0.8595 0.36687 0.180 0.604 0.216
#> GSM613660 2 0.0237 0.67736 0.000 0.996 0.004
#> GSM613661 1 0.0237 0.79040 0.996 0.000 0.004
#> GSM613662 2 0.3752 0.59997 0.144 0.856 0.000
#> GSM613663 1 0.0237 0.79041 0.996 0.000 0.004
#> GSM613664 2 0.4521 0.56783 0.180 0.816 0.004
#> GSM613665 2 0.3340 0.65813 0.000 0.880 0.120
#> GSM613666 1 0.0000 0.79098 1.000 0.000 0.000
#> GSM613667 1 0.4834 0.72108 0.792 0.004 0.204
#> GSM613668 1 0.0000 0.79098 1.000 0.000 0.000
#> GSM613669 1 0.0000 0.79098 1.000 0.000 0.000
#> GSM613670 2 0.6511 0.51132 0.180 0.748 0.072
#> GSM613671 1 0.0000 0.79098 1.000 0.000 0.000
#> GSM613672 1 0.0000 0.79098 1.000 0.000 0.000
#> GSM613673 1 0.3412 0.75791 0.876 0.000 0.124
#> GSM613674 2 0.3340 0.65813 0.000 0.880 0.120
#> GSM613675 2 0.0983 0.67425 0.016 0.980 0.004
#> GSM613676 2 0.3340 0.65813 0.000 0.880 0.120
#> GSM613677 3 0.6955 0.47939 0.016 0.492 0.492
#> GSM613678 1 0.9683 0.23250 0.416 0.368 0.216
#> GSM613679 2 0.0237 0.67876 0.004 0.996 0.000
#> GSM613680 1 0.0000 0.79098 1.000 0.000 0.000
#> GSM613681 1 0.0000 0.79098 1.000 0.000 0.000
#> GSM613682 1 0.4605 0.72270 0.796 0.000 0.204
#> GSM613683 1 0.0000 0.79098 1.000 0.000 0.000
#> GSM613684 2 0.3340 0.65813 0.000 0.880 0.120
#> GSM613685 2 0.3340 0.65813 0.000 0.880 0.120
#> GSM613686 1 0.4346 0.73310 0.816 0.000 0.184
#> GSM613687 1 0.0000 0.79098 1.000 0.000 0.000
#> GSM613688 2 0.5521 0.56840 0.180 0.788 0.032
#> GSM613689 3 0.5138 0.56395 0.000 0.252 0.748
#> GSM613690 3 0.4931 0.56833 0.000 0.232 0.768
#> GSM613691 2 0.5905 0.14633 0.000 0.648 0.352
#> GSM613692 1 0.6180 0.32945 0.584 0.000 0.416
#> GSM613693 2 0.4062 0.60617 0.000 0.836 0.164
#> GSM613694 1 0.9824 0.27362 0.404 0.248 0.348
#> GSM613695 3 0.5497 0.51012 0.000 0.292 0.708
#> GSM613696 2 0.5254 0.58129 0.000 0.736 0.264
#> GSM613697 3 0.3340 0.48853 0.000 0.120 0.880
#> GSM613698 3 0.3340 0.48853 0.000 0.120 0.880
#> GSM613699 3 0.6783 0.12029 0.016 0.396 0.588
#> GSM613700 2 0.0237 0.67736 0.000 0.996 0.004
#> GSM613701 2 0.8595 0.36687 0.180 0.604 0.216
#> GSM613702 1 0.9683 0.23250 0.416 0.368 0.216
#> GSM613703 1 0.0000 0.79098 1.000 0.000 0.000
#> GSM613704 2 0.2703 0.67970 0.016 0.928 0.056
#> GSM613705 3 0.6322 0.49824 0.024 0.276 0.700
#> GSM613706 1 0.9683 0.23250 0.416 0.368 0.216
#> GSM613707 2 0.3340 0.65813 0.000 0.880 0.120
#> GSM613708 1 0.0000 0.79098 1.000 0.000 0.000
#> GSM613709 1 0.0000 0.79098 1.000 0.000 0.000
#> GSM613710 2 0.0237 0.67736 0.000 0.996 0.004
#> GSM613711 3 0.6111 0.56252 0.000 0.396 0.604
#> GSM613712 3 0.3340 0.48853 0.000 0.120 0.880
#> GSM613713 2 0.3340 0.65813 0.000 0.880 0.120
#> GSM613714 3 0.5968 0.52283 0.000 0.364 0.636
#> GSM613715 3 0.6095 0.56392 0.000 0.392 0.608
#> GSM613716 3 0.6095 0.56392 0.000 0.392 0.608
#> GSM613717 3 0.6111 0.56252 0.000 0.396 0.604
#> GSM613718 3 0.6111 0.56252 0.000 0.396 0.604
#> GSM613719 3 0.4068 0.48368 0.016 0.120 0.864
#> GSM613720 3 0.6111 0.56252 0.000 0.396 0.604
#> GSM613721 2 0.5363 0.57457 0.000 0.724 0.276
#> GSM613722 2 0.1337 0.67131 0.016 0.972 0.012
#> GSM613723 1 0.4291 0.69068 0.820 0.000 0.180
#> GSM613724 1 0.0000 0.79098 1.000 0.000 0.000
#> GSM613725 2 0.3267 0.65987 0.000 0.884 0.116
#> GSM613726 1 0.7762 0.64269 0.668 0.120 0.212
#> GSM613727 1 0.0000 0.79098 1.000 0.000 0.000
#> GSM613728 2 0.0237 0.67736 0.000 0.996 0.004
#> GSM613729 1 0.0000 0.79098 1.000 0.000 0.000
#> GSM613730 2 0.9573 -0.00832 0.328 0.460 0.212
#> GSM613731 1 0.7804 0.63927 0.664 0.120 0.216
#> GSM613732 3 0.6111 0.56252 0.000 0.396 0.604
#> GSM613733 3 0.6111 0.56252 0.000 0.396 0.604
#> GSM613734 1 0.4291 0.69068 0.820 0.000 0.180
#> GSM613735 1 0.4291 0.69068 0.820 0.000 0.180
#> GSM613736 2 0.5138 0.45918 0.000 0.748 0.252
#> GSM613737 3 0.0237 0.52376 0.000 0.004 0.996
#> GSM613738 1 0.5650 0.54602 0.688 0.000 0.312
#> GSM613739 3 0.6252 -0.24186 0.444 0.000 0.556
#> GSM613740 3 0.6095 0.56392 0.000 0.392 0.608
#> GSM613741 2 0.9952 0.21394 0.292 0.376 0.332
#> GSM613742 3 0.6111 -0.22388 0.396 0.000 0.604
#> GSM613743 3 0.6111 0.56252 0.000 0.396 0.604
#> GSM613744 3 0.6111 0.56252 0.000 0.396 0.604
#> GSM613745 1 0.8445 0.54008 0.580 0.116 0.304
#> GSM613746 2 0.3340 0.65813 0.000 0.880 0.120
#> GSM613747 1 0.4291 0.69068 0.820 0.000 0.180
#> GSM613748 1 0.9386 0.44525 0.500 0.204 0.296
#> GSM613749 1 0.7525 0.65667 0.684 0.108 0.208
#> GSM613750 3 0.6095 0.56392 0.000 0.392 0.608
#> GSM613751 3 0.6111 0.56252 0.000 0.396 0.604
#> GSM613752 3 0.6111 0.56252 0.000 0.396 0.604
#> GSM613753 3 0.2356 0.54271 0.000 0.072 0.928
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 1 0.5000 -0.3945 0.500 0.000 0.500 0.000
#> GSM613639 1 0.3311 0.5533 0.828 0.000 0.000 0.172
#> GSM613640 1 0.4985 -0.3262 0.532 0.000 0.468 0.000
#> GSM613641 1 0.4994 0.5259 0.520 0.000 0.000 0.480
#> GSM613642 2 0.3668 0.7559 0.188 0.808 0.004 0.000
#> GSM613643 1 0.0000 0.5574 1.000 0.000 0.000 0.000
#> GSM613644 1 0.0000 0.5574 1.000 0.000 0.000 0.000
#> GSM613645 1 0.1940 0.5732 0.924 0.000 0.000 0.076
#> GSM613646 1 0.0000 0.5574 1.000 0.000 0.000 0.000
#> GSM613647 1 0.7519 -0.2396 0.480 0.000 0.208 0.312
#> GSM613648 3 0.0336 0.8477 0.008 0.000 0.992 0.000
#> GSM613649 3 0.2469 0.8029 0.000 0.108 0.892 0.000
#> GSM613650 1 0.2949 0.5640 0.888 0.000 0.024 0.088
#> GSM613651 4 0.7417 0.1860 0.208 0.000 0.284 0.508
#> GSM613652 4 0.0000 0.7785 0.000 0.000 0.000 1.000
#> GSM613653 3 0.3710 0.7242 0.192 0.004 0.804 0.000
#> GSM613654 4 0.0000 0.7785 0.000 0.000 0.000 1.000
#> GSM613655 1 0.4994 0.5259 0.520 0.000 0.000 0.480
#> GSM613656 4 0.0000 0.7785 0.000 0.000 0.000 1.000
#> GSM613657 3 0.0000 0.8494 0.000 0.000 1.000 0.000
#> GSM613658 1 0.4999 0.5089 0.508 0.000 0.000 0.492
#> GSM613659 2 0.3528 0.7522 0.192 0.808 0.000 0.000
#> GSM613660 2 0.2542 0.8471 0.084 0.904 0.012 0.000
#> GSM613661 1 0.4992 0.5260 0.524 0.000 0.000 0.476
#> GSM613662 2 0.0000 0.8884 0.000 1.000 0.000 0.000
#> GSM613663 1 0.4955 0.5293 0.556 0.000 0.000 0.444
#> GSM613664 2 0.0000 0.8884 0.000 1.000 0.000 0.000
#> GSM613665 2 0.0469 0.8861 0.000 0.988 0.012 0.000
#> GSM613666 1 0.4994 0.5259 0.520 0.000 0.000 0.480
#> GSM613667 1 0.2216 0.5736 0.908 0.000 0.000 0.092
#> GSM613668 1 0.4994 0.5259 0.520 0.000 0.000 0.480
#> GSM613669 1 0.4994 0.5259 0.520 0.000 0.000 0.480
#> GSM613670 2 0.0000 0.8884 0.000 1.000 0.000 0.000
#> GSM613671 1 0.4994 0.5259 0.520 0.000 0.000 0.480
#> GSM613672 1 0.4994 0.5259 0.520 0.000 0.000 0.480
#> GSM613673 1 0.4222 0.5534 0.728 0.000 0.000 0.272
#> GSM613674 2 0.0000 0.8884 0.000 1.000 0.000 0.000
#> GSM613675 2 0.0000 0.8884 0.000 1.000 0.000 0.000
#> GSM613676 2 0.0336 0.8872 0.000 0.992 0.008 0.000
#> GSM613677 3 0.2976 0.7996 0.008 0.120 0.872 0.000
#> GSM613678 1 0.2081 0.5347 0.916 0.084 0.000 0.000
#> GSM613679 2 0.0000 0.8884 0.000 1.000 0.000 0.000
#> GSM613680 1 0.4994 0.5259 0.520 0.000 0.000 0.480
#> GSM613681 1 0.4994 0.5259 0.520 0.000 0.000 0.480
#> GSM613682 1 0.2216 0.5736 0.908 0.000 0.000 0.092
#> GSM613683 1 0.4994 0.5259 0.520 0.000 0.000 0.480
#> GSM613684 2 0.3400 0.8147 0.000 0.820 0.180 0.000
#> GSM613685 2 0.0000 0.8884 0.000 1.000 0.000 0.000
#> GSM613686 1 0.2530 0.5737 0.888 0.000 0.000 0.112
#> GSM613687 1 0.4992 0.5267 0.524 0.000 0.000 0.476
#> GSM613688 2 0.3311 0.8210 0.000 0.828 0.172 0.000
#> GSM613689 3 0.0000 0.8494 0.000 0.000 1.000 0.000
#> GSM613690 3 0.0000 0.8494 0.000 0.000 1.000 0.000
#> GSM613691 3 0.4972 -0.0557 0.000 0.456 0.544 0.000
#> GSM613692 4 0.0000 0.7785 0.000 0.000 0.000 1.000
#> GSM613693 2 0.4624 0.6036 0.000 0.660 0.340 0.000
#> GSM613694 1 0.0000 0.5574 1.000 0.000 0.000 0.000
#> GSM613695 3 0.3688 0.7149 0.208 0.000 0.792 0.000
#> GSM613696 2 0.3852 0.8127 0.012 0.808 0.180 0.000
#> GSM613697 3 0.7573 0.2235 0.208 0.000 0.460 0.332
#> GSM613698 3 0.7453 0.3053 0.204 0.000 0.496 0.300
#> GSM613699 3 0.7587 0.0581 0.196 0.392 0.412 0.000
#> GSM613700 2 0.2125 0.8540 0.076 0.920 0.004 0.000
#> GSM613701 2 0.3528 0.7522 0.192 0.808 0.000 0.000
#> GSM613702 1 0.0000 0.5574 1.000 0.000 0.000 0.000
#> GSM613703 1 0.4994 0.5259 0.520 0.000 0.000 0.480
#> GSM613704 2 0.0000 0.8884 0.000 1.000 0.000 0.000
#> GSM613705 3 0.4955 0.4476 0.444 0.000 0.556 0.000
#> GSM613706 1 0.0000 0.5574 1.000 0.000 0.000 0.000
#> GSM613707 2 0.0469 0.8879 0.000 0.988 0.012 0.000
#> GSM613708 1 0.4994 0.5259 0.520 0.000 0.000 0.480
#> GSM613709 1 0.4994 0.5259 0.520 0.000 0.000 0.480
#> GSM613710 2 0.2542 0.8471 0.084 0.904 0.012 0.000
#> GSM613711 3 0.0469 0.8472 0.000 0.012 0.988 0.000
#> GSM613712 3 0.3688 0.7134 0.208 0.000 0.792 0.000
#> GSM613713 2 0.3649 0.8004 0.000 0.796 0.204 0.000
#> GSM613714 3 0.2589 0.7940 0.116 0.000 0.884 0.000
#> GSM613715 3 0.0000 0.8494 0.000 0.000 1.000 0.000
#> GSM613716 3 0.0817 0.8425 0.000 0.024 0.976 0.000
#> GSM613717 3 0.0188 0.8488 0.000 0.004 0.996 0.000
#> GSM613718 3 0.0000 0.8494 0.000 0.000 1.000 0.000
#> GSM613719 3 0.3649 0.7169 0.204 0.000 0.796 0.000
#> GSM613720 3 0.3024 0.7763 0.000 0.148 0.852 0.000
#> GSM613721 2 0.3852 0.8125 0.012 0.808 0.180 0.000
#> GSM613722 2 0.0000 0.8884 0.000 1.000 0.000 0.000
#> GSM613723 4 0.0000 0.7785 0.000 0.000 0.000 1.000
#> GSM613724 1 0.4994 0.5259 0.520 0.000 0.000 0.480
#> GSM613725 2 0.2149 0.8693 0.000 0.912 0.088 0.000
#> GSM613726 1 0.0000 0.5574 1.000 0.000 0.000 0.000
#> GSM613727 1 0.4994 0.5259 0.520 0.000 0.000 0.480
#> GSM613728 2 0.0000 0.8884 0.000 1.000 0.000 0.000
#> GSM613729 1 0.4994 0.5259 0.520 0.000 0.000 0.480
#> GSM613730 1 0.4372 0.2550 0.728 0.268 0.004 0.000
#> GSM613731 1 0.0000 0.5574 1.000 0.000 0.000 0.000
#> GSM613732 3 0.0000 0.8494 0.000 0.000 1.000 0.000
#> GSM613733 3 0.3172 0.7669 0.000 0.160 0.840 0.000
#> GSM613734 4 0.0000 0.7785 0.000 0.000 0.000 1.000
#> GSM613735 4 0.0000 0.7785 0.000 0.000 0.000 1.000
#> GSM613736 2 0.6559 0.2273 0.076 0.468 0.456 0.000
#> GSM613737 4 0.6937 0.3666 0.376 0.000 0.116 0.508
#> GSM613738 4 0.0469 0.7708 0.012 0.000 0.000 0.988
#> GSM613739 4 0.4250 0.5255 0.276 0.000 0.000 0.724
#> GSM613740 3 0.0000 0.8494 0.000 0.000 1.000 0.000
#> GSM613741 1 0.5721 0.0267 0.584 0.388 0.024 0.004
#> GSM613742 4 0.4804 0.3995 0.384 0.000 0.000 0.616
#> GSM613743 3 0.0000 0.8494 0.000 0.000 1.000 0.000
#> GSM613744 3 0.0000 0.8494 0.000 0.000 1.000 0.000
#> GSM613745 1 0.1576 0.5689 0.948 0.000 0.004 0.048
#> GSM613746 2 0.1940 0.8730 0.000 0.924 0.076 0.000
#> GSM613747 4 0.0000 0.7785 0.000 0.000 0.000 1.000
#> GSM613748 1 0.0000 0.5574 1.000 0.000 0.000 0.000
#> GSM613749 1 0.1940 0.5725 0.924 0.000 0.000 0.076
#> GSM613750 3 0.0000 0.8494 0.000 0.000 1.000 0.000
#> GSM613751 3 0.0592 0.8455 0.000 0.016 0.984 0.000
#> GSM613752 3 0.0188 0.8486 0.000 0.004 0.996 0.000
#> GSM613753 3 0.0000 0.8494 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
#> GSM613638 4 0.2966 0.6841 0.000 0.000 0.184 0.816 0.000
#> GSM613639 4 0.3700 0.6952 0.240 0.000 0.000 0.752 0.008
#> GSM613640 4 0.3495 0.7154 0.032 0.000 0.152 0.816 0.000
#> GSM613641 1 0.0000 0.8525 1.000 0.000 0.000 0.000 0.000
#> GSM613642 2 0.3521 0.6570 0.000 0.764 0.004 0.232 0.000
#> GSM613643 4 0.2966 0.7510 0.184 0.000 0.000 0.816 0.000
#> GSM613644 4 0.2966 0.7510 0.184 0.000 0.000 0.816 0.000
#> GSM613645 1 0.3689 0.6477 0.740 0.000 0.000 0.256 0.004
#> GSM613646 1 0.6265 0.4667 0.596 0.000 0.016 0.172 0.216
#> GSM613647 4 0.3647 0.6512 0.000 0.000 0.052 0.816 0.132
#> GSM613648 3 0.3731 0.6907 0.000 0.000 0.800 0.160 0.040
#> GSM613649 3 0.2592 0.8368 0.000 0.052 0.892 0.000 0.056
#> GSM613650 1 0.6818 0.2463 0.484 0.000 0.020 0.324 0.172
#> GSM613651 5 0.2249 0.6373 0.000 0.000 0.008 0.096 0.896
#> GSM613652 5 0.3561 0.7250 0.260 0.000 0.000 0.000 0.740
#> GSM613653 5 0.7005 -0.2458 0.000 0.208 0.388 0.016 0.388
#> GSM613654 5 0.3561 0.7250 0.260 0.000 0.000 0.000 0.740
#> GSM613655 1 0.0794 0.8298 0.972 0.000 0.000 0.000 0.028
#> GSM613656 5 0.3561 0.7250 0.260 0.000 0.000 0.000 0.740
#> GSM613657 3 0.0510 0.8519 0.000 0.000 0.984 0.000 0.016
#> GSM613658 1 0.0162 0.8495 0.996 0.000 0.000 0.000 0.004
#> GSM613659 2 0.4401 0.7109 0.000 0.764 0.000 0.104 0.132
#> GSM613660 4 0.5320 0.1645 0.000 0.424 0.052 0.524 0.000
#> GSM613661 1 0.0404 0.8485 0.988 0.000 0.000 0.012 0.000
#> GSM613662 2 0.0162 0.8147 0.000 0.996 0.000 0.000 0.004
#> GSM613663 1 0.0404 0.8487 0.988 0.000 0.000 0.012 0.000
#> GSM613664 2 0.0000 0.8148 0.000 1.000 0.000 0.000 0.000
#> GSM613665 2 0.1121 0.8057 0.000 0.956 0.044 0.000 0.000
#> GSM613666 1 0.0000 0.8525 1.000 0.000 0.000 0.000 0.000
#> GSM613667 1 0.3508 0.6538 0.748 0.000 0.000 0.252 0.000
#> GSM613668 1 0.0000 0.8525 1.000 0.000 0.000 0.000 0.000
#> GSM613669 1 0.0000 0.8525 1.000 0.000 0.000 0.000 0.000
#> GSM613670 2 0.0963 0.8116 0.000 0.964 0.000 0.000 0.036
#> GSM613671 1 0.0000 0.8525 1.000 0.000 0.000 0.000 0.000
#> GSM613672 1 0.0162 0.8515 0.996 0.000 0.000 0.004 0.000
#> GSM613673 1 0.2561 0.7641 0.856 0.000 0.000 0.144 0.000
#> GSM613674 2 0.0000 0.8148 0.000 1.000 0.000 0.000 0.000
#> GSM613675 2 0.0000 0.8148 0.000 1.000 0.000 0.000 0.000
#> GSM613676 2 0.1121 0.8053 0.000 0.956 0.044 0.000 0.000
#> GSM613677 4 0.7457 0.0781 0.000 0.124 0.384 0.408 0.084
#> GSM613678 1 0.5512 0.4987 0.620 0.104 0.000 0.276 0.000
#> GSM613679 2 0.0000 0.8148 0.000 1.000 0.000 0.000 0.000
#> GSM613680 1 0.0000 0.8525 1.000 0.000 0.000 0.000 0.000
#> GSM613681 1 0.0000 0.8525 1.000 0.000 0.000 0.000 0.000
#> GSM613682 1 0.3508 0.6538 0.748 0.000 0.000 0.252 0.000
#> GSM613683 1 0.0000 0.8525 1.000 0.000 0.000 0.000 0.000
#> GSM613684 2 0.2471 0.7696 0.000 0.864 0.136 0.000 0.000
#> GSM613685 2 0.0000 0.8148 0.000 1.000 0.000 0.000 0.000
#> GSM613686 1 0.3720 0.6733 0.760 0.000 0.000 0.228 0.012
#> GSM613687 1 0.0000 0.8525 1.000 0.000 0.000 0.000 0.000
#> GSM613688 2 0.3182 0.7853 0.000 0.864 0.092 0.016 0.028
#> GSM613689 3 0.2830 0.8180 0.000 0.000 0.876 0.044 0.080
#> GSM613690 3 0.3305 0.7268 0.000 0.000 0.776 0.000 0.224
#> GSM613691 2 0.5213 0.6513 0.000 0.696 0.176 0.004 0.124
#> GSM613692 5 0.3395 0.7294 0.236 0.000 0.000 0.000 0.764
#> GSM613693 2 0.4410 0.3383 0.000 0.556 0.440 0.000 0.004
#> GSM613694 1 0.5922 0.5138 0.604 0.000 0.016 0.096 0.284
#> GSM613695 4 0.6498 0.1682 0.000 0.000 0.352 0.452 0.196
#> GSM613696 2 0.4610 0.7037 0.000 0.740 0.040 0.016 0.204
#> GSM613697 5 0.4119 0.5488 0.000 0.000 0.152 0.068 0.780
#> GSM613698 5 0.3535 0.5187 0.000 0.000 0.164 0.028 0.808
#> GSM613699 2 0.7557 0.2447 0.000 0.440 0.268 0.056 0.236
#> GSM613700 2 0.4528 0.0933 0.000 0.548 0.008 0.444 0.000
#> GSM613701 2 0.3877 0.6712 0.000 0.764 0.000 0.212 0.024
#> GSM613702 4 0.2966 0.7510 0.184 0.000 0.000 0.816 0.000
#> GSM613703 1 0.0290 0.8501 0.992 0.000 0.000 0.000 0.008
#> GSM613704 2 0.0000 0.8148 0.000 1.000 0.000 0.000 0.000
#> GSM613705 4 0.3355 0.6773 0.000 0.000 0.184 0.804 0.012
#> GSM613706 4 0.2966 0.7510 0.184 0.000 0.000 0.816 0.000
#> GSM613707 2 0.0162 0.8150 0.000 0.996 0.004 0.000 0.000
#> GSM613708 1 0.0000 0.8525 1.000 0.000 0.000 0.000 0.000
#> GSM613709 1 0.0000 0.8525 1.000 0.000 0.000 0.000 0.000
#> GSM613710 2 0.5458 -0.0787 0.000 0.476 0.060 0.464 0.000
#> GSM613711 3 0.0162 0.8523 0.000 0.004 0.996 0.000 0.000
#> GSM613712 5 0.5688 0.1875 0.000 0.000 0.328 0.100 0.572
#> GSM613713 2 0.4161 0.4763 0.000 0.608 0.392 0.000 0.000
#> GSM613714 4 0.5873 0.4163 0.000 0.000 0.312 0.564 0.124
#> GSM613715 3 0.2325 0.8384 0.000 0.000 0.904 0.028 0.068
#> GSM613716 3 0.7524 0.3459 0.000 0.236 0.460 0.060 0.244
#> GSM613717 3 0.0671 0.8524 0.000 0.004 0.980 0.000 0.016
#> GSM613718 3 0.0000 0.8518 0.000 0.000 1.000 0.000 0.000
#> GSM613719 5 0.4491 0.2061 0.004 0.000 0.336 0.012 0.648
#> GSM613720 3 0.3141 0.7731 0.000 0.152 0.832 0.000 0.016
#> GSM613721 2 0.4498 0.7269 0.000 0.756 0.132 0.000 0.112
#> GSM613722 2 0.0000 0.8148 0.000 1.000 0.000 0.000 0.000
#> GSM613723 5 0.3561 0.7250 0.260 0.000 0.000 0.000 0.740
#> GSM613724 1 0.0000 0.8525 1.000 0.000 0.000 0.000 0.000
#> GSM613725 2 0.1544 0.8031 0.000 0.932 0.068 0.000 0.000
#> GSM613726 4 0.2966 0.7510 0.184 0.000 0.000 0.816 0.000
#> GSM613727 1 0.0000 0.8525 1.000 0.000 0.000 0.000 0.000
#> GSM613728 2 0.0000 0.8148 0.000 1.000 0.000 0.000 0.000
#> GSM613729 1 0.0000 0.8525 1.000 0.000 0.000 0.000 0.000
#> GSM613730 4 0.4512 0.7442 0.140 0.044 0.000 0.780 0.036
#> GSM613731 4 0.2966 0.7510 0.184 0.000 0.000 0.816 0.000
#> GSM613732 3 0.0794 0.8493 0.000 0.000 0.972 0.000 0.028
#> GSM613733 3 0.2020 0.8151 0.000 0.100 0.900 0.000 0.000
#> GSM613734 5 0.3586 0.7213 0.264 0.000 0.000 0.000 0.736
#> GSM613735 5 0.3561 0.7250 0.260 0.000 0.000 0.000 0.740
#> GSM613736 3 0.4791 0.6209 0.000 0.124 0.740 0.132 0.004
#> GSM613737 5 0.2331 0.6293 0.000 0.000 0.020 0.080 0.900
#> GSM613738 5 0.3890 0.7257 0.252 0.000 0.000 0.012 0.736
#> GSM613739 5 0.4610 0.6308 0.092 0.000 0.000 0.168 0.740
#> GSM613740 3 0.0000 0.8518 0.000 0.000 1.000 0.000 0.000
#> GSM613741 2 0.8213 0.0933 0.220 0.352 0.028 0.052 0.348
#> GSM613742 5 0.2848 0.6115 0.004 0.000 0.000 0.156 0.840
#> GSM613743 3 0.0000 0.8518 0.000 0.000 1.000 0.000 0.000
#> GSM613744 3 0.0880 0.8491 0.000 0.000 0.968 0.000 0.032
#> GSM613745 1 0.5728 0.4925 0.588 0.000 0.024 0.052 0.336
#> GSM613746 2 0.1965 0.8058 0.000 0.924 0.052 0.000 0.024
#> GSM613747 5 0.4088 0.5819 0.368 0.000 0.000 0.000 0.632
#> GSM613748 4 0.2966 0.7510 0.184 0.000 0.000 0.816 0.000
#> GSM613749 1 0.4101 0.4584 0.628 0.000 0.000 0.372 0.000
#> GSM613750 3 0.3724 0.7652 0.000 0.000 0.788 0.184 0.028
#> GSM613751 3 0.4707 0.7493 0.000 0.040 0.748 0.184 0.028
#> GSM613752 3 0.3724 0.7652 0.000 0.000 0.788 0.184 0.028
#> GSM613753 3 0.5577 0.6946 0.000 0.000 0.644 0.184 0.172
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM613638 4 0.0000 0.8073 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613639 4 0.1787 0.7518 0.068 0.000 0.000 0.920 0.008 0.004
#> GSM613640 4 0.0000 0.8073 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613641 1 0.0458 0.8529 0.984 0.000 0.000 0.000 0.000 0.016
#> GSM613642 2 0.3074 0.7281 0.000 0.792 0.004 0.200 0.000 0.004
#> GSM613643 4 0.0000 0.8073 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613644 4 0.0000 0.8073 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613645 1 0.3383 0.6822 0.728 0.000 0.000 0.268 0.000 0.004
#> GSM613646 1 0.5493 0.5590 0.640 0.000 0.000 0.056 0.224 0.080
#> GSM613647 4 0.0146 0.8065 0.000 0.000 0.000 0.996 0.004 0.000
#> GSM613648 3 0.4184 0.5097 0.000 0.000 0.744 0.196 0.028 0.032
#> GSM613649 3 0.1492 0.7412 0.000 0.024 0.940 0.000 0.000 0.036
#> GSM613650 4 0.6711 -0.0410 0.368 0.000 0.000 0.404 0.168 0.060
#> GSM613651 5 0.2149 0.5761 0.000 0.000 0.004 0.104 0.888 0.004
#> GSM613652 5 0.4518 0.6511 0.200 0.000 0.000 0.000 0.696 0.104
#> GSM613653 5 0.7461 -0.1026 0.000 0.272 0.284 0.008 0.344 0.092
#> GSM613654 5 0.4518 0.6511 0.200 0.000 0.000 0.000 0.696 0.104
#> GSM613655 1 0.1950 0.8299 0.912 0.000 0.000 0.000 0.024 0.064
#> GSM613656 5 0.4641 0.6464 0.200 0.000 0.000 0.000 0.684 0.116
#> GSM613657 3 0.0363 0.7518 0.000 0.000 0.988 0.000 0.000 0.012
#> GSM613658 1 0.1588 0.8402 0.924 0.000 0.000 0.000 0.004 0.072
#> GSM613659 2 0.4179 0.7569 0.000 0.776 0.000 0.080 0.116 0.028
#> GSM613660 4 0.4911 0.5552 0.000 0.204 0.116 0.672 0.000 0.008
#> GSM613661 1 0.2740 0.8169 0.864 0.000 0.000 0.076 0.000 0.060
#> GSM613662 2 0.1327 0.8405 0.000 0.936 0.000 0.000 0.000 0.064
#> GSM613663 1 0.0363 0.8515 0.988 0.000 0.000 0.012 0.000 0.000
#> GSM613664 2 0.1501 0.8421 0.000 0.924 0.000 0.000 0.000 0.076
#> GSM613665 2 0.2937 0.7951 0.000 0.848 0.096 0.000 0.000 0.056
#> GSM613666 1 0.0458 0.8529 0.984 0.000 0.000 0.000 0.000 0.016
#> GSM613667 1 0.2793 0.7422 0.800 0.000 0.000 0.200 0.000 0.000
#> GSM613668 1 0.0000 0.8524 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613669 1 0.1501 0.8425 0.924 0.000 0.000 0.000 0.000 0.076
#> GSM613670 2 0.1858 0.8394 0.000 0.904 0.000 0.000 0.004 0.092
#> GSM613671 1 0.0458 0.8529 0.984 0.000 0.000 0.000 0.000 0.016
#> GSM613672 1 0.0260 0.8525 0.992 0.000 0.000 0.008 0.000 0.000
#> GSM613673 1 0.2527 0.7756 0.832 0.000 0.000 0.168 0.000 0.000
#> GSM613674 2 0.0547 0.8394 0.000 0.980 0.000 0.000 0.000 0.020
#> GSM613675 2 0.1610 0.8382 0.000 0.916 0.000 0.000 0.000 0.084
#> GSM613676 2 0.2668 0.7375 0.000 0.828 0.168 0.000 0.000 0.004
#> GSM613677 4 0.6881 0.3296 0.000 0.124 0.264 0.520 0.052 0.040
#> GSM613678 1 0.4664 0.6118 0.644 0.076 0.000 0.280 0.000 0.000
#> GSM613679 2 0.0363 0.8396 0.000 0.988 0.000 0.000 0.000 0.012
#> GSM613680 1 0.0000 0.8524 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613681 1 0.0146 0.8526 0.996 0.000 0.000 0.000 0.000 0.004
#> GSM613682 1 0.2996 0.7229 0.772 0.000 0.000 0.228 0.000 0.000
#> GSM613683 1 0.1267 0.8438 0.940 0.000 0.000 0.000 0.000 0.060
#> GSM613684 2 0.2356 0.8120 0.000 0.884 0.096 0.000 0.004 0.016
#> GSM613685 2 0.0547 0.8394 0.000 0.980 0.000 0.000 0.000 0.020
#> GSM613686 1 0.3053 0.7572 0.812 0.000 0.000 0.168 0.000 0.020
#> GSM613687 1 0.0000 0.8524 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613688 2 0.2602 0.8248 0.000 0.892 0.052 0.004 0.020 0.032
#> GSM613689 3 0.3620 0.6046 0.000 0.000 0.808 0.060 0.120 0.012
#> GSM613690 3 0.5147 0.4127 0.000 0.000 0.652 0.060 0.248 0.040
#> GSM613691 2 0.5104 0.6806 0.000 0.664 0.168 0.000 0.012 0.156
#> GSM613692 5 0.3141 0.6597 0.200 0.000 0.000 0.000 0.788 0.012
#> GSM613693 3 0.4473 -0.1941 0.000 0.480 0.492 0.000 0.000 0.028
#> GSM613694 1 0.4436 0.5418 0.632 0.000 0.000 0.028 0.332 0.008
#> GSM613695 4 0.6089 0.3059 0.000 0.000 0.224 0.524 0.232 0.020
#> GSM613696 2 0.4358 0.6690 0.000 0.704 0.028 0.000 0.244 0.024
#> GSM613697 5 0.3429 0.5199 0.000 0.000 0.108 0.056 0.824 0.012
#> GSM613698 5 0.3894 0.4360 0.000 0.000 0.152 0.008 0.776 0.064
#> GSM613699 2 0.7272 0.0515 0.000 0.360 0.292 0.024 0.284 0.040
#> GSM613700 4 0.4336 0.4013 0.000 0.408 0.012 0.572 0.000 0.008
#> GSM613701 2 0.3589 0.7255 0.004 0.776 0.000 0.196 0.016 0.008
#> GSM613702 4 0.0520 0.8039 0.000 0.000 0.000 0.984 0.008 0.008
#> GSM613703 1 0.1663 0.8431 0.912 0.000 0.000 0.000 0.000 0.088
#> GSM613704 2 0.1267 0.8400 0.000 0.940 0.000 0.000 0.000 0.060
#> GSM613705 4 0.0547 0.8003 0.000 0.000 0.000 0.980 0.020 0.000
#> GSM613706 4 0.0000 0.8073 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613707 2 0.0806 0.8407 0.000 0.972 0.008 0.000 0.000 0.020
#> GSM613708 1 0.0632 0.8520 0.976 0.000 0.000 0.000 0.000 0.024
#> GSM613709 1 0.1501 0.8425 0.924 0.000 0.000 0.000 0.000 0.076
#> GSM613710 4 0.5405 0.4801 0.000 0.208 0.172 0.612 0.000 0.008
#> GSM613711 3 0.0146 0.7522 0.000 0.004 0.996 0.000 0.000 0.000
#> GSM613712 5 0.5041 0.3088 0.000 0.000 0.248 0.044 0.660 0.048
#> GSM613713 2 0.4066 0.4258 0.000 0.596 0.392 0.000 0.000 0.012
#> GSM613714 4 0.4508 0.6169 0.000 0.000 0.136 0.740 0.104 0.020
#> GSM613715 3 0.2179 0.7199 0.000 0.000 0.900 0.000 0.036 0.064
#> GSM613716 3 0.8411 0.1115 0.000 0.184 0.376 0.128 0.204 0.108
#> GSM613717 3 0.0405 0.7530 0.000 0.004 0.988 0.000 0.000 0.008
#> GSM613718 3 0.0000 0.7516 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613719 5 0.4837 0.3357 0.000 0.000 0.248 0.008 0.660 0.084
#> GSM613720 3 0.2875 0.6711 0.000 0.096 0.852 0.000 0.000 0.052
#> GSM613721 2 0.4597 0.7585 0.000 0.756 0.080 0.000 0.084 0.080
#> GSM613722 2 0.0363 0.8403 0.000 0.988 0.000 0.000 0.000 0.012
#> GSM613723 5 0.4641 0.6464 0.200 0.000 0.000 0.000 0.684 0.116
#> GSM613724 1 0.1267 0.8438 0.940 0.000 0.000 0.000 0.000 0.060
#> GSM613725 2 0.1682 0.8337 0.000 0.928 0.052 0.000 0.000 0.020
#> GSM613726 4 0.0000 0.8073 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613727 1 0.1501 0.8425 0.924 0.000 0.000 0.000 0.000 0.076
#> GSM613728 2 0.1204 0.8402 0.000 0.944 0.000 0.000 0.000 0.056
#> GSM613729 1 0.1501 0.8425 0.924 0.000 0.000 0.000 0.000 0.076
#> GSM613730 4 0.1493 0.7821 0.000 0.004 0.000 0.936 0.004 0.056
#> GSM613731 4 0.0000 0.8073 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613732 3 0.0260 0.7500 0.000 0.000 0.992 0.000 0.000 0.008
#> GSM613733 3 0.1267 0.7208 0.000 0.060 0.940 0.000 0.000 0.000
#> GSM613734 5 0.4641 0.6464 0.200 0.000 0.000 0.000 0.684 0.116
#> GSM613735 5 0.3925 0.6572 0.200 0.000 0.000 0.000 0.744 0.056
#> GSM613736 3 0.4497 0.3495 0.000 0.028 0.708 0.232 0.028 0.004
#> GSM613737 5 0.0767 0.5698 0.000 0.000 0.004 0.012 0.976 0.008
#> GSM613738 5 0.3858 0.6586 0.196 0.000 0.000 0.032 0.760 0.012
#> GSM613739 5 0.4618 0.6082 0.080 0.000 0.000 0.120 0.748 0.052
#> GSM613740 3 0.0000 0.7516 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613741 5 0.7545 -0.0917 0.220 0.332 0.008 0.008 0.348 0.084
#> GSM613742 5 0.2178 0.5736 0.000 0.000 0.000 0.132 0.868 0.000
#> GSM613743 3 0.0000 0.7516 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613744 3 0.0260 0.7500 0.000 0.000 0.992 0.000 0.000 0.008
#> GSM613745 1 0.5205 0.4555 0.572 0.000 0.000 0.008 0.336 0.084
#> GSM613746 2 0.2696 0.8291 0.000 0.856 0.028 0.000 0.000 0.116
#> GSM613747 5 0.4866 0.6113 0.236 0.000 0.000 0.000 0.648 0.116
#> GSM613748 4 0.0000 0.8073 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613749 1 0.3531 0.6049 0.672 0.000 0.000 0.328 0.000 0.000
#> GSM613750 6 0.3464 0.8976 0.000 0.000 0.312 0.000 0.000 0.688
#> GSM613751 6 0.3879 0.8898 0.000 0.020 0.292 0.000 0.000 0.688
#> GSM613752 6 0.3464 0.8976 0.000 0.000 0.312 0.000 0.000 0.688
#> GSM613753 6 0.4493 0.7546 0.000 0.000 0.160 0.000 0.132 0.708
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) k
#> MAD:pam 101 1.41e-01 2
#> MAD:pam 88 5.57e-03 3
#> MAD:pam 102 8.82e-03 4
#> MAD:pam 97 2.30e-05 5
#> MAD:pam 99 2.37e-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["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 27425 rows and 116 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 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 0.466 0.800 0.867 0.4596 0.529 0.529
#> 3 3 0.358 0.511 0.720 0.2934 0.795 0.629
#> 4 4 0.394 0.424 0.680 0.1696 0.766 0.477
#> 5 5 0.693 0.720 0.844 0.0870 0.858 0.571
#> 6 6 0.832 0.787 0.894 0.0701 0.884 0.560
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
#> GSM613638 2 0.8713 0.7737 0.292 0.708
#> GSM613639 1 0.0376 0.9025 0.996 0.004
#> GSM613640 2 0.8909 0.7693 0.308 0.692
#> GSM613641 1 0.0376 0.9025 0.996 0.004
#> GSM613642 2 0.8909 0.7693 0.308 0.692
#> GSM613643 1 0.0938 0.8983 0.988 0.012
#> GSM613644 1 0.5294 0.8181 0.880 0.120
#> GSM613645 1 0.0376 0.9025 0.996 0.004
#> GSM613646 2 0.5842 0.8316 0.140 0.860
#> GSM613647 2 0.3733 0.8343 0.072 0.928
#> GSM613648 2 0.0000 0.8025 0.000 1.000
#> GSM613649 2 0.0938 0.8097 0.012 0.988
#> GSM613650 2 0.9963 0.0436 0.464 0.536
#> GSM613651 2 0.8909 0.5118 0.308 0.692
#> GSM613652 1 0.8081 0.7113 0.752 0.248
#> GSM613653 2 0.4690 0.8378 0.100 0.900
#> GSM613654 1 0.8081 0.7113 0.752 0.248
#> GSM613655 1 0.0376 0.9025 0.996 0.004
#> GSM613656 1 0.8081 0.7113 0.752 0.248
#> GSM613657 2 0.0000 0.8025 0.000 1.000
#> GSM613658 1 0.0672 0.9008 0.992 0.008
#> GSM613659 2 0.9000 0.7660 0.316 0.684
#> GSM613660 2 0.8955 0.7685 0.312 0.688
#> GSM613661 1 0.0376 0.9025 0.996 0.004
#> GSM613662 2 0.9000 0.7671 0.316 0.684
#> GSM613663 1 0.0376 0.9025 0.996 0.004
#> GSM613664 2 0.8955 0.7685 0.312 0.688
#> GSM613665 2 0.8955 0.7685 0.312 0.688
#> GSM613666 1 0.0376 0.9025 0.996 0.004
#> GSM613667 1 0.0376 0.9025 0.996 0.004
#> GSM613668 1 0.0376 0.9025 0.996 0.004
#> GSM613669 1 0.0376 0.9025 0.996 0.004
#> GSM613670 2 0.9000 0.7671 0.316 0.684
#> GSM613671 1 0.0376 0.9025 0.996 0.004
#> GSM613672 1 0.0938 0.8983 0.988 0.012
#> GSM613673 1 0.0376 0.9025 0.996 0.004
#> GSM613674 2 0.8955 0.7685 0.312 0.688
#> GSM613675 2 0.9000 0.7671 0.316 0.684
#> GSM613676 2 0.8955 0.7685 0.312 0.688
#> GSM613677 2 0.6712 0.8210 0.176 0.824
#> GSM613678 1 0.9922 -0.2679 0.552 0.448
#> GSM613679 2 0.8955 0.7685 0.312 0.688
#> GSM613680 1 0.0376 0.9025 0.996 0.004
#> GSM613681 1 0.0376 0.9025 0.996 0.004
#> GSM613682 1 0.0376 0.9025 0.996 0.004
#> GSM613683 1 0.0376 0.9025 0.996 0.004
#> GSM613684 2 0.8955 0.7685 0.312 0.688
#> GSM613685 2 0.8955 0.7685 0.312 0.688
#> GSM613686 1 0.0376 0.9025 0.996 0.004
#> GSM613687 1 0.0376 0.9025 0.996 0.004
#> GSM613688 2 0.8955 0.7685 0.312 0.688
#> GSM613689 2 0.3584 0.8344 0.068 0.932
#> GSM613690 2 0.3584 0.8344 0.068 0.932
#> GSM613691 2 0.4690 0.8382 0.100 0.900
#> GSM613692 1 0.8081 0.7113 0.752 0.248
#> GSM613693 2 0.4562 0.8382 0.096 0.904
#> GSM613694 2 0.3879 0.8333 0.076 0.924
#> GSM613695 2 0.3733 0.8343 0.072 0.928
#> GSM613696 2 0.4022 0.8362 0.080 0.920
#> GSM613697 2 0.9323 0.4109 0.348 0.652
#> GSM613698 2 0.3733 0.8343 0.072 0.928
#> GSM613699 2 0.3733 0.8343 0.072 0.928
#> GSM613700 2 0.8955 0.7685 0.312 0.688
#> GSM613701 2 0.9000 0.7660 0.316 0.684
#> GSM613702 2 0.9000 0.7660 0.316 0.684
#> GSM613703 1 0.0376 0.9025 0.996 0.004
#> GSM613704 2 0.9000 0.7671 0.316 0.684
#> GSM613705 2 0.3733 0.8343 0.072 0.928
#> GSM613706 2 0.8909 0.7693 0.308 0.692
#> GSM613707 2 0.8955 0.7685 0.312 0.688
#> GSM613708 1 0.0376 0.9025 0.996 0.004
#> GSM613709 1 0.0376 0.9025 0.996 0.004
#> GSM613710 2 0.8955 0.7685 0.312 0.688
#> GSM613711 2 0.0000 0.8025 0.000 1.000
#> GSM613712 2 0.3733 0.8343 0.072 0.928
#> GSM613713 2 0.4161 0.8387 0.084 0.916
#> GSM613714 2 0.3584 0.8344 0.068 0.932
#> GSM613715 2 0.2423 0.8242 0.040 0.960
#> GSM613716 2 0.4022 0.8371 0.080 0.920
#> GSM613717 2 0.0938 0.8094 0.012 0.988
#> GSM613718 2 0.0000 0.8025 0.000 1.000
#> GSM613719 2 0.5178 0.8210 0.116 0.884
#> GSM613720 2 0.4022 0.8371 0.080 0.920
#> GSM613721 2 0.4815 0.8377 0.104 0.896
#> GSM613722 2 0.8955 0.7685 0.312 0.688
#> GSM613723 1 0.8081 0.7113 0.752 0.248
#> GSM613724 1 0.0672 0.9008 0.992 0.008
#> GSM613725 2 0.8955 0.7685 0.312 0.688
#> GSM613726 1 0.0376 0.9025 0.996 0.004
#> GSM613727 1 0.0376 0.9025 0.996 0.004
#> GSM613728 2 0.8955 0.7685 0.312 0.688
#> GSM613729 1 0.0376 0.9025 0.996 0.004
#> GSM613730 2 0.9000 0.7660 0.316 0.684
#> GSM613731 1 0.0672 0.9006 0.992 0.008
#> GSM613732 2 0.0000 0.8025 0.000 1.000
#> GSM613733 2 0.4161 0.8384 0.084 0.916
#> GSM613734 1 0.2603 0.8786 0.956 0.044
#> GSM613735 1 0.8081 0.7113 0.752 0.248
#> GSM613736 2 0.3584 0.8344 0.068 0.932
#> GSM613737 2 0.3733 0.8343 0.072 0.928
#> GSM613738 1 0.8081 0.7113 0.752 0.248
#> GSM613739 1 0.8081 0.7113 0.752 0.248
#> GSM613740 2 0.0000 0.8025 0.000 1.000
#> GSM613741 2 0.4815 0.8377 0.104 0.896
#> GSM613742 1 0.8081 0.7113 0.752 0.248
#> GSM613743 2 0.0000 0.8025 0.000 1.000
#> GSM613744 2 0.0000 0.8025 0.000 1.000
#> GSM613745 2 0.4815 0.8377 0.104 0.896
#> GSM613746 2 0.4690 0.8382 0.100 0.900
#> GSM613747 1 0.8081 0.7113 0.752 0.248
#> GSM613748 2 0.9000 0.7660 0.316 0.684
#> GSM613749 1 0.0376 0.9025 0.996 0.004
#> GSM613750 2 0.3114 0.8309 0.056 0.944
#> GSM613751 2 0.0000 0.8025 0.000 1.000
#> GSM613752 2 0.0000 0.8025 0.000 1.000
#> GSM613753 2 0.3584 0.8344 0.068 0.932
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM613638 3 0.2297 0.4913 0.036 0.020 0.944
#> GSM613639 1 0.7158 0.3298 0.596 0.032 0.372
#> GSM613640 3 0.6742 0.2388 0.240 0.052 0.708
#> GSM613641 1 0.0661 0.7996 0.988 0.008 0.004
#> GSM613642 3 0.8491 -0.3273 0.116 0.312 0.572
#> GSM613643 1 0.7015 0.2820 0.584 0.024 0.392
#> GSM613644 3 0.6813 0.0743 0.468 0.012 0.520
#> GSM613645 1 0.4172 0.7028 0.840 0.004 0.156
#> GSM613646 3 0.7872 0.2427 0.296 0.084 0.620
#> GSM613647 3 0.0237 0.5185 0.004 0.000 0.996
#> GSM613648 3 0.4121 0.4214 0.000 0.168 0.832
#> GSM613649 3 0.5216 0.4355 0.000 0.260 0.740
#> GSM613650 3 0.5986 0.3030 0.284 0.012 0.704
#> GSM613651 3 0.1765 0.5128 0.040 0.004 0.956
#> GSM613652 1 0.9213 0.5653 0.536 0.236 0.228
#> GSM613653 3 0.8172 0.2452 0.272 0.112 0.616
#> GSM613654 1 0.9213 0.5653 0.536 0.236 0.228
#> GSM613655 1 0.0829 0.7996 0.984 0.012 0.004
#> GSM613656 1 0.9213 0.5653 0.536 0.236 0.228
#> GSM613657 3 0.5443 0.4332 0.004 0.260 0.736
#> GSM613658 1 0.1585 0.7963 0.964 0.028 0.008
#> GSM613659 3 0.8985 -0.1365 0.216 0.220 0.564
#> GSM613660 2 0.6962 0.8629 0.020 0.568 0.412
#> GSM613661 1 0.3769 0.7439 0.880 0.016 0.104
#> GSM613662 2 0.7334 0.7677 0.048 0.624 0.328
#> GSM613663 1 0.0829 0.7996 0.984 0.012 0.004
#> GSM613664 2 0.7334 0.7677 0.048 0.624 0.328
#> GSM613665 2 0.7601 0.8479 0.044 0.540 0.416
#> GSM613666 1 0.1399 0.7961 0.968 0.028 0.004
#> GSM613667 1 0.3941 0.7039 0.844 0.000 0.156
#> GSM613668 1 0.0829 0.7996 0.984 0.012 0.004
#> GSM613669 1 0.1267 0.7961 0.972 0.024 0.004
#> GSM613670 2 0.7759 0.4554 0.048 0.480 0.472
#> GSM613671 1 0.1267 0.7961 0.972 0.024 0.004
#> GSM613672 1 0.0829 0.7996 0.984 0.012 0.004
#> GSM613673 1 0.0829 0.7996 0.984 0.012 0.004
#> GSM613674 2 0.6962 0.8629 0.020 0.568 0.412
#> GSM613675 2 0.7334 0.7677 0.048 0.624 0.328
#> GSM613676 2 0.7411 0.8520 0.036 0.548 0.416
#> GSM613677 3 0.8132 -0.0928 0.104 0.284 0.612
#> GSM613678 3 0.9527 -0.0756 0.300 0.220 0.480
#> GSM613679 2 0.6962 0.8629 0.020 0.568 0.412
#> GSM613680 1 0.0829 0.7996 0.984 0.012 0.004
#> GSM613681 1 0.0237 0.7987 0.996 0.000 0.004
#> GSM613682 1 0.0829 0.7996 0.984 0.012 0.004
#> GSM613683 1 0.1267 0.7991 0.972 0.024 0.004
#> GSM613684 2 0.7411 0.8520 0.036 0.548 0.416
#> GSM613685 2 0.6962 0.8629 0.020 0.568 0.412
#> GSM613686 1 0.1170 0.7979 0.976 0.016 0.008
#> GSM613687 1 0.0829 0.7996 0.984 0.012 0.004
#> GSM613688 2 0.7767 0.8402 0.052 0.536 0.412
#> GSM613689 3 0.1878 0.5096 0.004 0.044 0.952
#> GSM613690 3 0.3573 0.4669 0.004 0.120 0.876
#> GSM613691 2 0.6667 0.7282 0.016 0.616 0.368
#> GSM613692 1 0.6793 0.2541 0.536 0.012 0.452
#> GSM613693 3 0.6836 -0.1372 0.016 0.412 0.572
#> GSM613694 3 0.0237 0.5185 0.004 0.000 0.996
#> GSM613695 3 0.0237 0.5185 0.004 0.000 0.996
#> GSM613696 3 0.3030 0.4797 0.004 0.092 0.904
#> GSM613697 3 0.1878 0.5112 0.044 0.004 0.952
#> GSM613698 3 0.3112 0.4769 0.004 0.096 0.900
#> GSM613699 3 0.0475 0.5172 0.004 0.004 0.992
#> GSM613700 2 0.6962 0.8629 0.020 0.568 0.412
#> GSM613701 3 0.8944 -0.1407 0.204 0.228 0.568
#> GSM613702 3 0.8948 -0.1380 0.208 0.224 0.568
#> GSM613703 1 0.6486 0.6266 0.760 0.096 0.144
#> GSM613704 2 0.7334 0.7677 0.048 0.624 0.328
#> GSM613705 3 0.1315 0.5122 0.008 0.020 0.972
#> GSM613706 3 0.7169 0.1474 0.404 0.028 0.568
#> GSM613707 2 0.6962 0.8629 0.020 0.568 0.412
#> GSM613708 1 0.0983 0.7982 0.980 0.016 0.004
#> GSM613709 1 0.0237 0.7987 0.996 0.000 0.004
#> GSM613710 2 0.6962 0.8629 0.020 0.568 0.412
#> GSM613711 3 0.5443 0.4332 0.004 0.260 0.736
#> GSM613712 3 0.0661 0.5170 0.004 0.008 0.988
#> GSM613713 3 0.5291 0.4060 0.000 0.268 0.732
#> GSM613714 3 0.3784 0.4557 0.004 0.132 0.864
#> GSM613715 3 0.4351 0.4224 0.004 0.168 0.828
#> GSM613716 3 0.6543 0.1479 0.016 0.344 0.640
#> GSM613717 3 0.5443 0.4332 0.004 0.260 0.736
#> GSM613718 3 0.5443 0.4332 0.004 0.260 0.736
#> GSM613719 3 0.3459 0.4714 0.012 0.096 0.892
#> GSM613720 3 0.6848 -0.1392 0.016 0.416 0.568
#> GSM613721 3 0.8157 -0.0654 0.096 0.308 0.596
#> GSM613722 2 0.6962 0.8629 0.020 0.568 0.412
#> GSM613723 1 0.9213 0.5653 0.536 0.236 0.228
#> GSM613724 1 0.1399 0.7981 0.968 0.028 0.004
#> GSM613725 2 0.6962 0.8629 0.020 0.568 0.412
#> GSM613726 1 0.4514 0.7036 0.832 0.012 0.156
#> GSM613727 1 0.0983 0.7995 0.980 0.016 0.004
#> GSM613728 2 0.8018 0.8389 0.064 0.520 0.416
#> GSM613729 1 0.1399 0.7961 0.968 0.028 0.004
#> GSM613730 3 0.9442 -0.3126 0.216 0.288 0.496
#> GSM613731 1 0.7015 0.2820 0.584 0.024 0.392
#> GSM613732 3 0.5443 0.4332 0.004 0.260 0.736
#> GSM613733 3 0.6053 0.1848 0.020 0.260 0.720
#> GSM613734 1 0.8957 0.5913 0.564 0.244 0.192
#> GSM613735 1 0.9211 0.5670 0.536 0.240 0.224
#> GSM613736 3 0.4351 0.4224 0.004 0.168 0.828
#> GSM613737 3 0.0475 0.5182 0.004 0.004 0.992
#> GSM613738 1 0.6793 0.2541 0.536 0.012 0.452
#> GSM613739 1 0.9213 0.5653 0.536 0.236 0.228
#> GSM613740 3 0.5443 0.4332 0.004 0.260 0.736
#> GSM613741 3 0.8013 0.2602 0.252 0.112 0.636
#> GSM613742 1 0.6669 0.2308 0.524 0.008 0.468
#> GSM613743 3 0.5443 0.4332 0.004 0.260 0.736
#> GSM613744 3 0.5443 0.4332 0.004 0.260 0.736
#> GSM613745 3 0.7180 0.3085 0.168 0.116 0.716
#> GSM613746 2 0.6737 0.7045 0.016 0.600 0.384
#> GSM613747 1 0.9208 0.5696 0.536 0.244 0.220
#> GSM613748 3 0.8944 -0.1407 0.204 0.228 0.568
#> GSM613749 3 0.9022 0.0545 0.384 0.136 0.480
#> GSM613750 3 0.4351 0.4224 0.004 0.168 0.828
#> GSM613751 3 0.5216 0.4355 0.000 0.260 0.740
#> GSM613752 3 0.5443 0.4332 0.004 0.260 0.736
#> GSM613753 3 0.0983 0.5161 0.004 0.016 0.980
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 3 0.6185 0.3591 0.056 0.208 0.700 0.036
#> GSM613639 1 0.8916 0.1615 0.496 0.124 0.172 0.208
#> GSM613640 3 0.7512 0.1799 0.116 0.272 0.576 0.036
#> GSM613641 1 0.0336 0.7800 0.992 0.000 0.000 0.008
#> GSM613642 2 0.7348 0.2675 0.080 0.524 0.364 0.032
#> GSM613643 1 0.8012 0.1146 0.480 0.136 0.348 0.036
#> GSM613644 3 0.8602 -0.0491 0.368 0.136 0.424 0.072
#> GSM613645 1 0.3821 0.6804 0.840 0.000 0.120 0.040
#> GSM613646 3 0.9068 -0.3392 0.128 0.124 0.388 0.360
#> GSM613647 3 0.5436 0.4267 0.040 0.136 0.772 0.052
#> GSM613648 3 0.3333 0.5133 0.000 0.088 0.872 0.040
#> GSM613649 3 0.4093 0.5023 0.000 0.072 0.832 0.096
#> GSM613650 3 0.8590 -0.0770 0.108 0.124 0.512 0.256
#> GSM613651 3 0.7572 0.2556 0.092 0.064 0.596 0.248
#> GSM613652 3 0.7902 0.0575 0.328 0.000 0.368 0.304
#> GSM613653 4 0.7020 0.3982 0.000 0.124 0.376 0.500
#> GSM613654 3 0.7902 0.0575 0.328 0.000 0.368 0.304
#> GSM613655 1 0.0469 0.7819 0.988 0.012 0.000 0.000
#> GSM613656 3 0.7902 0.0575 0.328 0.000 0.368 0.304
#> GSM613657 3 0.4332 0.4983 0.000 0.072 0.816 0.112
#> GSM613658 1 0.3801 0.5708 0.780 0.000 0.000 0.220
#> GSM613659 1 0.9875 -0.3182 0.300 0.292 0.196 0.212
#> GSM613660 2 0.0336 0.6533 0.000 0.992 0.008 0.000
#> GSM613661 1 0.3089 0.7397 0.896 0.008 0.052 0.044
#> GSM613662 2 0.7444 0.4435 0.032 0.544 0.096 0.328
#> GSM613663 1 0.0469 0.7819 0.988 0.012 0.000 0.000
#> GSM613664 2 0.7080 0.4506 0.016 0.560 0.096 0.328
#> GSM613665 2 0.3110 0.6481 0.004 0.892 0.056 0.048
#> GSM613666 1 0.0336 0.7800 0.992 0.000 0.000 0.008
#> GSM613667 1 0.3198 0.7179 0.880 0.000 0.080 0.040
#> GSM613668 1 0.0469 0.7819 0.988 0.012 0.000 0.000
#> GSM613669 1 0.0336 0.7800 0.992 0.000 0.000 0.008
#> GSM613670 2 0.9342 0.2750 0.228 0.348 0.096 0.328
#> GSM613671 1 0.0336 0.7800 0.992 0.000 0.000 0.008
#> GSM613672 1 0.0469 0.7819 0.988 0.012 0.000 0.000
#> GSM613673 1 0.0469 0.7819 0.988 0.012 0.000 0.000
#> GSM613674 2 0.0000 0.6530 0.000 1.000 0.000 0.000
#> GSM613675 2 0.7080 0.4506 0.016 0.560 0.096 0.328
#> GSM613676 2 0.3914 0.6314 0.008 0.848 0.104 0.040
#> GSM613677 3 0.6842 0.3671 0.028 0.288 0.612 0.072
#> GSM613678 1 0.7841 0.3095 0.584 0.168 0.196 0.052
#> GSM613679 2 0.0000 0.6530 0.000 1.000 0.000 0.000
#> GSM613680 1 0.0469 0.7819 0.988 0.012 0.000 0.000
#> GSM613681 1 0.0336 0.7800 0.992 0.000 0.000 0.008
#> GSM613682 1 0.0469 0.7819 0.988 0.012 0.000 0.000
#> GSM613683 1 0.0469 0.7819 0.988 0.012 0.000 0.000
#> GSM613684 2 0.4939 0.5819 0.020 0.768 0.188 0.024
#> GSM613685 2 0.0000 0.6530 0.000 1.000 0.000 0.000
#> GSM613686 1 0.0895 0.7773 0.976 0.000 0.004 0.020
#> GSM613687 1 0.0469 0.7819 0.988 0.012 0.000 0.000
#> GSM613688 2 0.7364 0.5019 0.200 0.624 0.132 0.044
#> GSM613689 3 0.5437 0.4458 0.020 0.244 0.712 0.024
#> GSM613690 3 0.2408 0.5057 0.000 0.104 0.896 0.000
#> GSM613691 4 0.6952 -0.1163 0.000 0.364 0.120 0.516
#> GSM613692 4 0.8378 0.2376 0.316 0.040 0.184 0.460
#> GSM613693 4 0.7902 0.1530 0.000 0.336 0.300 0.364
#> GSM613694 3 0.5827 0.3957 0.060 0.164 0.740 0.036
#> GSM613695 3 0.3762 0.4696 0.024 0.072 0.868 0.036
#> GSM613696 3 0.7555 -0.0547 0.028 0.124 0.552 0.296
#> GSM613697 3 0.7345 0.2637 0.080 0.056 0.604 0.260
#> GSM613698 3 0.7515 -0.1262 0.024 0.112 0.520 0.344
#> GSM613699 3 0.5161 0.4179 0.028 0.124 0.788 0.060
#> GSM613700 2 0.0000 0.6530 0.000 1.000 0.000 0.000
#> GSM613701 2 0.8117 0.3562 0.264 0.508 0.196 0.032
#> GSM613702 2 0.8176 0.3565 0.260 0.508 0.196 0.036
#> GSM613703 1 0.6152 0.4346 0.668 0.120 0.000 0.212
#> GSM613704 2 0.7080 0.4506 0.016 0.560 0.096 0.328
#> GSM613705 3 0.5458 0.3961 0.028 0.192 0.744 0.036
#> GSM613706 1 0.8491 -0.0891 0.420 0.336 0.208 0.036
#> GSM613707 2 0.0000 0.6530 0.000 1.000 0.000 0.000
#> GSM613708 1 0.2921 0.6772 0.860 0.000 0.000 0.140
#> GSM613709 1 0.0336 0.7800 0.992 0.000 0.000 0.008
#> GSM613710 2 0.1022 0.6452 0.000 0.968 0.032 0.000
#> GSM613711 3 0.4332 0.4983 0.000 0.072 0.816 0.112
#> GSM613712 3 0.5008 0.4263 0.028 0.124 0.796 0.052
#> GSM613713 3 0.6031 0.4883 0.000 0.216 0.676 0.108
#> GSM613714 3 0.4706 0.4574 0.020 0.248 0.732 0.000
#> GSM613715 3 0.3043 0.5117 0.004 0.112 0.876 0.008
#> GSM613716 3 0.7206 -0.2507 0.000 0.140 0.460 0.400
#> GSM613717 3 0.5798 0.5027 0.000 0.184 0.704 0.112
#> GSM613718 3 0.4332 0.4983 0.000 0.072 0.816 0.112
#> GSM613719 3 0.7584 -0.1854 0.020 0.124 0.500 0.356
#> GSM613720 4 0.7530 0.3293 0.000 0.212 0.308 0.480
#> GSM613721 4 0.7193 0.4021 0.000 0.152 0.340 0.508
#> GSM613722 2 0.0804 0.6560 0.008 0.980 0.012 0.000
#> GSM613723 3 0.7902 0.0575 0.328 0.000 0.368 0.304
#> GSM613724 1 0.3113 0.7030 0.876 0.012 0.004 0.108
#> GSM613725 2 0.0188 0.6522 0.000 0.996 0.004 0.000
#> GSM613726 1 0.4028 0.6945 0.848 0.020 0.100 0.032
#> GSM613727 1 0.0469 0.7819 0.988 0.012 0.000 0.000
#> GSM613728 2 0.4108 0.6323 0.012 0.844 0.092 0.052
#> GSM613729 1 0.0336 0.7800 0.992 0.000 0.000 0.008
#> GSM613730 2 0.8346 0.4159 0.260 0.516 0.164 0.060
#> GSM613731 1 0.7038 0.4222 0.652 0.136 0.176 0.036
#> GSM613732 3 0.4332 0.4983 0.000 0.072 0.816 0.112
#> GSM613733 2 0.6396 -0.1699 0.000 0.468 0.468 0.064
#> GSM613734 1 0.8279 -0.1602 0.360 0.012 0.328 0.300
#> GSM613735 4 0.7191 0.1988 0.328 0.000 0.156 0.516
#> GSM613736 3 0.5091 0.5078 0.000 0.180 0.752 0.068
#> GSM613737 3 0.4906 0.4465 0.028 0.096 0.808 0.068
#> GSM613738 4 0.7862 0.2276 0.328 0.016 0.176 0.480
#> GSM613739 3 0.7902 0.0575 0.328 0.000 0.368 0.304
#> GSM613740 3 0.4332 0.4983 0.000 0.072 0.816 0.112
#> GSM613741 4 0.7020 0.3982 0.000 0.124 0.376 0.500
#> GSM613742 4 0.8235 0.2242 0.260 0.028 0.232 0.480
#> GSM613743 3 0.4332 0.4983 0.000 0.072 0.816 0.112
#> GSM613744 3 0.4332 0.4983 0.000 0.072 0.816 0.112
#> GSM613745 4 0.7049 0.3764 0.000 0.124 0.392 0.484
#> GSM613746 2 0.7641 0.1843 0.000 0.452 0.224 0.324
#> GSM613747 3 0.7908 0.0474 0.336 0.000 0.360 0.304
#> GSM613748 2 0.8177 0.3462 0.260 0.500 0.208 0.032
#> GSM613749 1 0.7419 0.3737 0.620 0.140 0.196 0.044
#> GSM613750 3 0.3117 0.5141 0.000 0.092 0.880 0.028
#> GSM613751 3 0.4332 0.4983 0.000 0.072 0.816 0.112
#> GSM613752 3 0.4332 0.4983 0.000 0.072 0.816 0.112
#> GSM613753 3 0.2882 0.4987 0.024 0.084 0.892 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM613638 3 0.1533 0.728 0.004 0.016 0.952 0.004 0.024
#> GSM613639 1 0.4153 0.628 0.756 0.000 0.212 0.008 0.024
#> GSM613640 2 0.5305 0.251 0.008 0.484 0.480 0.004 0.024
#> GSM613641 1 0.0000 0.887 1.000 0.000 0.000 0.000 0.000
#> GSM613642 2 0.4304 0.661 0.000 0.736 0.232 0.008 0.024
#> GSM613643 1 0.4935 0.493 0.668 0.016 0.288 0.000 0.028
#> GSM613644 1 0.4853 0.483 0.664 0.008 0.296 0.000 0.032
#> GSM613645 1 0.2444 0.837 0.912 0.000 0.036 0.028 0.024
#> GSM613646 4 0.6891 0.656 0.184 0.000 0.296 0.496 0.024
#> GSM613647 3 0.2605 0.642 0.000 0.000 0.852 0.000 0.148
#> GSM613648 3 0.1943 0.747 0.000 0.000 0.924 0.056 0.020
#> GSM613649 3 0.4181 0.689 0.000 0.000 0.712 0.268 0.020
#> GSM613650 3 0.5678 0.264 0.128 0.000 0.612 0.000 0.260
#> GSM613651 5 0.3796 0.538 0.000 0.000 0.300 0.000 0.700
#> GSM613652 5 0.1121 0.812 0.044 0.000 0.000 0.000 0.956
#> GSM613653 4 0.4425 0.861 0.000 0.000 0.296 0.680 0.024
#> GSM613654 5 0.1121 0.812 0.044 0.000 0.000 0.000 0.956
#> GSM613655 1 0.0000 0.887 1.000 0.000 0.000 0.000 0.000
#> GSM613656 5 0.1121 0.812 0.044 0.000 0.000 0.000 0.956
#> GSM613657 3 0.4181 0.689 0.000 0.000 0.712 0.268 0.020
#> GSM613658 1 0.0000 0.887 1.000 0.000 0.000 0.000 0.000
#> GSM613659 4 0.5857 0.851 0.000 0.096 0.240 0.640 0.024
#> GSM613660 2 0.0000 0.788 0.000 1.000 0.000 0.000 0.000
#> GSM613661 1 0.0992 0.870 0.968 0.000 0.008 0.000 0.024
#> GSM613662 4 0.4803 0.853 0.000 0.096 0.184 0.720 0.000
#> GSM613663 1 0.0000 0.887 1.000 0.000 0.000 0.000 0.000
#> GSM613664 4 0.5251 0.818 0.000 0.136 0.184 0.680 0.000
#> GSM613665 2 0.0912 0.786 0.000 0.972 0.016 0.012 0.000
#> GSM613666 1 0.0000 0.887 1.000 0.000 0.000 0.000 0.000
#> GSM613667 1 0.0992 0.869 0.968 0.000 0.008 0.000 0.024
#> GSM613668 1 0.0000 0.887 1.000 0.000 0.000 0.000 0.000
#> GSM613669 1 0.0000 0.887 1.000 0.000 0.000 0.000 0.000
#> GSM613670 4 0.4725 0.865 0.000 0.080 0.200 0.720 0.000
#> GSM613671 1 0.0000 0.887 1.000 0.000 0.000 0.000 0.000
#> GSM613672 1 0.0000 0.887 1.000 0.000 0.000 0.000 0.000
#> GSM613673 1 0.0000 0.887 1.000 0.000 0.000 0.000 0.000
#> GSM613674 2 0.0000 0.788 0.000 1.000 0.000 0.000 0.000
#> GSM613675 4 0.4803 0.853 0.000 0.096 0.184 0.720 0.000
#> GSM613676 2 0.1956 0.773 0.000 0.916 0.076 0.008 0.000
#> GSM613677 3 0.1377 0.732 0.000 0.020 0.956 0.004 0.020
#> GSM613678 1 0.7478 0.244 0.548 0.064 0.228 0.136 0.024
#> GSM613679 2 0.0000 0.788 0.000 1.000 0.000 0.000 0.000
#> GSM613680 1 0.0000 0.887 1.000 0.000 0.000 0.000 0.000
#> GSM613681 1 0.0000 0.887 1.000 0.000 0.000 0.000 0.000
#> GSM613682 1 0.0000 0.887 1.000 0.000 0.000 0.000 0.000
#> GSM613683 1 0.0000 0.887 1.000 0.000 0.000 0.000 0.000
#> GSM613684 2 0.3757 0.701 0.000 0.772 0.208 0.020 0.000
#> GSM613685 2 0.0000 0.788 0.000 1.000 0.000 0.000 0.000
#> GSM613686 1 0.0404 0.881 0.988 0.000 0.000 0.000 0.012
#> GSM613687 1 0.0000 0.887 1.000 0.000 0.000 0.000 0.000
#> GSM613688 2 0.4301 0.687 0.000 0.756 0.204 0.020 0.020
#> GSM613689 3 0.0404 0.743 0.000 0.000 0.988 0.000 0.012
#> GSM613690 3 0.0000 0.746 0.000 0.000 1.000 0.000 0.000
#> GSM613691 4 0.4106 0.876 0.000 0.020 0.256 0.724 0.000
#> GSM613692 5 0.4689 0.618 0.048 0.000 0.264 0.000 0.688
#> GSM613693 3 0.4641 -0.410 0.000 0.012 0.532 0.456 0.000
#> GSM613694 3 0.1121 0.734 0.000 0.000 0.956 0.000 0.044
#> GSM613695 3 0.0703 0.739 0.000 0.000 0.976 0.000 0.024
#> GSM613696 3 0.1195 0.734 0.000 0.000 0.960 0.012 0.028
#> GSM613697 5 0.3774 0.542 0.000 0.000 0.296 0.000 0.704
#> GSM613698 3 0.2248 0.693 0.000 0.000 0.900 0.012 0.088
#> GSM613699 3 0.0963 0.737 0.000 0.000 0.964 0.000 0.036
#> GSM613700 2 0.0000 0.788 0.000 1.000 0.000 0.000 0.000
#> GSM613701 2 0.4089 0.691 0.000 0.764 0.204 0.008 0.024
#> GSM613702 2 0.4089 0.691 0.000 0.764 0.204 0.008 0.024
#> GSM613703 1 0.6368 -0.219 0.436 0.000 0.164 0.400 0.000
#> GSM613704 4 0.4803 0.853 0.000 0.096 0.184 0.720 0.000
#> GSM613705 3 0.1043 0.735 0.000 0.000 0.960 0.000 0.040
#> GSM613706 2 0.5679 0.538 0.056 0.640 0.276 0.004 0.024
#> GSM613707 2 0.0000 0.788 0.000 1.000 0.000 0.000 0.000
#> GSM613708 1 0.0000 0.887 1.000 0.000 0.000 0.000 0.000
#> GSM613709 1 0.0000 0.887 1.000 0.000 0.000 0.000 0.000
#> GSM613710 2 0.0000 0.788 0.000 1.000 0.000 0.000 0.000
#> GSM613711 3 0.4181 0.689 0.000 0.000 0.712 0.268 0.020
#> GSM613712 3 0.1043 0.735 0.000 0.000 0.960 0.000 0.040
#> GSM613713 3 0.3416 0.730 0.000 0.016 0.840 0.124 0.020
#> GSM613714 3 0.0000 0.746 0.000 0.000 1.000 0.000 0.000
#> GSM613715 3 0.0000 0.746 0.000 0.000 1.000 0.000 0.000
#> GSM613716 3 0.2890 0.566 0.000 0.000 0.836 0.160 0.004
#> GSM613717 3 0.4181 0.689 0.000 0.000 0.712 0.268 0.020
#> GSM613718 3 0.4181 0.689 0.000 0.000 0.712 0.268 0.020
#> GSM613719 3 0.5726 0.184 0.000 0.000 0.612 0.140 0.248
#> GSM613720 3 0.3752 0.247 0.000 0.000 0.708 0.292 0.000
#> GSM613721 4 0.4737 0.869 0.000 0.012 0.284 0.680 0.024
#> GSM613722 2 0.0000 0.788 0.000 1.000 0.000 0.000 0.000
#> GSM613723 5 0.1121 0.812 0.044 0.000 0.000 0.000 0.956
#> GSM613724 1 0.0000 0.887 1.000 0.000 0.000 0.000 0.000
#> GSM613725 2 0.0000 0.788 0.000 1.000 0.000 0.000 0.000
#> GSM613726 1 0.2300 0.819 0.904 0.000 0.072 0.000 0.024
#> GSM613727 1 0.0000 0.887 1.000 0.000 0.000 0.000 0.000
#> GSM613728 2 0.4133 0.659 0.000 0.768 0.052 0.180 0.000
#> GSM613729 1 0.0000 0.887 1.000 0.000 0.000 0.000 0.000
#> GSM613730 2 0.5858 0.501 0.000 0.632 0.204 0.156 0.008
#> GSM613731 1 0.4743 0.531 0.692 0.016 0.268 0.000 0.024
#> GSM613732 3 0.4181 0.689 0.000 0.000 0.712 0.268 0.020
#> GSM613733 3 0.3904 0.684 0.000 0.116 0.820 0.044 0.020
#> GSM613734 5 0.1544 0.793 0.068 0.000 0.000 0.000 0.932
#> GSM613735 5 0.1121 0.812 0.044 0.000 0.000 0.000 0.956
#> GSM613736 3 0.3621 0.715 0.000 0.000 0.788 0.192 0.020
#> GSM613737 3 0.1043 0.736 0.000 0.000 0.960 0.000 0.040
#> GSM613738 5 0.4689 0.618 0.048 0.000 0.264 0.000 0.688
#> GSM613739 5 0.1121 0.812 0.044 0.000 0.000 0.000 0.956
#> GSM613740 3 0.4181 0.689 0.000 0.000 0.712 0.268 0.020
#> GSM613741 4 0.4425 0.861 0.000 0.000 0.296 0.680 0.024
#> GSM613742 5 0.4268 0.592 0.024 0.000 0.268 0.000 0.708
#> GSM613743 3 0.4181 0.689 0.000 0.000 0.712 0.268 0.020
#> GSM613744 3 0.4181 0.689 0.000 0.000 0.712 0.268 0.020
#> GSM613745 4 0.4465 0.855 0.000 0.000 0.304 0.672 0.024
#> GSM613746 4 0.3967 0.873 0.000 0.012 0.264 0.724 0.000
#> GSM613747 5 0.1121 0.812 0.044 0.000 0.000 0.000 0.956
#> GSM613748 2 0.4388 0.642 0.000 0.724 0.244 0.008 0.024
#> GSM613749 1 0.5115 0.584 0.716 0.048 0.208 0.004 0.024
#> GSM613750 3 0.1568 0.749 0.000 0.000 0.944 0.036 0.020
#> GSM613751 3 0.4181 0.689 0.000 0.000 0.712 0.268 0.020
#> GSM613752 3 0.4181 0.689 0.000 0.000 0.712 0.268 0.020
#> GSM613753 3 0.0000 0.746 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
#> GSM613638 4 0.0363 0.78603 0.000 0.012 0.000 0.988 0.000 0.000
#> GSM613639 1 0.4698 0.51699 0.648 0.000 0.000 0.296 0.028 0.028
#> GSM613640 4 0.0363 0.78603 0.000 0.012 0.000 0.988 0.000 0.000
#> GSM613641 1 0.0632 0.91276 0.976 0.000 0.000 0.000 0.024 0.000
#> GSM613642 2 0.4083 0.22985 0.000 0.532 0.000 0.460 0.000 0.008
#> GSM613643 4 0.0363 0.78603 0.000 0.012 0.000 0.988 0.000 0.000
#> GSM613644 4 0.1003 0.78171 0.000 0.004 0.000 0.964 0.028 0.004
#> GSM613645 1 0.3276 0.82334 0.840 0.000 0.000 0.100 0.028 0.032
#> GSM613646 4 0.1492 0.76026 0.000 0.000 0.000 0.940 0.024 0.036
#> GSM613647 4 0.0508 0.78822 0.000 0.000 0.004 0.984 0.012 0.000
#> GSM613648 3 0.0520 0.95828 0.000 0.000 0.984 0.008 0.000 0.008
#> GSM613649 3 0.0146 0.96220 0.000 0.000 0.996 0.000 0.000 0.004
#> GSM613650 4 0.0713 0.78278 0.000 0.000 0.000 0.972 0.028 0.000
#> GSM613651 4 0.2902 0.72872 0.000 0.000 0.004 0.800 0.196 0.000
#> GSM613652 5 0.1341 0.95928 0.028 0.000 0.000 0.024 0.948 0.000
#> GSM613653 6 0.4263 0.40579 0.000 0.000 0.000 0.376 0.024 0.600
#> GSM613654 5 0.1341 0.95928 0.028 0.000 0.000 0.024 0.948 0.000
#> GSM613655 1 0.0146 0.91441 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM613656 5 0.1341 0.95928 0.028 0.000 0.000 0.024 0.948 0.000
#> GSM613657 3 0.0000 0.96294 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613658 1 0.0777 0.90643 0.972 0.000 0.000 0.024 0.004 0.000
#> GSM613659 6 0.4042 0.50702 0.000 0.016 0.000 0.316 0.004 0.664
#> GSM613660 2 0.0000 0.84609 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613661 1 0.2266 0.88349 0.908 0.000 0.000 0.040 0.028 0.024
#> GSM613662 6 0.0260 0.76103 0.000 0.000 0.000 0.008 0.000 0.992
#> GSM613663 1 0.0291 0.91438 0.992 0.000 0.000 0.000 0.004 0.004
#> GSM613664 6 0.1524 0.72194 0.000 0.060 0.000 0.008 0.000 0.932
#> GSM613665 2 0.0937 0.83507 0.000 0.960 0.000 0.000 0.000 0.040
#> GSM613666 1 0.0777 0.91266 0.972 0.000 0.000 0.000 0.024 0.004
#> GSM613667 1 0.2351 0.88681 0.904 0.000 0.000 0.032 0.028 0.036
#> GSM613668 1 0.0291 0.91438 0.992 0.000 0.000 0.000 0.004 0.004
#> GSM613669 1 0.0777 0.91266 0.972 0.000 0.000 0.000 0.024 0.004
#> GSM613670 6 0.0260 0.76103 0.000 0.000 0.000 0.008 0.000 0.992
#> GSM613671 1 0.0777 0.91266 0.972 0.000 0.000 0.000 0.024 0.004
#> GSM613672 1 0.0291 0.91438 0.992 0.000 0.000 0.000 0.004 0.004
#> GSM613673 1 0.0976 0.91156 0.968 0.000 0.000 0.016 0.008 0.008
#> GSM613674 2 0.0000 0.84609 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613675 6 0.0260 0.76103 0.000 0.000 0.000 0.008 0.000 0.992
#> GSM613676 2 0.0937 0.83507 0.000 0.960 0.000 0.000 0.000 0.040
#> GSM613677 4 0.2393 0.73407 0.000 0.064 0.004 0.892 0.000 0.040
#> GSM613678 1 0.5081 0.37738 0.584 0.000 0.000 0.348 0.028 0.040
#> GSM613679 2 0.0000 0.84609 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613680 1 0.0291 0.91438 0.992 0.000 0.000 0.000 0.004 0.004
#> GSM613681 1 0.0777 0.91266 0.972 0.000 0.000 0.000 0.024 0.004
#> GSM613682 1 0.0976 0.91156 0.968 0.000 0.000 0.016 0.008 0.008
#> GSM613683 1 0.0291 0.91438 0.992 0.000 0.000 0.000 0.004 0.004
#> GSM613684 2 0.2556 0.80009 0.000 0.888 0.052 0.012 0.000 0.048
#> GSM613685 2 0.0000 0.84609 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613686 1 0.2045 0.89268 0.920 0.000 0.000 0.024 0.028 0.028
#> GSM613687 1 0.0551 0.91407 0.984 0.000 0.000 0.004 0.004 0.008
#> GSM613688 2 0.4243 0.68992 0.000 0.732 0.000 0.104 0.000 0.164
#> GSM613689 3 0.2778 0.77793 0.000 0.000 0.824 0.168 0.000 0.008
#> GSM613690 3 0.1643 0.92018 0.000 0.000 0.924 0.068 0.000 0.008
#> GSM613691 6 0.0547 0.76021 0.000 0.000 0.000 0.020 0.000 0.980
#> GSM613692 4 0.5034 0.48406 0.132 0.000 0.000 0.628 0.240 0.000
#> GSM613693 6 0.4333 0.07500 0.000 0.000 0.468 0.020 0.000 0.512
#> GSM613694 4 0.0405 0.78763 0.000 0.000 0.004 0.988 0.008 0.000
#> GSM613695 4 0.2994 0.66358 0.000 0.000 0.208 0.788 0.000 0.004
#> GSM613696 4 0.3546 0.70815 0.000 0.000 0.076 0.808 0.004 0.112
#> GSM613697 4 0.2902 0.72872 0.000 0.000 0.004 0.800 0.196 0.000
#> GSM613698 4 0.2805 0.73344 0.000 0.000 0.004 0.812 0.184 0.000
#> GSM613699 4 0.0405 0.78718 0.000 0.000 0.008 0.988 0.004 0.000
#> GSM613700 2 0.0000 0.84609 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613701 2 0.4230 0.47695 0.000 0.648 0.000 0.324 0.004 0.024
#> GSM613702 2 0.4115 0.59060 0.000 0.696 0.000 0.268 0.004 0.032
#> GSM613703 1 0.2125 0.89015 0.916 0.000 0.000 0.028 0.028 0.028
#> GSM613704 6 0.0260 0.76103 0.000 0.000 0.000 0.008 0.000 0.992
#> GSM613705 4 0.0405 0.78763 0.000 0.000 0.004 0.988 0.008 0.000
#> GSM613706 4 0.3774 0.09079 0.000 0.408 0.000 0.592 0.000 0.000
#> GSM613707 2 0.0000 0.84609 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613708 1 0.1036 0.90971 0.964 0.000 0.000 0.008 0.004 0.024
#> GSM613709 1 0.0777 0.91266 0.972 0.000 0.000 0.000 0.024 0.004
#> GSM613710 2 0.0000 0.84609 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613711 3 0.0000 0.96294 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613712 4 0.3014 0.68732 0.000 0.000 0.184 0.804 0.012 0.000
#> GSM613713 3 0.0000 0.96294 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613714 3 0.1918 0.90069 0.000 0.000 0.904 0.088 0.000 0.008
#> GSM613715 3 0.1265 0.93753 0.000 0.000 0.948 0.044 0.000 0.008
#> GSM613716 4 0.5037 0.50960 0.000 0.000 0.188 0.640 0.000 0.172
#> GSM613717 3 0.0000 0.96294 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613718 3 0.0000 0.96294 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613719 4 0.3403 0.72283 0.000 0.000 0.000 0.768 0.212 0.020
#> GSM613720 3 0.1983 0.90047 0.000 0.000 0.908 0.020 0.000 0.072
#> GSM613721 6 0.3789 0.59792 0.000 0.000 0.000 0.260 0.024 0.716
#> GSM613722 2 0.0260 0.84469 0.000 0.992 0.000 0.000 0.000 0.008
#> GSM613723 5 0.1341 0.95928 0.028 0.000 0.000 0.024 0.948 0.000
#> GSM613724 1 0.0146 0.91441 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM613725 2 0.0146 0.84566 0.000 0.996 0.000 0.000 0.000 0.004
#> GSM613726 1 0.3240 0.78338 0.820 0.000 0.000 0.144 0.028 0.008
#> GSM613727 1 0.0146 0.91441 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM613728 2 0.2838 0.73913 0.000 0.808 0.000 0.004 0.000 0.188
#> GSM613729 1 0.0777 0.91266 0.972 0.000 0.000 0.000 0.024 0.004
#> GSM613730 2 0.5672 0.44385 0.000 0.512 0.000 0.304 0.000 0.184
#> GSM613731 4 0.4300 -0.00122 0.456 0.012 0.000 0.528 0.004 0.000
#> GSM613732 3 0.0000 0.96294 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613733 3 0.0260 0.96087 0.000 0.000 0.992 0.008 0.000 0.000
#> GSM613734 5 0.1492 0.95108 0.036 0.000 0.000 0.024 0.940 0.000
#> GSM613735 5 0.1341 0.95928 0.028 0.000 0.000 0.024 0.948 0.000
#> GSM613736 3 0.0520 0.95828 0.000 0.000 0.984 0.008 0.000 0.008
#> GSM613737 4 0.3247 0.74481 0.000 0.000 0.036 0.808 0.156 0.000
#> GSM613738 5 0.4691 0.63580 0.108 0.000 0.000 0.220 0.672 0.000
#> GSM613739 5 0.1341 0.95928 0.028 0.000 0.000 0.024 0.948 0.000
#> GSM613740 3 0.0000 0.96294 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613741 6 0.4251 0.46138 0.000 0.000 0.000 0.348 0.028 0.624
#> GSM613742 4 0.3470 0.70158 0.028 0.000 0.000 0.772 0.200 0.000
#> GSM613743 3 0.0000 0.96294 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613744 3 0.0000 0.96294 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613745 4 0.2333 0.73630 0.000 0.000 0.000 0.884 0.024 0.092
#> GSM613746 6 0.0547 0.76021 0.000 0.000 0.000 0.020 0.000 0.980
#> GSM613747 5 0.1341 0.95928 0.028 0.000 0.000 0.024 0.948 0.000
#> GSM613748 4 0.4417 0.00625 0.000 0.416 0.000 0.556 0.000 0.028
#> GSM613749 1 0.4643 0.50906 0.648 0.000 0.000 0.300 0.028 0.024
#> GSM613750 3 0.1049 0.94600 0.000 0.000 0.960 0.032 0.000 0.008
#> GSM613751 3 0.0146 0.96220 0.000 0.000 0.996 0.000 0.000 0.004
#> GSM613752 3 0.0000 0.96294 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613753 3 0.1701 0.91690 0.000 0.000 0.920 0.072 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) k
#> MAD:mclust 113 0.086411 2
#> MAD:mclust 65 0.542675 3
#> MAD:mclust 46 0.137276 4
#> MAD:mclust 107 0.093447 5
#> MAD:mclust 105 0.000444 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 27425 rows and 116 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 0.844 0.919 0.965 0.4989 0.499 0.499
#> 3 3 0.677 0.775 0.902 0.3070 0.752 0.547
#> 4 4 0.690 0.752 0.873 0.1163 0.859 0.628
#> 5 5 0.593 0.599 0.780 0.0746 0.877 0.601
#> 6 6 0.594 0.448 0.607 0.0415 0.951 0.791
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
#> GSM613638 2 0.7815 0.70505 0.232 0.768
#> GSM613639 1 0.0000 0.96509 1.000 0.000
#> GSM613640 2 0.4939 0.86828 0.108 0.892
#> GSM613641 1 0.0000 0.96509 1.000 0.000
#> GSM613642 2 0.0000 0.95969 0.000 1.000
#> GSM613643 1 0.0000 0.96509 1.000 0.000
#> GSM613644 1 0.0000 0.96509 1.000 0.000
#> GSM613645 1 0.0000 0.96509 1.000 0.000
#> GSM613646 1 0.6438 0.80445 0.836 0.164
#> GSM613647 1 0.9998 0.00846 0.508 0.492
#> GSM613648 2 0.0000 0.95969 0.000 1.000
#> GSM613649 2 0.0000 0.95969 0.000 1.000
#> GSM613650 1 0.0000 0.96509 1.000 0.000
#> GSM613651 1 0.6801 0.78405 0.820 0.180
#> GSM613652 1 0.0000 0.96509 1.000 0.000
#> GSM613653 1 0.4562 0.88124 0.904 0.096
#> GSM613654 1 0.0000 0.96509 1.000 0.000
#> GSM613655 1 0.0000 0.96509 1.000 0.000
#> GSM613656 1 0.0000 0.96509 1.000 0.000
#> GSM613657 2 0.0000 0.95969 0.000 1.000
#> GSM613658 1 0.0000 0.96509 1.000 0.000
#> GSM613659 2 0.0000 0.95969 0.000 1.000
#> GSM613660 2 0.0000 0.95969 0.000 1.000
#> GSM613661 1 0.0000 0.96509 1.000 0.000
#> GSM613662 2 0.0000 0.95969 0.000 1.000
#> GSM613663 1 0.0000 0.96509 1.000 0.000
#> GSM613664 2 0.0000 0.95969 0.000 1.000
#> GSM613665 2 0.0000 0.95969 0.000 1.000
#> GSM613666 1 0.0000 0.96509 1.000 0.000
#> GSM613667 1 0.0000 0.96509 1.000 0.000
#> GSM613668 1 0.0000 0.96509 1.000 0.000
#> GSM613669 1 0.0000 0.96509 1.000 0.000
#> GSM613670 2 0.8207 0.65745 0.256 0.744
#> GSM613671 1 0.0000 0.96509 1.000 0.000
#> GSM613672 1 0.0000 0.96509 1.000 0.000
#> GSM613673 1 0.0000 0.96509 1.000 0.000
#> GSM613674 2 0.0000 0.95969 0.000 1.000
#> GSM613675 2 0.0000 0.95969 0.000 1.000
#> GSM613676 2 0.0000 0.95969 0.000 1.000
#> GSM613677 2 0.0000 0.95969 0.000 1.000
#> GSM613678 1 0.0000 0.96509 1.000 0.000
#> GSM613679 2 0.0000 0.95969 0.000 1.000
#> GSM613680 1 0.0000 0.96509 1.000 0.000
#> GSM613681 1 0.0000 0.96509 1.000 0.000
#> GSM613682 1 0.0000 0.96509 1.000 0.000
#> GSM613683 1 0.0000 0.96509 1.000 0.000
#> GSM613684 2 0.0000 0.95969 0.000 1.000
#> GSM613685 2 0.0000 0.95969 0.000 1.000
#> GSM613686 1 0.0000 0.96509 1.000 0.000
#> GSM613687 1 0.0000 0.96509 1.000 0.000
#> GSM613688 2 0.0000 0.95969 0.000 1.000
#> GSM613689 2 0.0000 0.95969 0.000 1.000
#> GSM613690 2 0.0000 0.95969 0.000 1.000
#> GSM613691 2 0.0000 0.95969 0.000 1.000
#> GSM613692 1 0.0000 0.96509 1.000 0.000
#> GSM613693 2 0.0000 0.95969 0.000 1.000
#> GSM613694 1 0.8207 0.66250 0.744 0.256
#> GSM613695 2 0.0000 0.95969 0.000 1.000
#> GSM613696 2 0.1633 0.94164 0.024 0.976
#> GSM613697 1 0.6973 0.77313 0.812 0.188
#> GSM613698 2 0.8861 0.57561 0.304 0.696
#> GSM613699 2 0.6148 0.81589 0.152 0.848
#> GSM613700 2 0.0000 0.95969 0.000 1.000
#> GSM613701 2 0.3274 0.91167 0.060 0.940
#> GSM613702 2 0.3879 0.89539 0.076 0.924
#> GSM613703 1 0.0000 0.96509 1.000 0.000
#> GSM613704 2 0.0000 0.95969 0.000 1.000
#> GSM613705 2 0.6343 0.80633 0.160 0.840
#> GSM613706 1 0.2423 0.93352 0.960 0.040
#> GSM613707 2 0.0000 0.95969 0.000 1.000
#> GSM613708 1 0.0000 0.96509 1.000 0.000
#> GSM613709 1 0.0000 0.96509 1.000 0.000
#> GSM613710 2 0.0000 0.95969 0.000 1.000
#> GSM613711 2 0.0000 0.95969 0.000 1.000
#> GSM613712 2 0.7376 0.74146 0.208 0.792
#> GSM613713 2 0.0000 0.95969 0.000 1.000
#> GSM613714 2 0.0000 0.95969 0.000 1.000
#> GSM613715 2 0.0000 0.95969 0.000 1.000
#> GSM613716 2 0.0000 0.95969 0.000 1.000
#> GSM613717 2 0.0000 0.95969 0.000 1.000
#> GSM613718 2 0.0000 0.95969 0.000 1.000
#> GSM613719 1 0.7056 0.76707 0.808 0.192
#> GSM613720 2 0.0000 0.95969 0.000 1.000
#> GSM613721 2 0.0000 0.95969 0.000 1.000
#> GSM613722 2 0.0000 0.95969 0.000 1.000
#> GSM613723 1 0.0000 0.96509 1.000 0.000
#> GSM613724 1 0.0000 0.96509 1.000 0.000
#> GSM613725 2 0.0000 0.95969 0.000 1.000
#> GSM613726 1 0.0000 0.96509 1.000 0.000
#> GSM613727 1 0.0000 0.96509 1.000 0.000
#> GSM613728 2 0.0000 0.95969 0.000 1.000
#> GSM613729 1 0.0000 0.96509 1.000 0.000
#> GSM613730 2 0.0000 0.95969 0.000 1.000
#> GSM613731 1 0.0000 0.96509 1.000 0.000
#> GSM613732 2 0.0000 0.95969 0.000 1.000
#> GSM613733 2 0.0000 0.95969 0.000 1.000
#> GSM613734 1 0.0000 0.96509 1.000 0.000
#> GSM613735 1 0.0000 0.96509 1.000 0.000
#> GSM613736 2 0.0000 0.95969 0.000 1.000
#> GSM613737 2 0.9866 0.24609 0.432 0.568
#> GSM613738 1 0.0000 0.96509 1.000 0.000
#> GSM613739 1 0.0000 0.96509 1.000 0.000
#> GSM613740 2 0.0000 0.95969 0.000 1.000
#> GSM613741 1 0.4562 0.88129 0.904 0.096
#> GSM613742 1 0.0000 0.96509 1.000 0.000
#> GSM613743 2 0.0000 0.95969 0.000 1.000
#> GSM613744 2 0.0000 0.95969 0.000 1.000
#> GSM613745 2 0.9209 0.50771 0.336 0.664
#> GSM613746 2 0.0000 0.95969 0.000 1.000
#> GSM613747 1 0.0000 0.96509 1.000 0.000
#> GSM613748 2 0.0376 0.95678 0.004 0.996
#> GSM613749 1 0.0000 0.96509 1.000 0.000
#> GSM613750 2 0.0000 0.95969 0.000 1.000
#> GSM613751 2 0.0000 0.95969 0.000 1.000
#> GSM613752 2 0.0000 0.95969 0.000 1.000
#> GSM613753 2 0.0000 0.95969 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM613638 3 0.5016 0.6716 0.240 0.000 0.760
#> GSM613639 1 0.0424 0.9517 0.992 0.008 0.000
#> GSM613640 3 0.4047 0.7431 0.148 0.004 0.848
#> GSM613641 1 0.0000 0.9563 1.000 0.000 0.000
#> GSM613642 3 0.6180 0.1388 0.000 0.416 0.584
#> GSM613643 1 0.0237 0.9557 0.996 0.000 0.004
#> GSM613644 1 0.0237 0.9557 0.996 0.000 0.004
#> GSM613645 2 0.5760 0.4845 0.328 0.672 0.000
#> GSM613646 1 0.4504 0.7253 0.804 0.000 0.196
#> GSM613647 3 0.5760 0.5424 0.328 0.000 0.672
#> GSM613648 3 0.0000 0.8178 0.000 0.000 1.000
#> GSM613649 3 0.0000 0.8178 0.000 0.000 1.000
#> GSM613650 1 0.1031 0.9411 0.976 0.000 0.024
#> GSM613651 3 0.6286 0.2323 0.464 0.000 0.536
#> GSM613652 1 0.0237 0.9557 0.996 0.000 0.004
#> GSM613653 1 0.4504 0.7241 0.804 0.000 0.196
#> GSM613654 1 0.0237 0.9557 0.996 0.000 0.004
#> GSM613655 1 0.0000 0.9563 1.000 0.000 0.000
#> GSM613656 1 0.0237 0.9557 0.996 0.000 0.004
#> GSM613657 3 0.0237 0.8180 0.000 0.004 0.996
#> GSM613658 1 0.0000 0.9563 1.000 0.000 0.000
#> GSM613659 2 0.0000 0.8646 0.000 1.000 0.000
#> GSM613660 3 0.6215 0.0958 0.000 0.428 0.572
#> GSM613661 1 0.0000 0.9563 1.000 0.000 0.000
#> GSM613662 2 0.0000 0.8646 0.000 1.000 0.000
#> GSM613663 1 0.0000 0.9563 1.000 0.000 0.000
#> GSM613664 2 0.0000 0.8646 0.000 1.000 0.000
#> GSM613665 2 0.4654 0.7642 0.000 0.792 0.208
#> GSM613666 1 0.0892 0.9432 0.980 0.020 0.000
#> GSM613667 1 0.2625 0.8863 0.916 0.084 0.000
#> GSM613668 1 0.0000 0.9563 1.000 0.000 0.000
#> GSM613669 1 0.0000 0.9563 1.000 0.000 0.000
#> GSM613670 2 0.0237 0.8636 0.004 0.996 0.000
#> GSM613671 1 0.0000 0.9563 1.000 0.000 0.000
#> GSM613672 1 0.0000 0.9563 1.000 0.000 0.000
#> GSM613673 1 0.2448 0.8937 0.924 0.076 0.000
#> GSM613674 2 0.1964 0.8565 0.000 0.944 0.056
#> GSM613675 2 0.0237 0.8640 0.000 0.996 0.004
#> GSM613676 3 0.5560 0.4413 0.000 0.300 0.700
#> GSM613677 3 0.0424 0.8165 0.000 0.008 0.992
#> GSM613678 2 0.0237 0.8636 0.004 0.996 0.000
#> GSM613679 2 0.4121 0.8035 0.000 0.832 0.168
#> GSM613680 1 0.0000 0.9563 1.000 0.000 0.000
#> GSM613681 1 0.0000 0.9563 1.000 0.000 0.000
#> GSM613682 1 0.6274 0.1149 0.544 0.456 0.000
#> GSM613683 1 0.0000 0.9563 1.000 0.000 0.000
#> GSM613684 3 0.6307 -0.1213 0.000 0.488 0.512
#> GSM613685 2 0.4399 0.7871 0.000 0.812 0.188
#> GSM613686 2 0.2625 0.8241 0.084 0.916 0.000
#> GSM613687 1 0.0000 0.9563 1.000 0.000 0.000
#> GSM613688 2 0.2537 0.8479 0.000 0.920 0.080
#> GSM613689 3 0.0237 0.8180 0.000 0.004 0.996
#> GSM613690 3 0.0000 0.8178 0.000 0.000 1.000
#> GSM613691 2 0.6062 0.2360 0.000 0.616 0.384
#> GSM613692 1 0.0424 0.9533 0.992 0.000 0.008
#> GSM613693 3 0.0592 0.8142 0.000 0.012 0.988
#> GSM613694 3 0.6215 0.3319 0.428 0.000 0.572
#> GSM613695 3 0.0000 0.8178 0.000 0.000 1.000
#> GSM613696 3 0.1878 0.8008 0.044 0.004 0.952
#> GSM613697 3 0.6260 0.2776 0.448 0.000 0.552
#> GSM613698 3 0.4796 0.6877 0.220 0.000 0.780
#> GSM613699 3 0.3038 0.7676 0.104 0.000 0.896
#> GSM613700 2 0.4121 0.8037 0.000 0.832 0.168
#> GSM613701 2 0.4663 0.7606 0.156 0.828 0.016
#> GSM613702 2 0.0237 0.8636 0.004 0.996 0.000
#> GSM613703 1 0.4796 0.7115 0.780 0.220 0.000
#> GSM613704 2 0.0000 0.8646 0.000 1.000 0.000
#> GSM613705 3 0.4178 0.7234 0.172 0.000 0.828
#> GSM613706 2 0.6302 0.0862 0.480 0.520 0.000
#> GSM613707 2 0.4178 0.8008 0.000 0.828 0.172
#> GSM613708 1 0.0000 0.9563 1.000 0.000 0.000
#> GSM613709 1 0.0000 0.9563 1.000 0.000 0.000
#> GSM613710 3 0.5926 0.3063 0.000 0.356 0.644
#> GSM613711 3 0.0237 0.8180 0.000 0.004 0.996
#> GSM613712 3 0.4555 0.7031 0.200 0.000 0.800
#> GSM613713 3 0.0237 0.8180 0.000 0.004 0.996
#> GSM613714 3 0.0000 0.8178 0.000 0.000 1.000
#> GSM613715 3 0.0000 0.8178 0.000 0.000 1.000
#> GSM613716 3 0.0424 0.8165 0.000 0.008 0.992
#> GSM613717 3 0.0237 0.8180 0.000 0.004 0.996
#> GSM613718 3 0.0237 0.8180 0.000 0.004 0.996
#> GSM613719 3 0.6302 0.1804 0.480 0.000 0.520
#> GSM613720 3 0.0424 0.8165 0.000 0.008 0.992
#> GSM613721 3 0.5968 0.4499 0.000 0.364 0.636
#> GSM613722 2 0.4504 0.7792 0.000 0.804 0.196
#> GSM613723 1 0.0237 0.9557 0.996 0.000 0.004
#> GSM613724 1 0.0000 0.9563 1.000 0.000 0.000
#> GSM613725 2 0.4605 0.7711 0.000 0.796 0.204
#> GSM613726 1 0.1411 0.9312 0.964 0.036 0.000
#> GSM613727 1 0.0000 0.9563 1.000 0.000 0.000
#> GSM613728 2 0.0000 0.8646 0.000 1.000 0.000
#> GSM613729 1 0.0000 0.9563 1.000 0.000 0.000
#> GSM613730 2 0.0000 0.8646 0.000 1.000 0.000
#> GSM613731 1 0.0000 0.9563 1.000 0.000 0.000
#> GSM613732 3 0.0237 0.8180 0.000 0.004 0.996
#> GSM613733 3 0.0237 0.8180 0.000 0.004 0.996
#> GSM613734 1 0.0237 0.9557 0.996 0.000 0.004
#> GSM613735 1 0.0237 0.9557 0.996 0.000 0.004
#> GSM613736 3 0.0237 0.8180 0.000 0.004 0.996
#> GSM613737 3 0.5098 0.6620 0.248 0.000 0.752
#> GSM613738 1 0.0237 0.9557 0.996 0.000 0.004
#> GSM613739 1 0.0237 0.9557 0.996 0.000 0.004
#> GSM613740 3 0.0237 0.8180 0.000 0.004 0.996
#> GSM613741 1 0.7493 0.6465 0.696 0.136 0.168
#> GSM613742 1 0.1163 0.9377 0.972 0.000 0.028
#> GSM613743 3 0.0237 0.8180 0.000 0.004 0.996
#> GSM613744 3 0.0237 0.8180 0.000 0.004 0.996
#> GSM613745 3 0.8557 0.5248 0.180 0.212 0.608
#> GSM613746 3 0.5988 0.4725 0.000 0.368 0.632
#> GSM613747 1 0.0237 0.9557 0.996 0.000 0.004
#> GSM613748 2 0.1765 0.8610 0.004 0.956 0.040
#> GSM613749 2 0.0592 0.8621 0.012 0.988 0.000
#> GSM613750 3 0.0000 0.8178 0.000 0.000 1.000
#> GSM613751 3 0.0237 0.8180 0.000 0.004 0.996
#> GSM613752 3 0.0237 0.8180 0.000 0.004 0.996
#> GSM613753 3 0.0000 0.8178 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 3 0.7827 -0.06778 0.260 0.352 0.388 0.000
#> GSM613639 1 0.5276 0.29116 0.560 0.004 0.004 0.432
#> GSM613640 2 0.6515 0.60717 0.128 0.624 0.248 0.000
#> GSM613641 1 0.0376 0.90617 0.992 0.004 0.000 0.004
#> GSM613642 2 0.3400 0.78399 0.000 0.820 0.180 0.000
#> GSM613643 1 0.0000 0.90741 1.000 0.000 0.000 0.000
#> GSM613644 1 0.0376 0.90651 0.992 0.000 0.004 0.004
#> GSM613645 1 0.6965 0.00198 0.460 0.112 0.000 0.428
#> GSM613646 4 0.4898 0.69833 0.072 0.000 0.156 0.772
#> GSM613647 3 0.3356 0.73284 0.176 0.000 0.824 0.000
#> GSM613648 3 0.0779 0.82630 0.000 0.004 0.980 0.016
#> GSM613649 3 0.1576 0.81726 0.000 0.004 0.948 0.048
#> GSM613650 1 0.3764 0.68255 0.784 0.000 0.216 0.000
#> GSM613651 3 0.4564 0.55000 0.328 0.000 0.672 0.000
#> GSM613652 1 0.0188 0.90644 0.996 0.000 0.004 0.000
#> GSM613653 4 0.2867 0.78685 0.012 0.000 0.104 0.884
#> GSM613654 1 0.0000 0.90741 1.000 0.000 0.000 0.000
#> GSM613655 1 0.0000 0.90741 1.000 0.000 0.000 0.000
#> GSM613656 1 0.0000 0.90741 1.000 0.000 0.000 0.000
#> GSM613657 3 0.0817 0.82285 0.000 0.024 0.976 0.000
#> GSM613658 1 0.0376 0.90651 0.992 0.000 0.004 0.004
#> GSM613659 4 0.2704 0.76681 0.000 0.124 0.000 0.876
#> GSM613660 2 0.3074 0.80118 0.000 0.848 0.152 0.000
#> GSM613661 1 0.0336 0.90626 0.992 0.000 0.000 0.008
#> GSM613662 4 0.1792 0.79548 0.000 0.068 0.000 0.932
#> GSM613663 1 0.0000 0.90741 1.000 0.000 0.000 0.000
#> GSM613664 4 0.4382 0.59219 0.000 0.296 0.000 0.704
#> GSM613665 2 0.2563 0.83984 0.000 0.908 0.072 0.020
#> GSM613666 1 0.5070 0.44259 0.620 0.008 0.000 0.372
#> GSM613667 1 0.2578 0.86005 0.912 0.052 0.000 0.036
#> GSM613668 1 0.0000 0.90741 1.000 0.000 0.000 0.000
#> GSM613669 1 0.1661 0.88176 0.944 0.004 0.000 0.052
#> GSM613670 4 0.2011 0.79182 0.000 0.080 0.000 0.920
#> GSM613671 1 0.4990 0.48327 0.640 0.008 0.000 0.352
#> GSM613672 1 0.0000 0.90741 1.000 0.000 0.000 0.000
#> GSM613673 1 0.2281 0.84203 0.904 0.096 0.000 0.000
#> GSM613674 2 0.0927 0.83379 0.000 0.976 0.008 0.016
#> GSM613675 4 0.1004 0.80446 0.000 0.024 0.004 0.972
#> GSM613676 2 0.3764 0.75623 0.000 0.784 0.216 0.000
#> GSM613677 3 0.1302 0.81512 0.000 0.044 0.956 0.000
#> GSM613678 4 0.4830 0.40508 0.000 0.392 0.000 0.608
#> GSM613679 2 0.1520 0.83683 0.000 0.956 0.020 0.024
#> GSM613680 1 0.0000 0.90741 1.000 0.000 0.000 0.000
#> GSM613681 1 0.1004 0.89796 0.972 0.004 0.000 0.024
#> GSM613682 1 0.4423 0.72359 0.788 0.176 0.000 0.036
#> GSM613683 1 0.0000 0.90741 1.000 0.000 0.000 0.000
#> GSM613684 2 0.5700 0.72723 0.000 0.716 0.164 0.120
#> GSM613685 2 0.1452 0.84377 0.000 0.956 0.036 0.008
#> GSM613686 4 0.7894 0.20556 0.320 0.304 0.000 0.376
#> GSM613687 1 0.0592 0.90191 0.984 0.016 0.000 0.000
#> GSM613688 2 0.4807 0.58157 0.000 0.728 0.024 0.248
#> GSM613689 3 0.2814 0.73357 0.000 0.132 0.868 0.000
#> GSM613690 3 0.0921 0.82289 0.000 0.000 0.972 0.028
#> GSM613691 4 0.1474 0.80577 0.000 0.000 0.052 0.948
#> GSM613692 1 0.4932 0.61994 0.728 0.000 0.240 0.032
#> GSM613693 3 0.4889 0.48122 0.000 0.004 0.636 0.360
#> GSM613694 3 0.5000 0.10882 0.500 0.000 0.500 0.000
#> GSM613695 3 0.0469 0.82588 0.000 0.012 0.988 0.000
#> GSM613696 3 0.4964 0.64490 0.032 0.000 0.724 0.244
#> GSM613697 3 0.4304 0.61414 0.284 0.000 0.716 0.000
#> GSM613698 3 0.5033 0.70504 0.072 0.000 0.760 0.168
#> GSM613699 3 0.2623 0.80065 0.064 0.000 0.908 0.028
#> GSM613700 2 0.1042 0.84112 0.000 0.972 0.020 0.008
#> GSM613701 2 0.1404 0.83640 0.012 0.964 0.012 0.012
#> GSM613702 2 0.1004 0.82241 0.004 0.972 0.000 0.024
#> GSM613703 4 0.3709 0.74830 0.100 0.040 0.004 0.856
#> GSM613704 4 0.1474 0.79955 0.000 0.052 0.000 0.948
#> GSM613705 3 0.6664 0.50468 0.232 0.152 0.616 0.000
#> GSM613706 2 0.3787 0.74902 0.124 0.840 0.036 0.000
#> GSM613707 2 0.1388 0.84221 0.000 0.960 0.028 0.012
#> GSM613708 1 0.0336 0.90626 0.992 0.000 0.000 0.008
#> GSM613709 1 0.0336 0.90626 0.992 0.000 0.000 0.008
#> GSM613710 2 0.3649 0.76567 0.000 0.796 0.204 0.000
#> GSM613711 3 0.0469 0.82582 0.000 0.012 0.988 0.000
#> GSM613712 3 0.4123 0.74701 0.136 0.000 0.820 0.044
#> GSM613713 3 0.3557 0.76869 0.000 0.108 0.856 0.036
#> GSM613714 3 0.1867 0.79213 0.000 0.072 0.928 0.000
#> GSM613715 3 0.1118 0.82054 0.000 0.000 0.964 0.036
#> GSM613716 3 0.4679 0.50679 0.000 0.000 0.648 0.352
#> GSM613717 3 0.0707 0.82402 0.000 0.020 0.980 0.000
#> GSM613718 3 0.0672 0.82676 0.000 0.008 0.984 0.008
#> GSM613719 3 0.6948 0.51240 0.204 0.000 0.588 0.208
#> GSM613720 3 0.4837 0.51556 0.000 0.004 0.648 0.348
#> GSM613721 4 0.2149 0.79775 0.000 0.000 0.088 0.912
#> GSM613722 2 0.1398 0.84348 0.000 0.956 0.040 0.004
#> GSM613723 1 0.0336 0.90451 0.992 0.000 0.008 0.000
#> GSM613724 1 0.0000 0.90741 1.000 0.000 0.000 0.000
#> GSM613725 2 0.1716 0.83917 0.000 0.936 0.064 0.000
#> GSM613726 1 0.1557 0.87723 0.944 0.056 0.000 0.000
#> GSM613727 1 0.0000 0.90741 1.000 0.000 0.000 0.000
#> GSM613728 2 0.1211 0.81490 0.000 0.960 0.000 0.040
#> GSM613729 1 0.1396 0.89350 0.960 0.004 0.004 0.032
#> GSM613730 2 0.3529 0.72255 0.000 0.836 0.012 0.152
#> GSM613731 1 0.0188 0.90657 0.996 0.004 0.000 0.000
#> GSM613732 3 0.1042 0.82610 0.000 0.008 0.972 0.020
#> GSM613733 2 0.4998 0.21569 0.000 0.512 0.488 0.000
#> GSM613734 1 0.0000 0.90741 1.000 0.000 0.000 0.000
#> GSM613735 1 0.0188 0.90644 0.996 0.000 0.004 0.000
#> GSM613736 3 0.1637 0.80213 0.000 0.060 0.940 0.000
#> GSM613737 3 0.3554 0.75690 0.136 0.000 0.844 0.020
#> GSM613738 1 0.1824 0.86630 0.936 0.000 0.060 0.004
#> GSM613739 1 0.1557 0.87151 0.944 0.000 0.056 0.000
#> GSM613740 3 0.1256 0.82460 0.000 0.008 0.964 0.028
#> GSM613741 4 0.1940 0.80244 0.000 0.000 0.076 0.924
#> GSM613742 1 0.4988 0.53178 0.692 0.000 0.288 0.020
#> GSM613743 3 0.1022 0.81994 0.000 0.032 0.968 0.000
#> GSM613744 3 0.0672 0.82676 0.000 0.008 0.984 0.008
#> GSM613745 4 0.3610 0.66332 0.000 0.000 0.200 0.800
#> GSM613746 4 0.2011 0.79989 0.000 0.000 0.080 0.920
#> GSM613747 1 0.0000 0.90741 1.000 0.000 0.000 0.000
#> GSM613748 2 0.1492 0.84022 0.004 0.956 0.036 0.004
#> GSM613749 2 0.4673 0.66026 0.076 0.792 0.000 0.132
#> GSM613750 3 0.0336 0.82633 0.000 0.008 0.992 0.000
#> GSM613751 3 0.0707 0.82402 0.000 0.020 0.980 0.000
#> GSM613752 3 0.1042 0.82610 0.000 0.008 0.972 0.020
#> GSM613753 3 0.0592 0.82608 0.000 0.000 0.984 0.016
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM613638 5 0.5733 0.5556 0.208 0.124 0.004 0.008 0.656
#> GSM613639 4 0.4637 0.5376 0.160 0.000 0.100 0.740 0.000
#> GSM613640 5 0.6380 0.3224 0.004 0.208 0.004 0.220 0.564
#> GSM613641 1 0.1197 0.8367 0.952 0.000 0.000 0.048 0.000
#> GSM613642 2 0.5237 0.6231 0.000 0.696 0.004 0.140 0.160
#> GSM613643 1 0.7508 0.2308 0.492 0.096 0.000 0.264 0.148
#> GSM613644 4 0.5773 0.1969 0.100 0.000 0.000 0.544 0.356
#> GSM613645 4 0.3248 0.5865 0.084 0.020 0.032 0.864 0.000
#> GSM613646 3 0.5244 0.5873 0.084 0.004 0.728 0.160 0.024
#> GSM613647 5 0.2731 0.7398 0.016 0.000 0.004 0.104 0.876
#> GSM613648 5 0.2344 0.7574 0.000 0.000 0.032 0.064 0.904
#> GSM613649 5 0.2149 0.7556 0.000 0.000 0.048 0.036 0.916
#> GSM613650 1 0.3343 0.7909 0.864 0.000 0.028 0.040 0.068
#> GSM613651 5 0.5302 0.5144 0.280 0.000 0.032 0.032 0.656
#> GSM613652 1 0.0162 0.8382 0.996 0.000 0.000 0.004 0.000
#> GSM613653 3 0.3831 0.6438 0.004 0.000 0.784 0.188 0.024
#> GSM613654 1 0.0510 0.8364 0.984 0.000 0.000 0.016 0.000
#> GSM613655 1 0.0162 0.8387 0.996 0.000 0.000 0.004 0.000
#> GSM613656 1 0.0000 0.8381 1.000 0.000 0.000 0.000 0.000
#> GSM613657 5 0.1372 0.7694 0.000 0.024 0.016 0.004 0.956
#> GSM613658 1 0.0955 0.8394 0.968 0.000 0.000 0.028 0.004
#> GSM613659 4 0.3209 0.4695 0.000 0.008 0.180 0.812 0.000
#> GSM613660 2 0.4123 0.6646 0.000 0.796 0.004 0.092 0.108
#> GSM613661 4 0.4397 0.1002 0.432 0.000 0.000 0.564 0.004
#> GSM613662 4 0.4359 0.1843 0.000 0.004 0.412 0.584 0.000
#> GSM613663 1 0.2020 0.8118 0.900 0.000 0.000 0.100 0.000
#> GSM613664 2 0.5887 0.1109 0.000 0.476 0.424 0.100 0.000
#> GSM613665 2 0.4631 0.5686 0.000 0.704 0.004 0.252 0.040
#> GSM613666 1 0.5589 0.4701 0.628 0.000 0.128 0.244 0.000
#> GSM613667 4 0.3611 0.5530 0.208 0.008 0.000 0.780 0.004
#> GSM613668 1 0.0162 0.8384 0.996 0.000 0.000 0.004 0.000
#> GSM613669 1 0.3928 0.6054 0.700 0.000 0.004 0.296 0.000
#> GSM613670 4 0.4166 0.3061 0.000 0.004 0.348 0.648 0.000
#> GSM613671 1 0.5154 0.3791 0.580 0.000 0.048 0.372 0.000
#> GSM613672 1 0.1121 0.8382 0.956 0.000 0.000 0.044 0.000
#> GSM613673 1 0.3307 0.7603 0.844 0.104 0.000 0.052 0.000
#> GSM613674 2 0.2583 0.6579 0.000 0.864 0.132 0.004 0.000
#> GSM613675 4 0.3689 0.4021 0.000 0.000 0.256 0.740 0.004
#> GSM613676 2 0.6188 0.4831 0.000 0.552 0.004 0.152 0.292
#> GSM613677 5 0.2102 0.7614 0.000 0.012 0.004 0.068 0.916
#> GSM613678 4 0.3012 0.5488 0.000 0.104 0.036 0.860 0.000
#> GSM613679 2 0.2464 0.6743 0.000 0.892 0.012 0.092 0.004
#> GSM613680 1 0.0880 0.8391 0.968 0.000 0.000 0.032 0.000
#> GSM613681 1 0.2230 0.8054 0.884 0.000 0.000 0.116 0.000
#> GSM613682 1 0.2513 0.7803 0.876 0.116 0.000 0.008 0.000
#> GSM613683 1 0.0404 0.8398 0.988 0.000 0.000 0.012 0.000
#> GSM613684 2 0.4993 0.5173 0.000 0.672 0.268 0.004 0.056
#> GSM613685 2 0.2798 0.6536 0.000 0.852 0.140 0.000 0.008
#> GSM613686 4 0.4737 0.5812 0.148 0.080 0.016 0.756 0.000
#> GSM613687 1 0.0963 0.8390 0.964 0.000 0.000 0.036 0.000
#> GSM613688 2 0.5288 0.5018 0.000 0.664 0.260 0.064 0.012
#> GSM613689 5 0.5833 0.0306 0.000 0.440 0.080 0.004 0.476
#> GSM613690 5 0.1992 0.7581 0.000 0.000 0.044 0.032 0.924
#> GSM613691 3 0.3551 0.6153 0.000 0.000 0.772 0.220 0.008
#> GSM613692 1 0.6108 0.4965 0.644 0.000 0.128 0.036 0.192
#> GSM613693 3 0.3919 0.6175 0.000 0.100 0.816 0.008 0.076
#> GSM613694 1 0.5715 0.6088 0.732 0.128 0.052 0.048 0.040
#> GSM613695 5 0.1116 0.7708 0.004 0.004 0.000 0.028 0.964
#> GSM613696 3 0.5342 0.5612 0.032 0.124 0.732 0.004 0.108
#> GSM613697 5 0.4419 0.6369 0.188 0.000 0.020 0.032 0.760
#> GSM613698 5 0.6410 0.3302 0.056 0.000 0.300 0.072 0.572
#> GSM613699 5 0.8539 0.1560 0.204 0.160 0.260 0.008 0.368
#> GSM613700 2 0.2722 0.6690 0.000 0.872 0.000 0.108 0.020
#> GSM613701 2 0.1772 0.6834 0.016 0.944 0.012 0.024 0.004
#> GSM613702 2 0.4305 0.1685 0.000 0.512 0.000 0.488 0.000
#> GSM613703 4 0.5103 0.1935 0.040 0.000 0.404 0.556 0.000
#> GSM613704 3 0.4473 0.4433 0.000 0.020 0.656 0.324 0.000
#> GSM613705 5 0.3319 0.7488 0.052 0.040 0.004 0.032 0.872
#> GSM613706 2 0.6060 0.5090 0.156 0.672 0.004 0.124 0.044
#> GSM613707 2 0.3250 0.6351 0.000 0.820 0.168 0.004 0.008
#> GSM613708 1 0.3480 0.6853 0.752 0.000 0.000 0.248 0.000
#> GSM613709 1 0.3586 0.6583 0.736 0.000 0.000 0.264 0.000
#> GSM613710 2 0.3906 0.6705 0.000 0.812 0.004 0.080 0.104
#> GSM613711 5 0.2504 0.7576 0.000 0.064 0.032 0.004 0.900
#> GSM613712 5 0.5410 0.5735 0.204 0.000 0.080 0.024 0.692
#> GSM613713 2 0.5863 0.4224 0.000 0.588 0.292 0.004 0.116
#> GSM613714 5 0.3174 0.7459 0.000 0.080 0.036 0.016 0.868
#> GSM613715 5 0.2074 0.7570 0.000 0.000 0.044 0.036 0.920
#> GSM613716 3 0.5915 0.2966 0.000 0.000 0.508 0.108 0.384
#> GSM613717 5 0.3693 0.7131 0.000 0.124 0.044 0.008 0.824
#> GSM613718 5 0.0992 0.7713 0.000 0.008 0.024 0.000 0.968
#> GSM613719 3 0.6540 0.4705 0.108 0.000 0.572 0.044 0.276
#> GSM613720 3 0.4932 0.5634 0.000 0.004 0.668 0.048 0.280
#> GSM613721 3 0.2361 0.6247 0.000 0.096 0.892 0.012 0.000
#> GSM613722 2 0.3216 0.6703 0.000 0.848 0.000 0.108 0.044
#> GSM613723 1 0.0000 0.8381 1.000 0.000 0.000 0.000 0.000
#> GSM613724 1 0.1197 0.8346 0.952 0.000 0.000 0.048 0.000
#> GSM613725 2 0.1179 0.6856 0.000 0.964 0.016 0.004 0.016
#> GSM613726 1 0.4701 0.6552 0.720 0.076 0.000 0.204 0.000
#> GSM613727 1 0.0963 0.8376 0.964 0.000 0.000 0.036 0.000
#> GSM613728 2 0.3928 0.5220 0.000 0.700 0.000 0.296 0.004
#> GSM613729 1 0.3607 0.6843 0.752 0.000 0.004 0.244 0.000
#> GSM613730 4 0.4347 0.3626 0.000 0.264 0.012 0.712 0.012
#> GSM613731 4 0.6702 0.2445 0.336 0.176 0.000 0.476 0.012
#> GSM613732 5 0.1560 0.7724 0.000 0.020 0.028 0.004 0.948
#> GSM613733 2 0.5175 0.3096 0.000 0.584 0.040 0.004 0.372
#> GSM613734 1 0.0000 0.8381 1.000 0.000 0.000 0.000 0.000
#> GSM613735 1 0.0162 0.8380 0.996 0.000 0.004 0.000 0.000
#> GSM613736 2 0.6620 0.1407 0.000 0.480 0.104 0.032 0.384
#> GSM613737 5 0.5347 0.6314 0.180 0.008 0.076 0.020 0.716
#> GSM613738 1 0.2313 0.8007 0.912 0.000 0.044 0.004 0.040
#> GSM613739 1 0.4078 0.6574 0.776 0.000 0.004 0.040 0.180
#> GSM613740 5 0.5618 0.5764 0.000 0.192 0.152 0.004 0.652
#> GSM613741 3 0.3246 0.6407 0.000 0.000 0.808 0.184 0.008
#> GSM613742 1 0.4872 0.6353 0.744 0.000 0.072 0.020 0.164
#> GSM613743 5 0.5932 0.3155 0.000 0.336 0.096 0.008 0.560
#> GSM613744 5 0.1168 0.7712 0.000 0.008 0.032 0.000 0.960
#> GSM613745 3 0.4461 0.6524 0.000 0.000 0.728 0.220 0.052
#> GSM613746 3 0.2332 0.6591 0.000 0.016 0.904 0.076 0.004
#> GSM613747 1 0.0162 0.8384 0.996 0.000 0.000 0.004 0.000
#> GSM613748 4 0.5139 0.1245 0.000 0.360 0.004 0.596 0.040
#> GSM613749 2 0.5763 0.4040 0.096 0.604 0.008 0.292 0.000
#> GSM613750 5 0.1830 0.7681 0.000 0.012 0.052 0.004 0.932
#> GSM613751 5 0.3215 0.7379 0.000 0.068 0.068 0.004 0.860
#> GSM613752 5 0.3629 0.7302 0.000 0.072 0.092 0.004 0.832
#> GSM613753 5 0.1571 0.7657 0.000 0.000 0.060 0.004 0.936
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM613638 3 0.6241 0.1676 0.224 0.312 0.452 0.008 0.004 0.000
#> GSM613639 4 0.5492 0.2587 0.060 0.020 0.000 0.472 0.004 0.444
#> GSM613640 2 0.7028 0.2364 0.004 0.472 0.268 0.168 0.084 0.004
#> GSM613641 1 0.2594 0.7415 0.884 0.000 0.000 0.072 0.016 0.028
#> GSM613642 2 0.6928 0.3672 0.008 0.484 0.280 0.116 0.112 0.000
#> GSM613643 1 0.6671 0.1490 0.496 0.172 0.076 0.256 0.000 0.000
#> GSM613644 4 0.5301 0.1417 0.004 0.032 0.200 0.684 0.068 0.012
#> GSM613645 4 0.5444 0.4577 0.024 0.068 0.000 0.656 0.024 0.228
#> GSM613646 6 0.6985 0.3347 0.016 0.012 0.052 0.272 0.144 0.504
#> GSM613647 3 0.6448 0.4814 0.016 0.036 0.544 0.296 0.096 0.012
#> GSM613648 3 0.7240 0.4364 0.000 0.128 0.500 0.196 0.156 0.020
#> GSM613649 3 0.4832 0.5939 0.000 0.032 0.752 0.124 0.040 0.052
#> GSM613650 1 0.8093 -0.0417 0.368 0.008 0.196 0.060 0.076 0.292
#> GSM613651 3 0.6078 0.3520 0.260 0.000 0.544 0.172 0.016 0.008
#> GSM613652 1 0.0692 0.7609 0.976 0.000 0.000 0.020 0.004 0.000
#> GSM613653 6 0.2290 0.5326 0.016 0.000 0.020 0.012 0.040 0.912
#> GSM613654 1 0.1333 0.7502 0.944 0.000 0.000 0.048 0.008 0.000
#> GSM613655 1 0.0260 0.7647 0.992 0.000 0.000 0.008 0.000 0.000
#> GSM613656 1 0.0291 0.7634 0.992 0.000 0.000 0.004 0.004 0.000
#> GSM613657 3 0.4121 0.5206 0.000 0.200 0.736 0.000 0.060 0.004
#> GSM613658 1 0.1036 0.7627 0.964 0.000 0.000 0.024 0.008 0.004
#> GSM613659 4 0.5533 0.3417 0.000 0.048 0.000 0.644 0.108 0.200
#> GSM613660 2 0.2325 0.4944 0.000 0.884 0.100 0.008 0.008 0.000
#> GSM613661 4 0.6446 0.1721 0.392 0.012 0.008 0.420 0.008 0.160
#> GSM613662 6 0.4578 -0.0900 0.000 0.032 0.000 0.396 0.004 0.568
#> GSM613663 1 0.1858 0.7455 0.904 0.000 0.000 0.092 0.004 0.000
#> GSM613664 5 0.5265 0.7087 0.000 0.252 0.000 0.028 0.636 0.084
#> GSM613665 2 0.4707 0.4600 0.000 0.696 0.068 0.220 0.012 0.004
#> GSM613666 1 0.3910 0.6849 0.792 0.000 0.000 0.100 0.016 0.092
#> GSM613667 4 0.5954 0.4868 0.096 0.072 0.000 0.644 0.016 0.172
#> GSM613668 1 0.0291 0.7642 0.992 0.000 0.000 0.004 0.004 0.000
#> GSM613669 1 0.5262 0.4558 0.632 0.000 0.000 0.204 0.008 0.156
#> GSM613670 6 0.5023 -0.0440 0.000 0.056 0.000 0.356 0.012 0.576
#> GSM613671 1 0.5976 0.2157 0.508 0.000 0.000 0.188 0.012 0.292
#> GSM613672 1 0.0972 0.7660 0.964 0.008 0.000 0.028 0.000 0.000
#> GSM613673 1 0.3989 0.6475 0.776 0.096 0.000 0.120 0.008 0.000
#> GSM613674 5 0.4141 0.6494 0.000 0.388 0.000 0.016 0.596 0.000
#> GSM613675 4 0.6058 0.0995 0.000 0.040 0.052 0.568 0.036 0.304
#> GSM613676 2 0.6079 0.3689 0.000 0.484 0.336 0.160 0.020 0.000
#> GSM613677 3 0.4854 0.5226 0.000 0.036 0.708 0.208 0.024 0.024
#> GSM613678 4 0.5467 0.3667 0.000 0.256 0.000 0.608 0.020 0.116
#> GSM613679 2 0.4735 0.0492 0.000 0.628 0.000 0.076 0.296 0.000
#> GSM613680 1 0.1615 0.7469 0.928 0.004 0.000 0.064 0.004 0.000
#> GSM613681 1 0.3352 0.6994 0.812 0.000 0.000 0.148 0.008 0.032
#> GSM613682 1 0.4462 0.5971 0.748 0.072 0.000 0.032 0.148 0.000
#> GSM613683 1 0.0603 0.7656 0.980 0.000 0.000 0.016 0.004 0.000
#> GSM613684 5 0.3858 0.7183 0.000 0.248 0.000 0.004 0.724 0.024
#> GSM613685 5 0.4047 0.6557 0.000 0.384 0.000 0.012 0.604 0.000
#> GSM613686 4 0.6843 0.4534 0.140 0.076 0.000 0.516 0.016 0.252
#> GSM613687 1 0.1493 0.7621 0.936 0.004 0.000 0.056 0.004 0.000
#> GSM613688 5 0.4601 0.6853 0.000 0.348 0.000 0.020 0.612 0.020
#> GSM613689 3 0.5787 0.2573 0.000 0.372 0.504 0.016 0.104 0.004
#> GSM613690 3 0.3277 0.5841 0.000 0.008 0.836 0.120 0.020 0.016
#> GSM613691 6 0.1838 0.5215 0.000 0.000 0.012 0.040 0.020 0.928
#> GSM613692 1 0.7131 0.1191 0.444 0.000 0.288 0.196 0.036 0.036
#> GSM613693 5 0.4562 0.5033 0.000 0.016 0.012 0.020 0.676 0.276
#> GSM613694 1 0.8565 0.0101 0.396 0.084 0.200 0.164 0.140 0.016
#> GSM613695 3 0.5768 0.5613 0.012 0.036 0.660 0.172 0.112 0.008
#> GSM613696 5 0.5051 0.4504 0.016 0.004 0.024 0.028 0.660 0.268
#> GSM613697 3 0.5584 0.4477 0.184 0.000 0.628 0.164 0.020 0.004
#> GSM613698 3 0.7398 0.2518 0.032 0.000 0.444 0.280 0.080 0.164
#> GSM613699 3 0.9627 0.2098 0.144 0.184 0.300 0.112 0.148 0.112
#> GSM613700 2 0.2796 0.4369 0.000 0.868 0.008 0.044 0.080 0.000
#> GSM613701 2 0.4012 0.2149 0.024 0.724 0.000 0.012 0.240 0.000
#> GSM613702 2 0.4667 0.2264 0.000 0.576 0.000 0.380 0.040 0.004
#> GSM613703 6 0.4924 0.1371 0.072 0.004 0.000 0.248 0.012 0.664
#> GSM613704 6 0.2742 0.4804 0.000 0.016 0.000 0.072 0.036 0.876
#> GSM613705 3 0.5871 0.4512 0.032 0.272 0.604 0.068 0.020 0.004
#> GSM613706 2 0.4312 0.4739 0.112 0.784 0.024 0.060 0.020 0.000
#> GSM613707 5 0.3841 0.6603 0.000 0.380 0.000 0.004 0.616 0.000
#> GSM613708 1 0.2955 0.6979 0.816 0.000 0.000 0.172 0.008 0.004
#> GSM613709 1 0.4675 0.5604 0.696 0.000 0.000 0.200 0.008 0.096
#> GSM613710 2 0.2573 0.4807 0.000 0.856 0.132 0.004 0.008 0.000
#> GSM613711 3 0.4977 0.4859 0.000 0.232 0.668 0.012 0.084 0.004
#> GSM613712 3 0.6459 0.4182 0.176 0.000 0.580 0.176 0.032 0.036
#> GSM613713 5 0.4651 0.7026 0.000 0.232 0.020 0.000 0.692 0.056
#> GSM613714 3 0.6959 0.3286 0.000 0.288 0.468 0.084 0.152 0.008
#> GSM613715 3 0.2996 0.6089 0.000 0.020 0.872 0.064 0.012 0.032
#> GSM613716 6 0.6651 0.3583 0.000 0.000 0.164 0.264 0.076 0.496
#> GSM613717 3 0.6521 0.3527 0.000 0.296 0.516 0.044 0.128 0.016
#> GSM613718 3 0.2734 0.6037 0.000 0.064 0.876 0.004 0.052 0.004
#> GSM613719 6 0.6738 0.4026 0.076 0.000 0.196 0.080 0.064 0.584
#> GSM613720 6 0.6886 0.3427 0.000 0.000 0.184 0.192 0.124 0.500
#> GSM613721 5 0.3955 0.4579 0.000 0.012 0.004 0.000 0.668 0.316
#> GSM613722 2 0.4442 0.4008 0.000 0.760 0.048 0.068 0.124 0.000
#> GSM613723 1 0.0405 0.7629 0.988 0.000 0.000 0.008 0.004 0.000
#> GSM613724 1 0.1606 0.7546 0.932 0.000 0.000 0.056 0.008 0.004
#> GSM613725 2 0.3183 0.2932 0.000 0.788 0.008 0.004 0.200 0.000
#> GSM613726 1 0.4735 0.5788 0.700 0.064 0.000 0.216 0.008 0.012
#> GSM613727 1 0.1124 0.7612 0.956 0.000 0.000 0.036 0.008 0.000
#> GSM613728 2 0.5899 0.2787 0.000 0.636 0.004 0.136 0.072 0.152
#> GSM613729 1 0.5570 0.3528 0.568 0.000 0.000 0.148 0.008 0.276
#> GSM613730 2 0.7847 -0.1815 0.000 0.356 0.052 0.264 0.068 0.260
#> GSM613731 4 0.6325 0.2724 0.272 0.280 0.008 0.436 0.004 0.000
#> GSM613732 3 0.2697 0.5962 0.000 0.004 0.872 0.092 0.028 0.004
#> GSM613733 2 0.5139 -0.0520 0.000 0.516 0.416 0.012 0.056 0.000
#> GSM613734 1 0.0291 0.7634 0.992 0.000 0.000 0.004 0.004 0.000
#> GSM613735 1 0.0520 0.7639 0.984 0.000 0.000 0.008 0.008 0.000
#> GSM613736 2 0.7924 -0.1387 0.000 0.304 0.264 0.156 0.260 0.016
#> GSM613737 3 0.8758 0.3089 0.204 0.060 0.408 0.136 0.128 0.064
#> GSM613738 1 0.4721 0.6176 0.752 0.000 0.064 0.132 0.020 0.032
#> GSM613739 1 0.5229 0.4407 0.632 0.000 0.220 0.140 0.008 0.000
#> GSM613740 3 0.5952 0.4640 0.000 0.176 0.616 0.004 0.152 0.052
#> GSM613741 6 0.2011 0.5333 0.000 0.000 0.004 0.020 0.064 0.912
#> GSM613742 1 0.6170 0.4444 0.608 0.000 0.124 0.204 0.028 0.036
#> GSM613743 3 0.6714 0.2761 0.000 0.320 0.460 0.028 0.172 0.020
#> GSM613744 3 0.2006 0.6103 0.000 0.060 0.916 0.004 0.016 0.004
#> GSM613745 6 0.6267 0.3841 0.004 0.008 0.048 0.244 0.120 0.576
#> GSM613746 6 0.4063 0.0651 0.000 0.000 0.004 0.004 0.420 0.572
#> GSM613747 1 0.0622 0.7629 0.980 0.000 0.000 0.012 0.008 0.000
#> GSM613748 2 0.5271 0.2498 0.000 0.608 0.032 0.316 0.024 0.020
#> GSM613749 2 0.6847 -0.0794 0.084 0.456 0.000 0.360 0.032 0.068
#> GSM613750 3 0.2711 0.6034 0.000 0.012 0.872 0.004 0.096 0.016
#> GSM613751 3 0.3237 0.5926 0.000 0.036 0.836 0.004 0.116 0.008
#> GSM613752 3 0.3272 0.5879 0.000 0.020 0.820 0.000 0.144 0.016
#> GSM613753 3 0.2293 0.6094 0.000 0.004 0.896 0.016 0.080 0.004
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n disease.state(p) k
#> MAD:NMF 114 0.0403 2
#> MAD:NMF 101 0.0436 3
#> MAD:NMF 106 0.3869 4
#> MAD:NMF 87 0.2175 5
#> MAD:NMF 50 0.3268 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 27425 rows and 116 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 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 0.354 0.697 0.867 0.4478 0.505 0.505
#> 3 3 0.511 0.676 0.840 0.4178 0.635 0.414
#> 4 4 0.624 0.669 0.810 0.1490 0.838 0.587
#> 5 5 0.712 0.645 0.819 0.0551 0.942 0.789
#> 6 6 0.760 0.619 0.768 0.0340 0.903 0.636
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
#> GSM613638 1 0.9170 0.546 0.668 0.332
#> GSM613639 1 0.6887 0.777 0.816 0.184
#> GSM613640 1 0.7453 0.750 0.788 0.212
#> GSM613641 1 0.0000 0.844 1.000 0.000
#> GSM613642 1 0.6801 0.780 0.820 0.180
#> GSM613643 1 0.8144 0.698 0.748 0.252
#> GSM613644 1 0.8016 0.709 0.756 0.244
#> GSM613645 1 0.0000 0.844 1.000 0.000
#> GSM613646 2 0.9944 0.209 0.456 0.544
#> GSM613647 2 0.0000 0.794 0.000 1.000
#> GSM613648 2 0.0000 0.794 0.000 1.000
#> GSM613649 2 0.0000 0.794 0.000 1.000
#> GSM613650 2 0.9909 0.247 0.444 0.556
#> GSM613651 2 0.0000 0.794 0.000 1.000
#> GSM613652 2 0.0000 0.794 0.000 1.000
#> GSM613653 2 0.9993 0.098 0.484 0.516
#> GSM613654 2 0.0000 0.794 0.000 1.000
#> GSM613655 1 0.5519 0.817 0.872 0.128
#> GSM613656 2 0.0000 0.794 0.000 1.000
#> GSM613657 2 0.7815 0.635 0.232 0.768
#> GSM613658 1 0.9580 0.423 0.620 0.380
#> GSM613659 1 0.7056 0.770 0.808 0.192
#> GSM613660 1 0.7528 0.746 0.784 0.216
#> GSM613661 1 0.5178 0.822 0.884 0.116
#> GSM613662 1 0.0000 0.844 1.000 0.000
#> GSM613663 1 0.5178 0.822 0.884 0.116
#> GSM613664 1 0.0000 0.844 1.000 0.000
#> GSM613665 1 0.0000 0.844 1.000 0.000
#> GSM613666 1 0.0000 0.844 1.000 0.000
#> GSM613667 1 0.0000 0.844 1.000 0.000
#> GSM613668 1 0.4939 0.825 0.892 0.108
#> GSM613669 1 0.0000 0.844 1.000 0.000
#> GSM613670 1 0.0000 0.844 1.000 0.000
#> GSM613671 1 0.0000 0.844 1.000 0.000
#> GSM613672 1 0.2778 0.839 0.952 0.048
#> GSM613673 1 0.0000 0.844 1.000 0.000
#> GSM613674 1 0.0000 0.844 1.000 0.000
#> GSM613675 1 0.4815 0.827 0.896 0.104
#> GSM613676 1 0.4939 0.825 0.892 0.108
#> GSM613677 1 0.8207 0.691 0.744 0.256
#> GSM613678 1 0.0000 0.844 1.000 0.000
#> GSM613679 1 0.0000 0.844 1.000 0.000
#> GSM613680 1 0.0376 0.844 0.996 0.004
#> GSM613681 1 0.0376 0.844 0.996 0.004
#> GSM613682 1 0.5737 0.812 0.864 0.136
#> GSM613683 1 0.8763 0.622 0.704 0.296
#> GSM613684 1 0.7376 0.751 0.792 0.208
#> GSM613685 1 0.0000 0.844 1.000 0.000
#> GSM613686 1 0.0000 0.844 1.000 0.000
#> GSM613687 1 0.0376 0.844 0.996 0.004
#> GSM613688 1 0.6801 0.780 0.820 0.180
#> GSM613689 2 0.9686 0.371 0.396 0.604
#> GSM613690 2 0.0000 0.794 0.000 1.000
#> GSM613691 1 0.9954 0.139 0.540 0.460
#> GSM613692 2 0.0000 0.794 0.000 1.000
#> GSM613693 2 0.9970 0.167 0.468 0.532
#> GSM613694 2 0.9833 0.304 0.424 0.576
#> GSM613695 2 0.0000 0.794 0.000 1.000
#> GSM613696 2 0.9044 0.517 0.320 0.680
#> GSM613697 2 0.0000 0.794 0.000 1.000
#> GSM613698 2 0.0000 0.794 0.000 1.000
#> GSM613699 2 0.9710 0.362 0.400 0.600
#> GSM613700 1 0.0000 0.844 1.000 0.000
#> GSM613701 1 0.0000 0.844 1.000 0.000
#> GSM613702 1 0.0000 0.844 1.000 0.000
#> GSM613703 1 0.0000 0.844 1.000 0.000
#> GSM613704 1 0.0000 0.844 1.000 0.000
#> GSM613705 1 0.9209 0.537 0.664 0.336
#> GSM613706 1 0.7376 0.754 0.792 0.208
#> GSM613707 1 0.2603 0.839 0.956 0.044
#> GSM613708 1 0.8016 0.709 0.756 0.244
#> GSM613709 1 0.0000 0.844 1.000 0.000
#> GSM613710 1 0.6801 0.780 0.820 0.180
#> GSM613711 2 0.8386 0.596 0.268 0.732
#> GSM613712 2 0.0000 0.794 0.000 1.000
#> GSM613713 2 0.9970 0.167 0.468 0.532
#> GSM613714 2 0.7950 0.627 0.240 0.760
#> GSM613715 2 0.0000 0.794 0.000 1.000
#> GSM613716 2 0.9833 0.303 0.424 0.576
#> GSM613717 2 0.8386 0.596 0.268 0.732
#> GSM613718 2 0.0000 0.794 0.000 1.000
#> GSM613719 2 0.0000 0.794 0.000 1.000
#> GSM613720 2 0.0000 0.794 0.000 1.000
#> GSM613721 2 0.9970 0.167 0.468 0.532
#> GSM613722 1 0.0000 0.844 1.000 0.000
#> GSM613723 2 0.0000 0.794 0.000 1.000
#> GSM613724 1 0.9580 0.423 0.620 0.380
#> GSM613725 1 0.0000 0.844 1.000 0.000
#> GSM613726 1 0.5294 0.820 0.880 0.120
#> GSM613727 1 0.0000 0.844 1.000 0.000
#> GSM613728 1 0.0000 0.844 1.000 0.000
#> GSM613729 1 0.0000 0.844 1.000 0.000
#> GSM613730 1 0.7528 0.746 0.784 0.216
#> GSM613731 1 0.5294 0.820 0.880 0.120
#> GSM613732 2 0.0000 0.794 0.000 1.000
#> GSM613733 1 0.9944 0.156 0.544 0.456
#> GSM613734 1 0.9833 0.281 0.576 0.424
#> GSM613735 2 0.0000 0.794 0.000 1.000
#> GSM613736 2 0.8327 0.601 0.264 0.736
#> GSM613737 2 0.0000 0.794 0.000 1.000
#> GSM613738 2 0.0000 0.794 0.000 1.000
#> GSM613739 2 0.0000 0.794 0.000 1.000
#> GSM613740 2 0.0000 0.794 0.000 1.000
#> GSM613741 2 0.9954 0.196 0.460 0.540
#> GSM613742 2 0.0000 0.794 0.000 1.000
#> GSM613743 2 0.8327 0.601 0.264 0.736
#> GSM613744 2 0.0000 0.794 0.000 1.000
#> GSM613745 2 0.9944 0.209 0.456 0.544
#> GSM613746 2 0.9970 0.167 0.468 0.532
#> GSM613747 1 0.9833 0.281 0.576 0.424
#> GSM613748 1 0.4815 0.827 0.896 0.104
#> GSM613749 1 0.0000 0.844 1.000 0.000
#> GSM613750 2 0.0000 0.794 0.000 1.000
#> GSM613751 2 0.0000 0.794 0.000 1.000
#> GSM613752 2 0.0000 0.794 0.000 1.000
#> GSM613753 2 0.0000 0.794 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM613638 1 0.2297 0.6711 0.944 0.020 0.036
#> GSM613639 1 0.3983 0.6236 0.852 0.144 0.004
#> GSM613640 1 0.3500 0.6406 0.880 0.116 0.004
#> GSM613641 2 0.4842 0.6765 0.224 0.776 0.000
#> GSM613642 1 0.4842 0.5519 0.776 0.224 0.000
#> GSM613643 1 0.3031 0.6577 0.912 0.076 0.012
#> GSM613644 1 0.2682 0.6537 0.920 0.076 0.004
#> GSM613645 2 0.6309 0.1849 0.500 0.500 0.000
#> GSM613646 1 0.5502 0.6502 0.744 0.008 0.248
#> GSM613647 3 0.0424 0.9905 0.008 0.000 0.992
#> GSM613648 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613649 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613650 1 0.5443 0.6386 0.736 0.004 0.260
#> GSM613651 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613652 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613653 1 0.5202 0.6636 0.772 0.008 0.220
#> GSM613654 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613655 1 0.5016 0.5099 0.760 0.240 0.000
#> GSM613656 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613657 1 0.6309 0.1906 0.504 0.000 0.496
#> GSM613658 1 0.2625 0.6776 0.916 0.000 0.084
#> GSM613659 1 0.4047 0.6257 0.848 0.148 0.004
#> GSM613660 1 0.3682 0.6432 0.876 0.116 0.008
#> GSM613661 1 0.5216 0.4865 0.740 0.260 0.000
#> GSM613662 2 0.0000 0.8316 0.000 1.000 0.000
#> GSM613663 1 0.5254 0.4800 0.736 0.264 0.000
#> GSM613664 2 0.0000 0.8316 0.000 1.000 0.000
#> GSM613665 2 0.0000 0.8316 0.000 1.000 0.000
#> GSM613666 2 0.6126 0.4106 0.400 0.600 0.000
#> GSM613667 1 0.6308 -0.1894 0.508 0.492 0.000
#> GSM613668 1 0.5465 0.4299 0.712 0.288 0.000
#> GSM613669 2 0.0000 0.8316 0.000 1.000 0.000
#> GSM613670 2 0.0000 0.8316 0.000 1.000 0.000
#> GSM613671 2 0.0000 0.8316 0.000 1.000 0.000
#> GSM613672 1 0.5968 0.2470 0.636 0.364 0.000
#> GSM613673 2 0.6305 0.2211 0.484 0.516 0.000
#> GSM613674 2 0.5591 0.5675 0.304 0.696 0.000
#> GSM613675 1 0.5678 0.4103 0.684 0.316 0.000
#> GSM613676 1 0.5650 0.4187 0.688 0.312 0.000
#> GSM613677 1 0.3183 0.6593 0.908 0.076 0.016
#> GSM613678 1 0.6309 -0.1626 0.504 0.496 0.000
#> GSM613679 2 0.0000 0.8316 0.000 1.000 0.000
#> GSM613680 1 0.6267 -0.0494 0.548 0.452 0.000
#> GSM613681 1 0.6267 -0.0494 0.548 0.452 0.000
#> GSM613682 1 0.4974 0.5240 0.764 0.236 0.000
#> GSM613683 1 0.3899 0.6711 0.888 0.056 0.056
#> GSM613684 1 0.3918 0.6325 0.856 0.140 0.004
#> GSM613685 2 0.5591 0.5675 0.304 0.696 0.000
#> GSM613686 2 0.0000 0.8316 0.000 1.000 0.000
#> GSM613687 1 0.6267 -0.0494 0.548 0.452 0.000
#> GSM613688 1 0.4233 0.6185 0.836 0.160 0.004
#> GSM613689 1 0.5929 0.5742 0.676 0.004 0.320
#> GSM613690 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613691 1 0.4921 0.6745 0.816 0.020 0.164
#> GSM613692 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613693 1 0.5378 0.6593 0.756 0.008 0.236
#> GSM613694 1 0.5623 0.6189 0.716 0.004 0.280
#> GSM613695 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613696 1 0.6079 0.4589 0.612 0.000 0.388
#> GSM613697 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613698 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613699 1 0.5815 0.5911 0.692 0.004 0.304
#> GSM613700 2 0.0000 0.8316 0.000 1.000 0.000
#> GSM613701 2 0.0000 0.8316 0.000 1.000 0.000
#> GSM613702 2 0.0000 0.8316 0.000 1.000 0.000
#> GSM613703 2 0.0000 0.8316 0.000 1.000 0.000
#> GSM613704 2 0.0000 0.8316 0.000 1.000 0.000
#> GSM613705 1 0.2414 0.6720 0.940 0.020 0.040
#> GSM613706 1 0.3573 0.6385 0.876 0.120 0.004
#> GSM613707 2 0.6095 0.3941 0.392 0.608 0.000
#> GSM613708 1 0.2682 0.6537 0.920 0.076 0.004
#> GSM613709 2 0.6309 0.1849 0.500 0.500 0.000
#> GSM613710 1 0.4842 0.5519 0.776 0.224 0.000
#> GSM613711 1 0.6235 0.3487 0.564 0.000 0.436
#> GSM613712 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613713 1 0.5378 0.6593 0.756 0.008 0.236
#> GSM613714 1 0.6286 0.2753 0.536 0.000 0.464
#> GSM613715 3 0.0424 0.9905 0.008 0.000 0.992
#> GSM613716 1 0.5623 0.6171 0.716 0.004 0.280
#> GSM613717 1 0.6235 0.3487 0.564 0.000 0.436
#> GSM613718 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613719 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613720 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613721 1 0.5378 0.6593 0.756 0.008 0.236
#> GSM613722 2 0.0000 0.8316 0.000 1.000 0.000
#> GSM613723 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613724 1 0.2625 0.6776 0.916 0.000 0.084
#> GSM613725 2 0.0000 0.8316 0.000 1.000 0.000
#> GSM613726 1 0.5138 0.5112 0.748 0.252 0.000
#> GSM613727 2 0.5968 0.4834 0.364 0.636 0.000
#> GSM613728 2 0.0000 0.8316 0.000 1.000 0.000
#> GSM613729 2 0.3941 0.7404 0.156 0.844 0.000
#> GSM613730 1 0.3682 0.6432 0.876 0.116 0.008
#> GSM613731 1 0.5138 0.5112 0.748 0.252 0.000
#> GSM613732 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613733 1 0.4862 0.6751 0.820 0.020 0.160
#> GSM613734 1 0.3482 0.6778 0.872 0.000 0.128
#> GSM613735 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613736 1 0.6252 0.3316 0.556 0.000 0.444
#> GSM613737 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613738 3 0.0237 0.9952 0.004 0.000 0.996
#> GSM613739 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613740 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613741 1 0.5461 0.6533 0.748 0.008 0.244
#> GSM613742 3 0.0237 0.9952 0.004 0.000 0.996
#> GSM613743 1 0.6252 0.3316 0.556 0.000 0.444
#> GSM613744 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613745 1 0.5502 0.6502 0.744 0.008 0.248
#> GSM613746 1 0.5378 0.6593 0.756 0.008 0.236
#> GSM613747 1 0.3482 0.6778 0.872 0.000 0.128
#> GSM613748 1 0.5678 0.4103 0.684 0.316 0.000
#> GSM613749 2 0.0000 0.8316 0.000 1.000 0.000
#> GSM613750 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613751 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613752 3 0.0000 0.9990 0.000 0.000 1.000
#> GSM613753 3 0.0000 0.9990 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 4 0.4855 0.00209 0.400 0.000 0.000 0.600
#> GSM613639 1 0.5721 0.59296 0.660 0.056 0.000 0.284
#> GSM613640 1 0.5182 0.57859 0.684 0.028 0.000 0.288
#> GSM613641 2 0.4290 0.58550 0.212 0.772 0.000 0.016
#> GSM613642 1 0.6634 0.55815 0.592 0.116 0.000 0.292
#> GSM613643 1 0.4877 0.45543 0.592 0.000 0.000 0.408
#> GSM613644 1 0.4790 0.49079 0.620 0.000 0.000 0.380
#> GSM613645 1 0.5466 0.17020 0.548 0.436 0.000 0.016
#> GSM613646 4 0.2198 0.75302 0.008 0.000 0.072 0.920
#> GSM613647 3 0.0336 0.99080 0.000 0.000 0.992 0.008
#> GSM613648 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613649 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613650 4 0.2266 0.75686 0.004 0.000 0.084 0.912
#> GSM613651 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613652 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613653 4 0.2670 0.70019 0.072 0.000 0.024 0.904
#> GSM613654 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613655 1 0.5417 0.56045 0.732 0.180 0.000 0.088
#> GSM613656 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613657 4 0.4978 0.54120 0.004 0.000 0.384 0.612
#> GSM613658 1 0.4948 0.05574 0.560 0.000 0.000 0.440
#> GSM613659 1 0.6000 0.54535 0.592 0.052 0.000 0.356
#> GSM613660 1 0.5478 0.54418 0.628 0.028 0.000 0.344
#> GSM613661 1 0.4956 0.55536 0.756 0.188 0.000 0.056
#> GSM613662 2 0.0000 0.83565 0.000 1.000 0.000 0.000
#> GSM613663 1 0.4996 0.55257 0.752 0.192 0.000 0.056
#> GSM613664 2 0.0000 0.83565 0.000 1.000 0.000 0.000
#> GSM613665 2 0.0000 0.83565 0.000 1.000 0.000 0.000
#> GSM613666 2 0.5268 0.26608 0.396 0.592 0.000 0.012
#> GSM613667 1 0.5503 0.05746 0.516 0.468 0.000 0.016
#> GSM613668 1 0.5090 0.51171 0.728 0.228 0.000 0.044
#> GSM613669 2 0.0000 0.83565 0.000 1.000 0.000 0.000
#> GSM613670 2 0.0000 0.83565 0.000 1.000 0.000 0.000
#> GSM613671 2 0.0000 0.83565 0.000 1.000 0.000 0.000
#> GSM613672 1 0.5254 0.42544 0.672 0.300 0.000 0.028
#> GSM613673 1 0.5512 -0.01536 0.492 0.492 0.000 0.016
#> GSM613674 2 0.7201 0.28916 0.224 0.552 0.000 0.224
#> GSM613675 1 0.7433 0.56492 0.504 0.208 0.000 0.288
#> GSM613676 1 0.7407 0.56617 0.508 0.204 0.000 0.288
#> GSM613677 1 0.4907 0.43545 0.580 0.000 0.000 0.420
#> GSM613678 2 0.7796 -0.34163 0.360 0.392 0.000 0.248
#> GSM613679 2 0.0000 0.83565 0.000 1.000 0.000 0.000
#> GSM613680 1 0.5244 0.27805 0.600 0.388 0.000 0.012
#> GSM613681 1 0.5244 0.27805 0.600 0.388 0.000 0.012
#> GSM613682 1 0.4955 0.56087 0.772 0.144 0.000 0.084
#> GSM613683 1 0.3942 0.47923 0.764 0.000 0.000 0.236
#> GSM613684 1 0.4713 0.47263 0.640 0.000 0.000 0.360
#> GSM613685 2 0.7201 0.28916 0.224 0.552 0.000 0.224
#> GSM613686 2 0.0000 0.83565 0.000 1.000 0.000 0.000
#> GSM613687 1 0.5244 0.27805 0.600 0.388 0.000 0.012
#> GSM613688 1 0.5742 0.50788 0.596 0.036 0.000 0.368
#> GSM613689 4 0.3668 0.73218 0.004 0.000 0.188 0.808
#> GSM613690 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613691 4 0.3447 0.62717 0.128 0.000 0.020 0.852
#> GSM613692 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613693 4 0.1677 0.73954 0.012 0.000 0.040 0.948
#> GSM613694 4 0.2714 0.75637 0.004 0.000 0.112 0.884
#> GSM613695 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613696 4 0.4428 0.68500 0.004 0.000 0.276 0.720
#> GSM613697 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613698 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613699 4 0.3257 0.74832 0.004 0.000 0.152 0.844
#> GSM613700 2 0.0000 0.83565 0.000 1.000 0.000 0.000
#> GSM613701 2 0.0000 0.83565 0.000 1.000 0.000 0.000
#> GSM613702 2 0.0000 0.83565 0.000 1.000 0.000 0.000
#> GSM613703 2 0.0000 0.83565 0.000 1.000 0.000 0.000
#> GSM613704 2 0.0000 0.83565 0.000 1.000 0.000 0.000
#> GSM613705 4 0.4843 0.01803 0.396 0.000 0.000 0.604
#> GSM613706 1 0.5272 0.57978 0.680 0.032 0.000 0.288
#> GSM613707 2 0.7687 -0.02951 0.348 0.428 0.000 0.224
#> GSM613708 1 0.4790 0.49079 0.620 0.000 0.000 0.380
#> GSM613709 1 0.5466 0.17020 0.548 0.436 0.000 0.016
#> GSM613710 1 0.6634 0.55815 0.592 0.116 0.000 0.292
#> GSM613711 4 0.4535 0.67823 0.004 0.000 0.292 0.704
#> GSM613712 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613713 4 0.1677 0.73954 0.012 0.000 0.040 0.948
#> GSM613714 4 0.4699 0.64919 0.004 0.000 0.320 0.676
#> GSM613715 3 0.0336 0.99080 0.000 0.000 0.992 0.008
#> GSM613716 4 0.2593 0.75866 0.004 0.000 0.104 0.892
#> GSM613717 4 0.4535 0.67823 0.004 0.000 0.292 0.704
#> GSM613718 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613719 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613720 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613721 4 0.1677 0.73954 0.012 0.000 0.040 0.948
#> GSM613722 2 0.0000 0.83565 0.000 1.000 0.000 0.000
#> GSM613723 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613724 1 0.4948 0.05574 0.560 0.000 0.000 0.440
#> GSM613725 2 0.0000 0.83565 0.000 1.000 0.000 0.000
#> GSM613726 1 0.6613 0.62518 0.628 0.172 0.000 0.200
#> GSM613727 2 0.5127 0.37574 0.356 0.632 0.000 0.012
#> GSM613728 2 0.0000 0.83565 0.000 1.000 0.000 0.000
#> GSM613729 2 0.3479 0.68216 0.148 0.840 0.000 0.012
#> GSM613730 1 0.5495 0.54085 0.624 0.028 0.000 0.348
#> GSM613731 1 0.6613 0.62518 0.628 0.172 0.000 0.200
#> GSM613732 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613733 4 0.3335 0.62447 0.128 0.000 0.016 0.856
#> GSM613734 4 0.4925 0.26612 0.428 0.000 0.000 0.572
#> GSM613735 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613736 4 0.4608 0.66942 0.004 0.000 0.304 0.692
#> GSM613737 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613738 3 0.0188 0.99517 0.000 0.000 0.996 0.004
#> GSM613739 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613740 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613741 4 0.2376 0.75213 0.016 0.000 0.068 0.916
#> GSM613742 3 0.0188 0.99517 0.000 0.000 0.996 0.004
#> GSM613743 4 0.4608 0.66942 0.004 0.000 0.304 0.692
#> GSM613744 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613745 4 0.2329 0.75344 0.012 0.000 0.072 0.916
#> GSM613746 4 0.1677 0.73954 0.012 0.000 0.040 0.948
#> GSM613747 4 0.4925 0.26612 0.428 0.000 0.000 0.572
#> GSM613748 1 0.7433 0.56492 0.504 0.208 0.000 0.288
#> GSM613749 2 0.0000 0.83565 0.000 1.000 0.000 0.000
#> GSM613750 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613751 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613752 3 0.0000 0.99898 0.000 0.000 1.000 0.000
#> GSM613753 3 0.0000 0.99898 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
#> GSM613638 1 0.6631 0.1582 0.452 0.000 0.292 0.256 0.000
#> GSM613639 1 0.4518 0.3728 0.732 0.004 0.048 0.216 0.000
#> GSM613640 1 0.4589 0.3664 0.704 0.000 0.048 0.248 0.000
#> GSM613641 2 0.3861 0.5948 0.264 0.728 0.000 0.008 0.000
#> GSM613642 1 0.4924 0.1777 0.552 0.000 0.028 0.420 0.000
#> GSM613643 1 0.5776 0.2878 0.588 0.000 0.124 0.288 0.000
#> GSM613644 1 0.5613 0.2984 0.604 0.000 0.108 0.288 0.000
#> GSM613645 1 0.5233 0.2802 0.636 0.288 0.000 0.076 0.000
#> GSM613646 3 0.1989 0.7868 0.020 0.000 0.932 0.016 0.032
#> GSM613647 5 0.0290 0.9907 0.000 0.000 0.008 0.000 0.992
#> GSM613648 5 0.0162 0.9955 0.000 0.000 0.004 0.000 0.996
#> GSM613649 5 0.0162 0.9955 0.000 0.000 0.004 0.000 0.996
#> GSM613650 3 0.1988 0.7927 0.016 0.000 0.928 0.008 0.048
#> GSM613651 5 0.0000 0.9981 0.000 0.000 0.000 0.000 1.000
#> GSM613652 5 0.0000 0.9981 0.000 0.000 0.000 0.000 1.000
#> GSM613653 3 0.2504 0.7187 0.064 0.000 0.896 0.040 0.000
#> GSM613654 5 0.0000 0.9981 0.000 0.000 0.000 0.000 1.000
#> GSM613655 1 0.2859 0.4168 0.876 0.096 0.016 0.012 0.000
#> GSM613656 5 0.0000 0.9981 0.000 0.000 0.000 0.000 1.000
#> GSM613657 3 0.4999 0.6049 0.004 0.000 0.604 0.032 0.360
#> GSM613658 1 0.5390 0.2337 0.600 0.000 0.324 0.076 0.000
#> GSM613659 1 0.5275 0.2674 0.640 0.004 0.068 0.288 0.000
#> GSM613660 1 0.5361 0.3311 0.648 0.004 0.084 0.264 0.000
#> GSM613661 1 0.2305 0.4134 0.896 0.092 0.000 0.012 0.000
#> GSM613662 2 0.0404 0.9061 0.012 0.988 0.000 0.000 0.000
#> GSM613663 1 0.2361 0.4135 0.892 0.096 0.000 0.012 0.000
#> GSM613664 2 0.0000 0.9069 0.000 1.000 0.000 0.000 0.000
#> GSM613665 2 0.0404 0.9061 0.012 0.988 0.000 0.000 0.000
#> GSM613666 2 0.4546 0.2128 0.460 0.532 0.000 0.008 0.000
#> GSM613667 1 0.4866 0.1552 0.580 0.392 0.000 0.028 0.000
#> GSM613668 1 0.2753 0.3998 0.856 0.136 0.000 0.008 0.000
#> GSM613669 2 0.0000 0.9069 0.000 1.000 0.000 0.000 0.000
#> GSM613670 2 0.0000 0.9069 0.000 1.000 0.000 0.000 0.000
#> GSM613671 2 0.0000 0.9069 0.000 1.000 0.000 0.000 0.000
#> GSM613672 1 0.3805 0.3697 0.784 0.184 0.000 0.032 0.000
#> GSM613673 1 0.4833 0.0997 0.564 0.412 0.000 0.024 0.000
#> GSM613674 4 0.4229 0.6682 0.104 0.104 0.004 0.788 0.000
#> GSM613675 1 0.5119 0.1578 0.576 0.008 0.028 0.388 0.000
#> GSM613676 1 0.5109 0.1627 0.580 0.008 0.028 0.384 0.000
#> GSM613677 1 0.5905 0.2750 0.572 0.000 0.136 0.292 0.000
#> GSM613678 1 0.7033 0.0153 0.440 0.172 0.028 0.360 0.000
#> GSM613679 2 0.0000 0.9069 0.000 1.000 0.000 0.000 0.000
#> GSM613680 1 0.4959 0.3151 0.684 0.240 0.000 0.076 0.000
#> GSM613681 1 0.4959 0.3151 0.684 0.240 0.000 0.076 0.000
#> GSM613682 1 0.5136 0.3135 0.736 0.084 0.032 0.148 0.000
#> GSM613683 1 0.4410 0.3673 0.764 0.000 0.124 0.112 0.000
#> GSM613684 4 0.5847 -0.1467 0.424 0.000 0.096 0.480 0.000
#> GSM613685 4 0.4229 0.6682 0.104 0.104 0.004 0.788 0.000
#> GSM613686 2 0.0000 0.9069 0.000 1.000 0.000 0.000 0.000
#> GSM613687 1 0.4959 0.3151 0.684 0.240 0.000 0.076 0.000
#> GSM613688 1 0.5691 0.0692 0.536 0.000 0.088 0.376 0.000
#> GSM613689 3 0.3853 0.7738 0.008 0.000 0.804 0.036 0.152
#> GSM613690 5 0.0000 0.9981 0.000 0.000 0.000 0.000 1.000
#> GSM613691 3 0.4959 0.5286 0.160 0.000 0.712 0.128 0.000
#> GSM613692 5 0.0000 0.9981 0.000 0.000 0.000 0.000 1.000
#> GSM613693 3 0.1124 0.7571 0.004 0.000 0.960 0.036 0.000
#> GSM613694 3 0.3089 0.7915 0.012 0.000 0.872 0.040 0.076
#> GSM613695 5 0.0000 0.9981 0.000 0.000 0.000 0.000 1.000
#> GSM613696 3 0.4532 0.7193 0.004 0.000 0.712 0.036 0.248
#> GSM613697 5 0.0000 0.9981 0.000 0.000 0.000 0.000 1.000
#> GSM613698 5 0.0000 0.9981 0.000 0.000 0.000 0.000 1.000
#> GSM613699 3 0.3446 0.7869 0.008 0.000 0.840 0.036 0.116
#> GSM613700 2 0.0000 0.9069 0.000 1.000 0.000 0.000 0.000
#> GSM613701 2 0.0404 0.9061 0.012 0.988 0.000 0.000 0.000
#> GSM613702 2 0.0404 0.9061 0.012 0.988 0.000 0.000 0.000
#> GSM613703 2 0.0000 0.9069 0.000 1.000 0.000 0.000 0.000
#> GSM613704 2 0.0000 0.9069 0.000 1.000 0.000 0.000 0.000
#> GSM613705 1 0.6627 0.1564 0.452 0.000 0.296 0.252 0.000
#> GSM613706 1 0.4717 0.3675 0.704 0.004 0.048 0.244 0.000
#> GSM613707 4 0.2921 0.6233 0.148 0.004 0.004 0.844 0.000
#> GSM613708 1 0.5613 0.2984 0.604 0.000 0.108 0.288 0.000
#> GSM613709 1 0.5233 0.2802 0.636 0.288 0.000 0.076 0.000
#> GSM613710 1 0.4924 0.1777 0.552 0.000 0.028 0.420 0.000
#> GSM613711 3 0.4928 0.7176 0.012 0.000 0.684 0.040 0.264
#> GSM613712 5 0.0000 0.9981 0.000 0.000 0.000 0.000 1.000
#> GSM613713 3 0.1124 0.7611 0.004 0.000 0.960 0.036 0.000
#> GSM613714 3 0.5011 0.6927 0.012 0.000 0.660 0.036 0.292
#> GSM613715 5 0.0290 0.9907 0.000 0.000 0.008 0.000 0.992
#> GSM613716 3 0.2331 0.7961 0.016 0.000 0.908 0.008 0.068
#> GSM613717 3 0.4782 0.7193 0.012 0.000 0.692 0.032 0.264
#> GSM613718 5 0.0000 0.9981 0.000 0.000 0.000 0.000 1.000
#> GSM613719 5 0.0162 0.9955 0.000 0.000 0.004 0.000 0.996
#> GSM613720 5 0.0162 0.9955 0.000 0.000 0.004 0.000 0.996
#> GSM613721 3 0.1124 0.7571 0.004 0.000 0.960 0.036 0.000
#> GSM613722 2 0.0404 0.9061 0.012 0.988 0.000 0.000 0.000
#> GSM613723 5 0.0000 0.9981 0.000 0.000 0.000 0.000 1.000
#> GSM613724 1 0.5390 0.2337 0.600 0.000 0.324 0.076 0.000
#> GSM613725 2 0.0290 0.9066 0.008 0.992 0.000 0.000 0.000
#> GSM613726 1 0.4527 0.4060 0.780 0.080 0.020 0.120 0.000
#> GSM613727 2 0.4455 0.3608 0.404 0.588 0.000 0.008 0.000
#> GSM613728 2 0.0404 0.9061 0.012 0.988 0.000 0.000 0.000
#> GSM613729 2 0.3353 0.6922 0.196 0.796 0.000 0.008 0.000
#> GSM613730 1 0.5455 0.3302 0.636 0.004 0.088 0.272 0.000
#> GSM613731 1 0.4527 0.4060 0.780 0.080 0.020 0.120 0.000
#> GSM613732 5 0.0000 0.9981 0.000 0.000 0.000 0.000 1.000
#> GSM613733 3 0.5237 0.4884 0.160 0.000 0.684 0.156 0.000
#> GSM613734 1 0.5295 -0.1105 0.488 0.000 0.464 0.048 0.000
#> GSM613735 5 0.0000 0.9981 0.000 0.000 0.000 0.000 1.000
#> GSM613736 3 0.4997 0.7081 0.012 0.000 0.672 0.040 0.276
#> GSM613737 5 0.0162 0.9955 0.000 0.000 0.004 0.000 0.996
#> GSM613738 5 0.0162 0.9949 0.000 0.000 0.004 0.000 0.996
#> GSM613739 5 0.0000 0.9981 0.000 0.000 0.000 0.000 1.000
#> GSM613740 5 0.0000 0.9981 0.000 0.000 0.000 0.000 1.000
#> GSM613741 3 0.2450 0.7843 0.028 0.000 0.912 0.028 0.032
#> GSM613742 5 0.0162 0.9949 0.000 0.000 0.004 0.000 0.996
#> GSM613743 3 0.4997 0.7081 0.012 0.000 0.672 0.040 0.276
#> GSM613744 5 0.0000 0.9981 0.000 0.000 0.000 0.000 1.000
#> GSM613745 3 0.2362 0.7850 0.024 0.000 0.916 0.028 0.032
#> GSM613746 3 0.1124 0.7571 0.004 0.000 0.960 0.036 0.000
#> GSM613747 1 0.5295 -0.1105 0.488 0.000 0.464 0.048 0.000
#> GSM613748 1 0.5119 0.1578 0.576 0.008 0.028 0.388 0.000
#> GSM613749 2 0.0162 0.9069 0.004 0.996 0.000 0.000 0.000
#> GSM613750 5 0.0000 0.9981 0.000 0.000 0.000 0.000 1.000
#> GSM613751 5 0.0000 0.9981 0.000 0.000 0.000 0.000 1.000
#> GSM613752 5 0.0000 0.9981 0.000 0.000 0.000 0.000 1.000
#> GSM613753 5 0.0000 0.9981 0.000 0.000 0.000 0.000 1.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM613638 4 0.4029 0.5352 0.220 0.000 0.032 0.736 0.000 0.012
#> GSM613639 4 0.3764 0.6431 0.160 0.000 0.012 0.784 0.000 0.044
#> GSM613640 4 0.3257 0.6617 0.152 0.000 0.012 0.816 0.000 0.020
#> GSM613641 2 0.4811 0.5770 0.196 0.704 0.000 0.064 0.000 0.036
#> GSM613642 4 0.2668 0.6626 0.004 0.000 0.000 0.828 0.000 0.168
#> GSM613643 4 0.1820 0.6967 0.044 0.000 0.012 0.928 0.000 0.016
#> GSM613644 4 0.1332 0.7035 0.008 0.000 0.012 0.952 0.000 0.028
#> GSM613645 1 0.7367 0.3119 0.400 0.256 0.000 0.184 0.000 0.160
#> GSM613646 3 0.4749 0.6984 0.176 0.000 0.716 0.076 0.032 0.000
#> GSM613647 5 0.0260 0.9682 0.008 0.000 0.000 0.000 0.992 0.000
#> GSM613648 5 0.0146 0.9715 0.000 0.000 0.004 0.000 0.996 0.000
#> GSM613649 5 0.0146 0.9715 0.000 0.000 0.004 0.000 0.996 0.000
#> GSM613650 3 0.5103 0.6943 0.196 0.000 0.684 0.072 0.048 0.000
#> GSM613651 5 0.0000 0.9735 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613652 5 0.0000 0.9735 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613653 3 0.3098 0.4784 0.164 0.000 0.812 0.000 0.000 0.024
#> GSM613654 5 0.0000 0.9735 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613655 1 0.6360 0.2069 0.496 0.076 0.000 0.328 0.000 0.100
#> GSM613656 5 0.0000 0.9735 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613657 5 0.6807 -0.4060 0.296 0.000 0.312 0.024 0.360 0.008
#> GSM613658 1 0.3230 0.2268 0.776 0.000 0.012 0.212 0.000 0.000
#> GSM613659 4 0.3400 0.6991 0.044 0.000 0.008 0.816 0.000 0.132
#> GSM613660 4 0.2790 0.7060 0.080 0.000 0.028 0.872 0.000 0.020
#> GSM613661 1 0.6448 0.0995 0.420 0.072 0.000 0.404 0.000 0.104
#> GSM613662 2 0.0363 0.8652 0.000 0.988 0.000 0.000 0.000 0.012
#> GSM613663 1 0.6486 0.1066 0.420 0.076 0.000 0.400 0.000 0.104
#> GSM613664 2 0.0000 0.8631 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613665 2 0.0363 0.8652 0.000 0.988 0.000 0.000 0.000 0.012
#> GSM613666 2 0.6041 0.1991 0.348 0.512 0.000 0.072 0.000 0.068
#> GSM613667 1 0.6780 0.1467 0.420 0.360 0.000 0.128 0.000 0.092
#> GSM613668 1 0.6752 0.2287 0.452 0.116 0.000 0.328 0.000 0.104
#> GSM613669 2 0.0508 0.8609 0.012 0.984 0.000 0.000 0.000 0.004
#> GSM613670 2 0.0000 0.8631 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613671 2 0.0508 0.8609 0.012 0.984 0.000 0.000 0.000 0.004
#> GSM613672 1 0.7158 0.2785 0.424 0.156 0.000 0.284 0.000 0.136
#> GSM613673 2 0.6824 -0.1567 0.388 0.388 0.000 0.128 0.000 0.096
#> GSM613674 6 0.2504 0.9163 0.004 0.088 0.000 0.028 0.000 0.880
#> GSM613675 4 0.3494 0.6203 0.012 0.000 0.000 0.736 0.000 0.252
#> GSM613676 4 0.3470 0.6247 0.012 0.000 0.000 0.740 0.000 0.248
#> GSM613677 4 0.2164 0.6892 0.060 0.000 0.012 0.908 0.000 0.020
#> GSM613678 4 0.5993 0.3573 0.032 0.148 0.000 0.552 0.000 0.268
#> GSM613679 2 0.0000 0.8631 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613680 1 0.7411 0.3224 0.400 0.208 0.000 0.224 0.000 0.168
#> GSM613681 1 0.7411 0.3224 0.400 0.208 0.000 0.224 0.000 0.168
#> GSM613682 4 0.7066 -0.0784 0.352 0.080 0.000 0.356 0.000 0.212
#> GSM613683 1 0.4045 -0.0163 0.564 0.000 0.000 0.428 0.000 0.008
#> GSM613684 4 0.3692 0.5157 0.008 0.000 0.012 0.736 0.000 0.244
#> GSM613685 6 0.2504 0.9163 0.004 0.088 0.000 0.028 0.000 0.880
#> GSM613686 2 0.0146 0.8640 0.004 0.996 0.000 0.000 0.000 0.000
#> GSM613687 1 0.7411 0.3224 0.400 0.208 0.000 0.224 0.000 0.168
#> GSM613688 4 0.3616 0.6156 0.012 0.000 0.008 0.748 0.000 0.232
#> GSM613689 3 0.6776 0.5392 0.316 0.000 0.464 0.060 0.152 0.008
#> GSM613690 5 0.0000 0.9735 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613691 3 0.5317 0.4730 0.112 0.000 0.568 0.316 0.000 0.004
#> GSM613692 5 0.0000 0.9735 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613693 3 0.0508 0.6273 0.004 0.000 0.984 0.000 0.000 0.012
#> GSM613694 3 0.6329 0.5725 0.356 0.000 0.492 0.068 0.076 0.008
#> GSM613695 5 0.0000 0.9735 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613696 3 0.7000 0.4209 0.320 0.000 0.380 0.044 0.248 0.008
#> GSM613697 5 0.0000 0.9735 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613698 5 0.0000 0.9735 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613699 3 0.6579 0.5531 0.344 0.000 0.472 0.060 0.116 0.008
#> GSM613700 2 0.0000 0.8631 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613701 2 0.0363 0.8652 0.000 0.988 0.000 0.000 0.000 0.012
#> GSM613702 2 0.0363 0.8652 0.000 0.988 0.000 0.000 0.000 0.012
#> GSM613703 2 0.0146 0.8640 0.004 0.996 0.000 0.000 0.000 0.000
#> GSM613704 2 0.0000 0.8631 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613705 4 0.4056 0.5316 0.224 0.000 0.032 0.732 0.000 0.012
#> GSM613706 4 0.3411 0.6565 0.160 0.000 0.012 0.804 0.000 0.024
#> GSM613707 6 0.1957 0.8183 0.000 0.000 0.000 0.112 0.000 0.888
#> GSM613708 4 0.1332 0.7035 0.008 0.000 0.012 0.952 0.000 0.028
#> GSM613709 1 0.7367 0.3119 0.400 0.256 0.000 0.184 0.000 0.160
#> GSM613710 4 0.2778 0.6632 0.008 0.000 0.000 0.824 0.000 0.168
#> GSM613711 1 0.7267 -0.3917 0.360 0.000 0.300 0.068 0.264 0.008
#> GSM613712 5 0.0000 0.9735 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613713 3 0.1053 0.6366 0.020 0.000 0.964 0.004 0.000 0.012
#> GSM613714 1 0.7239 -0.3657 0.360 0.000 0.276 0.064 0.292 0.008
#> GSM613715 5 0.0260 0.9682 0.008 0.000 0.000 0.000 0.992 0.000
#> GSM613716 3 0.5482 0.6851 0.212 0.000 0.648 0.072 0.068 0.000
#> GSM613717 1 0.7280 -0.4081 0.340 0.000 0.320 0.068 0.264 0.008
#> GSM613718 5 0.0000 0.9735 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613719 5 0.0146 0.9715 0.000 0.000 0.004 0.000 0.996 0.000
#> GSM613720 5 0.0146 0.9715 0.000 0.000 0.004 0.000 0.996 0.000
#> GSM613721 3 0.0508 0.6273 0.004 0.000 0.984 0.000 0.000 0.012
#> GSM613722 2 0.0363 0.8652 0.000 0.988 0.000 0.000 0.000 0.012
#> GSM613723 5 0.0000 0.9735 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613724 1 0.3230 0.2268 0.776 0.000 0.012 0.212 0.000 0.000
#> GSM613725 2 0.0260 0.8650 0.000 0.992 0.000 0.000 0.000 0.008
#> GSM613726 4 0.6013 0.2930 0.276 0.060 0.000 0.564 0.000 0.100
#> GSM613727 2 0.5520 0.3150 0.340 0.560 0.000 0.060 0.000 0.040
#> GSM613728 2 0.0363 0.8652 0.000 0.988 0.000 0.000 0.000 0.012
#> GSM613729 2 0.4284 0.6564 0.132 0.768 0.000 0.060 0.000 0.040
#> GSM613730 4 0.2615 0.7083 0.088 0.000 0.028 0.876 0.000 0.008
#> GSM613731 4 0.6013 0.2930 0.276 0.060 0.000 0.564 0.000 0.100
#> GSM613732 5 0.0000 0.9735 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613733 3 0.5466 0.4351 0.120 0.000 0.532 0.344 0.000 0.004
#> GSM613734 1 0.2113 0.1980 0.912 0.000 0.032 0.048 0.000 0.008
#> GSM613735 5 0.0000 0.9735 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613736 1 0.7272 -0.3772 0.360 0.000 0.288 0.068 0.276 0.008
#> GSM613737 5 0.0146 0.9715 0.000 0.000 0.004 0.000 0.996 0.000
#> GSM613738 5 0.0146 0.9714 0.004 0.000 0.000 0.000 0.996 0.000
#> GSM613739 5 0.0000 0.9735 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613740 5 0.0000 0.9735 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613741 3 0.4528 0.6913 0.140 0.000 0.752 0.072 0.032 0.004
#> GSM613742 5 0.0146 0.9714 0.004 0.000 0.000 0.000 0.996 0.000
#> GSM613743 1 0.7272 -0.3772 0.360 0.000 0.288 0.068 0.276 0.008
#> GSM613744 5 0.0000 0.9735 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613745 3 0.4542 0.6928 0.136 0.000 0.752 0.076 0.032 0.004
#> GSM613746 3 0.0603 0.6237 0.004 0.000 0.980 0.000 0.000 0.016
#> GSM613747 1 0.2113 0.1980 0.912 0.000 0.032 0.048 0.000 0.008
#> GSM613748 4 0.3494 0.6203 0.012 0.000 0.000 0.736 0.000 0.252
#> GSM613749 2 0.0405 0.8643 0.008 0.988 0.000 0.000 0.000 0.004
#> GSM613750 5 0.0260 0.9697 0.000 0.000 0.000 0.000 0.992 0.008
#> GSM613751 5 0.0260 0.9697 0.000 0.000 0.000 0.000 0.992 0.008
#> GSM613752 5 0.0260 0.9697 0.000 0.000 0.000 0.000 0.992 0.008
#> GSM613753 5 0.0260 0.9697 0.000 0.000 0.000 0.000 0.992 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) k
#> ATC:hclust 97 0.015 2
#> ATC:hclust 91 0.220 3
#> ATC:hclust 90 0.344 4
#> ATC:hclust 73 0.413 5
#> ATC:hclust 83 0.316 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 27425 rows and 116 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'ATC' method.
#> Subgroups are detected by 'kmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 1.000 0.995 0.998 0.5041 0.496 0.496
#> 3 3 0.720 0.834 0.910 0.3190 0.741 0.523
#> 4 4 0.747 0.856 0.899 0.1227 0.795 0.475
#> 5 5 0.724 0.588 0.760 0.0595 0.946 0.793
#> 6 6 0.737 0.717 0.789 0.0361 0.920 0.679
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
#> GSM613638 2 0.0000 0.996 0.000 1.000
#> GSM613639 1 0.0000 1.000 1.000 0.000
#> GSM613640 1 0.0000 1.000 1.000 0.000
#> GSM613641 1 0.0000 1.000 1.000 0.000
#> GSM613642 1 0.0000 1.000 1.000 0.000
#> GSM613643 1 0.0000 1.000 1.000 0.000
#> GSM613644 1 0.0000 1.000 1.000 0.000
#> GSM613645 1 0.0000 1.000 1.000 0.000
#> GSM613646 2 0.0000 0.996 0.000 1.000
#> GSM613647 2 0.0000 0.996 0.000 1.000
#> GSM613648 2 0.0000 0.996 0.000 1.000
#> GSM613649 2 0.0000 0.996 0.000 1.000
#> GSM613650 2 0.0000 0.996 0.000 1.000
#> GSM613651 2 0.0000 0.996 0.000 1.000
#> GSM613652 2 0.0000 0.996 0.000 1.000
#> GSM613653 2 0.0000 0.996 0.000 1.000
#> GSM613654 2 0.0000 0.996 0.000 1.000
#> GSM613655 1 0.0000 1.000 1.000 0.000
#> GSM613656 2 0.0000 0.996 0.000 1.000
#> GSM613657 2 0.0000 0.996 0.000 1.000
#> GSM613658 2 0.0938 0.984 0.012 0.988
#> GSM613659 1 0.0000 1.000 1.000 0.000
#> GSM613660 1 0.0000 1.000 1.000 0.000
#> GSM613661 1 0.0000 1.000 1.000 0.000
#> GSM613662 1 0.0000 1.000 1.000 0.000
#> GSM613663 1 0.0000 1.000 1.000 0.000
#> GSM613664 1 0.0000 1.000 1.000 0.000
#> GSM613665 1 0.0000 1.000 1.000 0.000
#> GSM613666 1 0.0000 1.000 1.000 0.000
#> GSM613667 1 0.0000 1.000 1.000 0.000
#> GSM613668 1 0.0000 1.000 1.000 0.000
#> GSM613669 1 0.0000 1.000 1.000 0.000
#> GSM613670 1 0.0000 1.000 1.000 0.000
#> GSM613671 1 0.0000 1.000 1.000 0.000
#> GSM613672 1 0.0000 1.000 1.000 0.000
#> GSM613673 1 0.0000 1.000 1.000 0.000
#> GSM613674 1 0.0000 1.000 1.000 0.000
#> GSM613675 1 0.0000 1.000 1.000 0.000
#> GSM613676 1 0.0000 1.000 1.000 0.000
#> GSM613677 1 0.0000 1.000 1.000 0.000
#> GSM613678 1 0.0000 1.000 1.000 0.000
#> GSM613679 1 0.0000 1.000 1.000 0.000
#> GSM613680 1 0.0000 1.000 1.000 0.000
#> GSM613681 1 0.0000 1.000 1.000 0.000
#> GSM613682 1 0.0000 1.000 1.000 0.000
#> GSM613683 1 0.0000 1.000 1.000 0.000
#> GSM613684 1 0.1414 0.979 0.980 0.020
#> GSM613685 1 0.0000 1.000 1.000 0.000
#> GSM613686 1 0.0000 1.000 1.000 0.000
#> GSM613687 1 0.0000 1.000 1.000 0.000
#> GSM613688 1 0.0000 1.000 1.000 0.000
#> GSM613689 2 0.0000 0.996 0.000 1.000
#> GSM613690 2 0.0000 0.996 0.000 1.000
#> GSM613691 1 0.0000 1.000 1.000 0.000
#> GSM613692 2 0.0000 0.996 0.000 1.000
#> GSM613693 2 0.0000 0.996 0.000 1.000
#> GSM613694 2 0.0000 0.996 0.000 1.000
#> GSM613695 2 0.0000 0.996 0.000 1.000
#> GSM613696 2 0.0000 0.996 0.000 1.000
#> GSM613697 2 0.0000 0.996 0.000 1.000
#> GSM613698 2 0.0000 0.996 0.000 1.000
#> GSM613699 2 0.0000 0.996 0.000 1.000
#> GSM613700 1 0.0000 1.000 1.000 0.000
#> GSM613701 1 0.0000 1.000 1.000 0.000
#> GSM613702 1 0.0000 1.000 1.000 0.000
#> GSM613703 1 0.0000 1.000 1.000 0.000
#> GSM613704 1 0.0000 1.000 1.000 0.000
#> GSM613705 2 0.0000 0.996 0.000 1.000
#> GSM613706 1 0.0000 1.000 1.000 0.000
#> GSM613707 1 0.0000 1.000 1.000 0.000
#> GSM613708 1 0.0000 1.000 1.000 0.000
#> GSM613709 1 0.0000 1.000 1.000 0.000
#> GSM613710 1 0.0000 1.000 1.000 0.000
#> GSM613711 2 0.0000 0.996 0.000 1.000
#> GSM613712 2 0.0000 0.996 0.000 1.000
#> GSM613713 2 0.0000 0.996 0.000 1.000
#> GSM613714 2 0.0000 0.996 0.000 1.000
#> GSM613715 2 0.0000 0.996 0.000 1.000
#> GSM613716 2 0.0000 0.996 0.000 1.000
#> GSM613717 2 0.0000 0.996 0.000 1.000
#> GSM613718 2 0.0000 0.996 0.000 1.000
#> GSM613719 2 0.0000 0.996 0.000 1.000
#> GSM613720 2 0.0000 0.996 0.000 1.000
#> GSM613721 2 0.7745 0.705 0.228 0.772
#> GSM613722 1 0.0000 1.000 1.000 0.000
#> GSM613723 2 0.0000 0.996 0.000 1.000
#> GSM613724 1 0.0000 1.000 1.000 0.000
#> GSM613725 1 0.0000 1.000 1.000 0.000
#> GSM613726 1 0.0000 1.000 1.000 0.000
#> GSM613727 1 0.0000 1.000 1.000 0.000
#> GSM613728 1 0.0000 1.000 1.000 0.000
#> GSM613729 1 0.0000 1.000 1.000 0.000
#> GSM613730 1 0.0000 1.000 1.000 0.000
#> GSM613731 1 0.0000 1.000 1.000 0.000
#> GSM613732 2 0.0000 0.996 0.000 1.000
#> GSM613733 2 0.0000 0.996 0.000 1.000
#> GSM613734 2 0.0000 0.996 0.000 1.000
#> GSM613735 2 0.0000 0.996 0.000 1.000
#> GSM613736 2 0.0000 0.996 0.000 1.000
#> GSM613737 2 0.0000 0.996 0.000 1.000
#> GSM613738 2 0.0000 0.996 0.000 1.000
#> GSM613739 2 0.0000 0.996 0.000 1.000
#> GSM613740 2 0.0000 0.996 0.000 1.000
#> GSM613741 2 0.0000 0.996 0.000 1.000
#> GSM613742 2 0.0000 0.996 0.000 1.000
#> GSM613743 2 0.0000 0.996 0.000 1.000
#> GSM613744 2 0.0000 0.996 0.000 1.000
#> GSM613745 2 0.0000 0.996 0.000 1.000
#> GSM613746 2 0.0000 0.996 0.000 1.000
#> GSM613747 2 0.0000 0.996 0.000 1.000
#> GSM613748 1 0.0000 1.000 1.000 0.000
#> GSM613749 1 0.0000 1.000 1.000 0.000
#> GSM613750 2 0.0000 0.996 0.000 1.000
#> GSM613751 2 0.0000 0.996 0.000 1.000
#> GSM613752 2 0.0000 0.996 0.000 1.000
#> GSM613753 2 0.0000 0.996 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM613638 2 0.1643 0.8467 0.000 0.956 0.044
#> GSM613639 1 0.5882 0.6039 0.652 0.348 0.000
#> GSM613640 2 0.2165 0.8358 0.064 0.936 0.000
#> GSM613641 1 0.0747 0.9074 0.984 0.016 0.000
#> GSM613642 2 0.2165 0.8365 0.064 0.936 0.000
#> GSM613643 2 0.1753 0.8408 0.048 0.952 0.000
#> GSM613644 2 0.1753 0.8408 0.048 0.952 0.000
#> GSM613645 1 0.3816 0.8617 0.852 0.148 0.000
#> GSM613646 2 0.3038 0.8276 0.000 0.896 0.104
#> GSM613647 3 0.0747 0.9405 0.000 0.016 0.984
#> GSM613648 3 0.1411 0.9319 0.000 0.036 0.964
#> GSM613649 3 0.1411 0.9319 0.000 0.036 0.964
#> GSM613650 2 0.5016 0.6958 0.000 0.760 0.240
#> GSM613651 3 0.0747 0.9405 0.000 0.016 0.984
#> GSM613652 3 0.0747 0.9405 0.000 0.016 0.984
#> GSM613653 2 0.3267 0.8212 0.000 0.884 0.116
#> GSM613654 3 0.0747 0.9405 0.000 0.016 0.984
#> GSM613655 1 0.5497 0.7016 0.708 0.292 0.000
#> GSM613656 3 0.0747 0.9405 0.000 0.016 0.984
#> GSM613657 3 0.1529 0.9296 0.000 0.040 0.960
#> GSM613658 2 0.1999 0.8413 0.012 0.952 0.036
#> GSM613659 2 0.2165 0.8361 0.064 0.936 0.000
#> GSM613660 2 0.2356 0.8345 0.072 0.928 0.000
#> GSM613661 1 0.5926 0.5880 0.644 0.356 0.000
#> GSM613662 1 0.0424 0.9082 0.992 0.008 0.000
#> GSM613663 1 0.3879 0.8593 0.848 0.152 0.000
#> GSM613664 1 0.0424 0.9082 0.992 0.008 0.000
#> GSM613665 1 0.0424 0.9082 0.992 0.008 0.000
#> GSM613666 1 0.0747 0.9074 0.984 0.016 0.000
#> GSM613667 1 0.0747 0.9074 0.984 0.016 0.000
#> GSM613668 1 0.3879 0.8593 0.848 0.152 0.000
#> GSM613669 1 0.0747 0.9074 0.984 0.016 0.000
#> GSM613670 1 0.0424 0.9082 0.992 0.008 0.000
#> GSM613671 1 0.0747 0.9074 0.984 0.016 0.000
#> GSM613672 1 0.4235 0.8409 0.824 0.176 0.000
#> GSM613673 1 0.1289 0.9059 0.968 0.032 0.000
#> GSM613674 1 0.0424 0.9082 0.992 0.008 0.000
#> GSM613675 1 0.4974 0.7756 0.764 0.236 0.000
#> GSM613676 2 0.4178 0.7328 0.172 0.828 0.000
#> GSM613677 2 0.2066 0.8365 0.060 0.940 0.000
#> GSM613678 1 0.2537 0.8909 0.920 0.080 0.000
#> GSM613679 1 0.0424 0.9082 0.992 0.008 0.000
#> GSM613680 1 0.4121 0.8474 0.832 0.168 0.000
#> GSM613681 1 0.3816 0.8617 0.852 0.148 0.000
#> GSM613682 1 0.4235 0.8415 0.824 0.176 0.000
#> GSM613683 2 0.1860 0.8400 0.052 0.948 0.000
#> GSM613684 2 0.1453 0.8447 0.008 0.968 0.024
#> GSM613685 1 0.1860 0.8869 0.948 0.052 0.000
#> GSM613686 1 0.0000 0.9080 1.000 0.000 0.000
#> GSM613687 1 0.3879 0.8593 0.848 0.152 0.000
#> GSM613688 2 0.5621 0.4723 0.308 0.692 0.000
#> GSM613689 3 0.1529 0.9296 0.000 0.040 0.960
#> GSM613690 3 0.0000 0.9432 0.000 0.000 1.000
#> GSM613691 2 0.1289 0.8431 0.032 0.968 0.000
#> GSM613692 3 0.0747 0.9405 0.000 0.016 0.984
#> GSM613693 2 0.3192 0.8231 0.000 0.888 0.112
#> GSM613694 3 0.6079 0.3362 0.000 0.388 0.612
#> GSM613695 3 0.0000 0.9432 0.000 0.000 1.000
#> GSM613696 3 0.1529 0.9296 0.000 0.040 0.960
#> GSM613697 3 0.0747 0.9405 0.000 0.016 0.984
#> GSM613698 3 0.0000 0.9432 0.000 0.000 1.000
#> GSM613699 3 0.6126 0.3013 0.000 0.400 0.600
#> GSM613700 1 0.0424 0.9082 0.992 0.008 0.000
#> GSM613701 1 0.0424 0.9082 0.992 0.008 0.000
#> GSM613702 1 0.0424 0.9082 0.992 0.008 0.000
#> GSM613703 1 0.0237 0.9080 0.996 0.004 0.000
#> GSM613704 1 0.0424 0.9082 0.992 0.008 0.000
#> GSM613705 2 0.4178 0.7789 0.000 0.828 0.172
#> GSM613706 2 0.2165 0.8358 0.064 0.936 0.000
#> GSM613707 2 0.6305 -0.0892 0.484 0.516 0.000
#> GSM613708 2 0.2165 0.8358 0.064 0.936 0.000
#> GSM613709 1 0.1860 0.9012 0.948 0.052 0.000
#> GSM613710 2 0.4178 0.7328 0.172 0.828 0.000
#> GSM613711 3 0.3267 0.8546 0.000 0.116 0.884
#> GSM613712 3 0.0747 0.9405 0.000 0.016 0.984
#> GSM613713 2 0.6008 0.4395 0.000 0.628 0.372
#> GSM613714 3 0.1411 0.9319 0.000 0.036 0.964
#> GSM613715 3 0.0000 0.9432 0.000 0.000 1.000
#> GSM613716 2 0.4399 0.7596 0.000 0.812 0.188
#> GSM613717 2 0.4605 0.7405 0.000 0.796 0.204
#> GSM613718 3 0.0000 0.9432 0.000 0.000 1.000
#> GSM613719 3 0.1411 0.9319 0.000 0.036 0.964
#> GSM613720 3 0.1289 0.9337 0.000 0.032 0.968
#> GSM613721 2 0.3295 0.8301 0.008 0.896 0.096
#> GSM613722 1 0.0424 0.9082 0.992 0.008 0.000
#> GSM613723 3 0.0747 0.9405 0.000 0.016 0.984
#> GSM613724 2 0.1753 0.8408 0.048 0.952 0.000
#> GSM613725 1 0.0424 0.9082 0.992 0.008 0.000
#> GSM613726 1 0.3619 0.8680 0.864 0.136 0.000
#> GSM613727 1 0.0747 0.9074 0.984 0.016 0.000
#> GSM613728 1 0.0424 0.9082 0.992 0.008 0.000
#> GSM613729 1 0.0747 0.9074 0.984 0.016 0.000
#> GSM613730 2 0.2066 0.8365 0.060 0.940 0.000
#> GSM613731 1 0.6008 0.5557 0.628 0.372 0.000
#> GSM613732 3 0.0000 0.9432 0.000 0.000 1.000
#> GSM613733 2 0.3038 0.8276 0.000 0.896 0.104
#> GSM613734 2 0.3826 0.8029 0.008 0.868 0.124
#> GSM613735 3 0.0747 0.9405 0.000 0.016 0.984
#> GSM613736 2 0.6062 0.4094 0.000 0.616 0.384
#> GSM613737 3 0.0000 0.9432 0.000 0.000 1.000
#> GSM613738 3 0.0747 0.9405 0.000 0.016 0.984
#> GSM613739 3 0.0747 0.9405 0.000 0.016 0.984
#> GSM613740 3 0.0747 0.9398 0.000 0.016 0.984
#> GSM613741 2 0.4291 0.7683 0.000 0.820 0.180
#> GSM613742 3 0.0747 0.9405 0.000 0.016 0.984
#> GSM613743 3 0.1529 0.9296 0.000 0.040 0.960
#> GSM613744 3 0.0747 0.9398 0.000 0.016 0.984
#> GSM613745 2 0.4291 0.7683 0.000 0.820 0.180
#> GSM613746 2 0.3686 0.8030 0.000 0.860 0.140
#> GSM613747 3 0.6305 -0.0490 0.000 0.484 0.516
#> GSM613748 1 0.5397 0.7234 0.720 0.280 0.000
#> GSM613749 1 0.0424 0.9082 0.992 0.008 0.000
#> GSM613750 3 0.0000 0.9432 0.000 0.000 1.000
#> GSM613751 3 0.0747 0.9398 0.000 0.016 0.984
#> GSM613752 3 0.0000 0.9432 0.000 0.000 1.000
#> GSM613753 3 0.0000 0.9432 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 1 0.4889 0.590 0.636 0.000 0.004 0.360
#> GSM613639 1 0.2408 0.831 0.896 0.104 0.000 0.000
#> GSM613640 1 0.3852 0.842 0.808 0.012 0.000 0.180
#> GSM613641 2 0.2973 0.869 0.144 0.856 0.000 0.000
#> GSM613642 1 0.3969 0.839 0.804 0.016 0.000 0.180
#> GSM613643 1 0.3681 0.842 0.816 0.008 0.000 0.176
#> GSM613644 1 0.3808 0.834 0.808 0.004 0.004 0.184
#> GSM613645 1 0.2647 0.820 0.880 0.120 0.000 0.000
#> GSM613646 4 0.1398 0.864 0.040 0.004 0.000 0.956
#> GSM613647 3 0.0469 0.941 0.012 0.000 0.988 0.000
#> GSM613648 3 0.3311 0.832 0.000 0.000 0.828 0.172
#> GSM613649 3 0.3311 0.832 0.000 0.000 0.828 0.172
#> GSM613650 4 0.0524 0.869 0.004 0.000 0.008 0.988
#> GSM613651 3 0.0592 0.941 0.016 0.000 0.984 0.000
#> GSM613652 3 0.0592 0.941 0.016 0.000 0.984 0.000
#> GSM613653 4 0.1398 0.865 0.040 0.000 0.004 0.956
#> GSM613654 3 0.0592 0.941 0.016 0.000 0.984 0.000
#> GSM613655 1 0.2408 0.831 0.896 0.104 0.000 0.000
#> GSM613656 3 0.0592 0.941 0.016 0.000 0.984 0.000
#> GSM613657 3 0.4643 0.522 0.000 0.000 0.656 0.344
#> GSM613658 1 0.3099 0.850 0.876 0.000 0.020 0.104
#> GSM613659 1 0.3969 0.839 0.804 0.016 0.000 0.180
#> GSM613660 1 0.4012 0.836 0.800 0.016 0.000 0.184
#> GSM613661 1 0.2281 0.834 0.904 0.096 0.000 0.000
#> GSM613662 2 0.0000 0.930 0.000 1.000 0.000 0.000
#> GSM613663 1 0.2760 0.813 0.872 0.128 0.000 0.000
#> GSM613664 2 0.0000 0.930 0.000 1.000 0.000 0.000
#> GSM613665 2 0.0188 0.929 0.004 0.996 0.000 0.000
#> GSM613666 2 0.2973 0.870 0.144 0.856 0.000 0.000
#> GSM613667 2 0.3024 0.867 0.148 0.852 0.000 0.000
#> GSM613668 1 0.2760 0.813 0.872 0.128 0.000 0.000
#> GSM613669 2 0.1792 0.908 0.068 0.932 0.000 0.000
#> GSM613670 2 0.0000 0.930 0.000 1.000 0.000 0.000
#> GSM613671 2 0.1792 0.908 0.068 0.932 0.000 0.000
#> GSM613672 1 0.2281 0.834 0.904 0.096 0.000 0.000
#> GSM613673 2 0.3764 0.792 0.216 0.784 0.000 0.000
#> GSM613674 2 0.0188 0.928 0.004 0.996 0.000 0.000
#> GSM613675 1 0.3828 0.857 0.848 0.084 0.000 0.068
#> GSM613676 1 0.4149 0.845 0.804 0.028 0.000 0.168
#> GSM613677 1 0.4054 0.836 0.796 0.016 0.000 0.188
#> GSM613678 2 0.4830 0.412 0.392 0.608 0.000 0.000
#> GSM613679 2 0.0000 0.930 0.000 1.000 0.000 0.000
#> GSM613680 1 0.2589 0.823 0.884 0.116 0.000 0.000
#> GSM613681 1 0.4072 0.641 0.748 0.252 0.000 0.000
#> GSM613682 1 0.2408 0.831 0.896 0.104 0.000 0.000
#> GSM613683 1 0.1722 0.857 0.944 0.008 0.000 0.048
#> GSM613684 1 0.4074 0.820 0.792 0.004 0.008 0.196
#> GSM613685 2 0.1398 0.904 0.040 0.956 0.000 0.004
#> GSM613686 2 0.0188 0.929 0.004 0.996 0.000 0.000
#> GSM613687 1 0.2647 0.820 0.880 0.120 0.000 0.000
#> GSM613688 1 0.4322 0.850 0.804 0.044 0.000 0.152
#> GSM613689 4 0.3528 0.746 0.000 0.000 0.192 0.808
#> GSM613690 3 0.1489 0.943 0.004 0.000 0.952 0.044
#> GSM613691 4 0.3982 0.646 0.220 0.004 0.000 0.776
#> GSM613692 3 0.0592 0.941 0.016 0.000 0.984 0.000
#> GSM613693 4 0.1489 0.864 0.044 0.004 0.000 0.952
#> GSM613694 4 0.3172 0.781 0.000 0.000 0.160 0.840
#> GSM613695 3 0.1302 0.942 0.000 0.000 0.956 0.044
#> GSM613696 4 0.3486 0.749 0.000 0.000 0.188 0.812
#> GSM613697 3 0.0592 0.941 0.016 0.000 0.984 0.000
#> GSM613698 3 0.1388 0.944 0.012 0.000 0.960 0.028
#> GSM613699 4 0.3123 0.785 0.000 0.000 0.156 0.844
#> GSM613700 2 0.0000 0.930 0.000 1.000 0.000 0.000
#> GSM613701 2 0.0188 0.929 0.004 0.996 0.000 0.000
#> GSM613702 2 0.0188 0.929 0.004 0.996 0.000 0.000
#> GSM613703 2 0.0188 0.929 0.004 0.996 0.000 0.000
#> GSM613704 2 0.0000 0.930 0.000 1.000 0.000 0.000
#> GSM613705 4 0.1854 0.865 0.048 0.000 0.012 0.940
#> GSM613706 1 0.2805 0.859 0.888 0.012 0.000 0.100
#> GSM613707 1 0.4356 0.850 0.804 0.048 0.000 0.148
#> GSM613708 1 0.2867 0.860 0.884 0.012 0.000 0.104
#> GSM613709 2 0.4356 0.674 0.292 0.708 0.000 0.000
#> GSM613710 1 0.4149 0.845 0.804 0.028 0.000 0.168
#> GSM613711 4 0.2408 0.828 0.000 0.000 0.104 0.896
#> GSM613712 3 0.1452 0.944 0.008 0.000 0.956 0.036
#> GSM613713 4 0.0376 0.868 0.004 0.000 0.004 0.992
#> GSM613714 4 0.3610 0.743 0.000 0.000 0.200 0.800
#> GSM613715 3 0.1302 0.942 0.000 0.000 0.956 0.044
#> GSM613716 4 0.1022 0.867 0.032 0.000 0.000 0.968
#> GSM613717 4 0.0000 0.868 0.000 0.000 0.000 1.000
#> GSM613718 3 0.2111 0.939 0.024 0.000 0.932 0.044
#> GSM613719 3 0.3266 0.833 0.000 0.000 0.832 0.168
#> GSM613720 3 0.1557 0.940 0.000 0.000 0.944 0.056
#> GSM613721 4 0.1489 0.864 0.044 0.004 0.000 0.952
#> GSM613722 2 0.0000 0.930 0.000 1.000 0.000 0.000
#> GSM613723 3 0.1118 0.934 0.036 0.000 0.964 0.000
#> GSM613724 1 0.2345 0.855 0.900 0.000 0.000 0.100
#> GSM613725 2 0.0000 0.930 0.000 1.000 0.000 0.000
#> GSM613726 1 0.3873 0.689 0.772 0.228 0.000 0.000
#> GSM613727 2 0.3024 0.867 0.148 0.852 0.000 0.000
#> GSM613728 2 0.0188 0.929 0.004 0.996 0.000 0.000
#> GSM613729 2 0.2921 0.872 0.140 0.860 0.000 0.000
#> GSM613730 1 0.4054 0.836 0.796 0.016 0.000 0.188
#> GSM613731 1 0.1792 0.847 0.932 0.068 0.000 0.000
#> GSM613732 3 0.2002 0.940 0.020 0.000 0.936 0.044
#> GSM613733 4 0.1398 0.864 0.040 0.004 0.000 0.956
#> GSM613734 4 0.5973 0.432 0.332 0.000 0.056 0.612
#> GSM613735 3 0.0592 0.941 0.016 0.000 0.984 0.000
#> GSM613736 4 0.0592 0.866 0.000 0.000 0.016 0.984
#> GSM613737 3 0.1389 0.943 0.000 0.000 0.952 0.048
#> GSM613738 3 0.0592 0.941 0.016 0.000 0.984 0.000
#> GSM613739 3 0.0592 0.941 0.016 0.000 0.984 0.000
#> GSM613740 3 0.1576 0.941 0.004 0.000 0.948 0.048
#> GSM613741 4 0.1398 0.865 0.040 0.000 0.004 0.956
#> GSM613742 3 0.0592 0.941 0.016 0.000 0.984 0.000
#> GSM613743 4 0.3668 0.755 0.004 0.000 0.188 0.808
#> GSM613744 3 0.1576 0.941 0.004 0.000 0.948 0.048
#> GSM613745 4 0.1398 0.865 0.040 0.000 0.004 0.956
#> GSM613746 4 0.1489 0.864 0.044 0.004 0.000 0.952
#> GSM613747 4 0.5038 0.583 0.012 0.000 0.336 0.652
#> GSM613748 1 0.3009 0.862 0.892 0.056 0.000 0.052
#> GSM613749 2 0.0000 0.930 0.000 1.000 0.000 0.000
#> GSM613750 3 0.2408 0.935 0.036 0.000 0.920 0.044
#> GSM613751 3 0.2494 0.934 0.036 0.000 0.916 0.048
#> GSM613752 3 0.2408 0.935 0.036 0.000 0.920 0.044
#> GSM613753 3 0.2408 0.935 0.036 0.000 0.920 0.044
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM613638 4 0.6155 0.4846 0.336 0.000 0.148 0.516 0.000
#> GSM613639 1 0.1626 0.4309 0.940 0.016 0.000 0.044 0.000
#> GSM613640 1 0.4559 -0.6531 0.512 0.000 0.008 0.480 0.000
#> GSM613641 2 0.4298 0.6098 0.352 0.640 0.000 0.008 0.000
#> GSM613642 4 0.4481 0.7734 0.416 0.000 0.008 0.576 0.000
#> GSM613643 1 0.4560 -0.6519 0.508 0.000 0.008 0.484 0.000
#> GSM613644 1 0.4560 -0.6609 0.508 0.000 0.008 0.484 0.000
#> GSM613645 1 0.0609 0.4485 0.980 0.000 0.000 0.020 0.000
#> GSM613646 3 0.1851 0.8778 0.000 0.000 0.912 0.088 0.000
#> GSM613647 5 0.1732 0.8949 0.000 0.000 0.000 0.080 0.920
#> GSM613648 5 0.4101 0.7384 0.000 0.000 0.184 0.048 0.768
#> GSM613649 5 0.4096 0.7246 0.000 0.000 0.200 0.040 0.760
#> GSM613650 3 0.0324 0.8873 0.000 0.000 0.992 0.004 0.004
#> GSM613651 5 0.1908 0.8925 0.000 0.000 0.000 0.092 0.908
#> GSM613652 5 0.1851 0.8917 0.000 0.000 0.000 0.088 0.912
#> GSM613653 3 0.1851 0.8778 0.000 0.000 0.912 0.088 0.000
#> GSM613654 5 0.2074 0.8891 0.000 0.000 0.000 0.104 0.896
#> GSM613655 1 0.0798 0.4513 0.976 0.016 0.000 0.008 0.000
#> GSM613656 5 0.1792 0.8922 0.000 0.000 0.000 0.084 0.916
#> GSM613657 5 0.5519 0.2061 0.000 0.000 0.412 0.068 0.520
#> GSM613658 1 0.4481 -0.4621 0.576 0.000 0.008 0.416 0.000
#> GSM613659 4 0.4538 0.7627 0.452 0.000 0.008 0.540 0.000
#> GSM613660 4 0.4562 0.6785 0.492 0.000 0.008 0.500 0.000
#> GSM613661 1 0.1270 0.4142 0.948 0.000 0.000 0.052 0.000
#> GSM613662 2 0.0162 0.8289 0.004 0.996 0.000 0.000 0.000
#> GSM613663 1 0.0510 0.4522 0.984 0.016 0.000 0.000 0.000
#> GSM613664 2 0.0000 0.8289 0.000 1.000 0.000 0.000 0.000
#> GSM613665 2 0.3596 0.7453 0.212 0.776 0.000 0.012 0.000
#> GSM613666 2 0.4522 0.5253 0.440 0.552 0.000 0.008 0.000
#> GSM613667 2 0.4562 0.4497 0.492 0.500 0.000 0.008 0.000
#> GSM613668 1 0.1211 0.4501 0.960 0.016 0.000 0.024 0.000
#> GSM613669 2 0.2753 0.7823 0.136 0.856 0.000 0.008 0.000
#> GSM613670 2 0.0162 0.8287 0.000 0.996 0.000 0.004 0.000
#> GSM613671 2 0.2753 0.7823 0.136 0.856 0.000 0.008 0.000
#> GSM613672 1 0.0000 0.4482 1.000 0.000 0.000 0.000 0.000
#> GSM613673 1 0.4655 -0.4437 0.512 0.476 0.000 0.012 0.000
#> GSM613674 2 0.2488 0.7636 0.004 0.872 0.000 0.124 0.000
#> GSM613675 1 0.4426 -0.2885 0.612 0.004 0.004 0.380 0.000
#> GSM613676 4 0.4651 0.7583 0.428 0.004 0.008 0.560 0.000
#> GSM613677 1 0.4560 -0.6609 0.508 0.000 0.008 0.484 0.000
#> GSM613678 1 0.5931 0.2330 0.596 0.204 0.000 0.200 0.000
#> GSM613679 2 0.0000 0.8289 0.000 1.000 0.000 0.000 0.000
#> GSM613680 1 0.0609 0.4485 0.980 0.000 0.000 0.020 0.000
#> GSM613681 1 0.2144 0.4258 0.912 0.068 0.000 0.020 0.000
#> GSM613682 1 0.2690 0.3484 0.844 0.000 0.000 0.156 0.000
#> GSM613683 1 0.4201 -0.4531 0.592 0.000 0.000 0.408 0.000
#> GSM613684 4 0.4387 0.7296 0.348 0.000 0.012 0.640 0.000
#> GSM613685 2 0.5892 0.5613 0.180 0.600 0.000 0.220 0.000
#> GSM613686 2 0.0290 0.8285 0.000 0.992 0.000 0.008 0.000
#> GSM613687 1 0.0609 0.4485 0.980 0.000 0.000 0.020 0.000
#> GSM613688 4 0.4706 0.5226 0.488 0.004 0.008 0.500 0.000
#> GSM613689 3 0.3169 0.8471 0.000 0.000 0.856 0.060 0.084
#> GSM613690 5 0.1282 0.8958 0.000 0.000 0.004 0.044 0.952
#> GSM613691 3 0.4394 0.7225 0.048 0.000 0.732 0.220 0.000
#> GSM613692 5 0.1851 0.8926 0.000 0.000 0.000 0.088 0.912
#> GSM613693 3 0.2179 0.8704 0.000 0.000 0.888 0.112 0.000
#> GSM613694 3 0.0992 0.8852 0.000 0.000 0.968 0.024 0.008
#> GSM613695 5 0.1638 0.8930 0.000 0.000 0.004 0.064 0.932
#> GSM613696 3 0.1195 0.8849 0.000 0.000 0.960 0.028 0.012
#> GSM613697 5 0.1965 0.8925 0.000 0.000 0.000 0.096 0.904
#> GSM613698 5 0.1197 0.8963 0.000 0.000 0.000 0.048 0.952
#> GSM613699 3 0.0290 0.8873 0.000 0.000 0.992 0.000 0.008
#> GSM613700 2 0.0000 0.8289 0.000 1.000 0.000 0.000 0.000
#> GSM613701 2 0.3141 0.7774 0.152 0.832 0.000 0.016 0.000
#> GSM613702 2 0.3143 0.7578 0.204 0.796 0.000 0.000 0.000
#> GSM613703 2 0.0290 0.8285 0.000 0.992 0.000 0.008 0.000
#> GSM613704 2 0.0000 0.8289 0.000 1.000 0.000 0.000 0.000
#> GSM613705 3 0.5301 0.6361 0.088 0.000 0.688 0.212 0.012
#> GSM613706 1 0.3550 0.0573 0.760 0.000 0.004 0.236 0.000
#> GSM613707 1 0.4702 -0.5223 0.512 0.004 0.008 0.476 0.000
#> GSM613708 1 0.4560 -0.6609 0.508 0.000 0.008 0.484 0.000
#> GSM613709 1 0.4380 -0.1757 0.616 0.376 0.000 0.008 0.000
#> GSM613710 4 0.4533 0.7644 0.448 0.000 0.008 0.544 0.000
#> GSM613711 3 0.3180 0.8492 0.000 0.000 0.856 0.068 0.076
#> GSM613712 5 0.0880 0.8982 0.000 0.000 0.000 0.032 0.968
#> GSM613713 3 0.1851 0.8844 0.000 0.000 0.912 0.088 0.000
#> GSM613714 3 0.3297 0.8446 0.000 0.000 0.848 0.068 0.084
#> GSM613715 5 0.1357 0.8955 0.000 0.000 0.004 0.048 0.948
#> GSM613716 3 0.0794 0.8858 0.000 0.000 0.972 0.028 0.000
#> GSM613717 3 0.0609 0.8864 0.000 0.000 0.980 0.020 0.000
#> GSM613718 5 0.1952 0.8891 0.000 0.000 0.004 0.084 0.912
#> GSM613719 5 0.4054 0.7239 0.000 0.000 0.204 0.036 0.760
#> GSM613720 5 0.1894 0.8919 0.000 0.000 0.008 0.072 0.920
#> GSM613721 3 0.2179 0.8704 0.000 0.000 0.888 0.112 0.000
#> GSM613722 2 0.0000 0.8289 0.000 1.000 0.000 0.000 0.000
#> GSM613723 5 0.2127 0.8886 0.000 0.000 0.000 0.108 0.892
#> GSM613724 1 0.4367 -0.4605 0.580 0.000 0.004 0.416 0.000
#> GSM613725 2 0.0000 0.8289 0.000 1.000 0.000 0.000 0.000
#> GSM613726 1 0.2377 0.3943 0.872 0.128 0.000 0.000 0.000
#> GSM613727 2 0.4555 0.4803 0.472 0.520 0.000 0.008 0.000
#> GSM613728 2 0.3318 0.7660 0.180 0.808 0.000 0.012 0.000
#> GSM613729 2 0.4380 0.5891 0.376 0.616 0.000 0.008 0.000
#> GSM613730 1 0.4555 -0.6547 0.520 0.000 0.008 0.472 0.000
#> GSM613731 1 0.1270 0.4152 0.948 0.000 0.000 0.052 0.000
#> GSM613732 5 0.1704 0.8923 0.000 0.000 0.004 0.068 0.928
#> GSM613733 3 0.0880 0.8869 0.000 0.000 0.968 0.032 0.000
#> GSM613734 3 0.7210 0.3955 0.300 0.000 0.500 0.128 0.072
#> GSM613735 5 0.1792 0.8922 0.000 0.000 0.000 0.084 0.916
#> GSM613736 3 0.3055 0.8523 0.000 0.000 0.864 0.072 0.064
#> GSM613737 5 0.1408 0.8952 0.000 0.000 0.008 0.044 0.948
#> GSM613738 5 0.1908 0.8921 0.000 0.000 0.000 0.092 0.908
#> GSM613739 5 0.1851 0.8917 0.000 0.000 0.000 0.088 0.912
#> GSM613740 5 0.2069 0.8885 0.000 0.000 0.012 0.076 0.912
#> GSM613741 3 0.1851 0.8778 0.000 0.000 0.912 0.088 0.000
#> GSM613742 5 0.1908 0.8921 0.000 0.000 0.000 0.092 0.908
#> GSM613743 3 0.3242 0.8473 0.000 0.000 0.852 0.072 0.076
#> GSM613744 5 0.2006 0.8892 0.000 0.000 0.012 0.072 0.916
#> GSM613745 3 0.0703 0.8862 0.000 0.000 0.976 0.024 0.000
#> GSM613746 3 0.2179 0.8704 0.000 0.000 0.888 0.112 0.000
#> GSM613747 3 0.6190 0.5384 0.032 0.000 0.616 0.112 0.240
#> GSM613748 1 0.4182 -0.2748 0.644 0.000 0.004 0.352 0.000
#> GSM613749 2 0.0290 0.8285 0.000 0.992 0.000 0.008 0.000
#> GSM613750 5 0.2536 0.8732 0.000 0.000 0.004 0.128 0.868
#> GSM613751 5 0.2930 0.8566 0.000 0.000 0.004 0.164 0.832
#> GSM613752 5 0.2536 0.8732 0.000 0.000 0.004 0.128 0.868
#> GSM613753 5 0.2536 0.8732 0.000 0.000 0.004 0.128 0.868
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM613638 4 0.3376 0.701 0.060 0.000 0.084 0.836 0.000 NA
#> GSM613639 1 0.3450 0.761 0.780 0.000 0.000 0.188 0.000 NA
#> GSM613640 4 0.1285 0.766 0.052 0.000 0.000 0.944 0.000 NA
#> GSM613641 1 0.4312 0.396 0.604 0.368 0.000 0.000 0.000 NA
#> GSM613642 4 0.2020 0.754 0.008 0.000 0.000 0.896 0.000 NA
#> GSM613643 4 0.1141 0.763 0.052 0.000 0.000 0.948 0.000 NA
#> GSM613644 4 0.1219 0.765 0.048 0.000 0.000 0.948 0.000 NA
#> GSM613645 1 0.2668 0.777 0.828 0.000 0.000 0.168 0.000 NA
#> GSM613646 3 0.2961 0.818 0.048 0.000 0.860 0.012 0.000 NA
#> GSM613647 5 0.3052 0.819 0.004 0.000 0.000 0.000 0.780 NA
#> GSM613648 5 0.4692 0.691 0.012 0.000 0.108 0.000 0.708 NA
#> GSM613649 5 0.4733 0.688 0.012 0.000 0.112 0.000 0.704 NA
#> GSM613650 3 0.1296 0.836 0.004 0.000 0.948 0.004 0.000 NA
#> GSM613651 5 0.2871 0.820 0.004 0.000 0.000 0.000 0.804 NA
#> GSM613652 5 0.2793 0.816 0.000 0.000 0.000 0.000 0.800 NA
#> GSM613653 3 0.3413 0.818 0.052 0.000 0.824 0.012 0.000 NA
#> GSM613654 5 0.3215 0.812 0.004 0.000 0.000 0.000 0.756 NA
#> GSM613655 1 0.3312 0.769 0.792 0.000 0.000 0.180 0.000 NA
#> GSM613656 5 0.2793 0.816 0.000 0.000 0.000 0.000 0.800 NA
#> GSM613657 5 0.6138 0.165 0.012 0.000 0.324 0.000 0.460 NA
#> GSM613658 4 0.3010 0.698 0.148 0.000 0.004 0.828 0.000 NA
#> GSM613659 4 0.3555 0.712 0.044 0.000 0.000 0.780 0.000 NA
#> GSM613660 4 0.2685 0.763 0.060 0.000 0.000 0.868 0.000 NA
#> GSM613661 1 0.3377 0.759 0.784 0.000 0.000 0.188 0.000 NA
#> GSM613662 2 0.0291 0.826 0.004 0.992 0.000 0.000 0.000 NA
#> GSM613663 1 0.3245 0.771 0.800 0.000 0.000 0.172 0.000 NA
#> GSM613664 2 0.0000 0.825 0.000 1.000 0.000 0.000 0.000 NA
#> GSM613665 2 0.4723 0.508 0.296 0.636 0.000 0.004 0.000 NA
#> GSM613666 1 0.4009 0.536 0.684 0.288 0.000 0.000 0.000 NA
#> GSM613667 1 0.3460 0.631 0.760 0.220 0.000 0.000 0.000 NA
#> GSM613668 1 0.2743 0.778 0.828 0.000 0.000 0.164 0.000 NA
#> GSM613669 2 0.3668 0.592 0.228 0.744 0.000 0.000 0.000 NA
#> GSM613670 2 0.0508 0.824 0.004 0.984 0.000 0.000 0.000 NA
#> GSM613671 2 0.3668 0.592 0.228 0.744 0.000 0.000 0.000 NA
#> GSM613672 1 0.3279 0.768 0.796 0.000 0.000 0.176 0.000 NA
#> GSM613673 1 0.3471 0.683 0.784 0.188 0.000 0.020 0.000 NA
#> GSM613674 2 0.4985 0.624 0.024 0.640 0.004 0.044 0.000 NA
#> GSM613675 4 0.5611 0.331 0.292 0.000 0.000 0.528 0.000 NA
#> GSM613676 4 0.3683 0.703 0.048 0.000 0.000 0.768 0.000 NA
#> GSM613677 4 0.1285 0.766 0.052 0.000 0.000 0.944 0.000 NA
#> GSM613678 1 0.6634 0.476 0.532 0.100 0.000 0.192 0.000 NA
#> GSM613679 2 0.0405 0.825 0.004 0.988 0.000 0.000 0.000 NA
#> GSM613680 1 0.2703 0.775 0.824 0.000 0.000 0.172 0.000 NA
#> GSM613681 1 0.3125 0.779 0.828 0.032 0.000 0.136 0.000 NA
#> GSM613682 1 0.5777 0.365 0.500 0.000 0.000 0.216 0.000 NA
#> GSM613683 4 0.2790 0.700 0.140 0.000 0.000 0.840 0.000 NA
#> GSM613684 4 0.4327 0.675 0.020 0.000 0.028 0.700 0.000 NA
#> GSM613685 2 0.6929 0.378 0.124 0.428 0.004 0.100 0.000 NA
#> GSM613686 2 0.1168 0.815 0.016 0.956 0.000 0.000 0.000 NA
#> GSM613687 1 0.2668 0.777 0.828 0.000 0.000 0.168 0.000 NA
#> GSM613688 4 0.5315 0.541 0.104 0.000 0.004 0.552 0.000 NA
#> GSM613689 3 0.4947 0.694 0.008 0.000 0.676 0.000 0.156 NA
#> GSM613690 5 0.0260 0.832 0.000 0.000 0.008 0.000 0.992 NA
#> GSM613691 3 0.4796 0.721 0.048 0.000 0.732 0.116 0.000 NA
#> GSM613692 5 0.2941 0.817 0.000 0.000 0.000 0.000 0.780 NA
#> GSM613693 3 0.3128 0.812 0.052 0.000 0.844 0.008 0.000 NA
#> GSM613694 3 0.1845 0.833 0.008 0.000 0.916 0.000 0.004 NA
#> GSM613695 5 0.1542 0.826 0.004 0.000 0.008 0.000 0.936 NA
#> GSM613696 3 0.2445 0.823 0.008 0.000 0.868 0.000 0.004 NA
#> GSM613697 5 0.2871 0.825 0.004 0.000 0.000 0.000 0.804 NA
#> GSM613698 5 0.2572 0.826 0.012 0.000 0.000 0.000 0.852 NA
#> GSM613699 3 0.1728 0.834 0.008 0.000 0.924 0.000 0.004 NA
#> GSM613700 2 0.0146 0.826 0.004 0.996 0.000 0.000 0.000 NA
#> GSM613701 2 0.4817 0.647 0.132 0.680 0.000 0.004 0.000 NA
#> GSM613702 2 0.3867 0.497 0.328 0.660 0.000 0.000 0.000 NA
#> GSM613703 2 0.0858 0.820 0.004 0.968 0.000 0.000 0.000 NA
#> GSM613704 2 0.0146 0.826 0.004 0.996 0.000 0.000 0.000 NA
#> GSM613705 4 0.5859 0.111 0.028 0.000 0.372 0.524 0.024 NA
#> GSM613706 4 0.4065 0.485 0.300 0.000 0.000 0.672 0.000 NA
#> GSM613707 4 0.5859 0.501 0.116 0.004 0.016 0.508 0.000 NA
#> GSM613708 4 0.1471 0.764 0.064 0.000 0.000 0.932 0.000 NA
#> GSM613709 1 0.3726 0.721 0.796 0.144 0.000 0.040 0.000 NA
#> GSM613710 4 0.2432 0.750 0.024 0.000 0.000 0.876 0.000 NA
#> GSM613711 3 0.4325 0.762 0.008 0.000 0.760 0.008 0.124 NA
#> GSM613712 5 0.0405 0.834 0.000 0.000 0.004 0.000 0.988 NA
#> GSM613713 3 0.2487 0.835 0.032 0.000 0.876 0.000 0.000 NA
#> GSM613714 3 0.4670 0.727 0.008 0.000 0.716 0.004 0.164 NA
#> GSM613715 5 0.1194 0.829 0.004 0.000 0.008 0.000 0.956 NA
#> GSM613716 3 0.0870 0.835 0.004 0.000 0.972 0.012 0.000 NA
#> GSM613717 3 0.1493 0.832 0.004 0.000 0.936 0.004 0.000 NA
#> GSM613718 5 0.1719 0.824 0.008 0.000 0.008 0.000 0.928 NA
#> GSM613719 5 0.4804 0.683 0.012 0.000 0.140 0.000 0.700 NA
#> GSM613720 5 0.2841 0.800 0.012 0.000 0.012 0.000 0.848 NA
#> GSM613721 3 0.3176 0.812 0.052 0.000 0.840 0.008 0.000 NA
#> GSM613722 2 0.0146 0.826 0.004 0.996 0.000 0.000 0.000 NA
#> GSM613723 5 0.2941 0.813 0.000 0.000 0.000 0.000 0.780 NA
#> GSM613724 4 0.3010 0.698 0.148 0.000 0.004 0.828 0.000 NA
#> GSM613725 2 0.0260 0.824 0.000 0.992 0.000 0.000 0.000 NA
#> GSM613726 1 0.3743 0.779 0.792 0.024 0.000 0.152 0.000 NA
#> GSM613727 1 0.3956 0.594 0.712 0.252 0.000 0.000 0.000 NA
#> GSM613728 2 0.4632 0.544 0.276 0.656 0.000 0.004 0.000 NA
#> GSM613729 1 0.4249 0.479 0.640 0.328 0.000 0.000 0.000 NA
#> GSM613730 4 0.1950 0.767 0.064 0.000 0.000 0.912 0.000 NA
#> GSM613731 1 0.3694 0.711 0.740 0.000 0.000 0.232 0.000 NA
#> GSM613732 5 0.0976 0.829 0.008 0.000 0.008 0.000 0.968 NA
#> GSM613733 3 0.1296 0.835 0.004 0.000 0.952 0.012 0.000 NA
#> GSM613734 3 0.7813 0.180 0.088 0.000 0.380 0.256 0.040 NA
#> GSM613735 5 0.2793 0.816 0.000 0.000 0.000 0.000 0.800 NA
#> GSM613736 3 0.4196 0.770 0.008 0.000 0.772 0.008 0.116 NA
#> GSM613737 5 0.3231 0.805 0.012 0.000 0.008 0.000 0.800 NA
#> GSM613738 5 0.2969 0.816 0.000 0.000 0.000 0.000 0.776 NA
#> GSM613739 5 0.2762 0.817 0.000 0.000 0.000 0.000 0.804 NA
#> GSM613740 5 0.2704 0.805 0.012 0.000 0.020 0.000 0.868 NA
#> GSM613741 3 0.3368 0.819 0.052 0.000 0.828 0.012 0.000 NA
#> GSM613742 5 0.2969 0.816 0.000 0.000 0.000 0.000 0.776 NA
#> GSM613743 3 0.4257 0.759 0.008 0.000 0.760 0.004 0.128 NA
#> GSM613744 5 0.2752 0.803 0.012 0.000 0.020 0.000 0.864 NA
#> GSM613745 3 0.1138 0.835 0.004 0.000 0.960 0.012 0.000 NA
#> GSM613746 3 0.3176 0.812 0.052 0.000 0.840 0.008 0.000 NA
#> GSM613747 3 0.6881 0.490 0.024 0.000 0.528 0.104 0.096 NA
#> GSM613748 4 0.5438 0.329 0.304 0.000 0.000 0.548 0.000 NA
#> GSM613749 2 0.0777 0.821 0.004 0.972 0.000 0.000 0.000 NA
#> GSM613750 5 0.3618 0.777 0.080 0.000 0.008 0.000 0.808 NA
#> GSM613751 5 0.4507 0.744 0.088 0.000 0.020 0.000 0.736 NA
#> GSM613752 5 0.3836 0.769 0.080 0.000 0.008 0.000 0.788 NA
#> GSM613753 5 0.3618 0.777 0.080 0.000 0.008 0.000 0.808 NA
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) k
#> ATC:kmeans 116 0.00835 2
#> ATC:kmeans 109 0.03614 3
#> ATC:kmeans 114 0.05669 4
#> ATC:kmeans 82 0.10712 5
#> ATC:kmeans 103 0.05998 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 27425 rows and 116 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 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 1.000 0.998 0.999 0.5043 0.496 0.496
#> 3 3 0.831 0.905 0.945 0.2173 0.894 0.788
#> 4 4 0.918 0.889 0.939 0.1130 0.922 0.805
#> 5 5 0.790 0.667 0.833 0.0799 0.989 0.966
#> 6 6 0.747 0.476 0.763 0.0540 0.908 0.716
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 4
#> 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
#> GSM613638 2 0.000 1.000 0.0 1.0
#> GSM613639 1 0.000 0.998 1.0 0.0
#> GSM613640 1 0.000 0.998 1.0 0.0
#> GSM613641 1 0.000 0.998 1.0 0.0
#> GSM613642 1 0.000 0.998 1.0 0.0
#> GSM613643 1 0.000 0.998 1.0 0.0
#> GSM613644 1 0.000 0.998 1.0 0.0
#> GSM613645 1 0.000 0.998 1.0 0.0
#> GSM613646 2 0.000 1.000 0.0 1.0
#> GSM613647 2 0.000 1.000 0.0 1.0
#> GSM613648 2 0.000 1.000 0.0 1.0
#> GSM613649 2 0.000 1.000 0.0 1.0
#> GSM613650 2 0.000 1.000 0.0 1.0
#> GSM613651 2 0.000 1.000 0.0 1.0
#> GSM613652 2 0.000 1.000 0.0 1.0
#> GSM613653 2 0.000 1.000 0.0 1.0
#> GSM613654 2 0.000 1.000 0.0 1.0
#> GSM613655 1 0.000 0.998 1.0 0.0
#> GSM613656 2 0.000 1.000 0.0 1.0
#> GSM613657 2 0.000 1.000 0.0 1.0
#> GSM613658 2 0.000 1.000 0.0 1.0
#> GSM613659 1 0.000 0.998 1.0 0.0
#> GSM613660 1 0.000 0.998 1.0 0.0
#> GSM613661 1 0.000 0.998 1.0 0.0
#> GSM613662 1 0.000 0.998 1.0 0.0
#> GSM613663 1 0.000 0.998 1.0 0.0
#> GSM613664 1 0.000 0.998 1.0 0.0
#> GSM613665 1 0.000 0.998 1.0 0.0
#> GSM613666 1 0.000 0.998 1.0 0.0
#> GSM613667 1 0.000 0.998 1.0 0.0
#> GSM613668 1 0.000 0.998 1.0 0.0
#> GSM613669 1 0.000 0.998 1.0 0.0
#> GSM613670 1 0.000 0.998 1.0 0.0
#> GSM613671 1 0.000 0.998 1.0 0.0
#> GSM613672 1 0.000 0.998 1.0 0.0
#> GSM613673 1 0.000 0.998 1.0 0.0
#> GSM613674 1 0.000 0.998 1.0 0.0
#> GSM613675 1 0.000 0.998 1.0 0.0
#> GSM613676 1 0.000 0.998 1.0 0.0
#> GSM613677 1 0.000 0.998 1.0 0.0
#> GSM613678 1 0.000 0.998 1.0 0.0
#> GSM613679 1 0.000 0.998 1.0 0.0
#> GSM613680 1 0.000 0.998 1.0 0.0
#> GSM613681 1 0.000 0.998 1.0 0.0
#> GSM613682 1 0.000 0.998 1.0 0.0
#> GSM613683 1 0.000 0.998 1.0 0.0
#> GSM613684 1 0.469 0.889 0.9 0.1
#> GSM613685 1 0.000 0.998 1.0 0.0
#> GSM613686 1 0.000 0.998 1.0 0.0
#> GSM613687 1 0.000 0.998 1.0 0.0
#> GSM613688 1 0.000 0.998 1.0 0.0
#> GSM613689 2 0.000 1.000 0.0 1.0
#> GSM613690 2 0.000 1.000 0.0 1.0
#> GSM613691 1 0.000 0.998 1.0 0.0
#> GSM613692 2 0.000 1.000 0.0 1.0
#> GSM613693 2 0.000 1.000 0.0 1.0
#> GSM613694 2 0.000 1.000 0.0 1.0
#> GSM613695 2 0.000 1.000 0.0 1.0
#> GSM613696 2 0.000 1.000 0.0 1.0
#> GSM613697 2 0.000 1.000 0.0 1.0
#> GSM613698 2 0.000 1.000 0.0 1.0
#> GSM613699 2 0.000 1.000 0.0 1.0
#> GSM613700 1 0.000 0.998 1.0 0.0
#> GSM613701 1 0.000 0.998 1.0 0.0
#> GSM613702 1 0.000 0.998 1.0 0.0
#> GSM613703 1 0.000 0.998 1.0 0.0
#> GSM613704 1 0.000 0.998 1.0 0.0
#> GSM613705 2 0.000 1.000 0.0 1.0
#> GSM613706 1 0.000 0.998 1.0 0.0
#> GSM613707 1 0.000 0.998 1.0 0.0
#> GSM613708 1 0.000 0.998 1.0 0.0
#> GSM613709 1 0.000 0.998 1.0 0.0
#> GSM613710 1 0.000 0.998 1.0 0.0
#> GSM613711 2 0.000 1.000 0.0 1.0
#> GSM613712 2 0.000 1.000 0.0 1.0
#> GSM613713 2 0.000 1.000 0.0 1.0
#> GSM613714 2 0.000 1.000 0.0 1.0
#> GSM613715 2 0.000 1.000 0.0 1.0
#> GSM613716 2 0.000 1.000 0.0 1.0
#> GSM613717 2 0.000 1.000 0.0 1.0
#> GSM613718 2 0.000 1.000 0.0 1.0
#> GSM613719 2 0.000 1.000 0.0 1.0
#> GSM613720 2 0.000 1.000 0.0 1.0
#> GSM613721 2 0.000 1.000 0.0 1.0
#> GSM613722 1 0.000 0.998 1.0 0.0
#> GSM613723 2 0.000 1.000 0.0 1.0
#> GSM613724 1 0.000 0.998 1.0 0.0
#> GSM613725 1 0.000 0.998 1.0 0.0
#> GSM613726 1 0.000 0.998 1.0 0.0
#> GSM613727 1 0.000 0.998 1.0 0.0
#> GSM613728 1 0.000 0.998 1.0 0.0
#> GSM613729 1 0.000 0.998 1.0 0.0
#> GSM613730 1 0.000 0.998 1.0 0.0
#> GSM613731 1 0.000 0.998 1.0 0.0
#> GSM613732 2 0.000 1.000 0.0 1.0
#> GSM613733 2 0.000 1.000 0.0 1.0
#> GSM613734 2 0.000 1.000 0.0 1.0
#> GSM613735 2 0.000 1.000 0.0 1.0
#> GSM613736 2 0.000 1.000 0.0 1.0
#> GSM613737 2 0.000 1.000 0.0 1.0
#> GSM613738 2 0.000 1.000 0.0 1.0
#> GSM613739 2 0.000 1.000 0.0 1.0
#> GSM613740 2 0.000 1.000 0.0 1.0
#> GSM613741 2 0.000 1.000 0.0 1.0
#> GSM613742 2 0.000 1.000 0.0 1.0
#> GSM613743 2 0.000 1.000 0.0 1.0
#> GSM613744 2 0.000 1.000 0.0 1.0
#> GSM613745 2 0.000 1.000 0.0 1.0
#> GSM613746 2 0.000 1.000 0.0 1.0
#> GSM613747 2 0.000 1.000 0.0 1.0
#> GSM613748 1 0.000 0.998 1.0 0.0
#> GSM613749 1 0.000 0.998 1.0 0.0
#> GSM613750 2 0.000 1.000 0.0 1.0
#> GSM613751 2 0.000 1.000 0.0 1.0
#> GSM613752 2 0.000 1.000 0.0 1.0
#> GSM613753 2 0.000 1.000 0.0 1.0
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM613638 2 0.3551 0.804 0.000 0.868 0.132
#> GSM613639 1 0.3482 0.899 0.872 0.128 0.000
#> GSM613640 2 0.0424 0.888 0.008 0.992 0.000
#> GSM613641 1 0.3482 0.899 0.872 0.128 0.000
#> GSM613642 2 0.3619 0.866 0.136 0.864 0.000
#> GSM613643 2 0.0237 0.890 0.000 0.996 0.004
#> GSM613644 2 0.0237 0.890 0.000 0.996 0.004
#> GSM613645 1 0.3482 0.899 0.872 0.128 0.000
#> GSM613646 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613647 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613648 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613649 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613650 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613651 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613652 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613653 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613654 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613655 1 0.3482 0.899 0.872 0.128 0.000
#> GSM613656 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613657 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613658 2 0.0237 0.890 0.000 0.996 0.004
#> GSM613659 1 0.6062 0.182 0.616 0.384 0.000
#> GSM613660 1 0.0000 0.885 1.000 0.000 0.000
#> GSM613661 1 0.3482 0.899 0.872 0.128 0.000
#> GSM613662 1 0.0000 0.885 1.000 0.000 0.000
#> GSM613663 1 0.3482 0.899 0.872 0.128 0.000
#> GSM613664 1 0.0000 0.885 1.000 0.000 0.000
#> GSM613665 1 0.0000 0.885 1.000 0.000 0.000
#> GSM613666 1 0.3482 0.899 0.872 0.128 0.000
#> GSM613667 1 0.3482 0.899 0.872 0.128 0.000
#> GSM613668 1 0.3482 0.899 0.872 0.128 0.000
#> GSM613669 1 0.3482 0.899 0.872 0.128 0.000
#> GSM613670 1 0.0000 0.885 1.000 0.000 0.000
#> GSM613671 1 0.3482 0.899 0.872 0.128 0.000
#> GSM613672 1 0.3482 0.899 0.872 0.128 0.000
#> GSM613673 1 0.3482 0.899 0.872 0.128 0.000
#> GSM613674 1 0.0000 0.885 1.000 0.000 0.000
#> GSM613675 1 0.2537 0.817 0.920 0.080 0.000
#> GSM613676 2 0.6295 0.287 0.472 0.528 0.000
#> GSM613677 2 0.3340 0.873 0.120 0.880 0.000
#> GSM613678 1 0.0000 0.885 1.000 0.000 0.000
#> GSM613679 1 0.0000 0.885 1.000 0.000 0.000
#> GSM613680 1 0.3482 0.899 0.872 0.128 0.000
#> GSM613681 1 0.3482 0.899 0.872 0.128 0.000
#> GSM613682 1 0.3267 0.899 0.884 0.116 0.000
#> GSM613683 2 0.0237 0.890 0.004 0.996 0.000
#> GSM613684 2 0.3896 0.866 0.128 0.864 0.008
#> GSM613685 1 0.0000 0.885 1.000 0.000 0.000
#> GSM613686 1 0.3267 0.899 0.884 0.116 0.000
#> GSM613687 1 0.3482 0.899 0.872 0.128 0.000
#> GSM613688 1 0.0000 0.885 1.000 0.000 0.000
#> GSM613689 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613690 3 0.0000 0.988 0.000 0.000 1.000
#> GSM613691 1 0.0475 0.880 0.992 0.004 0.004
#> GSM613692 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613693 3 0.1878 0.946 0.044 0.004 0.952
#> GSM613694 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613695 3 0.0000 0.988 0.000 0.000 1.000
#> GSM613696 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613697 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613698 3 0.0000 0.988 0.000 0.000 1.000
#> GSM613699 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613700 1 0.0000 0.885 1.000 0.000 0.000
#> GSM613701 1 0.0000 0.885 1.000 0.000 0.000
#> GSM613702 1 0.0000 0.885 1.000 0.000 0.000
#> GSM613703 1 0.3267 0.899 0.884 0.116 0.000
#> GSM613704 1 0.0000 0.885 1.000 0.000 0.000
#> GSM613705 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613706 1 0.3482 0.899 0.872 0.128 0.000
#> GSM613707 1 0.6286 -0.134 0.536 0.464 0.000
#> GSM613708 2 0.0424 0.888 0.008 0.992 0.000
#> GSM613709 1 0.3482 0.899 0.872 0.128 0.000
#> GSM613710 2 0.3619 0.866 0.136 0.864 0.000
#> GSM613711 3 0.0000 0.988 0.000 0.000 1.000
#> GSM613712 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613713 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613714 3 0.0000 0.988 0.000 0.000 1.000
#> GSM613715 3 0.0000 0.988 0.000 0.000 1.000
#> GSM613716 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613717 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613718 3 0.0000 0.988 0.000 0.000 1.000
#> GSM613719 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613720 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613721 3 0.3784 0.841 0.132 0.004 0.864
#> GSM613722 1 0.0000 0.885 1.000 0.000 0.000
#> GSM613723 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613724 2 0.0237 0.890 0.000 0.996 0.004
#> GSM613725 1 0.0000 0.885 1.000 0.000 0.000
#> GSM613726 1 0.3482 0.899 0.872 0.128 0.000
#> GSM613727 1 0.3482 0.899 0.872 0.128 0.000
#> GSM613728 1 0.0000 0.885 1.000 0.000 0.000
#> GSM613729 1 0.3482 0.899 0.872 0.128 0.000
#> GSM613730 2 0.3482 0.871 0.128 0.872 0.000
#> GSM613731 1 0.3482 0.899 0.872 0.128 0.000
#> GSM613732 3 0.0000 0.988 0.000 0.000 1.000
#> GSM613733 3 0.3349 0.870 0.108 0.004 0.888
#> GSM613734 3 0.3551 0.836 0.000 0.132 0.868
#> GSM613735 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613736 3 0.0000 0.988 0.000 0.000 1.000
#> GSM613737 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613738 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613739 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613740 3 0.0000 0.988 0.000 0.000 1.000
#> GSM613741 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613742 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613743 3 0.0000 0.988 0.000 0.000 1.000
#> GSM613744 3 0.0000 0.988 0.000 0.000 1.000
#> GSM613745 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613746 3 0.1878 0.946 0.044 0.004 0.952
#> GSM613747 3 0.0237 0.987 0.000 0.004 0.996
#> GSM613748 1 0.5859 0.310 0.656 0.344 0.000
#> GSM613749 1 0.0000 0.885 1.000 0.000 0.000
#> GSM613750 3 0.0000 0.988 0.000 0.000 1.000
#> GSM613751 3 0.0000 0.988 0.000 0.000 1.000
#> GSM613752 3 0.0000 0.988 0.000 0.000 1.000
#> GSM613753 3 0.0000 0.988 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 2 0.2266 0.798 0.000 0.912 0.084 0.004
#> GSM613639 1 0.0000 0.937 1.000 0.000 0.000 0.000
#> GSM613640 2 0.1474 0.852 0.052 0.948 0.000 0.000
#> GSM613641 1 0.0000 0.937 1.000 0.000 0.000 0.000
#> GSM613642 2 0.0188 0.847 0.000 0.996 0.000 0.004
#> GSM613643 2 0.1576 0.852 0.048 0.948 0.000 0.004
#> GSM613644 2 0.1771 0.852 0.036 0.948 0.012 0.004
#> GSM613645 1 0.0000 0.937 1.000 0.000 0.000 0.000
#> GSM613646 4 0.1022 0.957 0.000 0.000 0.032 0.968
#> GSM613647 3 0.0188 0.944 0.000 0.000 0.996 0.004
#> GSM613648 3 0.2469 0.911 0.000 0.000 0.892 0.108
#> GSM613649 3 0.2469 0.911 0.000 0.000 0.892 0.108
#> GSM613650 3 0.2589 0.905 0.000 0.000 0.884 0.116
#> GSM613651 3 0.0188 0.944 0.000 0.000 0.996 0.004
#> GSM613652 3 0.0188 0.944 0.000 0.000 0.996 0.004
#> GSM613653 4 0.1302 0.956 0.000 0.000 0.044 0.956
#> GSM613654 3 0.0188 0.944 0.000 0.000 0.996 0.004
#> GSM613655 1 0.0000 0.937 1.000 0.000 0.000 0.000
#> GSM613656 3 0.0188 0.944 0.000 0.000 0.996 0.004
#> GSM613657 3 0.2469 0.911 0.000 0.000 0.892 0.108
#> GSM613658 2 0.4041 0.776 0.056 0.840 0.100 0.004
#> GSM613659 1 0.6005 0.131 0.500 0.460 0.000 0.040
#> GSM613660 1 0.2546 0.920 0.912 0.060 0.000 0.028
#> GSM613661 1 0.0000 0.937 1.000 0.000 0.000 0.000
#> GSM613662 1 0.2385 0.923 0.920 0.052 0.000 0.028
#> GSM613663 1 0.0000 0.937 1.000 0.000 0.000 0.000
#> GSM613664 1 0.2385 0.923 0.920 0.052 0.000 0.028
#> GSM613665 1 0.2385 0.923 0.920 0.052 0.000 0.028
#> GSM613666 1 0.0000 0.937 1.000 0.000 0.000 0.000
#> GSM613667 1 0.0000 0.937 1.000 0.000 0.000 0.000
#> GSM613668 1 0.0000 0.937 1.000 0.000 0.000 0.000
#> GSM613669 1 0.0000 0.937 1.000 0.000 0.000 0.000
#> GSM613670 1 0.2385 0.923 0.920 0.052 0.000 0.028
#> GSM613671 1 0.0000 0.937 1.000 0.000 0.000 0.000
#> GSM613672 1 0.0000 0.937 1.000 0.000 0.000 0.000
#> GSM613673 1 0.0000 0.937 1.000 0.000 0.000 0.000
#> GSM613674 1 0.2759 0.915 0.904 0.052 0.000 0.044
#> GSM613675 1 0.4775 0.720 0.740 0.232 0.000 0.028
#> GSM613676 2 0.5331 0.406 0.332 0.644 0.000 0.024
#> GSM613677 2 0.0188 0.849 0.004 0.996 0.000 0.000
#> GSM613678 1 0.2413 0.921 0.916 0.064 0.000 0.020
#> GSM613679 1 0.2385 0.923 0.920 0.052 0.000 0.028
#> GSM613680 1 0.0000 0.937 1.000 0.000 0.000 0.000
#> GSM613681 1 0.0000 0.937 1.000 0.000 0.000 0.000
#> GSM613682 1 0.0592 0.935 0.984 0.000 0.000 0.016
#> GSM613683 2 0.1637 0.848 0.060 0.940 0.000 0.000
#> GSM613684 2 0.0707 0.842 0.000 0.980 0.000 0.020
#> GSM613685 1 0.4070 0.843 0.824 0.132 0.000 0.044
#> GSM613686 1 0.0376 0.936 0.992 0.004 0.000 0.004
#> GSM613687 1 0.0000 0.937 1.000 0.000 0.000 0.000
#> GSM613688 1 0.2840 0.913 0.900 0.056 0.000 0.044
#> GSM613689 3 0.2345 0.916 0.000 0.000 0.900 0.100
#> GSM613690 3 0.0188 0.945 0.000 0.000 0.996 0.004
#> GSM613691 4 0.0524 0.922 0.004 0.008 0.000 0.988
#> GSM613692 3 0.0188 0.944 0.000 0.000 0.996 0.004
#> GSM613693 4 0.0817 0.954 0.000 0.000 0.024 0.976
#> GSM613694 3 0.2408 0.914 0.000 0.000 0.896 0.104
#> GSM613695 3 0.0188 0.945 0.000 0.000 0.996 0.004
#> GSM613696 3 0.2704 0.899 0.000 0.000 0.876 0.124
#> GSM613697 3 0.0188 0.944 0.000 0.000 0.996 0.004
#> GSM613698 3 0.0000 0.944 0.000 0.000 1.000 0.000
#> GSM613699 3 0.2814 0.891 0.000 0.000 0.868 0.132
#> GSM613700 1 0.2385 0.923 0.920 0.052 0.000 0.028
#> GSM613701 1 0.2385 0.923 0.920 0.052 0.000 0.028
#> GSM613702 1 0.2174 0.925 0.928 0.052 0.000 0.020
#> GSM613703 1 0.0524 0.936 0.988 0.004 0.000 0.008
#> GSM613704 1 0.2385 0.923 0.920 0.052 0.000 0.028
#> GSM613705 3 0.0188 0.944 0.000 0.000 0.996 0.004
#> GSM613706 1 0.0000 0.937 1.000 0.000 0.000 0.000
#> GSM613707 2 0.5905 0.208 0.396 0.564 0.000 0.040
#> GSM613708 2 0.1474 0.852 0.052 0.948 0.000 0.000
#> GSM613709 1 0.0000 0.937 1.000 0.000 0.000 0.000
#> GSM613710 2 0.0188 0.847 0.000 0.996 0.000 0.004
#> GSM613711 3 0.2216 0.921 0.000 0.000 0.908 0.092
#> GSM613712 3 0.0188 0.944 0.000 0.000 0.996 0.004
#> GSM613713 4 0.1389 0.954 0.000 0.000 0.048 0.952
#> GSM613714 3 0.1118 0.943 0.000 0.000 0.964 0.036
#> GSM613715 3 0.0469 0.945 0.000 0.000 0.988 0.012
#> GSM613716 3 0.2216 0.921 0.000 0.000 0.908 0.092
#> GSM613717 3 0.4967 0.248 0.000 0.000 0.548 0.452
#> GSM613718 3 0.1118 0.943 0.000 0.000 0.964 0.036
#> GSM613719 3 0.2530 0.908 0.000 0.000 0.888 0.112
#> GSM613720 3 0.2469 0.911 0.000 0.000 0.892 0.108
#> GSM613721 4 0.0336 0.936 0.000 0.000 0.008 0.992
#> GSM613722 1 0.2385 0.923 0.920 0.052 0.000 0.028
#> GSM613723 3 0.0188 0.944 0.000 0.000 0.996 0.004
#> GSM613724 2 0.3504 0.810 0.056 0.872 0.068 0.004
#> GSM613725 1 0.2385 0.923 0.920 0.052 0.000 0.028
#> GSM613726 1 0.0000 0.937 1.000 0.000 0.000 0.000
#> GSM613727 1 0.0000 0.937 1.000 0.000 0.000 0.000
#> GSM613728 1 0.2385 0.923 0.920 0.052 0.000 0.028
#> GSM613729 1 0.0000 0.937 1.000 0.000 0.000 0.000
#> GSM613730 2 0.0188 0.848 0.004 0.996 0.000 0.000
#> GSM613731 1 0.0000 0.937 1.000 0.000 0.000 0.000
#> GSM613732 3 0.0469 0.945 0.000 0.000 0.988 0.012
#> GSM613733 4 0.1940 0.928 0.000 0.000 0.076 0.924
#> GSM613734 3 0.1743 0.897 0.056 0.000 0.940 0.004
#> GSM613735 3 0.0188 0.944 0.000 0.000 0.996 0.004
#> GSM613736 3 0.1118 0.943 0.000 0.000 0.964 0.036
#> GSM613737 3 0.2469 0.911 0.000 0.000 0.892 0.108
#> GSM613738 3 0.0188 0.944 0.000 0.000 0.996 0.004
#> GSM613739 3 0.0188 0.944 0.000 0.000 0.996 0.004
#> GSM613740 3 0.1118 0.943 0.000 0.000 0.964 0.036
#> GSM613741 4 0.1474 0.952 0.000 0.000 0.052 0.948
#> GSM613742 3 0.0188 0.944 0.000 0.000 0.996 0.004
#> GSM613743 3 0.1867 0.930 0.000 0.000 0.928 0.072
#> GSM613744 3 0.1118 0.943 0.000 0.000 0.964 0.036
#> GSM613745 4 0.2469 0.888 0.000 0.000 0.108 0.892
#> GSM613746 4 0.0817 0.954 0.000 0.000 0.024 0.976
#> GSM613747 3 0.0188 0.944 0.000 0.000 0.996 0.004
#> GSM613748 1 0.5483 0.225 0.536 0.448 0.000 0.016
#> GSM613749 1 0.2089 0.926 0.932 0.048 0.000 0.020
#> GSM613750 3 0.0469 0.945 0.000 0.000 0.988 0.012
#> GSM613751 3 0.1118 0.943 0.000 0.000 0.964 0.036
#> GSM613752 3 0.1118 0.943 0.000 0.000 0.964 0.036
#> GSM613753 3 0.0188 0.945 0.000 0.000 0.996 0.004
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM613638 4 0.1557 0.810 0.000 0.052 0.000 0.940 0.008
#> GSM613639 1 0.4150 0.659 0.612 0.388 0.000 0.000 0.000
#> GSM613640 4 0.0404 0.822 0.000 0.012 0.000 0.988 0.000
#> GSM613641 1 0.4101 0.661 0.628 0.372 0.000 0.000 0.000
#> GSM613642 4 0.3550 0.651 0.004 0.236 0.000 0.760 0.000
#> GSM613643 4 0.0162 0.822 0.000 0.004 0.000 0.996 0.000
#> GSM613644 4 0.0290 0.823 0.000 0.008 0.000 0.992 0.000
#> GSM613645 1 0.4126 0.660 0.620 0.380 0.000 0.000 0.000
#> GSM613646 3 0.0865 0.938 0.000 0.004 0.972 0.000 0.024
#> GSM613647 5 0.2582 0.884 0.000 0.080 0.024 0.004 0.892
#> GSM613648 5 0.2077 0.891 0.000 0.008 0.084 0.000 0.908
#> GSM613649 5 0.2136 0.888 0.000 0.008 0.088 0.000 0.904
#> GSM613650 5 0.2685 0.875 0.000 0.028 0.092 0.000 0.880
#> GSM613651 5 0.2582 0.884 0.000 0.080 0.024 0.004 0.892
#> GSM613652 5 0.2582 0.884 0.000 0.080 0.024 0.004 0.892
#> GSM613653 3 0.1059 0.936 0.004 0.008 0.968 0.000 0.020
#> GSM613654 5 0.2582 0.884 0.000 0.080 0.024 0.004 0.892
#> GSM613655 1 0.4331 0.653 0.596 0.400 0.000 0.004 0.000
#> GSM613656 5 0.2582 0.884 0.000 0.080 0.024 0.004 0.892
#> GSM613657 5 0.2136 0.888 0.000 0.008 0.088 0.000 0.904
#> GSM613658 4 0.3917 0.708 0.000 0.184 0.024 0.784 0.008
#> GSM613659 1 0.6003 -0.784 0.448 0.440 0.000 0.112 0.000
#> GSM613660 1 0.2561 0.200 0.856 0.144 0.000 0.000 0.000
#> GSM613661 1 0.4192 0.653 0.596 0.404 0.000 0.000 0.000
#> GSM613662 1 0.0000 0.478 1.000 0.000 0.000 0.000 0.000
#> GSM613663 1 0.4192 0.653 0.596 0.404 0.000 0.000 0.000
#> GSM613664 1 0.0000 0.478 1.000 0.000 0.000 0.000 0.000
#> GSM613665 1 0.0510 0.455 0.984 0.016 0.000 0.000 0.000
#> GSM613666 1 0.4030 0.659 0.648 0.352 0.000 0.000 0.000
#> GSM613667 1 0.4161 0.658 0.608 0.392 0.000 0.000 0.000
#> GSM613668 1 0.4101 0.659 0.628 0.372 0.000 0.000 0.000
#> GSM613669 1 0.4138 0.659 0.616 0.384 0.000 0.000 0.000
#> GSM613670 1 0.0000 0.478 1.000 0.000 0.000 0.000 0.000
#> GSM613671 1 0.4088 0.661 0.632 0.368 0.000 0.000 0.000
#> GSM613672 1 0.4341 0.651 0.592 0.404 0.000 0.004 0.000
#> GSM613673 1 0.4060 0.660 0.640 0.360 0.000 0.000 0.000
#> GSM613674 1 0.4256 -0.639 0.564 0.436 0.000 0.000 0.000
#> GSM613675 1 0.5684 -0.640 0.564 0.340 0.000 0.096 0.000
#> GSM613676 2 0.6576 0.646 0.340 0.444 0.000 0.216 0.000
#> GSM613677 4 0.0451 0.820 0.004 0.008 0.000 0.988 0.000
#> GSM613678 1 0.3636 -0.256 0.728 0.272 0.000 0.000 0.000
#> GSM613679 1 0.0162 0.473 0.996 0.004 0.000 0.000 0.000
#> GSM613680 1 0.4310 0.655 0.604 0.392 0.000 0.004 0.000
#> GSM613681 1 0.4161 0.657 0.608 0.392 0.000 0.000 0.000
#> GSM613682 2 0.4114 0.390 0.376 0.624 0.000 0.000 0.000
#> GSM613683 4 0.1792 0.780 0.000 0.084 0.000 0.916 0.000
#> GSM613684 4 0.4680 0.301 0.008 0.448 0.004 0.540 0.000
#> GSM613685 1 0.5548 -0.738 0.492 0.440 0.000 0.068 0.000
#> GSM613686 1 0.3895 0.649 0.680 0.320 0.000 0.000 0.000
#> GSM613687 1 0.4150 0.658 0.612 0.388 0.000 0.000 0.000
#> GSM613688 1 0.4256 -0.639 0.564 0.436 0.000 0.000 0.000
#> GSM613689 5 0.2208 0.892 0.000 0.020 0.072 0.000 0.908
#> GSM613690 5 0.0162 0.910 0.000 0.004 0.000 0.000 0.996
#> GSM613691 3 0.2769 0.800 0.092 0.032 0.876 0.000 0.000
#> GSM613692 5 0.2582 0.884 0.000 0.080 0.024 0.004 0.892
#> GSM613693 3 0.0865 0.938 0.000 0.004 0.972 0.000 0.024
#> GSM613694 5 0.2423 0.886 0.000 0.024 0.080 0.000 0.896
#> GSM613695 5 0.0162 0.910 0.000 0.004 0.000 0.000 0.996
#> GSM613696 5 0.2597 0.877 0.000 0.024 0.092 0.000 0.884
#> GSM613697 5 0.2582 0.884 0.000 0.080 0.024 0.004 0.892
#> GSM613698 5 0.0324 0.910 0.000 0.004 0.004 0.000 0.992
#> GSM613699 5 0.2707 0.871 0.000 0.024 0.100 0.000 0.876
#> GSM613700 1 0.0000 0.478 1.000 0.000 0.000 0.000 0.000
#> GSM613701 1 0.0162 0.473 0.996 0.004 0.000 0.000 0.000
#> GSM613702 1 0.0000 0.478 1.000 0.000 0.000 0.000 0.000
#> GSM613703 1 0.3837 0.645 0.692 0.308 0.000 0.000 0.000
#> GSM613704 1 0.0000 0.478 1.000 0.000 0.000 0.000 0.000
#> GSM613705 5 0.3281 0.867 0.000 0.080 0.024 0.032 0.864
#> GSM613706 1 0.4138 0.659 0.616 0.384 0.000 0.000 0.000
#> GSM613707 2 0.6344 0.701 0.400 0.440 0.000 0.160 0.000
#> GSM613708 4 0.0162 0.822 0.000 0.004 0.000 0.996 0.000
#> GSM613709 1 0.4150 0.658 0.612 0.388 0.000 0.000 0.000
#> GSM613710 4 0.5091 0.509 0.088 0.236 0.000 0.676 0.000
#> GSM613711 5 0.1845 0.901 0.000 0.016 0.056 0.000 0.928
#> GSM613712 5 0.0865 0.905 0.000 0.004 0.024 0.000 0.972
#> GSM613713 3 0.2144 0.905 0.000 0.020 0.912 0.000 0.068
#> GSM613714 5 0.1211 0.909 0.000 0.016 0.024 0.000 0.960
#> GSM613715 5 0.0162 0.910 0.000 0.004 0.000 0.000 0.996
#> GSM613716 5 0.1638 0.901 0.000 0.004 0.064 0.000 0.932
#> GSM613717 5 0.4789 0.345 0.000 0.024 0.392 0.000 0.584
#> GSM613718 5 0.0865 0.910 0.000 0.004 0.024 0.000 0.972
#> GSM613719 5 0.2193 0.886 0.000 0.008 0.092 0.000 0.900
#> GSM613720 5 0.2077 0.891 0.000 0.008 0.084 0.000 0.908
#> GSM613721 3 0.0960 0.924 0.016 0.004 0.972 0.000 0.008
#> GSM613722 1 0.0000 0.478 1.000 0.000 0.000 0.000 0.000
#> GSM613723 5 0.2582 0.884 0.000 0.080 0.024 0.004 0.892
#> GSM613724 4 0.3565 0.722 0.000 0.176 0.024 0.800 0.000
#> GSM613725 1 0.0162 0.473 0.996 0.004 0.000 0.000 0.000
#> GSM613726 1 0.4138 0.659 0.616 0.384 0.000 0.000 0.000
#> GSM613727 1 0.4171 0.656 0.604 0.396 0.000 0.000 0.000
#> GSM613728 1 0.0404 0.461 0.988 0.012 0.000 0.000 0.000
#> GSM613729 1 0.4138 0.659 0.616 0.384 0.000 0.000 0.000
#> GSM613730 4 0.4430 0.641 0.076 0.172 0.000 0.752 0.000
#> GSM613731 1 0.4192 0.653 0.596 0.404 0.000 0.000 0.000
#> GSM613732 5 0.0162 0.910 0.000 0.004 0.000 0.000 0.996
#> GSM613733 3 0.2628 0.877 0.000 0.028 0.884 0.000 0.088
#> GSM613734 5 0.5299 0.697 0.000 0.204 0.024 0.072 0.700
#> GSM613735 5 0.2582 0.884 0.000 0.080 0.024 0.004 0.892
#> GSM613736 5 0.1386 0.907 0.000 0.016 0.032 0.000 0.952
#> GSM613737 5 0.2077 0.891 0.000 0.008 0.084 0.000 0.908
#> GSM613738 5 0.2582 0.884 0.000 0.080 0.024 0.004 0.892
#> GSM613739 5 0.2582 0.884 0.000 0.080 0.024 0.004 0.892
#> GSM613740 5 0.1386 0.907 0.000 0.016 0.032 0.000 0.952
#> GSM613741 3 0.1106 0.936 0.000 0.012 0.964 0.000 0.024
#> GSM613742 5 0.2582 0.884 0.000 0.080 0.024 0.004 0.892
#> GSM613743 5 0.1626 0.904 0.000 0.016 0.044 0.000 0.940
#> GSM613744 5 0.1168 0.908 0.000 0.008 0.032 0.000 0.960
#> GSM613745 3 0.2653 0.869 0.000 0.024 0.880 0.000 0.096
#> GSM613746 3 0.0865 0.938 0.000 0.004 0.972 0.000 0.024
#> GSM613747 5 0.3206 0.863 0.000 0.108 0.024 0.012 0.856
#> GSM613748 1 0.6220 -0.607 0.540 0.272 0.000 0.188 0.000
#> GSM613749 1 0.0963 0.501 0.964 0.036 0.000 0.000 0.000
#> GSM613750 5 0.0000 0.910 0.000 0.000 0.000 0.000 1.000
#> GSM613751 5 0.0703 0.910 0.000 0.000 0.024 0.000 0.976
#> GSM613752 5 0.0865 0.910 0.000 0.004 0.024 0.000 0.972
#> GSM613753 5 0.0000 0.910 0.000 0.000 0.000 0.000 1.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM613638 4 0.2357 0.7593 0.012 0.000 0.000 0.872 0.116 0.000
#> GSM613639 1 0.3838 0.8333 0.552 0.448 0.000 0.000 0.000 0.000
#> GSM613640 4 0.1572 0.7822 0.028 0.000 0.000 0.936 0.036 0.000
#> GSM613641 1 0.3854 0.8296 0.536 0.464 0.000 0.000 0.000 0.000
#> GSM613642 4 0.3961 0.7119 0.124 0.000 0.000 0.764 0.112 0.000
#> GSM613643 4 0.0458 0.7854 0.000 0.000 0.000 0.984 0.016 0.000
#> GSM613644 4 0.0000 0.7878 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613645 1 0.3797 0.8383 0.580 0.420 0.000 0.000 0.000 0.000
#> GSM613646 6 0.0713 0.8655 0.000 0.000 0.000 0.000 0.028 0.972
#> GSM613647 3 0.0146 0.4637 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM613648 3 0.4605 0.2464 0.008 0.000 0.596 0.000 0.364 0.032
#> GSM613649 3 0.4767 0.2230 0.008 0.000 0.592 0.000 0.356 0.044
#> GSM613650 3 0.5236 -0.0709 0.008 0.000 0.548 0.000 0.364 0.080
#> GSM613651 3 0.0000 0.4637 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613652 3 0.0146 0.4628 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM613653 6 0.1555 0.8572 0.004 0.004 0.000 0.000 0.060 0.932
#> GSM613654 3 0.0146 0.4628 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM613655 1 0.4101 0.8360 0.580 0.408 0.000 0.000 0.012 0.000
#> GSM613656 3 0.0146 0.4628 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM613657 3 0.4630 0.1483 0.008 0.000 0.560 0.000 0.404 0.028
#> GSM613658 4 0.6031 0.5019 0.016 0.000 0.188 0.512 0.284 0.000
#> GSM613659 2 0.6253 0.2944 0.364 0.452 0.000 0.020 0.160 0.004
#> GSM613660 2 0.3210 0.5573 0.168 0.804 0.000 0.000 0.028 0.000
#> GSM613661 1 0.3782 0.8390 0.588 0.412 0.000 0.000 0.000 0.000
#> GSM613662 2 0.0146 0.5995 0.004 0.996 0.000 0.000 0.000 0.000
#> GSM613663 1 0.3789 0.8406 0.584 0.416 0.000 0.000 0.000 0.000
#> GSM613664 2 0.0000 0.6021 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613665 2 0.0632 0.6045 0.024 0.976 0.000 0.000 0.000 0.000
#> GSM613666 2 0.3868 -0.7861 0.492 0.508 0.000 0.000 0.000 0.000
#> GSM613667 1 0.3833 0.8411 0.556 0.444 0.000 0.000 0.000 0.000
#> GSM613668 1 0.3857 0.8251 0.532 0.468 0.000 0.000 0.000 0.000
#> GSM613669 1 0.3854 0.8295 0.536 0.464 0.000 0.000 0.000 0.000
#> GSM613670 2 0.0146 0.5995 0.004 0.996 0.000 0.000 0.000 0.000
#> GSM613671 1 0.3860 0.8221 0.528 0.472 0.000 0.000 0.000 0.000
#> GSM613672 1 0.3737 0.8285 0.608 0.392 0.000 0.000 0.000 0.000
#> GSM613673 1 0.3862 0.8159 0.524 0.476 0.000 0.000 0.000 0.000
#> GSM613674 2 0.5436 0.3614 0.364 0.528 0.000 0.000 0.100 0.008
#> GSM613675 2 0.5537 0.4608 0.280 0.588 0.000 0.020 0.112 0.000
#> GSM613676 1 0.7494 -0.4275 0.360 0.268 0.000 0.212 0.160 0.000
#> GSM613677 4 0.0458 0.7883 0.000 0.000 0.000 0.984 0.016 0.000
#> GSM613678 2 0.4513 0.5328 0.212 0.700 0.000 0.004 0.084 0.000
#> GSM613679 2 0.0000 0.6021 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613680 1 0.3782 0.8362 0.588 0.412 0.000 0.000 0.000 0.000
#> GSM613681 1 0.3797 0.8376 0.580 0.420 0.000 0.000 0.000 0.000
#> GSM613682 1 0.5063 -0.2792 0.604 0.284 0.000 0.000 0.112 0.000
#> GSM613683 4 0.2872 0.7392 0.024 0.000 0.000 0.836 0.140 0.000
#> GSM613684 4 0.6181 0.4449 0.364 0.000 0.000 0.436 0.184 0.016
#> GSM613685 2 0.5993 0.3128 0.364 0.468 0.000 0.004 0.156 0.008
#> GSM613686 2 0.3866 -0.7732 0.484 0.516 0.000 0.000 0.000 0.000
#> GSM613687 1 0.3804 0.8398 0.576 0.424 0.000 0.000 0.000 0.000
#> GSM613688 2 0.5443 0.3587 0.364 0.520 0.000 0.000 0.112 0.004
#> GSM613689 3 0.4550 -0.0426 0.008 0.000 0.524 0.000 0.448 0.020
#> GSM613690 3 0.3428 0.4313 0.000 0.000 0.696 0.000 0.304 0.000
#> GSM613691 6 0.1788 0.8228 0.028 0.040 0.000 0.000 0.004 0.928
#> GSM613692 3 0.0146 0.4628 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM613693 6 0.0806 0.8648 0.008 0.000 0.000 0.000 0.020 0.972
#> GSM613694 3 0.5024 -0.2583 0.008 0.000 0.500 0.000 0.440 0.052
#> GSM613695 3 0.3515 0.4205 0.000 0.000 0.676 0.000 0.324 0.000
#> GSM613696 3 0.5300 -0.3929 0.008 0.000 0.468 0.000 0.448 0.076
#> GSM613697 3 0.0000 0.4637 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613698 3 0.2553 0.4555 0.008 0.000 0.848 0.000 0.144 0.000
#> GSM613699 3 0.5451 -0.4682 0.008 0.000 0.456 0.000 0.444 0.092
#> GSM613700 2 0.0146 0.5995 0.004 0.996 0.000 0.000 0.000 0.000
#> GSM613701 2 0.0146 0.6036 0.004 0.996 0.000 0.000 0.000 0.000
#> GSM613702 2 0.0146 0.5995 0.004 0.996 0.000 0.000 0.000 0.000
#> GSM613703 2 0.3774 -0.6331 0.408 0.592 0.000 0.000 0.000 0.000
#> GSM613704 2 0.0146 0.5995 0.004 0.996 0.000 0.000 0.000 0.000
#> GSM613705 3 0.0806 0.4425 0.000 0.000 0.972 0.020 0.008 0.000
#> GSM613706 1 0.4229 0.7954 0.548 0.436 0.000 0.000 0.016 0.000
#> GSM613707 2 0.6799 0.2331 0.364 0.416 0.000 0.052 0.160 0.008
#> GSM613708 4 0.0508 0.7886 0.012 0.000 0.000 0.984 0.004 0.000
#> GSM613709 1 0.3797 0.8383 0.580 0.420 0.000 0.000 0.000 0.000
#> GSM613710 4 0.5108 0.6742 0.152 0.036 0.000 0.692 0.120 0.000
#> GSM613711 3 0.4101 0.2225 0.000 0.000 0.580 0.000 0.408 0.012
#> GSM613712 3 0.2340 0.4569 0.000 0.000 0.852 0.000 0.148 0.000
#> GSM613713 6 0.3840 0.6247 0.000 0.000 0.020 0.000 0.284 0.696
#> GSM613714 3 0.3747 0.2950 0.000 0.000 0.604 0.000 0.396 0.000
#> GSM613715 3 0.3464 0.4277 0.000 0.000 0.688 0.000 0.312 0.000
#> GSM613716 3 0.4289 0.3224 0.000 0.000 0.612 0.000 0.360 0.028
#> GSM613717 5 0.5900 0.0000 0.004 0.000 0.336 0.000 0.472 0.188
#> GSM613718 3 0.3607 0.3936 0.000 0.000 0.652 0.000 0.348 0.000
#> GSM613719 3 0.4937 0.1841 0.008 0.000 0.592 0.000 0.340 0.060
#> GSM613720 3 0.4679 0.2260 0.008 0.000 0.588 0.000 0.368 0.036
#> GSM613721 6 0.0291 0.8636 0.004 0.000 0.000 0.000 0.004 0.992
#> GSM613722 2 0.0146 0.5995 0.004 0.996 0.000 0.000 0.000 0.000
#> GSM613723 3 0.0146 0.4628 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM613724 4 0.5512 0.5760 0.016 0.000 0.116 0.584 0.284 0.000
#> GSM613725 2 0.0146 0.6035 0.004 0.996 0.000 0.000 0.000 0.000
#> GSM613726 1 0.3828 0.8382 0.560 0.440 0.000 0.000 0.000 0.000
#> GSM613727 1 0.3810 0.8414 0.572 0.428 0.000 0.000 0.000 0.000
#> GSM613728 2 0.0547 0.6047 0.020 0.980 0.000 0.000 0.000 0.000
#> GSM613729 1 0.3833 0.8396 0.556 0.444 0.000 0.000 0.000 0.000
#> GSM613730 4 0.4905 0.6984 0.148 0.044 0.000 0.716 0.092 0.000
#> GSM613731 1 0.4057 0.8240 0.600 0.388 0.000 0.000 0.012 0.000
#> GSM613732 3 0.3547 0.4140 0.000 0.000 0.668 0.000 0.332 0.000
#> GSM613733 6 0.4107 0.6768 0.000 0.000 0.044 0.000 0.256 0.700
#> GSM613734 3 0.4712 0.0414 0.016 0.000 0.648 0.044 0.292 0.000
#> GSM613735 3 0.0146 0.4628 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM613736 3 0.4076 0.0280 0.000 0.000 0.540 0.000 0.452 0.008
#> GSM613737 3 0.4645 0.2596 0.008 0.000 0.616 0.000 0.336 0.040
#> GSM613738 3 0.0146 0.4628 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM613739 3 0.0146 0.4628 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM613740 3 0.3737 0.3062 0.000 0.000 0.608 0.000 0.392 0.000
#> GSM613741 6 0.1531 0.8567 0.004 0.000 0.000 0.000 0.068 0.928
#> GSM613742 3 0.0146 0.4628 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM613743 3 0.4076 0.0280 0.000 0.000 0.540 0.000 0.452 0.008
#> GSM613744 3 0.3695 0.3443 0.000 0.000 0.624 0.000 0.376 0.000
#> GSM613745 6 0.4000 0.7458 0.004 0.000 0.060 0.000 0.184 0.752
#> GSM613746 6 0.0291 0.8636 0.004 0.000 0.000 0.000 0.004 0.992
#> GSM613747 3 0.3259 0.1686 0.000 0.000 0.772 0.012 0.216 0.000
#> GSM613748 2 0.6886 0.2942 0.212 0.488 0.000 0.196 0.104 0.000
#> GSM613749 2 0.1007 0.5322 0.044 0.956 0.000 0.000 0.000 0.000
#> GSM613750 3 0.3547 0.4140 0.000 0.000 0.668 0.000 0.332 0.000
#> GSM613751 3 0.3578 0.4044 0.000 0.000 0.660 0.000 0.340 0.000
#> GSM613752 3 0.3578 0.4044 0.000 0.000 0.660 0.000 0.340 0.000
#> GSM613753 3 0.3531 0.4175 0.000 0.000 0.672 0.000 0.328 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) k
#> ATC:skmeans 116 0.00835 2
#> ATC:skmeans 112 0.00141 3
#> ATC:skmeans 111 0.02037 4
#> ATC:skmeans 93 0.20474 5
#> ATC:skmeans 58 0.15102 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 27425 rows and 116 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 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 1.000 0.979 0.992 0.5011 0.499 0.499
#> 3 3 0.873 0.932 0.964 0.3051 0.770 0.571
#> 4 4 0.979 0.947 0.977 0.1105 0.911 0.749
#> 5 5 0.878 0.843 0.929 0.0725 0.951 0.825
#> 6 6 0.836 0.718 0.865 0.0340 0.970 0.873
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 4
#> 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
#> GSM613638 2 0.0000 0.992 0.000 1.000
#> GSM613639 1 0.0000 0.992 1.000 0.000
#> GSM613640 1 0.0000 0.992 1.000 0.000
#> GSM613641 1 0.0000 0.992 1.000 0.000
#> GSM613642 1 0.0000 0.992 1.000 0.000
#> GSM613643 1 0.0000 0.992 1.000 0.000
#> GSM613644 1 0.1414 0.973 0.980 0.020
#> GSM613645 1 0.0000 0.992 1.000 0.000
#> GSM613646 1 0.9686 0.339 0.604 0.396
#> GSM613647 2 0.0000 0.992 0.000 1.000
#> GSM613648 2 0.0000 0.992 0.000 1.000
#> GSM613649 2 0.0000 0.992 0.000 1.000
#> GSM613650 2 0.0000 0.992 0.000 1.000
#> GSM613651 2 0.0000 0.992 0.000 1.000
#> GSM613652 2 0.0000 0.992 0.000 1.000
#> GSM613653 2 0.0000 0.992 0.000 1.000
#> GSM613654 2 0.0000 0.992 0.000 1.000
#> GSM613655 1 0.0000 0.992 1.000 0.000
#> GSM613656 2 0.0000 0.992 0.000 1.000
#> GSM613657 2 0.0000 0.992 0.000 1.000
#> GSM613658 1 0.3274 0.931 0.940 0.060
#> GSM613659 1 0.0000 0.992 1.000 0.000
#> GSM613660 1 0.0000 0.992 1.000 0.000
#> GSM613661 1 0.0000 0.992 1.000 0.000
#> GSM613662 1 0.0000 0.992 1.000 0.000
#> GSM613663 1 0.0000 0.992 1.000 0.000
#> GSM613664 1 0.0000 0.992 1.000 0.000
#> GSM613665 1 0.0000 0.992 1.000 0.000
#> GSM613666 1 0.0000 0.992 1.000 0.000
#> GSM613667 1 0.0000 0.992 1.000 0.000
#> GSM613668 1 0.0000 0.992 1.000 0.000
#> GSM613669 1 0.0000 0.992 1.000 0.000
#> GSM613670 1 0.0000 0.992 1.000 0.000
#> GSM613671 1 0.0000 0.992 1.000 0.000
#> GSM613672 1 0.0000 0.992 1.000 0.000
#> GSM613673 1 0.0000 0.992 1.000 0.000
#> GSM613674 1 0.0000 0.992 1.000 0.000
#> GSM613675 1 0.0000 0.992 1.000 0.000
#> GSM613676 1 0.0000 0.992 1.000 0.000
#> GSM613677 1 0.1184 0.977 0.984 0.016
#> GSM613678 1 0.0000 0.992 1.000 0.000
#> GSM613679 1 0.0000 0.992 1.000 0.000
#> GSM613680 1 0.0000 0.992 1.000 0.000
#> GSM613681 1 0.0000 0.992 1.000 0.000
#> GSM613682 1 0.0000 0.992 1.000 0.000
#> GSM613683 1 0.0000 0.992 1.000 0.000
#> GSM613684 1 0.0000 0.992 1.000 0.000
#> GSM613685 1 0.0000 0.992 1.000 0.000
#> GSM613686 1 0.0000 0.992 1.000 0.000
#> GSM613687 1 0.0000 0.992 1.000 0.000
#> GSM613688 1 0.0000 0.992 1.000 0.000
#> GSM613689 2 0.0000 0.992 0.000 1.000
#> GSM613690 2 0.0000 0.992 0.000 1.000
#> GSM613691 1 0.0000 0.992 1.000 0.000
#> GSM613692 2 0.0000 0.992 0.000 1.000
#> GSM613693 2 0.1414 0.972 0.020 0.980
#> GSM613694 2 0.0000 0.992 0.000 1.000
#> GSM613695 2 0.0000 0.992 0.000 1.000
#> GSM613696 2 0.0000 0.992 0.000 1.000
#> GSM613697 2 0.0000 0.992 0.000 1.000
#> GSM613698 2 0.0000 0.992 0.000 1.000
#> GSM613699 2 0.0000 0.992 0.000 1.000
#> GSM613700 1 0.0000 0.992 1.000 0.000
#> GSM613701 1 0.0000 0.992 1.000 0.000
#> GSM613702 1 0.0000 0.992 1.000 0.000
#> GSM613703 1 0.0000 0.992 1.000 0.000
#> GSM613704 1 0.0000 0.992 1.000 0.000
#> GSM613705 2 0.0000 0.992 0.000 1.000
#> GSM613706 1 0.0000 0.992 1.000 0.000
#> GSM613707 1 0.0000 0.992 1.000 0.000
#> GSM613708 1 0.0000 0.992 1.000 0.000
#> GSM613709 1 0.0000 0.992 1.000 0.000
#> GSM613710 1 0.0000 0.992 1.000 0.000
#> GSM613711 2 0.0000 0.992 0.000 1.000
#> GSM613712 2 0.0000 0.992 0.000 1.000
#> GSM613713 2 0.0000 0.992 0.000 1.000
#> GSM613714 2 0.0000 0.992 0.000 1.000
#> GSM613715 2 0.0000 0.992 0.000 1.000
#> GSM613716 2 0.0000 0.992 0.000 1.000
#> GSM613717 2 0.0000 0.992 0.000 1.000
#> GSM613718 2 0.0000 0.992 0.000 1.000
#> GSM613719 2 0.0000 0.992 0.000 1.000
#> GSM613720 2 0.0000 0.992 0.000 1.000
#> GSM613721 1 0.0672 0.985 0.992 0.008
#> GSM613722 1 0.0000 0.992 1.000 0.000
#> GSM613723 2 0.0000 0.992 0.000 1.000
#> GSM613724 1 0.0000 0.992 1.000 0.000
#> GSM613725 1 0.0000 0.992 1.000 0.000
#> GSM613726 1 0.0000 0.992 1.000 0.000
#> GSM613727 1 0.0000 0.992 1.000 0.000
#> GSM613728 1 0.0000 0.992 1.000 0.000
#> GSM613729 1 0.0000 0.992 1.000 0.000
#> GSM613730 1 0.0000 0.992 1.000 0.000
#> GSM613731 1 0.0000 0.992 1.000 0.000
#> GSM613732 2 0.0000 0.992 0.000 1.000
#> GSM613733 2 0.0000 0.992 0.000 1.000
#> GSM613734 2 0.9732 0.310 0.404 0.596
#> GSM613735 2 0.0000 0.992 0.000 1.000
#> GSM613736 2 0.0000 0.992 0.000 1.000
#> GSM613737 2 0.0000 0.992 0.000 1.000
#> GSM613738 2 0.0000 0.992 0.000 1.000
#> GSM613739 2 0.0000 0.992 0.000 1.000
#> GSM613740 2 0.0000 0.992 0.000 1.000
#> GSM613741 2 0.0000 0.992 0.000 1.000
#> GSM613742 2 0.0000 0.992 0.000 1.000
#> GSM613743 2 0.0000 0.992 0.000 1.000
#> GSM613744 2 0.0000 0.992 0.000 1.000
#> GSM613745 2 0.0000 0.992 0.000 1.000
#> GSM613746 2 0.0000 0.992 0.000 1.000
#> GSM613747 2 0.0000 0.992 0.000 1.000
#> GSM613748 1 0.0000 0.992 1.000 0.000
#> GSM613749 1 0.0000 0.992 1.000 0.000
#> GSM613750 2 0.0000 0.992 0.000 1.000
#> GSM613751 2 0.0000 0.992 0.000 1.000
#> GSM613752 2 0.0000 0.992 0.000 1.000
#> GSM613753 2 0.0000 0.992 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM613638 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613639 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613640 2 0.0237 0.967 0.004 0.996 0.000
#> GSM613641 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613642 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613643 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613644 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613645 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613646 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613647 3 0.0592 0.923 0.000 0.012 0.988
#> GSM613648 3 0.4062 0.877 0.000 0.164 0.836
#> GSM613649 3 0.4062 0.877 0.000 0.164 0.836
#> GSM613650 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613651 3 0.0000 0.926 0.000 0.000 1.000
#> GSM613652 3 0.0000 0.926 0.000 0.000 1.000
#> GSM613653 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613654 3 0.0000 0.926 0.000 0.000 1.000
#> GSM613655 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613656 3 0.0000 0.926 0.000 0.000 1.000
#> GSM613657 3 0.4062 0.877 0.000 0.164 0.836
#> GSM613658 2 0.2400 0.901 0.064 0.932 0.004
#> GSM613659 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613660 1 0.6267 0.196 0.548 0.452 0.000
#> GSM613661 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613662 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613663 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613664 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613665 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613666 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613667 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613668 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613669 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613670 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613671 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613672 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613673 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613674 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613675 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613676 1 0.5785 0.508 0.668 0.332 0.000
#> GSM613677 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613678 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613679 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613680 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613681 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613682 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613683 1 0.1643 0.934 0.956 0.044 0.000
#> GSM613684 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613685 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613686 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613687 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613688 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613689 3 0.4062 0.877 0.000 0.164 0.836
#> GSM613690 3 0.0000 0.926 0.000 0.000 1.000
#> GSM613691 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613692 3 0.0000 0.926 0.000 0.000 1.000
#> GSM613693 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613694 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613695 3 0.3551 0.889 0.000 0.132 0.868
#> GSM613696 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613697 3 0.0000 0.926 0.000 0.000 1.000
#> GSM613698 3 0.0000 0.926 0.000 0.000 1.000
#> GSM613699 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613700 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613701 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613702 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613703 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613704 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613705 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613706 1 0.4504 0.748 0.804 0.196 0.000
#> GSM613707 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613708 1 0.0424 0.968 0.992 0.008 0.000
#> GSM613709 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613710 1 0.4555 0.736 0.800 0.200 0.000
#> GSM613711 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613712 3 0.4062 0.877 0.000 0.164 0.836
#> GSM613713 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613714 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613715 3 0.4062 0.877 0.000 0.164 0.836
#> GSM613716 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613717 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613718 3 0.0000 0.926 0.000 0.000 1.000
#> GSM613719 3 0.4062 0.877 0.000 0.164 0.836
#> GSM613720 3 0.4062 0.877 0.000 0.164 0.836
#> GSM613721 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613722 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613723 3 0.0000 0.926 0.000 0.000 1.000
#> GSM613724 2 0.5138 0.655 0.252 0.748 0.000
#> GSM613725 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613726 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613727 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613728 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613729 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613730 2 0.3267 0.841 0.116 0.884 0.000
#> GSM613731 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613732 3 0.0000 0.926 0.000 0.000 1.000
#> GSM613733 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613734 2 0.4782 0.788 0.016 0.820 0.164
#> GSM613735 3 0.0000 0.926 0.000 0.000 1.000
#> GSM613736 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613737 3 0.0000 0.926 0.000 0.000 1.000
#> GSM613738 3 0.0000 0.926 0.000 0.000 1.000
#> GSM613739 3 0.0000 0.926 0.000 0.000 1.000
#> GSM613740 3 0.4062 0.877 0.000 0.164 0.836
#> GSM613741 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613742 3 0.0000 0.926 0.000 0.000 1.000
#> GSM613743 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613744 3 0.4062 0.877 0.000 0.164 0.836
#> GSM613745 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613746 2 0.0000 0.971 0.000 1.000 0.000
#> GSM613747 2 0.4062 0.799 0.000 0.836 0.164
#> GSM613748 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613749 1 0.0000 0.974 1.000 0.000 0.000
#> GSM613750 3 0.0000 0.926 0.000 0.000 1.000
#> GSM613751 3 0.4062 0.877 0.000 0.164 0.836
#> GSM613752 3 0.4062 0.877 0.000 0.164 0.836
#> GSM613753 3 0.0000 0.926 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 1 0.0000 0.941 1.000 0.000 0.000 0.000
#> GSM613639 2 0.0188 0.978 0.004 0.996 0.000 0.000
#> GSM613640 1 0.0000 0.941 1.000 0.000 0.000 0.000
#> GSM613641 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613642 1 0.0000 0.941 1.000 0.000 0.000 0.000
#> GSM613643 1 0.0000 0.941 1.000 0.000 0.000 0.000
#> GSM613644 1 0.0000 0.941 1.000 0.000 0.000 0.000
#> GSM613645 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613646 4 0.0000 0.985 0.000 0.000 0.000 1.000
#> GSM613647 3 0.0000 0.980 0.000 0.000 1.000 0.000
#> GSM613648 3 0.4817 0.373 0.000 0.000 0.612 0.388
#> GSM613649 3 0.0592 0.974 0.000 0.000 0.984 0.016
#> GSM613650 4 0.0000 0.985 0.000 0.000 0.000 1.000
#> GSM613651 3 0.0000 0.980 0.000 0.000 1.000 0.000
#> GSM613652 3 0.0000 0.980 0.000 0.000 1.000 0.000
#> GSM613653 4 0.0000 0.985 0.000 0.000 0.000 1.000
#> GSM613654 3 0.0000 0.980 0.000 0.000 1.000 0.000
#> GSM613655 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613656 3 0.0000 0.980 0.000 0.000 1.000 0.000
#> GSM613657 3 0.0469 0.977 0.000 0.000 0.988 0.012
#> GSM613658 1 0.0000 0.941 1.000 0.000 0.000 0.000
#> GSM613659 2 0.3444 0.775 0.184 0.816 0.000 0.000
#> GSM613660 1 0.3569 0.741 0.804 0.000 0.000 0.196
#> GSM613661 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613662 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613663 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613664 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613665 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613666 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613667 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613668 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613669 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613670 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613671 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613672 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613673 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613674 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613675 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613676 2 0.6537 0.508 0.200 0.636 0.000 0.164
#> GSM613677 1 0.0000 0.941 1.000 0.000 0.000 0.000
#> GSM613678 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613679 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613680 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613681 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613682 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613683 1 0.0000 0.941 1.000 0.000 0.000 0.000
#> GSM613684 4 0.4304 0.566 0.284 0.000 0.000 0.716
#> GSM613685 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613686 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613687 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613688 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613689 3 0.1716 0.927 0.000 0.000 0.936 0.064
#> GSM613690 3 0.0000 0.980 0.000 0.000 1.000 0.000
#> GSM613691 4 0.0000 0.985 0.000 0.000 0.000 1.000
#> GSM613692 3 0.0000 0.980 0.000 0.000 1.000 0.000
#> GSM613693 4 0.0000 0.985 0.000 0.000 0.000 1.000
#> GSM613694 4 0.0000 0.985 0.000 0.000 0.000 1.000
#> GSM613695 3 0.0188 0.979 0.000 0.000 0.996 0.004
#> GSM613696 4 0.0000 0.985 0.000 0.000 0.000 1.000
#> GSM613697 3 0.0000 0.980 0.000 0.000 1.000 0.000
#> GSM613698 3 0.0000 0.980 0.000 0.000 1.000 0.000
#> GSM613699 4 0.0000 0.985 0.000 0.000 0.000 1.000
#> GSM613700 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613701 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613702 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613703 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613704 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613705 1 0.3311 0.793 0.828 0.000 0.000 0.172
#> GSM613706 1 0.0000 0.941 1.000 0.000 0.000 0.000
#> GSM613707 2 0.0592 0.966 0.000 0.984 0.000 0.016
#> GSM613708 1 0.0000 0.941 1.000 0.000 0.000 0.000
#> GSM613709 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613710 1 0.0000 0.941 1.000 0.000 0.000 0.000
#> GSM613711 4 0.0000 0.985 0.000 0.000 0.000 1.000
#> GSM613712 3 0.0188 0.979 0.000 0.000 0.996 0.004
#> GSM613713 4 0.0000 0.985 0.000 0.000 0.000 1.000
#> GSM613714 4 0.0000 0.985 0.000 0.000 0.000 1.000
#> GSM613715 3 0.0469 0.977 0.000 0.000 0.988 0.012
#> GSM613716 4 0.0000 0.985 0.000 0.000 0.000 1.000
#> GSM613717 4 0.0000 0.985 0.000 0.000 0.000 1.000
#> GSM613718 3 0.0336 0.978 0.000 0.000 0.992 0.008
#> GSM613719 3 0.0469 0.977 0.000 0.000 0.988 0.012
#> GSM613720 3 0.0469 0.977 0.000 0.000 0.988 0.012
#> GSM613721 4 0.0000 0.985 0.000 0.000 0.000 1.000
#> GSM613722 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613723 3 0.0000 0.980 0.000 0.000 1.000 0.000
#> GSM613724 1 0.0000 0.941 1.000 0.000 0.000 0.000
#> GSM613725 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613726 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613727 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613728 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613729 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613730 1 0.0000 0.941 1.000 0.000 0.000 0.000
#> GSM613731 1 0.0000 0.941 1.000 0.000 0.000 0.000
#> GSM613732 3 0.0000 0.980 0.000 0.000 1.000 0.000
#> GSM613733 4 0.0000 0.985 0.000 0.000 0.000 1.000
#> GSM613734 1 0.3718 0.792 0.820 0.000 0.012 0.168
#> GSM613735 3 0.0000 0.980 0.000 0.000 1.000 0.000
#> GSM613736 4 0.0000 0.985 0.000 0.000 0.000 1.000
#> GSM613737 3 0.0000 0.980 0.000 0.000 1.000 0.000
#> GSM613738 3 0.0000 0.980 0.000 0.000 1.000 0.000
#> GSM613739 3 0.0000 0.980 0.000 0.000 1.000 0.000
#> GSM613740 3 0.0469 0.977 0.000 0.000 0.988 0.012
#> GSM613741 4 0.0000 0.985 0.000 0.000 0.000 1.000
#> GSM613742 3 0.0000 0.980 0.000 0.000 1.000 0.000
#> GSM613743 4 0.0000 0.985 0.000 0.000 0.000 1.000
#> GSM613744 3 0.0469 0.977 0.000 0.000 0.988 0.012
#> GSM613745 4 0.0000 0.985 0.000 0.000 0.000 1.000
#> GSM613746 4 0.0000 0.985 0.000 0.000 0.000 1.000
#> GSM613747 1 0.5300 0.350 0.580 0.000 0.012 0.408
#> GSM613748 2 0.4164 0.645 0.264 0.736 0.000 0.000
#> GSM613749 2 0.0000 0.981 0.000 1.000 0.000 0.000
#> GSM613750 3 0.0000 0.980 0.000 0.000 1.000 0.000
#> GSM613751 3 0.0469 0.977 0.000 0.000 0.988 0.012
#> GSM613752 3 0.0469 0.977 0.000 0.000 0.988 0.012
#> GSM613753 3 0.0000 0.980 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
#> GSM613638 4 0.0000 0.9288 0.000 0.000 0.000 1.000 0.000
#> GSM613639 1 0.0162 0.8446 0.996 0.000 0.000 0.004 0.000
#> GSM613640 4 0.0000 0.9288 0.000 0.000 0.000 1.000 0.000
#> GSM613641 1 0.2127 0.7556 0.892 0.108 0.000 0.000 0.000
#> GSM613642 4 0.0000 0.9288 0.000 0.000 0.000 1.000 0.000
#> GSM613643 4 0.0000 0.9288 0.000 0.000 0.000 1.000 0.000
#> GSM613644 4 0.0000 0.9288 0.000 0.000 0.000 1.000 0.000
#> GSM613645 1 0.0000 0.8470 1.000 0.000 0.000 0.000 0.000
#> GSM613646 3 0.0000 0.9839 0.000 0.000 1.000 0.000 0.000
#> GSM613647 5 0.0000 0.9642 0.000 0.000 0.000 0.000 1.000
#> GSM613648 5 0.4774 0.4433 0.000 0.028 0.360 0.000 0.612
#> GSM613649 5 0.1270 0.9422 0.000 0.000 0.052 0.000 0.948
#> GSM613650 3 0.0000 0.9839 0.000 0.000 1.000 0.000 0.000
#> GSM613651 5 0.0000 0.9642 0.000 0.000 0.000 0.000 1.000
#> GSM613652 5 0.0000 0.9642 0.000 0.000 0.000 0.000 1.000
#> GSM613653 3 0.0000 0.9839 0.000 0.000 1.000 0.000 0.000
#> GSM613654 5 0.0000 0.9642 0.000 0.000 0.000 0.000 1.000
#> GSM613655 1 0.0000 0.8470 1.000 0.000 0.000 0.000 0.000
#> GSM613656 5 0.0000 0.9642 0.000 0.000 0.000 0.000 1.000
#> GSM613657 5 0.1197 0.9452 0.000 0.000 0.048 0.000 0.952
#> GSM613658 4 0.0000 0.9288 0.000 0.000 0.000 1.000 0.000
#> GSM613659 1 0.5038 0.6080 0.704 0.164 0.000 0.132 0.000
#> GSM613660 4 0.3695 0.7172 0.000 0.164 0.036 0.800 0.000
#> GSM613661 1 0.0000 0.8470 1.000 0.000 0.000 0.000 0.000
#> GSM613662 2 0.3707 0.6293 0.284 0.716 0.000 0.000 0.000
#> GSM613663 1 0.0000 0.8470 1.000 0.000 0.000 0.000 0.000
#> GSM613664 2 0.0963 0.7810 0.036 0.964 0.000 0.000 0.000
#> GSM613665 1 0.2773 0.7425 0.836 0.164 0.000 0.000 0.000
#> GSM613666 1 0.0000 0.8470 1.000 0.000 0.000 0.000 0.000
#> GSM613667 1 0.0000 0.8470 1.000 0.000 0.000 0.000 0.000
#> GSM613668 1 0.0000 0.8470 1.000 0.000 0.000 0.000 0.000
#> GSM613669 2 0.3837 0.6119 0.308 0.692 0.000 0.000 0.000
#> GSM613670 2 0.0963 0.7810 0.036 0.964 0.000 0.000 0.000
#> GSM613671 1 0.3366 0.5847 0.768 0.232 0.000 0.000 0.000
#> GSM613672 1 0.0000 0.8470 1.000 0.000 0.000 0.000 0.000
#> GSM613673 1 0.0000 0.8470 1.000 0.000 0.000 0.000 0.000
#> GSM613674 1 0.4126 0.4083 0.620 0.380 0.000 0.000 0.000
#> GSM613675 1 0.2773 0.7425 0.836 0.164 0.000 0.000 0.000
#> GSM613676 1 0.5887 0.5496 0.668 0.164 0.032 0.136 0.000
#> GSM613677 4 0.0000 0.9288 0.000 0.000 0.000 1.000 0.000
#> GSM613678 1 0.0000 0.8470 1.000 0.000 0.000 0.000 0.000
#> GSM613679 2 0.4227 0.1517 0.420 0.580 0.000 0.000 0.000
#> GSM613680 1 0.0000 0.8470 1.000 0.000 0.000 0.000 0.000
#> GSM613681 1 0.0000 0.8470 1.000 0.000 0.000 0.000 0.000
#> GSM613682 1 0.0000 0.8470 1.000 0.000 0.000 0.000 0.000
#> GSM613683 4 0.0000 0.9288 0.000 0.000 0.000 1.000 0.000
#> GSM613684 3 0.3707 0.5689 0.000 0.000 0.716 0.284 0.000
#> GSM613685 1 0.3612 0.6236 0.732 0.268 0.000 0.000 0.000
#> GSM613686 1 0.4242 -0.0168 0.572 0.428 0.000 0.000 0.000
#> GSM613687 1 0.0000 0.8470 1.000 0.000 0.000 0.000 0.000
#> GSM613688 1 0.1043 0.8289 0.960 0.040 0.000 0.000 0.000
#> GSM613689 5 0.2020 0.8936 0.000 0.000 0.100 0.000 0.900
#> GSM613690 5 0.0963 0.9612 0.000 0.036 0.000 0.000 0.964
#> GSM613691 3 0.0000 0.9839 0.000 0.000 1.000 0.000 0.000
#> GSM613692 5 0.0000 0.9642 0.000 0.000 0.000 0.000 1.000
#> GSM613693 3 0.0000 0.9839 0.000 0.000 1.000 0.000 0.000
#> GSM613694 3 0.0000 0.9839 0.000 0.000 1.000 0.000 0.000
#> GSM613695 5 0.1124 0.9610 0.000 0.036 0.004 0.000 0.960
#> GSM613696 3 0.0000 0.9839 0.000 0.000 1.000 0.000 0.000
#> GSM613697 5 0.0000 0.9642 0.000 0.000 0.000 0.000 1.000
#> GSM613698 5 0.0000 0.9642 0.000 0.000 0.000 0.000 1.000
#> GSM613699 3 0.0000 0.9839 0.000 0.000 1.000 0.000 0.000
#> GSM613700 2 0.0963 0.7810 0.036 0.964 0.000 0.000 0.000
#> GSM613701 1 0.0000 0.8470 1.000 0.000 0.000 0.000 0.000
#> GSM613702 1 0.2773 0.7425 0.836 0.164 0.000 0.000 0.000
#> GSM613703 2 0.3109 0.6948 0.200 0.800 0.000 0.000 0.000
#> GSM613704 2 0.0963 0.7810 0.036 0.964 0.000 0.000 0.000
#> GSM613705 4 0.2852 0.7729 0.000 0.000 0.172 0.828 0.000
#> GSM613706 4 0.0404 0.9170 0.012 0.000 0.000 0.988 0.000
#> GSM613707 1 0.3053 0.7385 0.828 0.164 0.008 0.000 0.000
#> GSM613708 4 0.0000 0.9288 0.000 0.000 0.000 1.000 0.000
#> GSM613709 1 0.0000 0.8470 1.000 0.000 0.000 0.000 0.000
#> GSM613710 4 0.0000 0.9288 0.000 0.000 0.000 1.000 0.000
#> GSM613711 3 0.0000 0.9839 0.000 0.000 1.000 0.000 0.000
#> GSM613712 5 0.0451 0.9642 0.000 0.008 0.004 0.000 0.988
#> GSM613713 3 0.0000 0.9839 0.000 0.000 1.000 0.000 0.000
#> GSM613714 3 0.0000 0.9839 0.000 0.000 1.000 0.000 0.000
#> GSM613715 5 0.1364 0.9592 0.000 0.036 0.012 0.000 0.952
#> GSM613716 3 0.0000 0.9839 0.000 0.000 1.000 0.000 0.000
#> GSM613717 3 0.0000 0.9839 0.000 0.000 1.000 0.000 0.000
#> GSM613718 5 0.1251 0.9602 0.000 0.036 0.008 0.000 0.956
#> GSM613719 5 0.1121 0.9479 0.000 0.000 0.044 0.000 0.956
#> GSM613720 5 0.1364 0.9592 0.000 0.036 0.012 0.000 0.952
#> GSM613721 3 0.0000 0.9839 0.000 0.000 1.000 0.000 0.000
#> GSM613722 2 0.3895 0.5718 0.320 0.680 0.000 0.000 0.000
#> GSM613723 5 0.0000 0.9642 0.000 0.000 0.000 0.000 1.000
#> GSM613724 4 0.0000 0.9288 0.000 0.000 0.000 1.000 0.000
#> GSM613725 1 0.4219 0.3146 0.584 0.416 0.000 0.000 0.000
#> GSM613726 1 0.0000 0.8470 1.000 0.000 0.000 0.000 0.000
#> GSM613727 1 0.0000 0.8470 1.000 0.000 0.000 0.000 0.000
#> GSM613728 1 0.2813 0.7394 0.832 0.168 0.000 0.000 0.000
#> GSM613729 1 0.2127 0.7556 0.892 0.108 0.000 0.000 0.000
#> GSM613730 4 0.0000 0.9288 0.000 0.000 0.000 1.000 0.000
#> GSM613731 4 0.0000 0.9288 0.000 0.000 0.000 1.000 0.000
#> GSM613732 5 0.0963 0.9612 0.000 0.036 0.000 0.000 0.964
#> GSM613733 3 0.0000 0.9839 0.000 0.000 1.000 0.000 0.000
#> GSM613734 4 0.3953 0.7479 0.000 0.000 0.168 0.784 0.048
#> GSM613735 5 0.0000 0.9642 0.000 0.000 0.000 0.000 1.000
#> GSM613736 3 0.0000 0.9839 0.000 0.000 1.000 0.000 0.000
#> GSM613737 5 0.0000 0.9642 0.000 0.000 0.000 0.000 1.000
#> GSM613738 5 0.0000 0.9642 0.000 0.000 0.000 0.000 1.000
#> GSM613739 5 0.0000 0.9642 0.000 0.000 0.000 0.000 1.000
#> GSM613740 5 0.1364 0.9592 0.000 0.036 0.012 0.000 0.952
#> GSM613741 3 0.0000 0.9839 0.000 0.000 1.000 0.000 0.000
#> GSM613742 5 0.0000 0.9642 0.000 0.000 0.000 0.000 1.000
#> GSM613743 3 0.0000 0.9839 0.000 0.000 1.000 0.000 0.000
#> GSM613744 5 0.1364 0.9592 0.000 0.036 0.012 0.000 0.952
#> GSM613745 3 0.0000 0.9839 0.000 0.000 1.000 0.000 0.000
#> GSM613746 3 0.0000 0.9839 0.000 0.000 1.000 0.000 0.000
#> GSM613747 4 0.5236 0.3008 0.000 0.000 0.408 0.544 0.048
#> GSM613748 1 0.4467 0.6685 0.752 0.164 0.000 0.084 0.000
#> GSM613749 1 0.4030 0.1983 0.648 0.352 0.000 0.000 0.000
#> GSM613750 5 0.0963 0.9612 0.000 0.036 0.000 0.000 0.964
#> GSM613751 5 0.1364 0.9592 0.000 0.036 0.012 0.000 0.952
#> GSM613752 5 0.1364 0.9592 0.000 0.036 0.012 0.000 0.952
#> GSM613753 5 0.0963 0.9612 0.000 0.036 0.000 0.000 0.964
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM613638 4 0.0000 0.9677 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613639 1 0.0146 0.8256 0.996 0.000 0.000 0.004 0.000 0.000
#> GSM613640 4 0.0000 0.9677 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613641 1 0.2135 0.7247 0.872 0.128 0.000 0.000 0.000 0.000
#> GSM613642 4 0.0146 0.9649 0.000 0.000 0.000 0.996 0.000 0.004
#> GSM613643 4 0.0000 0.9677 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613644 4 0.0000 0.9677 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613645 1 0.0000 0.8276 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613646 3 0.0000 0.9833 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613647 5 0.3695 0.5263 0.000 0.000 0.000 0.000 0.624 0.376
#> GSM613648 5 0.5526 0.2471 0.000 0.000 0.324 0.000 0.524 0.152
#> GSM613649 5 0.5182 0.4612 0.000 0.000 0.096 0.000 0.532 0.372
#> GSM613650 3 0.0000 0.9833 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613651 5 0.0000 0.5508 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613652 5 0.0000 0.5508 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613653 3 0.0000 0.9833 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613654 5 0.0000 0.5508 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613655 1 0.0000 0.8276 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613656 5 0.0000 0.5508 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613657 5 0.5152 0.4626 0.000 0.000 0.092 0.000 0.532 0.376
#> GSM613658 4 0.0000 0.9677 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613659 1 0.4929 0.5599 0.664 0.200 0.000 0.132 0.000 0.004
#> GSM613660 4 0.2793 0.7057 0.000 0.200 0.000 0.800 0.000 0.000
#> GSM613661 1 0.0000 0.8276 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613662 2 0.3641 0.6091 0.248 0.732 0.000 0.000 0.000 0.020
#> GSM613663 1 0.0000 0.8276 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613664 2 0.0000 0.7140 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613665 1 0.3315 0.6880 0.780 0.200 0.000 0.000 0.000 0.020
#> GSM613666 1 0.0000 0.8276 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613667 1 0.0000 0.8276 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613668 1 0.0000 0.8276 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613669 2 0.3446 0.5547 0.308 0.692 0.000 0.000 0.000 0.000
#> GSM613670 2 0.0000 0.7140 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613671 1 0.3023 0.5939 0.768 0.232 0.000 0.000 0.000 0.000
#> GSM613672 1 0.0000 0.8276 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613673 1 0.0000 0.8276 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613674 1 0.4620 0.4016 0.584 0.368 0.000 0.000 0.000 0.048
#> GSM613675 1 0.2933 0.6959 0.796 0.200 0.000 0.000 0.000 0.004
#> GSM613676 1 0.4929 0.5535 0.664 0.200 0.000 0.132 0.000 0.004
#> GSM613677 4 0.0000 0.9677 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613678 1 0.0000 0.8276 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613679 2 0.3955 0.1590 0.384 0.608 0.000 0.000 0.000 0.008
#> GSM613680 1 0.0000 0.8276 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613681 1 0.0000 0.8276 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613682 1 0.0000 0.8276 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613683 4 0.0000 0.9677 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613684 3 0.3468 0.5795 0.000 0.000 0.712 0.284 0.000 0.004
#> GSM613685 1 0.4460 0.5243 0.644 0.304 0.000 0.000 0.000 0.052
#> GSM613686 1 0.3810 0.0544 0.572 0.428 0.000 0.000 0.000 0.000
#> GSM613687 1 0.0000 0.8276 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613688 1 0.1528 0.8032 0.936 0.048 0.000 0.000 0.000 0.016
#> GSM613689 5 0.5576 0.3740 0.000 0.000 0.144 0.000 0.480 0.376
#> GSM613690 5 0.3857 0.4653 0.000 0.000 0.000 0.000 0.532 0.468
#> GSM613691 3 0.0000 0.9833 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613692 5 0.3221 0.5492 0.000 0.000 0.000 0.000 0.736 0.264
#> GSM613693 3 0.0000 0.9833 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613694 3 0.0000 0.9833 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613695 5 0.3857 0.4653 0.000 0.000 0.000 0.000 0.532 0.468
#> GSM613696 3 0.0000 0.9833 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613697 5 0.3221 0.5492 0.000 0.000 0.000 0.000 0.736 0.264
#> GSM613698 5 0.3695 0.5263 0.000 0.000 0.000 0.000 0.624 0.376
#> GSM613699 3 0.0000 0.9833 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613700 2 0.0000 0.7140 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613701 1 0.1075 0.8081 0.952 0.000 0.000 0.000 0.000 0.048
#> GSM613702 1 0.3806 0.6700 0.752 0.200 0.000 0.000 0.000 0.048
#> GSM613703 2 0.2793 0.6087 0.200 0.800 0.000 0.000 0.000 0.000
#> GSM613704 2 0.0000 0.7140 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613705 4 0.2562 0.7570 0.000 0.000 0.172 0.828 0.000 0.000
#> GSM613706 4 0.0363 0.9547 0.012 0.000 0.000 0.988 0.000 0.000
#> GSM613707 1 0.3867 0.6671 0.748 0.200 0.000 0.000 0.000 0.052
#> GSM613708 4 0.0000 0.9677 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613709 1 0.0000 0.8276 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613710 4 0.0000 0.9677 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613711 3 0.0000 0.9833 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613712 5 0.3756 0.5146 0.000 0.000 0.000 0.000 0.600 0.400
#> GSM613713 3 0.0000 0.9833 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613714 3 0.0000 0.9833 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613715 5 0.3857 0.4653 0.000 0.000 0.000 0.000 0.532 0.468
#> GSM613716 3 0.0000 0.9833 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613717 3 0.0000 0.9833 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613718 5 0.3857 0.4653 0.000 0.000 0.000 0.000 0.532 0.468
#> GSM613719 5 0.5029 0.4767 0.000 0.000 0.080 0.000 0.544 0.376
#> GSM613720 5 0.3857 0.4653 0.000 0.000 0.000 0.000 0.532 0.468
#> GSM613721 3 0.0000 0.9833 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613722 2 0.4313 0.5339 0.284 0.668 0.000 0.000 0.000 0.048
#> GSM613723 5 0.0363 0.5407 0.000 0.000 0.000 0.000 0.988 0.012
#> GSM613724 4 0.0000 0.9677 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613725 1 0.4697 0.3155 0.548 0.404 0.000 0.000 0.000 0.048
#> GSM613726 1 0.0000 0.8276 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM613727 1 0.0146 0.8260 0.996 0.004 0.000 0.000 0.000 0.000
#> GSM613728 1 0.3835 0.6661 0.748 0.204 0.000 0.000 0.000 0.048
#> GSM613729 1 0.2135 0.7247 0.872 0.128 0.000 0.000 0.000 0.000
#> GSM613730 4 0.0000 0.9677 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613731 4 0.0000 0.9677 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM613732 5 0.3857 0.4653 0.000 0.000 0.000 0.000 0.532 0.468
#> GSM613733 3 0.0000 0.9833 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613734 5 0.5709 -0.2159 0.000 0.000 0.168 0.364 0.468 0.000
#> GSM613735 5 0.0000 0.5508 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613736 3 0.0000 0.9833 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613737 5 0.0000 0.5508 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613738 5 0.0000 0.5508 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613739 5 0.0000 0.5508 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613740 5 0.3857 0.4653 0.000 0.000 0.000 0.000 0.532 0.468
#> GSM613741 3 0.0000 0.9833 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613742 5 0.0000 0.5508 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM613743 3 0.0000 0.9833 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613744 5 0.3857 0.4653 0.000 0.000 0.000 0.000 0.532 0.468
#> GSM613745 3 0.0000 0.9833 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613746 3 0.0000 0.9833 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM613747 5 0.5495 -0.1706 0.000 0.000 0.404 0.128 0.468 0.000
#> GSM613748 1 0.3945 0.6609 0.748 0.200 0.000 0.048 0.000 0.004
#> GSM613749 1 0.3620 0.2516 0.648 0.352 0.000 0.000 0.000 0.000
#> GSM613750 6 0.1141 0.9976 0.000 0.000 0.000 0.000 0.052 0.948
#> GSM613751 6 0.1204 0.9928 0.000 0.000 0.000 0.000 0.056 0.944
#> GSM613752 6 0.1141 0.9976 0.000 0.000 0.000 0.000 0.052 0.948
#> GSM613753 6 0.1141 0.9976 0.000 0.000 0.000 0.000 0.052 0.948
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) k
#> ATC:pam 114 0.00782 2
#> ATC:pam 115 0.01264 3
#> ATC:pam 114 0.03159 4
#> ATC:pam 109 0.06145 5
#> ATC:pam 96 0.00675 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 27425 rows and 116 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 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 1.000 0.988 0.995 0.5019 0.498 0.498
#> 3 3 0.766 0.799 0.895 0.1706 0.965 0.930
#> 4 4 0.571 0.421 0.744 0.1791 0.866 0.718
#> 5 5 0.593 0.436 0.681 0.0813 0.814 0.545
#> 6 6 0.615 0.611 0.740 0.0544 0.833 0.493
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
#> GSM613638 1 0.118 0.983 0.984 0.016
#> GSM613639 1 0.000 0.999 1.000 0.000
#> GSM613640 1 0.000 0.999 1.000 0.000
#> GSM613641 1 0.000 0.999 1.000 0.000
#> GSM613642 1 0.000 0.999 1.000 0.000
#> GSM613643 1 0.000 0.999 1.000 0.000
#> GSM613644 1 0.000 0.999 1.000 0.000
#> GSM613645 1 0.000 0.999 1.000 0.000
#> GSM613646 2 0.000 0.991 0.000 1.000
#> GSM613647 2 0.000 0.991 0.000 1.000
#> GSM613648 2 0.000 0.991 0.000 1.000
#> GSM613649 2 0.000 0.991 0.000 1.000
#> GSM613650 2 0.000 0.991 0.000 1.000
#> GSM613651 2 0.000 0.991 0.000 1.000
#> GSM613652 2 0.000 0.991 0.000 1.000
#> GSM613653 2 0.000 0.991 0.000 1.000
#> GSM613654 2 0.000 0.991 0.000 1.000
#> GSM613655 1 0.000 0.999 1.000 0.000
#> GSM613656 2 0.000 0.991 0.000 1.000
#> GSM613657 2 0.000 0.991 0.000 1.000
#> GSM613658 1 0.118 0.983 0.984 0.016
#> GSM613659 1 0.000 0.999 1.000 0.000
#> GSM613660 1 0.000 0.999 1.000 0.000
#> GSM613661 1 0.000 0.999 1.000 0.000
#> GSM613662 1 0.000 0.999 1.000 0.000
#> GSM613663 1 0.000 0.999 1.000 0.000
#> GSM613664 1 0.000 0.999 1.000 0.000
#> GSM613665 1 0.000 0.999 1.000 0.000
#> GSM613666 1 0.000 0.999 1.000 0.000
#> GSM613667 1 0.000 0.999 1.000 0.000
#> GSM613668 1 0.000 0.999 1.000 0.000
#> GSM613669 1 0.000 0.999 1.000 0.000
#> GSM613670 1 0.000 0.999 1.000 0.000
#> GSM613671 1 0.000 0.999 1.000 0.000
#> GSM613672 1 0.000 0.999 1.000 0.000
#> GSM613673 1 0.000 0.999 1.000 0.000
#> GSM613674 1 0.000 0.999 1.000 0.000
#> GSM613675 1 0.000 0.999 1.000 0.000
#> GSM613676 1 0.000 0.999 1.000 0.000
#> GSM613677 1 0.000 0.999 1.000 0.000
#> GSM613678 1 0.000 0.999 1.000 0.000
#> GSM613679 1 0.000 0.999 1.000 0.000
#> GSM613680 1 0.000 0.999 1.000 0.000
#> GSM613681 1 0.000 0.999 1.000 0.000
#> GSM613682 1 0.000 0.999 1.000 0.000
#> GSM613683 1 0.000 0.999 1.000 0.000
#> GSM613684 1 0.000 0.999 1.000 0.000
#> GSM613685 1 0.000 0.999 1.000 0.000
#> GSM613686 1 0.000 0.999 1.000 0.000
#> GSM613687 1 0.000 0.999 1.000 0.000
#> GSM613688 1 0.000 0.999 1.000 0.000
#> GSM613689 2 0.000 0.991 0.000 1.000
#> GSM613690 2 0.000 0.991 0.000 1.000
#> GSM613691 2 0.118 0.976 0.016 0.984
#> GSM613692 2 0.000 0.991 0.000 1.000
#> GSM613693 2 0.000 0.991 0.000 1.000
#> GSM613694 2 0.000 0.991 0.000 1.000
#> GSM613695 2 0.000 0.991 0.000 1.000
#> GSM613696 2 0.000 0.991 0.000 1.000
#> GSM613697 2 0.000 0.991 0.000 1.000
#> GSM613698 2 0.000 0.991 0.000 1.000
#> GSM613699 2 0.000 0.991 0.000 1.000
#> GSM613700 1 0.000 0.999 1.000 0.000
#> GSM613701 1 0.000 0.999 1.000 0.000
#> GSM613702 1 0.000 0.999 1.000 0.000
#> GSM613703 1 0.000 0.999 1.000 0.000
#> GSM613704 1 0.000 0.999 1.000 0.000
#> GSM613705 2 0.988 0.225 0.436 0.564
#> GSM613706 1 0.000 0.999 1.000 0.000
#> GSM613707 1 0.000 0.999 1.000 0.000
#> GSM613708 1 0.000 0.999 1.000 0.000
#> GSM613709 1 0.000 0.999 1.000 0.000
#> GSM613710 1 0.000 0.999 1.000 0.000
#> GSM613711 2 0.000 0.991 0.000 1.000
#> GSM613712 2 0.000 0.991 0.000 1.000
#> GSM613713 2 0.000 0.991 0.000 1.000
#> GSM613714 2 0.000 0.991 0.000 1.000
#> GSM613715 2 0.000 0.991 0.000 1.000
#> GSM613716 2 0.000 0.991 0.000 1.000
#> GSM613717 2 0.000 0.991 0.000 1.000
#> GSM613718 2 0.000 0.991 0.000 1.000
#> GSM613719 2 0.000 0.991 0.000 1.000
#> GSM613720 2 0.000 0.991 0.000 1.000
#> GSM613721 2 0.118 0.976 0.016 0.984
#> GSM613722 1 0.000 0.999 1.000 0.000
#> GSM613723 2 0.000 0.991 0.000 1.000
#> GSM613724 1 0.000 0.999 1.000 0.000
#> GSM613725 1 0.000 0.999 1.000 0.000
#> GSM613726 1 0.000 0.999 1.000 0.000
#> GSM613727 1 0.000 0.999 1.000 0.000
#> GSM613728 1 0.000 0.999 1.000 0.000
#> GSM613729 1 0.000 0.999 1.000 0.000
#> GSM613730 1 0.000 0.999 1.000 0.000
#> GSM613731 1 0.000 0.999 1.000 0.000
#> GSM613732 2 0.000 0.991 0.000 1.000
#> GSM613733 2 0.000 0.991 0.000 1.000
#> GSM613734 1 0.295 0.946 0.948 0.052
#> GSM613735 2 0.000 0.991 0.000 1.000
#> GSM613736 2 0.000 0.991 0.000 1.000
#> GSM613737 2 0.000 0.991 0.000 1.000
#> GSM613738 2 0.000 0.991 0.000 1.000
#> GSM613739 2 0.000 0.991 0.000 1.000
#> GSM613740 2 0.000 0.991 0.000 1.000
#> GSM613741 2 0.000 0.991 0.000 1.000
#> GSM613742 2 0.000 0.991 0.000 1.000
#> GSM613743 2 0.000 0.991 0.000 1.000
#> GSM613744 2 0.000 0.991 0.000 1.000
#> GSM613745 2 0.000 0.991 0.000 1.000
#> GSM613746 2 0.000 0.991 0.000 1.000
#> GSM613747 2 0.000 0.991 0.000 1.000
#> GSM613748 1 0.000 0.999 1.000 0.000
#> GSM613749 1 0.000 0.999 1.000 0.000
#> GSM613750 2 0.000 0.991 0.000 1.000
#> GSM613751 2 0.000 0.991 0.000 1.000
#> GSM613752 2 0.000 0.991 0.000 1.000
#> GSM613753 2 0.000 0.991 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM613638 1 0.6192 0.1879 0.580 0.420 0.000
#> GSM613639 1 0.0000 0.8440 1.000 0.000 0.000
#> GSM613640 1 0.5529 0.4957 0.704 0.296 0.000
#> GSM613641 1 0.0000 0.8440 1.000 0.000 0.000
#> GSM613642 1 0.6252 0.0844 0.556 0.444 0.000
#> GSM613643 1 0.5706 0.4505 0.680 0.320 0.000
#> GSM613644 1 0.6192 0.1823 0.580 0.420 0.000
#> GSM613645 1 0.0000 0.8440 1.000 0.000 0.000
#> GSM613646 3 0.1643 0.9122 0.000 0.044 0.956
#> GSM613647 3 0.3267 0.9058 0.000 0.116 0.884
#> GSM613648 3 0.2448 0.9189 0.000 0.076 0.924
#> GSM613649 3 0.2448 0.9189 0.000 0.076 0.924
#> GSM613650 3 0.1643 0.9122 0.000 0.044 0.956
#> GSM613651 3 0.3879 0.9112 0.000 0.152 0.848
#> GSM613652 3 0.3686 0.9145 0.000 0.140 0.860
#> GSM613653 3 0.2448 0.9189 0.000 0.076 0.924
#> GSM613654 3 0.3752 0.9136 0.000 0.144 0.856
#> GSM613655 1 0.0000 0.8440 1.000 0.000 0.000
#> GSM613656 3 0.2448 0.9161 0.000 0.076 0.924
#> GSM613657 3 0.2448 0.9189 0.000 0.076 0.924
#> GSM613658 1 0.2711 0.7588 0.912 0.088 0.000
#> GSM613659 1 0.6168 0.2156 0.588 0.412 0.000
#> GSM613660 1 0.7864 0.2646 0.596 0.332 0.072
#> GSM613661 1 0.0000 0.8440 1.000 0.000 0.000
#> GSM613662 1 0.0237 0.8423 0.996 0.004 0.000
#> GSM613663 1 0.0000 0.8440 1.000 0.000 0.000
#> GSM613664 1 0.0747 0.8361 0.984 0.016 0.000
#> GSM613665 1 0.2796 0.7728 0.908 0.092 0.000
#> GSM613666 1 0.0000 0.8440 1.000 0.000 0.000
#> GSM613667 1 0.0000 0.8440 1.000 0.000 0.000
#> GSM613668 1 0.0000 0.8440 1.000 0.000 0.000
#> GSM613669 1 0.0000 0.8440 1.000 0.000 0.000
#> GSM613670 1 0.0747 0.8361 0.984 0.016 0.000
#> GSM613671 1 0.0000 0.8440 1.000 0.000 0.000
#> GSM613672 1 0.0000 0.8440 1.000 0.000 0.000
#> GSM613673 1 0.0000 0.8440 1.000 0.000 0.000
#> GSM613674 2 0.4654 1.0000 0.208 0.792 0.000
#> GSM613675 1 0.5926 0.3719 0.644 0.356 0.000
#> GSM613676 1 0.6260 0.0662 0.552 0.448 0.000
#> GSM613677 1 0.5988 0.3413 0.632 0.368 0.000
#> GSM613678 1 0.1643 0.8189 0.956 0.044 0.000
#> GSM613679 1 0.0000 0.8440 1.000 0.000 0.000
#> GSM613680 1 0.0237 0.8428 0.996 0.004 0.000
#> GSM613681 1 0.0000 0.8440 1.000 0.000 0.000
#> GSM613682 1 0.1964 0.8097 0.944 0.056 0.000
#> GSM613683 1 0.0892 0.8353 0.980 0.020 0.000
#> GSM613684 2 0.4654 1.0000 0.208 0.792 0.000
#> GSM613685 2 0.4654 1.0000 0.208 0.792 0.000
#> GSM613686 1 0.0000 0.8440 1.000 0.000 0.000
#> GSM613687 1 0.0000 0.8440 1.000 0.000 0.000
#> GSM613688 1 0.6180 0.2021 0.584 0.416 0.000
#> GSM613689 3 0.2066 0.9218 0.000 0.060 0.940
#> GSM613690 3 0.3752 0.9136 0.000 0.144 0.856
#> GSM613691 3 0.1643 0.9122 0.000 0.044 0.956
#> GSM613692 3 0.3267 0.9058 0.000 0.116 0.884
#> GSM613693 3 0.1643 0.9122 0.000 0.044 0.956
#> GSM613694 3 0.1289 0.9157 0.000 0.032 0.968
#> GSM613695 3 0.3267 0.9058 0.000 0.116 0.884
#> GSM613696 3 0.2261 0.9205 0.000 0.068 0.932
#> GSM613697 3 0.3879 0.9112 0.000 0.152 0.848
#> GSM613698 3 0.2537 0.9187 0.000 0.080 0.920
#> GSM613699 3 0.2261 0.9205 0.000 0.068 0.932
#> GSM613700 1 0.0747 0.8361 0.984 0.016 0.000
#> GSM613701 1 0.0892 0.8369 0.980 0.020 0.000
#> GSM613702 1 0.0000 0.8440 1.000 0.000 0.000
#> GSM613703 1 0.0424 0.8409 0.992 0.008 0.000
#> GSM613704 1 0.0747 0.8361 0.984 0.016 0.000
#> GSM613705 3 0.8857 0.1697 0.344 0.132 0.524
#> GSM613706 1 0.0592 0.8394 0.988 0.012 0.000
#> GSM613707 2 0.4654 1.0000 0.208 0.792 0.000
#> GSM613708 1 0.5859 0.4003 0.656 0.344 0.000
#> GSM613709 1 0.0000 0.8440 1.000 0.000 0.000
#> GSM613710 1 0.6180 0.1968 0.584 0.416 0.000
#> GSM613711 3 0.1643 0.9122 0.000 0.044 0.956
#> GSM613712 3 0.3116 0.9180 0.000 0.108 0.892
#> GSM613713 3 0.0424 0.9205 0.000 0.008 0.992
#> GSM613714 3 0.3267 0.9058 0.000 0.116 0.884
#> GSM613715 3 0.3340 0.9175 0.000 0.120 0.880
#> GSM613716 3 0.1643 0.9122 0.000 0.044 0.956
#> GSM613717 3 0.1643 0.9122 0.000 0.044 0.956
#> GSM613718 3 0.3816 0.9127 0.000 0.148 0.852
#> GSM613719 3 0.2448 0.9189 0.000 0.076 0.924
#> GSM613720 3 0.2448 0.9189 0.000 0.076 0.924
#> GSM613721 3 0.0592 0.9199 0.000 0.012 0.988
#> GSM613722 1 0.0747 0.8361 0.984 0.016 0.000
#> GSM613723 3 0.3686 0.9147 0.000 0.140 0.860
#> GSM613724 1 0.0747 0.8373 0.984 0.016 0.000
#> GSM613725 1 0.0747 0.8361 0.984 0.016 0.000
#> GSM613726 1 0.0000 0.8440 1.000 0.000 0.000
#> GSM613727 1 0.0000 0.8440 1.000 0.000 0.000
#> GSM613728 1 0.0237 0.8425 0.996 0.004 0.000
#> GSM613729 1 0.0000 0.8440 1.000 0.000 0.000
#> GSM613730 1 0.5859 0.4003 0.656 0.344 0.000
#> GSM613731 1 0.0000 0.8440 1.000 0.000 0.000
#> GSM613732 3 0.3752 0.9138 0.000 0.144 0.856
#> GSM613733 3 0.1643 0.9122 0.000 0.044 0.956
#> GSM613734 1 0.5117 0.6281 0.832 0.108 0.060
#> GSM613735 3 0.2796 0.9133 0.000 0.092 0.908
#> GSM613736 3 0.1643 0.9122 0.000 0.044 0.956
#> GSM613737 3 0.2448 0.9189 0.000 0.076 0.924
#> GSM613738 3 0.2796 0.9133 0.000 0.092 0.908
#> GSM613739 3 0.3752 0.9136 0.000 0.144 0.856
#> GSM613740 3 0.2356 0.9198 0.000 0.072 0.928
#> GSM613741 3 0.0747 0.9191 0.000 0.016 0.984
#> GSM613742 3 0.2711 0.9141 0.000 0.088 0.912
#> GSM613743 3 0.1529 0.9135 0.000 0.040 0.960
#> GSM613744 3 0.2261 0.9205 0.000 0.068 0.932
#> GSM613745 3 0.1643 0.9122 0.000 0.044 0.956
#> GSM613746 3 0.2356 0.9198 0.000 0.072 0.928
#> GSM613747 3 0.3267 0.9058 0.000 0.116 0.884
#> GSM613748 1 0.5835 0.4092 0.660 0.340 0.000
#> GSM613749 1 0.0424 0.8402 0.992 0.008 0.000
#> GSM613750 3 0.3816 0.9127 0.000 0.148 0.852
#> GSM613751 3 0.1753 0.9128 0.000 0.048 0.952
#> GSM613752 3 0.3816 0.9127 0.000 0.148 0.852
#> GSM613753 3 0.3816 0.9127 0.000 0.148 0.852
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 2 0.3266 0.7254 0.168 0.832 0.000 0.000
#> GSM613639 1 0.3610 0.5650 0.800 0.200 0.000 0.000
#> GSM613640 2 0.3486 0.7193 0.188 0.812 0.000 0.000
#> GSM613641 1 0.0000 0.6640 1.000 0.000 0.000 0.000
#> GSM613642 2 0.2973 0.7254 0.144 0.856 0.000 0.000
#> GSM613643 2 0.3801 0.6979 0.220 0.780 0.000 0.000
#> GSM613644 2 0.3400 0.7165 0.180 0.820 0.000 0.000
#> GSM613645 1 0.4992 -0.1640 0.524 0.476 0.000 0.000
#> GSM613646 3 0.3123 0.4462 0.000 0.000 0.844 0.156
#> GSM613647 3 0.1940 0.5920 0.000 0.000 0.924 0.076
#> GSM613648 3 0.4761 -0.2720 0.000 0.000 0.628 0.372
#> GSM613649 3 0.4967 -0.5419 0.000 0.000 0.548 0.452
#> GSM613650 3 0.2530 0.5028 0.000 0.000 0.888 0.112
#> GSM613651 3 0.3649 0.5264 0.000 0.000 0.796 0.204
#> GSM613652 3 0.2704 0.5857 0.000 0.000 0.876 0.124
#> GSM613653 3 0.4941 -0.7807 0.000 0.000 0.564 0.436
#> GSM613654 3 0.2647 0.5943 0.000 0.000 0.880 0.120
#> GSM613655 1 0.3024 0.6076 0.852 0.148 0.000 0.000
#> GSM613656 3 0.2345 0.5858 0.000 0.000 0.900 0.100
#> GSM613657 3 0.4877 -0.4015 0.000 0.000 0.592 0.408
#> GSM613658 2 0.4972 0.3270 0.456 0.544 0.000 0.000
#> GSM613659 2 0.2149 0.6915 0.088 0.912 0.000 0.000
#> GSM613660 2 0.4661 0.2959 0.348 0.652 0.000 0.000
#> GSM613661 1 0.3688 0.5504 0.792 0.208 0.000 0.000
#> GSM613662 1 0.5058 0.6085 0.768 0.104 0.000 0.128
#> GSM613663 1 0.2814 0.6160 0.868 0.132 0.000 0.000
#> GSM613664 1 0.5812 0.5400 0.708 0.156 0.000 0.136
#> GSM613665 1 0.4741 0.4725 0.668 0.328 0.000 0.004
#> GSM613666 1 0.0707 0.6622 0.980 0.020 0.000 0.000
#> GSM613667 1 0.2704 0.6214 0.876 0.124 0.000 0.000
#> GSM613668 1 0.3528 0.5636 0.808 0.192 0.000 0.000
#> GSM613669 1 0.0000 0.6640 1.000 0.000 0.000 0.000
#> GSM613670 1 0.5102 0.5907 0.764 0.100 0.000 0.136
#> GSM613671 1 0.0000 0.6640 1.000 0.000 0.000 0.000
#> GSM613672 1 0.4989 -0.1500 0.528 0.472 0.000 0.000
#> GSM613673 1 0.4661 0.2227 0.652 0.348 0.000 0.000
#> GSM613674 2 0.7095 0.2053 0.260 0.560 0.000 0.180
#> GSM613675 2 0.3219 0.7247 0.164 0.836 0.000 0.000
#> GSM613676 2 0.2281 0.7005 0.096 0.904 0.000 0.000
#> GSM613677 2 0.3172 0.7266 0.160 0.840 0.000 0.000
#> GSM613678 2 0.4985 0.2659 0.468 0.532 0.000 0.000
#> GSM613679 1 0.5051 0.5930 0.768 0.100 0.000 0.132
#> GSM613680 1 0.4996 -0.1910 0.516 0.484 0.000 0.000
#> GSM613681 1 0.4961 -0.0757 0.552 0.448 0.000 0.000
#> GSM613682 2 0.4977 0.2932 0.460 0.540 0.000 0.000
#> GSM613683 2 0.4925 0.3863 0.428 0.572 0.000 0.000
#> GSM613684 2 0.3400 0.5302 0.000 0.820 0.000 0.180
#> GSM613685 2 0.5536 0.4355 0.096 0.724 0.000 0.180
#> GSM613686 1 0.0000 0.6640 1.000 0.000 0.000 0.000
#> GSM613687 1 0.4981 -0.1237 0.536 0.464 0.000 0.000
#> GSM613688 2 0.3606 0.5642 0.140 0.840 0.000 0.020
#> GSM613689 3 0.2408 0.5668 0.000 0.000 0.896 0.104
#> GSM613690 3 0.3172 0.5431 0.000 0.000 0.840 0.160
#> GSM613691 3 0.3172 0.4378 0.000 0.000 0.840 0.160
#> GSM613692 3 0.1867 0.5935 0.000 0.000 0.928 0.072
#> GSM613693 3 0.3610 0.3397 0.000 0.000 0.800 0.200
#> GSM613694 3 0.2081 0.5439 0.000 0.000 0.916 0.084
#> GSM613695 3 0.0336 0.6125 0.000 0.000 0.992 0.008
#> GSM613696 3 0.3764 0.4383 0.000 0.000 0.784 0.216
#> GSM613697 3 0.3528 0.5336 0.000 0.000 0.808 0.192
#> GSM613698 3 0.3266 0.5353 0.000 0.000 0.832 0.168
#> GSM613699 3 0.4382 -0.1929 0.000 0.000 0.704 0.296
#> GSM613700 1 0.5102 0.5907 0.764 0.100 0.000 0.136
#> GSM613701 1 0.5764 0.5093 0.644 0.304 0.000 0.052
#> GSM613702 1 0.1637 0.6621 0.940 0.060 0.000 0.000
#> GSM613703 1 0.3803 0.6230 0.836 0.032 0.000 0.132
#> GSM613704 1 0.5102 0.5907 0.764 0.100 0.000 0.136
#> GSM613705 3 0.7243 0.0199 0.092 0.220 0.632 0.056
#> GSM613706 1 0.4697 0.3386 0.644 0.356 0.000 0.000
#> GSM613707 2 0.3852 0.5266 0.012 0.808 0.000 0.180
#> GSM613708 2 0.4250 0.6392 0.276 0.724 0.000 0.000
#> GSM613709 1 0.4746 0.1684 0.632 0.368 0.000 0.000
#> GSM613710 2 0.3024 0.7263 0.148 0.852 0.000 0.000
#> GSM613711 3 0.1118 0.6009 0.000 0.000 0.964 0.036
#> GSM613712 3 0.1716 0.6108 0.000 0.000 0.936 0.064
#> GSM613713 3 0.3610 0.3397 0.000 0.000 0.800 0.200
#> GSM613714 3 0.0592 0.6067 0.000 0.000 0.984 0.016
#> GSM613715 3 0.1211 0.6161 0.000 0.000 0.960 0.040
#> GSM613716 3 0.1211 0.5939 0.000 0.000 0.960 0.040
#> GSM613717 3 0.2868 0.4781 0.000 0.000 0.864 0.136
#> GSM613718 3 0.3172 0.5326 0.000 0.000 0.840 0.160
#> GSM613719 3 0.4967 -0.5419 0.000 0.000 0.548 0.452
#> GSM613720 3 0.4955 -0.5168 0.000 0.000 0.556 0.444
#> GSM613721 3 0.4961 -0.7572 0.000 0.000 0.552 0.448
#> GSM613722 1 0.5051 0.5930 0.768 0.100 0.000 0.132
#> GSM613723 3 0.3528 0.5440 0.000 0.000 0.808 0.192
#> GSM613724 2 0.4941 0.3714 0.436 0.564 0.000 0.000
#> GSM613725 1 0.5722 0.5482 0.716 0.148 0.000 0.136
#> GSM613726 1 0.2760 0.6203 0.872 0.128 0.000 0.000
#> GSM613727 1 0.1557 0.6535 0.944 0.056 0.000 0.000
#> GSM613728 1 0.6194 0.5342 0.668 0.200 0.000 0.132
#> GSM613729 1 0.0000 0.6640 1.000 0.000 0.000 0.000
#> GSM613730 2 0.3123 0.7262 0.156 0.844 0.000 0.000
#> GSM613731 1 0.4008 0.4989 0.756 0.244 0.000 0.000
#> GSM613732 3 0.3123 0.5372 0.000 0.000 0.844 0.156
#> GSM613733 3 0.2868 0.4781 0.000 0.000 0.864 0.136
#> GSM613734 1 0.5227 0.3496 0.668 0.312 0.008 0.012
#> GSM613735 3 0.2281 0.5801 0.000 0.000 0.904 0.096
#> GSM613736 3 0.0707 0.6049 0.000 0.000 0.980 0.020
#> GSM613737 3 0.4955 -0.5168 0.000 0.000 0.556 0.444
#> GSM613738 3 0.2216 0.5882 0.000 0.000 0.908 0.092
#> GSM613739 3 0.2647 0.5861 0.000 0.000 0.880 0.120
#> GSM613740 3 0.3172 0.5326 0.000 0.000 0.840 0.160
#> GSM613741 3 0.4776 -0.6466 0.000 0.000 0.624 0.376
#> GSM613742 3 0.2216 0.5881 0.000 0.000 0.908 0.092
#> GSM613743 3 0.1022 0.6029 0.000 0.000 0.968 0.032
#> GSM613744 3 0.3074 0.5417 0.000 0.000 0.848 0.152
#> GSM613745 3 0.2647 0.4934 0.000 0.000 0.880 0.120
#> GSM613746 4 0.4999 0.0000 0.000 0.000 0.492 0.508
#> GSM613747 3 0.3323 0.5182 0.064 0.000 0.876 0.060
#> GSM613748 2 0.3569 0.7164 0.196 0.804 0.000 0.000
#> GSM613749 1 0.2266 0.6467 0.912 0.084 0.000 0.004
#> GSM613750 3 0.3123 0.5372 0.000 0.000 0.844 0.156
#> GSM613751 3 0.0592 0.6067 0.000 0.000 0.984 0.016
#> GSM613752 3 0.3172 0.5326 0.000 0.000 0.840 0.160
#> GSM613753 3 0.3123 0.5372 0.000 0.000 0.844 0.156
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM613638 1 0.5102 0.18875 0.660 0.032 0.020 0.288 0.000
#> GSM613639 1 0.4974 -0.21606 0.508 0.464 0.000 0.028 0.000
#> GSM613640 1 0.3910 0.40027 0.772 0.032 0.000 0.196 0.000
#> GSM613641 2 0.4824 0.48962 0.376 0.596 0.000 0.028 0.000
#> GSM613642 1 0.3861 0.22065 0.712 0.004 0.000 0.284 0.000
#> GSM613643 1 0.2329 0.48542 0.876 0.000 0.000 0.124 0.000
#> GSM613644 1 0.2329 0.48530 0.876 0.000 0.000 0.124 0.000
#> GSM613645 1 0.0451 0.53409 0.988 0.008 0.000 0.004 0.000
#> GSM613646 5 0.5637 0.31058 0.000 0.000 0.284 0.112 0.604
#> GSM613647 5 0.5790 0.50365 0.000 0.000 0.184 0.200 0.616
#> GSM613648 5 0.3752 0.08370 0.000 0.000 0.292 0.000 0.708
#> GSM613649 3 0.4268 0.67780 0.000 0.000 0.556 0.000 0.444
#> GSM613650 5 0.4329 0.37816 0.000 0.000 0.252 0.032 0.716
#> GSM613651 5 0.2519 0.62197 0.000 0.000 0.100 0.016 0.884
#> GSM613652 5 0.4065 0.55575 0.000 0.000 0.180 0.048 0.772
#> GSM613653 3 0.3395 0.71205 0.000 0.000 0.764 0.000 0.236
#> GSM613654 5 0.3513 0.57627 0.000 0.000 0.180 0.020 0.800
#> GSM613655 1 0.5032 -0.17898 0.520 0.448 0.000 0.032 0.000
#> GSM613656 5 0.5050 0.54688 0.000 0.000 0.180 0.120 0.700
#> GSM613657 5 0.3969 0.00939 0.000 0.000 0.304 0.004 0.692
#> GSM613658 1 0.4970 0.47443 0.728 0.156 0.008 0.108 0.000
#> GSM613659 1 0.6128 0.00634 0.560 0.188 0.000 0.252 0.000
#> GSM613660 2 0.6883 0.28414 0.224 0.484 0.000 0.276 0.016
#> GSM613661 1 0.4965 -0.18684 0.520 0.452 0.000 0.028 0.000
#> GSM613662 2 0.1670 0.68378 0.052 0.936 0.000 0.012 0.000
#> GSM613663 1 0.4876 -0.03917 0.576 0.396 0.000 0.028 0.000
#> GSM613664 2 0.2674 0.59730 0.004 0.856 0.000 0.140 0.000
#> GSM613665 2 0.5357 0.50180 0.264 0.640 0.000 0.096 0.000
#> GSM613666 2 0.4824 0.48962 0.376 0.596 0.000 0.028 0.000
#> GSM613667 1 0.4876 -0.07270 0.576 0.396 0.000 0.028 0.000
#> GSM613668 2 0.4980 0.23083 0.484 0.488 0.000 0.028 0.000
#> GSM613669 2 0.4616 0.56849 0.288 0.676 0.000 0.036 0.000
#> GSM613670 2 0.2674 0.60193 0.004 0.856 0.000 0.140 0.000
#> GSM613671 2 0.4503 0.55470 0.312 0.664 0.000 0.024 0.000
#> GSM613672 1 0.0451 0.53409 0.988 0.008 0.000 0.004 0.000
#> GSM613673 1 0.3370 0.47549 0.824 0.148 0.000 0.028 0.000
#> GSM613674 2 0.5002 0.37919 0.040 0.596 0.000 0.364 0.000
#> GSM613675 1 0.3487 0.29163 0.780 0.008 0.000 0.212 0.000
#> GSM613676 1 0.4106 0.17824 0.724 0.020 0.000 0.256 0.000
#> GSM613677 1 0.4338 0.23872 0.696 0.024 0.000 0.280 0.000
#> GSM613678 1 0.0771 0.52658 0.976 0.004 0.000 0.020 0.000
#> GSM613679 2 0.1469 0.66475 0.036 0.948 0.000 0.016 0.000
#> GSM613680 1 0.0290 0.53335 0.992 0.008 0.000 0.000 0.000
#> GSM613681 1 0.0451 0.53409 0.988 0.008 0.000 0.004 0.000
#> GSM613682 1 0.3339 0.46059 0.840 0.112 0.000 0.048 0.000
#> GSM613683 1 0.2233 0.49861 0.892 0.004 0.000 0.104 0.000
#> GSM613684 4 0.5015 0.46860 0.392 0.028 0.004 0.576 0.000
#> GSM613685 4 0.5773 0.47927 0.436 0.088 0.000 0.476 0.000
#> GSM613686 2 0.4484 0.55777 0.308 0.668 0.000 0.024 0.000
#> GSM613687 1 0.0451 0.53409 0.988 0.008 0.000 0.004 0.000
#> GSM613688 2 0.6158 0.39214 0.184 0.552 0.000 0.264 0.000
#> GSM613689 5 0.1124 0.62409 0.000 0.000 0.036 0.004 0.960
#> GSM613690 5 0.0000 0.64578 0.000 0.000 0.000 0.000 1.000
#> GSM613691 5 0.5906 0.28860 0.000 0.000 0.284 0.140 0.576
#> GSM613692 5 0.5844 0.49283 0.000 0.000 0.184 0.208 0.608
#> GSM613693 5 0.5729 0.02209 0.000 0.000 0.396 0.088 0.516
#> GSM613694 5 0.4367 0.49214 0.000 0.000 0.192 0.060 0.748
#> GSM613695 5 0.2864 0.62170 0.000 0.000 0.012 0.136 0.852
#> GSM613696 5 0.4522 -0.20049 0.000 0.000 0.440 0.008 0.552
#> GSM613697 5 0.1106 0.64528 0.000 0.000 0.024 0.012 0.964
#> GSM613698 5 0.0510 0.64132 0.000 0.000 0.016 0.000 0.984
#> GSM613699 3 0.4437 0.45408 0.000 0.000 0.532 0.004 0.464
#> GSM613700 2 0.2674 0.60193 0.004 0.856 0.000 0.140 0.000
#> GSM613701 2 0.3112 0.66635 0.044 0.856 0.000 0.100 0.000
#> GSM613702 2 0.4924 0.44222 0.420 0.552 0.000 0.028 0.000
#> GSM613703 2 0.4720 0.65023 0.124 0.736 0.000 0.140 0.000
#> GSM613704 2 0.2798 0.60040 0.008 0.852 0.000 0.140 0.000
#> GSM613705 4 0.9023 -0.14899 0.104 0.068 0.180 0.364 0.284
#> GSM613706 1 0.5557 -0.22081 0.468 0.464 0.000 0.068 0.000
#> GSM613707 4 0.5042 0.47310 0.460 0.032 0.000 0.508 0.000
#> GSM613708 1 0.2280 0.48833 0.880 0.000 0.000 0.120 0.000
#> GSM613709 1 0.1300 0.52651 0.956 0.016 0.000 0.028 0.000
#> GSM613710 1 0.3689 0.25743 0.740 0.004 0.000 0.256 0.000
#> GSM613711 5 0.4541 0.55506 0.000 0.000 0.112 0.136 0.752
#> GSM613712 5 0.0898 0.64740 0.000 0.000 0.020 0.008 0.972
#> GSM613713 5 0.4882 -0.13168 0.000 0.000 0.444 0.024 0.532
#> GSM613714 5 0.3098 0.61342 0.000 0.000 0.016 0.148 0.836
#> GSM613715 5 0.0000 0.64578 0.000 0.000 0.000 0.000 1.000
#> GSM613716 5 0.5155 0.49007 0.000 0.000 0.168 0.140 0.692
#> GSM613717 5 0.5265 0.32765 0.000 0.000 0.284 0.080 0.636
#> GSM613718 5 0.0771 0.64149 0.000 0.000 0.020 0.004 0.976
#> GSM613719 3 0.4268 0.67780 0.000 0.000 0.556 0.000 0.444
#> GSM613720 3 0.4262 0.67735 0.000 0.000 0.560 0.000 0.440
#> GSM613721 3 0.3210 0.69799 0.000 0.000 0.788 0.000 0.212
#> GSM613722 2 0.0898 0.66756 0.008 0.972 0.000 0.020 0.000
#> GSM613723 5 0.4065 0.55575 0.000 0.000 0.180 0.048 0.772
#> GSM613724 1 0.2984 0.50244 0.860 0.032 0.000 0.108 0.000
#> GSM613725 2 0.1082 0.66530 0.008 0.964 0.000 0.028 0.000
#> GSM613726 1 0.4974 -0.21506 0.508 0.464 0.000 0.028 0.000
#> GSM613727 2 0.4942 0.38147 0.432 0.540 0.000 0.028 0.000
#> GSM613728 2 0.1845 0.67993 0.056 0.928 0.000 0.016 0.000
#> GSM613729 2 0.4722 0.49969 0.368 0.608 0.000 0.024 0.000
#> GSM613730 1 0.4735 0.25529 0.680 0.048 0.000 0.272 0.000
#> GSM613731 1 0.4957 -0.16925 0.528 0.444 0.000 0.028 0.000
#> GSM613732 5 0.0451 0.64487 0.000 0.000 0.008 0.004 0.988
#> GSM613733 5 0.5870 0.29691 0.000 0.000 0.284 0.136 0.580
#> GSM613734 1 0.8083 -0.02138 0.392 0.264 0.044 0.276 0.024
#> GSM613735 5 0.5867 0.48474 0.000 0.000 0.180 0.216 0.604
#> GSM613736 5 0.5258 0.49589 0.000 0.000 0.140 0.180 0.680
#> GSM613737 3 0.4268 0.67780 0.000 0.000 0.556 0.000 0.444
#> GSM613738 5 0.3513 0.57627 0.000 0.000 0.180 0.020 0.800
#> GSM613739 5 0.3513 0.57627 0.000 0.000 0.180 0.020 0.800
#> GSM613740 5 0.0771 0.64149 0.000 0.000 0.020 0.004 0.976
#> GSM613741 3 0.4196 0.66430 0.000 0.000 0.640 0.004 0.356
#> GSM613742 5 0.4444 0.57971 0.000 0.000 0.180 0.072 0.748
#> GSM613743 5 0.3767 0.60194 0.000 0.000 0.068 0.120 0.812
#> GSM613744 5 0.0451 0.64487 0.000 0.000 0.008 0.004 0.988
#> GSM613745 5 0.5640 0.32832 0.000 0.000 0.276 0.116 0.608
#> GSM613746 3 0.3177 0.69907 0.000 0.000 0.792 0.000 0.208
#> GSM613747 5 0.7260 0.41622 0.076 0.000 0.164 0.232 0.528
#> GSM613748 1 0.1952 0.49563 0.912 0.004 0.000 0.084 0.000
#> GSM613749 2 0.2331 0.68244 0.080 0.900 0.000 0.020 0.000
#> GSM613750 5 0.1216 0.64168 0.000 0.000 0.020 0.020 0.960
#> GSM613751 5 0.3123 0.60899 0.000 0.000 0.012 0.160 0.828
#> GSM613752 5 0.0771 0.64149 0.000 0.000 0.020 0.004 0.976
#> GSM613753 5 0.1216 0.64168 0.000 0.000 0.020 0.020 0.960
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM613638 4 0.4624 0.647 0.140 0.104 0.000 0.732 0.024 0.000
#> GSM613639 1 0.3192 0.575 0.776 0.216 0.000 0.004 0.004 0.000
#> GSM613640 4 0.4693 0.236 0.424 0.016 0.000 0.540 0.020 0.000
#> GSM613641 1 0.2697 0.629 0.812 0.188 0.000 0.000 0.000 0.000
#> GSM613642 4 0.3323 0.658 0.240 0.008 0.000 0.752 0.000 0.000
#> GSM613643 1 0.4153 0.360 0.636 0.000 0.000 0.340 0.024 0.000
#> GSM613644 1 0.4273 0.266 0.596 0.000 0.000 0.380 0.024 0.000
#> GSM613645 1 0.2454 0.578 0.840 0.000 0.000 0.160 0.000 0.000
#> GSM613646 3 0.4904 0.645 0.000 0.000 0.656 0.000 0.148 0.196
#> GSM613647 5 0.3076 0.732 0.000 0.000 0.240 0.000 0.760 0.000
#> GSM613648 3 0.2376 0.695 0.000 0.000 0.888 0.000 0.068 0.044
#> GSM613649 6 0.3907 0.795 0.000 0.000 0.176 0.000 0.068 0.756
#> GSM613650 3 0.4079 0.703 0.000 0.000 0.744 0.000 0.172 0.084
#> GSM613651 3 0.1958 0.638 0.000 0.000 0.896 0.000 0.100 0.004
#> GSM613652 5 0.3756 0.782 0.000 0.000 0.400 0.000 0.600 0.000
#> GSM613653 6 0.1649 0.739 0.000 0.000 0.032 0.000 0.036 0.932
#> GSM613654 3 0.3864 -0.680 0.000 0.000 0.520 0.000 0.480 0.000
#> GSM613655 1 0.2615 0.649 0.852 0.136 0.000 0.008 0.004 0.000
#> GSM613656 5 0.3695 0.789 0.000 0.000 0.376 0.000 0.624 0.000
#> GSM613657 3 0.5041 0.432 0.000 0.000 0.624 0.000 0.128 0.248
#> GSM613658 1 0.5696 0.460 0.576 0.112 0.000 0.284 0.028 0.000
#> GSM613659 4 0.5604 0.515 0.268 0.172 0.000 0.556 0.004 0.000
#> GSM613660 2 0.5895 0.580 0.280 0.580 0.008 0.108 0.008 0.016
#> GSM613661 1 0.2504 0.646 0.856 0.136 0.000 0.004 0.004 0.000
#> GSM613662 2 0.2378 0.806 0.152 0.848 0.000 0.000 0.000 0.000
#> GSM613663 1 0.1524 0.656 0.932 0.060 0.000 0.008 0.000 0.000
#> GSM613664 2 0.0260 0.775 0.000 0.992 0.000 0.008 0.000 0.000
#> GSM613665 2 0.3737 0.563 0.392 0.608 0.000 0.000 0.000 0.000
#> GSM613666 1 0.2762 0.616 0.804 0.196 0.000 0.000 0.000 0.000
#> GSM613667 1 0.1088 0.647 0.960 0.024 0.000 0.016 0.000 0.000
#> GSM613668 1 0.2597 0.634 0.824 0.176 0.000 0.000 0.000 0.000
#> GSM613669 1 0.3756 0.365 0.600 0.400 0.000 0.000 0.000 0.000
#> GSM613670 2 0.0000 0.778 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613671 1 0.3244 0.491 0.732 0.268 0.000 0.000 0.000 0.000
#> GSM613672 1 0.2454 0.578 0.840 0.000 0.000 0.160 0.000 0.000
#> GSM613673 1 0.0603 0.643 0.980 0.004 0.000 0.016 0.000 0.000
#> GSM613674 2 0.4925 0.702 0.132 0.680 0.000 0.180 0.004 0.004
#> GSM613675 4 0.4018 0.548 0.412 0.008 0.000 0.580 0.000 0.000
#> GSM613676 4 0.4147 0.653 0.304 0.024 0.000 0.668 0.004 0.000
#> GSM613677 4 0.3617 0.644 0.244 0.000 0.000 0.736 0.020 0.000
#> GSM613678 1 0.2743 0.573 0.828 0.008 0.000 0.164 0.000 0.000
#> GSM613679 2 0.3151 0.734 0.252 0.748 0.000 0.000 0.000 0.000
#> GSM613680 1 0.2454 0.578 0.840 0.000 0.000 0.160 0.000 0.000
#> GSM613681 1 0.2454 0.578 0.840 0.000 0.000 0.160 0.000 0.000
#> GSM613682 1 0.4393 0.589 0.716 0.112 0.000 0.172 0.000 0.000
#> GSM613683 1 0.4139 0.364 0.640 0.000 0.000 0.336 0.024 0.000
#> GSM613684 4 0.1003 0.569 0.000 0.016 0.000 0.964 0.020 0.000
#> GSM613685 4 0.3849 0.580 0.112 0.060 0.000 0.804 0.020 0.004
#> GSM613686 1 0.3288 0.479 0.724 0.276 0.000 0.000 0.000 0.000
#> GSM613687 1 0.2454 0.578 0.840 0.000 0.000 0.160 0.000 0.000
#> GSM613688 4 0.6011 0.131 0.296 0.272 0.000 0.432 0.000 0.000
#> GSM613689 3 0.2706 0.711 0.000 0.000 0.852 0.000 0.124 0.024
#> GSM613690 3 0.1531 0.665 0.000 0.000 0.928 0.000 0.068 0.004
#> GSM613691 3 0.5188 0.629 0.000 0.000 0.632 0.004 0.160 0.204
#> GSM613692 5 0.3076 0.732 0.000 0.000 0.240 0.000 0.760 0.000
#> GSM613693 3 0.4261 0.633 0.000 0.000 0.692 0.000 0.056 0.252
#> GSM613694 3 0.3874 0.704 0.000 0.000 0.760 0.000 0.172 0.068
#> GSM613695 3 0.3409 0.511 0.000 0.000 0.700 0.000 0.300 0.000
#> GSM613696 3 0.4387 0.676 0.000 0.000 0.720 0.000 0.152 0.128
#> GSM613697 3 0.1082 0.679 0.000 0.000 0.956 0.000 0.040 0.004
#> GSM613698 3 0.0777 0.683 0.000 0.000 0.972 0.000 0.024 0.004
#> GSM613699 3 0.4536 0.659 0.000 0.000 0.700 0.000 0.120 0.180
#> GSM613700 2 0.0000 0.778 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613701 2 0.3023 0.766 0.232 0.768 0.000 0.000 0.000 0.000
#> GSM613702 1 0.3371 0.376 0.708 0.292 0.000 0.000 0.000 0.000
#> GSM613703 2 0.0260 0.778 0.008 0.992 0.000 0.000 0.000 0.000
#> GSM613704 2 0.0000 0.778 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM613705 5 0.3834 0.408 0.040 0.032 0.008 0.108 0.812 0.000
#> GSM613706 2 0.4663 0.310 0.472 0.492 0.000 0.032 0.004 0.000
#> GSM613707 4 0.3460 0.606 0.132 0.024 0.000 0.820 0.020 0.004
#> GSM613708 1 0.4139 0.364 0.640 0.000 0.000 0.336 0.024 0.000
#> GSM613709 1 0.2454 0.578 0.840 0.000 0.000 0.160 0.000 0.000
#> GSM613710 4 0.3601 0.648 0.312 0.004 0.000 0.684 0.000 0.000
#> GSM613711 3 0.4134 0.671 0.000 0.000 0.656 0.000 0.316 0.028
#> GSM613712 3 0.1814 0.653 0.000 0.000 0.900 0.000 0.100 0.000
#> GSM613713 3 0.4546 0.650 0.000 0.000 0.692 0.000 0.104 0.204
#> GSM613714 3 0.3747 0.563 0.000 0.000 0.604 0.000 0.396 0.000
#> GSM613715 3 0.2300 0.653 0.000 0.000 0.856 0.000 0.144 0.000
#> GSM613716 3 0.4697 0.660 0.000 0.000 0.612 0.000 0.324 0.064
#> GSM613717 3 0.4358 0.693 0.000 0.000 0.712 0.000 0.196 0.092
#> GSM613718 3 0.1471 0.678 0.000 0.000 0.932 0.000 0.064 0.004
#> GSM613719 6 0.3939 0.792 0.000 0.000 0.180 0.000 0.068 0.752
#> GSM613720 6 0.3923 0.792 0.000 0.000 0.192 0.000 0.060 0.748
#> GSM613721 6 0.4050 0.501 0.000 0.000 0.236 0.000 0.048 0.716
#> GSM613722 2 0.2219 0.810 0.136 0.864 0.000 0.000 0.000 0.000
#> GSM613723 5 0.3706 0.785 0.000 0.000 0.380 0.000 0.620 0.000
#> GSM613724 1 0.5828 0.403 0.528 0.108 0.000 0.336 0.028 0.000
#> GSM613725 2 0.2178 0.810 0.132 0.868 0.000 0.000 0.000 0.000
#> GSM613726 1 0.2402 0.646 0.856 0.140 0.000 0.004 0.000 0.000
#> GSM613727 1 0.2454 0.641 0.840 0.160 0.000 0.000 0.000 0.000
#> GSM613728 2 0.3126 0.753 0.248 0.752 0.000 0.000 0.000 0.000
#> GSM613729 1 0.2762 0.625 0.804 0.196 0.000 0.000 0.000 0.000
#> GSM613730 4 0.4806 0.640 0.160 0.112 0.000 0.708 0.020 0.000
#> GSM613731 1 0.2806 0.649 0.844 0.136 0.000 0.016 0.004 0.000
#> GSM613732 3 0.1411 0.673 0.000 0.000 0.936 0.000 0.060 0.004
#> GSM613733 3 0.5065 0.637 0.000 0.000 0.636 0.000 0.172 0.192
#> GSM613734 1 0.5711 0.424 0.612 0.032 0.000 0.160 0.196 0.000
#> GSM613735 5 0.3390 0.768 0.000 0.000 0.296 0.000 0.704 0.000
#> GSM613736 3 0.4499 0.559 0.000 0.000 0.540 0.000 0.428 0.032
#> GSM613737 6 0.3916 0.788 0.000 0.000 0.184 0.000 0.064 0.752
#> GSM613738 5 0.3866 0.681 0.000 0.000 0.484 0.000 0.516 0.000
#> GSM613739 5 0.3857 0.702 0.000 0.000 0.468 0.000 0.532 0.000
#> GSM613740 3 0.1588 0.696 0.000 0.000 0.924 0.000 0.072 0.004
#> GSM613741 3 0.4467 0.574 0.000 0.000 0.632 0.000 0.048 0.320
#> GSM613742 5 0.3756 0.787 0.000 0.000 0.400 0.000 0.600 0.000
#> GSM613743 3 0.3421 0.702 0.000 0.000 0.736 0.000 0.256 0.008
#> GSM613744 3 0.1285 0.683 0.000 0.000 0.944 0.000 0.052 0.004
#> GSM613745 3 0.4787 0.666 0.000 0.000 0.656 0.000 0.236 0.108
#> GSM613746 6 0.1528 0.717 0.000 0.000 0.016 0.000 0.048 0.936
#> GSM613747 5 0.2456 0.559 0.000 0.000 0.076 0.028 0.888 0.008
#> GSM613748 1 0.3563 0.232 0.664 0.000 0.000 0.336 0.000 0.000
#> GSM613749 2 0.2260 0.809 0.140 0.860 0.000 0.000 0.000 0.000
#> GSM613750 3 0.2122 0.678 0.000 0.000 0.900 0.000 0.076 0.024
#> GSM613751 3 0.3371 0.525 0.000 0.000 0.708 0.000 0.292 0.000
#> GSM613752 3 0.1471 0.683 0.000 0.000 0.932 0.000 0.064 0.004
#> GSM613753 3 0.2176 0.677 0.000 0.000 0.896 0.000 0.080 0.024
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n disease.state(p) k
#> ATC:mclust 115 0.0235 2
#> ATC:mclust 100 0.0575 3
#> ATC:mclust 77 0.1166 4
#> ATC:mclust 59 0.1116 5
#> ATC:mclust 98 0.0464 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 27425 rows and 116 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'ATC' method.
#> Subgroups are detected by 'NMF' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 1.000 0.963 0.985 0.5042 0.496 0.496
#> 3 3 0.541 0.706 0.818 0.2694 0.867 0.736
#> 4 4 0.642 0.710 0.831 0.0992 0.843 0.618
#> 5 5 0.561 0.609 0.757 0.0747 0.903 0.690
#> 6 6 0.609 0.567 0.751 0.0523 0.898 0.630
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
#> GSM613638 2 0.0000 0.9876 0.000 1.000
#> GSM613639 1 0.0000 0.9808 1.000 0.000
#> GSM613640 1 0.0000 0.9808 1.000 0.000
#> GSM613641 1 0.0000 0.9808 1.000 0.000
#> GSM613642 1 0.0000 0.9808 1.000 0.000
#> GSM613643 1 0.8909 0.5526 0.692 0.308
#> GSM613644 1 0.9988 0.0731 0.520 0.480
#> GSM613645 1 0.0000 0.9808 1.000 0.000
#> GSM613646 2 0.0376 0.9843 0.004 0.996
#> GSM613647 2 0.0000 0.9876 0.000 1.000
#> GSM613648 2 0.0000 0.9876 0.000 1.000
#> GSM613649 2 0.0000 0.9876 0.000 1.000
#> GSM613650 2 0.0000 0.9876 0.000 1.000
#> GSM613651 2 0.0000 0.9876 0.000 1.000
#> GSM613652 2 0.0000 0.9876 0.000 1.000
#> GSM613653 2 0.2236 0.9539 0.036 0.964
#> GSM613654 2 0.0000 0.9876 0.000 1.000
#> GSM613655 1 0.0000 0.9808 1.000 0.000
#> GSM613656 2 0.0000 0.9876 0.000 1.000
#> GSM613657 2 0.0000 0.9876 0.000 1.000
#> GSM613658 2 0.0672 0.9808 0.008 0.992
#> GSM613659 1 0.0000 0.9808 1.000 0.000
#> GSM613660 1 0.0000 0.9808 1.000 0.000
#> GSM613661 1 0.0000 0.9808 1.000 0.000
#> GSM613662 1 0.0000 0.9808 1.000 0.000
#> GSM613663 1 0.0000 0.9808 1.000 0.000
#> GSM613664 1 0.0000 0.9808 1.000 0.000
#> GSM613665 1 0.0000 0.9808 1.000 0.000
#> GSM613666 1 0.0000 0.9808 1.000 0.000
#> GSM613667 1 0.0000 0.9808 1.000 0.000
#> GSM613668 1 0.0000 0.9808 1.000 0.000
#> GSM613669 1 0.0000 0.9808 1.000 0.000
#> GSM613670 1 0.0000 0.9808 1.000 0.000
#> GSM613671 1 0.0000 0.9808 1.000 0.000
#> GSM613672 1 0.0000 0.9808 1.000 0.000
#> GSM613673 1 0.0000 0.9808 1.000 0.000
#> GSM613674 1 0.0000 0.9808 1.000 0.000
#> GSM613675 1 0.0000 0.9808 1.000 0.000
#> GSM613676 1 0.0000 0.9808 1.000 0.000
#> GSM613677 1 0.8267 0.6441 0.740 0.260
#> GSM613678 1 0.0000 0.9808 1.000 0.000
#> GSM613679 1 0.0000 0.9808 1.000 0.000
#> GSM613680 1 0.0000 0.9808 1.000 0.000
#> GSM613681 1 0.0000 0.9808 1.000 0.000
#> GSM613682 1 0.0000 0.9808 1.000 0.000
#> GSM613683 1 0.0000 0.9808 1.000 0.000
#> GSM613684 2 0.7219 0.7506 0.200 0.800
#> GSM613685 1 0.0000 0.9808 1.000 0.000
#> GSM613686 1 0.0000 0.9808 1.000 0.000
#> GSM613687 1 0.0000 0.9808 1.000 0.000
#> GSM613688 1 0.0000 0.9808 1.000 0.000
#> GSM613689 2 0.0000 0.9876 0.000 1.000
#> GSM613690 2 0.0000 0.9876 0.000 1.000
#> GSM613691 1 0.1184 0.9658 0.984 0.016
#> GSM613692 2 0.0000 0.9876 0.000 1.000
#> GSM613693 2 0.0000 0.9876 0.000 1.000
#> GSM613694 2 0.0000 0.9876 0.000 1.000
#> GSM613695 2 0.0000 0.9876 0.000 1.000
#> GSM613696 2 0.0000 0.9876 0.000 1.000
#> GSM613697 2 0.0000 0.9876 0.000 1.000
#> GSM613698 2 0.0000 0.9876 0.000 1.000
#> GSM613699 2 0.0000 0.9876 0.000 1.000
#> GSM613700 1 0.0000 0.9808 1.000 0.000
#> GSM613701 1 0.0000 0.9808 1.000 0.000
#> GSM613702 1 0.0000 0.9808 1.000 0.000
#> GSM613703 1 0.0000 0.9808 1.000 0.000
#> GSM613704 1 0.0000 0.9808 1.000 0.000
#> GSM613705 2 0.0000 0.9876 0.000 1.000
#> GSM613706 1 0.0000 0.9808 1.000 0.000
#> GSM613707 1 0.0000 0.9808 1.000 0.000
#> GSM613708 1 0.0000 0.9808 1.000 0.000
#> GSM613709 1 0.0000 0.9808 1.000 0.000
#> GSM613710 1 0.0000 0.9808 1.000 0.000
#> GSM613711 2 0.0000 0.9876 0.000 1.000
#> GSM613712 2 0.0000 0.9876 0.000 1.000
#> GSM613713 2 0.0000 0.9876 0.000 1.000
#> GSM613714 2 0.0000 0.9876 0.000 1.000
#> GSM613715 2 0.0000 0.9876 0.000 1.000
#> GSM613716 2 0.0000 0.9876 0.000 1.000
#> GSM613717 2 0.0000 0.9876 0.000 1.000
#> GSM613718 2 0.0000 0.9876 0.000 1.000
#> GSM613719 2 0.0000 0.9876 0.000 1.000
#> GSM613720 2 0.0000 0.9876 0.000 1.000
#> GSM613721 2 0.6712 0.7873 0.176 0.824
#> GSM613722 1 0.0000 0.9808 1.000 0.000
#> GSM613723 2 0.0000 0.9876 0.000 1.000
#> GSM613724 2 0.8267 0.6494 0.260 0.740
#> GSM613725 1 0.0000 0.9808 1.000 0.000
#> GSM613726 1 0.0000 0.9808 1.000 0.000
#> GSM613727 1 0.0000 0.9808 1.000 0.000
#> GSM613728 1 0.0000 0.9808 1.000 0.000
#> GSM613729 1 0.0000 0.9808 1.000 0.000
#> GSM613730 1 0.0000 0.9808 1.000 0.000
#> GSM613731 1 0.0000 0.9808 1.000 0.000
#> GSM613732 2 0.0000 0.9876 0.000 1.000
#> GSM613733 2 0.0376 0.9843 0.004 0.996
#> GSM613734 2 0.0000 0.9876 0.000 1.000
#> GSM613735 2 0.0000 0.9876 0.000 1.000
#> GSM613736 2 0.0000 0.9876 0.000 1.000
#> GSM613737 2 0.0000 0.9876 0.000 1.000
#> GSM613738 2 0.0000 0.9876 0.000 1.000
#> GSM613739 2 0.0000 0.9876 0.000 1.000
#> GSM613740 2 0.0000 0.9876 0.000 1.000
#> GSM613741 2 0.0000 0.9876 0.000 1.000
#> GSM613742 2 0.0000 0.9876 0.000 1.000
#> GSM613743 2 0.0000 0.9876 0.000 1.000
#> GSM613744 2 0.0000 0.9876 0.000 1.000
#> GSM613745 2 0.0000 0.9876 0.000 1.000
#> GSM613746 2 0.0000 0.9876 0.000 1.000
#> GSM613747 2 0.0000 0.9876 0.000 1.000
#> GSM613748 1 0.0000 0.9808 1.000 0.000
#> GSM613749 1 0.0000 0.9808 1.000 0.000
#> GSM613750 2 0.0000 0.9876 0.000 1.000
#> GSM613751 2 0.0000 0.9876 0.000 1.000
#> GSM613752 2 0.0000 0.9876 0.000 1.000
#> GSM613753 2 0.0000 0.9876 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM613638 3 0.6432 0.2843 0.428 0.004 0.568
#> GSM613639 2 0.3619 0.7635 0.136 0.864 0.000
#> GSM613640 2 0.6798 0.3275 0.400 0.584 0.016
#> GSM613641 2 0.5465 0.5395 0.288 0.712 0.000
#> GSM613642 2 0.6357 0.5224 0.336 0.652 0.012
#> GSM613643 1 0.6079 0.6810 0.784 0.088 0.128
#> GSM613644 1 0.5467 0.6722 0.816 0.072 0.112
#> GSM613645 2 0.5216 0.6626 0.260 0.740 0.000
#> GSM613646 3 0.6594 0.7469 0.128 0.116 0.756
#> GSM613647 3 0.2537 0.8332 0.080 0.000 0.920
#> GSM613648 3 0.1860 0.8556 0.052 0.000 0.948
#> GSM613649 3 0.2878 0.8428 0.096 0.000 0.904
#> GSM613650 3 0.1289 0.8591 0.032 0.000 0.968
#> GSM613651 3 0.1411 0.8538 0.036 0.000 0.964
#> GSM613652 3 0.5760 0.5318 0.328 0.000 0.672
#> GSM613653 3 0.7273 0.7020 0.156 0.132 0.712
#> GSM613654 3 0.5733 0.5330 0.324 0.000 0.676
#> GSM613655 1 0.5465 0.6582 0.712 0.288 0.000
#> GSM613656 3 0.6079 0.4077 0.388 0.000 0.612
#> GSM613657 3 0.3030 0.8440 0.092 0.004 0.904
#> GSM613658 1 0.5756 0.6348 0.764 0.028 0.208
#> GSM613659 2 0.3619 0.7734 0.136 0.864 0.000
#> GSM613660 2 0.3370 0.7313 0.024 0.904 0.072
#> GSM613661 1 0.6260 0.3660 0.552 0.448 0.000
#> GSM613662 2 0.0892 0.7892 0.020 0.980 0.000
#> GSM613663 1 0.5291 0.6660 0.732 0.268 0.000
#> GSM613664 2 0.0892 0.7787 0.020 0.980 0.000
#> GSM613665 2 0.1411 0.7889 0.036 0.964 0.000
#> GSM613666 2 0.3619 0.7601 0.136 0.864 0.000
#> GSM613667 2 0.4346 0.7392 0.184 0.816 0.000
#> GSM613668 2 0.6280 -0.0272 0.460 0.540 0.000
#> GSM613669 2 0.4235 0.7434 0.176 0.824 0.000
#> GSM613670 2 0.1753 0.7788 0.048 0.952 0.000
#> GSM613671 2 0.3941 0.7502 0.156 0.844 0.000
#> GSM613672 1 0.5216 0.6719 0.740 0.260 0.000
#> GSM613673 2 0.4399 0.7359 0.188 0.812 0.000
#> GSM613674 2 0.3412 0.7359 0.124 0.876 0.000
#> GSM613675 2 0.4555 0.7375 0.200 0.800 0.000
#> GSM613676 2 0.4654 0.7298 0.208 0.792 0.000
#> GSM613677 1 0.9792 0.3250 0.436 0.288 0.276
#> GSM613678 2 0.4291 0.7615 0.180 0.820 0.000
#> GSM613679 2 0.1031 0.7899 0.024 0.976 0.000
#> GSM613680 1 0.5327 0.6634 0.728 0.272 0.000
#> GSM613681 1 0.6008 0.5034 0.628 0.372 0.000
#> GSM613682 2 0.4931 0.7456 0.232 0.768 0.000
#> GSM613683 1 0.5688 0.6942 0.788 0.168 0.044
#> GSM613684 3 0.8854 0.4073 0.236 0.188 0.576
#> GSM613685 2 0.3551 0.7334 0.132 0.868 0.000
#> GSM613686 2 0.2959 0.7786 0.100 0.900 0.000
#> GSM613687 2 0.6235 0.2008 0.436 0.564 0.000
#> GSM613688 2 0.2878 0.7617 0.096 0.904 0.000
#> GSM613689 3 0.2066 0.8540 0.060 0.000 0.940
#> GSM613690 3 0.1031 0.8576 0.024 0.000 0.976
#> GSM613691 2 0.8957 0.1376 0.152 0.536 0.312
#> GSM613692 3 0.3038 0.8175 0.104 0.000 0.896
#> GSM613693 3 0.7412 0.6956 0.176 0.124 0.700
#> GSM613694 3 0.1163 0.8594 0.028 0.000 0.972
#> GSM613695 3 0.1163 0.8566 0.028 0.000 0.972
#> GSM613696 3 0.3425 0.8359 0.112 0.004 0.884
#> GSM613697 3 0.1163 0.8566 0.028 0.000 0.972
#> GSM613698 3 0.0000 0.8602 0.000 0.000 1.000
#> GSM613699 3 0.3192 0.8371 0.112 0.000 0.888
#> GSM613700 2 0.1031 0.7869 0.024 0.976 0.000
#> GSM613701 2 0.2625 0.7651 0.084 0.916 0.000
#> GSM613702 2 0.2356 0.7911 0.072 0.928 0.000
#> GSM613703 2 0.2625 0.7835 0.084 0.916 0.000
#> GSM613704 2 0.1753 0.7678 0.048 0.952 0.000
#> GSM613705 3 0.4504 0.7355 0.196 0.000 0.804
#> GSM613706 2 0.4062 0.7526 0.164 0.836 0.000
#> GSM613707 2 0.3619 0.7341 0.136 0.864 0.000
#> GSM613708 1 0.4861 0.6826 0.800 0.192 0.008
#> GSM613709 1 0.6026 0.5049 0.624 0.376 0.000
#> GSM613710 2 0.5178 0.6684 0.256 0.744 0.000
#> GSM613711 3 0.2527 0.8559 0.044 0.020 0.936
#> GSM613712 3 0.1031 0.8576 0.024 0.000 0.976
#> GSM613713 3 0.5239 0.7950 0.160 0.032 0.808
#> GSM613714 3 0.1031 0.8576 0.024 0.000 0.976
#> GSM613715 3 0.1031 0.8576 0.024 0.000 0.976
#> GSM613716 3 0.0000 0.8602 0.000 0.000 1.000
#> GSM613717 3 0.4676 0.8179 0.112 0.040 0.848
#> GSM613718 3 0.0424 0.8596 0.008 0.000 0.992
#> GSM613719 3 0.2796 0.8446 0.092 0.000 0.908
#> GSM613720 3 0.2537 0.8478 0.080 0.000 0.920
#> GSM613721 3 0.8472 0.5692 0.160 0.228 0.612
#> GSM613722 2 0.0592 0.7863 0.012 0.988 0.000
#> GSM613723 3 0.4178 0.7568 0.172 0.000 0.828
#> GSM613724 1 0.6093 0.6688 0.776 0.068 0.156
#> GSM613725 2 0.1860 0.7683 0.052 0.948 0.000
#> GSM613726 2 0.4002 0.7473 0.160 0.840 0.000
#> GSM613727 1 0.6280 0.3420 0.540 0.460 0.000
#> GSM613728 2 0.1289 0.7759 0.032 0.968 0.000
#> GSM613729 2 0.5016 0.6475 0.240 0.760 0.000
#> GSM613730 2 0.5216 0.6711 0.260 0.740 0.000
#> GSM613731 1 0.5678 0.6180 0.684 0.316 0.000
#> GSM613732 3 0.1031 0.8576 0.024 0.000 0.976
#> GSM613733 3 0.5650 0.7891 0.108 0.084 0.808
#> GSM613734 1 0.5327 0.5268 0.728 0.000 0.272
#> GSM613735 3 0.6215 0.3077 0.428 0.000 0.572
#> GSM613736 3 0.3886 0.8277 0.096 0.024 0.880
#> GSM613737 3 0.2261 0.8516 0.068 0.000 0.932
#> GSM613738 3 0.4796 0.7000 0.220 0.000 0.780
#> GSM613739 3 0.5497 0.5955 0.292 0.000 0.708
#> GSM613740 3 0.0424 0.8610 0.008 0.000 0.992
#> GSM613741 3 0.4195 0.8207 0.136 0.012 0.852
#> GSM613742 3 0.2356 0.8373 0.072 0.000 0.928
#> GSM613743 3 0.3207 0.8455 0.084 0.012 0.904
#> GSM613744 3 0.0000 0.8602 0.000 0.000 1.000
#> GSM613745 3 0.0892 0.8602 0.020 0.000 0.980
#> GSM613746 3 0.7256 0.7097 0.164 0.124 0.712
#> GSM613747 1 0.6180 0.1700 0.584 0.000 0.416
#> GSM613748 2 0.5397 0.6572 0.280 0.720 0.000
#> GSM613749 2 0.1411 0.7890 0.036 0.964 0.000
#> GSM613750 3 0.1031 0.8576 0.024 0.000 0.976
#> GSM613751 3 0.1031 0.8576 0.024 0.000 0.976
#> GSM613752 3 0.0424 0.8609 0.008 0.000 0.992
#> GSM613753 3 0.1031 0.8576 0.024 0.000 0.976
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM613638 2 0.7906 0.1102 0.300 0.356 0.344 0.000
#> GSM613639 4 0.4542 0.7321 0.088 0.108 0.000 0.804
#> GSM613640 2 0.5897 0.4463 0.368 0.588 0.000 0.044
#> GSM613641 4 0.5935 0.6028 0.256 0.080 0.000 0.664
#> GSM613642 2 0.2915 0.7335 0.080 0.892 0.000 0.028
#> GSM613643 1 0.2400 0.7388 0.928 0.032 0.028 0.012
#> GSM613644 2 0.5033 0.6427 0.220 0.740 0.036 0.004
#> GSM613645 2 0.6337 0.1302 0.468 0.472 0.000 0.060
#> GSM613646 3 0.4298 0.8527 0.036 0.032 0.840 0.092
#> GSM613647 3 0.1118 0.9267 0.036 0.000 0.964 0.000
#> GSM613648 3 0.0712 0.9314 0.008 0.004 0.984 0.004
#> GSM613649 3 0.1820 0.9192 0.036 0.000 0.944 0.020
#> GSM613650 3 0.1004 0.9284 0.024 0.000 0.972 0.004
#> GSM613651 3 0.0592 0.9320 0.016 0.000 0.984 0.000
#> GSM613652 3 0.2973 0.8461 0.144 0.000 0.856 0.000
#> GSM613653 4 0.5083 0.3481 0.036 0.000 0.248 0.716
#> GSM613654 3 0.3157 0.8428 0.144 0.000 0.852 0.004
#> GSM613655 1 0.3479 0.7281 0.840 0.012 0.000 0.148
#> GSM613656 3 0.4193 0.6770 0.268 0.000 0.732 0.000
#> GSM613657 3 0.1229 0.9277 0.020 0.008 0.968 0.004
#> GSM613658 1 0.1940 0.7067 0.924 0.000 0.076 0.000
#> GSM613659 2 0.2319 0.7283 0.040 0.924 0.000 0.036
#> GSM613660 2 0.6618 -0.2585 0.012 0.472 0.052 0.464
#> GSM613661 4 0.5695 0.1059 0.476 0.024 0.000 0.500
#> GSM613662 4 0.4663 0.6874 0.012 0.272 0.000 0.716
#> GSM613663 1 0.2796 0.7601 0.892 0.016 0.000 0.092
#> GSM613664 4 0.3972 0.7245 0.008 0.204 0.000 0.788
#> GSM613665 2 0.5693 -0.2418 0.024 0.504 0.000 0.472
#> GSM613666 4 0.5948 0.7000 0.160 0.144 0.000 0.696
#> GSM613667 4 0.6773 0.6071 0.136 0.276 0.000 0.588
#> GSM613668 1 0.6248 0.5005 0.644 0.104 0.000 0.252
#> GSM613669 4 0.3144 0.7004 0.072 0.044 0.000 0.884
#> GSM613670 4 0.0921 0.6802 0.000 0.028 0.000 0.972
#> GSM613671 4 0.5669 0.7205 0.092 0.200 0.000 0.708
#> GSM613672 1 0.2466 0.7580 0.916 0.028 0.000 0.056
#> GSM613673 1 0.7905 -0.0713 0.368 0.312 0.000 0.320
#> GSM613674 2 0.1302 0.7013 0.000 0.956 0.000 0.044
#> GSM613675 2 0.3421 0.7279 0.088 0.868 0.000 0.044
#> GSM613676 2 0.2002 0.7282 0.044 0.936 0.000 0.020
#> GSM613677 2 0.5947 0.4507 0.376 0.588 0.016 0.020
#> GSM613678 2 0.4426 0.6965 0.096 0.812 0.000 0.092
#> GSM613679 4 0.5364 0.5250 0.016 0.392 0.000 0.592
#> GSM613680 1 0.2926 0.7546 0.896 0.048 0.000 0.056
#> GSM613681 1 0.5062 0.6382 0.752 0.184 0.000 0.064
#> GSM613682 2 0.3144 0.7288 0.072 0.884 0.000 0.044
#> GSM613683 1 0.1929 0.7518 0.940 0.024 0.000 0.036
#> GSM613684 2 0.1635 0.6659 0.008 0.948 0.044 0.000
#> GSM613685 2 0.0469 0.7099 0.000 0.988 0.000 0.012
#> GSM613686 4 0.5157 0.6748 0.028 0.284 0.000 0.688
#> GSM613687 1 0.5327 0.5754 0.720 0.220 0.000 0.060
#> GSM613688 2 0.0895 0.7088 0.004 0.976 0.000 0.020
#> GSM613689 3 0.0524 0.9318 0.004 0.008 0.988 0.000
#> GSM613690 3 0.0779 0.9319 0.016 0.004 0.980 0.000
#> GSM613691 4 0.6426 0.4173 0.024 0.064 0.256 0.656
#> GSM613692 3 0.1109 0.9289 0.028 0.004 0.968 0.000
#> GSM613693 3 0.3845 0.8456 0.012 0.132 0.840 0.016
#> GSM613694 3 0.0376 0.9322 0.000 0.004 0.992 0.004
#> GSM613695 3 0.1004 0.9301 0.024 0.004 0.972 0.000
#> GSM613696 3 0.1510 0.9227 0.028 0.016 0.956 0.000
#> GSM613697 3 0.0592 0.9320 0.016 0.000 0.984 0.000
#> GSM613698 3 0.0188 0.9323 0.000 0.000 0.996 0.004
#> GSM613699 3 0.1913 0.9177 0.040 0.000 0.940 0.020
#> GSM613700 4 0.3636 0.7319 0.008 0.172 0.000 0.820
#> GSM613701 2 0.2647 0.6631 0.000 0.880 0.000 0.120
#> GSM613702 4 0.5630 0.5637 0.032 0.360 0.000 0.608
#> GSM613703 4 0.0927 0.6695 0.008 0.016 0.000 0.976
#> GSM613704 4 0.1792 0.7073 0.000 0.068 0.000 0.932
#> GSM613705 3 0.2647 0.8695 0.120 0.000 0.880 0.000
#> GSM613706 4 0.6412 0.6679 0.200 0.124 0.008 0.668
#> GSM613707 2 0.0712 0.6978 0.008 0.984 0.004 0.004
#> GSM613708 1 0.4379 0.6476 0.792 0.172 0.000 0.036
#> GSM613709 1 0.4669 0.7164 0.796 0.104 0.000 0.100
#> GSM613710 2 0.3706 0.7249 0.112 0.848 0.000 0.040
#> GSM613711 3 0.1398 0.9268 0.004 0.040 0.956 0.000
#> GSM613712 3 0.0895 0.9311 0.020 0.004 0.976 0.000
#> GSM613713 3 0.3625 0.8272 0.012 0.160 0.828 0.000
#> GSM613714 3 0.0779 0.9319 0.016 0.004 0.980 0.000
#> GSM613715 3 0.0779 0.9319 0.016 0.004 0.980 0.000
#> GSM613716 3 0.0188 0.9326 0.000 0.004 0.996 0.000
#> GSM613717 3 0.2179 0.9065 0.012 0.064 0.924 0.000
#> GSM613718 3 0.0524 0.9325 0.008 0.004 0.988 0.000
#> GSM613719 3 0.2660 0.9019 0.036 0.000 0.908 0.056
#> GSM613720 3 0.1114 0.9291 0.016 0.008 0.972 0.004
#> GSM613721 4 0.5270 0.3911 0.044 0.008 0.212 0.736
#> GSM613722 4 0.4328 0.7071 0.008 0.244 0.000 0.748
#> GSM613723 3 0.1389 0.9219 0.048 0.000 0.952 0.000
#> GSM613724 1 0.1675 0.7290 0.948 0.004 0.044 0.004
#> GSM613725 4 0.4746 0.5882 0.000 0.368 0.000 0.632
#> GSM613726 4 0.5972 0.6902 0.176 0.132 0.000 0.692
#> GSM613727 1 0.5833 0.0571 0.528 0.032 0.000 0.440
#> GSM613728 4 0.4522 0.6481 0.000 0.320 0.000 0.680
#> GSM613729 4 0.3597 0.6556 0.148 0.016 0.000 0.836
#> GSM613730 2 0.5090 0.6448 0.228 0.728 0.000 0.044
#> GSM613731 1 0.3335 0.7442 0.856 0.016 0.000 0.128
#> GSM613732 3 0.0657 0.9322 0.012 0.004 0.984 0.000
#> GSM613733 3 0.2125 0.9144 0.012 0.052 0.932 0.004
#> GSM613734 1 0.2647 0.6707 0.880 0.000 0.120 0.000
#> GSM613735 3 0.4804 0.4440 0.384 0.000 0.616 0.000
#> GSM613736 2 0.5217 0.1813 0.012 0.608 0.380 0.000
#> GSM613737 3 0.1151 0.9278 0.024 0.000 0.968 0.008
#> GSM613738 3 0.1474 0.9194 0.052 0.000 0.948 0.000
#> GSM613739 3 0.1716 0.9122 0.064 0.000 0.936 0.000
#> GSM613740 3 0.0937 0.9316 0.012 0.012 0.976 0.000
#> GSM613741 3 0.5577 0.5914 0.036 0.000 0.636 0.328
#> GSM613742 3 0.1004 0.9301 0.024 0.004 0.972 0.000
#> GSM613743 3 0.3695 0.8366 0.016 0.156 0.828 0.000
#> GSM613744 3 0.0524 0.9325 0.004 0.008 0.988 0.000
#> GSM613745 3 0.0712 0.9315 0.008 0.004 0.984 0.004
#> GSM613746 3 0.6528 0.6388 0.036 0.056 0.656 0.252
#> GSM613747 1 0.4134 0.5111 0.740 0.000 0.260 0.000
#> GSM613748 2 0.4719 0.6821 0.180 0.772 0.000 0.048
#> GSM613749 4 0.3498 0.7334 0.008 0.160 0.000 0.832
#> GSM613750 3 0.0657 0.9322 0.012 0.004 0.984 0.000
#> GSM613751 3 0.1004 0.9306 0.004 0.024 0.972 0.000
#> GSM613752 3 0.0937 0.9316 0.012 0.012 0.976 0.000
#> GSM613753 3 0.0779 0.9319 0.016 0.004 0.980 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM613638 4 0.5571 0.2262 0.060 0.000 0.008 0.568 0.364
#> GSM613639 2 0.3380 0.7384 0.008 0.840 0.028 0.124 0.000
#> GSM613640 4 0.5446 0.6532 0.044 0.200 0.012 0.708 0.036
#> GSM613641 2 0.3724 0.6559 0.204 0.776 0.000 0.020 0.000
#> GSM613642 4 0.1843 0.6134 0.008 0.008 0.052 0.932 0.000
#> GSM613643 4 0.5013 0.5665 0.240 0.008 0.008 0.700 0.044
#> GSM613644 4 0.2460 0.6525 0.072 0.000 0.004 0.900 0.024
#> GSM613645 4 0.5055 0.6638 0.096 0.196 0.004 0.704 0.000
#> GSM613646 5 0.7673 0.3044 0.056 0.168 0.308 0.012 0.456
#> GSM613647 5 0.1518 0.8361 0.016 0.000 0.012 0.020 0.952
#> GSM613648 5 0.2864 0.8233 0.024 0.000 0.112 0.000 0.864
#> GSM613649 5 0.4238 0.7591 0.028 0.000 0.228 0.004 0.740
#> GSM613650 5 0.5067 0.7159 0.072 0.000 0.224 0.008 0.696
#> GSM613651 5 0.1251 0.8423 0.008 0.000 0.036 0.000 0.956
#> GSM613652 5 0.4400 0.5423 0.308 0.000 0.020 0.000 0.672
#> GSM613653 2 0.8096 -0.0572 0.100 0.464 0.284 0.028 0.124
#> GSM613654 5 0.4600 0.7671 0.136 0.000 0.104 0.004 0.756
#> GSM613655 1 0.3575 0.5725 0.800 0.180 0.004 0.016 0.000
#> GSM613656 1 0.4653 0.0142 0.516 0.000 0.012 0.000 0.472
#> GSM613657 5 0.1372 0.8447 0.016 0.000 0.024 0.004 0.956
#> GSM613658 1 0.3353 0.5848 0.852 0.004 0.004 0.040 0.100
#> GSM613659 4 0.6479 0.3981 0.004 0.264 0.188 0.540 0.004
#> GSM613660 2 0.7309 0.1026 0.012 0.460 0.036 0.348 0.144
#> GSM613661 2 0.4973 0.6785 0.164 0.720 0.004 0.112 0.000
#> GSM613662 2 0.3093 0.7221 0.000 0.824 0.008 0.168 0.000
#> GSM613663 1 0.4840 0.3926 0.640 0.320 0.000 0.040 0.000
#> GSM613664 2 0.2077 0.7408 0.000 0.920 0.040 0.040 0.000
#> GSM613665 4 0.4446 0.0435 0.004 0.476 0.000 0.520 0.000
#> GSM613666 2 0.3894 0.6988 0.156 0.800 0.008 0.036 0.000
#> GSM613667 2 0.4295 0.6400 0.024 0.724 0.004 0.248 0.000
#> GSM613668 1 0.4926 0.4922 0.676 0.276 0.012 0.036 0.000
#> GSM613669 2 0.1885 0.7364 0.032 0.936 0.012 0.020 0.000
#> GSM613670 2 0.0609 0.7214 0.000 0.980 0.020 0.000 0.000
#> GSM613671 2 0.3078 0.7331 0.016 0.848 0.004 0.132 0.000
#> GSM613672 1 0.3828 0.5692 0.808 0.120 0.000 0.072 0.000
#> GSM613673 2 0.6514 0.4264 0.268 0.548 0.016 0.168 0.000
#> GSM613674 3 0.5681 0.5926 0.000 0.124 0.608 0.268 0.000
#> GSM613675 4 0.3769 0.6888 0.004 0.172 0.028 0.796 0.000
#> GSM613676 4 0.3130 0.5949 0.000 0.048 0.096 0.856 0.000
#> GSM613677 4 0.5530 0.6047 0.156 0.024 0.008 0.712 0.100
#> GSM613678 4 0.3722 0.6703 0.004 0.144 0.040 0.812 0.000
#> GSM613679 2 0.4587 0.5810 0.008 0.692 0.024 0.276 0.000
#> GSM613680 1 0.4860 -0.0159 0.540 0.016 0.004 0.440 0.000
#> GSM613681 1 0.5875 -0.0217 0.512 0.088 0.004 0.396 0.000
#> GSM613682 3 0.7269 0.4843 0.076 0.124 0.484 0.316 0.000
#> GSM613683 1 0.3010 0.5334 0.824 0.004 0.000 0.172 0.000
#> GSM613684 3 0.4888 0.6147 0.000 0.016 0.652 0.312 0.020
#> GSM613685 3 0.4752 0.6080 0.000 0.036 0.648 0.316 0.000
#> GSM613686 2 0.3807 0.6868 0.008 0.776 0.012 0.204 0.000
#> GSM613687 1 0.6574 0.1231 0.492 0.208 0.004 0.296 0.000
#> GSM613688 3 0.6058 0.4638 0.004 0.244 0.588 0.164 0.000
#> GSM613689 5 0.1571 0.8405 0.004 0.000 0.060 0.000 0.936
#> GSM613690 5 0.0579 0.8393 0.000 0.000 0.008 0.008 0.984
#> GSM613691 2 0.6562 0.1060 0.032 0.568 0.308 0.016 0.076
#> GSM613692 5 0.3821 0.6855 0.216 0.000 0.020 0.000 0.764
#> GSM613693 3 0.4978 0.6222 0.000 0.016 0.736 0.092 0.156
#> GSM613694 5 0.3933 0.7758 0.020 0.000 0.196 0.008 0.776
#> GSM613695 5 0.1200 0.8365 0.008 0.000 0.016 0.012 0.964
#> GSM613696 5 0.4863 0.5080 0.016 0.000 0.384 0.008 0.592
#> GSM613697 5 0.1557 0.8424 0.008 0.000 0.052 0.000 0.940
#> GSM613698 5 0.2130 0.8335 0.012 0.000 0.080 0.000 0.908
#> GSM613699 5 0.4541 0.7730 0.020 0.028 0.168 0.012 0.772
#> GSM613700 2 0.1830 0.7438 0.004 0.932 0.012 0.052 0.000
#> GSM613701 2 0.6602 0.2236 0.000 0.456 0.304 0.240 0.000
#> GSM613702 2 0.4227 0.2820 0.000 0.580 0.000 0.420 0.000
#> GSM613703 2 0.0798 0.7212 0.008 0.976 0.016 0.000 0.000
#> GSM613704 2 0.0854 0.7253 0.004 0.976 0.012 0.008 0.000
#> GSM613705 5 0.5655 0.5830 0.088 0.000 0.036 0.192 0.684
#> GSM613706 2 0.5368 0.6460 0.016 0.696 0.064 0.216 0.008
#> GSM613707 3 0.4624 0.5948 0.000 0.024 0.636 0.340 0.000
#> GSM613708 4 0.4116 0.5796 0.248 0.016 0.004 0.732 0.000
#> GSM613709 4 0.6519 0.2205 0.380 0.168 0.004 0.448 0.000
#> GSM613710 4 0.2840 0.7131 0.012 0.108 0.004 0.872 0.004
#> GSM613711 5 0.1954 0.8320 0.008 0.000 0.028 0.032 0.932
#> GSM613712 5 0.0451 0.8411 0.000 0.000 0.004 0.008 0.988
#> GSM613713 3 0.4844 0.6145 0.000 0.000 0.720 0.108 0.172
#> GSM613714 5 0.1153 0.8435 0.004 0.000 0.024 0.008 0.964
#> GSM613715 5 0.1507 0.8421 0.012 0.000 0.024 0.012 0.952
#> GSM613716 5 0.3579 0.8081 0.032 0.000 0.116 0.016 0.836
#> GSM613717 5 0.4089 0.7699 0.024 0.000 0.180 0.016 0.780
#> GSM613718 5 0.0912 0.8374 0.000 0.000 0.016 0.012 0.972
#> GSM613719 5 0.5888 0.6659 0.072 0.012 0.248 0.020 0.648
#> GSM613720 5 0.3241 0.8059 0.024 0.000 0.144 0.000 0.832
#> GSM613721 3 0.8006 0.2291 0.072 0.328 0.436 0.028 0.136
#> GSM613722 2 0.2674 0.7340 0.000 0.856 0.004 0.140 0.000
#> GSM613723 5 0.1399 0.8367 0.028 0.000 0.020 0.000 0.952
#> GSM613724 1 0.2628 0.5803 0.884 0.000 0.000 0.088 0.028
#> GSM613725 2 0.4010 0.7066 0.000 0.784 0.056 0.160 0.000
#> GSM613726 2 0.3675 0.7392 0.032 0.828 0.016 0.124 0.000
#> GSM613727 1 0.4675 0.2884 0.600 0.380 0.000 0.020 0.000
#> GSM613728 2 0.4181 0.6629 0.008 0.736 0.016 0.240 0.000
#> GSM613729 2 0.1921 0.7120 0.044 0.932 0.012 0.012 0.000
#> GSM613730 4 0.4468 0.6969 0.044 0.160 0.008 0.776 0.012
#> GSM613731 4 0.6564 0.4718 0.132 0.292 0.028 0.548 0.000
#> GSM613732 5 0.1074 0.8368 0.004 0.000 0.016 0.012 0.968
#> GSM613733 5 0.5646 0.6878 0.032 0.004 0.164 0.100 0.700
#> GSM613734 1 0.2149 0.5841 0.916 0.000 0.000 0.048 0.036
#> GSM613735 1 0.4659 -0.0416 0.500 0.000 0.012 0.000 0.488
#> GSM613736 3 0.6630 0.4391 0.000 0.000 0.444 0.240 0.316
#> GSM613737 5 0.4694 0.7385 0.040 0.000 0.228 0.012 0.720
#> GSM613738 5 0.3532 0.8189 0.092 0.000 0.076 0.000 0.832
#> GSM613739 5 0.2236 0.8332 0.068 0.000 0.024 0.000 0.908
#> GSM613740 5 0.0609 0.8398 0.000 0.000 0.020 0.000 0.980
#> GSM613741 5 0.8462 0.2518 0.100 0.216 0.248 0.024 0.412
#> GSM613742 5 0.1725 0.8402 0.044 0.000 0.020 0.000 0.936
#> GSM613743 5 0.5223 0.5682 0.000 0.000 0.220 0.108 0.672
#> GSM613744 5 0.0324 0.8408 0.000 0.000 0.004 0.004 0.992
#> GSM613745 5 0.4792 0.7503 0.076 0.000 0.196 0.004 0.724
#> GSM613746 3 0.5098 0.4755 0.060 0.016 0.716 0.004 0.204
#> GSM613747 1 0.3543 0.5352 0.832 0.000 0.008 0.036 0.124
#> GSM613748 4 0.3689 0.7121 0.048 0.128 0.004 0.820 0.000
#> GSM613749 2 0.1569 0.7397 0.008 0.948 0.012 0.032 0.000
#> GSM613750 5 0.1173 0.8368 0.004 0.000 0.020 0.012 0.964
#> GSM613751 5 0.1885 0.8272 0.004 0.000 0.044 0.020 0.932
#> GSM613752 5 0.1364 0.8367 0.000 0.000 0.036 0.012 0.952
#> GSM613753 5 0.1173 0.8368 0.004 0.000 0.020 0.012 0.964
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM613638 4 0.6284 0.21054 0.000 0.008 0.404 0.424 0.020 0.144
#> GSM613639 1 0.3280 0.80780 0.844 0.012 0.000 0.084 0.004 0.056
#> GSM613640 4 0.4314 0.73310 0.096 0.000 0.040 0.772 0.000 0.092
#> GSM613641 1 0.3351 0.76609 0.808 0.000 0.000 0.036 0.152 0.004
#> GSM613642 4 0.3174 0.75051 0.016 0.052 0.016 0.872 0.012 0.032
#> GSM613643 4 0.3281 0.72963 0.004 0.000 0.008 0.832 0.120 0.036
#> GSM613644 4 0.3406 0.73736 0.004 0.016 0.024 0.856 0.048 0.052
#> GSM613645 4 0.3252 0.73014 0.124 0.008 0.000 0.832 0.032 0.004
#> GSM613646 6 0.5961 0.64890 0.104 0.040 0.236 0.008 0.004 0.608
#> GSM613647 3 0.1464 0.66001 0.000 0.000 0.944 0.016 0.004 0.036
#> GSM613648 3 0.3975 -0.14643 0.000 0.000 0.544 0.004 0.000 0.452
#> GSM613649 6 0.3930 0.49450 0.000 0.004 0.420 0.000 0.000 0.576
#> GSM613650 6 0.4157 0.59993 0.004 0.004 0.360 0.000 0.008 0.624
#> GSM613651 3 0.2805 0.61224 0.000 0.000 0.828 0.012 0.000 0.160
#> GSM613652 3 0.4420 0.38939 0.000 0.000 0.620 0.000 0.340 0.040
#> GSM613653 6 0.4682 0.56525 0.176 0.008 0.088 0.004 0.004 0.720
#> GSM613654 3 0.5595 0.17362 0.000 0.000 0.540 0.000 0.192 0.268
#> GSM613655 5 0.1686 0.69681 0.052 0.000 0.004 0.008 0.932 0.004
#> GSM613656 3 0.4335 0.16162 0.000 0.000 0.508 0.000 0.472 0.020
#> GSM613657 3 0.1471 0.66189 0.000 0.000 0.932 0.004 0.000 0.064
#> GSM613658 5 0.2218 0.68963 0.000 0.008 0.028 0.020 0.916 0.028
#> GSM613659 1 0.7767 0.41019 0.468 0.120 0.072 0.248 0.008 0.084
#> GSM613660 1 0.6899 0.47514 0.548 0.008 0.192 0.112 0.008 0.132
#> GSM613661 1 0.4587 0.77412 0.764 0.012 0.000 0.104 0.084 0.036
#> GSM613662 1 0.2673 0.81114 0.856 0.004 0.000 0.128 0.004 0.008
#> GSM613663 1 0.4533 0.33232 0.540 0.000 0.000 0.020 0.432 0.008
#> GSM613664 1 0.1564 0.80813 0.936 0.040 0.000 0.024 0.000 0.000
#> GSM613665 1 0.3905 0.72341 0.712 0.012 0.000 0.264 0.000 0.012
#> GSM613666 1 0.3057 0.80642 0.864 0.012 0.000 0.052 0.064 0.008
#> GSM613667 1 0.3799 0.78218 0.768 0.004 0.000 0.188 0.036 0.004
#> GSM613668 5 0.3533 0.65231 0.128 0.040 0.000 0.012 0.816 0.004
#> GSM613669 1 0.1251 0.79948 0.956 0.000 0.000 0.012 0.024 0.008
#> GSM613670 1 0.1003 0.79129 0.964 0.000 0.000 0.004 0.004 0.028
#> GSM613671 1 0.2906 0.80778 0.844 0.004 0.000 0.132 0.016 0.004
#> GSM613672 5 0.2527 0.68263 0.084 0.000 0.000 0.040 0.876 0.000
#> GSM613673 1 0.4690 0.75822 0.720 0.012 0.000 0.160 0.104 0.004
#> GSM613674 2 0.2230 0.78322 0.084 0.892 0.000 0.024 0.000 0.000
#> GSM613675 4 0.4412 0.70906 0.156 0.036 0.004 0.764 0.012 0.028
#> GSM613676 4 0.3073 0.75258 0.032 0.060 0.008 0.868 0.000 0.032
#> GSM613677 4 0.5502 0.60493 0.008 0.008 0.168 0.688 0.068 0.060
#> GSM613678 4 0.3151 0.74107 0.112 0.040 0.000 0.840 0.004 0.004
#> GSM613679 1 0.3680 0.74586 0.744 0.020 0.000 0.232 0.000 0.004
#> GSM613680 4 0.4262 0.29268 0.012 0.000 0.000 0.560 0.424 0.004
#> GSM613681 5 0.5249 -0.14468 0.068 0.004 0.000 0.460 0.464 0.004
#> GSM613682 2 0.3932 0.72501 0.032 0.800 0.000 0.088 0.080 0.000
#> GSM613683 5 0.3121 0.58779 0.000 0.004 0.000 0.180 0.804 0.012
#> GSM613684 2 0.1769 0.80504 0.012 0.924 0.000 0.060 0.000 0.004
#> GSM613685 2 0.1686 0.80487 0.012 0.924 0.000 0.064 0.000 0.000
#> GSM613686 1 0.3166 0.78269 0.800 0.008 0.000 0.184 0.000 0.008
#> GSM613687 5 0.6034 0.16802 0.208 0.004 0.000 0.296 0.488 0.004
#> GSM613688 2 0.4976 0.39232 0.304 0.624 0.000 0.048 0.000 0.024
#> GSM613689 3 0.3290 0.48703 0.000 0.004 0.744 0.000 0.000 0.252
#> GSM613690 3 0.1010 0.66197 0.000 0.000 0.960 0.004 0.000 0.036
#> GSM613691 6 0.6702 0.31508 0.272 0.168 0.076 0.000 0.000 0.484
#> GSM613692 3 0.4385 0.49002 0.000 0.004 0.704 0.004 0.236 0.052
#> GSM613693 2 0.1562 0.78601 0.004 0.940 0.024 0.000 0.000 0.032
#> GSM613694 3 0.4590 -0.24794 0.000 0.020 0.512 0.004 0.004 0.460
#> GSM613695 3 0.0713 0.65365 0.000 0.000 0.972 0.000 0.000 0.028
#> GSM613696 6 0.6111 0.43520 0.000 0.340 0.296 0.000 0.000 0.364
#> GSM613697 3 0.2357 0.64489 0.000 0.000 0.872 0.012 0.000 0.116
#> GSM613698 3 0.3437 0.53307 0.000 0.000 0.752 0.008 0.004 0.236
#> GSM613699 3 0.4605 0.00379 0.016 0.016 0.552 0.000 0.000 0.416
#> GSM613700 1 0.1333 0.81126 0.944 0.000 0.000 0.048 0.000 0.008
#> GSM613701 1 0.5647 0.54650 0.580 0.280 0.000 0.116 0.000 0.024
#> GSM613702 1 0.4394 0.53605 0.608 0.008 0.000 0.364 0.000 0.020
#> GSM613703 1 0.1116 0.79363 0.960 0.000 0.000 0.008 0.004 0.028
#> GSM613704 1 0.0891 0.79763 0.968 0.000 0.000 0.008 0.000 0.024
#> GSM613705 3 0.5551 -0.05664 0.000 0.004 0.460 0.448 0.016 0.072
#> GSM613706 1 0.5148 0.69515 0.668 0.012 0.004 0.228 0.008 0.080
#> GSM613707 2 0.1967 0.79857 0.012 0.904 0.000 0.084 0.000 0.000
#> GSM613708 4 0.3037 0.73147 0.016 0.016 0.000 0.848 0.116 0.004
#> GSM613709 4 0.5314 0.51402 0.164 0.000 0.000 0.612 0.220 0.004
#> GSM613710 4 0.1934 0.75936 0.040 0.000 0.000 0.916 0.000 0.044
#> GSM613711 3 0.2544 0.64325 0.000 0.008 0.888 0.028 0.004 0.072
#> GSM613712 3 0.1536 0.65954 0.000 0.004 0.940 0.016 0.000 0.040
#> GSM613713 2 0.1644 0.77493 0.000 0.932 0.028 0.000 0.000 0.040
#> GSM613714 3 0.4221 0.56029 0.000 0.008 0.744 0.056 0.004 0.188
#> GSM613715 3 0.2678 0.64300 0.000 0.004 0.860 0.020 0.000 0.116
#> GSM613716 3 0.4463 -0.24949 0.000 0.004 0.508 0.020 0.000 0.468
#> GSM613717 6 0.5348 0.55802 0.004 0.024 0.352 0.044 0.004 0.572
#> GSM613718 3 0.1226 0.66006 0.000 0.004 0.952 0.004 0.000 0.040
#> GSM613719 6 0.3721 0.64496 0.000 0.000 0.308 0.004 0.004 0.684
#> GSM613720 3 0.3810 0.02684 0.000 0.000 0.572 0.000 0.000 0.428
#> GSM613721 6 0.5761 0.38814 0.060 0.256 0.084 0.000 0.000 0.600
#> GSM613722 1 0.2191 0.80705 0.876 0.000 0.000 0.120 0.000 0.004
#> GSM613723 3 0.2106 0.66294 0.000 0.000 0.904 0.000 0.032 0.064
#> GSM613724 5 0.1225 0.69024 0.000 0.000 0.012 0.036 0.952 0.000
#> GSM613725 1 0.3839 0.79468 0.796 0.032 0.000 0.132 0.000 0.040
#> GSM613726 1 0.3818 0.80482 0.812 0.004 0.000 0.104 0.040 0.040
#> GSM613727 5 0.4150 0.24007 0.368 0.000 0.000 0.008 0.616 0.008
#> GSM613728 1 0.4635 0.61756 0.648 0.004 0.000 0.288 0.000 0.060
#> GSM613729 1 0.2228 0.79621 0.912 0.004 0.000 0.024 0.044 0.016
#> GSM613730 4 0.4297 0.71059 0.076 0.008 0.020 0.792 0.012 0.092
#> GSM613731 4 0.5965 0.40983 0.284 0.004 0.000 0.560 0.120 0.032
#> GSM613732 3 0.0806 0.66007 0.000 0.000 0.972 0.008 0.000 0.020
#> GSM613733 6 0.6157 0.49876 0.012 0.012 0.268 0.144 0.008 0.556
#> GSM613734 5 0.0951 0.68278 0.000 0.000 0.020 0.004 0.968 0.008
#> GSM613735 5 0.4175 -0.12173 0.000 0.000 0.464 0.000 0.524 0.012
#> GSM613736 3 0.7217 0.05080 0.004 0.324 0.428 0.124 0.008 0.112
#> GSM613737 6 0.3830 0.57360 0.000 0.000 0.376 0.000 0.004 0.620
#> GSM613738 3 0.5124 0.24242 0.000 0.004 0.596 0.012 0.060 0.328
#> GSM613739 3 0.4016 0.59539 0.000 0.000 0.772 0.008 0.088 0.132
#> GSM613740 3 0.2308 0.64327 0.000 0.008 0.880 0.004 0.000 0.108
#> GSM613741 6 0.4769 0.65781 0.040 0.008 0.284 0.000 0.012 0.656
#> GSM613742 3 0.3694 0.60335 0.000 0.000 0.788 0.008 0.048 0.156
#> GSM613743 3 0.5626 0.41228 0.000 0.164 0.644 0.036 0.004 0.152
#> GSM613744 3 0.2445 0.63637 0.000 0.000 0.868 0.008 0.004 0.120
#> GSM613745 6 0.4513 0.58800 0.000 0.000 0.372 0.016 0.016 0.596
#> GSM613746 2 0.4878 0.03825 0.000 0.516 0.060 0.000 0.000 0.424
#> GSM613747 5 0.2697 0.63906 0.000 0.000 0.068 0.008 0.876 0.048
#> GSM613748 4 0.3167 0.74039 0.052 0.004 0.000 0.852 0.012 0.080
#> GSM613749 1 0.1349 0.81243 0.940 0.000 0.000 0.056 0.000 0.004
#> GSM613750 3 0.2113 0.61773 0.000 0.008 0.896 0.004 0.000 0.092
#> GSM613751 3 0.2803 0.58902 0.000 0.016 0.856 0.012 0.000 0.116
#> GSM613752 3 0.2301 0.62238 0.000 0.020 0.884 0.000 0.000 0.096
#> GSM613753 3 0.2009 0.62793 0.000 0.008 0.904 0.004 0.000 0.084
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n disease.state(p) k
#> ATC:NMF 115 0.00706 2
#> ATC:NMF 104 0.15393 3
#> ATC:NMF 102 0.40694 4
#> ATC:NMF 90 0.11451 5
#> ATC:NMF 85 0.02302 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