Date: 2019-12-25 21:23:58 CET, cola version: 1.3.2
Document is loading...
All available functions which can be applied to this res_list object:
res_list
#> A 'ConsensusPartitionList' object with 24 methods.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows are extracted by 'SD, CV, MAD, ATC' methods.
#> Subgroups are detected by 'hclust, kmeans, skmeans, pam, mclust, NMF' method.
#> Number of partitions are tried for k = 2, 3, 4, 5, 6.
#> Performed in total 30000 partitions by row resampling.
#>
#> Following methods can be applied to this 'ConsensusPartitionList' object:
#> [1] "cola_report" "collect_classes" "collect_plots" "collect_stats"
#> [5] "colnames" "functional_enrichment" "get_anno_col" "get_anno"
#> [9] "get_classes" "get_matrix" "get_membership" "get_stats"
#> [13] "is_best_k" "is_stable_k" "ncol" "nrow"
#> [17] "rownames" "show" "suggest_best_k" "test_to_known_factors"
#> [21] "top_rows_heatmap" "top_rows_overlap"
#>
#> You can get result for a single method by, e.g. object["SD", "hclust"] or object["SD:hclust"]
#> or a subset of methods by object[c("SD", "CV")], c("hclust", "kmeans")]
The call of run_all_consensus_partition_methods() was:
#> run_all_consensus_partition_methods(data = mat, mc.cores = 4, anno = anno)
Dimension of the input matrix:
mat = get_matrix(res_list)
dim(mat)
#> [1] 51941 103
The density distribution for each sample is visualized as in one column in the following heatmap. The clustering is based on the distance which is the Kolmogorov-Smirnov statistic between two distributions.
library(ComplexHeatmap)
densityHeatmap(mat, top_annotation = HeatmapAnnotation(df = get_anno(res_list),
col = get_anno_col(res_list)), ylab = "value", cluster_columns = TRUE, show_column_names = FALSE,
mc.cores = 4)
Folowing table shows the best k (number of partitions) for each combination
of top-value methods and partition methods. Clicking on the method name in
the table goes to the section for a single combination of methods.
The cola vignette explains the definition of the metrics used for determining the best number of partitions.
suggest_best_k(res_list)
| The best k | 1-PAC | Mean silhouette | Concordance | Optional k | ||
|---|---|---|---|---|---|---|
| SD:skmeans | 2 | 1.000 | 0.963 | 0.984 | ** | |
| CV:NMF | 2 | 1.000 | 0.958 | 0.983 | ** | |
| MAD:skmeans | 2 | 1.000 | 0.975 | 0.989 | ** | |
| MAD:kmeans | 2 | 0.979 | 0.959 | 0.983 | ** | |
| ATC:kmeans | 2 | 0.979 | 0.924 | 0.972 | ** | |
| CV:mclust | 3 | 0.968 | 0.949 | 0.981 | ** | |
| ATC:pam | 3 | 0.954 | 0.912 | 0.966 | ** | |
| ATC:skmeans | 4 | 0.933 | 0.913 | 0.950 | * | 2,3 |
| SD:mclust | 3 | 0.924 | 0.920 | 0.957 | * | |
| CV:skmeans | 3 | 0.900 | 0.919 | 0.964 | * | 2 |
| MAD:NMF | 2 | 0.890 | 0.888 | 0.944 | ||
| SD:NMF | 2 | 0.880 | 0.924 | 0.967 | ||
| ATC:NMF | 2 | 0.863 | 0.895 | 0.959 | ||
| SD:kmeans | 2 | 0.786 | 0.879 | 0.944 | ||
| CV:pam | 4 | 0.717 | 0.829 | 0.906 | ||
| MAD:pam | 3 | 0.712 | 0.838 | 0.925 | ||
| MAD:mclust | 2 | 0.675 | 0.904 | 0.950 | ||
| CV:kmeans | 2 | 0.670 | 0.866 | 0.935 | ||
| SD:pam | 2 | 0.608 | 0.920 | 0.947 | ||
| ATC:hclust | 3 | 0.596 | 0.795 | 0.898 | ||
| CV:hclust | 2 | 0.557 | 0.807 | 0.910 | ||
| SD:hclust | 3 | 0.505 | 0.729 | 0.862 | ||
| ATC:mclust | 2 | 0.483 | 0.844 | 0.896 | ||
| MAD:hclust | 2 | 0.192 | 0.646 | 0.773 |
**: 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 0.880 0.924 0.967 0.468 0.525 0.525
#> CV:NMF 2 1.000 0.958 0.983 0.427 0.575 0.575
#> MAD:NMF 2 0.890 0.888 0.944 0.444 0.575 0.575
#> ATC:NMF 2 0.863 0.895 0.959 0.438 0.560 0.560
#> SD:skmeans 2 1.000 0.963 0.984 0.495 0.506 0.506
#> CV:skmeans 2 0.901 0.953 0.979 0.497 0.503 0.503
#> MAD:skmeans 2 1.000 0.975 0.989 0.499 0.501 0.501
#> ATC:skmeans 2 1.000 0.955 0.983 0.505 0.496 0.496
#> SD:mclust 2 0.616 0.828 0.907 0.437 0.600 0.600
#> CV:mclust 2 0.689 0.826 0.911 0.464 0.497 0.497
#> MAD:mclust 2 0.675 0.904 0.950 0.488 0.499 0.499
#> ATC:mclust 2 0.483 0.844 0.896 0.482 0.503 0.503
#> SD:kmeans 2 0.786 0.879 0.944 0.443 0.530 0.530
#> CV:kmeans 2 0.670 0.866 0.935 0.431 0.600 0.600
#> MAD:kmeans 2 0.979 0.959 0.983 0.479 0.520 0.520
#> ATC:kmeans 2 0.979 0.924 0.972 0.504 0.496 0.496
#> SD:pam 2 0.608 0.920 0.947 0.458 0.525 0.525
#> CV:pam 2 0.455 0.754 0.870 0.405 0.541 0.541
#> MAD:pam 2 0.608 0.780 0.914 0.496 0.506 0.506
#> ATC:pam 2 0.697 0.898 0.951 0.468 0.535 0.535
#> SD:hclust 2 0.552 0.826 0.916 0.323 0.672 0.672
#> CV:hclust 2 0.557 0.807 0.910 0.343 0.650 0.650
#> MAD:hclust 2 0.192 0.646 0.773 0.430 0.547 0.547
#> ATC:hclust 2 0.382 0.807 0.848 0.395 0.639 0.639
get_stats(res_list, k = 3)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 3 0.727 0.804 0.920 0.330 0.747 0.558
#> CV:NMF 3 0.738 0.803 0.918 0.509 0.698 0.508
#> MAD:NMF 3 0.526 0.651 0.778 0.403 0.758 0.595
#> ATC:NMF 3 0.867 0.863 0.941 0.423 0.728 0.548
#> SD:skmeans 3 0.816 0.820 0.930 0.306 0.745 0.540
#> CV:skmeans 3 0.900 0.919 0.964 0.328 0.742 0.532
#> MAD:skmeans 3 0.569 0.734 0.846 0.315 0.781 0.584
#> ATC:skmeans 3 1.000 0.963 0.986 0.282 0.816 0.644
#> SD:mclust 3 0.924 0.920 0.957 0.285 0.808 0.692
#> CV:mclust 3 0.968 0.949 0.981 0.223 0.872 0.757
#> MAD:mclust 3 0.848 0.885 0.937 0.137 0.815 0.674
#> ATC:mclust 3 0.610 0.814 0.862 0.312 0.719 0.517
#> SD:kmeans 3 0.733 0.802 0.887 0.356 0.830 0.693
#> CV:kmeans 3 0.619 0.808 0.895 0.405 0.714 0.548
#> MAD:kmeans 3 0.480 0.534 0.757 0.328 0.791 0.619
#> ATC:kmeans 3 0.729 0.855 0.922 0.281 0.641 0.407
#> SD:pam 3 0.678 0.795 0.792 0.376 0.753 0.552
#> CV:pam 3 0.584 0.593 0.800 0.501 0.843 0.721
#> MAD:pam 3 0.712 0.838 0.925 0.246 0.756 0.566
#> ATC:pam 3 0.954 0.912 0.966 0.367 0.684 0.474
#> SD:hclust 3 0.505 0.729 0.862 0.373 0.928 0.894
#> CV:hclust 3 0.528 0.795 0.902 0.271 0.898 0.845
#> MAD:hclust 3 0.392 0.542 0.747 0.302 0.822 0.713
#> ATC:hclust 3 0.596 0.795 0.898 0.488 0.817 0.714
get_stats(res_list, k = 4)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 4 0.773 0.829 0.919 0.1300 0.869 0.674
#> CV:NMF 4 0.789 0.808 0.912 0.0967 0.843 0.613
#> MAD:NMF 4 0.622 0.722 0.858 0.1220 0.678 0.363
#> ATC:NMF 4 0.734 0.712 0.855 0.1265 0.882 0.700
#> SD:skmeans 4 0.868 0.878 0.938 0.1627 0.788 0.475
#> CV:skmeans 4 0.842 0.846 0.930 0.1382 0.839 0.571
#> MAD:skmeans 4 0.797 0.747 0.893 0.1405 0.832 0.554
#> ATC:skmeans 4 0.933 0.913 0.950 0.0984 0.876 0.673
#> SD:mclust 4 0.543 0.476 0.787 0.2056 0.937 0.864
#> CV:mclust 4 0.624 0.603 0.789 0.2008 0.916 0.806
#> MAD:mclust 4 0.467 0.662 0.766 0.2419 0.787 0.545
#> ATC:mclust 4 0.624 0.733 0.808 0.1524 0.816 0.550
#> SD:kmeans 4 0.653 0.676 0.779 0.1578 0.893 0.753
#> CV:kmeans 4 0.639 0.714 0.800 0.1544 0.904 0.763
#> MAD:kmeans 4 0.534 0.604 0.736 0.1429 0.731 0.399
#> ATC:kmeans 4 0.735 0.822 0.875 0.1406 0.789 0.487
#> SD:pam 4 0.742 0.829 0.900 0.1536 0.930 0.789
#> CV:pam 4 0.717 0.829 0.906 0.1930 0.746 0.466
#> MAD:pam 4 0.684 0.728 0.833 0.1587 0.824 0.583
#> ATC:pam 4 0.778 0.752 0.845 0.1172 0.949 0.856
#> SD:hclust 4 0.450 0.703 0.828 0.2425 0.801 0.691
#> CV:hclust 4 0.546 0.763 0.865 0.1547 0.973 0.953
#> MAD:hclust 4 0.457 0.538 0.743 0.1458 0.882 0.776
#> ATC:hclust 4 0.567 0.646 0.777 0.1254 0.945 0.881
get_stats(res_list, k = 5)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 5 0.598 0.531 0.752 0.0755 0.892 0.688
#> CV:NMF 5 0.642 0.572 0.787 0.0692 0.912 0.739
#> MAD:NMF 5 0.587 0.610 0.788 0.0791 0.813 0.514
#> ATC:NMF 5 0.633 0.601 0.787 0.0818 0.884 0.650
#> SD:skmeans 5 0.758 0.725 0.847 0.0581 0.929 0.730
#> CV:skmeans 5 0.780 0.771 0.854 0.0588 0.905 0.653
#> MAD:skmeans 5 0.703 0.715 0.822 0.0650 0.859 0.522
#> ATC:skmeans 5 0.763 0.791 0.860 0.0764 0.844 0.539
#> SD:mclust 5 0.593 0.645 0.776 0.1152 0.787 0.504
#> CV:mclust 5 0.612 0.589 0.793 0.0759 0.818 0.557
#> MAD:mclust 5 0.579 0.733 0.814 0.0935 0.931 0.757
#> ATC:mclust 5 0.553 0.573 0.760 0.0606 0.920 0.711
#> SD:kmeans 5 0.673 0.770 0.841 0.1004 0.831 0.546
#> CV:kmeans 5 0.706 0.757 0.839 0.0887 0.834 0.543
#> MAD:kmeans 5 0.656 0.662 0.775 0.0730 0.898 0.649
#> ATC:kmeans 5 0.850 0.786 0.882 0.0693 0.905 0.664
#> SD:pam 5 0.608 0.600 0.784 0.0589 0.820 0.460
#> CV:pam 5 0.639 0.701 0.798 0.0639 0.833 0.490
#> MAD:pam 5 0.752 0.661 0.822 0.0900 0.784 0.411
#> ATC:pam 5 0.843 0.877 0.920 0.1103 0.822 0.490
#> SD:hclust 5 0.490 0.745 0.821 0.1069 0.946 0.888
#> CV:hclust 5 0.538 0.656 0.793 0.1813 0.835 0.700
#> MAD:hclust 5 0.475 0.418 0.664 0.0901 0.797 0.556
#> ATC:hclust 5 0.667 0.737 0.819 0.1447 0.771 0.476
get_stats(res_list, k = 6)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> SD:NMF 6 0.601 0.474 0.713 0.0500 0.931 0.763
#> CV:NMF 6 0.617 0.537 0.722 0.0608 0.840 0.497
#> MAD:NMF 6 0.626 0.531 0.734 0.0631 0.899 0.647
#> ATC:NMF 6 0.569 0.501 0.688 0.0455 0.913 0.690
#> SD:skmeans 6 0.724 0.603 0.763 0.0445 0.931 0.688
#> CV:skmeans 6 0.770 0.624 0.794 0.0459 0.906 0.593
#> MAD:skmeans 6 0.737 0.698 0.810 0.0390 0.955 0.785
#> ATC:skmeans 6 0.746 0.623 0.785 0.0381 0.946 0.785
#> SD:mclust 6 0.669 0.704 0.821 0.0671 0.840 0.444
#> CV:mclust 6 0.692 0.503 0.709 0.0887 0.808 0.423
#> MAD:mclust 6 0.674 0.648 0.801 0.0515 0.879 0.560
#> ATC:mclust 6 0.642 0.336 0.689 0.0506 0.845 0.461
#> SD:kmeans 6 0.691 0.637 0.774 0.0551 0.926 0.699
#> CV:kmeans 6 0.689 0.639 0.805 0.0511 0.936 0.745
#> MAD:kmeans 6 0.696 0.595 0.760 0.0513 0.843 0.440
#> ATC:kmeans 6 0.758 0.634 0.770 0.0469 0.938 0.731
#> SD:pam 6 0.675 0.642 0.807 0.0581 0.876 0.525
#> CV:pam 6 0.695 0.681 0.801 0.0585 0.877 0.521
#> MAD:pam 6 0.824 0.759 0.876 0.0472 0.911 0.640
#> ATC:pam 6 0.849 0.813 0.896 0.0425 0.971 0.861
#> SD:hclust 6 0.444 0.678 0.778 0.0682 0.978 0.950
#> CV:hclust 6 0.521 0.688 0.779 0.0721 0.910 0.773
#> MAD:hclust 6 0.540 0.549 0.683 0.0589 0.910 0.719
#> ATC:hclust 6 0.737 0.746 0.790 0.0407 0.992 0.964
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) development.stage(p) other(p) k
#> SD:NMF 100 9.58e-11 0.1858 0.7059 2
#> CV:NMF 101 7.92e-14 0.4649 0.0464 2
#> MAD:NMF 97 9.99e-08 0.0619 1.0000 2
#> ATC:NMF 98 1.48e-02 0.6046 0.3513 2
#> SD:skmeans 101 9.92e-09 0.0116 0.7049 2
#> CV:skmeans 102 1.54e-08 0.0919 0.6747 2
#> MAD:skmeans 102 5.70e-08 0.0175 0.5734 2
#> ATC:skmeans 99 4.23e-01 0.6820 0.3753 2
#> SD:mclust 101 1.16e-13 0.2475 0.0599 2
#> CV:mclust 90 7.48e-10 0.0756 0.0412 2
#> MAD:mclust 101 1.34e-07 0.0190 0.5039 2
#> ATC:mclust 101 2.13e-06 0.3473 0.3170 2
#> SD:kmeans 94 8.69e-13 0.6174 0.0927 2
#> CV:kmeans 102 6.19e-16 0.2501 0.0543 2
#> MAD:kmeans 102 3.30e-10 0.0508 0.9555 2
#> ATC:kmeans 98 2.76e-01 0.6956 0.3958 2
#> SD:pam 102 1.97e-05 0.0379 0.9555 2
#> CV:pam 94 1.31e-05 0.0237 1.0000 2
#> MAD:pam 86 1.74e-06 0.0220 0.7514 2
#> ATC:pam 101 6.68e-01 0.4062 0.1793 2
#> SD:hclust 97 3.71e-20 0.0872 0.1708 2
#> CV:hclust 96 8.70e-17 0.1235 0.1234 2
#> MAD:hclust 88 3.21e-09 0.2340 1.0000 2
#> ATC:hclust 101 2.79e-02 0.5659 0.3288 2
test_to_known_factors(res_list, k = 3)
#> n disease.state(p) development.stage(p) other(p) k
#> SD:NMF 90 1.90e-13 0.004660 0.1596 3
#> CV:NMF 90 1.01e-13 0.001385 0.1017 3
#> MAD:NMF 85 1.11e-05 0.076048 0.8135 3
#> ATC:NMF 95 2.96e-05 0.223732 0.1258 3
#> SD:skmeans 91 1.21e-14 0.001450 0.0483 3
#> CV:skmeans 98 8.30e-15 0.012671 0.0649 3
#> MAD:skmeans 93 4.23e-09 0.198182 0.1811 3
#> ATC:skmeans 102 1.08e-03 0.461874 0.3183 3
#> SD:mclust 102 2.75e-13 0.117063 0.0594 3
#> CV:mclust 101 1.37e-12 0.102526 0.0548 3
#> MAD:mclust 100 7.38e-15 0.157108 0.0229 3
#> ATC:mclust 103 2.65e-09 0.083725 0.0967 3
#> SD:kmeans 92 1.06e-15 0.000678 0.1167 3
#> CV:kmeans 96 7.68e-15 0.000971 0.1540 3
#> MAD:kmeans 65 6.95e-12 0.021763 0.1445 3
#> ATC:kmeans 99 6.39e-02 0.365935 0.2380 3
#> SD:pam 96 4.85e-06 0.140038 0.5089 3
#> CV:pam 76 1.00e+00 0.001065 0.5034 3
#> MAD:pam 100 3.34e-14 0.059599 0.2784 3
#> ATC:pam 97 3.96e-03 0.194572 0.1351 3
#> SD:hclust 81 2.58e-18 0.682987 0.3354 3
#> CV:hclust 95 3.63e-17 0.349802 0.1712 3
#> MAD:hclust 75 6.65e-05 0.005649 0.4364 3
#> ATC:hclust 92 1.02e-01 0.527731 0.2697 3
test_to_known_factors(res_list, k = 4)
#> n disease.state(p) development.stage(p) other(p) k
#> SD:NMF 96 7.90e-12 0.04025 0.0394 4
#> CV:NMF 93 8.25e-11 0.03818 0.0727 4
#> MAD:NMF 90 3.04e-10 0.00440 0.0195 4
#> ATC:NMF 83 3.47e-06 0.35582 0.2822 4
#> SD:skmeans 99 8.15e-16 0.00833 0.1534 4
#> CV:skmeans 96 1.08e-13 0.01844 0.0702 4
#> MAD:skmeans 82 7.41e-13 0.02497 0.0731 4
#> ATC:skmeans 102 7.13e-10 0.43173 0.3537 4
#> SD:mclust 45 3.36e-04 0.52976 0.0286 4
#> CV:mclust 75 1.12e-07 0.39825 0.1008 4
#> MAD:mclust 91 3.02e-12 0.10916 0.0773 4
#> ATC:mclust 85 3.02e-07 0.65512 0.1009 4
#> SD:kmeans 85 5.07e-15 0.01338 0.3715 4
#> CV:kmeans 94 2.54e-14 0.00539 0.1725 4
#> MAD:kmeans 77 6.35e-13 0.00277 0.1634 4
#> ATC:kmeans 99 3.95e-03 0.68110 0.6064 4
#> SD:pam 97 8.95e-13 0.02597 0.3328 4
#> CV:pam 95 1.54e-11 0.03690 0.3317 4
#> MAD:pam 94 1.72e-14 0.00825 0.3953 4
#> ATC:pam 101 1.17e-07 0.12494 0.1687 4
#> SD:hclust 88 2.83e-17 0.02011 0.1684 4
#> CV:hclust 92 8.31e-15 0.54893 0.3856 4
#> MAD:hclust 74 1.70e-05 0.07244 0.6137 4
#> ATC:hclust 89 5.01e-04 0.14935 0.4513 4
test_to_known_factors(res_list, k = 5)
#> n disease.state(p) development.stage(p) other(p) k
#> SD:NMF 65 4.71e-11 0.000622 0.1521 5
#> CV:NMF 76 1.55e-09 0.012188 0.1389 5
#> MAD:NMF 79 8.67e-08 0.023465 0.0495 5
#> ATC:NMF 72 2.24e-04 0.114191 0.4779 5
#> SD:skmeans 92 2.44e-13 0.005856 0.1533 5
#> CV:skmeans 92 6.59e-11 0.031276 0.1437 5
#> MAD:skmeans 89 4.25e-14 0.004629 0.2497 5
#> ATC:skmeans 96 1.19e-06 0.817874 0.6785 5
#> SD:mclust 84 1.89e-13 0.107194 0.1273 5
#> CV:mclust 73 1.92e-11 0.049620 0.0549 5
#> MAD:mclust 95 5.03e-14 0.011134 0.1091 5
#> ATC:mclust 74 3.56e-08 0.582653 0.1779 5
#> SD:kmeans 96 7.75e-13 0.009664 0.1531 5
#> CV:kmeans 93 2.07e-12 0.005035 0.1536 5
#> MAD:kmeans 88 1.97e-12 0.019285 0.1173 5
#> ATC:kmeans 96 3.68e-05 0.454861 0.5173 5
#> SD:pam 82 8.65e-13 0.054105 0.2753 5
#> CV:pam 90 9.77e-13 0.016498 0.1362 5
#> MAD:pam 84 5.01e-12 0.007487 0.4314 5
#> ATC:pam 101 9.13e-07 0.255962 0.2180 5
#> SD:hclust 91 2.28e-16 0.005295 0.2033 5
#> CV:hclust 83 1.47e-13 0.213102 0.2918 5
#> MAD:hclust 58 6.40e-10 0.048739 0.2107 5
#> ATC:hclust 95 1.21e-05 0.168243 0.4918 5
test_to_known_factors(res_list, k = 6)
#> n disease.state(p) development.stage(p) other(p) k
#> SD:NMF 54 8.16e-07 0.013272 0.3874 6
#> CV:NMF 61 1.83e-07 0.005383 0.2440 6
#> MAD:NMF 66 8.77e-07 0.001472 0.0763 6
#> ATC:NMF 61 8.20e-01 0.321505 0.4730 6
#> SD:skmeans 76 8.20e-11 0.076060 0.2738 6
#> CV:skmeans 65 3.46e-07 0.330490 0.1276 6
#> MAD:skmeans 88 4.07e-14 0.011115 0.3566 6
#> ATC:skmeans 74 9.81e-06 0.524852 0.8808 6
#> SD:mclust 93 8.39e-12 0.231068 0.2786 6
#> CV:mclust 53 1.13e-04 0.291833 0.0859 6
#> MAD:mclust 74 4.06e-09 0.041079 0.0467 6
#> ATC:mclust 38 6.76e-04 0.444790 0.2872 6
#> SD:kmeans 82 3.25e-12 0.016027 0.1226 6
#> CV:kmeans 81 1.12e-11 0.012007 0.1641 6
#> MAD:kmeans 78 3.38e-10 0.008727 0.1348 6
#> ATC:kmeans 82 3.55e-07 0.166913 0.7143 6
#> SD:pam 82 3.66e-12 0.015402 0.2503 6
#> CV:pam 85 5.01e-11 0.003376 0.2260 6
#> MAD:pam 90 3.22e-12 0.026478 0.5361 6
#> ATC:pam 97 6.36e-09 0.347140 0.2958 6
#> SD:hclust 78 2.19e-15 0.000909 0.1728 6
#> CV:hclust 83 9.86e-14 0.106667 0.4614 6
#> MAD:hclust 74 3.54e-12 0.050883 0.0917 6
#> ATC:hclust 90 2.48e-06 0.243453 0.5275 6
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["SD", "hclust"]
# you can also extract it by
# res = res_list["SD:hclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'SD' method.
#> Subgroups are detected by 'hclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 3.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.552 0.826 0.916 0.3232 0.672 0.672
#> 3 3 0.505 0.729 0.862 0.3728 0.928 0.894
#> 4 4 0.450 0.703 0.828 0.2425 0.801 0.691
#> 5 5 0.490 0.745 0.821 0.1069 0.946 0.888
#> 6 6 0.444 0.678 0.778 0.0682 0.978 0.950
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 3
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM647569 2 0.6531 0.779 0.168 0.832
#> GSM647574 2 0.6623 0.774 0.172 0.828
#> GSM647577 2 0.6531 0.779 0.168 0.832
#> GSM647547 2 0.9087 0.445 0.324 0.676
#> GSM647552 2 0.4298 0.869 0.088 0.912
#> GSM647553 2 0.6623 0.774 0.172 0.828
#> GSM647565 2 0.5408 0.827 0.124 0.876
#> GSM647545 2 0.0000 0.925 0.000 1.000
#> GSM647549 2 0.0000 0.925 0.000 1.000
#> GSM647550 2 0.0000 0.925 0.000 1.000
#> GSM647560 2 0.0000 0.925 0.000 1.000
#> GSM647617 2 0.6623 0.774 0.172 0.828
#> GSM647528 2 0.0000 0.925 0.000 1.000
#> GSM647529 1 0.9944 0.366 0.544 0.456
#> GSM647531 2 0.1633 0.915 0.024 0.976
#> GSM647540 2 0.0000 0.925 0.000 1.000
#> GSM647541 2 0.0000 0.925 0.000 1.000
#> GSM647546 2 0.0376 0.924 0.004 0.996
#> GSM647557 2 0.0672 0.923 0.008 0.992
#> GSM647561 2 0.0000 0.925 0.000 1.000
#> GSM647567 2 0.1633 0.914 0.024 0.976
#> GSM647568 2 0.0000 0.925 0.000 1.000
#> GSM647570 2 0.0000 0.925 0.000 1.000
#> GSM647573 2 0.9087 0.445 0.324 0.676
#> GSM647576 2 0.0000 0.925 0.000 1.000
#> GSM647579 2 0.0376 0.924 0.004 0.996
#> GSM647580 2 0.6623 0.774 0.172 0.828
#> GSM647583 2 0.6531 0.779 0.168 0.832
#> GSM647592 2 0.2423 0.904 0.040 0.960
#> GSM647593 2 0.2423 0.904 0.040 0.960
#> GSM647595 2 0.2236 0.906 0.036 0.964
#> GSM647597 2 0.4022 0.872 0.080 0.920
#> GSM647598 2 0.0000 0.925 0.000 1.000
#> GSM647613 2 0.0000 0.925 0.000 1.000
#> GSM647615 2 0.0000 0.925 0.000 1.000
#> GSM647616 2 0.6531 0.779 0.168 0.832
#> GSM647619 2 0.2423 0.904 0.040 0.960
#> GSM647582 2 0.0376 0.924 0.004 0.996
#> GSM647591 2 0.2236 0.906 0.036 0.964
#> GSM647527 2 0.0000 0.925 0.000 1.000
#> GSM647530 2 0.5294 0.833 0.120 0.880
#> GSM647532 1 0.9922 0.390 0.552 0.448
#> GSM647544 2 0.0000 0.925 0.000 1.000
#> GSM647551 2 0.1414 0.916 0.020 0.980
#> GSM647556 2 0.6712 0.768 0.176 0.824
#> GSM647558 2 0.2236 0.908 0.036 0.964
#> GSM647572 2 0.1843 0.912 0.028 0.972
#> GSM647578 2 0.0000 0.925 0.000 1.000
#> GSM647581 2 0.2236 0.908 0.036 0.964
#> GSM647594 2 0.2948 0.894 0.052 0.948
#> GSM647599 2 0.8016 0.653 0.244 0.756
#> GSM647600 2 0.1414 0.916 0.020 0.980
#> GSM647601 2 0.0000 0.925 0.000 1.000
#> GSM647603 2 0.0000 0.925 0.000 1.000
#> GSM647610 2 0.4431 0.875 0.092 0.908
#> GSM647611 2 0.0000 0.925 0.000 1.000
#> GSM647612 2 0.0000 0.925 0.000 1.000
#> GSM647614 2 0.0000 0.925 0.000 1.000
#> GSM647618 2 0.0376 0.924 0.004 0.996
#> GSM647629 2 0.0000 0.925 0.000 1.000
#> GSM647535 2 0.0000 0.925 0.000 1.000
#> GSM647563 2 0.0000 0.925 0.000 1.000
#> GSM647542 2 0.0000 0.925 0.000 1.000
#> GSM647543 2 0.0000 0.925 0.000 1.000
#> GSM647548 2 0.5408 0.827 0.124 0.876
#> GSM647554 2 0.0000 0.925 0.000 1.000
#> GSM647555 2 0.0000 0.925 0.000 1.000
#> GSM647559 2 0.0000 0.925 0.000 1.000
#> GSM647562 2 0.0000 0.925 0.000 1.000
#> GSM647564 2 0.6623 0.774 0.172 0.828
#> GSM647571 2 0.0000 0.925 0.000 1.000
#> GSM647584 2 0.0672 0.922 0.008 0.992
#> GSM647585 2 0.6712 0.768 0.176 0.824
#> GSM647586 2 0.0000 0.925 0.000 1.000
#> GSM647587 2 0.0000 0.925 0.000 1.000
#> GSM647588 2 0.0000 0.925 0.000 1.000
#> GSM647596 2 0.0000 0.925 0.000 1.000
#> GSM647602 2 0.6623 0.774 0.172 0.828
#> GSM647609 2 0.0000 0.925 0.000 1.000
#> GSM647620 2 0.0000 0.925 0.000 1.000
#> GSM647627 2 0.0000 0.925 0.000 1.000
#> GSM647628 2 0.0000 0.925 0.000 1.000
#> GSM647533 1 0.0000 0.779 1.000 0.000
#> GSM647536 1 0.9922 0.390 0.552 0.448
#> GSM647537 1 0.0000 0.779 1.000 0.000
#> GSM647606 1 0.0000 0.779 1.000 0.000
#> GSM647621 2 0.9850 0.094 0.428 0.572
#> GSM647626 2 0.8661 0.556 0.288 0.712
#> GSM647538 1 0.5946 0.745 0.856 0.144
#> GSM647575 1 0.9427 0.593 0.640 0.360
#> GSM647590 1 0.8443 0.696 0.728 0.272
#> GSM647605 1 0.0000 0.779 1.000 0.000
#> GSM647607 1 0.9427 0.593 0.640 0.360
#> GSM647608 1 0.9460 0.588 0.636 0.364
#> GSM647622 1 0.0000 0.779 1.000 0.000
#> GSM647623 1 0.0000 0.779 1.000 0.000
#> GSM647624 1 0.0000 0.779 1.000 0.000
#> GSM647625 1 0.0000 0.779 1.000 0.000
#> GSM647534 1 0.5946 0.745 0.856 0.144
#> GSM647539 1 0.8499 0.693 0.724 0.276
#> GSM647566 1 0.8443 0.698 0.728 0.272
#> GSM647589 1 0.9460 0.588 0.636 0.364
#> GSM647604 1 0.0000 0.779 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 2 0.6345 0.3637 0.400 0.596 0.004
#> GSM647574 2 0.6215 0.2969 0.428 0.572 0.000
#> GSM647577 2 0.6345 0.3637 0.400 0.596 0.004
#> GSM647547 1 0.6713 0.3981 0.572 0.416 0.012
#> GSM647552 2 0.4569 0.7712 0.068 0.860 0.072
#> GSM647553 2 0.6386 0.3342 0.412 0.584 0.004
#> GSM647565 2 0.4974 0.6451 0.236 0.764 0.000
#> GSM647545 2 0.0592 0.8614 0.012 0.988 0.000
#> GSM647549 2 0.0892 0.8572 0.020 0.980 0.000
#> GSM647550 2 0.1964 0.8435 0.056 0.944 0.000
#> GSM647560 2 0.0424 0.8620 0.008 0.992 0.000
#> GSM647617 2 0.6373 0.3484 0.408 0.588 0.004
#> GSM647528 2 0.0000 0.8614 0.000 1.000 0.000
#> GSM647529 1 0.9877 0.4093 0.388 0.260 0.352
#> GSM647531 2 0.2280 0.8381 0.052 0.940 0.008
#> GSM647540 2 0.1964 0.8435 0.056 0.944 0.000
#> GSM647541 2 0.0237 0.8618 0.004 0.996 0.000
#> GSM647546 2 0.3412 0.7969 0.124 0.876 0.000
#> GSM647557 2 0.1832 0.8489 0.036 0.956 0.008
#> GSM647561 2 0.0892 0.8572 0.020 0.980 0.000
#> GSM647567 2 0.3183 0.8319 0.076 0.908 0.016
#> GSM647568 2 0.0237 0.8619 0.004 0.996 0.000
#> GSM647570 2 0.0424 0.8621 0.008 0.992 0.000
#> GSM647573 1 0.6713 0.3981 0.572 0.416 0.012
#> GSM647576 2 0.2261 0.8384 0.068 0.932 0.000
#> GSM647579 2 0.2448 0.8328 0.076 0.924 0.000
#> GSM647580 2 0.6373 0.3484 0.408 0.588 0.004
#> GSM647583 2 0.6345 0.3637 0.400 0.596 0.004
#> GSM647592 2 0.2918 0.8303 0.044 0.924 0.032
#> GSM647593 2 0.2313 0.8398 0.024 0.944 0.032
#> GSM647595 2 0.2050 0.8418 0.020 0.952 0.028
#> GSM647597 2 0.4652 0.7689 0.080 0.856 0.064
#> GSM647598 2 0.0000 0.8614 0.000 1.000 0.000
#> GSM647613 2 0.0237 0.8615 0.004 0.996 0.000
#> GSM647615 2 0.0892 0.8612 0.020 0.980 0.000
#> GSM647616 2 0.6345 0.3637 0.400 0.596 0.004
#> GSM647619 2 0.2313 0.8398 0.024 0.944 0.032
#> GSM647582 2 0.0829 0.8610 0.012 0.984 0.004
#> GSM647591 2 0.2050 0.8418 0.020 0.952 0.028
#> GSM647527 2 0.0000 0.8614 0.000 1.000 0.000
#> GSM647530 2 0.5585 0.6335 0.204 0.772 0.024
#> GSM647532 1 0.9850 0.4018 0.392 0.252 0.356
#> GSM647544 2 0.0424 0.8613 0.008 0.992 0.000
#> GSM647551 2 0.1482 0.8512 0.020 0.968 0.012
#> GSM647556 2 0.6386 0.3378 0.412 0.584 0.004
#> GSM647558 2 0.3267 0.7962 0.116 0.884 0.000
#> GSM647572 2 0.3267 0.8008 0.116 0.884 0.000
#> GSM647578 2 0.1163 0.8585 0.028 0.972 0.000
#> GSM647581 2 0.3340 0.7928 0.120 0.880 0.000
#> GSM647594 2 0.2527 0.8341 0.020 0.936 0.044
#> GSM647599 2 0.8255 0.4466 0.196 0.636 0.168
#> GSM647600 2 0.1482 0.8512 0.020 0.968 0.012
#> GSM647601 2 0.0000 0.8614 0.000 1.000 0.000
#> GSM647603 2 0.1289 0.8591 0.032 0.968 0.000
#> GSM647610 2 0.5631 0.7303 0.164 0.792 0.044
#> GSM647611 2 0.0424 0.8613 0.008 0.992 0.000
#> GSM647612 2 0.0424 0.8620 0.008 0.992 0.000
#> GSM647614 2 0.0237 0.8619 0.004 0.996 0.000
#> GSM647618 2 0.0829 0.8610 0.012 0.984 0.004
#> GSM647629 2 0.0424 0.8619 0.008 0.992 0.000
#> GSM647535 2 0.0237 0.8618 0.004 0.996 0.000
#> GSM647563 2 0.0424 0.8612 0.008 0.992 0.000
#> GSM647542 2 0.0237 0.8619 0.004 0.996 0.000
#> GSM647543 2 0.0237 0.8619 0.004 0.996 0.000
#> GSM647548 2 0.4931 0.6487 0.232 0.768 0.000
#> GSM647554 2 0.1964 0.8428 0.056 0.944 0.000
#> GSM647555 2 0.0424 0.8620 0.008 0.992 0.000
#> GSM647559 2 0.0424 0.8613 0.008 0.992 0.000
#> GSM647562 2 0.0424 0.8613 0.008 0.992 0.000
#> GSM647564 2 0.6373 0.3484 0.408 0.588 0.004
#> GSM647571 2 0.1289 0.8591 0.032 0.968 0.000
#> GSM647584 2 0.0892 0.8571 0.020 0.980 0.000
#> GSM647585 2 0.6386 0.3378 0.412 0.584 0.004
#> GSM647586 2 0.0000 0.8614 0.000 1.000 0.000
#> GSM647587 2 0.0424 0.8613 0.008 0.992 0.000
#> GSM647588 2 0.0747 0.8617 0.016 0.984 0.000
#> GSM647596 2 0.0000 0.8614 0.000 1.000 0.000
#> GSM647602 2 0.6373 0.3484 0.408 0.588 0.004
#> GSM647609 2 0.0000 0.8614 0.000 1.000 0.000
#> GSM647620 2 0.0237 0.8618 0.004 0.996 0.000
#> GSM647627 2 0.0000 0.8614 0.000 1.000 0.000
#> GSM647628 2 0.0000 0.8614 0.000 1.000 0.000
#> GSM647533 3 0.0000 0.9307 0.000 0.000 1.000
#> GSM647536 1 0.9850 0.4018 0.392 0.252 0.356
#> GSM647537 3 0.0000 0.9307 0.000 0.000 1.000
#> GSM647606 3 0.0000 0.9307 0.000 0.000 1.000
#> GSM647621 1 0.8801 0.5445 0.560 0.292 0.148
#> GSM647626 2 0.8784 0.0236 0.388 0.496 0.116
#> GSM647538 3 0.7044 0.6217 0.168 0.108 0.724
#> GSM647575 1 0.7588 0.6266 0.684 0.120 0.196
#> GSM647590 1 0.4963 0.4465 0.792 0.008 0.200
#> GSM647605 3 0.0000 0.9307 0.000 0.000 1.000
#> GSM647607 1 0.7588 0.6266 0.684 0.120 0.196
#> GSM647608 1 0.7542 0.6272 0.688 0.120 0.192
#> GSM647622 3 0.0237 0.9301 0.004 0.000 0.996
#> GSM647623 3 0.0237 0.9301 0.004 0.000 0.996
#> GSM647624 3 0.0237 0.9301 0.004 0.000 0.996
#> GSM647625 3 0.0237 0.9301 0.004 0.000 0.996
#> GSM647534 3 0.7044 0.6217 0.168 0.108 0.724
#> GSM647539 1 0.5072 0.4562 0.792 0.012 0.196
#> GSM647566 1 0.5122 0.4431 0.788 0.012 0.200
#> GSM647589 1 0.7542 0.6272 0.688 0.120 0.192
#> GSM647604 3 0.0000 0.9307 0.000 0.000 1.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 3 0.4741 0.58859 0.004 0.328 0.668 0.000
#> GSM647574 3 0.4406 0.58596 0.000 0.300 0.700 0.000
#> GSM647577 3 0.4741 0.58859 0.004 0.328 0.668 0.000
#> GSM647547 3 0.6140 0.36023 0.000 0.252 0.652 0.096
#> GSM647552 2 0.5757 0.68670 0.028 0.704 0.032 0.236
#> GSM647553 3 0.4946 0.58691 0.004 0.308 0.680 0.008
#> GSM647565 2 0.5932 0.53420 0.000 0.680 0.224 0.096
#> GSM647545 2 0.1406 0.88022 0.000 0.960 0.024 0.016
#> GSM647549 2 0.1820 0.87105 0.000 0.944 0.020 0.036
#> GSM647550 2 0.3032 0.82557 0.000 0.868 0.124 0.008
#> GSM647560 2 0.1042 0.88162 0.000 0.972 0.020 0.008
#> GSM647617 3 0.4699 0.59078 0.004 0.320 0.676 0.000
#> GSM647528 2 0.0000 0.88017 0.000 1.000 0.000 0.000
#> GSM647529 3 0.8498 -0.24941 0.128 0.068 0.416 0.388
#> GSM647531 2 0.3301 0.83733 0.000 0.876 0.076 0.048
#> GSM647540 2 0.3142 0.81864 0.000 0.860 0.132 0.008
#> GSM647541 2 0.1722 0.87623 0.000 0.944 0.048 0.008
#> GSM647546 2 0.4018 0.69306 0.000 0.772 0.224 0.004
#> GSM647557 2 0.3117 0.84734 0.000 0.880 0.028 0.092
#> GSM647561 2 0.1724 0.87250 0.000 0.948 0.020 0.032
#> GSM647567 2 0.5102 0.76677 0.000 0.764 0.136 0.100
#> GSM647568 2 0.0707 0.87925 0.000 0.980 0.020 0.000
#> GSM647570 2 0.1004 0.87981 0.000 0.972 0.024 0.004
#> GSM647573 3 0.6140 0.36023 0.000 0.252 0.652 0.096
#> GSM647576 2 0.2973 0.80334 0.000 0.856 0.144 0.000
#> GSM647579 2 0.2921 0.81178 0.000 0.860 0.140 0.000
#> GSM647580 3 0.4699 0.59078 0.004 0.320 0.676 0.000
#> GSM647583 3 0.4741 0.58859 0.004 0.328 0.668 0.000
#> GSM647592 2 0.4175 0.75769 0.000 0.784 0.016 0.200
#> GSM647593 2 0.3591 0.78241 0.000 0.824 0.008 0.168
#> GSM647595 2 0.3351 0.79559 0.000 0.844 0.008 0.148
#> GSM647597 2 0.5355 0.65118 0.016 0.692 0.016 0.276
#> GSM647598 2 0.0000 0.88017 0.000 1.000 0.000 0.000
#> GSM647613 2 0.0376 0.88108 0.000 0.992 0.004 0.004
#> GSM647615 2 0.1302 0.87629 0.000 0.956 0.044 0.000
#> GSM647616 3 0.4741 0.58859 0.004 0.328 0.668 0.000
#> GSM647619 2 0.3636 0.78037 0.000 0.820 0.008 0.172
#> GSM647582 2 0.2142 0.87235 0.000 0.928 0.016 0.056
#> GSM647591 2 0.3351 0.79559 0.000 0.844 0.008 0.148
#> GSM647527 2 0.0000 0.88017 0.000 1.000 0.000 0.000
#> GSM647530 2 0.5693 0.55082 0.000 0.688 0.240 0.072
#> GSM647532 3 0.8426 -0.26032 0.132 0.060 0.416 0.392
#> GSM647544 2 0.1109 0.88010 0.000 0.968 0.004 0.028
#> GSM647551 2 0.2867 0.83578 0.000 0.884 0.012 0.104
#> GSM647556 3 0.4677 0.58871 0.004 0.316 0.680 0.000
#> GSM647558 2 0.3760 0.77390 0.000 0.836 0.136 0.028
#> GSM647572 2 0.3764 0.75204 0.000 0.816 0.172 0.012
#> GSM647578 2 0.1474 0.87569 0.000 0.948 0.052 0.000
#> GSM647581 2 0.3948 0.76437 0.000 0.828 0.136 0.036
#> GSM647594 2 0.3591 0.78145 0.000 0.824 0.008 0.168
#> GSM647599 2 0.9261 -0.15275 0.136 0.388 0.332 0.144
#> GSM647600 2 0.2867 0.83578 0.000 0.884 0.012 0.104
#> GSM647601 2 0.0188 0.88037 0.000 0.996 0.004 0.000
#> GSM647603 2 0.2483 0.86645 0.000 0.916 0.052 0.032
#> GSM647610 2 0.7585 0.29522 0.012 0.528 0.288 0.172
#> GSM647611 2 0.1109 0.87981 0.000 0.968 0.004 0.028
#> GSM647612 2 0.0817 0.87912 0.000 0.976 0.024 0.000
#> GSM647614 2 0.0592 0.87993 0.000 0.984 0.016 0.000
#> GSM647618 2 0.2142 0.87235 0.000 0.928 0.016 0.056
#> GSM647629 2 0.1042 0.88113 0.000 0.972 0.020 0.008
#> GSM647535 2 0.0804 0.88110 0.000 0.980 0.012 0.008
#> GSM647563 2 0.0657 0.88267 0.000 0.984 0.012 0.004
#> GSM647542 2 0.0707 0.87925 0.000 0.980 0.020 0.000
#> GSM647543 2 0.0707 0.87925 0.000 0.980 0.020 0.000
#> GSM647548 2 0.5900 0.53756 0.000 0.684 0.220 0.096
#> GSM647554 2 0.3196 0.81408 0.000 0.856 0.136 0.008
#> GSM647555 2 0.0817 0.87912 0.000 0.976 0.024 0.000
#> GSM647559 2 0.0921 0.87987 0.000 0.972 0.000 0.028
#> GSM647562 2 0.0921 0.87987 0.000 0.972 0.000 0.028
#> GSM647564 3 0.4699 0.59078 0.004 0.320 0.676 0.000
#> GSM647571 2 0.2483 0.86645 0.000 0.916 0.052 0.032
#> GSM647584 2 0.2676 0.84500 0.000 0.896 0.012 0.092
#> GSM647585 3 0.4677 0.58871 0.004 0.316 0.680 0.000
#> GSM647586 2 0.0000 0.88017 0.000 1.000 0.000 0.000
#> GSM647587 2 0.0921 0.87987 0.000 0.972 0.000 0.028
#> GSM647588 2 0.1211 0.87958 0.000 0.960 0.040 0.000
#> GSM647596 2 0.0000 0.88017 0.000 1.000 0.000 0.000
#> GSM647602 3 0.4699 0.59078 0.004 0.320 0.676 0.000
#> GSM647609 2 0.0188 0.88037 0.000 0.996 0.004 0.000
#> GSM647620 2 0.0804 0.88110 0.000 0.980 0.012 0.008
#> GSM647627 2 0.0188 0.88037 0.000 0.996 0.004 0.000
#> GSM647628 2 0.0188 0.88030 0.000 0.996 0.004 0.000
#> GSM647533 1 0.1211 0.95724 0.960 0.000 0.000 0.040
#> GSM647536 3 0.8426 -0.26032 0.132 0.060 0.416 0.392
#> GSM647537 1 0.1211 0.95724 0.960 0.000 0.000 0.040
#> GSM647606 1 0.0336 0.98067 0.992 0.000 0.000 0.008
#> GSM647621 3 0.4389 0.25654 0.132 0.020 0.820 0.028
#> GSM647626 3 0.6602 0.52563 0.112 0.264 0.620 0.004
#> GSM647538 4 0.4957 1.00000 0.300 0.000 0.016 0.684
#> GSM647575 3 0.6287 0.15655 0.092 0.004 0.648 0.256
#> GSM647590 3 0.6677 -0.00952 0.096 0.000 0.540 0.364
#> GSM647605 1 0.0469 0.97984 0.988 0.000 0.000 0.012
#> GSM647607 3 0.6287 0.15655 0.092 0.004 0.648 0.256
#> GSM647608 3 0.6230 0.16107 0.088 0.004 0.652 0.256
#> GSM647622 1 0.0000 0.98061 1.000 0.000 0.000 0.000
#> GSM647623 1 0.0000 0.98061 1.000 0.000 0.000 0.000
#> GSM647624 1 0.0000 0.98061 1.000 0.000 0.000 0.000
#> GSM647625 1 0.0000 0.98061 1.000 0.000 0.000 0.000
#> GSM647534 4 0.4957 1.00000 0.300 0.000 0.016 0.684
#> GSM647539 3 0.6626 -0.00581 0.092 0.000 0.544 0.364
#> GSM647566 3 0.6658 -0.02764 0.092 0.000 0.532 0.376
#> GSM647589 3 0.6230 0.16107 0.088 0.004 0.652 0.256
#> GSM647604 1 0.0469 0.97984 0.988 0.000 0.000 0.012
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.3300 0.9151 0.000 0.204 0.792 0.000 0.004
#> GSM647574 3 0.4041 0.8699 0.000 0.176 0.780 0.040 0.004
#> GSM647577 3 0.3300 0.9151 0.000 0.204 0.792 0.000 0.004
#> GSM647547 4 0.6948 0.2521 0.000 0.200 0.148 0.576 0.076
#> GSM647552 2 0.6419 0.5997 0.020 0.608 0.148 0.008 0.216
#> GSM647553 3 0.4000 0.8814 0.000 0.180 0.784 0.020 0.016
#> GSM647565 2 0.6518 0.4531 0.000 0.612 0.092 0.220 0.076
#> GSM647545 2 0.2300 0.8340 0.000 0.908 0.052 0.000 0.040
#> GSM647549 2 0.2804 0.8254 0.000 0.888 0.048 0.008 0.056
#> GSM647550 2 0.3109 0.7381 0.000 0.800 0.200 0.000 0.000
#> GSM647560 2 0.1628 0.8380 0.000 0.936 0.056 0.000 0.008
#> GSM647617 3 0.3300 0.9159 0.000 0.204 0.792 0.000 0.004
#> GSM647528 2 0.0000 0.8412 0.000 1.000 0.000 0.000 0.000
#> GSM647529 5 0.6751 0.5142 0.048 0.016 0.056 0.376 0.504
#> GSM647531 2 0.4152 0.7836 0.000 0.816 0.060 0.036 0.088
#> GSM647540 2 0.3274 0.7117 0.000 0.780 0.220 0.000 0.000
#> GSM647541 2 0.2068 0.8315 0.000 0.904 0.092 0.000 0.004
#> GSM647546 2 0.4046 0.5403 0.000 0.696 0.296 0.000 0.008
#> GSM647557 2 0.3910 0.7872 0.000 0.808 0.040 0.012 0.140
#> GSM647561 2 0.2663 0.8284 0.000 0.896 0.048 0.008 0.048
#> GSM647567 2 0.4484 0.6513 0.000 0.668 0.308 0.000 0.024
#> GSM647568 2 0.1357 0.8330 0.000 0.948 0.048 0.000 0.004
#> GSM647570 2 0.1557 0.8335 0.000 0.940 0.052 0.000 0.008
#> GSM647573 4 0.6914 0.2515 0.000 0.200 0.144 0.580 0.076
#> GSM647576 2 0.3366 0.7010 0.000 0.784 0.212 0.000 0.004
#> GSM647579 2 0.3642 0.6832 0.000 0.760 0.232 0.000 0.008
#> GSM647580 3 0.3300 0.9159 0.000 0.204 0.792 0.000 0.004
#> GSM647583 3 0.3300 0.9151 0.000 0.204 0.792 0.000 0.004
#> GSM647592 2 0.5182 0.6773 0.000 0.708 0.164 0.008 0.120
#> GSM647593 2 0.4719 0.7048 0.000 0.748 0.156 0.008 0.088
#> GSM647595 2 0.4436 0.7209 0.000 0.768 0.156 0.008 0.068
#> GSM647597 2 0.6357 0.5555 0.012 0.600 0.156 0.008 0.224
#> GSM647598 2 0.0162 0.8420 0.000 0.996 0.000 0.000 0.004
#> GSM647613 2 0.0451 0.8431 0.000 0.988 0.004 0.000 0.008
#> GSM647615 2 0.2006 0.8271 0.000 0.916 0.072 0.000 0.012
#> GSM647616 3 0.3300 0.9151 0.000 0.204 0.792 0.000 0.004
#> GSM647619 2 0.4772 0.7023 0.000 0.744 0.156 0.008 0.092
#> GSM647582 2 0.2983 0.8252 0.000 0.868 0.032 0.004 0.096
#> GSM647591 2 0.4436 0.7209 0.000 0.768 0.156 0.008 0.068
#> GSM647527 2 0.0000 0.8412 0.000 1.000 0.000 0.000 0.000
#> GSM647530 2 0.5926 0.5323 0.000 0.644 0.024 0.216 0.116
#> GSM647532 5 0.6719 0.5233 0.052 0.012 0.056 0.376 0.504
#> GSM647544 2 0.0955 0.8432 0.000 0.968 0.000 0.004 0.028
#> GSM647551 2 0.3484 0.7876 0.000 0.824 0.144 0.004 0.028
#> GSM647556 3 0.3422 0.9103 0.000 0.200 0.792 0.004 0.004
#> GSM647558 2 0.4637 0.7201 0.000 0.784 0.056 0.108 0.052
#> GSM647572 2 0.3878 0.6364 0.000 0.748 0.236 0.000 0.016
#> GSM647578 2 0.2248 0.8308 0.000 0.900 0.088 0.000 0.012
#> GSM647581 2 0.4826 0.7060 0.000 0.772 0.052 0.108 0.068
#> GSM647594 2 0.4719 0.7050 0.000 0.748 0.156 0.008 0.088
#> GSM647599 3 0.7804 0.1762 0.112 0.336 0.452 0.024 0.076
#> GSM647600 2 0.3484 0.7876 0.000 0.824 0.144 0.004 0.028
#> GSM647601 2 0.0880 0.8419 0.000 0.968 0.032 0.000 0.000
#> GSM647603 2 0.2676 0.8196 0.000 0.884 0.080 0.000 0.036
#> GSM647610 2 0.6171 0.1432 0.000 0.464 0.416 0.004 0.116
#> GSM647611 2 0.1753 0.8402 0.000 0.936 0.032 0.000 0.032
#> GSM647612 2 0.1430 0.8324 0.000 0.944 0.052 0.000 0.004
#> GSM647614 2 0.1121 0.8353 0.000 0.956 0.044 0.000 0.000
#> GSM647618 2 0.2983 0.8252 0.000 0.868 0.032 0.004 0.096
#> GSM647629 2 0.1408 0.8439 0.000 0.948 0.044 0.000 0.008
#> GSM647535 2 0.0880 0.8425 0.000 0.968 0.032 0.000 0.000
#> GSM647563 2 0.0740 0.8442 0.000 0.980 0.008 0.004 0.008
#> GSM647542 2 0.1357 0.8330 0.000 0.948 0.048 0.000 0.004
#> GSM647543 2 0.1357 0.8330 0.000 0.948 0.048 0.000 0.004
#> GSM647548 2 0.6396 0.4665 0.000 0.620 0.080 0.224 0.076
#> GSM647554 2 0.3210 0.7223 0.000 0.788 0.212 0.000 0.000
#> GSM647555 2 0.1430 0.8324 0.000 0.944 0.052 0.000 0.004
#> GSM647559 2 0.0794 0.8427 0.000 0.972 0.000 0.000 0.028
#> GSM647562 2 0.0794 0.8427 0.000 0.972 0.000 0.000 0.028
#> GSM647564 3 0.3300 0.9159 0.000 0.204 0.792 0.000 0.004
#> GSM647571 2 0.2676 0.8196 0.000 0.884 0.080 0.000 0.036
#> GSM647584 2 0.3073 0.8030 0.000 0.856 0.116 0.004 0.024
#> GSM647585 3 0.3422 0.9103 0.000 0.200 0.792 0.004 0.004
#> GSM647586 2 0.0000 0.8412 0.000 1.000 0.000 0.000 0.000
#> GSM647587 2 0.0794 0.8427 0.000 0.972 0.000 0.000 0.028
#> GSM647588 2 0.2069 0.8360 0.000 0.912 0.076 0.000 0.012
#> GSM647596 2 0.0000 0.8412 0.000 1.000 0.000 0.000 0.000
#> GSM647602 3 0.3300 0.9159 0.000 0.204 0.792 0.000 0.004
#> GSM647609 2 0.0880 0.8419 0.000 0.968 0.032 0.000 0.000
#> GSM647620 2 0.0880 0.8425 0.000 0.968 0.032 0.000 0.000
#> GSM647627 2 0.0880 0.8419 0.000 0.968 0.032 0.000 0.000
#> GSM647628 2 0.0162 0.8414 0.000 0.996 0.004 0.000 0.000
#> GSM647533 1 0.1732 0.9249 0.920 0.000 0.000 0.000 0.080
#> GSM647536 5 0.6719 0.5233 0.052 0.012 0.056 0.376 0.504
#> GSM647537 1 0.1732 0.9249 0.920 0.000 0.000 0.000 0.080
#> GSM647606 1 0.0290 0.9739 0.992 0.000 0.000 0.000 0.008
#> GSM647621 4 0.7203 0.0894 0.108 0.000 0.384 0.436 0.072
#> GSM647626 3 0.5762 0.7824 0.092 0.180 0.692 0.020 0.016
#> GSM647538 5 0.6380 0.4613 0.188 0.000 0.072 0.104 0.636
#> GSM647575 4 0.1965 0.5667 0.000 0.000 0.096 0.904 0.000
#> GSM647590 4 0.4131 0.4673 0.004 0.000 0.064 0.788 0.144
#> GSM647605 1 0.0404 0.9732 0.988 0.000 0.000 0.000 0.012
#> GSM647607 4 0.1965 0.5667 0.000 0.000 0.096 0.904 0.000
#> GSM647608 4 0.2127 0.5672 0.000 0.000 0.108 0.892 0.000
#> GSM647622 1 0.0000 0.9740 1.000 0.000 0.000 0.000 0.000
#> GSM647623 1 0.0000 0.9740 1.000 0.000 0.000 0.000 0.000
#> GSM647624 1 0.0000 0.9740 1.000 0.000 0.000 0.000 0.000
#> GSM647625 1 0.0000 0.9740 1.000 0.000 0.000 0.000 0.000
#> GSM647534 5 0.6380 0.4613 0.188 0.000 0.072 0.104 0.636
#> GSM647539 4 0.3975 0.4703 0.000 0.000 0.064 0.792 0.144
#> GSM647566 4 0.4098 0.4600 0.000 0.000 0.064 0.780 0.156
#> GSM647589 4 0.2127 0.5672 0.000 0.000 0.108 0.892 0.000
#> GSM647604 1 0.0404 0.9732 0.988 0.000 0.000 0.000 0.012
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.2912 0.9139 0.000 0.172 0.816 0.012 0.000 0.000
#> GSM647574 3 0.3637 0.8835 0.000 0.164 0.780 0.056 0.000 0.000
#> GSM647577 3 0.2912 0.9139 0.000 0.172 0.816 0.012 0.000 0.000
#> GSM647547 4 0.3763 0.3737 0.000 0.172 0.060 0.768 0.000 0.000
#> GSM647552 2 0.6275 0.3653 0.000 0.520 0.040 0.036 0.344 0.060
#> GSM647553 3 0.3718 0.8887 0.000 0.164 0.780 0.052 0.000 0.004
#> GSM647565 2 0.5094 0.4291 0.000 0.568 0.080 0.348 0.004 0.000
#> GSM647545 2 0.2954 0.7827 0.000 0.868 0.044 0.060 0.028 0.000
#> GSM647549 2 0.3317 0.7607 0.000 0.828 0.004 0.080 0.088 0.000
#> GSM647550 2 0.3974 0.7019 0.000 0.768 0.172 0.008 0.048 0.004
#> GSM647560 2 0.2158 0.7910 0.000 0.912 0.056 0.012 0.016 0.004
#> GSM647617 3 0.2703 0.9151 0.000 0.172 0.824 0.000 0.000 0.004
#> GSM647528 2 0.0363 0.7950 0.000 0.988 0.000 0.000 0.012 0.000
#> GSM647529 4 0.6472 0.4097 0.012 0.000 0.016 0.448 0.336 0.188
#> GSM647531 2 0.4022 0.7151 0.000 0.764 0.004 0.144 0.088 0.000
#> GSM647540 2 0.4133 0.6782 0.000 0.748 0.192 0.008 0.048 0.004
#> GSM647541 2 0.2881 0.7867 0.000 0.872 0.064 0.012 0.048 0.004
#> GSM647546 2 0.4127 0.5183 0.000 0.672 0.304 0.016 0.004 0.004
#> GSM647557 2 0.4652 0.7003 0.000 0.736 0.004 0.076 0.156 0.028
#> GSM647561 2 0.3210 0.7642 0.000 0.836 0.004 0.072 0.088 0.000
#> GSM647567 2 0.5697 0.5346 0.000 0.584 0.208 0.008 0.196 0.004
#> GSM647568 2 0.1769 0.7857 0.000 0.924 0.060 0.012 0.004 0.000
#> GSM647570 2 0.1889 0.7863 0.000 0.920 0.056 0.020 0.004 0.000
#> GSM647573 4 0.3706 0.3737 0.000 0.172 0.056 0.772 0.000 0.000
#> GSM647576 2 0.3627 0.6640 0.000 0.760 0.216 0.016 0.004 0.004
#> GSM647579 2 0.4246 0.6433 0.000 0.720 0.232 0.012 0.032 0.004
#> GSM647580 3 0.2703 0.9151 0.000 0.172 0.824 0.000 0.000 0.004
#> GSM647583 3 0.2912 0.9139 0.000 0.172 0.816 0.012 0.000 0.000
#> GSM647592 2 0.4902 0.2238 0.000 0.500 0.012 0.000 0.452 0.036
#> GSM647593 2 0.4093 0.3917 0.000 0.584 0.012 0.000 0.404 0.000
#> GSM647595 2 0.4057 0.4132 0.000 0.600 0.012 0.000 0.388 0.000
#> GSM647597 5 0.4719 -0.2855 0.000 0.408 0.012 0.004 0.556 0.020
#> GSM647598 2 0.0632 0.7968 0.000 0.976 0.000 0.000 0.024 0.000
#> GSM647613 2 0.0806 0.7975 0.000 0.972 0.000 0.008 0.020 0.000
#> GSM647615 2 0.2398 0.7767 0.000 0.888 0.080 0.028 0.004 0.000
#> GSM647616 3 0.2912 0.9139 0.000 0.172 0.816 0.012 0.000 0.000
#> GSM647619 2 0.4116 0.3773 0.000 0.572 0.012 0.000 0.416 0.000
#> GSM647582 2 0.3899 0.7534 0.000 0.800 0.012 0.032 0.132 0.024
#> GSM647591 2 0.4057 0.4132 0.000 0.600 0.012 0.000 0.388 0.000
#> GSM647527 2 0.0363 0.7950 0.000 0.988 0.000 0.000 0.012 0.000
#> GSM647530 2 0.4769 0.4510 0.000 0.604 0.004 0.336 0.056 0.000
#> GSM647532 4 0.6496 0.4095 0.012 0.000 0.016 0.448 0.328 0.196
#> GSM647544 2 0.1624 0.7940 0.000 0.936 0.000 0.004 0.040 0.020
#> GSM647551 2 0.3766 0.6641 0.000 0.748 0.040 0.000 0.212 0.000
#> GSM647556 3 0.2920 0.9084 0.000 0.168 0.820 0.004 0.000 0.008
#> GSM647558 2 0.4401 0.6680 0.000 0.732 0.052 0.192 0.024 0.000
#> GSM647572 2 0.4523 0.5802 0.000 0.704 0.240 0.012 0.020 0.024
#> GSM647578 2 0.3013 0.7858 0.000 0.864 0.064 0.028 0.044 0.000
#> GSM647581 2 0.4502 0.6509 0.000 0.720 0.048 0.204 0.028 0.000
#> GSM647594 2 0.4123 0.3514 0.000 0.568 0.012 0.000 0.420 0.000
#> GSM647599 3 0.8649 -0.0281 0.096 0.240 0.300 0.016 0.268 0.080
#> GSM647600 2 0.3766 0.6641 0.000 0.748 0.040 0.000 0.212 0.000
#> GSM647601 2 0.1007 0.7928 0.000 0.956 0.000 0.000 0.044 0.000
#> GSM647603 2 0.3425 0.7679 0.000 0.844 0.080 0.008 0.036 0.032
#> GSM647610 2 0.7412 -0.1337 0.000 0.332 0.252 0.012 0.328 0.076
#> GSM647611 2 0.2039 0.7865 0.000 0.904 0.000 0.000 0.076 0.020
#> GSM647612 2 0.1913 0.7854 0.000 0.920 0.060 0.012 0.004 0.004
#> GSM647614 2 0.1285 0.7907 0.000 0.944 0.052 0.000 0.004 0.000
#> GSM647618 2 0.3899 0.7534 0.000 0.800 0.012 0.032 0.132 0.024
#> GSM647629 2 0.2124 0.7957 0.000 0.916 0.016 0.016 0.048 0.004
#> GSM647535 2 0.1371 0.7946 0.000 0.948 0.004 0.004 0.040 0.004
#> GSM647563 2 0.1381 0.7997 0.000 0.952 0.004 0.020 0.020 0.004
#> GSM647542 2 0.1769 0.7857 0.000 0.924 0.060 0.012 0.004 0.000
#> GSM647543 2 0.1769 0.7857 0.000 0.924 0.060 0.012 0.004 0.000
#> GSM647548 2 0.4968 0.4393 0.000 0.576 0.068 0.352 0.004 0.000
#> GSM647554 2 0.4163 0.6802 0.000 0.748 0.188 0.008 0.052 0.004
#> GSM647555 2 0.1913 0.7854 0.000 0.920 0.060 0.012 0.004 0.004
#> GSM647559 2 0.1480 0.7936 0.000 0.940 0.000 0.000 0.040 0.020
#> GSM647562 2 0.1480 0.7936 0.000 0.940 0.000 0.000 0.040 0.020
#> GSM647564 3 0.2845 0.9148 0.000 0.172 0.820 0.004 0.000 0.004
#> GSM647571 2 0.3425 0.7679 0.000 0.844 0.080 0.008 0.036 0.032
#> GSM647584 2 0.3156 0.7107 0.000 0.800 0.020 0.000 0.180 0.000
#> GSM647585 3 0.2778 0.9094 0.000 0.168 0.824 0.000 0.000 0.008
#> GSM647586 2 0.0363 0.7950 0.000 0.988 0.000 0.000 0.012 0.000
#> GSM647587 2 0.1480 0.7936 0.000 0.940 0.000 0.000 0.040 0.020
#> GSM647588 2 0.2906 0.7892 0.000 0.872 0.052 0.032 0.044 0.000
#> GSM647596 2 0.0363 0.7950 0.000 0.988 0.000 0.000 0.012 0.000
#> GSM647602 3 0.2845 0.9148 0.000 0.172 0.820 0.004 0.000 0.004
#> GSM647609 2 0.1007 0.7928 0.000 0.956 0.000 0.000 0.044 0.000
#> GSM647620 2 0.1225 0.7958 0.000 0.956 0.004 0.004 0.032 0.004
#> GSM647627 2 0.1007 0.7928 0.000 0.956 0.000 0.000 0.044 0.000
#> GSM647628 2 0.0291 0.7963 0.000 0.992 0.004 0.000 0.004 0.000
#> GSM647533 1 0.2490 0.8986 0.892 0.000 0.012 0.000 0.044 0.052
#> GSM647536 4 0.6496 0.4095 0.012 0.000 0.016 0.448 0.328 0.196
#> GSM647537 1 0.2490 0.8986 0.892 0.000 0.012 0.000 0.044 0.052
#> GSM647606 1 0.0000 0.9678 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647621 4 0.6873 0.2196 0.092 0.000 0.304 0.496 0.028 0.080
#> GSM647626 3 0.5234 0.7884 0.084 0.160 0.704 0.008 0.004 0.040
#> GSM647538 5 0.8127 0.0609 0.136 0.000 0.164 0.080 0.420 0.200
#> GSM647575 4 0.2631 0.3116 0.000 0.000 0.008 0.840 0.000 0.152
#> GSM647590 6 0.3619 0.9864 0.004 0.000 0.000 0.316 0.000 0.680
#> GSM647605 1 0.0146 0.9672 0.996 0.000 0.004 0.000 0.000 0.000
#> GSM647607 4 0.2631 0.3116 0.000 0.000 0.008 0.840 0.000 0.152
#> GSM647608 4 0.2869 0.3080 0.000 0.000 0.020 0.832 0.000 0.148
#> GSM647622 1 0.0260 0.9680 0.992 0.000 0.000 0.000 0.000 0.008
#> GSM647623 1 0.0260 0.9680 0.992 0.000 0.000 0.000 0.000 0.008
#> GSM647624 1 0.0260 0.9680 0.992 0.000 0.000 0.000 0.000 0.008
#> GSM647625 1 0.0260 0.9680 0.992 0.000 0.000 0.000 0.000 0.008
#> GSM647534 5 0.8127 0.0609 0.136 0.000 0.164 0.080 0.420 0.200
#> GSM647539 6 0.3499 0.9856 0.000 0.000 0.000 0.320 0.000 0.680
#> GSM647566 6 0.3446 0.9808 0.000 0.000 0.000 0.308 0.000 0.692
#> GSM647589 4 0.2869 0.3080 0.000 0.000 0.020 0.832 0.000 0.148
#> GSM647604 1 0.0146 0.9672 0.996 0.000 0.004 0.000 0.000 0.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n disease.state(p) development.stage(p) other(p) k
#> SD:hclust 97 3.71e-20 0.087188 0.171 2
#> SD:hclust 81 2.58e-18 0.682987 0.335 3
#> SD:hclust 88 2.83e-17 0.020106 0.168 4
#> SD:hclust 91 2.28e-16 0.005295 0.203 5
#> SD:hclust 78 2.19e-15 0.000909 0.173 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["SD", "kmeans"]
# you can also extract it by
# res = res_list["SD:kmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'SD' method.
#> Subgroups are detected by 'kmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.786 0.879 0.944 0.4429 0.530 0.530
#> 3 3 0.733 0.802 0.887 0.3560 0.830 0.693
#> 4 4 0.653 0.676 0.779 0.1578 0.893 0.753
#> 5 5 0.673 0.770 0.841 0.1004 0.831 0.546
#> 6 6 0.691 0.637 0.774 0.0551 0.926 0.699
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
#> GSM647569 1 0.9866 0.431 0.568 0.432
#> GSM647574 1 0.9850 0.439 0.572 0.428
#> GSM647577 1 0.9866 0.431 0.568 0.432
#> GSM647547 1 0.9248 0.587 0.660 0.340
#> GSM647552 2 0.2423 0.938 0.040 0.960
#> GSM647553 1 0.1633 0.853 0.976 0.024
#> GSM647565 2 0.1184 0.969 0.016 0.984
#> GSM647545 2 0.0000 0.980 0.000 1.000
#> GSM647549 2 0.0376 0.980 0.004 0.996
#> GSM647550 2 0.0376 0.980 0.004 0.996
#> GSM647560 2 0.0376 0.980 0.004 0.996
#> GSM647617 1 0.9866 0.431 0.568 0.432
#> GSM647528 2 0.0000 0.980 0.000 1.000
#> GSM647529 1 0.0376 0.863 0.996 0.004
#> GSM647531 2 0.0000 0.980 0.000 1.000
#> GSM647540 2 0.0376 0.980 0.004 0.996
#> GSM647541 2 0.0376 0.980 0.004 0.996
#> GSM647546 2 0.4298 0.880 0.088 0.912
#> GSM647557 2 0.0000 0.980 0.000 1.000
#> GSM647561 2 0.0000 0.980 0.000 1.000
#> GSM647567 2 0.9427 0.276 0.360 0.640
#> GSM647568 2 0.0376 0.980 0.004 0.996
#> GSM647570 2 0.0376 0.980 0.004 0.996
#> GSM647573 1 0.1414 0.855 0.980 0.020
#> GSM647576 2 0.0376 0.980 0.004 0.996
#> GSM647579 2 0.0376 0.980 0.004 0.996
#> GSM647580 1 0.9393 0.566 0.644 0.356
#> GSM647583 1 0.9866 0.431 0.568 0.432
#> GSM647592 2 0.0000 0.980 0.000 1.000
#> GSM647593 2 0.0000 0.980 0.000 1.000
#> GSM647595 2 0.0000 0.980 0.000 1.000
#> GSM647597 2 0.9795 0.201 0.416 0.584
#> GSM647598 2 0.0000 0.980 0.000 1.000
#> GSM647613 2 0.0000 0.980 0.000 1.000
#> GSM647615 2 0.0376 0.980 0.004 0.996
#> GSM647616 1 0.9866 0.431 0.568 0.432
#> GSM647619 2 0.0000 0.980 0.000 1.000
#> GSM647582 2 0.0000 0.980 0.000 1.000
#> GSM647591 2 0.0000 0.980 0.000 1.000
#> GSM647527 2 0.0000 0.980 0.000 1.000
#> GSM647530 2 0.0000 0.980 0.000 1.000
#> GSM647532 1 0.0376 0.863 0.996 0.004
#> GSM647544 2 0.0000 0.980 0.000 1.000
#> GSM647551 2 0.0000 0.980 0.000 1.000
#> GSM647556 1 0.9393 0.566 0.644 0.356
#> GSM647558 2 0.0376 0.980 0.004 0.996
#> GSM647572 2 0.1633 0.961 0.024 0.976
#> GSM647578 2 0.0376 0.980 0.004 0.996
#> GSM647581 2 0.0376 0.980 0.004 0.996
#> GSM647594 2 0.0000 0.980 0.000 1.000
#> GSM647599 1 0.0376 0.863 0.996 0.004
#> GSM647600 2 0.0000 0.980 0.000 1.000
#> GSM647601 2 0.0000 0.980 0.000 1.000
#> GSM647603 2 0.0000 0.980 0.000 1.000
#> GSM647610 2 0.0376 0.978 0.004 0.996
#> GSM647611 2 0.0000 0.980 0.000 1.000
#> GSM647612 2 0.0376 0.980 0.004 0.996
#> GSM647614 2 0.0376 0.980 0.004 0.996
#> GSM647618 2 0.0000 0.980 0.000 1.000
#> GSM647629 2 0.0000 0.980 0.000 1.000
#> GSM647535 2 0.0376 0.980 0.004 0.996
#> GSM647563 2 0.0376 0.980 0.004 0.996
#> GSM647542 2 0.0376 0.980 0.004 0.996
#> GSM647543 2 0.0376 0.980 0.004 0.996
#> GSM647548 2 0.1184 0.969 0.016 0.984
#> GSM647554 2 0.0000 0.980 0.000 1.000
#> GSM647555 2 0.0376 0.980 0.004 0.996
#> GSM647559 2 0.0376 0.980 0.004 0.996
#> GSM647562 2 0.0000 0.980 0.000 1.000
#> GSM647564 1 0.9866 0.431 0.568 0.432
#> GSM647571 2 0.0376 0.980 0.004 0.996
#> GSM647584 2 0.0000 0.980 0.000 1.000
#> GSM647585 1 0.7376 0.726 0.792 0.208
#> GSM647586 2 0.0000 0.980 0.000 1.000
#> GSM647587 2 0.0000 0.980 0.000 1.000
#> GSM647588 2 0.0376 0.980 0.004 0.996
#> GSM647596 2 0.0000 0.980 0.000 1.000
#> GSM647602 1 0.9393 0.566 0.644 0.356
#> GSM647609 2 0.0000 0.980 0.000 1.000
#> GSM647620 2 0.0000 0.980 0.000 1.000
#> GSM647627 2 0.0000 0.980 0.000 1.000
#> GSM647628 2 0.0376 0.980 0.004 0.996
#> GSM647533 1 0.0376 0.863 0.996 0.004
#> GSM647536 1 0.0376 0.863 0.996 0.004
#> GSM647537 1 0.0376 0.863 0.996 0.004
#> GSM647606 1 0.0376 0.863 0.996 0.004
#> GSM647621 1 0.0000 0.862 1.000 0.000
#> GSM647626 1 0.0000 0.862 1.000 0.000
#> GSM647538 1 0.0376 0.863 0.996 0.004
#> GSM647575 1 0.0000 0.862 1.000 0.000
#> GSM647590 1 0.0000 0.862 1.000 0.000
#> GSM647605 1 0.0376 0.863 0.996 0.004
#> GSM647607 1 0.0000 0.862 1.000 0.000
#> GSM647608 1 0.0000 0.862 1.000 0.000
#> GSM647622 1 0.0376 0.863 0.996 0.004
#> GSM647623 1 0.0376 0.863 0.996 0.004
#> GSM647624 1 0.0376 0.863 0.996 0.004
#> GSM647625 1 0.0376 0.863 0.996 0.004
#> GSM647534 1 0.0376 0.863 0.996 0.004
#> GSM647539 1 0.0000 0.862 1.000 0.000
#> GSM647566 1 0.0000 0.862 1.000 0.000
#> GSM647589 1 0.0000 0.862 1.000 0.000
#> GSM647604 1 0.0376 0.863 0.996 0.004
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 3 0.3530 0.8158 0.068 0.032 0.900
#> GSM647574 3 0.3116 0.7726 0.108 0.000 0.892
#> GSM647577 3 0.3530 0.8158 0.068 0.032 0.900
#> GSM647547 3 0.3412 0.7612 0.124 0.000 0.876
#> GSM647552 2 0.3805 0.8813 0.024 0.884 0.092
#> GSM647553 3 0.2261 0.7870 0.068 0.000 0.932
#> GSM647565 3 0.7962 0.4461 0.072 0.352 0.576
#> GSM647545 2 0.0424 0.9180 0.000 0.992 0.008
#> GSM647549 2 0.0424 0.9180 0.000 0.992 0.008
#> GSM647550 2 0.5254 0.6124 0.000 0.736 0.264
#> GSM647560 2 0.2066 0.8897 0.000 0.940 0.060
#> GSM647617 3 0.3434 0.8150 0.064 0.032 0.904
#> GSM647528 2 0.0000 0.9192 0.000 1.000 0.000
#> GSM647529 1 0.1753 0.8313 0.952 0.000 0.048
#> GSM647531 2 0.1491 0.9179 0.016 0.968 0.016
#> GSM647540 3 0.6126 0.3840 0.000 0.400 0.600
#> GSM647541 2 0.0237 0.9188 0.000 0.996 0.004
#> GSM647546 3 0.3879 0.7440 0.000 0.152 0.848
#> GSM647557 2 0.1491 0.9179 0.016 0.968 0.016
#> GSM647561 2 0.0661 0.9192 0.008 0.988 0.004
#> GSM647567 3 0.4712 0.7525 0.044 0.108 0.848
#> GSM647568 2 0.4605 0.7164 0.000 0.796 0.204
#> GSM647570 2 0.0424 0.9180 0.000 0.992 0.008
#> GSM647573 3 0.5327 0.5970 0.272 0.000 0.728
#> GSM647576 2 0.6302 -0.0198 0.000 0.520 0.480
#> GSM647579 3 0.5988 0.4103 0.000 0.368 0.632
#> GSM647580 3 0.3530 0.8158 0.068 0.032 0.900
#> GSM647583 3 0.3530 0.8158 0.068 0.032 0.900
#> GSM647592 2 0.2846 0.9069 0.020 0.924 0.056
#> GSM647593 2 0.2846 0.9069 0.020 0.924 0.056
#> GSM647595 2 0.2846 0.9069 0.020 0.924 0.056
#> GSM647597 1 0.7992 0.3451 0.592 0.328 0.080
#> GSM647598 2 0.2384 0.9116 0.008 0.936 0.056
#> GSM647613 2 0.0237 0.9188 0.000 0.996 0.004
#> GSM647615 2 0.1964 0.8926 0.000 0.944 0.056
#> GSM647616 3 0.3530 0.8158 0.068 0.032 0.900
#> GSM647619 2 0.2846 0.9069 0.020 0.924 0.056
#> GSM647582 2 0.2384 0.9116 0.008 0.936 0.056
#> GSM647591 2 0.2982 0.9053 0.024 0.920 0.056
#> GSM647527 2 0.0000 0.9192 0.000 1.000 0.000
#> GSM647530 2 0.4443 0.8321 0.084 0.864 0.052
#> GSM647532 1 0.1753 0.8411 0.952 0.000 0.048
#> GSM647544 2 0.0424 0.9180 0.000 0.992 0.008
#> GSM647551 2 0.2846 0.9069 0.020 0.924 0.056
#> GSM647556 3 0.3530 0.8158 0.068 0.032 0.900
#> GSM647558 2 0.0424 0.9180 0.000 0.992 0.008
#> GSM647572 3 0.4235 0.7231 0.000 0.176 0.824
#> GSM647578 2 0.6111 0.2729 0.000 0.604 0.396
#> GSM647581 2 0.1015 0.9181 0.012 0.980 0.008
#> GSM647594 2 0.2846 0.9069 0.020 0.924 0.056
#> GSM647599 1 0.2796 0.8699 0.908 0.000 0.092
#> GSM647600 2 0.2550 0.9096 0.012 0.932 0.056
#> GSM647601 2 0.2384 0.9116 0.008 0.936 0.056
#> GSM647603 2 0.1643 0.9158 0.000 0.956 0.044
#> GSM647610 2 0.5406 0.7400 0.012 0.764 0.224
#> GSM647611 2 0.1964 0.9132 0.000 0.944 0.056
#> GSM647612 2 0.0424 0.9180 0.000 0.992 0.008
#> GSM647614 2 0.1860 0.8954 0.000 0.948 0.052
#> GSM647618 2 0.2550 0.9109 0.012 0.932 0.056
#> GSM647629 2 0.1643 0.9158 0.000 0.956 0.044
#> GSM647535 2 0.0000 0.9192 0.000 1.000 0.000
#> GSM647563 2 0.0424 0.9180 0.000 0.992 0.008
#> GSM647542 2 0.2261 0.8833 0.000 0.932 0.068
#> GSM647543 2 0.2261 0.8833 0.000 0.932 0.068
#> GSM647548 2 0.8071 0.1635 0.072 0.548 0.380
#> GSM647554 2 0.5098 0.6959 0.000 0.752 0.248
#> GSM647555 2 0.0892 0.9137 0.000 0.980 0.020
#> GSM647559 2 0.0237 0.9188 0.000 0.996 0.004
#> GSM647562 2 0.0848 0.9186 0.008 0.984 0.008
#> GSM647564 3 0.3234 0.7949 0.020 0.072 0.908
#> GSM647571 2 0.2261 0.8833 0.000 0.932 0.068
#> GSM647584 2 0.2200 0.9125 0.004 0.940 0.056
#> GSM647585 3 0.3530 0.8158 0.068 0.032 0.900
#> GSM647586 2 0.1529 0.9166 0.000 0.960 0.040
#> GSM647587 2 0.0424 0.9197 0.000 0.992 0.008
#> GSM647588 2 0.0237 0.9188 0.000 0.996 0.004
#> GSM647596 2 0.0747 0.9199 0.000 0.984 0.016
#> GSM647602 3 0.3530 0.8158 0.068 0.032 0.900
#> GSM647609 2 0.1964 0.9132 0.000 0.944 0.056
#> GSM647620 2 0.1643 0.9158 0.000 0.956 0.044
#> GSM647627 2 0.1643 0.9158 0.000 0.956 0.044
#> GSM647628 2 0.0424 0.9180 0.000 0.992 0.008
#> GSM647533 1 0.2796 0.8699 0.908 0.000 0.092
#> GSM647536 1 0.1643 0.8403 0.956 0.000 0.044
#> GSM647537 1 0.2796 0.8699 0.908 0.000 0.092
#> GSM647606 1 0.2625 0.8709 0.916 0.000 0.084
#> GSM647621 1 0.5785 0.5291 0.668 0.000 0.332
#> GSM647626 3 0.3192 0.7730 0.112 0.000 0.888
#> GSM647538 1 0.2537 0.8710 0.920 0.000 0.080
#> GSM647575 1 0.5835 0.4781 0.660 0.000 0.340
#> GSM647590 1 0.1964 0.8497 0.944 0.000 0.056
#> GSM647605 1 0.2356 0.8690 0.928 0.000 0.072
#> GSM647607 1 0.3619 0.7937 0.864 0.000 0.136
#> GSM647608 3 0.6280 0.1358 0.460 0.000 0.540
#> GSM647622 1 0.2796 0.8699 0.908 0.000 0.092
#> GSM647623 1 0.2796 0.8699 0.908 0.000 0.092
#> GSM647624 1 0.1964 0.8673 0.944 0.000 0.056
#> GSM647625 1 0.2796 0.8699 0.908 0.000 0.092
#> GSM647534 1 0.3573 0.8311 0.876 0.004 0.120
#> GSM647539 1 0.7150 0.4418 0.616 0.036 0.348
#> GSM647566 1 0.2878 0.8644 0.904 0.000 0.096
#> GSM647589 3 0.5968 0.4216 0.364 0.000 0.636
#> GSM647604 1 0.2356 0.8690 0.928 0.000 0.072
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 3 0.0469 0.8898 0.012 0.000 0.988 0.000
#> GSM647574 3 0.1297 0.8682 0.020 0.000 0.964 0.016
#> GSM647577 3 0.0657 0.8905 0.012 0.000 0.984 0.004
#> GSM647547 4 0.5590 0.2012 0.020 0.000 0.456 0.524
#> GSM647552 2 0.2654 0.6714 0.000 0.888 0.004 0.108
#> GSM647553 3 0.0657 0.8905 0.012 0.000 0.984 0.004
#> GSM647565 4 0.3236 0.4190 0.004 0.088 0.028 0.880
#> GSM647545 2 0.5329 0.7154 0.000 0.568 0.012 0.420
#> GSM647549 2 0.5320 0.7162 0.000 0.572 0.012 0.416
#> GSM647550 2 0.7683 0.5096 0.000 0.400 0.216 0.384
#> GSM647560 2 0.5526 0.7127 0.000 0.564 0.020 0.416
#> GSM647617 3 0.0524 0.8900 0.008 0.000 0.988 0.004
#> GSM647528 2 0.3933 0.7540 0.000 0.792 0.008 0.200
#> GSM647529 4 0.4948 0.2632 0.440 0.000 0.000 0.560
#> GSM647531 2 0.5016 0.7129 0.000 0.600 0.004 0.396
#> GSM647540 3 0.2706 0.7975 0.000 0.020 0.900 0.080
#> GSM647541 2 0.5231 0.7303 0.000 0.604 0.012 0.384
#> GSM647546 3 0.0817 0.8731 0.000 0.000 0.976 0.024
#> GSM647557 2 0.5028 0.7118 0.000 0.596 0.004 0.400
#> GSM647561 2 0.4877 0.7408 0.000 0.664 0.008 0.328
#> GSM647567 3 0.1843 0.8606 0.008 0.028 0.948 0.016
#> GSM647568 2 0.5550 0.7051 0.000 0.552 0.020 0.428
#> GSM647570 2 0.5337 0.7117 0.000 0.564 0.012 0.424
#> GSM647573 4 0.4205 0.5283 0.056 0.000 0.124 0.820
#> GSM647576 3 0.6292 0.3185 0.000 0.076 0.592 0.332
#> GSM647579 3 0.2816 0.8065 0.000 0.036 0.900 0.064
#> GSM647580 3 0.0657 0.8905 0.012 0.000 0.984 0.004
#> GSM647583 3 0.0657 0.8905 0.012 0.000 0.984 0.004
#> GSM647592 2 0.1118 0.7131 0.000 0.964 0.000 0.036
#> GSM647593 2 0.0707 0.7211 0.000 0.980 0.000 0.020
#> GSM647595 2 0.0707 0.7211 0.000 0.980 0.000 0.020
#> GSM647597 2 0.6677 0.0394 0.348 0.552 0.000 0.100
#> GSM647598 2 0.0000 0.7278 0.000 1.000 0.000 0.000
#> GSM647613 2 0.4955 0.7377 0.000 0.648 0.008 0.344
#> GSM647615 2 0.5550 0.7065 0.000 0.552 0.020 0.428
#> GSM647616 3 0.0657 0.8905 0.012 0.000 0.984 0.004
#> GSM647619 2 0.1022 0.7152 0.000 0.968 0.000 0.032
#> GSM647582 2 0.0817 0.7214 0.000 0.976 0.000 0.024
#> GSM647591 2 0.1474 0.7047 0.000 0.948 0.000 0.052
#> GSM647527 2 0.3933 0.7540 0.000 0.792 0.008 0.200
#> GSM647530 4 0.2973 0.4804 0.020 0.096 0.000 0.884
#> GSM647532 4 0.4967 0.2521 0.452 0.000 0.000 0.548
#> GSM647544 2 0.5279 0.7249 0.000 0.588 0.012 0.400
#> GSM647551 2 0.0895 0.7205 0.000 0.976 0.004 0.020
#> GSM647556 3 0.0469 0.8898 0.012 0.000 0.988 0.000
#> GSM647558 2 0.5345 0.7109 0.000 0.560 0.012 0.428
#> GSM647572 3 0.0921 0.8707 0.000 0.000 0.972 0.028
#> GSM647578 3 0.7839 -0.2968 0.000 0.352 0.384 0.264
#> GSM647581 2 0.5392 0.6869 0.000 0.528 0.012 0.460
#> GSM647594 2 0.0707 0.7211 0.000 0.980 0.000 0.020
#> GSM647599 1 0.1042 0.8551 0.972 0.000 0.020 0.008
#> GSM647600 2 0.0779 0.7208 0.000 0.980 0.004 0.016
#> GSM647601 2 0.0000 0.7278 0.000 1.000 0.000 0.000
#> GSM647603 2 0.2329 0.7325 0.000 0.916 0.012 0.072
#> GSM647610 2 0.3587 0.6308 0.000 0.856 0.104 0.040
#> GSM647611 2 0.1022 0.7271 0.000 0.968 0.000 0.032
#> GSM647612 2 0.5444 0.7096 0.000 0.560 0.016 0.424
#> GSM647614 2 0.5444 0.7096 0.000 0.560 0.016 0.424
#> GSM647618 2 0.1940 0.6912 0.000 0.924 0.000 0.076
#> GSM647629 2 0.2281 0.7399 0.000 0.904 0.000 0.096
#> GSM647535 2 0.4744 0.7501 0.000 0.704 0.012 0.284
#> GSM647563 2 0.5320 0.7158 0.000 0.572 0.012 0.416
#> GSM647542 2 0.5550 0.7051 0.000 0.552 0.020 0.428
#> GSM647543 2 0.5558 0.7041 0.000 0.548 0.020 0.432
#> GSM647548 4 0.2497 0.4875 0.020 0.040 0.016 0.924
#> GSM647554 2 0.5106 0.5264 0.000 0.720 0.240 0.040
#> GSM647555 2 0.5427 0.7144 0.000 0.568 0.016 0.416
#> GSM647559 2 0.4978 0.7448 0.000 0.664 0.012 0.324
#> GSM647562 2 0.4857 0.7436 0.000 0.668 0.008 0.324
#> GSM647564 3 0.0188 0.8867 0.000 0.000 0.996 0.004
#> GSM647571 2 0.5498 0.7197 0.000 0.576 0.020 0.404
#> GSM647584 2 0.0000 0.7278 0.000 1.000 0.000 0.000
#> GSM647585 3 0.0469 0.8898 0.012 0.000 0.988 0.000
#> GSM647586 2 0.1389 0.7400 0.000 0.952 0.000 0.048
#> GSM647587 2 0.3024 0.7497 0.000 0.852 0.000 0.148
#> GSM647588 2 0.5244 0.7288 0.000 0.600 0.012 0.388
#> GSM647596 2 0.2408 0.7488 0.000 0.896 0.000 0.104
#> GSM647602 3 0.0657 0.8905 0.012 0.000 0.984 0.004
#> GSM647609 2 0.0000 0.7278 0.000 1.000 0.000 0.000
#> GSM647620 2 0.0817 0.7334 0.000 0.976 0.000 0.024
#> GSM647627 2 0.0817 0.7334 0.000 0.976 0.000 0.024
#> GSM647628 2 0.5337 0.7117 0.000 0.564 0.012 0.424
#> GSM647533 1 0.0707 0.8605 0.980 0.000 0.020 0.000
#> GSM647536 4 0.4967 0.2521 0.452 0.000 0.000 0.548
#> GSM647537 1 0.0707 0.8605 0.980 0.000 0.020 0.000
#> GSM647606 1 0.0707 0.8605 0.980 0.000 0.020 0.000
#> GSM647621 4 0.6213 0.2491 0.464 0.000 0.052 0.484
#> GSM647626 3 0.0592 0.8872 0.016 0.000 0.984 0.000
#> GSM647538 1 0.1411 0.8490 0.960 0.000 0.020 0.020
#> GSM647575 4 0.6102 0.3328 0.420 0.000 0.048 0.532
#> GSM647590 1 0.4382 0.3760 0.704 0.000 0.000 0.296
#> GSM647605 1 0.0707 0.8605 0.980 0.000 0.020 0.000
#> GSM647607 1 0.5409 -0.2810 0.496 0.000 0.012 0.492
#> GSM647608 4 0.7494 0.4279 0.236 0.000 0.264 0.500
#> GSM647622 1 0.0707 0.8605 0.980 0.000 0.020 0.000
#> GSM647623 1 0.0707 0.8605 0.980 0.000 0.020 0.000
#> GSM647624 1 0.0000 0.8434 1.000 0.000 0.000 0.000
#> GSM647625 1 0.0707 0.8605 0.980 0.000 0.020 0.000
#> GSM647534 1 0.3942 0.6991 0.848 0.108 0.016 0.028
#> GSM647539 4 0.4706 0.4892 0.248 0.000 0.020 0.732
#> GSM647566 1 0.5291 0.3109 0.652 0.000 0.024 0.324
#> GSM647589 4 0.7268 0.4424 0.172 0.000 0.312 0.516
#> GSM647604 1 0.0707 0.8605 0.980 0.000 0.020 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.0000 0.9391 0.000 0.000 1.000 0.000 0.000
#> GSM647574 3 0.0693 0.9302 0.000 0.000 0.980 0.012 0.008
#> GSM647577 3 0.0162 0.9386 0.000 0.000 0.996 0.000 0.004
#> GSM647547 4 0.4004 0.6568 0.000 0.004 0.232 0.748 0.016
#> GSM647552 5 0.3075 0.7042 0.000 0.048 0.000 0.092 0.860
#> GSM647553 3 0.0451 0.9349 0.000 0.000 0.988 0.004 0.008
#> GSM647565 4 0.5507 0.2048 0.000 0.456 0.000 0.480 0.064
#> GSM647545 2 0.2153 0.8224 0.000 0.916 0.000 0.040 0.044
#> GSM647549 2 0.2153 0.8224 0.000 0.916 0.000 0.040 0.044
#> GSM647550 2 0.3241 0.7003 0.000 0.832 0.144 0.024 0.000
#> GSM647560 2 0.1211 0.8212 0.000 0.960 0.016 0.024 0.000
#> GSM647617 3 0.0000 0.9391 0.000 0.000 1.000 0.000 0.000
#> GSM647528 2 0.3940 0.6685 0.000 0.756 0.000 0.024 0.220
#> GSM647529 4 0.4373 0.7327 0.080 0.000 0.000 0.760 0.160
#> GSM647531 2 0.5091 0.6150 0.000 0.672 0.000 0.084 0.244
#> GSM647540 3 0.2299 0.8851 0.000 0.052 0.912 0.032 0.004
#> GSM647541 2 0.1211 0.8218 0.000 0.960 0.000 0.024 0.016
#> GSM647546 3 0.0000 0.9391 0.000 0.000 1.000 0.000 0.000
#> GSM647557 2 0.5164 0.6034 0.000 0.660 0.000 0.084 0.256
#> GSM647561 2 0.2864 0.7926 0.000 0.864 0.000 0.024 0.112
#> GSM647567 3 0.4796 0.6866 0.000 0.024 0.736 0.044 0.196
#> GSM647568 2 0.1018 0.8228 0.000 0.968 0.016 0.016 0.000
#> GSM647570 2 0.1300 0.8280 0.000 0.956 0.000 0.028 0.016
#> GSM647573 4 0.3345 0.7496 0.004 0.088 0.036 0.860 0.012
#> GSM647576 3 0.5117 0.4761 0.000 0.340 0.616 0.036 0.008
#> GSM647579 3 0.2813 0.8549 0.000 0.084 0.880 0.032 0.004
#> GSM647580 3 0.0000 0.9391 0.000 0.000 1.000 0.000 0.000
#> GSM647583 3 0.0162 0.9386 0.000 0.000 0.996 0.000 0.004
#> GSM647592 5 0.3280 0.8290 0.004 0.160 0.000 0.012 0.824
#> GSM647593 5 0.3231 0.8364 0.000 0.196 0.000 0.004 0.800
#> GSM647595 5 0.3143 0.8336 0.000 0.204 0.000 0.000 0.796
#> GSM647597 5 0.3100 0.6693 0.040 0.020 0.000 0.064 0.876
#> GSM647598 5 0.3336 0.8277 0.000 0.228 0.000 0.000 0.772
#> GSM647613 2 0.2362 0.8115 0.000 0.900 0.000 0.024 0.076
#> GSM647615 2 0.1588 0.8228 0.000 0.948 0.016 0.028 0.008
#> GSM647616 3 0.0162 0.9386 0.000 0.000 0.996 0.000 0.004
#> GSM647619 5 0.3048 0.8334 0.000 0.176 0.000 0.004 0.820
#> GSM647582 5 0.3993 0.8181 0.000 0.216 0.000 0.028 0.756
#> GSM647591 5 0.3238 0.8064 0.000 0.136 0.000 0.028 0.836
#> GSM647527 2 0.3940 0.6685 0.000 0.756 0.000 0.024 0.220
#> GSM647530 4 0.5074 0.6576 0.000 0.132 0.000 0.700 0.168
#> GSM647532 4 0.4247 0.7416 0.092 0.000 0.000 0.776 0.132
#> GSM647544 2 0.3146 0.7820 0.000 0.844 0.000 0.028 0.128
#> GSM647551 5 0.3779 0.8338 0.000 0.200 0.000 0.024 0.776
#> GSM647556 3 0.0290 0.9362 0.000 0.000 0.992 0.000 0.008
#> GSM647558 2 0.1568 0.8256 0.000 0.944 0.000 0.036 0.020
#> GSM647572 3 0.1522 0.9065 0.000 0.044 0.944 0.012 0.000
#> GSM647578 2 0.5072 0.4861 0.000 0.652 0.300 0.032 0.016
#> GSM647581 2 0.2983 0.7958 0.000 0.868 0.000 0.056 0.076
#> GSM647594 5 0.3123 0.8344 0.000 0.184 0.000 0.004 0.812
#> GSM647599 1 0.1211 0.9465 0.960 0.000 0.000 0.016 0.024
#> GSM647600 5 0.4042 0.8295 0.000 0.212 0.000 0.032 0.756
#> GSM647601 5 0.3305 0.8305 0.000 0.224 0.000 0.000 0.776
#> GSM647603 5 0.5273 0.5984 0.000 0.380 0.012 0.032 0.576
#> GSM647610 5 0.4837 0.7960 0.004 0.172 0.036 0.036 0.752
#> GSM647611 5 0.3487 0.8260 0.000 0.212 0.000 0.008 0.780
#> GSM647612 2 0.0693 0.8262 0.000 0.980 0.008 0.012 0.000
#> GSM647614 2 0.0912 0.8239 0.000 0.972 0.016 0.012 0.000
#> GSM647618 5 0.3622 0.7995 0.000 0.136 0.000 0.048 0.816
#> GSM647629 5 0.4886 0.5387 0.000 0.448 0.000 0.024 0.528
#> GSM647535 2 0.2511 0.7878 0.000 0.892 0.000 0.028 0.080
#> GSM647563 2 0.1300 0.8288 0.000 0.956 0.000 0.028 0.016
#> GSM647542 2 0.0912 0.8239 0.000 0.972 0.016 0.012 0.000
#> GSM647543 2 0.1405 0.8222 0.000 0.956 0.016 0.020 0.008
#> GSM647548 4 0.4588 0.6561 0.000 0.220 0.000 0.720 0.060
#> GSM647554 5 0.6971 0.5466 0.000 0.244 0.196 0.036 0.524
#> GSM647555 2 0.0693 0.8265 0.000 0.980 0.008 0.012 0.000
#> GSM647559 2 0.3427 0.7201 0.000 0.796 0.000 0.012 0.192
#> GSM647562 2 0.3993 0.6978 0.000 0.756 0.000 0.028 0.216
#> GSM647564 3 0.0000 0.9391 0.000 0.000 1.000 0.000 0.000
#> GSM647571 2 0.2374 0.8154 0.000 0.912 0.016 0.020 0.052
#> GSM647584 5 0.3305 0.8290 0.000 0.224 0.000 0.000 0.776
#> GSM647585 3 0.0290 0.9362 0.000 0.000 0.992 0.000 0.008
#> GSM647586 2 0.4046 0.5354 0.000 0.696 0.000 0.008 0.296
#> GSM647587 2 0.4292 0.6081 0.000 0.704 0.000 0.024 0.272
#> GSM647588 2 0.1661 0.8262 0.000 0.940 0.000 0.036 0.024
#> GSM647596 2 0.4047 0.4964 0.000 0.676 0.000 0.004 0.320
#> GSM647602 3 0.0000 0.9391 0.000 0.000 1.000 0.000 0.000
#> GSM647609 5 0.3550 0.8244 0.000 0.236 0.000 0.004 0.760
#> GSM647620 5 0.4436 0.5838 0.000 0.396 0.000 0.008 0.596
#> GSM647627 2 0.4538 -0.0559 0.000 0.540 0.000 0.008 0.452
#> GSM647628 2 0.0609 0.8279 0.000 0.980 0.000 0.020 0.000
#> GSM647533 1 0.1082 0.9593 0.964 0.000 0.000 0.008 0.028
#> GSM647536 4 0.4343 0.7399 0.096 0.000 0.000 0.768 0.136
#> GSM647537 1 0.1195 0.9579 0.960 0.000 0.000 0.012 0.028
#> GSM647606 1 0.0324 0.9694 0.992 0.000 0.000 0.004 0.004
#> GSM647621 4 0.4037 0.7279 0.188 0.000 0.008 0.776 0.028
#> GSM647626 3 0.0613 0.9326 0.004 0.000 0.984 0.008 0.004
#> GSM647538 1 0.3267 0.8305 0.844 0.000 0.000 0.112 0.044
#> GSM647575 4 0.3115 0.7616 0.120 0.012 0.004 0.856 0.008
#> GSM647590 4 0.5216 0.2546 0.436 0.000 0.000 0.520 0.044
#> GSM647605 1 0.0290 0.9679 0.992 0.000 0.000 0.000 0.008
#> GSM647607 4 0.3013 0.7415 0.160 0.000 0.000 0.832 0.008
#> GSM647608 4 0.3682 0.7561 0.088 0.000 0.064 0.836 0.012
#> GSM647622 1 0.0451 0.9696 0.988 0.000 0.000 0.004 0.008
#> GSM647623 1 0.0451 0.9696 0.988 0.000 0.000 0.004 0.008
#> GSM647624 1 0.0451 0.9696 0.988 0.000 0.000 0.004 0.008
#> GSM647625 1 0.0324 0.9700 0.992 0.000 0.000 0.004 0.004
#> GSM647534 5 0.6173 -0.1479 0.396 0.000 0.000 0.136 0.468
#> GSM647539 4 0.3572 0.7666 0.084 0.044 0.000 0.848 0.024
#> GSM647566 4 0.4639 0.6501 0.236 0.000 0.000 0.708 0.056
#> GSM647589 4 0.3804 0.7482 0.052 0.004 0.100 0.832 0.012
#> GSM647604 1 0.0162 0.9690 0.996 0.000 0.000 0.000 0.004
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.0000 0.92997 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647574 3 0.1007 0.90215 0.000 0.000 0.956 0.044 0.000 0.000
#> GSM647577 3 0.0000 0.92997 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647547 4 0.3546 0.66398 0.000 0.008 0.128 0.808 0.000 0.056
#> GSM647552 6 0.4161 0.12407 0.000 0.012 0.000 0.004 0.376 0.608
#> GSM647553 3 0.0547 0.91895 0.000 0.000 0.980 0.020 0.000 0.000
#> GSM647565 2 0.5128 0.32566 0.000 0.636 0.000 0.240 0.008 0.116
#> GSM647545 2 0.2866 0.70102 0.000 0.868 0.000 0.012 0.060 0.060
#> GSM647549 2 0.3076 0.69610 0.000 0.856 0.000 0.016 0.064 0.064
#> GSM647550 2 0.3638 0.63942 0.000 0.828 0.068 0.008 0.020 0.076
#> GSM647560 2 0.1707 0.71023 0.000 0.928 0.000 0.004 0.012 0.056
#> GSM647617 3 0.0000 0.92997 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647528 2 0.5034 0.31793 0.000 0.520 0.000 0.000 0.404 0.076
#> GSM647529 4 0.4997 0.43983 0.032 0.000 0.000 0.492 0.020 0.456
#> GSM647531 6 0.5932 0.11150 0.000 0.412 0.000 0.020 0.124 0.444
#> GSM647540 3 0.4298 0.74947 0.000 0.108 0.768 0.008 0.012 0.104
#> GSM647541 2 0.2537 0.69140 0.000 0.880 0.000 0.008 0.024 0.088
#> GSM647546 3 0.0000 0.92997 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647557 6 0.5850 0.15325 0.000 0.396 0.000 0.016 0.124 0.464
#> GSM647561 2 0.4906 0.56742 0.000 0.656 0.000 0.012 0.252 0.080
#> GSM647567 3 0.5388 0.46027 0.000 0.056 0.560 0.004 0.024 0.356
#> GSM647568 2 0.0820 0.72210 0.000 0.972 0.000 0.012 0.000 0.016
#> GSM647570 2 0.2538 0.72279 0.000 0.892 0.000 0.020 0.040 0.048
#> GSM647573 4 0.2465 0.71241 0.000 0.040 0.008 0.896 0.004 0.052
#> GSM647576 2 0.5663 0.12599 0.000 0.532 0.356 0.008 0.012 0.092
#> GSM647579 3 0.4634 0.71399 0.000 0.128 0.736 0.008 0.012 0.116
#> GSM647580 3 0.0000 0.92997 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647583 3 0.0000 0.92997 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647592 5 0.3837 0.61180 0.000 0.044 0.000 0.008 0.768 0.180
#> GSM647593 5 0.3548 0.66242 0.000 0.068 0.000 0.000 0.796 0.136
#> GSM647595 5 0.3587 0.66074 0.000 0.068 0.000 0.000 0.792 0.140
#> GSM647597 6 0.4413 -0.05898 0.012 0.000 0.000 0.008 0.488 0.492
#> GSM647598 5 0.2237 0.67908 0.000 0.068 0.000 0.000 0.896 0.036
#> GSM647613 2 0.4296 0.63621 0.000 0.732 0.000 0.012 0.196 0.060
#> GSM647615 2 0.1434 0.71804 0.000 0.948 0.000 0.020 0.008 0.024
#> GSM647616 3 0.0000 0.92997 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647619 5 0.3624 0.66289 0.000 0.060 0.000 0.000 0.784 0.156
#> GSM647582 5 0.4434 0.65078 0.000 0.116 0.000 0.000 0.712 0.172
#> GSM647591 5 0.3738 0.58556 0.000 0.040 0.000 0.000 0.752 0.208
#> GSM647527 2 0.5034 0.31793 0.000 0.520 0.000 0.000 0.404 0.076
#> GSM647530 6 0.6035 -0.31010 0.000 0.076 0.000 0.420 0.056 0.448
#> GSM647532 4 0.4603 0.50977 0.040 0.000 0.000 0.544 0.000 0.416
#> GSM647544 2 0.5114 0.57229 0.000 0.632 0.000 0.008 0.252 0.108
#> GSM647551 5 0.4200 0.62679 0.000 0.072 0.000 0.000 0.720 0.208
#> GSM647556 3 0.0260 0.92806 0.000 0.000 0.992 0.000 0.000 0.008
#> GSM647558 2 0.2665 0.70870 0.000 0.884 0.000 0.024 0.032 0.060
#> GSM647572 3 0.3042 0.82704 0.000 0.088 0.856 0.008 0.004 0.044
#> GSM647578 2 0.6013 0.36503 0.000 0.592 0.236 0.008 0.040 0.124
#> GSM647581 2 0.4035 0.62335 0.000 0.780 0.000 0.028 0.052 0.140
#> GSM647594 5 0.4005 0.62148 0.000 0.056 0.000 0.004 0.748 0.192
#> GSM647599 1 0.2476 0.87027 0.888 0.000 0.000 0.008 0.032 0.072
#> GSM647600 5 0.4513 0.61105 0.000 0.084 0.000 0.004 0.700 0.212
#> GSM647601 5 0.1444 0.68100 0.000 0.072 0.000 0.000 0.928 0.000
#> GSM647603 5 0.5687 0.45669 0.000 0.284 0.000 0.008 0.548 0.160
#> GSM647610 5 0.4777 0.53589 0.000 0.064 0.004 0.012 0.680 0.240
#> GSM647611 5 0.3167 0.65191 0.000 0.096 0.000 0.000 0.832 0.072
#> GSM647612 2 0.0870 0.72402 0.000 0.972 0.000 0.012 0.004 0.012
#> GSM647614 2 0.1078 0.72490 0.000 0.964 0.000 0.012 0.008 0.016
#> GSM647618 5 0.3652 0.60426 0.000 0.044 0.000 0.000 0.768 0.188
#> GSM647629 5 0.5805 0.30566 0.000 0.408 0.000 0.008 0.444 0.140
#> GSM647535 2 0.4624 0.60207 0.000 0.692 0.000 0.004 0.208 0.096
#> GSM647563 2 0.4141 0.67923 0.000 0.760 0.000 0.008 0.140 0.092
#> GSM647542 2 0.1078 0.72490 0.000 0.964 0.000 0.012 0.008 0.016
#> GSM647543 2 0.1148 0.71997 0.000 0.960 0.000 0.016 0.004 0.020
#> GSM647548 4 0.4920 0.41613 0.000 0.220 0.000 0.648 0.000 0.132
#> GSM647554 5 0.7579 0.18369 0.000 0.204 0.172 0.008 0.408 0.208
#> GSM647555 2 0.1340 0.72556 0.000 0.948 0.000 0.004 0.008 0.040
#> GSM647559 2 0.5057 0.51362 0.000 0.612 0.000 0.004 0.288 0.096
#> GSM647562 2 0.5200 0.48881 0.000 0.588 0.000 0.004 0.304 0.104
#> GSM647564 3 0.0146 0.92895 0.000 0.000 0.996 0.000 0.000 0.004
#> GSM647571 2 0.3419 0.69566 0.000 0.828 0.000 0.012 0.072 0.088
#> GSM647584 5 0.3206 0.67539 0.000 0.068 0.000 0.000 0.828 0.104
#> GSM647585 3 0.0260 0.92806 0.000 0.000 0.992 0.000 0.000 0.008
#> GSM647586 5 0.4950 0.26861 0.000 0.344 0.000 0.000 0.576 0.080
#> GSM647587 2 0.5261 0.12357 0.000 0.460 0.000 0.000 0.444 0.096
#> GSM647588 2 0.3452 0.71086 0.000 0.828 0.000 0.020 0.052 0.100
#> GSM647596 5 0.4356 0.32610 0.000 0.360 0.000 0.000 0.608 0.032
#> GSM647602 3 0.0000 0.92997 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647609 5 0.1501 0.68049 0.000 0.076 0.000 0.000 0.924 0.000
#> GSM647620 5 0.4340 0.56711 0.000 0.200 0.000 0.000 0.712 0.088
#> GSM647627 5 0.4382 0.54180 0.000 0.228 0.000 0.000 0.696 0.076
#> GSM647628 2 0.2467 0.72567 0.000 0.896 0.000 0.020 0.036 0.048
#> GSM647533 1 0.1908 0.89338 0.900 0.000 0.000 0.000 0.004 0.096
#> GSM647536 4 0.4660 0.50712 0.044 0.000 0.000 0.540 0.000 0.416
#> GSM647537 1 0.1700 0.90245 0.916 0.000 0.000 0.000 0.004 0.080
#> GSM647606 1 0.0000 0.93850 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647621 4 0.4242 0.69907 0.108 0.000 0.012 0.788 0.032 0.060
#> GSM647626 3 0.0622 0.92036 0.000 0.000 0.980 0.000 0.008 0.012
#> GSM647538 1 0.5177 0.63501 0.668 0.000 0.000 0.120 0.024 0.188
#> GSM647575 4 0.1601 0.74555 0.028 0.004 0.004 0.944 0.004 0.016
#> GSM647590 4 0.5547 0.53513 0.212 0.000 0.000 0.620 0.024 0.144
#> GSM647605 1 0.0146 0.93741 0.996 0.000 0.000 0.004 0.000 0.000
#> GSM647607 4 0.1693 0.74411 0.044 0.000 0.000 0.932 0.004 0.020
#> GSM647608 4 0.1168 0.74529 0.028 0.000 0.016 0.956 0.000 0.000
#> GSM647622 1 0.0260 0.93768 0.992 0.000 0.000 0.000 0.000 0.008
#> GSM647623 1 0.0260 0.93768 0.992 0.000 0.000 0.000 0.000 0.008
#> GSM647624 1 0.0260 0.93768 0.992 0.000 0.000 0.000 0.000 0.008
#> GSM647625 1 0.0000 0.93850 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647534 6 0.6877 -0.00385 0.260 0.000 0.000 0.120 0.140 0.480
#> GSM647539 4 0.2883 0.72750 0.020 0.008 0.000 0.872 0.020 0.080
#> GSM647566 4 0.5179 0.60012 0.104 0.000 0.000 0.660 0.024 0.212
#> GSM647589 4 0.1168 0.74272 0.016 0.000 0.028 0.956 0.000 0.000
#> GSM647604 1 0.0000 0.93850 1.000 0.000 0.000 0.000 0.000 0.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
#> Error in mat[ceiling(1:nr/h_ratio), ceiling(1:nc/w_ratio), drop = FALSE]: subscript out of bounds
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) development.stage(p) other(p) k
#> SD:kmeans 94 8.69e-13 0.617422 0.0927 2
#> SD:kmeans 92 1.06e-15 0.000678 0.1167 3
#> SD:kmeans 85 5.07e-15 0.013378 0.3715 4
#> SD:kmeans 96 7.75e-13 0.009664 0.1531 5
#> SD:kmeans 82 3.25e-12 0.016027 0.1226 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["SD", "skmeans"]
# you can also extract it by
# res = res_list["SD:skmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'SD' method.
#> Subgroups are detected by 'skmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 1.000 0.963 0.984 0.4946 0.506 0.506
#> 3 3 0.816 0.820 0.930 0.3056 0.745 0.540
#> 4 4 0.868 0.878 0.938 0.1627 0.788 0.475
#> 5 5 0.758 0.725 0.847 0.0581 0.929 0.730
#> 6 6 0.724 0.603 0.763 0.0445 0.931 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
#> GSM647569 1 0.0000 0.981 1.000 0.000
#> GSM647574 1 0.0000 0.981 1.000 0.000
#> GSM647577 1 0.0000 0.981 1.000 0.000
#> GSM647547 1 0.0000 0.981 1.000 0.000
#> GSM647552 1 0.7219 0.751 0.800 0.200
#> GSM647553 1 0.0000 0.981 1.000 0.000
#> GSM647565 1 0.7219 0.751 0.800 0.200
#> GSM647545 2 0.0000 0.985 0.000 1.000
#> GSM647549 2 0.0000 0.985 0.000 1.000
#> GSM647550 2 0.0000 0.985 0.000 1.000
#> GSM647560 2 0.0000 0.985 0.000 1.000
#> GSM647617 1 0.0000 0.981 1.000 0.000
#> GSM647528 2 0.0000 0.985 0.000 1.000
#> GSM647529 1 0.0000 0.981 1.000 0.000
#> GSM647531 2 0.0000 0.985 0.000 1.000
#> GSM647540 2 0.0672 0.978 0.008 0.992
#> GSM647541 2 0.0000 0.985 0.000 1.000
#> GSM647546 1 0.0000 0.981 1.000 0.000
#> GSM647557 2 0.0000 0.985 0.000 1.000
#> GSM647561 2 0.0000 0.985 0.000 1.000
#> GSM647567 1 0.0000 0.981 1.000 0.000
#> GSM647568 2 0.0000 0.985 0.000 1.000
#> GSM647570 2 0.0000 0.985 0.000 1.000
#> GSM647573 1 0.0000 0.981 1.000 0.000
#> GSM647576 2 0.0000 0.985 0.000 1.000
#> GSM647579 2 0.2423 0.947 0.040 0.960
#> GSM647580 1 0.0000 0.981 1.000 0.000
#> GSM647583 1 0.0000 0.981 1.000 0.000
#> GSM647592 2 0.0000 0.985 0.000 1.000
#> GSM647593 2 0.0000 0.985 0.000 1.000
#> GSM647595 2 0.0000 0.985 0.000 1.000
#> GSM647597 2 0.9552 0.376 0.376 0.624
#> GSM647598 2 0.0000 0.985 0.000 1.000
#> GSM647613 2 0.0000 0.985 0.000 1.000
#> GSM647615 2 0.0000 0.985 0.000 1.000
#> GSM647616 1 0.0000 0.981 1.000 0.000
#> GSM647619 2 0.0000 0.985 0.000 1.000
#> GSM647582 2 0.0000 0.985 0.000 1.000
#> GSM647591 2 0.0000 0.985 0.000 1.000
#> GSM647527 2 0.0000 0.985 0.000 1.000
#> GSM647530 2 0.0000 0.985 0.000 1.000
#> GSM647532 1 0.0000 0.981 1.000 0.000
#> GSM647544 2 0.0000 0.985 0.000 1.000
#> GSM647551 2 0.0000 0.985 0.000 1.000
#> GSM647556 1 0.0000 0.981 1.000 0.000
#> GSM647558 2 0.0000 0.985 0.000 1.000
#> GSM647572 1 0.0000 0.981 1.000 0.000
#> GSM647578 2 0.7056 0.761 0.192 0.808
#> GSM647581 2 0.0000 0.985 0.000 1.000
#> GSM647594 2 0.0000 0.985 0.000 1.000
#> GSM647599 1 0.0000 0.981 1.000 0.000
#> GSM647600 2 0.0000 0.985 0.000 1.000
#> GSM647601 2 0.0000 0.985 0.000 1.000
#> GSM647603 2 0.0000 0.985 0.000 1.000
#> GSM647610 2 0.7219 0.749 0.200 0.800
#> GSM647611 2 0.0000 0.985 0.000 1.000
#> GSM647612 2 0.0000 0.985 0.000 1.000
#> GSM647614 2 0.0000 0.985 0.000 1.000
#> GSM647618 2 0.0000 0.985 0.000 1.000
#> GSM647629 2 0.0000 0.985 0.000 1.000
#> GSM647535 2 0.0000 0.985 0.000 1.000
#> GSM647563 2 0.0000 0.985 0.000 1.000
#> GSM647542 2 0.0000 0.985 0.000 1.000
#> GSM647543 2 0.0000 0.985 0.000 1.000
#> GSM647548 1 0.9608 0.389 0.616 0.384
#> GSM647554 2 0.0000 0.985 0.000 1.000
#> GSM647555 2 0.0000 0.985 0.000 1.000
#> GSM647559 2 0.0000 0.985 0.000 1.000
#> GSM647562 2 0.0000 0.985 0.000 1.000
#> GSM647564 1 0.0000 0.981 1.000 0.000
#> GSM647571 2 0.0000 0.985 0.000 1.000
#> GSM647584 2 0.0000 0.985 0.000 1.000
#> GSM647585 1 0.0000 0.981 1.000 0.000
#> GSM647586 2 0.0000 0.985 0.000 1.000
#> GSM647587 2 0.0000 0.985 0.000 1.000
#> GSM647588 2 0.0000 0.985 0.000 1.000
#> GSM647596 2 0.0000 0.985 0.000 1.000
#> GSM647602 1 0.0000 0.981 1.000 0.000
#> GSM647609 2 0.0000 0.985 0.000 1.000
#> GSM647620 2 0.0000 0.985 0.000 1.000
#> GSM647627 2 0.0000 0.985 0.000 1.000
#> GSM647628 2 0.0000 0.985 0.000 1.000
#> GSM647533 1 0.0000 0.981 1.000 0.000
#> GSM647536 1 0.0000 0.981 1.000 0.000
#> GSM647537 1 0.0000 0.981 1.000 0.000
#> GSM647606 1 0.0000 0.981 1.000 0.000
#> GSM647621 1 0.0000 0.981 1.000 0.000
#> GSM647626 1 0.0000 0.981 1.000 0.000
#> GSM647538 1 0.0000 0.981 1.000 0.000
#> GSM647575 1 0.0000 0.981 1.000 0.000
#> GSM647590 1 0.0000 0.981 1.000 0.000
#> GSM647605 1 0.0000 0.981 1.000 0.000
#> GSM647607 1 0.0000 0.981 1.000 0.000
#> GSM647608 1 0.0000 0.981 1.000 0.000
#> GSM647622 1 0.0000 0.981 1.000 0.000
#> GSM647623 1 0.0000 0.981 1.000 0.000
#> GSM647624 1 0.0000 0.981 1.000 0.000
#> GSM647625 1 0.0000 0.981 1.000 0.000
#> GSM647534 1 0.0000 0.981 1.000 0.000
#> GSM647539 1 0.0000 0.981 1.000 0.000
#> GSM647566 1 0.0000 0.981 1.000 0.000
#> GSM647589 1 0.0000 0.981 1.000 0.000
#> GSM647604 1 0.0000 0.981 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 3 0.0592 0.8254 0.012 0.000 0.988
#> GSM647574 3 0.0592 0.8254 0.012 0.000 0.988
#> GSM647577 3 0.0592 0.8254 0.012 0.000 0.988
#> GSM647547 3 0.0592 0.8254 0.012 0.000 0.988
#> GSM647552 1 0.0592 0.9453 0.988 0.012 0.000
#> GSM647553 3 0.0592 0.8254 0.012 0.000 0.988
#> GSM647565 3 0.4178 0.7216 0.000 0.172 0.828
#> GSM647545 2 0.0592 0.9411 0.000 0.988 0.012
#> GSM647549 2 0.0592 0.9411 0.000 0.988 0.012
#> GSM647550 3 0.4235 0.6994 0.000 0.176 0.824
#> GSM647560 3 0.6286 0.2373 0.000 0.464 0.536
#> GSM647617 3 0.0592 0.8254 0.012 0.000 0.988
#> GSM647528 2 0.0237 0.9435 0.000 0.996 0.004
#> GSM647529 1 0.0000 0.9553 1.000 0.000 0.000
#> GSM647531 2 0.0237 0.9435 0.000 0.996 0.004
#> GSM647540 3 0.0000 0.8233 0.000 0.000 1.000
#> GSM647541 2 0.0592 0.9411 0.000 0.988 0.012
#> GSM647546 3 0.0237 0.8244 0.004 0.000 0.996
#> GSM647557 2 0.0237 0.9435 0.000 0.996 0.004
#> GSM647561 2 0.0237 0.9435 0.000 0.996 0.004
#> GSM647567 1 0.6308 0.1127 0.508 0.000 0.492
#> GSM647568 3 0.5016 0.6480 0.000 0.240 0.760
#> GSM647570 2 0.0592 0.9411 0.000 0.988 0.012
#> GSM647573 1 0.3619 0.8144 0.864 0.000 0.136
#> GSM647576 3 0.0000 0.8233 0.000 0.000 1.000
#> GSM647579 3 0.0237 0.8237 0.000 0.004 0.996
#> GSM647580 3 0.0592 0.8254 0.012 0.000 0.988
#> GSM647583 3 0.0592 0.8254 0.012 0.000 0.988
#> GSM647592 2 0.0000 0.9435 0.000 1.000 0.000
#> GSM647593 2 0.0000 0.9435 0.000 1.000 0.000
#> GSM647595 2 0.0000 0.9435 0.000 1.000 0.000
#> GSM647597 1 0.0592 0.9453 0.988 0.012 0.000
#> GSM647598 2 0.0000 0.9435 0.000 1.000 0.000
#> GSM647613 2 0.0237 0.9435 0.000 0.996 0.004
#> GSM647615 3 0.6302 0.1867 0.000 0.480 0.520
#> GSM647616 3 0.0592 0.8254 0.012 0.000 0.988
#> GSM647619 2 0.0000 0.9435 0.000 1.000 0.000
#> GSM647582 2 0.0000 0.9435 0.000 1.000 0.000
#> GSM647591 2 0.0000 0.9435 0.000 1.000 0.000
#> GSM647527 2 0.0237 0.9435 0.000 0.996 0.004
#> GSM647530 1 0.6180 0.4799 0.660 0.332 0.008
#> GSM647532 1 0.0000 0.9553 1.000 0.000 0.000
#> GSM647544 2 0.0592 0.9411 0.000 0.988 0.012
#> GSM647551 2 0.0000 0.9435 0.000 1.000 0.000
#> GSM647556 3 0.0592 0.8254 0.012 0.000 0.988
#> GSM647558 2 0.0592 0.9411 0.000 0.988 0.012
#> GSM647572 3 0.0237 0.8244 0.004 0.000 0.996
#> GSM647578 3 0.2356 0.7862 0.000 0.072 0.928
#> GSM647581 2 0.0592 0.9411 0.000 0.988 0.012
#> GSM647594 2 0.0000 0.9435 0.000 1.000 0.000
#> GSM647599 1 0.0000 0.9553 1.000 0.000 0.000
#> GSM647600 2 0.0000 0.9435 0.000 1.000 0.000
#> GSM647601 2 0.0000 0.9435 0.000 1.000 0.000
#> GSM647603 2 0.3551 0.8009 0.000 0.868 0.132
#> GSM647610 2 0.7129 0.5744 0.104 0.716 0.180
#> GSM647611 2 0.0000 0.9435 0.000 1.000 0.000
#> GSM647612 2 0.5058 0.6136 0.000 0.756 0.244
#> GSM647614 2 0.6286 -0.0252 0.000 0.536 0.464
#> GSM647618 2 0.0000 0.9435 0.000 1.000 0.000
#> GSM647629 2 0.0000 0.9435 0.000 1.000 0.000
#> GSM647535 2 0.0592 0.9411 0.000 0.988 0.012
#> GSM647563 2 0.0592 0.9411 0.000 0.988 0.012
#> GSM647542 3 0.6260 0.2831 0.000 0.448 0.552
#> GSM647543 3 0.6260 0.2831 0.000 0.448 0.552
#> GSM647548 3 0.7932 0.3741 0.064 0.384 0.552
#> GSM647554 2 0.6126 0.2458 0.000 0.600 0.400
#> GSM647555 2 0.6252 0.0477 0.000 0.556 0.444
#> GSM647559 2 0.0592 0.9411 0.000 0.988 0.012
#> GSM647562 2 0.0424 0.9424 0.000 0.992 0.008
#> GSM647564 3 0.0592 0.8254 0.012 0.000 0.988
#> GSM647571 3 0.6267 0.2723 0.000 0.452 0.548
#> GSM647584 2 0.0000 0.9435 0.000 1.000 0.000
#> GSM647585 3 0.0592 0.8254 0.012 0.000 0.988
#> GSM647586 2 0.0237 0.9435 0.000 0.996 0.004
#> GSM647587 2 0.0237 0.9435 0.000 0.996 0.004
#> GSM647588 2 0.0592 0.9411 0.000 0.988 0.012
#> GSM647596 2 0.0000 0.9435 0.000 1.000 0.000
#> GSM647602 3 0.0592 0.8254 0.012 0.000 0.988
#> GSM647609 2 0.0000 0.9435 0.000 1.000 0.000
#> GSM647620 2 0.0000 0.9435 0.000 1.000 0.000
#> GSM647627 2 0.0000 0.9435 0.000 1.000 0.000
#> GSM647628 2 0.0592 0.9411 0.000 0.988 0.012
#> GSM647533 1 0.0000 0.9553 1.000 0.000 0.000
#> GSM647536 1 0.0000 0.9553 1.000 0.000 0.000
#> GSM647537 1 0.0000 0.9553 1.000 0.000 0.000
#> GSM647606 1 0.0000 0.9553 1.000 0.000 0.000
#> GSM647621 1 0.0000 0.9553 1.000 0.000 0.000
#> GSM647626 3 0.6260 0.0150 0.448 0.000 0.552
#> GSM647538 1 0.0000 0.9553 1.000 0.000 0.000
#> GSM647575 1 0.0000 0.9553 1.000 0.000 0.000
#> GSM647590 1 0.0000 0.9553 1.000 0.000 0.000
#> GSM647605 1 0.0000 0.9553 1.000 0.000 0.000
#> GSM647607 1 0.0000 0.9553 1.000 0.000 0.000
#> GSM647608 1 0.0000 0.9553 1.000 0.000 0.000
#> GSM647622 1 0.0000 0.9553 1.000 0.000 0.000
#> GSM647623 1 0.0000 0.9553 1.000 0.000 0.000
#> GSM647624 1 0.0000 0.9553 1.000 0.000 0.000
#> GSM647625 1 0.0000 0.9553 1.000 0.000 0.000
#> GSM647534 1 0.0237 0.9522 0.996 0.004 0.000
#> GSM647539 1 0.0000 0.9553 1.000 0.000 0.000
#> GSM647566 1 0.0000 0.9553 1.000 0.000 0.000
#> GSM647589 1 0.2711 0.8716 0.912 0.000 0.088
#> GSM647604 1 0.0000 0.9553 1.000 0.000 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 3 0.0000 0.989 0.000 0.000 1.000 0.000
#> GSM647574 3 0.0000 0.989 0.000 0.000 1.000 0.000
#> GSM647577 3 0.0000 0.989 0.000 0.000 1.000 0.000
#> GSM647547 3 0.0469 0.980 0.000 0.000 0.988 0.012
#> GSM647552 2 0.4535 0.640 0.240 0.744 0.000 0.016
#> GSM647553 3 0.0000 0.989 0.000 0.000 1.000 0.000
#> GSM647565 4 0.0000 0.865 0.000 0.000 0.000 1.000
#> GSM647545 4 0.0592 0.864 0.000 0.016 0.000 0.984
#> GSM647549 4 0.0592 0.862 0.000 0.016 0.000 0.984
#> GSM647550 4 0.4679 0.476 0.000 0.000 0.352 0.648
#> GSM647560 4 0.2300 0.841 0.000 0.016 0.064 0.920
#> GSM647617 3 0.0000 0.989 0.000 0.000 1.000 0.000
#> GSM647528 4 0.4776 0.541 0.000 0.376 0.000 0.624
#> GSM647529 1 0.0336 0.982 0.992 0.008 0.000 0.000
#> GSM647531 4 0.2345 0.835 0.000 0.100 0.000 0.900
#> GSM647540 3 0.0000 0.989 0.000 0.000 1.000 0.000
#> GSM647541 4 0.1637 0.856 0.000 0.060 0.000 0.940
#> GSM647546 3 0.0000 0.989 0.000 0.000 1.000 0.000
#> GSM647557 4 0.3907 0.705 0.000 0.232 0.000 0.768
#> GSM647561 4 0.2408 0.839 0.000 0.104 0.000 0.896
#> GSM647567 3 0.1940 0.918 0.076 0.000 0.924 0.000
#> GSM647568 4 0.0469 0.867 0.000 0.012 0.000 0.988
#> GSM647570 4 0.0592 0.867 0.000 0.016 0.000 0.984
#> GSM647573 1 0.1637 0.932 0.940 0.000 0.000 0.060
#> GSM647576 3 0.0188 0.986 0.000 0.000 0.996 0.004
#> GSM647579 3 0.0000 0.989 0.000 0.000 1.000 0.000
#> GSM647580 3 0.0000 0.989 0.000 0.000 1.000 0.000
#> GSM647583 3 0.0000 0.989 0.000 0.000 1.000 0.000
#> GSM647592 2 0.0000 0.914 0.000 1.000 0.000 0.000
#> GSM647593 2 0.0336 0.915 0.000 0.992 0.000 0.008
#> GSM647595 2 0.0707 0.912 0.000 0.980 0.000 0.020
#> GSM647597 2 0.2401 0.843 0.092 0.904 0.000 0.004
#> GSM647598 2 0.0336 0.915 0.000 0.992 0.000 0.008
#> GSM647613 4 0.2149 0.847 0.000 0.088 0.000 0.912
#> GSM647615 4 0.0188 0.866 0.000 0.004 0.000 0.996
#> GSM647616 3 0.0000 0.989 0.000 0.000 1.000 0.000
#> GSM647619 2 0.0000 0.914 0.000 1.000 0.000 0.000
#> GSM647582 2 0.0000 0.914 0.000 1.000 0.000 0.000
#> GSM647591 2 0.0817 0.910 0.000 0.976 0.000 0.024
#> GSM647527 4 0.4776 0.541 0.000 0.376 0.000 0.624
#> GSM647530 4 0.4875 0.719 0.160 0.068 0.000 0.772
#> GSM647532 1 0.0000 0.988 1.000 0.000 0.000 0.000
#> GSM647544 4 0.4431 0.651 0.000 0.304 0.000 0.696
#> GSM647551 2 0.0336 0.915 0.000 0.992 0.000 0.008
#> GSM647556 3 0.0000 0.989 0.000 0.000 1.000 0.000
#> GSM647558 4 0.0188 0.864 0.000 0.004 0.000 0.996
#> GSM647572 3 0.0000 0.989 0.000 0.000 1.000 0.000
#> GSM647578 3 0.2973 0.870 0.000 0.020 0.884 0.096
#> GSM647581 4 0.0707 0.861 0.000 0.020 0.000 0.980
#> GSM647594 2 0.0707 0.912 0.000 0.980 0.000 0.020
#> GSM647599 1 0.0000 0.988 1.000 0.000 0.000 0.000
#> GSM647600 2 0.0336 0.915 0.000 0.992 0.000 0.008
#> GSM647601 2 0.0336 0.915 0.000 0.992 0.000 0.008
#> GSM647603 2 0.1284 0.903 0.000 0.964 0.012 0.024
#> GSM647610 2 0.1637 0.877 0.000 0.940 0.060 0.000
#> GSM647611 2 0.0592 0.910 0.000 0.984 0.000 0.016
#> GSM647612 4 0.0592 0.867 0.000 0.016 0.000 0.984
#> GSM647614 4 0.0592 0.867 0.000 0.016 0.000 0.984
#> GSM647618 2 0.0592 0.908 0.000 0.984 0.000 0.016
#> GSM647629 2 0.3486 0.750 0.000 0.812 0.000 0.188
#> GSM647535 4 0.4585 0.599 0.000 0.332 0.000 0.668
#> GSM647563 4 0.0592 0.867 0.000 0.016 0.000 0.984
#> GSM647542 4 0.0592 0.867 0.000 0.016 0.000 0.984
#> GSM647543 4 0.0188 0.866 0.000 0.004 0.000 0.996
#> GSM647548 4 0.0336 0.863 0.000 0.008 0.000 0.992
#> GSM647554 2 0.4855 0.314 0.000 0.600 0.400 0.000
#> GSM647555 4 0.0592 0.867 0.000 0.016 0.000 0.984
#> GSM647559 4 0.4761 0.556 0.000 0.372 0.000 0.628
#> GSM647562 4 0.4477 0.642 0.000 0.312 0.000 0.688
#> GSM647564 3 0.0000 0.989 0.000 0.000 1.000 0.000
#> GSM647571 4 0.2973 0.807 0.000 0.144 0.000 0.856
#> GSM647584 2 0.0336 0.915 0.000 0.992 0.000 0.008
#> GSM647585 3 0.0000 0.989 0.000 0.000 1.000 0.000
#> GSM647586 2 0.4697 0.318 0.000 0.644 0.000 0.356
#> GSM647587 4 0.4916 0.448 0.000 0.424 0.000 0.576
#> GSM647588 4 0.1637 0.851 0.000 0.060 0.000 0.940
#> GSM647596 2 0.3486 0.721 0.000 0.812 0.000 0.188
#> GSM647602 3 0.0000 0.989 0.000 0.000 1.000 0.000
#> GSM647609 2 0.0592 0.913 0.000 0.984 0.000 0.016
#> GSM647620 2 0.1022 0.905 0.000 0.968 0.000 0.032
#> GSM647627 2 0.1302 0.897 0.000 0.956 0.000 0.044
#> GSM647628 4 0.0592 0.867 0.000 0.016 0.000 0.984
#> GSM647533 1 0.0000 0.988 1.000 0.000 0.000 0.000
#> GSM647536 1 0.0000 0.988 1.000 0.000 0.000 0.000
#> GSM647537 1 0.0000 0.988 1.000 0.000 0.000 0.000
#> GSM647606 1 0.0000 0.988 1.000 0.000 0.000 0.000
#> GSM647621 1 0.0000 0.988 1.000 0.000 0.000 0.000
#> GSM647626 3 0.0000 0.989 0.000 0.000 1.000 0.000
#> GSM647538 1 0.0000 0.988 1.000 0.000 0.000 0.000
#> GSM647575 1 0.0000 0.988 1.000 0.000 0.000 0.000
#> GSM647590 1 0.0000 0.988 1.000 0.000 0.000 0.000
#> GSM647605 1 0.0000 0.988 1.000 0.000 0.000 0.000
#> GSM647607 1 0.0000 0.988 1.000 0.000 0.000 0.000
#> GSM647608 1 0.0000 0.988 1.000 0.000 0.000 0.000
#> GSM647622 1 0.0000 0.988 1.000 0.000 0.000 0.000
#> GSM647623 1 0.0000 0.988 1.000 0.000 0.000 0.000
#> GSM647624 1 0.0000 0.988 1.000 0.000 0.000 0.000
#> GSM647625 1 0.0000 0.988 1.000 0.000 0.000 0.000
#> GSM647534 1 0.3172 0.802 0.840 0.160 0.000 0.000
#> GSM647539 1 0.0921 0.964 0.972 0.000 0.000 0.028
#> GSM647566 1 0.0000 0.988 1.000 0.000 0.000 0.000
#> GSM647589 1 0.0336 0.982 0.992 0.000 0.008 0.000
#> GSM647604 1 0.0000 0.988 1.000 0.000 0.000 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.0000 0.9647 0.000 0.000 1.000 0.000 0.000
#> GSM647574 3 0.0609 0.9515 0.000 0.000 0.980 0.020 0.000
#> GSM647577 3 0.0000 0.9647 0.000 0.000 1.000 0.000 0.000
#> GSM647547 4 0.4586 0.3267 0.004 0.016 0.336 0.644 0.000
#> GSM647552 1 0.6350 0.2967 0.524 0.000 0.000 0.236 0.240
#> GSM647553 3 0.0000 0.9647 0.000 0.000 1.000 0.000 0.000
#> GSM647565 4 0.3534 0.4420 0.000 0.256 0.000 0.744 0.000
#> GSM647545 2 0.3039 0.7506 0.000 0.836 0.000 0.152 0.012
#> GSM647549 2 0.3163 0.7438 0.000 0.824 0.000 0.164 0.012
#> GSM647550 2 0.4338 0.5520 0.000 0.696 0.280 0.024 0.000
#> GSM647560 2 0.1549 0.7782 0.000 0.944 0.016 0.040 0.000
#> GSM647617 3 0.0000 0.9647 0.000 0.000 1.000 0.000 0.000
#> GSM647528 2 0.4972 0.5243 0.000 0.620 0.000 0.044 0.336
#> GSM647529 1 0.3689 0.5811 0.740 0.000 0.000 0.256 0.004
#> GSM647531 4 0.6513 -0.3291 0.000 0.384 0.000 0.424 0.192
#> GSM647540 3 0.0579 0.9564 0.000 0.008 0.984 0.008 0.000
#> GSM647541 2 0.0703 0.7813 0.000 0.976 0.000 0.024 0.000
#> GSM647546 3 0.0000 0.9647 0.000 0.000 1.000 0.000 0.000
#> GSM647557 2 0.6738 0.2769 0.000 0.376 0.000 0.368 0.256
#> GSM647561 2 0.5478 0.6874 0.000 0.656 0.000 0.180 0.164
#> GSM647567 3 0.4313 0.6138 0.260 0.000 0.716 0.008 0.016
#> GSM647568 2 0.1197 0.7807 0.000 0.952 0.000 0.048 0.000
#> GSM647570 2 0.1197 0.7823 0.000 0.952 0.000 0.048 0.000
#> GSM647573 4 0.4456 0.5628 0.320 0.020 0.000 0.660 0.000
#> GSM647576 3 0.1764 0.9036 0.000 0.064 0.928 0.008 0.000
#> GSM647579 3 0.0579 0.9564 0.000 0.008 0.984 0.008 0.000
#> GSM647580 3 0.0000 0.9647 0.000 0.000 1.000 0.000 0.000
#> GSM647583 3 0.0000 0.9647 0.000 0.000 1.000 0.000 0.000
#> GSM647592 5 0.0963 0.8647 0.000 0.000 0.000 0.036 0.964
#> GSM647593 5 0.1444 0.8699 0.000 0.012 0.000 0.040 0.948
#> GSM647595 5 0.1444 0.8699 0.000 0.012 0.000 0.040 0.948
#> GSM647597 1 0.6158 0.2951 0.528 0.000 0.000 0.156 0.316
#> GSM647598 5 0.2036 0.8681 0.000 0.024 0.000 0.056 0.920
#> GSM647613 2 0.5074 0.7109 0.000 0.700 0.000 0.168 0.132
#> GSM647615 2 0.2286 0.7633 0.000 0.888 0.000 0.108 0.004
#> GSM647616 3 0.0000 0.9647 0.000 0.000 1.000 0.000 0.000
#> GSM647619 5 0.1121 0.8660 0.000 0.000 0.000 0.044 0.956
#> GSM647582 5 0.1197 0.8620 0.000 0.000 0.000 0.048 0.952
#> GSM647591 5 0.2561 0.8000 0.000 0.000 0.000 0.144 0.856
#> GSM647527 2 0.4972 0.5243 0.000 0.620 0.000 0.044 0.336
#> GSM647530 4 0.1990 0.5263 0.004 0.040 0.000 0.928 0.028
#> GSM647532 4 0.4300 0.1274 0.476 0.000 0.000 0.524 0.000
#> GSM647544 2 0.5059 0.6207 0.000 0.668 0.000 0.076 0.256
#> GSM647551 5 0.1444 0.8699 0.000 0.012 0.000 0.040 0.948
#> GSM647556 3 0.0000 0.9647 0.000 0.000 1.000 0.000 0.000
#> GSM647558 2 0.2605 0.7493 0.000 0.852 0.000 0.148 0.000
#> GSM647572 3 0.0000 0.9647 0.000 0.000 1.000 0.000 0.000
#> GSM647578 3 0.2824 0.8308 0.000 0.116 0.864 0.020 0.000
#> GSM647581 2 0.3318 0.7328 0.000 0.800 0.000 0.192 0.008
#> GSM647594 5 0.1444 0.8699 0.000 0.012 0.000 0.040 0.948
#> GSM647599 1 0.0000 0.8345 1.000 0.000 0.000 0.000 0.000
#> GSM647600 5 0.1522 0.8696 0.000 0.012 0.000 0.044 0.944
#> GSM647601 5 0.0912 0.8698 0.000 0.012 0.000 0.016 0.972
#> GSM647603 5 0.3780 0.7724 0.000 0.132 0.000 0.060 0.808
#> GSM647610 5 0.2015 0.8546 0.020 0.004 0.008 0.036 0.932
#> GSM647611 5 0.2193 0.8467 0.000 0.028 0.000 0.060 0.912
#> GSM647612 2 0.1043 0.7816 0.000 0.960 0.000 0.040 0.000
#> GSM647614 2 0.1043 0.7816 0.000 0.960 0.000 0.040 0.000
#> GSM647618 5 0.3163 0.8136 0.000 0.012 0.000 0.164 0.824
#> GSM647629 5 0.3642 0.7039 0.000 0.232 0.000 0.008 0.760
#> GSM647535 2 0.4689 0.6107 0.000 0.688 0.000 0.048 0.264
#> GSM647563 2 0.2036 0.7767 0.000 0.920 0.000 0.056 0.024
#> GSM647542 2 0.0963 0.7817 0.000 0.964 0.000 0.036 0.000
#> GSM647543 2 0.2230 0.7588 0.000 0.884 0.000 0.116 0.000
#> GSM647548 4 0.2605 0.5377 0.000 0.148 0.000 0.852 0.000
#> GSM647554 5 0.4994 0.3129 0.000 0.016 0.396 0.012 0.576
#> GSM647555 2 0.0794 0.7808 0.000 0.972 0.000 0.028 0.000
#> GSM647559 2 0.5062 0.5988 0.000 0.656 0.000 0.068 0.276
#> GSM647562 2 0.5040 0.6050 0.000 0.660 0.000 0.068 0.272
#> GSM647564 3 0.0000 0.9647 0.000 0.000 1.000 0.000 0.000
#> GSM647571 2 0.3798 0.7375 0.000 0.808 0.000 0.064 0.128
#> GSM647584 5 0.1444 0.8699 0.000 0.012 0.000 0.040 0.948
#> GSM647585 3 0.0000 0.9647 0.000 0.000 1.000 0.000 0.000
#> GSM647586 5 0.5091 0.2598 0.000 0.372 0.000 0.044 0.584
#> GSM647587 2 0.5439 0.4229 0.000 0.560 0.000 0.068 0.372
#> GSM647588 2 0.3888 0.7496 0.000 0.800 0.000 0.136 0.064
#> GSM647596 5 0.3400 0.8027 0.000 0.136 0.000 0.036 0.828
#> GSM647602 3 0.0000 0.9647 0.000 0.000 1.000 0.000 0.000
#> GSM647609 5 0.0912 0.8698 0.000 0.012 0.000 0.016 0.972
#> GSM647620 5 0.3608 0.7670 0.000 0.148 0.000 0.040 0.812
#> GSM647627 5 0.3848 0.7361 0.000 0.172 0.000 0.040 0.788
#> GSM647628 2 0.1121 0.7828 0.000 0.956 0.000 0.044 0.000
#> GSM647533 1 0.0000 0.8345 1.000 0.000 0.000 0.000 0.000
#> GSM647536 1 0.3684 0.5362 0.720 0.000 0.000 0.280 0.000
#> GSM647537 1 0.0000 0.8345 1.000 0.000 0.000 0.000 0.000
#> GSM647606 1 0.0000 0.8345 1.000 0.000 0.000 0.000 0.000
#> GSM647621 1 0.4182 -0.0842 0.600 0.000 0.000 0.400 0.000
#> GSM647626 3 0.1270 0.9207 0.052 0.000 0.948 0.000 0.000
#> GSM647538 1 0.0000 0.8345 1.000 0.000 0.000 0.000 0.000
#> GSM647575 4 0.4161 0.5353 0.392 0.000 0.000 0.608 0.000
#> GSM647590 1 0.2179 0.7175 0.888 0.000 0.000 0.112 0.000
#> GSM647605 1 0.0000 0.8345 1.000 0.000 0.000 0.000 0.000
#> GSM647607 4 0.4210 0.5061 0.412 0.000 0.000 0.588 0.000
#> GSM647608 4 0.4161 0.5353 0.392 0.000 0.000 0.608 0.000
#> GSM647622 1 0.0000 0.8345 1.000 0.000 0.000 0.000 0.000
#> GSM647623 1 0.0000 0.8345 1.000 0.000 0.000 0.000 0.000
#> GSM647624 1 0.0000 0.8345 1.000 0.000 0.000 0.000 0.000
#> GSM647625 1 0.0000 0.8345 1.000 0.000 0.000 0.000 0.000
#> GSM647534 1 0.1041 0.8050 0.964 0.000 0.000 0.004 0.032
#> GSM647539 4 0.4138 0.5406 0.384 0.000 0.000 0.616 0.000
#> GSM647566 1 0.1544 0.7747 0.932 0.000 0.000 0.068 0.000
#> GSM647589 4 0.4403 0.5404 0.384 0.000 0.008 0.608 0.000
#> GSM647604 1 0.0000 0.8345 1.000 0.000 0.000 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.0000 0.91652 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647574 3 0.2300 0.80195 0.000 0.000 0.856 0.144 0.000 0.000
#> GSM647577 3 0.0000 0.91652 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647547 4 0.3301 0.62389 0.000 0.024 0.188 0.788 0.000 0.000
#> GSM647552 5 0.7461 0.08049 0.280 0.000 0.000 0.160 0.364 0.196
#> GSM647553 3 0.0713 0.90119 0.000 0.000 0.972 0.028 0.000 0.000
#> GSM647565 4 0.3956 0.40890 0.000 0.292 0.000 0.684 0.000 0.024
#> GSM647545 2 0.4141 0.59069 0.000 0.740 0.000 0.040 0.016 0.204
#> GSM647549 2 0.4859 0.52538 0.000 0.656 0.000 0.084 0.008 0.252
#> GSM647550 2 0.6475 0.22894 0.000 0.464 0.268 0.032 0.000 0.236
#> GSM647560 2 0.2094 0.68507 0.000 0.908 0.008 0.016 0.000 0.068
#> GSM647617 3 0.0000 0.91652 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647528 6 0.5605 0.58197 0.000 0.244 0.000 0.000 0.212 0.544
#> GSM647529 1 0.5451 0.19955 0.532 0.000 0.000 0.328 0.000 0.140
#> GSM647531 6 0.7342 0.13292 0.000 0.140 0.000 0.224 0.232 0.404
#> GSM647540 3 0.3069 0.83860 0.000 0.020 0.852 0.032 0.000 0.096
#> GSM647541 2 0.3658 0.58250 0.000 0.752 0.000 0.032 0.000 0.216
#> GSM647546 3 0.0000 0.91652 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647557 6 0.7367 0.11029 0.000 0.140 0.000 0.212 0.256 0.392
#> GSM647561 6 0.6906 0.05961 0.000 0.352 0.000 0.060 0.220 0.368
#> GSM647567 3 0.5582 0.63433 0.160 0.000 0.664 0.020 0.024 0.132
#> GSM647568 2 0.0000 0.70940 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647570 2 0.0891 0.71018 0.000 0.968 0.000 0.008 0.000 0.024
#> GSM647573 4 0.3523 0.73302 0.180 0.040 0.000 0.780 0.000 0.000
#> GSM647576 3 0.3822 0.74735 0.000 0.180 0.772 0.016 0.000 0.032
#> GSM647579 3 0.3005 0.84263 0.000 0.016 0.856 0.036 0.000 0.092
#> GSM647580 3 0.0000 0.91652 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647583 3 0.0000 0.91652 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647592 5 0.1663 0.64542 0.000 0.000 0.000 0.000 0.912 0.088
#> GSM647593 5 0.0000 0.65436 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM647595 5 0.0260 0.65326 0.000 0.000 0.000 0.000 0.992 0.008
#> GSM647597 5 0.6978 -0.00344 0.368 0.000 0.000 0.096 0.380 0.156
#> GSM647598 5 0.2527 0.58821 0.000 0.000 0.000 0.000 0.832 0.168
#> GSM647613 2 0.6312 0.06982 0.000 0.460 0.000 0.032 0.164 0.344
#> GSM647615 2 0.0909 0.70474 0.000 0.968 0.000 0.012 0.000 0.020
#> GSM647616 3 0.0000 0.91652 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647619 5 0.0458 0.65559 0.000 0.000 0.000 0.000 0.984 0.016
#> GSM647582 5 0.3383 0.53318 0.000 0.004 0.000 0.000 0.728 0.268
#> GSM647591 5 0.2197 0.61528 0.000 0.000 0.000 0.056 0.900 0.044
#> GSM647527 6 0.5605 0.58197 0.000 0.244 0.000 0.000 0.212 0.544
#> GSM647530 4 0.3969 0.46925 0.000 0.012 0.000 0.700 0.012 0.276
#> GSM647532 4 0.5346 0.33464 0.324 0.000 0.000 0.548 0.000 0.128
#> GSM647544 6 0.4808 0.54780 0.000 0.272 0.000 0.000 0.092 0.636
#> GSM647551 5 0.1204 0.64529 0.000 0.000 0.000 0.000 0.944 0.056
#> GSM647556 3 0.0000 0.91652 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647558 2 0.4299 0.58162 0.000 0.720 0.000 0.092 0.000 0.188
#> GSM647572 3 0.0436 0.91263 0.000 0.004 0.988 0.004 0.000 0.004
#> GSM647578 3 0.5824 0.51765 0.000 0.156 0.592 0.032 0.000 0.220
#> GSM647581 2 0.5250 0.48070 0.000 0.612 0.000 0.116 0.008 0.264
#> GSM647594 5 0.0972 0.65327 0.008 0.000 0.000 0.000 0.964 0.028
#> GSM647599 1 0.0000 0.89745 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647600 5 0.1411 0.64216 0.000 0.000 0.000 0.004 0.936 0.060
#> GSM647601 5 0.2631 0.58055 0.000 0.000 0.000 0.000 0.820 0.180
#> GSM647603 6 0.5665 -0.08169 0.000 0.108 0.000 0.012 0.420 0.460
#> GSM647610 5 0.4321 0.51003 0.028 0.000 0.004 0.004 0.668 0.296
#> GSM647611 5 0.4039 0.31861 0.000 0.008 0.000 0.000 0.568 0.424
#> GSM647612 2 0.0260 0.70937 0.000 0.992 0.000 0.000 0.000 0.008
#> GSM647614 2 0.0363 0.70857 0.000 0.988 0.000 0.000 0.000 0.012
#> GSM647618 5 0.5077 0.27648 0.000 0.000 0.000 0.080 0.516 0.404
#> GSM647629 5 0.5431 0.38441 0.000 0.228 0.000 0.024 0.628 0.120
#> GSM647535 6 0.5888 0.42881 0.000 0.320 0.000 0.016 0.148 0.516
#> GSM647563 2 0.4097 -0.06821 0.000 0.500 0.000 0.000 0.008 0.492
#> GSM647542 2 0.0937 0.70011 0.000 0.960 0.000 0.000 0.000 0.040
#> GSM647543 2 0.0603 0.70658 0.000 0.980 0.000 0.004 0.000 0.016
#> GSM647548 4 0.1951 0.66361 0.000 0.076 0.000 0.908 0.000 0.016
#> GSM647554 5 0.6820 0.16244 0.000 0.016 0.344 0.036 0.428 0.176
#> GSM647555 2 0.2402 0.63868 0.000 0.868 0.000 0.012 0.000 0.120
#> GSM647559 6 0.4873 0.55608 0.000 0.268 0.000 0.000 0.100 0.632
#> GSM647562 6 0.4845 0.53876 0.000 0.280 0.000 0.000 0.092 0.628
#> GSM647564 3 0.0000 0.91652 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647571 2 0.3927 0.26363 0.000 0.644 0.000 0.000 0.012 0.344
#> GSM647584 5 0.0547 0.65507 0.000 0.000 0.000 0.000 0.980 0.020
#> GSM647585 3 0.0000 0.91652 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647586 6 0.5495 0.48510 0.000 0.156 0.000 0.000 0.304 0.540
#> GSM647587 6 0.5053 0.58998 0.000 0.204 0.000 0.000 0.160 0.636
#> GSM647588 2 0.5865 0.26522 0.000 0.472 0.000 0.080 0.040 0.408
#> GSM647596 5 0.4173 0.43540 0.000 0.044 0.000 0.000 0.688 0.268
#> GSM647602 3 0.0000 0.91652 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647609 5 0.2697 0.57451 0.000 0.000 0.000 0.000 0.812 0.188
#> GSM647620 5 0.4870 0.04110 0.000 0.048 0.000 0.004 0.512 0.436
#> GSM647627 5 0.4984 -0.04793 0.000 0.068 0.000 0.000 0.492 0.440
#> GSM647628 2 0.1644 0.69153 0.000 0.920 0.000 0.004 0.000 0.076
#> GSM647533 1 0.0000 0.89745 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647536 1 0.5456 0.10830 0.500 0.000 0.000 0.372 0.000 0.128
#> GSM647537 1 0.0000 0.89745 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647606 1 0.0000 0.89745 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647621 4 0.3867 0.32727 0.488 0.000 0.000 0.512 0.000 0.000
#> GSM647626 3 0.2340 0.78762 0.148 0.000 0.852 0.000 0.000 0.000
#> GSM647538 1 0.0363 0.88995 0.988 0.000 0.000 0.012 0.000 0.000
#> GSM647575 4 0.3101 0.73271 0.244 0.000 0.000 0.756 0.000 0.000
#> GSM647590 1 0.2135 0.76454 0.872 0.000 0.000 0.128 0.000 0.000
#> GSM647605 1 0.0000 0.89745 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647607 4 0.3175 0.72358 0.256 0.000 0.000 0.744 0.000 0.000
#> GSM647608 4 0.3126 0.73019 0.248 0.000 0.000 0.752 0.000 0.000
#> GSM647622 1 0.0000 0.89745 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647623 1 0.0000 0.89745 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647624 1 0.0000 0.89745 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647625 1 0.0000 0.89745 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647534 1 0.1346 0.86342 0.952 0.000 0.000 0.008 0.024 0.016
#> GSM647539 4 0.3101 0.73271 0.244 0.000 0.000 0.756 0.000 0.000
#> GSM647566 1 0.1814 0.80465 0.900 0.000 0.000 0.100 0.000 0.000
#> GSM647589 4 0.3368 0.73400 0.232 0.000 0.012 0.756 0.000 0.000
#> GSM647604 1 0.0000 0.89745 1.000 0.000 0.000 0.000 0.000 0.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
#> Error in mat[ceiling(1:nr/h_ratio), ceiling(1:nc/w_ratio), drop = FALSE]: subscript out of bounds
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) development.stage(p) other(p) k
#> SD:skmeans 101 9.92e-09 0.01162 0.7049 2
#> SD:skmeans 91 1.21e-14 0.00145 0.0483 3
#> SD:skmeans 99 8.15e-16 0.00833 0.1534 4
#> SD:skmeans 92 2.44e-13 0.00586 0.1533 5
#> SD:skmeans 76 8.20e-11 0.07606 0.2738 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["SD", "pam"]
# you can also extract it by
# res = res_list["SD:pam"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'SD' method.
#> Subgroups are detected by 'pam' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 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 0.608 0.920 0.947 0.4577 0.525 0.525
#> 3 3 0.678 0.795 0.792 0.3762 0.753 0.552
#> 4 4 0.742 0.829 0.900 0.1536 0.930 0.789
#> 5 5 0.608 0.600 0.784 0.0589 0.820 0.460
#> 6 6 0.675 0.642 0.807 0.0581 0.876 0.525
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
#> GSM647569 1 0.6048 0.913 0.852 0.148
#> GSM647574 1 0.6048 0.913 0.852 0.148
#> GSM647577 1 0.6048 0.913 0.852 0.148
#> GSM647547 1 0.6048 0.913 0.852 0.148
#> GSM647552 1 0.8813 0.721 0.700 0.300
#> GSM647553 1 0.6048 0.913 0.852 0.148
#> GSM647565 2 0.0938 0.960 0.012 0.988
#> GSM647545 2 0.0000 0.970 0.000 1.000
#> GSM647549 2 0.0000 0.970 0.000 1.000
#> GSM647550 2 0.0938 0.960 0.012 0.988
#> GSM647560 2 0.0376 0.967 0.004 0.996
#> GSM647617 1 0.6048 0.913 0.852 0.148
#> GSM647528 2 0.0000 0.970 0.000 1.000
#> GSM647529 2 0.6048 0.820 0.148 0.852
#> GSM647531 2 0.0000 0.970 0.000 1.000
#> GSM647540 1 0.6343 0.902 0.840 0.160
#> GSM647541 2 0.0000 0.970 0.000 1.000
#> GSM647546 1 0.6048 0.913 0.852 0.148
#> GSM647557 2 0.0000 0.970 0.000 1.000
#> GSM647561 2 0.0000 0.970 0.000 1.000
#> GSM647567 1 0.6048 0.913 0.852 0.148
#> GSM647568 2 0.0938 0.960 0.012 0.988
#> GSM647570 2 0.0000 0.970 0.000 1.000
#> GSM647573 2 0.1184 0.957 0.016 0.984
#> GSM647576 1 0.6048 0.913 0.852 0.148
#> GSM647579 1 0.6048 0.913 0.852 0.148
#> GSM647580 1 0.6048 0.913 0.852 0.148
#> GSM647583 1 0.6048 0.913 0.852 0.148
#> GSM647592 2 0.0000 0.970 0.000 1.000
#> GSM647593 2 0.0000 0.970 0.000 1.000
#> GSM647595 2 0.0000 0.970 0.000 1.000
#> GSM647597 2 0.5946 0.825 0.144 0.856
#> GSM647598 2 0.0000 0.970 0.000 1.000
#> GSM647613 2 0.0000 0.970 0.000 1.000
#> GSM647615 2 0.0000 0.970 0.000 1.000
#> GSM647616 1 0.6048 0.913 0.852 0.148
#> GSM647619 2 0.0000 0.970 0.000 1.000
#> GSM647582 2 0.0000 0.970 0.000 1.000
#> GSM647591 2 0.0000 0.970 0.000 1.000
#> GSM647527 2 0.0000 0.970 0.000 1.000
#> GSM647530 2 0.0000 0.970 0.000 1.000
#> GSM647532 2 0.9944 0.219 0.456 0.544
#> GSM647544 2 0.0000 0.970 0.000 1.000
#> GSM647551 2 0.0000 0.970 0.000 1.000
#> GSM647556 1 0.6048 0.913 0.852 0.148
#> GSM647558 2 0.0000 0.970 0.000 1.000
#> GSM647572 1 0.6048 0.913 0.852 0.148
#> GSM647578 2 0.8327 0.590 0.264 0.736
#> GSM647581 2 0.0000 0.970 0.000 1.000
#> GSM647594 2 0.0000 0.970 0.000 1.000
#> GSM647599 1 0.0000 0.895 1.000 0.000
#> GSM647600 1 0.9000 0.693 0.684 0.316
#> GSM647601 2 0.0000 0.970 0.000 1.000
#> GSM647603 2 0.0000 0.970 0.000 1.000
#> GSM647610 2 0.5629 0.821 0.132 0.868
#> GSM647611 2 0.0000 0.970 0.000 1.000
#> GSM647612 2 0.0000 0.970 0.000 1.000
#> GSM647614 2 0.0000 0.970 0.000 1.000
#> GSM647618 2 0.0000 0.970 0.000 1.000
#> GSM647629 2 0.0376 0.967 0.004 0.996
#> GSM647535 2 0.0000 0.970 0.000 1.000
#> GSM647563 2 0.0000 0.970 0.000 1.000
#> GSM647542 2 0.0000 0.970 0.000 1.000
#> GSM647543 2 0.0000 0.970 0.000 1.000
#> GSM647548 2 0.0000 0.970 0.000 1.000
#> GSM647554 2 0.6343 0.780 0.160 0.840
#> GSM647555 2 0.0000 0.970 0.000 1.000
#> GSM647559 2 0.0000 0.970 0.000 1.000
#> GSM647562 2 0.0000 0.970 0.000 1.000
#> GSM647564 1 0.6048 0.913 0.852 0.148
#> GSM647571 2 0.0000 0.970 0.000 1.000
#> GSM647584 2 0.0000 0.970 0.000 1.000
#> GSM647585 1 0.6048 0.913 0.852 0.148
#> GSM647586 2 0.0000 0.970 0.000 1.000
#> GSM647587 2 0.0000 0.970 0.000 1.000
#> GSM647588 2 0.0000 0.970 0.000 1.000
#> GSM647596 2 0.0000 0.970 0.000 1.000
#> GSM647602 1 0.6048 0.913 0.852 0.148
#> GSM647609 2 0.0000 0.970 0.000 1.000
#> GSM647620 2 0.0000 0.970 0.000 1.000
#> GSM647627 2 0.0000 0.970 0.000 1.000
#> GSM647628 2 0.0000 0.970 0.000 1.000
#> GSM647533 1 0.0000 0.895 1.000 0.000
#> GSM647536 2 0.6048 0.820 0.148 0.852
#> GSM647537 1 0.0000 0.895 1.000 0.000
#> GSM647606 1 0.0000 0.895 1.000 0.000
#> GSM647621 1 0.0000 0.895 1.000 0.000
#> GSM647626 1 0.0000 0.895 1.000 0.000
#> GSM647538 1 0.0000 0.895 1.000 0.000
#> GSM647575 2 0.3274 0.920 0.060 0.940
#> GSM647590 1 0.0000 0.895 1.000 0.000
#> GSM647605 1 0.0000 0.895 1.000 0.000
#> GSM647607 2 0.6343 0.811 0.160 0.840
#> GSM647608 1 0.4815 0.910 0.896 0.104
#> GSM647622 1 0.0000 0.895 1.000 0.000
#> GSM647623 1 0.0000 0.895 1.000 0.000
#> GSM647624 1 0.0000 0.895 1.000 0.000
#> GSM647625 1 0.0000 0.895 1.000 0.000
#> GSM647534 1 0.1414 0.896 0.980 0.020
#> GSM647539 2 0.0000 0.970 0.000 1.000
#> GSM647566 1 0.1414 0.896 0.980 0.020
#> GSM647589 1 0.5294 0.912 0.880 0.120
#> GSM647604 1 0.0000 0.895 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 3 0.0000 0.853 0.000 0.000 1.000
#> GSM647574 3 0.0000 0.853 0.000 0.000 1.000
#> GSM647577 3 0.0000 0.853 0.000 0.000 1.000
#> GSM647547 1 0.6244 0.223 0.560 0.000 0.440
#> GSM647552 3 0.4504 0.653 0.196 0.000 0.804
#> GSM647553 3 0.0000 0.853 0.000 0.000 1.000
#> GSM647565 1 0.1289 0.848 0.968 0.000 0.032
#> GSM647545 1 0.0000 0.871 1.000 0.000 0.000
#> GSM647549 1 0.0000 0.871 1.000 0.000 0.000
#> GSM647550 1 0.2066 0.816 0.940 0.000 0.060
#> GSM647560 1 0.0592 0.866 0.988 0.000 0.012
#> GSM647617 3 0.0000 0.853 0.000 0.000 1.000
#> GSM647528 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647529 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647531 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647540 3 0.0000 0.853 0.000 0.000 1.000
#> GSM647541 1 0.0000 0.871 1.000 0.000 0.000
#> GSM647546 3 0.0000 0.853 0.000 0.000 1.000
#> GSM647557 2 0.6302 0.823 0.480 0.520 0.000
#> GSM647561 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647567 3 0.0237 0.850 0.004 0.000 0.996
#> GSM647568 1 0.0237 0.872 0.996 0.000 0.004
#> GSM647570 1 0.0000 0.871 1.000 0.000 0.000
#> GSM647573 1 0.2878 0.774 0.904 0.000 0.096
#> GSM647576 3 0.0000 0.853 0.000 0.000 1.000
#> GSM647579 3 0.0000 0.853 0.000 0.000 1.000
#> GSM647580 3 0.0000 0.853 0.000 0.000 1.000
#> GSM647583 3 0.0000 0.853 0.000 0.000 1.000
#> GSM647592 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647593 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647595 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647597 2 0.6204 0.868 0.424 0.576 0.000
#> GSM647598 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647613 1 0.0237 0.865 0.996 0.004 0.000
#> GSM647615 1 0.1411 0.844 0.964 0.000 0.036
#> GSM647616 3 0.0000 0.853 0.000 0.000 1.000
#> GSM647619 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647582 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647591 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647527 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647530 1 0.0000 0.871 1.000 0.000 0.000
#> GSM647532 1 0.7640 0.397 0.592 0.352 0.056
#> GSM647544 1 0.0000 0.871 1.000 0.000 0.000
#> GSM647551 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647556 3 0.0000 0.853 0.000 0.000 1.000
#> GSM647558 1 0.0000 0.871 1.000 0.000 0.000
#> GSM647572 3 0.0000 0.853 0.000 0.000 1.000
#> GSM647578 1 0.7013 0.229 0.548 0.020 0.432
#> GSM647581 1 0.0000 0.871 1.000 0.000 0.000
#> GSM647594 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647599 3 0.6180 0.741 0.000 0.416 0.584
#> GSM647600 2 0.9003 0.604 0.240 0.560 0.200
#> GSM647601 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647603 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647610 2 0.8889 0.662 0.276 0.560 0.164
#> GSM647611 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647612 1 0.0237 0.872 0.996 0.000 0.004
#> GSM647614 1 0.0237 0.872 0.996 0.000 0.004
#> GSM647618 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647629 2 0.6451 0.881 0.436 0.560 0.004
#> GSM647535 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647563 1 0.0000 0.871 1.000 0.000 0.000
#> GSM647542 1 0.0237 0.872 0.996 0.000 0.004
#> GSM647543 1 0.0237 0.872 0.996 0.000 0.004
#> GSM647548 1 0.0237 0.872 0.996 0.000 0.004
#> GSM647554 2 0.9009 0.606 0.236 0.560 0.204
#> GSM647555 1 0.0237 0.872 0.996 0.000 0.004
#> GSM647559 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647562 1 0.0000 0.871 1.000 0.000 0.000
#> GSM647564 3 0.0000 0.853 0.000 0.000 1.000
#> GSM647571 1 0.0237 0.872 0.996 0.000 0.004
#> GSM647584 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647585 3 0.0000 0.853 0.000 0.000 1.000
#> GSM647586 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647587 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647588 2 0.6260 0.875 0.448 0.552 0.000
#> GSM647596 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647602 3 0.0000 0.853 0.000 0.000 1.000
#> GSM647609 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647620 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647627 2 0.6244 0.886 0.440 0.560 0.000
#> GSM647628 1 0.0000 0.871 1.000 0.000 0.000
#> GSM647533 3 0.6244 0.737 0.000 0.440 0.560
#> GSM647536 2 0.5416 0.360 0.100 0.820 0.080
#> GSM647537 3 0.6244 0.737 0.000 0.440 0.560
#> GSM647606 3 0.6244 0.737 0.000 0.440 0.560
#> GSM647621 3 0.5216 0.785 0.000 0.260 0.740
#> GSM647626 3 0.0000 0.853 0.000 0.000 1.000
#> GSM647538 3 0.6244 0.737 0.000 0.440 0.560
#> GSM647575 1 0.2749 0.800 0.924 0.064 0.012
#> GSM647590 3 0.6244 0.737 0.000 0.440 0.560
#> GSM647605 3 0.6286 0.721 0.000 0.464 0.536
#> GSM647607 1 0.7546 0.333 0.560 0.396 0.044
#> GSM647608 3 0.0000 0.853 0.000 0.000 1.000
#> GSM647622 3 0.6244 0.737 0.000 0.440 0.560
#> GSM647623 3 0.6244 0.737 0.000 0.440 0.560
#> GSM647624 3 0.6244 0.737 0.000 0.440 0.560
#> GSM647625 3 0.6244 0.737 0.000 0.440 0.560
#> GSM647534 2 0.4931 0.181 0.032 0.828 0.140
#> GSM647539 1 0.0237 0.872 0.996 0.000 0.004
#> GSM647566 2 0.9989 -0.474 0.316 0.356 0.328
#> GSM647589 3 0.0000 0.853 0.000 0.000 1.000
#> GSM647604 3 0.6280 0.724 0.000 0.460 0.540
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 3 0.0000 0.9407 0.000 0.000 1.000 0.000
#> GSM647574 3 0.0000 0.9407 0.000 0.000 1.000 0.000
#> GSM647577 3 0.0000 0.9407 0.000 0.000 1.000 0.000
#> GSM647547 4 0.4981 0.1920 0.000 0.000 0.464 0.536
#> GSM647552 3 0.7300 0.3737 0.000 0.276 0.528 0.196
#> GSM647553 3 0.0921 0.9267 0.000 0.000 0.972 0.028
#> GSM647565 4 0.0376 0.8042 0.000 0.004 0.004 0.992
#> GSM647545 4 0.2149 0.8310 0.000 0.088 0.000 0.912
#> GSM647549 4 0.2081 0.8312 0.000 0.084 0.000 0.916
#> GSM647550 4 0.3910 0.8378 0.000 0.156 0.024 0.820
#> GSM647560 4 0.3444 0.8396 0.000 0.184 0.000 0.816
#> GSM647617 3 0.0000 0.9407 0.000 0.000 1.000 0.000
#> GSM647528 2 0.0921 0.9155 0.000 0.972 0.000 0.028
#> GSM647529 2 0.2813 0.8684 0.080 0.896 0.000 0.024
#> GSM647531 2 0.3123 0.8159 0.000 0.844 0.000 0.156
#> GSM647540 3 0.1389 0.9091 0.000 0.000 0.952 0.048
#> GSM647541 4 0.3356 0.8392 0.000 0.176 0.000 0.824
#> GSM647546 3 0.0188 0.9391 0.000 0.000 0.996 0.004
#> GSM647557 2 0.4730 0.5238 0.000 0.636 0.000 0.364
#> GSM647561 2 0.3311 0.8125 0.000 0.828 0.000 0.172
#> GSM647567 3 0.1151 0.9211 0.000 0.024 0.968 0.008
#> GSM647568 4 0.1118 0.8242 0.000 0.036 0.000 0.964
#> GSM647570 4 0.3837 0.8308 0.000 0.224 0.000 0.776
#> GSM647573 4 0.1398 0.7923 0.000 0.004 0.040 0.956
#> GSM647576 3 0.3528 0.7610 0.000 0.000 0.808 0.192
#> GSM647579 3 0.1389 0.9091 0.000 0.000 0.952 0.048
#> GSM647580 3 0.0000 0.9407 0.000 0.000 1.000 0.000
#> GSM647583 3 0.0000 0.9407 0.000 0.000 1.000 0.000
#> GSM647592 2 0.0000 0.9159 0.000 1.000 0.000 0.000
#> GSM647593 2 0.0000 0.9159 0.000 1.000 0.000 0.000
#> GSM647595 2 0.0188 0.9155 0.000 0.996 0.000 0.004
#> GSM647597 2 0.0000 0.9159 0.000 1.000 0.000 0.000
#> GSM647598 2 0.0188 0.9165 0.000 0.996 0.000 0.004
#> GSM647613 4 0.3649 0.8275 0.000 0.204 0.000 0.796
#> GSM647615 4 0.1706 0.8190 0.000 0.036 0.016 0.948
#> GSM647616 3 0.0000 0.9407 0.000 0.000 1.000 0.000
#> GSM647619 2 0.0000 0.9159 0.000 1.000 0.000 0.000
#> GSM647582 2 0.0817 0.9166 0.000 0.976 0.000 0.024
#> GSM647591 2 0.2921 0.8165 0.000 0.860 0.000 0.140
#> GSM647527 2 0.0921 0.9155 0.000 0.972 0.000 0.028
#> GSM647530 4 0.2149 0.8310 0.000 0.088 0.000 0.912
#> GSM647532 4 0.7117 0.2412 0.180 0.000 0.264 0.556
#> GSM647544 4 0.3873 0.8281 0.000 0.228 0.000 0.772
#> GSM647551 2 0.2973 0.8157 0.000 0.856 0.000 0.144
#> GSM647556 3 0.0000 0.9407 0.000 0.000 1.000 0.000
#> GSM647558 4 0.1211 0.8258 0.000 0.040 0.000 0.960
#> GSM647572 3 0.0188 0.9391 0.000 0.000 0.996 0.004
#> GSM647578 4 0.6280 0.5407 0.000 0.084 0.304 0.612
#> GSM647581 4 0.2081 0.8312 0.000 0.084 0.000 0.916
#> GSM647594 2 0.0000 0.9159 0.000 1.000 0.000 0.000
#> GSM647599 1 0.4866 0.2993 0.596 0.000 0.404 0.000
#> GSM647600 2 0.2089 0.8777 0.000 0.932 0.020 0.048
#> GSM647601 2 0.0188 0.9165 0.000 0.996 0.000 0.004
#> GSM647603 2 0.0921 0.9155 0.000 0.972 0.000 0.028
#> GSM647610 2 0.2131 0.8819 0.000 0.932 0.036 0.032
#> GSM647611 2 0.0817 0.9164 0.000 0.976 0.000 0.024
#> GSM647612 4 0.3356 0.8392 0.000 0.176 0.000 0.824
#> GSM647614 4 0.3837 0.8308 0.000 0.224 0.000 0.776
#> GSM647618 2 0.0707 0.9169 0.000 0.980 0.000 0.020
#> GSM647629 2 0.1474 0.8899 0.000 0.948 0.000 0.052
#> GSM647535 2 0.0921 0.9155 0.000 0.972 0.000 0.028
#> GSM647563 4 0.3873 0.8281 0.000 0.228 0.000 0.772
#> GSM647542 4 0.3837 0.8308 0.000 0.224 0.000 0.776
#> GSM647543 4 0.1211 0.8258 0.000 0.040 0.000 0.960
#> GSM647548 4 0.1474 0.8203 0.000 0.052 0.000 0.948
#> GSM647554 2 0.4205 0.7900 0.000 0.820 0.124 0.056
#> GSM647555 4 0.3356 0.8392 0.000 0.176 0.000 0.824
#> GSM647559 2 0.1302 0.9052 0.000 0.956 0.000 0.044
#> GSM647562 4 0.3873 0.8281 0.000 0.228 0.000 0.772
#> GSM647564 3 0.0000 0.9407 0.000 0.000 1.000 0.000
#> GSM647571 4 0.3837 0.8308 0.000 0.224 0.000 0.776
#> GSM647584 2 0.0000 0.9159 0.000 1.000 0.000 0.000
#> GSM647585 3 0.0000 0.9407 0.000 0.000 1.000 0.000
#> GSM647586 2 0.0921 0.9155 0.000 0.972 0.000 0.028
#> GSM647587 2 0.0921 0.9155 0.000 0.972 0.000 0.028
#> GSM647588 2 0.4643 0.6066 0.000 0.656 0.000 0.344
#> GSM647596 2 0.0817 0.9166 0.000 0.976 0.000 0.024
#> GSM647602 3 0.0000 0.9407 0.000 0.000 1.000 0.000
#> GSM647609 2 0.0469 0.9171 0.000 0.988 0.000 0.012
#> GSM647620 2 0.0817 0.9164 0.000 0.976 0.000 0.024
#> GSM647627 2 0.0817 0.9164 0.000 0.976 0.000 0.024
#> GSM647628 4 0.3873 0.8281 0.000 0.228 0.000 0.772
#> GSM647533 1 0.0188 0.9095 0.996 0.000 0.000 0.004
#> GSM647536 1 0.4656 0.7528 0.784 0.056 0.000 0.160
#> GSM647537 1 0.0000 0.9107 1.000 0.000 0.000 0.000
#> GSM647606 1 0.0000 0.9107 1.000 0.000 0.000 0.000
#> GSM647621 3 0.5025 0.5901 0.252 0.000 0.716 0.032
#> GSM647626 3 0.0000 0.9407 0.000 0.000 1.000 0.000
#> GSM647538 1 0.0188 0.9095 0.996 0.000 0.000 0.004
#> GSM647575 4 0.3796 0.7945 0.096 0.056 0.000 0.848
#> GSM647590 1 0.0188 0.9095 0.996 0.000 0.000 0.004
#> GSM647605 1 0.0000 0.9107 1.000 0.000 0.000 0.000
#> GSM647607 4 0.4464 0.6638 0.208 0.000 0.024 0.768
#> GSM647608 3 0.1118 0.9219 0.000 0.000 0.964 0.036
#> GSM647622 1 0.0000 0.9107 1.000 0.000 0.000 0.000
#> GSM647623 1 0.0000 0.9107 1.000 0.000 0.000 0.000
#> GSM647624 1 0.0000 0.9107 1.000 0.000 0.000 0.000
#> GSM647625 1 0.0000 0.9107 1.000 0.000 0.000 0.000
#> GSM647534 2 0.7081 0.0289 0.416 0.472 0.108 0.004
#> GSM647539 4 0.0188 0.8057 0.000 0.004 0.000 0.996
#> GSM647566 1 0.7704 0.2122 0.432 0.000 0.336 0.232
#> GSM647589 3 0.1022 0.9240 0.000 0.000 0.968 0.032
#> GSM647604 1 0.0000 0.9107 1.000 0.000 0.000 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.2773 0.76804 0.000 0.000 0.836 0.164 0.000
#> GSM647574 3 0.4182 0.46449 0.000 0.000 0.600 0.400 0.000
#> GSM647577 3 0.2773 0.76804 0.000 0.000 0.836 0.164 0.000
#> GSM647547 4 0.3689 0.41306 0.000 0.004 0.256 0.740 0.000
#> GSM647552 5 0.7289 -0.00145 0.000 0.196 0.364 0.036 0.404
#> GSM647553 3 0.4161 0.48461 0.000 0.000 0.608 0.392 0.000
#> GSM647565 4 0.4341 0.62907 0.000 0.364 0.000 0.628 0.008
#> GSM647545 2 0.0865 0.68116 0.000 0.972 0.000 0.004 0.024
#> GSM647549 2 0.1493 0.67249 0.000 0.948 0.000 0.028 0.024
#> GSM647550 2 0.6388 0.59304 0.000 0.628 0.200 0.060 0.112
#> GSM647560 2 0.5768 0.63925 0.000 0.672 0.164 0.024 0.140
#> GSM647617 3 0.2773 0.76804 0.000 0.000 0.836 0.164 0.000
#> GSM647528 2 0.4161 0.55210 0.000 0.608 0.000 0.000 0.392
#> GSM647529 4 0.5800 0.03448 0.008 0.068 0.000 0.488 0.436
#> GSM647531 5 0.4948 0.21708 0.000 0.436 0.000 0.028 0.536
#> GSM647540 3 0.2661 0.69740 0.000 0.056 0.888 0.056 0.000
#> GSM647541 2 0.6427 0.61431 0.000 0.632 0.164 0.060 0.144
#> GSM647546 3 0.2813 0.76691 0.000 0.000 0.832 0.168 0.000
#> GSM647557 2 0.3961 0.59082 0.000 0.760 0.000 0.028 0.212
#> GSM647561 2 0.3508 0.56708 0.000 0.748 0.000 0.000 0.252
#> GSM647567 3 0.4232 0.63427 0.000 0.032 0.804 0.048 0.116
#> GSM647568 2 0.1410 0.65173 0.000 0.940 0.000 0.060 0.000
#> GSM647570 2 0.2930 0.72529 0.000 0.832 0.000 0.004 0.164
#> GSM647573 4 0.4168 0.68716 0.000 0.200 0.044 0.756 0.000
#> GSM647576 3 0.4670 0.55936 0.000 0.200 0.724 0.076 0.000
#> GSM647579 3 0.2661 0.69740 0.000 0.056 0.888 0.056 0.000
#> GSM647580 3 0.2773 0.76804 0.000 0.000 0.836 0.164 0.000
#> GSM647583 3 0.2773 0.76804 0.000 0.000 0.836 0.164 0.000
#> GSM647592 5 0.0000 0.69167 0.000 0.000 0.000 0.000 1.000
#> GSM647593 5 0.0000 0.69167 0.000 0.000 0.000 0.000 1.000
#> GSM647595 5 0.0162 0.69097 0.000 0.004 0.000 0.000 0.996
#> GSM647597 5 0.0000 0.69167 0.000 0.000 0.000 0.000 1.000
#> GSM647598 5 0.0703 0.68374 0.000 0.024 0.000 0.000 0.976
#> GSM647613 2 0.4843 0.55871 0.000 0.660 0.000 0.048 0.292
#> GSM647615 2 0.3962 0.51353 0.000 0.800 0.112 0.088 0.000
#> GSM647616 3 0.2773 0.76804 0.000 0.000 0.836 0.164 0.000
#> GSM647619 5 0.0000 0.69167 0.000 0.000 0.000 0.000 1.000
#> GSM647582 2 0.4307 0.33909 0.000 0.504 0.000 0.000 0.496
#> GSM647591 5 0.2516 0.56470 0.000 0.140 0.000 0.000 0.860
#> GSM647527 2 0.4161 0.55210 0.000 0.608 0.000 0.000 0.392
#> GSM647530 2 0.1836 0.67005 0.000 0.932 0.000 0.032 0.036
#> GSM647532 4 0.4034 0.64895 0.040 0.128 0.004 0.812 0.016
#> GSM647544 2 0.3231 0.71909 0.000 0.800 0.000 0.004 0.196
#> GSM647551 5 0.2605 0.56687 0.000 0.148 0.000 0.000 0.852
#> GSM647556 3 0.0000 0.76141 0.000 0.000 1.000 0.000 0.000
#> GSM647558 2 0.1792 0.64730 0.000 0.916 0.000 0.084 0.000
#> GSM647572 3 0.0671 0.75739 0.000 0.004 0.980 0.016 0.000
#> GSM647578 3 0.6587 -0.06943 0.000 0.380 0.496 0.060 0.064
#> GSM647581 2 0.1907 0.66480 0.000 0.928 0.000 0.028 0.044
#> GSM647594 5 0.0000 0.69167 0.000 0.000 0.000 0.000 1.000
#> GSM647599 1 0.6242 0.34539 0.584 0.000 0.244 0.160 0.012
#> GSM647600 5 0.1471 0.67455 0.000 0.024 0.020 0.004 0.952
#> GSM647601 5 0.1121 0.67367 0.000 0.044 0.000 0.000 0.956
#> GSM647603 2 0.5816 0.62658 0.000 0.608 0.164 0.000 0.228
#> GSM647610 5 0.1493 0.68067 0.000 0.024 0.028 0.000 0.948
#> GSM647611 5 0.4161 -0.00729 0.000 0.392 0.000 0.000 0.608
#> GSM647612 2 0.3868 0.70095 0.000 0.800 0.000 0.060 0.140
#> GSM647614 2 0.2930 0.72529 0.000 0.832 0.000 0.004 0.164
#> GSM647618 5 0.4201 -0.07565 0.000 0.408 0.000 0.000 0.592
#> GSM647629 5 0.5301 0.47577 0.000 0.056 0.164 0.056 0.724
#> GSM647535 2 0.4126 0.56383 0.000 0.620 0.000 0.000 0.380
#> GSM647563 2 0.3109 0.71783 0.000 0.800 0.000 0.000 0.200
#> GSM647542 2 0.2930 0.72529 0.000 0.832 0.000 0.004 0.164
#> GSM647543 2 0.1410 0.65173 0.000 0.940 0.000 0.060 0.000
#> GSM647548 4 0.4734 0.63149 0.000 0.372 0.000 0.604 0.024
#> GSM647554 5 0.7755 0.11054 0.000 0.292 0.292 0.056 0.360
#> GSM647555 2 0.5768 0.64009 0.000 0.672 0.164 0.024 0.140
#> GSM647559 2 0.4161 0.55210 0.000 0.608 0.000 0.000 0.392
#> GSM647562 2 0.3109 0.71783 0.000 0.800 0.000 0.000 0.200
#> GSM647564 3 0.0963 0.77045 0.000 0.000 0.964 0.036 0.000
#> GSM647571 2 0.2930 0.72480 0.000 0.832 0.000 0.004 0.164
#> GSM647584 5 0.0566 0.68861 0.000 0.012 0.000 0.004 0.984
#> GSM647585 3 0.0703 0.76886 0.000 0.000 0.976 0.024 0.000
#> GSM647586 2 0.4161 0.55210 0.000 0.608 0.000 0.000 0.392
#> GSM647587 2 0.4161 0.55210 0.000 0.608 0.000 0.000 0.392
#> GSM647588 2 0.6584 0.30589 0.000 0.580 0.068 0.084 0.268
#> GSM647596 5 0.4201 -0.05781 0.000 0.408 0.000 0.000 0.592
#> GSM647602 3 0.0162 0.76305 0.000 0.000 0.996 0.004 0.000
#> GSM647609 5 0.3395 0.42955 0.000 0.236 0.000 0.000 0.764
#> GSM647620 5 0.4262 -0.15988 0.000 0.440 0.000 0.000 0.560
#> GSM647627 5 0.4262 -0.15988 0.000 0.440 0.000 0.000 0.560
#> GSM647628 2 0.3231 0.71875 0.000 0.800 0.000 0.004 0.196
#> GSM647533 1 0.0510 0.94274 0.984 0.000 0.000 0.016 0.000
#> GSM647536 4 0.8204 0.30038 0.192 0.136 0.000 0.352 0.320
#> GSM647537 1 0.0290 0.94618 0.992 0.000 0.000 0.008 0.000
#> GSM647606 1 0.0000 0.94893 1.000 0.000 0.000 0.000 0.000
#> GSM647621 4 0.4724 0.54744 0.164 0.000 0.104 0.732 0.000
#> GSM647626 3 0.2773 0.76804 0.000 0.000 0.836 0.164 0.000
#> GSM647538 1 0.0703 0.93833 0.976 0.000 0.000 0.024 0.000
#> GSM647575 4 0.3305 0.68632 0.000 0.224 0.000 0.776 0.000
#> GSM647590 1 0.0703 0.93833 0.976 0.000 0.000 0.024 0.000
#> GSM647605 1 0.0000 0.94893 1.000 0.000 0.000 0.000 0.000
#> GSM647607 4 0.4435 0.68337 0.056 0.164 0.012 0.768 0.000
#> GSM647608 4 0.1965 0.60478 0.000 0.000 0.096 0.904 0.000
#> GSM647622 1 0.0000 0.94893 1.000 0.000 0.000 0.000 0.000
#> GSM647623 1 0.0000 0.94893 1.000 0.000 0.000 0.000 0.000
#> GSM647624 1 0.0000 0.94893 1.000 0.000 0.000 0.000 0.000
#> GSM647625 1 0.0000 0.94893 1.000 0.000 0.000 0.000 0.000
#> GSM647534 5 0.7045 0.23180 0.148 0.000 0.104 0.168 0.580
#> GSM647539 4 0.3039 0.68521 0.000 0.192 0.000 0.808 0.000
#> GSM647566 3 0.6593 0.30459 0.172 0.024 0.560 0.244 0.000
#> GSM647589 4 0.2179 0.59431 0.000 0.000 0.112 0.888 0.000
#> GSM647604 1 0.0000 0.94893 1.000 0.000 0.000 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.0000 0.8553 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647574 3 0.2883 0.6248 0.000 0.000 0.788 0.212 0.000 0.000
#> GSM647577 3 0.0000 0.8553 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647547 4 0.3756 0.4936 0.000 0.000 0.352 0.644 0.000 0.004
#> GSM647552 5 0.5300 0.0353 0.000 0.000 0.116 0.000 0.540 0.344
#> GSM647553 3 0.3198 0.5272 0.000 0.000 0.740 0.260 0.000 0.000
#> GSM647565 4 0.5275 0.5387 0.000 0.168 0.000 0.600 0.000 0.232
#> GSM647545 2 0.2597 0.5774 0.000 0.824 0.000 0.000 0.000 0.176
#> GSM647549 2 0.2473 0.6080 0.000 0.856 0.000 0.000 0.008 0.136
#> GSM647550 6 0.2909 0.6776 0.000 0.136 0.028 0.000 0.000 0.836
#> GSM647560 6 0.3847 0.2041 0.000 0.456 0.000 0.000 0.000 0.544
#> GSM647617 3 0.0000 0.8553 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647528 2 0.2527 0.6897 0.000 0.832 0.000 0.000 0.168 0.000
#> GSM647529 4 0.5031 0.1601 0.004 0.060 0.000 0.476 0.460 0.000
#> GSM647531 2 0.7029 0.1227 0.000 0.400 0.000 0.120 0.344 0.136
#> GSM647540 6 0.2491 0.6077 0.000 0.000 0.164 0.000 0.000 0.836
#> GSM647541 6 0.2491 0.6680 0.000 0.164 0.000 0.000 0.000 0.836
#> GSM647546 3 0.0458 0.8507 0.000 0.000 0.984 0.000 0.000 0.016
#> GSM647557 2 0.4745 0.6462 0.000 0.676 0.000 0.000 0.188 0.136
#> GSM647561 2 0.4595 0.6565 0.000 0.696 0.000 0.000 0.168 0.136
#> GSM647567 3 0.4176 0.7138 0.000 0.000 0.716 0.000 0.064 0.220
#> GSM647568 6 0.3101 0.5911 0.000 0.244 0.000 0.000 0.000 0.756
#> GSM647570 2 0.0146 0.7116 0.000 0.996 0.000 0.000 0.000 0.004
#> GSM647573 4 0.4795 0.6521 0.000 0.164 0.032 0.728 0.008 0.068
#> GSM647576 6 0.1267 0.6465 0.000 0.000 0.060 0.000 0.000 0.940
#> GSM647579 6 0.2527 0.6037 0.000 0.000 0.168 0.000 0.000 0.832
#> GSM647580 3 0.0000 0.8553 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647583 3 0.0000 0.8553 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647592 5 0.2135 0.7958 0.000 0.128 0.000 0.000 0.872 0.000
#> GSM647593 5 0.1814 0.8040 0.000 0.100 0.000 0.000 0.900 0.000
#> GSM647595 5 0.1908 0.8037 0.000 0.096 0.000 0.000 0.900 0.004
#> GSM647597 5 0.0790 0.7649 0.000 0.032 0.000 0.000 0.968 0.000
#> GSM647598 5 0.2527 0.7697 0.000 0.168 0.000 0.000 0.832 0.000
#> GSM647613 2 0.4940 -0.1867 0.000 0.532 0.000 0.000 0.068 0.400
#> GSM647615 6 0.2762 0.6087 0.000 0.196 0.000 0.000 0.000 0.804
#> GSM647616 3 0.0000 0.8553 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647619 5 0.1957 0.8022 0.000 0.112 0.000 0.000 0.888 0.000
#> GSM647582 2 0.5015 0.4013 0.000 0.564 0.000 0.000 0.352 0.084
#> GSM647591 5 0.1814 0.7303 0.000 0.000 0.000 0.000 0.900 0.100
#> GSM647527 2 0.2527 0.6897 0.000 0.832 0.000 0.000 0.168 0.000
#> GSM647530 2 0.4940 0.5803 0.000 0.720 0.000 0.120 0.108 0.052
#> GSM647532 4 0.3760 0.7081 0.008 0.000 0.040 0.816 0.108 0.028
#> GSM647544 2 0.0000 0.7125 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647551 5 0.2432 0.7373 0.000 0.024 0.000 0.000 0.876 0.100
#> GSM647556 3 0.2854 0.7787 0.000 0.000 0.792 0.000 0.000 0.208
#> GSM647558 6 0.3765 0.4090 0.000 0.404 0.000 0.000 0.000 0.596
#> GSM647572 3 0.3043 0.7852 0.000 0.000 0.792 0.008 0.000 0.200
#> GSM647578 6 0.3063 0.6712 0.000 0.068 0.092 0.000 0.000 0.840
#> GSM647581 2 0.2831 0.6005 0.000 0.840 0.000 0.000 0.024 0.136
#> GSM647594 5 0.1814 0.8040 0.000 0.100 0.000 0.000 0.900 0.000
#> GSM647599 1 0.4534 0.3844 0.580 0.000 0.380 0.000 0.040 0.000
#> GSM647600 5 0.3066 0.7863 0.000 0.124 0.000 0.000 0.832 0.044
#> GSM647601 5 0.2730 0.7472 0.000 0.192 0.000 0.000 0.808 0.000
#> GSM647603 2 0.2941 0.5752 0.000 0.780 0.000 0.000 0.000 0.220
#> GSM647610 5 0.5476 0.4171 0.000 0.120 0.008 0.000 0.560 0.312
#> GSM647611 2 0.3864 0.1534 0.000 0.520 0.000 0.000 0.480 0.000
#> GSM647612 6 0.3706 0.5709 0.000 0.380 0.000 0.000 0.000 0.620
#> GSM647614 2 0.0146 0.7116 0.000 0.996 0.000 0.000 0.000 0.004
#> GSM647618 2 0.3867 0.1902 0.000 0.512 0.000 0.000 0.488 0.000
#> GSM647629 6 0.5527 0.0606 0.000 0.136 0.000 0.000 0.380 0.484
#> GSM647535 2 0.2527 0.6897 0.000 0.832 0.000 0.000 0.168 0.000
#> GSM647563 2 0.0000 0.7125 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647542 2 0.0146 0.7116 0.000 0.996 0.000 0.000 0.000 0.004
#> GSM647543 6 0.3175 0.5856 0.000 0.256 0.000 0.000 0.000 0.744
#> GSM647548 4 0.4932 0.5903 0.000 0.228 0.000 0.644 0.000 0.128
#> GSM647554 6 0.3319 0.6663 0.000 0.052 0.096 0.000 0.016 0.836
#> GSM647555 2 0.3390 0.4783 0.000 0.704 0.000 0.000 0.000 0.296
#> GSM647559 2 0.2527 0.6897 0.000 0.832 0.000 0.000 0.168 0.000
#> GSM647562 2 0.0000 0.7125 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647564 3 0.2491 0.8122 0.000 0.000 0.836 0.000 0.000 0.164
#> GSM647571 2 0.0146 0.7116 0.000 0.996 0.000 0.000 0.000 0.004
#> GSM647584 5 0.2340 0.7870 0.000 0.148 0.000 0.000 0.852 0.000
#> GSM647585 3 0.2597 0.8066 0.000 0.000 0.824 0.000 0.000 0.176
#> GSM647586 2 0.2527 0.6897 0.000 0.832 0.000 0.000 0.168 0.000
#> GSM647587 2 0.2527 0.6897 0.000 0.832 0.000 0.000 0.168 0.000
#> GSM647588 6 0.3092 0.6294 0.000 0.060 0.000 0.000 0.104 0.836
#> GSM647596 2 0.3782 0.3509 0.000 0.588 0.000 0.000 0.412 0.000
#> GSM647602 3 0.2697 0.7940 0.000 0.000 0.812 0.000 0.000 0.188
#> GSM647609 5 0.3804 0.1908 0.000 0.424 0.000 0.000 0.576 0.000
#> GSM647620 2 0.3727 0.4014 0.000 0.612 0.000 0.000 0.388 0.000
#> GSM647627 2 0.3727 0.4014 0.000 0.612 0.000 0.000 0.388 0.000
#> GSM647628 2 0.0000 0.7125 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647533 1 0.1480 0.9106 0.940 0.000 0.000 0.040 0.000 0.020
#> GSM647536 4 0.5115 0.4361 0.016 0.004 0.000 0.564 0.372 0.044
#> GSM647537 1 0.0458 0.9298 0.984 0.000 0.000 0.016 0.000 0.000
#> GSM647606 1 0.0000 0.9346 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647621 4 0.5693 0.6320 0.116 0.000 0.204 0.628 0.052 0.000
#> GSM647626 3 0.0000 0.8553 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647538 1 0.2186 0.8919 0.908 0.000 0.000 0.056 0.012 0.024
#> GSM647575 4 0.0870 0.7124 0.000 0.012 0.000 0.972 0.012 0.004
#> GSM647590 1 0.2186 0.8919 0.908 0.000 0.000 0.056 0.012 0.024
#> GSM647605 1 0.0000 0.9346 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647607 4 0.1109 0.7131 0.016 0.004 0.000 0.964 0.012 0.004
#> GSM647608 4 0.2416 0.6938 0.000 0.000 0.156 0.844 0.000 0.000
#> GSM647622 1 0.0000 0.9346 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647623 1 0.0260 0.9331 0.992 0.000 0.000 0.000 0.000 0.008
#> GSM647624 1 0.0000 0.9346 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647625 1 0.0000 0.9346 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647534 5 0.6880 0.3516 0.116 0.000 0.064 0.184 0.572 0.064
#> GSM647539 4 0.4179 0.5467 0.000 0.048 0.000 0.736 0.012 0.204
#> GSM647566 6 0.5203 0.4084 0.112 0.000 0.004 0.220 0.012 0.652
#> GSM647589 4 0.2597 0.6831 0.000 0.000 0.176 0.824 0.000 0.000
#> GSM647604 1 0.0000 0.9346 1.000 0.000 0.000 0.000 0.000 0.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n disease.state(p) development.stage(p) other(p) k
#> SD:pam 102 1.97e-05 0.0379 0.956 2
#> SD:pam 96 4.85e-06 0.1400 0.509 3
#> SD:pam 97 8.95e-13 0.0260 0.333 4
#> SD:pam 82 8.65e-13 0.0541 0.275 5
#> SD:pam 82 3.66e-12 0.0154 0.250 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["SD", "mclust"]
# you can also extract it by
# res = res_list["SD:mclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'SD' method.
#> Subgroups are detected by 'mclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 3.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.616 0.828 0.907 0.4372 0.600 0.600
#> 3 3 0.924 0.920 0.957 0.2851 0.808 0.692
#> 4 4 0.543 0.476 0.787 0.2056 0.937 0.864
#> 5 5 0.593 0.645 0.776 0.1152 0.787 0.504
#> 6 6 0.669 0.704 0.821 0.0671 0.840 0.444
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 3
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM647569 2 0.9491 0.606 0.368 0.632
#> GSM647574 2 0.9491 0.606 0.368 0.632
#> GSM647577 2 0.9491 0.606 0.368 0.632
#> GSM647547 1 0.0000 0.986 1.000 0.000
#> GSM647552 2 0.9580 0.587 0.380 0.620
#> GSM647553 2 0.9608 0.580 0.384 0.616
#> GSM647565 2 0.9909 0.456 0.444 0.556
#> GSM647545 2 0.0000 0.860 0.000 1.000
#> GSM647549 2 0.0000 0.860 0.000 1.000
#> GSM647550 2 0.2043 0.849 0.032 0.968
#> GSM647560 2 0.0000 0.860 0.000 1.000
#> GSM647617 2 0.9491 0.606 0.368 0.632
#> GSM647528 2 0.0000 0.860 0.000 1.000
#> GSM647529 1 0.0000 0.986 1.000 0.000
#> GSM647531 2 0.0672 0.856 0.008 0.992
#> GSM647540 2 0.9393 0.619 0.356 0.644
#> GSM647541 2 0.0000 0.860 0.000 1.000
#> GSM647546 2 0.9491 0.606 0.368 0.632
#> GSM647557 2 0.0672 0.856 0.008 0.992
#> GSM647561 2 0.0000 0.860 0.000 1.000
#> GSM647567 2 0.9491 0.606 0.368 0.632
#> GSM647568 2 0.0000 0.860 0.000 1.000
#> GSM647570 2 0.0000 0.860 0.000 1.000
#> GSM647573 1 0.0000 0.986 1.000 0.000
#> GSM647576 2 0.8713 0.681 0.292 0.708
#> GSM647579 2 0.9460 0.610 0.364 0.636
#> GSM647580 2 0.9491 0.606 0.368 0.632
#> GSM647583 2 0.9491 0.606 0.368 0.632
#> GSM647592 2 0.6887 0.766 0.184 0.816
#> GSM647593 2 0.0000 0.860 0.000 1.000
#> GSM647595 2 0.0000 0.860 0.000 1.000
#> GSM647597 1 0.0376 0.981 0.996 0.004
#> GSM647598 2 0.0000 0.860 0.000 1.000
#> GSM647613 2 0.0000 0.860 0.000 1.000
#> GSM647615 2 0.4431 0.821 0.092 0.908
#> GSM647616 2 0.9491 0.606 0.368 0.632
#> GSM647619 2 0.0000 0.860 0.000 1.000
#> GSM647582 2 0.0000 0.860 0.000 1.000
#> GSM647591 2 0.0000 0.860 0.000 1.000
#> GSM647527 2 0.0000 0.860 0.000 1.000
#> GSM647530 1 0.0000 0.986 1.000 0.000
#> GSM647532 1 0.0000 0.986 1.000 0.000
#> GSM647544 2 0.0000 0.860 0.000 1.000
#> GSM647551 2 0.0000 0.860 0.000 1.000
#> GSM647556 2 0.9491 0.606 0.368 0.632
#> GSM647558 2 0.0000 0.860 0.000 1.000
#> GSM647572 2 0.9491 0.606 0.368 0.632
#> GSM647578 2 0.6887 0.766 0.184 0.816
#> GSM647581 2 0.0672 0.856 0.008 0.992
#> GSM647594 2 0.7219 0.750 0.200 0.800
#> GSM647599 1 0.0000 0.986 1.000 0.000
#> GSM647600 2 0.7219 0.751 0.200 0.800
#> GSM647601 2 0.0000 0.860 0.000 1.000
#> GSM647603 2 0.0672 0.858 0.008 0.992
#> GSM647610 2 0.9393 0.619 0.356 0.644
#> GSM647611 2 0.0000 0.860 0.000 1.000
#> GSM647612 2 0.0000 0.860 0.000 1.000
#> GSM647614 2 0.0000 0.860 0.000 1.000
#> GSM647618 2 0.0000 0.860 0.000 1.000
#> GSM647629 2 0.0000 0.860 0.000 1.000
#> GSM647535 2 0.0000 0.860 0.000 1.000
#> GSM647563 2 0.0000 0.860 0.000 1.000
#> GSM647542 2 0.0000 0.860 0.000 1.000
#> GSM647543 2 0.0000 0.860 0.000 1.000
#> GSM647548 1 0.0000 0.986 1.000 0.000
#> GSM647554 2 0.6712 0.771 0.176 0.824
#> GSM647555 2 0.0000 0.860 0.000 1.000
#> GSM647559 2 0.0000 0.860 0.000 1.000
#> GSM647562 2 0.0000 0.860 0.000 1.000
#> GSM647564 2 0.9491 0.606 0.368 0.632
#> GSM647571 2 0.0000 0.860 0.000 1.000
#> GSM647584 2 0.0000 0.860 0.000 1.000
#> GSM647585 2 0.9491 0.606 0.368 0.632
#> GSM647586 2 0.0000 0.860 0.000 1.000
#> GSM647587 2 0.0000 0.860 0.000 1.000
#> GSM647588 2 0.2603 0.844 0.044 0.956
#> GSM647596 2 0.0000 0.860 0.000 1.000
#> GSM647602 2 0.9491 0.606 0.368 0.632
#> GSM647609 2 0.0000 0.860 0.000 1.000
#> GSM647620 2 0.0000 0.860 0.000 1.000
#> GSM647627 2 0.0000 0.860 0.000 1.000
#> GSM647628 2 0.0000 0.860 0.000 1.000
#> GSM647533 1 0.0000 0.986 1.000 0.000
#> GSM647536 1 0.0000 0.986 1.000 0.000
#> GSM647537 1 0.0000 0.986 1.000 0.000
#> GSM647606 1 0.0000 0.986 1.000 0.000
#> GSM647621 1 0.0000 0.986 1.000 0.000
#> GSM647626 2 0.9580 0.587 0.380 0.620
#> GSM647538 1 0.0000 0.986 1.000 0.000
#> GSM647575 1 0.0000 0.986 1.000 0.000
#> GSM647590 1 0.0000 0.986 1.000 0.000
#> GSM647605 1 0.0000 0.986 1.000 0.000
#> GSM647607 1 0.0000 0.986 1.000 0.000
#> GSM647608 1 0.0000 0.986 1.000 0.000
#> GSM647622 1 0.0000 0.986 1.000 0.000
#> GSM647623 1 0.0000 0.986 1.000 0.000
#> GSM647624 1 0.0000 0.986 1.000 0.000
#> GSM647625 1 0.0000 0.986 1.000 0.000
#> GSM647534 1 0.8861 0.400 0.696 0.304
#> GSM647539 1 0.0000 0.986 1.000 0.000
#> GSM647566 1 0.0000 0.986 1.000 0.000
#> GSM647589 1 0.0000 0.986 1.000 0.000
#> GSM647604 1 0.0000 0.986 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 3 0.0983 1.000 0.016 0.004 0.980
#> GSM647574 1 0.4974 0.711 0.764 0.000 0.236
#> GSM647577 3 0.0983 1.000 0.016 0.004 0.980
#> GSM647547 1 0.2356 0.901 0.928 0.000 0.072
#> GSM647552 2 0.1636 0.949 0.016 0.964 0.020
#> GSM647553 1 0.4291 0.789 0.820 0.000 0.180
#> GSM647565 1 0.5986 0.628 0.736 0.240 0.024
#> GSM647545 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647549 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647550 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647560 2 0.0892 0.955 0.000 0.980 0.020
#> GSM647617 3 0.0983 1.000 0.016 0.004 0.980
#> GSM647528 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647529 1 0.0000 0.935 1.000 0.000 0.000
#> GSM647531 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647540 2 0.5506 0.729 0.016 0.764 0.220
#> GSM647541 2 0.0892 0.955 0.000 0.980 0.020
#> GSM647546 2 0.6905 0.257 0.016 0.544 0.440
#> GSM647557 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647561 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647567 2 0.5167 0.785 0.024 0.804 0.172
#> GSM647568 2 0.0424 0.956 0.008 0.992 0.000
#> GSM647570 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647573 1 0.2689 0.903 0.932 0.032 0.036
#> GSM647576 2 0.1636 0.949 0.016 0.964 0.020
#> GSM647579 2 0.2383 0.934 0.016 0.940 0.044
#> GSM647580 3 0.0983 1.000 0.016 0.004 0.980
#> GSM647583 3 0.0983 1.000 0.016 0.004 0.980
#> GSM647592 2 0.2269 0.943 0.016 0.944 0.040
#> GSM647593 2 0.1529 0.951 0.000 0.960 0.040
#> GSM647595 2 0.1529 0.951 0.000 0.960 0.040
#> GSM647597 1 0.1753 0.896 0.952 0.048 0.000
#> GSM647598 2 0.0747 0.956 0.000 0.984 0.016
#> GSM647613 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647615 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647616 3 0.0983 1.000 0.016 0.004 0.980
#> GSM647619 2 0.1529 0.951 0.000 0.960 0.040
#> GSM647582 2 0.1289 0.953 0.000 0.968 0.032
#> GSM647591 2 0.1529 0.951 0.000 0.960 0.040
#> GSM647527 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647530 1 0.5254 0.603 0.736 0.264 0.000
#> GSM647532 1 0.0237 0.934 0.996 0.000 0.004
#> GSM647544 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647551 2 0.1411 0.952 0.000 0.964 0.036
#> GSM647556 3 0.0983 1.000 0.016 0.004 0.980
#> GSM647558 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647572 2 0.5595 0.695 0.016 0.756 0.228
#> GSM647578 2 0.4796 0.743 0.000 0.780 0.220
#> GSM647581 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647594 2 0.4974 0.684 0.236 0.764 0.000
#> GSM647599 1 0.0000 0.935 1.000 0.000 0.000
#> GSM647600 2 0.1636 0.949 0.016 0.964 0.020
#> GSM647601 2 0.1411 0.952 0.000 0.964 0.036
#> GSM647603 2 0.1482 0.951 0.012 0.968 0.020
#> GSM647610 2 0.4209 0.847 0.120 0.860 0.020
#> GSM647611 2 0.1411 0.952 0.000 0.964 0.036
#> GSM647612 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647614 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647618 2 0.0237 0.958 0.000 0.996 0.004
#> GSM647629 2 0.1289 0.953 0.000 0.968 0.032
#> GSM647535 2 0.0892 0.955 0.000 0.980 0.020
#> GSM647563 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647542 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647543 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647548 1 0.5945 0.635 0.740 0.236 0.024
#> GSM647554 2 0.1525 0.952 0.004 0.964 0.032
#> GSM647555 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647559 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647562 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647564 3 0.0983 1.000 0.016 0.004 0.980
#> GSM647571 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647584 2 0.1529 0.951 0.000 0.960 0.040
#> GSM647585 3 0.0983 1.000 0.016 0.004 0.980
#> GSM647586 2 0.0237 0.958 0.000 0.996 0.004
#> GSM647587 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647588 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647596 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647602 3 0.0983 1.000 0.016 0.004 0.980
#> GSM647609 2 0.1411 0.952 0.000 0.964 0.036
#> GSM647620 2 0.1289 0.953 0.000 0.968 0.032
#> GSM647627 2 0.1289 0.953 0.000 0.968 0.032
#> GSM647628 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647533 1 0.0000 0.935 1.000 0.000 0.000
#> GSM647536 1 0.0000 0.935 1.000 0.000 0.000
#> GSM647537 1 0.0000 0.935 1.000 0.000 0.000
#> GSM647606 1 0.0000 0.935 1.000 0.000 0.000
#> GSM647621 1 0.1031 0.929 0.976 0.000 0.024
#> GSM647626 1 0.2356 0.901 0.928 0.000 0.072
#> GSM647538 1 0.0000 0.935 1.000 0.000 0.000
#> GSM647575 1 0.1031 0.929 0.976 0.000 0.024
#> GSM647590 1 0.0000 0.935 1.000 0.000 0.000
#> GSM647605 1 0.0000 0.935 1.000 0.000 0.000
#> GSM647607 1 0.1031 0.929 0.976 0.000 0.024
#> GSM647608 1 0.1163 0.927 0.972 0.000 0.028
#> GSM647622 1 0.0000 0.935 1.000 0.000 0.000
#> GSM647623 1 0.0000 0.935 1.000 0.000 0.000
#> GSM647624 1 0.0000 0.935 1.000 0.000 0.000
#> GSM647625 1 0.0000 0.935 1.000 0.000 0.000
#> GSM647534 1 0.0000 0.935 1.000 0.000 0.000
#> GSM647539 1 0.1031 0.929 0.976 0.000 0.024
#> GSM647566 1 0.0000 0.935 1.000 0.000 0.000
#> GSM647589 1 0.2261 0.903 0.932 0.000 0.068
#> GSM647604 1 0.0000 0.935 1.000 0.000 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 3 0.0000 0.9405 0.000 0.000 1.000 0.000
#> GSM647574 1 0.4454 0.6212 0.692 0.000 0.308 0.000
#> GSM647577 3 0.0000 0.9405 0.000 0.000 1.000 0.000
#> GSM647547 1 0.3004 0.8238 0.884 0.008 0.008 0.100
#> GSM647552 2 0.5376 0.0254 0.176 0.736 0.088 0.000
#> GSM647553 1 0.4250 0.6686 0.724 0.000 0.276 0.000
#> GSM647565 1 0.4431 0.5073 0.696 0.304 0.000 0.000
#> GSM647545 2 0.4643 0.4604 0.000 0.656 0.000 0.344
#> GSM647549 2 0.4643 0.4604 0.000 0.656 0.000 0.344
#> GSM647550 2 0.0817 0.4187 0.000 0.976 0.000 0.024
#> GSM647560 2 0.0707 0.4165 0.000 0.980 0.000 0.020
#> GSM647617 3 0.0000 0.9405 0.000 0.000 1.000 0.000
#> GSM647528 2 0.4477 0.3437 0.000 0.688 0.000 0.312
#> GSM647529 1 0.2469 0.8264 0.892 0.000 0.000 0.108
#> GSM647531 2 0.4643 0.4604 0.000 0.656 0.000 0.344
#> GSM647540 2 0.3610 0.1892 0.000 0.800 0.200 0.000
#> GSM647541 2 0.0000 0.3999 0.000 1.000 0.000 0.000
#> GSM647546 3 0.7803 0.1101 0.316 0.268 0.416 0.000
#> GSM647557 2 0.4643 0.4604 0.000 0.656 0.000 0.344
#> GSM647561 2 0.4585 0.4577 0.000 0.668 0.000 0.332
#> GSM647567 2 0.7002 -0.0508 0.164 0.568 0.268 0.000
#> GSM647568 2 0.3726 0.4755 0.000 0.788 0.000 0.212
#> GSM647570 2 0.4643 0.4604 0.000 0.656 0.000 0.344
#> GSM647573 1 0.2469 0.8264 0.892 0.000 0.000 0.108
#> GSM647576 2 0.0707 0.4165 0.000 0.980 0.000 0.020
#> GSM647579 2 0.4399 0.1562 0.020 0.768 0.212 0.000
#> GSM647580 3 0.0000 0.9405 0.000 0.000 1.000 0.000
#> GSM647583 3 0.0000 0.9405 0.000 0.000 1.000 0.000
#> GSM647592 2 0.6414 -0.2760 0.240 0.636 0.000 0.124
#> GSM647593 2 0.4855 -0.5990 0.000 0.600 0.000 0.400
#> GSM647595 2 0.4855 -0.5990 0.000 0.600 0.000 0.400
#> GSM647597 1 0.3764 0.7220 0.816 0.172 0.000 0.012
#> GSM647598 4 0.4746 0.6792 0.000 0.368 0.000 0.632
#> GSM647613 2 0.4843 0.4140 0.000 0.604 0.000 0.396
#> GSM647615 2 0.2011 0.4398 0.000 0.920 0.000 0.080
#> GSM647616 3 0.0000 0.9405 0.000 0.000 1.000 0.000
#> GSM647619 2 0.4855 -0.5990 0.000 0.600 0.000 0.400
#> GSM647582 2 0.1474 0.3316 0.000 0.948 0.000 0.052
#> GSM647591 2 0.4855 -0.5990 0.000 0.600 0.000 0.400
#> GSM647527 2 0.4477 0.3437 0.000 0.688 0.000 0.312
#> GSM647530 1 0.3356 0.7193 0.824 0.176 0.000 0.000
#> GSM647532 1 0.2469 0.8264 0.892 0.000 0.000 0.108
#> GSM647544 2 0.4790 0.4312 0.000 0.620 0.000 0.380
#> GSM647551 2 0.4761 -0.5723 0.000 0.628 0.000 0.372
#> GSM647556 3 0.0000 0.9405 0.000 0.000 1.000 0.000
#> GSM647558 2 0.4643 0.4604 0.000 0.656 0.000 0.344
#> GSM647572 2 0.5694 0.2073 0.000 0.696 0.224 0.080
#> GSM647578 2 0.3356 0.2206 0.000 0.824 0.176 0.000
#> GSM647581 2 0.4643 0.4604 0.000 0.656 0.000 0.344
#> GSM647594 1 0.7902 -0.3449 0.364 0.336 0.000 0.300
#> GSM647599 1 0.3399 0.8027 0.868 0.000 0.092 0.040
#> GSM647600 2 0.3764 0.0835 0.172 0.816 0.000 0.012
#> GSM647601 4 0.4989 0.8154 0.000 0.472 0.000 0.528
#> GSM647603 2 0.0000 0.3999 0.000 1.000 0.000 0.000
#> GSM647610 2 0.5581 -0.1575 0.340 0.632 0.008 0.020
#> GSM647611 4 0.5000 0.7765 0.000 0.500 0.000 0.500
#> GSM647612 2 0.4431 0.4704 0.000 0.696 0.000 0.304
#> GSM647614 2 0.4564 0.4657 0.000 0.672 0.000 0.328
#> GSM647618 2 0.4564 0.3692 0.000 0.672 0.000 0.328
#> GSM647629 2 0.0000 0.3999 0.000 1.000 0.000 0.000
#> GSM647535 2 0.0188 0.4027 0.000 0.996 0.000 0.004
#> GSM647563 2 0.4643 0.4604 0.000 0.656 0.000 0.344
#> GSM647542 2 0.3311 0.4700 0.000 0.828 0.000 0.172
#> GSM647543 2 0.2408 0.4511 0.000 0.896 0.000 0.104
#> GSM647548 1 0.3610 0.6948 0.800 0.200 0.000 0.000
#> GSM647554 2 0.0188 0.3989 0.000 0.996 0.004 0.000
#> GSM647555 2 0.1637 0.4392 0.000 0.940 0.000 0.060
#> GSM647559 2 0.4331 0.4689 0.000 0.712 0.000 0.288
#> GSM647562 2 0.4843 0.4140 0.000 0.604 0.000 0.396
#> GSM647564 3 0.0188 0.9372 0.004 0.000 0.996 0.000
#> GSM647571 2 0.4008 0.4769 0.000 0.756 0.000 0.244
#> GSM647584 2 0.4855 -0.5990 0.000 0.600 0.000 0.400
#> GSM647585 3 0.0000 0.9405 0.000 0.000 1.000 0.000
#> GSM647586 2 0.4522 0.3274 0.000 0.680 0.000 0.320
#> GSM647587 2 0.4564 0.3685 0.000 0.672 0.000 0.328
#> GSM647588 2 0.1867 0.4411 0.000 0.928 0.000 0.072
#> GSM647596 2 0.4454 0.4459 0.000 0.692 0.000 0.308
#> GSM647602 3 0.0000 0.9405 0.000 0.000 1.000 0.000
#> GSM647609 2 0.4855 -0.5990 0.000 0.600 0.000 0.400
#> GSM647620 2 0.2011 0.2952 0.000 0.920 0.000 0.080
#> GSM647627 2 0.4925 -0.3856 0.000 0.572 0.000 0.428
#> GSM647628 2 0.4643 0.4604 0.000 0.656 0.000 0.344
#> GSM647533 1 0.3024 0.8190 0.852 0.000 0.000 0.148
#> GSM647536 1 0.2469 0.8264 0.892 0.000 0.000 0.108
#> GSM647537 1 0.3024 0.8190 0.852 0.000 0.000 0.148
#> GSM647606 1 0.3024 0.8190 0.852 0.000 0.000 0.148
#> GSM647621 1 0.0000 0.8326 1.000 0.000 0.000 0.000
#> GSM647626 1 0.4049 0.7374 0.780 0.000 0.212 0.008
#> GSM647538 1 0.3024 0.8190 0.852 0.000 0.000 0.148
#> GSM647575 1 0.2469 0.8264 0.892 0.000 0.000 0.108
#> GSM647590 1 0.3486 0.8298 0.812 0.000 0.000 0.188
#> GSM647605 1 0.3024 0.8190 0.852 0.000 0.000 0.148
#> GSM647607 1 0.2469 0.8264 0.892 0.000 0.000 0.108
#> GSM647608 1 0.2469 0.8264 0.892 0.000 0.000 0.108
#> GSM647622 1 0.3024 0.8190 0.852 0.000 0.000 0.148
#> GSM647623 1 0.3024 0.8190 0.852 0.000 0.000 0.148
#> GSM647624 1 0.3024 0.8190 0.852 0.000 0.000 0.148
#> GSM647625 1 0.3024 0.8190 0.852 0.000 0.000 0.148
#> GSM647534 1 0.4880 0.7742 0.812 0.052 0.096 0.040
#> GSM647539 1 0.2469 0.8264 0.892 0.000 0.000 0.108
#> GSM647566 1 0.3048 0.8252 0.876 0.000 0.016 0.108
#> GSM647589 1 0.2469 0.8264 0.892 0.000 0.000 0.108
#> GSM647604 1 0.3024 0.8190 0.852 0.000 0.000 0.148
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.0000 0.7737 0.000 0.000 1.000 0.000 0.000
#> GSM647574 3 0.4074 0.3993 0.000 0.000 0.636 0.364 0.000
#> GSM647577 3 0.0000 0.7737 0.000 0.000 1.000 0.000 0.000
#> GSM647547 4 0.0000 0.7963 0.000 0.000 0.000 1.000 0.000
#> GSM647552 5 0.5959 0.4251 0.008 0.132 0.008 0.212 0.640
#> GSM647553 3 0.4300 0.1461 0.000 0.000 0.524 0.476 0.000
#> GSM647565 4 0.4182 0.4114 0.004 0.352 0.000 0.644 0.000
#> GSM647545 2 0.0324 0.7374 0.004 0.992 0.000 0.000 0.004
#> GSM647549 2 0.0324 0.7370 0.004 0.992 0.000 0.004 0.000
#> GSM647550 2 0.4338 0.6681 0.024 0.696 0.000 0.000 0.280
#> GSM647560 2 0.4639 0.6097 0.024 0.632 0.000 0.000 0.344
#> GSM647617 3 0.0000 0.7737 0.000 0.000 1.000 0.000 0.000
#> GSM647528 2 0.4069 0.6601 0.096 0.792 0.000 0.000 0.112
#> GSM647529 4 0.0290 0.7927 0.008 0.000 0.000 0.992 0.000
#> GSM647531 2 0.1430 0.7194 0.004 0.944 0.000 0.052 0.000
#> GSM647540 3 0.7099 0.3813 0.024 0.084 0.516 0.044 0.332
#> GSM647541 2 0.4338 0.6681 0.024 0.696 0.000 0.000 0.280
#> GSM647546 3 0.5178 0.6213 0.016 0.000 0.712 0.088 0.184
#> GSM647557 2 0.1704 0.7092 0.004 0.928 0.000 0.068 0.000
#> GSM647561 2 0.1638 0.7178 0.004 0.932 0.000 0.000 0.064
#> GSM647567 5 0.8043 0.1027 0.020 0.112 0.252 0.136 0.480
#> GSM647568 2 0.3745 0.7187 0.024 0.780 0.000 0.000 0.196
#> GSM647570 2 0.0324 0.7373 0.004 0.992 0.000 0.000 0.004
#> GSM647573 4 0.0000 0.7963 0.000 0.000 0.000 1.000 0.000
#> GSM647576 2 0.5273 0.5860 0.024 0.608 0.024 0.000 0.344
#> GSM647579 3 0.7369 0.3804 0.024 0.088 0.496 0.060 0.332
#> GSM647580 3 0.0000 0.7737 0.000 0.000 1.000 0.000 0.000
#> GSM647583 3 0.0000 0.7737 0.000 0.000 1.000 0.000 0.000
#> GSM647592 5 0.6332 0.6518 0.096 0.080 0.000 0.180 0.644
#> GSM647593 5 0.4343 0.7513 0.096 0.136 0.000 0.000 0.768
#> GSM647595 5 0.4343 0.7513 0.096 0.136 0.000 0.000 0.768
#> GSM647597 4 0.4305 0.1140 0.000 0.000 0.000 0.512 0.488
#> GSM647598 5 0.5335 0.6226 0.096 0.260 0.000 0.000 0.644
#> GSM647613 2 0.2074 0.6996 0.000 0.896 0.000 0.000 0.104
#> GSM647615 2 0.4404 0.6560 0.024 0.684 0.000 0.000 0.292
#> GSM647616 3 0.0000 0.7737 0.000 0.000 1.000 0.000 0.000
#> GSM647619 5 0.4343 0.7513 0.096 0.136 0.000 0.000 0.768
#> GSM647582 2 0.4283 0.6155 0.008 0.644 0.000 0.000 0.348
#> GSM647591 5 0.4343 0.7513 0.096 0.136 0.000 0.000 0.768
#> GSM647527 2 0.4069 0.6601 0.096 0.792 0.000 0.000 0.112
#> GSM647530 4 0.4403 0.1808 0.004 0.436 0.000 0.560 0.000
#> GSM647532 4 0.0000 0.7963 0.000 0.000 0.000 1.000 0.000
#> GSM647544 2 0.2074 0.6996 0.000 0.896 0.000 0.000 0.104
#> GSM647551 5 0.2843 0.7164 0.048 0.076 0.000 0.000 0.876
#> GSM647556 3 0.0000 0.7737 0.000 0.000 1.000 0.000 0.000
#> GSM647558 2 0.0162 0.7377 0.004 0.996 0.000 0.000 0.000
#> GSM647572 3 0.7428 0.3230 0.024 0.124 0.480 0.040 0.332
#> GSM647578 2 0.6732 0.4876 0.024 0.512 0.128 0.004 0.332
#> GSM647581 2 0.1768 0.7071 0.004 0.924 0.000 0.072 0.000
#> GSM647594 5 0.5382 0.4925 0.000 0.100 0.000 0.260 0.640
#> GSM647599 4 0.5397 -0.1849 0.468 0.000 0.032 0.488 0.012
#> GSM647600 5 0.4306 0.5689 0.012 0.100 0.000 0.096 0.792
#> GSM647601 5 0.4698 0.7273 0.096 0.172 0.000 0.000 0.732
#> GSM647603 2 0.4998 0.5963 0.024 0.596 0.000 0.008 0.372
#> GSM647610 5 0.4097 0.5197 0.008 0.020 0.000 0.216 0.756
#> GSM647611 5 0.4836 0.7139 0.096 0.188 0.000 0.000 0.716
#> GSM647612 2 0.3368 0.7272 0.024 0.820 0.000 0.000 0.156
#> GSM647614 2 0.3326 0.7274 0.024 0.824 0.000 0.000 0.152
#> GSM647618 2 0.4455 0.5744 0.068 0.744 0.000 0.000 0.188
#> GSM647629 5 0.4867 -0.2293 0.024 0.432 0.000 0.000 0.544
#> GSM647535 2 0.4292 0.6762 0.024 0.704 0.000 0.000 0.272
#> GSM647563 2 0.0451 0.7364 0.004 0.988 0.000 0.000 0.008
#> GSM647542 2 0.3779 0.7173 0.024 0.776 0.000 0.000 0.200
#> GSM647543 2 0.4223 0.6947 0.028 0.724 0.000 0.000 0.248
#> GSM647548 4 0.2806 0.6534 0.004 0.152 0.000 0.844 0.000
#> GSM647554 2 0.5916 0.3978 0.024 0.492 0.028 0.012 0.444
#> GSM647555 2 0.3970 0.7071 0.024 0.752 0.000 0.000 0.224
#> GSM647559 2 0.1195 0.7380 0.028 0.960 0.000 0.000 0.012
#> GSM647562 2 0.2329 0.6854 0.000 0.876 0.000 0.000 0.124
#> GSM647564 3 0.1043 0.7604 0.000 0.000 0.960 0.000 0.040
#> GSM647571 2 0.3586 0.7229 0.020 0.792 0.000 0.000 0.188
#> GSM647584 5 0.4386 0.7497 0.096 0.140 0.000 0.000 0.764
#> GSM647585 3 0.0000 0.7737 0.000 0.000 1.000 0.000 0.000
#> GSM647586 2 0.4698 0.5869 0.096 0.732 0.000 0.000 0.172
#> GSM647587 2 0.4386 0.6277 0.096 0.764 0.000 0.000 0.140
#> GSM647588 2 0.4086 0.6994 0.024 0.736 0.000 0.000 0.240
#> GSM647596 2 0.2648 0.6750 0.000 0.848 0.000 0.000 0.152
#> GSM647602 3 0.0000 0.7737 0.000 0.000 1.000 0.000 0.000
#> GSM647609 5 0.4386 0.7497 0.096 0.140 0.000 0.000 0.764
#> GSM647620 2 0.5821 0.1741 0.096 0.504 0.000 0.000 0.400
#> GSM647627 2 0.5794 0.1118 0.096 0.520 0.000 0.000 0.384
#> GSM647628 2 0.0290 0.7384 0.000 0.992 0.000 0.000 0.008
#> GSM647533 1 0.2329 0.9509 0.876 0.000 0.000 0.124 0.000
#> GSM647536 4 0.0000 0.7963 0.000 0.000 0.000 1.000 0.000
#> GSM647537 1 0.2329 0.9509 0.876 0.000 0.000 0.124 0.000
#> GSM647606 1 0.2648 0.9395 0.848 0.000 0.000 0.152 0.000
#> GSM647621 4 0.1043 0.7717 0.040 0.000 0.000 0.960 0.000
#> GSM647626 3 0.4440 0.1592 0.004 0.000 0.528 0.468 0.000
#> GSM647538 1 0.2329 0.9509 0.876 0.000 0.000 0.124 0.000
#> GSM647575 4 0.0000 0.7963 0.000 0.000 0.000 1.000 0.000
#> GSM647590 4 0.1965 0.7086 0.096 0.000 0.000 0.904 0.000
#> GSM647605 1 0.3424 0.8474 0.760 0.000 0.000 0.240 0.000
#> GSM647607 4 0.0000 0.7963 0.000 0.000 0.000 1.000 0.000
#> GSM647608 4 0.0000 0.7963 0.000 0.000 0.000 1.000 0.000
#> GSM647622 1 0.2329 0.9509 0.876 0.000 0.000 0.124 0.000
#> GSM647623 1 0.2329 0.9509 0.876 0.000 0.000 0.124 0.000
#> GSM647624 1 0.3480 0.8350 0.752 0.000 0.000 0.248 0.000
#> GSM647625 1 0.2329 0.9509 0.876 0.000 0.000 0.124 0.000
#> GSM647534 4 0.6930 0.0207 0.340 0.000 0.024 0.464 0.172
#> GSM647539 4 0.0000 0.7963 0.000 0.000 0.000 1.000 0.000
#> GSM647566 4 0.0771 0.7833 0.004 0.000 0.020 0.976 0.000
#> GSM647589 4 0.0000 0.7963 0.000 0.000 0.000 1.000 0.000
#> GSM647604 1 0.2852 0.9253 0.828 0.000 0.000 0.172 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.0000 0.93321 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647574 4 0.3923 0.50949 0.008 0.000 0.372 0.620 0.000 0.000
#> GSM647577 3 0.0000 0.93321 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647547 4 0.0146 0.80854 0.000 0.000 0.004 0.996 0.000 0.000
#> GSM647552 4 0.7266 0.06922 0.000 0.112 0.000 0.364 0.204 0.320
#> GSM647553 4 0.3774 0.58225 0.008 0.000 0.328 0.664 0.000 0.000
#> GSM647565 4 0.2454 0.74109 0.000 0.160 0.000 0.840 0.000 0.000
#> GSM647545 2 0.0146 0.80847 0.000 0.996 0.000 0.000 0.004 0.000
#> GSM647549 2 0.0000 0.80671 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647550 6 0.3946 0.74404 0.000 0.168 0.000 0.000 0.076 0.756
#> GSM647560 6 0.2094 0.74548 0.000 0.020 0.000 0.000 0.080 0.900
#> GSM647617 3 0.0000 0.93321 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647528 2 0.3390 0.64940 0.000 0.704 0.000 0.000 0.296 0.000
#> GSM647529 4 0.0547 0.80526 0.020 0.000 0.000 0.980 0.000 0.000
#> GSM647531 2 0.0458 0.80416 0.000 0.984 0.000 0.016 0.000 0.000
#> GSM647540 6 0.1610 0.74040 0.000 0.000 0.000 0.000 0.084 0.916
#> GSM647541 6 0.3667 0.74524 0.000 0.132 0.000 0.000 0.080 0.788
#> GSM647546 3 0.6538 0.04615 0.000 0.000 0.396 0.208 0.032 0.364
#> GSM647557 2 0.0692 0.80171 0.000 0.976 0.000 0.020 0.000 0.004
#> GSM647561 2 0.1714 0.80760 0.000 0.908 0.000 0.000 0.092 0.000
#> GSM647567 6 0.5352 0.52205 0.000 0.000 0.000 0.204 0.204 0.592
#> GSM647568 6 0.3175 0.69831 0.000 0.256 0.000 0.000 0.000 0.744
#> GSM647570 2 0.0000 0.80671 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647573 4 0.0000 0.80870 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM647576 6 0.1913 0.74416 0.000 0.012 0.000 0.000 0.080 0.908
#> GSM647579 6 0.1866 0.73934 0.000 0.000 0.000 0.008 0.084 0.908
#> GSM647580 3 0.0000 0.93321 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647583 3 0.0000 0.93321 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647592 5 0.3843 0.73053 0.000 0.104 0.000 0.108 0.784 0.004
#> GSM647593 5 0.2053 0.80849 0.000 0.108 0.000 0.000 0.888 0.004
#> GSM647595 5 0.2053 0.80849 0.000 0.108 0.000 0.000 0.888 0.004
#> GSM647597 4 0.4196 0.57356 0.028 0.000 0.000 0.640 0.332 0.000
#> GSM647598 5 0.3266 0.61797 0.000 0.272 0.000 0.000 0.728 0.000
#> GSM647613 2 0.2527 0.77893 0.000 0.832 0.000 0.000 0.168 0.000
#> GSM647615 6 0.5077 0.55697 0.000 0.404 0.000 0.000 0.080 0.516
#> GSM647616 3 0.0000 0.93321 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647619 5 0.2053 0.80849 0.000 0.108 0.000 0.000 0.888 0.004
#> GSM647582 5 0.5320 0.37762 0.000 0.352 0.000 0.000 0.532 0.116
#> GSM647591 5 0.2100 0.80774 0.000 0.112 0.000 0.000 0.884 0.004
#> GSM647527 2 0.3390 0.64940 0.000 0.704 0.000 0.000 0.296 0.000
#> GSM647530 4 0.3287 0.68779 0.012 0.220 0.000 0.768 0.000 0.000
#> GSM647532 4 0.0000 0.80870 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM647544 2 0.2562 0.77664 0.000 0.828 0.000 0.000 0.172 0.000
#> GSM647551 5 0.3383 0.55437 0.000 0.004 0.000 0.000 0.728 0.268
#> GSM647556 3 0.0000 0.93321 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647558 2 0.0000 0.80671 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647572 6 0.2294 0.73524 0.000 0.000 0.000 0.036 0.072 0.892
#> GSM647578 6 0.1610 0.74040 0.000 0.000 0.000 0.000 0.084 0.916
#> GSM647581 2 0.0547 0.80245 0.000 0.980 0.000 0.020 0.000 0.000
#> GSM647594 5 0.5221 0.55276 0.012 0.116 0.000 0.240 0.632 0.000
#> GSM647599 4 0.4746 0.55544 0.236 0.000 0.000 0.660 0.104 0.000
#> GSM647600 5 0.5578 0.12704 0.000 0.004 0.000 0.124 0.484 0.388
#> GSM647601 5 0.1957 0.80806 0.000 0.112 0.000 0.000 0.888 0.000
#> GSM647603 6 0.1910 0.73183 0.000 0.000 0.000 0.000 0.108 0.892
#> GSM647610 6 0.5820 -0.00872 0.000 0.000 0.000 0.184 0.400 0.416
#> GSM647611 5 0.2003 0.80649 0.000 0.116 0.000 0.000 0.884 0.000
#> GSM647612 6 0.3221 0.68866 0.000 0.264 0.000 0.000 0.000 0.736
#> GSM647614 6 0.3351 0.66289 0.000 0.288 0.000 0.000 0.000 0.712
#> GSM647618 2 0.3659 0.45732 0.000 0.636 0.000 0.000 0.364 0.000
#> GSM647629 6 0.2969 0.62459 0.000 0.000 0.000 0.000 0.224 0.776
#> GSM647535 6 0.4663 0.71225 0.000 0.252 0.000 0.000 0.088 0.660
#> GSM647563 2 0.0458 0.81150 0.000 0.984 0.000 0.000 0.016 0.000
#> GSM647542 6 0.3126 0.70427 0.000 0.248 0.000 0.000 0.000 0.752
#> GSM647543 6 0.3221 0.70321 0.000 0.264 0.000 0.000 0.000 0.736
#> GSM647548 4 0.2597 0.72993 0.000 0.176 0.000 0.824 0.000 0.000
#> GSM647554 6 0.2416 0.70028 0.000 0.000 0.000 0.000 0.156 0.844
#> GSM647555 6 0.3974 0.73397 0.000 0.224 0.000 0.000 0.048 0.728
#> GSM647559 2 0.2482 0.78821 0.000 0.848 0.000 0.000 0.148 0.004
#> GSM647562 2 0.2527 0.77893 0.000 0.832 0.000 0.000 0.168 0.000
#> GSM647564 3 0.0363 0.92225 0.000 0.000 0.988 0.000 0.000 0.012
#> GSM647571 6 0.3464 0.64254 0.000 0.312 0.000 0.000 0.000 0.688
#> GSM647584 5 0.2100 0.80851 0.000 0.112 0.000 0.000 0.884 0.004
#> GSM647585 3 0.0000 0.93321 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647586 5 0.3868 -0.08515 0.000 0.496 0.000 0.000 0.504 0.000
#> GSM647587 2 0.3330 0.66561 0.000 0.716 0.000 0.000 0.284 0.000
#> GSM647588 6 0.4781 0.68813 0.000 0.296 0.000 0.000 0.080 0.624
#> GSM647596 2 0.3765 0.35021 0.000 0.596 0.000 0.000 0.404 0.000
#> GSM647602 3 0.0000 0.93321 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647609 5 0.1957 0.80806 0.000 0.112 0.000 0.000 0.888 0.000
#> GSM647620 5 0.2340 0.78421 0.000 0.148 0.000 0.000 0.852 0.000
#> GSM647627 5 0.2854 0.72677 0.000 0.208 0.000 0.000 0.792 0.000
#> GSM647628 2 0.2178 0.72100 0.000 0.868 0.000 0.000 0.000 0.132
#> GSM647533 1 0.0363 0.84265 0.988 0.000 0.000 0.012 0.000 0.000
#> GSM647536 4 0.0000 0.80870 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM647537 1 0.0363 0.84265 0.988 0.000 0.000 0.012 0.000 0.000
#> GSM647606 1 0.2340 0.77918 0.852 0.000 0.000 0.148 0.000 0.000
#> GSM647621 4 0.1714 0.77027 0.092 0.000 0.000 0.908 0.000 0.000
#> GSM647626 4 0.4141 0.47610 0.016 0.000 0.388 0.596 0.000 0.000
#> GSM647538 1 0.0547 0.84148 0.980 0.000 0.000 0.020 0.000 0.000
#> GSM647575 4 0.0000 0.80870 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM647590 4 0.2048 0.74257 0.120 0.000 0.000 0.880 0.000 0.000
#> GSM647605 1 0.3446 0.58207 0.692 0.000 0.000 0.308 0.000 0.000
#> GSM647607 4 0.0000 0.80870 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM647608 4 0.0260 0.80689 0.008 0.000 0.000 0.992 0.000 0.000
#> GSM647622 1 0.0363 0.84265 0.988 0.000 0.000 0.012 0.000 0.000
#> GSM647623 1 0.0363 0.84265 0.988 0.000 0.000 0.012 0.000 0.000
#> GSM647624 1 0.3833 0.21404 0.556 0.000 0.000 0.444 0.000 0.000
#> GSM647625 1 0.0363 0.84265 0.988 0.000 0.000 0.012 0.000 0.000
#> GSM647534 4 0.5534 0.52761 0.220 0.000 0.000 0.608 0.156 0.016
#> GSM647539 4 0.0000 0.80870 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM647566 4 0.2118 0.77368 0.008 0.000 0.000 0.888 0.104 0.000
#> GSM647589 4 0.0000 0.80870 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM647604 1 0.3101 0.68441 0.756 0.000 0.000 0.244 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) development.stage(p) other(p) k
#> SD:mclust 101 1.16e-13 0.248 0.0599 2
#> SD:mclust 102 2.75e-13 0.117 0.0594 3
#> SD:mclust 45 3.36e-04 0.530 0.0286 4
#> SD:mclust 84 1.89e-13 0.107 0.1273 5
#> SD:mclust 93 8.39e-12 0.231 0.2786 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["SD", "NMF"]
# you can also extract it by
# res = res_list["SD:NMF"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'SD' method.
#> Subgroups are detected by 'NMF' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.880 0.924 0.967 0.4677 0.525 0.525
#> 3 3 0.727 0.804 0.920 0.3305 0.747 0.558
#> 4 4 0.773 0.829 0.919 0.1300 0.869 0.674
#> 5 5 0.598 0.531 0.752 0.0755 0.892 0.688
#> 6 6 0.601 0.474 0.713 0.0500 0.931 0.763
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
#> GSM647569 1 0.4815 0.863 0.896 0.104
#> GSM647574 1 0.0672 0.932 0.992 0.008
#> GSM647577 1 0.8763 0.614 0.704 0.296
#> GSM647547 1 0.0000 0.935 1.000 0.000
#> GSM647552 2 0.0000 0.982 0.000 1.000
#> GSM647553 1 0.0000 0.935 1.000 0.000
#> GSM647565 2 0.0000 0.982 0.000 1.000
#> GSM647545 2 0.0000 0.982 0.000 1.000
#> GSM647549 2 0.0000 0.982 0.000 1.000
#> GSM647550 2 0.0000 0.982 0.000 1.000
#> GSM647560 2 0.0000 0.982 0.000 1.000
#> GSM647617 1 0.9881 0.282 0.564 0.436
#> GSM647528 2 0.0000 0.982 0.000 1.000
#> GSM647529 1 0.6438 0.795 0.836 0.164
#> GSM647531 2 0.0000 0.982 0.000 1.000
#> GSM647540 2 0.0000 0.982 0.000 1.000
#> GSM647541 2 0.0000 0.982 0.000 1.000
#> GSM647546 2 0.6887 0.755 0.184 0.816
#> GSM647557 2 0.0000 0.982 0.000 1.000
#> GSM647561 2 0.0000 0.982 0.000 1.000
#> GSM647567 1 0.8661 0.627 0.712 0.288
#> GSM647568 2 0.0000 0.982 0.000 1.000
#> GSM647570 2 0.0000 0.982 0.000 1.000
#> GSM647573 1 0.0376 0.934 0.996 0.004
#> GSM647576 2 0.0000 0.982 0.000 1.000
#> GSM647579 2 0.0000 0.982 0.000 1.000
#> GSM647580 1 0.1414 0.925 0.980 0.020
#> GSM647583 1 0.8144 0.688 0.748 0.252
#> GSM647592 2 0.0000 0.982 0.000 1.000
#> GSM647593 2 0.0000 0.982 0.000 1.000
#> GSM647595 2 0.0000 0.982 0.000 1.000
#> GSM647597 1 0.9754 0.359 0.592 0.408
#> GSM647598 2 0.0000 0.982 0.000 1.000
#> GSM647613 2 0.0000 0.982 0.000 1.000
#> GSM647615 2 0.0000 0.982 0.000 1.000
#> GSM647616 1 0.0000 0.935 1.000 0.000
#> GSM647619 2 0.0000 0.982 0.000 1.000
#> GSM647582 2 0.0000 0.982 0.000 1.000
#> GSM647591 2 0.0000 0.982 0.000 1.000
#> GSM647527 2 0.0000 0.982 0.000 1.000
#> GSM647530 2 0.0000 0.982 0.000 1.000
#> GSM647532 1 0.0376 0.934 0.996 0.004
#> GSM647544 2 0.0000 0.982 0.000 1.000
#> GSM647551 2 0.0000 0.982 0.000 1.000
#> GSM647556 1 0.4562 0.870 0.904 0.096
#> GSM647558 2 0.0000 0.982 0.000 1.000
#> GSM647572 2 0.7139 0.736 0.196 0.804
#> GSM647578 2 0.0000 0.982 0.000 1.000
#> GSM647581 2 0.0000 0.982 0.000 1.000
#> GSM647594 2 0.0000 0.982 0.000 1.000
#> GSM647599 1 0.0000 0.935 1.000 0.000
#> GSM647600 2 0.0000 0.982 0.000 1.000
#> GSM647601 2 0.0000 0.982 0.000 1.000
#> GSM647603 2 0.0000 0.982 0.000 1.000
#> GSM647610 2 0.7883 0.668 0.236 0.764
#> GSM647611 2 0.0000 0.982 0.000 1.000
#> GSM647612 2 0.0000 0.982 0.000 1.000
#> GSM647614 2 0.0000 0.982 0.000 1.000
#> GSM647618 2 0.0000 0.982 0.000 1.000
#> GSM647629 2 0.0000 0.982 0.000 1.000
#> GSM647535 2 0.0000 0.982 0.000 1.000
#> GSM647563 2 0.0000 0.982 0.000 1.000
#> GSM647542 2 0.0000 0.982 0.000 1.000
#> GSM647543 2 0.0000 0.982 0.000 1.000
#> GSM647548 2 0.0000 0.982 0.000 1.000
#> GSM647554 2 0.0000 0.982 0.000 1.000
#> GSM647555 2 0.0000 0.982 0.000 1.000
#> GSM647559 2 0.0000 0.982 0.000 1.000
#> GSM647562 2 0.0000 0.982 0.000 1.000
#> GSM647564 2 0.9754 0.252 0.408 0.592
#> GSM647571 2 0.0000 0.982 0.000 1.000
#> GSM647584 2 0.0000 0.982 0.000 1.000
#> GSM647585 1 0.0000 0.935 1.000 0.000
#> GSM647586 2 0.0000 0.982 0.000 1.000
#> GSM647587 2 0.0000 0.982 0.000 1.000
#> GSM647588 2 0.0000 0.982 0.000 1.000
#> GSM647596 2 0.0000 0.982 0.000 1.000
#> GSM647602 1 0.7376 0.749 0.792 0.208
#> GSM647609 2 0.0000 0.982 0.000 1.000
#> GSM647620 2 0.0000 0.982 0.000 1.000
#> GSM647627 2 0.0000 0.982 0.000 1.000
#> GSM647628 2 0.0000 0.982 0.000 1.000
#> GSM647533 1 0.0000 0.935 1.000 0.000
#> GSM647536 1 0.0000 0.935 1.000 0.000
#> GSM647537 1 0.0000 0.935 1.000 0.000
#> GSM647606 1 0.0000 0.935 1.000 0.000
#> GSM647621 1 0.0000 0.935 1.000 0.000
#> GSM647626 1 0.0000 0.935 1.000 0.000
#> GSM647538 1 0.0000 0.935 1.000 0.000
#> GSM647575 1 0.0000 0.935 1.000 0.000
#> GSM647590 1 0.0000 0.935 1.000 0.000
#> GSM647605 1 0.0000 0.935 1.000 0.000
#> GSM647607 1 0.0000 0.935 1.000 0.000
#> GSM647608 1 0.0000 0.935 1.000 0.000
#> GSM647622 1 0.0000 0.935 1.000 0.000
#> GSM647623 1 0.0000 0.935 1.000 0.000
#> GSM647624 1 0.0000 0.935 1.000 0.000
#> GSM647625 1 0.0000 0.935 1.000 0.000
#> GSM647534 1 0.0000 0.935 1.000 0.000
#> GSM647539 1 0.3431 0.895 0.936 0.064
#> GSM647566 1 0.0000 0.935 1.000 0.000
#> GSM647589 1 0.0000 0.935 1.000 0.000
#> GSM647604 1 0.0000 0.935 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 3 0.0000 0.7929 0.000 0.000 1.000
#> GSM647574 3 0.0000 0.7929 0.000 0.000 1.000
#> GSM647577 3 0.0000 0.7929 0.000 0.000 1.000
#> GSM647547 3 0.0000 0.7929 0.000 0.000 1.000
#> GSM647552 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647553 3 0.0000 0.7929 0.000 0.000 1.000
#> GSM647565 3 0.4555 0.7093 0.000 0.200 0.800
#> GSM647545 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647549 2 0.0237 0.9389 0.000 0.996 0.004
#> GSM647550 3 0.6026 0.4733 0.000 0.376 0.624
#> GSM647560 2 0.3412 0.8201 0.000 0.876 0.124
#> GSM647617 3 0.0000 0.7929 0.000 0.000 1.000
#> GSM647528 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647529 1 0.0000 0.9469 1.000 0.000 0.000
#> GSM647531 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647540 3 0.2165 0.7693 0.000 0.064 0.936
#> GSM647541 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647546 3 0.0000 0.7929 0.000 0.000 1.000
#> GSM647557 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647561 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647567 3 0.8255 0.0521 0.428 0.076 0.496
#> GSM647568 3 0.4931 0.6847 0.000 0.232 0.768
#> GSM647570 2 0.4346 0.7351 0.000 0.816 0.184
#> GSM647573 3 0.5067 0.7295 0.052 0.116 0.832
#> GSM647576 3 0.5363 0.6346 0.000 0.276 0.724
#> GSM647579 3 0.6225 0.3345 0.000 0.432 0.568
#> GSM647580 3 0.0000 0.7929 0.000 0.000 1.000
#> GSM647583 3 0.0000 0.7929 0.000 0.000 1.000
#> GSM647592 2 0.2165 0.8838 0.064 0.936 0.000
#> GSM647593 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647595 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647597 1 0.0237 0.9432 0.996 0.004 0.000
#> GSM647598 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647613 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647615 2 0.3551 0.8086 0.000 0.868 0.132
#> GSM647616 3 0.0000 0.7929 0.000 0.000 1.000
#> GSM647619 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647582 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647591 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647527 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647530 2 0.2537 0.8728 0.080 0.920 0.000
#> GSM647532 1 0.0237 0.9443 0.996 0.000 0.004
#> GSM647544 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647551 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647556 3 0.0000 0.7929 0.000 0.000 1.000
#> GSM647558 2 0.5560 0.5176 0.000 0.700 0.300
#> GSM647572 3 0.0000 0.7929 0.000 0.000 1.000
#> GSM647578 3 0.5760 0.5279 0.000 0.328 0.672
#> GSM647581 2 0.0237 0.9389 0.000 0.996 0.004
#> GSM647594 2 0.0892 0.9260 0.020 0.980 0.000
#> GSM647599 1 0.0000 0.9469 1.000 0.000 0.000
#> GSM647600 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647601 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647603 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647610 2 0.3267 0.8217 0.116 0.884 0.000
#> GSM647611 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647612 2 0.6079 0.2812 0.000 0.612 0.388
#> GSM647614 2 0.6095 0.2687 0.000 0.608 0.392
#> GSM647618 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647629 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647535 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647563 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647542 3 0.5968 0.4948 0.000 0.364 0.636
#> GSM647543 3 0.6267 0.2816 0.000 0.452 0.548
#> GSM647548 3 0.6140 0.4041 0.000 0.404 0.596
#> GSM647554 2 0.0892 0.9260 0.000 0.980 0.020
#> GSM647555 2 0.5785 0.4408 0.000 0.668 0.332
#> GSM647559 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647562 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647564 3 0.0000 0.7929 0.000 0.000 1.000
#> GSM647571 3 0.6252 0.3039 0.000 0.444 0.556
#> GSM647584 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647585 3 0.0000 0.7929 0.000 0.000 1.000
#> GSM647586 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647587 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647588 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647596 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647602 3 0.0000 0.7929 0.000 0.000 1.000
#> GSM647609 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647620 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647627 2 0.0000 0.9417 0.000 1.000 0.000
#> GSM647628 2 0.4346 0.7348 0.000 0.816 0.184
#> GSM647533 1 0.0000 0.9469 1.000 0.000 0.000
#> GSM647536 1 0.0000 0.9469 1.000 0.000 0.000
#> GSM647537 1 0.0000 0.9469 1.000 0.000 0.000
#> GSM647606 1 0.0000 0.9469 1.000 0.000 0.000
#> GSM647621 1 0.5650 0.5328 0.688 0.000 0.312
#> GSM647626 3 0.5760 0.3446 0.328 0.000 0.672
#> GSM647538 1 0.0000 0.9469 1.000 0.000 0.000
#> GSM647575 1 0.6267 0.1413 0.548 0.000 0.452
#> GSM647590 1 0.0747 0.9351 0.984 0.000 0.016
#> GSM647605 1 0.0000 0.9469 1.000 0.000 0.000
#> GSM647607 1 0.3941 0.7825 0.844 0.000 0.156
#> GSM647608 3 0.0000 0.7929 0.000 0.000 1.000
#> GSM647622 1 0.0000 0.9469 1.000 0.000 0.000
#> GSM647623 1 0.0000 0.9469 1.000 0.000 0.000
#> GSM647624 1 0.0000 0.9469 1.000 0.000 0.000
#> GSM647625 1 0.0000 0.9469 1.000 0.000 0.000
#> GSM647534 1 0.0000 0.9469 1.000 0.000 0.000
#> GSM647539 3 0.6373 0.2456 0.408 0.004 0.588
#> GSM647566 1 0.0000 0.9469 1.000 0.000 0.000
#> GSM647589 3 0.0000 0.7929 0.000 0.000 1.000
#> GSM647604 1 0.0000 0.9469 1.000 0.000 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 3 0.0000 0.911 0.000 0.000 1.000 0.000
#> GSM647574 3 0.3123 0.805 0.000 0.000 0.844 0.156
#> GSM647577 3 0.0000 0.911 0.000 0.000 1.000 0.000
#> GSM647547 4 0.0188 0.849 0.004 0.000 0.000 0.996
#> GSM647552 2 0.3392 0.829 0.020 0.856 0.000 0.124
#> GSM647553 3 0.2011 0.870 0.000 0.000 0.920 0.080
#> GSM647565 4 0.0707 0.851 0.000 0.020 0.000 0.980
#> GSM647545 2 0.2814 0.831 0.000 0.868 0.000 0.132
#> GSM647549 2 0.3801 0.737 0.000 0.780 0.000 0.220
#> GSM647550 2 0.4106 0.804 0.000 0.832 0.084 0.084
#> GSM647560 2 0.0804 0.902 0.000 0.980 0.008 0.012
#> GSM647617 3 0.0000 0.911 0.000 0.000 1.000 0.000
#> GSM647528 2 0.0000 0.906 0.000 1.000 0.000 0.000
#> GSM647529 1 0.1474 0.927 0.948 0.000 0.000 0.052
#> GSM647531 2 0.4830 0.421 0.000 0.608 0.000 0.392
#> GSM647540 3 0.0469 0.906 0.000 0.012 0.988 0.000
#> GSM647541 2 0.0921 0.897 0.000 0.972 0.000 0.028
#> GSM647546 3 0.1302 0.894 0.000 0.000 0.956 0.044
#> GSM647557 2 0.4761 0.470 0.000 0.628 0.000 0.372
#> GSM647561 2 0.1118 0.893 0.000 0.964 0.000 0.036
#> GSM647567 3 0.7356 0.178 0.368 0.164 0.468 0.000
#> GSM647568 4 0.2271 0.835 0.000 0.076 0.008 0.916
#> GSM647570 4 0.4134 0.671 0.000 0.260 0.000 0.740
#> GSM647573 4 0.0188 0.849 0.004 0.000 0.000 0.996
#> GSM647576 3 0.5496 0.654 0.000 0.160 0.732 0.108
#> GSM647579 3 0.3726 0.688 0.000 0.212 0.788 0.000
#> GSM647580 3 0.0000 0.911 0.000 0.000 1.000 0.000
#> GSM647583 3 0.1474 0.889 0.000 0.000 0.948 0.052
#> GSM647592 2 0.1661 0.874 0.052 0.944 0.000 0.004
#> GSM647593 2 0.0188 0.905 0.000 0.996 0.000 0.004
#> GSM647595 2 0.0000 0.906 0.000 1.000 0.000 0.000
#> GSM647597 1 0.0524 0.946 0.988 0.008 0.000 0.004
#> GSM647598 2 0.0000 0.906 0.000 1.000 0.000 0.000
#> GSM647613 2 0.0336 0.904 0.000 0.992 0.000 0.008
#> GSM647615 2 0.3219 0.802 0.000 0.836 0.000 0.164
#> GSM647616 3 0.0000 0.911 0.000 0.000 1.000 0.000
#> GSM647619 2 0.0188 0.905 0.000 0.996 0.000 0.004
#> GSM647582 2 0.0000 0.906 0.000 1.000 0.000 0.000
#> GSM647591 2 0.0336 0.905 0.000 0.992 0.000 0.008
#> GSM647527 2 0.0000 0.906 0.000 1.000 0.000 0.000
#> GSM647530 4 0.0524 0.851 0.004 0.008 0.000 0.988
#> GSM647532 4 0.3266 0.728 0.168 0.000 0.000 0.832
#> GSM647544 2 0.4843 0.302 0.000 0.604 0.000 0.396
#> GSM647551 2 0.0000 0.906 0.000 1.000 0.000 0.000
#> GSM647556 3 0.0000 0.911 0.000 0.000 1.000 0.000
#> GSM647558 4 0.2589 0.813 0.000 0.116 0.000 0.884
#> GSM647572 3 0.2216 0.852 0.000 0.000 0.908 0.092
#> GSM647578 2 0.4981 0.165 0.000 0.536 0.464 0.000
#> GSM647581 4 0.1940 0.838 0.000 0.076 0.000 0.924
#> GSM647594 2 0.0188 0.906 0.004 0.996 0.000 0.000
#> GSM647599 1 0.0188 0.951 0.996 0.000 0.000 0.004
#> GSM647600 2 0.0000 0.906 0.000 1.000 0.000 0.000
#> GSM647601 2 0.0188 0.905 0.000 0.996 0.000 0.004
#> GSM647603 2 0.0188 0.905 0.000 0.996 0.000 0.004
#> GSM647610 2 0.2300 0.857 0.064 0.920 0.000 0.016
#> GSM647611 2 0.0188 0.905 0.000 0.996 0.000 0.004
#> GSM647612 2 0.3024 0.803 0.000 0.852 0.000 0.148
#> GSM647614 2 0.4961 0.107 0.000 0.552 0.000 0.448
#> GSM647618 2 0.0707 0.899 0.000 0.980 0.000 0.020
#> GSM647629 2 0.0000 0.906 0.000 1.000 0.000 0.000
#> GSM647535 2 0.0000 0.906 0.000 1.000 0.000 0.000
#> GSM647563 2 0.1211 0.892 0.000 0.960 0.000 0.040
#> GSM647542 4 0.5471 0.632 0.000 0.268 0.048 0.684
#> GSM647543 4 0.5916 0.591 0.000 0.272 0.072 0.656
#> GSM647548 4 0.0188 0.850 0.000 0.004 0.000 0.996
#> GSM647554 2 0.0188 0.906 0.000 0.996 0.004 0.000
#> GSM647555 2 0.2831 0.839 0.000 0.876 0.004 0.120
#> GSM647559 2 0.0469 0.902 0.000 0.988 0.000 0.012
#> GSM647562 2 0.2149 0.861 0.000 0.912 0.000 0.088
#> GSM647564 3 0.0000 0.911 0.000 0.000 1.000 0.000
#> GSM647571 4 0.3668 0.767 0.000 0.188 0.004 0.808
#> GSM647584 2 0.0000 0.906 0.000 1.000 0.000 0.000
#> GSM647585 3 0.0000 0.911 0.000 0.000 1.000 0.000
#> GSM647586 2 0.0000 0.906 0.000 1.000 0.000 0.000
#> GSM647587 2 0.0336 0.904 0.000 0.992 0.000 0.008
#> GSM647588 2 0.2589 0.840 0.000 0.884 0.000 0.116
#> GSM647596 2 0.0000 0.906 0.000 1.000 0.000 0.000
#> GSM647602 3 0.0000 0.911 0.000 0.000 1.000 0.000
#> GSM647609 2 0.0000 0.906 0.000 1.000 0.000 0.000
#> GSM647620 2 0.0000 0.906 0.000 1.000 0.000 0.000
#> GSM647627 2 0.0000 0.906 0.000 1.000 0.000 0.000
#> GSM647628 2 0.4564 0.497 0.000 0.672 0.000 0.328
#> GSM647533 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM647536 1 0.2868 0.858 0.864 0.000 0.000 0.136
#> GSM647537 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM647606 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM647621 1 0.4522 0.559 0.680 0.000 0.000 0.320
#> GSM647626 3 0.0188 0.910 0.004 0.000 0.996 0.000
#> GSM647538 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM647575 4 0.2760 0.773 0.128 0.000 0.000 0.872
#> GSM647590 1 0.1867 0.911 0.928 0.000 0.000 0.072
#> GSM647605 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM647607 4 0.3356 0.725 0.176 0.000 0.000 0.824
#> GSM647608 4 0.0921 0.842 0.028 0.000 0.000 0.972
#> GSM647622 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM647623 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM647624 1 0.0188 0.951 0.996 0.000 0.000 0.004
#> GSM647625 1 0.0000 0.953 1.000 0.000 0.000 0.000
#> GSM647534 1 0.0376 0.948 0.992 0.004 0.000 0.004
#> GSM647539 4 0.1792 0.820 0.068 0.000 0.000 0.932
#> GSM647566 1 0.3486 0.792 0.812 0.000 0.000 0.188
#> GSM647589 4 0.1940 0.816 0.000 0.000 0.076 0.924
#> GSM647604 1 0.0000 0.953 1.000 0.000 0.000 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.0000 0.78986 0.000 0.000 1.000 0.000 0.000
#> GSM647574 3 0.3480 0.64407 0.000 0.000 0.752 0.248 0.000
#> GSM647577 3 0.0290 0.78938 0.000 0.000 0.992 0.008 0.000
#> GSM647547 4 0.3586 0.39751 0.000 0.000 0.000 0.736 0.264
#> GSM647552 5 0.7991 0.15589 0.128 0.256 0.000 0.184 0.432
#> GSM647553 3 0.3561 0.60536 0.000 0.000 0.740 0.260 0.000
#> GSM647565 4 0.2077 0.35297 0.000 0.008 0.000 0.908 0.084
#> GSM647545 2 0.4151 0.58228 0.000 0.652 0.000 0.344 0.004
#> GSM647549 2 0.4872 0.43968 0.000 0.540 0.000 0.436 0.024
#> GSM647550 2 0.4400 0.68347 0.000 0.780 0.108 0.104 0.008
#> GSM647560 2 0.3662 0.65524 0.000 0.744 0.000 0.252 0.004
#> GSM647617 3 0.0000 0.78986 0.000 0.000 1.000 0.000 0.000
#> GSM647528 2 0.1331 0.73143 0.000 0.952 0.000 0.040 0.008
#> GSM647529 5 0.6323 0.19001 0.292 0.000 0.000 0.192 0.516
#> GSM647531 4 0.6206 0.04132 0.000 0.172 0.000 0.532 0.296
#> GSM647540 3 0.1121 0.76863 0.000 0.044 0.956 0.000 0.000
#> GSM647541 2 0.3582 0.67285 0.000 0.768 0.000 0.224 0.008
#> GSM647546 3 0.3366 0.63348 0.000 0.000 0.768 0.232 0.000
#> GSM647557 4 0.6222 0.04721 0.000 0.216 0.000 0.548 0.236
#> GSM647561 2 0.3992 0.64684 0.000 0.720 0.000 0.268 0.012
#> GSM647567 2 0.6751 -0.04695 0.020 0.420 0.144 0.000 0.416
#> GSM647568 4 0.4061 0.18646 0.000 0.240 0.004 0.740 0.016
#> GSM647570 2 0.4760 0.46503 0.000 0.564 0.000 0.416 0.020
#> GSM647573 4 0.3707 0.39550 0.000 0.000 0.000 0.716 0.284
#> GSM647576 3 0.6957 -0.01295 0.000 0.320 0.348 0.328 0.004
#> GSM647579 3 0.4313 0.38330 0.000 0.356 0.636 0.008 0.000
#> GSM647580 3 0.0000 0.78986 0.000 0.000 1.000 0.000 0.000
#> GSM647583 3 0.2377 0.73666 0.000 0.000 0.872 0.128 0.000
#> GSM647592 2 0.5013 0.45370 0.232 0.684 0.000 0.000 0.084
#> GSM647593 2 0.2074 0.69894 0.000 0.896 0.000 0.000 0.104
#> GSM647595 2 0.2448 0.71241 0.000 0.892 0.000 0.020 0.088
#> GSM647597 1 0.2597 0.82026 0.884 0.024 0.000 0.000 0.092
#> GSM647598 2 0.0162 0.73104 0.000 0.996 0.000 0.004 0.000
#> GSM647613 2 0.3452 0.66113 0.000 0.756 0.000 0.244 0.000
#> GSM647615 2 0.4425 0.52281 0.000 0.600 0.000 0.392 0.008
#> GSM647616 3 0.0963 0.78135 0.000 0.000 0.964 0.036 0.000
#> GSM647619 2 0.3074 0.63499 0.000 0.804 0.000 0.000 0.196
#> GSM647582 2 0.2376 0.73326 0.000 0.904 0.000 0.044 0.052
#> GSM647591 2 0.3327 0.67789 0.000 0.828 0.000 0.028 0.144
#> GSM647527 2 0.1168 0.73167 0.000 0.960 0.000 0.032 0.008
#> GSM647530 4 0.3884 0.39048 0.004 0.000 0.000 0.708 0.288
#> GSM647532 4 0.6385 -0.09243 0.296 0.000 0.000 0.504 0.200
#> GSM647544 5 0.6245 0.09388 0.000 0.236 0.000 0.220 0.544
#> GSM647551 2 0.3661 0.53713 0.000 0.724 0.000 0.000 0.276
#> GSM647556 3 0.0290 0.78816 0.000 0.000 0.992 0.000 0.008
#> GSM647558 4 0.4232 0.13324 0.000 0.312 0.000 0.676 0.012
#> GSM647572 3 0.5771 0.14872 0.000 0.024 0.476 0.040 0.460
#> GSM647578 3 0.5049 -0.02726 0.000 0.480 0.488 0.000 0.032
#> GSM647581 4 0.1671 0.29439 0.000 0.076 0.000 0.924 0.000
#> GSM647594 2 0.4701 0.34949 0.368 0.612 0.000 0.004 0.016
#> GSM647599 1 0.1300 0.88559 0.956 0.016 0.000 0.000 0.028
#> GSM647600 2 0.3003 0.63950 0.000 0.812 0.000 0.000 0.188
#> GSM647601 2 0.0609 0.72702 0.000 0.980 0.000 0.000 0.020
#> GSM647603 2 0.2773 0.65122 0.000 0.836 0.000 0.000 0.164
#> GSM647610 2 0.5858 0.24091 0.124 0.568 0.000 0.000 0.308
#> GSM647611 2 0.1608 0.71206 0.000 0.928 0.000 0.000 0.072
#> GSM647612 2 0.4025 0.63075 0.000 0.700 0.000 0.292 0.008
#> GSM647614 2 0.4251 0.60720 0.000 0.672 0.000 0.316 0.012
#> GSM647618 2 0.4249 0.51896 0.000 0.688 0.000 0.016 0.296
#> GSM647629 2 0.2969 0.71864 0.000 0.852 0.000 0.128 0.020
#> GSM647535 2 0.0693 0.73158 0.000 0.980 0.000 0.012 0.008
#> GSM647563 2 0.3060 0.71421 0.000 0.848 0.000 0.128 0.024
#> GSM647542 2 0.4806 0.47870 0.000 0.572 0.004 0.408 0.016
#> GSM647543 4 0.4706 -0.36009 0.000 0.488 0.004 0.500 0.008
#> GSM647548 4 0.3876 0.38509 0.000 0.000 0.000 0.684 0.316
#> GSM647554 2 0.3508 0.57190 0.000 0.748 0.000 0.000 0.252
#> GSM647555 2 0.4484 0.61328 0.000 0.668 0.000 0.308 0.024
#> GSM647559 2 0.4269 0.45427 0.000 0.684 0.000 0.016 0.300
#> GSM647562 2 0.4982 0.24814 0.000 0.556 0.000 0.032 0.412
#> GSM647564 3 0.0000 0.78986 0.000 0.000 1.000 0.000 0.000
#> GSM647571 5 0.6227 0.06828 0.000 0.280 0.000 0.184 0.536
#> GSM647584 2 0.1671 0.71208 0.000 0.924 0.000 0.000 0.076
#> GSM647585 3 0.0162 0.78922 0.000 0.000 0.996 0.000 0.004
#> GSM647586 2 0.0579 0.73129 0.000 0.984 0.000 0.008 0.008
#> GSM647587 2 0.3835 0.55207 0.000 0.744 0.000 0.012 0.244
#> GSM647588 2 0.5273 0.56994 0.000 0.680 0.000 0.156 0.164
#> GSM647596 2 0.0579 0.73130 0.000 0.984 0.000 0.008 0.008
#> GSM647602 3 0.0000 0.78986 0.000 0.000 1.000 0.000 0.000
#> GSM647609 2 0.0703 0.72683 0.000 0.976 0.000 0.000 0.024
#> GSM647620 2 0.0404 0.72842 0.000 0.988 0.000 0.000 0.012
#> GSM647627 2 0.0451 0.73104 0.000 0.988 0.000 0.004 0.008
#> GSM647628 2 0.4819 0.62462 0.000 0.724 0.000 0.164 0.112
#> GSM647533 1 0.2377 0.83420 0.872 0.000 0.000 0.000 0.128
#> GSM647536 4 0.6615 -0.19113 0.376 0.000 0.000 0.408 0.216
#> GSM647537 1 0.1892 0.87124 0.916 0.000 0.000 0.004 0.080
#> GSM647606 1 0.0404 0.90924 0.988 0.000 0.000 0.000 0.012
#> GSM647621 5 0.6169 0.16716 0.392 0.000 0.000 0.136 0.472
#> GSM647626 3 0.0404 0.78533 0.012 0.000 0.988 0.000 0.000
#> GSM647538 1 0.3642 0.70513 0.760 0.000 0.000 0.008 0.232
#> GSM647575 4 0.4300 0.20766 0.000 0.000 0.000 0.524 0.476
#> GSM647590 1 0.4017 0.68692 0.788 0.000 0.000 0.148 0.064
#> GSM647605 1 0.0290 0.90851 0.992 0.000 0.000 0.000 0.008
#> GSM647607 4 0.6109 0.21207 0.172 0.000 0.000 0.556 0.272
#> GSM647608 4 0.4706 0.35817 0.004 0.000 0.020 0.632 0.344
#> GSM647622 1 0.0162 0.91034 0.996 0.000 0.000 0.004 0.000
#> GSM647623 1 0.0324 0.91039 0.992 0.000 0.000 0.004 0.004
#> GSM647624 1 0.0324 0.91012 0.992 0.000 0.000 0.004 0.004
#> GSM647625 1 0.0162 0.90935 0.996 0.000 0.000 0.000 0.004
#> GSM647534 5 0.6539 -0.00625 0.368 0.200 0.000 0.000 0.432
#> GSM647539 4 0.4150 0.34183 0.000 0.000 0.000 0.612 0.388
#> GSM647566 5 0.6187 0.02951 0.200 0.000 0.000 0.248 0.552
#> GSM647589 4 0.5615 0.31039 0.000 0.000 0.096 0.584 0.320
#> GSM647604 1 0.0290 0.90851 0.992 0.000 0.000 0.000 0.008
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.0000 0.7708 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647574 3 0.5378 0.4392 0.000 0.000 0.544 0.132 0.324 0.000
#> GSM647577 3 0.1267 0.7591 0.000 0.000 0.940 0.000 0.060 0.000
#> GSM647547 4 0.2092 0.6365 0.000 0.000 0.000 0.876 0.124 0.000
#> GSM647552 5 0.5740 -0.0946 0.028 0.072 0.000 0.012 0.568 0.320
#> GSM647553 3 0.4360 0.5886 0.000 0.000 0.680 0.060 0.260 0.000
#> GSM647565 4 0.4128 0.1352 0.000 0.004 0.000 0.504 0.488 0.004
#> GSM647545 5 0.4228 0.3544 0.000 0.392 0.000 0.020 0.588 0.000
#> GSM647549 5 0.2933 0.6552 0.000 0.200 0.000 0.004 0.796 0.000
#> GSM647550 2 0.4847 0.4768 0.000 0.700 0.144 0.008 0.144 0.004
#> GSM647560 2 0.4109 0.3510 0.000 0.652 0.012 0.008 0.328 0.000
#> GSM647617 3 0.0000 0.7708 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647528 2 0.1644 0.5945 0.000 0.920 0.000 0.004 0.076 0.000
#> GSM647529 6 0.6231 0.0715 0.148 0.000 0.000 0.244 0.056 0.552
#> GSM647531 5 0.3192 0.5711 0.000 0.084 0.000 0.048 0.848 0.020
#> GSM647540 3 0.1007 0.7528 0.000 0.044 0.956 0.000 0.000 0.000
#> GSM647541 2 0.3265 0.4754 0.000 0.748 0.000 0.004 0.248 0.000
#> GSM647546 3 0.3309 0.5892 0.000 0.000 0.720 0.000 0.280 0.000
#> GSM647557 5 0.3139 0.5862 0.000 0.084 0.000 0.056 0.848 0.012
#> GSM647561 2 0.3860 0.0399 0.000 0.528 0.000 0.000 0.472 0.000
#> GSM647567 6 0.7337 0.1518 0.000 0.264 0.080 0.016 0.216 0.424
#> GSM647568 5 0.5151 0.5724 0.000 0.284 0.012 0.088 0.616 0.000
#> GSM647570 2 0.4933 0.2931 0.000 0.616 0.000 0.080 0.300 0.004
#> GSM647573 4 0.1429 0.6680 0.004 0.000 0.000 0.940 0.052 0.004
#> GSM647576 5 0.5032 0.6280 0.000 0.212 0.120 0.004 0.660 0.004
#> GSM647579 3 0.4200 0.2586 0.000 0.392 0.592 0.000 0.012 0.004
#> GSM647580 3 0.0000 0.7708 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647583 3 0.3742 0.5379 0.000 0.000 0.648 0.004 0.348 0.000
#> GSM647592 2 0.5362 0.3944 0.200 0.652 0.000 0.000 0.032 0.116
#> GSM647593 2 0.4392 0.4987 0.000 0.720 0.000 0.000 0.144 0.136
#> GSM647595 2 0.4589 0.4920 0.000 0.696 0.000 0.000 0.172 0.132
#> GSM647597 1 0.6463 0.2204 0.512 0.104 0.000 0.004 0.076 0.304
#> GSM647598 2 0.1461 0.6108 0.000 0.940 0.000 0.000 0.044 0.016
#> GSM647613 2 0.3565 0.4067 0.000 0.692 0.000 0.004 0.304 0.000
#> GSM647615 2 0.4561 0.1595 0.000 0.568 0.000 0.040 0.392 0.000
#> GSM647616 3 0.2941 0.6788 0.000 0.000 0.780 0.000 0.220 0.000
#> GSM647619 2 0.5088 0.4185 0.000 0.632 0.000 0.000 0.168 0.200
#> GSM647582 2 0.4557 0.4738 0.000 0.660 0.000 0.000 0.268 0.072
#> GSM647591 5 0.5159 -0.0278 0.000 0.444 0.000 0.004 0.480 0.072
#> GSM647527 2 0.1588 0.5963 0.000 0.924 0.000 0.004 0.072 0.000
#> GSM647530 4 0.2549 0.6356 0.008 0.000 0.000 0.884 0.036 0.072
#> GSM647532 4 0.7461 -0.1177 0.136 0.000 0.000 0.328 0.228 0.308
#> GSM647544 4 0.6234 -0.0357 0.000 0.336 0.000 0.456 0.020 0.188
#> GSM647551 2 0.5563 0.3102 0.000 0.544 0.000 0.000 0.184 0.272
#> GSM647556 3 0.1075 0.7528 0.000 0.000 0.952 0.000 0.000 0.048
#> GSM647558 5 0.4408 0.5878 0.000 0.292 0.000 0.052 0.656 0.000
#> GSM647572 3 0.6977 0.2580 0.000 0.128 0.512 0.144 0.008 0.208
#> GSM647578 3 0.6267 0.0662 0.000 0.416 0.436 0.016 0.024 0.108
#> GSM647581 5 0.4416 0.5855 0.000 0.124 0.000 0.160 0.716 0.000
#> GSM647594 2 0.5453 0.1124 0.448 0.464 0.000 0.000 0.068 0.020
#> GSM647599 1 0.1616 0.7608 0.940 0.020 0.000 0.000 0.012 0.028
#> GSM647600 2 0.5111 0.4080 0.000 0.624 0.000 0.000 0.152 0.224
#> GSM647601 2 0.1633 0.6046 0.000 0.932 0.000 0.000 0.044 0.024
#> GSM647603 2 0.3740 0.4828 0.000 0.728 0.000 0.012 0.008 0.252
#> GSM647610 2 0.6322 -0.0436 0.136 0.432 0.000 0.016 0.016 0.400
#> GSM647611 2 0.1563 0.6063 0.000 0.932 0.000 0.000 0.012 0.056
#> GSM647612 2 0.3719 0.4543 0.000 0.728 0.000 0.024 0.248 0.000
#> GSM647614 2 0.4632 0.3887 0.000 0.668 0.000 0.072 0.256 0.004
#> GSM647618 2 0.5681 0.1694 0.000 0.476 0.000 0.008 0.124 0.392
#> GSM647629 2 0.3490 0.4844 0.000 0.724 0.000 0.000 0.268 0.008
#> GSM647535 2 0.1401 0.6118 0.000 0.948 0.000 0.004 0.028 0.020
#> GSM647563 2 0.2814 0.5439 0.000 0.820 0.000 0.008 0.172 0.000
#> GSM647542 2 0.5201 0.2242 0.000 0.588 0.012 0.056 0.336 0.008
#> GSM647543 5 0.4687 0.6143 0.000 0.280 0.036 0.024 0.660 0.000
#> GSM647548 4 0.1563 0.6625 0.000 0.000 0.000 0.932 0.056 0.012
#> GSM647554 2 0.5406 0.3387 0.000 0.568 0.000 0.000 0.160 0.272
#> GSM647555 2 0.4034 0.3281 0.000 0.648 0.000 0.012 0.336 0.004
#> GSM647559 2 0.4950 0.2864 0.000 0.592 0.000 0.036 0.024 0.348
#> GSM647562 2 0.5796 0.2295 0.000 0.544 0.000 0.120 0.024 0.312
#> GSM647564 3 0.0000 0.7708 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647571 6 0.6630 -0.0277 0.000 0.344 0.000 0.268 0.028 0.360
#> GSM647584 2 0.4631 0.4833 0.000 0.692 0.000 0.000 0.140 0.168
#> GSM647585 3 0.0790 0.7613 0.000 0.000 0.968 0.000 0.000 0.032
#> GSM647586 2 0.0692 0.6097 0.000 0.976 0.000 0.004 0.020 0.000
#> GSM647587 2 0.4054 0.5066 0.000 0.736 0.000 0.020 0.024 0.220
#> GSM647588 2 0.5828 0.4017 0.000 0.576 0.000 0.028 0.144 0.252
#> GSM647596 2 0.2764 0.6086 0.020 0.872 0.000 0.000 0.084 0.024
#> GSM647602 3 0.0000 0.7708 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647609 2 0.1934 0.6010 0.000 0.916 0.000 0.000 0.044 0.040
#> GSM647620 2 0.1088 0.6101 0.000 0.960 0.000 0.000 0.016 0.024
#> GSM647627 2 0.0692 0.6098 0.000 0.976 0.000 0.000 0.020 0.004
#> GSM647628 2 0.4602 0.4812 0.000 0.720 0.000 0.112 0.156 0.012
#> GSM647533 1 0.4640 0.6032 0.684 0.000 0.000 0.012 0.064 0.240
#> GSM647536 6 0.7704 0.0212 0.236 0.000 0.000 0.244 0.224 0.296
#> GSM647537 1 0.4176 0.6465 0.732 0.000 0.000 0.004 0.064 0.200
#> GSM647606 1 0.0820 0.7947 0.972 0.000 0.000 0.000 0.012 0.016
#> GSM647621 4 0.6128 -0.0631 0.340 0.000 0.000 0.344 0.000 0.316
#> GSM647626 3 0.0363 0.7683 0.012 0.000 0.988 0.000 0.000 0.000
#> GSM647538 1 0.5138 0.4181 0.536 0.000 0.000 0.028 0.036 0.400
#> GSM647575 4 0.1364 0.6687 0.016 0.000 0.000 0.952 0.012 0.020
#> GSM647590 1 0.6118 0.3574 0.532 0.000 0.000 0.256 0.028 0.184
#> GSM647605 1 0.0717 0.7929 0.976 0.000 0.000 0.000 0.008 0.016
#> GSM647607 4 0.1745 0.6520 0.068 0.000 0.000 0.920 0.000 0.012
#> GSM647608 4 0.1448 0.6672 0.016 0.000 0.000 0.948 0.012 0.024
#> GSM647622 1 0.0000 0.7963 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647623 1 0.0547 0.7965 0.980 0.000 0.000 0.000 0.000 0.020
#> GSM647624 1 0.0881 0.7944 0.972 0.000 0.000 0.008 0.012 0.008
#> GSM647625 1 0.0146 0.7959 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM647534 6 0.6796 0.0735 0.236 0.076 0.000 0.024 0.124 0.540
#> GSM647539 4 0.3624 0.6055 0.024 0.012 0.000 0.820 0.024 0.120
#> GSM647566 4 0.5642 0.3134 0.064 0.004 0.000 0.556 0.036 0.340
#> GSM647589 4 0.1251 0.6662 0.000 0.000 0.024 0.956 0.012 0.008
#> GSM647604 1 0.0291 0.7949 0.992 0.000 0.000 0.000 0.004 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)
#> Error in mat[ceiling(1:nr/h_ratio), ceiling(1:nc/w_ratio), drop = FALSE]: subscript out of bounds
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) development.stage(p) other(p) k
#> SD:NMF 100 9.58e-11 0.185797 0.7059 2
#> SD:NMF 90 1.90e-13 0.004660 0.1596 3
#> SD:NMF 96 7.90e-12 0.040254 0.0394 4
#> SD:NMF 65 4.71e-11 0.000622 0.1521 5
#> SD:NMF 54 8.16e-07 0.013272 0.3874 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["CV", "hclust"]
# you can also extract it by
# res = res_list["CV:hclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'CV' method.
#> Subgroups are detected by 'hclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.557 0.807 0.910 0.3432 0.650 0.650
#> 3 3 0.528 0.795 0.902 0.2706 0.898 0.845
#> 4 4 0.546 0.763 0.865 0.1547 0.973 0.953
#> 5 5 0.538 0.656 0.793 0.1813 0.835 0.700
#> 6 6 0.521 0.688 0.779 0.0721 0.910 0.773
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 2
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM647569 2 0.3431 0.8875 0.064 0.936
#> GSM647574 2 0.9209 0.3789 0.336 0.664
#> GSM647577 2 0.3431 0.8875 0.064 0.936
#> GSM647547 2 1.0000 -0.2681 0.500 0.500
#> GSM647552 2 0.0938 0.9163 0.012 0.988
#> GSM647553 2 0.9286 0.3540 0.344 0.656
#> GSM647565 2 0.9427 0.2815 0.360 0.640
#> GSM647545 2 0.0000 0.9208 0.000 1.000
#> GSM647549 2 0.0376 0.9198 0.004 0.996
#> GSM647550 2 0.0000 0.9208 0.000 1.000
#> GSM647560 2 0.0000 0.9208 0.000 1.000
#> GSM647617 2 0.3431 0.8875 0.064 0.936
#> GSM647528 2 0.0000 0.9208 0.000 1.000
#> GSM647529 1 0.6801 0.7757 0.820 0.180
#> GSM647531 2 0.0938 0.9175 0.012 0.988
#> GSM647540 2 0.0000 0.9208 0.000 1.000
#> GSM647541 2 0.0000 0.9208 0.000 1.000
#> GSM647546 2 0.2948 0.8948 0.052 0.948
#> GSM647557 2 0.0938 0.9163 0.012 0.988
#> GSM647561 2 0.0376 0.9198 0.004 0.996
#> GSM647567 2 0.1414 0.9134 0.020 0.980
#> GSM647568 2 0.0000 0.9208 0.000 1.000
#> GSM647570 2 0.0000 0.9208 0.000 1.000
#> GSM647573 1 0.9983 0.3091 0.524 0.476
#> GSM647576 2 0.1633 0.9113 0.024 0.976
#> GSM647579 2 0.0938 0.9168 0.012 0.988
#> GSM647580 2 0.3431 0.8875 0.064 0.936
#> GSM647583 2 0.3431 0.8875 0.064 0.936
#> GSM647592 2 0.5519 0.8149 0.128 0.872
#> GSM647593 2 0.5178 0.8279 0.116 0.884
#> GSM647595 2 0.5178 0.8279 0.116 0.884
#> GSM647597 2 0.7453 0.6867 0.212 0.788
#> GSM647598 2 0.0376 0.9197 0.004 0.996
#> GSM647613 2 0.0376 0.9197 0.004 0.996
#> GSM647615 2 0.0000 0.9208 0.000 1.000
#> GSM647616 2 0.3431 0.8875 0.064 0.936
#> GSM647619 2 0.5059 0.8324 0.112 0.888
#> GSM647582 2 0.0000 0.9208 0.000 1.000
#> GSM647591 2 0.5178 0.8279 0.116 0.884
#> GSM647527 2 0.0000 0.9208 0.000 1.000
#> GSM647530 1 0.8955 0.6784 0.688 0.312
#> GSM647532 1 0.6801 0.7757 0.820 0.180
#> GSM647544 2 0.0000 0.9208 0.000 1.000
#> GSM647551 2 0.0376 0.9198 0.004 0.996
#> GSM647556 2 0.3431 0.8875 0.064 0.936
#> GSM647558 2 0.5294 0.8201 0.120 0.880
#> GSM647572 2 0.1633 0.9113 0.024 0.976
#> GSM647578 2 0.0000 0.9208 0.000 1.000
#> GSM647581 2 0.5294 0.8201 0.120 0.880
#> GSM647594 2 0.6247 0.7777 0.156 0.844
#> GSM647599 2 0.7453 0.6950 0.212 0.788
#> GSM647600 2 0.0376 0.9198 0.004 0.996
#> GSM647601 2 0.0000 0.9208 0.000 1.000
#> GSM647603 2 0.1414 0.9134 0.020 0.980
#> GSM647610 2 0.5519 0.8219 0.128 0.872
#> GSM647611 2 0.0000 0.9208 0.000 1.000
#> GSM647612 2 0.0000 0.9208 0.000 1.000
#> GSM647614 2 0.0000 0.9208 0.000 1.000
#> GSM647618 2 0.0000 0.9208 0.000 1.000
#> GSM647629 2 0.0000 0.9208 0.000 1.000
#> GSM647535 2 0.0000 0.9208 0.000 1.000
#> GSM647563 2 0.0000 0.9208 0.000 1.000
#> GSM647542 2 0.0000 0.9208 0.000 1.000
#> GSM647543 2 0.0000 0.9208 0.000 1.000
#> GSM647548 2 0.9815 0.0578 0.420 0.580
#> GSM647554 2 0.0000 0.9208 0.000 1.000
#> GSM647555 2 0.0000 0.9208 0.000 1.000
#> GSM647559 2 0.0000 0.9208 0.000 1.000
#> GSM647562 2 0.0376 0.9195 0.004 0.996
#> GSM647564 2 0.3431 0.8875 0.064 0.936
#> GSM647571 2 0.1414 0.9134 0.020 0.980
#> GSM647584 2 0.0376 0.9198 0.004 0.996
#> GSM647585 2 0.3431 0.8875 0.064 0.936
#> GSM647586 2 0.0000 0.9208 0.000 1.000
#> GSM647587 2 0.0000 0.9208 0.000 1.000
#> GSM647588 2 0.0000 0.9208 0.000 1.000
#> GSM647596 2 0.0000 0.9208 0.000 1.000
#> GSM647602 2 0.3431 0.8875 0.064 0.936
#> GSM647609 2 0.0000 0.9208 0.000 1.000
#> GSM647620 2 0.0000 0.9208 0.000 1.000
#> GSM647627 2 0.0000 0.9208 0.000 1.000
#> GSM647628 2 0.0000 0.9208 0.000 1.000
#> GSM647533 1 0.0376 0.7797 0.996 0.004
#> GSM647536 1 0.6801 0.7757 0.820 0.180
#> GSM647537 1 0.0376 0.7797 0.996 0.004
#> GSM647606 1 0.0376 0.7802 0.996 0.004
#> GSM647621 2 0.9993 -0.1704 0.484 0.516
#> GSM647626 2 0.4562 0.8639 0.096 0.904
#> GSM647538 1 0.7950 0.7032 0.760 0.240
#> GSM647575 1 0.9129 0.6684 0.672 0.328
#> GSM647590 1 0.9087 0.6730 0.676 0.324
#> GSM647605 1 0.0376 0.7802 0.996 0.004
#> GSM647607 1 0.9129 0.6684 0.672 0.328
#> GSM647608 1 0.9580 0.5821 0.620 0.380
#> GSM647622 1 0.0376 0.7802 0.996 0.004
#> GSM647623 1 0.1843 0.7816 0.972 0.028
#> GSM647624 1 0.0376 0.7802 0.996 0.004
#> GSM647625 1 0.1843 0.7816 0.972 0.028
#> GSM647534 1 0.8081 0.6968 0.752 0.248
#> GSM647539 1 0.9248 0.6553 0.660 0.340
#> GSM647566 1 0.9358 0.6412 0.648 0.352
#> GSM647589 1 0.9580 0.5821 0.620 0.380
#> GSM647604 1 0.0376 0.7802 0.996 0.004
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 2 0.3784 0.831 0.004 0.864 0.132
#> GSM647574 2 0.6680 -0.250 0.008 0.508 0.484
#> GSM647577 2 0.3784 0.831 0.004 0.864 0.132
#> GSM647547 3 0.5797 0.588 0.008 0.280 0.712
#> GSM647552 2 0.1015 0.921 0.012 0.980 0.008
#> GSM647553 3 0.6676 0.301 0.008 0.476 0.516
#> GSM647565 3 0.6235 0.444 0.000 0.436 0.564
#> GSM647545 2 0.0424 0.926 0.000 0.992 0.008
#> GSM647549 2 0.0661 0.925 0.004 0.988 0.008
#> GSM647550 2 0.0747 0.924 0.000 0.984 0.016
#> GSM647560 2 0.0424 0.926 0.000 0.992 0.008
#> GSM647617 2 0.3784 0.831 0.004 0.864 0.132
#> GSM647528 2 0.0237 0.926 0.000 0.996 0.004
#> GSM647529 1 0.8547 0.486 0.532 0.104 0.364
#> GSM647531 2 0.1453 0.916 0.008 0.968 0.024
#> GSM647540 2 0.0747 0.924 0.000 0.984 0.016
#> GSM647541 2 0.0592 0.925 0.000 0.988 0.012
#> GSM647546 2 0.3500 0.846 0.004 0.880 0.116
#> GSM647557 2 0.1015 0.921 0.012 0.980 0.008
#> GSM647561 2 0.0661 0.925 0.004 0.988 0.008
#> GSM647567 2 0.1636 0.919 0.020 0.964 0.016
#> GSM647568 2 0.0424 0.926 0.000 0.992 0.008
#> GSM647570 2 0.0237 0.926 0.000 0.996 0.004
#> GSM647573 3 0.5502 0.598 0.008 0.248 0.744
#> GSM647576 2 0.2261 0.891 0.000 0.932 0.068
#> GSM647579 2 0.1163 0.919 0.000 0.972 0.028
#> GSM647580 2 0.3784 0.831 0.004 0.864 0.132
#> GSM647583 2 0.3784 0.831 0.004 0.864 0.132
#> GSM647592 2 0.3482 0.819 0.128 0.872 0.000
#> GSM647593 2 0.3500 0.831 0.116 0.880 0.004
#> GSM647595 2 0.3500 0.831 0.116 0.880 0.004
#> GSM647597 2 0.5366 0.679 0.208 0.776 0.016
#> GSM647598 2 0.0475 0.926 0.004 0.992 0.004
#> GSM647613 2 0.0475 0.926 0.004 0.992 0.004
#> GSM647615 2 0.0237 0.926 0.000 0.996 0.004
#> GSM647616 2 0.3784 0.831 0.004 0.864 0.132
#> GSM647619 2 0.3425 0.836 0.112 0.884 0.004
#> GSM647582 2 0.0237 0.926 0.000 0.996 0.004
#> GSM647591 2 0.3500 0.831 0.116 0.880 0.004
#> GSM647527 2 0.0237 0.926 0.000 0.996 0.004
#> GSM647530 1 0.9755 0.104 0.396 0.228 0.376
#> GSM647532 1 0.8547 0.486 0.532 0.104 0.364
#> GSM647544 2 0.0237 0.926 0.000 0.996 0.004
#> GSM647551 2 0.0475 0.926 0.004 0.992 0.004
#> GSM647556 2 0.3784 0.831 0.004 0.864 0.132
#> GSM647558 2 0.3752 0.800 0.000 0.856 0.144
#> GSM647572 2 0.1753 0.906 0.000 0.952 0.048
#> GSM647578 2 0.0424 0.926 0.000 0.992 0.008
#> GSM647581 2 0.3752 0.800 0.000 0.856 0.144
#> GSM647594 2 0.4291 0.781 0.152 0.840 0.008
#> GSM647599 2 0.6402 0.652 0.200 0.744 0.056
#> GSM647600 2 0.0475 0.927 0.004 0.992 0.004
#> GSM647601 2 0.0237 0.926 0.000 0.996 0.004
#> GSM647603 2 0.0892 0.921 0.000 0.980 0.020
#> GSM647610 2 0.3715 0.824 0.128 0.868 0.004
#> GSM647611 2 0.0237 0.926 0.000 0.996 0.004
#> GSM647612 2 0.0424 0.926 0.000 0.992 0.008
#> GSM647614 2 0.0424 0.926 0.000 0.992 0.008
#> GSM647618 2 0.0237 0.926 0.000 0.996 0.004
#> GSM647629 2 0.0424 0.926 0.000 0.992 0.008
#> GSM647535 2 0.0237 0.926 0.000 0.996 0.004
#> GSM647563 2 0.0237 0.926 0.000 0.996 0.004
#> GSM647542 2 0.0424 0.926 0.000 0.992 0.008
#> GSM647543 2 0.0424 0.926 0.000 0.992 0.008
#> GSM647548 3 0.6264 0.524 0.004 0.380 0.616
#> GSM647554 2 0.0747 0.924 0.000 0.984 0.016
#> GSM647555 2 0.0237 0.926 0.000 0.996 0.004
#> GSM647559 2 0.0237 0.926 0.000 0.996 0.004
#> GSM647562 2 0.0475 0.926 0.004 0.992 0.004
#> GSM647564 2 0.3784 0.831 0.004 0.864 0.132
#> GSM647571 2 0.0892 0.921 0.000 0.980 0.020
#> GSM647584 2 0.0475 0.926 0.004 0.992 0.004
#> GSM647585 2 0.3784 0.831 0.004 0.864 0.132
#> GSM647586 2 0.0237 0.926 0.000 0.996 0.004
#> GSM647587 2 0.0237 0.926 0.000 0.996 0.004
#> GSM647588 2 0.0424 0.926 0.000 0.992 0.008
#> GSM647596 2 0.0237 0.926 0.000 0.996 0.004
#> GSM647602 2 0.3784 0.831 0.004 0.864 0.132
#> GSM647609 2 0.0237 0.926 0.000 0.996 0.004
#> GSM647620 2 0.0237 0.926 0.000 0.996 0.004
#> GSM647627 2 0.0237 0.926 0.000 0.996 0.004
#> GSM647628 2 0.0237 0.926 0.000 0.996 0.004
#> GSM647533 1 0.0424 0.763 0.992 0.000 0.008
#> GSM647536 1 0.8547 0.486 0.532 0.104 0.364
#> GSM647537 1 0.0424 0.763 0.992 0.000 0.008
#> GSM647606 1 0.1860 0.772 0.948 0.000 0.052
#> GSM647621 3 0.8665 0.455 0.124 0.324 0.552
#> GSM647626 2 0.5053 0.776 0.024 0.812 0.164
#> GSM647538 1 0.7413 0.543 0.692 0.204 0.104
#> GSM647575 3 0.1482 0.548 0.020 0.012 0.968
#> GSM647590 3 0.1267 0.533 0.024 0.004 0.972
#> GSM647605 1 0.1860 0.772 0.948 0.000 0.052
#> GSM647607 3 0.1315 0.543 0.020 0.008 0.972
#> GSM647608 3 0.3375 0.607 0.008 0.100 0.892
#> GSM647622 1 0.1860 0.772 0.948 0.000 0.052
#> GSM647623 1 0.1585 0.764 0.964 0.028 0.008
#> GSM647624 1 0.1860 0.772 0.948 0.000 0.052
#> GSM647625 1 0.1585 0.764 0.964 0.028 0.008
#> GSM647534 1 0.7501 0.529 0.684 0.212 0.104
#> GSM647539 3 0.0661 0.543 0.004 0.008 0.988
#> GSM647566 3 0.1620 0.542 0.012 0.024 0.964
#> GSM647589 3 0.3375 0.607 0.008 0.100 0.892
#> GSM647604 1 0.1860 0.772 0.948 0.000 0.052
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 2 0.5314 0.699 0.000 0.740 0.084 0.176
#> GSM647574 4 0.6520 0.373 0.000 0.384 0.080 0.536
#> GSM647577 2 0.5314 0.699 0.000 0.740 0.084 0.176
#> GSM647547 4 0.4253 0.513 0.000 0.208 0.016 0.776
#> GSM647552 2 0.1474 0.867 0.000 0.948 0.052 0.000
#> GSM647553 4 0.6176 0.399 0.000 0.368 0.060 0.572
#> GSM647565 4 0.5298 0.413 0.000 0.372 0.016 0.612
#> GSM647545 2 0.0921 0.875 0.000 0.972 0.028 0.000
#> GSM647549 2 0.1118 0.872 0.000 0.964 0.036 0.000
#> GSM647550 2 0.3301 0.827 0.000 0.876 0.076 0.048
#> GSM647560 2 0.0524 0.877 0.000 0.988 0.008 0.004
#> GSM647617 2 0.5314 0.699 0.000 0.740 0.084 0.176
#> GSM647528 2 0.0469 0.878 0.000 0.988 0.012 0.000
#> GSM647529 3 0.7964 0.741 0.128 0.048 0.532 0.292
#> GSM647531 2 0.1798 0.865 0.000 0.944 0.040 0.016
#> GSM647540 2 0.3383 0.825 0.000 0.872 0.076 0.052
#> GSM647541 2 0.3081 0.835 0.000 0.888 0.064 0.048
#> GSM647546 2 0.5011 0.723 0.000 0.764 0.076 0.160
#> GSM647557 2 0.1302 0.869 0.000 0.956 0.044 0.000
#> GSM647561 2 0.1118 0.872 0.000 0.964 0.036 0.000
#> GSM647567 2 0.4387 0.797 0.000 0.804 0.144 0.052
#> GSM647568 2 0.0657 0.877 0.000 0.984 0.012 0.004
#> GSM647570 2 0.0469 0.879 0.000 0.988 0.012 0.000
#> GSM647573 4 0.3925 0.515 0.000 0.176 0.016 0.808
#> GSM647576 2 0.4130 0.789 0.000 0.828 0.064 0.108
#> GSM647579 2 0.3239 0.831 0.000 0.880 0.052 0.068
#> GSM647580 2 0.5314 0.699 0.000 0.740 0.084 0.176
#> GSM647583 2 0.5314 0.699 0.000 0.740 0.084 0.176
#> GSM647592 2 0.4355 0.710 0.012 0.772 0.212 0.004
#> GSM647593 2 0.3726 0.724 0.000 0.788 0.212 0.000
#> GSM647595 2 0.3726 0.724 0.000 0.788 0.212 0.000
#> GSM647597 2 0.5732 0.568 0.064 0.672 0.264 0.000
#> GSM647598 2 0.0817 0.876 0.000 0.976 0.024 0.000
#> GSM647613 2 0.0817 0.876 0.000 0.976 0.024 0.000
#> GSM647615 2 0.0336 0.877 0.000 0.992 0.008 0.000
#> GSM647616 2 0.5314 0.699 0.000 0.740 0.084 0.176
#> GSM647619 2 0.3649 0.733 0.000 0.796 0.204 0.000
#> GSM647582 2 0.0707 0.877 0.000 0.980 0.020 0.000
#> GSM647591 2 0.3726 0.724 0.000 0.788 0.212 0.000
#> GSM647527 2 0.0469 0.878 0.000 0.988 0.012 0.000
#> GSM647530 3 0.7892 0.470 0.024 0.164 0.504 0.308
#> GSM647532 3 0.7964 0.741 0.128 0.048 0.532 0.292
#> GSM647544 2 0.0592 0.879 0.000 0.984 0.016 0.000
#> GSM647551 2 0.1022 0.875 0.000 0.968 0.032 0.000
#> GSM647556 2 0.5355 0.694 0.000 0.736 0.084 0.180
#> GSM647558 2 0.3812 0.768 0.000 0.832 0.028 0.140
#> GSM647572 2 0.2844 0.845 0.000 0.900 0.048 0.052
#> GSM647578 2 0.1406 0.872 0.000 0.960 0.024 0.016
#> GSM647581 2 0.3812 0.768 0.000 0.832 0.028 0.140
#> GSM647594 2 0.4516 0.654 0.012 0.736 0.252 0.000
#> GSM647599 2 0.7427 0.502 0.112 0.604 0.240 0.044
#> GSM647600 2 0.1545 0.874 0.000 0.952 0.040 0.008
#> GSM647601 2 0.0469 0.878 0.000 0.988 0.012 0.000
#> GSM647603 2 0.1388 0.872 0.000 0.960 0.012 0.028
#> GSM647610 2 0.5075 0.726 0.040 0.752 0.200 0.008
#> GSM647611 2 0.0707 0.877 0.000 0.980 0.020 0.000
#> GSM647612 2 0.0524 0.877 0.000 0.988 0.008 0.004
#> GSM647614 2 0.0524 0.877 0.000 0.988 0.008 0.004
#> GSM647618 2 0.0817 0.876 0.000 0.976 0.024 0.000
#> GSM647629 2 0.1284 0.872 0.000 0.964 0.024 0.012
#> GSM647535 2 0.0469 0.878 0.000 0.988 0.012 0.000
#> GSM647563 2 0.0707 0.877 0.000 0.980 0.020 0.000
#> GSM647542 2 0.0657 0.877 0.000 0.984 0.012 0.004
#> GSM647543 2 0.0657 0.877 0.000 0.984 0.012 0.004
#> GSM647548 4 0.5271 0.419 0.000 0.340 0.020 0.640
#> GSM647554 2 0.3383 0.825 0.000 0.872 0.076 0.052
#> GSM647555 2 0.0469 0.878 0.000 0.988 0.012 0.000
#> GSM647559 2 0.0707 0.877 0.000 0.980 0.020 0.000
#> GSM647562 2 0.0817 0.876 0.000 0.976 0.024 0.000
#> GSM647564 2 0.5355 0.694 0.000 0.736 0.084 0.180
#> GSM647571 2 0.1388 0.872 0.000 0.960 0.012 0.028
#> GSM647584 2 0.1022 0.875 0.000 0.968 0.032 0.000
#> GSM647585 2 0.5355 0.694 0.000 0.736 0.084 0.180
#> GSM647586 2 0.0469 0.878 0.000 0.988 0.012 0.000
#> GSM647587 2 0.0707 0.877 0.000 0.980 0.020 0.000
#> GSM647588 2 0.1042 0.875 0.000 0.972 0.020 0.008
#> GSM647596 2 0.0592 0.878 0.000 0.984 0.016 0.000
#> GSM647602 2 0.5355 0.694 0.000 0.736 0.084 0.180
#> GSM647609 2 0.0469 0.878 0.000 0.988 0.012 0.000
#> GSM647620 2 0.0469 0.878 0.000 0.988 0.012 0.000
#> GSM647627 2 0.0469 0.878 0.000 0.988 0.012 0.000
#> GSM647628 2 0.0376 0.877 0.000 0.992 0.004 0.004
#> GSM647533 1 0.2149 0.922 0.912 0.000 0.088 0.000
#> GSM647536 3 0.7964 0.741 0.128 0.048 0.532 0.292
#> GSM647537 1 0.2149 0.922 0.912 0.000 0.088 0.000
#> GSM647606 1 0.0000 0.956 1.000 0.000 0.000 0.000
#> GSM647621 4 0.8360 0.373 0.112 0.204 0.128 0.556
#> GSM647626 2 0.6408 0.647 0.020 0.692 0.124 0.164
#> GSM647538 3 0.3893 0.519 0.196 0.000 0.796 0.008
#> GSM647575 4 0.1902 0.448 0.004 0.000 0.064 0.932
#> GSM647590 4 0.2124 0.443 0.008 0.000 0.068 0.924
#> GSM647605 1 0.0000 0.956 1.000 0.000 0.000 0.000
#> GSM647607 4 0.1978 0.445 0.004 0.000 0.068 0.928
#> GSM647608 4 0.1211 0.508 0.000 0.040 0.000 0.960
#> GSM647622 1 0.0000 0.956 1.000 0.000 0.000 0.000
#> GSM647623 1 0.1798 0.926 0.944 0.016 0.040 0.000
#> GSM647624 1 0.0000 0.956 1.000 0.000 0.000 0.000
#> GSM647625 1 0.1798 0.926 0.944 0.016 0.040 0.000
#> GSM647534 3 0.4034 0.525 0.192 0.004 0.796 0.008
#> GSM647539 4 0.1867 0.444 0.000 0.000 0.072 0.928
#> GSM647566 4 0.2408 0.419 0.000 0.000 0.104 0.896
#> GSM647589 4 0.1211 0.508 0.000 0.040 0.000 0.960
#> GSM647604 1 0.0000 0.956 1.000 0.000 0.000 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.4256 0.7774 0.000 0.436 0.564 0.000 0.000
#> GSM647574 3 0.6257 0.0545 0.000 0.168 0.512 0.320 0.000
#> GSM647577 3 0.4256 0.7774 0.000 0.436 0.564 0.000 0.000
#> GSM647547 4 0.5896 0.4814 0.000 0.128 0.308 0.564 0.000
#> GSM647552 2 0.2172 0.7628 0.000 0.908 0.076 0.000 0.016
#> GSM647553 3 0.6300 -0.0689 0.000 0.164 0.488 0.348 0.000
#> GSM647565 4 0.6656 0.1093 0.000 0.308 0.252 0.440 0.000
#> GSM647545 2 0.0771 0.8056 0.000 0.976 0.020 0.000 0.004
#> GSM647549 2 0.1357 0.7905 0.000 0.948 0.048 0.000 0.004
#> GSM647550 2 0.3210 0.5227 0.000 0.788 0.212 0.000 0.000
#> GSM647560 2 0.0880 0.8009 0.000 0.968 0.032 0.000 0.000
#> GSM647617 3 0.4256 0.7774 0.000 0.436 0.564 0.000 0.000
#> GSM647528 2 0.0000 0.8085 0.000 1.000 0.000 0.000 0.000
#> GSM647529 5 0.6598 0.7273 0.064 0.032 0.036 0.264 0.604
#> GSM647531 2 0.2050 0.7786 0.000 0.920 0.064 0.008 0.008
#> GSM647540 2 0.3210 0.5196 0.000 0.788 0.212 0.000 0.000
#> GSM647541 2 0.3109 0.5505 0.000 0.800 0.200 0.000 0.000
#> GSM647546 3 0.4294 0.7159 0.000 0.468 0.532 0.000 0.000
#> GSM647557 2 0.2046 0.7688 0.000 0.916 0.068 0.000 0.016
#> GSM647561 2 0.1357 0.7905 0.000 0.948 0.048 0.000 0.004
#> GSM647567 2 0.4613 0.2828 0.000 0.620 0.360 0.000 0.020
#> GSM647568 2 0.1341 0.7866 0.000 0.944 0.056 0.000 0.000
#> GSM647570 2 0.0703 0.8069 0.000 0.976 0.024 0.000 0.000
#> GSM647573 4 0.5512 0.5068 0.000 0.104 0.276 0.620 0.000
#> GSM647576 2 0.4030 -0.0573 0.000 0.648 0.352 0.000 0.000
#> GSM647579 2 0.3395 0.4554 0.000 0.764 0.236 0.000 0.000
#> GSM647580 3 0.4256 0.7774 0.000 0.436 0.564 0.000 0.000
#> GSM647583 3 0.4256 0.7774 0.000 0.436 0.564 0.000 0.000
#> GSM647592 2 0.5654 0.3605 0.008 0.592 0.324 0.000 0.076
#> GSM647593 2 0.5104 0.4074 0.000 0.632 0.308 0.000 0.060
#> GSM647595 2 0.5104 0.4074 0.000 0.632 0.308 0.000 0.060
#> GSM647597 2 0.6886 0.2169 0.040 0.508 0.316 0.000 0.136
#> GSM647598 2 0.0451 0.8096 0.000 0.988 0.004 0.000 0.008
#> GSM647613 2 0.0451 0.8096 0.000 0.988 0.004 0.000 0.008
#> GSM647615 2 0.1121 0.7940 0.000 0.956 0.044 0.000 0.000
#> GSM647616 3 0.4256 0.7774 0.000 0.436 0.564 0.000 0.000
#> GSM647619 2 0.5086 0.4156 0.000 0.636 0.304 0.000 0.060
#> GSM647582 2 0.0566 0.8089 0.000 0.984 0.012 0.000 0.004
#> GSM647591 2 0.5104 0.4074 0.000 0.632 0.308 0.000 0.060
#> GSM647527 2 0.0000 0.8085 0.000 1.000 0.000 0.000 0.000
#> GSM647530 5 0.7383 0.4514 0.008 0.164 0.052 0.272 0.504
#> GSM647532 5 0.6598 0.7273 0.064 0.032 0.036 0.264 0.604
#> GSM647544 2 0.0693 0.8095 0.000 0.980 0.008 0.000 0.012
#> GSM647551 2 0.1121 0.7960 0.000 0.956 0.044 0.000 0.000
#> GSM647556 3 0.4242 0.7763 0.000 0.428 0.572 0.000 0.000
#> GSM647558 2 0.4102 0.5817 0.000 0.796 0.080 0.120 0.004
#> GSM647572 2 0.3596 0.5316 0.000 0.784 0.200 0.000 0.016
#> GSM647578 2 0.1671 0.7655 0.000 0.924 0.076 0.000 0.000
#> GSM647581 2 0.4102 0.5817 0.000 0.796 0.080 0.120 0.004
#> GSM647594 2 0.5892 0.3277 0.008 0.580 0.312 0.000 0.100
#> GSM647599 3 0.7104 0.3468 0.096 0.316 0.512 0.004 0.072
#> GSM647600 2 0.1851 0.7856 0.000 0.912 0.088 0.000 0.000
#> GSM647601 2 0.0000 0.8085 0.000 1.000 0.000 0.000 0.000
#> GSM647603 2 0.2464 0.7323 0.000 0.888 0.096 0.000 0.016
#> GSM647610 2 0.5723 0.1547 0.024 0.556 0.376 0.000 0.044
#> GSM647611 2 0.0566 0.8089 0.000 0.984 0.012 0.000 0.004
#> GSM647612 2 0.0880 0.7990 0.000 0.968 0.032 0.000 0.000
#> GSM647614 2 0.0880 0.7990 0.000 0.968 0.032 0.000 0.000
#> GSM647618 2 0.0693 0.8079 0.000 0.980 0.012 0.000 0.008
#> GSM647629 2 0.1732 0.7618 0.000 0.920 0.080 0.000 0.000
#> GSM647535 2 0.0609 0.8057 0.000 0.980 0.020 0.000 0.000
#> GSM647563 2 0.0566 0.8089 0.000 0.984 0.012 0.000 0.004
#> GSM647542 2 0.1341 0.7866 0.000 0.944 0.056 0.000 0.000
#> GSM647543 2 0.1341 0.7866 0.000 0.944 0.056 0.000 0.000
#> GSM647548 4 0.6555 0.3091 0.000 0.284 0.212 0.500 0.004
#> GSM647554 2 0.3242 0.5141 0.000 0.784 0.216 0.000 0.000
#> GSM647555 2 0.1121 0.7961 0.000 0.956 0.044 0.000 0.000
#> GSM647559 2 0.0566 0.8089 0.000 0.984 0.012 0.000 0.004
#> GSM647562 2 0.0693 0.8083 0.000 0.980 0.012 0.000 0.008
#> GSM647564 3 0.4249 0.7778 0.000 0.432 0.568 0.000 0.000
#> GSM647571 2 0.2519 0.7272 0.000 0.884 0.100 0.000 0.016
#> GSM647584 2 0.1121 0.7960 0.000 0.956 0.044 0.000 0.000
#> GSM647585 3 0.4262 0.7649 0.000 0.440 0.560 0.000 0.000
#> GSM647586 2 0.0000 0.8085 0.000 1.000 0.000 0.000 0.000
#> GSM647587 2 0.0566 0.8089 0.000 0.984 0.012 0.000 0.004
#> GSM647588 2 0.1478 0.7778 0.000 0.936 0.064 0.000 0.000
#> GSM647596 2 0.0162 0.8091 0.000 0.996 0.000 0.000 0.004
#> GSM647602 3 0.4249 0.7778 0.000 0.432 0.568 0.000 0.000
#> GSM647609 2 0.0000 0.8085 0.000 1.000 0.000 0.000 0.000
#> GSM647620 2 0.0609 0.8057 0.000 0.980 0.020 0.000 0.000
#> GSM647627 2 0.0000 0.8085 0.000 1.000 0.000 0.000 0.000
#> GSM647628 2 0.0703 0.8022 0.000 0.976 0.024 0.000 0.000
#> GSM647533 1 0.2732 0.8484 0.840 0.000 0.000 0.000 0.160
#> GSM647536 5 0.6598 0.7273 0.064 0.032 0.036 0.264 0.604
#> GSM647537 1 0.2732 0.8484 0.840 0.000 0.000 0.000 0.160
#> GSM647606 1 0.0000 0.9433 1.000 0.000 0.000 0.000 0.000
#> GSM647621 3 0.7346 -0.4602 0.096 0.008 0.436 0.388 0.072
#> GSM647626 3 0.5703 0.7146 0.008 0.380 0.552 0.004 0.056
#> GSM647538 5 0.2959 0.5823 0.112 0.000 0.016 0.008 0.864
#> GSM647575 4 0.0613 0.5331 0.004 0.000 0.004 0.984 0.008
#> GSM647590 4 0.1756 0.5193 0.008 0.000 0.036 0.940 0.016
#> GSM647605 1 0.0000 0.9433 1.000 0.000 0.000 0.000 0.000
#> GSM647607 4 0.0451 0.5305 0.004 0.000 0.000 0.988 0.008
#> GSM647608 4 0.3942 0.5567 0.000 0.020 0.232 0.748 0.000
#> GSM647622 1 0.0000 0.9433 1.000 0.000 0.000 0.000 0.000
#> GSM647623 1 0.1430 0.9173 0.944 0.000 0.052 0.000 0.004
#> GSM647624 1 0.0000 0.9433 1.000 0.000 0.000 0.000 0.000
#> GSM647625 1 0.1430 0.9173 0.944 0.000 0.052 0.000 0.004
#> GSM647534 5 0.3096 0.5852 0.108 0.000 0.024 0.008 0.860
#> GSM647539 4 0.1648 0.5226 0.000 0.000 0.040 0.940 0.020
#> GSM647566 4 0.2300 0.4968 0.000 0.000 0.040 0.908 0.052
#> GSM647589 4 0.3942 0.5567 0.000 0.020 0.232 0.748 0.000
#> GSM647604 1 0.0000 0.9433 1.000 0.000 0.000 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.3765 0.76349 0.000 0.404 0.596 0.000 0.000 0.000
#> GSM647574 3 0.5701 0.16382 0.000 0.144 0.616 0.204 0.036 0.000
#> GSM647577 3 0.3765 0.76349 0.000 0.404 0.596 0.000 0.000 0.000
#> GSM647547 4 0.6400 0.39520 0.000 0.104 0.388 0.440 0.068 0.000
#> GSM647552 2 0.2135 0.76493 0.000 0.872 0.000 0.000 0.128 0.000
#> GSM647553 3 0.5827 0.03832 0.000 0.128 0.600 0.228 0.044 0.000
#> GSM647565 3 0.7052 -0.13251 0.000 0.280 0.332 0.324 0.064 0.000
#> GSM647545 2 0.1075 0.84873 0.000 0.952 0.000 0.000 0.048 0.000
#> GSM647549 2 0.1610 0.81609 0.000 0.916 0.000 0.000 0.084 0.000
#> GSM647550 2 0.3287 0.55873 0.000 0.768 0.220 0.000 0.012 0.000
#> GSM647560 2 0.0935 0.85548 0.000 0.964 0.032 0.000 0.004 0.000
#> GSM647617 3 0.3899 0.76123 0.000 0.404 0.592 0.000 0.004 0.000
#> GSM647528 2 0.0777 0.85897 0.000 0.972 0.004 0.000 0.024 0.000
#> GSM647529 6 0.6429 0.72511 0.012 0.016 0.044 0.236 0.108 0.584
#> GSM647531 2 0.2214 0.79621 0.000 0.892 0.012 0.004 0.092 0.000
#> GSM647540 2 0.3190 0.56713 0.000 0.772 0.220 0.000 0.008 0.000
#> GSM647541 2 0.3171 0.59754 0.000 0.784 0.204 0.000 0.012 0.000
#> GSM647546 3 0.3955 0.69719 0.000 0.436 0.560 0.000 0.004 0.000
#> GSM647557 2 0.2048 0.77456 0.000 0.880 0.000 0.000 0.120 0.000
#> GSM647561 2 0.1610 0.81609 0.000 0.916 0.000 0.000 0.084 0.000
#> GSM647567 2 0.5648 0.08343 0.000 0.536 0.240 0.000 0.224 0.000
#> GSM647568 2 0.1349 0.84135 0.000 0.940 0.056 0.000 0.004 0.000
#> GSM647570 2 0.1003 0.85818 0.000 0.964 0.020 0.000 0.016 0.000
#> GSM647573 4 0.6141 0.41450 0.000 0.080 0.356 0.496 0.068 0.000
#> GSM647576 2 0.3899 0.00611 0.000 0.628 0.364 0.000 0.008 0.000
#> GSM647579 2 0.3373 0.49982 0.000 0.744 0.248 0.000 0.008 0.000
#> GSM647580 3 0.3899 0.76123 0.000 0.404 0.592 0.000 0.004 0.000
#> GSM647583 3 0.3765 0.76349 0.000 0.404 0.596 0.000 0.000 0.000
#> GSM647592 5 0.3844 0.75440 0.004 0.312 0.008 0.000 0.676 0.000
#> GSM647593 5 0.3881 0.78355 0.000 0.396 0.004 0.000 0.600 0.000
#> GSM647595 5 0.3881 0.78355 0.000 0.396 0.004 0.000 0.600 0.000
#> GSM647597 5 0.4424 0.60150 0.004 0.224 0.004 0.000 0.708 0.060
#> GSM647598 2 0.1082 0.85902 0.000 0.956 0.004 0.000 0.040 0.000
#> GSM647613 2 0.1082 0.85902 0.000 0.956 0.004 0.000 0.040 0.000
#> GSM647615 2 0.1265 0.84930 0.000 0.948 0.044 0.000 0.008 0.000
#> GSM647616 3 0.3765 0.76349 0.000 0.404 0.596 0.000 0.000 0.000
#> GSM647619 5 0.3899 0.77340 0.000 0.404 0.004 0.000 0.592 0.000
#> GSM647582 2 0.1007 0.85479 0.000 0.956 0.000 0.000 0.044 0.000
#> GSM647591 5 0.3881 0.78355 0.000 0.396 0.004 0.000 0.600 0.000
#> GSM647527 2 0.0777 0.85897 0.000 0.972 0.004 0.000 0.024 0.000
#> GSM647530 6 0.7754 0.48513 0.000 0.136 0.056 0.240 0.120 0.448
#> GSM647532 6 0.6429 0.72511 0.012 0.016 0.044 0.236 0.108 0.584
#> GSM647544 2 0.1367 0.86015 0.000 0.944 0.012 0.000 0.044 0.000
#> GSM647551 2 0.1714 0.81739 0.000 0.908 0.000 0.000 0.092 0.000
#> GSM647556 3 0.3975 0.76031 0.000 0.392 0.600 0.000 0.008 0.000
#> GSM647558 2 0.4375 0.60020 0.000 0.772 0.076 0.092 0.060 0.000
#> GSM647572 2 0.3487 0.55112 0.000 0.756 0.224 0.000 0.020 0.000
#> GSM647578 2 0.1812 0.81668 0.000 0.912 0.080 0.000 0.008 0.000
#> GSM647581 2 0.4375 0.60020 0.000 0.772 0.076 0.092 0.060 0.000
#> GSM647594 5 0.3822 0.72511 0.004 0.300 0.004 0.000 0.688 0.004
#> GSM647599 5 0.6477 0.17982 0.024 0.160 0.308 0.000 0.492 0.016
#> GSM647600 2 0.2724 0.81784 0.000 0.864 0.052 0.000 0.084 0.000
#> GSM647601 2 0.0790 0.85906 0.000 0.968 0.000 0.000 0.032 0.000
#> GSM647603 2 0.2558 0.78281 0.000 0.868 0.104 0.000 0.028 0.000
#> GSM647610 5 0.6028 0.48677 0.000 0.340 0.176 0.000 0.472 0.012
#> GSM647611 2 0.1267 0.85238 0.000 0.940 0.000 0.000 0.060 0.000
#> GSM647612 2 0.0935 0.85157 0.000 0.964 0.032 0.000 0.004 0.000
#> GSM647614 2 0.0935 0.85157 0.000 0.964 0.032 0.000 0.004 0.000
#> GSM647618 2 0.1075 0.85246 0.000 0.952 0.000 0.000 0.048 0.000
#> GSM647629 2 0.1866 0.81366 0.000 0.908 0.084 0.000 0.008 0.000
#> GSM647535 2 0.0820 0.85967 0.000 0.972 0.016 0.000 0.012 0.000
#> GSM647563 2 0.1152 0.85657 0.000 0.952 0.004 0.000 0.044 0.000
#> GSM647542 2 0.1349 0.84135 0.000 0.940 0.056 0.000 0.004 0.000
#> GSM647543 2 0.1349 0.84135 0.000 0.940 0.056 0.000 0.004 0.000
#> GSM647548 4 0.7020 0.21285 0.000 0.260 0.284 0.388 0.068 0.000
#> GSM647554 2 0.3314 0.55001 0.000 0.764 0.224 0.000 0.012 0.000
#> GSM647555 2 0.1075 0.85121 0.000 0.952 0.048 0.000 0.000 0.000
#> GSM647559 2 0.1124 0.85982 0.000 0.956 0.008 0.000 0.036 0.000
#> GSM647562 2 0.1219 0.85538 0.000 0.948 0.004 0.000 0.048 0.000
#> GSM647564 3 0.3993 0.76398 0.000 0.400 0.592 0.000 0.008 0.000
#> GSM647571 2 0.2573 0.77380 0.000 0.864 0.112 0.000 0.024 0.000
#> GSM647584 2 0.1714 0.81739 0.000 0.908 0.000 0.000 0.092 0.000
#> GSM647585 3 0.3899 0.75581 0.000 0.404 0.592 0.000 0.004 0.000
#> GSM647586 2 0.0777 0.85897 0.000 0.972 0.004 0.000 0.024 0.000
#> GSM647587 2 0.1082 0.85671 0.000 0.956 0.004 0.000 0.040 0.000
#> GSM647588 2 0.1643 0.82859 0.000 0.924 0.068 0.000 0.008 0.000
#> GSM647596 2 0.0777 0.85996 0.000 0.972 0.004 0.000 0.024 0.000
#> GSM647602 3 0.3993 0.76398 0.000 0.400 0.592 0.000 0.008 0.000
#> GSM647609 2 0.0790 0.85906 0.000 0.968 0.000 0.000 0.032 0.000
#> GSM647620 2 0.0820 0.85967 0.000 0.972 0.016 0.000 0.012 0.000
#> GSM647627 2 0.0790 0.85906 0.000 0.968 0.000 0.000 0.032 0.000
#> GSM647628 2 0.0777 0.85422 0.000 0.972 0.024 0.000 0.004 0.000
#> GSM647533 1 0.3126 0.74104 0.752 0.000 0.000 0.000 0.000 0.248
#> GSM647536 6 0.6429 0.72511 0.012 0.016 0.044 0.236 0.108 0.584
#> GSM647537 1 0.3126 0.74104 0.752 0.000 0.000 0.000 0.000 0.248
#> GSM647606 1 0.0000 0.90621 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647621 3 0.6706 -0.43802 0.024 0.000 0.472 0.284 0.200 0.020
#> GSM647626 3 0.5250 0.66345 0.000 0.352 0.556 0.000 0.084 0.008
#> GSM647538 6 0.1053 0.60970 0.020 0.000 0.004 0.000 0.012 0.964
#> GSM647575 4 0.0551 0.44925 0.000 0.000 0.004 0.984 0.004 0.008
#> GSM647590 4 0.3804 0.41120 0.000 0.000 0.184 0.768 0.040 0.008
#> GSM647605 1 0.0000 0.90621 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647607 4 0.0405 0.44692 0.000 0.000 0.000 0.988 0.004 0.008
#> GSM647608 4 0.4750 0.47382 0.000 0.016 0.316 0.628 0.040 0.000
#> GSM647622 1 0.1124 0.90322 0.956 0.000 0.008 0.000 0.036 0.000
#> GSM647623 1 0.2094 0.88454 0.900 0.000 0.020 0.000 0.080 0.000
#> GSM647624 1 0.1124 0.90322 0.956 0.000 0.008 0.000 0.036 0.000
#> GSM647625 1 0.2094 0.88454 0.900 0.000 0.020 0.000 0.080 0.000
#> GSM647534 6 0.0914 0.61155 0.016 0.000 0.000 0.000 0.016 0.968
#> GSM647539 4 0.4201 0.39648 0.000 0.000 0.216 0.728 0.044 0.012
#> GSM647566 4 0.4700 0.37853 0.000 0.000 0.212 0.704 0.044 0.040
#> GSM647589 4 0.4750 0.47382 0.000 0.016 0.316 0.628 0.040 0.000
#> GSM647604 1 0.0000 0.90621 1.000 0.000 0.000 0.000 0.000 0.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
#> Error in mat[ceiling(1:nr/h_ratio), ceiling(1:nc/w_ratio), drop = FALSE]: subscript out of bounds
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) development.stage(p) other(p) k
#> CV:hclust 96 8.70e-17 0.123 0.123 2
#> CV:hclust 95 3.63e-17 0.350 0.171 3
#> CV:hclust 92 8.31e-15 0.549 0.386 4
#> CV:hclust 83 1.47e-13 0.213 0.292 5
#> CV:hclust 83 9.86e-14 0.107 0.461 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["CV", "kmeans"]
# you can also extract it by
# res = res_list["CV:kmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'CV' method.
#> Subgroups are detected by 'kmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 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 0.670 0.866 0.935 0.4309 0.600 0.600
#> 3 3 0.619 0.808 0.895 0.4051 0.714 0.548
#> 4 4 0.639 0.714 0.800 0.1544 0.904 0.763
#> 5 5 0.706 0.757 0.839 0.0887 0.834 0.543
#> 6 6 0.689 0.639 0.805 0.0511 0.936 0.745
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
#> GSM647569 2 0.9427 0.528 0.360 0.640
#> GSM647574 2 0.9427 0.528 0.360 0.640
#> GSM647577 2 0.9427 0.528 0.360 0.640
#> GSM647547 2 0.9427 0.528 0.360 0.640
#> GSM647552 2 0.1184 0.915 0.016 0.984
#> GSM647553 1 0.8763 0.523 0.704 0.296
#> GSM647565 2 0.6623 0.778 0.172 0.828
#> GSM647545 2 0.0376 0.915 0.004 0.996
#> GSM647549 2 0.0376 0.915 0.004 0.996
#> GSM647550 2 0.0000 0.914 0.000 1.000
#> GSM647560 2 0.0000 0.914 0.000 1.000
#> GSM647617 2 0.9427 0.528 0.360 0.640
#> GSM647528 2 0.1184 0.915 0.016 0.984
#> GSM647529 1 0.0000 0.965 1.000 0.000
#> GSM647531 2 0.1184 0.915 0.016 0.984
#> GSM647540 2 0.0000 0.914 0.000 1.000
#> GSM647541 2 0.0000 0.914 0.000 1.000
#> GSM647546 2 0.6973 0.763 0.188 0.812
#> GSM647557 2 0.1184 0.915 0.016 0.984
#> GSM647561 2 0.1184 0.915 0.016 0.984
#> GSM647567 2 0.9661 0.485 0.392 0.608
#> GSM647568 2 0.0000 0.914 0.000 1.000
#> GSM647570 2 0.0376 0.915 0.004 0.996
#> GSM647573 1 0.0938 0.962 0.988 0.012
#> GSM647576 2 0.0000 0.914 0.000 1.000
#> GSM647579 2 0.0000 0.914 0.000 1.000
#> GSM647580 2 0.9427 0.528 0.360 0.640
#> GSM647583 2 0.9427 0.528 0.360 0.640
#> GSM647592 2 0.1184 0.915 0.016 0.984
#> GSM647593 2 0.1184 0.915 0.016 0.984
#> GSM647595 2 0.1184 0.915 0.016 0.984
#> GSM647597 1 0.6623 0.769 0.828 0.172
#> GSM647598 2 0.1184 0.915 0.016 0.984
#> GSM647613 2 0.1184 0.915 0.016 0.984
#> GSM647615 2 0.0376 0.915 0.004 0.996
#> GSM647616 2 0.9427 0.528 0.360 0.640
#> GSM647619 2 0.1184 0.915 0.016 0.984
#> GSM647582 2 0.1184 0.915 0.016 0.984
#> GSM647591 2 0.1184 0.915 0.016 0.984
#> GSM647527 2 0.1184 0.915 0.016 0.984
#> GSM647530 1 0.7376 0.713 0.792 0.208
#> GSM647532 1 0.0000 0.965 1.000 0.000
#> GSM647544 2 0.0376 0.915 0.004 0.996
#> GSM647551 2 0.1184 0.915 0.016 0.984
#> GSM647556 2 0.9427 0.528 0.360 0.640
#> GSM647558 2 0.0376 0.915 0.004 0.996
#> GSM647572 2 0.6247 0.795 0.156 0.844
#> GSM647578 2 0.0000 0.914 0.000 1.000
#> GSM647581 2 0.0376 0.915 0.004 0.996
#> GSM647594 2 0.5178 0.830 0.116 0.884
#> GSM647599 1 0.0000 0.965 1.000 0.000
#> GSM647600 2 0.1184 0.915 0.016 0.984
#> GSM647601 2 0.1184 0.915 0.016 0.984
#> GSM647603 2 0.0000 0.914 0.000 1.000
#> GSM647610 2 0.2603 0.901 0.044 0.956
#> GSM647611 2 0.1184 0.915 0.016 0.984
#> GSM647612 2 0.0000 0.914 0.000 1.000
#> GSM647614 2 0.0000 0.914 0.000 1.000
#> GSM647618 2 0.1184 0.915 0.016 0.984
#> GSM647629 2 0.0938 0.914 0.012 0.988
#> GSM647535 2 0.0000 0.914 0.000 1.000
#> GSM647563 2 0.0376 0.915 0.004 0.996
#> GSM647542 2 0.0000 0.914 0.000 1.000
#> GSM647543 2 0.0000 0.914 0.000 1.000
#> GSM647548 2 0.6247 0.798 0.156 0.844
#> GSM647554 2 0.0938 0.914 0.012 0.988
#> GSM647555 2 0.0000 0.914 0.000 1.000
#> GSM647559 2 0.0376 0.915 0.004 0.996
#> GSM647562 2 0.0938 0.915 0.012 0.988
#> GSM647564 2 0.7056 0.758 0.192 0.808
#> GSM647571 2 0.0000 0.914 0.000 1.000
#> GSM647584 2 0.1184 0.915 0.016 0.984
#> GSM647585 2 0.9427 0.528 0.360 0.640
#> GSM647586 2 0.1184 0.915 0.016 0.984
#> GSM647587 2 0.1184 0.915 0.016 0.984
#> GSM647588 2 0.0000 0.914 0.000 1.000
#> GSM647596 2 0.1184 0.915 0.016 0.984
#> GSM647602 2 0.9427 0.528 0.360 0.640
#> GSM647609 2 0.1184 0.915 0.016 0.984
#> GSM647620 2 0.1184 0.915 0.016 0.984
#> GSM647627 2 0.1184 0.915 0.016 0.984
#> GSM647628 2 0.0376 0.915 0.004 0.996
#> GSM647533 1 0.0000 0.965 1.000 0.000
#> GSM647536 1 0.0000 0.965 1.000 0.000
#> GSM647537 1 0.0000 0.965 1.000 0.000
#> GSM647606 1 0.0000 0.965 1.000 0.000
#> GSM647621 1 0.0938 0.962 0.988 0.012
#> GSM647626 1 0.1184 0.960 0.984 0.016
#> GSM647538 1 0.0000 0.965 1.000 0.000
#> GSM647575 1 0.0938 0.962 0.988 0.012
#> GSM647590 1 0.0938 0.962 0.988 0.012
#> GSM647605 1 0.0000 0.965 1.000 0.000
#> GSM647607 1 0.0938 0.962 0.988 0.012
#> GSM647608 1 0.1184 0.960 0.984 0.016
#> GSM647622 1 0.0000 0.965 1.000 0.000
#> GSM647623 1 0.0000 0.965 1.000 0.000
#> GSM647624 1 0.0000 0.965 1.000 0.000
#> GSM647625 1 0.0000 0.965 1.000 0.000
#> GSM647534 1 0.1414 0.949 0.980 0.020
#> GSM647539 1 0.0938 0.962 0.988 0.012
#> GSM647566 1 0.0938 0.962 0.988 0.012
#> GSM647589 1 0.1184 0.960 0.984 0.016
#> GSM647604 1 0.0000 0.965 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 3 0.4047 0.8364 0.004 0.148 0.848
#> GSM647574 3 0.1585 0.7477 0.008 0.028 0.964
#> GSM647577 3 0.4047 0.8364 0.004 0.148 0.848
#> GSM647547 3 0.0424 0.7151 0.008 0.000 0.992
#> GSM647552 2 0.1182 0.9098 0.012 0.976 0.012
#> GSM647553 3 0.1267 0.7463 0.004 0.024 0.972
#> GSM647565 3 0.4912 0.6992 0.008 0.196 0.796
#> GSM647545 2 0.0592 0.9192 0.000 0.988 0.012
#> GSM647549 2 0.0592 0.9192 0.000 0.988 0.012
#> GSM647550 3 0.6299 0.2621 0.000 0.476 0.524
#> GSM647560 2 0.4346 0.7177 0.000 0.816 0.184
#> GSM647617 3 0.4047 0.8364 0.004 0.148 0.848
#> GSM647528 2 0.0592 0.9192 0.000 0.988 0.012
#> GSM647529 1 0.1643 0.9176 0.956 0.000 0.044
#> GSM647531 2 0.0983 0.9176 0.004 0.980 0.016
#> GSM647540 3 0.5760 0.6516 0.000 0.328 0.672
#> GSM647541 2 0.0237 0.9198 0.000 0.996 0.004
#> GSM647546 3 0.3816 0.8320 0.000 0.148 0.852
#> GSM647557 2 0.1170 0.9163 0.008 0.976 0.016
#> GSM647561 2 0.0592 0.9192 0.000 0.988 0.012
#> GSM647567 3 0.6698 0.7211 0.036 0.280 0.684
#> GSM647568 3 0.4887 0.7815 0.000 0.228 0.772
#> GSM647570 2 0.1860 0.8925 0.000 0.948 0.052
#> GSM647573 3 0.4002 0.5573 0.160 0.000 0.840
#> GSM647576 3 0.4504 0.8159 0.000 0.196 0.804
#> GSM647579 3 0.5760 0.6516 0.000 0.328 0.672
#> GSM647580 3 0.4047 0.8364 0.004 0.148 0.848
#> GSM647583 3 0.4047 0.8364 0.004 0.148 0.848
#> GSM647592 2 0.0424 0.9191 0.008 0.992 0.000
#> GSM647593 2 0.0237 0.9200 0.004 0.996 0.000
#> GSM647595 2 0.0237 0.9200 0.004 0.996 0.000
#> GSM647597 1 0.1337 0.9166 0.972 0.012 0.016
#> GSM647598 2 0.0000 0.9206 0.000 1.000 0.000
#> GSM647613 2 0.0592 0.9192 0.000 0.988 0.012
#> GSM647615 2 0.4504 0.7161 0.000 0.804 0.196
#> GSM647616 3 0.4047 0.8364 0.004 0.148 0.848
#> GSM647619 2 0.0424 0.9191 0.008 0.992 0.000
#> GSM647582 2 0.0237 0.9202 0.004 0.996 0.000
#> GSM647591 2 0.0661 0.9175 0.008 0.988 0.004
#> GSM647527 2 0.0592 0.9192 0.000 0.988 0.012
#> GSM647530 2 0.8749 0.3422 0.276 0.572 0.152
#> GSM647532 1 0.3686 0.8857 0.860 0.000 0.140
#> GSM647544 2 0.0983 0.9175 0.004 0.980 0.016
#> GSM647551 2 0.0237 0.9200 0.004 0.996 0.000
#> GSM647556 3 0.4047 0.8364 0.004 0.148 0.848
#> GSM647558 2 0.1860 0.8925 0.000 0.948 0.052
#> GSM647572 3 0.3879 0.8311 0.000 0.152 0.848
#> GSM647578 2 0.6309 -0.2470 0.000 0.504 0.496
#> GSM647581 2 0.0747 0.9182 0.000 0.984 0.016
#> GSM647594 2 0.2200 0.8787 0.056 0.940 0.004
#> GSM647599 1 0.1753 0.9163 0.952 0.000 0.048
#> GSM647600 2 0.0000 0.9206 0.000 1.000 0.000
#> GSM647601 2 0.0000 0.9206 0.000 1.000 0.000
#> GSM647603 2 0.0424 0.9185 0.000 0.992 0.008
#> GSM647610 2 0.0983 0.9118 0.004 0.980 0.016
#> GSM647611 2 0.0237 0.9202 0.004 0.996 0.000
#> GSM647612 2 0.4504 0.7169 0.000 0.804 0.196
#> GSM647614 2 0.4605 0.7037 0.000 0.796 0.204
#> GSM647618 2 0.0475 0.9192 0.004 0.992 0.004
#> GSM647629 2 0.0000 0.9206 0.000 1.000 0.000
#> GSM647535 2 0.0000 0.9206 0.000 1.000 0.000
#> GSM647563 2 0.0592 0.9192 0.000 0.988 0.012
#> GSM647542 3 0.6291 0.2996 0.000 0.468 0.532
#> GSM647543 2 0.6235 0.0336 0.000 0.564 0.436
#> GSM647548 3 0.5578 0.6298 0.012 0.240 0.748
#> GSM647554 2 0.4121 0.7184 0.000 0.832 0.168
#> GSM647555 2 0.4002 0.7703 0.000 0.840 0.160
#> GSM647559 2 0.0829 0.9190 0.004 0.984 0.012
#> GSM647562 2 0.0983 0.9175 0.004 0.980 0.016
#> GSM647564 3 0.3879 0.8356 0.000 0.152 0.848
#> GSM647571 2 0.6148 0.3428 0.004 0.640 0.356
#> GSM647584 2 0.0000 0.9206 0.000 1.000 0.000
#> GSM647585 3 0.4047 0.8364 0.004 0.148 0.848
#> GSM647586 2 0.0000 0.9206 0.000 1.000 0.000
#> GSM647587 2 0.0829 0.9190 0.004 0.984 0.012
#> GSM647588 2 0.0000 0.9206 0.000 1.000 0.000
#> GSM647596 2 0.0592 0.9192 0.000 0.988 0.012
#> GSM647602 3 0.4047 0.8364 0.004 0.148 0.848
#> GSM647609 2 0.0000 0.9206 0.000 1.000 0.000
#> GSM647620 2 0.0000 0.9206 0.000 1.000 0.000
#> GSM647627 2 0.0000 0.9206 0.000 1.000 0.000
#> GSM647628 2 0.1860 0.8925 0.000 0.948 0.052
#> GSM647533 1 0.0747 0.9240 0.984 0.000 0.016
#> GSM647536 1 0.3267 0.8968 0.884 0.000 0.116
#> GSM647537 1 0.0747 0.9240 0.984 0.000 0.016
#> GSM647606 1 0.0747 0.9240 0.984 0.000 0.016
#> GSM647621 1 0.5465 0.7553 0.712 0.000 0.288
#> GSM647626 3 0.4059 0.7012 0.128 0.012 0.860
#> GSM647538 1 0.1289 0.9238 0.968 0.000 0.032
#> GSM647575 1 0.5529 0.7582 0.704 0.000 0.296
#> GSM647590 1 0.3686 0.8902 0.860 0.000 0.140
#> GSM647605 1 0.0592 0.9229 0.988 0.000 0.012
#> GSM647607 1 0.4235 0.8722 0.824 0.000 0.176
#> GSM647608 3 0.6280 -0.2722 0.460 0.000 0.540
#> GSM647622 1 0.0747 0.9240 0.984 0.000 0.016
#> GSM647623 1 0.0747 0.9240 0.984 0.000 0.016
#> GSM647624 1 0.0592 0.9235 0.988 0.000 0.012
#> GSM647625 1 0.0747 0.9240 0.984 0.000 0.016
#> GSM647534 1 0.3213 0.8798 0.912 0.060 0.028
#> GSM647539 1 0.5621 0.7465 0.692 0.000 0.308
#> GSM647566 1 0.3619 0.8919 0.864 0.000 0.136
#> GSM647589 3 0.1643 0.6894 0.044 0.000 0.956
#> GSM647604 1 0.0592 0.9229 0.988 0.000 0.012
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 3 0.1059 0.8699 0.016 0.012 0.972 0.000
#> GSM647574 3 0.1004 0.8546 0.000 0.004 0.972 0.024
#> GSM647577 3 0.1247 0.8705 0.016 0.012 0.968 0.004
#> GSM647547 4 0.4978 0.3738 0.000 0.004 0.384 0.612
#> GSM647552 2 0.1661 0.7488 0.000 0.944 0.004 0.052
#> GSM647553 3 0.1114 0.8625 0.016 0.004 0.972 0.008
#> GSM647565 4 0.4127 0.4422 0.000 0.124 0.052 0.824
#> GSM647545 2 0.5220 0.7341 0.000 0.632 0.016 0.352
#> GSM647549 2 0.5220 0.7341 0.000 0.632 0.016 0.352
#> GSM647550 3 0.7359 0.2323 0.000 0.184 0.504 0.312
#> GSM647560 2 0.7449 0.5937 0.000 0.464 0.180 0.356
#> GSM647617 3 0.1247 0.8705 0.016 0.012 0.968 0.004
#> GSM647528 2 0.3743 0.7883 0.000 0.824 0.016 0.160
#> GSM647529 1 0.4655 0.3672 0.684 0.000 0.004 0.312
#> GSM647531 2 0.4482 0.7674 0.000 0.728 0.008 0.264
#> GSM647540 3 0.2032 0.8356 0.000 0.028 0.936 0.036
#> GSM647541 2 0.5038 0.7622 0.000 0.684 0.020 0.296
#> GSM647546 3 0.0657 0.8668 0.000 0.012 0.984 0.004
#> GSM647557 2 0.4452 0.7682 0.000 0.732 0.008 0.260
#> GSM647561 2 0.4535 0.7770 0.000 0.744 0.016 0.240
#> GSM647567 3 0.4195 0.7171 0.016 0.160 0.812 0.012
#> GSM647568 3 0.7729 -0.0516 0.000 0.228 0.400 0.372
#> GSM647570 2 0.5284 0.7259 0.000 0.616 0.016 0.368
#> GSM647573 4 0.4805 0.6328 0.132 0.000 0.084 0.784
#> GSM647576 3 0.2706 0.8041 0.000 0.020 0.900 0.080
#> GSM647579 3 0.2131 0.8343 0.000 0.032 0.932 0.036
#> GSM647580 3 0.1247 0.8705 0.016 0.012 0.968 0.004
#> GSM647583 3 0.1247 0.8705 0.016 0.012 0.968 0.004
#> GSM647592 2 0.1398 0.7486 0.000 0.956 0.004 0.040
#> GSM647593 2 0.0336 0.7651 0.000 0.992 0.000 0.008
#> GSM647595 2 0.0469 0.7665 0.000 0.988 0.000 0.012
#> GSM647597 1 0.6101 0.4401 0.628 0.308 0.004 0.060
#> GSM647598 2 0.0188 0.7691 0.000 0.996 0.000 0.004
#> GSM647613 2 0.4831 0.7655 0.000 0.704 0.016 0.280
#> GSM647615 2 0.7392 0.5921 0.000 0.460 0.168 0.372
#> GSM647616 3 0.1247 0.8705 0.016 0.012 0.968 0.004
#> GSM647619 2 0.1118 0.7531 0.000 0.964 0.000 0.036
#> GSM647582 2 0.0469 0.7681 0.000 0.988 0.000 0.012
#> GSM647591 2 0.1302 0.7490 0.000 0.956 0.000 0.044
#> GSM647527 2 0.3743 0.7883 0.000 0.824 0.016 0.160
#> GSM647530 4 0.2561 0.5321 0.016 0.068 0.004 0.912
#> GSM647532 4 0.5004 0.5449 0.392 0.000 0.004 0.604
#> GSM647544 2 0.5220 0.7374 0.000 0.632 0.016 0.352
#> GSM647551 2 0.0657 0.7662 0.000 0.984 0.004 0.012
#> GSM647556 3 0.1059 0.8699 0.016 0.012 0.972 0.000
#> GSM647558 2 0.5284 0.7259 0.000 0.616 0.016 0.368
#> GSM647572 3 0.0657 0.8668 0.000 0.012 0.984 0.004
#> GSM647578 3 0.6788 0.4249 0.000 0.188 0.608 0.204
#> GSM647581 2 0.5298 0.7259 0.000 0.612 0.016 0.372
#> GSM647594 2 0.1302 0.7490 0.000 0.956 0.000 0.044
#> GSM647599 1 0.1059 0.8512 0.972 0.000 0.012 0.016
#> GSM647600 2 0.0779 0.7717 0.000 0.980 0.004 0.016
#> GSM647601 2 0.0000 0.7681 0.000 1.000 0.000 0.000
#> GSM647603 2 0.4344 0.7437 0.000 0.816 0.108 0.076
#> GSM647610 2 0.1733 0.7514 0.000 0.948 0.028 0.024
#> GSM647611 2 0.0336 0.7661 0.000 0.992 0.000 0.008
#> GSM647612 2 0.7356 0.6014 0.000 0.468 0.164 0.368
#> GSM647614 2 0.7392 0.5921 0.000 0.460 0.168 0.372
#> GSM647618 2 0.1389 0.7471 0.000 0.952 0.000 0.048
#> GSM647629 2 0.2048 0.7791 0.000 0.928 0.008 0.064
#> GSM647535 2 0.4214 0.7854 0.000 0.780 0.016 0.204
#> GSM647563 2 0.5253 0.7308 0.000 0.624 0.016 0.360
#> GSM647542 2 0.7658 0.5214 0.000 0.416 0.212 0.372
#> GSM647543 2 0.7595 0.5426 0.000 0.428 0.200 0.372
#> GSM647548 4 0.2197 0.5408 0.000 0.024 0.048 0.928
#> GSM647554 2 0.4908 0.4031 0.000 0.692 0.292 0.016
#> GSM647555 2 0.7371 0.6055 0.000 0.472 0.168 0.360
#> GSM647559 2 0.4630 0.7784 0.000 0.732 0.016 0.252
#> GSM647562 2 0.5090 0.7455 0.000 0.660 0.016 0.324
#> GSM647564 3 0.0469 0.8665 0.000 0.012 0.988 0.000
#> GSM647571 2 0.7506 0.5672 0.000 0.440 0.184 0.376
#> GSM647584 2 0.0469 0.7712 0.000 0.988 0.000 0.012
#> GSM647585 3 0.0927 0.8675 0.016 0.008 0.976 0.000
#> GSM647586 2 0.1807 0.7815 0.000 0.940 0.008 0.052
#> GSM647587 2 0.3695 0.7888 0.000 0.828 0.016 0.156
#> GSM647588 2 0.4831 0.7683 0.000 0.704 0.016 0.280
#> GSM647596 2 0.3390 0.7891 0.000 0.852 0.016 0.132
#> GSM647602 3 0.1247 0.8705 0.016 0.012 0.968 0.004
#> GSM647609 2 0.0000 0.7681 0.000 1.000 0.000 0.000
#> GSM647620 2 0.1209 0.7768 0.000 0.964 0.004 0.032
#> GSM647627 2 0.1635 0.7795 0.000 0.948 0.008 0.044
#> GSM647628 2 0.5284 0.7259 0.000 0.616 0.016 0.368
#> GSM647533 1 0.0524 0.8643 0.988 0.000 0.004 0.008
#> GSM647536 4 0.5004 0.5449 0.392 0.000 0.004 0.604
#> GSM647537 1 0.0336 0.8651 0.992 0.000 0.000 0.008
#> GSM647606 1 0.0000 0.8674 1.000 0.000 0.000 0.000
#> GSM647621 4 0.6139 0.5623 0.404 0.000 0.052 0.544
#> GSM647626 3 0.1042 0.8567 0.020 0.000 0.972 0.008
#> GSM647538 1 0.1902 0.8127 0.932 0.000 0.004 0.064
#> GSM647575 4 0.5773 0.6291 0.320 0.000 0.048 0.632
#> GSM647590 4 0.4941 0.5321 0.436 0.000 0.000 0.564
#> GSM647605 1 0.0000 0.8674 1.000 0.000 0.000 0.000
#> GSM647607 4 0.5203 0.5591 0.416 0.000 0.008 0.576
#> GSM647608 4 0.6352 0.6347 0.260 0.000 0.108 0.632
#> GSM647622 1 0.0000 0.8674 1.000 0.000 0.000 0.000
#> GSM647623 1 0.0188 0.8664 0.996 0.000 0.004 0.000
#> GSM647624 1 0.0592 0.8538 0.984 0.000 0.000 0.016
#> GSM647625 1 0.0000 0.8674 1.000 0.000 0.000 0.000
#> GSM647534 1 0.6351 0.4742 0.640 0.272 0.008 0.080
#> GSM647539 4 0.4630 0.6401 0.196 0.000 0.036 0.768
#> GSM647566 4 0.5229 0.5367 0.428 0.000 0.008 0.564
#> GSM647589 4 0.6338 0.5863 0.120 0.000 0.236 0.644
#> GSM647604 1 0.0000 0.8674 1.000 0.000 0.000 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.0451 0.94916 0.000 0.004 0.988 0.000 0.008
#> GSM647574 3 0.1211 0.93161 0.000 0.000 0.960 0.024 0.016
#> GSM647577 3 0.0486 0.95027 0.000 0.004 0.988 0.004 0.004
#> GSM647547 4 0.3308 0.82955 0.000 0.032 0.076 0.864 0.028
#> GSM647552 5 0.3292 0.72834 0.000 0.120 0.004 0.032 0.844
#> GSM647553 3 0.0579 0.94676 0.000 0.000 0.984 0.008 0.008
#> GSM647565 4 0.5123 0.41327 0.000 0.376 0.016 0.588 0.020
#> GSM647545 2 0.0566 0.76987 0.000 0.984 0.000 0.012 0.004
#> GSM647549 2 0.0566 0.76987 0.000 0.984 0.000 0.012 0.004
#> GSM647550 2 0.4880 0.51389 0.000 0.664 0.296 0.028 0.012
#> GSM647560 2 0.2647 0.74744 0.000 0.892 0.076 0.024 0.008
#> GSM647617 3 0.0324 0.95062 0.000 0.004 0.992 0.004 0.000
#> GSM647528 2 0.3163 0.66832 0.000 0.824 0.000 0.012 0.164
#> GSM647529 4 0.4930 0.74393 0.084 0.000 0.000 0.696 0.220
#> GSM647531 2 0.4620 0.14486 0.000 0.592 0.000 0.016 0.392
#> GSM647540 3 0.1908 0.92102 0.000 0.024 0.936 0.024 0.016
#> GSM647541 2 0.1507 0.76624 0.000 0.952 0.012 0.024 0.012
#> GSM647546 3 0.0486 0.95027 0.000 0.004 0.988 0.004 0.004
#> GSM647557 2 0.4793 -0.00706 0.000 0.544 0.000 0.020 0.436
#> GSM647561 2 0.2574 0.71495 0.000 0.876 0.000 0.012 0.112
#> GSM647567 3 0.5552 0.26493 0.000 0.024 0.516 0.028 0.432
#> GSM647568 2 0.3801 0.66509 0.000 0.808 0.152 0.028 0.012
#> GSM647570 2 0.1116 0.76959 0.000 0.964 0.004 0.028 0.004
#> GSM647573 4 0.2576 0.85158 0.012 0.048 0.008 0.908 0.024
#> GSM647576 3 0.2522 0.87358 0.000 0.076 0.896 0.024 0.004
#> GSM647579 3 0.1908 0.92102 0.000 0.024 0.936 0.024 0.016
#> GSM647580 3 0.0486 0.95086 0.000 0.004 0.988 0.004 0.004
#> GSM647583 3 0.0486 0.95027 0.000 0.004 0.988 0.004 0.004
#> GSM647592 5 0.3720 0.82357 0.000 0.228 0.000 0.012 0.760
#> GSM647593 5 0.3774 0.83244 0.000 0.296 0.000 0.000 0.704
#> GSM647595 5 0.3774 0.83244 0.000 0.296 0.000 0.000 0.704
#> GSM647597 5 0.3346 0.55791 0.108 0.008 0.000 0.036 0.848
#> GSM647598 5 0.3969 0.82729 0.000 0.304 0.000 0.004 0.692
#> GSM647613 2 0.1942 0.74546 0.000 0.920 0.000 0.012 0.068
#> GSM647615 2 0.2012 0.75556 0.000 0.920 0.060 0.020 0.000
#> GSM647616 3 0.0486 0.95027 0.000 0.004 0.988 0.004 0.004
#> GSM647619 5 0.3607 0.83332 0.000 0.244 0.000 0.004 0.752
#> GSM647582 5 0.4678 0.81296 0.000 0.300 0.004 0.028 0.668
#> GSM647591 5 0.3766 0.83490 0.000 0.268 0.000 0.004 0.728
#> GSM647527 2 0.3163 0.66832 0.000 0.824 0.000 0.012 0.164
#> GSM647530 4 0.3578 0.81967 0.000 0.048 0.000 0.820 0.132
#> GSM647532 4 0.4372 0.79560 0.072 0.000 0.000 0.756 0.172
#> GSM647544 2 0.2927 0.74398 0.000 0.868 0.000 0.040 0.092
#> GSM647551 5 0.4178 0.82895 0.000 0.292 0.004 0.008 0.696
#> GSM647556 3 0.0771 0.94512 0.000 0.004 0.976 0.000 0.020
#> GSM647558 2 0.1116 0.76959 0.000 0.964 0.004 0.028 0.004
#> GSM647572 3 0.0740 0.94869 0.000 0.004 0.980 0.008 0.008
#> GSM647578 2 0.5253 0.29278 0.000 0.564 0.396 0.024 0.016
#> GSM647581 2 0.0955 0.76931 0.000 0.968 0.000 0.028 0.004
#> GSM647594 5 0.3421 0.79791 0.000 0.204 0.000 0.008 0.788
#> GSM647599 1 0.2103 0.91614 0.920 0.000 0.004 0.020 0.056
#> GSM647600 5 0.4422 0.81782 0.000 0.300 0.004 0.016 0.680
#> GSM647601 5 0.4088 0.82589 0.000 0.304 0.000 0.008 0.688
#> GSM647603 2 0.5948 -0.03188 0.000 0.508 0.040 0.036 0.416
#> GSM647610 5 0.4443 0.81231 0.000 0.212 0.016 0.028 0.744
#> GSM647611 5 0.4275 0.82781 0.000 0.284 0.000 0.020 0.696
#> GSM647612 2 0.2236 0.75124 0.000 0.908 0.068 0.024 0.000
#> GSM647614 2 0.2104 0.75512 0.000 0.916 0.060 0.024 0.000
#> GSM647618 5 0.4080 0.83172 0.000 0.252 0.000 0.020 0.728
#> GSM647629 5 0.5253 0.54950 0.000 0.464 0.012 0.024 0.500
#> GSM647535 2 0.1668 0.76162 0.000 0.940 0.000 0.032 0.028
#> GSM647563 2 0.0898 0.76947 0.000 0.972 0.000 0.020 0.008
#> GSM647542 2 0.3023 0.72432 0.000 0.868 0.096 0.028 0.008
#> GSM647543 2 0.2845 0.72764 0.000 0.876 0.096 0.020 0.008
#> GSM647548 4 0.2597 0.82837 0.000 0.092 0.000 0.884 0.024
#> GSM647554 5 0.6917 0.49040 0.000 0.200 0.276 0.024 0.500
#> GSM647555 2 0.2456 0.75252 0.000 0.904 0.064 0.024 0.008
#> GSM647559 2 0.3012 0.71823 0.000 0.852 0.000 0.024 0.124
#> GSM647562 2 0.3489 0.69997 0.000 0.820 0.000 0.036 0.144
#> GSM647564 3 0.0486 0.95086 0.000 0.004 0.988 0.004 0.004
#> GSM647571 2 0.4010 0.73524 0.000 0.828 0.068 0.044 0.060
#> GSM647584 5 0.3966 0.80187 0.000 0.336 0.000 0.000 0.664
#> GSM647585 3 0.0771 0.94512 0.000 0.004 0.976 0.000 0.020
#> GSM647586 2 0.3563 0.60908 0.000 0.780 0.000 0.012 0.208
#> GSM647587 2 0.3586 0.64715 0.000 0.792 0.000 0.020 0.188
#> GSM647588 2 0.1299 0.76827 0.000 0.960 0.008 0.020 0.012
#> GSM647596 2 0.3582 0.58161 0.000 0.768 0.000 0.008 0.224
#> GSM647602 3 0.0486 0.95086 0.000 0.004 0.988 0.004 0.004
#> GSM647609 5 0.4127 0.81876 0.000 0.312 0.000 0.008 0.680
#> GSM647620 2 0.4659 -0.37714 0.000 0.500 0.000 0.012 0.488
#> GSM647627 2 0.4547 0.00588 0.000 0.588 0.000 0.012 0.400
#> GSM647628 2 0.0771 0.77024 0.000 0.976 0.000 0.020 0.004
#> GSM647533 1 0.2237 0.92777 0.904 0.000 0.004 0.008 0.084
#> GSM647536 4 0.4725 0.78245 0.076 0.000 0.004 0.732 0.188
#> GSM647537 1 0.1990 0.93402 0.920 0.000 0.004 0.008 0.068
#> GSM647606 1 0.0000 0.96215 1.000 0.000 0.000 0.000 0.000
#> GSM647621 4 0.3322 0.84355 0.104 0.000 0.004 0.848 0.044
#> GSM647626 3 0.0727 0.94677 0.004 0.000 0.980 0.004 0.012
#> GSM647538 1 0.3323 0.88093 0.844 0.000 0.004 0.036 0.116
#> GSM647575 4 0.1901 0.86151 0.056 0.012 0.000 0.928 0.004
#> GSM647590 4 0.3262 0.83719 0.124 0.000 0.000 0.840 0.036
#> GSM647605 1 0.0510 0.96045 0.984 0.000 0.000 0.000 0.016
#> GSM647607 4 0.2068 0.85267 0.092 0.000 0.000 0.904 0.004
#> GSM647608 4 0.2473 0.85532 0.032 0.004 0.040 0.912 0.012
#> GSM647622 1 0.0000 0.96215 1.000 0.000 0.000 0.000 0.000
#> GSM647623 1 0.0000 0.96215 1.000 0.000 0.000 0.000 0.000
#> GSM647624 1 0.0162 0.96091 0.996 0.000 0.000 0.000 0.004
#> GSM647625 1 0.0000 0.96215 1.000 0.000 0.000 0.000 0.000
#> GSM647534 5 0.4268 0.37402 0.172 0.000 0.008 0.048 0.772
#> GSM647539 4 0.2607 0.86095 0.040 0.032 0.000 0.904 0.024
#> GSM647566 4 0.3494 0.84018 0.096 0.000 0.004 0.840 0.060
#> GSM647589 4 0.2597 0.84614 0.012 0.008 0.060 0.904 0.016
#> GSM647604 1 0.0510 0.96045 0.984 0.000 0.000 0.000 0.016
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.0146 0.9264 0.000 0.004 0.996 0.000 0.000 0.000
#> GSM647574 3 0.1471 0.8809 0.000 0.000 0.932 0.064 0.000 0.004
#> GSM647577 3 0.0146 0.9264 0.000 0.004 0.996 0.000 0.000 0.000
#> GSM647547 4 0.2981 0.6691 0.000 0.052 0.040 0.868 0.000 0.040
#> GSM647552 5 0.4408 0.3445 0.000 0.036 0.000 0.000 0.608 0.356
#> GSM647553 3 0.0363 0.9202 0.000 0.000 0.988 0.012 0.000 0.000
#> GSM647565 2 0.4606 0.0589 0.000 0.548 0.000 0.420 0.012 0.020
#> GSM647545 2 0.2190 0.7447 0.000 0.900 0.000 0.000 0.060 0.040
#> GSM647549 2 0.2190 0.7459 0.000 0.900 0.000 0.000 0.060 0.040
#> GSM647550 2 0.4751 0.5922 0.000 0.700 0.204 0.004 0.012 0.080
#> GSM647560 2 0.1477 0.7588 0.000 0.940 0.008 0.004 0.000 0.048
#> GSM647617 3 0.0146 0.9264 0.000 0.004 0.996 0.000 0.000 0.000
#> GSM647528 2 0.4831 0.2158 0.000 0.548 0.000 0.000 0.392 0.060
#> GSM647529 6 0.5340 -0.3735 0.012 0.000 0.000 0.436 0.072 0.480
#> GSM647531 2 0.5992 0.0582 0.000 0.420 0.000 0.000 0.340 0.240
#> GSM647540 3 0.2822 0.8373 0.000 0.032 0.856 0.004 0.000 0.108
#> GSM647541 2 0.2701 0.7373 0.000 0.864 0.000 0.004 0.028 0.104
#> GSM647546 3 0.0291 0.9253 0.000 0.004 0.992 0.000 0.000 0.004
#> GSM647557 2 0.6033 -0.0584 0.000 0.388 0.000 0.000 0.364 0.248
#> GSM647561 2 0.4616 0.4967 0.000 0.648 0.000 0.000 0.280 0.072
#> GSM647567 3 0.5950 0.0454 0.000 0.000 0.436 0.004 0.188 0.372
#> GSM647568 2 0.1492 0.7504 0.000 0.940 0.036 0.000 0.000 0.024
#> GSM647570 2 0.0508 0.7633 0.000 0.984 0.000 0.000 0.004 0.012
#> GSM647573 4 0.1367 0.7188 0.000 0.012 0.000 0.944 0.000 0.044
#> GSM647576 3 0.3633 0.7548 0.000 0.136 0.796 0.004 0.000 0.064
#> GSM647579 3 0.3185 0.8142 0.000 0.048 0.832 0.004 0.000 0.116
#> GSM647580 3 0.0291 0.9260 0.000 0.004 0.992 0.000 0.000 0.004
#> GSM647583 3 0.0146 0.9264 0.000 0.004 0.996 0.000 0.000 0.000
#> GSM647592 5 0.3313 0.6844 0.000 0.060 0.000 0.000 0.816 0.124
#> GSM647593 5 0.3055 0.7259 0.000 0.096 0.000 0.000 0.840 0.064
#> GSM647595 5 0.3150 0.7261 0.000 0.104 0.000 0.000 0.832 0.064
#> GSM647597 5 0.4334 -0.0129 0.024 0.000 0.000 0.000 0.568 0.408
#> GSM647598 5 0.2912 0.7388 0.000 0.116 0.000 0.000 0.844 0.040
#> GSM647613 2 0.3646 0.6709 0.000 0.776 0.000 0.000 0.172 0.052
#> GSM647615 2 0.0717 0.7636 0.000 0.976 0.008 0.000 0.000 0.016
#> GSM647616 3 0.0146 0.9264 0.000 0.004 0.996 0.000 0.000 0.000
#> GSM647619 5 0.2801 0.7112 0.000 0.068 0.000 0.000 0.860 0.072
#> GSM647582 5 0.4140 0.7107 0.000 0.152 0.000 0.000 0.744 0.104
#> GSM647591 5 0.2856 0.7138 0.000 0.076 0.000 0.000 0.856 0.068
#> GSM647527 2 0.4831 0.2158 0.000 0.548 0.000 0.000 0.392 0.060
#> GSM647530 4 0.5264 0.1865 0.000 0.016 0.000 0.556 0.068 0.360
#> GSM647532 4 0.4953 0.0826 0.008 0.000 0.000 0.524 0.048 0.420
#> GSM647544 2 0.3784 0.6821 0.000 0.776 0.000 0.000 0.144 0.080
#> GSM647551 5 0.4183 0.7114 0.000 0.108 0.000 0.000 0.740 0.152
#> GSM647556 3 0.0748 0.9214 0.000 0.004 0.976 0.000 0.004 0.016
#> GSM647558 2 0.1261 0.7605 0.000 0.952 0.000 0.000 0.024 0.024
#> GSM647572 3 0.1633 0.8930 0.000 0.024 0.932 0.000 0.000 0.044
#> GSM647578 2 0.6034 0.4181 0.000 0.556 0.276 0.004 0.032 0.132
#> GSM647581 2 0.2571 0.7412 0.000 0.876 0.000 0.000 0.064 0.060
#> GSM647594 5 0.3699 0.5151 0.000 0.036 0.000 0.000 0.752 0.212
#> GSM647599 1 0.3265 0.7738 0.844 0.004 0.004 0.008 0.040 0.100
#> GSM647600 5 0.4425 0.7079 0.000 0.132 0.000 0.000 0.716 0.152
#> GSM647601 5 0.2651 0.7369 0.000 0.112 0.000 0.000 0.860 0.028
#> GSM647603 5 0.5731 0.3972 0.000 0.336 0.008 0.000 0.512 0.144
#> GSM647610 5 0.3888 0.6567 0.000 0.064 0.004 0.004 0.780 0.148
#> GSM647611 5 0.3270 0.7251 0.000 0.120 0.000 0.000 0.820 0.060
#> GSM647612 2 0.0806 0.7634 0.000 0.972 0.008 0.000 0.000 0.020
#> GSM647614 2 0.0806 0.7634 0.000 0.972 0.008 0.000 0.000 0.020
#> GSM647618 5 0.3068 0.7217 0.000 0.088 0.000 0.000 0.840 0.072
#> GSM647629 5 0.5261 0.5755 0.000 0.300 0.000 0.004 0.584 0.112
#> GSM647535 2 0.4041 0.6943 0.000 0.764 0.000 0.004 0.096 0.136
#> GSM647563 2 0.2511 0.7395 0.000 0.880 0.000 0.000 0.064 0.056
#> GSM647542 2 0.0972 0.7626 0.000 0.964 0.008 0.000 0.000 0.028
#> GSM647543 2 0.0972 0.7626 0.000 0.964 0.008 0.000 0.000 0.028
#> GSM647548 4 0.3522 0.5392 0.000 0.172 0.000 0.784 0.000 0.044
#> GSM647554 5 0.6979 0.2812 0.000 0.096 0.252 0.004 0.476 0.172
#> GSM647555 2 0.1554 0.7618 0.000 0.940 0.008 0.004 0.004 0.044
#> GSM647559 2 0.3996 0.6619 0.000 0.752 0.000 0.000 0.168 0.080
#> GSM647562 2 0.4300 0.6160 0.000 0.712 0.000 0.000 0.208 0.080
#> GSM647564 3 0.0291 0.9260 0.000 0.004 0.992 0.000 0.000 0.004
#> GSM647571 2 0.2753 0.7487 0.000 0.872 0.008 0.000 0.048 0.072
#> GSM647584 5 0.3522 0.7378 0.000 0.128 0.000 0.000 0.800 0.072
#> GSM647585 3 0.0748 0.9214 0.000 0.004 0.976 0.000 0.004 0.016
#> GSM647586 5 0.4868 0.2358 0.000 0.416 0.000 0.000 0.524 0.060
#> GSM647587 2 0.5061 0.0811 0.000 0.496 0.000 0.000 0.428 0.076
#> GSM647588 2 0.2964 0.7343 0.000 0.848 0.000 0.004 0.040 0.108
#> GSM647596 5 0.4513 0.1924 0.000 0.440 0.000 0.000 0.528 0.032
#> GSM647602 3 0.0291 0.9260 0.000 0.004 0.992 0.000 0.000 0.004
#> GSM647609 5 0.2858 0.7374 0.000 0.124 0.000 0.000 0.844 0.032
#> GSM647620 5 0.4455 0.6517 0.000 0.232 0.000 0.000 0.688 0.080
#> GSM647627 5 0.4368 0.5573 0.000 0.296 0.000 0.000 0.656 0.048
#> GSM647628 2 0.0405 0.7639 0.000 0.988 0.000 0.000 0.004 0.008
#> GSM647533 1 0.3564 0.7276 0.724 0.000 0.000 0.000 0.012 0.264
#> GSM647536 4 0.5032 -0.0496 0.008 0.000 0.000 0.484 0.052 0.456
#> GSM647537 1 0.3314 0.7603 0.764 0.000 0.000 0.000 0.012 0.224
#> GSM647606 1 0.0909 0.8761 0.968 0.000 0.000 0.000 0.012 0.020
#> GSM647621 4 0.3358 0.6685 0.040 0.004 0.004 0.844 0.016 0.092
#> GSM647626 3 0.0146 0.9235 0.000 0.000 0.996 0.000 0.000 0.004
#> GSM647538 1 0.4868 0.3959 0.524 0.000 0.000 0.060 0.000 0.416
#> GSM647575 4 0.0405 0.7266 0.008 0.000 0.000 0.988 0.000 0.004
#> GSM647590 4 0.3843 0.6246 0.036 0.004 0.004 0.776 0.004 0.176
#> GSM647605 1 0.0993 0.8755 0.964 0.000 0.000 0.000 0.012 0.024
#> GSM647607 4 0.0912 0.7254 0.008 0.004 0.000 0.972 0.004 0.012
#> GSM647608 4 0.0291 0.7262 0.004 0.000 0.004 0.992 0.000 0.000
#> GSM647622 1 0.0146 0.8764 0.996 0.000 0.004 0.000 0.000 0.000
#> GSM647623 1 0.0146 0.8764 0.996 0.000 0.004 0.000 0.000 0.000
#> GSM647624 1 0.0551 0.8725 0.984 0.000 0.004 0.000 0.004 0.008
#> GSM647625 1 0.0000 0.8767 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647534 6 0.5369 0.2286 0.076 0.000 0.000 0.040 0.252 0.632
#> GSM647539 4 0.2355 0.6887 0.004 0.008 0.000 0.876 0.000 0.112
#> GSM647566 4 0.4111 0.4878 0.024 0.004 0.000 0.676 0.000 0.296
#> GSM647589 4 0.0436 0.7250 0.000 0.004 0.004 0.988 0.000 0.004
#> GSM647604 1 0.0993 0.8755 0.964 0.000 0.000 0.000 0.012 0.024
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n disease.state(p) development.stage(p) other(p) k
#> CV:kmeans 102 6.19e-16 0.250098 0.0543 2
#> CV:kmeans 96 7.68e-15 0.000971 0.1540 3
#> CV:kmeans 94 2.54e-14 0.005389 0.1725 4
#> CV:kmeans 93 2.07e-12 0.005035 0.1536 5
#> CV:kmeans 81 1.12e-11 0.012007 0.1641 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["CV", "skmeans"]
# you can also extract it by
# res = res_list["CV:skmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'CV' method.
#> Subgroups are detected by 'skmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 3.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.901 0.953 0.979 0.4971 0.503 0.503
#> 3 3 0.900 0.919 0.964 0.3276 0.742 0.532
#> 4 4 0.842 0.846 0.930 0.1382 0.839 0.571
#> 5 5 0.780 0.771 0.854 0.0588 0.905 0.653
#> 6 6 0.770 0.624 0.794 0.0459 0.906 0.593
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 3
#> attr(,"optional")
#> [1] 2
There is also optional best \(k\) = 2 that is worth to check.
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM647569 1 0.0000 0.9748 1.000 0.000
#> GSM647574 1 0.0000 0.9748 1.000 0.000
#> GSM647577 1 0.0000 0.9748 1.000 0.000
#> GSM647547 1 0.0000 0.9748 1.000 0.000
#> GSM647552 2 0.6148 0.8162 0.152 0.848
#> GSM647553 1 0.0000 0.9748 1.000 0.000
#> GSM647565 1 0.7139 0.7622 0.804 0.196
#> GSM647545 2 0.0000 0.9808 0.000 1.000
#> GSM647549 2 0.0000 0.9808 0.000 1.000
#> GSM647550 2 0.0672 0.9744 0.008 0.992
#> GSM647560 2 0.0000 0.9808 0.000 1.000
#> GSM647617 1 0.0000 0.9748 1.000 0.000
#> GSM647528 2 0.0000 0.9808 0.000 1.000
#> GSM647529 1 0.0376 0.9713 0.996 0.004
#> GSM647531 2 0.0000 0.9808 0.000 1.000
#> GSM647540 2 0.6438 0.8136 0.164 0.836
#> GSM647541 2 0.0000 0.9808 0.000 1.000
#> GSM647546 1 0.0000 0.9748 1.000 0.000
#> GSM647557 2 0.0000 0.9808 0.000 1.000
#> GSM647561 2 0.0000 0.9808 0.000 1.000
#> GSM647567 1 0.0000 0.9748 1.000 0.000
#> GSM647568 2 0.0000 0.9808 0.000 1.000
#> GSM647570 2 0.0000 0.9808 0.000 1.000
#> GSM647573 1 0.0000 0.9748 1.000 0.000
#> GSM647576 2 0.6048 0.8332 0.148 0.852
#> GSM647579 2 0.6438 0.8136 0.164 0.836
#> GSM647580 1 0.0000 0.9748 1.000 0.000
#> GSM647583 1 0.0000 0.9748 1.000 0.000
#> GSM647592 2 0.0000 0.9808 0.000 1.000
#> GSM647593 2 0.0000 0.9808 0.000 1.000
#> GSM647595 2 0.0000 0.9808 0.000 1.000
#> GSM647597 1 0.9996 0.0746 0.512 0.488
#> GSM647598 2 0.0000 0.9808 0.000 1.000
#> GSM647613 2 0.0000 0.9808 0.000 1.000
#> GSM647615 2 0.0000 0.9808 0.000 1.000
#> GSM647616 1 0.0000 0.9748 1.000 0.000
#> GSM647619 2 0.0000 0.9808 0.000 1.000
#> GSM647582 2 0.0000 0.9808 0.000 1.000
#> GSM647591 2 0.0000 0.9808 0.000 1.000
#> GSM647527 2 0.0000 0.9808 0.000 1.000
#> GSM647530 1 0.7299 0.7513 0.796 0.204
#> GSM647532 1 0.0000 0.9748 1.000 0.000
#> GSM647544 2 0.0000 0.9808 0.000 1.000
#> GSM647551 2 0.0000 0.9808 0.000 1.000
#> GSM647556 1 0.0000 0.9748 1.000 0.000
#> GSM647558 2 0.0000 0.9808 0.000 1.000
#> GSM647572 1 0.0000 0.9748 1.000 0.000
#> GSM647578 2 0.6438 0.8136 0.164 0.836
#> GSM647581 2 0.0000 0.9808 0.000 1.000
#> GSM647594 2 0.0000 0.9808 0.000 1.000
#> GSM647599 1 0.0000 0.9748 1.000 0.000
#> GSM647600 2 0.0000 0.9808 0.000 1.000
#> GSM647601 2 0.0000 0.9808 0.000 1.000
#> GSM647603 2 0.0000 0.9808 0.000 1.000
#> GSM647610 2 0.7219 0.7638 0.200 0.800
#> GSM647611 2 0.0000 0.9808 0.000 1.000
#> GSM647612 2 0.0000 0.9808 0.000 1.000
#> GSM647614 2 0.0000 0.9808 0.000 1.000
#> GSM647618 2 0.0000 0.9808 0.000 1.000
#> GSM647629 2 0.0000 0.9808 0.000 1.000
#> GSM647535 2 0.0000 0.9808 0.000 1.000
#> GSM647563 2 0.0000 0.9808 0.000 1.000
#> GSM647542 2 0.0000 0.9808 0.000 1.000
#> GSM647543 2 0.0000 0.9808 0.000 1.000
#> GSM647548 1 0.7139 0.7622 0.804 0.196
#> GSM647554 2 0.2603 0.9428 0.044 0.956
#> GSM647555 2 0.0000 0.9808 0.000 1.000
#> GSM647559 2 0.0000 0.9808 0.000 1.000
#> GSM647562 2 0.0000 0.9808 0.000 1.000
#> GSM647564 1 0.0000 0.9748 1.000 0.000
#> GSM647571 2 0.0000 0.9808 0.000 1.000
#> GSM647584 2 0.0000 0.9808 0.000 1.000
#> GSM647585 1 0.0000 0.9748 1.000 0.000
#> GSM647586 2 0.0000 0.9808 0.000 1.000
#> GSM647587 2 0.0000 0.9808 0.000 1.000
#> GSM647588 2 0.0000 0.9808 0.000 1.000
#> GSM647596 2 0.0000 0.9808 0.000 1.000
#> GSM647602 1 0.0000 0.9748 1.000 0.000
#> GSM647609 2 0.0000 0.9808 0.000 1.000
#> GSM647620 2 0.0000 0.9808 0.000 1.000
#> GSM647627 2 0.0000 0.9808 0.000 1.000
#> GSM647628 2 0.0000 0.9808 0.000 1.000
#> GSM647533 1 0.0000 0.9748 1.000 0.000
#> GSM647536 1 0.0000 0.9748 1.000 0.000
#> GSM647537 1 0.0000 0.9748 1.000 0.000
#> GSM647606 1 0.0000 0.9748 1.000 0.000
#> GSM647621 1 0.0000 0.9748 1.000 0.000
#> GSM647626 1 0.0000 0.9748 1.000 0.000
#> GSM647538 1 0.0000 0.9748 1.000 0.000
#> GSM647575 1 0.0000 0.9748 1.000 0.000
#> GSM647590 1 0.0000 0.9748 1.000 0.000
#> GSM647605 1 0.0000 0.9748 1.000 0.000
#> GSM647607 1 0.0000 0.9748 1.000 0.000
#> GSM647608 1 0.0000 0.9748 1.000 0.000
#> GSM647622 1 0.0000 0.9748 1.000 0.000
#> GSM647623 1 0.0000 0.9748 1.000 0.000
#> GSM647624 1 0.0000 0.9748 1.000 0.000
#> GSM647625 1 0.0000 0.9748 1.000 0.000
#> GSM647534 1 0.0000 0.9748 1.000 0.000
#> GSM647539 1 0.0000 0.9748 1.000 0.000
#> GSM647566 1 0.0000 0.9748 1.000 0.000
#> GSM647589 1 0.0000 0.9748 1.000 0.000
#> GSM647604 1 0.0000 0.9748 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 3 0.0000 0.944 0.000 0.000 1.000
#> GSM647574 3 0.0000 0.944 0.000 0.000 1.000
#> GSM647577 3 0.0000 0.944 0.000 0.000 1.000
#> GSM647547 3 0.0237 0.941 0.004 0.000 0.996
#> GSM647552 2 0.2711 0.881 0.088 0.912 0.000
#> GSM647553 3 0.0000 0.944 0.000 0.000 1.000
#> GSM647565 3 0.0000 0.944 0.000 0.000 1.000
#> GSM647545 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647549 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647550 3 0.0237 0.941 0.000 0.004 0.996
#> GSM647560 3 0.3816 0.819 0.000 0.148 0.852
#> GSM647617 3 0.0000 0.944 0.000 0.000 1.000
#> GSM647528 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647529 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647531 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647540 3 0.0000 0.944 0.000 0.000 1.000
#> GSM647541 2 0.4796 0.717 0.000 0.780 0.220
#> GSM647546 3 0.0000 0.944 0.000 0.000 1.000
#> GSM647557 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647561 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647567 1 0.5835 0.485 0.660 0.000 0.340
#> GSM647568 3 0.0000 0.944 0.000 0.000 1.000
#> GSM647570 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647573 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647576 3 0.0000 0.944 0.000 0.000 1.000
#> GSM647579 3 0.0000 0.944 0.000 0.000 1.000
#> GSM647580 3 0.0000 0.944 0.000 0.000 1.000
#> GSM647583 3 0.0000 0.944 0.000 0.000 1.000
#> GSM647592 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647593 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647595 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647597 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647598 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647613 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647615 3 0.5988 0.469 0.000 0.368 0.632
#> GSM647616 3 0.0000 0.944 0.000 0.000 1.000
#> GSM647619 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647582 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647591 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647527 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647530 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647532 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647544 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647551 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647556 3 0.0000 0.944 0.000 0.000 1.000
#> GSM647558 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647572 3 0.0000 0.944 0.000 0.000 1.000
#> GSM647578 3 0.0237 0.941 0.000 0.004 0.996
#> GSM647581 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647594 2 0.6079 0.362 0.388 0.612 0.000
#> GSM647599 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647600 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647601 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647603 2 0.5254 0.649 0.000 0.736 0.264
#> GSM647610 2 0.5558 0.777 0.152 0.800 0.048
#> GSM647611 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647612 3 0.3482 0.841 0.000 0.128 0.872
#> GSM647614 3 0.5905 0.504 0.000 0.352 0.648
#> GSM647618 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647629 2 0.3551 0.833 0.000 0.868 0.132
#> GSM647535 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647563 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647542 3 0.0000 0.944 0.000 0.000 1.000
#> GSM647543 3 0.0000 0.944 0.000 0.000 1.000
#> GSM647548 3 0.7190 0.487 0.320 0.044 0.636
#> GSM647554 2 0.5926 0.475 0.000 0.644 0.356
#> GSM647555 3 0.2356 0.890 0.000 0.072 0.928
#> GSM647559 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647562 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647564 3 0.0000 0.944 0.000 0.000 1.000
#> GSM647571 3 0.3879 0.819 0.000 0.152 0.848
#> GSM647584 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647585 3 0.0000 0.944 0.000 0.000 1.000
#> GSM647586 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647587 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647588 2 0.2537 0.888 0.000 0.920 0.080
#> GSM647596 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647602 3 0.0000 0.944 0.000 0.000 1.000
#> GSM647609 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647620 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647627 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647628 2 0.0000 0.958 0.000 1.000 0.000
#> GSM647533 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647536 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647537 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647606 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647621 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647626 3 0.0000 0.944 0.000 0.000 1.000
#> GSM647538 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647575 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647590 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647605 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647607 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647608 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647622 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647623 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647624 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647625 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647534 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647539 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647566 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647589 1 0.0000 0.987 1.000 0.000 0.000
#> GSM647604 1 0.0000 0.987 1.000 0.000 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 3 0.0000 0.9611 0.000 0.000 1.000 0.000
#> GSM647574 3 0.0000 0.9611 0.000 0.000 1.000 0.000
#> GSM647577 3 0.0000 0.9611 0.000 0.000 1.000 0.000
#> GSM647547 3 0.1867 0.8956 0.000 0.000 0.928 0.072
#> GSM647552 2 0.0376 0.8798 0.004 0.992 0.000 0.004
#> GSM647553 3 0.0000 0.9611 0.000 0.000 1.000 0.000
#> GSM647565 4 0.0336 0.8766 0.000 0.000 0.008 0.992
#> GSM647545 4 0.0817 0.8749 0.000 0.024 0.000 0.976
#> GSM647549 4 0.0707 0.8751 0.000 0.020 0.000 0.980
#> GSM647550 4 0.4817 0.3479 0.000 0.000 0.388 0.612
#> GSM647560 4 0.1978 0.8405 0.000 0.004 0.068 0.928
#> GSM647617 3 0.0000 0.9611 0.000 0.000 1.000 0.000
#> GSM647528 2 0.3907 0.7019 0.000 0.768 0.000 0.232
#> GSM647529 1 0.0000 0.9737 1.000 0.000 0.000 0.000
#> GSM647531 2 0.4382 0.6288 0.000 0.704 0.000 0.296
#> GSM647540 3 0.0000 0.9611 0.000 0.000 1.000 0.000
#> GSM647541 4 0.3172 0.7603 0.000 0.160 0.000 0.840
#> GSM647546 3 0.0000 0.9611 0.000 0.000 1.000 0.000
#> GSM647557 2 0.3311 0.7831 0.000 0.828 0.000 0.172
#> GSM647561 2 0.4477 0.5870 0.000 0.688 0.000 0.312
#> GSM647567 3 0.4981 0.1509 0.464 0.000 0.536 0.000
#> GSM647568 4 0.0592 0.8758 0.000 0.000 0.016 0.984
#> GSM647570 4 0.0336 0.8780 0.000 0.008 0.000 0.992
#> GSM647573 1 0.1557 0.9249 0.944 0.000 0.000 0.056
#> GSM647576 3 0.0000 0.9611 0.000 0.000 1.000 0.000
#> GSM647579 3 0.0000 0.9611 0.000 0.000 1.000 0.000
#> GSM647580 3 0.0000 0.9611 0.000 0.000 1.000 0.000
#> GSM647583 3 0.0000 0.9611 0.000 0.000 1.000 0.000
#> GSM647592 2 0.0000 0.8823 0.000 1.000 0.000 0.000
#> GSM647593 2 0.0336 0.8838 0.000 0.992 0.000 0.008
#> GSM647595 2 0.0336 0.8838 0.000 0.992 0.000 0.008
#> GSM647597 1 0.4655 0.5466 0.684 0.312 0.000 0.004
#> GSM647598 2 0.0336 0.8838 0.000 0.992 0.000 0.008
#> GSM647613 2 0.4972 0.2227 0.000 0.544 0.000 0.456
#> GSM647615 4 0.0376 0.8786 0.000 0.004 0.004 0.992
#> GSM647616 3 0.0000 0.9611 0.000 0.000 1.000 0.000
#> GSM647619 2 0.0000 0.8823 0.000 1.000 0.000 0.000
#> GSM647582 2 0.0000 0.8823 0.000 1.000 0.000 0.000
#> GSM647591 2 0.0469 0.8830 0.000 0.988 0.000 0.012
#> GSM647527 2 0.3907 0.7019 0.000 0.768 0.000 0.232
#> GSM647530 1 0.0336 0.9719 0.992 0.000 0.000 0.008
#> GSM647532 1 0.0336 0.9719 0.992 0.000 0.000 0.008
#> GSM647544 4 0.4304 0.6123 0.000 0.284 0.000 0.716
#> GSM647551 2 0.0336 0.8838 0.000 0.992 0.000 0.008
#> GSM647556 3 0.0000 0.9611 0.000 0.000 1.000 0.000
#> GSM647558 4 0.0336 0.8778 0.000 0.008 0.000 0.992
#> GSM647572 3 0.0000 0.9611 0.000 0.000 1.000 0.000
#> GSM647578 3 0.4552 0.7535 0.000 0.072 0.800 0.128
#> GSM647581 4 0.0707 0.8751 0.000 0.020 0.000 0.980
#> GSM647594 2 0.4059 0.7087 0.200 0.788 0.000 0.012
#> GSM647599 1 0.0000 0.9737 1.000 0.000 0.000 0.000
#> GSM647600 2 0.0336 0.8838 0.000 0.992 0.000 0.008
#> GSM647601 2 0.0336 0.8838 0.000 0.992 0.000 0.008
#> GSM647603 2 0.2706 0.8261 0.000 0.900 0.080 0.020
#> GSM647610 2 0.2266 0.8274 0.004 0.912 0.084 0.000
#> GSM647611 2 0.0188 0.8820 0.000 0.996 0.000 0.004
#> GSM647612 4 0.0376 0.8786 0.000 0.004 0.004 0.992
#> GSM647614 4 0.0376 0.8786 0.000 0.004 0.004 0.992
#> GSM647618 2 0.0188 0.8813 0.000 0.996 0.000 0.004
#> GSM647629 2 0.3569 0.7344 0.000 0.804 0.000 0.196
#> GSM647535 4 0.4998 0.0519 0.000 0.488 0.000 0.512
#> GSM647563 4 0.0592 0.8770 0.000 0.016 0.000 0.984
#> GSM647542 4 0.0592 0.8758 0.000 0.000 0.016 0.984
#> GSM647543 4 0.0469 0.8773 0.000 0.000 0.012 0.988
#> GSM647548 4 0.0336 0.8761 0.000 0.008 0.000 0.992
#> GSM647554 2 0.4855 0.3177 0.000 0.600 0.400 0.000
#> GSM647555 4 0.0592 0.8758 0.000 0.000 0.016 0.984
#> GSM647559 4 0.4746 0.4593 0.000 0.368 0.000 0.632
#> GSM647562 4 0.4605 0.5195 0.000 0.336 0.000 0.664
#> GSM647564 3 0.0000 0.9611 0.000 0.000 1.000 0.000
#> GSM647571 4 0.2124 0.8456 0.000 0.068 0.008 0.924
#> GSM647584 2 0.0336 0.8838 0.000 0.992 0.000 0.008
#> GSM647585 3 0.0000 0.9611 0.000 0.000 1.000 0.000
#> GSM647586 2 0.0817 0.8800 0.000 0.976 0.000 0.024
#> GSM647587 2 0.3649 0.7279 0.000 0.796 0.000 0.204
#> GSM647588 4 0.4543 0.4929 0.000 0.324 0.000 0.676
#> GSM647596 2 0.2589 0.8227 0.000 0.884 0.000 0.116
#> GSM647602 3 0.0000 0.9611 0.000 0.000 1.000 0.000
#> GSM647609 2 0.0336 0.8838 0.000 0.992 0.000 0.008
#> GSM647620 2 0.0592 0.8823 0.000 0.984 0.000 0.016
#> GSM647627 2 0.0592 0.8823 0.000 0.984 0.000 0.016
#> GSM647628 4 0.0336 0.8780 0.000 0.008 0.000 0.992
#> GSM647533 1 0.0000 0.9737 1.000 0.000 0.000 0.000
#> GSM647536 1 0.0336 0.9719 0.992 0.000 0.000 0.008
#> GSM647537 1 0.0000 0.9737 1.000 0.000 0.000 0.000
#> GSM647606 1 0.0000 0.9737 1.000 0.000 0.000 0.000
#> GSM647621 1 0.0188 0.9734 0.996 0.000 0.000 0.004
#> GSM647626 3 0.0000 0.9611 0.000 0.000 1.000 0.000
#> GSM647538 1 0.0000 0.9737 1.000 0.000 0.000 0.000
#> GSM647575 1 0.0188 0.9734 0.996 0.000 0.000 0.004
#> GSM647590 1 0.0188 0.9734 0.996 0.000 0.000 0.004
#> GSM647605 1 0.0000 0.9737 1.000 0.000 0.000 0.000
#> GSM647607 1 0.0188 0.9734 0.996 0.000 0.000 0.004
#> GSM647608 1 0.0188 0.9734 0.996 0.000 0.000 0.004
#> GSM647622 1 0.0000 0.9737 1.000 0.000 0.000 0.000
#> GSM647623 1 0.0000 0.9737 1.000 0.000 0.000 0.000
#> GSM647624 1 0.0000 0.9737 1.000 0.000 0.000 0.000
#> GSM647625 1 0.0000 0.9737 1.000 0.000 0.000 0.000
#> GSM647534 1 0.3569 0.7569 0.804 0.196 0.000 0.000
#> GSM647539 1 0.0188 0.9734 0.996 0.000 0.000 0.004
#> GSM647566 1 0.0188 0.9734 0.996 0.000 0.000 0.004
#> GSM647589 1 0.0188 0.9734 0.996 0.000 0.000 0.004
#> GSM647604 1 0.0000 0.9737 1.000 0.000 0.000 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.0000 0.9910 0.000 0.000 1.000 0.000 0.000
#> GSM647574 3 0.0703 0.9700 0.000 0.000 0.976 0.024 0.000
#> GSM647577 3 0.0000 0.9910 0.000 0.000 1.000 0.000 0.000
#> GSM647547 4 0.3675 0.6757 0.000 0.024 0.188 0.788 0.000
#> GSM647552 5 0.6183 0.3895 0.308 0.004 0.000 0.144 0.544
#> GSM647553 3 0.0000 0.9910 0.000 0.000 1.000 0.000 0.000
#> GSM647565 4 0.3816 0.5813 0.000 0.304 0.000 0.696 0.000
#> GSM647545 2 0.1981 0.7890 0.000 0.924 0.000 0.028 0.048
#> GSM647549 2 0.1830 0.7915 0.000 0.932 0.000 0.028 0.040
#> GSM647550 2 0.4717 0.3289 0.000 0.584 0.396 0.020 0.000
#> GSM647560 2 0.0579 0.8013 0.000 0.984 0.008 0.008 0.000
#> GSM647617 3 0.0000 0.9910 0.000 0.000 1.000 0.000 0.000
#> GSM647528 2 0.5605 0.1761 0.000 0.464 0.000 0.072 0.464
#> GSM647529 1 0.0609 0.9080 0.980 0.000 0.000 0.020 0.000
#> GSM647531 5 0.5019 0.3975 0.000 0.316 0.000 0.052 0.632
#> GSM647540 3 0.0290 0.9854 0.000 0.000 0.992 0.008 0.000
#> GSM647541 2 0.0794 0.8031 0.000 0.972 0.000 0.028 0.000
#> GSM647546 3 0.0000 0.9910 0.000 0.000 1.000 0.000 0.000
#> GSM647557 5 0.5045 0.6025 0.000 0.196 0.000 0.108 0.696
#> GSM647561 2 0.5509 0.1596 0.000 0.468 0.000 0.064 0.468
#> GSM647567 1 0.4909 0.2393 0.560 0.000 0.412 0.000 0.028
#> GSM647568 2 0.0162 0.8024 0.000 0.996 0.004 0.000 0.000
#> GSM647570 2 0.0162 0.8030 0.000 0.996 0.000 0.004 0.000
#> GSM647573 4 0.3242 0.8679 0.216 0.000 0.000 0.784 0.000
#> GSM647576 3 0.0000 0.9910 0.000 0.000 1.000 0.000 0.000
#> GSM647579 3 0.0290 0.9854 0.000 0.000 0.992 0.008 0.000
#> GSM647580 3 0.0000 0.9910 0.000 0.000 1.000 0.000 0.000
#> GSM647583 3 0.0000 0.9910 0.000 0.000 1.000 0.000 0.000
#> GSM647592 5 0.1012 0.8203 0.012 0.000 0.000 0.020 0.968
#> GSM647593 5 0.0671 0.8174 0.000 0.004 0.000 0.016 0.980
#> GSM647595 5 0.0865 0.8154 0.000 0.004 0.000 0.024 0.972
#> GSM647597 1 0.3303 0.7687 0.848 0.000 0.000 0.076 0.076
#> GSM647598 5 0.1282 0.8172 0.000 0.004 0.000 0.044 0.952
#> GSM647613 2 0.5006 0.5123 0.000 0.624 0.000 0.048 0.328
#> GSM647615 2 0.0000 0.8033 0.000 1.000 0.000 0.000 0.000
#> GSM647616 3 0.0000 0.9910 0.000 0.000 1.000 0.000 0.000
#> GSM647619 5 0.0703 0.8204 0.000 0.000 0.000 0.024 0.976
#> GSM647582 5 0.2605 0.7901 0.000 0.000 0.000 0.148 0.852
#> GSM647591 5 0.1124 0.8125 0.000 0.004 0.000 0.036 0.960
#> GSM647527 2 0.5605 0.1761 0.000 0.464 0.000 0.072 0.464
#> GSM647530 4 0.3048 0.8505 0.176 0.000 0.000 0.820 0.004
#> GSM647532 4 0.3966 0.7423 0.336 0.000 0.000 0.664 0.000
#> GSM647544 2 0.5344 0.6366 0.000 0.672 0.000 0.164 0.164
#> GSM647551 5 0.0865 0.8169 0.000 0.004 0.000 0.024 0.972
#> GSM647556 3 0.0000 0.9910 0.000 0.000 1.000 0.000 0.000
#> GSM647558 2 0.0912 0.7998 0.000 0.972 0.000 0.016 0.012
#> GSM647572 3 0.0000 0.9910 0.000 0.000 1.000 0.000 0.000
#> GSM647578 3 0.2448 0.8725 0.000 0.088 0.892 0.020 0.000
#> GSM647581 2 0.1836 0.7918 0.000 0.932 0.000 0.032 0.036
#> GSM647594 5 0.5315 0.0602 0.456 0.004 0.000 0.040 0.500
#> GSM647599 1 0.0000 0.9234 1.000 0.000 0.000 0.000 0.000
#> GSM647600 5 0.0955 0.8187 0.000 0.004 0.000 0.028 0.968
#> GSM647601 5 0.0963 0.8180 0.000 0.000 0.000 0.036 0.964
#> GSM647603 5 0.5090 0.7057 0.000 0.092 0.016 0.168 0.724
#> GSM647610 5 0.4807 0.7074 0.140 0.000 0.000 0.132 0.728
#> GSM647611 5 0.3183 0.7818 0.000 0.016 0.000 0.156 0.828
#> GSM647612 2 0.0000 0.8033 0.000 1.000 0.000 0.000 0.000
#> GSM647614 2 0.0000 0.8033 0.000 1.000 0.000 0.000 0.000
#> GSM647618 5 0.2773 0.7895 0.000 0.000 0.000 0.164 0.836
#> GSM647629 5 0.2971 0.7400 0.000 0.156 0.000 0.008 0.836
#> GSM647535 2 0.5559 0.3506 0.000 0.544 0.000 0.076 0.380
#> GSM647563 2 0.2864 0.7711 0.000 0.864 0.000 0.112 0.024
#> GSM647542 2 0.0162 0.8024 0.000 0.996 0.004 0.000 0.000
#> GSM647543 2 0.0000 0.8033 0.000 1.000 0.000 0.000 0.000
#> GSM647548 4 0.2648 0.7141 0.000 0.152 0.000 0.848 0.000
#> GSM647554 5 0.4425 0.3443 0.000 0.000 0.392 0.008 0.600
#> GSM647555 2 0.0955 0.8014 0.000 0.968 0.004 0.028 0.000
#> GSM647559 2 0.5854 0.5367 0.000 0.600 0.000 0.160 0.240
#> GSM647562 2 0.5447 0.6280 0.000 0.660 0.000 0.168 0.172
#> GSM647564 3 0.0000 0.9910 0.000 0.000 1.000 0.000 0.000
#> GSM647571 2 0.3386 0.7519 0.000 0.832 0.000 0.128 0.040
#> GSM647584 5 0.0771 0.8166 0.000 0.004 0.000 0.020 0.976
#> GSM647585 3 0.0000 0.9910 0.000 0.000 1.000 0.000 0.000
#> GSM647586 5 0.2853 0.7908 0.000 0.052 0.000 0.072 0.876
#> GSM647587 5 0.6338 -0.0576 0.000 0.392 0.000 0.160 0.448
#> GSM647588 2 0.4550 0.5291 0.000 0.688 0.000 0.036 0.276
#> GSM647596 5 0.2946 0.7769 0.000 0.088 0.000 0.044 0.868
#> GSM647602 3 0.0000 0.9910 0.000 0.000 1.000 0.000 0.000
#> GSM647609 5 0.0963 0.8180 0.000 0.000 0.000 0.036 0.964
#> GSM647620 5 0.2236 0.8045 0.000 0.024 0.000 0.068 0.908
#> GSM647627 5 0.2325 0.8031 0.000 0.028 0.000 0.068 0.904
#> GSM647628 2 0.0000 0.8033 0.000 1.000 0.000 0.000 0.000
#> GSM647533 1 0.0000 0.9234 1.000 0.000 0.000 0.000 0.000
#> GSM647536 1 0.2813 0.7175 0.832 0.000 0.000 0.168 0.000
#> GSM647537 1 0.0000 0.9234 1.000 0.000 0.000 0.000 0.000
#> GSM647606 1 0.0000 0.9234 1.000 0.000 0.000 0.000 0.000
#> GSM647621 4 0.4088 0.7196 0.368 0.000 0.000 0.632 0.000
#> GSM647626 3 0.0000 0.9910 0.000 0.000 1.000 0.000 0.000
#> GSM647538 1 0.0000 0.9234 1.000 0.000 0.000 0.000 0.000
#> GSM647575 4 0.3242 0.8679 0.216 0.000 0.000 0.784 0.000
#> GSM647590 4 0.3661 0.8312 0.276 0.000 0.000 0.724 0.000
#> GSM647605 1 0.0000 0.9234 1.000 0.000 0.000 0.000 0.000
#> GSM647607 4 0.3242 0.8679 0.216 0.000 0.000 0.784 0.000
#> GSM647608 4 0.3242 0.8679 0.216 0.000 0.000 0.784 0.000
#> GSM647622 1 0.0000 0.9234 1.000 0.000 0.000 0.000 0.000
#> GSM647623 1 0.0000 0.9234 1.000 0.000 0.000 0.000 0.000
#> GSM647624 1 0.0000 0.9234 1.000 0.000 0.000 0.000 0.000
#> GSM647625 1 0.0000 0.9234 1.000 0.000 0.000 0.000 0.000
#> GSM647534 1 0.0963 0.8886 0.964 0.000 0.000 0.000 0.036
#> GSM647539 4 0.3242 0.8679 0.216 0.000 0.000 0.784 0.000
#> GSM647566 4 0.3857 0.7960 0.312 0.000 0.000 0.688 0.000
#> GSM647589 4 0.3366 0.8665 0.212 0.000 0.004 0.784 0.000
#> GSM647604 1 0.0000 0.9234 1.000 0.000 0.000 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.0000 0.9688 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647574 3 0.1806 0.8904 0.000 0.004 0.908 0.088 0.000 0.000
#> GSM647577 3 0.0000 0.9688 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647547 4 0.1349 0.8265 0.000 0.004 0.056 0.940 0.000 0.000
#> GSM647552 5 0.5055 0.3723 0.136 0.000 0.000 0.044 0.704 0.116
#> GSM647553 3 0.0260 0.9643 0.000 0.000 0.992 0.008 0.000 0.000
#> GSM647565 4 0.3109 0.6355 0.000 0.224 0.000 0.772 0.004 0.000
#> GSM647545 2 0.5361 0.5872 0.000 0.628 0.000 0.040 0.260 0.072
#> GSM647549 2 0.5650 0.5744 0.000 0.608 0.000 0.044 0.252 0.096
#> GSM647550 2 0.6539 0.2844 0.000 0.472 0.348 0.008 0.056 0.116
#> GSM647560 2 0.2138 0.7686 0.000 0.908 0.004 0.000 0.052 0.036
#> GSM647617 3 0.0000 0.9688 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647528 6 0.3732 0.5191 0.000 0.144 0.000 0.000 0.076 0.780
#> GSM647529 1 0.2384 0.8339 0.884 0.000 0.000 0.032 0.084 0.000
#> GSM647531 5 0.5455 0.2646 0.000 0.104 0.000 0.064 0.668 0.164
#> GSM647540 3 0.2145 0.9075 0.000 0.004 0.912 0.008 0.056 0.020
#> GSM647541 2 0.3284 0.7316 0.000 0.832 0.000 0.008 0.056 0.104
#> GSM647546 3 0.0000 0.9688 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647557 5 0.4747 0.3057 0.000 0.052 0.000 0.064 0.728 0.156
#> GSM647561 5 0.6585 -0.0212 0.000 0.212 0.000 0.036 0.416 0.336
#> GSM647567 1 0.5473 0.2114 0.504 0.000 0.400 0.008 0.084 0.004
#> GSM647568 2 0.0000 0.8056 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647570 2 0.0870 0.8013 0.000 0.972 0.000 0.012 0.004 0.012
#> GSM647573 4 0.1471 0.8631 0.064 0.004 0.000 0.932 0.000 0.000
#> GSM647576 3 0.0363 0.9615 0.000 0.012 0.988 0.000 0.000 0.000
#> GSM647579 3 0.1801 0.9164 0.000 0.000 0.924 0.004 0.056 0.016
#> GSM647580 3 0.0000 0.9688 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647583 3 0.0000 0.9688 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647592 5 0.4107 0.3564 0.004 0.000 0.000 0.004 0.540 0.452
#> GSM647593 5 0.3620 0.4795 0.000 0.000 0.000 0.000 0.648 0.352
#> GSM647595 5 0.3531 0.4936 0.000 0.000 0.000 0.000 0.672 0.328
#> GSM647597 1 0.3488 0.7723 0.804 0.000 0.000 0.012 0.152 0.032
#> GSM647598 5 0.3868 0.2580 0.000 0.000 0.000 0.000 0.504 0.496
#> GSM647613 5 0.6437 -0.1767 0.000 0.372 0.000 0.024 0.392 0.212
#> GSM647615 2 0.0146 0.8053 0.000 0.996 0.000 0.000 0.004 0.000
#> GSM647616 3 0.0000 0.9688 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647619 5 0.3774 0.4226 0.000 0.000 0.000 0.000 0.592 0.408
#> GSM647582 6 0.3607 0.1112 0.000 0.000 0.000 0.000 0.348 0.652
#> GSM647591 5 0.3601 0.4961 0.000 0.000 0.000 0.004 0.684 0.312
#> GSM647527 6 0.3732 0.5191 0.000 0.144 0.000 0.000 0.076 0.780
#> GSM647530 4 0.2830 0.7794 0.020 0.000 0.000 0.836 0.144 0.000
#> GSM647532 4 0.5024 0.4930 0.340 0.000 0.000 0.572 0.088 0.000
#> GSM647544 6 0.3797 0.3765 0.000 0.292 0.000 0.000 0.016 0.692
#> GSM647551 5 0.3531 0.4897 0.000 0.000 0.000 0.000 0.672 0.328
#> GSM647556 3 0.0000 0.9688 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647558 2 0.4005 0.7226 0.000 0.800 0.000 0.052 0.076 0.072
#> GSM647572 3 0.0000 0.9688 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647578 3 0.5376 0.6410 0.000 0.128 0.696 0.008 0.060 0.108
#> GSM647581 2 0.5937 0.5497 0.000 0.580 0.000 0.052 0.256 0.112
#> GSM647594 5 0.5444 0.2129 0.368 0.000 0.000 0.008 0.524 0.100
#> GSM647599 1 0.0146 0.9034 0.996 0.000 0.000 0.004 0.000 0.000
#> GSM647600 5 0.3741 0.4567 0.000 0.008 0.000 0.000 0.672 0.320
#> GSM647601 6 0.3843 -0.2104 0.000 0.000 0.000 0.000 0.452 0.548
#> GSM647603 6 0.3712 0.4241 0.000 0.052 0.000 0.000 0.180 0.768
#> GSM647610 6 0.5021 0.0240 0.080 0.000 0.000 0.004 0.324 0.592
#> GSM647611 6 0.2631 0.3695 0.000 0.000 0.000 0.000 0.180 0.820
#> GSM647612 2 0.0000 0.8056 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647614 2 0.0000 0.8056 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647618 6 0.2854 0.3516 0.000 0.000 0.000 0.000 0.208 0.792
#> GSM647629 5 0.5934 0.2736 0.000 0.192 0.000 0.008 0.500 0.300
#> GSM647535 6 0.5005 0.4207 0.000 0.296 0.000 0.004 0.088 0.612
#> GSM647563 6 0.4546 0.0655 0.000 0.432 0.000 0.012 0.016 0.540
#> GSM647542 2 0.0547 0.7995 0.000 0.980 0.000 0.000 0.000 0.020
#> GSM647543 2 0.0000 0.8056 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647548 4 0.0547 0.8344 0.000 0.020 0.000 0.980 0.000 0.000
#> GSM647554 5 0.6328 0.1705 0.000 0.004 0.356 0.008 0.400 0.232
#> GSM647555 2 0.2859 0.6874 0.000 0.828 0.000 0.000 0.016 0.156
#> GSM647559 6 0.3288 0.4401 0.000 0.276 0.000 0.000 0.000 0.724
#> GSM647562 6 0.4011 0.3448 0.000 0.304 0.000 0.000 0.024 0.672
#> GSM647564 3 0.0000 0.9688 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647571 2 0.3782 0.2464 0.000 0.588 0.000 0.000 0.000 0.412
#> GSM647584 5 0.3659 0.4744 0.000 0.000 0.000 0.000 0.636 0.364
#> GSM647585 3 0.0000 0.9688 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647586 6 0.2250 0.4771 0.000 0.020 0.000 0.000 0.092 0.888
#> GSM647587 6 0.2100 0.5256 0.000 0.112 0.000 0.000 0.004 0.884
#> GSM647588 6 0.5623 0.0911 0.000 0.408 0.000 0.012 0.104 0.476
#> GSM647596 6 0.4630 -0.0406 0.000 0.048 0.000 0.000 0.372 0.580
#> GSM647602 3 0.0000 0.9688 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647609 6 0.3862 -0.2576 0.000 0.000 0.000 0.000 0.476 0.524
#> GSM647620 6 0.2668 0.4220 0.000 0.004 0.000 0.000 0.168 0.828
#> GSM647627 6 0.2896 0.4403 0.000 0.016 0.000 0.000 0.160 0.824
#> GSM647628 2 0.1010 0.7985 0.000 0.960 0.000 0.000 0.004 0.036
#> GSM647533 1 0.0000 0.9057 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647536 1 0.4159 0.6560 0.736 0.000 0.000 0.176 0.088 0.000
#> GSM647537 1 0.0000 0.9057 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647606 1 0.0000 0.9057 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647621 4 0.3330 0.6978 0.284 0.000 0.000 0.716 0.000 0.000
#> GSM647626 3 0.0000 0.9688 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647538 1 0.0146 0.9033 0.996 0.000 0.000 0.000 0.004 0.000
#> GSM647575 4 0.1644 0.8638 0.076 0.000 0.000 0.920 0.004 0.000
#> GSM647590 4 0.3290 0.7475 0.252 0.000 0.000 0.744 0.004 0.000
#> GSM647605 1 0.0000 0.9057 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647607 4 0.1644 0.8638 0.076 0.000 0.000 0.920 0.004 0.000
#> GSM647608 4 0.1501 0.8637 0.076 0.000 0.000 0.924 0.000 0.000
#> GSM647622 1 0.0000 0.9057 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647623 1 0.0000 0.9057 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647624 1 0.0000 0.9057 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647625 1 0.0000 0.9057 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647534 1 0.2632 0.7498 0.832 0.000 0.000 0.000 0.164 0.004
#> GSM647539 4 0.1588 0.8641 0.072 0.000 0.000 0.924 0.004 0.000
#> GSM647566 4 0.3565 0.6778 0.304 0.000 0.000 0.692 0.004 0.000
#> GSM647589 4 0.1728 0.8622 0.064 0.004 0.008 0.924 0.000 0.000
#> GSM647604 1 0.0000 0.9057 1.000 0.000 0.000 0.000 0.000 0.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n disease.state(p) development.stage(p) other(p) k
#> CV:skmeans 102 1.54e-08 0.0919 0.6747 2
#> CV:skmeans 98 8.30e-15 0.0127 0.0649 3
#> CV:skmeans 96 1.08e-13 0.0184 0.0702 4
#> CV:skmeans 92 6.59e-11 0.0313 0.1437 5
#> CV:skmeans 65 3.46e-07 0.3305 0.1276 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["CV", "pam"]
# you can also extract it by
# res = res_list["CV:pam"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'CV' method.
#> Subgroups are detected by 'pam' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 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 0.455 0.754 0.870 0.4045 0.541 0.541
#> 3 3 0.584 0.593 0.800 0.5012 0.843 0.721
#> 4 4 0.717 0.829 0.906 0.1930 0.746 0.466
#> 5 5 0.639 0.701 0.798 0.0639 0.833 0.490
#> 6 6 0.695 0.681 0.801 0.0585 0.877 0.521
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
#> GSM647569 1 0.9635 0.697 0.612 0.388
#> GSM647574 1 0.9635 0.697 0.612 0.388
#> GSM647577 1 0.9635 0.697 0.612 0.388
#> GSM647547 1 0.9635 0.697 0.612 0.388
#> GSM647552 2 0.6438 0.685 0.164 0.836
#> GSM647553 1 0.9635 0.697 0.612 0.388
#> GSM647565 2 0.8081 0.486 0.248 0.752
#> GSM647545 2 0.0000 0.902 0.000 1.000
#> GSM647549 2 0.0000 0.902 0.000 1.000
#> GSM647550 2 0.7139 0.625 0.196 0.804
#> GSM647560 2 0.0672 0.895 0.008 0.992
#> GSM647617 1 0.9635 0.697 0.612 0.388
#> GSM647528 2 0.0000 0.902 0.000 1.000
#> GSM647529 2 0.9635 0.298 0.388 0.612
#> GSM647531 2 0.0000 0.902 0.000 1.000
#> GSM647540 2 0.9460 0.106 0.364 0.636
#> GSM647541 2 0.0000 0.902 0.000 1.000
#> GSM647546 1 0.9635 0.697 0.612 0.388
#> GSM647557 2 0.0000 0.902 0.000 1.000
#> GSM647561 2 0.0000 0.902 0.000 1.000
#> GSM647567 1 0.9635 0.697 0.612 0.388
#> GSM647568 2 0.7453 0.579 0.212 0.788
#> GSM647570 2 0.0000 0.902 0.000 1.000
#> GSM647573 2 0.8144 0.480 0.252 0.748
#> GSM647576 1 0.9635 0.697 0.612 0.388
#> GSM647579 1 0.9635 0.697 0.612 0.388
#> GSM647580 1 0.9635 0.697 0.612 0.388
#> GSM647583 1 0.9635 0.697 0.612 0.388
#> GSM647592 2 0.0000 0.902 0.000 1.000
#> GSM647593 2 0.0000 0.902 0.000 1.000
#> GSM647595 2 0.0000 0.902 0.000 1.000
#> GSM647597 2 0.9608 0.305 0.384 0.616
#> GSM647598 2 0.0000 0.902 0.000 1.000
#> GSM647613 2 0.0000 0.902 0.000 1.000
#> GSM647615 2 0.0000 0.902 0.000 1.000
#> GSM647616 1 0.9635 0.697 0.612 0.388
#> GSM647619 2 0.0000 0.902 0.000 1.000
#> GSM647582 2 0.0000 0.902 0.000 1.000
#> GSM647591 2 0.0000 0.902 0.000 1.000
#> GSM647527 2 0.0000 0.902 0.000 1.000
#> GSM647530 2 0.0000 0.902 0.000 1.000
#> GSM647532 1 0.9580 0.365 0.620 0.380
#> GSM647544 2 0.0000 0.902 0.000 1.000
#> GSM647551 2 0.0000 0.902 0.000 1.000
#> GSM647556 1 0.9635 0.697 0.612 0.388
#> GSM647558 2 0.0000 0.902 0.000 1.000
#> GSM647572 1 0.9635 0.697 0.612 0.388
#> GSM647578 2 0.7219 0.617 0.200 0.800
#> GSM647581 2 0.0000 0.902 0.000 1.000
#> GSM647594 2 0.0000 0.902 0.000 1.000
#> GSM647599 1 0.5408 0.677 0.876 0.124
#> GSM647600 2 0.6438 0.685 0.164 0.836
#> GSM647601 2 0.0000 0.902 0.000 1.000
#> GSM647603 2 0.0376 0.899 0.004 0.996
#> GSM647610 2 0.4161 0.811 0.084 0.916
#> GSM647611 2 0.0000 0.902 0.000 1.000
#> GSM647612 2 0.0000 0.902 0.000 1.000
#> GSM647614 2 0.0000 0.902 0.000 1.000
#> GSM647618 2 0.0000 0.902 0.000 1.000
#> GSM647629 2 0.6623 0.674 0.172 0.828
#> GSM647535 2 0.0000 0.902 0.000 1.000
#> GSM647563 2 0.0000 0.902 0.000 1.000
#> GSM647542 2 0.0000 0.902 0.000 1.000
#> GSM647543 2 0.7219 0.607 0.200 0.800
#> GSM647548 2 0.0376 0.899 0.004 0.996
#> GSM647554 2 0.7056 0.634 0.192 0.808
#> GSM647555 2 0.0000 0.902 0.000 1.000
#> GSM647559 2 0.0000 0.902 0.000 1.000
#> GSM647562 2 0.0000 0.902 0.000 1.000
#> GSM647564 1 0.9635 0.697 0.612 0.388
#> GSM647571 2 0.0000 0.902 0.000 1.000
#> GSM647584 2 0.0000 0.902 0.000 1.000
#> GSM647585 1 0.9635 0.697 0.612 0.388
#> GSM647586 2 0.0000 0.902 0.000 1.000
#> GSM647587 2 0.0000 0.902 0.000 1.000
#> GSM647588 2 0.0000 0.902 0.000 1.000
#> GSM647596 2 0.0000 0.902 0.000 1.000
#> GSM647602 1 0.9635 0.697 0.612 0.388
#> GSM647609 2 0.0000 0.902 0.000 1.000
#> GSM647620 2 0.0000 0.902 0.000 1.000
#> GSM647627 2 0.0000 0.902 0.000 1.000
#> GSM647628 2 0.0000 0.902 0.000 1.000
#> GSM647533 1 0.0000 0.664 1.000 0.000
#> GSM647536 2 0.9635 0.298 0.388 0.612
#> GSM647537 1 0.0000 0.664 1.000 0.000
#> GSM647606 1 0.0000 0.664 1.000 0.000
#> GSM647621 1 0.0000 0.664 1.000 0.000
#> GSM647626 1 0.9635 0.697 0.612 0.388
#> GSM647538 1 0.0000 0.664 1.000 0.000
#> GSM647575 2 0.6712 0.661 0.176 0.824
#> GSM647590 1 0.2948 0.647 0.948 0.052
#> GSM647605 1 0.0376 0.663 0.996 0.004
#> GSM647607 1 0.9460 0.273 0.636 0.364
#> GSM647608 1 0.9635 0.697 0.612 0.388
#> GSM647622 1 0.0000 0.664 1.000 0.000
#> GSM647623 1 0.0000 0.664 1.000 0.000
#> GSM647624 1 0.0000 0.664 1.000 0.000
#> GSM647625 1 0.0000 0.664 1.000 0.000
#> GSM647534 2 0.6712 0.673 0.176 0.824
#> GSM647539 2 0.0000 0.902 0.000 1.000
#> GSM647566 2 0.8909 0.421 0.308 0.692
#> GSM647589 1 0.9635 0.697 0.612 0.388
#> GSM647604 1 0.4161 0.630 0.916 0.084
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 3 0.0000 0.813 0.000 0.000 1.000
#> GSM647574 3 0.0000 0.813 0.000 0.000 1.000
#> GSM647577 3 0.0000 0.813 0.000 0.000 1.000
#> GSM647547 3 0.6111 0.178 0.396 0.000 0.604
#> GSM647552 3 0.6302 -0.103 0.000 0.480 0.520
#> GSM647553 3 0.0000 0.813 0.000 0.000 1.000
#> GSM647565 1 0.9786 -0.188 0.400 0.364 0.236
#> GSM647545 2 0.6126 0.605 0.400 0.600 0.000
#> GSM647549 2 0.6126 0.605 0.400 0.600 0.000
#> GSM647550 1 0.9863 -0.166 0.400 0.340 0.260
#> GSM647560 2 0.8693 0.497 0.232 0.592 0.176
#> GSM647617 3 0.0000 0.813 0.000 0.000 1.000
#> GSM647528 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647529 2 0.4842 0.504 0.224 0.776 0.000
#> GSM647531 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647540 3 0.0000 0.813 0.000 0.000 1.000
#> GSM647541 2 0.6111 0.608 0.396 0.604 0.000
#> GSM647546 3 0.0237 0.809 0.004 0.000 0.996
#> GSM647557 2 0.0424 0.755 0.008 0.992 0.000
#> GSM647561 2 0.0424 0.755 0.008 0.992 0.000
#> GSM647567 3 0.0592 0.796 0.000 0.012 0.988
#> GSM647568 2 0.9217 0.343 0.400 0.448 0.152
#> GSM647570 2 0.6126 0.605 0.400 0.600 0.000
#> GSM647573 1 0.9315 0.183 0.520 0.220 0.260
#> GSM647576 3 0.0237 0.809 0.004 0.000 0.996
#> GSM647579 3 0.0000 0.813 0.000 0.000 1.000
#> GSM647580 3 0.0000 0.813 0.000 0.000 1.000
#> GSM647583 3 0.0000 0.813 0.000 0.000 1.000
#> GSM647592 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647593 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647595 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647597 2 0.1411 0.729 0.036 0.964 0.000
#> GSM647598 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647613 2 0.6026 0.617 0.376 0.624 0.000
#> GSM647615 2 0.7156 0.575 0.400 0.572 0.028
#> GSM647616 3 0.0000 0.813 0.000 0.000 1.000
#> GSM647619 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647582 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647591 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647527 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647530 2 0.6111 0.608 0.396 0.604 0.000
#> GSM647532 1 0.8624 0.137 0.596 0.240 0.164
#> GSM647544 2 0.6111 0.608 0.396 0.604 0.000
#> GSM647551 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647556 3 0.0000 0.813 0.000 0.000 1.000
#> GSM647558 2 0.6661 0.595 0.400 0.588 0.012
#> GSM647572 3 0.0237 0.809 0.004 0.000 0.996
#> GSM647578 3 0.7940 0.186 0.332 0.076 0.592
#> GSM647581 2 0.6126 0.605 0.400 0.600 0.000
#> GSM647594 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647599 3 0.5591 0.344 0.304 0.000 0.696
#> GSM647600 2 0.0237 0.753 0.000 0.996 0.004
#> GSM647601 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647603 2 0.0237 0.753 0.000 0.996 0.004
#> GSM647610 2 0.2796 0.670 0.000 0.908 0.092
#> GSM647611 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647612 2 0.9293 0.324 0.400 0.440 0.160
#> GSM647614 2 0.6513 0.599 0.400 0.592 0.008
#> GSM647618 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647629 2 0.4291 0.549 0.000 0.820 0.180
#> GSM647535 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647563 2 0.6111 0.608 0.396 0.604 0.000
#> GSM647542 2 0.6661 0.595 0.400 0.588 0.012
#> GSM647543 2 0.6661 0.595 0.400 0.588 0.012
#> GSM647548 2 0.6661 0.595 0.400 0.588 0.012
#> GSM647554 2 0.5254 0.405 0.000 0.736 0.264
#> GSM647555 2 0.6661 0.595 0.400 0.588 0.012
#> GSM647559 2 0.0592 0.754 0.012 0.988 0.000
#> GSM647562 2 0.6111 0.608 0.396 0.604 0.000
#> GSM647564 3 0.0000 0.813 0.000 0.000 1.000
#> GSM647571 2 0.6661 0.595 0.400 0.588 0.012
#> GSM647584 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647585 3 0.0000 0.813 0.000 0.000 1.000
#> GSM647586 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647587 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647588 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647596 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647602 3 0.0000 0.813 0.000 0.000 1.000
#> GSM647609 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647620 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647627 2 0.0000 0.756 0.000 1.000 0.000
#> GSM647628 2 0.6126 0.605 0.400 0.600 0.000
#> GSM647533 3 0.5621 0.346 0.308 0.000 0.692
#> GSM647536 2 0.4589 0.577 0.172 0.820 0.008
#> GSM647537 3 0.5560 0.361 0.300 0.000 0.700
#> GSM647606 1 0.6126 0.323 0.600 0.000 0.400
#> GSM647621 3 0.5650 0.326 0.312 0.000 0.688
#> GSM647626 3 0.0000 0.813 0.000 0.000 1.000
#> GSM647538 1 0.6126 0.323 0.600 0.000 0.400
#> GSM647575 2 0.6937 0.582 0.404 0.576 0.020
#> GSM647590 1 0.6095 0.326 0.608 0.000 0.392
#> GSM647605 1 0.8631 0.340 0.600 0.180 0.220
#> GSM647607 1 0.6053 0.227 0.720 0.020 0.260
#> GSM647608 3 0.0000 0.813 0.000 0.000 1.000
#> GSM647622 1 0.6126 0.323 0.600 0.000 0.400
#> GSM647623 1 0.6126 0.323 0.600 0.000 0.400
#> GSM647624 1 0.6111 0.324 0.604 0.000 0.396
#> GSM647625 1 0.6126 0.323 0.600 0.000 0.400
#> GSM647534 2 0.5656 0.544 0.068 0.804 0.128
#> GSM647539 2 0.6661 0.595 0.400 0.588 0.012
#> GSM647566 1 0.7634 0.274 0.668 0.100 0.232
#> GSM647589 3 0.6111 0.178 0.396 0.000 0.604
#> GSM647604 1 0.8643 0.335 0.600 0.212 0.188
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 3 0.0000 0.9270 0.000 0.000 1.000 0.000
#> GSM647574 3 0.0000 0.9270 0.000 0.000 1.000 0.000
#> GSM647577 3 0.0000 0.9270 0.000 0.000 1.000 0.000
#> GSM647547 4 0.4996 -0.0174 0.000 0.000 0.484 0.516
#> GSM647552 2 0.6338 0.5607 0.000 0.644 0.236 0.120
#> GSM647553 3 0.0469 0.9206 0.000 0.000 0.988 0.012
#> GSM647565 4 0.0336 0.8336 0.000 0.000 0.008 0.992
#> GSM647545 4 0.0921 0.8502 0.000 0.028 0.000 0.972
#> GSM647549 4 0.1118 0.8507 0.000 0.036 0.000 0.964
#> GSM647550 4 0.3958 0.7642 0.000 0.024 0.160 0.816
#> GSM647560 4 0.3649 0.8133 0.000 0.204 0.000 0.796
#> GSM647617 3 0.0000 0.9270 0.000 0.000 1.000 0.000
#> GSM647528 2 0.1022 0.9160 0.000 0.968 0.000 0.032
#> GSM647529 1 0.5436 0.4644 0.620 0.356 0.000 0.024
#> GSM647531 2 0.3444 0.8028 0.000 0.816 0.000 0.184
#> GSM647540 3 0.0524 0.9212 0.000 0.004 0.988 0.008
#> GSM647541 4 0.3356 0.8347 0.000 0.176 0.000 0.824
#> GSM647546 3 0.0000 0.9270 0.000 0.000 1.000 0.000
#> GSM647557 2 0.4992 0.2213 0.000 0.524 0.000 0.476
#> GSM647561 2 0.4933 0.3460 0.000 0.568 0.000 0.432
#> GSM647567 3 0.2799 0.8139 0.000 0.108 0.884 0.008
#> GSM647568 4 0.0921 0.8502 0.000 0.028 0.000 0.972
#> GSM647570 4 0.2408 0.8552 0.000 0.104 0.000 0.896
#> GSM647573 4 0.0469 0.8312 0.000 0.000 0.012 0.988
#> GSM647576 3 0.1118 0.9064 0.000 0.000 0.964 0.036
#> GSM647579 3 0.0524 0.9212 0.000 0.004 0.988 0.008
#> GSM647580 3 0.0000 0.9270 0.000 0.000 1.000 0.000
#> GSM647583 3 0.0000 0.9270 0.000 0.000 1.000 0.000
#> GSM647592 2 0.0000 0.9115 0.000 1.000 0.000 0.000
#> GSM647593 2 0.0000 0.9115 0.000 1.000 0.000 0.000
#> GSM647595 2 0.0000 0.9115 0.000 1.000 0.000 0.000
#> GSM647597 2 0.0000 0.9115 0.000 1.000 0.000 0.000
#> GSM647598 2 0.0817 0.9179 0.000 0.976 0.000 0.024
#> GSM647613 4 0.3649 0.8002 0.000 0.204 0.000 0.796
#> GSM647615 4 0.1211 0.8525 0.000 0.040 0.000 0.960
#> GSM647616 3 0.0000 0.9270 0.000 0.000 1.000 0.000
#> GSM647619 2 0.0000 0.9115 0.000 1.000 0.000 0.000
#> GSM647582 2 0.1022 0.9160 0.000 0.968 0.000 0.032
#> GSM647591 2 0.2281 0.8490 0.000 0.904 0.000 0.096
#> GSM647527 2 0.1022 0.9160 0.000 0.968 0.000 0.032
#> GSM647530 4 0.0707 0.8458 0.000 0.020 0.000 0.980
#> GSM647532 4 0.6683 0.4240 0.072 0.024 0.276 0.628
#> GSM647544 4 0.3444 0.8311 0.000 0.184 0.000 0.816
#> GSM647551 2 0.2530 0.8537 0.000 0.888 0.000 0.112
#> GSM647556 3 0.0000 0.9270 0.000 0.000 1.000 0.000
#> GSM647558 4 0.1022 0.8508 0.000 0.032 0.000 0.968
#> GSM647572 3 0.0000 0.9270 0.000 0.000 1.000 0.000
#> GSM647578 3 0.7188 0.3938 0.000 0.292 0.536 0.172
#> GSM647581 4 0.1022 0.8500 0.000 0.032 0.000 0.968
#> GSM647594 2 0.1716 0.8771 0.000 0.936 0.000 0.064
#> GSM647599 3 0.6637 0.4685 0.144 0.240 0.616 0.000
#> GSM647600 2 0.1004 0.9147 0.000 0.972 0.004 0.024
#> GSM647601 2 0.0817 0.9179 0.000 0.976 0.000 0.024
#> GSM647603 2 0.1488 0.9130 0.000 0.956 0.012 0.032
#> GSM647610 2 0.0672 0.9055 0.000 0.984 0.008 0.008
#> GSM647611 2 0.0817 0.9179 0.000 0.976 0.000 0.024
#> GSM647612 4 0.2868 0.8489 0.000 0.136 0.000 0.864
#> GSM647614 4 0.2973 0.8480 0.000 0.144 0.000 0.856
#> GSM647618 2 0.0336 0.9127 0.000 0.992 0.000 0.008
#> GSM647629 2 0.1411 0.9085 0.000 0.960 0.020 0.020
#> GSM647535 2 0.0817 0.9179 0.000 0.976 0.000 0.024
#> GSM647563 4 0.3444 0.8311 0.000 0.184 0.000 0.816
#> GSM647542 4 0.3123 0.8450 0.000 0.156 0.000 0.844
#> GSM647543 4 0.0921 0.8502 0.000 0.028 0.000 0.972
#> GSM647548 4 0.0336 0.8393 0.000 0.008 0.000 0.992
#> GSM647554 2 0.4776 0.6089 0.000 0.712 0.272 0.016
#> GSM647555 4 0.3356 0.8332 0.000 0.176 0.000 0.824
#> GSM647559 2 0.2814 0.8237 0.000 0.868 0.000 0.132
#> GSM647562 4 0.3074 0.8469 0.000 0.152 0.000 0.848
#> GSM647564 3 0.0000 0.9270 0.000 0.000 1.000 0.000
#> GSM647571 4 0.3444 0.8311 0.000 0.184 0.000 0.816
#> GSM647584 2 0.0817 0.9179 0.000 0.976 0.000 0.024
#> GSM647585 3 0.0000 0.9270 0.000 0.000 1.000 0.000
#> GSM647586 2 0.1022 0.9160 0.000 0.968 0.000 0.032
#> GSM647587 2 0.1022 0.9160 0.000 0.968 0.000 0.032
#> GSM647588 2 0.2704 0.8574 0.000 0.876 0.000 0.124
#> GSM647596 2 0.0817 0.9179 0.000 0.976 0.000 0.024
#> GSM647602 3 0.0000 0.9270 0.000 0.000 1.000 0.000
#> GSM647609 2 0.0817 0.9179 0.000 0.976 0.000 0.024
#> GSM647620 2 0.0817 0.9179 0.000 0.976 0.000 0.024
#> GSM647627 2 0.0817 0.9179 0.000 0.976 0.000 0.024
#> GSM647628 4 0.3610 0.8186 0.000 0.200 0.000 0.800
#> GSM647533 1 0.2921 0.8139 0.860 0.000 0.140 0.000
#> GSM647536 1 0.5159 0.7657 0.756 0.088 0.000 0.156
#> GSM647537 1 0.2973 0.8096 0.856 0.000 0.144 0.000
#> GSM647606 1 0.0000 0.9202 1.000 0.000 0.000 0.000
#> GSM647621 3 0.3913 0.7720 0.148 0.000 0.824 0.028
#> GSM647626 3 0.0000 0.9270 0.000 0.000 1.000 0.000
#> GSM647538 1 0.0188 0.9191 0.996 0.004 0.000 0.000
#> GSM647575 4 0.2921 0.8433 0.000 0.140 0.000 0.860
#> GSM647590 1 0.0469 0.9154 0.988 0.000 0.000 0.012
#> GSM647605 1 0.0000 0.9202 1.000 0.000 0.000 0.000
#> GSM647607 4 0.3730 0.7560 0.144 0.004 0.016 0.836
#> GSM647608 3 0.1211 0.9037 0.000 0.000 0.960 0.040
#> GSM647622 1 0.0000 0.9202 1.000 0.000 0.000 0.000
#> GSM647623 1 0.0469 0.9145 0.988 0.000 0.012 0.000
#> GSM647624 1 0.0000 0.9202 1.000 0.000 0.000 0.000
#> GSM647625 1 0.0000 0.9202 1.000 0.000 0.000 0.000
#> GSM647534 2 0.1114 0.8967 0.004 0.972 0.016 0.008
#> GSM647539 4 0.0000 0.8367 0.000 0.000 0.000 1.000
#> GSM647566 4 0.6214 0.2514 0.052 0.004 0.368 0.576
#> GSM647589 3 0.4008 0.6525 0.000 0.000 0.756 0.244
#> GSM647604 1 0.0000 0.9202 1.000 0.000 0.000 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.0162 0.871 0.000 0.000 0.996 0.004 0.000
#> GSM647574 3 0.2280 0.775 0.000 0.000 0.880 0.120 0.000
#> GSM647577 3 0.0162 0.871 0.000 0.000 0.996 0.004 0.000
#> GSM647547 4 0.4219 0.750 0.000 0.116 0.104 0.780 0.000
#> GSM647552 5 0.7902 0.148 0.000 0.220 0.248 0.100 0.432
#> GSM647553 3 0.3242 0.643 0.000 0.000 0.784 0.216 0.000
#> GSM647565 4 0.3534 0.715 0.000 0.256 0.000 0.744 0.000
#> GSM647545 2 0.1281 0.748 0.000 0.956 0.000 0.012 0.032
#> GSM647549 2 0.0162 0.740 0.000 0.996 0.000 0.000 0.004
#> GSM647550 2 0.3294 0.679 0.000 0.844 0.124 0.024 0.008
#> GSM647560 2 0.3342 0.756 0.000 0.836 0.008 0.020 0.136
#> GSM647617 3 0.0162 0.871 0.000 0.000 0.996 0.004 0.000
#> GSM647528 2 0.4150 0.572 0.000 0.612 0.000 0.000 0.388
#> GSM647529 4 0.5938 0.160 0.360 0.028 0.000 0.556 0.056
#> GSM647531 2 0.5357 0.381 0.000 0.588 0.000 0.068 0.344
#> GSM647540 3 0.3061 0.755 0.000 0.136 0.844 0.020 0.000
#> GSM647541 2 0.2919 0.752 0.000 0.868 0.004 0.024 0.104
#> GSM647546 3 0.0162 0.871 0.000 0.000 0.996 0.004 0.000
#> GSM647557 2 0.3012 0.728 0.000 0.860 0.000 0.036 0.104
#> GSM647561 2 0.3662 0.663 0.000 0.744 0.000 0.004 0.252
#> GSM647567 3 0.5710 0.589 0.000 0.120 0.668 0.020 0.192
#> GSM647568 2 0.2270 0.669 0.000 0.904 0.076 0.020 0.000
#> GSM647570 2 0.1043 0.753 0.000 0.960 0.000 0.000 0.040
#> GSM647573 4 0.3160 0.743 0.000 0.188 0.004 0.808 0.000
#> GSM647576 3 0.3675 0.708 0.000 0.188 0.788 0.024 0.000
#> GSM647579 3 0.3061 0.755 0.000 0.136 0.844 0.020 0.000
#> GSM647580 3 0.0162 0.871 0.000 0.000 0.996 0.004 0.000
#> GSM647583 3 0.0162 0.871 0.000 0.000 0.996 0.004 0.000
#> GSM647592 5 0.0000 0.804 0.000 0.000 0.000 0.000 1.000
#> GSM647593 5 0.0000 0.804 0.000 0.000 0.000 0.000 1.000
#> GSM647595 5 0.0162 0.804 0.000 0.004 0.000 0.000 0.996
#> GSM647597 5 0.1965 0.747 0.000 0.000 0.000 0.096 0.904
#> GSM647598 5 0.0880 0.801 0.000 0.032 0.000 0.000 0.968
#> GSM647613 2 0.3596 0.727 0.000 0.784 0.000 0.016 0.200
#> GSM647615 2 0.3504 0.570 0.000 0.816 0.160 0.016 0.008
#> GSM647616 3 0.0162 0.871 0.000 0.000 0.996 0.004 0.000
#> GSM647619 5 0.0000 0.804 0.000 0.000 0.000 0.000 1.000
#> GSM647582 2 0.4383 0.506 0.000 0.572 0.000 0.004 0.424
#> GSM647591 5 0.1410 0.776 0.000 0.060 0.000 0.000 0.940
#> GSM647527 2 0.4150 0.572 0.000 0.612 0.000 0.000 0.388
#> GSM647530 4 0.4060 0.393 0.000 0.360 0.000 0.640 0.000
#> GSM647532 4 0.1059 0.726 0.000 0.008 0.004 0.968 0.020
#> GSM647544 2 0.3884 0.677 0.000 0.708 0.000 0.004 0.288
#> GSM647551 5 0.1608 0.778 0.000 0.072 0.000 0.000 0.928
#> GSM647556 3 0.0162 0.869 0.000 0.000 0.996 0.004 0.000
#> GSM647558 2 0.0404 0.735 0.000 0.988 0.000 0.012 0.000
#> GSM647572 3 0.0290 0.869 0.000 0.000 0.992 0.008 0.000
#> GSM647578 3 0.7198 0.193 0.000 0.268 0.436 0.024 0.272
#> GSM647581 2 0.0000 0.737 0.000 1.000 0.000 0.000 0.000
#> GSM647594 5 0.1043 0.789 0.000 0.040 0.000 0.000 0.960
#> GSM647599 3 0.5641 0.499 0.136 0.000 0.644 0.004 0.216
#> GSM647600 5 0.0798 0.804 0.000 0.008 0.000 0.016 0.976
#> GSM647601 5 0.1608 0.782 0.000 0.072 0.000 0.000 0.928
#> GSM647603 2 0.4039 0.683 0.000 0.720 0.004 0.008 0.268
#> GSM647610 5 0.1197 0.792 0.000 0.048 0.000 0.000 0.952
#> GSM647611 5 0.3452 0.562 0.000 0.244 0.000 0.000 0.756
#> GSM647612 2 0.4058 0.703 0.000 0.816 0.092 0.020 0.072
#> GSM647614 2 0.1704 0.756 0.000 0.928 0.000 0.004 0.068
#> GSM647618 2 0.4437 0.450 0.000 0.532 0.000 0.004 0.464
#> GSM647629 5 0.3642 0.668 0.000 0.144 0.016 0.020 0.820
#> GSM647535 5 0.4242 0.199 0.000 0.428 0.000 0.000 0.572
#> GSM647563 2 0.3333 0.736 0.000 0.788 0.000 0.004 0.208
#> GSM647542 2 0.1892 0.759 0.000 0.916 0.000 0.004 0.080
#> GSM647543 2 0.0609 0.727 0.000 0.980 0.000 0.020 0.000
#> GSM647548 4 0.3305 0.736 0.000 0.224 0.000 0.776 0.000
#> GSM647554 5 0.6335 0.475 0.000 0.204 0.180 0.020 0.596
#> GSM647555 2 0.2833 0.757 0.000 0.864 0.004 0.012 0.120
#> GSM647559 2 0.4114 0.589 0.000 0.624 0.000 0.000 0.376
#> GSM647562 2 0.3550 0.709 0.000 0.760 0.000 0.004 0.236
#> GSM647564 3 0.0162 0.869 0.000 0.000 0.996 0.004 0.000
#> GSM647571 2 0.2997 0.752 0.000 0.840 0.000 0.012 0.148
#> GSM647584 5 0.0794 0.802 0.000 0.028 0.000 0.000 0.972
#> GSM647585 3 0.0000 0.870 0.000 0.000 1.000 0.000 0.000
#> GSM647586 2 0.4150 0.572 0.000 0.612 0.000 0.000 0.388
#> GSM647587 2 0.4288 0.575 0.000 0.612 0.000 0.004 0.384
#> GSM647588 2 0.4658 0.251 0.000 0.576 0.000 0.016 0.408
#> GSM647596 5 0.4101 0.195 0.000 0.372 0.000 0.000 0.628
#> GSM647602 3 0.0162 0.869 0.000 0.000 0.996 0.004 0.000
#> GSM647609 5 0.2127 0.753 0.000 0.108 0.000 0.000 0.892
#> GSM647620 5 0.3508 0.549 0.000 0.252 0.000 0.000 0.748
#> GSM647627 5 0.3508 0.549 0.000 0.252 0.000 0.000 0.748
#> GSM647628 2 0.5074 0.697 0.000 0.700 0.000 0.132 0.168
#> GSM647533 1 0.1082 0.926 0.964 0.000 0.028 0.008 0.000
#> GSM647536 4 0.2864 0.685 0.064 0.008 0.000 0.884 0.044
#> GSM647537 1 0.1106 0.928 0.964 0.000 0.024 0.012 0.000
#> GSM647606 1 0.0000 0.944 1.000 0.000 0.000 0.000 0.000
#> GSM647621 4 0.4898 0.450 0.032 0.004 0.332 0.632 0.000
#> GSM647626 3 0.0162 0.871 0.000 0.000 0.996 0.004 0.000
#> GSM647538 1 0.2773 0.830 0.836 0.000 0.000 0.164 0.000
#> GSM647575 4 0.2790 0.738 0.000 0.068 0.000 0.880 0.052
#> GSM647590 1 0.3684 0.623 0.720 0.000 0.000 0.280 0.000
#> GSM647605 1 0.0000 0.944 1.000 0.000 0.000 0.000 0.000
#> GSM647607 4 0.2104 0.733 0.044 0.024 0.008 0.924 0.000
#> GSM647608 4 0.3365 0.740 0.000 0.044 0.120 0.836 0.000
#> GSM647622 1 0.0000 0.944 1.000 0.000 0.000 0.000 0.000
#> GSM647623 1 0.0794 0.927 0.972 0.000 0.028 0.000 0.000
#> GSM647624 1 0.0000 0.944 1.000 0.000 0.000 0.000 0.000
#> GSM647625 1 0.0000 0.944 1.000 0.000 0.000 0.000 0.000
#> GSM647534 5 0.0000 0.804 0.000 0.000 0.000 0.000 1.000
#> GSM647539 4 0.2329 0.755 0.000 0.124 0.000 0.876 0.000
#> GSM647566 4 0.7183 0.106 0.028 0.200 0.368 0.404 0.000
#> GSM647589 4 0.4098 0.726 0.000 0.064 0.156 0.780 0.000
#> GSM647604 1 0.0000 0.944 1.000 0.000 0.000 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.0000 0.8239 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647574 3 0.1411 0.7893 0.000 0.000 0.936 0.060 0.000 0.004
#> GSM647577 3 0.0000 0.8239 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647547 4 0.2915 0.8017 0.000 0.008 0.024 0.848 0.000 0.120
#> GSM647552 5 0.4985 0.4801 0.000 0.016 0.048 0.028 0.696 0.212
#> GSM647553 3 0.2823 0.6301 0.000 0.000 0.796 0.204 0.000 0.000
#> GSM647565 4 0.3279 0.7678 0.000 0.028 0.000 0.796 0.000 0.176
#> GSM647545 6 0.4261 0.3576 0.000 0.408 0.000 0.000 0.020 0.572
#> GSM647549 2 0.2581 0.7232 0.000 0.860 0.000 0.000 0.020 0.120
#> GSM647550 6 0.2358 0.6207 0.000 0.016 0.108 0.000 0.000 0.876
#> GSM647560 6 0.2838 0.6615 0.000 0.188 0.004 0.000 0.000 0.808
#> GSM647617 3 0.0000 0.8239 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647528 2 0.0713 0.8032 0.000 0.972 0.000 0.000 0.028 0.000
#> GSM647529 4 0.6598 0.1810 0.304 0.008 0.000 0.432 0.236 0.020
#> GSM647531 2 0.5778 0.2318 0.000 0.508 0.000 0.020 0.360 0.112
#> GSM647540 6 0.2854 0.5233 0.000 0.000 0.208 0.000 0.000 0.792
#> GSM647541 6 0.2147 0.6734 0.000 0.084 0.000 0.000 0.020 0.896
#> GSM647546 3 0.0146 0.8220 0.000 0.000 0.996 0.000 0.000 0.004
#> GSM647557 2 0.3123 0.7402 0.000 0.832 0.000 0.000 0.056 0.112
#> GSM647561 2 0.2651 0.7578 0.000 0.860 0.000 0.000 0.028 0.112
#> GSM647567 3 0.5313 0.3261 0.000 0.000 0.508 0.000 0.108 0.384
#> GSM647568 6 0.3672 0.5203 0.000 0.304 0.008 0.000 0.000 0.688
#> GSM647570 2 0.2048 0.7404 0.000 0.880 0.000 0.000 0.000 0.120
#> GSM647573 4 0.2949 0.7984 0.000 0.028 0.000 0.848 0.008 0.116
#> GSM647576 6 0.3789 0.3028 0.000 0.000 0.416 0.000 0.000 0.584
#> GSM647579 6 0.2941 0.5082 0.000 0.000 0.220 0.000 0.000 0.780
#> GSM647580 3 0.0000 0.8239 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647583 3 0.0000 0.8239 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647592 5 0.2260 0.8378 0.000 0.140 0.000 0.000 0.860 0.000
#> GSM647593 5 0.2048 0.8449 0.000 0.120 0.000 0.000 0.880 0.000
#> GSM647595 5 0.2053 0.8454 0.000 0.108 0.000 0.000 0.888 0.004
#> GSM647597 5 0.1921 0.7985 0.000 0.056 0.000 0.012 0.920 0.012
#> GSM647598 5 0.3023 0.7683 0.000 0.232 0.000 0.000 0.768 0.000
#> GSM647613 6 0.5034 0.1866 0.000 0.460 0.000 0.000 0.072 0.468
#> GSM647615 6 0.1701 0.6645 0.000 0.072 0.008 0.000 0.000 0.920
#> GSM647616 3 0.0000 0.8239 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647619 5 0.1957 0.8453 0.000 0.112 0.000 0.000 0.888 0.000
#> GSM647582 2 0.3456 0.6715 0.000 0.788 0.000 0.000 0.172 0.040
#> GSM647591 5 0.2390 0.8171 0.000 0.056 0.000 0.000 0.888 0.056
#> GSM647527 2 0.0713 0.8032 0.000 0.972 0.000 0.000 0.028 0.000
#> GSM647530 4 0.5680 0.5009 0.000 0.268 0.000 0.600 0.072 0.060
#> GSM647532 4 0.2122 0.7769 0.000 0.000 0.000 0.900 0.076 0.024
#> GSM647544 2 0.0000 0.8013 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647551 5 0.2568 0.8231 0.000 0.068 0.000 0.000 0.876 0.056
#> GSM647556 3 0.3288 0.6638 0.000 0.000 0.724 0.000 0.000 0.276
#> GSM647558 6 0.3695 0.4324 0.000 0.376 0.000 0.000 0.000 0.624
#> GSM647572 3 0.3405 0.6676 0.000 0.000 0.724 0.004 0.000 0.272
#> GSM647578 6 0.3031 0.6232 0.000 0.044 0.108 0.000 0.004 0.844
#> GSM647581 2 0.2618 0.7242 0.000 0.860 0.000 0.000 0.024 0.116
#> GSM647594 5 0.2365 0.8305 0.000 0.072 0.000 0.000 0.888 0.040
#> GSM647599 3 0.6372 0.2877 0.104 0.140 0.572 0.000 0.184 0.000
#> GSM647600 5 0.3883 0.7923 0.000 0.144 0.000 0.000 0.768 0.088
#> GSM647601 5 0.3409 0.6862 0.000 0.300 0.000 0.000 0.700 0.000
#> GSM647603 2 0.3748 0.4323 0.000 0.688 0.000 0.000 0.012 0.300
#> GSM647610 5 0.5480 0.3963 0.000 0.144 0.000 0.000 0.528 0.328
#> GSM647611 2 0.3737 0.2472 0.000 0.608 0.000 0.000 0.392 0.000
#> GSM647612 6 0.2668 0.6758 0.000 0.168 0.004 0.000 0.000 0.828
#> GSM647614 2 0.1957 0.7483 0.000 0.888 0.000 0.000 0.000 0.112
#> GSM647618 2 0.3592 0.4371 0.000 0.656 0.000 0.000 0.344 0.000
#> GSM647629 6 0.5704 -0.0711 0.000 0.140 0.004 0.000 0.400 0.456
#> GSM647535 2 0.1610 0.7737 0.000 0.916 0.000 0.000 0.084 0.000
#> GSM647563 2 0.0000 0.8013 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647542 2 0.1765 0.7620 0.000 0.904 0.000 0.000 0.000 0.096
#> GSM647543 6 0.3464 0.5112 0.000 0.312 0.000 0.000 0.000 0.688
#> GSM647548 4 0.2843 0.7962 0.000 0.036 0.000 0.848 0.000 0.116
#> GSM647554 6 0.3801 0.5909 0.000 0.012 0.132 0.000 0.064 0.792
#> GSM647555 2 0.3747 0.2472 0.000 0.604 0.000 0.000 0.000 0.396
#> GSM647559 2 0.0713 0.8037 0.000 0.972 0.000 0.000 0.028 0.000
#> GSM647562 2 0.1204 0.7744 0.000 0.944 0.000 0.000 0.000 0.056
#> GSM647564 3 0.3076 0.6977 0.000 0.000 0.760 0.000 0.000 0.240
#> GSM647571 2 0.0000 0.8013 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647584 5 0.2854 0.7934 0.000 0.208 0.000 0.000 0.792 0.000
#> GSM647585 3 0.2340 0.7639 0.000 0.000 0.852 0.000 0.000 0.148
#> GSM647586 2 0.0713 0.8032 0.000 0.972 0.000 0.000 0.028 0.000
#> GSM647587 2 0.0713 0.8032 0.000 0.972 0.000 0.000 0.028 0.000
#> GSM647588 6 0.4305 0.6020 0.000 0.216 0.000 0.000 0.076 0.708
#> GSM647596 2 0.3050 0.6149 0.000 0.764 0.000 0.000 0.236 0.000
#> GSM647602 3 0.3244 0.6704 0.000 0.000 0.732 0.000 0.000 0.268
#> GSM647609 5 0.3810 0.3988 0.000 0.428 0.000 0.000 0.572 0.000
#> GSM647620 2 0.3076 0.6099 0.000 0.760 0.000 0.000 0.240 0.000
#> GSM647627 2 0.3076 0.6099 0.000 0.760 0.000 0.000 0.240 0.000
#> GSM647628 2 0.0547 0.8028 0.000 0.980 0.000 0.000 0.020 0.000
#> GSM647533 1 0.2143 0.9148 0.916 0.000 0.008 0.012 0.048 0.016
#> GSM647536 4 0.3679 0.7056 0.012 0.000 0.000 0.772 0.192 0.024
#> GSM647537 1 0.2143 0.9148 0.916 0.000 0.008 0.012 0.048 0.016
#> GSM647606 1 0.0000 0.9431 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647621 4 0.5497 0.1431 0.036 0.000 0.436 0.488 0.028 0.012
#> GSM647626 3 0.0000 0.8239 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647538 1 0.4066 0.8311 0.788 0.000 0.000 0.064 0.112 0.036
#> GSM647575 4 0.1285 0.7930 0.000 0.052 0.000 0.944 0.000 0.004
#> GSM647590 1 0.4072 0.7483 0.772 0.000 0.000 0.148 0.060 0.020
#> GSM647605 1 0.0000 0.9431 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647607 4 0.1387 0.7717 0.068 0.000 0.000 0.932 0.000 0.000
#> GSM647608 4 0.1845 0.8024 0.000 0.000 0.028 0.920 0.000 0.052
#> GSM647622 1 0.0000 0.9431 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647623 1 0.0937 0.9184 0.960 0.000 0.040 0.000 0.000 0.000
#> GSM647624 1 0.0000 0.9431 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647625 1 0.0000 0.9431 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647534 5 0.1957 0.8457 0.000 0.112 0.000 0.000 0.888 0.000
#> GSM647539 4 0.2355 0.8046 0.000 0.008 0.000 0.876 0.004 0.112
#> GSM647566 6 0.4256 0.4181 0.004 0.008 0.012 0.276 0.008 0.692
#> GSM647589 4 0.1829 0.8028 0.000 0.000 0.024 0.920 0.000 0.056
#> GSM647604 1 0.0000 0.9431 1.000 0.000 0.000 0.000 0.000 0.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n disease.state(p) development.stage(p) other(p) k
#> CV:pam 94 1.31e-05 0.02371 1.000 2
#> CV:pam 76 1.00e+00 0.00107 0.503 3
#> CV:pam 95 1.54e-11 0.03690 0.332 4
#> CV:pam 90 9.77e-13 0.01650 0.136 5
#> CV:pam 85 5.01e-11 0.00338 0.226 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["CV", "mclust"]
# you can also extract it by
# res = res_list["CV:mclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'CV' method.
#> Subgroups are detected by 'mclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 3.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.689 0.826 0.911 0.4638 0.497 0.497
#> 3 3 0.968 0.949 0.981 0.2232 0.872 0.757
#> 4 4 0.624 0.603 0.789 0.2008 0.916 0.806
#> 5 5 0.612 0.589 0.793 0.0759 0.818 0.557
#> 6 6 0.692 0.503 0.709 0.0887 0.808 0.423
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 3
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM647569 1 0.9922 0.484 0.552 0.448
#> GSM647574 1 0.9922 0.485 0.552 0.448
#> GSM647577 1 0.9963 0.453 0.536 0.464
#> GSM647547 1 0.1414 0.798 0.980 0.020
#> GSM647552 1 0.9954 0.461 0.540 0.460
#> GSM647553 1 0.9087 0.635 0.676 0.324
#> GSM647565 1 0.8555 0.672 0.720 0.280
#> GSM647545 2 0.0000 0.982 0.000 1.000
#> GSM647549 2 0.0000 0.982 0.000 1.000
#> GSM647550 2 0.0000 0.982 0.000 1.000
#> GSM647560 2 0.0000 0.982 0.000 1.000
#> GSM647617 1 0.9970 0.443 0.532 0.468
#> GSM647528 2 0.0000 0.982 0.000 1.000
#> GSM647529 1 0.0000 0.803 1.000 0.000
#> GSM647531 2 0.0000 0.982 0.000 1.000
#> GSM647540 2 0.0000 0.982 0.000 1.000
#> GSM647541 2 0.0000 0.982 0.000 1.000
#> GSM647546 1 0.9970 0.443 0.532 0.468
#> GSM647557 2 0.0000 0.982 0.000 1.000
#> GSM647561 2 0.0000 0.982 0.000 1.000
#> GSM647567 1 0.9286 0.617 0.656 0.344
#> GSM647568 2 0.0000 0.982 0.000 1.000
#> GSM647570 2 0.0000 0.982 0.000 1.000
#> GSM647573 1 0.0000 0.803 1.000 0.000
#> GSM647576 2 0.2603 0.925 0.044 0.956
#> GSM647579 2 0.9983 -0.307 0.476 0.524
#> GSM647580 1 0.9896 0.498 0.560 0.440
#> GSM647583 1 0.9963 0.453 0.536 0.464
#> GSM647592 2 0.8081 0.576 0.248 0.752
#> GSM647593 2 0.0000 0.982 0.000 1.000
#> GSM647595 2 0.0000 0.982 0.000 1.000
#> GSM647597 1 0.0672 0.801 0.992 0.008
#> GSM647598 2 0.0000 0.982 0.000 1.000
#> GSM647613 2 0.0000 0.982 0.000 1.000
#> GSM647615 2 0.0000 0.982 0.000 1.000
#> GSM647616 1 0.9944 0.469 0.544 0.456
#> GSM647619 2 0.0000 0.982 0.000 1.000
#> GSM647582 2 0.0000 0.982 0.000 1.000
#> GSM647591 2 0.0000 0.982 0.000 1.000
#> GSM647527 2 0.0000 0.982 0.000 1.000
#> GSM647530 1 0.0000 0.803 1.000 0.000
#> GSM647532 1 0.0000 0.803 1.000 0.000
#> GSM647544 2 0.0000 0.982 0.000 1.000
#> GSM647551 2 0.0000 0.982 0.000 1.000
#> GSM647556 1 0.9833 0.523 0.576 0.424
#> GSM647558 2 0.0000 0.982 0.000 1.000
#> GSM647572 1 0.9933 0.477 0.548 0.452
#> GSM647578 2 0.0000 0.982 0.000 1.000
#> GSM647581 2 0.0000 0.982 0.000 1.000
#> GSM647594 1 0.7883 0.701 0.764 0.236
#> GSM647599 1 0.0000 0.803 1.000 0.000
#> GSM647600 2 0.0000 0.982 0.000 1.000
#> GSM647601 2 0.0000 0.982 0.000 1.000
#> GSM647603 2 0.0000 0.982 0.000 1.000
#> GSM647610 1 0.9850 0.491 0.572 0.428
#> GSM647611 2 0.0000 0.982 0.000 1.000
#> GSM647612 2 0.0000 0.982 0.000 1.000
#> GSM647614 2 0.0000 0.982 0.000 1.000
#> GSM647618 2 0.0000 0.982 0.000 1.000
#> GSM647629 2 0.0000 0.982 0.000 1.000
#> GSM647535 2 0.0000 0.982 0.000 1.000
#> GSM647563 2 0.0000 0.982 0.000 1.000
#> GSM647542 2 0.0000 0.982 0.000 1.000
#> GSM647543 2 0.0000 0.982 0.000 1.000
#> GSM647548 1 0.0000 0.803 1.000 0.000
#> GSM647554 2 0.0000 0.982 0.000 1.000
#> GSM647555 2 0.0000 0.982 0.000 1.000
#> GSM647559 2 0.0000 0.982 0.000 1.000
#> GSM647562 2 0.0000 0.982 0.000 1.000
#> GSM647564 1 0.9963 0.453 0.536 0.464
#> GSM647571 2 0.0000 0.982 0.000 1.000
#> GSM647584 2 0.0000 0.982 0.000 1.000
#> GSM647585 1 0.9754 0.544 0.592 0.408
#> GSM647586 2 0.0000 0.982 0.000 1.000
#> GSM647587 2 0.0000 0.982 0.000 1.000
#> GSM647588 2 0.0000 0.982 0.000 1.000
#> GSM647596 2 0.0000 0.982 0.000 1.000
#> GSM647602 1 0.9833 0.523 0.576 0.424
#> GSM647609 2 0.0000 0.982 0.000 1.000
#> GSM647620 2 0.0000 0.982 0.000 1.000
#> GSM647627 2 0.0000 0.982 0.000 1.000
#> GSM647628 2 0.0000 0.982 0.000 1.000
#> GSM647533 1 0.0000 0.803 1.000 0.000
#> GSM647536 1 0.0000 0.803 1.000 0.000
#> GSM647537 1 0.0000 0.803 1.000 0.000
#> GSM647606 1 0.0000 0.803 1.000 0.000
#> GSM647621 1 0.0000 0.803 1.000 0.000
#> GSM647626 1 0.9129 0.631 0.672 0.328
#> GSM647538 1 0.0000 0.803 1.000 0.000
#> GSM647575 1 0.0000 0.803 1.000 0.000
#> GSM647590 1 0.0000 0.803 1.000 0.000
#> GSM647605 1 0.0000 0.803 1.000 0.000
#> GSM647607 1 0.0000 0.803 1.000 0.000
#> GSM647608 1 0.0000 0.803 1.000 0.000
#> GSM647622 1 0.0000 0.803 1.000 0.000
#> GSM647623 1 0.0000 0.803 1.000 0.000
#> GSM647624 1 0.0000 0.803 1.000 0.000
#> GSM647625 1 0.0000 0.803 1.000 0.000
#> GSM647534 1 0.6438 0.740 0.836 0.164
#> GSM647539 1 0.0000 0.803 1.000 0.000
#> GSM647566 1 0.0000 0.803 1.000 0.000
#> GSM647589 1 0.0000 0.803 1.000 0.000
#> GSM647604 1 0.0000 0.803 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 3 0.0000 0.954 0.000 0.000 1.000
#> GSM647574 1 0.4555 0.730 0.800 0.000 0.200
#> GSM647577 3 0.0000 0.954 0.000 0.000 1.000
#> GSM647547 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647552 2 0.4291 0.763 0.180 0.820 0.000
#> GSM647553 1 0.1860 0.918 0.948 0.000 0.052
#> GSM647565 1 0.0747 0.949 0.984 0.016 0.000
#> GSM647545 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647549 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647550 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647560 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647617 3 0.0000 0.954 0.000 0.000 1.000
#> GSM647528 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647529 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647531 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647540 2 0.0237 0.981 0.000 0.996 0.004
#> GSM647541 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647546 3 0.5948 0.421 0.000 0.360 0.640
#> GSM647557 2 0.0237 0.980 0.004 0.996 0.000
#> GSM647561 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647567 1 0.6126 0.409 0.644 0.352 0.004
#> GSM647568 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647570 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647573 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647576 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647579 2 0.0237 0.981 0.000 0.996 0.004
#> GSM647580 3 0.0000 0.954 0.000 0.000 1.000
#> GSM647583 3 0.0000 0.954 0.000 0.000 1.000
#> GSM647592 2 0.4555 0.735 0.200 0.800 0.000
#> GSM647593 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647595 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647597 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647598 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647613 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647615 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647616 3 0.0000 0.954 0.000 0.000 1.000
#> GSM647619 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647582 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647591 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647527 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647530 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647532 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647544 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647551 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647556 3 0.0000 0.954 0.000 0.000 1.000
#> GSM647558 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647572 2 0.5696 0.759 0.064 0.800 0.136
#> GSM647578 2 0.0237 0.981 0.000 0.996 0.004
#> GSM647581 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647594 1 0.4605 0.668 0.796 0.204 0.000
#> GSM647599 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647600 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647601 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647603 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647610 2 0.4555 0.735 0.200 0.800 0.000
#> GSM647611 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647612 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647614 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647618 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647629 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647535 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647563 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647542 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647543 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647548 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647554 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647555 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647559 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647562 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647564 3 0.0000 0.954 0.000 0.000 1.000
#> GSM647571 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647584 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647585 3 0.0000 0.954 0.000 0.000 1.000
#> GSM647586 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647587 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647588 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647596 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647602 3 0.0000 0.954 0.000 0.000 1.000
#> GSM647609 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647620 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647627 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647628 2 0.0000 0.984 0.000 1.000 0.000
#> GSM647533 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647536 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647537 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647606 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647621 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647626 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647538 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647575 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647590 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647605 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647607 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647608 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647622 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647623 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647624 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647625 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647534 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647539 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647566 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647589 1 0.0000 0.967 1.000 0.000 0.000
#> GSM647604 1 0.0000 0.967 1.000 0.000 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 3 0.0000 0.94559 0.000 0.000 1.000 0.000
#> GSM647574 1 0.4697 0.53716 0.644 0.000 0.356 0.000
#> GSM647577 3 0.0000 0.94559 0.000 0.000 1.000 0.000
#> GSM647547 1 0.0188 0.86571 0.996 0.000 0.004 0.000
#> GSM647552 2 0.8649 -0.25563 0.092 0.436 0.116 0.356
#> GSM647553 1 0.4134 0.69839 0.740 0.000 0.260 0.000
#> GSM647565 1 0.2466 0.79039 0.900 0.096 0.000 0.004
#> GSM647545 2 0.0188 0.59971 0.000 0.996 0.004 0.000
#> GSM647549 2 0.0592 0.60172 0.000 0.984 0.016 0.000
#> GSM647550 2 0.5269 0.29614 0.000 0.620 0.016 0.364
#> GSM647560 2 0.5269 0.29614 0.000 0.620 0.016 0.364
#> GSM647617 3 0.0000 0.94559 0.000 0.000 1.000 0.000
#> GSM647528 2 0.2081 0.52855 0.000 0.916 0.000 0.084
#> GSM647529 1 0.0779 0.86396 0.980 0.016 0.000 0.004
#> GSM647531 2 0.0000 0.59805 0.000 1.000 0.000 0.000
#> GSM647540 2 0.7042 0.05004 0.000 0.516 0.132 0.352
#> GSM647541 2 0.5269 0.29614 0.000 0.620 0.016 0.364
#> GSM647546 3 0.8727 0.10772 0.172 0.072 0.460 0.296
#> GSM647557 2 0.0524 0.59935 0.004 0.988 0.000 0.008
#> GSM647561 2 0.0469 0.59359 0.000 0.988 0.000 0.012
#> GSM647567 1 0.5862 0.75709 0.748 0.068 0.140 0.044
#> GSM647568 2 0.4054 0.51798 0.000 0.796 0.016 0.188
#> GSM647570 2 0.0000 0.59805 0.000 1.000 0.000 0.000
#> GSM647573 1 0.0000 0.86592 1.000 0.000 0.000 0.000
#> GSM647576 2 0.5269 0.29614 0.000 0.620 0.016 0.364
#> GSM647579 2 0.7318 -0.00901 0.000 0.476 0.160 0.364
#> GSM647580 3 0.0000 0.94559 0.000 0.000 1.000 0.000
#> GSM647583 3 0.0000 0.94559 0.000 0.000 1.000 0.000
#> GSM647592 4 0.7539 0.45676 0.252 0.256 0.000 0.492
#> GSM647593 4 0.4679 0.75297 0.000 0.352 0.000 0.648
#> GSM647595 4 0.4679 0.75297 0.000 0.352 0.000 0.648
#> GSM647597 1 0.2111 0.86067 0.932 0.024 0.000 0.044
#> GSM647598 2 0.4643 -0.02957 0.000 0.656 0.000 0.344
#> GSM647613 2 0.1118 0.57775 0.000 0.964 0.000 0.036
#> GSM647615 2 0.4980 0.35331 0.000 0.680 0.016 0.304
#> GSM647616 3 0.0000 0.94559 0.000 0.000 1.000 0.000
#> GSM647619 4 0.4679 0.75297 0.000 0.352 0.000 0.648
#> GSM647582 2 0.4730 0.17626 0.000 0.636 0.000 0.364
#> GSM647591 4 0.4679 0.75297 0.000 0.352 0.000 0.648
#> GSM647527 2 0.2345 0.51058 0.000 0.900 0.000 0.100
#> GSM647530 1 0.0592 0.86340 0.984 0.016 0.000 0.000
#> GSM647532 1 0.0000 0.86592 1.000 0.000 0.000 0.000
#> GSM647544 2 0.0592 0.59217 0.000 0.984 0.000 0.016
#> GSM647551 4 0.4866 0.69575 0.000 0.404 0.000 0.596
#> GSM647556 3 0.0000 0.94559 0.000 0.000 1.000 0.000
#> GSM647558 2 0.0592 0.60172 0.000 0.984 0.016 0.000
#> GSM647572 2 0.8060 -0.19869 0.004 0.368 0.312 0.316
#> GSM647578 2 0.6909 0.07335 0.000 0.520 0.116 0.364
#> GSM647581 2 0.0592 0.59217 0.000 0.984 0.000 0.016
#> GSM647594 1 0.3910 0.75271 0.820 0.156 0.000 0.024
#> GSM647599 1 0.3996 0.83158 0.836 0.000 0.104 0.060
#> GSM647600 2 0.5253 0.26079 0.000 0.624 0.016 0.360
#> GSM647601 2 0.4961 -0.29815 0.000 0.552 0.000 0.448
#> GSM647603 2 0.5269 0.29614 0.000 0.620 0.016 0.364
#> GSM647610 4 0.7812 0.33256 0.256 0.348 0.000 0.396
#> GSM647611 2 0.4713 -0.07012 0.000 0.640 0.000 0.360
#> GSM647612 2 0.2730 0.58025 0.000 0.896 0.016 0.088
#> GSM647614 2 0.1975 0.58888 0.000 0.936 0.016 0.048
#> GSM647618 2 0.1940 0.54600 0.000 0.924 0.000 0.076
#> GSM647629 2 0.5269 0.29614 0.000 0.620 0.016 0.364
#> GSM647535 2 0.5186 0.32869 0.000 0.640 0.016 0.344
#> GSM647563 2 0.0592 0.60172 0.000 0.984 0.016 0.000
#> GSM647542 2 0.4136 0.51192 0.000 0.788 0.016 0.196
#> GSM647543 2 0.4831 0.42090 0.000 0.704 0.016 0.280
#> GSM647548 1 0.0000 0.86592 1.000 0.000 0.000 0.000
#> GSM647554 2 0.5269 0.29614 0.000 0.620 0.016 0.364
#> GSM647555 2 0.4857 0.42059 0.000 0.700 0.016 0.284
#> GSM647559 2 0.0927 0.60225 0.000 0.976 0.016 0.008
#> GSM647562 2 0.0927 0.58720 0.008 0.976 0.000 0.016
#> GSM647564 3 0.0188 0.94274 0.000 0.000 0.996 0.004
#> GSM647571 2 0.4136 0.51192 0.000 0.788 0.016 0.196
#> GSM647584 4 0.4916 0.65810 0.000 0.424 0.000 0.576
#> GSM647585 3 0.0188 0.94258 0.004 0.000 0.996 0.000
#> GSM647586 2 0.2589 0.48912 0.000 0.884 0.000 0.116
#> GSM647587 2 0.2530 0.49492 0.000 0.888 0.000 0.112
#> GSM647588 2 0.3280 0.56738 0.000 0.860 0.016 0.124
#> GSM647596 2 0.1488 0.58946 0.000 0.956 0.012 0.032
#> GSM647602 3 0.0000 0.94559 0.000 0.000 1.000 0.000
#> GSM647609 4 0.4916 0.67870 0.000 0.424 0.000 0.576
#> GSM647620 2 0.4957 0.26480 0.000 0.684 0.016 0.300
#> GSM647627 2 0.3649 0.37440 0.000 0.796 0.000 0.204
#> GSM647628 2 0.0592 0.60172 0.000 0.984 0.016 0.000
#> GSM647533 1 0.4331 0.81411 0.712 0.000 0.000 0.288
#> GSM647536 1 0.0000 0.86592 1.000 0.000 0.000 0.000
#> GSM647537 1 0.4331 0.81411 0.712 0.000 0.000 0.288
#> GSM647606 1 0.4331 0.81411 0.712 0.000 0.000 0.288
#> GSM647621 1 0.0707 0.86655 0.980 0.000 0.000 0.020
#> GSM647626 1 0.3494 0.79927 0.824 0.000 0.172 0.004
#> GSM647538 1 0.4331 0.81411 0.712 0.000 0.000 0.288
#> GSM647575 1 0.0000 0.86592 1.000 0.000 0.000 0.000
#> GSM647590 1 0.3486 0.83880 0.812 0.000 0.000 0.188
#> GSM647605 1 0.4331 0.81411 0.712 0.000 0.000 0.288
#> GSM647607 1 0.0000 0.86592 1.000 0.000 0.000 0.000
#> GSM647608 1 0.0000 0.86592 1.000 0.000 0.000 0.000
#> GSM647622 1 0.4331 0.81411 0.712 0.000 0.000 0.288
#> GSM647623 1 0.4331 0.81411 0.712 0.000 0.000 0.288
#> GSM647624 1 0.4040 0.82116 0.752 0.000 0.000 0.248
#> GSM647625 1 0.4331 0.81411 0.712 0.000 0.000 0.288
#> GSM647534 1 0.4623 0.82105 0.812 0.012 0.116 0.060
#> GSM647539 1 0.0000 0.86592 1.000 0.000 0.000 0.000
#> GSM647566 1 0.0000 0.86592 1.000 0.000 0.000 0.000
#> GSM647589 1 0.0000 0.86592 1.000 0.000 0.000 0.000
#> GSM647604 1 0.4331 0.81411 0.712 0.000 0.000 0.288
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.0000 0.7940 0.000 0.000 1.000 0.000 0.000
#> GSM647574 3 0.5104 0.5176 0.116 0.000 0.692 0.192 0.000
#> GSM647577 3 0.0000 0.7940 0.000 0.000 1.000 0.000 0.000
#> GSM647547 4 0.2377 0.9443 0.128 0.000 0.000 0.872 0.000
#> GSM647552 5 0.4458 0.3655 0.000 0.192 0.056 0.004 0.748
#> GSM647553 3 0.5525 0.4138 0.124 0.000 0.636 0.240 0.000
#> GSM647565 4 0.5324 0.5855 0.128 0.204 0.000 0.668 0.000
#> GSM647545 2 0.0000 0.7094 0.000 1.000 0.000 0.000 0.000
#> GSM647549 2 0.0162 0.7096 0.000 0.996 0.000 0.000 0.004
#> GSM647550 2 0.3563 0.6819 0.000 0.780 0.012 0.000 0.208
#> GSM647560 2 0.4088 0.5234 0.000 0.632 0.000 0.000 0.368
#> GSM647617 3 0.0000 0.7940 0.000 0.000 1.000 0.000 0.000
#> GSM647528 2 0.2771 0.6865 0.000 0.860 0.000 0.128 0.012
#> GSM647529 4 0.4890 0.5837 0.332 0.000 0.000 0.628 0.040
#> GSM647531 2 0.0794 0.7102 0.000 0.972 0.000 0.000 0.028
#> GSM647540 3 0.6593 0.1003 0.000 0.220 0.440 0.000 0.340
#> GSM647541 2 0.3274 0.6802 0.000 0.780 0.000 0.000 0.220
#> GSM647546 3 0.3048 0.7115 0.000 0.000 0.820 0.004 0.176
#> GSM647557 2 0.1205 0.7071 0.000 0.956 0.000 0.004 0.040
#> GSM647561 2 0.0290 0.7079 0.000 0.992 0.000 0.000 0.008
#> GSM647567 5 0.8322 -0.0887 0.104 0.008 0.288 0.232 0.368
#> GSM647568 2 0.3074 0.6894 0.000 0.804 0.000 0.000 0.196
#> GSM647570 2 0.0162 0.7096 0.000 0.996 0.000 0.000 0.004
#> GSM647573 4 0.2377 0.9443 0.128 0.000 0.000 0.872 0.000
#> GSM647576 2 0.5480 0.4332 0.000 0.560 0.072 0.000 0.368
#> GSM647579 3 0.6539 0.1202 0.000 0.200 0.432 0.000 0.368
#> GSM647580 3 0.0000 0.7940 0.000 0.000 1.000 0.000 0.000
#> GSM647583 3 0.0000 0.7940 0.000 0.000 1.000 0.000 0.000
#> GSM647592 5 0.6886 0.1772 0.020 0.344 0.000 0.176 0.460
#> GSM647593 2 0.6132 -0.0271 0.000 0.444 0.000 0.128 0.428
#> GSM647595 2 0.6130 -0.0186 0.000 0.448 0.000 0.128 0.424
#> GSM647597 5 0.5810 0.0800 0.152 0.000 0.000 0.244 0.604
#> GSM647598 2 0.6088 0.0589 0.000 0.492 0.000 0.128 0.380
#> GSM647613 2 0.0404 0.7071 0.000 0.988 0.000 0.000 0.012
#> GSM647615 2 0.3949 0.5552 0.000 0.668 0.000 0.000 0.332
#> GSM647616 3 0.0000 0.7940 0.000 0.000 1.000 0.000 0.000
#> GSM647619 5 0.6133 -0.0722 0.000 0.436 0.000 0.128 0.436
#> GSM647582 2 0.3731 0.6948 0.000 0.800 0.000 0.040 0.160
#> GSM647591 2 0.6130 -0.0186 0.000 0.448 0.000 0.128 0.424
#> GSM647527 2 0.2771 0.6865 0.000 0.860 0.000 0.128 0.012
#> GSM647530 4 0.2377 0.9443 0.128 0.000 0.000 0.872 0.000
#> GSM647532 4 0.2377 0.9443 0.128 0.000 0.000 0.872 0.000
#> GSM647544 2 0.0290 0.7079 0.000 0.992 0.000 0.000 0.008
#> GSM647551 5 0.5519 0.1675 0.000 0.332 0.000 0.084 0.584
#> GSM647556 3 0.0000 0.7940 0.000 0.000 1.000 0.000 0.000
#> GSM647558 2 0.0162 0.7096 0.000 0.996 0.000 0.000 0.004
#> GSM647572 3 0.3895 0.5823 0.000 0.000 0.680 0.000 0.320
#> GSM647578 2 0.6157 0.3221 0.000 0.496 0.140 0.000 0.364
#> GSM647581 2 0.0579 0.7074 0.000 0.984 0.000 0.008 0.008
#> GSM647594 5 0.6315 0.1462 0.148 0.028 0.000 0.216 0.608
#> GSM647599 1 0.6666 0.2900 0.520 0.000 0.012 0.232 0.236
#> GSM647600 5 0.4161 -0.0111 0.000 0.392 0.000 0.000 0.608
#> GSM647601 2 0.6118 0.0208 0.000 0.468 0.000 0.128 0.404
#> GSM647603 2 0.4415 0.4994 0.000 0.604 0.008 0.000 0.388
#> GSM647610 5 0.5087 0.3369 0.024 0.216 0.000 0.052 0.708
#> GSM647611 2 0.6066 0.1053 0.000 0.504 0.000 0.128 0.368
#> GSM647612 2 0.2929 0.6943 0.000 0.820 0.000 0.000 0.180
#> GSM647614 2 0.2891 0.6949 0.000 0.824 0.000 0.000 0.176
#> GSM647618 2 0.4845 0.5509 0.000 0.724 0.000 0.128 0.148
#> GSM647629 2 0.4302 0.3728 0.000 0.520 0.000 0.000 0.480
#> GSM647535 2 0.3143 0.6883 0.000 0.796 0.000 0.000 0.204
#> GSM647563 2 0.0000 0.7094 0.000 1.000 0.000 0.000 0.000
#> GSM647542 2 0.2929 0.6943 0.000 0.820 0.000 0.000 0.180
#> GSM647543 2 0.3177 0.6862 0.000 0.792 0.000 0.000 0.208
#> GSM647548 4 0.2660 0.9352 0.128 0.008 0.000 0.864 0.000
#> GSM647554 2 0.5587 0.3443 0.000 0.500 0.072 0.000 0.428
#> GSM647555 2 0.3003 0.6941 0.000 0.812 0.000 0.000 0.188
#> GSM647559 2 0.0579 0.7123 0.000 0.984 0.000 0.008 0.008
#> GSM647562 2 0.0451 0.7068 0.000 0.988 0.000 0.004 0.008
#> GSM647564 3 0.2605 0.7311 0.000 0.000 0.852 0.000 0.148
#> GSM647571 2 0.3039 0.6907 0.000 0.808 0.000 0.000 0.192
#> GSM647584 2 0.6031 0.1581 0.000 0.520 0.000 0.128 0.352
#> GSM647585 3 0.0000 0.7940 0.000 0.000 1.000 0.000 0.000
#> GSM647586 2 0.2873 0.6842 0.000 0.856 0.000 0.128 0.016
#> GSM647587 2 0.2969 0.6820 0.000 0.852 0.000 0.128 0.020
#> GSM647588 2 0.3003 0.6942 0.000 0.812 0.000 0.000 0.188
#> GSM647596 2 0.1628 0.6933 0.000 0.936 0.000 0.008 0.056
#> GSM647602 3 0.0000 0.7940 0.000 0.000 1.000 0.000 0.000
#> GSM647609 2 0.6100 0.0652 0.000 0.484 0.000 0.128 0.388
#> GSM647620 2 0.4255 0.6327 0.000 0.776 0.000 0.128 0.096
#> GSM647627 2 0.5201 0.4890 0.000 0.684 0.000 0.128 0.188
#> GSM647628 2 0.0162 0.7096 0.000 0.996 0.000 0.000 0.004
#> GSM647533 1 0.0000 0.8726 1.000 0.000 0.000 0.000 0.000
#> GSM647536 4 0.2471 0.9381 0.136 0.000 0.000 0.864 0.000
#> GSM647537 1 0.0000 0.8726 1.000 0.000 0.000 0.000 0.000
#> GSM647606 1 0.0000 0.8726 1.000 0.000 0.000 0.000 0.000
#> GSM647621 4 0.2813 0.9034 0.168 0.000 0.000 0.832 0.000
#> GSM647626 3 0.5211 0.4974 0.100 0.000 0.668 0.232 0.000
#> GSM647538 1 0.1197 0.8428 0.952 0.000 0.000 0.048 0.000
#> GSM647575 4 0.2377 0.9443 0.128 0.000 0.000 0.872 0.000
#> GSM647590 1 0.4307 -0.1721 0.504 0.000 0.000 0.496 0.000
#> GSM647605 1 0.0404 0.8692 0.988 0.000 0.000 0.012 0.000
#> GSM647607 4 0.2377 0.9443 0.128 0.000 0.000 0.872 0.000
#> GSM647608 4 0.2377 0.9443 0.128 0.000 0.000 0.872 0.000
#> GSM647622 1 0.0000 0.8726 1.000 0.000 0.000 0.000 0.000
#> GSM647623 1 0.2471 0.7342 0.864 0.000 0.000 0.136 0.000
#> GSM647624 1 0.0703 0.8628 0.976 0.000 0.000 0.024 0.000
#> GSM647625 1 0.0000 0.8726 1.000 0.000 0.000 0.000 0.000
#> GSM647534 5 0.6582 0.0182 0.220 0.000 0.012 0.232 0.536
#> GSM647539 4 0.2377 0.9443 0.128 0.000 0.000 0.872 0.000
#> GSM647566 4 0.2377 0.9443 0.128 0.000 0.000 0.872 0.000
#> GSM647589 4 0.2377 0.9443 0.128 0.000 0.000 0.872 0.000
#> GSM647604 1 0.0000 0.8726 1.000 0.000 0.000 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.0458 0.858616 0.000 0.000 0.984 0.000 0.016 0.000
#> GSM647574 3 0.3974 0.603075 0.000 0.000 0.728 0.224 0.048 0.000
#> GSM647577 3 0.0000 0.859961 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647547 4 0.0146 0.893740 0.000 0.000 0.000 0.996 0.004 0.000
#> GSM647552 5 0.7528 0.092831 0.124 0.180 0.000 0.068 0.508 0.120
#> GSM647553 3 0.4455 0.510109 0.000 0.000 0.680 0.264 0.048 0.008
#> GSM647565 4 0.1168 0.837533 0.000 0.028 0.000 0.956 0.016 0.000
#> GSM647545 2 0.0000 0.777686 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647549 2 0.0000 0.777686 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647550 5 0.5152 0.326240 0.000 0.400 0.000 0.000 0.512 0.088
#> GSM647560 5 0.3482 0.432813 0.000 0.316 0.000 0.000 0.684 0.000
#> GSM647617 3 0.0000 0.859961 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647528 2 0.1663 0.749279 0.088 0.912 0.000 0.000 0.000 0.000
#> GSM647529 4 0.2969 0.508755 0.000 0.000 0.000 0.776 0.000 0.224
#> GSM647531 2 0.0632 0.766797 0.000 0.976 0.000 0.000 0.024 0.000
#> GSM647540 5 0.3460 0.323887 0.000 0.020 0.220 0.000 0.760 0.000
#> GSM647541 5 0.3706 0.365060 0.000 0.380 0.000 0.000 0.620 0.000
#> GSM647546 3 0.3278 0.743101 0.000 0.000 0.808 0.040 0.152 0.000
#> GSM647557 2 0.0713 0.764190 0.000 0.972 0.000 0.000 0.028 0.000
#> GSM647561 2 0.0000 0.777686 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647567 6 0.7441 0.713976 0.072 0.000 0.024 0.344 0.196 0.364
#> GSM647568 5 0.5359 0.286710 0.000 0.432 0.000 0.000 0.460 0.108
#> GSM647570 2 0.0000 0.777686 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647573 4 0.0146 0.893740 0.000 0.000 0.000 0.996 0.004 0.000
#> GSM647576 5 0.4141 0.457871 0.000 0.092 0.168 0.000 0.740 0.000
#> GSM647579 5 0.3221 0.281120 0.000 0.000 0.264 0.000 0.736 0.000
#> GSM647580 3 0.0000 0.859961 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647583 3 0.0000 0.859961 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647592 5 0.8394 -0.120118 0.264 0.152 0.000 0.104 0.352 0.128
#> GSM647593 1 0.5834 0.164061 0.468 0.204 0.000 0.000 0.328 0.000
#> GSM647595 1 0.5844 0.165274 0.468 0.208 0.000 0.000 0.324 0.000
#> GSM647597 6 0.5439 0.784810 0.080 0.000 0.000 0.380 0.016 0.524
#> GSM647598 2 0.5052 0.332200 0.388 0.532 0.000 0.000 0.080 0.000
#> GSM647613 2 0.0146 0.777081 0.004 0.996 0.000 0.000 0.000 0.000
#> GSM647615 2 0.4101 0.080043 0.000 0.580 0.000 0.000 0.408 0.012
#> GSM647616 3 0.0000 0.859961 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647619 1 0.5811 0.158920 0.468 0.196 0.000 0.000 0.336 0.000
#> GSM647582 2 0.5301 0.319595 0.132 0.568 0.000 0.000 0.300 0.000
#> GSM647591 1 0.5854 0.165848 0.468 0.212 0.000 0.000 0.320 0.000
#> GSM647527 2 0.1663 0.749279 0.088 0.912 0.000 0.000 0.000 0.000
#> GSM647530 4 0.1285 0.858603 0.000 0.000 0.000 0.944 0.004 0.052
#> GSM647532 4 0.0458 0.889287 0.000 0.000 0.000 0.984 0.000 0.016
#> GSM647544 2 0.0000 0.777686 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647551 5 0.4847 0.038215 0.376 0.064 0.000 0.000 0.560 0.000
#> GSM647556 3 0.0458 0.858616 0.000 0.000 0.984 0.000 0.016 0.000
#> GSM647558 2 0.0000 0.777686 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647572 3 0.4300 0.330508 0.000 0.000 0.548 0.020 0.432 0.000
#> GSM647578 5 0.3490 0.468711 0.000 0.268 0.008 0.000 0.724 0.000
#> GSM647581 2 0.0000 0.777686 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647594 6 0.5999 0.778388 0.128 0.000 0.000 0.376 0.024 0.472
#> GSM647599 6 0.5888 0.670449 0.036 0.000 0.028 0.412 0.036 0.488
#> GSM647600 5 0.3352 0.337561 0.172 0.012 0.000 0.016 0.800 0.000
#> GSM647601 1 0.5834 0.102178 0.480 0.304 0.000 0.000 0.216 0.000
#> GSM647603 5 0.2488 0.485083 0.044 0.076 0.000 0.000 0.880 0.000
#> GSM647610 5 0.5612 0.014460 0.124 0.000 0.000 0.116 0.664 0.096
#> GSM647611 1 0.5414 -0.174093 0.468 0.416 0.000 0.000 0.116 0.000
#> GSM647612 5 0.5359 0.286710 0.000 0.432 0.000 0.000 0.460 0.108
#> GSM647614 2 0.5350 -0.226020 0.000 0.476 0.000 0.000 0.416 0.108
#> GSM647618 2 0.3284 0.659986 0.168 0.800 0.000 0.000 0.032 0.000
#> GSM647629 5 0.1958 0.407707 0.100 0.004 0.000 0.000 0.896 0.000
#> GSM647535 2 0.4800 -0.119236 0.052 0.500 0.000 0.000 0.448 0.000
#> GSM647563 2 0.0000 0.777686 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647542 5 0.5357 0.294933 0.000 0.428 0.000 0.000 0.464 0.108
#> GSM647543 5 0.5357 0.294933 0.000 0.428 0.000 0.000 0.464 0.108
#> GSM647548 4 0.0291 0.891861 0.000 0.004 0.000 0.992 0.004 0.000
#> GSM647554 5 0.1668 0.430259 0.060 0.008 0.004 0.000 0.928 0.000
#> GSM647555 5 0.5216 0.304515 0.000 0.424 0.000 0.000 0.484 0.092
#> GSM647559 2 0.0000 0.777686 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647562 2 0.0000 0.777686 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647564 3 0.0865 0.844433 0.000 0.000 0.964 0.000 0.036 0.000
#> GSM647571 5 0.5359 0.287291 0.000 0.432 0.000 0.000 0.460 0.108
#> GSM647584 1 0.5901 0.173609 0.472 0.256 0.000 0.000 0.272 0.000
#> GSM647585 3 0.0458 0.858616 0.000 0.000 0.984 0.000 0.016 0.000
#> GSM647586 2 0.3231 0.659891 0.200 0.784 0.000 0.000 0.016 0.000
#> GSM647587 2 0.2019 0.742517 0.088 0.900 0.000 0.000 0.012 0.000
#> GSM647588 2 0.3851 -0.064701 0.000 0.540 0.000 0.000 0.460 0.000
#> GSM647596 2 0.3738 0.548010 0.280 0.704 0.000 0.000 0.016 0.000
#> GSM647602 3 0.0000 0.859961 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647609 1 0.5888 0.170960 0.476 0.268 0.000 0.000 0.256 0.000
#> GSM647620 1 0.5422 -0.215254 0.448 0.436 0.000 0.000 0.116 0.000
#> GSM647627 2 0.5002 0.320497 0.412 0.516 0.000 0.000 0.072 0.000
#> GSM647628 2 0.0363 0.772114 0.000 0.988 0.000 0.000 0.012 0.000
#> GSM647533 1 0.4184 0.238134 0.504 0.000 0.000 0.012 0.000 0.484
#> GSM647536 4 0.1387 0.842752 0.000 0.000 0.000 0.932 0.000 0.068
#> GSM647537 1 0.4184 0.238134 0.504 0.000 0.000 0.012 0.000 0.484
#> GSM647606 1 0.5216 0.168580 0.484 0.000 0.000 0.092 0.000 0.424
#> GSM647621 4 0.1556 0.775062 0.000 0.000 0.000 0.920 0.000 0.080
#> GSM647626 3 0.4963 0.482941 0.000 0.000 0.672 0.216 0.016 0.096
#> GSM647538 1 0.5054 0.164444 0.504 0.000 0.000 0.076 0.000 0.420
#> GSM647575 4 0.0146 0.894037 0.000 0.000 0.000 0.996 0.000 0.004
#> GSM647590 4 0.4476 0.118898 0.308 0.000 0.000 0.640 0.000 0.052
#> GSM647605 1 0.5901 0.000614 0.408 0.000 0.000 0.204 0.000 0.388
#> GSM647607 4 0.0146 0.894037 0.000 0.000 0.000 0.996 0.000 0.004
#> GSM647608 4 0.0000 0.893617 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM647622 1 0.4184 0.238134 0.504 0.000 0.000 0.012 0.000 0.484
#> GSM647623 1 0.4337 0.233077 0.500 0.000 0.000 0.020 0.000 0.480
#> GSM647624 1 0.5937 -0.025901 0.416 0.000 0.000 0.216 0.000 0.368
#> GSM647625 1 0.4184 0.238134 0.504 0.000 0.000 0.012 0.000 0.484
#> GSM647534 6 0.6468 0.799059 0.080 0.000 0.000 0.344 0.104 0.472
#> GSM647539 4 0.0146 0.894037 0.000 0.000 0.000 0.996 0.000 0.004
#> GSM647566 4 0.0363 0.887789 0.000 0.000 0.000 0.988 0.000 0.012
#> GSM647589 4 0.0146 0.893740 0.000 0.000 0.000 0.996 0.004 0.000
#> GSM647604 1 0.5784 0.054337 0.420 0.000 0.000 0.176 0.000 0.404
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)
#> Error in mat[ceiling(1:nr/h_ratio), ceiling(1:nc/w_ratio), drop = FALSE]: subscript out of bounds
get_signatures(res, k = 6, scale_rows = FALSE)
#> Error in mat[ceiling(1:nr/h_ratio), ceiling(1:nc/w_ratio), drop = FALSE]: subscript out of bounds
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) development.stage(p) other(p) k
#> CV:mclust 90 7.48e-10 0.0756 0.0412 2
#> CV:mclust 101 1.37e-12 0.1025 0.0548 3
#> CV:mclust 75 1.12e-07 0.3983 0.1008 4
#> CV:mclust 73 1.92e-11 0.0496 0.0549 5
#> CV:mclust 53 1.13e-04 0.2918 0.0859 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["CV", "NMF"]
# you can also extract it by
# res = res_list["CV:NMF"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'CV' method.
#> Subgroups are detected by 'NMF' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 1.000 0.958 0.983 0.4267 0.575 0.575
#> 3 3 0.738 0.803 0.918 0.5093 0.698 0.508
#> 4 4 0.789 0.808 0.912 0.0967 0.843 0.613
#> 5 5 0.642 0.572 0.787 0.0692 0.912 0.739
#> 6 6 0.617 0.537 0.722 0.0608 0.840 0.497
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
#> GSM647569 2 0.0000 0.985 0.000 1.000
#> GSM647574 2 0.9850 0.228 0.428 0.572
#> GSM647577 2 0.0000 0.985 0.000 1.000
#> GSM647547 1 0.2948 0.930 0.948 0.052
#> GSM647552 2 0.0000 0.985 0.000 1.000
#> GSM647553 1 0.5946 0.831 0.856 0.144
#> GSM647565 2 0.0000 0.985 0.000 1.000
#> GSM647545 2 0.0000 0.985 0.000 1.000
#> GSM647549 2 0.0000 0.985 0.000 1.000
#> GSM647550 2 0.0000 0.985 0.000 1.000
#> GSM647560 2 0.0000 0.985 0.000 1.000
#> GSM647617 2 0.0000 0.985 0.000 1.000
#> GSM647528 2 0.0000 0.985 0.000 1.000
#> GSM647529 1 0.0000 0.975 1.000 0.000
#> GSM647531 2 0.0000 0.985 0.000 1.000
#> GSM647540 2 0.0000 0.985 0.000 1.000
#> GSM647541 2 0.0000 0.985 0.000 1.000
#> GSM647546 2 0.0000 0.985 0.000 1.000
#> GSM647557 2 0.0000 0.985 0.000 1.000
#> GSM647561 2 0.0000 0.985 0.000 1.000
#> GSM647567 1 0.9000 0.550 0.684 0.316
#> GSM647568 2 0.0000 0.985 0.000 1.000
#> GSM647570 2 0.0000 0.985 0.000 1.000
#> GSM647573 1 0.0000 0.975 1.000 0.000
#> GSM647576 2 0.0000 0.985 0.000 1.000
#> GSM647579 2 0.0000 0.985 0.000 1.000
#> GSM647580 2 0.0000 0.985 0.000 1.000
#> GSM647583 2 0.0000 0.985 0.000 1.000
#> GSM647592 2 0.0672 0.977 0.008 0.992
#> GSM647593 2 0.0000 0.985 0.000 1.000
#> GSM647595 2 0.0000 0.985 0.000 1.000
#> GSM647597 1 0.0000 0.975 1.000 0.000
#> GSM647598 2 0.0000 0.985 0.000 1.000
#> GSM647613 2 0.0000 0.985 0.000 1.000
#> GSM647615 2 0.0000 0.985 0.000 1.000
#> GSM647616 2 0.7376 0.725 0.208 0.792
#> GSM647619 2 0.0000 0.985 0.000 1.000
#> GSM647582 2 0.0000 0.985 0.000 1.000
#> GSM647591 2 0.0000 0.985 0.000 1.000
#> GSM647527 2 0.0000 0.985 0.000 1.000
#> GSM647530 1 0.0376 0.971 0.996 0.004
#> GSM647532 1 0.0000 0.975 1.000 0.000
#> GSM647544 2 0.0000 0.985 0.000 1.000
#> GSM647551 2 0.0000 0.985 0.000 1.000
#> GSM647556 2 0.0000 0.985 0.000 1.000
#> GSM647558 2 0.0000 0.985 0.000 1.000
#> GSM647572 2 0.0000 0.985 0.000 1.000
#> GSM647578 2 0.0000 0.985 0.000 1.000
#> GSM647581 2 0.0000 0.985 0.000 1.000
#> GSM647594 2 0.9460 0.415 0.364 0.636
#> GSM647599 1 0.0000 0.975 1.000 0.000
#> GSM647600 2 0.0000 0.985 0.000 1.000
#> GSM647601 2 0.0000 0.985 0.000 1.000
#> GSM647603 2 0.0000 0.985 0.000 1.000
#> GSM647610 2 0.0000 0.985 0.000 1.000
#> GSM647611 2 0.0000 0.985 0.000 1.000
#> GSM647612 2 0.0000 0.985 0.000 1.000
#> GSM647614 2 0.0000 0.985 0.000 1.000
#> GSM647618 2 0.0000 0.985 0.000 1.000
#> GSM647629 2 0.0000 0.985 0.000 1.000
#> GSM647535 2 0.0000 0.985 0.000 1.000
#> GSM647563 2 0.0000 0.985 0.000 1.000
#> GSM647542 2 0.0000 0.985 0.000 1.000
#> GSM647543 2 0.0000 0.985 0.000 1.000
#> GSM647548 2 0.0000 0.985 0.000 1.000
#> GSM647554 2 0.0000 0.985 0.000 1.000
#> GSM647555 2 0.0000 0.985 0.000 1.000
#> GSM647559 2 0.0000 0.985 0.000 1.000
#> GSM647562 2 0.0000 0.985 0.000 1.000
#> GSM647564 2 0.0000 0.985 0.000 1.000
#> GSM647571 2 0.0000 0.985 0.000 1.000
#> GSM647584 2 0.0000 0.985 0.000 1.000
#> GSM647585 1 0.7745 0.713 0.772 0.228
#> GSM647586 2 0.0000 0.985 0.000 1.000
#> GSM647587 2 0.0000 0.985 0.000 1.000
#> GSM647588 2 0.0000 0.985 0.000 1.000
#> GSM647596 2 0.0000 0.985 0.000 1.000
#> GSM647602 2 0.0000 0.985 0.000 1.000
#> GSM647609 2 0.0000 0.985 0.000 1.000
#> GSM647620 2 0.0000 0.985 0.000 1.000
#> GSM647627 2 0.0000 0.985 0.000 1.000
#> GSM647628 2 0.0000 0.985 0.000 1.000
#> GSM647533 1 0.0000 0.975 1.000 0.000
#> GSM647536 1 0.0000 0.975 1.000 0.000
#> GSM647537 1 0.0000 0.975 1.000 0.000
#> GSM647606 1 0.0000 0.975 1.000 0.000
#> GSM647621 1 0.0000 0.975 1.000 0.000
#> GSM647626 1 0.0000 0.975 1.000 0.000
#> GSM647538 1 0.0000 0.975 1.000 0.000
#> GSM647575 1 0.0000 0.975 1.000 0.000
#> GSM647590 1 0.0000 0.975 1.000 0.000
#> GSM647605 1 0.0000 0.975 1.000 0.000
#> GSM647607 1 0.0000 0.975 1.000 0.000
#> GSM647608 1 0.0000 0.975 1.000 0.000
#> GSM647622 1 0.0000 0.975 1.000 0.000
#> GSM647623 1 0.0000 0.975 1.000 0.000
#> GSM647624 1 0.0000 0.975 1.000 0.000
#> GSM647625 1 0.0000 0.975 1.000 0.000
#> GSM647534 1 0.0000 0.975 1.000 0.000
#> GSM647539 1 0.0000 0.975 1.000 0.000
#> GSM647566 1 0.0000 0.975 1.000 0.000
#> GSM647589 1 0.0000 0.975 1.000 0.000
#> GSM647604 1 0.0000 0.975 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 3 0.0424 0.8164 0.000 0.008 0.992
#> GSM647574 3 0.0000 0.8158 0.000 0.000 1.000
#> GSM647577 3 0.0000 0.8158 0.000 0.000 1.000
#> GSM647547 3 0.0000 0.8158 0.000 0.000 1.000
#> GSM647552 2 0.0747 0.9216 0.016 0.984 0.000
#> GSM647553 3 0.0000 0.8158 0.000 0.000 1.000
#> GSM647565 3 0.4346 0.7272 0.000 0.184 0.816
#> GSM647545 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647549 2 0.1289 0.9083 0.000 0.968 0.032
#> GSM647550 3 0.3116 0.7856 0.000 0.108 0.892
#> GSM647560 2 0.4178 0.7447 0.000 0.828 0.172
#> GSM647617 3 0.0000 0.8158 0.000 0.000 1.000
#> GSM647528 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647529 1 0.0000 0.9583 1.000 0.000 0.000
#> GSM647531 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647540 3 0.4399 0.7135 0.000 0.188 0.812
#> GSM647541 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647546 3 0.0237 0.8166 0.000 0.004 0.996
#> GSM647557 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647561 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647567 1 0.5948 0.4398 0.640 0.000 0.360
#> GSM647568 3 0.0747 0.8159 0.000 0.016 0.984
#> GSM647570 2 0.6280 0.0442 0.000 0.540 0.460
#> GSM647573 3 0.4605 0.6557 0.204 0.000 0.796
#> GSM647576 3 0.1031 0.8140 0.000 0.024 0.976
#> GSM647579 3 0.6126 0.3513 0.000 0.400 0.600
#> GSM647580 3 0.0000 0.8158 0.000 0.000 1.000
#> GSM647583 3 0.0000 0.8158 0.000 0.000 1.000
#> GSM647592 2 0.0592 0.9252 0.012 0.988 0.000
#> GSM647593 2 0.0237 0.9302 0.004 0.996 0.000
#> GSM647595 2 0.0237 0.9302 0.004 0.996 0.000
#> GSM647597 1 0.0424 0.9535 0.992 0.008 0.000
#> GSM647598 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647613 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647615 2 0.5785 0.4453 0.000 0.668 0.332
#> GSM647616 3 0.0000 0.8158 0.000 0.000 1.000
#> GSM647619 2 0.0424 0.9276 0.008 0.992 0.000
#> GSM647582 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647591 2 0.0237 0.9302 0.004 0.996 0.000
#> GSM647527 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647530 1 0.1877 0.9290 0.956 0.032 0.012
#> GSM647532 1 0.0424 0.9563 0.992 0.000 0.008
#> GSM647544 2 0.2066 0.8818 0.000 0.940 0.060
#> GSM647551 2 0.0424 0.9276 0.008 0.992 0.000
#> GSM647556 3 0.0237 0.8166 0.000 0.004 0.996
#> GSM647558 3 0.6308 0.1010 0.000 0.492 0.508
#> GSM647572 3 0.0237 0.8166 0.000 0.004 0.996
#> GSM647578 3 0.5810 0.4924 0.000 0.336 0.664
#> GSM647581 2 0.4452 0.7179 0.000 0.808 0.192
#> GSM647594 2 0.5058 0.6728 0.244 0.756 0.000
#> GSM647599 1 0.0000 0.9583 1.000 0.000 0.000
#> GSM647600 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647601 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647603 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647610 2 0.2297 0.8895 0.020 0.944 0.036
#> GSM647611 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647612 3 0.5905 0.4921 0.000 0.352 0.648
#> GSM647614 3 0.6235 0.2857 0.000 0.436 0.564
#> GSM647618 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647629 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647535 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647563 2 0.0237 0.9298 0.000 0.996 0.004
#> GSM647542 3 0.2165 0.8024 0.000 0.064 0.936
#> GSM647543 3 0.5178 0.6532 0.000 0.256 0.744
#> GSM647548 3 0.5291 0.6299 0.000 0.268 0.732
#> GSM647554 2 0.4291 0.7222 0.000 0.820 0.180
#> GSM647555 2 0.6260 0.0791 0.000 0.552 0.448
#> GSM647559 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647562 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647564 3 0.0424 0.8164 0.000 0.008 0.992
#> GSM647571 3 0.5529 0.5934 0.000 0.296 0.704
#> GSM647584 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647585 3 0.1860 0.7837 0.052 0.000 0.948
#> GSM647586 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647587 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647588 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647596 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647602 3 0.0237 0.8166 0.000 0.004 0.996
#> GSM647609 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647620 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647627 2 0.0000 0.9324 0.000 1.000 0.000
#> GSM647628 2 0.5760 0.4559 0.000 0.672 0.328
#> GSM647533 1 0.0000 0.9583 1.000 0.000 0.000
#> GSM647536 1 0.0237 0.9576 0.996 0.000 0.004
#> GSM647537 1 0.0000 0.9583 1.000 0.000 0.000
#> GSM647606 1 0.0000 0.9583 1.000 0.000 0.000
#> GSM647621 1 0.3879 0.8125 0.848 0.000 0.152
#> GSM647626 3 0.6026 0.2796 0.376 0.000 0.624
#> GSM647538 1 0.0000 0.9583 1.000 0.000 0.000
#> GSM647575 1 0.4121 0.7859 0.832 0.000 0.168
#> GSM647590 1 0.0747 0.9519 0.984 0.000 0.016
#> GSM647605 1 0.0000 0.9583 1.000 0.000 0.000
#> GSM647607 1 0.1964 0.9199 0.944 0.000 0.056
#> GSM647608 3 0.6260 0.1792 0.448 0.000 0.552
#> GSM647622 1 0.0237 0.9576 0.996 0.000 0.004
#> GSM647623 1 0.0000 0.9583 1.000 0.000 0.000
#> GSM647624 1 0.0424 0.9563 0.992 0.000 0.008
#> GSM647625 1 0.0000 0.9583 1.000 0.000 0.000
#> GSM647534 1 0.0424 0.9535 0.992 0.008 0.000
#> GSM647539 3 0.6307 0.0624 0.488 0.000 0.512
#> GSM647566 1 0.0424 0.9563 0.992 0.000 0.008
#> GSM647589 3 0.0000 0.8158 0.000 0.000 1.000
#> GSM647604 1 0.0000 0.9583 1.000 0.000 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 3 0.0000 0.952 0.000 0.000 1.000 0.000
#> GSM647574 3 0.3311 0.762 0.000 0.000 0.828 0.172
#> GSM647577 3 0.0000 0.952 0.000 0.000 1.000 0.000
#> GSM647547 4 0.0000 0.772 0.000 0.000 0.000 1.000
#> GSM647552 2 0.2654 0.821 0.108 0.888 0.000 0.004
#> GSM647553 3 0.0469 0.943 0.000 0.000 0.988 0.012
#> GSM647565 4 0.0000 0.772 0.000 0.000 0.000 1.000
#> GSM647545 2 0.1867 0.878 0.000 0.928 0.000 0.072
#> GSM647549 2 0.2011 0.873 0.000 0.920 0.000 0.080
#> GSM647550 2 0.6160 0.488 0.000 0.612 0.316 0.072
#> GSM647560 2 0.2670 0.865 0.000 0.908 0.052 0.040
#> GSM647617 3 0.0000 0.952 0.000 0.000 1.000 0.000
#> GSM647528 2 0.0817 0.896 0.000 0.976 0.000 0.024
#> GSM647529 1 0.1389 0.907 0.952 0.000 0.000 0.048
#> GSM647531 2 0.1716 0.882 0.000 0.936 0.000 0.064
#> GSM647540 3 0.0000 0.952 0.000 0.000 1.000 0.000
#> GSM647541 2 0.1557 0.885 0.000 0.944 0.000 0.056
#> GSM647546 3 0.0000 0.952 0.000 0.000 1.000 0.000
#> GSM647557 2 0.2469 0.859 0.000 0.892 0.000 0.108
#> GSM647561 2 0.1211 0.891 0.000 0.960 0.000 0.040
#> GSM647567 1 0.3768 0.757 0.808 0.008 0.184 0.000
#> GSM647568 4 0.4624 0.661 0.000 0.052 0.164 0.784
#> GSM647570 4 0.4679 0.441 0.000 0.352 0.000 0.648
#> GSM647573 4 0.1118 0.770 0.036 0.000 0.000 0.964
#> GSM647576 3 0.2256 0.879 0.000 0.020 0.924 0.056
#> GSM647579 3 0.0000 0.952 0.000 0.000 1.000 0.000
#> GSM647580 3 0.0000 0.952 0.000 0.000 1.000 0.000
#> GSM647583 3 0.0000 0.952 0.000 0.000 1.000 0.000
#> GSM647592 2 0.2973 0.783 0.144 0.856 0.000 0.000
#> GSM647593 2 0.0000 0.901 0.000 1.000 0.000 0.000
#> GSM647595 2 0.0000 0.901 0.000 1.000 0.000 0.000
#> GSM647597 1 0.1022 0.907 0.968 0.032 0.000 0.000
#> GSM647598 2 0.0000 0.901 0.000 1.000 0.000 0.000
#> GSM647613 2 0.1302 0.890 0.000 0.956 0.000 0.044
#> GSM647615 2 0.2081 0.871 0.000 0.916 0.000 0.084
#> GSM647616 3 0.0000 0.952 0.000 0.000 1.000 0.000
#> GSM647619 2 0.0000 0.901 0.000 1.000 0.000 0.000
#> GSM647582 2 0.0000 0.901 0.000 1.000 0.000 0.000
#> GSM647591 2 0.0000 0.901 0.000 1.000 0.000 0.000
#> GSM647527 2 0.0707 0.897 0.000 0.980 0.000 0.020
#> GSM647530 4 0.1474 0.766 0.052 0.000 0.000 0.948
#> GSM647532 4 0.4679 0.313 0.352 0.000 0.000 0.648
#> GSM647544 4 0.4999 0.102 0.000 0.492 0.000 0.508
#> GSM647551 2 0.0000 0.901 0.000 1.000 0.000 0.000
#> GSM647556 3 0.0000 0.952 0.000 0.000 1.000 0.000
#> GSM647558 4 0.4304 0.577 0.000 0.284 0.000 0.716
#> GSM647572 3 0.1118 0.922 0.000 0.000 0.964 0.036
#> GSM647578 3 0.4790 0.343 0.000 0.380 0.620 0.000
#> GSM647581 4 0.3975 0.642 0.000 0.240 0.000 0.760
#> GSM647594 2 0.4564 0.525 0.328 0.672 0.000 0.000
#> GSM647599 1 0.0188 0.931 0.996 0.004 0.000 0.000
#> GSM647600 2 0.0000 0.901 0.000 1.000 0.000 0.000
#> GSM647601 2 0.0000 0.901 0.000 1.000 0.000 0.000
#> GSM647603 2 0.0000 0.901 0.000 1.000 0.000 0.000
#> GSM647610 2 0.4004 0.739 0.164 0.812 0.024 0.000
#> GSM647611 2 0.0000 0.901 0.000 1.000 0.000 0.000
#> GSM647612 2 0.4677 0.542 0.000 0.680 0.004 0.316
#> GSM647614 2 0.4961 0.191 0.000 0.552 0.000 0.448
#> GSM647618 2 0.0000 0.901 0.000 1.000 0.000 0.000
#> GSM647629 2 0.0000 0.901 0.000 1.000 0.000 0.000
#> GSM647535 2 0.0188 0.901 0.000 0.996 0.000 0.004
#> GSM647563 2 0.1637 0.885 0.000 0.940 0.000 0.060
#> GSM647542 4 0.6570 0.463 0.000 0.116 0.280 0.604
#> GSM647543 2 0.7576 0.182 0.000 0.472 0.308 0.220
#> GSM647548 4 0.0000 0.772 0.000 0.000 0.000 1.000
#> GSM647554 2 0.3266 0.762 0.000 0.832 0.168 0.000
#> GSM647555 2 0.1978 0.879 0.000 0.928 0.004 0.068
#> GSM647559 2 0.0336 0.900 0.000 0.992 0.000 0.008
#> GSM647562 2 0.4898 0.236 0.000 0.584 0.000 0.416
#> GSM647564 3 0.0000 0.952 0.000 0.000 1.000 0.000
#> GSM647571 4 0.3547 0.725 0.000 0.144 0.016 0.840
#> GSM647584 2 0.0000 0.901 0.000 1.000 0.000 0.000
#> GSM647585 3 0.0000 0.952 0.000 0.000 1.000 0.000
#> GSM647586 2 0.0000 0.901 0.000 1.000 0.000 0.000
#> GSM647587 2 0.0000 0.901 0.000 1.000 0.000 0.000
#> GSM647588 2 0.1474 0.887 0.000 0.948 0.000 0.052
#> GSM647596 2 0.0000 0.901 0.000 1.000 0.000 0.000
#> GSM647602 3 0.0000 0.952 0.000 0.000 1.000 0.000
#> GSM647609 2 0.0000 0.901 0.000 1.000 0.000 0.000
#> GSM647620 2 0.0000 0.901 0.000 1.000 0.000 0.000
#> GSM647627 2 0.0000 0.901 0.000 1.000 0.000 0.000
#> GSM647628 2 0.3942 0.692 0.000 0.764 0.000 0.236
#> GSM647533 1 0.0000 0.934 1.000 0.000 0.000 0.000
#> GSM647536 1 0.3569 0.773 0.804 0.000 0.000 0.196
#> GSM647537 1 0.0000 0.934 1.000 0.000 0.000 0.000
#> GSM647606 1 0.0000 0.934 1.000 0.000 0.000 0.000
#> GSM647621 4 0.4454 0.446 0.308 0.000 0.000 0.692
#> GSM647626 3 0.0000 0.952 0.000 0.000 1.000 0.000
#> GSM647538 1 0.0188 0.933 0.996 0.000 0.000 0.004
#> GSM647575 4 0.1792 0.758 0.068 0.000 0.000 0.932
#> GSM647590 1 0.4164 0.687 0.736 0.000 0.000 0.264
#> GSM647605 1 0.0000 0.934 1.000 0.000 0.000 0.000
#> GSM647607 4 0.1940 0.752 0.076 0.000 0.000 0.924
#> GSM647608 4 0.1867 0.755 0.072 0.000 0.000 0.928
#> GSM647622 1 0.0000 0.934 1.000 0.000 0.000 0.000
#> GSM647623 1 0.0000 0.934 1.000 0.000 0.000 0.000
#> GSM647624 1 0.0469 0.929 0.988 0.000 0.000 0.012
#> GSM647625 1 0.0000 0.934 1.000 0.000 0.000 0.000
#> GSM647534 1 0.0707 0.919 0.980 0.020 0.000 0.000
#> GSM647539 4 0.1557 0.764 0.056 0.000 0.000 0.944
#> GSM647566 1 0.4164 0.688 0.736 0.000 0.000 0.264
#> GSM647589 4 0.1398 0.769 0.040 0.000 0.004 0.956
#> GSM647604 1 0.0000 0.934 1.000 0.000 0.000 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.0000 0.888572 0.000 0.000 1.000 0.000 0.000
#> GSM647574 3 0.3757 0.675874 0.000 0.000 0.772 0.208 0.020
#> GSM647577 3 0.0000 0.888572 0.000 0.000 1.000 0.000 0.000
#> GSM647547 4 0.0609 0.702931 0.000 0.000 0.000 0.980 0.020
#> GSM647552 5 0.6285 0.361781 0.140 0.356 0.000 0.004 0.500
#> GSM647553 3 0.1942 0.835804 0.000 0.000 0.920 0.068 0.012
#> GSM647565 4 0.3123 0.598823 0.000 0.012 0.000 0.828 0.160
#> GSM647545 2 0.3662 0.650022 0.000 0.744 0.000 0.004 0.252
#> GSM647549 2 0.4026 0.645765 0.000 0.736 0.000 0.020 0.244
#> GSM647550 2 0.6012 0.512774 0.000 0.612 0.168 0.008 0.212
#> GSM647560 2 0.3521 0.656652 0.000 0.764 0.000 0.004 0.232
#> GSM647617 3 0.0000 0.888572 0.000 0.000 1.000 0.000 0.000
#> GSM647528 2 0.1410 0.701803 0.000 0.940 0.000 0.000 0.060
#> GSM647529 5 0.6148 -0.061317 0.304 0.000 0.000 0.160 0.536
#> GSM647531 5 0.5039 -0.358113 0.000 0.456 0.000 0.032 0.512
#> GSM647540 3 0.0000 0.888572 0.000 0.000 1.000 0.000 0.000
#> GSM647541 2 0.3521 0.657384 0.000 0.764 0.000 0.004 0.232
#> GSM647546 3 0.1792 0.821416 0.000 0.000 0.916 0.000 0.084
#> GSM647557 2 0.5216 0.361982 0.000 0.520 0.000 0.044 0.436
#> GSM647561 2 0.3336 0.660683 0.000 0.772 0.000 0.000 0.228
#> GSM647567 5 0.6721 0.018548 0.392 0.036 0.092 0.004 0.476
#> GSM647568 4 0.6495 0.223263 0.000 0.232 0.004 0.520 0.244
#> GSM647570 2 0.6304 0.412519 0.000 0.532 0.000 0.220 0.248
#> GSM647573 4 0.0510 0.705022 0.000 0.000 0.000 0.984 0.016
#> GSM647576 3 0.6740 0.092761 0.000 0.272 0.484 0.008 0.236
#> GSM647579 3 0.0162 0.885823 0.000 0.004 0.996 0.000 0.000
#> GSM647580 3 0.0000 0.888572 0.000 0.000 1.000 0.000 0.000
#> GSM647583 3 0.0000 0.888572 0.000 0.000 1.000 0.000 0.000
#> GSM647592 2 0.5382 0.346576 0.212 0.660 0.000 0.000 0.128
#> GSM647593 2 0.1544 0.679622 0.000 0.932 0.000 0.000 0.068
#> GSM647595 2 0.1341 0.686386 0.000 0.944 0.000 0.000 0.056
#> GSM647597 1 0.2408 0.714277 0.892 0.016 0.000 0.000 0.092
#> GSM647598 2 0.0290 0.699145 0.000 0.992 0.000 0.000 0.008
#> GSM647613 2 0.3395 0.657981 0.000 0.764 0.000 0.000 0.236
#> GSM647615 2 0.4114 0.640529 0.000 0.732 0.000 0.024 0.244
#> GSM647616 3 0.0000 0.888572 0.000 0.000 1.000 0.000 0.000
#> GSM647619 2 0.3940 0.525466 0.024 0.756 0.000 0.000 0.220
#> GSM647582 2 0.3242 0.622581 0.000 0.784 0.000 0.000 0.216
#> GSM647591 2 0.1544 0.678080 0.000 0.932 0.000 0.000 0.068
#> GSM647527 2 0.1270 0.702060 0.000 0.948 0.000 0.000 0.052
#> GSM647530 4 0.1701 0.688605 0.048 0.000 0.000 0.936 0.016
#> GSM647532 4 0.5714 0.266176 0.292 0.000 0.000 0.592 0.116
#> GSM647544 4 0.6166 0.315799 0.000 0.200 0.000 0.556 0.244
#> GSM647551 2 0.3932 0.307774 0.000 0.672 0.000 0.000 0.328
#> GSM647556 3 0.0000 0.888572 0.000 0.000 1.000 0.000 0.000
#> GSM647558 2 0.6538 0.328868 0.000 0.480 0.000 0.272 0.248
#> GSM647572 3 0.5273 0.600322 0.000 0.004 0.692 0.164 0.140
#> GSM647578 3 0.4588 0.262432 0.000 0.380 0.604 0.000 0.016
#> GSM647581 4 0.6590 0.130606 0.000 0.288 0.000 0.464 0.248
#> GSM647594 1 0.4088 -0.027568 0.632 0.368 0.000 0.000 0.000
#> GSM647599 1 0.3636 0.634025 0.844 0.040 0.004 0.016 0.096
#> GSM647600 2 0.2690 0.607288 0.000 0.844 0.000 0.000 0.156
#> GSM647601 2 0.0794 0.692949 0.000 0.972 0.000 0.000 0.028
#> GSM647603 2 0.3452 0.530088 0.000 0.756 0.000 0.000 0.244
#> GSM647610 2 0.6496 0.042167 0.232 0.488 0.000 0.000 0.280
#> GSM647611 2 0.3039 0.583140 0.000 0.808 0.000 0.000 0.192
#> GSM647612 2 0.4563 0.625151 0.000 0.708 0.000 0.048 0.244
#> GSM647614 2 0.5215 0.582827 0.000 0.664 0.000 0.096 0.240
#> GSM647618 2 0.3508 0.536304 0.000 0.748 0.000 0.000 0.252
#> GSM647629 2 0.2773 0.684198 0.000 0.836 0.000 0.000 0.164
#> GSM647535 2 0.0510 0.699720 0.000 0.984 0.000 0.000 0.016
#> GSM647563 2 0.3462 0.676589 0.000 0.792 0.000 0.012 0.196
#> GSM647542 2 0.6965 0.343425 0.000 0.484 0.020 0.248 0.248
#> GSM647543 2 0.5240 0.606971 0.000 0.684 0.036 0.036 0.244
#> GSM647548 4 0.0609 0.703048 0.000 0.000 0.000 0.980 0.020
#> GSM647554 2 0.4777 0.321717 0.000 0.664 0.044 0.000 0.292
#> GSM647555 2 0.3607 0.652563 0.000 0.752 0.000 0.004 0.244
#> GSM647559 2 0.4141 0.511935 0.000 0.728 0.000 0.024 0.248
#> GSM647562 2 0.6630 0.189321 0.000 0.444 0.000 0.316 0.240
#> GSM647564 3 0.0000 0.888572 0.000 0.000 1.000 0.000 0.000
#> GSM647571 4 0.6637 0.183441 0.000 0.268 0.000 0.452 0.280
#> GSM647584 2 0.1544 0.677857 0.000 0.932 0.000 0.000 0.068
#> GSM647585 3 0.0000 0.888572 0.000 0.000 1.000 0.000 0.000
#> GSM647586 2 0.0609 0.695985 0.000 0.980 0.000 0.000 0.020
#> GSM647587 2 0.3728 0.527232 0.000 0.748 0.000 0.008 0.244
#> GSM647588 2 0.3010 0.643951 0.000 0.824 0.000 0.004 0.172
#> GSM647596 2 0.0955 0.699015 0.000 0.968 0.000 0.004 0.028
#> GSM647602 3 0.0000 0.888572 0.000 0.000 1.000 0.000 0.000
#> GSM647609 2 0.0794 0.692949 0.000 0.972 0.000 0.000 0.028
#> GSM647620 2 0.0794 0.692949 0.000 0.972 0.000 0.000 0.028
#> GSM647627 2 0.0609 0.695208 0.000 0.980 0.000 0.000 0.020
#> GSM647628 2 0.4238 0.668785 0.000 0.768 0.000 0.068 0.164
#> GSM647533 1 0.3487 0.585769 0.780 0.000 0.000 0.008 0.212
#> GSM647536 4 0.6700 -0.052082 0.324 0.000 0.000 0.420 0.256
#> GSM647537 1 0.3093 0.635169 0.824 0.000 0.000 0.008 0.168
#> GSM647606 1 0.0898 0.740015 0.972 0.000 0.000 0.008 0.020
#> GSM647621 1 0.6646 0.000303 0.396 0.000 0.000 0.380 0.224
#> GSM647626 3 0.0162 0.886092 0.004 0.000 0.996 0.000 0.000
#> GSM647538 1 0.4329 0.421554 0.672 0.000 0.000 0.016 0.312
#> GSM647575 4 0.0671 0.702790 0.016 0.000 0.000 0.980 0.004
#> GSM647590 1 0.5129 0.388325 0.616 0.000 0.000 0.328 0.056
#> GSM647605 1 0.0404 0.743536 0.988 0.000 0.000 0.000 0.012
#> GSM647607 4 0.0955 0.700113 0.028 0.000 0.000 0.968 0.004
#> GSM647608 4 0.1211 0.693819 0.024 0.000 0.000 0.960 0.016
#> GSM647622 1 0.0609 0.742188 0.980 0.000 0.000 0.000 0.020
#> GSM647623 1 0.0404 0.743364 0.988 0.000 0.000 0.000 0.012
#> GSM647624 1 0.0992 0.740383 0.968 0.000 0.000 0.024 0.008
#> GSM647625 1 0.0609 0.740733 0.980 0.000 0.000 0.000 0.020
#> GSM647534 5 0.6172 0.150964 0.356 0.144 0.000 0.000 0.500
#> GSM647539 4 0.0324 0.705099 0.004 0.000 0.000 0.992 0.004
#> GSM647566 4 0.4960 0.424063 0.064 0.000 0.000 0.668 0.268
#> GSM647589 4 0.0324 0.704893 0.000 0.000 0.004 0.992 0.004
#> GSM647604 1 0.0510 0.743142 0.984 0.000 0.000 0.000 0.016
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.0000 0.8679 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647574 3 0.5029 0.4774 0.000 0.112 0.612 0.276 0.000 0.000
#> GSM647577 3 0.0000 0.8679 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647547 4 0.1637 0.7484 0.004 0.056 0.004 0.932 0.004 0.000
#> GSM647552 6 0.6340 0.4525 0.092 0.148 0.000 0.000 0.188 0.572
#> GSM647553 3 0.2890 0.7807 0.000 0.124 0.848 0.016 0.000 0.012
#> GSM647565 4 0.4171 0.3909 0.000 0.380 0.000 0.604 0.004 0.012
#> GSM647545 2 0.1644 0.7014 0.000 0.920 0.000 0.004 0.076 0.000
#> GSM647549 2 0.1700 0.6969 0.000 0.916 0.000 0.000 0.080 0.004
#> GSM647550 2 0.5145 0.4582 0.000 0.624 0.200 0.000 0.176 0.000
#> GSM647560 2 0.3261 0.6652 0.000 0.780 0.016 0.000 0.204 0.000
#> GSM647617 3 0.0000 0.8679 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647528 5 0.3833 0.2784 0.000 0.444 0.000 0.000 0.556 0.000
#> GSM647529 6 0.6468 0.3933 0.220 0.004 0.000 0.152 0.072 0.552
#> GSM647531 2 0.3000 0.6595 0.000 0.856 0.000 0.012 0.088 0.044
#> GSM647540 3 0.0146 0.8670 0.000 0.000 0.996 0.000 0.004 0.000
#> GSM647541 2 0.2969 0.6311 0.000 0.776 0.000 0.000 0.224 0.000
#> GSM647546 3 0.2823 0.7162 0.000 0.204 0.796 0.000 0.000 0.000
#> GSM647557 2 0.2955 0.6658 0.000 0.860 0.000 0.016 0.088 0.036
#> GSM647561 2 0.2762 0.6728 0.000 0.804 0.000 0.000 0.196 0.000
#> GSM647567 6 0.5747 0.4821 0.056 0.008 0.092 0.004 0.184 0.656
#> GSM647568 2 0.2377 0.6087 0.000 0.868 0.004 0.124 0.004 0.000
#> GSM647570 2 0.3566 0.6614 0.000 0.788 0.000 0.056 0.156 0.000
#> GSM647573 4 0.0405 0.7680 0.000 0.008 0.000 0.988 0.004 0.000
#> GSM647576 2 0.2900 0.6388 0.000 0.856 0.112 0.004 0.016 0.012
#> GSM647579 3 0.0622 0.8599 0.000 0.012 0.980 0.000 0.008 0.000
#> GSM647580 3 0.0000 0.8679 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647583 3 0.2520 0.7758 0.000 0.152 0.844 0.000 0.000 0.004
#> GSM647592 5 0.4153 0.4747 0.248 0.020 0.000 0.000 0.712 0.020
#> GSM647593 5 0.4039 0.5512 0.000 0.208 0.000 0.000 0.732 0.060
#> GSM647595 5 0.5178 0.4596 0.000 0.304 0.000 0.000 0.580 0.116
#> GSM647597 1 0.5036 0.3115 0.632 0.000 0.000 0.000 0.140 0.228
#> GSM647598 5 0.3807 0.4227 0.004 0.368 0.000 0.000 0.628 0.000
#> GSM647613 2 0.3076 0.6321 0.000 0.760 0.000 0.000 0.240 0.000
#> GSM647615 2 0.1910 0.7054 0.000 0.892 0.000 0.000 0.108 0.000
#> GSM647616 3 0.1556 0.8346 0.000 0.080 0.920 0.000 0.000 0.000
#> GSM647619 5 0.4085 0.5284 0.000 0.120 0.000 0.000 0.752 0.128
#> GSM647582 5 0.5868 0.2610 0.000 0.348 0.000 0.000 0.448 0.204
#> GSM647591 5 0.4630 0.3893 0.000 0.372 0.000 0.000 0.580 0.048
#> GSM647527 5 0.3823 0.3025 0.000 0.436 0.000 0.000 0.564 0.000
#> GSM647530 4 0.4102 0.5808 0.016 0.028 0.000 0.744 0.004 0.208
#> GSM647532 6 0.6379 0.3574 0.316 0.016 0.000 0.216 0.004 0.448
#> GSM647544 5 0.6203 -0.0941 0.000 0.080 0.000 0.412 0.440 0.068
#> GSM647551 5 0.5202 0.4248 0.000 0.140 0.000 0.000 0.600 0.260
#> GSM647556 3 0.0820 0.8587 0.000 0.000 0.972 0.000 0.012 0.016
#> GSM647558 2 0.1933 0.6943 0.000 0.920 0.000 0.044 0.032 0.004
#> GSM647572 3 0.6616 0.4441 0.000 0.020 0.584 0.128 0.168 0.100
#> GSM647578 3 0.6079 0.1431 0.000 0.116 0.508 0.000 0.336 0.040
#> GSM647581 2 0.2679 0.6662 0.000 0.868 0.000 0.096 0.032 0.004
#> GSM647594 1 0.5128 0.3081 0.692 0.176 0.000 0.000 0.072 0.060
#> GSM647599 1 0.2309 0.6014 0.888 0.000 0.000 0.000 0.084 0.028
#> GSM647600 5 0.4513 0.5181 0.000 0.172 0.000 0.000 0.704 0.124
#> GSM647601 5 0.3426 0.5344 0.000 0.276 0.000 0.000 0.720 0.004
#> GSM647603 5 0.5231 0.4393 0.000 0.168 0.000 0.000 0.608 0.224
#> GSM647610 5 0.5779 0.2744 0.192 0.012 0.000 0.000 0.560 0.236
#> GSM647611 5 0.3580 0.5510 0.004 0.196 0.000 0.000 0.772 0.028
#> GSM647612 2 0.3163 0.6039 0.000 0.764 0.000 0.004 0.232 0.000
#> GSM647614 2 0.4127 0.5191 0.000 0.680 0.000 0.036 0.284 0.000
#> GSM647618 5 0.5111 0.4389 0.000 0.152 0.000 0.000 0.624 0.224
#> GSM647629 2 0.3817 0.1650 0.000 0.568 0.000 0.000 0.432 0.000
#> GSM647535 5 0.3833 0.4873 0.000 0.344 0.000 0.000 0.648 0.008
#> GSM647563 2 0.4070 0.1072 0.000 0.568 0.000 0.004 0.424 0.004
#> GSM647542 2 0.3499 0.6898 0.000 0.816 0.020 0.036 0.128 0.000
#> GSM647543 2 0.1682 0.6994 0.000 0.928 0.052 0.000 0.020 0.000
#> GSM647548 4 0.0858 0.7668 0.000 0.028 0.000 0.968 0.004 0.000
#> GSM647554 5 0.5045 0.4449 0.000 0.112 0.008 0.000 0.648 0.232
#> GSM647555 2 0.2981 0.6756 0.000 0.820 0.020 0.000 0.160 0.000
#> GSM647559 5 0.5683 0.4203 0.000 0.172 0.000 0.020 0.596 0.212
#> GSM647562 5 0.7420 0.0270 0.000 0.132 0.000 0.292 0.352 0.224
#> GSM647564 3 0.0000 0.8679 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647571 5 0.7452 -0.0433 0.000 0.136 0.000 0.308 0.332 0.224
#> GSM647584 5 0.4932 0.5139 0.000 0.228 0.000 0.000 0.644 0.128
#> GSM647585 3 0.0713 0.8579 0.000 0.000 0.972 0.000 0.000 0.028
#> GSM647586 5 0.3707 0.5166 0.000 0.312 0.000 0.000 0.680 0.008
#> GSM647587 5 0.4582 0.4903 0.000 0.160 0.000 0.008 0.716 0.116
#> GSM647588 5 0.5438 0.4350 0.000 0.260 0.000 0.000 0.568 0.172
#> GSM647596 5 0.5547 0.4757 0.152 0.244 0.000 0.000 0.592 0.012
#> GSM647602 3 0.0000 0.8679 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647609 5 0.3834 0.5379 0.000 0.268 0.000 0.000 0.708 0.024
#> GSM647620 5 0.3797 0.5300 0.000 0.292 0.000 0.000 0.692 0.016
#> GSM647627 5 0.3835 0.5080 0.000 0.320 0.000 0.000 0.668 0.012
#> GSM647628 2 0.5162 0.0586 0.000 0.504 0.000 0.088 0.408 0.000
#> GSM647533 1 0.4315 -0.1697 0.492 0.000 0.000 0.004 0.012 0.492
#> GSM647536 6 0.5501 0.3954 0.320 0.008 0.000 0.120 0.000 0.552
#> GSM647537 1 0.3995 -0.0958 0.516 0.000 0.000 0.000 0.004 0.480
#> GSM647606 1 0.2462 0.6496 0.860 0.000 0.000 0.004 0.004 0.132
#> GSM647621 4 0.6625 0.2015 0.300 0.000 0.000 0.436 0.040 0.224
#> GSM647626 3 0.0260 0.8657 0.008 0.000 0.992 0.000 0.000 0.000
#> GSM647538 6 0.4470 0.2174 0.408 0.004 0.000 0.008 0.012 0.568
#> GSM647575 4 0.1053 0.7685 0.000 0.020 0.000 0.964 0.004 0.012
#> GSM647590 4 0.6142 -0.0128 0.304 0.004 0.000 0.460 0.004 0.228
#> GSM647605 1 0.0717 0.7029 0.976 0.000 0.000 0.000 0.008 0.016
#> GSM647607 4 0.0924 0.7657 0.008 0.008 0.000 0.972 0.004 0.008
#> GSM647608 4 0.0777 0.7659 0.000 0.004 0.000 0.972 0.000 0.024
#> GSM647622 1 0.0777 0.7082 0.972 0.000 0.000 0.000 0.004 0.024
#> GSM647623 1 0.0291 0.7072 0.992 0.004 0.000 0.000 0.000 0.004
#> GSM647624 1 0.2541 0.6683 0.884 0.004 0.000 0.028 0.004 0.080
#> GSM647625 1 0.0000 0.7081 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647534 6 0.5399 0.4658 0.176 0.000 0.000 0.004 0.220 0.600
#> GSM647539 4 0.2675 0.7332 0.004 0.036 0.000 0.888 0.020 0.052
#> GSM647566 4 0.5004 0.3892 0.012 0.004 0.000 0.608 0.052 0.324
#> GSM647589 4 0.0405 0.7689 0.000 0.008 0.000 0.988 0.004 0.000
#> GSM647604 1 0.0858 0.7091 0.968 0.000 0.000 0.000 0.004 0.028
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
#> Error in mat[ceiling(1:nr/h_ratio), ceiling(1:nc/w_ratio), drop = FALSE]: subscript out of bounds
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) development.stage(p) other(p) k
#> CV:NMF 101 7.92e-14 0.46488 0.0464 2
#> CV:NMF 90 1.01e-13 0.00139 0.1017 3
#> CV:NMF 93 8.25e-11 0.03818 0.0727 4
#> CV:NMF 76 1.55e-09 0.01219 0.1389 5
#> CV:NMF 61 1.83e-07 0.00538 0.2440 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["MAD", "hclust"]
# you can also extract it by
# res = res_list["MAD:hclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'MAD' method.
#> Subgroups are detected by 'hclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 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 0.192 0.646 0.773 0.4297 0.547 0.547
#> 3 3 0.392 0.542 0.747 0.3019 0.822 0.713
#> 4 4 0.457 0.538 0.743 0.1458 0.882 0.776
#> 5 5 0.475 0.418 0.664 0.0901 0.797 0.556
#> 6 6 0.540 0.549 0.683 0.0589 0.910 0.719
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
#> GSM647569 1 0.9358 0.68379 0.648 0.352
#> GSM647574 1 0.9580 0.65677 0.620 0.380
#> GSM647577 1 0.9358 0.68379 0.648 0.352
#> GSM647547 2 0.5842 0.56059 0.140 0.860
#> GSM647552 1 0.9710 -0.00125 0.600 0.400
#> GSM647553 1 0.9358 0.68379 0.648 0.352
#> GSM647565 2 0.1843 0.71796 0.028 0.972
#> GSM647545 2 0.7056 0.78546 0.192 0.808
#> GSM647549 2 0.7056 0.78546 0.192 0.808
#> GSM647550 2 0.8081 0.76432 0.248 0.752
#> GSM647560 2 0.5519 0.75469 0.128 0.872
#> GSM647617 1 0.9323 0.68528 0.652 0.348
#> GSM647528 2 0.6887 0.78610 0.184 0.816
#> GSM647529 1 0.9754 0.37063 0.592 0.408
#> GSM647531 2 0.7056 0.78546 0.192 0.808
#> GSM647540 2 0.7745 0.77447 0.228 0.772
#> GSM647541 2 0.8081 0.76432 0.248 0.752
#> GSM647546 2 0.0000 0.72964 0.000 1.000
#> GSM647557 2 0.7815 0.77567 0.232 0.768
#> GSM647561 2 0.7056 0.78546 0.192 0.808
#> GSM647567 2 0.9896 0.41228 0.440 0.560
#> GSM647568 2 0.0000 0.72964 0.000 1.000
#> GSM647570 2 0.0000 0.72964 0.000 1.000
#> GSM647573 2 0.5842 0.56059 0.140 0.860
#> GSM647576 2 0.0000 0.72964 0.000 1.000
#> GSM647579 2 0.5519 0.75469 0.128 0.872
#> GSM647580 1 0.9323 0.68528 0.652 0.348
#> GSM647583 1 0.9358 0.68379 0.648 0.352
#> GSM647592 2 0.9909 0.47442 0.444 0.556
#> GSM647593 2 0.8909 0.71510 0.308 0.692
#> GSM647595 2 0.8909 0.71510 0.308 0.692
#> GSM647597 1 0.9881 -0.11682 0.564 0.436
#> GSM647598 2 0.7219 0.78235 0.200 0.800
#> GSM647613 2 0.7219 0.78235 0.200 0.800
#> GSM647615 2 0.0376 0.72760 0.004 0.996
#> GSM647616 1 0.9358 0.68379 0.648 0.352
#> GSM647619 2 0.8909 0.71510 0.308 0.692
#> GSM647582 2 0.7602 0.77655 0.220 0.780
#> GSM647591 2 0.8909 0.71510 0.308 0.692
#> GSM647527 2 0.6887 0.78610 0.184 0.816
#> GSM647530 2 0.4815 0.77481 0.104 0.896
#> GSM647532 1 0.9754 0.37063 0.592 0.408
#> GSM647544 2 0.5629 0.78370 0.132 0.868
#> GSM647551 1 0.9850 -0.11907 0.572 0.428
#> GSM647556 1 0.7528 0.72060 0.784 0.216
#> GSM647558 2 0.0938 0.73656 0.012 0.988
#> GSM647572 2 0.2948 0.70613 0.052 0.948
#> GSM647578 2 0.8144 0.76457 0.252 0.748
#> GSM647581 2 0.0938 0.73656 0.012 0.988
#> GSM647594 2 0.8144 0.75450 0.252 0.748
#> GSM647599 1 0.5408 0.73899 0.876 0.124
#> GSM647600 1 0.9850 -0.11907 0.572 0.428
#> GSM647601 2 0.8661 0.73521 0.288 0.712
#> GSM647603 2 0.5629 0.75981 0.132 0.868
#> GSM647610 2 0.9970 0.42071 0.468 0.532
#> GSM647611 2 0.8443 0.75173 0.272 0.728
#> GSM647612 2 0.0000 0.72964 0.000 1.000
#> GSM647614 2 0.0000 0.72964 0.000 1.000
#> GSM647618 2 0.7376 0.78156 0.208 0.792
#> GSM647629 2 0.8386 0.75242 0.268 0.732
#> GSM647535 2 0.7950 0.76920 0.240 0.760
#> GSM647563 2 0.5629 0.78370 0.132 0.868
#> GSM647542 2 0.0000 0.72964 0.000 1.000
#> GSM647543 2 0.0000 0.72964 0.000 1.000
#> GSM647548 2 0.3584 0.66569 0.068 0.932
#> GSM647554 2 0.9732 0.56644 0.404 0.596
#> GSM647555 2 0.0672 0.73248 0.008 0.992
#> GSM647559 2 0.5842 0.78490 0.140 0.860
#> GSM647562 2 0.5629 0.78370 0.132 0.868
#> GSM647564 1 0.9358 0.68379 0.648 0.352
#> GSM647571 2 0.1184 0.72008 0.016 0.984
#> GSM647584 2 0.8909 0.71510 0.308 0.692
#> GSM647585 1 0.7528 0.72060 0.784 0.216
#> GSM647586 2 0.6887 0.78610 0.184 0.816
#> GSM647587 2 0.6887 0.78610 0.184 0.816
#> GSM647588 2 0.8144 0.76457 0.252 0.748
#> GSM647596 2 0.6887 0.78688 0.184 0.816
#> GSM647602 1 0.9323 0.68528 0.652 0.348
#> GSM647609 2 0.8661 0.73521 0.288 0.712
#> GSM647620 2 0.8081 0.76358 0.248 0.752
#> GSM647627 2 0.6887 0.78610 0.184 0.816
#> GSM647628 2 0.0000 0.72964 0.000 1.000
#> GSM647533 1 0.1414 0.71335 0.980 0.020
#> GSM647536 1 0.9552 0.45476 0.624 0.376
#> GSM647537 1 0.1414 0.71335 0.980 0.020
#> GSM647606 1 0.3733 0.73802 0.928 0.072
#> GSM647621 1 0.9944 0.55517 0.544 0.456
#> GSM647626 1 0.5294 0.74025 0.880 0.120
#> GSM647538 1 0.4161 0.74160 0.916 0.084
#> GSM647575 2 0.8909 0.11651 0.308 0.692
#> GSM647590 1 0.5178 0.74221 0.884 0.116
#> GSM647605 1 0.1414 0.71335 0.980 0.020
#> GSM647607 2 0.8909 0.11651 0.308 0.692
#> GSM647608 2 0.9635 -0.18950 0.388 0.612
#> GSM647622 1 0.4431 0.74232 0.908 0.092
#> GSM647623 1 0.4431 0.74232 0.908 0.092
#> GSM647624 1 0.4431 0.74232 0.908 0.092
#> GSM647625 1 0.3733 0.73802 0.928 0.072
#> GSM647534 1 0.4298 0.66628 0.912 0.088
#> GSM647539 2 0.9460 0.15265 0.364 0.636
#> GSM647566 1 0.4431 0.74182 0.908 0.092
#> GSM647589 2 0.9635 -0.18950 0.388 0.612
#> GSM647604 1 0.1414 0.71335 0.980 0.020
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 1 0.6158 0.59057 0.760 0.052 0.188
#> GSM647574 1 0.6491 0.56473 0.732 0.052 0.216
#> GSM647577 1 0.6158 0.59057 0.760 0.052 0.188
#> GSM647547 2 0.9789 -0.14429 0.236 0.396 0.368
#> GSM647552 2 0.8100 -0.02974 0.068 0.512 0.420
#> GSM647553 1 0.6158 0.59057 0.760 0.052 0.188
#> GSM647565 2 0.7238 0.47053 0.044 0.628 0.328
#> GSM647545 2 0.0747 0.73941 0.000 0.984 0.016
#> GSM647549 2 0.0747 0.73941 0.000 0.984 0.016
#> GSM647550 2 0.2400 0.72580 0.004 0.932 0.064
#> GSM647560 2 0.6096 0.65767 0.040 0.752 0.208
#> GSM647617 1 0.6107 0.59122 0.764 0.052 0.184
#> GSM647528 2 0.0661 0.73866 0.004 0.988 0.008
#> GSM647529 3 0.9865 0.69226 0.332 0.264 0.404
#> GSM647531 2 0.0592 0.73884 0.000 0.988 0.012
#> GSM647540 2 0.3120 0.73118 0.012 0.908 0.080
#> GSM647541 2 0.2400 0.72580 0.004 0.932 0.064
#> GSM647546 2 0.6703 0.57177 0.040 0.692 0.268
#> GSM647557 2 0.2165 0.73422 0.000 0.936 0.064
#> GSM647561 2 0.0747 0.73941 0.000 0.984 0.016
#> GSM647567 2 0.7745 0.39214 0.092 0.648 0.260
#> GSM647568 2 0.5992 0.59403 0.016 0.716 0.268
#> GSM647570 2 0.6161 0.57531 0.016 0.696 0.288
#> GSM647573 2 0.9789 -0.14429 0.236 0.396 0.368
#> GSM647576 2 0.6703 0.57177 0.040 0.692 0.268
#> GSM647579 2 0.6142 0.65591 0.040 0.748 0.212
#> GSM647580 1 0.6107 0.59122 0.764 0.052 0.184
#> GSM647583 1 0.6158 0.59057 0.760 0.052 0.188
#> GSM647592 2 0.6322 0.44286 0.024 0.700 0.276
#> GSM647593 2 0.3349 0.69121 0.004 0.888 0.108
#> GSM647595 2 0.3349 0.69121 0.004 0.888 0.108
#> GSM647597 2 0.8661 -0.00053 0.116 0.536 0.348
#> GSM647598 2 0.0237 0.73703 0.000 0.996 0.004
#> GSM647613 2 0.0424 0.73808 0.000 0.992 0.008
#> GSM647615 2 0.6475 0.56982 0.028 0.692 0.280
#> GSM647616 1 0.6158 0.59057 0.760 0.052 0.188
#> GSM647619 2 0.3349 0.69121 0.004 0.888 0.108
#> GSM647582 2 0.3755 0.72564 0.008 0.872 0.120
#> GSM647591 2 0.3349 0.69121 0.004 0.888 0.108
#> GSM647527 2 0.0661 0.73866 0.004 0.988 0.008
#> GSM647530 2 0.4411 0.68918 0.016 0.844 0.140
#> GSM647532 3 0.9865 0.69226 0.332 0.264 0.404
#> GSM647544 2 0.3030 0.71792 0.004 0.904 0.092
#> GSM647551 2 0.7945 0.08767 0.064 0.548 0.388
#> GSM647556 1 0.7138 0.43350 0.720 0.160 0.120
#> GSM647558 2 0.5763 0.59507 0.008 0.716 0.276
#> GSM647572 2 0.7416 0.51849 0.068 0.656 0.276
#> GSM647578 2 0.2682 0.72447 0.004 0.920 0.076
#> GSM647581 2 0.5763 0.59507 0.008 0.716 0.276
#> GSM647594 2 0.1964 0.72292 0.000 0.944 0.056
#> GSM647599 1 0.2116 0.55813 0.948 0.012 0.040
#> GSM647600 2 0.7945 0.08767 0.064 0.548 0.388
#> GSM647601 2 0.2945 0.70586 0.004 0.908 0.088
#> GSM647603 2 0.6247 0.65170 0.044 0.744 0.212
#> GSM647610 2 0.6621 0.41958 0.032 0.684 0.284
#> GSM647611 2 0.2939 0.71862 0.012 0.916 0.072
#> GSM647612 2 0.5992 0.59403 0.016 0.716 0.268
#> GSM647614 2 0.5992 0.59403 0.016 0.716 0.268
#> GSM647618 2 0.1267 0.73690 0.004 0.972 0.024
#> GSM647629 2 0.3193 0.71691 0.004 0.896 0.100
#> GSM647535 2 0.2400 0.72906 0.004 0.932 0.064
#> GSM647563 2 0.3030 0.71792 0.004 0.904 0.092
#> GSM647542 2 0.5992 0.59403 0.016 0.716 0.268
#> GSM647543 2 0.5992 0.59403 0.016 0.716 0.268
#> GSM647548 2 0.8179 0.33258 0.084 0.564 0.352
#> GSM647554 2 0.5115 0.56007 0.004 0.768 0.228
#> GSM647555 2 0.5803 0.60873 0.016 0.736 0.248
#> GSM647559 2 0.2860 0.72091 0.004 0.912 0.084
#> GSM647562 2 0.3030 0.71792 0.004 0.904 0.092
#> GSM647564 1 0.6158 0.59057 0.760 0.052 0.188
#> GSM647571 2 0.6229 0.57873 0.020 0.700 0.280
#> GSM647584 2 0.3349 0.69121 0.004 0.888 0.108
#> GSM647585 1 0.7138 0.43350 0.720 0.160 0.120
#> GSM647586 2 0.0661 0.73866 0.004 0.988 0.008
#> GSM647587 2 0.0661 0.73866 0.004 0.988 0.008
#> GSM647588 2 0.2682 0.72447 0.004 0.920 0.076
#> GSM647596 2 0.0892 0.73967 0.000 0.980 0.020
#> GSM647602 1 0.6107 0.59122 0.764 0.052 0.184
#> GSM647609 2 0.2945 0.70586 0.004 0.908 0.088
#> GSM647620 2 0.1989 0.72536 0.004 0.948 0.048
#> GSM647627 2 0.0661 0.73866 0.004 0.988 0.008
#> GSM647628 2 0.6082 0.57068 0.012 0.692 0.296
#> GSM647533 1 0.5070 0.36797 0.772 0.004 0.224
#> GSM647536 3 0.9773 0.64807 0.352 0.236 0.412
#> GSM647537 1 0.5070 0.36797 0.772 0.004 0.224
#> GSM647606 1 0.3193 0.49810 0.896 0.004 0.100
#> GSM647621 1 0.7181 0.46821 0.648 0.048 0.304
#> GSM647626 1 0.1751 0.55914 0.960 0.012 0.028
#> GSM647538 1 0.6793 0.38004 0.740 0.100 0.160
#> GSM647575 1 0.9808 -0.05947 0.392 0.240 0.368
#> GSM647590 1 0.2165 0.54017 0.936 0.000 0.064
#> GSM647605 1 0.5070 0.36797 0.772 0.004 0.224
#> GSM647607 1 0.9808 -0.05947 0.392 0.240 0.368
#> GSM647608 1 0.9423 0.11910 0.484 0.196 0.320
#> GSM647622 1 0.2096 0.53283 0.944 0.004 0.052
#> GSM647623 1 0.1878 0.53728 0.952 0.004 0.044
#> GSM647624 1 0.2096 0.53283 0.944 0.004 0.052
#> GSM647625 1 0.3193 0.49810 0.896 0.004 0.100
#> GSM647534 3 0.8433 0.34462 0.176 0.204 0.620
#> GSM647539 1 0.9984 -0.27142 0.360 0.328 0.312
#> GSM647566 1 0.6920 0.36893 0.732 0.104 0.164
#> GSM647589 1 0.9423 0.11910 0.484 0.196 0.320
#> GSM647604 1 0.5070 0.36797 0.772 0.004 0.224
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 3 0.5346 0.5918 0.004 0.032 0.692 0.272
#> GSM647574 3 0.5454 0.5480 0.004 0.028 0.664 0.304
#> GSM647577 3 0.5346 0.5918 0.004 0.032 0.692 0.272
#> GSM647547 4 0.3266 0.5947 0.000 0.040 0.084 0.876
#> GSM647552 1 0.5244 0.7155 0.600 0.388 0.000 0.012
#> GSM647553 3 0.5346 0.5918 0.004 0.032 0.692 0.272
#> GSM647565 4 0.4608 0.2319 0.004 0.304 0.000 0.692
#> GSM647545 2 0.1022 0.6888 0.000 0.968 0.000 0.032
#> GSM647549 2 0.1022 0.6888 0.000 0.968 0.000 0.032
#> GSM647550 2 0.2844 0.6733 0.052 0.900 0.000 0.048
#> GSM647560 2 0.5625 0.5823 0.056 0.720 0.012 0.212
#> GSM647617 3 0.5169 0.5927 0.000 0.032 0.696 0.272
#> GSM647528 2 0.1022 0.6879 0.000 0.968 0.000 0.032
#> GSM647529 4 0.8792 0.3715 0.292 0.068 0.192 0.448
#> GSM647531 2 0.1398 0.6894 0.004 0.956 0.000 0.040
#> GSM647540 2 0.3266 0.6757 0.048 0.884 0.004 0.064
#> GSM647541 2 0.2844 0.6733 0.052 0.900 0.000 0.048
#> GSM647546 2 0.5417 0.4836 0.000 0.572 0.016 0.412
#> GSM647557 2 0.2408 0.6768 0.044 0.920 0.000 0.036
#> GSM647561 2 0.1022 0.6888 0.000 0.968 0.000 0.032
#> GSM647567 2 0.6827 -0.2354 0.380 0.544 0.032 0.044
#> GSM647568 2 0.4866 0.5130 0.000 0.596 0.000 0.404
#> GSM647570 2 0.4933 0.4750 0.000 0.568 0.000 0.432
#> GSM647573 4 0.3266 0.5947 0.000 0.040 0.084 0.876
#> GSM647576 2 0.5417 0.4836 0.000 0.572 0.016 0.412
#> GSM647579 2 0.5800 0.5742 0.060 0.704 0.012 0.224
#> GSM647580 3 0.5169 0.5927 0.000 0.032 0.696 0.272
#> GSM647583 3 0.5346 0.5918 0.004 0.032 0.692 0.272
#> GSM647592 2 0.4800 -0.0419 0.340 0.656 0.000 0.004
#> GSM647593 2 0.2469 0.6056 0.108 0.892 0.000 0.000
#> GSM647595 2 0.2469 0.6056 0.108 0.892 0.000 0.000
#> GSM647597 2 0.7192 -0.5538 0.420 0.480 0.080 0.020
#> GSM647598 2 0.0524 0.6815 0.004 0.988 0.000 0.008
#> GSM647613 2 0.0817 0.6865 0.000 0.976 0.000 0.024
#> GSM647615 2 0.5438 0.4197 0.004 0.536 0.008 0.452
#> GSM647616 3 0.5346 0.5918 0.004 0.032 0.692 0.272
#> GSM647619 2 0.2469 0.6056 0.108 0.892 0.000 0.000
#> GSM647582 2 0.3508 0.6667 0.060 0.872 0.004 0.064
#> GSM647591 2 0.2469 0.6056 0.108 0.892 0.000 0.000
#> GSM647527 2 0.1022 0.6879 0.000 0.968 0.000 0.032
#> GSM647530 2 0.4401 0.5892 0.004 0.724 0.000 0.272
#> GSM647532 4 0.8792 0.3715 0.292 0.068 0.192 0.448
#> GSM647544 2 0.2973 0.6648 0.000 0.856 0.000 0.144
#> GSM647551 1 0.4925 0.7021 0.572 0.428 0.000 0.000
#> GSM647556 3 0.7776 0.5268 0.168 0.072 0.608 0.152
#> GSM647558 2 0.4933 0.4748 0.000 0.568 0.000 0.432
#> GSM647572 2 0.5950 0.4263 0.000 0.544 0.040 0.416
#> GSM647578 2 0.3168 0.6675 0.060 0.884 0.000 0.056
#> GSM647581 2 0.4933 0.4748 0.000 0.568 0.000 0.432
#> GSM647594 2 0.1970 0.6540 0.060 0.932 0.000 0.008
#> GSM647599 3 0.1792 0.6381 0.000 0.000 0.932 0.068
#> GSM647600 1 0.4925 0.7021 0.572 0.428 0.000 0.000
#> GSM647601 2 0.2149 0.6261 0.088 0.912 0.000 0.000
#> GSM647603 2 0.5804 0.5664 0.036 0.676 0.016 0.272
#> GSM647610 2 0.5525 -0.0829 0.328 0.644 0.008 0.020
#> GSM647611 2 0.2271 0.6426 0.076 0.916 0.000 0.008
#> GSM647612 2 0.4866 0.5130 0.000 0.596 0.000 0.404
#> GSM647614 2 0.4866 0.5130 0.000 0.596 0.000 0.404
#> GSM647618 2 0.1520 0.6817 0.020 0.956 0.000 0.024
#> GSM647629 2 0.3176 0.6469 0.084 0.880 0.000 0.036
#> GSM647535 2 0.2483 0.6712 0.052 0.916 0.000 0.032
#> GSM647563 2 0.3074 0.6623 0.000 0.848 0.000 0.152
#> GSM647542 2 0.4866 0.5130 0.000 0.596 0.000 0.404
#> GSM647543 2 0.4866 0.5130 0.000 0.596 0.000 0.404
#> GSM647548 4 0.3400 0.4758 0.000 0.180 0.000 0.820
#> GSM647554 2 0.4252 0.3274 0.252 0.744 0.000 0.004
#> GSM647555 2 0.4776 0.5297 0.000 0.624 0.000 0.376
#> GSM647559 2 0.2921 0.6665 0.000 0.860 0.000 0.140
#> GSM647562 2 0.3024 0.6639 0.000 0.852 0.000 0.148
#> GSM647564 3 0.5346 0.5918 0.004 0.032 0.692 0.272
#> GSM647571 2 0.5088 0.4897 0.000 0.572 0.004 0.424
#> GSM647584 2 0.2469 0.6056 0.108 0.892 0.000 0.000
#> GSM647585 3 0.7776 0.5268 0.168 0.072 0.608 0.152
#> GSM647586 2 0.1022 0.6879 0.000 0.968 0.000 0.032
#> GSM647587 2 0.1022 0.6879 0.000 0.968 0.000 0.032
#> GSM647588 2 0.3168 0.6675 0.060 0.884 0.000 0.056
#> GSM647596 2 0.1867 0.6882 0.000 0.928 0.000 0.072
#> GSM647602 3 0.5169 0.5927 0.000 0.032 0.696 0.272
#> GSM647609 2 0.2149 0.6261 0.088 0.912 0.000 0.000
#> GSM647620 2 0.1807 0.6597 0.052 0.940 0.000 0.008
#> GSM647627 2 0.1209 0.6873 0.004 0.964 0.000 0.032
#> GSM647628 2 0.4977 0.4291 0.000 0.540 0.000 0.460
#> GSM647533 3 0.5025 0.4850 0.252 0.000 0.716 0.032
#> GSM647536 4 0.8757 0.3391 0.308 0.056 0.208 0.428
#> GSM647537 3 0.5025 0.4850 0.252 0.000 0.716 0.032
#> GSM647606 3 0.2924 0.5992 0.100 0.000 0.884 0.016
#> GSM647621 3 0.4933 0.3078 0.000 0.000 0.568 0.432
#> GSM647626 3 0.1637 0.6397 0.000 0.000 0.940 0.060
#> GSM647538 3 0.6732 0.4490 0.336 0.000 0.556 0.108
#> GSM647575 4 0.4616 0.5214 0.020 0.004 0.216 0.760
#> GSM647590 3 0.4483 0.5953 0.104 0.000 0.808 0.088
#> GSM647605 3 0.5055 0.4836 0.256 0.000 0.712 0.032
#> GSM647607 4 0.4616 0.5214 0.020 0.004 0.216 0.760
#> GSM647608 4 0.5134 0.3604 0.012 0.004 0.320 0.664
#> GSM647622 3 0.2021 0.6199 0.056 0.000 0.932 0.012
#> GSM647623 3 0.1938 0.6237 0.052 0.000 0.936 0.012
#> GSM647624 3 0.2021 0.6199 0.056 0.000 0.932 0.012
#> GSM647625 3 0.2924 0.5992 0.100 0.000 0.884 0.016
#> GSM647534 1 0.1821 0.1946 0.948 0.032 0.012 0.008
#> GSM647539 4 0.6972 0.5122 0.120 0.044 0.172 0.664
#> GSM647566 3 0.6732 0.4410 0.336 0.000 0.556 0.108
#> GSM647589 4 0.5134 0.3604 0.012 0.004 0.320 0.664
#> GSM647604 3 0.5055 0.4836 0.256 0.000 0.712 0.032
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.6634 -0.03421 0.376 0.000 0.472 0.132 0.020
#> GSM647574 3 0.6819 -0.04319 0.348 0.000 0.468 0.164 0.020
#> GSM647577 3 0.6634 -0.03421 0.376 0.000 0.472 0.132 0.020
#> GSM647547 4 0.5383 0.63942 0.036 0.012 0.292 0.648 0.012
#> GSM647552 5 0.4235 0.74068 0.000 0.336 0.000 0.008 0.656
#> GSM647553 3 0.6634 -0.03421 0.376 0.000 0.472 0.132 0.020
#> GSM647565 3 0.6409 -0.12566 0.000 0.152 0.516 0.324 0.008
#> GSM647545 2 0.1798 0.74841 0.000 0.928 0.064 0.004 0.004
#> GSM647549 2 0.1864 0.74773 0.000 0.924 0.068 0.004 0.004
#> GSM647550 2 0.3400 0.70871 0.000 0.840 0.116 0.004 0.040
#> GSM647560 2 0.6220 0.44023 0.008 0.584 0.304 0.020 0.084
#> GSM647617 3 0.6710 -0.03703 0.376 0.000 0.468 0.132 0.024
#> GSM647528 2 0.1671 0.74426 0.000 0.924 0.076 0.000 0.000
#> GSM647529 4 0.8866 0.40532 0.184 0.040 0.144 0.396 0.236
#> GSM647531 2 0.2054 0.74976 0.000 0.916 0.072 0.004 0.008
#> GSM647540 2 0.3875 0.70186 0.004 0.820 0.120 0.008 0.048
#> GSM647541 2 0.3449 0.70589 0.000 0.836 0.120 0.004 0.040
#> GSM647546 3 0.4962 0.11651 0.008 0.432 0.544 0.016 0.000
#> GSM647557 2 0.2122 0.74226 0.000 0.924 0.032 0.008 0.036
#> GSM647561 2 0.1798 0.74841 0.000 0.928 0.064 0.004 0.004
#> GSM647567 2 0.6541 -0.38961 0.012 0.472 0.088 0.016 0.412
#> GSM647568 3 0.4397 0.11053 0.000 0.432 0.564 0.004 0.000
#> GSM647570 3 0.5483 0.08989 0.000 0.424 0.512 0.064 0.000
#> GSM647573 4 0.5383 0.63942 0.036 0.012 0.292 0.648 0.012
#> GSM647576 3 0.4962 0.11651 0.008 0.432 0.544 0.016 0.000
#> GSM647579 2 0.6251 0.43599 0.008 0.584 0.300 0.020 0.088
#> GSM647580 3 0.6710 -0.03703 0.376 0.000 0.468 0.132 0.024
#> GSM647583 3 0.6634 -0.03421 0.376 0.000 0.472 0.132 0.020
#> GSM647592 2 0.4288 -0.16147 0.000 0.612 0.004 0.000 0.384
#> GSM647593 2 0.2074 0.67402 0.000 0.896 0.000 0.000 0.104
#> GSM647595 2 0.2074 0.67402 0.000 0.896 0.000 0.000 0.104
#> GSM647597 5 0.6218 0.55918 0.076 0.428 0.016 0.004 0.476
#> GSM647598 2 0.1124 0.74500 0.000 0.960 0.036 0.000 0.004
#> GSM647613 2 0.1502 0.74840 0.000 0.940 0.056 0.004 0.000
#> GSM647615 3 0.5253 0.16060 0.000 0.384 0.572 0.036 0.008
#> GSM647616 3 0.6634 -0.03421 0.376 0.000 0.472 0.132 0.020
#> GSM647619 2 0.2074 0.67402 0.000 0.896 0.000 0.000 0.104
#> GSM647582 2 0.3197 0.71696 0.000 0.864 0.076 0.008 0.052
#> GSM647591 2 0.2074 0.67402 0.000 0.896 0.000 0.000 0.104
#> GSM647527 2 0.1671 0.74426 0.000 0.924 0.076 0.000 0.000
#> GSM647530 2 0.5608 0.52965 0.000 0.652 0.224 0.116 0.008
#> GSM647532 4 0.8866 0.40532 0.184 0.040 0.144 0.396 0.236
#> GSM647544 2 0.3656 0.66511 0.000 0.800 0.168 0.032 0.000
#> GSM647551 5 0.4114 0.73300 0.000 0.376 0.000 0.000 0.624
#> GSM647556 3 0.8817 -0.19782 0.300 0.040 0.360 0.116 0.184
#> GSM647558 2 0.6130 -0.00291 0.000 0.448 0.424 0.128 0.000
#> GSM647572 3 0.5515 0.14213 0.012 0.404 0.548 0.028 0.008
#> GSM647578 2 0.3693 0.69866 0.000 0.824 0.124 0.008 0.044
#> GSM647581 2 0.6121 0.03018 0.000 0.464 0.408 0.128 0.000
#> GSM647594 2 0.2616 0.71677 0.000 0.888 0.036 0.000 0.076
#> GSM647599 1 0.5028 0.50180 0.744 0.000 0.140 0.088 0.028
#> GSM647600 5 0.4114 0.73300 0.000 0.376 0.000 0.000 0.624
#> GSM647601 2 0.1732 0.69486 0.000 0.920 0.000 0.000 0.080
#> GSM647603 2 0.5955 0.33851 0.008 0.552 0.372 0.020 0.048
#> GSM647610 2 0.4759 -0.19595 0.000 0.600 0.012 0.008 0.380
#> GSM647611 2 0.1942 0.71867 0.000 0.920 0.012 0.000 0.068
#> GSM647612 3 0.4397 0.11053 0.000 0.432 0.564 0.004 0.000
#> GSM647614 3 0.4397 0.11053 0.000 0.432 0.564 0.004 0.000
#> GSM647618 2 0.1670 0.74719 0.000 0.936 0.052 0.000 0.012
#> GSM647629 2 0.3748 0.68165 0.000 0.824 0.080 0.004 0.092
#> GSM647535 2 0.2650 0.73147 0.000 0.892 0.068 0.004 0.036
#> GSM647563 2 0.3883 0.65658 0.000 0.780 0.184 0.036 0.000
#> GSM647542 3 0.4397 0.11053 0.000 0.432 0.564 0.004 0.000
#> GSM647543 3 0.4397 0.11053 0.000 0.432 0.564 0.004 0.000
#> GSM647548 3 0.5947 -0.37749 0.000 0.072 0.476 0.440 0.012
#> GSM647554 2 0.4468 0.30737 0.000 0.696 0.024 0.004 0.276
#> GSM647555 3 0.4437 0.03956 0.000 0.464 0.532 0.004 0.000
#> GSM647559 2 0.3656 0.66835 0.000 0.800 0.168 0.032 0.000
#> GSM647562 2 0.3694 0.66349 0.000 0.796 0.172 0.032 0.000
#> GSM647564 3 0.6634 -0.03421 0.376 0.000 0.472 0.132 0.020
#> GSM647571 3 0.4858 0.11135 0.000 0.424 0.556 0.012 0.008
#> GSM647584 2 0.2074 0.67402 0.000 0.896 0.000 0.000 0.104
#> GSM647585 3 0.8817 -0.19782 0.300 0.040 0.360 0.116 0.184
#> GSM647586 2 0.1671 0.74426 0.000 0.924 0.076 0.000 0.000
#> GSM647587 2 0.1671 0.74426 0.000 0.924 0.076 0.000 0.000
#> GSM647588 2 0.3693 0.69866 0.000 0.824 0.124 0.008 0.044
#> GSM647596 2 0.2813 0.70194 0.000 0.832 0.168 0.000 0.000
#> GSM647602 3 0.6710 -0.03703 0.376 0.000 0.468 0.132 0.024
#> GSM647609 2 0.1732 0.69486 0.000 0.920 0.000 0.000 0.080
#> GSM647620 2 0.1646 0.73316 0.000 0.944 0.020 0.004 0.032
#> GSM647627 2 0.1831 0.74441 0.000 0.920 0.076 0.000 0.004
#> GSM647628 3 0.5928 0.11010 0.000 0.392 0.500 0.108 0.000
#> GSM647533 1 0.4714 0.58944 0.756 0.000 0.044 0.032 0.168
#> GSM647536 4 0.8956 0.37529 0.212 0.040 0.140 0.372 0.236
#> GSM647537 1 0.4714 0.58944 0.756 0.000 0.044 0.032 0.168
#> GSM647606 1 0.1106 0.66738 0.964 0.000 0.000 0.012 0.024
#> GSM647621 1 0.7409 -0.15900 0.360 0.000 0.312 0.300 0.028
#> GSM647626 1 0.5631 0.41962 0.672 0.000 0.216 0.084 0.028
#> GSM647538 1 0.7622 0.34914 0.464 0.000 0.076 0.248 0.212
#> GSM647575 4 0.5521 0.65107 0.124 0.000 0.216 0.656 0.004
#> GSM647590 1 0.5682 0.52253 0.668 0.000 0.088 0.216 0.028
#> GSM647605 1 0.4751 0.58768 0.752 0.000 0.044 0.032 0.172
#> GSM647607 4 0.5521 0.65107 0.124 0.000 0.216 0.656 0.004
#> GSM647608 4 0.6437 0.57237 0.212 0.000 0.232 0.548 0.008
#> GSM647622 1 0.0671 0.66316 0.980 0.000 0.016 0.000 0.004
#> GSM647623 1 0.1282 0.65170 0.952 0.000 0.044 0.000 0.004
#> GSM647624 1 0.0671 0.66316 0.980 0.000 0.016 0.000 0.004
#> GSM647625 1 0.1106 0.66738 0.964 0.000 0.000 0.012 0.024
#> GSM647534 5 0.3515 0.14080 0.068 0.020 0.028 0.020 0.864
#> GSM647539 4 0.5738 0.48934 0.060 0.016 0.236 0.668 0.020
#> GSM647566 1 0.7680 0.33752 0.448 0.000 0.076 0.264 0.212
#> GSM647589 4 0.6437 0.57237 0.212 0.000 0.232 0.548 0.008
#> GSM647604 1 0.4751 0.58768 0.752 0.000 0.044 0.032 0.172
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.139 0.83660 0.000 0.000 0.932 0.000 0.000 0.068
#> GSM647574 3 0.236 0.80750 0.000 0.000 0.888 0.040 0.000 0.072
#> GSM647577 3 0.139 0.83660 0.000 0.000 0.932 0.000 0.000 0.068
#> GSM647547 4 0.502 0.74928 0.004 0.000 0.096 0.680 0.016 0.204
#> GSM647552 5 0.371 0.74521 0.004 0.340 0.000 0.000 0.656 0.000
#> GSM647553 3 0.139 0.83660 0.000 0.000 0.932 0.000 0.000 0.068
#> GSM647565 6 0.465 0.27634 0.004 0.040 0.008 0.236 0.012 0.700
#> GSM647545 2 0.209 0.69658 0.000 0.876 0.000 0.000 0.000 0.124
#> GSM647549 2 0.214 0.69487 0.000 0.872 0.000 0.000 0.000 0.128
#> GSM647550 2 0.371 0.62266 0.000 0.792 0.004 0.008 0.040 0.156
#> GSM647560 2 0.658 0.02089 0.000 0.500 0.108 0.004 0.084 0.304
#> GSM647617 3 0.144 0.83559 0.000 0.000 0.928 0.000 0.000 0.072
#> GSM647528 2 0.256 0.67092 0.000 0.840 0.000 0.004 0.000 0.156
#> GSM647529 1 0.836 -0.06523 0.332 0.036 0.028 0.328 0.148 0.128
#> GSM647531 2 0.238 0.69780 0.004 0.868 0.000 0.000 0.004 0.124
#> GSM647540 2 0.433 0.60804 0.000 0.764 0.028 0.008 0.048 0.152
#> GSM647541 2 0.374 0.61748 0.000 0.788 0.004 0.008 0.040 0.160
#> GSM647546 6 0.504 0.79884 0.000 0.288 0.108 0.000 0.000 0.604
#> GSM647557 2 0.238 0.71662 0.000 0.892 0.004 0.000 0.036 0.068
#> GSM647561 2 0.209 0.69658 0.000 0.876 0.000 0.000 0.000 0.124
#> GSM647567 2 0.604 -0.39790 0.000 0.456 0.084 0.004 0.416 0.040
#> GSM647568 6 0.451 0.82054 0.000 0.280 0.064 0.000 0.000 0.656
#> GSM647570 6 0.449 0.79221 0.000 0.272 0.016 0.036 0.000 0.676
#> GSM647573 4 0.502 0.74928 0.004 0.000 0.096 0.680 0.016 0.204
#> GSM647576 6 0.504 0.79884 0.000 0.288 0.108 0.000 0.000 0.604
#> GSM647579 2 0.660 0.01312 0.000 0.504 0.108 0.004 0.088 0.296
#> GSM647580 3 0.144 0.83559 0.000 0.000 0.928 0.000 0.000 0.072
#> GSM647583 3 0.139 0.83660 0.000 0.000 0.932 0.000 0.000 0.068
#> GSM647592 2 0.403 -0.18026 0.000 0.612 0.000 0.000 0.376 0.012
#> GSM647593 2 0.150 0.65079 0.000 0.924 0.000 0.000 0.076 0.000
#> GSM647595 2 0.144 0.65466 0.000 0.928 0.000 0.000 0.072 0.000
#> GSM647597 2 0.642 -0.54093 0.136 0.420 0.000 0.008 0.404 0.032
#> GSM647598 2 0.161 0.70647 0.000 0.916 0.000 0.000 0.000 0.084
#> GSM647613 2 0.214 0.69409 0.000 0.872 0.000 0.000 0.000 0.128
#> GSM647615 6 0.531 0.79806 0.004 0.244 0.088 0.016 0.004 0.644
#> GSM647616 3 0.139 0.83660 0.000 0.000 0.932 0.000 0.000 0.068
#> GSM647619 2 0.150 0.65079 0.000 0.924 0.000 0.000 0.076 0.000
#> GSM647582 2 0.343 0.67987 0.000 0.844 0.036 0.004 0.056 0.060
#> GSM647591 2 0.144 0.65466 0.000 0.928 0.000 0.000 0.072 0.000
#> GSM647527 2 0.256 0.67092 0.000 0.840 0.000 0.004 0.000 0.156
#> GSM647530 2 0.538 0.25033 0.004 0.572 0.000 0.072 0.016 0.336
#> GSM647532 1 0.836 -0.06523 0.332 0.036 0.028 0.328 0.148 0.128
#> GSM647544 2 0.371 0.48658 0.000 0.704 0.000 0.008 0.004 0.284
#> GSM647551 5 0.385 0.73725 0.004 0.384 0.000 0.000 0.612 0.000
#> GSM647556 3 0.394 0.65794 0.000 0.024 0.772 0.004 0.176 0.024
#> GSM647558 6 0.497 0.61231 0.000 0.336 0.000 0.064 0.008 0.592
#> GSM647572 6 0.565 0.77581 0.008 0.276 0.128 0.008 0.000 0.580
#> GSM647578 2 0.394 0.62056 0.000 0.784 0.008 0.012 0.044 0.152
#> GSM647581 6 0.503 0.57659 0.000 0.356 0.000 0.064 0.008 0.572
#> GSM647594 2 0.263 0.69611 0.000 0.872 0.000 0.000 0.064 0.064
#> GSM647599 3 0.534 -0.00560 0.396 0.000 0.532 0.044 0.008 0.020
#> GSM647600 5 0.385 0.73725 0.004 0.384 0.000 0.000 0.612 0.000
#> GSM647601 2 0.127 0.68087 0.000 0.948 0.000 0.000 0.044 0.008
#> GSM647603 2 0.644 -0.37053 0.008 0.448 0.100 0.008 0.036 0.400
#> GSM647610 2 0.478 -0.22230 0.008 0.592 0.000 0.008 0.364 0.028
#> GSM647611 2 0.245 0.70995 0.000 0.884 0.000 0.000 0.052 0.064
#> GSM647612 6 0.451 0.82054 0.000 0.280 0.064 0.000 0.000 0.656
#> GSM647614 6 0.451 0.82054 0.000 0.280 0.064 0.000 0.000 0.656
#> GSM647618 2 0.191 0.70717 0.000 0.900 0.000 0.000 0.004 0.096
#> GSM647629 2 0.377 0.63879 0.000 0.808 0.012 0.004 0.084 0.092
#> GSM647535 2 0.281 0.69152 0.000 0.876 0.012 0.008 0.028 0.076
#> GSM647563 2 0.381 0.46797 0.000 0.684 0.000 0.008 0.004 0.304
#> GSM647542 6 0.451 0.82054 0.000 0.280 0.064 0.000 0.000 0.656
#> GSM647543 6 0.451 0.82054 0.000 0.280 0.064 0.000 0.000 0.656
#> GSM647548 6 0.465 -0.16551 0.004 0.000 0.016 0.372 0.016 0.592
#> GSM647554 2 0.429 0.27579 0.000 0.692 0.008 0.004 0.268 0.028
#> GSM647555 6 0.465 0.78857 0.000 0.312 0.064 0.000 0.000 0.624
#> GSM647559 2 0.371 0.49363 0.000 0.704 0.000 0.008 0.004 0.284
#> GSM647562 2 0.373 0.48575 0.000 0.700 0.000 0.008 0.004 0.288
#> GSM647564 3 0.139 0.83660 0.000 0.000 0.932 0.000 0.000 0.068
#> GSM647571 6 0.505 0.80949 0.008 0.280 0.068 0.008 0.000 0.636
#> GSM647584 2 0.144 0.65442 0.000 0.928 0.000 0.000 0.072 0.000
#> GSM647585 3 0.394 0.65794 0.000 0.024 0.772 0.004 0.176 0.024
#> GSM647586 2 0.256 0.67092 0.000 0.840 0.000 0.004 0.000 0.156
#> GSM647587 2 0.256 0.67092 0.000 0.840 0.000 0.004 0.000 0.156
#> GSM647588 2 0.394 0.62056 0.000 0.784 0.008 0.012 0.044 0.152
#> GSM647596 2 0.343 0.50579 0.000 0.720 0.000 0.004 0.000 0.276
#> GSM647602 3 0.144 0.83559 0.000 0.000 0.928 0.000 0.000 0.072
#> GSM647609 2 0.127 0.68087 0.000 0.948 0.000 0.000 0.044 0.008
#> GSM647620 2 0.131 0.70700 0.000 0.952 0.000 0.004 0.016 0.028
#> GSM647627 2 0.248 0.67660 0.000 0.848 0.000 0.004 0.000 0.148
#> GSM647628 6 0.491 0.76094 0.000 0.252 0.012 0.080 0.000 0.656
#> GSM647533 1 0.218 0.57117 0.908 0.000 0.064 0.008 0.016 0.004
#> GSM647536 1 0.827 -0.04126 0.356 0.036 0.028 0.320 0.144 0.116
#> GSM647537 1 0.218 0.57117 0.908 0.000 0.064 0.008 0.016 0.004
#> GSM647606 1 0.375 0.51804 0.696 0.000 0.292 0.008 0.000 0.004
#> GSM647621 3 0.674 -0.00234 0.140 0.000 0.456 0.336 0.008 0.060
#> GSM647626 3 0.369 0.38721 0.288 0.000 0.700 0.000 0.000 0.012
#> GSM647538 1 0.830 0.24456 0.352 0.000 0.152 0.220 0.216 0.060
#> GSM647575 4 0.380 0.77776 0.020 0.000 0.108 0.812 0.008 0.052
#> GSM647590 1 0.737 0.39857 0.460 0.000 0.236 0.204 0.056 0.044
#> GSM647605 1 0.227 0.57026 0.904 0.000 0.064 0.008 0.020 0.004
#> GSM647607 4 0.380 0.77776 0.020 0.000 0.108 0.812 0.008 0.052
#> GSM647608 4 0.541 0.72026 0.080 0.000 0.176 0.680 0.008 0.056
#> GSM647622 1 0.405 0.46459 0.644 0.000 0.340 0.012 0.000 0.004
#> GSM647623 1 0.417 0.39993 0.604 0.000 0.380 0.012 0.000 0.004
#> GSM647624 1 0.405 0.46459 0.644 0.000 0.340 0.012 0.000 0.004
#> GSM647625 1 0.375 0.51804 0.696 0.000 0.292 0.008 0.000 0.004
#> GSM647534 5 0.477 0.16048 0.136 0.028 0.000 0.024 0.748 0.064
#> GSM647539 4 0.640 0.46251 0.052 0.000 0.048 0.572 0.064 0.264
#> GSM647566 1 0.833 0.22948 0.336 0.000 0.152 0.236 0.216 0.060
#> GSM647589 4 0.541 0.72026 0.080 0.000 0.176 0.680 0.008 0.056
#> GSM647604 1 0.227 0.57026 0.904 0.000 0.064 0.008 0.020 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) development.stage(p) other(p) k
#> MAD:hclust 88 3.21e-09 0.23396 1.0000 2
#> MAD:hclust 75 6.65e-05 0.00565 0.4364 3
#> MAD:hclust 74 1.70e-05 0.07244 0.6137 4
#> MAD:hclust 58 6.40e-10 0.04874 0.2107 5
#> MAD:hclust 74 3.54e-12 0.05088 0.0917 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["MAD", "kmeans"]
# you can also extract it by
# res = res_list["MAD:kmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'MAD' method.
#> Subgroups are detected by 'kmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 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 0.979 0.959 0.983 0.4787 0.520 0.520
#> 3 3 0.480 0.534 0.757 0.3275 0.791 0.619
#> 4 4 0.534 0.604 0.736 0.1429 0.731 0.399
#> 5 5 0.656 0.662 0.775 0.0730 0.898 0.649
#> 6 6 0.696 0.595 0.760 0.0513 0.843 0.440
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
#> GSM647569 1 0.000 0.973 1.000 0.000
#> GSM647574 1 0.000 0.973 1.000 0.000
#> GSM647577 1 0.000 0.973 1.000 0.000
#> GSM647547 1 0.000 0.973 1.000 0.000
#> GSM647552 1 0.745 0.731 0.788 0.212
#> GSM647553 1 0.000 0.973 1.000 0.000
#> GSM647565 2 0.000 0.987 0.000 1.000
#> GSM647545 2 0.000 0.987 0.000 1.000
#> GSM647549 2 0.000 0.987 0.000 1.000
#> GSM647550 2 0.000 0.987 0.000 1.000
#> GSM647560 2 0.000 0.987 0.000 1.000
#> GSM647617 1 0.000 0.973 1.000 0.000
#> GSM647528 2 0.000 0.987 0.000 1.000
#> GSM647529 1 0.949 0.425 0.632 0.368
#> GSM647531 2 0.000 0.987 0.000 1.000
#> GSM647540 2 0.000 0.987 0.000 1.000
#> GSM647541 2 0.000 0.987 0.000 1.000
#> GSM647546 1 0.541 0.849 0.876 0.124
#> GSM647557 2 0.000 0.987 0.000 1.000
#> GSM647561 2 0.000 0.987 0.000 1.000
#> GSM647567 2 0.844 0.622 0.272 0.728
#> GSM647568 2 0.000 0.987 0.000 1.000
#> GSM647570 2 0.000 0.987 0.000 1.000
#> GSM647573 1 0.000 0.973 1.000 0.000
#> GSM647576 2 0.000 0.987 0.000 1.000
#> GSM647579 2 0.827 0.644 0.260 0.740
#> GSM647580 1 0.000 0.973 1.000 0.000
#> GSM647583 1 0.000 0.973 1.000 0.000
#> GSM647592 2 0.000 0.987 0.000 1.000
#> GSM647593 2 0.000 0.987 0.000 1.000
#> GSM647595 2 0.000 0.987 0.000 1.000
#> GSM647597 2 0.000 0.987 0.000 1.000
#> GSM647598 2 0.000 0.987 0.000 1.000
#> GSM647613 2 0.000 0.987 0.000 1.000
#> GSM647615 2 0.000 0.987 0.000 1.000
#> GSM647616 1 0.000 0.973 1.000 0.000
#> GSM647619 2 0.000 0.987 0.000 1.000
#> GSM647582 2 0.000 0.987 0.000 1.000
#> GSM647591 2 0.000 0.987 0.000 1.000
#> GSM647527 2 0.000 0.987 0.000 1.000
#> GSM647530 2 0.000 0.987 0.000 1.000
#> GSM647532 1 0.000 0.973 1.000 0.000
#> GSM647544 2 0.000 0.987 0.000 1.000
#> GSM647551 2 0.000 0.987 0.000 1.000
#> GSM647556 1 0.000 0.973 1.000 0.000
#> GSM647558 2 0.000 0.987 0.000 1.000
#> GSM647572 2 0.802 0.672 0.244 0.756
#> GSM647578 2 0.000 0.987 0.000 1.000
#> GSM647581 2 0.000 0.987 0.000 1.000
#> GSM647594 2 0.000 0.987 0.000 1.000
#> GSM647599 1 0.000 0.973 1.000 0.000
#> GSM647600 2 0.000 0.987 0.000 1.000
#> GSM647601 2 0.000 0.987 0.000 1.000
#> GSM647603 2 0.000 0.987 0.000 1.000
#> GSM647610 2 0.000 0.987 0.000 1.000
#> GSM647611 2 0.000 0.987 0.000 1.000
#> GSM647612 2 0.000 0.987 0.000 1.000
#> GSM647614 2 0.000 0.987 0.000 1.000
#> GSM647618 2 0.000 0.987 0.000 1.000
#> GSM647629 2 0.000 0.987 0.000 1.000
#> GSM647535 2 0.000 0.987 0.000 1.000
#> GSM647563 2 0.000 0.987 0.000 1.000
#> GSM647542 2 0.000 0.987 0.000 1.000
#> GSM647543 2 0.000 0.987 0.000 1.000
#> GSM647548 2 0.000 0.987 0.000 1.000
#> GSM647554 2 0.000 0.987 0.000 1.000
#> GSM647555 2 0.000 0.987 0.000 1.000
#> GSM647559 2 0.000 0.987 0.000 1.000
#> GSM647562 2 0.000 0.987 0.000 1.000
#> GSM647564 1 0.000 0.973 1.000 0.000
#> GSM647571 2 0.000 0.987 0.000 1.000
#> GSM647584 2 0.000 0.987 0.000 1.000
#> GSM647585 1 0.000 0.973 1.000 0.000
#> GSM647586 2 0.000 0.987 0.000 1.000
#> GSM647587 2 0.000 0.987 0.000 1.000
#> GSM647588 2 0.000 0.987 0.000 1.000
#> GSM647596 2 0.000 0.987 0.000 1.000
#> GSM647602 1 0.000 0.973 1.000 0.000
#> GSM647609 2 0.000 0.987 0.000 1.000
#> GSM647620 2 0.000 0.987 0.000 1.000
#> GSM647627 2 0.000 0.987 0.000 1.000
#> GSM647628 2 0.000 0.987 0.000 1.000
#> GSM647533 1 0.000 0.973 1.000 0.000
#> GSM647536 1 0.000 0.973 1.000 0.000
#> GSM647537 1 0.000 0.973 1.000 0.000
#> GSM647606 1 0.000 0.973 1.000 0.000
#> GSM647621 1 0.000 0.973 1.000 0.000
#> GSM647626 1 0.000 0.973 1.000 0.000
#> GSM647538 1 0.000 0.973 1.000 0.000
#> GSM647575 1 0.000 0.973 1.000 0.000
#> GSM647590 1 0.000 0.973 1.000 0.000
#> GSM647605 1 0.000 0.973 1.000 0.000
#> GSM647607 1 0.000 0.973 1.000 0.000
#> GSM647608 1 0.000 0.973 1.000 0.000
#> GSM647622 1 0.000 0.973 1.000 0.000
#> GSM647623 1 0.000 0.973 1.000 0.000
#> GSM647624 1 0.000 0.973 1.000 0.000
#> GSM647625 1 0.000 0.973 1.000 0.000
#> GSM647534 1 0.000 0.973 1.000 0.000
#> GSM647539 1 0.886 0.573 0.696 0.304
#> GSM647566 1 0.000 0.973 1.000 0.000
#> GSM647589 1 0.000 0.973 1.000 0.000
#> GSM647604 1 0.000 0.973 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 1 0.6309 0.4738 0.500 0.000 0.500
#> GSM647574 3 0.6204 -0.4168 0.424 0.000 0.576
#> GSM647577 1 0.6309 0.4767 0.504 0.000 0.496
#> GSM647547 3 0.5098 -0.0224 0.248 0.000 0.752
#> GSM647552 2 0.6936 0.0147 0.460 0.524 0.016
#> GSM647553 1 0.6305 0.4902 0.516 0.000 0.484
#> GSM647565 3 0.1289 0.5287 0.000 0.032 0.968
#> GSM647545 2 0.6062 0.5257 0.000 0.616 0.384
#> GSM647549 2 0.6062 0.5257 0.000 0.616 0.384
#> GSM647550 2 0.6252 0.4160 0.000 0.556 0.444
#> GSM647560 3 0.6026 0.2075 0.000 0.376 0.624
#> GSM647617 3 0.6260 -0.4182 0.448 0.000 0.552
#> GSM647528 2 0.4750 0.7088 0.000 0.784 0.216
#> GSM647529 1 0.8203 0.1068 0.484 0.444 0.072
#> GSM647531 2 0.3482 0.7355 0.000 0.872 0.128
#> GSM647540 3 0.6192 0.1024 0.000 0.420 0.580
#> GSM647541 2 0.5650 0.6206 0.000 0.688 0.312
#> GSM647546 3 0.0475 0.5007 0.004 0.004 0.992
#> GSM647557 2 0.1289 0.7383 0.000 0.968 0.032
#> GSM647561 2 0.4750 0.7088 0.000 0.784 0.216
#> GSM647567 2 0.6054 0.4956 0.052 0.768 0.180
#> GSM647568 3 0.5216 0.4701 0.000 0.260 0.740
#> GSM647570 2 0.6274 0.3854 0.000 0.544 0.456
#> GSM647573 3 0.3619 0.3083 0.136 0.000 0.864
#> GSM647576 3 0.4555 0.5224 0.000 0.200 0.800
#> GSM647579 3 0.8518 0.3335 0.104 0.356 0.540
#> GSM647580 1 0.6309 0.4767 0.504 0.000 0.496
#> GSM647583 1 0.6309 0.4767 0.504 0.000 0.496
#> GSM647592 2 0.0000 0.7401 0.000 1.000 0.000
#> GSM647593 2 0.0000 0.7401 0.000 1.000 0.000
#> GSM647595 2 0.0000 0.7401 0.000 1.000 0.000
#> GSM647597 2 0.6205 0.2988 0.336 0.656 0.008
#> GSM647598 2 0.0000 0.7401 0.000 1.000 0.000
#> GSM647613 2 0.4974 0.6952 0.000 0.764 0.236
#> GSM647615 3 0.5254 0.4640 0.000 0.264 0.736
#> GSM647616 1 0.6309 0.4767 0.504 0.000 0.496
#> GSM647619 2 0.0000 0.7401 0.000 1.000 0.000
#> GSM647582 2 0.0000 0.7401 0.000 1.000 0.000
#> GSM647591 2 0.0000 0.7401 0.000 1.000 0.000
#> GSM647527 2 0.4750 0.7088 0.000 0.784 0.216
#> GSM647530 2 0.5560 0.6386 0.000 0.700 0.300
#> GSM647532 1 0.4062 0.6104 0.836 0.000 0.164
#> GSM647544 2 0.5529 0.6376 0.000 0.704 0.296
#> GSM647551 2 0.0237 0.7378 0.000 0.996 0.004
#> GSM647556 1 0.6305 0.4927 0.516 0.000 0.484
#> GSM647558 2 0.6267 0.3954 0.000 0.548 0.452
#> GSM647572 3 0.0592 0.5088 0.000 0.012 0.988
#> GSM647578 2 0.6299 0.2993 0.000 0.524 0.476
#> GSM647581 2 0.6079 0.5228 0.000 0.612 0.388
#> GSM647594 2 0.0000 0.7401 0.000 1.000 0.000
#> GSM647599 1 0.0000 0.7068 1.000 0.000 0.000
#> GSM647600 2 0.1170 0.7230 0.016 0.976 0.008
#> GSM647601 2 0.0000 0.7401 0.000 1.000 0.000
#> GSM647603 2 0.3752 0.6941 0.000 0.856 0.144
#> GSM647610 2 0.1753 0.7216 0.000 0.952 0.048
#> GSM647611 2 0.0424 0.7416 0.000 0.992 0.008
#> GSM647612 3 0.6267 -0.1201 0.000 0.452 0.548
#> GSM647614 3 0.5882 0.3005 0.000 0.348 0.652
#> GSM647618 2 0.0000 0.7401 0.000 1.000 0.000
#> GSM647629 2 0.2165 0.7281 0.000 0.936 0.064
#> GSM647535 2 0.4399 0.7200 0.000 0.812 0.188
#> GSM647563 2 0.5968 0.5564 0.000 0.636 0.364
#> GSM647542 3 0.5905 0.2914 0.000 0.352 0.648
#> GSM647543 3 0.5905 0.2914 0.000 0.352 0.648
#> GSM647548 3 0.3551 0.5626 0.000 0.132 0.868
#> GSM647554 2 0.1529 0.7311 0.000 0.960 0.040
#> GSM647555 2 0.6305 0.3110 0.000 0.516 0.484
#> GSM647559 2 0.4931 0.6981 0.000 0.768 0.232
#> GSM647562 2 0.5529 0.6376 0.000 0.704 0.296
#> GSM647564 3 0.6095 -0.3168 0.392 0.000 0.608
#> GSM647571 3 0.5363 0.4483 0.000 0.276 0.724
#> GSM647584 2 0.0000 0.7401 0.000 1.000 0.000
#> GSM647585 1 0.5988 0.5810 0.632 0.000 0.368
#> GSM647586 2 0.3879 0.7313 0.000 0.848 0.152
#> GSM647587 2 0.4750 0.7088 0.000 0.784 0.216
#> GSM647588 2 0.4974 0.6961 0.000 0.764 0.236
#> GSM647596 2 0.4750 0.7088 0.000 0.784 0.216
#> GSM647602 1 0.6309 0.4767 0.504 0.000 0.496
#> GSM647609 2 0.0000 0.7401 0.000 1.000 0.000
#> GSM647620 2 0.0424 0.7416 0.000 0.992 0.008
#> GSM647627 2 0.3879 0.7313 0.000 0.848 0.152
#> GSM647628 2 0.6295 0.3420 0.000 0.528 0.472
#> GSM647533 1 0.0000 0.7068 1.000 0.000 0.000
#> GSM647536 1 0.4068 0.6233 0.864 0.016 0.120
#> GSM647537 1 0.0000 0.7068 1.000 0.000 0.000
#> GSM647606 1 0.0000 0.7068 1.000 0.000 0.000
#> GSM647621 1 0.6140 0.5503 0.596 0.000 0.404
#> GSM647626 1 0.5363 0.6316 0.724 0.000 0.276
#> GSM647538 1 0.0000 0.7068 1.000 0.000 0.000
#> GSM647575 1 0.6280 0.4584 0.540 0.000 0.460
#> GSM647590 1 0.0747 0.7022 0.984 0.000 0.016
#> GSM647605 1 0.0000 0.7068 1.000 0.000 0.000
#> GSM647607 1 0.6260 0.4777 0.552 0.000 0.448
#> GSM647608 1 0.5905 0.5856 0.648 0.000 0.352
#> GSM647622 1 0.0000 0.7068 1.000 0.000 0.000
#> GSM647623 1 0.0000 0.7068 1.000 0.000 0.000
#> GSM647624 1 0.0747 0.7022 0.984 0.000 0.016
#> GSM647625 1 0.0000 0.7068 1.000 0.000 0.000
#> GSM647534 1 0.5588 0.4296 0.720 0.276 0.004
#> GSM647539 3 0.5404 0.2679 0.256 0.004 0.740
#> GSM647566 1 0.0237 0.7051 0.996 0.000 0.004
#> GSM647589 1 0.6299 0.4661 0.524 0.000 0.476
#> GSM647604 1 0.0000 0.7068 1.000 0.000 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 3 0.3494 0.76527 0.172 0.004 0.824 0.000
#> GSM647574 3 0.3077 0.73023 0.068 0.004 0.892 0.036
#> GSM647577 3 0.3311 0.76640 0.172 0.000 0.828 0.000
#> GSM647547 3 0.4888 0.62444 0.004 0.072 0.784 0.140
#> GSM647552 2 0.6281 0.49055 0.184 0.704 0.080 0.032
#> GSM647553 3 0.3569 0.75219 0.196 0.000 0.804 0.000
#> GSM647565 4 0.5314 0.47704 0.000 0.084 0.176 0.740
#> GSM647545 4 0.3217 0.67143 0.000 0.128 0.012 0.860
#> GSM647549 4 0.3088 0.67024 0.000 0.128 0.008 0.864
#> GSM647550 4 0.2984 0.68308 0.000 0.084 0.028 0.888
#> GSM647560 4 0.5496 0.44698 0.000 0.036 0.312 0.652
#> GSM647617 3 0.3450 0.76534 0.156 0.000 0.836 0.008
#> GSM647528 4 0.5112 0.19761 0.000 0.436 0.004 0.560
#> GSM647529 2 0.7594 -0.37057 0.436 0.440 0.092 0.032
#> GSM647531 2 0.5588 0.35048 0.004 0.600 0.020 0.376
#> GSM647540 3 0.6337 -0.02098 0.000 0.060 0.476 0.464
#> GSM647541 4 0.4059 0.60425 0.000 0.200 0.012 0.788
#> GSM647546 3 0.2589 0.70693 0.000 0.000 0.884 0.116
#> GSM647557 2 0.3730 0.73064 0.004 0.836 0.016 0.144
#> GSM647561 4 0.5060 0.26221 0.000 0.412 0.004 0.584
#> GSM647567 2 0.6373 0.50909 0.012 0.656 0.248 0.084
#> GSM647568 4 0.2773 0.65757 0.000 0.004 0.116 0.880
#> GSM647570 4 0.1706 0.68644 0.000 0.036 0.016 0.948
#> GSM647573 3 0.7152 0.42501 0.024 0.088 0.564 0.324
#> GSM647576 4 0.5088 0.21839 0.000 0.004 0.424 0.572
#> GSM647579 3 0.6557 0.60163 0.020 0.140 0.680 0.160
#> GSM647580 3 0.3311 0.76640 0.172 0.000 0.828 0.000
#> GSM647583 3 0.3311 0.76640 0.172 0.000 0.828 0.000
#> GSM647592 2 0.2831 0.77825 0.000 0.876 0.004 0.120
#> GSM647593 2 0.2760 0.77963 0.000 0.872 0.000 0.128
#> GSM647595 2 0.2814 0.77933 0.000 0.868 0.000 0.132
#> GSM647597 2 0.5096 0.57835 0.168 0.772 0.020 0.040
#> GSM647598 2 0.4188 0.70385 0.000 0.752 0.004 0.244
#> GSM647613 4 0.4720 0.46267 0.000 0.324 0.004 0.672
#> GSM647615 4 0.4677 0.56918 0.000 0.040 0.192 0.768
#> GSM647616 3 0.3311 0.76640 0.172 0.000 0.828 0.000
#> GSM647619 2 0.2704 0.77924 0.000 0.876 0.000 0.124
#> GSM647582 2 0.3335 0.77769 0.000 0.856 0.016 0.128
#> GSM647591 2 0.2760 0.77963 0.000 0.872 0.000 0.128
#> GSM647527 4 0.5112 0.19761 0.000 0.436 0.004 0.560
#> GSM647530 4 0.5290 0.55609 0.004 0.292 0.024 0.680
#> GSM647532 1 0.6666 0.66088 0.696 0.104 0.148 0.052
#> GSM647544 4 0.4252 0.56910 0.000 0.252 0.004 0.744
#> GSM647551 2 0.3219 0.77122 0.000 0.868 0.020 0.112
#> GSM647556 3 0.3895 0.75126 0.184 0.012 0.804 0.000
#> GSM647558 4 0.2376 0.68545 0.000 0.068 0.016 0.916
#> GSM647572 3 0.4164 0.61685 0.000 0.000 0.736 0.264
#> GSM647578 4 0.6723 0.52341 0.000 0.196 0.188 0.616
#> GSM647581 4 0.3402 0.66604 0.000 0.164 0.004 0.832
#> GSM647594 2 0.3668 0.75853 0.000 0.808 0.004 0.188
#> GSM647599 1 0.1807 0.82583 0.940 0.008 0.052 0.000
#> GSM647600 2 0.3996 0.74677 0.000 0.836 0.060 0.104
#> GSM647601 2 0.3751 0.75401 0.000 0.800 0.004 0.196
#> GSM647603 2 0.6571 0.51815 0.000 0.612 0.124 0.264
#> GSM647610 2 0.3708 0.75279 0.000 0.832 0.020 0.148
#> GSM647611 2 0.3982 0.73322 0.000 0.776 0.004 0.220
#> GSM647612 4 0.1913 0.68390 0.000 0.020 0.040 0.940
#> GSM647614 4 0.2530 0.66170 0.000 0.000 0.112 0.888
#> GSM647618 2 0.3626 0.75918 0.000 0.812 0.004 0.184
#> GSM647629 2 0.4576 0.69239 0.000 0.728 0.012 0.260
#> GSM647535 4 0.5119 0.14494 0.000 0.440 0.004 0.556
#> GSM647563 4 0.2999 0.66322 0.000 0.132 0.004 0.864
#> GSM647542 4 0.2714 0.66327 0.000 0.004 0.112 0.884
#> GSM647543 4 0.2714 0.66327 0.000 0.004 0.112 0.884
#> GSM647548 4 0.5653 0.46948 0.000 0.096 0.192 0.712
#> GSM647554 2 0.3790 0.74683 0.000 0.820 0.016 0.164
#> GSM647555 4 0.2644 0.68679 0.000 0.060 0.032 0.908
#> GSM647559 4 0.4761 0.45635 0.000 0.332 0.004 0.664
#> GSM647562 4 0.4283 0.56542 0.000 0.256 0.004 0.740
#> GSM647564 3 0.3216 0.74768 0.076 0.000 0.880 0.044
#> GSM647571 4 0.2714 0.66095 0.000 0.004 0.112 0.884
#> GSM647584 2 0.2814 0.77933 0.000 0.868 0.000 0.132
#> GSM647585 3 0.4059 0.74748 0.200 0.012 0.788 0.000
#> GSM647586 2 0.5168 -0.00634 0.000 0.500 0.004 0.496
#> GSM647587 4 0.5147 0.12726 0.000 0.460 0.004 0.536
#> GSM647588 4 0.4761 0.41763 0.000 0.332 0.004 0.664
#> GSM647596 4 0.5050 0.27001 0.000 0.408 0.004 0.588
#> GSM647602 3 0.3494 0.76599 0.172 0.004 0.824 0.000
#> GSM647609 2 0.3751 0.75401 0.000 0.800 0.004 0.196
#> GSM647620 2 0.4343 0.67941 0.000 0.732 0.004 0.264
#> GSM647627 2 0.5168 -0.00634 0.000 0.500 0.004 0.496
#> GSM647628 4 0.1733 0.68485 0.000 0.028 0.024 0.948
#> GSM647533 1 0.0469 0.85798 0.988 0.000 0.012 0.000
#> GSM647536 1 0.6351 0.67805 0.716 0.112 0.132 0.040
#> GSM647537 1 0.0469 0.85798 0.988 0.000 0.012 0.000
#> GSM647606 1 0.0336 0.85862 0.992 0.000 0.008 0.000
#> GSM647621 3 0.7410 0.35930 0.308 0.052 0.568 0.072
#> GSM647626 3 0.4509 0.66196 0.288 0.004 0.708 0.000
#> GSM647538 1 0.0336 0.85854 0.992 0.000 0.008 0.000
#> GSM647575 1 0.8919 0.10243 0.392 0.076 0.356 0.176
#> GSM647590 1 0.1488 0.84646 0.956 0.012 0.032 0.000
#> GSM647605 1 0.0000 0.85814 1.000 0.000 0.000 0.000
#> GSM647607 1 0.8584 0.33030 0.492 0.076 0.276 0.156
#> GSM647608 3 0.7336 0.29259 0.336 0.052 0.552 0.060
#> GSM647622 1 0.0657 0.85757 0.984 0.004 0.012 0.000
#> GSM647623 1 0.0469 0.85798 0.988 0.000 0.012 0.000
#> GSM647624 1 0.1388 0.84813 0.960 0.012 0.028 0.000
#> GSM647625 1 0.0469 0.85798 0.988 0.000 0.012 0.000
#> GSM647534 1 0.5143 0.59559 0.708 0.256 0.036 0.000
#> GSM647539 4 0.8564 0.20909 0.196 0.108 0.160 0.536
#> GSM647566 1 0.1411 0.85138 0.960 0.020 0.020 0.000
#> GSM647589 3 0.7624 0.42032 0.248 0.052 0.588 0.112
#> GSM647604 1 0.0000 0.85814 1.000 0.000 0.000 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.1864 0.8351 0.068 0.000 0.924 0.004 0.004
#> GSM647574 3 0.2077 0.7792 0.008 0.000 0.908 0.084 0.000
#> GSM647577 3 0.1704 0.8371 0.068 0.000 0.928 0.004 0.000
#> GSM647547 4 0.4339 0.5910 0.000 0.020 0.296 0.684 0.000
#> GSM647552 5 0.5104 0.6106 0.028 0.004 0.036 0.224 0.708
#> GSM647553 3 0.1704 0.8371 0.068 0.000 0.928 0.004 0.000
#> GSM647565 4 0.5262 0.3264 0.000 0.460 0.020 0.504 0.016
#> GSM647545 2 0.2625 0.6933 0.000 0.900 0.016 0.028 0.056
#> GSM647549 2 0.2243 0.6933 0.000 0.916 0.012 0.016 0.056
#> GSM647550 2 0.2511 0.6721 0.000 0.892 0.028 0.080 0.000
#> GSM647560 2 0.5939 0.3443 0.000 0.608 0.252 0.132 0.008
#> GSM647617 3 0.1357 0.8334 0.048 0.000 0.948 0.004 0.000
#> GSM647528 2 0.5370 0.4969 0.000 0.584 0.000 0.068 0.348
#> GSM647529 4 0.6049 0.5513 0.148 0.004 0.016 0.640 0.192
#> GSM647531 2 0.6385 0.2867 0.000 0.468 0.016 0.108 0.408
#> GSM647540 3 0.6397 0.4713 0.000 0.248 0.588 0.136 0.028
#> GSM647541 2 0.3880 0.6578 0.000 0.828 0.024 0.096 0.052
#> GSM647546 3 0.2473 0.7611 0.000 0.072 0.896 0.032 0.000
#> GSM647557 5 0.4060 0.7305 0.000 0.068 0.016 0.104 0.812
#> GSM647561 2 0.5002 0.5514 0.000 0.636 0.000 0.052 0.312
#> GSM647567 5 0.6516 0.5301 0.004 0.032 0.168 0.188 0.608
#> GSM647568 2 0.2754 0.6344 0.000 0.880 0.040 0.080 0.000
#> GSM647570 2 0.1901 0.6708 0.000 0.928 0.012 0.056 0.004
#> GSM647573 4 0.4670 0.6643 0.000 0.200 0.076 0.724 0.000
#> GSM647576 3 0.6232 0.3141 0.000 0.380 0.488 0.128 0.004
#> GSM647579 3 0.6016 0.5804 0.000 0.112 0.680 0.136 0.072
#> GSM647580 3 0.1704 0.8371 0.068 0.000 0.928 0.004 0.000
#> GSM647583 3 0.1704 0.8371 0.068 0.000 0.928 0.004 0.000
#> GSM647592 5 0.2227 0.7737 0.004 0.048 0.000 0.032 0.916
#> GSM647593 5 0.2067 0.7737 0.000 0.048 0.000 0.032 0.920
#> GSM647595 5 0.1430 0.7682 0.000 0.052 0.000 0.004 0.944
#> GSM647597 5 0.4466 0.6682 0.080 0.008 0.016 0.100 0.796
#> GSM647598 5 0.5288 -0.0122 0.000 0.404 0.000 0.052 0.544
#> GSM647613 2 0.4730 0.6017 0.000 0.688 0.000 0.052 0.260
#> GSM647615 2 0.4832 0.4757 0.000 0.740 0.168 0.080 0.012
#> GSM647616 3 0.1704 0.8371 0.068 0.000 0.928 0.004 0.000
#> GSM647619 5 0.2067 0.7736 0.000 0.048 0.000 0.032 0.920
#> GSM647582 5 0.3030 0.7707 0.000 0.040 0.004 0.088 0.868
#> GSM647591 5 0.1444 0.7720 0.000 0.040 0.000 0.012 0.948
#> GSM647527 2 0.5370 0.4969 0.000 0.584 0.000 0.068 0.348
#> GSM647530 2 0.5757 0.5806 0.000 0.640 0.008 0.136 0.216
#> GSM647532 4 0.5078 0.5970 0.272 0.004 0.016 0.676 0.032
#> GSM647544 2 0.4930 0.6008 0.000 0.684 0.000 0.072 0.244
#> GSM647551 5 0.3911 0.7545 0.004 0.036 0.020 0.116 0.824
#> GSM647556 3 0.1717 0.8302 0.052 0.000 0.936 0.008 0.004
#> GSM647558 2 0.1412 0.6803 0.000 0.952 0.008 0.036 0.004
#> GSM647572 3 0.5403 0.5045 0.000 0.248 0.644 0.108 0.000
#> GSM647578 2 0.6646 0.4740 0.000 0.604 0.200 0.132 0.064
#> GSM647581 2 0.3239 0.6829 0.000 0.852 0.000 0.068 0.080
#> GSM647594 5 0.3365 0.6988 0.000 0.120 0.000 0.044 0.836
#> GSM647599 1 0.1934 0.8831 0.928 0.000 0.016 0.052 0.004
#> GSM647600 5 0.4188 0.7469 0.004 0.036 0.024 0.132 0.804
#> GSM647601 5 0.4098 0.6564 0.000 0.156 0.000 0.064 0.780
#> GSM647603 5 0.7181 0.5069 0.000 0.220 0.088 0.144 0.548
#> GSM647610 5 0.4710 0.7409 0.004 0.064 0.020 0.144 0.768
#> GSM647611 5 0.4495 0.5953 0.000 0.200 0.000 0.064 0.736
#> GSM647612 2 0.2504 0.6470 0.000 0.896 0.040 0.064 0.000
#> GSM647614 2 0.2754 0.6344 0.000 0.880 0.040 0.080 0.000
#> GSM647618 5 0.3593 0.6923 0.000 0.116 0.000 0.060 0.824
#> GSM647629 5 0.5460 0.6880 0.000 0.140 0.028 0.124 0.708
#> GSM647535 2 0.5375 0.5206 0.000 0.604 0.000 0.076 0.320
#> GSM647563 2 0.3731 0.6679 0.000 0.816 0.000 0.072 0.112
#> GSM647542 2 0.2754 0.6344 0.000 0.880 0.040 0.080 0.000
#> GSM647543 2 0.2754 0.6344 0.000 0.880 0.040 0.080 0.000
#> GSM647548 4 0.4624 0.6067 0.000 0.296 0.012 0.676 0.016
#> GSM647554 5 0.4941 0.7263 0.000 0.076 0.024 0.156 0.744
#> GSM647555 2 0.2359 0.6581 0.000 0.904 0.036 0.060 0.000
#> GSM647559 2 0.5200 0.5552 0.000 0.628 0.000 0.068 0.304
#> GSM647562 2 0.4877 0.6064 0.000 0.692 0.000 0.072 0.236
#> GSM647564 3 0.0609 0.8071 0.000 0.020 0.980 0.000 0.000
#> GSM647571 2 0.2983 0.6373 0.000 0.864 0.040 0.096 0.000
#> GSM647584 5 0.1430 0.7682 0.000 0.052 0.000 0.004 0.944
#> GSM647585 3 0.1990 0.8340 0.068 0.000 0.920 0.008 0.004
#> GSM647586 2 0.5423 0.4262 0.000 0.548 0.000 0.064 0.388
#> GSM647587 2 0.5395 0.4852 0.000 0.576 0.000 0.068 0.356
#> GSM647588 2 0.5261 0.6137 0.000 0.696 0.012 0.092 0.200
#> GSM647596 2 0.5069 0.5366 0.000 0.620 0.000 0.052 0.328
#> GSM647602 3 0.1704 0.8371 0.068 0.000 0.928 0.004 0.000
#> GSM647609 5 0.4098 0.6564 0.000 0.156 0.000 0.064 0.780
#> GSM647620 5 0.5555 -0.1995 0.000 0.452 0.000 0.068 0.480
#> GSM647627 2 0.5423 0.4262 0.000 0.548 0.000 0.064 0.388
#> GSM647628 2 0.2208 0.6583 0.000 0.908 0.020 0.072 0.000
#> GSM647533 1 0.0566 0.9230 0.984 0.000 0.012 0.004 0.000
#> GSM647536 4 0.5261 0.5521 0.308 0.004 0.016 0.640 0.032
#> GSM647537 1 0.0566 0.9230 0.984 0.000 0.012 0.004 0.000
#> GSM647606 1 0.0404 0.9232 0.988 0.000 0.012 0.000 0.000
#> GSM647621 4 0.5857 0.6752 0.160 0.000 0.216 0.620 0.004
#> GSM647626 3 0.3047 0.7493 0.160 0.000 0.832 0.004 0.004
#> GSM647538 1 0.0867 0.9202 0.976 0.000 0.008 0.008 0.008
#> GSM647575 4 0.5638 0.7014 0.192 0.044 0.076 0.688 0.000
#> GSM647590 1 0.1492 0.8974 0.948 0.000 0.004 0.040 0.008
#> GSM647605 1 0.0162 0.9207 0.996 0.000 0.000 0.004 0.000
#> GSM647607 4 0.5658 0.6743 0.232 0.040 0.052 0.672 0.004
#> GSM647608 4 0.5715 0.6735 0.152 0.000 0.228 0.620 0.000
#> GSM647622 1 0.0566 0.9225 0.984 0.000 0.012 0.004 0.000
#> GSM647623 1 0.0566 0.9225 0.984 0.000 0.012 0.004 0.000
#> GSM647624 1 0.1124 0.9024 0.960 0.000 0.004 0.036 0.000
#> GSM647625 1 0.0404 0.9232 0.988 0.000 0.012 0.000 0.000
#> GSM647534 1 0.6381 0.2424 0.504 0.000 0.028 0.088 0.380
#> GSM647539 4 0.4950 0.6943 0.088 0.164 0.004 0.736 0.008
#> GSM647566 1 0.2703 0.8562 0.896 0.000 0.024 0.060 0.020
#> GSM647589 4 0.5979 0.6812 0.124 0.020 0.224 0.632 0.000
#> GSM647604 1 0.0162 0.9207 0.996 0.000 0.000 0.004 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.0363 0.9371 0.012 0.000 0.988 0.000 0.000 0.000
#> GSM647574 3 0.1364 0.9038 0.000 0.004 0.944 0.048 0.000 0.004
#> GSM647577 3 0.0653 0.9371 0.012 0.000 0.980 0.004 0.000 0.004
#> GSM647547 4 0.2809 0.8045 0.000 0.020 0.128 0.848 0.000 0.004
#> GSM647552 6 0.3557 0.6476 0.000 0.000 0.004 0.056 0.140 0.800
#> GSM647553 3 0.0881 0.9361 0.012 0.000 0.972 0.008 0.000 0.008
#> GSM647565 2 0.4471 0.1586 0.000 0.556 0.004 0.420 0.004 0.016
#> GSM647545 2 0.3149 0.6366 0.000 0.836 0.000 0.024 0.124 0.016
#> GSM647549 2 0.3627 0.5906 0.000 0.796 0.000 0.028 0.156 0.020
#> GSM647550 2 0.3876 0.6905 0.000 0.804 0.000 0.032 0.072 0.092
#> GSM647560 2 0.4277 0.6765 0.000 0.776 0.076 0.016 0.012 0.120
#> GSM647617 3 0.0291 0.9349 0.004 0.004 0.992 0.000 0.000 0.000
#> GSM647528 5 0.3595 0.5532 0.000 0.288 0.000 0.008 0.704 0.000
#> GSM647529 4 0.4625 0.6554 0.028 0.000 0.008 0.656 0.012 0.296
#> GSM647531 5 0.7311 0.3117 0.004 0.216 0.008 0.072 0.396 0.304
#> GSM647540 2 0.6652 0.2534 0.000 0.448 0.312 0.016 0.020 0.204
#> GSM647541 2 0.4473 0.6404 0.000 0.748 0.000 0.024 0.120 0.108
#> GSM647546 3 0.2706 0.8060 0.000 0.124 0.852 0.024 0.000 0.000
#> GSM647557 6 0.5830 0.5419 0.004 0.076 0.008 0.068 0.200 0.644
#> GSM647561 5 0.4498 0.5162 0.000 0.320 0.000 0.024 0.640 0.016
#> GSM647567 6 0.4574 0.6018 0.004 0.048 0.076 0.016 0.076 0.780
#> GSM647568 2 0.1007 0.7397 0.000 0.968 0.004 0.016 0.004 0.008
#> GSM647570 2 0.2358 0.6687 0.000 0.876 0.000 0.016 0.108 0.000
#> GSM647573 4 0.2629 0.8072 0.000 0.092 0.040 0.868 0.000 0.000
#> GSM647576 2 0.5540 0.5101 0.000 0.624 0.216 0.028 0.000 0.132
#> GSM647579 3 0.5928 0.3879 0.000 0.208 0.556 0.020 0.000 0.216
#> GSM647580 3 0.0653 0.9371 0.012 0.000 0.980 0.004 0.000 0.004
#> GSM647583 3 0.0653 0.9371 0.012 0.000 0.980 0.004 0.000 0.004
#> GSM647592 5 0.4117 -0.4767 0.004 0.000 0.000 0.004 0.528 0.464
#> GSM647593 5 0.3989 -0.4780 0.004 0.000 0.000 0.000 0.528 0.468
#> GSM647595 5 0.4098 -0.4502 0.004 0.000 0.000 0.004 0.548 0.444
#> GSM647597 6 0.4973 0.6059 0.016 0.000 0.004 0.064 0.260 0.656
#> GSM647598 5 0.2152 0.5142 0.000 0.068 0.000 0.004 0.904 0.024
#> GSM647613 5 0.4528 0.4354 0.000 0.380 0.000 0.020 0.588 0.012
#> GSM647615 2 0.2867 0.7164 0.000 0.872 0.040 0.024 0.000 0.064
#> GSM647616 3 0.0653 0.9371 0.012 0.000 0.980 0.004 0.000 0.004
#> GSM647619 5 0.3979 -0.4700 0.004 0.000 0.000 0.000 0.540 0.456
#> GSM647582 6 0.3817 0.5915 0.000 0.000 0.000 0.000 0.432 0.568
#> GSM647591 5 0.4120 -0.4808 0.004 0.000 0.000 0.004 0.524 0.468
#> GSM647527 5 0.3595 0.5532 0.000 0.288 0.000 0.008 0.704 0.000
#> GSM647530 5 0.7368 0.3594 0.004 0.216 0.008 0.120 0.460 0.192
#> GSM647532 4 0.4472 0.7240 0.064 0.000 0.008 0.700 0.000 0.228
#> GSM647544 5 0.4734 0.4235 0.000 0.372 0.000 0.028 0.584 0.016
#> GSM647551 6 0.3706 0.6415 0.000 0.000 0.000 0.000 0.380 0.620
#> GSM647556 3 0.0870 0.9357 0.012 0.000 0.972 0.004 0.000 0.012
#> GSM647558 2 0.2771 0.6539 0.000 0.852 0.000 0.032 0.116 0.000
#> GSM647572 2 0.5677 0.3166 0.000 0.544 0.336 0.028 0.000 0.092
#> GSM647578 2 0.6494 0.5410 0.000 0.584 0.080 0.032 0.080 0.224
#> GSM647581 2 0.5555 -0.0982 0.000 0.512 0.004 0.052 0.400 0.032
#> GSM647594 5 0.2913 0.2566 0.004 0.000 0.000 0.004 0.812 0.180
#> GSM647599 1 0.2964 0.8681 0.856 0.000 0.020 0.100 0.000 0.024
#> GSM647600 6 0.3714 0.6720 0.000 0.004 0.000 0.000 0.340 0.656
#> GSM647601 5 0.0935 0.4369 0.000 0.004 0.000 0.000 0.964 0.032
#> GSM647603 2 0.7054 -0.0104 0.000 0.404 0.028 0.024 0.276 0.268
#> GSM647610 6 0.5234 0.6373 0.004 0.032 0.004 0.024 0.380 0.556
#> GSM647611 5 0.1485 0.4640 0.000 0.024 0.000 0.004 0.944 0.028
#> GSM647612 2 0.0810 0.7391 0.000 0.976 0.004 0.004 0.008 0.008
#> GSM647614 2 0.1026 0.7398 0.000 0.968 0.004 0.012 0.008 0.008
#> GSM647618 5 0.2146 0.3496 0.000 0.000 0.000 0.004 0.880 0.116
#> GSM647629 6 0.5693 0.5991 0.000 0.116 0.000 0.016 0.340 0.528
#> GSM647535 5 0.3834 0.5541 0.000 0.268 0.000 0.000 0.708 0.024
#> GSM647563 5 0.4405 0.2267 0.000 0.472 0.000 0.024 0.504 0.000
#> GSM647542 2 0.1026 0.7398 0.000 0.968 0.004 0.012 0.008 0.008
#> GSM647543 2 0.0982 0.7385 0.000 0.968 0.004 0.020 0.004 0.004
#> GSM647548 4 0.3476 0.6270 0.000 0.260 0.000 0.732 0.004 0.004
#> GSM647554 6 0.4827 0.6518 0.000 0.048 0.000 0.012 0.328 0.612
#> GSM647555 2 0.0810 0.7390 0.000 0.976 0.004 0.004 0.008 0.008
#> GSM647559 5 0.4380 0.5180 0.000 0.312 0.000 0.024 0.652 0.012
#> GSM647562 5 0.4680 0.4101 0.000 0.384 0.000 0.028 0.576 0.012
#> GSM647564 3 0.0547 0.9231 0.000 0.020 0.980 0.000 0.000 0.000
#> GSM647571 2 0.2026 0.7345 0.000 0.924 0.004 0.020 0.028 0.024
#> GSM647584 5 0.3961 -0.4450 0.000 0.000 0.000 0.004 0.556 0.440
#> GSM647585 3 0.0767 0.9364 0.012 0.000 0.976 0.004 0.000 0.008
#> GSM647586 5 0.2527 0.5770 0.000 0.168 0.000 0.000 0.832 0.000
#> GSM647587 5 0.3905 0.5641 0.000 0.264 0.000 0.012 0.712 0.012
#> GSM647588 5 0.5787 0.2810 0.000 0.400 0.000 0.044 0.488 0.068
#> GSM647596 5 0.4466 0.5347 0.000 0.312 0.000 0.016 0.648 0.024
#> GSM647602 3 0.0653 0.9371 0.012 0.000 0.980 0.004 0.000 0.004
#> GSM647609 5 0.1152 0.4222 0.000 0.004 0.000 0.000 0.952 0.044
#> GSM647620 5 0.2165 0.5428 0.000 0.108 0.000 0.000 0.884 0.008
#> GSM647627 5 0.2562 0.5783 0.000 0.172 0.000 0.000 0.828 0.000
#> GSM647628 2 0.2060 0.6909 0.000 0.900 0.000 0.016 0.084 0.000
#> GSM647533 1 0.0717 0.9557 0.976 0.000 0.016 0.000 0.000 0.008
#> GSM647536 4 0.4808 0.7093 0.072 0.000 0.008 0.672 0.004 0.244
#> GSM647537 1 0.0717 0.9557 0.976 0.000 0.016 0.000 0.000 0.008
#> GSM647606 1 0.0622 0.9558 0.980 0.000 0.012 0.000 0.000 0.008
#> GSM647621 4 0.3726 0.8194 0.072 0.000 0.092 0.812 0.000 0.024
#> GSM647626 3 0.1649 0.9062 0.040 0.000 0.936 0.008 0.000 0.016
#> GSM647538 1 0.1390 0.9444 0.948 0.000 0.016 0.004 0.000 0.032
#> GSM647575 4 0.2819 0.8237 0.104 0.008 0.016 0.864 0.000 0.008
#> GSM647590 1 0.2022 0.9255 0.916 0.000 0.008 0.052 0.000 0.024
#> GSM647605 1 0.0405 0.9536 0.988 0.000 0.004 0.000 0.000 0.008
#> GSM647607 4 0.3001 0.8135 0.120 0.008 0.016 0.848 0.000 0.008
#> GSM647608 4 0.3477 0.8221 0.092 0.000 0.080 0.820 0.000 0.008
#> GSM647622 1 0.0964 0.9533 0.968 0.000 0.016 0.004 0.000 0.012
#> GSM647623 1 0.0964 0.9533 0.968 0.000 0.016 0.004 0.000 0.012
#> GSM647624 1 0.1666 0.9374 0.936 0.000 0.008 0.036 0.000 0.020
#> GSM647625 1 0.0603 0.9556 0.980 0.000 0.016 0.000 0.000 0.004
#> GSM647534 6 0.5336 0.0405 0.444 0.000 0.000 0.024 0.052 0.480
#> GSM647539 4 0.2945 0.8239 0.064 0.040 0.000 0.868 0.000 0.028
#> GSM647566 1 0.3693 0.8353 0.800 0.000 0.016 0.048 0.000 0.136
#> GSM647589 4 0.3501 0.8246 0.060 0.008 0.096 0.828 0.000 0.008
#> GSM647604 1 0.0405 0.9536 0.988 0.000 0.004 0.000 0.000 0.008
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n disease.state(p) development.stage(p) other(p) k
#> MAD:kmeans 102 3.30e-10 0.05082 0.956 2
#> MAD:kmeans 65 6.95e-12 0.02176 0.144 3
#> MAD:kmeans 77 6.35e-13 0.00277 0.163 4
#> MAD:kmeans 88 1.97e-12 0.01929 0.117 5
#> MAD:kmeans 78 3.38e-10 0.00873 0.135 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["MAD", "skmeans"]
# you can also extract it by
# res = res_list["MAD:skmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'MAD' method.
#> Subgroups are detected by 'skmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 1.000 0.975 0.989 0.499 0.501 0.501
#> 3 3 0.569 0.734 0.846 0.315 0.781 0.584
#> 4 4 0.797 0.747 0.893 0.140 0.832 0.554
#> 5 5 0.703 0.715 0.822 0.065 0.859 0.522
#> 6 6 0.737 0.698 0.810 0.039 0.955 0.785
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
#> GSM647569 1 0.0000 0.985 1.000 0.000
#> GSM647574 1 0.0000 0.985 1.000 0.000
#> GSM647577 1 0.0000 0.985 1.000 0.000
#> GSM647547 1 0.0000 0.985 1.000 0.000
#> GSM647552 1 0.0000 0.985 1.000 0.000
#> GSM647553 1 0.0000 0.985 1.000 0.000
#> GSM647565 1 0.0672 0.978 0.992 0.008
#> GSM647545 2 0.0000 0.992 0.000 1.000
#> GSM647549 2 0.0000 0.992 0.000 1.000
#> GSM647550 2 0.0000 0.992 0.000 1.000
#> GSM647560 2 0.0000 0.992 0.000 1.000
#> GSM647617 1 0.0000 0.985 1.000 0.000
#> GSM647528 2 0.0000 0.992 0.000 1.000
#> GSM647529 1 0.0000 0.985 1.000 0.000
#> GSM647531 2 0.0000 0.992 0.000 1.000
#> GSM647540 2 0.0000 0.992 0.000 1.000
#> GSM647541 2 0.0000 0.992 0.000 1.000
#> GSM647546 1 0.0000 0.985 1.000 0.000
#> GSM647557 2 0.0000 0.992 0.000 1.000
#> GSM647561 2 0.0000 0.992 0.000 1.000
#> GSM647567 1 0.2603 0.945 0.956 0.044
#> GSM647568 2 0.0000 0.992 0.000 1.000
#> GSM647570 2 0.0000 0.992 0.000 1.000
#> GSM647573 1 0.0000 0.985 1.000 0.000
#> GSM647576 2 0.9552 0.375 0.376 0.624
#> GSM647579 1 0.7219 0.756 0.800 0.200
#> GSM647580 1 0.0000 0.985 1.000 0.000
#> GSM647583 1 0.0000 0.985 1.000 0.000
#> GSM647592 2 0.0000 0.992 0.000 1.000
#> GSM647593 2 0.0000 0.992 0.000 1.000
#> GSM647595 2 0.0000 0.992 0.000 1.000
#> GSM647597 2 0.0672 0.985 0.008 0.992
#> GSM647598 2 0.0000 0.992 0.000 1.000
#> GSM647613 2 0.0000 0.992 0.000 1.000
#> GSM647615 1 0.8763 0.591 0.704 0.296
#> GSM647616 1 0.0000 0.985 1.000 0.000
#> GSM647619 2 0.0000 0.992 0.000 1.000
#> GSM647582 2 0.0000 0.992 0.000 1.000
#> GSM647591 2 0.0000 0.992 0.000 1.000
#> GSM647527 2 0.0000 0.992 0.000 1.000
#> GSM647530 2 0.0000 0.992 0.000 1.000
#> GSM647532 1 0.0000 0.985 1.000 0.000
#> GSM647544 2 0.0000 0.992 0.000 1.000
#> GSM647551 2 0.0000 0.992 0.000 1.000
#> GSM647556 1 0.0000 0.985 1.000 0.000
#> GSM647558 2 0.0000 0.992 0.000 1.000
#> GSM647572 1 0.0000 0.985 1.000 0.000
#> GSM647578 2 0.1633 0.969 0.024 0.976
#> GSM647581 2 0.0000 0.992 0.000 1.000
#> GSM647594 2 0.0000 0.992 0.000 1.000
#> GSM647599 1 0.0000 0.985 1.000 0.000
#> GSM647600 2 0.0000 0.992 0.000 1.000
#> GSM647601 2 0.0000 0.992 0.000 1.000
#> GSM647603 2 0.0000 0.992 0.000 1.000
#> GSM647610 2 0.0938 0.981 0.012 0.988
#> GSM647611 2 0.0000 0.992 0.000 1.000
#> GSM647612 2 0.0000 0.992 0.000 1.000
#> GSM647614 2 0.0000 0.992 0.000 1.000
#> GSM647618 2 0.0000 0.992 0.000 1.000
#> GSM647629 2 0.0000 0.992 0.000 1.000
#> GSM647535 2 0.0000 0.992 0.000 1.000
#> GSM647563 2 0.0000 0.992 0.000 1.000
#> GSM647542 2 0.0000 0.992 0.000 1.000
#> GSM647543 2 0.0000 0.992 0.000 1.000
#> GSM647548 1 0.5629 0.849 0.868 0.132
#> GSM647554 2 0.0000 0.992 0.000 1.000
#> GSM647555 2 0.0000 0.992 0.000 1.000
#> GSM647559 2 0.0000 0.992 0.000 1.000
#> GSM647562 2 0.0000 0.992 0.000 1.000
#> GSM647564 1 0.0000 0.985 1.000 0.000
#> GSM647571 2 0.0000 0.992 0.000 1.000
#> GSM647584 2 0.0000 0.992 0.000 1.000
#> GSM647585 1 0.0000 0.985 1.000 0.000
#> GSM647586 2 0.0000 0.992 0.000 1.000
#> GSM647587 2 0.0000 0.992 0.000 1.000
#> GSM647588 2 0.0000 0.992 0.000 1.000
#> GSM647596 2 0.0000 0.992 0.000 1.000
#> GSM647602 1 0.0000 0.985 1.000 0.000
#> GSM647609 2 0.0000 0.992 0.000 1.000
#> GSM647620 2 0.0000 0.992 0.000 1.000
#> GSM647627 2 0.0000 0.992 0.000 1.000
#> GSM647628 2 0.0000 0.992 0.000 1.000
#> GSM647533 1 0.0000 0.985 1.000 0.000
#> GSM647536 1 0.0000 0.985 1.000 0.000
#> GSM647537 1 0.0000 0.985 1.000 0.000
#> GSM647606 1 0.0000 0.985 1.000 0.000
#> GSM647621 1 0.0000 0.985 1.000 0.000
#> GSM647626 1 0.0000 0.985 1.000 0.000
#> GSM647538 1 0.0000 0.985 1.000 0.000
#> GSM647575 1 0.0000 0.985 1.000 0.000
#> GSM647590 1 0.0000 0.985 1.000 0.000
#> GSM647605 1 0.0000 0.985 1.000 0.000
#> GSM647607 1 0.0000 0.985 1.000 0.000
#> GSM647608 1 0.0000 0.985 1.000 0.000
#> GSM647622 1 0.0000 0.985 1.000 0.000
#> GSM647623 1 0.0000 0.985 1.000 0.000
#> GSM647624 1 0.0000 0.985 1.000 0.000
#> GSM647625 1 0.0000 0.985 1.000 0.000
#> GSM647534 1 0.0000 0.985 1.000 0.000
#> GSM647539 1 0.0000 0.985 1.000 0.000
#> GSM647566 1 0.0000 0.985 1.000 0.000
#> GSM647589 1 0.0000 0.985 1.000 0.000
#> GSM647604 1 0.0000 0.985 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 1 0.5254 0.7784 0.736 0.000 0.264
#> GSM647574 1 0.5291 0.7763 0.732 0.000 0.268
#> GSM647577 1 0.5254 0.7784 0.736 0.000 0.264
#> GSM647547 3 0.6192 -0.2010 0.420 0.000 0.580
#> GSM647552 1 0.4062 0.7273 0.836 0.164 0.000
#> GSM647553 1 0.4796 0.7991 0.780 0.000 0.220
#> GSM647565 3 0.0892 0.6600 0.020 0.000 0.980
#> GSM647545 3 0.5859 0.6053 0.000 0.344 0.656
#> GSM647549 3 0.5905 0.5922 0.000 0.352 0.648
#> GSM647550 3 0.5291 0.7002 0.000 0.268 0.732
#> GSM647560 3 0.5285 0.7222 0.004 0.244 0.752
#> GSM647617 1 0.5254 0.7784 0.736 0.000 0.264
#> GSM647528 2 0.4062 0.7997 0.000 0.836 0.164
#> GSM647529 1 0.5926 0.4484 0.644 0.356 0.000
#> GSM647531 2 0.3340 0.8234 0.000 0.880 0.120
#> GSM647540 3 0.5404 0.4935 0.004 0.256 0.740
#> GSM647541 3 0.6260 0.3579 0.000 0.448 0.552
#> GSM647546 3 0.4062 0.4460 0.164 0.000 0.836
#> GSM647557 2 0.0000 0.8634 0.000 1.000 0.000
#> GSM647561 2 0.4062 0.7997 0.000 0.836 0.164
#> GSM647567 1 0.8717 0.6220 0.592 0.220 0.188
#> GSM647568 3 0.4399 0.7463 0.000 0.188 0.812
#> GSM647570 3 0.5254 0.7037 0.000 0.264 0.736
#> GSM647573 1 0.6305 0.0558 0.516 0.000 0.484
#> GSM647576 3 0.3116 0.5376 0.108 0.000 0.892
#> GSM647579 1 0.7699 0.5306 0.532 0.048 0.420
#> GSM647580 1 0.5254 0.7784 0.736 0.000 0.264
#> GSM647583 1 0.5254 0.7784 0.736 0.000 0.264
#> GSM647592 2 0.0000 0.8634 0.000 1.000 0.000
#> GSM647593 2 0.0000 0.8634 0.000 1.000 0.000
#> GSM647595 2 0.0000 0.8634 0.000 1.000 0.000
#> GSM647597 2 0.5216 0.5105 0.260 0.740 0.000
#> GSM647598 2 0.1643 0.8518 0.000 0.956 0.044
#> GSM647613 2 0.4062 0.7997 0.000 0.836 0.164
#> GSM647615 3 0.6696 0.7197 0.076 0.188 0.736
#> GSM647616 1 0.5254 0.7784 0.736 0.000 0.264
#> GSM647619 2 0.0000 0.8634 0.000 1.000 0.000
#> GSM647582 2 0.0000 0.8634 0.000 1.000 0.000
#> GSM647591 2 0.0000 0.8634 0.000 1.000 0.000
#> GSM647527 2 0.4062 0.7997 0.000 0.836 0.164
#> GSM647530 2 0.5431 0.5996 0.000 0.716 0.284
#> GSM647532 1 0.0237 0.8496 0.996 0.000 0.004
#> GSM647544 2 0.5431 0.5996 0.000 0.716 0.284
#> GSM647551 2 0.0000 0.8634 0.000 1.000 0.000
#> GSM647556 1 0.4399 0.8091 0.812 0.000 0.188
#> GSM647558 3 0.5254 0.7037 0.000 0.264 0.736
#> GSM647572 3 0.4062 0.4460 0.164 0.000 0.836
#> GSM647578 3 0.5810 0.4032 0.000 0.336 0.664
#> GSM647581 3 0.5926 0.5850 0.000 0.356 0.644
#> GSM647594 2 0.0000 0.8634 0.000 1.000 0.000
#> GSM647599 1 0.0000 0.8511 1.000 0.000 0.000
#> GSM647600 2 0.0237 0.8604 0.004 0.996 0.000
#> GSM647601 2 0.0000 0.8634 0.000 1.000 0.000
#> GSM647603 2 0.3983 0.6988 0.004 0.852 0.144
#> GSM647610 2 0.5243 0.6546 0.100 0.828 0.072
#> GSM647611 2 0.0000 0.8634 0.000 1.000 0.000
#> GSM647612 3 0.4399 0.7463 0.000 0.188 0.812
#> GSM647614 3 0.4399 0.7463 0.000 0.188 0.812
#> GSM647618 2 0.0000 0.8634 0.000 1.000 0.000
#> GSM647629 2 0.0000 0.8634 0.000 1.000 0.000
#> GSM647535 2 0.3941 0.8056 0.000 0.844 0.156
#> GSM647563 3 0.6095 0.5105 0.000 0.392 0.608
#> GSM647542 3 0.4399 0.7463 0.000 0.188 0.812
#> GSM647543 3 0.4399 0.7463 0.000 0.188 0.812
#> GSM647548 3 0.5235 0.7373 0.036 0.152 0.812
#> GSM647554 2 0.0000 0.8634 0.000 1.000 0.000
#> GSM647555 3 0.5016 0.7216 0.000 0.240 0.760
#> GSM647559 2 0.4062 0.7997 0.000 0.836 0.164
#> GSM647562 2 0.5785 0.4789 0.000 0.668 0.332
#> GSM647564 1 0.5254 0.7784 0.736 0.000 0.264
#> GSM647571 3 0.4399 0.7463 0.000 0.188 0.812
#> GSM647584 2 0.0000 0.8634 0.000 1.000 0.000
#> GSM647585 1 0.4399 0.8091 0.812 0.000 0.188
#> GSM647586 2 0.3941 0.8056 0.000 0.844 0.156
#> GSM647587 2 0.4062 0.7997 0.000 0.836 0.164
#> GSM647588 2 0.4002 0.8030 0.000 0.840 0.160
#> GSM647596 2 0.4062 0.7997 0.000 0.836 0.164
#> GSM647602 1 0.5254 0.7784 0.736 0.000 0.264
#> GSM647609 2 0.0000 0.8634 0.000 1.000 0.000
#> GSM647620 2 0.0000 0.8634 0.000 1.000 0.000
#> GSM647627 2 0.3941 0.8056 0.000 0.844 0.156
#> GSM647628 3 0.5216 0.7073 0.000 0.260 0.740
#> GSM647533 1 0.0000 0.8511 1.000 0.000 0.000
#> GSM647536 1 0.0000 0.8511 1.000 0.000 0.000
#> GSM647537 1 0.0000 0.8511 1.000 0.000 0.000
#> GSM647606 1 0.0000 0.8511 1.000 0.000 0.000
#> GSM647621 1 0.1163 0.8461 0.972 0.000 0.028
#> GSM647626 1 0.4399 0.8091 0.812 0.000 0.188
#> GSM647538 1 0.0000 0.8511 1.000 0.000 0.000
#> GSM647575 1 0.2261 0.8126 0.932 0.000 0.068
#> GSM647590 1 0.0000 0.8511 1.000 0.000 0.000
#> GSM647605 1 0.0000 0.8511 1.000 0.000 0.000
#> GSM647607 1 0.2261 0.8126 0.932 0.000 0.068
#> GSM647608 1 0.0000 0.8511 1.000 0.000 0.000
#> GSM647622 1 0.0000 0.8511 1.000 0.000 0.000
#> GSM647623 1 0.0000 0.8511 1.000 0.000 0.000
#> GSM647624 1 0.0000 0.8511 1.000 0.000 0.000
#> GSM647625 1 0.0000 0.8511 1.000 0.000 0.000
#> GSM647534 1 0.4062 0.7273 0.836 0.164 0.000
#> GSM647539 3 0.6267 0.2113 0.452 0.000 0.548
#> GSM647566 1 0.0000 0.8511 1.000 0.000 0.000
#> GSM647589 1 0.2959 0.8064 0.900 0.000 0.100
#> GSM647604 1 0.0000 0.8511 1.000 0.000 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 3 0.0469 0.9360 0.012 0.000 0.988 0.000
#> GSM647574 3 0.0592 0.9303 0.016 0.000 0.984 0.000
#> GSM647577 3 0.0336 0.9373 0.008 0.000 0.992 0.000
#> GSM647547 3 0.2489 0.8673 0.020 0.000 0.912 0.068
#> GSM647552 1 0.4990 0.5109 0.640 0.352 0.008 0.000
#> GSM647553 3 0.0336 0.9373 0.008 0.000 0.992 0.000
#> GSM647565 4 0.1059 0.8246 0.012 0.000 0.016 0.972
#> GSM647545 4 0.0188 0.8290 0.000 0.004 0.000 0.996
#> GSM647549 4 0.0336 0.8276 0.000 0.008 0.000 0.992
#> GSM647550 4 0.0000 0.8294 0.000 0.000 0.000 1.000
#> GSM647560 4 0.4916 0.1835 0.000 0.000 0.424 0.576
#> GSM647617 3 0.0336 0.9373 0.008 0.000 0.992 0.000
#> GSM647528 2 0.4898 0.3753 0.000 0.584 0.000 0.416
#> GSM647529 1 0.0188 0.9221 0.996 0.004 0.000 0.000
#> GSM647531 2 0.4543 0.5353 0.000 0.676 0.000 0.324
#> GSM647540 3 0.1284 0.9212 0.000 0.012 0.964 0.024
#> GSM647541 4 0.4522 0.4145 0.000 0.320 0.000 0.680
#> GSM647546 3 0.0336 0.9299 0.000 0.000 0.992 0.008
#> GSM647557 2 0.1389 0.7890 0.000 0.952 0.000 0.048
#> GSM647561 2 0.4967 0.2818 0.000 0.548 0.000 0.452
#> GSM647567 3 0.7542 0.3090 0.212 0.312 0.476 0.000
#> GSM647568 4 0.0469 0.8301 0.000 0.000 0.012 0.988
#> GSM647570 4 0.0188 0.8302 0.000 0.000 0.004 0.996
#> GSM647573 1 0.5599 0.4651 0.616 0.000 0.032 0.352
#> GSM647576 3 0.4605 0.4880 0.000 0.000 0.664 0.336
#> GSM647579 3 0.0469 0.9322 0.000 0.012 0.988 0.000
#> GSM647580 3 0.0336 0.9373 0.008 0.000 0.992 0.000
#> GSM647583 3 0.0336 0.9373 0.008 0.000 0.992 0.000
#> GSM647592 2 0.0000 0.8109 0.000 1.000 0.000 0.000
#> GSM647593 2 0.0000 0.8109 0.000 1.000 0.000 0.000
#> GSM647595 2 0.0000 0.8109 0.000 1.000 0.000 0.000
#> GSM647597 2 0.4746 0.2722 0.368 0.632 0.000 0.000
#> GSM647598 2 0.0707 0.8080 0.000 0.980 0.000 0.020
#> GSM647613 4 0.4989 -0.0834 0.000 0.472 0.000 0.528
#> GSM647615 4 0.4776 0.2697 0.000 0.000 0.376 0.624
#> GSM647616 3 0.0336 0.9373 0.008 0.000 0.992 0.000
#> GSM647619 2 0.0000 0.8109 0.000 1.000 0.000 0.000
#> GSM647582 2 0.0000 0.8109 0.000 1.000 0.000 0.000
#> GSM647591 2 0.0000 0.8109 0.000 1.000 0.000 0.000
#> GSM647527 2 0.4898 0.3753 0.000 0.584 0.000 0.416
#> GSM647530 4 0.4585 0.3860 0.000 0.332 0.000 0.668
#> GSM647532 1 0.0000 0.9231 1.000 0.000 0.000 0.000
#> GSM647544 4 0.4679 0.3329 0.000 0.352 0.000 0.648
#> GSM647551 2 0.0000 0.8109 0.000 1.000 0.000 0.000
#> GSM647556 3 0.0469 0.9360 0.012 0.000 0.988 0.000
#> GSM647558 4 0.0000 0.8294 0.000 0.000 0.000 1.000
#> GSM647572 3 0.0524 0.9288 0.004 0.000 0.988 0.008
#> GSM647578 3 0.4008 0.7802 0.000 0.148 0.820 0.032
#> GSM647581 4 0.0592 0.8232 0.000 0.016 0.000 0.984
#> GSM647594 2 0.0469 0.8104 0.000 0.988 0.000 0.012
#> GSM647599 1 0.0469 0.9248 0.988 0.000 0.012 0.000
#> GSM647600 2 0.0336 0.8064 0.000 0.992 0.008 0.000
#> GSM647601 2 0.0336 0.8109 0.000 0.992 0.000 0.008
#> GSM647603 2 0.3946 0.6630 0.000 0.812 0.168 0.020
#> GSM647610 2 0.0188 0.8103 0.000 0.996 0.000 0.004
#> GSM647611 2 0.0469 0.8106 0.000 0.988 0.000 0.012
#> GSM647612 4 0.0336 0.8306 0.000 0.000 0.008 0.992
#> GSM647614 4 0.0469 0.8301 0.000 0.000 0.012 0.988
#> GSM647618 2 0.0469 0.8104 0.000 0.988 0.000 0.012
#> GSM647629 2 0.1211 0.7889 0.000 0.960 0.000 0.040
#> GSM647535 2 0.4730 0.4690 0.000 0.636 0.000 0.364
#> GSM647563 4 0.1118 0.8074 0.000 0.036 0.000 0.964
#> GSM647542 4 0.0469 0.8301 0.000 0.000 0.012 0.988
#> GSM647543 4 0.0469 0.8301 0.000 0.000 0.012 0.988
#> GSM647548 4 0.0937 0.8259 0.012 0.000 0.012 0.976
#> GSM647554 2 0.0000 0.8109 0.000 1.000 0.000 0.000
#> GSM647555 4 0.0336 0.8306 0.000 0.000 0.008 0.992
#> GSM647559 2 0.4989 0.2224 0.000 0.528 0.000 0.472
#> GSM647562 4 0.4543 0.4023 0.000 0.324 0.000 0.676
#> GSM647564 3 0.0336 0.9373 0.008 0.000 0.992 0.000
#> GSM647571 4 0.0469 0.8301 0.000 0.000 0.012 0.988
#> GSM647584 2 0.0000 0.8109 0.000 1.000 0.000 0.000
#> GSM647585 3 0.0469 0.9360 0.012 0.000 0.988 0.000
#> GSM647586 2 0.4661 0.4953 0.000 0.652 0.000 0.348
#> GSM647587 2 0.4888 0.3839 0.000 0.588 0.000 0.412
#> GSM647588 4 0.4967 0.0285 0.000 0.452 0.000 0.548
#> GSM647596 2 0.4843 0.4132 0.000 0.604 0.000 0.396
#> GSM647602 3 0.0336 0.9373 0.008 0.000 0.992 0.000
#> GSM647609 2 0.0336 0.8109 0.000 0.992 0.000 0.008
#> GSM647620 2 0.0592 0.8098 0.000 0.984 0.000 0.016
#> GSM647627 2 0.4661 0.4953 0.000 0.652 0.000 0.348
#> GSM647628 4 0.0336 0.8306 0.000 0.000 0.008 0.992
#> GSM647533 1 0.0469 0.9248 0.988 0.000 0.012 0.000
#> GSM647536 1 0.0000 0.9231 1.000 0.000 0.000 0.000
#> GSM647537 1 0.0469 0.9248 0.988 0.000 0.012 0.000
#> GSM647606 1 0.0469 0.9248 0.988 0.000 0.012 0.000
#> GSM647621 1 0.1022 0.9084 0.968 0.000 0.032 0.000
#> GSM647626 3 0.0469 0.9360 0.012 0.000 0.988 0.000
#> GSM647538 1 0.0469 0.9248 0.988 0.000 0.012 0.000
#> GSM647575 1 0.1807 0.8896 0.940 0.000 0.008 0.052
#> GSM647590 1 0.0000 0.9231 1.000 0.000 0.000 0.000
#> GSM647605 1 0.0336 0.9244 0.992 0.000 0.008 0.000
#> GSM647607 1 0.1722 0.8926 0.944 0.000 0.008 0.048
#> GSM647608 1 0.0188 0.9221 0.996 0.000 0.004 0.000
#> GSM647622 1 0.0469 0.9248 0.988 0.000 0.012 0.000
#> GSM647623 1 0.0469 0.9248 0.988 0.000 0.012 0.000
#> GSM647624 1 0.0000 0.9231 1.000 0.000 0.000 0.000
#> GSM647625 1 0.0469 0.9248 0.988 0.000 0.012 0.000
#> GSM647534 1 0.4262 0.6975 0.756 0.236 0.008 0.000
#> GSM647539 1 0.4360 0.6670 0.744 0.000 0.008 0.248
#> GSM647566 1 0.0469 0.9248 0.988 0.000 0.012 0.000
#> GSM647589 1 0.4880 0.7090 0.760 0.000 0.188 0.052
#> GSM647604 1 0.0469 0.9248 0.988 0.000 0.012 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.0000 0.9131 0.000 0.000 1.000 0.000 0.000
#> GSM647574 3 0.3265 0.7940 0.012 0.000 0.848 0.120 0.020
#> GSM647577 3 0.0000 0.9131 0.000 0.000 1.000 0.000 0.000
#> GSM647547 4 0.5633 0.1084 0.020 0.000 0.372 0.564 0.044
#> GSM647552 5 0.4126 0.3468 0.380 0.000 0.000 0.000 0.620
#> GSM647553 3 0.0000 0.9131 0.000 0.000 1.000 0.000 0.000
#> GSM647565 4 0.1787 0.7078 0.012 0.016 0.000 0.940 0.032
#> GSM647545 4 0.4436 0.4724 0.000 0.396 0.000 0.596 0.008
#> GSM647549 2 0.4547 0.1505 0.000 0.588 0.000 0.400 0.012
#> GSM647550 2 0.4855 0.5347 0.000 0.720 0.000 0.168 0.112
#> GSM647560 4 0.5768 0.5317 0.000 0.076 0.268 0.632 0.024
#> GSM647617 3 0.0000 0.9131 0.000 0.000 1.000 0.000 0.000
#> GSM647528 2 0.0609 0.7613 0.000 0.980 0.000 0.000 0.020
#> GSM647529 1 0.2054 0.8677 0.920 0.000 0.000 0.052 0.028
#> GSM647531 2 0.3488 0.6770 0.000 0.808 0.000 0.024 0.168
#> GSM647540 3 0.3276 0.8166 0.000 0.000 0.836 0.032 0.132
#> GSM647541 2 0.4887 0.6041 0.000 0.720 0.000 0.132 0.148
#> GSM647546 3 0.0794 0.8979 0.000 0.000 0.972 0.028 0.000
#> GSM647557 5 0.4339 0.6925 0.000 0.296 0.000 0.020 0.684
#> GSM647561 2 0.1668 0.7549 0.000 0.940 0.000 0.028 0.032
#> GSM647567 5 0.5723 0.4018 0.124 0.000 0.248 0.004 0.624
#> GSM647568 4 0.2813 0.7882 0.000 0.168 0.000 0.832 0.000
#> GSM647570 4 0.3636 0.7200 0.000 0.272 0.000 0.728 0.000
#> GSM647573 4 0.5601 0.3044 0.236 0.000 0.052 0.668 0.044
#> GSM647576 3 0.5317 0.4056 0.000 0.008 0.604 0.340 0.048
#> GSM647579 3 0.2818 0.8279 0.000 0.000 0.856 0.012 0.132
#> GSM647580 3 0.0000 0.9131 0.000 0.000 1.000 0.000 0.000
#> GSM647583 3 0.0000 0.9131 0.000 0.000 1.000 0.000 0.000
#> GSM647592 5 0.3336 0.7861 0.000 0.228 0.000 0.000 0.772
#> GSM647593 5 0.3177 0.8010 0.000 0.208 0.000 0.000 0.792
#> GSM647595 5 0.3210 0.7990 0.000 0.212 0.000 0.000 0.788
#> GSM647597 5 0.4482 0.7143 0.160 0.088 0.000 0.000 0.752
#> GSM647598 2 0.3242 0.5996 0.000 0.784 0.000 0.000 0.216
#> GSM647613 2 0.1830 0.7385 0.000 0.924 0.000 0.068 0.008
#> GSM647615 4 0.3155 0.7047 0.000 0.020 0.120 0.852 0.008
#> GSM647616 3 0.0000 0.9131 0.000 0.000 1.000 0.000 0.000
#> GSM647619 5 0.3210 0.8000 0.000 0.212 0.000 0.000 0.788
#> GSM647582 5 0.3003 0.8077 0.000 0.188 0.000 0.000 0.812
#> GSM647591 5 0.3074 0.8029 0.000 0.196 0.000 0.000 0.804
#> GSM647527 2 0.0609 0.7613 0.000 0.980 0.000 0.000 0.020
#> GSM647530 2 0.2927 0.7299 0.000 0.872 0.000 0.068 0.060
#> GSM647532 1 0.2628 0.8555 0.884 0.000 0.000 0.088 0.028
#> GSM647544 2 0.1300 0.7608 0.000 0.956 0.000 0.016 0.028
#> GSM647551 5 0.2773 0.8081 0.000 0.164 0.000 0.000 0.836
#> GSM647556 3 0.0000 0.9131 0.000 0.000 1.000 0.000 0.000
#> GSM647558 2 0.4287 -0.0738 0.000 0.540 0.000 0.460 0.000
#> GSM647572 3 0.4527 0.6052 0.000 0.000 0.692 0.272 0.036
#> GSM647578 3 0.5638 0.6469 0.000 0.132 0.680 0.020 0.168
#> GSM647581 2 0.4211 0.2689 0.000 0.636 0.000 0.360 0.004
#> GSM647594 2 0.4262 0.1376 0.000 0.560 0.000 0.000 0.440
#> GSM647599 1 0.0566 0.8881 0.984 0.000 0.012 0.000 0.004
#> GSM647600 5 0.1732 0.7818 0.000 0.080 0.000 0.000 0.920
#> GSM647601 2 0.3752 0.4745 0.000 0.708 0.000 0.000 0.292
#> GSM647603 5 0.6338 0.5492 0.000 0.172 0.180 0.032 0.616
#> GSM647610 5 0.2605 0.7647 0.000 0.148 0.000 0.000 0.852
#> GSM647611 2 0.3707 0.5070 0.000 0.716 0.000 0.000 0.284
#> GSM647612 4 0.3210 0.7728 0.000 0.212 0.000 0.788 0.000
#> GSM647614 4 0.2852 0.7880 0.000 0.172 0.000 0.828 0.000
#> GSM647618 2 0.4138 0.3539 0.000 0.616 0.000 0.000 0.384
#> GSM647629 5 0.3452 0.7506 0.000 0.148 0.000 0.032 0.820
#> GSM647535 2 0.2011 0.7475 0.000 0.908 0.000 0.004 0.088
#> GSM647563 2 0.2773 0.6243 0.000 0.836 0.000 0.164 0.000
#> GSM647542 4 0.3039 0.7849 0.000 0.192 0.000 0.808 0.000
#> GSM647543 4 0.2891 0.7858 0.000 0.176 0.000 0.824 0.000
#> GSM647548 4 0.1869 0.7056 0.012 0.016 0.000 0.936 0.036
#> GSM647554 5 0.2753 0.7656 0.000 0.136 0.000 0.008 0.856
#> GSM647555 4 0.3424 0.7516 0.000 0.240 0.000 0.760 0.000
#> GSM647559 2 0.0955 0.7618 0.000 0.968 0.000 0.004 0.028
#> GSM647562 2 0.1981 0.7460 0.000 0.924 0.000 0.048 0.028
#> GSM647564 3 0.0000 0.9131 0.000 0.000 1.000 0.000 0.000
#> GSM647571 4 0.3391 0.7771 0.000 0.188 0.000 0.800 0.012
#> GSM647584 5 0.3210 0.7990 0.000 0.212 0.000 0.000 0.788
#> GSM647585 3 0.0000 0.9131 0.000 0.000 1.000 0.000 0.000
#> GSM647586 2 0.1341 0.7503 0.000 0.944 0.000 0.000 0.056
#> GSM647587 2 0.0794 0.7617 0.000 0.972 0.000 0.000 0.028
#> GSM647588 2 0.4270 0.6950 0.000 0.776 0.000 0.112 0.112
#> GSM647596 2 0.1364 0.7621 0.000 0.952 0.000 0.012 0.036
#> GSM647602 3 0.0000 0.9131 0.000 0.000 1.000 0.000 0.000
#> GSM647609 2 0.3932 0.3952 0.000 0.672 0.000 0.000 0.328
#> GSM647620 2 0.3300 0.6083 0.000 0.792 0.000 0.004 0.204
#> GSM647627 2 0.1544 0.7452 0.000 0.932 0.000 0.000 0.068
#> GSM647628 4 0.3274 0.7720 0.000 0.220 0.000 0.780 0.000
#> GSM647533 1 0.0404 0.8882 0.988 0.000 0.012 0.000 0.000
#> GSM647536 1 0.1845 0.8698 0.928 0.000 0.000 0.056 0.016
#> GSM647537 1 0.0404 0.8882 0.988 0.000 0.012 0.000 0.000
#> GSM647606 1 0.0404 0.8882 0.988 0.000 0.012 0.000 0.000
#> GSM647621 1 0.5431 0.7314 0.696 0.000 0.060 0.204 0.040
#> GSM647626 3 0.0794 0.8952 0.028 0.000 0.972 0.000 0.000
#> GSM647538 1 0.0404 0.8882 0.988 0.000 0.012 0.000 0.000
#> GSM647575 1 0.4384 0.7558 0.728 0.000 0.000 0.228 0.044
#> GSM647590 1 0.1299 0.8849 0.960 0.000 0.012 0.020 0.008
#> GSM647605 1 0.0404 0.8882 0.988 0.000 0.012 0.000 0.000
#> GSM647607 1 0.4355 0.7591 0.732 0.000 0.000 0.224 0.044
#> GSM647608 1 0.4484 0.7762 0.752 0.000 0.012 0.192 0.044
#> GSM647622 1 0.0404 0.8882 0.988 0.000 0.012 0.000 0.000
#> GSM647623 1 0.0404 0.8882 0.988 0.000 0.012 0.000 0.000
#> GSM647624 1 0.1299 0.8849 0.960 0.000 0.012 0.020 0.008
#> GSM647625 1 0.0404 0.8882 0.988 0.000 0.012 0.000 0.000
#> GSM647534 1 0.4126 0.2926 0.620 0.000 0.000 0.000 0.380
#> GSM647539 1 0.5024 0.6551 0.640 0.004 0.000 0.312 0.044
#> GSM647566 1 0.0693 0.8877 0.980 0.000 0.012 0.000 0.008
#> GSM647589 1 0.5936 0.6688 0.636 0.000 0.068 0.252 0.044
#> GSM647604 1 0.0404 0.8882 0.988 0.000 0.012 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.0000 0.8715 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647574 3 0.2871 0.6903 0.000 0.000 0.804 0.192 0.000 0.004
#> GSM647577 3 0.0000 0.8715 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647547 4 0.5046 0.4556 0.004 0.000 0.276 0.620 0.000 0.100
#> GSM647552 5 0.4740 0.5250 0.260 0.004 0.000 0.060 0.668 0.008
#> GSM647553 3 0.0146 0.8698 0.000 0.000 0.996 0.004 0.000 0.000
#> GSM647565 6 0.3866 0.0516 0.000 0.000 0.000 0.484 0.000 0.516
#> GSM647545 6 0.4757 0.6503 0.000 0.192 0.000 0.100 0.012 0.696
#> GSM647549 6 0.5468 0.4418 0.000 0.304 0.000 0.112 0.012 0.572
#> GSM647550 2 0.6731 0.2624 0.000 0.468 0.000 0.172 0.072 0.288
#> GSM647560 6 0.4088 0.6532 0.000 0.016 0.160 0.032 0.016 0.776
#> GSM647617 3 0.0000 0.8715 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647528 2 0.1552 0.7873 0.000 0.940 0.000 0.004 0.020 0.036
#> GSM647529 1 0.4718 0.3624 0.640 0.008 0.000 0.308 0.036 0.008
#> GSM647531 2 0.5547 0.5953 0.000 0.636 0.000 0.160 0.172 0.032
#> GSM647540 3 0.5456 0.6604 0.000 0.008 0.672 0.172 0.108 0.040
#> GSM647541 2 0.6756 0.2827 0.000 0.472 0.000 0.148 0.088 0.292
#> GSM647546 3 0.0713 0.8587 0.000 0.000 0.972 0.000 0.000 0.028
#> GSM647557 5 0.5666 0.5304 0.000 0.228 0.000 0.168 0.588 0.016
#> GSM647561 2 0.3843 0.7448 0.000 0.808 0.000 0.088 0.036 0.068
#> GSM647567 5 0.6790 0.5259 0.092 0.012 0.132 0.164 0.584 0.016
#> GSM647568 6 0.0777 0.8245 0.000 0.024 0.000 0.004 0.000 0.972
#> GSM647570 6 0.2147 0.8037 0.000 0.084 0.000 0.020 0.000 0.896
#> GSM647573 4 0.5664 0.6668 0.180 0.000 0.032 0.620 0.000 0.168
#> GSM647576 3 0.5098 0.2084 0.000 0.000 0.512 0.052 0.012 0.424
#> GSM647579 3 0.4704 0.7039 0.000 0.000 0.724 0.144 0.108 0.024
#> GSM647580 3 0.0000 0.8715 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647583 3 0.0000 0.8715 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647592 5 0.3046 0.7709 0.000 0.188 0.000 0.012 0.800 0.000
#> GSM647593 5 0.2595 0.7899 0.000 0.160 0.000 0.004 0.836 0.000
#> GSM647595 5 0.2778 0.7844 0.000 0.168 0.000 0.008 0.824 0.000
#> GSM647597 5 0.4503 0.7136 0.128 0.048 0.000 0.052 0.764 0.008
#> GSM647598 2 0.2302 0.7536 0.000 0.872 0.000 0.008 0.120 0.000
#> GSM647613 2 0.3850 0.7374 0.000 0.800 0.000 0.084 0.020 0.096
#> GSM647615 6 0.2088 0.7831 0.000 0.000 0.028 0.068 0.000 0.904
#> GSM647616 3 0.0000 0.8715 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647619 5 0.2668 0.7878 0.000 0.168 0.000 0.004 0.828 0.000
#> GSM647582 5 0.2669 0.7963 0.000 0.156 0.000 0.008 0.836 0.000
#> GSM647591 5 0.2841 0.7883 0.000 0.164 0.000 0.012 0.824 0.000
#> GSM647527 2 0.1552 0.7873 0.000 0.940 0.000 0.004 0.020 0.036
#> GSM647530 2 0.4146 0.7010 0.000 0.752 0.000 0.180 0.052 0.016
#> GSM647532 1 0.4750 -0.0381 0.544 0.008 0.000 0.420 0.020 0.008
#> GSM647544 2 0.2187 0.7832 0.000 0.912 0.000 0.024 0.024 0.040
#> GSM647551 5 0.2358 0.7994 0.000 0.108 0.000 0.016 0.876 0.000
#> GSM647556 3 0.0146 0.8705 0.000 0.000 0.996 0.004 0.000 0.000
#> GSM647558 6 0.4950 0.3878 0.000 0.344 0.000 0.080 0.000 0.576
#> GSM647572 3 0.4702 0.7022 0.000 0.004 0.732 0.080 0.028 0.156
#> GSM647578 3 0.7819 0.3434 0.000 0.188 0.440 0.192 0.136 0.044
#> GSM647581 2 0.5544 0.3270 0.000 0.556 0.000 0.116 0.012 0.316
#> GSM647594 2 0.4463 0.3512 0.000 0.588 0.000 0.036 0.376 0.000
#> GSM647599 1 0.0146 0.8594 0.996 0.000 0.000 0.004 0.000 0.000
#> GSM647600 5 0.2209 0.7873 0.000 0.052 0.000 0.040 0.904 0.004
#> GSM647601 2 0.2941 0.6552 0.000 0.780 0.000 0.000 0.220 0.000
#> GSM647603 5 0.6539 0.6127 0.000 0.160 0.080 0.080 0.616 0.064
#> GSM647610 5 0.3852 0.7472 0.000 0.116 0.000 0.088 0.788 0.008
#> GSM647611 2 0.3171 0.6645 0.000 0.784 0.000 0.012 0.204 0.000
#> GSM647612 6 0.0632 0.8248 0.000 0.024 0.000 0.000 0.000 0.976
#> GSM647614 6 0.0777 0.8245 0.000 0.024 0.000 0.004 0.000 0.972
#> GSM647618 2 0.3819 0.5178 0.000 0.672 0.000 0.012 0.316 0.000
#> GSM647629 5 0.4726 0.7267 0.000 0.100 0.000 0.140 0.728 0.032
#> GSM647535 2 0.2384 0.7728 0.000 0.900 0.000 0.040 0.044 0.016
#> GSM647563 2 0.2740 0.7391 0.000 0.852 0.000 0.028 0.000 0.120
#> GSM647542 6 0.0777 0.8245 0.000 0.024 0.000 0.004 0.000 0.972
#> GSM647543 6 0.0547 0.8241 0.000 0.020 0.000 0.000 0.000 0.980
#> GSM647548 4 0.3804 0.1346 0.000 0.000 0.000 0.576 0.000 0.424
#> GSM647554 5 0.4075 0.7131 0.000 0.060 0.000 0.168 0.760 0.012
#> GSM647555 6 0.1333 0.8224 0.000 0.048 0.000 0.008 0.000 0.944
#> GSM647559 2 0.1851 0.7839 0.000 0.928 0.000 0.012 0.024 0.036
#> GSM647562 2 0.2216 0.7806 0.000 0.908 0.000 0.016 0.024 0.052
#> GSM647564 3 0.0000 0.8715 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647571 6 0.2349 0.7946 0.000 0.080 0.000 0.020 0.008 0.892
#> GSM647584 5 0.2946 0.7818 0.000 0.176 0.000 0.012 0.812 0.000
#> GSM647585 3 0.0146 0.8705 0.000 0.000 0.996 0.004 0.000 0.000
#> GSM647586 2 0.1049 0.7836 0.000 0.960 0.000 0.000 0.032 0.008
#> GSM647587 2 0.1630 0.7843 0.000 0.940 0.000 0.016 0.024 0.020
#> GSM647588 2 0.4498 0.7060 0.000 0.744 0.000 0.152 0.072 0.032
#> GSM647596 2 0.2084 0.7837 0.000 0.916 0.000 0.016 0.044 0.024
#> GSM647602 3 0.0000 0.8715 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647609 2 0.3390 0.5342 0.000 0.704 0.000 0.000 0.296 0.000
#> GSM647620 2 0.2455 0.7396 0.000 0.872 0.000 0.012 0.112 0.004
#> GSM647627 2 0.1265 0.7810 0.000 0.948 0.000 0.000 0.044 0.008
#> GSM647628 6 0.1528 0.8210 0.000 0.048 0.000 0.016 0.000 0.936
#> GSM647533 1 0.0000 0.8614 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647536 1 0.4245 0.4707 0.696 0.008 0.000 0.268 0.020 0.008
#> GSM647537 1 0.0000 0.8614 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647606 1 0.0000 0.8614 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647621 4 0.4575 0.7013 0.352 0.000 0.048 0.600 0.000 0.000
#> GSM647626 3 0.2135 0.7681 0.128 0.000 0.872 0.000 0.000 0.000
#> GSM647538 1 0.0260 0.8568 0.992 0.000 0.000 0.008 0.000 0.000
#> GSM647575 4 0.4004 0.6991 0.368 0.000 0.000 0.620 0.000 0.012
#> GSM647590 1 0.1387 0.8027 0.932 0.000 0.000 0.068 0.000 0.000
#> GSM647605 1 0.0000 0.8614 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647607 4 0.3934 0.6918 0.376 0.000 0.000 0.616 0.000 0.008
#> GSM647608 4 0.3955 0.6813 0.384 0.000 0.008 0.608 0.000 0.000
#> GSM647622 1 0.0000 0.8614 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647623 1 0.0000 0.8614 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647624 1 0.1327 0.8065 0.936 0.000 0.000 0.064 0.000 0.000
#> GSM647625 1 0.0000 0.8614 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647534 1 0.3916 0.4289 0.680 0.000 0.000 0.020 0.300 0.000
#> GSM647539 4 0.4249 0.7156 0.328 0.000 0.000 0.640 0.000 0.032
#> GSM647566 1 0.0547 0.8521 0.980 0.000 0.000 0.020 0.000 0.000
#> GSM647589 4 0.5001 0.7187 0.308 0.000 0.060 0.616 0.000 0.016
#> GSM647604 1 0.0000 0.8614 1.000 0.000 0.000 0.000 0.000 0.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n disease.state(p) development.stage(p) other(p) k
#> MAD:skmeans 102 5.70e-08 0.01748 0.5734 2
#> MAD:skmeans 93 4.23e-09 0.19818 0.1811 3
#> MAD:skmeans 82 7.41e-13 0.02497 0.0731 4
#> MAD:skmeans 89 4.25e-14 0.00463 0.2497 5
#> MAD:skmeans 88 4.07e-14 0.01111 0.3566 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["MAD", "pam"]
# you can also extract it by
# res = res_list["MAD:pam"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'MAD' method.
#> Subgroups are detected by 'pam' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 3.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.608 0.780 0.914 0.4959 0.506 0.506
#> 3 3 0.712 0.838 0.925 0.2462 0.756 0.566
#> 4 4 0.684 0.728 0.833 0.1587 0.824 0.583
#> 5 5 0.752 0.661 0.822 0.0900 0.784 0.411
#> 6 6 0.824 0.759 0.876 0.0472 0.911 0.640
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 3
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM647569 1 0.0000 0.9030 1.000 0.000
#> GSM647574 1 0.0000 0.9030 1.000 0.000
#> GSM647577 1 0.0000 0.9030 1.000 0.000
#> GSM647547 1 0.0000 0.9030 1.000 0.000
#> GSM647552 1 0.5946 0.8047 0.856 0.144
#> GSM647553 1 0.0000 0.9030 1.000 0.000
#> GSM647565 2 0.9954 0.1541 0.460 0.540
#> GSM647545 2 0.0000 0.8919 0.000 1.000
#> GSM647549 2 0.0000 0.8919 0.000 1.000
#> GSM647550 2 0.0000 0.8919 0.000 1.000
#> GSM647560 1 0.9754 0.2924 0.592 0.408
#> GSM647617 1 0.0000 0.9030 1.000 0.000
#> GSM647528 2 0.0000 0.8919 0.000 1.000
#> GSM647529 2 0.4562 0.8034 0.096 0.904
#> GSM647531 2 0.0000 0.8919 0.000 1.000
#> GSM647540 1 0.5737 0.8077 0.864 0.136
#> GSM647541 2 0.0000 0.8919 0.000 1.000
#> GSM647546 1 0.5737 0.8077 0.864 0.136
#> GSM647557 2 0.0000 0.8919 0.000 1.000
#> GSM647561 2 0.0000 0.8919 0.000 1.000
#> GSM647567 2 0.9970 0.0394 0.468 0.532
#> GSM647568 2 0.9732 0.3177 0.404 0.596
#> GSM647570 2 0.0000 0.8919 0.000 1.000
#> GSM647573 1 0.2236 0.8819 0.964 0.036
#> GSM647576 1 0.5737 0.8077 0.864 0.136
#> GSM647579 1 0.5737 0.8077 0.864 0.136
#> GSM647580 1 0.0000 0.9030 1.000 0.000
#> GSM647583 1 0.0000 0.9030 1.000 0.000
#> GSM647592 2 0.0000 0.8919 0.000 1.000
#> GSM647593 2 0.0000 0.8919 0.000 1.000
#> GSM647595 2 0.0000 0.8919 0.000 1.000
#> GSM647597 2 0.0000 0.8919 0.000 1.000
#> GSM647598 2 0.0000 0.8919 0.000 1.000
#> GSM647613 2 0.0000 0.8919 0.000 1.000
#> GSM647615 1 0.9686 0.3225 0.604 0.396
#> GSM647616 1 0.0000 0.9030 1.000 0.000
#> GSM647619 2 0.0000 0.8919 0.000 1.000
#> GSM647582 2 0.0000 0.8919 0.000 1.000
#> GSM647591 2 0.0000 0.8919 0.000 1.000
#> GSM647527 2 0.0000 0.8919 0.000 1.000
#> GSM647530 2 0.0000 0.8919 0.000 1.000
#> GSM647532 1 0.0672 0.8989 0.992 0.008
#> GSM647544 2 0.0000 0.8919 0.000 1.000
#> GSM647551 2 0.0000 0.8919 0.000 1.000
#> GSM647556 1 0.0000 0.9030 1.000 0.000
#> GSM647558 2 0.0000 0.8919 0.000 1.000
#> GSM647572 1 0.5737 0.8077 0.864 0.136
#> GSM647578 1 0.9944 0.1793 0.544 0.456
#> GSM647581 2 0.0000 0.8919 0.000 1.000
#> GSM647594 2 0.0000 0.8919 0.000 1.000
#> GSM647599 1 0.0000 0.9030 1.000 0.000
#> GSM647600 2 0.9954 0.0660 0.460 0.540
#> GSM647601 2 0.0000 0.8919 0.000 1.000
#> GSM647603 2 0.6247 0.7350 0.156 0.844
#> GSM647610 2 0.4939 0.7918 0.108 0.892
#> GSM647611 2 0.0000 0.8919 0.000 1.000
#> GSM647612 2 0.9732 0.3177 0.404 0.596
#> GSM647614 2 0.9732 0.3177 0.404 0.596
#> GSM647618 2 0.0000 0.8919 0.000 1.000
#> GSM647629 2 0.0000 0.8919 0.000 1.000
#> GSM647535 2 0.0000 0.8919 0.000 1.000
#> GSM647563 2 0.0000 0.8919 0.000 1.000
#> GSM647542 2 0.9393 0.4248 0.356 0.644
#> GSM647543 2 0.9732 0.3177 0.404 0.596
#> GSM647548 2 0.9732 0.3177 0.404 0.596
#> GSM647554 2 0.0000 0.8919 0.000 1.000
#> GSM647555 2 0.0000 0.8919 0.000 1.000
#> GSM647559 2 0.0000 0.8919 0.000 1.000
#> GSM647562 2 0.0000 0.8919 0.000 1.000
#> GSM647564 1 0.5629 0.8114 0.868 0.132
#> GSM647571 2 0.9686 0.3370 0.396 0.604
#> GSM647584 2 0.0000 0.8919 0.000 1.000
#> GSM647585 1 0.0000 0.9030 1.000 0.000
#> GSM647586 2 0.0000 0.8919 0.000 1.000
#> GSM647587 2 0.0000 0.8919 0.000 1.000
#> GSM647588 2 0.0000 0.8919 0.000 1.000
#> GSM647596 2 0.0000 0.8919 0.000 1.000
#> GSM647602 1 0.0000 0.9030 1.000 0.000
#> GSM647609 2 0.0000 0.8919 0.000 1.000
#> GSM647620 2 0.0000 0.8919 0.000 1.000
#> GSM647627 2 0.0000 0.8919 0.000 1.000
#> GSM647628 2 0.0000 0.8919 0.000 1.000
#> GSM647533 1 0.0000 0.9030 1.000 0.000
#> GSM647536 2 0.9661 0.3170 0.392 0.608
#> GSM647537 1 0.0000 0.9030 1.000 0.000
#> GSM647606 1 0.0000 0.9030 1.000 0.000
#> GSM647621 1 0.0000 0.9030 1.000 0.000
#> GSM647626 1 0.0000 0.9030 1.000 0.000
#> GSM647538 1 0.0000 0.9030 1.000 0.000
#> GSM647575 1 0.6973 0.7179 0.812 0.188
#> GSM647590 1 0.0000 0.9030 1.000 0.000
#> GSM647605 1 0.9661 0.3131 0.608 0.392
#> GSM647607 1 0.2236 0.8819 0.964 0.036
#> GSM647608 1 0.0000 0.9030 1.000 0.000
#> GSM647622 1 0.0000 0.9030 1.000 0.000
#> GSM647623 1 0.0000 0.9030 1.000 0.000
#> GSM647624 1 0.0000 0.9030 1.000 0.000
#> GSM647625 1 0.0000 0.9030 1.000 0.000
#> GSM647534 1 0.9732 0.2820 0.596 0.404
#> GSM647539 2 0.9686 0.3700 0.396 0.604
#> GSM647566 1 0.0000 0.9030 1.000 0.000
#> GSM647589 1 0.0000 0.9030 1.000 0.000
#> GSM647604 1 0.7950 0.6336 0.760 0.240
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 3 0.0000 0.824 0.000 0.000 1.000
#> GSM647574 3 0.0000 0.824 0.000 0.000 1.000
#> GSM647577 3 0.0000 0.824 0.000 0.000 1.000
#> GSM647547 3 0.0000 0.824 0.000 0.000 1.000
#> GSM647552 1 0.8843 0.513 0.564 0.276 0.160
#> GSM647553 3 0.0237 0.823 0.004 0.000 0.996
#> GSM647565 3 0.1163 0.816 0.000 0.028 0.972
#> GSM647545 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647549 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647550 2 0.6111 0.173 0.000 0.604 0.396
#> GSM647560 3 0.6026 0.545 0.000 0.376 0.624
#> GSM647617 3 0.0000 0.824 0.000 0.000 1.000
#> GSM647528 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647529 2 0.3941 0.787 0.156 0.844 0.000
#> GSM647531 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647540 3 0.0000 0.824 0.000 0.000 1.000
#> GSM647541 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647546 3 0.0000 0.824 0.000 0.000 1.000
#> GSM647557 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647561 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647567 2 0.5621 0.550 0.000 0.692 0.308
#> GSM647568 3 0.5465 0.662 0.000 0.288 0.712
#> GSM647570 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647573 3 0.0000 0.824 0.000 0.000 1.000
#> GSM647576 3 0.0000 0.824 0.000 0.000 1.000
#> GSM647579 3 0.0000 0.824 0.000 0.000 1.000
#> GSM647580 3 0.0000 0.824 0.000 0.000 1.000
#> GSM647583 3 0.0000 0.824 0.000 0.000 1.000
#> GSM647592 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647593 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647595 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647597 2 0.3482 0.825 0.128 0.872 0.000
#> GSM647598 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647613 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647615 3 0.3192 0.777 0.000 0.112 0.888
#> GSM647616 3 0.0000 0.824 0.000 0.000 1.000
#> GSM647619 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647582 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647591 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647527 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647530 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647532 3 0.6095 0.431 0.392 0.000 0.608
#> GSM647544 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647551 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647556 3 0.0000 0.824 0.000 0.000 1.000
#> GSM647558 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647572 3 0.0000 0.824 0.000 0.000 1.000
#> GSM647578 3 0.5254 0.571 0.000 0.264 0.736
#> GSM647581 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647594 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647599 1 0.0424 0.901 0.992 0.000 0.008
#> GSM647600 2 0.3192 0.847 0.000 0.888 0.112
#> GSM647601 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647603 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647610 2 0.4002 0.787 0.000 0.840 0.160
#> GSM647611 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647612 3 0.5560 0.652 0.000 0.300 0.700
#> GSM647614 3 0.5678 0.638 0.000 0.316 0.684
#> GSM647618 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647629 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647535 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647563 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647542 3 0.5835 0.608 0.000 0.340 0.660
#> GSM647543 3 0.5560 0.652 0.000 0.300 0.700
#> GSM647548 3 0.5216 0.683 0.000 0.260 0.740
#> GSM647554 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647555 3 0.5835 0.608 0.000 0.340 0.660
#> GSM647559 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647562 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647564 3 0.0000 0.824 0.000 0.000 1.000
#> GSM647571 3 0.5835 0.608 0.000 0.340 0.660
#> GSM647584 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647585 3 0.0000 0.824 0.000 0.000 1.000
#> GSM647586 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647587 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647588 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647596 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647602 3 0.0000 0.824 0.000 0.000 1.000
#> GSM647609 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647620 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647627 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647628 2 0.0000 0.968 0.000 1.000 0.000
#> GSM647533 1 0.0000 0.907 1.000 0.000 0.000
#> GSM647536 1 0.4654 0.724 0.792 0.208 0.000
#> GSM647537 1 0.0000 0.907 1.000 0.000 0.000
#> GSM647606 1 0.0000 0.907 1.000 0.000 0.000
#> GSM647621 3 0.4555 0.699 0.200 0.000 0.800
#> GSM647626 1 0.4931 0.677 0.768 0.000 0.232
#> GSM647538 1 0.0000 0.907 1.000 0.000 0.000
#> GSM647575 3 0.5016 0.659 0.240 0.000 0.760
#> GSM647590 1 0.0000 0.907 1.000 0.000 0.000
#> GSM647605 1 0.0000 0.907 1.000 0.000 0.000
#> GSM647607 3 0.5058 0.652 0.244 0.000 0.756
#> GSM647608 3 0.6309 0.127 0.496 0.000 0.504
#> GSM647622 1 0.0000 0.907 1.000 0.000 0.000
#> GSM647623 1 0.0000 0.907 1.000 0.000 0.000
#> GSM647624 1 0.0000 0.907 1.000 0.000 0.000
#> GSM647625 1 0.0000 0.907 1.000 0.000 0.000
#> GSM647534 1 0.4702 0.722 0.788 0.212 0.000
#> GSM647539 3 0.3454 0.773 0.104 0.008 0.888
#> GSM647566 1 0.4796 0.655 0.780 0.000 0.220
#> GSM647589 3 0.4555 0.699 0.200 0.000 0.800
#> GSM647604 1 0.0000 0.907 1.000 0.000 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 3 0.4843 0.665 0.000 0.000 0.604 0.396
#> GSM647574 4 0.0000 0.583 0.000 0.000 0.000 1.000
#> GSM647577 3 0.4985 0.627 0.000 0.000 0.532 0.468
#> GSM647547 4 0.3975 0.672 0.000 0.000 0.240 0.760
#> GSM647552 3 0.6656 0.641 0.100 0.008 0.616 0.276
#> GSM647553 4 0.0000 0.583 0.000 0.000 0.000 1.000
#> GSM647565 4 0.4804 0.639 0.000 0.000 0.384 0.616
#> GSM647545 2 0.3219 0.813 0.000 0.836 0.164 0.000
#> GSM647549 2 0.4866 0.490 0.000 0.596 0.404 0.000
#> GSM647550 3 0.3074 0.587 0.000 0.152 0.848 0.000
#> GSM647560 3 0.1209 0.605 0.000 0.004 0.964 0.032
#> GSM647617 3 0.4941 0.653 0.000 0.000 0.564 0.436
#> GSM647528 2 0.0188 0.924 0.000 0.996 0.004 0.000
#> GSM647529 2 0.2706 0.857 0.080 0.900 0.000 0.020
#> GSM647531 2 0.0188 0.923 0.000 0.996 0.004 0.000
#> GSM647540 3 0.4804 0.668 0.000 0.000 0.616 0.384
#> GSM647541 3 0.4103 0.541 0.000 0.256 0.744 0.000
#> GSM647546 3 0.3528 0.613 0.000 0.000 0.808 0.192
#> GSM647557 2 0.0188 0.923 0.000 0.996 0.004 0.000
#> GSM647561 2 0.0188 0.924 0.000 0.996 0.004 0.000
#> GSM647567 3 0.5986 0.663 0.000 0.060 0.620 0.320
#> GSM647568 4 0.5212 0.603 0.000 0.008 0.420 0.572
#> GSM647570 2 0.4817 0.513 0.000 0.612 0.388 0.000
#> GSM647573 4 0.4193 0.671 0.000 0.000 0.268 0.732
#> GSM647576 3 0.3311 0.608 0.000 0.000 0.828 0.172
#> GSM647579 3 0.4804 0.668 0.000 0.000 0.616 0.384
#> GSM647580 3 0.4941 0.653 0.000 0.000 0.564 0.436
#> GSM647583 3 0.4985 0.627 0.000 0.000 0.532 0.468
#> GSM647592 2 0.0188 0.923 0.000 0.996 0.004 0.000
#> GSM647593 2 0.0188 0.923 0.000 0.996 0.004 0.000
#> GSM647595 2 0.0188 0.923 0.000 0.996 0.004 0.000
#> GSM647597 2 0.0188 0.923 0.000 0.996 0.004 0.000
#> GSM647598 2 0.0188 0.923 0.000 0.996 0.004 0.000
#> GSM647613 2 0.2408 0.863 0.000 0.896 0.104 0.000
#> GSM647615 3 0.1792 0.581 0.000 0.000 0.932 0.068
#> GSM647616 4 0.3444 0.211 0.000 0.000 0.184 0.816
#> GSM647619 2 0.0188 0.923 0.000 0.996 0.004 0.000
#> GSM647582 2 0.0188 0.924 0.000 0.996 0.004 0.000
#> GSM647591 2 0.0188 0.923 0.000 0.996 0.004 0.000
#> GSM647527 2 0.0188 0.924 0.000 0.996 0.004 0.000
#> GSM647530 2 0.1557 0.896 0.000 0.944 0.056 0.000
#> GSM647532 4 0.5510 0.464 0.376 0.000 0.024 0.600
#> GSM647544 2 0.0592 0.919 0.000 0.984 0.016 0.000
#> GSM647551 2 0.0188 0.923 0.000 0.996 0.004 0.000
#> GSM647556 3 0.4843 0.665 0.000 0.000 0.604 0.396
#> GSM647558 2 0.4454 0.639 0.000 0.692 0.308 0.000
#> GSM647572 3 0.4222 0.642 0.000 0.000 0.728 0.272
#> GSM647578 3 0.4244 0.658 0.000 0.036 0.804 0.160
#> GSM647581 2 0.4697 0.566 0.000 0.644 0.356 0.000
#> GSM647594 2 0.0188 0.923 0.000 0.996 0.004 0.000
#> GSM647599 1 0.1118 0.898 0.964 0.000 0.000 0.036
#> GSM647600 3 0.5920 0.521 0.000 0.336 0.612 0.052
#> GSM647601 2 0.0000 0.923 0.000 1.000 0.000 0.000
#> GSM647603 3 0.5467 0.502 0.000 0.364 0.612 0.024
#> GSM647610 2 0.3356 0.731 0.000 0.824 0.176 0.000
#> GSM647611 2 0.0188 0.924 0.000 0.996 0.004 0.000
#> GSM647612 3 0.0188 0.584 0.000 0.004 0.996 0.000
#> GSM647614 3 0.5150 -0.357 0.000 0.008 0.596 0.396
#> GSM647618 2 0.0188 0.924 0.000 0.996 0.004 0.000
#> GSM647629 3 0.4790 0.488 0.000 0.380 0.620 0.000
#> GSM647535 2 0.0188 0.924 0.000 0.996 0.004 0.000
#> GSM647563 2 0.2760 0.842 0.000 0.872 0.128 0.000
#> GSM647542 3 0.1545 0.567 0.000 0.008 0.952 0.040
#> GSM647543 3 0.1545 0.567 0.000 0.008 0.952 0.040
#> GSM647548 4 0.5125 0.631 0.000 0.008 0.388 0.604
#> GSM647554 3 0.4790 0.488 0.000 0.380 0.620 0.000
#> GSM647555 3 0.0188 0.584 0.000 0.004 0.996 0.000
#> GSM647559 2 0.0188 0.924 0.000 0.996 0.004 0.000
#> GSM647562 2 0.2647 0.849 0.000 0.880 0.120 0.000
#> GSM647564 3 0.4843 0.665 0.000 0.000 0.604 0.396
#> GSM647571 3 0.1545 0.567 0.000 0.008 0.952 0.040
#> GSM647584 2 0.0188 0.923 0.000 0.996 0.004 0.000
#> GSM647585 3 0.4830 0.666 0.000 0.000 0.608 0.392
#> GSM647586 2 0.0188 0.924 0.000 0.996 0.004 0.000
#> GSM647587 2 0.0188 0.924 0.000 0.996 0.004 0.000
#> GSM647588 2 0.1557 0.889 0.000 0.944 0.056 0.000
#> GSM647596 2 0.0188 0.924 0.000 0.996 0.004 0.000
#> GSM647602 3 0.4941 0.653 0.000 0.000 0.564 0.436
#> GSM647609 2 0.0188 0.923 0.000 0.996 0.004 0.000
#> GSM647620 2 0.0188 0.924 0.000 0.996 0.004 0.000
#> GSM647627 2 0.0188 0.924 0.000 0.996 0.004 0.000
#> GSM647628 2 0.4804 0.518 0.000 0.616 0.384 0.000
#> GSM647533 1 0.0000 0.933 1.000 0.000 0.000 0.000
#> GSM647536 1 0.4988 0.461 0.692 0.288 0.000 0.020
#> GSM647537 1 0.0000 0.933 1.000 0.000 0.000 0.000
#> GSM647606 1 0.0000 0.933 1.000 0.000 0.000 0.000
#> GSM647621 4 0.4797 0.632 0.260 0.000 0.020 0.720
#> GSM647626 1 0.4008 0.600 0.756 0.000 0.000 0.244
#> GSM647538 1 0.0000 0.933 1.000 0.000 0.000 0.000
#> GSM647575 4 0.5169 0.625 0.272 0.000 0.032 0.696
#> GSM647590 1 0.0000 0.933 1.000 0.000 0.000 0.000
#> GSM647605 1 0.0000 0.933 1.000 0.000 0.000 0.000
#> GSM647607 4 0.5228 0.629 0.268 0.000 0.036 0.696
#> GSM647608 4 0.4406 0.549 0.300 0.000 0.000 0.700
#> GSM647622 1 0.0000 0.933 1.000 0.000 0.000 0.000
#> GSM647623 1 0.0000 0.933 1.000 0.000 0.000 0.000
#> GSM647624 1 0.0000 0.933 1.000 0.000 0.000 0.000
#> GSM647625 1 0.0000 0.933 1.000 0.000 0.000 0.000
#> GSM647534 3 0.5980 0.386 0.396 0.000 0.560 0.044
#> GSM647539 4 0.4978 0.640 0.004 0.000 0.384 0.612
#> GSM647566 3 0.6121 0.389 0.396 0.000 0.552 0.052
#> GSM647589 4 0.4387 0.657 0.200 0.000 0.024 0.776
#> GSM647604 1 0.0000 0.933 1.000 0.000 0.000 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.0000 0.689 0.000 0.000 1.000 0.000 0.000
#> GSM647574 4 0.4306 0.440 0.000 0.000 0.492 0.508 0.000
#> GSM647577 3 0.0000 0.689 0.000 0.000 1.000 0.000 0.000
#> GSM647547 4 0.5386 0.566 0.000 0.064 0.372 0.564 0.000
#> GSM647552 3 0.5491 0.606 0.004 0.000 0.616 0.080 0.300
#> GSM647553 3 0.0162 0.686 0.000 0.000 0.996 0.004 0.000
#> GSM647565 2 0.1768 0.767 0.000 0.924 0.004 0.072 0.000
#> GSM647545 2 0.3620 0.725 0.000 0.824 0.000 0.108 0.068
#> GSM647549 2 0.0703 0.799 0.000 0.976 0.000 0.024 0.000
#> GSM647550 2 0.4443 0.393 0.000 0.524 0.000 0.004 0.472
#> GSM647560 3 0.6215 0.499 0.000 0.140 0.448 0.000 0.412
#> GSM647617 3 0.0000 0.689 0.000 0.000 1.000 0.000 0.000
#> GSM647528 5 0.4833 0.871 0.000 0.024 0.000 0.412 0.564
#> GSM647529 5 0.5757 0.749 0.064 0.008 0.000 0.448 0.480
#> GSM647531 5 0.4610 0.864 0.000 0.012 0.000 0.432 0.556
#> GSM647540 3 0.4909 0.586 0.000 0.028 0.560 0.000 0.412
#> GSM647541 5 0.4452 -0.542 0.000 0.496 0.000 0.004 0.500
#> GSM647546 3 0.6333 -0.505 0.000 0.136 0.432 0.428 0.004
#> GSM647557 5 0.4249 0.864 0.000 0.000 0.000 0.432 0.568
#> GSM647561 5 0.4833 0.871 0.000 0.024 0.000 0.412 0.564
#> GSM647567 3 0.4390 0.592 0.000 0.004 0.568 0.000 0.428
#> GSM647568 2 0.0404 0.794 0.000 0.988 0.000 0.012 0.000
#> GSM647570 2 0.0162 0.800 0.000 0.996 0.000 0.004 0.000
#> GSM647573 4 0.4497 0.376 0.000 0.424 0.008 0.568 0.000
#> GSM647576 3 0.4787 0.541 0.000 0.208 0.712 0.000 0.080
#> GSM647579 3 0.4359 0.599 0.000 0.004 0.584 0.000 0.412
#> GSM647580 3 0.0000 0.689 0.000 0.000 1.000 0.000 0.000
#> GSM647583 3 0.0000 0.689 0.000 0.000 1.000 0.000 0.000
#> GSM647592 5 0.4210 0.873 0.000 0.000 0.000 0.412 0.588
#> GSM647593 5 0.4210 0.873 0.000 0.000 0.000 0.412 0.588
#> GSM647595 5 0.4210 0.873 0.000 0.000 0.000 0.412 0.588
#> GSM647597 5 0.4210 0.873 0.000 0.000 0.000 0.412 0.588
#> GSM647598 5 0.4359 0.873 0.000 0.004 0.000 0.412 0.584
#> GSM647613 2 0.4528 0.656 0.000 0.752 0.000 0.144 0.104
#> GSM647615 2 0.3264 0.663 0.000 0.840 0.132 0.024 0.004
#> GSM647616 3 0.0000 0.689 0.000 0.000 1.000 0.000 0.000
#> GSM647619 5 0.4210 0.873 0.000 0.000 0.000 0.412 0.588
#> GSM647582 5 0.4574 0.873 0.000 0.012 0.000 0.412 0.576
#> GSM647591 5 0.4210 0.873 0.000 0.000 0.000 0.412 0.588
#> GSM647527 5 0.4833 0.871 0.000 0.024 0.000 0.412 0.564
#> GSM647530 2 0.6128 0.378 0.000 0.564 0.000 0.232 0.204
#> GSM647532 4 0.5825 0.548 0.320 0.000 0.116 0.564 0.000
#> GSM647544 2 0.6023 0.385 0.000 0.576 0.000 0.248 0.176
#> GSM647551 5 0.4210 0.873 0.000 0.000 0.000 0.412 0.588
#> GSM647556 3 0.3837 0.645 0.000 0.000 0.692 0.000 0.308
#> GSM647558 2 0.1282 0.799 0.000 0.952 0.000 0.044 0.004
#> GSM647572 4 0.7595 0.379 0.000 0.080 0.172 0.456 0.292
#> GSM647578 5 0.2873 0.257 0.000 0.120 0.020 0.000 0.860
#> GSM647581 2 0.1386 0.799 0.000 0.952 0.000 0.032 0.016
#> GSM647594 5 0.4210 0.873 0.000 0.000 0.000 0.412 0.588
#> GSM647599 1 0.3210 0.589 0.788 0.000 0.212 0.000 0.000
#> GSM647600 3 0.6248 0.441 0.000 0.000 0.468 0.148 0.384
#> GSM647601 5 0.4473 0.873 0.000 0.008 0.000 0.412 0.580
#> GSM647603 5 0.4422 -0.393 0.000 0.012 0.320 0.004 0.664
#> GSM647610 5 0.2536 0.632 0.000 0.000 0.004 0.128 0.868
#> GSM647611 5 0.4574 0.873 0.000 0.012 0.000 0.412 0.576
#> GSM647612 2 0.0162 0.799 0.000 0.996 0.000 0.000 0.004
#> GSM647614 2 0.0404 0.794 0.000 0.988 0.000 0.012 0.000
#> GSM647618 5 0.4833 0.871 0.000 0.024 0.000 0.412 0.564
#> GSM647629 5 0.0794 0.428 0.000 0.028 0.000 0.000 0.972
#> GSM647535 5 0.4833 0.871 0.000 0.024 0.000 0.412 0.564
#> GSM647563 2 0.4016 0.698 0.000 0.796 0.000 0.092 0.112
#> GSM647542 2 0.0000 0.800 0.000 1.000 0.000 0.000 0.000
#> GSM647543 2 0.0000 0.800 0.000 1.000 0.000 0.000 0.000
#> GSM647548 4 0.4219 0.362 0.000 0.416 0.000 0.584 0.000
#> GSM647554 5 0.0794 0.428 0.000 0.028 0.000 0.000 0.972
#> GSM647555 2 0.4074 0.452 0.000 0.636 0.000 0.000 0.364
#> GSM647559 5 0.4833 0.871 0.000 0.024 0.000 0.412 0.564
#> GSM647562 2 0.4221 0.685 0.000 0.780 0.000 0.108 0.112
#> GSM647564 3 0.0609 0.690 0.000 0.000 0.980 0.000 0.020
#> GSM647571 2 0.0000 0.800 0.000 1.000 0.000 0.000 0.000
#> GSM647584 5 0.4210 0.873 0.000 0.000 0.000 0.412 0.588
#> GSM647585 3 0.3816 0.647 0.000 0.000 0.696 0.000 0.304
#> GSM647586 5 0.4833 0.871 0.000 0.024 0.000 0.412 0.564
#> GSM647587 5 0.4833 0.871 0.000 0.024 0.000 0.412 0.564
#> GSM647588 5 0.3876 0.643 0.000 0.032 0.000 0.192 0.776
#> GSM647596 5 0.4752 0.872 0.000 0.020 0.000 0.412 0.568
#> GSM647602 3 0.0000 0.689 0.000 0.000 1.000 0.000 0.000
#> GSM647609 5 0.4210 0.873 0.000 0.000 0.000 0.412 0.588
#> GSM647620 5 0.4833 0.871 0.000 0.024 0.000 0.412 0.564
#> GSM647627 5 0.4833 0.871 0.000 0.024 0.000 0.412 0.564
#> GSM647628 2 0.0865 0.798 0.000 0.972 0.000 0.004 0.024
#> GSM647533 1 0.0000 0.831 1.000 0.000 0.000 0.000 0.000
#> GSM647536 1 0.5647 0.390 0.660 0.008 0.000 0.160 0.172
#> GSM647537 1 0.0000 0.831 1.000 0.000 0.000 0.000 0.000
#> GSM647606 1 0.0000 0.831 1.000 0.000 0.000 0.000 0.000
#> GSM647621 4 0.6073 0.669 0.172 0.000 0.264 0.564 0.000
#> GSM647626 3 0.2966 0.522 0.184 0.000 0.816 0.000 0.000
#> GSM647538 1 0.0000 0.831 1.000 0.000 0.000 0.000 0.000
#> GSM647575 4 0.6621 0.548 0.276 0.116 0.000 0.564 0.044
#> GSM647590 1 0.0000 0.831 1.000 0.000 0.000 0.000 0.000
#> GSM647605 1 0.0000 0.831 1.000 0.000 0.000 0.000 0.000
#> GSM647607 4 0.6726 0.580 0.272 0.116 0.052 0.560 0.000
#> GSM647608 4 0.6199 0.653 0.212 0.000 0.236 0.552 0.000
#> GSM647622 1 0.0000 0.831 1.000 0.000 0.000 0.000 0.000
#> GSM647623 1 0.0000 0.831 1.000 0.000 0.000 0.000 0.000
#> GSM647624 1 0.0000 0.831 1.000 0.000 0.000 0.000 0.000
#> GSM647625 1 0.0000 0.831 1.000 0.000 0.000 0.000 0.000
#> GSM647534 1 0.6373 -0.118 0.424 0.000 0.412 0.000 0.164
#> GSM647539 2 0.2124 0.753 0.004 0.900 0.000 0.096 0.000
#> GSM647566 1 0.6247 -0.112 0.432 0.000 0.424 0.000 0.144
#> GSM647589 4 0.6022 0.663 0.156 0.000 0.280 0.564 0.000
#> GSM647604 1 0.0000 0.831 1.000 0.000 0.000 0.000 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.0000 0.8499 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647574 4 0.3482 0.5923 0.000 0.000 0.316 0.684 0.000 0.000
#> GSM647577 3 0.0000 0.8499 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647547 4 0.3062 0.7829 0.000 0.032 0.144 0.824 0.000 0.000
#> GSM647552 6 0.5973 0.3569 0.000 0.000 0.328 0.120 0.032 0.520
#> GSM647553 3 0.0632 0.8337 0.000 0.000 0.976 0.024 0.000 0.000
#> GSM647565 2 0.2300 0.7566 0.000 0.856 0.000 0.144 0.000 0.000
#> GSM647545 2 0.3979 0.7638 0.000 0.772 0.000 0.160 0.052 0.016
#> GSM647549 2 0.3030 0.7721 0.000 0.816 0.000 0.168 0.008 0.008
#> GSM647550 6 0.0260 0.7732 0.000 0.000 0.000 0.000 0.008 0.992
#> GSM647560 6 0.0363 0.7722 0.000 0.012 0.000 0.000 0.000 0.988
#> GSM647617 3 0.0000 0.8499 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647528 5 0.1141 0.9302 0.000 0.052 0.000 0.000 0.948 0.000
#> GSM647529 5 0.4602 0.6389 0.032 0.024 0.000 0.276 0.668 0.000
#> GSM647531 5 0.3534 0.7935 0.000 0.032 0.000 0.168 0.792 0.008
#> GSM647540 6 0.0260 0.7729 0.000 0.000 0.008 0.000 0.000 0.992
#> GSM647541 6 0.0260 0.7732 0.000 0.000 0.000 0.000 0.008 0.992
#> GSM647546 3 0.4405 0.5844 0.000 0.072 0.688 0.000 0.000 0.240
#> GSM647557 5 0.3030 0.7965 0.000 0.008 0.000 0.168 0.816 0.008
#> GSM647561 5 0.1141 0.9302 0.000 0.052 0.000 0.000 0.948 0.000
#> GSM647567 6 0.0858 0.7673 0.000 0.000 0.028 0.004 0.000 0.968
#> GSM647568 2 0.1088 0.7891 0.000 0.960 0.000 0.024 0.000 0.016
#> GSM647570 2 0.0260 0.8054 0.000 0.992 0.000 0.000 0.000 0.008
#> GSM647573 4 0.2597 0.7867 0.000 0.176 0.000 0.824 0.000 0.000
#> GSM647576 3 0.5705 0.4094 0.000 0.204 0.516 0.000 0.000 0.280
#> GSM647579 6 0.0713 0.7672 0.000 0.000 0.028 0.000 0.000 0.972
#> GSM647580 3 0.0000 0.8499 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647583 3 0.0000 0.8499 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647592 5 0.0260 0.9351 0.000 0.000 0.000 0.000 0.992 0.008
#> GSM647593 5 0.0260 0.9351 0.000 0.000 0.000 0.000 0.992 0.008
#> GSM647595 5 0.0260 0.9351 0.000 0.000 0.000 0.000 0.992 0.008
#> GSM647597 5 0.0405 0.9342 0.000 0.000 0.000 0.004 0.988 0.008
#> GSM647598 5 0.0260 0.9351 0.000 0.000 0.000 0.000 0.992 0.008
#> GSM647613 2 0.3872 0.6724 0.000 0.712 0.000 0.004 0.264 0.020
#> GSM647615 2 0.5337 -0.0626 0.000 0.476 0.448 0.052 0.000 0.024
#> GSM647616 3 0.0000 0.8499 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647619 5 0.0260 0.9351 0.000 0.000 0.000 0.000 0.992 0.008
#> GSM647582 5 0.1949 0.9158 0.000 0.020 0.000 0.036 0.924 0.020
#> GSM647591 5 0.0260 0.9351 0.000 0.000 0.000 0.000 0.992 0.008
#> GSM647527 5 0.1141 0.9302 0.000 0.052 0.000 0.000 0.948 0.000
#> GSM647530 2 0.5507 0.5208 0.000 0.548 0.000 0.168 0.284 0.000
#> GSM647532 4 0.0865 0.8068 0.036 0.000 0.000 0.964 0.000 0.000
#> GSM647544 2 0.3907 0.4086 0.000 0.588 0.000 0.004 0.408 0.000
#> GSM647551 5 0.0405 0.9342 0.000 0.000 0.000 0.004 0.988 0.008
#> GSM647556 6 0.3747 0.3796 0.000 0.000 0.396 0.000 0.000 0.604
#> GSM647558 2 0.2556 0.8016 0.000 0.888 0.000 0.052 0.048 0.012
#> GSM647572 3 0.4263 0.1995 0.000 0.016 0.504 0.000 0.000 0.480
#> GSM647578 6 0.0260 0.7723 0.000 0.008 0.000 0.000 0.000 0.992
#> GSM647581 2 0.3219 0.7704 0.000 0.808 0.000 0.168 0.016 0.008
#> GSM647594 5 0.0260 0.9351 0.000 0.000 0.000 0.000 0.992 0.008
#> GSM647599 1 0.3867 -0.0145 0.512 0.000 0.488 0.000 0.000 0.000
#> GSM647600 6 0.2996 0.6055 0.000 0.000 0.000 0.000 0.228 0.772
#> GSM647601 5 0.0458 0.9354 0.000 0.016 0.000 0.000 0.984 0.000
#> GSM647603 6 0.0806 0.7704 0.000 0.020 0.000 0.000 0.008 0.972
#> GSM647610 6 0.3851 0.0180 0.000 0.000 0.000 0.000 0.460 0.540
#> GSM647611 5 0.0547 0.9352 0.000 0.020 0.000 0.000 0.980 0.000
#> GSM647612 2 0.1267 0.7807 0.000 0.940 0.000 0.000 0.000 0.060
#> GSM647614 2 0.0993 0.7906 0.000 0.964 0.000 0.024 0.000 0.012
#> GSM647618 5 0.1007 0.9321 0.000 0.044 0.000 0.000 0.956 0.000
#> GSM647629 6 0.0790 0.7611 0.000 0.000 0.000 0.000 0.032 0.968
#> GSM647535 5 0.1075 0.9314 0.000 0.048 0.000 0.000 0.952 0.000
#> GSM647563 2 0.3052 0.7146 0.000 0.780 0.000 0.004 0.216 0.000
#> GSM647542 2 0.0000 0.8049 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647543 2 0.0363 0.8024 0.000 0.988 0.000 0.000 0.000 0.012
#> GSM647548 4 0.2135 0.7967 0.000 0.128 0.000 0.872 0.000 0.000
#> GSM647554 6 0.0000 0.7727 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM647555 6 0.2278 0.7070 0.000 0.128 0.000 0.000 0.004 0.868
#> GSM647559 5 0.1075 0.9314 0.000 0.048 0.000 0.000 0.952 0.000
#> GSM647562 2 0.2969 0.7092 0.000 0.776 0.000 0.000 0.224 0.000
#> GSM647564 3 0.1204 0.8133 0.000 0.000 0.944 0.000 0.000 0.056
#> GSM647571 2 0.0000 0.8049 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647584 5 0.0260 0.9351 0.000 0.000 0.000 0.000 0.992 0.008
#> GSM647585 6 0.3592 0.4607 0.000 0.000 0.344 0.000 0.000 0.656
#> GSM647586 5 0.1141 0.9302 0.000 0.052 0.000 0.000 0.948 0.000
#> GSM647587 5 0.1141 0.9302 0.000 0.052 0.000 0.000 0.948 0.000
#> GSM647588 5 0.4493 0.4773 0.000 0.000 0.000 0.052 0.636 0.312
#> GSM647596 5 0.0713 0.9347 0.000 0.028 0.000 0.000 0.972 0.000
#> GSM647602 3 0.0000 0.8499 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647609 5 0.0260 0.9351 0.000 0.000 0.000 0.000 0.992 0.008
#> GSM647620 5 0.1007 0.9321 0.000 0.044 0.000 0.000 0.956 0.000
#> GSM647627 5 0.1141 0.9302 0.000 0.052 0.000 0.000 0.948 0.000
#> GSM647628 2 0.0260 0.8054 0.000 0.992 0.000 0.000 0.008 0.000
#> GSM647533 1 0.0000 0.8980 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647536 1 0.5894 0.2864 0.500 0.004 0.000 0.216 0.280 0.000
#> GSM647537 1 0.0000 0.8980 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647606 1 0.0000 0.8980 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647621 4 0.2778 0.8464 0.168 0.000 0.008 0.824 0.000 0.000
#> GSM647626 3 0.2664 0.6659 0.184 0.000 0.816 0.000 0.000 0.000
#> GSM647538 1 0.0000 0.8980 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647575 4 0.2527 0.8461 0.168 0.000 0.000 0.832 0.000 0.000
#> GSM647590 1 0.0000 0.8980 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647605 1 0.0000 0.8980 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647607 4 0.2668 0.8466 0.168 0.004 0.000 0.828 0.000 0.000
#> GSM647608 4 0.2915 0.8325 0.184 0.000 0.008 0.808 0.000 0.000
#> GSM647622 1 0.0000 0.8980 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647623 1 0.0000 0.8980 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647624 1 0.0000 0.8980 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647625 1 0.0000 0.8980 1.000 0.000 0.000 0.000 0.000 0.000
#> GSM647534 6 0.5445 0.2348 0.404 0.000 0.064 0.000 0.024 0.508
#> GSM647539 2 0.2762 0.7598 0.000 0.804 0.000 0.196 0.000 0.000
#> GSM647566 6 0.5556 0.1301 0.412 0.000 0.136 0.000 0.000 0.452
#> GSM647589 4 0.3073 0.8517 0.152 0.008 0.016 0.824 0.000 0.000
#> GSM647604 1 0.0000 0.8980 1.000 0.000 0.000 0.000 0.000 0.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
Compare the overlap of signatures from different k:
compare_signatures(res)
get_signature() returns a data frame invisibly. TO get the list of signatures, the function
call should be assigned to a variable explicitly. In following code, if plot argument is set
to FALSE, no heatmap is plotted while only the differential analysis is performed.
# code only for demonstration
tb = get_signature(res, k = ..., plot = FALSE)
An example of the output of tb is:
#> which_row fdr mean_1 mean_2 scaled_mean_1 scaled_mean_2 km
#> 1 38 0.042760348 8.373488 9.131774 -0.5533452 0.5164555 1
#> 2 40 0.018707592 7.106213 8.469186 -0.6173731 0.5762149 1
#> 3 55 0.019134737 10.221463 11.207825 -0.6159697 0.5749050 1
#> 4 59 0.006059896 5.921854 7.869574 -0.6899429 0.6439467 1
#> 5 60 0.018055526 8.928898 10.211722 -0.6204761 0.5791110 1
#> 6 98 0.009384629 15.714769 14.887706 0.6635654 -0.6193277 2
...
The columns in tb are:
which_row: row indices corresponding to the input matrix.fdr: FDR for the differential test. mean_x: The mean value in group x.scaled_mean_x: The mean value in group x after rows are scaled.km: Row groups if k-means clustering is applied to rows.UMAP plot which shows how samples are separated.
dimension_reduction(res, k = 2, method = "UMAP")
dimension_reduction(res, k = 3, method = "UMAP")
dimension_reduction(res, k = 4, method = "UMAP")
dimension_reduction(res, k = 5, method = "UMAP")
dimension_reduction(res, k = 6, method = "UMAP")
Following heatmap shows how subgroups are split when increasing k:
collect_classes(res)
Test correlation between subgroups and known annotations. If the known annotation is numeric, one-way ANOVA test is applied, and if the known annotation is discrete, chi-squared contingency table test is applied.
test_to_known_factors(res)
#> n disease.state(p) development.stage(p) other(p) k
#> MAD:pam 86 1.74e-06 0.02199 0.751 2
#> MAD:pam 100 3.34e-14 0.05960 0.278 3
#> MAD:pam 94 1.72e-14 0.00825 0.395 4
#> MAD:pam 84 5.01e-12 0.00749 0.431 5
#> MAD:pam 90 3.22e-12 0.02648 0.536 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["MAD", "mclust"]
# you can also extract it by
# res = res_list["MAD:mclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'MAD' method.
#> Subgroups are detected by 'mclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 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 0.675 0.904 0.950 0.4879 0.499 0.499
#> 3 3 0.848 0.885 0.937 0.1371 0.815 0.674
#> 4 4 0.467 0.662 0.766 0.2419 0.787 0.545
#> 5 5 0.579 0.733 0.814 0.0935 0.931 0.757
#> 6 6 0.674 0.648 0.801 0.0515 0.879 0.560
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
#> GSM647569 1 0.4939 0.9035 0.892 0.108
#> GSM647574 1 0.4939 0.9035 0.892 0.108
#> GSM647577 1 0.4939 0.9035 0.892 0.108
#> GSM647547 1 0.0672 0.9289 0.992 0.008
#> GSM647552 1 0.5737 0.8797 0.864 0.136
#> GSM647553 1 0.4298 0.9105 0.912 0.088
#> GSM647565 1 0.5408 0.8910 0.876 0.124
#> GSM647545 2 0.0000 0.9576 0.000 1.000
#> GSM647549 2 0.0000 0.9576 0.000 1.000
#> GSM647550 2 0.1414 0.9523 0.020 0.980
#> GSM647560 2 0.6531 0.7927 0.168 0.832
#> GSM647617 1 0.4939 0.9035 0.892 0.108
#> GSM647528 2 0.0000 0.9576 0.000 1.000
#> GSM647529 1 0.1184 0.9259 0.984 0.016
#> GSM647531 2 0.0376 0.9567 0.004 0.996
#> GSM647540 2 0.8955 0.5280 0.312 0.688
#> GSM647541 2 0.1414 0.9523 0.020 0.980
#> GSM647546 1 0.5408 0.8910 0.876 0.124
#> GSM647557 2 0.1414 0.9523 0.020 0.980
#> GSM647561 2 0.0000 0.9576 0.000 1.000
#> GSM647567 1 0.8909 0.6318 0.692 0.308
#> GSM647568 2 0.3431 0.9190 0.064 0.936
#> GSM647570 2 0.0000 0.9576 0.000 1.000
#> GSM647573 1 0.0376 0.9290 0.996 0.004
#> GSM647576 2 0.9977 0.0168 0.472 0.528
#> GSM647579 1 0.8386 0.7047 0.732 0.268
#> GSM647580 1 0.4939 0.9035 0.892 0.108
#> GSM647583 1 0.4939 0.9035 0.892 0.108
#> GSM647592 2 0.1184 0.9536 0.016 0.984
#> GSM647593 2 0.0000 0.9576 0.000 1.000
#> GSM647595 2 0.0000 0.9576 0.000 1.000
#> GSM647597 1 0.1843 0.9220 0.972 0.028
#> GSM647598 2 0.0000 0.9576 0.000 1.000
#> GSM647613 2 0.0000 0.9576 0.000 1.000
#> GSM647615 2 0.9491 0.3846 0.368 0.632
#> GSM647616 1 0.4939 0.9035 0.892 0.108
#> GSM647619 2 0.0000 0.9576 0.000 1.000
#> GSM647582 2 0.1414 0.9523 0.020 0.980
#> GSM647591 2 0.0000 0.9576 0.000 1.000
#> GSM647527 2 0.0000 0.9576 0.000 1.000
#> GSM647530 2 0.6048 0.8368 0.148 0.852
#> GSM647532 1 0.0000 0.9289 1.000 0.000
#> GSM647544 2 0.0000 0.9576 0.000 1.000
#> GSM647551 2 0.2778 0.9337 0.048 0.952
#> GSM647556 1 0.4939 0.9035 0.892 0.108
#> GSM647558 2 0.0000 0.9576 0.000 1.000
#> GSM647572 1 0.8016 0.7435 0.756 0.244
#> GSM647578 2 0.2778 0.9341 0.048 0.952
#> GSM647581 2 0.0000 0.9576 0.000 1.000
#> GSM647594 2 0.1414 0.9523 0.020 0.980
#> GSM647599 1 0.0000 0.9289 1.000 0.000
#> GSM647600 1 0.9427 0.5183 0.640 0.360
#> GSM647601 2 0.0000 0.9576 0.000 1.000
#> GSM647603 2 0.5408 0.8519 0.124 0.876
#> GSM647610 2 0.2948 0.9310 0.052 0.948
#> GSM647611 2 0.0000 0.9576 0.000 1.000
#> GSM647612 2 0.1414 0.9523 0.020 0.980
#> GSM647614 2 0.1843 0.9481 0.028 0.972
#> GSM647618 2 0.0000 0.9576 0.000 1.000
#> GSM647629 2 0.2236 0.9427 0.036 0.964
#> GSM647535 2 0.0000 0.9576 0.000 1.000
#> GSM647563 2 0.0000 0.9576 0.000 1.000
#> GSM647542 2 0.1633 0.9503 0.024 0.976
#> GSM647543 2 0.2423 0.9401 0.040 0.960
#> GSM647548 1 0.1843 0.9253 0.972 0.028
#> GSM647554 2 0.1414 0.9523 0.020 0.980
#> GSM647555 2 0.1414 0.9523 0.020 0.980
#> GSM647559 2 0.0000 0.9576 0.000 1.000
#> GSM647562 2 0.0000 0.9576 0.000 1.000
#> GSM647564 1 0.4939 0.9035 0.892 0.108
#> GSM647571 2 0.2423 0.9401 0.040 0.960
#> GSM647584 2 0.0000 0.9576 0.000 1.000
#> GSM647585 1 0.4939 0.9035 0.892 0.108
#> GSM647586 2 0.0000 0.9576 0.000 1.000
#> GSM647587 2 0.0000 0.9576 0.000 1.000
#> GSM647588 2 0.0000 0.9576 0.000 1.000
#> GSM647596 2 0.0000 0.9576 0.000 1.000
#> GSM647602 1 0.4939 0.9035 0.892 0.108
#> GSM647609 2 0.0000 0.9576 0.000 1.000
#> GSM647620 2 0.0000 0.9576 0.000 1.000
#> GSM647627 2 0.0000 0.9576 0.000 1.000
#> GSM647628 2 0.0000 0.9576 0.000 1.000
#> GSM647533 1 0.0000 0.9289 1.000 0.000
#> GSM647536 1 0.0000 0.9289 1.000 0.000
#> GSM647537 1 0.0000 0.9289 1.000 0.000
#> GSM647606 1 0.0000 0.9289 1.000 0.000
#> GSM647621 1 0.0000 0.9289 1.000 0.000
#> GSM647626 1 0.4815 0.9049 0.896 0.104
#> GSM647538 1 0.0000 0.9289 1.000 0.000
#> GSM647575 1 0.0000 0.9289 1.000 0.000
#> GSM647590 1 0.0000 0.9289 1.000 0.000
#> GSM647605 1 0.0000 0.9289 1.000 0.000
#> GSM647607 1 0.0000 0.9289 1.000 0.000
#> GSM647608 1 0.0000 0.9289 1.000 0.000
#> GSM647622 1 0.0000 0.9289 1.000 0.000
#> GSM647623 1 0.0000 0.9289 1.000 0.000
#> GSM647624 1 0.0000 0.9289 1.000 0.000
#> GSM647625 1 0.0000 0.9289 1.000 0.000
#> GSM647534 1 0.0938 0.9286 0.988 0.012
#> GSM647539 1 0.0000 0.9289 1.000 0.000
#> GSM647566 1 0.0376 0.9291 0.996 0.004
#> GSM647589 1 0.0000 0.9289 1.000 0.000
#> GSM647604 1 0.0000 0.9289 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 3 0.3116 0.943 0.108 0.000 0.892
#> GSM647574 1 0.5882 0.432 0.652 0.000 0.348
#> GSM647577 3 0.1643 0.961 0.044 0.000 0.956
#> GSM647547 1 0.1753 0.859 0.952 0.000 0.048
#> GSM647552 2 0.7576 0.556 0.276 0.648 0.076
#> GSM647553 1 0.5591 0.524 0.696 0.000 0.304
#> GSM647565 1 0.6168 0.320 0.588 0.412 0.000
#> GSM647545 2 0.0000 0.948 0.000 1.000 0.000
#> GSM647549 2 0.0000 0.948 0.000 1.000 0.000
#> GSM647550 2 0.2066 0.936 0.000 0.940 0.060
#> GSM647560 2 0.3670 0.909 0.020 0.888 0.092
#> GSM647617 3 0.1643 0.961 0.044 0.000 0.956
#> GSM647528 2 0.0000 0.948 0.000 1.000 0.000
#> GSM647529 1 0.0237 0.886 0.996 0.004 0.000
#> GSM647531 2 0.0000 0.948 0.000 1.000 0.000
#> GSM647540 2 0.4316 0.890 0.044 0.868 0.088
#> GSM647541 2 0.2200 0.936 0.004 0.940 0.056
#> GSM647546 2 0.8298 0.530 0.152 0.628 0.220
#> GSM647557 2 0.0000 0.948 0.000 1.000 0.000
#> GSM647561 2 0.0000 0.948 0.000 1.000 0.000
#> GSM647567 2 0.2955 0.914 0.080 0.912 0.008
#> GSM647568 2 0.3572 0.916 0.040 0.900 0.060
#> GSM647570 2 0.0237 0.948 0.000 0.996 0.004
#> GSM647573 1 0.1643 0.862 0.956 0.000 0.044
#> GSM647576 2 0.4316 0.890 0.044 0.868 0.088
#> GSM647579 2 0.5737 0.818 0.104 0.804 0.092
#> GSM647580 3 0.1643 0.961 0.044 0.000 0.956
#> GSM647583 3 0.1643 0.961 0.044 0.000 0.956
#> GSM647592 2 0.1315 0.945 0.008 0.972 0.020
#> GSM647593 2 0.0892 0.946 0.000 0.980 0.020
#> GSM647595 2 0.0892 0.946 0.000 0.980 0.020
#> GSM647597 1 0.4605 0.636 0.796 0.204 0.000
#> GSM647598 2 0.0000 0.948 0.000 1.000 0.000
#> GSM647613 2 0.0000 0.948 0.000 1.000 0.000
#> GSM647615 2 0.3481 0.917 0.044 0.904 0.052
#> GSM647616 3 0.1643 0.961 0.044 0.000 0.956
#> GSM647619 2 0.0892 0.946 0.000 0.980 0.020
#> GSM647582 2 0.2599 0.935 0.016 0.932 0.052
#> GSM647591 2 0.0892 0.946 0.000 0.980 0.020
#> GSM647527 2 0.0000 0.948 0.000 1.000 0.000
#> GSM647530 1 0.6260 0.225 0.552 0.448 0.000
#> GSM647532 1 0.0000 0.887 1.000 0.000 0.000
#> GSM647544 2 0.0000 0.948 0.000 1.000 0.000
#> GSM647551 2 0.1860 0.942 0.000 0.948 0.052
#> GSM647556 3 0.3619 0.913 0.136 0.000 0.864
#> GSM647558 2 0.0237 0.948 0.000 0.996 0.004
#> GSM647572 2 0.5435 0.827 0.048 0.808 0.144
#> GSM647578 2 0.2846 0.930 0.020 0.924 0.056
#> GSM647581 2 0.0000 0.948 0.000 1.000 0.000
#> GSM647594 2 0.2261 0.923 0.068 0.932 0.000
#> GSM647599 1 0.0000 0.887 1.000 0.000 0.000
#> GSM647600 2 0.4316 0.890 0.044 0.868 0.088
#> GSM647601 2 0.0892 0.946 0.000 0.980 0.020
#> GSM647603 2 0.3587 0.910 0.020 0.892 0.088
#> GSM647610 2 0.2176 0.939 0.020 0.948 0.032
#> GSM647611 2 0.0237 0.948 0.000 0.996 0.004
#> GSM647612 2 0.2947 0.929 0.020 0.920 0.060
#> GSM647614 2 0.2846 0.931 0.020 0.924 0.056
#> GSM647618 2 0.0000 0.948 0.000 1.000 0.000
#> GSM647629 2 0.2846 0.930 0.020 0.924 0.056
#> GSM647535 2 0.0237 0.948 0.000 0.996 0.004
#> GSM647563 2 0.0000 0.948 0.000 1.000 0.000
#> GSM647542 2 0.2947 0.929 0.020 0.920 0.060
#> GSM647543 2 0.2947 0.929 0.020 0.920 0.060
#> GSM647548 1 0.4887 0.606 0.772 0.228 0.000
#> GSM647554 2 0.2448 0.934 0.000 0.924 0.076
#> GSM647555 2 0.2066 0.936 0.000 0.940 0.060
#> GSM647559 2 0.0000 0.948 0.000 1.000 0.000
#> GSM647562 2 0.0000 0.948 0.000 1.000 0.000
#> GSM647564 3 0.3116 0.943 0.108 0.000 0.892
#> GSM647571 2 0.3356 0.922 0.036 0.908 0.056
#> GSM647584 2 0.0892 0.946 0.000 0.980 0.020
#> GSM647585 3 0.3192 0.940 0.112 0.000 0.888
#> GSM647586 2 0.0000 0.948 0.000 1.000 0.000
#> GSM647587 2 0.0000 0.948 0.000 1.000 0.000
#> GSM647588 2 0.0000 0.948 0.000 1.000 0.000
#> GSM647596 2 0.0000 0.948 0.000 1.000 0.000
#> GSM647602 3 0.1964 0.960 0.056 0.000 0.944
#> GSM647609 2 0.0892 0.946 0.000 0.980 0.020
#> GSM647620 2 0.0000 0.948 0.000 1.000 0.000
#> GSM647627 2 0.0000 0.948 0.000 1.000 0.000
#> GSM647628 2 0.0237 0.948 0.000 0.996 0.004
#> GSM647533 1 0.0892 0.880 0.980 0.000 0.020
#> GSM647536 1 0.0000 0.887 1.000 0.000 0.000
#> GSM647537 1 0.0892 0.880 0.980 0.000 0.020
#> GSM647606 1 0.0892 0.880 0.980 0.000 0.020
#> GSM647621 1 0.0000 0.887 1.000 0.000 0.000
#> GSM647626 1 0.4504 0.693 0.804 0.000 0.196
#> GSM647538 1 0.0892 0.880 0.980 0.000 0.020
#> GSM647575 1 0.0000 0.887 1.000 0.000 0.000
#> GSM647590 1 0.0000 0.887 1.000 0.000 0.000
#> GSM647605 1 0.0000 0.887 1.000 0.000 0.000
#> GSM647607 1 0.0000 0.887 1.000 0.000 0.000
#> GSM647608 1 0.0000 0.887 1.000 0.000 0.000
#> GSM647622 1 0.0892 0.880 0.980 0.000 0.020
#> GSM647623 1 0.0892 0.880 0.980 0.000 0.020
#> GSM647624 1 0.0000 0.887 1.000 0.000 0.000
#> GSM647625 1 0.0892 0.880 0.980 0.000 0.020
#> GSM647534 1 0.1964 0.839 0.944 0.056 0.000
#> GSM647539 1 0.1163 0.869 0.972 0.028 0.000
#> GSM647566 1 0.0000 0.887 1.000 0.000 0.000
#> GSM647589 1 0.0000 0.887 1.000 0.000 0.000
#> GSM647604 1 0.0000 0.887 1.000 0.000 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 3 0.5770 0.7621 0.148 0.000 0.712 0.140
#> GSM647574 3 0.7307 0.3418 0.404 0.000 0.444 0.152
#> GSM647577 3 0.3377 0.7725 0.012 0.000 0.848 0.140
#> GSM647547 1 0.6916 0.5807 0.588 0.000 0.176 0.236
#> GSM647552 4 0.9229 0.1776 0.224 0.220 0.116 0.440
#> GSM647553 3 0.7313 0.3051 0.416 0.000 0.432 0.152
#> GSM647565 4 0.6074 -0.3808 0.456 0.044 0.000 0.500
#> GSM647545 2 0.4040 0.6051 0.000 0.752 0.000 0.248
#> GSM647549 2 0.4250 0.5635 0.000 0.724 0.000 0.276
#> GSM647550 4 0.4331 0.6367 0.000 0.288 0.000 0.712
#> GSM647560 4 0.5627 0.7391 0.032 0.200 0.036 0.732
#> GSM647617 3 0.3377 0.7725 0.012 0.000 0.848 0.140
#> GSM647528 2 0.1118 0.7982 0.000 0.964 0.000 0.036
#> GSM647529 1 0.3873 0.8211 0.772 0.000 0.000 0.228
#> GSM647531 2 0.1211 0.7975 0.000 0.960 0.000 0.040
#> GSM647540 4 0.5641 0.6767 0.056 0.096 0.076 0.772
#> GSM647541 4 0.4955 0.5788 0.000 0.344 0.008 0.648
#> GSM647546 4 0.7867 -0.1707 0.148 0.024 0.344 0.484
#> GSM647557 2 0.1211 0.7975 0.000 0.960 0.000 0.040
#> GSM647561 2 0.1118 0.7982 0.000 0.964 0.000 0.036
#> GSM647567 4 0.7652 0.4425 0.288 0.156 0.020 0.536
#> GSM647568 4 0.4004 0.7478 0.024 0.164 0.000 0.812
#> GSM647570 2 0.4431 0.5256 0.000 0.696 0.000 0.304
#> GSM647573 1 0.6613 0.6236 0.596 0.000 0.116 0.288
#> GSM647576 4 0.5342 0.6789 0.044 0.092 0.076 0.788
#> GSM647579 4 0.6721 0.5355 0.148 0.068 0.088 0.696
#> GSM647580 3 0.3377 0.7725 0.012 0.000 0.848 0.140
#> GSM647583 3 0.3377 0.7725 0.012 0.000 0.848 0.140
#> GSM647592 2 0.5325 0.7072 0.044 0.788 0.100 0.068
#> GSM647593 2 0.4405 0.7026 0.000 0.800 0.152 0.048
#> GSM647595 2 0.4405 0.7026 0.000 0.800 0.152 0.048
#> GSM647597 1 0.7001 0.5037 0.580 0.224 0.000 0.196
#> GSM647598 2 0.0000 0.7937 0.000 1.000 0.000 0.000
#> GSM647613 2 0.1302 0.7969 0.000 0.956 0.000 0.044
#> GSM647615 4 0.4956 0.7434 0.044 0.168 0.012 0.776
#> GSM647616 3 0.3377 0.7725 0.012 0.000 0.848 0.140
#> GSM647619 2 0.4322 0.7046 0.000 0.804 0.152 0.044
#> GSM647582 2 0.5773 -0.0672 0.004 0.564 0.024 0.408
#> GSM647591 2 0.4237 0.7068 0.000 0.808 0.152 0.040
#> GSM647527 2 0.1118 0.7982 0.000 0.964 0.000 0.036
#> GSM647530 2 0.7710 -0.1484 0.368 0.408 0.000 0.224
#> GSM647532 1 0.3873 0.8211 0.772 0.000 0.000 0.228
#> GSM647544 2 0.1557 0.7928 0.000 0.944 0.000 0.056
#> GSM647551 2 0.7111 -0.1139 0.004 0.480 0.112 0.404
#> GSM647556 3 0.6698 0.6644 0.256 0.000 0.604 0.140
#> GSM647558 2 0.4331 0.5513 0.000 0.712 0.000 0.288
#> GSM647572 4 0.5401 0.6936 0.052 0.104 0.060 0.784
#> GSM647578 4 0.4745 0.7487 0.036 0.176 0.008 0.780
#> GSM647581 2 0.2281 0.7721 0.000 0.904 0.000 0.096
#> GSM647594 2 0.2732 0.7448 0.076 0.904 0.008 0.012
#> GSM647599 1 0.3105 0.8323 0.856 0.000 0.004 0.140
#> GSM647600 4 0.8357 0.4445 0.148 0.244 0.076 0.532
#> GSM647601 2 0.2335 0.7732 0.000 0.920 0.060 0.020
#> GSM647603 4 0.5752 0.7386 0.036 0.204 0.036 0.724
#> GSM647610 4 0.6442 0.3962 0.068 0.440 0.000 0.492
#> GSM647611 2 0.1398 0.7859 0.000 0.956 0.040 0.004
#> GSM647612 4 0.4008 0.6932 0.000 0.244 0.000 0.756
#> GSM647614 4 0.4262 0.7069 0.008 0.236 0.000 0.756
#> GSM647618 2 0.0592 0.7974 0.000 0.984 0.000 0.016
#> GSM647629 4 0.5772 0.6614 0.024 0.312 0.016 0.648
#> GSM647535 2 0.4679 0.3920 0.000 0.648 0.000 0.352
#> GSM647563 2 0.3311 0.6999 0.000 0.828 0.000 0.172
#> GSM647542 4 0.4137 0.7306 0.012 0.208 0.000 0.780
#> GSM647543 4 0.4284 0.7168 0.012 0.224 0.000 0.764
#> GSM647548 1 0.5088 0.5543 0.572 0.004 0.000 0.424
#> GSM647554 4 0.5634 0.6302 0.008 0.312 0.028 0.652
#> GSM647555 4 0.4406 0.6208 0.000 0.300 0.000 0.700
#> GSM647559 2 0.2469 0.7624 0.000 0.892 0.000 0.108
#> GSM647562 2 0.1557 0.7928 0.000 0.944 0.000 0.056
#> GSM647564 3 0.7216 0.5966 0.148 0.004 0.540 0.308
#> GSM647571 4 0.4054 0.7452 0.016 0.188 0.000 0.796
#> GSM647584 2 0.4405 0.7026 0.000 0.800 0.152 0.048
#> GSM647585 3 0.5770 0.7621 0.148 0.000 0.712 0.140
#> GSM647586 2 0.0707 0.7969 0.000 0.980 0.000 0.020
#> GSM647587 2 0.0707 0.7978 0.000 0.980 0.000 0.020
#> GSM647588 2 0.3801 0.6361 0.000 0.780 0.000 0.220
#> GSM647596 2 0.1389 0.7954 0.000 0.952 0.000 0.048
#> GSM647602 3 0.3999 0.7756 0.036 0.000 0.824 0.140
#> GSM647609 2 0.3013 0.7595 0.000 0.888 0.080 0.032
#> GSM647620 2 0.1677 0.7846 0.000 0.948 0.040 0.012
#> GSM647627 2 0.0188 0.7928 0.000 0.996 0.000 0.004
#> GSM647628 2 0.4406 0.5333 0.000 0.700 0.000 0.300
#> GSM647533 1 0.0188 0.7771 0.996 0.000 0.000 0.004
#> GSM647536 1 0.3873 0.8211 0.772 0.000 0.000 0.228
#> GSM647537 1 0.0188 0.7771 0.996 0.000 0.000 0.004
#> GSM647606 1 0.0188 0.7771 0.996 0.000 0.000 0.004
#> GSM647621 1 0.4284 0.8213 0.780 0.000 0.020 0.200
#> GSM647626 3 0.7142 0.5467 0.324 0.000 0.524 0.152
#> GSM647538 1 0.0188 0.7771 0.996 0.000 0.000 0.004
#> GSM647575 1 0.3873 0.8211 0.772 0.000 0.000 0.228
#> GSM647590 1 0.2345 0.8276 0.900 0.000 0.000 0.100
#> GSM647605 1 0.2345 0.8276 0.900 0.000 0.000 0.100
#> GSM647607 1 0.3873 0.8211 0.772 0.000 0.000 0.228
#> GSM647608 1 0.3123 0.8329 0.844 0.000 0.000 0.156
#> GSM647622 1 0.0188 0.7771 0.996 0.000 0.000 0.004
#> GSM647623 1 0.0188 0.7771 0.996 0.000 0.000 0.004
#> GSM647624 1 0.2345 0.8276 0.900 0.000 0.000 0.100
#> GSM647625 1 0.0188 0.7771 0.996 0.000 0.000 0.004
#> GSM647534 1 0.3754 0.8219 0.852 0.008 0.028 0.112
#> GSM647539 1 0.3942 0.8176 0.764 0.000 0.000 0.236
#> GSM647566 1 0.3999 0.8210 0.824 0.000 0.036 0.140
#> GSM647589 1 0.6753 0.6141 0.608 0.000 0.164 0.228
#> GSM647604 1 0.2345 0.8276 0.900 0.000 0.000 0.100
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.2889 0.896 0.084 0.000 0.880 0.020 0.016
#> GSM647574 3 0.2981 0.894 0.084 0.000 0.876 0.024 0.016
#> GSM647577 3 0.0162 0.860 0.000 0.000 0.996 0.000 0.004
#> GSM647547 4 0.4568 0.614 0.304 0.000 0.012 0.672 0.012
#> GSM647552 5 0.5931 0.563 0.084 0.140 0.000 0.088 0.688
#> GSM647553 3 0.2981 0.894 0.084 0.000 0.876 0.024 0.016
#> GSM647565 4 0.5777 0.573 0.104 0.008 0.000 0.612 0.276
#> GSM647545 2 0.3911 0.734 0.000 0.796 0.000 0.060 0.144
#> GSM647549 2 0.4179 0.715 0.000 0.776 0.000 0.072 0.152
#> GSM647550 5 0.4841 0.684 0.000 0.208 0.000 0.084 0.708
#> GSM647560 5 0.4007 0.661 0.084 0.020 0.076 0.000 0.820
#> GSM647617 3 0.0162 0.860 0.000 0.000 0.996 0.000 0.004
#> GSM647528 2 0.0451 0.851 0.000 0.988 0.000 0.004 0.008
#> GSM647529 4 0.2522 0.817 0.108 0.000 0.000 0.880 0.012
#> GSM647531 2 0.0794 0.845 0.000 0.972 0.000 0.000 0.028
#> GSM647540 5 0.4155 0.638 0.084 0.000 0.080 0.024 0.812
#> GSM647541 5 0.2690 0.708 0.000 0.156 0.000 0.000 0.844
#> GSM647546 3 0.5782 0.588 0.084 0.000 0.640 0.024 0.252
#> GSM647557 2 0.2011 0.839 0.004 0.908 0.000 0.000 0.088
#> GSM647561 2 0.0290 0.850 0.000 0.992 0.000 0.000 0.008
#> GSM647567 5 0.4297 0.647 0.084 0.060 0.008 0.032 0.816
#> GSM647568 5 0.4637 0.692 0.000 0.160 0.000 0.100 0.740
#> GSM647570 2 0.4049 0.743 0.000 0.792 0.000 0.084 0.124
#> GSM647573 4 0.3544 0.787 0.164 0.000 0.008 0.812 0.016
#> GSM647576 5 0.4212 0.637 0.084 0.000 0.084 0.024 0.808
#> GSM647579 5 0.5052 0.581 0.084 0.000 0.156 0.024 0.736
#> GSM647580 3 0.0162 0.860 0.000 0.000 0.996 0.000 0.004
#> GSM647583 3 0.0162 0.860 0.000 0.000 0.996 0.000 0.004
#> GSM647592 2 0.3805 0.778 0.008 0.784 0.000 0.016 0.192
#> GSM647593 2 0.3866 0.772 0.000 0.780 0.004 0.024 0.192
#> GSM647595 2 0.3866 0.772 0.000 0.780 0.004 0.024 0.192
#> GSM647597 4 0.6885 0.466 0.112 0.228 0.000 0.576 0.084
#> GSM647598 2 0.0451 0.849 0.000 0.988 0.000 0.008 0.004
#> GSM647613 2 0.0609 0.848 0.000 0.980 0.000 0.000 0.020
#> GSM647615 5 0.5544 0.672 0.084 0.168 0.000 0.044 0.704
#> GSM647616 3 0.0162 0.860 0.000 0.000 0.996 0.000 0.004
#> GSM647619 2 0.3866 0.772 0.000 0.780 0.004 0.024 0.192
#> GSM647582 5 0.4464 0.218 0.000 0.408 0.000 0.008 0.584
#> GSM647591 2 0.3583 0.777 0.000 0.792 0.004 0.012 0.192
#> GSM647527 2 0.0451 0.851 0.000 0.988 0.000 0.004 0.008
#> GSM647530 2 0.6132 0.283 0.092 0.580 0.000 0.304 0.024
#> GSM647532 4 0.2574 0.818 0.112 0.000 0.000 0.876 0.012
#> GSM647544 2 0.0510 0.849 0.000 0.984 0.000 0.000 0.016
#> GSM647551 5 0.4508 0.334 0.000 0.332 0.000 0.020 0.648
#> GSM647556 3 0.2889 0.896 0.084 0.000 0.880 0.020 0.016
#> GSM647558 2 0.4049 0.742 0.000 0.792 0.000 0.084 0.124
#> GSM647572 5 0.4571 0.642 0.084 0.012 0.076 0.028 0.800
#> GSM647578 5 0.3815 0.688 0.080 0.088 0.000 0.008 0.824
#> GSM647581 2 0.2127 0.791 0.000 0.892 0.000 0.000 0.108
#> GSM647594 2 0.3678 0.782 0.040 0.816 0.000 0.004 0.140
#> GSM647599 1 0.3383 0.777 0.856 0.000 0.072 0.060 0.012
#> GSM647600 5 0.4463 0.634 0.076 0.112 0.000 0.024 0.788
#> GSM647601 2 0.3438 0.788 0.000 0.808 0.000 0.020 0.172
#> GSM647603 5 0.2913 0.678 0.080 0.032 0.004 0.004 0.880
#> GSM647610 5 0.2864 0.641 0.000 0.112 0.000 0.024 0.864
#> GSM647611 2 0.2763 0.810 0.000 0.848 0.000 0.004 0.148
#> GSM647612 5 0.5505 0.563 0.000 0.304 0.000 0.092 0.604
#> GSM647614 5 0.5717 0.434 0.000 0.368 0.000 0.092 0.540
#> GSM647618 2 0.0290 0.850 0.000 0.992 0.000 0.000 0.008
#> GSM647629 5 0.2230 0.658 0.000 0.116 0.000 0.000 0.884
#> GSM647535 2 0.3039 0.746 0.000 0.808 0.000 0.000 0.192
#> GSM647563 2 0.2127 0.791 0.000 0.892 0.000 0.000 0.108
#> GSM647542 5 0.5216 0.640 0.000 0.248 0.000 0.092 0.660
#> GSM647543 5 0.4535 0.692 0.000 0.160 0.000 0.092 0.748
#> GSM647548 4 0.4841 0.701 0.104 0.004 0.000 0.732 0.160
#> GSM647554 5 0.2674 0.643 0.000 0.120 0.000 0.012 0.868
#> GSM647555 5 0.5599 0.521 0.000 0.328 0.000 0.092 0.580
#> GSM647559 2 0.1851 0.809 0.000 0.912 0.000 0.000 0.088
#> GSM647562 2 0.0404 0.850 0.000 0.988 0.000 0.000 0.012
#> GSM647564 3 0.2889 0.896 0.084 0.000 0.880 0.020 0.016
#> GSM647571 5 0.5707 0.450 0.000 0.364 0.000 0.092 0.544
#> GSM647584 2 0.3866 0.772 0.000 0.780 0.004 0.024 0.192
#> GSM647585 3 0.2889 0.896 0.084 0.000 0.880 0.020 0.016
#> GSM647586 2 0.0451 0.850 0.000 0.988 0.000 0.008 0.004
#> GSM647587 2 0.0162 0.850 0.000 0.996 0.000 0.000 0.004
#> GSM647588 2 0.3550 0.687 0.000 0.760 0.000 0.004 0.236
#> GSM647596 2 0.0510 0.849 0.000 0.984 0.000 0.000 0.016
#> GSM647602 3 0.2233 0.893 0.080 0.000 0.904 0.000 0.016
#> GSM647609 2 0.3513 0.783 0.000 0.800 0.000 0.020 0.180
#> GSM647620 2 0.2522 0.827 0.000 0.880 0.000 0.012 0.108
#> GSM647627 2 0.0566 0.850 0.000 0.984 0.000 0.012 0.004
#> GSM647628 2 0.4226 0.728 0.000 0.776 0.000 0.084 0.140
#> GSM647533 1 0.0000 0.823 1.000 0.000 0.000 0.000 0.000
#> GSM647536 4 0.2574 0.818 0.112 0.000 0.000 0.876 0.012
#> GSM647537 1 0.0000 0.823 1.000 0.000 0.000 0.000 0.000
#> GSM647606 1 0.0162 0.824 0.996 0.000 0.000 0.004 0.000
#> GSM647621 1 0.3863 0.670 0.740 0.000 0.000 0.248 0.012
#> GSM647626 3 0.3038 0.891 0.088 0.000 0.872 0.024 0.016
#> GSM647538 1 0.0162 0.824 0.996 0.000 0.000 0.004 0.000
#> GSM647575 4 0.2771 0.814 0.128 0.000 0.000 0.860 0.012
#> GSM647590 1 0.3280 0.751 0.812 0.000 0.000 0.176 0.012
#> GSM647605 1 0.3659 0.677 0.768 0.000 0.000 0.220 0.012
#> GSM647607 4 0.2771 0.814 0.128 0.000 0.000 0.860 0.012
#> GSM647608 1 0.3863 0.670 0.740 0.000 0.000 0.248 0.012
#> GSM647622 1 0.0000 0.823 1.000 0.000 0.000 0.000 0.000
#> GSM647623 1 0.0000 0.823 1.000 0.000 0.000 0.000 0.000
#> GSM647624 1 0.2953 0.774 0.844 0.000 0.000 0.144 0.012
#> GSM647625 1 0.0000 0.823 1.000 0.000 0.000 0.000 0.000
#> GSM647534 1 0.6846 0.207 0.476 0.012 0.000 0.232 0.280
#> GSM647539 4 0.2574 0.818 0.112 0.000 0.000 0.876 0.012
#> GSM647566 1 0.5097 0.679 0.728 0.000 0.108 0.148 0.016
#> GSM647589 4 0.4723 0.490 0.368 0.000 0.008 0.612 0.012
#> GSM647604 1 0.2997 0.766 0.840 0.000 0.000 0.148 0.012
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.2260 0.8701 0.000 0.000 0.860 0.140 0.000 0.000
#> GSM647574 3 0.2664 0.8300 0.000 0.000 0.816 0.184 0.000 0.000
#> GSM647577 3 0.0000 0.8508 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647547 4 0.2156 0.7498 0.020 0.000 0.048 0.912 0.000 0.020
#> GSM647552 5 0.6351 0.3559 0.000 0.056 0.000 0.180 0.540 0.224
#> GSM647553 3 0.2631 0.8345 0.000 0.000 0.820 0.180 0.000 0.000
#> GSM647565 4 0.3254 0.6829 0.000 0.000 0.000 0.820 0.056 0.124
#> GSM647545 2 0.1387 0.8252 0.000 0.932 0.000 0.000 0.000 0.068
#> GSM647549 2 0.2554 0.7771 0.000 0.876 0.000 0.000 0.048 0.076
#> GSM647550 5 0.4118 -0.0205 0.000 0.028 0.000 0.000 0.660 0.312
#> GSM647560 5 0.4039 0.2092 0.000 0.000 0.004 0.040 0.724 0.232
#> GSM647617 3 0.0000 0.8508 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647528 2 0.0146 0.8464 0.000 0.996 0.000 0.000 0.000 0.004
#> GSM647529 4 0.1471 0.7512 0.000 0.000 0.000 0.932 0.004 0.064
#> GSM647531 2 0.0547 0.8453 0.000 0.980 0.000 0.000 0.000 0.020
#> GSM647540 5 0.4210 0.3414 0.000 0.000 0.044 0.136 0.772 0.048
#> GSM647541 5 0.3936 0.2914 0.000 0.060 0.000 0.004 0.760 0.176
#> GSM647546 3 0.5874 0.5962 0.000 0.000 0.616 0.156 0.172 0.056
#> GSM647557 2 0.1225 0.8345 0.000 0.952 0.000 0.000 0.036 0.012
#> GSM647561 2 0.0260 0.8469 0.000 0.992 0.000 0.000 0.000 0.008
#> GSM647567 5 0.4141 0.3843 0.000 0.000 0.000 0.168 0.740 0.092
#> GSM647568 6 0.3482 0.9712 0.000 0.000 0.000 0.000 0.316 0.684
#> GSM647570 2 0.3746 0.6866 0.000 0.760 0.000 0.000 0.048 0.192
#> GSM647573 4 0.0692 0.7573 0.000 0.000 0.004 0.976 0.000 0.020
#> GSM647576 5 0.5164 0.1064 0.000 0.000 0.072 0.040 0.664 0.224
#> GSM647579 5 0.5154 0.2269 0.000 0.000 0.140 0.136 0.688 0.036
#> GSM647580 3 0.0000 0.8508 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647583 3 0.0000 0.8508 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647592 5 0.5036 0.1276 0.004 0.432 0.000 0.016 0.516 0.032
#> GSM647593 5 0.5056 0.1563 0.004 0.424 0.000 0.000 0.508 0.064
#> GSM647595 5 0.5060 0.1480 0.004 0.428 0.000 0.000 0.504 0.064
#> GSM647597 4 0.5436 0.6231 0.000 0.084 0.000 0.648 0.052 0.216
#> GSM647598 2 0.0405 0.8443 0.000 0.988 0.000 0.000 0.008 0.004
#> GSM647613 2 0.0260 0.8475 0.000 0.992 0.000 0.000 0.000 0.008
#> GSM647615 5 0.5415 0.1886 0.000 0.012 0.000 0.164 0.620 0.204
#> GSM647616 3 0.0000 0.8508 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647619 5 0.5056 0.1563 0.004 0.424 0.000 0.000 0.508 0.064
#> GSM647582 5 0.3314 0.4658 0.000 0.256 0.000 0.000 0.740 0.004
#> GSM647591 5 0.4313 0.0385 0.004 0.480 0.000 0.000 0.504 0.012
#> GSM647527 2 0.0146 0.8464 0.000 0.996 0.000 0.000 0.000 0.004
#> GSM647530 4 0.4064 0.4215 0.000 0.360 0.000 0.624 0.000 0.016
#> GSM647532 4 0.0146 0.7589 0.000 0.000 0.000 0.996 0.000 0.004
#> GSM647544 2 0.0260 0.8469 0.000 0.992 0.000 0.000 0.000 0.008
#> GSM647551 5 0.3121 0.4753 0.004 0.192 0.000 0.000 0.796 0.008
#> GSM647556 3 0.2260 0.8701 0.000 0.000 0.860 0.140 0.000 0.000
#> GSM647558 2 0.3551 0.7085 0.000 0.784 0.000 0.000 0.048 0.168
#> GSM647572 5 0.5110 0.0981 0.000 0.000 0.044 0.056 0.660 0.240
#> GSM647578 5 0.3372 0.3716 0.000 0.000 0.000 0.100 0.816 0.084
#> GSM647581 2 0.1444 0.8227 0.000 0.928 0.000 0.000 0.000 0.072
#> GSM647594 2 0.4462 0.6036 0.000 0.712 0.000 0.136 0.152 0.000
#> GSM647599 4 0.3911 0.5922 0.368 0.000 0.008 0.624 0.000 0.000
#> GSM647600 5 0.2390 0.4815 0.000 0.044 0.000 0.052 0.896 0.008
#> GSM647601 2 0.2838 0.7057 0.000 0.808 0.000 0.000 0.188 0.004
#> GSM647603 5 0.2680 0.4176 0.000 0.000 0.000 0.076 0.868 0.056
#> GSM647610 5 0.1251 0.4663 0.000 0.012 0.000 0.024 0.956 0.008
#> GSM647611 2 0.1686 0.8121 0.000 0.924 0.000 0.000 0.064 0.012
#> GSM647612 6 0.3482 0.9712 0.000 0.000 0.000 0.000 0.316 0.684
#> GSM647614 6 0.3652 0.9667 0.000 0.004 0.000 0.000 0.324 0.672
#> GSM647618 2 0.0520 0.8465 0.000 0.984 0.000 0.000 0.008 0.008
#> GSM647629 5 0.1230 0.4426 0.000 0.008 0.000 0.008 0.956 0.028
#> GSM647535 2 0.3982 -0.0459 0.000 0.536 0.000 0.000 0.460 0.004
#> GSM647563 2 0.1387 0.8252 0.000 0.932 0.000 0.000 0.000 0.068
#> GSM647542 6 0.3482 0.9712 0.000 0.000 0.000 0.000 0.316 0.684
#> GSM647543 6 0.3482 0.9712 0.000 0.000 0.000 0.000 0.316 0.684
#> GSM647548 4 0.3113 0.6975 0.000 0.008 0.000 0.844 0.048 0.100
#> GSM647554 5 0.0146 0.4476 0.000 0.000 0.000 0.000 0.996 0.004
#> GSM647555 6 0.4052 0.9098 0.000 0.016 0.000 0.000 0.356 0.628
#> GSM647559 2 0.1141 0.8336 0.000 0.948 0.000 0.000 0.000 0.052
#> GSM647562 2 0.0260 0.8469 0.000 0.992 0.000 0.000 0.000 0.008
#> GSM647564 3 0.2260 0.8701 0.000 0.000 0.860 0.140 0.000 0.000
#> GSM647571 6 0.4412 0.9245 0.000 0.024 0.000 0.012 0.320 0.644
#> GSM647584 5 0.4659 0.0853 0.004 0.460 0.000 0.000 0.504 0.032
#> GSM647585 3 0.2260 0.8701 0.000 0.000 0.860 0.140 0.000 0.000
#> GSM647586 2 0.0405 0.8443 0.000 0.988 0.000 0.000 0.008 0.004
#> GSM647587 2 0.0260 0.8469 0.000 0.992 0.000 0.000 0.000 0.008
#> GSM647588 2 0.4614 0.5838 0.000 0.676 0.000 0.000 0.228 0.096
#> GSM647596 2 0.0260 0.8475 0.000 0.992 0.000 0.000 0.000 0.008
#> GSM647602 3 0.0146 0.8523 0.000 0.000 0.996 0.004 0.000 0.000
#> GSM647609 2 0.4184 -0.0540 0.000 0.500 0.000 0.000 0.488 0.012
#> GSM647620 2 0.4116 0.1821 0.000 0.572 0.000 0.000 0.416 0.012
#> GSM647627 2 0.1010 0.8319 0.000 0.960 0.000 0.000 0.036 0.004
#> GSM647628 2 0.3920 0.6602 0.000 0.736 0.000 0.000 0.048 0.216
#> GSM647533 1 0.0146 0.9788 0.996 0.000 0.000 0.004 0.000 0.000
#> GSM647536 4 0.0146 0.7589 0.000 0.000 0.000 0.996 0.000 0.004
#> GSM647537 1 0.0146 0.9788 0.996 0.000 0.000 0.004 0.000 0.000
#> GSM647606 1 0.1007 0.9431 0.956 0.000 0.000 0.044 0.000 0.000
#> GSM647621 4 0.3023 0.6997 0.232 0.000 0.000 0.768 0.000 0.000
#> GSM647626 3 0.2378 0.8614 0.000 0.000 0.848 0.152 0.000 0.000
#> GSM647538 1 0.1141 0.9306 0.948 0.000 0.000 0.052 0.000 0.000
#> GSM647575 4 0.0000 0.7588 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM647590 4 0.3659 0.6042 0.364 0.000 0.000 0.636 0.000 0.000
#> GSM647605 4 0.3804 0.5351 0.424 0.000 0.000 0.576 0.000 0.000
#> GSM647607 4 0.0000 0.7588 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM647608 4 0.3175 0.6852 0.256 0.000 0.000 0.744 0.000 0.000
#> GSM647622 1 0.0146 0.9788 0.996 0.000 0.000 0.004 0.000 0.000
#> GSM647623 1 0.0146 0.9788 0.996 0.000 0.000 0.004 0.000 0.000
#> GSM647624 4 0.3797 0.5404 0.420 0.000 0.000 0.580 0.000 0.000
#> GSM647625 1 0.0146 0.9788 0.996 0.000 0.000 0.004 0.000 0.000
#> GSM647534 4 0.7575 0.2454 0.204 0.000 0.000 0.348 0.256 0.192
#> GSM647539 4 0.0000 0.7588 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM647566 4 0.4533 0.6850 0.208 0.000 0.004 0.700 0.000 0.088
#> GSM647589 4 0.1956 0.7540 0.080 0.000 0.008 0.908 0.000 0.004
#> GSM647604 4 0.3804 0.5351 0.424 0.000 0.000 0.576 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)
#> Error in mat[ceiling(1:nr/h_ratio), ceiling(1:nc/w_ratio), drop = FALSE]: subscript out of bounds
get_signatures(res, k = 4, scale_rows = FALSE)
get_signatures(res, k = 5, scale_rows = FALSE)
get_signatures(res, k = 6, scale_rows = FALSE)
#> Error in mat[ceiling(1:nr/h_ratio), ceiling(1:nc/w_ratio), drop = FALSE]: subscript out of bounds
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) development.stage(p) other(p) k
#> MAD:mclust 101 1.34e-07 0.0190 0.5039 2
#> MAD:mclust 100 7.38e-15 0.1571 0.0229 3
#> MAD:mclust 91 3.02e-12 0.1092 0.0773 4
#> MAD:mclust 95 5.03e-14 0.0111 0.1091 5
#> MAD:mclust 74 4.06e-09 0.0411 0.0467 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["MAD", "NMF"]
# you can also extract it by
# res = res_list["MAD:NMF"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'MAD' method.
#> Subgroups are detected by 'NMF' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.890 0.888 0.944 0.4438 0.575 0.575
#> 3 3 0.526 0.651 0.778 0.4027 0.758 0.595
#> 4 4 0.622 0.722 0.858 0.1220 0.678 0.363
#> 5 5 0.587 0.610 0.788 0.0791 0.813 0.514
#> 6 6 0.626 0.531 0.734 0.0631 0.899 0.647
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
#> GSM647569 1 0.2423 0.9478 0.960 0.040
#> GSM647574 1 0.3431 0.9457 0.936 0.064
#> GSM647577 1 0.3431 0.9457 0.936 0.064
#> GSM647547 1 0.3584 0.9429 0.932 0.068
#> GSM647552 2 0.3431 0.9064 0.064 0.936
#> GSM647553 1 0.3431 0.9457 0.936 0.064
#> GSM647565 2 0.1633 0.9296 0.024 0.976
#> GSM647545 2 0.0000 0.9379 0.000 1.000
#> GSM647549 2 0.0000 0.9379 0.000 1.000
#> GSM647550 2 0.0672 0.9364 0.008 0.992
#> GSM647560 2 0.0000 0.9379 0.000 1.000
#> GSM647617 1 0.3431 0.9457 0.936 0.064
#> GSM647528 2 0.0000 0.9379 0.000 1.000
#> GSM647529 2 0.9522 0.4800 0.372 0.628
#> GSM647531 2 0.0000 0.9379 0.000 1.000
#> GSM647540 2 0.0672 0.9363 0.008 0.992
#> GSM647541 2 0.0000 0.9379 0.000 1.000
#> GSM647546 2 0.9580 0.3802 0.380 0.620
#> GSM647557 2 0.0000 0.9379 0.000 1.000
#> GSM647561 2 0.0000 0.9379 0.000 1.000
#> GSM647567 2 0.8386 0.6838 0.268 0.732
#> GSM647568 2 0.0938 0.9352 0.012 0.988
#> GSM647570 2 0.0938 0.9352 0.012 0.988
#> GSM647573 2 0.9286 0.4692 0.344 0.656
#> GSM647576 2 0.0938 0.9352 0.012 0.988
#> GSM647579 2 0.0000 0.9379 0.000 1.000
#> GSM647580 1 0.3431 0.9457 0.936 0.064
#> GSM647583 1 0.3431 0.9457 0.936 0.064
#> GSM647592 2 0.3431 0.9064 0.064 0.936
#> GSM647593 2 0.3431 0.9064 0.064 0.936
#> GSM647595 2 0.3114 0.9116 0.056 0.944
#> GSM647597 2 0.3733 0.9031 0.072 0.928
#> GSM647598 2 0.0672 0.9363 0.008 0.992
#> GSM647613 2 0.0000 0.9379 0.000 1.000
#> GSM647615 2 0.0938 0.9352 0.012 0.988
#> GSM647616 1 0.3431 0.9457 0.936 0.064
#> GSM647619 2 0.3431 0.9064 0.064 0.936
#> GSM647582 2 0.0672 0.9363 0.008 0.992
#> GSM647591 2 0.3431 0.9064 0.064 0.936
#> GSM647527 2 0.0000 0.9379 0.000 1.000
#> GSM647530 2 0.0376 0.9373 0.004 0.996
#> GSM647532 2 0.9996 0.0426 0.488 0.512
#> GSM647544 2 0.0000 0.9379 0.000 1.000
#> GSM647551 2 0.3431 0.9064 0.064 0.936
#> GSM647556 1 0.0000 0.9450 1.000 0.000
#> GSM647558 2 0.0938 0.9352 0.012 0.988
#> GSM647572 2 0.4939 0.8585 0.108 0.892
#> GSM647578 2 0.1414 0.9301 0.020 0.980
#> GSM647581 2 0.0376 0.9373 0.004 0.996
#> GSM647594 2 0.3114 0.9116 0.056 0.944
#> GSM647599 1 0.0000 0.9450 1.000 0.000
#> GSM647600 2 0.3431 0.9064 0.064 0.936
#> GSM647601 2 0.1184 0.9334 0.016 0.984
#> GSM647603 2 0.0000 0.9379 0.000 1.000
#> GSM647610 2 0.7528 0.7586 0.216 0.784
#> GSM647611 2 0.0938 0.9349 0.012 0.988
#> GSM647612 2 0.0938 0.9352 0.012 0.988
#> GSM647614 2 0.0938 0.9352 0.012 0.988
#> GSM647618 2 0.0672 0.9363 0.008 0.992
#> GSM647629 2 0.0672 0.9363 0.008 0.992
#> GSM647535 2 0.0000 0.9379 0.000 1.000
#> GSM647563 2 0.0000 0.9379 0.000 1.000
#> GSM647542 2 0.0938 0.9352 0.012 0.988
#> GSM647543 2 0.0938 0.9352 0.012 0.988
#> GSM647548 2 0.1184 0.9336 0.016 0.984
#> GSM647554 2 0.2603 0.9188 0.044 0.956
#> GSM647555 2 0.0938 0.9352 0.012 0.988
#> GSM647559 2 0.0000 0.9379 0.000 1.000
#> GSM647562 2 0.0000 0.9379 0.000 1.000
#> GSM647564 1 0.5737 0.8737 0.864 0.136
#> GSM647571 2 0.0938 0.9352 0.012 0.988
#> GSM647584 2 0.2778 0.9165 0.048 0.952
#> GSM647585 1 0.0000 0.9450 1.000 0.000
#> GSM647586 2 0.0000 0.9379 0.000 1.000
#> GSM647587 2 0.0000 0.9379 0.000 1.000
#> GSM647588 2 0.0000 0.9379 0.000 1.000
#> GSM647596 2 0.0000 0.9379 0.000 1.000
#> GSM647602 1 0.3431 0.9457 0.936 0.064
#> GSM647609 2 0.1633 0.9297 0.024 0.976
#> GSM647620 2 0.0672 0.9363 0.008 0.992
#> GSM647627 2 0.0000 0.9379 0.000 1.000
#> GSM647628 2 0.0938 0.9352 0.012 0.988
#> GSM647533 1 0.0938 0.9421 0.988 0.012
#> GSM647536 1 0.9732 0.2368 0.596 0.404
#> GSM647537 1 0.0672 0.9435 0.992 0.008
#> GSM647606 1 0.0000 0.9450 1.000 0.000
#> GSM647621 1 0.3431 0.9457 0.936 0.064
#> GSM647626 1 0.0000 0.9450 1.000 0.000
#> GSM647538 1 0.0938 0.9421 0.988 0.012
#> GSM647575 2 0.8955 0.5411 0.312 0.688
#> GSM647590 1 0.1633 0.9477 0.976 0.024
#> GSM647605 1 0.0938 0.9421 0.988 0.012
#> GSM647607 1 0.3431 0.9457 0.936 0.064
#> GSM647608 1 0.3431 0.9457 0.936 0.064
#> GSM647622 1 0.0000 0.9450 1.000 0.000
#> GSM647623 1 0.0376 0.9443 0.996 0.004
#> GSM647624 1 0.0672 0.9461 0.992 0.008
#> GSM647625 1 0.0938 0.9421 0.988 0.012
#> GSM647534 2 0.9775 0.3819 0.412 0.588
#> GSM647539 2 0.1633 0.9296 0.024 0.976
#> GSM647566 2 0.8267 0.6927 0.260 0.740
#> GSM647589 1 0.3431 0.9457 0.936 0.064
#> GSM647604 1 0.0938 0.9421 0.988 0.012
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 3 0.1315 0.7249 0.020 0.008 0.972
#> GSM647574 3 0.5621 0.7433 0.000 0.308 0.692
#> GSM647577 3 0.5327 0.7662 0.000 0.272 0.728
#> GSM647547 3 0.5882 0.7010 0.000 0.348 0.652
#> GSM647552 1 0.0237 0.6999 0.996 0.004 0.000
#> GSM647553 3 0.5098 0.7717 0.000 0.248 0.752
#> GSM647565 2 0.2878 0.6582 0.000 0.904 0.096
#> GSM647545 2 0.4346 0.7640 0.184 0.816 0.000
#> GSM647549 2 0.3941 0.7630 0.156 0.844 0.000
#> GSM647550 2 0.0983 0.7336 0.016 0.980 0.004
#> GSM647560 2 0.2165 0.7479 0.064 0.936 0.000
#> GSM647617 3 0.5497 0.7548 0.000 0.292 0.708
#> GSM647528 2 0.5216 0.7493 0.260 0.740 0.000
#> GSM647529 1 0.5244 0.5445 0.756 0.004 0.240
#> GSM647531 2 0.5397 0.7376 0.280 0.720 0.000
#> GSM647540 2 0.4634 0.7617 0.164 0.824 0.012
#> GSM647541 2 0.5098 0.7541 0.248 0.752 0.000
#> GSM647546 2 0.5016 0.4006 0.000 0.760 0.240
#> GSM647557 2 0.5591 0.7152 0.304 0.696 0.000
#> GSM647561 2 0.5291 0.7449 0.268 0.732 0.000
#> GSM647567 1 0.7945 0.5816 0.652 0.124 0.224
#> GSM647568 2 0.2261 0.6847 0.000 0.932 0.068
#> GSM647570 2 0.0424 0.7317 0.008 0.992 0.000
#> GSM647573 2 0.4931 0.4253 0.000 0.768 0.232
#> GSM647576 2 0.1411 0.7100 0.000 0.964 0.036
#> GSM647579 2 0.5864 0.7328 0.288 0.704 0.008
#> GSM647580 3 0.5216 0.7708 0.000 0.260 0.740
#> GSM647583 3 0.5254 0.7698 0.000 0.264 0.736
#> GSM647592 1 0.1529 0.7047 0.960 0.040 0.000
#> GSM647593 1 0.2625 0.6848 0.916 0.084 0.000
#> GSM647595 1 0.5016 0.4948 0.760 0.240 0.000
#> GSM647597 1 0.2200 0.6794 0.940 0.004 0.056
#> GSM647598 2 0.5810 0.6760 0.336 0.664 0.000
#> GSM647613 2 0.5138 0.7525 0.252 0.748 0.000
#> GSM647615 2 0.0237 0.7303 0.004 0.996 0.000
#> GSM647616 3 0.5216 0.7708 0.000 0.260 0.740
#> GSM647619 1 0.2261 0.6947 0.932 0.068 0.000
#> GSM647582 2 0.5810 0.6758 0.336 0.664 0.000
#> GSM647591 1 0.2356 0.6926 0.928 0.072 0.000
#> GSM647527 2 0.5254 0.7473 0.264 0.736 0.000
#> GSM647530 2 0.4346 0.7618 0.184 0.816 0.000
#> GSM647532 3 0.9614 -0.0947 0.356 0.208 0.436
#> GSM647544 2 0.4121 0.7638 0.168 0.832 0.000
#> GSM647551 1 0.4235 0.5931 0.824 0.176 0.000
#> GSM647556 3 0.1411 0.7145 0.036 0.000 0.964
#> GSM647558 2 0.0475 0.7284 0.004 0.992 0.004
#> GSM647572 2 0.3116 0.6454 0.000 0.892 0.108
#> GSM647578 2 0.5292 0.7596 0.228 0.764 0.008
#> GSM647581 2 0.2448 0.7503 0.076 0.924 0.000
#> GSM647594 1 0.5327 0.4313 0.728 0.272 0.000
#> GSM647599 3 0.3340 0.6612 0.120 0.000 0.880
#> GSM647600 1 0.2356 0.6940 0.928 0.072 0.000
#> GSM647601 2 0.6260 0.4661 0.448 0.552 0.000
#> GSM647603 2 0.5529 0.7230 0.296 0.704 0.000
#> GSM647610 1 0.0829 0.6969 0.984 0.004 0.012
#> GSM647611 2 0.6140 0.5677 0.404 0.596 0.000
#> GSM647612 2 0.0892 0.7190 0.000 0.980 0.020
#> GSM647614 2 0.1529 0.7068 0.000 0.960 0.040
#> GSM647618 1 0.6008 0.0966 0.628 0.372 0.000
#> GSM647629 2 0.5650 0.7063 0.312 0.688 0.000
#> GSM647535 2 0.5254 0.7473 0.264 0.736 0.000
#> GSM647563 2 0.4974 0.7575 0.236 0.764 0.000
#> GSM647542 2 0.1643 0.7043 0.000 0.956 0.044
#> GSM647543 2 0.1643 0.7043 0.000 0.956 0.044
#> GSM647548 2 0.2356 0.6808 0.000 0.928 0.072
#> GSM647554 1 0.6252 -0.1490 0.556 0.444 0.000
#> GSM647555 2 0.0475 0.7289 0.004 0.992 0.004
#> GSM647559 2 0.5098 0.7541 0.248 0.752 0.000
#> GSM647562 2 0.5098 0.7543 0.248 0.752 0.000
#> GSM647564 3 0.5650 0.7396 0.000 0.312 0.688
#> GSM647571 2 0.1529 0.7068 0.000 0.960 0.040
#> GSM647584 1 0.6045 0.1165 0.620 0.380 0.000
#> GSM647585 3 0.1989 0.7109 0.048 0.004 0.948
#> GSM647586 2 0.5497 0.7270 0.292 0.708 0.000
#> GSM647587 2 0.5363 0.7396 0.276 0.724 0.000
#> GSM647588 2 0.5397 0.7367 0.280 0.720 0.000
#> GSM647596 2 0.5216 0.7493 0.260 0.740 0.000
#> GSM647602 3 0.5254 0.7698 0.000 0.264 0.736
#> GSM647609 2 0.6235 0.4912 0.436 0.564 0.000
#> GSM647620 2 0.5650 0.7062 0.312 0.688 0.000
#> GSM647627 2 0.5465 0.7303 0.288 0.712 0.000
#> GSM647628 2 0.1129 0.7207 0.004 0.976 0.020
#> GSM647533 3 0.5098 0.4850 0.248 0.000 0.752
#> GSM647536 1 0.5465 0.4915 0.712 0.000 0.288
#> GSM647537 3 0.4654 0.5489 0.208 0.000 0.792
#> GSM647606 3 0.2878 0.6752 0.096 0.000 0.904
#> GSM647621 3 0.4883 0.7693 0.004 0.208 0.788
#> GSM647626 3 0.1289 0.7170 0.032 0.000 0.968
#> GSM647538 1 0.5560 0.4778 0.700 0.000 0.300
#> GSM647575 2 0.6431 0.4679 0.084 0.760 0.156
#> GSM647590 3 0.0661 0.7269 0.008 0.004 0.988
#> GSM647605 1 0.5678 0.4560 0.684 0.000 0.316
#> GSM647607 3 0.6019 0.7578 0.012 0.288 0.700
#> GSM647608 3 0.5138 0.7716 0.000 0.252 0.748
#> GSM647622 3 0.2448 0.6901 0.076 0.000 0.924
#> GSM647623 3 0.4002 0.6134 0.160 0.000 0.840
#> GSM647624 3 0.1289 0.7175 0.032 0.000 0.968
#> GSM647625 1 0.5706 0.4504 0.680 0.000 0.320
#> GSM647534 1 0.3879 0.6163 0.848 0.000 0.152
#> GSM647539 2 0.2261 0.6844 0.000 0.932 0.068
#> GSM647566 1 0.8977 0.3467 0.564 0.232 0.204
#> GSM647589 3 0.5621 0.7433 0.000 0.308 0.692
#> GSM647604 1 0.5560 0.4777 0.700 0.000 0.300
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 3 0.0000 0.9689 0.000 0.000 1.000 0.000
#> GSM647574 3 0.1398 0.9204 0.000 0.004 0.956 0.040
#> GSM647577 3 0.0000 0.9689 0.000 0.000 1.000 0.000
#> GSM647547 4 0.0188 0.6990 0.000 0.004 0.000 0.996
#> GSM647552 2 0.4898 0.3944 0.416 0.584 0.000 0.000
#> GSM647553 3 0.0000 0.9689 0.000 0.000 1.000 0.000
#> GSM647565 4 0.1792 0.7171 0.000 0.068 0.000 0.932
#> GSM647545 2 0.2530 0.7675 0.000 0.888 0.000 0.112
#> GSM647549 2 0.2647 0.7593 0.000 0.880 0.000 0.120
#> GSM647550 2 0.2271 0.7971 0.000 0.916 0.008 0.076
#> GSM647560 2 0.1452 0.8262 0.000 0.956 0.036 0.008
#> GSM647617 3 0.0000 0.9689 0.000 0.000 1.000 0.000
#> GSM647528 2 0.0336 0.8372 0.000 0.992 0.000 0.008
#> GSM647529 1 0.2814 0.7857 0.868 0.000 0.000 0.132
#> GSM647531 2 0.4040 0.6113 0.000 0.752 0.000 0.248
#> GSM647540 2 0.4608 0.5350 0.000 0.692 0.304 0.004
#> GSM647541 2 0.0188 0.8378 0.000 0.996 0.000 0.004
#> GSM647546 3 0.5174 0.6425 0.000 0.124 0.760 0.116
#> GSM647557 2 0.0779 0.8364 0.004 0.980 0.000 0.016
#> GSM647561 2 0.0336 0.8372 0.000 0.992 0.000 0.008
#> GSM647567 2 0.4855 0.4193 0.400 0.600 0.000 0.000
#> GSM647568 4 0.4331 0.6700 0.000 0.288 0.000 0.712
#> GSM647570 4 0.4761 0.5624 0.000 0.372 0.000 0.628
#> GSM647573 4 0.0469 0.7036 0.000 0.012 0.000 0.988
#> GSM647576 2 0.5853 0.1469 0.000 0.508 0.460 0.032
#> GSM647579 2 0.4624 0.4873 0.000 0.660 0.340 0.000
#> GSM647580 3 0.0000 0.9689 0.000 0.000 1.000 0.000
#> GSM647583 3 0.0000 0.9689 0.000 0.000 1.000 0.000
#> GSM647592 2 0.4994 0.2499 0.480 0.520 0.000 0.000
#> GSM647593 2 0.2868 0.7784 0.136 0.864 0.000 0.000
#> GSM647595 2 0.1716 0.8208 0.064 0.936 0.000 0.000
#> GSM647597 1 0.1022 0.7811 0.968 0.032 0.000 0.000
#> GSM647598 2 0.0707 0.8365 0.020 0.980 0.000 0.000
#> GSM647613 2 0.0707 0.8329 0.000 0.980 0.000 0.020
#> GSM647615 2 0.4356 0.4737 0.000 0.708 0.000 0.292
#> GSM647616 3 0.0000 0.9689 0.000 0.000 1.000 0.000
#> GSM647619 2 0.4134 0.6629 0.260 0.740 0.000 0.000
#> GSM647582 2 0.0188 0.8380 0.004 0.996 0.000 0.000
#> GSM647591 2 0.4040 0.6793 0.248 0.752 0.000 0.000
#> GSM647527 2 0.0336 0.8372 0.000 0.992 0.000 0.008
#> GSM647530 4 0.0336 0.7017 0.000 0.008 0.000 0.992
#> GSM647532 4 0.4730 0.0112 0.364 0.000 0.000 0.636
#> GSM647544 4 0.3688 0.7204 0.000 0.208 0.000 0.792
#> GSM647551 2 0.2216 0.8058 0.092 0.908 0.000 0.000
#> GSM647556 3 0.0000 0.9689 0.000 0.000 1.000 0.000
#> GSM647558 4 0.4564 0.6240 0.000 0.328 0.000 0.672
#> GSM647572 4 0.7336 0.5367 0.000 0.256 0.216 0.528
#> GSM647578 2 0.1398 0.8276 0.000 0.956 0.040 0.004
#> GSM647581 4 0.3172 0.7261 0.000 0.160 0.000 0.840
#> GSM647594 2 0.3837 0.7086 0.224 0.776 0.000 0.000
#> GSM647599 1 0.5220 0.7526 0.752 0.000 0.156 0.092
#> GSM647600 2 0.2469 0.7966 0.108 0.892 0.000 0.000
#> GSM647601 2 0.1211 0.8307 0.040 0.960 0.000 0.000
#> GSM647603 2 0.0524 0.8369 0.000 0.988 0.008 0.004
#> GSM647610 2 0.4888 0.4267 0.412 0.588 0.000 0.000
#> GSM647611 2 0.1022 0.8344 0.032 0.968 0.000 0.000
#> GSM647612 4 0.4955 0.4059 0.000 0.444 0.000 0.556
#> GSM647614 4 0.4746 0.5688 0.000 0.368 0.000 0.632
#> GSM647618 2 0.3569 0.7447 0.196 0.804 0.000 0.000
#> GSM647629 2 0.0000 0.8380 0.000 1.000 0.000 0.000
#> GSM647535 2 0.0188 0.8378 0.000 0.996 0.000 0.004
#> GSM647563 2 0.3837 0.6150 0.000 0.776 0.000 0.224
#> GSM647542 4 0.5279 0.5023 0.000 0.400 0.012 0.588
#> GSM647543 4 0.6354 0.4202 0.000 0.416 0.064 0.520
#> GSM647548 4 0.0469 0.7036 0.000 0.012 0.000 0.988
#> GSM647554 2 0.0817 0.8355 0.024 0.976 0.000 0.000
#> GSM647555 2 0.3710 0.6641 0.000 0.804 0.004 0.192
#> GSM647559 2 0.2149 0.7925 0.000 0.912 0.000 0.088
#> GSM647562 2 0.4605 0.3825 0.000 0.664 0.000 0.336
#> GSM647564 3 0.0000 0.9689 0.000 0.000 1.000 0.000
#> GSM647571 4 0.3610 0.7236 0.000 0.200 0.000 0.800
#> GSM647584 2 0.1022 0.8336 0.032 0.968 0.000 0.000
#> GSM647585 3 0.0000 0.9689 0.000 0.000 1.000 0.000
#> GSM647586 2 0.0188 0.8378 0.000 0.996 0.000 0.004
#> GSM647587 2 0.0469 0.8374 0.000 0.988 0.000 0.012
#> GSM647588 2 0.0188 0.8378 0.000 0.996 0.000 0.004
#> GSM647596 2 0.0336 0.8372 0.000 0.992 0.000 0.008
#> GSM647602 3 0.0000 0.9689 0.000 0.000 1.000 0.000
#> GSM647609 2 0.1022 0.8336 0.032 0.968 0.000 0.000
#> GSM647620 2 0.0336 0.8377 0.008 0.992 0.000 0.000
#> GSM647627 2 0.0188 0.8378 0.000 0.996 0.000 0.004
#> GSM647628 4 0.3764 0.7193 0.000 0.216 0.000 0.784
#> GSM647533 1 0.3688 0.7415 0.792 0.000 0.208 0.000
#> GSM647536 1 0.4277 0.6899 0.720 0.000 0.000 0.280
#> GSM647537 1 0.3172 0.7717 0.840 0.000 0.160 0.000
#> GSM647606 1 0.3907 0.7259 0.768 0.000 0.232 0.000
#> GSM647621 4 0.5172 0.3828 0.188 0.000 0.068 0.744
#> GSM647626 3 0.0188 0.9644 0.004 0.000 0.996 0.000
#> GSM647538 1 0.0469 0.7975 0.988 0.000 0.000 0.012
#> GSM647575 4 0.0592 0.6846 0.016 0.000 0.000 0.984
#> GSM647590 1 0.5847 0.5098 0.560 0.000 0.036 0.404
#> GSM647605 1 0.0000 0.7952 1.000 0.000 0.000 0.000
#> GSM647607 4 0.1867 0.6290 0.072 0.000 0.000 0.928
#> GSM647608 4 0.1888 0.6550 0.044 0.000 0.016 0.940
#> GSM647622 1 0.4661 0.5764 0.652 0.000 0.348 0.000
#> GSM647623 1 0.3649 0.7478 0.796 0.000 0.204 0.000
#> GSM647624 1 0.5995 0.6927 0.660 0.000 0.084 0.256
#> GSM647625 1 0.0895 0.7989 0.976 0.000 0.020 0.004
#> GSM647534 1 0.1637 0.7603 0.940 0.060 0.000 0.000
#> GSM647539 4 0.0188 0.6927 0.004 0.000 0.000 0.996
#> GSM647566 1 0.7330 0.3944 0.512 0.304 0.000 0.184
#> GSM647589 4 0.0469 0.6962 0.000 0.000 0.012 0.988
#> GSM647604 1 0.0000 0.7952 1.000 0.000 0.000 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.0000 0.9119 0.000 0.000 1.000 0.000 0.000
#> GSM647574 3 0.4253 0.8009 0.000 0.080 0.812 0.064 0.044
#> GSM647577 3 0.0865 0.9049 0.000 0.024 0.972 0.000 0.004
#> GSM647547 4 0.3002 0.7628 0.008 0.068 0.000 0.876 0.048
#> GSM647552 5 0.5211 0.5237 0.232 0.100 0.000 0.000 0.668
#> GSM647553 3 0.2394 0.8776 0.004 0.004 0.912 0.036 0.044
#> GSM647565 4 0.3640 0.7270 0.008 0.108 0.000 0.832 0.052
#> GSM647545 2 0.1012 0.7083 0.000 0.968 0.000 0.012 0.020
#> GSM647549 2 0.2554 0.6916 0.000 0.892 0.000 0.036 0.072
#> GSM647550 2 0.4038 0.6867 0.000 0.812 0.012 0.088 0.088
#> GSM647560 2 0.0451 0.7096 0.000 0.988 0.004 0.000 0.008
#> GSM647617 3 0.0000 0.9119 0.000 0.000 1.000 0.000 0.000
#> GSM647528 2 0.1809 0.7073 0.000 0.928 0.000 0.012 0.060
#> GSM647529 1 0.4734 0.6660 0.732 0.000 0.000 0.160 0.108
#> GSM647531 2 0.6541 -0.0187 0.000 0.480 0.000 0.256 0.264
#> GSM647540 2 0.4876 0.2766 0.000 0.576 0.396 0.000 0.028
#> GSM647541 2 0.0609 0.7079 0.000 0.980 0.000 0.000 0.020
#> GSM647546 3 0.5209 0.4225 0.000 0.368 0.588 0.008 0.036
#> GSM647557 2 0.4141 0.4725 0.000 0.736 0.000 0.028 0.236
#> GSM647561 2 0.0609 0.7077 0.000 0.980 0.000 0.000 0.020
#> GSM647567 5 0.2848 0.6785 0.028 0.104 0.000 0.000 0.868
#> GSM647568 2 0.4337 0.5623 0.000 0.748 0.000 0.196 0.056
#> GSM647570 2 0.3090 0.6825 0.000 0.856 0.000 0.104 0.040
#> GSM647573 4 0.0771 0.7881 0.000 0.020 0.000 0.976 0.004
#> GSM647576 2 0.2670 0.6757 0.000 0.888 0.080 0.004 0.028
#> GSM647579 2 0.5289 0.3705 0.000 0.616 0.312 0.000 0.072
#> GSM647580 3 0.0000 0.9119 0.000 0.000 1.000 0.000 0.000
#> GSM647583 3 0.2574 0.8386 0.000 0.112 0.876 0.000 0.012
#> GSM647592 5 0.5294 0.2128 0.380 0.056 0.000 0.000 0.564
#> GSM647593 2 0.4627 0.2202 0.012 0.544 0.000 0.000 0.444
#> GSM647595 2 0.3774 0.5274 0.000 0.704 0.000 0.000 0.296
#> GSM647597 1 0.3461 0.5883 0.772 0.004 0.000 0.000 0.224
#> GSM647598 2 0.3741 0.5936 0.000 0.732 0.000 0.004 0.264
#> GSM647613 2 0.0771 0.7091 0.000 0.976 0.000 0.004 0.020
#> GSM647615 2 0.2304 0.6938 0.000 0.908 0.000 0.044 0.048
#> GSM647616 3 0.2189 0.8640 0.000 0.084 0.904 0.000 0.012
#> GSM647619 5 0.4674 0.2006 0.016 0.416 0.000 0.000 0.568
#> GSM647582 2 0.2020 0.6937 0.000 0.900 0.000 0.000 0.100
#> GSM647591 2 0.4321 0.3476 0.004 0.600 0.000 0.000 0.396
#> GSM647527 2 0.1764 0.7062 0.000 0.928 0.000 0.008 0.064
#> GSM647530 4 0.2568 0.7879 0.016 0.032 0.000 0.904 0.048
#> GSM647532 1 0.4659 0.0060 0.496 0.000 0.000 0.492 0.012
#> GSM647544 4 0.3142 0.7294 0.004 0.076 0.000 0.864 0.056
#> GSM647551 5 0.3242 0.6698 0.000 0.216 0.000 0.000 0.784
#> GSM647556 3 0.0963 0.8932 0.000 0.000 0.964 0.000 0.036
#> GSM647558 2 0.3401 0.6599 0.000 0.840 0.000 0.096 0.064
#> GSM647572 4 0.7119 0.0166 0.004 0.356 0.144 0.460 0.036
#> GSM647578 5 0.5951 0.5271 0.000 0.140 0.224 0.012 0.624
#> GSM647581 4 0.5069 0.4692 0.000 0.328 0.000 0.620 0.052
#> GSM647594 2 0.6365 0.1594 0.252 0.520 0.000 0.000 0.228
#> GSM647599 1 0.6038 0.5664 0.656 0.000 0.164 0.144 0.036
#> GSM647600 5 0.3508 0.6234 0.000 0.252 0.000 0.000 0.748
#> GSM647601 2 0.3752 0.5626 0.000 0.708 0.000 0.000 0.292
#> GSM647603 2 0.4179 0.6667 0.000 0.776 0.000 0.072 0.152
#> GSM647610 1 0.8160 -0.2539 0.336 0.240 0.000 0.108 0.316
#> GSM647611 2 0.5506 0.5101 0.000 0.616 0.000 0.100 0.284
#> GSM647612 2 0.1965 0.7030 0.000 0.924 0.000 0.052 0.024
#> GSM647614 2 0.2920 0.6827 0.000 0.852 0.000 0.132 0.016
#> GSM647618 2 0.4737 0.5998 0.068 0.708 0.000 0.000 0.224
#> GSM647629 2 0.1478 0.7024 0.000 0.936 0.000 0.000 0.064
#> GSM647535 2 0.3596 0.6460 0.000 0.784 0.000 0.016 0.200
#> GSM647563 2 0.3012 0.6924 0.000 0.860 0.000 0.104 0.036
#> GSM647542 2 0.2719 0.6850 0.000 0.884 0.000 0.068 0.048
#> GSM647543 2 0.2520 0.6879 0.000 0.896 0.000 0.056 0.048
#> GSM647548 4 0.1211 0.7902 0.000 0.024 0.000 0.960 0.016
#> GSM647554 5 0.2773 0.6979 0.000 0.164 0.000 0.000 0.836
#> GSM647555 2 0.0566 0.7096 0.000 0.984 0.000 0.012 0.004
#> GSM647559 2 0.5762 0.4807 0.004 0.588 0.000 0.308 0.100
#> GSM647562 2 0.5303 0.4514 0.004 0.576 0.000 0.372 0.048
#> GSM647564 3 0.0000 0.9119 0.000 0.000 1.000 0.000 0.000
#> GSM647571 2 0.5357 0.3265 0.004 0.520 0.000 0.432 0.044
#> GSM647584 5 0.4227 0.2718 0.000 0.420 0.000 0.000 0.580
#> GSM647585 3 0.0162 0.9106 0.000 0.000 0.996 0.000 0.004
#> GSM647586 2 0.3819 0.6246 0.000 0.756 0.000 0.016 0.228
#> GSM647587 2 0.6084 0.4733 0.000 0.572 0.000 0.220 0.208
#> GSM647588 5 0.4201 0.6413 0.000 0.204 0.000 0.044 0.752
#> GSM647596 2 0.3845 0.6435 0.000 0.768 0.000 0.024 0.208
#> GSM647602 3 0.0000 0.9119 0.000 0.000 1.000 0.000 0.000
#> GSM647609 2 0.3857 0.5358 0.000 0.688 0.000 0.000 0.312
#> GSM647620 2 0.3790 0.5823 0.000 0.724 0.000 0.004 0.272
#> GSM647627 2 0.3521 0.6238 0.000 0.764 0.000 0.004 0.232
#> GSM647628 2 0.4902 0.3556 0.000 0.564 0.000 0.408 0.028
#> GSM647533 1 0.2915 0.7234 0.860 0.000 0.116 0.000 0.024
#> GSM647536 1 0.4269 0.4844 0.684 0.000 0.000 0.300 0.016
#> GSM647537 1 0.1597 0.7525 0.940 0.000 0.048 0.000 0.012
#> GSM647606 1 0.1282 0.7540 0.952 0.000 0.044 0.004 0.000
#> GSM647621 4 0.5231 0.2621 0.356 0.000 0.020 0.600 0.024
#> GSM647626 3 0.0000 0.9119 0.000 0.000 1.000 0.000 0.000
#> GSM647538 1 0.3689 0.6119 0.740 0.000 0.000 0.004 0.256
#> GSM647575 4 0.1485 0.7774 0.020 0.000 0.000 0.948 0.032
#> GSM647590 1 0.4798 0.2731 0.580 0.000 0.000 0.396 0.024
#> GSM647605 1 0.2929 0.6719 0.820 0.000 0.000 0.000 0.180
#> GSM647607 4 0.2233 0.7378 0.104 0.000 0.000 0.892 0.004
#> GSM647608 4 0.3368 0.7402 0.080 0.000 0.028 0.860 0.032
#> GSM647622 1 0.1205 0.7548 0.956 0.000 0.040 0.004 0.000
#> GSM647623 1 0.0865 0.7543 0.972 0.000 0.024 0.000 0.004
#> GSM647624 1 0.1569 0.7456 0.944 0.000 0.004 0.044 0.008
#> GSM647625 1 0.0703 0.7501 0.976 0.000 0.000 0.000 0.024
#> GSM647534 5 0.2612 0.5715 0.124 0.008 0.000 0.000 0.868
#> GSM647539 4 0.1970 0.7778 0.004 0.012 0.000 0.924 0.060
#> GSM647566 5 0.5732 0.3331 0.128 0.008 0.000 0.224 0.640
#> GSM647589 4 0.1446 0.7830 0.004 0.004 0.036 0.952 0.004
#> GSM647604 1 0.1410 0.7454 0.940 0.000 0.000 0.000 0.060
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.0291 0.8257 0.000 0.004 0.992 0.000 0.000 0.004
#> GSM647574 3 0.4592 0.5303 0.000 0.020 0.668 0.276 0.000 0.036
#> GSM647577 3 0.0909 0.8214 0.000 0.012 0.968 0.000 0.000 0.020
#> GSM647547 4 0.0922 0.8197 0.004 0.004 0.000 0.968 0.000 0.024
#> GSM647552 5 0.6331 0.1727 0.320 0.120 0.000 0.000 0.500 0.060
#> GSM647553 3 0.3283 0.7160 0.000 0.000 0.804 0.160 0.000 0.036
#> GSM647565 4 0.1895 0.8031 0.000 0.016 0.000 0.912 0.000 0.072
#> GSM647545 2 0.2257 0.6334 0.000 0.904 0.000 0.008 0.040 0.048
#> GSM647549 2 0.3273 0.6039 0.000 0.848 0.000 0.032 0.052 0.068
#> GSM647550 2 0.7260 -0.0208 0.000 0.432 0.004 0.176 0.124 0.264
#> GSM647560 2 0.1390 0.6553 0.000 0.948 0.004 0.000 0.016 0.032
#> GSM647617 3 0.0000 0.8256 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647528 2 0.3230 0.5372 0.000 0.776 0.000 0.000 0.012 0.212
#> GSM647529 1 0.6034 0.5578 0.548 0.000 0.000 0.156 0.032 0.264
#> GSM647531 2 0.6873 0.0573 0.004 0.484 0.000 0.272 0.144 0.096
#> GSM647540 3 0.4306 0.0586 0.000 0.464 0.520 0.000 0.012 0.004
#> GSM647541 2 0.0909 0.6532 0.000 0.968 0.000 0.000 0.012 0.020
#> GSM647546 3 0.4312 0.1533 0.000 0.476 0.508 0.004 0.000 0.012
#> GSM647557 2 0.4713 0.4720 0.000 0.732 0.000 0.044 0.148 0.076
#> GSM647561 2 0.1528 0.6463 0.000 0.936 0.000 0.000 0.048 0.016
#> GSM647567 5 0.1038 0.6110 0.004 0.004 0.004 0.004 0.968 0.016
#> GSM647568 2 0.1845 0.6395 0.000 0.920 0.000 0.052 0.000 0.028
#> GSM647570 2 0.3017 0.5821 0.000 0.816 0.000 0.020 0.000 0.164
#> GSM647573 4 0.1757 0.8223 0.000 0.008 0.000 0.916 0.000 0.076
#> GSM647576 2 0.2927 0.6112 0.000 0.872 0.064 0.008 0.012 0.044
#> GSM647579 2 0.4133 0.4978 0.000 0.720 0.236 0.000 0.032 0.012
#> GSM647580 3 0.0000 0.8256 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647583 3 0.3485 0.7023 0.000 0.152 0.800 0.004 0.000 0.044
#> GSM647592 6 0.6535 0.0274 0.192 0.036 0.000 0.000 0.372 0.400
#> GSM647593 5 0.5284 0.1357 0.000 0.388 0.000 0.000 0.508 0.104
#> GSM647595 2 0.3929 0.4881 0.000 0.700 0.000 0.000 0.272 0.028
#> GSM647597 1 0.3835 0.6513 0.748 0.000 0.000 0.000 0.048 0.204
#> GSM647598 2 0.5701 0.2439 0.000 0.524 0.000 0.000 0.248 0.228
#> GSM647613 2 0.1010 0.6536 0.000 0.960 0.000 0.000 0.036 0.004
#> GSM647615 2 0.1320 0.6512 0.000 0.948 0.000 0.016 0.000 0.036
#> GSM647616 3 0.2066 0.7969 0.000 0.052 0.908 0.000 0.000 0.040
#> GSM647619 5 0.5197 0.4550 0.020 0.176 0.000 0.000 0.664 0.140
#> GSM647582 2 0.2230 0.6427 0.000 0.892 0.000 0.000 0.084 0.024
#> GSM647591 2 0.4840 0.3395 0.012 0.620 0.000 0.000 0.316 0.052
#> GSM647527 2 0.3460 0.5230 0.000 0.760 0.000 0.000 0.020 0.220
#> GSM647530 4 0.2729 0.7924 0.004 0.008 0.000 0.876 0.080 0.032
#> GSM647532 1 0.5417 0.4014 0.532 0.000 0.000 0.352 0.004 0.112
#> GSM647544 6 0.4991 0.1665 0.000 0.072 0.000 0.404 0.000 0.524
#> GSM647551 5 0.2946 0.6038 0.000 0.176 0.000 0.000 0.812 0.012
#> GSM647556 3 0.1586 0.8019 0.004 0.000 0.940 0.004 0.040 0.012
#> GSM647558 2 0.2860 0.6248 0.000 0.852 0.000 0.048 0.000 0.100
#> GSM647572 6 0.6389 0.4901 0.000 0.100 0.132 0.204 0.000 0.564
#> GSM647578 5 0.6802 0.3579 0.000 0.024 0.260 0.036 0.496 0.184
#> GSM647581 4 0.4038 0.5425 0.000 0.216 0.000 0.728 0.000 0.056
#> GSM647594 2 0.6728 0.1327 0.268 0.456 0.000 0.000 0.220 0.056
#> GSM647599 1 0.4220 0.2807 0.520 0.000 0.008 0.004 0.000 0.468
#> GSM647600 5 0.4378 0.4076 0.000 0.328 0.000 0.000 0.632 0.040
#> GSM647601 2 0.5575 0.2179 0.000 0.532 0.000 0.000 0.172 0.296
#> GSM647603 6 0.4493 0.3196 0.000 0.424 0.004 0.000 0.024 0.548
#> GSM647610 6 0.5278 0.3930 0.256 0.072 0.000 0.000 0.036 0.636
#> GSM647611 6 0.4753 0.4706 0.004 0.348 0.000 0.000 0.052 0.596
#> GSM647612 2 0.2783 0.5924 0.000 0.836 0.000 0.016 0.000 0.148
#> GSM647614 2 0.3585 0.5527 0.000 0.780 0.000 0.048 0.000 0.172
#> GSM647618 6 0.6269 0.2295 0.076 0.388 0.000 0.000 0.080 0.456
#> GSM647629 2 0.1838 0.6467 0.000 0.916 0.000 0.000 0.068 0.016
#> GSM647535 2 0.4845 0.4434 0.000 0.660 0.000 0.000 0.132 0.208
#> GSM647563 2 0.4783 0.2667 0.000 0.616 0.000 0.076 0.000 0.308
#> GSM647542 2 0.2266 0.6193 0.000 0.880 0.000 0.012 0.000 0.108
#> GSM647543 2 0.1820 0.6396 0.000 0.924 0.012 0.008 0.000 0.056
#> GSM647548 4 0.1701 0.8234 0.000 0.008 0.000 0.920 0.000 0.072
#> GSM647554 5 0.0725 0.6225 0.000 0.012 0.000 0.000 0.976 0.012
#> GSM647555 2 0.1845 0.6350 0.000 0.916 0.004 0.008 0.000 0.072
#> GSM647559 6 0.5164 0.6486 0.004 0.220 0.000 0.108 0.012 0.656
#> GSM647562 6 0.5206 0.6076 0.000 0.284 0.000 0.128 0.000 0.588
#> GSM647564 3 0.0000 0.8256 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647571 6 0.5473 0.6191 0.000 0.240 0.000 0.192 0.000 0.568
#> GSM647584 5 0.3876 0.4789 0.000 0.276 0.000 0.000 0.700 0.024
#> GSM647585 3 0.0551 0.8219 0.004 0.000 0.984 0.000 0.008 0.004
#> GSM647586 2 0.5257 0.0764 0.000 0.524 0.000 0.000 0.104 0.372
#> GSM647587 6 0.5515 0.6432 0.000 0.224 0.000 0.092 0.048 0.636
#> GSM647588 5 0.4940 0.4764 0.000 0.008 0.000 0.172 0.676 0.144
#> GSM647596 2 0.6429 0.1568 0.000 0.496 0.000 0.040 0.208 0.256
#> GSM647602 3 0.0146 0.8253 0.000 0.000 0.996 0.000 0.000 0.004
#> GSM647609 2 0.5830 0.1975 0.000 0.488 0.000 0.000 0.284 0.228
#> GSM647620 2 0.5738 0.1723 0.000 0.508 0.000 0.000 0.208 0.284
#> GSM647627 2 0.4838 0.0925 0.000 0.544 0.000 0.000 0.060 0.396
#> GSM647628 4 0.5896 -0.3097 0.000 0.220 0.000 0.456 0.000 0.324
#> GSM647533 1 0.3824 0.6601 0.780 0.000 0.164 0.000 0.016 0.040
#> GSM647536 1 0.5041 0.5452 0.624 0.000 0.000 0.280 0.008 0.088
#> GSM647537 1 0.1718 0.7392 0.932 0.000 0.016 0.000 0.008 0.044
#> GSM647606 1 0.0508 0.7433 0.984 0.000 0.000 0.000 0.004 0.012
#> GSM647621 1 0.5886 0.1936 0.412 0.000 0.000 0.388 0.000 0.200
#> GSM647626 3 0.1461 0.8000 0.044 0.000 0.940 0.000 0.000 0.016
#> GSM647538 1 0.5171 0.5124 0.628 0.000 0.000 0.004 0.228 0.140
#> GSM647575 4 0.1644 0.8239 0.000 0.000 0.000 0.920 0.004 0.076
#> GSM647590 1 0.4789 0.5447 0.640 0.000 0.000 0.268 0.000 0.092
#> GSM647605 1 0.4284 0.5615 0.688 0.000 0.000 0.000 0.256 0.056
#> GSM647607 4 0.1789 0.8205 0.032 0.000 0.000 0.924 0.000 0.044
#> GSM647608 4 0.0912 0.8256 0.004 0.000 0.008 0.972 0.004 0.012
#> GSM647622 1 0.0713 0.7434 0.972 0.000 0.000 0.000 0.000 0.028
#> GSM647623 1 0.0858 0.7429 0.968 0.000 0.000 0.000 0.004 0.028
#> GSM647624 1 0.2058 0.7314 0.908 0.000 0.000 0.036 0.000 0.056
#> GSM647625 1 0.1219 0.7398 0.948 0.000 0.000 0.000 0.004 0.048
#> GSM647534 5 0.1802 0.5889 0.012 0.000 0.000 0.000 0.916 0.072
#> GSM647539 4 0.4390 0.6935 0.016 0.004 0.000 0.720 0.040 0.220
#> GSM647566 5 0.6387 0.2355 0.032 0.004 0.000 0.276 0.504 0.184
#> GSM647589 4 0.1333 0.8288 0.000 0.000 0.008 0.944 0.000 0.048
#> GSM647604 1 0.1500 0.7383 0.936 0.000 0.000 0.000 0.012 0.052
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)
#> Error in mat[ceiling(1:nr/h_ratio), ceiling(1:nc/w_ratio), drop = FALSE]: subscript out of bounds
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) development.stage(p) other(p) k
#> MAD:NMF 97 9.99e-08 0.06193 1.0000 2
#> MAD:NMF 85 1.11e-05 0.07605 0.8135 3
#> MAD:NMF 90 3.04e-10 0.00440 0.0195 4
#> MAD:NMF 79 8.67e-08 0.02346 0.0495 5
#> MAD:NMF 66 8.77e-07 0.00147 0.0763 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["ATC", "hclust"]
# you can also extract it by
# res = res_list["ATC:hclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'ATC' method.
#> Subgroups are detected by 'hclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 3.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.382 0.807 0.848 0.3951 0.639 0.639
#> 3 3 0.596 0.795 0.898 0.4884 0.817 0.714
#> 4 4 0.567 0.646 0.777 0.1254 0.945 0.881
#> 5 5 0.667 0.737 0.819 0.1447 0.771 0.476
#> 6 6 0.737 0.746 0.790 0.0407 0.992 0.964
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 3
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM647569 2 0.0000 0.764 0.000 1.000
#> GSM647574 2 0.4431 0.798 0.092 0.908
#> GSM647577 2 0.0000 0.764 0.000 1.000
#> GSM647547 2 0.9998 0.497 0.492 0.508
#> GSM647552 2 0.3274 0.788 0.060 0.940
#> GSM647553 2 0.6343 0.810 0.160 0.840
#> GSM647565 1 0.0000 0.985 1.000 0.000
#> GSM647545 2 0.9815 0.663 0.420 0.580
#> GSM647549 1 0.0672 0.979 0.992 0.008
#> GSM647550 2 0.8661 0.797 0.288 0.712
#> GSM647560 2 0.0672 0.769 0.008 0.992
#> GSM647617 2 0.0000 0.764 0.000 1.000
#> GSM647528 2 0.9815 0.663 0.420 0.580
#> GSM647529 1 0.0000 0.985 1.000 0.000
#> GSM647531 1 0.0000 0.985 1.000 0.000
#> GSM647540 2 0.0000 0.764 0.000 1.000
#> GSM647541 2 0.7883 0.810 0.236 0.764
#> GSM647546 2 0.1414 0.774 0.020 0.980
#> GSM647557 1 0.0672 0.979 0.992 0.008
#> GSM647561 1 0.0000 0.985 1.000 0.000
#> GSM647567 2 0.9044 0.779 0.320 0.680
#> GSM647568 2 0.7219 0.813 0.200 0.800
#> GSM647570 2 0.9815 0.663 0.420 0.580
#> GSM647573 1 0.0000 0.985 1.000 0.000
#> GSM647576 2 0.1414 0.774 0.020 0.980
#> GSM647579 2 0.0000 0.764 0.000 1.000
#> GSM647580 2 0.0000 0.764 0.000 1.000
#> GSM647583 2 0.0000 0.764 0.000 1.000
#> GSM647592 2 0.8661 0.797 0.288 0.712
#> GSM647593 2 0.8713 0.795 0.292 0.708
#> GSM647595 2 0.9044 0.778 0.320 0.680
#> GSM647597 1 0.0000 0.985 1.000 0.000
#> GSM647598 2 0.9427 0.740 0.360 0.640
#> GSM647613 1 0.0000 0.985 1.000 0.000
#> GSM647615 2 0.8386 0.804 0.268 0.732
#> GSM647616 2 0.0000 0.764 0.000 1.000
#> GSM647619 2 0.8713 0.795 0.292 0.708
#> GSM647582 2 0.5842 0.808 0.140 0.860
#> GSM647591 2 0.9044 0.778 0.320 0.680
#> GSM647527 2 0.9815 0.663 0.420 0.580
#> GSM647530 1 0.0000 0.985 1.000 0.000
#> GSM647532 1 0.0000 0.985 1.000 0.000
#> GSM647544 2 0.9686 0.695 0.396 0.604
#> GSM647551 2 0.8713 0.795 0.292 0.708
#> GSM647556 2 0.0376 0.767 0.004 0.996
#> GSM647558 2 0.9815 0.663 0.420 0.580
#> GSM647572 2 0.4939 0.801 0.108 0.892
#> GSM647578 2 0.0376 0.767 0.004 0.996
#> GSM647581 1 0.0000 0.985 1.000 0.000
#> GSM647594 1 0.0000 0.985 1.000 0.000
#> GSM647599 2 0.0376 0.767 0.004 0.996
#> GSM647600 2 0.0000 0.764 0.000 1.000
#> GSM647601 2 0.9000 0.781 0.316 0.684
#> GSM647603 2 0.0000 0.764 0.000 1.000
#> GSM647610 2 0.7883 0.810 0.236 0.764
#> GSM647611 2 0.8661 0.797 0.288 0.712
#> GSM647612 2 0.8499 0.801 0.276 0.724
#> GSM647614 2 0.7219 0.813 0.200 0.800
#> GSM647618 2 0.9044 0.778 0.320 0.680
#> GSM647629 2 0.7745 0.812 0.228 0.772
#> GSM647535 2 0.1414 0.774 0.020 0.980
#> GSM647563 2 0.9393 0.741 0.356 0.644
#> GSM647542 2 0.7219 0.813 0.200 0.800
#> GSM647543 2 0.7219 0.813 0.200 0.800
#> GSM647548 1 0.0938 0.973 0.988 0.012
#> GSM647554 2 0.7883 0.810 0.236 0.764
#> GSM647555 2 0.1414 0.774 0.020 0.980
#> GSM647559 2 0.8813 0.791 0.300 0.700
#> GSM647562 1 0.0000 0.985 1.000 0.000
#> GSM647564 2 0.0376 0.767 0.004 0.996
#> GSM647571 2 0.1414 0.774 0.020 0.980
#> GSM647584 2 0.8713 0.795 0.292 0.708
#> GSM647585 2 0.0000 0.764 0.000 1.000
#> GSM647586 2 0.9000 0.781 0.316 0.684
#> GSM647587 2 0.9815 0.663 0.420 0.580
#> GSM647588 2 0.8763 0.793 0.296 0.704
#> GSM647596 2 0.9815 0.663 0.420 0.580
#> GSM647602 2 0.0000 0.764 0.000 1.000
#> GSM647609 2 0.8713 0.795 0.292 0.708
#> GSM647620 2 0.8608 0.798 0.284 0.716
#> GSM647627 2 0.8713 0.795 0.292 0.708
#> GSM647628 2 0.9661 0.699 0.392 0.608
#> GSM647533 2 0.7219 0.813 0.200 0.800
#> GSM647536 1 0.0000 0.985 1.000 0.000
#> GSM647537 2 0.7219 0.813 0.200 0.800
#> GSM647606 1 0.7139 0.639 0.804 0.196
#> GSM647621 2 0.9998 0.497 0.492 0.508
#> GSM647626 2 0.0000 0.764 0.000 1.000
#> GSM647538 2 0.8713 0.795 0.292 0.708
#> GSM647575 1 0.0376 0.983 0.996 0.004
#> GSM647590 1 0.0376 0.983 0.996 0.004
#> GSM647605 1 0.0376 0.983 0.996 0.004
#> GSM647607 1 0.0000 0.985 1.000 0.000
#> GSM647608 2 0.9993 0.517 0.484 0.516
#> GSM647622 2 0.5408 0.804 0.124 0.876
#> GSM647623 2 0.4431 0.798 0.092 0.908
#> GSM647624 1 0.0000 0.985 1.000 0.000
#> GSM647625 2 0.4431 0.798 0.092 0.908
#> GSM647534 2 0.0376 0.767 0.004 0.996
#> GSM647539 1 0.0000 0.985 1.000 0.000
#> GSM647566 2 0.8713 0.795 0.292 0.708
#> GSM647589 2 0.9993 0.517 0.484 0.516
#> GSM647604 1 0.0376 0.983 0.996 0.004
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 3 0.0000 0.934 0.000 0.000 1.000
#> GSM647574 2 0.5291 0.678 0.000 0.732 0.268
#> GSM647577 3 0.0000 0.934 0.000 0.000 1.000
#> GSM647547 2 0.5024 0.686 0.220 0.776 0.004
#> GSM647552 2 0.5650 0.602 0.000 0.688 0.312
#> GSM647553 2 0.3482 0.794 0.000 0.872 0.128
#> GSM647565 1 0.0000 0.962 1.000 0.000 0.000
#> GSM647545 2 0.3686 0.779 0.140 0.860 0.000
#> GSM647549 1 0.1411 0.943 0.964 0.036 0.000
#> GSM647550 2 0.0000 0.835 0.000 1.000 0.000
#> GSM647560 2 0.6267 0.321 0.000 0.548 0.452
#> GSM647617 3 0.0000 0.934 0.000 0.000 1.000
#> GSM647528 2 0.3686 0.779 0.140 0.860 0.000
#> GSM647529 1 0.0000 0.962 1.000 0.000 0.000
#> GSM647531 1 0.0000 0.962 1.000 0.000 0.000
#> GSM647540 3 0.0000 0.934 0.000 0.000 1.000
#> GSM647541 2 0.1860 0.828 0.000 0.948 0.052
#> GSM647546 2 0.6215 0.380 0.000 0.572 0.428
#> GSM647557 1 0.1411 0.943 0.964 0.036 0.000
#> GSM647561 1 0.0424 0.961 0.992 0.008 0.000
#> GSM647567 2 0.1529 0.832 0.040 0.960 0.000
#> GSM647568 2 0.3030 0.815 0.004 0.904 0.092
#> GSM647570 2 0.3686 0.779 0.140 0.860 0.000
#> GSM647573 1 0.0000 0.962 1.000 0.000 0.000
#> GSM647576 2 0.6204 0.389 0.000 0.576 0.424
#> GSM647579 3 0.0000 0.934 0.000 0.000 1.000
#> GSM647580 3 0.0000 0.934 0.000 0.000 1.000
#> GSM647583 3 0.0000 0.934 0.000 0.000 1.000
#> GSM647592 2 0.0000 0.835 0.000 1.000 0.000
#> GSM647593 2 0.0237 0.835 0.004 0.996 0.000
#> GSM647595 2 0.1289 0.833 0.032 0.968 0.000
#> GSM647597 1 0.0000 0.962 1.000 0.000 0.000
#> GSM647598 2 0.2537 0.814 0.080 0.920 0.000
#> GSM647613 1 0.0424 0.961 0.992 0.008 0.000
#> GSM647615 2 0.1031 0.836 0.000 0.976 0.024
#> GSM647616 3 0.0000 0.934 0.000 0.000 1.000
#> GSM647619 2 0.0237 0.835 0.004 0.996 0.000
#> GSM647582 2 0.4702 0.725 0.000 0.788 0.212
#> GSM647591 2 0.1289 0.833 0.032 0.968 0.000
#> GSM647527 2 0.3686 0.779 0.140 0.860 0.000
#> GSM647530 1 0.0000 0.962 1.000 0.000 0.000
#> GSM647532 1 0.0000 0.962 1.000 0.000 0.000
#> GSM647544 2 0.3267 0.794 0.116 0.884 0.000
#> GSM647551 2 0.0661 0.837 0.004 0.988 0.008
#> GSM647556 3 0.4605 0.653 0.000 0.204 0.796
#> GSM647558 2 0.3686 0.779 0.140 0.860 0.000
#> GSM647572 2 0.4346 0.752 0.000 0.816 0.184
#> GSM647578 2 0.6308 0.200 0.000 0.508 0.492
#> GSM647581 1 0.0000 0.962 1.000 0.000 0.000
#> GSM647594 1 0.0000 0.962 1.000 0.000 0.000
#> GSM647599 2 0.6307 0.214 0.000 0.512 0.488
#> GSM647600 3 0.0000 0.934 0.000 0.000 1.000
#> GSM647601 2 0.1289 0.833 0.032 0.968 0.000
#> GSM647603 3 0.0000 0.934 0.000 0.000 1.000
#> GSM647610 2 0.1860 0.828 0.000 0.948 0.052
#> GSM647611 2 0.0000 0.835 0.000 1.000 0.000
#> GSM647612 2 0.0592 0.835 0.000 0.988 0.012
#> GSM647614 2 0.3030 0.815 0.004 0.904 0.092
#> GSM647618 2 0.1289 0.833 0.032 0.968 0.000
#> GSM647629 2 0.2066 0.827 0.000 0.940 0.060
#> GSM647535 2 0.6215 0.380 0.000 0.572 0.428
#> GSM647563 2 0.2356 0.816 0.072 0.928 0.000
#> GSM647542 2 0.3030 0.815 0.004 0.904 0.092
#> GSM647543 2 0.3030 0.815 0.004 0.904 0.092
#> GSM647548 1 0.0892 0.952 0.980 0.020 0.000
#> GSM647554 2 0.1860 0.828 0.000 0.948 0.052
#> GSM647555 2 0.6215 0.380 0.000 0.572 0.428
#> GSM647559 2 0.0747 0.836 0.016 0.984 0.000
#> GSM647562 1 0.0424 0.961 0.992 0.008 0.000
#> GSM647564 3 0.6280 -0.101 0.000 0.460 0.540
#> GSM647571 2 0.6215 0.380 0.000 0.572 0.428
#> GSM647584 2 0.0237 0.835 0.004 0.996 0.000
#> GSM647585 3 0.0592 0.924 0.000 0.012 0.988
#> GSM647586 2 0.1289 0.833 0.032 0.968 0.000
#> GSM647587 2 0.3686 0.779 0.140 0.860 0.000
#> GSM647588 2 0.0592 0.836 0.012 0.988 0.000
#> GSM647596 2 0.3686 0.779 0.140 0.860 0.000
#> GSM647602 3 0.0000 0.934 0.000 0.000 1.000
#> GSM647609 2 0.0237 0.835 0.004 0.996 0.000
#> GSM647620 2 0.0237 0.835 0.000 0.996 0.004
#> GSM647627 2 0.0237 0.835 0.004 0.996 0.000
#> GSM647628 2 0.3349 0.797 0.108 0.888 0.004
#> GSM647533 2 0.2878 0.813 0.000 0.904 0.096
#> GSM647536 1 0.0000 0.962 1.000 0.000 0.000
#> GSM647537 2 0.2878 0.813 0.000 0.904 0.096
#> GSM647606 1 0.5835 0.489 0.660 0.340 0.000
#> GSM647621 2 0.5024 0.686 0.220 0.776 0.004
#> GSM647626 3 0.0000 0.934 0.000 0.000 1.000
#> GSM647538 2 0.0424 0.836 0.008 0.992 0.000
#> GSM647575 1 0.1643 0.938 0.956 0.044 0.000
#> GSM647590 1 0.1964 0.929 0.944 0.056 0.000
#> GSM647605 1 0.2261 0.918 0.932 0.068 0.000
#> GSM647607 1 0.0000 0.962 1.000 0.000 0.000
#> GSM647608 2 0.4931 0.696 0.212 0.784 0.004
#> GSM647622 2 0.4235 0.759 0.000 0.824 0.176
#> GSM647623 2 0.5138 0.682 0.000 0.748 0.252
#> GSM647624 1 0.0000 0.962 1.000 0.000 0.000
#> GSM647625 2 0.5138 0.682 0.000 0.748 0.252
#> GSM647534 2 0.6180 0.415 0.000 0.584 0.416
#> GSM647539 1 0.0000 0.962 1.000 0.000 0.000
#> GSM647566 2 0.0424 0.836 0.008 0.992 0.000
#> GSM647589 2 0.4931 0.696 0.212 0.784 0.004
#> GSM647604 1 0.2356 0.913 0.928 0.072 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 3 0.0000 0.8330 0.000 0.000 1.000 0.000
#> GSM647574 2 0.7203 0.5024 0.312 0.524 0.164 0.000
#> GSM647577 3 0.0000 0.8330 0.000 0.000 1.000 0.000
#> GSM647547 2 0.4713 0.5036 0.360 0.640 0.000 0.000
#> GSM647552 2 0.7429 0.4130 0.316 0.492 0.192 0.000
#> GSM647553 2 0.5882 0.6157 0.344 0.608 0.048 0.000
#> GSM647565 4 0.5000 -0.7088 0.496 0.000 0.000 0.504
#> GSM647545 2 0.3587 0.7091 0.088 0.860 0.000 0.052
#> GSM647549 4 0.1820 0.7946 0.020 0.036 0.000 0.944
#> GSM647550 2 0.1022 0.7725 0.032 0.968 0.000 0.000
#> GSM647560 2 0.7896 0.0441 0.292 0.360 0.348 0.000
#> GSM647617 3 0.0000 0.8330 0.000 0.000 1.000 0.000
#> GSM647528 2 0.3587 0.7091 0.088 0.860 0.000 0.052
#> GSM647529 4 0.0000 0.8479 0.000 0.000 0.000 1.000
#> GSM647531 4 0.0000 0.8479 0.000 0.000 0.000 1.000
#> GSM647540 3 0.0000 0.8330 0.000 0.000 1.000 0.000
#> GSM647541 2 0.2814 0.7551 0.132 0.868 0.000 0.000
#> GSM647546 2 0.7910 0.1097 0.320 0.364 0.316 0.000
#> GSM647557 4 0.1820 0.7946 0.020 0.036 0.000 0.944
#> GSM647561 4 0.1042 0.8346 0.020 0.008 0.000 0.972
#> GSM647567 2 0.2149 0.7618 0.088 0.912 0.000 0.000
#> GSM647568 2 0.4804 0.6896 0.276 0.708 0.016 0.000
#> GSM647570 2 0.3587 0.7091 0.088 0.860 0.000 0.052
#> GSM647573 1 0.4972 0.7533 0.544 0.000 0.000 0.456
#> GSM647576 2 0.7905 0.1215 0.320 0.368 0.312 0.000
#> GSM647579 3 0.0000 0.8330 0.000 0.000 1.000 0.000
#> GSM647580 3 0.0000 0.8330 0.000 0.000 1.000 0.000
#> GSM647583 3 0.0000 0.8330 0.000 0.000 1.000 0.000
#> GSM647592 2 0.1022 0.7725 0.032 0.968 0.000 0.000
#> GSM647593 2 0.0000 0.7690 0.000 1.000 0.000 0.000
#> GSM647595 2 0.1174 0.7646 0.020 0.968 0.000 0.012
#> GSM647597 4 0.0336 0.8452 0.008 0.000 0.000 0.992
#> GSM647598 2 0.2385 0.7472 0.028 0.920 0.000 0.052
#> GSM647613 4 0.1042 0.8346 0.020 0.008 0.000 0.972
#> GSM647615 2 0.2198 0.7698 0.072 0.920 0.008 0.000
#> GSM647616 3 0.0000 0.8330 0.000 0.000 1.000 0.000
#> GSM647619 2 0.0000 0.7690 0.000 1.000 0.000 0.000
#> GSM647582 2 0.5993 0.6423 0.160 0.692 0.148 0.000
#> GSM647591 2 0.1174 0.7646 0.020 0.968 0.000 0.012
#> GSM647527 2 0.3587 0.7091 0.088 0.860 0.000 0.052
#> GSM647530 4 0.0000 0.8479 0.000 0.000 0.000 1.000
#> GSM647532 4 0.0000 0.8479 0.000 0.000 0.000 1.000
#> GSM647544 2 0.3107 0.7222 0.080 0.884 0.000 0.036
#> GSM647551 2 0.0469 0.7713 0.012 0.988 0.000 0.000
#> GSM647556 3 0.5434 0.6405 0.188 0.084 0.728 0.000
#> GSM647558 2 0.3587 0.7091 0.088 0.860 0.000 0.052
#> GSM647572 2 0.6409 0.5634 0.364 0.560 0.076 0.000
#> GSM647578 3 0.7841 0.0230 0.272 0.332 0.396 0.000
#> GSM647581 4 0.0000 0.8479 0.000 0.000 0.000 1.000
#> GSM647594 4 0.0000 0.8479 0.000 0.000 0.000 1.000
#> GSM647599 3 0.7824 -0.0140 0.260 0.348 0.392 0.000
#> GSM647600 3 0.0000 0.8330 0.000 0.000 1.000 0.000
#> GSM647601 2 0.1151 0.7642 0.024 0.968 0.000 0.008
#> GSM647603 3 0.0000 0.8330 0.000 0.000 1.000 0.000
#> GSM647610 2 0.2760 0.7560 0.128 0.872 0.000 0.000
#> GSM647611 2 0.1022 0.7725 0.032 0.968 0.000 0.000
#> GSM647612 2 0.1716 0.7706 0.064 0.936 0.000 0.000
#> GSM647614 2 0.4804 0.6896 0.276 0.708 0.016 0.000
#> GSM647618 2 0.1174 0.7646 0.020 0.968 0.000 0.012
#> GSM647629 2 0.3196 0.7520 0.136 0.856 0.008 0.000
#> GSM647535 2 0.7910 0.1097 0.320 0.364 0.316 0.000
#> GSM647563 2 0.1978 0.7424 0.068 0.928 0.000 0.004
#> GSM647542 2 0.4804 0.6896 0.276 0.708 0.016 0.000
#> GSM647543 2 0.4804 0.6896 0.276 0.708 0.016 0.000
#> GSM647548 1 0.5607 0.6937 0.496 0.020 0.000 0.484
#> GSM647554 2 0.2760 0.7560 0.128 0.872 0.000 0.000
#> GSM647555 2 0.7910 0.1097 0.320 0.364 0.316 0.000
#> GSM647559 2 0.0657 0.7677 0.012 0.984 0.000 0.004
#> GSM647562 4 0.1151 0.8305 0.024 0.008 0.000 0.968
#> GSM647564 3 0.7710 0.1571 0.256 0.296 0.448 0.000
#> GSM647571 2 0.7910 0.1097 0.320 0.364 0.316 0.000
#> GSM647584 2 0.0000 0.7690 0.000 1.000 0.000 0.000
#> GSM647585 3 0.1557 0.8016 0.056 0.000 0.944 0.000
#> GSM647586 2 0.1151 0.7642 0.024 0.968 0.000 0.008
#> GSM647587 2 0.3587 0.7091 0.088 0.860 0.000 0.052
#> GSM647588 2 0.0524 0.7685 0.008 0.988 0.000 0.004
#> GSM647596 2 0.3587 0.7091 0.088 0.860 0.000 0.052
#> GSM647602 3 0.0000 0.8330 0.000 0.000 1.000 0.000
#> GSM647609 2 0.0000 0.7690 0.000 1.000 0.000 0.000
#> GSM647620 2 0.1389 0.7728 0.048 0.952 0.000 0.000
#> GSM647627 2 0.0469 0.7705 0.012 0.988 0.000 0.000
#> GSM647628 2 0.3266 0.7095 0.168 0.832 0.000 0.000
#> GSM647533 2 0.5159 0.6366 0.364 0.624 0.012 0.000
#> GSM647536 4 0.0000 0.8479 0.000 0.000 0.000 1.000
#> GSM647537 2 0.5159 0.6366 0.364 0.624 0.012 0.000
#> GSM647606 1 0.6783 0.4094 0.572 0.304 0.000 0.124
#> GSM647621 2 0.4713 0.5036 0.360 0.640 0.000 0.000
#> GSM647626 3 0.0469 0.8255 0.012 0.000 0.988 0.000
#> GSM647538 2 0.1474 0.7694 0.052 0.948 0.000 0.000
#> GSM647575 1 0.5933 0.7913 0.552 0.040 0.000 0.408
#> GSM647590 1 0.6111 0.7912 0.556 0.052 0.000 0.392
#> GSM647605 1 0.6276 0.7824 0.556 0.064 0.000 0.380
#> GSM647607 1 0.4972 0.7533 0.544 0.000 0.000 0.456
#> GSM647608 2 0.4804 0.5063 0.384 0.616 0.000 0.000
#> GSM647622 2 0.6306 0.5504 0.392 0.544 0.064 0.000
#> GSM647623 2 0.6936 0.5135 0.320 0.548 0.132 0.000
#> GSM647624 1 0.4972 0.7533 0.544 0.000 0.000 0.456
#> GSM647625 2 0.6936 0.5135 0.320 0.548 0.132 0.000
#> GSM647534 2 0.7875 0.1620 0.316 0.388 0.296 0.000
#> GSM647539 4 0.5000 -0.7088 0.496 0.000 0.000 0.504
#> GSM647566 2 0.1474 0.7694 0.052 0.948 0.000 0.000
#> GSM647589 2 0.4804 0.5063 0.384 0.616 0.000 0.000
#> GSM647604 1 0.6326 0.7767 0.556 0.068 0.000 0.376
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.0000 0.960 0.000 0.000 1.000 0.000 0.000
#> GSM647574 1 0.4211 0.655 0.792 0.032 0.148 0.028 0.000
#> GSM647577 3 0.0000 0.960 0.000 0.000 1.000 0.000 0.000
#> GSM647547 4 0.6100 0.204 0.388 0.128 0.000 0.484 0.000
#> GSM647552 1 0.5673 0.697 0.676 0.132 0.172 0.020 0.000
#> GSM647553 1 0.3806 0.665 0.840 0.056 0.040 0.064 0.000
#> GSM647565 4 0.4350 0.513 0.000 0.004 0.000 0.588 0.408
#> GSM647545 2 0.2946 0.824 0.000 0.868 0.000 0.088 0.044
#> GSM647549 5 0.1741 0.917 0.000 0.040 0.000 0.024 0.936
#> GSM647550 2 0.2286 0.817 0.108 0.888 0.000 0.004 0.000
#> GSM647560 1 0.5024 0.625 0.628 0.040 0.328 0.004 0.000
#> GSM647617 3 0.0000 0.960 0.000 0.000 1.000 0.000 0.000
#> GSM647528 2 0.2946 0.824 0.000 0.868 0.000 0.088 0.044
#> GSM647529 5 0.0000 0.969 0.000 0.000 0.000 0.000 1.000
#> GSM647531 5 0.0000 0.969 0.000 0.000 0.000 0.000 1.000
#> GSM647540 3 0.0000 0.960 0.000 0.000 1.000 0.000 0.000
#> GSM647541 2 0.3906 0.587 0.292 0.704 0.000 0.004 0.000
#> GSM647546 1 0.4880 0.662 0.660 0.040 0.296 0.004 0.000
#> GSM647557 5 0.1741 0.917 0.000 0.040 0.000 0.024 0.936
#> GSM647561 5 0.1106 0.954 0.000 0.012 0.000 0.024 0.964
#> GSM647567 2 0.5136 0.648 0.116 0.688 0.000 0.196 0.000
#> GSM647568 1 0.5241 0.524 0.672 0.252 0.012 0.064 0.000
#> GSM647570 2 0.2946 0.824 0.000 0.868 0.000 0.088 0.044
#> GSM647573 4 0.4196 0.576 0.000 0.004 0.000 0.640 0.356
#> GSM647576 1 0.4929 0.665 0.660 0.044 0.292 0.004 0.000
#> GSM647579 3 0.0000 0.960 0.000 0.000 1.000 0.000 0.000
#> GSM647580 3 0.0000 0.960 0.000 0.000 1.000 0.000 0.000
#> GSM647583 3 0.0000 0.960 0.000 0.000 1.000 0.000 0.000
#> GSM647592 2 0.1430 0.845 0.052 0.944 0.000 0.004 0.000
#> GSM647593 2 0.0510 0.854 0.016 0.984 0.000 0.000 0.000
#> GSM647595 2 0.0798 0.855 0.000 0.976 0.000 0.016 0.008
#> GSM647597 5 0.0290 0.966 0.000 0.000 0.000 0.008 0.992
#> GSM647598 2 0.1907 0.844 0.000 0.928 0.000 0.028 0.044
#> GSM647613 5 0.1106 0.954 0.000 0.012 0.000 0.024 0.964
#> GSM647615 2 0.3170 0.772 0.160 0.828 0.008 0.004 0.000
#> GSM647616 3 0.0000 0.960 0.000 0.000 1.000 0.000 0.000
#> GSM647619 2 0.0510 0.854 0.016 0.984 0.000 0.000 0.000
#> GSM647582 1 0.6659 0.374 0.472 0.372 0.136 0.020 0.000
#> GSM647591 2 0.0798 0.855 0.000 0.976 0.000 0.016 0.008
#> GSM647527 2 0.2946 0.824 0.000 0.868 0.000 0.088 0.044
#> GSM647530 5 0.0000 0.969 0.000 0.000 0.000 0.000 1.000
#> GSM647532 5 0.0000 0.969 0.000 0.000 0.000 0.000 1.000
#> GSM647544 2 0.2535 0.835 0.000 0.892 0.000 0.076 0.032
#> GSM647551 2 0.3106 0.779 0.140 0.840 0.000 0.020 0.000
#> GSM647556 3 0.3968 0.468 0.276 0.004 0.716 0.004 0.000
#> GSM647558 2 0.2946 0.824 0.000 0.868 0.000 0.088 0.044
#> GSM647572 1 0.3581 0.702 0.848 0.072 0.060 0.020 0.000
#> GSM647578 1 0.5118 0.556 0.584 0.036 0.376 0.004 0.000
#> GSM647581 5 0.0000 0.969 0.000 0.000 0.000 0.000 1.000
#> GSM647594 5 0.0000 0.969 0.000 0.000 0.000 0.000 1.000
#> GSM647599 1 0.5106 0.562 0.588 0.036 0.372 0.004 0.000
#> GSM647600 3 0.0000 0.960 0.000 0.000 1.000 0.000 0.000
#> GSM647601 2 0.0703 0.855 0.000 0.976 0.000 0.024 0.000
#> GSM647603 3 0.0000 0.960 0.000 0.000 1.000 0.000 0.000
#> GSM647610 2 0.3861 0.602 0.284 0.712 0.000 0.004 0.000
#> GSM647611 2 0.1430 0.845 0.052 0.944 0.000 0.004 0.000
#> GSM647612 2 0.2806 0.784 0.152 0.844 0.000 0.004 0.000
#> GSM647614 1 0.5241 0.524 0.672 0.252 0.012 0.064 0.000
#> GSM647618 2 0.0798 0.855 0.000 0.976 0.000 0.016 0.008
#> GSM647629 2 0.4240 0.550 0.304 0.684 0.008 0.004 0.000
#> GSM647535 1 0.4880 0.662 0.660 0.040 0.296 0.004 0.000
#> GSM647563 2 0.1704 0.848 0.004 0.928 0.000 0.068 0.000
#> GSM647542 1 0.5241 0.524 0.672 0.252 0.012 0.064 0.000
#> GSM647543 1 0.5241 0.524 0.672 0.252 0.012 0.064 0.000
#> GSM647548 4 0.4798 0.518 0.000 0.024 0.000 0.580 0.396
#> GSM647554 2 0.3861 0.602 0.284 0.712 0.000 0.004 0.000
#> GSM647555 1 0.4880 0.662 0.660 0.040 0.296 0.004 0.000
#> GSM647559 2 0.0566 0.856 0.004 0.984 0.000 0.012 0.000
#> GSM647562 5 0.1106 0.953 0.000 0.012 0.000 0.024 0.964
#> GSM647564 1 0.5155 0.458 0.536 0.032 0.428 0.004 0.000
#> GSM647571 1 0.4880 0.662 0.660 0.040 0.296 0.004 0.000
#> GSM647584 2 0.0510 0.854 0.016 0.984 0.000 0.000 0.000
#> GSM647585 3 0.1638 0.889 0.064 0.000 0.932 0.004 0.000
#> GSM647586 2 0.0703 0.855 0.000 0.976 0.000 0.024 0.000
#> GSM647587 2 0.2946 0.824 0.000 0.868 0.000 0.088 0.044
#> GSM647588 2 0.0451 0.855 0.004 0.988 0.000 0.008 0.000
#> GSM647596 2 0.2946 0.824 0.000 0.868 0.000 0.088 0.044
#> GSM647602 3 0.0000 0.960 0.000 0.000 1.000 0.000 0.000
#> GSM647609 2 0.0671 0.854 0.016 0.980 0.000 0.004 0.000
#> GSM647620 2 0.2930 0.768 0.164 0.832 0.000 0.004 0.000
#> GSM647627 2 0.0671 0.855 0.016 0.980 0.000 0.004 0.000
#> GSM647628 2 0.6371 0.352 0.200 0.508 0.000 0.292 0.000
#> GSM647533 1 0.2790 0.631 0.880 0.052 0.000 0.068 0.000
#> GSM647536 5 0.0000 0.969 0.000 0.000 0.000 0.000 1.000
#> GSM647537 1 0.2790 0.631 0.880 0.052 0.000 0.068 0.000
#> GSM647606 4 0.2845 0.529 0.032 0.048 0.000 0.892 0.028
#> GSM647621 4 0.6100 0.204 0.388 0.128 0.000 0.484 0.000
#> GSM647626 3 0.1670 0.908 0.012 0.000 0.936 0.052 0.000
#> GSM647538 2 0.4437 0.729 0.140 0.760 0.000 0.100 0.000
#> GSM647575 4 0.3990 0.601 0.000 0.004 0.000 0.688 0.308
#> GSM647590 4 0.3906 0.605 0.000 0.004 0.000 0.704 0.292
#> GSM647605 4 0.3838 0.606 0.000 0.004 0.000 0.716 0.280
#> GSM647607 4 0.4196 0.576 0.000 0.004 0.000 0.640 0.356
#> GSM647608 4 0.5601 0.160 0.448 0.072 0.000 0.480 0.000
#> GSM647622 1 0.2993 0.691 0.884 0.048 0.044 0.024 0.000
#> GSM647623 1 0.4940 0.717 0.748 0.120 0.112 0.020 0.000
#> GSM647624 4 0.4196 0.576 0.000 0.004 0.000 0.640 0.356
#> GSM647625 1 0.4940 0.717 0.748 0.120 0.112 0.020 0.000
#> GSM647534 1 0.5618 0.665 0.636 0.068 0.276 0.020 0.000
#> GSM647539 4 0.4350 0.513 0.000 0.004 0.000 0.588 0.408
#> GSM647566 2 0.4437 0.729 0.140 0.760 0.000 0.100 0.000
#> GSM647589 4 0.5601 0.160 0.448 0.072 0.000 0.480 0.000
#> GSM647604 4 0.3814 0.606 0.000 0.004 0.000 0.720 0.276
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.0000 0.9462 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647574 1 0.4992 0.4216 0.620 0.000 0.112 0.000 0.000 0.268
#> GSM647577 3 0.0000 0.9462 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647547 6 0.4278 0.9198 0.084 0.076 0.000 0.060 0.000 0.780
#> GSM647552 1 0.3128 0.6285 0.848 0.052 0.088 0.000 0.000 0.012
#> GSM647553 1 0.3972 0.4026 0.664 0.012 0.004 0.000 0.000 0.320
#> GSM647565 4 0.2730 0.8596 0.000 0.000 0.000 0.808 0.192 0.000
#> GSM647545 2 0.3006 0.8074 0.000 0.864 0.000 0.056 0.024 0.056
#> GSM647549 5 0.1930 0.9112 0.000 0.036 0.000 0.048 0.916 0.000
#> GSM647550 2 0.2624 0.7914 0.124 0.856 0.000 0.000 0.000 0.020
#> GSM647560 1 0.3240 0.6313 0.752 0.000 0.244 0.000 0.000 0.004
#> GSM647617 3 0.0000 0.9462 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647528 2 0.3006 0.8074 0.000 0.864 0.000 0.056 0.024 0.056
#> GSM647529 5 0.0146 0.9579 0.000 0.000 0.000 0.004 0.996 0.000
#> GSM647531 5 0.0146 0.9579 0.000 0.000 0.000 0.004 0.996 0.000
#> GSM647540 3 0.0000 0.9462 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647541 2 0.3835 0.5912 0.320 0.668 0.000 0.000 0.000 0.012
#> GSM647546 1 0.3301 0.6599 0.772 0.004 0.216 0.000 0.000 0.008
#> GSM647557 5 0.1930 0.9112 0.000 0.036 0.000 0.048 0.916 0.000
#> GSM647561 5 0.1333 0.9355 0.000 0.008 0.000 0.048 0.944 0.000
#> GSM647567 2 0.5008 0.5536 0.044 0.672 0.000 0.052 0.000 0.232
#> GSM647568 1 0.5827 0.1261 0.476 0.208 0.000 0.000 0.000 0.316
#> GSM647570 2 0.3006 0.8074 0.000 0.864 0.000 0.056 0.024 0.056
#> GSM647573 4 0.2092 0.8993 0.000 0.000 0.000 0.876 0.124 0.000
#> GSM647576 1 0.3133 0.6604 0.780 0.008 0.212 0.000 0.000 0.000
#> GSM647579 3 0.0000 0.9462 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647580 3 0.0000 0.9462 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647583 3 0.0000 0.9462 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647592 2 0.1745 0.8244 0.056 0.924 0.000 0.000 0.000 0.020
#> GSM647593 2 0.0909 0.8338 0.020 0.968 0.000 0.000 0.000 0.012
#> GSM647595 2 0.0713 0.8370 0.000 0.972 0.000 0.028 0.000 0.000
#> GSM647597 5 0.0458 0.9552 0.000 0.000 0.000 0.016 0.984 0.000
#> GSM647598 2 0.1765 0.8257 0.000 0.924 0.000 0.052 0.024 0.000
#> GSM647613 5 0.1333 0.9355 0.000 0.008 0.000 0.048 0.944 0.000
#> GSM647615 2 0.3221 0.7468 0.188 0.792 0.000 0.000 0.000 0.020
#> GSM647616 3 0.0000 0.9462 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647619 2 0.0909 0.8338 0.020 0.968 0.000 0.000 0.000 0.012
#> GSM647582 1 0.4797 0.3612 0.640 0.292 0.056 0.000 0.000 0.012
#> GSM647591 2 0.0713 0.8370 0.000 0.972 0.000 0.028 0.000 0.000
#> GSM647527 2 0.3006 0.8074 0.000 0.864 0.000 0.056 0.024 0.056
#> GSM647530 5 0.0146 0.9579 0.000 0.000 0.000 0.004 0.996 0.000
#> GSM647532 5 0.0146 0.9579 0.000 0.000 0.000 0.004 0.996 0.000
#> GSM647544 2 0.2665 0.8137 0.000 0.884 0.000 0.032 0.024 0.060
#> GSM647551 2 0.3290 0.7166 0.208 0.776 0.000 0.000 0.000 0.016
#> GSM647556 3 0.3464 0.4549 0.312 0.000 0.688 0.000 0.000 0.000
#> GSM647558 2 0.3006 0.8074 0.000 0.864 0.000 0.056 0.024 0.056
#> GSM647572 1 0.4260 0.5088 0.720 0.028 0.024 0.000 0.000 0.228
#> GSM647578 1 0.3390 0.5732 0.704 0.000 0.296 0.000 0.000 0.000
#> GSM647581 5 0.0146 0.9579 0.000 0.000 0.000 0.004 0.996 0.000
#> GSM647594 5 0.0146 0.9579 0.000 0.000 0.000 0.004 0.996 0.000
#> GSM647599 1 0.3595 0.5808 0.704 0.000 0.288 0.000 0.000 0.008
#> GSM647600 3 0.0000 0.9462 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647601 2 0.0777 0.8372 0.000 0.972 0.000 0.024 0.004 0.000
#> GSM647603 3 0.0000 0.9462 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647610 2 0.3802 0.6039 0.312 0.676 0.000 0.000 0.000 0.012
#> GSM647611 2 0.1745 0.8244 0.056 0.924 0.000 0.000 0.000 0.020
#> GSM647612 2 0.3088 0.7579 0.172 0.808 0.000 0.000 0.000 0.020
#> GSM647614 1 0.5827 0.1261 0.476 0.208 0.000 0.000 0.000 0.316
#> GSM647618 2 0.0713 0.8370 0.000 0.972 0.000 0.028 0.000 0.000
#> GSM647629 2 0.4124 0.5574 0.332 0.648 0.008 0.000 0.000 0.012
#> GSM647535 1 0.3052 0.6594 0.780 0.004 0.216 0.000 0.000 0.000
#> GSM647563 2 0.1606 0.8270 0.000 0.932 0.000 0.008 0.004 0.056
#> GSM647542 1 0.5827 0.1261 0.476 0.208 0.000 0.000 0.000 0.316
#> GSM647543 1 0.5827 0.1261 0.476 0.208 0.000 0.000 0.000 0.316
#> GSM647548 4 0.4485 0.8084 0.000 0.020 0.000 0.728 0.184 0.068
#> GSM647554 2 0.3802 0.6039 0.312 0.676 0.000 0.000 0.000 0.012
#> GSM647555 1 0.3052 0.6594 0.780 0.004 0.216 0.000 0.000 0.000
#> GSM647559 2 0.0405 0.8374 0.000 0.988 0.000 0.008 0.004 0.000
#> GSM647562 5 0.2020 0.8991 0.000 0.008 0.000 0.096 0.896 0.000
#> GSM647564 1 0.3607 0.4938 0.652 0.000 0.348 0.000 0.000 0.000
#> GSM647571 1 0.3052 0.6594 0.780 0.004 0.216 0.000 0.000 0.000
#> GSM647584 2 0.0909 0.8338 0.020 0.968 0.000 0.000 0.000 0.012
#> GSM647585 3 0.1387 0.8795 0.068 0.000 0.932 0.000 0.000 0.000
#> GSM647586 2 0.0777 0.8372 0.000 0.972 0.000 0.024 0.004 0.000
#> GSM647587 2 0.3006 0.8074 0.000 0.864 0.000 0.056 0.024 0.056
#> GSM647588 2 0.0291 0.8370 0.000 0.992 0.000 0.004 0.004 0.000
#> GSM647596 2 0.3006 0.8074 0.000 0.864 0.000 0.056 0.024 0.056
#> GSM647602 3 0.0000 0.9462 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647609 2 0.1088 0.8324 0.024 0.960 0.000 0.000 0.000 0.016
#> GSM647620 2 0.3253 0.7451 0.192 0.788 0.000 0.000 0.000 0.020
#> GSM647627 2 0.0725 0.8368 0.012 0.976 0.000 0.000 0.000 0.012
#> GSM647628 2 0.5464 -0.0736 0.032 0.468 0.000 0.052 0.000 0.448
#> GSM647533 1 0.3874 0.3409 0.636 0.008 0.000 0.000 0.000 0.356
#> GSM647536 5 0.0146 0.9579 0.000 0.000 0.000 0.004 0.996 0.000
#> GSM647537 1 0.3874 0.3409 0.636 0.008 0.000 0.000 0.000 0.356
#> GSM647606 4 0.4327 0.5064 0.020 0.032 0.000 0.708 0.000 0.240
#> GSM647621 6 0.4278 0.9198 0.084 0.076 0.000 0.060 0.000 0.780
#> GSM647626 3 0.4337 0.7061 0.028 0.000 0.756 0.068 0.000 0.148
#> GSM647538 2 0.4215 0.6636 0.080 0.724 0.000 0.000 0.000 0.196
#> GSM647575 4 0.1501 0.8926 0.000 0.000 0.000 0.924 0.076 0.000
#> GSM647590 4 0.1584 0.8872 0.000 0.000 0.000 0.928 0.064 0.008
#> GSM647605 4 0.1807 0.8829 0.000 0.000 0.000 0.920 0.060 0.020
#> GSM647607 4 0.2092 0.8993 0.000 0.000 0.000 0.876 0.124 0.000
#> GSM647608 6 0.3214 0.9183 0.116 0.016 0.000 0.032 0.000 0.836
#> GSM647622 1 0.3596 0.4881 0.740 0.008 0.008 0.000 0.000 0.244
#> GSM647623 1 0.2024 0.6152 0.920 0.036 0.028 0.000 0.000 0.016
#> GSM647624 4 0.2092 0.8993 0.000 0.000 0.000 0.876 0.124 0.000
#> GSM647625 1 0.2024 0.6152 0.920 0.036 0.028 0.000 0.000 0.016
#> GSM647534 1 0.2871 0.6486 0.804 0.000 0.192 0.000 0.000 0.004
#> GSM647539 4 0.2730 0.8596 0.000 0.000 0.000 0.808 0.192 0.000
#> GSM647566 2 0.4215 0.6636 0.080 0.724 0.000 0.000 0.000 0.196
#> GSM647589 6 0.3214 0.9183 0.116 0.016 0.000 0.032 0.000 0.836
#> GSM647604 4 0.1829 0.8792 0.000 0.000 0.000 0.920 0.056 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) development.stage(p) other(p) k
#> ATC:hclust 101 2.79e-02 0.566 0.329 2
#> ATC:hclust 92 1.02e-01 0.528 0.270 3
#> ATC:hclust 89 5.01e-04 0.149 0.451 4
#> ATC:hclust 95 1.21e-05 0.168 0.492 5
#> ATC:hclust 90 2.48e-06 0.243 0.527 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["ATC", "kmeans"]
# you can also extract it by
# res = res_list["ATC:kmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'ATC' method.
#> Subgroups are detected by 'kmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 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 0.979 0.924 0.972 0.5041 0.496 0.496
#> 3 3 0.729 0.855 0.922 0.2811 0.641 0.407
#> 4 4 0.735 0.822 0.875 0.1406 0.789 0.487
#> 5 5 0.850 0.786 0.882 0.0693 0.905 0.664
#> 6 6 0.758 0.634 0.770 0.0469 0.938 0.731
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
#> GSM647569 1 0.000 0.9568 1.000 0.000
#> GSM647574 1 0.000 0.9568 1.000 0.000
#> GSM647577 1 0.000 0.9568 1.000 0.000
#> GSM647547 2 0.000 0.9859 0.000 1.000
#> GSM647552 1 0.000 0.9568 1.000 0.000
#> GSM647553 1 0.000 0.9568 1.000 0.000
#> GSM647565 2 0.000 0.9859 0.000 1.000
#> GSM647545 2 0.000 0.9859 0.000 1.000
#> GSM647549 2 0.000 0.9859 0.000 1.000
#> GSM647550 1 0.000 0.9568 1.000 0.000
#> GSM647560 1 0.000 0.9568 1.000 0.000
#> GSM647617 1 0.000 0.9568 1.000 0.000
#> GSM647528 2 0.000 0.9859 0.000 1.000
#> GSM647529 2 0.000 0.9859 0.000 1.000
#> GSM647531 2 0.000 0.9859 0.000 1.000
#> GSM647540 1 0.000 0.9568 1.000 0.000
#> GSM647541 1 0.000 0.9568 1.000 0.000
#> GSM647546 1 0.000 0.9568 1.000 0.000
#> GSM647557 2 0.000 0.9859 0.000 1.000
#> GSM647561 2 0.000 0.9859 0.000 1.000
#> GSM647567 2 0.000 0.9859 0.000 1.000
#> GSM647568 1 0.000 0.9568 1.000 0.000
#> GSM647570 2 0.000 0.9859 0.000 1.000
#> GSM647573 2 0.000 0.9859 0.000 1.000
#> GSM647576 1 0.000 0.9568 1.000 0.000
#> GSM647579 1 0.000 0.9568 1.000 0.000
#> GSM647580 1 0.000 0.9568 1.000 0.000
#> GSM647583 1 0.000 0.9568 1.000 0.000
#> GSM647592 1 0.000 0.9568 1.000 0.000
#> GSM647593 2 0.955 0.3472 0.376 0.624
#> GSM647595 2 0.000 0.9859 0.000 1.000
#> GSM647597 2 0.000 0.9859 0.000 1.000
#> GSM647598 2 0.000 0.9859 0.000 1.000
#> GSM647613 2 0.000 0.9859 0.000 1.000
#> GSM647615 1 0.000 0.9568 1.000 0.000
#> GSM647616 1 0.000 0.9568 1.000 0.000
#> GSM647619 1 1.000 0.0933 0.512 0.488
#> GSM647582 1 0.000 0.9568 1.000 0.000
#> GSM647591 2 0.000 0.9859 0.000 1.000
#> GSM647527 2 0.000 0.9859 0.000 1.000
#> GSM647530 2 0.000 0.9859 0.000 1.000
#> GSM647532 2 0.000 0.9859 0.000 1.000
#> GSM647544 2 0.000 0.9859 0.000 1.000
#> GSM647551 1 0.000 0.9568 1.000 0.000
#> GSM647556 1 0.000 0.9568 1.000 0.000
#> GSM647558 2 0.000 0.9859 0.000 1.000
#> GSM647572 1 0.000 0.9568 1.000 0.000
#> GSM647578 1 0.000 0.9568 1.000 0.000
#> GSM647581 2 0.000 0.9859 0.000 1.000
#> GSM647594 2 0.000 0.9859 0.000 1.000
#> GSM647599 1 0.000 0.9568 1.000 0.000
#> GSM647600 1 0.000 0.9568 1.000 0.000
#> GSM647601 2 0.000 0.9859 0.000 1.000
#> GSM647603 1 0.000 0.9568 1.000 0.000
#> GSM647610 1 0.000 0.9568 1.000 0.000
#> GSM647611 1 0.000 0.9568 1.000 0.000
#> GSM647612 1 0.000 0.9568 1.000 0.000
#> GSM647614 1 0.000 0.9568 1.000 0.000
#> GSM647618 2 0.000 0.9859 0.000 1.000
#> GSM647629 1 0.000 0.9568 1.000 0.000
#> GSM647535 1 0.000 0.9568 1.000 0.000
#> GSM647563 2 0.000 0.9859 0.000 1.000
#> GSM647542 1 0.000 0.9568 1.000 0.000
#> GSM647543 1 0.000 0.9568 1.000 0.000
#> GSM647548 2 0.000 0.9859 0.000 1.000
#> GSM647554 1 0.000 0.9568 1.000 0.000
#> GSM647555 1 0.000 0.9568 1.000 0.000
#> GSM647559 2 0.000 0.9859 0.000 1.000
#> GSM647562 2 0.000 0.9859 0.000 1.000
#> GSM647564 1 0.000 0.9568 1.000 0.000
#> GSM647571 1 0.000 0.9568 1.000 0.000
#> GSM647584 1 1.000 0.0794 0.508 0.492
#> GSM647585 1 0.000 0.9568 1.000 0.000
#> GSM647586 2 0.000 0.9859 0.000 1.000
#> GSM647587 2 0.000 0.9859 0.000 1.000
#> GSM647588 2 0.000 0.9859 0.000 1.000
#> GSM647596 2 0.000 0.9859 0.000 1.000
#> GSM647602 1 0.000 0.9568 1.000 0.000
#> GSM647609 1 1.000 0.0794 0.508 0.492
#> GSM647620 1 0.000 0.9568 1.000 0.000
#> GSM647627 1 1.000 0.0794 0.508 0.492
#> GSM647628 2 0.000 0.9859 0.000 1.000
#> GSM647533 1 0.000 0.9568 1.000 0.000
#> GSM647536 2 0.000 0.9859 0.000 1.000
#> GSM647537 1 0.000 0.9568 1.000 0.000
#> GSM647606 2 0.000 0.9859 0.000 1.000
#> GSM647621 2 0.000 0.9859 0.000 1.000
#> GSM647626 1 0.000 0.9568 1.000 0.000
#> GSM647538 1 0.802 0.6633 0.756 0.244
#> GSM647575 2 0.000 0.9859 0.000 1.000
#> GSM647590 2 0.000 0.9859 0.000 1.000
#> GSM647605 2 0.000 0.9859 0.000 1.000
#> GSM647607 2 0.000 0.9859 0.000 1.000
#> GSM647608 2 0.000 0.9859 0.000 1.000
#> GSM647622 1 0.000 0.9568 1.000 0.000
#> GSM647623 1 0.000 0.9568 1.000 0.000
#> GSM647624 2 0.000 0.9859 0.000 1.000
#> GSM647625 1 0.000 0.9568 1.000 0.000
#> GSM647534 1 0.000 0.9568 1.000 0.000
#> GSM647539 2 0.000 0.9859 0.000 1.000
#> GSM647566 2 0.000 0.9859 0.000 1.000
#> GSM647589 2 0.814 0.6388 0.252 0.748
#> GSM647604 2 0.000 0.9859 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 3 0.0000 0.927 0.000 0.000 1.000
#> GSM647574 3 0.0747 0.916 0.000 0.016 0.984
#> GSM647577 3 0.0000 0.927 0.000 0.000 1.000
#> GSM647547 2 0.1411 0.882 0.036 0.964 0.000
#> GSM647552 3 0.5098 0.715 0.000 0.248 0.752
#> GSM647553 2 0.5882 0.436 0.000 0.652 0.348
#> GSM647565 1 0.0000 0.957 1.000 0.000 0.000
#> GSM647545 2 0.4062 0.786 0.164 0.836 0.000
#> GSM647549 1 0.1411 0.962 0.964 0.036 0.000
#> GSM647550 2 0.1860 0.882 0.000 0.948 0.052
#> GSM647560 3 0.0237 0.926 0.000 0.004 0.996
#> GSM647617 3 0.0000 0.927 0.000 0.000 1.000
#> GSM647528 2 0.3038 0.841 0.104 0.896 0.000
#> GSM647529 1 0.1411 0.962 0.964 0.036 0.000
#> GSM647531 1 0.1411 0.962 0.964 0.036 0.000
#> GSM647540 3 0.0000 0.927 0.000 0.000 1.000
#> GSM647541 2 0.2066 0.878 0.000 0.940 0.060
#> GSM647546 3 0.2711 0.890 0.000 0.088 0.912
#> GSM647557 1 0.1411 0.962 0.964 0.036 0.000
#> GSM647561 1 0.1411 0.962 0.964 0.036 0.000
#> GSM647567 2 0.1411 0.882 0.036 0.964 0.000
#> GSM647568 2 0.1411 0.883 0.000 0.964 0.036
#> GSM647570 2 0.4062 0.786 0.164 0.836 0.000
#> GSM647573 1 0.0000 0.957 1.000 0.000 0.000
#> GSM647576 3 0.3116 0.875 0.000 0.108 0.892
#> GSM647579 3 0.0000 0.927 0.000 0.000 1.000
#> GSM647580 3 0.0000 0.927 0.000 0.000 1.000
#> GSM647583 3 0.0000 0.927 0.000 0.000 1.000
#> GSM647592 2 0.1860 0.882 0.000 0.948 0.052
#> GSM647593 2 0.0829 0.888 0.004 0.984 0.012
#> GSM647595 2 0.2878 0.847 0.096 0.904 0.000
#> GSM647597 1 0.1411 0.962 0.964 0.036 0.000
#> GSM647598 2 0.3267 0.832 0.116 0.884 0.000
#> GSM647613 1 0.1411 0.962 0.964 0.036 0.000
#> GSM647615 2 0.1860 0.882 0.000 0.948 0.052
#> GSM647616 3 0.0000 0.927 0.000 0.000 1.000
#> GSM647619 2 0.0747 0.888 0.000 0.984 0.016
#> GSM647582 2 0.5216 0.644 0.000 0.740 0.260
#> GSM647591 2 0.2878 0.847 0.096 0.904 0.000
#> GSM647527 2 0.3267 0.832 0.116 0.884 0.000
#> GSM647530 1 0.1411 0.962 0.964 0.036 0.000
#> GSM647532 1 0.1411 0.962 0.964 0.036 0.000
#> GSM647544 2 0.3267 0.832 0.116 0.884 0.000
#> GSM647551 2 0.1860 0.882 0.000 0.948 0.052
#> GSM647556 3 0.0000 0.927 0.000 0.000 1.000
#> GSM647558 2 0.3267 0.832 0.116 0.884 0.000
#> GSM647572 3 0.5397 0.663 0.000 0.280 0.720
#> GSM647578 3 0.0000 0.927 0.000 0.000 1.000
#> GSM647581 1 0.1411 0.962 0.964 0.036 0.000
#> GSM647594 1 0.1411 0.962 0.964 0.036 0.000
#> GSM647599 3 0.0000 0.927 0.000 0.000 1.000
#> GSM647600 3 0.0000 0.927 0.000 0.000 1.000
#> GSM647601 2 0.0747 0.885 0.016 0.984 0.000
#> GSM647603 3 0.0000 0.927 0.000 0.000 1.000
#> GSM647610 2 0.3619 0.815 0.000 0.864 0.136
#> GSM647611 2 0.1860 0.882 0.000 0.948 0.052
#> GSM647612 2 0.1860 0.882 0.000 0.948 0.052
#> GSM647614 2 0.1411 0.883 0.000 0.964 0.036
#> GSM647618 2 0.2711 0.852 0.088 0.912 0.000
#> GSM647629 2 0.6309 -0.035 0.000 0.504 0.496
#> GSM647535 3 0.2711 0.890 0.000 0.088 0.912
#> GSM647563 2 0.0747 0.885 0.016 0.984 0.000
#> GSM647542 2 0.1643 0.883 0.000 0.956 0.044
#> GSM647543 2 0.1529 0.883 0.000 0.960 0.040
#> GSM647548 1 0.0000 0.957 1.000 0.000 0.000
#> GSM647554 2 0.2066 0.878 0.000 0.940 0.060
#> GSM647555 3 0.5254 0.691 0.000 0.264 0.736
#> GSM647559 2 0.0747 0.885 0.016 0.984 0.000
#> GSM647562 1 0.1411 0.962 0.964 0.036 0.000
#> GSM647564 3 0.0000 0.927 0.000 0.000 1.000
#> GSM647571 3 0.2165 0.902 0.000 0.064 0.936
#> GSM647584 2 0.0747 0.888 0.000 0.984 0.016
#> GSM647585 3 0.0000 0.927 0.000 0.000 1.000
#> GSM647586 2 0.0747 0.885 0.016 0.984 0.000
#> GSM647587 2 0.5291 0.634 0.268 0.732 0.000
#> GSM647588 2 0.0747 0.885 0.016 0.984 0.000
#> GSM647596 2 0.4062 0.786 0.164 0.836 0.000
#> GSM647602 3 0.0000 0.927 0.000 0.000 1.000
#> GSM647609 2 0.0747 0.888 0.000 0.984 0.016
#> GSM647620 2 0.1860 0.882 0.000 0.948 0.052
#> GSM647627 2 0.0747 0.888 0.000 0.984 0.016
#> GSM647628 2 0.1529 0.882 0.040 0.960 0.000
#> GSM647533 2 0.4270 0.811 0.024 0.860 0.116
#> GSM647536 1 0.1411 0.962 0.964 0.036 0.000
#> GSM647537 3 0.3116 0.884 0.000 0.108 0.892
#> GSM647606 1 0.6235 0.145 0.564 0.436 0.000
#> GSM647621 2 0.5835 0.523 0.340 0.660 0.000
#> GSM647626 3 0.0000 0.927 0.000 0.000 1.000
#> GSM647538 2 0.1411 0.882 0.036 0.964 0.000
#> GSM647575 1 0.0000 0.957 1.000 0.000 0.000
#> GSM647590 1 0.0237 0.954 0.996 0.004 0.000
#> GSM647605 1 0.0000 0.957 1.000 0.000 0.000
#> GSM647607 1 0.0000 0.957 1.000 0.000 0.000
#> GSM647608 2 0.5948 0.480 0.360 0.640 0.000
#> GSM647622 3 0.3038 0.887 0.000 0.104 0.896
#> GSM647623 3 0.5291 0.684 0.000 0.268 0.732
#> GSM647624 1 0.0000 0.957 1.000 0.000 0.000
#> GSM647625 3 0.5650 0.599 0.000 0.312 0.688
#> GSM647534 3 0.0000 0.927 0.000 0.000 1.000
#> GSM647539 1 0.0000 0.957 1.000 0.000 0.000
#> GSM647566 2 0.1411 0.882 0.036 0.964 0.000
#> GSM647589 2 0.5835 0.523 0.340 0.660 0.000
#> GSM647604 1 0.0000 0.957 1.000 0.000 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 3 0.0000 0.959 0.000 0.000 1.000 0.000
#> GSM647574 3 0.4955 0.158 0.444 0.000 0.556 0.000
#> GSM647577 3 0.0000 0.959 0.000 0.000 1.000 0.000
#> GSM647547 1 0.2402 0.690 0.912 0.076 0.000 0.012
#> GSM647552 1 0.5733 0.667 0.640 0.048 0.312 0.000
#> GSM647553 1 0.3587 0.756 0.860 0.052 0.088 0.000
#> GSM647565 4 0.2124 0.937 0.068 0.008 0.000 0.924
#> GSM647545 2 0.1489 0.897 0.004 0.952 0.000 0.044
#> GSM647549 4 0.1302 0.936 0.000 0.044 0.000 0.956
#> GSM647550 1 0.4746 0.584 0.632 0.368 0.000 0.000
#> GSM647560 1 0.4817 0.567 0.612 0.000 0.388 0.000
#> GSM647617 3 0.0000 0.959 0.000 0.000 1.000 0.000
#> GSM647528 2 0.1398 0.900 0.004 0.956 0.000 0.040
#> GSM647529 4 0.0336 0.950 0.000 0.008 0.000 0.992
#> GSM647531 4 0.0469 0.949 0.000 0.012 0.000 0.988
#> GSM647540 3 0.0000 0.959 0.000 0.000 1.000 0.000
#> GSM647541 1 0.5764 0.672 0.644 0.304 0.052 0.000
#> GSM647546 1 0.5203 0.624 0.636 0.016 0.348 0.000
#> GSM647557 4 0.1302 0.936 0.000 0.044 0.000 0.956
#> GSM647561 4 0.1302 0.936 0.000 0.044 0.000 0.956
#> GSM647567 2 0.5055 0.471 0.368 0.624 0.000 0.008
#> GSM647568 1 0.3161 0.753 0.864 0.124 0.012 0.000
#> GSM647570 2 0.1489 0.897 0.004 0.952 0.000 0.044
#> GSM647573 4 0.1109 0.946 0.028 0.004 0.000 0.968
#> GSM647576 1 0.5636 0.670 0.648 0.044 0.308 0.000
#> GSM647579 3 0.0000 0.959 0.000 0.000 1.000 0.000
#> GSM647580 3 0.0000 0.959 0.000 0.000 1.000 0.000
#> GSM647583 3 0.0000 0.959 0.000 0.000 1.000 0.000
#> GSM647592 2 0.3688 0.680 0.208 0.792 0.000 0.000
#> GSM647593 2 0.0921 0.908 0.028 0.972 0.000 0.000
#> GSM647595 2 0.1182 0.908 0.016 0.968 0.000 0.016
#> GSM647597 4 0.0469 0.949 0.000 0.012 0.000 0.988
#> GSM647598 2 0.1398 0.900 0.004 0.956 0.000 0.040
#> GSM647613 4 0.1211 0.939 0.000 0.040 0.000 0.960
#> GSM647615 1 0.5517 0.658 0.648 0.316 0.036 0.000
#> GSM647616 3 0.0000 0.959 0.000 0.000 1.000 0.000
#> GSM647619 2 0.0921 0.908 0.028 0.972 0.000 0.000
#> GSM647582 1 0.6404 0.732 0.644 0.220 0.136 0.000
#> GSM647591 2 0.1488 0.905 0.012 0.956 0.000 0.032
#> GSM647527 2 0.1398 0.900 0.004 0.956 0.000 0.040
#> GSM647530 4 0.0336 0.950 0.000 0.008 0.000 0.992
#> GSM647532 4 0.0336 0.950 0.000 0.008 0.000 0.992
#> GSM647544 2 0.1545 0.897 0.008 0.952 0.000 0.040
#> GSM647551 2 0.2281 0.848 0.096 0.904 0.000 0.000
#> GSM647556 3 0.1302 0.922 0.044 0.000 0.956 0.000
#> GSM647558 2 0.1398 0.900 0.004 0.956 0.000 0.040
#> GSM647572 1 0.4719 0.743 0.772 0.048 0.180 0.000
#> GSM647578 3 0.1637 0.905 0.060 0.000 0.940 0.000
#> GSM647581 4 0.0469 0.949 0.000 0.012 0.000 0.988
#> GSM647594 4 0.0469 0.949 0.000 0.012 0.000 0.988
#> GSM647599 1 0.4948 0.462 0.560 0.000 0.440 0.000
#> GSM647600 3 0.0000 0.959 0.000 0.000 1.000 0.000
#> GSM647601 2 0.0921 0.908 0.028 0.972 0.000 0.000
#> GSM647603 3 0.0000 0.959 0.000 0.000 1.000 0.000
#> GSM647610 1 0.5861 0.680 0.644 0.296 0.060 0.000
#> GSM647611 2 0.3649 0.688 0.204 0.796 0.000 0.000
#> GSM647612 1 0.4713 0.598 0.640 0.360 0.000 0.000
#> GSM647614 1 0.4250 0.685 0.724 0.276 0.000 0.000
#> GSM647618 2 0.0937 0.909 0.012 0.976 0.000 0.012
#> GSM647629 1 0.6393 0.737 0.652 0.160 0.188 0.000
#> GSM647535 1 0.5530 0.640 0.632 0.032 0.336 0.000
#> GSM647563 2 0.0707 0.908 0.020 0.980 0.000 0.000
#> GSM647542 1 0.4606 0.701 0.724 0.264 0.012 0.000
#> GSM647543 1 0.4277 0.684 0.720 0.280 0.000 0.000
#> GSM647548 4 0.3443 0.904 0.136 0.016 0.000 0.848
#> GSM647554 1 0.5764 0.672 0.644 0.304 0.052 0.000
#> GSM647555 1 0.5867 0.736 0.688 0.096 0.216 0.000
#> GSM647559 2 0.0921 0.908 0.028 0.972 0.000 0.000
#> GSM647562 4 0.0707 0.948 0.000 0.020 0.000 0.980
#> GSM647564 3 0.0336 0.953 0.008 0.000 0.992 0.000
#> GSM647571 1 0.5174 0.598 0.620 0.012 0.368 0.000
#> GSM647584 2 0.0921 0.908 0.028 0.972 0.000 0.000
#> GSM647585 3 0.0000 0.959 0.000 0.000 1.000 0.000
#> GSM647586 2 0.0921 0.908 0.028 0.972 0.000 0.000
#> GSM647587 2 0.1576 0.894 0.004 0.948 0.000 0.048
#> GSM647588 2 0.0921 0.908 0.028 0.972 0.000 0.000
#> GSM647596 2 0.1489 0.897 0.004 0.952 0.000 0.044
#> GSM647602 3 0.0000 0.959 0.000 0.000 1.000 0.000
#> GSM647609 2 0.0921 0.908 0.028 0.972 0.000 0.000
#> GSM647620 2 0.4713 0.295 0.360 0.640 0.000 0.000
#> GSM647627 2 0.0921 0.908 0.028 0.972 0.000 0.000
#> GSM647628 2 0.2589 0.838 0.116 0.884 0.000 0.000
#> GSM647533 1 0.1302 0.741 0.956 0.044 0.000 0.000
#> GSM647536 4 0.0336 0.950 0.000 0.008 0.000 0.992
#> GSM647537 1 0.3377 0.733 0.848 0.012 0.140 0.000
#> GSM647606 1 0.3239 0.665 0.880 0.068 0.000 0.052
#> GSM647621 1 0.3229 0.665 0.880 0.072 0.000 0.048
#> GSM647626 3 0.0000 0.959 0.000 0.000 1.000 0.000
#> GSM647538 1 0.2149 0.739 0.912 0.088 0.000 0.000
#> GSM647575 4 0.3052 0.908 0.136 0.004 0.000 0.860
#> GSM647590 4 0.3052 0.908 0.136 0.004 0.000 0.860
#> GSM647605 4 0.3052 0.908 0.136 0.004 0.000 0.860
#> GSM647607 4 0.1211 0.943 0.040 0.000 0.000 0.960
#> GSM647608 1 0.3229 0.665 0.880 0.072 0.000 0.048
#> GSM647622 1 0.3123 0.721 0.844 0.000 0.156 0.000
#> GSM647623 1 0.5067 0.731 0.736 0.048 0.216 0.000
#> GSM647624 4 0.3052 0.908 0.136 0.004 0.000 0.860
#> GSM647625 1 0.5109 0.734 0.736 0.052 0.212 0.000
#> GSM647534 3 0.1389 0.919 0.048 0.000 0.952 0.000
#> GSM647539 4 0.1792 0.936 0.068 0.000 0.000 0.932
#> GSM647566 1 0.2589 0.722 0.884 0.116 0.000 0.000
#> GSM647589 1 0.1975 0.683 0.936 0.016 0.000 0.048
#> GSM647604 4 0.3052 0.908 0.136 0.004 0.000 0.860
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.0162 0.927 0.000 0.000 0.996 0.000 0.004
#> GSM647574 3 0.5188 0.376 0.328 0.000 0.612 0.000 0.060
#> GSM647577 3 0.0162 0.927 0.000 0.000 0.996 0.000 0.004
#> GSM647547 1 0.2130 0.723 0.908 0.012 0.000 0.000 0.080
#> GSM647552 5 0.2054 0.839 0.008 0.004 0.072 0.000 0.916
#> GSM647553 1 0.4561 0.269 0.504 0.000 0.008 0.000 0.488
#> GSM647565 4 0.4735 0.676 0.352 0.000 0.004 0.624 0.020
#> GSM647545 2 0.0807 0.965 0.012 0.976 0.000 0.012 0.000
#> GSM647549 4 0.1106 0.807 0.012 0.024 0.000 0.964 0.000
#> GSM647550 5 0.1952 0.819 0.004 0.084 0.000 0.000 0.912
#> GSM647560 5 0.2293 0.828 0.016 0.000 0.084 0.000 0.900
#> GSM647617 3 0.0162 0.927 0.000 0.000 0.996 0.000 0.004
#> GSM647528 2 0.0693 0.967 0.008 0.980 0.000 0.012 0.000
#> GSM647529 4 0.0290 0.817 0.008 0.000 0.000 0.992 0.000
#> GSM647531 4 0.0000 0.816 0.000 0.000 0.000 1.000 0.000
#> GSM647540 3 0.0162 0.927 0.000 0.000 0.996 0.000 0.004
#> GSM647541 5 0.1885 0.841 0.004 0.044 0.020 0.000 0.932
#> GSM647546 5 0.2110 0.835 0.016 0.000 0.072 0.000 0.912
#> GSM647557 4 0.1106 0.807 0.012 0.024 0.000 0.964 0.000
#> GSM647561 4 0.1106 0.807 0.012 0.024 0.000 0.964 0.000
#> GSM647567 1 0.4046 0.613 0.780 0.180 0.000 0.008 0.032
#> GSM647568 5 0.4276 0.111 0.380 0.004 0.000 0.000 0.616
#> GSM647570 2 0.0807 0.965 0.012 0.976 0.000 0.012 0.000
#> GSM647573 4 0.2932 0.789 0.112 0.000 0.004 0.864 0.020
#> GSM647576 5 0.2110 0.835 0.016 0.000 0.072 0.000 0.912
#> GSM647579 3 0.0162 0.927 0.000 0.000 0.996 0.000 0.004
#> GSM647580 3 0.0162 0.927 0.000 0.000 0.996 0.000 0.004
#> GSM647583 3 0.0162 0.927 0.000 0.000 0.996 0.000 0.004
#> GSM647592 5 0.3461 0.668 0.004 0.224 0.000 0.000 0.772
#> GSM647593 2 0.0865 0.965 0.004 0.972 0.000 0.000 0.024
#> GSM647595 2 0.0566 0.971 0.000 0.984 0.000 0.004 0.012
#> GSM647597 4 0.0000 0.816 0.000 0.000 0.000 1.000 0.000
#> GSM647598 2 0.0324 0.969 0.004 0.992 0.000 0.004 0.000
#> GSM647613 4 0.0912 0.811 0.012 0.016 0.000 0.972 0.000
#> GSM647615 5 0.1885 0.841 0.004 0.044 0.020 0.000 0.932
#> GSM647616 3 0.0162 0.927 0.000 0.000 0.996 0.000 0.004
#> GSM647619 2 0.0865 0.965 0.004 0.972 0.000 0.000 0.024
#> GSM647582 5 0.1901 0.844 0.004 0.024 0.040 0.000 0.932
#> GSM647591 2 0.0566 0.971 0.000 0.984 0.000 0.004 0.012
#> GSM647527 2 0.0693 0.967 0.008 0.980 0.000 0.012 0.000
#> GSM647530 4 0.0290 0.817 0.008 0.000 0.000 0.992 0.000
#> GSM647532 4 0.0290 0.817 0.008 0.000 0.000 0.992 0.000
#> GSM647544 2 0.0798 0.965 0.016 0.976 0.000 0.008 0.000
#> GSM647551 5 0.3814 0.593 0.004 0.276 0.000 0.000 0.720
#> GSM647556 3 0.3727 0.694 0.016 0.000 0.768 0.000 0.216
#> GSM647558 2 0.0693 0.967 0.008 0.980 0.000 0.012 0.000
#> GSM647572 5 0.1399 0.829 0.020 0.000 0.028 0.000 0.952
#> GSM647578 5 0.3934 0.643 0.016 0.000 0.244 0.000 0.740
#> GSM647581 4 0.0000 0.816 0.000 0.000 0.000 1.000 0.000
#> GSM647594 4 0.0000 0.816 0.000 0.000 0.000 1.000 0.000
#> GSM647599 5 0.2351 0.826 0.016 0.000 0.088 0.000 0.896
#> GSM647600 3 0.0162 0.927 0.000 0.000 0.996 0.000 0.004
#> GSM647601 2 0.0510 0.970 0.000 0.984 0.000 0.000 0.016
#> GSM647603 3 0.0162 0.927 0.000 0.000 0.996 0.000 0.004
#> GSM647610 5 0.1885 0.841 0.004 0.044 0.020 0.000 0.932
#> GSM647611 5 0.3662 0.632 0.004 0.252 0.000 0.000 0.744
#> GSM647612 5 0.1704 0.826 0.004 0.068 0.000 0.000 0.928
#> GSM647614 5 0.2824 0.749 0.096 0.032 0.000 0.000 0.872
#> GSM647618 2 0.0566 0.971 0.000 0.984 0.000 0.004 0.012
#> GSM647629 5 0.1885 0.844 0.004 0.020 0.044 0.000 0.932
#> GSM647535 5 0.2172 0.833 0.016 0.000 0.076 0.000 0.908
#> GSM647563 2 0.0451 0.970 0.008 0.988 0.000 0.000 0.004
#> GSM647542 5 0.1041 0.831 0.004 0.032 0.000 0.000 0.964
#> GSM647543 5 0.1915 0.806 0.040 0.032 0.000 0.000 0.928
#> GSM647548 4 0.4945 0.606 0.440 0.000 0.004 0.536 0.020
#> GSM647554 5 0.1885 0.841 0.004 0.044 0.020 0.000 0.932
#> GSM647555 5 0.1913 0.843 0.016 0.008 0.044 0.000 0.932
#> GSM647559 2 0.0510 0.970 0.000 0.984 0.000 0.000 0.016
#> GSM647562 4 0.0807 0.812 0.012 0.012 0.000 0.976 0.000
#> GSM647564 3 0.2110 0.860 0.016 0.000 0.912 0.000 0.072
#> GSM647571 5 0.2172 0.833 0.016 0.000 0.076 0.000 0.908
#> GSM647584 2 0.0865 0.965 0.004 0.972 0.000 0.000 0.024
#> GSM647585 3 0.0162 0.927 0.000 0.000 0.996 0.000 0.004
#> GSM647586 2 0.0510 0.970 0.000 0.984 0.000 0.000 0.016
#> GSM647587 2 0.0807 0.965 0.012 0.976 0.000 0.012 0.000
#> GSM647588 2 0.0510 0.970 0.000 0.984 0.000 0.000 0.016
#> GSM647596 2 0.0807 0.965 0.012 0.976 0.000 0.012 0.000
#> GSM647602 3 0.0162 0.927 0.000 0.000 0.996 0.000 0.004
#> GSM647609 2 0.0865 0.965 0.004 0.972 0.000 0.000 0.024
#> GSM647620 5 0.2068 0.813 0.004 0.092 0.000 0.000 0.904
#> GSM647627 2 0.0771 0.967 0.004 0.976 0.000 0.000 0.020
#> GSM647628 2 0.4373 0.699 0.176 0.764 0.000 0.008 0.052
#> GSM647533 1 0.4235 0.435 0.576 0.000 0.000 0.000 0.424
#> GSM647536 4 0.0290 0.817 0.008 0.000 0.000 0.992 0.000
#> GSM647537 5 0.4561 -0.262 0.488 0.000 0.008 0.000 0.504
#> GSM647606 1 0.1808 0.707 0.936 0.012 0.000 0.008 0.044
#> GSM647621 1 0.2162 0.715 0.916 0.012 0.000 0.008 0.064
#> GSM647626 3 0.0932 0.914 0.020 0.004 0.972 0.000 0.004
#> GSM647538 1 0.4390 0.430 0.568 0.004 0.000 0.000 0.428
#> GSM647575 4 0.4945 0.605 0.440 0.000 0.004 0.536 0.020
#> GSM647590 4 0.4949 0.599 0.444 0.000 0.004 0.532 0.020
#> GSM647605 4 0.4940 0.609 0.436 0.000 0.004 0.540 0.020
#> GSM647607 4 0.3670 0.764 0.180 0.000 0.004 0.796 0.020
#> GSM647608 1 0.2095 0.714 0.920 0.012 0.000 0.008 0.060
#> GSM647622 5 0.4528 -0.116 0.444 0.000 0.008 0.000 0.548
#> GSM647623 5 0.1740 0.838 0.012 0.000 0.056 0.000 0.932
#> GSM647624 4 0.4940 0.609 0.436 0.000 0.004 0.540 0.020
#> GSM647625 5 0.1740 0.838 0.012 0.000 0.056 0.000 0.932
#> GSM647534 3 0.4114 0.609 0.016 0.000 0.712 0.000 0.272
#> GSM647539 4 0.4721 0.677 0.348 0.000 0.004 0.628 0.020
#> GSM647566 1 0.4173 0.620 0.688 0.012 0.000 0.000 0.300
#> GSM647589 1 0.1894 0.715 0.920 0.000 0.000 0.008 0.072
#> GSM647604 4 0.4945 0.605 0.440 0.000 0.004 0.536 0.020
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.0000 0.891 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647574 3 0.7447 -0.175 0.236 0.292 0.340 0.132 0.000 0.000
#> GSM647577 3 0.0000 0.891 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647547 4 0.3961 -0.249 0.440 0.004 0.000 0.556 0.000 0.000
#> GSM647552 2 0.3221 0.716 0.264 0.736 0.000 0.000 0.000 0.000
#> GSM647553 1 0.5399 0.695 0.584 0.208 0.000 0.208 0.000 0.000
#> GSM647565 4 0.4199 0.291 0.008 0.000 0.000 0.544 0.004 0.444
#> GSM647545 5 0.1531 0.856 0.000 0.000 0.000 0.068 0.928 0.004
#> GSM647549 6 0.4135 0.696 0.016 0.000 0.000 0.068 0.152 0.764
#> GSM647550 2 0.4396 0.654 0.352 0.612 0.000 0.000 0.036 0.000
#> GSM647560 2 0.1890 0.621 0.008 0.924 0.024 0.044 0.000 0.000
#> GSM647617 3 0.0000 0.891 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647528 5 0.1327 0.859 0.000 0.000 0.000 0.064 0.936 0.000
#> GSM647529 6 0.0508 0.810 0.012 0.000 0.000 0.004 0.000 0.984
#> GSM647531 6 0.0291 0.812 0.004 0.000 0.000 0.000 0.004 0.992
#> GSM647540 3 0.0363 0.888 0.000 0.000 0.988 0.012 0.000 0.000
#> GSM647541 2 0.3351 0.713 0.288 0.712 0.000 0.000 0.000 0.000
#> GSM647546 2 0.2015 0.620 0.016 0.916 0.012 0.056 0.000 0.000
#> GSM647557 6 0.4135 0.696 0.016 0.000 0.000 0.068 0.152 0.764
#> GSM647561 6 0.3930 0.710 0.016 0.000 0.000 0.064 0.136 0.784
#> GSM647567 1 0.5313 0.327 0.508 0.000 0.000 0.384 0.108 0.000
#> GSM647568 1 0.5803 0.325 0.412 0.408 0.000 0.180 0.000 0.000
#> GSM647570 5 0.1531 0.856 0.000 0.000 0.000 0.068 0.928 0.004
#> GSM647573 6 0.3899 0.207 0.008 0.000 0.000 0.364 0.000 0.628
#> GSM647576 2 0.0622 0.655 0.012 0.980 0.008 0.000 0.000 0.000
#> GSM647579 3 0.0000 0.891 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647580 3 0.0000 0.891 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647583 3 0.0000 0.891 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647592 2 0.5468 0.540 0.380 0.492 0.000 0.000 0.128 0.000
#> GSM647593 5 0.3500 0.784 0.204 0.028 0.000 0.000 0.768 0.000
#> GSM647595 5 0.1895 0.866 0.072 0.016 0.000 0.000 0.912 0.000
#> GSM647597 6 0.0964 0.807 0.016 0.000 0.000 0.012 0.004 0.968
#> GSM647598 5 0.1327 0.859 0.000 0.000 0.000 0.064 0.936 0.000
#> GSM647613 6 0.3591 0.737 0.016 0.000 0.000 0.064 0.104 0.816
#> GSM647615 2 0.3371 0.711 0.292 0.708 0.000 0.000 0.000 0.000
#> GSM647616 3 0.0000 0.891 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647619 5 0.3841 0.744 0.244 0.032 0.000 0.000 0.724 0.000
#> GSM647582 2 0.3351 0.713 0.288 0.712 0.000 0.000 0.000 0.000
#> GSM647591 5 0.1895 0.866 0.072 0.016 0.000 0.000 0.912 0.000
#> GSM647527 5 0.1327 0.859 0.000 0.000 0.000 0.064 0.936 0.000
#> GSM647530 6 0.0508 0.810 0.012 0.000 0.000 0.004 0.000 0.984
#> GSM647532 6 0.0508 0.810 0.012 0.000 0.000 0.004 0.000 0.984
#> GSM647544 5 0.1531 0.856 0.000 0.000 0.000 0.068 0.928 0.004
#> GSM647551 2 0.5582 0.519 0.380 0.476 0.000 0.000 0.144 0.000
#> GSM647556 3 0.4695 0.301 0.000 0.448 0.508 0.044 0.000 0.000
#> GSM647558 5 0.1327 0.859 0.000 0.000 0.000 0.064 0.936 0.000
#> GSM647572 2 0.2006 0.608 0.016 0.904 0.000 0.080 0.000 0.000
#> GSM647578 2 0.2595 0.587 0.000 0.872 0.084 0.044 0.000 0.000
#> GSM647581 6 0.0291 0.812 0.004 0.000 0.000 0.000 0.004 0.992
#> GSM647594 6 0.0363 0.811 0.012 0.000 0.000 0.000 0.000 0.988
#> GSM647599 2 0.1890 0.621 0.008 0.924 0.024 0.044 0.000 0.000
#> GSM647600 3 0.0363 0.888 0.000 0.000 0.988 0.012 0.000 0.000
#> GSM647601 5 0.1895 0.866 0.072 0.016 0.000 0.000 0.912 0.000
#> GSM647603 3 0.0363 0.888 0.000 0.000 0.988 0.012 0.000 0.000
#> GSM647610 2 0.3351 0.713 0.288 0.712 0.000 0.000 0.000 0.000
#> GSM647611 2 0.5468 0.542 0.380 0.492 0.000 0.000 0.128 0.000
#> GSM647612 2 0.4397 0.698 0.296 0.664 0.000 0.024 0.016 0.000
#> GSM647614 2 0.4892 0.579 0.272 0.628 0.000 0.100 0.000 0.000
#> GSM647618 5 0.1895 0.866 0.072 0.016 0.000 0.000 0.912 0.000
#> GSM647629 2 0.3221 0.716 0.264 0.736 0.000 0.000 0.000 0.000
#> GSM647535 2 0.1426 0.646 0.008 0.948 0.016 0.028 0.000 0.000
#> GSM647563 5 0.1642 0.866 0.028 0.004 0.000 0.032 0.936 0.000
#> GSM647542 2 0.3829 0.677 0.180 0.760 0.000 0.060 0.000 0.000
#> GSM647543 2 0.4507 0.654 0.268 0.664 0.000 0.068 0.000 0.000
#> GSM647548 4 0.3684 0.447 0.000 0.000 0.000 0.628 0.000 0.372
#> GSM647554 2 0.3351 0.713 0.288 0.712 0.000 0.000 0.000 0.000
#> GSM647555 2 0.1341 0.654 0.024 0.948 0.000 0.028 0.000 0.000
#> GSM647559 5 0.1838 0.866 0.068 0.016 0.000 0.000 0.916 0.000
#> GSM647562 6 0.2765 0.772 0.016 0.000 0.000 0.044 0.064 0.876
#> GSM647564 3 0.4377 0.539 0.000 0.312 0.644 0.044 0.000 0.000
#> GSM647571 2 0.1826 0.626 0.004 0.924 0.020 0.052 0.000 0.000
#> GSM647584 5 0.3816 0.748 0.240 0.032 0.000 0.000 0.728 0.000
#> GSM647585 3 0.0713 0.879 0.000 0.000 0.972 0.028 0.000 0.000
#> GSM647586 5 0.1719 0.867 0.060 0.016 0.000 0.000 0.924 0.000
#> GSM647587 5 0.1531 0.856 0.000 0.000 0.000 0.068 0.928 0.004
#> GSM647588 5 0.2163 0.859 0.092 0.016 0.000 0.000 0.892 0.000
#> GSM647596 5 0.1531 0.856 0.000 0.000 0.000 0.068 0.928 0.004
#> GSM647602 3 0.0000 0.891 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647609 5 0.3745 0.752 0.240 0.028 0.000 0.000 0.732 0.000
#> GSM647620 2 0.4903 0.604 0.380 0.552 0.000 0.000 0.068 0.000
#> GSM647627 5 0.3269 0.802 0.184 0.024 0.000 0.000 0.792 0.000
#> GSM647628 5 0.5279 0.429 0.196 0.000 0.000 0.200 0.604 0.000
#> GSM647533 1 0.4979 0.696 0.640 0.136 0.000 0.224 0.000 0.000
#> GSM647536 6 0.0508 0.810 0.012 0.000 0.000 0.004 0.000 0.984
#> GSM647537 1 0.5255 0.653 0.548 0.340 0.000 0.112 0.000 0.000
#> GSM647606 4 0.3860 -0.224 0.472 0.000 0.000 0.528 0.000 0.000
#> GSM647621 4 0.3982 -0.241 0.460 0.004 0.000 0.536 0.000 0.000
#> GSM647626 3 0.0405 0.885 0.008 0.000 0.988 0.004 0.000 0.000
#> GSM647538 1 0.4675 0.684 0.672 0.104 0.000 0.224 0.000 0.000
#> GSM647575 4 0.3684 0.447 0.000 0.000 0.000 0.628 0.000 0.372
#> GSM647590 4 0.3607 0.459 0.000 0.000 0.000 0.652 0.000 0.348
#> GSM647605 4 0.3695 0.442 0.000 0.000 0.000 0.624 0.000 0.376
#> GSM647607 6 0.3984 0.104 0.008 0.000 0.000 0.396 0.000 0.596
#> GSM647608 4 0.3854 -0.225 0.464 0.000 0.000 0.536 0.000 0.000
#> GSM647622 1 0.5189 0.511 0.468 0.444 0.000 0.088 0.000 0.000
#> GSM647623 2 0.3050 0.645 0.236 0.764 0.000 0.000 0.000 0.000
#> GSM647624 4 0.3695 0.442 0.000 0.000 0.000 0.624 0.000 0.376
#> GSM647625 2 0.3050 0.645 0.236 0.764 0.000 0.000 0.000 0.000
#> GSM647534 2 0.4832 -0.230 0.004 0.492 0.460 0.044 0.000 0.000
#> GSM647539 4 0.4067 0.298 0.008 0.000 0.000 0.548 0.000 0.444
#> GSM647566 1 0.4473 0.650 0.676 0.072 0.000 0.252 0.000 0.000
#> GSM647589 4 0.3986 -0.247 0.464 0.004 0.000 0.532 0.000 0.000
#> GSM647604 4 0.3607 0.459 0.000 0.000 0.000 0.652 0.000 0.348
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)
#> Error in mat[ceiling(1:nr/h_ratio), ceiling(1:nc/w_ratio), drop = FALSE]: subscript out of bounds
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) development.stage(p) other(p) k
#> ATC:kmeans 98 2.76e-01 0.696 0.396 2
#> ATC:kmeans 99 6.39e-02 0.366 0.238 3
#> ATC:kmeans 99 3.95e-03 0.681 0.606 4
#> ATC:kmeans 96 3.68e-05 0.455 0.517 5
#> ATC:kmeans 82 3.55e-07 0.167 0.714 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["ATC", "skmeans"]
# you can also extract it by
# res = res_list["ATC:skmeans"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'ATC' method.
#> Subgroups are detected by 'skmeans' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 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 0.955 0.983 0.5051 0.496 0.496
#> 3 3 1.000 0.963 0.986 0.2820 0.816 0.644
#> 4 4 0.933 0.913 0.950 0.0984 0.876 0.673
#> 5 5 0.763 0.791 0.860 0.0764 0.844 0.539
#> 6 6 0.746 0.623 0.785 0.0381 0.946 0.785
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 3
There is also optional best \(k\) = 2 3 that is worth to check.
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM647569 1 0.0000 1.000 1.000 0.000
#> GSM647574 1 0.0000 1.000 1.000 0.000
#> GSM647577 1 0.0000 1.000 1.000 0.000
#> GSM647547 2 0.0000 0.965 0.000 1.000
#> GSM647552 1 0.0000 1.000 1.000 0.000
#> GSM647553 1 0.0000 1.000 1.000 0.000
#> GSM647565 2 0.0000 0.965 0.000 1.000
#> GSM647545 2 0.0000 0.965 0.000 1.000
#> GSM647549 2 0.0000 0.965 0.000 1.000
#> GSM647550 1 0.0000 1.000 1.000 0.000
#> GSM647560 1 0.0000 1.000 1.000 0.000
#> GSM647617 1 0.0000 1.000 1.000 0.000
#> GSM647528 2 0.0000 0.965 0.000 1.000
#> GSM647529 2 0.0000 0.965 0.000 1.000
#> GSM647531 2 0.0000 0.965 0.000 1.000
#> GSM647540 1 0.0000 1.000 1.000 0.000
#> GSM647541 1 0.0000 1.000 1.000 0.000
#> GSM647546 1 0.0000 1.000 1.000 0.000
#> GSM647557 2 0.0000 0.965 0.000 1.000
#> GSM647561 2 0.0000 0.965 0.000 1.000
#> GSM647567 2 0.0000 0.965 0.000 1.000
#> GSM647568 1 0.0000 1.000 1.000 0.000
#> GSM647570 2 0.0000 0.965 0.000 1.000
#> GSM647573 2 0.0000 0.965 0.000 1.000
#> GSM647576 1 0.0000 1.000 1.000 0.000
#> GSM647579 1 0.0000 1.000 1.000 0.000
#> GSM647580 1 0.0000 1.000 1.000 0.000
#> GSM647583 1 0.0000 1.000 1.000 0.000
#> GSM647592 1 0.0000 1.000 1.000 0.000
#> GSM647593 2 0.1414 0.948 0.020 0.980
#> GSM647595 2 0.0000 0.965 0.000 1.000
#> GSM647597 2 0.0000 0.965 0.000 1.000
#> GSM647598 2 0.0000 0.965 0.000 1.000
#> GSM647613 2 0.0000 0.965 0.000 1.000
#> GSM647615 1 0.0000 1.000 1.000 0.000
#> GSM647616 1 0.0000 1.000 1.000 0.000
#> GSM647619 2 0.9954 0.193 0.460 0.540
#> GSM647582 1 0.0000 1.000 1.000 0.000
#> GSM647591 2 0.0000 0.965 0.000 1.000
#> GSM647527 2 0.0000 0.965 0.000 1.000
#> GSM647530 2 0.0000 0.965 0.000 1.000
#> GSM647532 2 0.0000 0.965 0.000 1.000
#> GSM647544 2 0.0000 0.965 0.000 1.000
#> GSM647551 1 0.0000 1.000 1.000 0.000
#> GSM647556 1 0.0000 1.000 1.000 0.000
#> GSM647558 2 0.0000 0.965 0.000 1.000
#> GSM647572 1 0.0000 1.000 1.000 0.000
#> GSM647578 1 0.0000 1.000 1.000 0.000
#> GSM647581 2 0.0000 0.965 0.000 1.000
#> GSM647594 2 0.0000 0.965 0.000 1.000
#> GSM647599 1 0.0000 1.000 1.000 0.000
#> GSM647600 1 0.0000 1.000 1.000 0.000
#> GSM647601 2 0.0000 0.965 0.000 1.000
#> GSM647603 1 0.0000 1.000 1.000 0.000
#> GSM647610 1 0.0000 1.000 1.000 0.000
#> GSM647611 1 0.0000 1.000 1.000 0.000
#> GSM647612 1 0.0000 1.000 1.000 0.000
#> GSM647614 1 0.0000 1.000 1.000 0.000
#> GSM647618 2 0.0000 0.965 0.000 1.000
#> GSM647629 1 0.0000 1.000 1.000 0.000
#> GSM647535 1 0.0000 1.000 1.000 0.000
#> GSM647563 2 0.0000 0.965 0.000 1.000
#> GSM647542 1 0.0000 1.000 1.000 0.000
#> GSM647543 1 0.0000 1.000 1.000 0.000
#> GSM647548 2 0.0000 0.965 0.000 1.000
#> GSM647554 1 0.0000 1.000 1.000 0.000
#> GSM647555 1 0.0000 1.000 1.000 0.000
#> GSM647559 2 0.0000 0.965 0.000 1.000
#> GSM647562 2 0.0000 0.965 0.000 1.000
#> GSM647564 1 0.0000 1.000 1.000 0.000
#> GSM647571 1 0.0000 1.000 1.000 0.000
#> GSM647584 2 0.9815 0.312 0.420 0.580
#> GSM647585 1 0.0000 1.000 1.000 0.000
#> GSM647586 2 0.0000 0.965 0.000 1.000
#> GSM647587 2 0.0000 0.965 0.000 1.000
#> GSM647588 2 0.0000 0.965 0.000 1.000
#> GSM647596 2 0.0000 0.965 0.000 1.000
#> GSM647602 1 0.0000 1.000 1.000 0.000
#> GSM647609 2 0.9815 0.312 0.420 0.580
#> GSM647620 1 0.0000 1.000 1.000 0.000
#> GSM647627 2 0.3114 0.914 0.056 0.944
#> GSM647628 2 0.0000 0.965 0.000 1.000
#> GSM647533 1 0.0000 1.000 1.000 0.000
#> GSM647536 2 0.0000 0.965 0.000 1.000
#> GSM647537 1 0.0000 1.000 1.000 0.000
#> GSM647606 2 0.0000 0.965 0.000 1.000
#> GSM647621 2 0.0000 0.965 0.000 1.000
#> GSM647626 1 0.0000 1.000 1.000 0.000
#> GSM647538 1 0.0376 0.996 0.996 0.004
#> GSM647575 2 0.0000 0.965 0.000 1.000
#> GSM647590 2 0.0000 0.965 0.000 1.000
#> GSM647605 2 0.0000 0.965 0.000 1.000
#> GSM647607 2 0.0000 0.965 0.000 1.000
#> GSM647608 2 0.0000 0.965 0.000 1.000
#> GSM647622 1 0.0000 1.000 1.000 0.000
#> GSM647623 1 0.0000 1.000 1.000 0.000
#> GSM647624 2 0.0000 0.965 0.000 1.000
#> GSM647625 1 0.0000 1.000 1.000 0.000
#> GSM647534 1 0.0000 1.000 1.000 0.000
#> GSM647539 2 0.0000 0.965 0.000 1.000
#> GSM647566 2 0.0000 0.965 0.000 1.000
#> GSM647589 2 0.9710 0.349 0.400 0.600
#> GSM647604 2 0.0000 0.965 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647574 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647577 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647547 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647552 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647553 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647565 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647545 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647549 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647550 3 0.6305 0.0509 0.000 0.484 0.516
#> GSM647560 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647617 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647528 2 0.0237 0.9673 0.004 0.996 0.000
#> GSM647529 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647531 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647540 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647541 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647546 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647557 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647561 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647567 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647568 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647570 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647573 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647576 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647579 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647580 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647583 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647592 2 0.0000 0.9699 0.000 1.000 0.000
#> GSM647593 2 0.0000 0.9699 0.000 1.000 0.000
#> GSM647595 2 0.0000 0.9699 0.000 1.000 0.000
#> GSM647597 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647598 2 0.0000 0.9699 0.000 1.000 0.000
#> GSM647613 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647615 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647616 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647619 2 0.0000 0.9699 0.000 1.000 0.000
#> GSM647582 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647591 2 0.0000 0.9699 0.000 1.000 0.000
#> GSM647527 2 0.0892 0.9551 0.020 0.980 0.000
#> GSM647530 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647532 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647544 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647551 2 0.0000 0.9699 0.000 1.000 0.000
#> GSM647556 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647558 2 0.5291 0.6555 0.268 0.732 0.000
#> GSM647572 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647578 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647581 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647594 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647599 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647600 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647601 2 0.0000 0.9699 0.000 1.000 0.000
#> GSM647603 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647610 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647611 2 0.0000 0.9699 0.000 1.000 0.000
#> GSM647612 3 0.0237 0.9848 0.000 0.004 0.996
#> GSM647614 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647618 2 0.0000 0.9699 0.000 1.000 0.000
#> GSM647629 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647535 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647563 2 0.0000 0.9699 0.000 1.000 0.000
#> GSM647542 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647543 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647548 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647554 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647555 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647559 2 0.0000 0.9699 0.000 1.000 0.000
#> GSM647562 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647564 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647571 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647584 2 0.0000 0.9699 0.000 1.000 0.000
#> GSM647585 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647586 2 0.0000 0.9699 0.000 1.000 0.000
#> GSM647587 2 0.5465 0.6211 0.288 0.712 0.000
#> GSM647588 2 0.0000 0.9699 0.000 1.000 0.000
#> GSM647596 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647602 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647609 2 0.0000 0.9699 0.000 1.000 0.000
#> GSM647620 2 0.1643 0.9293 0.000 0.956 0.044
#> GSM647627 2 0.0000 0.9699 0.000 1.000 0.000
#> GSM647628 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647533 3 0.0424 0.9801 0.008 0.000 0.992
#> GSM647536 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647537 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647606 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647621 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647626 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647538 1 0.4504 0.7390 0.804 0.000 0.196
#> GSM647575 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647590 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647605 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647607 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647608 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647622 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647623 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647624 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647625 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647534 3 0.0000 0.9885 0.000 0.000 1.000
#> GSM647539 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647566 1 0.0000 0.9871 1.000 0.000 0.000
#> GSM647589 1 0.4121 0.7780 0.832 0.000 0.168
#> GSM647604 1 0.0000 0.9871 1.000 0.000 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647574 3 0.1716 0.941 0.064 0.000 0.936 0.000
#> GSM647577 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647547 1 0.0188 0.800 0.996 0.000 0.000 0.004
#> GSM647552 3 0.0895 0.975 0.004 0.020 0.976 0.000
#> GSM647553 3 0.2081 0.924 0.084 0.000 0.916 0.000
#> GSM647565 4 0.4605 0.262 0.336 0.000 0.000 0.664
#> GSM647545 4 0.0000 0.937 0.000 0.000 0.000 1.000
#> GSM647549 4 0.0000 0.937 0.000 0.000 0.000 1.000
#> GSM647550 2 0.3402 0.753 0.004 0.832 0.164 0.000
#> GSM647560 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647617 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647528 4 0.2149 0.856 0.000 0.088 0.000 0.912
#> GSM647529 4 0.0592 0.925 0.016 0.000 0.000 0.984
#> GSM647531 4 0.0000 0.937 0.000 0.000 0.000 1.000
#> GSM647540 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647541 3 0.0895 0.975 0.004 0.020 0.976 0.000
#> GSM647546 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647557 4 0.0000 0.937 0.000 0.000 0.000 1.000
#> GSM647561 4 0.0000 0.937 0.000 0.000 0.000 1.000
#> GSM647567 1 0.4277 0.776 0.720 0.000 0.000 0.280
#> GSM647568 3 0.1637 0.945 0.060 0.000 0.940 0.000
#> GSM647570 4 0.0188 0.935 0.000 0.004 0.000 0.996
#> GSM647573 1 0.4888 0.578 0.588 0.000 0.000 0.412
#> GSM647576 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647579 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647580 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647583 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647592 2 0.0188 0.971 0.004 0.996 0.000 0.000
#> GSM647593 2 0.0000 0.972 0.000 1.000 0.000 0.000
#> GSM647595 2 0.0707 0.969 0.000 0.980 0.000 0.020
#> GSM647597 4 0.0000 0.937 0.000 0.000 0.000 1.000
#> GSM647598 4 0.3975 0.673 0.000 0.240 0.000 0.760
#> GSM647613 4 0.0000 0.937 0.000 0.000 0.000 1.000
#> GSM647615 3 0.0895 0.975 0.004 0.020 0.976 0.000
#> GSM647616 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647619 2 0.0000 0.972 0.000 1.000 0.000 0.000
#> GSM647582 3 0.0895 0.975 0.004 0.020 0.976 0.000
#> GSM647591 2 0.0817 0.967 0.000 0.976 0.000 0.024
#> GSM647527 4 0.2011 0.864 0.000 0.080 0.000 0.920
#> GSM647530 4 0.0336 0.931 0.008 0.000 0.000 0.992
#> GSM647532 4 0.1118 0.908 0.036 0.000 0.000 0.964
#> GSM647544 4 0.0000 0.937 0.000 0.000 0.000 1.000
#> GSM647551 2 0.0188 0.971 0.004 0.996 0.000 0.000
#> GSM647556 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647558 4 0.0188 0.935 0.000 0.004 0.000 0.996
#> GSM647572 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647578 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647581 4 0.0000 0.937 0.000 0.000 0.000 1.000
#> GSM647594 4 0.0000 0.937 0.000 0.000 0.000 1.000
#> GSM647599 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647600 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647601 2 0.0817 0.967 0.000 0.976 0.000 0.024
#> GSM647603 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647610 3 0.0895 0.975 0.004 0.020 0.976 0.000
#> GSM647611 2 0.0188 0.971 0.004 0.996 0.000 0.000
#> GSM647612 3 0.1489 0.956 0.004 0.044 0.952 0.000
#> GSM647614 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647618 2 0.1118 0.957 0.000 0.964 0.000 0.036
#> GSM647629 3 0.0657 0.979 0.004 0.012 0.984 0.000
#> GSM647535 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647563 4 0.3942 0.672 0.000 0.236 0.000 0.764
#> GSM647542 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647543 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647548 1 0.4661 0.689 0.652 0.000 0.000 0.348
#> GSM647554 3 0.0895 0.975 0.004 0.020 0.976 0.000
#> GSM647555 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647559 2 0.0817 0.967 0.000 0.976 0.000 0.024
#> GSM647562 4 0.0000 0.937 0.000 0.000 0.000 1.000
#> GSM647564 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647571 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647584 2 0.0000 0.972 0.000 1.000 0.000 0.000
#> GSM647585 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647586 2 0.0817 0.967 0.000 0.976 0.000 0.024
#> GSM647587 4 0.0188 0.935 0.000 0.004 0.000 0.996
#> GSM647588 2 0.0707 0.969 0.000 0.980 0.000 0.020
#> GSM647596 4 0.0000 0.937 0.000 0.000 0.000 1.000
#> GSM647602 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647609 2 0.0000 0.972 0.000 1.000 0.000 0.000
#> GSM647620 2 0.0188 0.971 0.004 0.996 0.000 0.000
#> GSM647627 2 0.0000 0.972 0.000 1.000 0.000 0.000
#> GSM647628 4 0.1211 0.905 0.040 0.000 0.000 0.960
#> GSM647533 1 0.1022 0.778 0.968 0.000 0.032 0.000
#> GSM647536 4 0.1118 0.908 0.036 0.000 0.000 0.964
#> GSM647537 3 0.2011 0.927 0.080 0.000 0.920 0.000
#> GSM647606 1 0.0188 0.800 0.996 0.000 0.000 0.004
#> GSM647621 1 0.0188 0.800 0.996 0.000 0.000 0.004
#> GSM647626 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647538 1 0.0188 0.797 0.996 0.000 0.004 0.000
#> GSM647575 1 0.4103 0.794 0.744 0.000 0.000 0.256
#> GSM647590 1 0.3942 0.798 0.764 0.000 0.000 0.236
#> GSM647605 1 0.4164 0.789 0.736 0.000 0.000 0.264
#> GSM647607 1 0.4222 0.783 0.728 0.000 0.000 0.272
#> GSM647608 1 0.0188 0.800 0.996 0.000 0.000 0.004
#> GSM647622 3 0.1867 0.935 0.072 0.000 0.928 0.000
#> GSM647623 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647624 1 0.4103 0.794 0.744 0.000 0.000 0.256
#> GSM647625 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647534 3 0.0000 0.987 0.000 0.000 1.000 0.000
#> GSM647539 1 0.4877 0.587 0.592 0.000 0.000 0.408
#> GSM647566 1 0.0188 0.800 0.996 0.000 0.000 0.004
#> GSM647589 1 0.0188 0.797 0.996 0.000 0.004 0.000
#> GSM647604 1 0.4103 0.794 0.744 0.000 0.000 0.256
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.0000 0.950 0.000 0.000 1.000 0.000 0.000
#> GSM647574 3 0.1357 0.915 0.048 0.000 0.948 0.000 0.004
#> GSM647577 3 0.0000 0.950 0.000 0.000 1.000 0.000 0.000
#> GSM647547 1 0.0671 0.890 0.980 0.000 0.000 0.004 0.016
#> GSM647552 5 0.3612 0.803 0.000 0.000 0.268 0.000 0.732
#> GSM647553 3 0.4675 0.690 0.164 0.000 0.736 0.000 0.100
#> GSM647565 4 0.2929 0.764 0.152 0.000 0.000 0.840 0.008
#> GSM647545 4 0.2179 0.759 0.000 0.100 0.000 0.896 0.004
#> GSM647549 4 0.0000 0.821 0.000 0.000 0.000 1.000 0.000
#> GSM647550 5 0.3596 0.678 0.000 0.200 0.016 0.000 0.784
#> GSM647560 3 0.0000 0.950 0.000 0.000 1.000 0.000 0.000
#> GSM647617 3 0.0000 0.950 0.000 0.000 1.000 0.000 0.000
#> GSM647528 2 0.3461 0.703 0.000 0.772 0.000 0.224 0.004
#> GSM647529 4 0.1357 0.814 0.048 0.000 0.000 0.948 0.004
#> GSM647531 4 0.0000 0.821 0.000 0.000 0.000 1.000 0.000
#> GSM647540 3 0.0000 0.950 0.000 0.000 1.000 0.000 0.000
#> GSM647541 5 0.3534 0.811 0.000 0.000 0.256 0.000 0.744
#> GSM647546 3 0.0000 0.950 0.000 0.000 1.000 0.000 0.000
#> GSM647557 4 0.0000 0.821 0.000 0.000 0.000 1.000 0.000
#> GSM647561 4 0.0324 0.819 0.000 0.004 0.000 0.992 0.004
#> GSM647567 4 0.4425 0.497 0.392 0.000 0.000 0.600 0.008
#> GSM647568 3 0.2905 0.851 0.036 0.000 0.868 0.000 0.096
#> GSM647570 4 0.3010 0.678 0.000 0.172 0.000 0.824 0.004
#> GSM647573 4 0.3487 0.721 0.212 0.000 0.000 0.780 0.008
#> GSM647576 3 0.0000 0.950 0.000 0.000 1.000 0.000 0.000
#> GSM647579 3 0.0000 0.950 0.000 0.000 1.000 0.000 0.000
#> GSM647580 3 0.0000 0.950 0.000 0.000 1.000 0.000 0.000
#> GSM647583 3 0.0000 0.950 0.000 0.000 1.000 0.000 0.000
#> GSM647592 5 0.3274 0.658 0.000 0.220 0.000 0.000 0.780
#> GSM647593 2 0.2966 0.683 0.000 0.816 0.000 0.000 0.184
#> GSM647595 2 0.1270 0.784 0.000 0.948 0.000 0.000 0.052
#> GSM647597 4 0.0000 0.821 0.000 0.000 0.000 1.000 0.000
#> GSM647598 2 0.3266 0.716 0.000 0.796 0.000 0.200 0.004
#> GSM647613 4 0.0162 0.820 0.000 0.000 0.000 0.996 0.004
#> GSM647615 5 0.3752 0.781 0.000 0.000 0.292 0.000 0.708
#> GSM647616 3 0.0000 0.950 0.000 0.000 1.000 0.000 0.000
#> GSM647619 2 0.3707 0.545 0.000 0.716 0.000 0.000 0.284
#> GSM647582 5 0.3534 0.811 0.000 0.000 0.256 0.000 0.744
#> GSM647591 2 0.1121 0.788 0.000 0.956 0.000 0.000 0.044
#> GSM647527 2 0.3579 0.691 0.000 0.756 0.000 0.240 0.004
#> GSM647530 4 0.0000 0.821 0.000 0.000 0.000 1.000 0.000
#> GSM647532 4 0.1502 0.812 0.056 0.000 0.000 0.940 0.004
#> GSM647544 4 0.1952 0.772 0.000 0.084 0.000 0.912 0.004
#> GSM647551 5 0.3274 0.658 0.000 0.220 0.000 0.000 0.780
#> GSM647556 3 0.0000 0.950 0.000 0.000 1.000 0.000 0.000
#> GSM647558 2 0.4321 0.456 0.000 0.600 0.000 0.396 0.004
#> GSM647572 3 0.0000 0.950 0.000 0.000 1.000 0.000 0.000
#> GSM647578 3 0.0000 0.950 0.000 0.000 1.000 0.000 0.000
#> GSM647581 4 0.0000 0.821 0.000 0.000 0.000 1.000 0.000
#> GSM647594 4 0.0000 0.821 0.000 0.000 0.000 1.000 0.000
#> GSM647599 3 0.0000 0.950 0.000 0.000 1.000 0.000 0.000
#> GSM647600 3 0.0000 0.950 0.000 0.000 1.000 0.000 0.000
#> GSM647601 2 0.0963 0.791 0.000 0.964 0.000 0.000 0.036
#> GSM647603 3 0.0000 0.950 0.000 0.000 1.000 0.000 0.000
#> GSM647610 5 0.3534 0.811 0.000 0.000 0.256 0.000 0.744
#> GSM647611 5 0.3274 0.658 0.000 0.220 0.000 0.000 0.780
#> GSM647612 5 0.3353 0.780 0.000 0.008 0.196 0.000 0.796
#> GSM647614 3 0.2124 0.875 0.004 0.000 0.900 0.000 0.096
#> GSM647618 2 0.1124 0.792 0.000 0.960 0.000 0.004 0.036
#> GSM647629 5 0.3932 0.737 0.000 0.000 0.328 0.000 0.672
#> GSM647535 3 0.0162 0.948 0.000 0.000 0.996 0.000 0.004
#> GSM647563 2 0.3430 0.705 0.000 0.776 0.000 0.220 0.004
#> GSM647542 3 0.2124 0.875 0.004 0.000 0.900 0.000 0.096
#> GSM647543 3 0.2179 0.873 0.004 0.000 0.896 0.000 0.100
#> GSM647548 4 0.3642 0.705 0.232 0.000 0.000 0.760 0.008
#> GSM647554 5 0.3534 0.811 0.000 0.000 0.256 0.000 0.744
#> GSM647555 3 0.0162 0.948 0.000 0.000 0.996 0.000 0.004
#> GSM647559 2 0.0000 0.789 0.000 1.000 0.000 0.000 0.000
#> GSM647562 4 0.0162 0.820 0.000 0.000 0.000 0.996 0.004
#> GSM647564 3 0.0000 0.950 0.000 0.000 1.000 0.000 0.000
#> GSM647571 3 0.0000 0.950 0.000 0.000 1.000 0.000 0.000
#> GSM647584 2 0.3586 0.579 0.000 0.736 0.000 0.000 0.264
#> GSM647585 3 0.0000 0.950 0.000 0.000 1.000 0.000 0.000
#> GSM647586 2 0.0000 0.789 0.000 1.000 0.000 0.000 0.000
#> GSM647587 2 0.4350 0.427 0.000 0.588 0.000 0.408 0.004
#> GSM647588 2 0.0880 0.792 0.000 0.968 0.000 0.000 0.032
#> GSM647596 4 0.2233 0.756 0.000 0.104 0.000 0.892 0.004
#> GSM647602 3 0.0000 0.950 0.000 0.000 1.000 0.000 0.000
#> GSM647609 2 0.3074 0.671 0.000 0.804 0.000 0.000 0.196
#> GSM647620 5 0.3366 0.666 0.000 0.212 0.004 0.000 0.784
#> GSM647627 2 0.0880 0.792 0.000 0.968 0.000 0.000 0.032
#> GSM647628 4 0.5204 0.716 0.064 0.092 0.000 0.748 0.096
#> GSM647533 1 0.2625 0.842 0.876 0.000 0.016 0.000 0.108
#> GSM647536 4 0.1502 0.812 0.056 0.000 0.000 0.940 0.004
#> GSM647537 3 0.4797 0.674 0.172 0.000 0.724 0.000 0.104
#> GSM647606 1 0.0162 0.894 0.996 0.000 0.000 0.004 0.000
#> GSM647621 1 0.0324 0.893 0.992 0.000 0.000 0.004 0.004
#> GSM647626 3 0.0000 0.950 0.000 0.000 1.000 0.000 0.000
#> GSM647538 1 0.2286 0.855 0.888 0.000 0.000 0.004 0.108
#> GSM647575 4 0.4517 0.408 0.436 0.000 0.000 0.556 0.008
#> GSM647590 1 0.4298 0.211 0.640 0.000 0.000 0.352 0.008
#> GSM647605 4 0.4354 0.539 0.368 0.000 0.000 0.624 0.008
#> GSM647607 4 0.4127 0.617 0.312 0.000 0.000 0.680 0.008
#> GSM647608 1 0.0290 0.893 0.992 0.000 0.000 0.008 0.000
#> GSM647622 3 0.4266 0.742 0.120 0.000 0.776 0.000 0.104
#> GSM647623 3 0.2068 0.876 0.004 0.000 0.904 0.000 0.092
#> GSM647624 4 0.4510 0.417 0.432 0.000 0.000 0.560 0.008
#> GSM647625 3 0.2233 0.867 0.004 0.000 0.892 0.000 0.104
#> GSM647534 3 0.0000 0.950 0.000 0.000 1.000 0.000 0.000
#> GSM647539 4 0.3582 0.712 0.224 0.000 0.000 0.768 0.008
#> GSM647566 1 0.2286 0.859 0.888 0.000 0.000 0.004 0.108
#> GSM647589 1 0.0324 0.894 0.992 0.000 0.000 0.004 0.004
#> GSM647604 4 0.4504 0.426 0.428 0.000 0.000 0.564 0.008
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.0000 0.8813 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647574 3 0.1793 0.8345 0.036 0.032 0.928 0.000 0.000 0.004
#> GSM647577 3 0.0000 0.8813 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647547 4 0.6093 -0.1527 0.284 0.216 0.000 0.488 0.000 0.012
#> GSM647552 6 0.2871 0.7935 0.000 0.004 0.192 0.000 0.000 0.804
#> GSM647553 3 0.4090 0.5254 0.328 0.016 0.652 0.000 0.000 0.004
#> GSM647565 4 0.3578 -0.3375 0.000 0.340 0.000 0.660 0.000 0.000
#> GSM647545 2 0.5220 0.6953 0.000 0.596 0.000 0.264 0.140 0.000
#> GSM647549 2 0.3804 0.8729 0.000 0.576 0.000 0.424 0.000 0.000
#> GSM647550 6 0.2062 0.7660 0.000 0.004 0.008 0.000 0.088 0.900
#> GSM647560 3 0.0000 0.8813 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647617 3 0.0000 0.8813 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647528 5 0.3337 0.6244 0.004 0.260 0.000 0.000 0.736 0.000
#> GSM647529 2 0.3866 0.7824 0.000 0.516 0.000 0.484 0.000 0.000
#> GSM647531 2 0.3804 0.8729 0.000 0.576 0.000 0.424 0.000 0.000
#> GSM647540 3 0.0000 0.8813 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647541 6 0.2558 0.8207 0.000 0.004 0.156 0.000 0.000 0.840
#> GSM647546 3 0.0000 0.8813 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647557 2 0.3804 0.8729 0.000 0.576 0.000 0.424 0.000 0.000
#> GSM647561 2 0.3789 0.8685 0.000 0.584 0.000 0.416 0.000 0.000
#> GSM647567 4 0.3141 0.1667 0.012 0.200 0.000 0.788 0.000 0.000
#> GSM647568 3 0.6458 0.3966 0.128 0.248 0.536 0.000 0.000 0.088
#> GSM647570 2 0.5383 0.5231 0.000 0.580 0.000 0.172 0.248 0.000
#> GSM647573 4 0.3023 0.0766 0.000 0.232 0.000 0.768 0.000 0.000
#> GSM647576 3 0.0146 0.8790 0.000 0.004 0.996 0.000 0.000 0.000
#> GSM647579 3 0.0000 0.8813 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647580 3 0.0000 0.8813 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647583 3 0.0000 0.8813 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647592 6 0.2752 0.7343 0.000 0.036 0.000 0.000 0.108 0.856
#> GSM647593 5 0.4201 0.5114 0.000 0.036 0.000 0.000 0.664 0.300
#> GSM647595 5 0.1866 0.7234 0.000 0.008 0.000 0.000 0.908 0.084
#> GSM647597 2 0.3804 0.8729 0.000 0.576 0.000 0.424 0.000 0.000
#> GSM647598 5 0.2668 0.6850 0.004 0.168 0.000 0.000 0.828 0.000
#> GSM647613 2 0.3797 0.8711 0.000 0.580 0.000 0.420 0.000 0.000
#> GSM647615 6 0.3584 0.6636 0.000 0.004 0.308 0.000 0.000 0.688
#> GSM647616 3 0.0000 0.8813 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647619 5 0.4443 0.3903 0.000 0.036 0.000 0.000 0.596 0.368
#> GSM647582 6 0.2558 0.8207 0.000 0.004 0.156 0.000 0.000 0.840
#> GSM647591 5 0.1701 0.7285 0.000 0.008 0.000 0.000 0.920 0.072
#> GSM647527 5 0.3489 0.6008 0.004 0.288 0.000 0.000 0.708 0.000
#> GSM647530 2 0.3823 0.8600 0.000 0.564 0.000 0.436 0.000 0.000
#> GSM647532 4 0.3869 -0.7760 0.000 0.500 0.000 0.500 0.000 0.000
#> GSM647544 2 0.5081 0.7398 0.000 0.588 0.000 0.308 0.104 0.000
#> GSM647551 6 0.2658 0.7414 0.000 0.036 0.000 0.000 0.100 0.864
#> GSM647556 3 0.0000 0.8813 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647558 5 0.4350 0.3216 0.004 0.428 0.000 0.016 0.552 0.000
#> GSM647572 3 0.0146 0.8794 0.000 0.000 0.996 0.000 0.000 0.004
#> GSM647578 3 0.0000 0.8813 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647581 2 0.3804 0.8729 0.000 0.576 0.000 0.424 0.000 0.000
#> GSM647594 2 0.3810 0.8693 0.000 0.572 0.000 0.428 0.000 0.000
#> GSM647599 3 0.0000 0.8813 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647600 3 0.0000 0.8813 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647601 5 0.0713 0.7429 0.000 0.000 0.000 0.000 0.972 0.028
#> GSM647603 3 0.0000 0.8813 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647610 6 0.2558 0.8207 0.000 0.004 0.156 0.000 0.000 0.840
#> GSM647611 6 0.2491 0.7405 0.000 0.020 0.000 0.000 0.112 0.868
#> GSM647612 6 0.3676 0.7573 0.020 0.052 0.120 0.000 0.000 0.808
#> GSM647614 3 0.6475 0.3892 0.128 0.252 0.532 0.000 0.000 0.088
#> GSM647618 5 0.0972 0.7436 0.000 0.008 0.000 0.000 0.964 0.028
#> GSM647629 6 0.3652 0.6412 0.000 0.004 0.324 0.000 0.000 0.672
#> GSM647535 3 0.0363 0.8733 0.000 0.000 0.988 0.000 0.000 0.012
#> GSM647563 5 0.2738 0.6821 0.004 0.176 0.000 0.000 0.820 0.000
#> GSM647542 3 0.6034 0.4969 0.120 0.204 0.600 0.000 0.000 0.076
#> GSM647543 3 0.6103 0.4802 0.120 0.216 0.588 0.000 0.000 0.076
#> GSM647548 4 0.2048 0.3358 0.000 0.120 0.000 0.880 0.000 0.000
#> GSM647554 6 0.2558 0.8207 0.000 0.004 0.156 0.000 0.000 0.840
#> GSM647555 3 0.0000 0.8813 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647559 5 0.0777 0.7374 0.004 0.024 0.000 0.000 0.972 0.000
#> GSM647562 2 0.3804 0.8729 0.000 0.576 0.000 0.424 0.000 0.000
#> GSM647564 3 0.0000 0.8813 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647571 3 0.0000 0.8813 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647584 5 0.4344 0.4540 0.000 0.036 0.000 0.000 0.628 0.336
#> GSM647585 3 0.0000 0.8813 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647586 5 0.0692 0.7379 0.004 0.020 0.000 0.000 0.976 0.000
#> GSM647587 5 0.4356 0.3106 0.004 0.432 0.000 0.016 0.548 0.000
#> GSM647588 5 0.0692 0.7431 0.000 0.004 0.000 0.000 0.976 0.020
#> GSM647596 2 0.5269 0.6693 0.000 0.596 0.000 0.248 0.156 0.000
#> GSM647602 3 0.0000 0.8813 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647609 5 0.4252 0.4944 0.000 0.036 0.000 0.000 0.652 0.312
#> GSM647620 6 0.1663 0.7603 0.000 0.000 0.000 0.000 0.088 0.912
#> GSM647627 5 0.1562 0.7424 0.004 0.032 0.000 0.000 0.940 0.024
#> GSM647628 4 0.7371 -0.0426 0.156 0.352 0.000 0.388 0.028 0.076
#> GSM647533 1 0.2933 0.9488 0.844 0.012 0.016 0.128 0.000 0.000
#> GSM647536 2 0.3868 0.7655 0.000 0.508 0.000 0.492 0.000 0.000
#> GSM647537 3 0.3999 0.1721 0.496 0.004 0.500 0.000 0.000 0.000
#> GSM647606 4 0.5297 -0.2897 0.412 0.088 0.000 0.496 0.000 0.004
#> GSM647621 4 0.6032 -0.1644 0.304 0.192 0.000 0.492 0.000 0.012
#> GSM647626 3 0.0000 0.8813 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647538 1 0.2513 0.9649 0.852 0.008 0.000 0.140 0.000 0.000
#> GSM647575 4 0.0858 0.4746 0.028 0.004 0.000 0.968 0.000 0.000
#> GSM647590 4 0.1610 0.4688 0.084 0.000 0.000 0.916 0.000 0.000
#> GSM647605 4 0.1957 0.3604 0.000 0.112 0.000 0.888 0.000 0.000
#> GSM647607 4 0.2416 0.2856 0.000 0.156 0.000 0.844 0.000 0.000
#> GSM647608 4 0.5818 -0.2330 0.364 0.136 0.000 0.488 0.000 0.012
#> GSM647622 3 0.3961 0.3269 0.440 0.004 0.556 0.000 0.000 0.000
#> GSM647623 3 0.4165 0.5487 0.308 0.004 0.664 0.000 0.000 0.024
#> GSM647624 4 0.0692 0.4677 0.020 0.004 0.000 0.976 0.000 0.000
#> GSM647625 3 0.4323 0.5314 0.312 0.004 0.652 0.000 0.000 0.032
#> GSM647534 3 0.0858 0.8581 0.000 0.004 0.968 0.000 0.000 0.028
#> GSM647539 4 0.3221 -0.0433 0.000 0.264 0.000 0.736 0.000 0.000
#> GSM647566 1 0.2743 0.9549 0.828 0.008 0.000 0.164 0.000 0.000
#> GSM647589 4 0.6063 -0.1802 0.316 0.192 0.000 0.480 0.000 0.012
#> GSM647604 4 0.1753 0.3981 0.004 0.084 0.000 0.912 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)
#> Error in mat[ceiling(1:nr/h_ratio), ceiling(1:nc/w_ratio), drop = FALSE]: subscript out of bounds
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) development.stage(p) other(p) k
#> ATC:skmeans 99 4.23e-01 0.682 0.375 2
#> ATC:skmeans 102 1.08e-03 0.462 0.318 3
#> ATC:skmeans 102 7.13e-10 0.432 0.354 4
#> ATC:skmeans 96 1.19e-06 0.818 0.678 5
#> ATC:skmeans 74 9.81e-06 0.525 0.881 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["ATC", "pam"]
# you can also extract it by
# res = res_list["ATC:pam"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'ATC' method.
#> Subgroups are detected by 'pam' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 3.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.697 0.898 0.951 0.4677 0.535 0.535
#> 3 3 0.954 0.912 0.966 0.3670 0.684 0.474
#> 4 4 0.778 0.752 0.845 0.1172 0.949 0.856
#> 5 5 0.843 0.877 0.920 0.1103 0.822 0.490
#> 6 6 0.849 0.813 0.896 0.0425 0.971 0.861
suggest_best_k() suggests the best \(k\) based on these statistics. The rules are as follows:
suggest_best_k(res)
#> [1] 3
Following shows the table of the partitions (You need to click the show/hide
code output link to see it). The membership matrix (columns with name p*)
is inferred by
clue::cl_consensus()
function with the SE method. Basically the value in the membership matrix
represents the probability to belong to a certain group. The finall class
label for an item is determined with the group with highest probability it
belongs to.
In get_classes() function, the entropy is calculated from the membership
matrix and the silhouette score is calculated from the consensus matrix.
cbind(get_classes(res, k = 2), get_membership(res, k = 2))
#> class entropy silhouette p1 p2
#> GSM647569 1 0.000 0.957 1.000 0.000
#> GSM647574 1 0.000 0.957 1.000 0.000
#> GSM647577 1 0.000 0.957 1.000 0.000
#> GSM647547 2 0.443 0.876 0.092 0.908
#> GSM647552 1 0.000 0.957 1.000 0.000
#> GSM647553 2 0.978 0.370 0.412 0.588
#> GSM647565 2 0.000 0.938 0.000 1.000
#> GSM647545 2 0.000 0.938 0.000 1.000
#> GSM647549 2 0.000 0.938 0.000 1.000
#> GSM647550 2 0.781 0.738 0.232 0.768
#> GSM647560 1 0.000 0.957 1.000 0.000
#> GSM647617 1 0.000 0.957 1.000 0.000
#> GSM647528 2 0.000 0.938 0.000 1.000
#> GSM647529 2 0.000 0.938 0.000 1.000
#> GSM647531 2 0.000 0.938 0.000 1.000
#> GSM647540 1 0.000 0.957 1.000 0.000
#> GSM647541 1 0.662 0.805 0.828 0.172
#> GSM647546 1 0.000 0.957 1.000 0.000
#> GSM647557 2 0.000 0.938 0.000 1.000
#> GSM647561 2 0.000 0.938 0.000 1.000
#> GSM647567 2 0.000 0.938 0.000 1.000
#> GSM647568 2 0.781 0.738 0.232 0.768
#> GSM647570 2 0.000 0.938 0.000 1.000
#> GSM647573 2 0.000 0.938 0.000 1.000
#> GSM647576 1 0.000 0.957 1.000 0.000
#> GSM647579 1 0.000 0.957 1.000 0.000
#> GSM647580 1 0.000 0.957 1.000 0.000
#> GSM647583 1 0.000 0.957 1.000 0.000
#> GSM647592 2 0.605 0.827 0.148 0.852
#> GSM647593 2 0.000 0.938 0.000 1.000
#> GSM647595 2 0.000 0.938 0.000 1.000
#> GSM647597 2 0.000 0.938 0.000 1.000
#> GSM647598 2 0.000 0.938 0.000 1.000
#> GSM647613 2 0.000 0.938 0.000 1.000
#> GSM647615 1 0.814 0.671 0.748 0.252
#> GSM647616 1 0.000 0.957 1.000 0.000
#> GSM647619 2 0.000 0.938 0.000 1.000
#> GSM647582 1 0.662 0.805 0.828 0.172
#> GSM647591 2 0.000 0.938 0.000 1.000
#> GSM647527 2 0.000 0.938 0.000 1.000
#> GSM647530 2 0.000 0.938 0.000 1.000
#> GSM647532 2 0.000 0.938 0.000 1.000
#> GSM647544 2 0.000 0.938 0.000 1.000
#> GSM647551 2 0.871 0.617 0.292 0.708
#> GSM647556 1 0.000 0.957 1.000 0.000
#> GSM647558 2 0.000 0.938 0.000 1.000
#> GSM647572 1 0.242 0.931 0.960 0.040
#> GSM647578 1 0.000 0.957 1.000 0.000
#> GSM647581 2 0.000 0.938 0.000 1.000
#> GSM647594 2 0.000 0.938 0.000 1.000
#> GSM647599 1 0.000 0.957 1.000 0.000
#> GSM647600 1 0.000 0.957 1.000 0.000
#> GSM647601 2 0.000 0.938 0.000 1.000
#> GSM647603 1 0.000 0.957 1.000 0.000
#> GSM647610 1 0.662 0.805 0.828 0.172
#> GSM647611 2 0.574 0.838 0.136 0.864
#> GSM647612 2 0.781 0.738 0.232 0.768
#> GSM647614 2 0.781 0.738 0.232 0.768
#> GSM647618 2 0.000 0.938 0.000 1.000
#> GSM647629 1 0.662 0.805 0.828 0.172
#> GSM647535 1 0.000 0.957 1.000 0.000
#> GSM647563 2 0.000 0.938 0.000 1.000
#> GSM647542 2 0.781 0.738 0.232 0.768
#> GSM647543 2 0.781 0.738 0.232 0.768
#> GSM647548 2 0.000 0.938 0.000 1.000
#> GSM647554 1 0.662 0.805 0.828 0.172
#> GSM647555 1 0.118 0.947 0.984 0.016
#> GSM647559 2 0.000 0.938 0.000 1.000
#> GSM647562 2 0.000 0.938 0.000 1.000
#> GSM647564 1 0.000 0.957 1.000 0.000
#> GSM647571 1 0.000 0.957 1.000 0.000
#> GSM647584 2 0.000 0.938 0.000 1.000
#> GSM647585 1 0.000 0.957 1.000 0.000
#> GSM647586 2 0.000 0.938 0.000 1.000
#> GSM647587 2 0.000 0.938 0.000 1.000
#> GSM647588 2 0.000 0.938 0.000 1.000
#> GSM647596 2 0.000 0.938 0.000 1.000
#> GSM647602 1 0.000 0.957 1.000 0.000
#> GSM647609 2 0.000 0.938 0.000 1.000
#> GSM647620 2 0.781 0.738 0.232 0.768
#> GSM647627 2 0.000 0.938 0.000 1.000
#> GSM647628 2 0.000 0.938 0.000 1.000
#> GSM647533 2 0.973 0.392 0.404 0.596
#> GSM647536 2 0.000 0.938 0.000 1.000
#> GSM647537 1 0.000 0.957 1.000 0.000
#> GSM647606 2 0.295 0.905 0.052 0.948
#> GSM647621 2 0.456 0.873 0.096 0.904
#> GSM647626 1 0.000 0.957 1.000 0.000
#> GSM647538 2 0.753 0.757 0.216 0.784
#> GSM647575 2 0.000 0.938 0.000 1.000
#> GSM647590 2 0.000 0.938 0.000 1.000
#> GSM647605 2 0.000 0.938 0.000 1.000
#> GSM647607 2 0.000 0.938 0.000 1.000
#> GSM647608 2 0.000 0.938 0.000 1.000
#> GSM647622 1 0.000 0.957 1.000 0.000
#> GSM647623 1 0.224 0.934 0.964 0.036
#> GSM647624 2 0.000 0.938 0.000 1.000
#> GSM647625 1 0.653 0.810 0.832 0.168
#> GSM647534 1 0.000 0.957 1.000 0.000
#> GSM647539 2 0.000 0.938 0.000 1.000
#> GSM647566 2 0.358 0.894 0.068 0.932
#> GSM647589 2 0.680 0.797 0.180 0.820
#> GSM647604 2 0.000 0.938 0.000 1.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 3 0.0000 0.95377 0.000 0.000 1.000
#> GSM647574 3 0.0000 0.95377 0.000 0.000 1.000
#> GSM647577 3 0.0000 0.95377 0.000 0.000 1.000
#> GSM647547 1 0.6204 0.34286 0.576 0.424 0.000
#> GSM647552 3 0.4555 0.73653 0.000 0.200 0.800
#> GSM647553 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647565 1 0.0000 0.91595 1.000 0.000 0.000
#> GSM647545 2 0.0237 0.98294 0.004 0.996 0.000
#> GSM647549 1 0.0000 0.91595 1.000 0.000 0.000
#> GSM647550 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647560 3 0.0000 0.95377 0.000 0.000 1.000
#> GSM647617 3 0.0000 0.95377 0.000 0.000 1.000
#> GSM647528 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647529 1 0.0000 0.91595 1.000 0.000 0.000
#> GSM647531 1 0.0000 0.91595 1.000 0.000 0.000
#> GSM647540 3 0.0000 0.95377 0.000 0.000 1.000
#> GSM647541 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647546 3 0.0747 0.93986 0.000 0.016 0.984
#> GSM647557 1 0.0000 0.91595 1.000 0.000 0.000
#> GSM647561 1 0.0000 0.91595 1.000 0.000 0.000
#> GSM647567 2 0.1643 0.94272 0.044 0.956 0.000
#> GSM647568 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647570 2 0.0424 0.97932 0.008 0.992 0.000
#> GSM647573 1 0.0000 0.91595 1.000 0.000 0.000
#> GSM647576 3 0.2796 0.86353 0.000 0.092 0.908
#> GSM647579 3 0.0000 0.95377 0.000 0.000 1.000
#> GSM647580 3 0.0000 0.95377 0.000 0.000 1.000
#> GSM647583 3 0.0000 0.95377 0.000 0.000 1.000
#> GSM647592 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647593 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647595 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647597 1 0.0000 0.91595 1.000 0.000 0.000
#> GSM647598 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647613 1 0.0000 0.91595 1.000 0.000 0.000
#> GSM647615 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647616 3 0.0000 0.95377 0.000 0.000 1.000
#> GSM647619 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647582 2 0.1753 0.93862 0.000 0.952 0.048
#> GSM647591 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647527 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647530 1 0.0000 0.91595 1.000 0.000 0.000
#> GSM647532 1 0.0000 0.91595 1.000 0.000 0.000
#> GSM647544 2 0.1753 0.93746 0.048 0.952 0.000
#> GSM647551 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647556 3 0.0000 0.95377 0.000 0.000 1.000
#> GSM647558 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647572 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647578 3 0.0000 0.95377 0.000 0.000 1.000
#> GSM647581 1 0.0000 0.91595 1.000 0.000 0.000
#> GSM647594 1 0.0000 0.91595 1.000 0.000 0.000
#> GSM647599 3 0.0000 0.95377 0.000 0.000 1.000
#> GSM647600 3 0.0000 0.95377 0.000 0.000 1.000
#> GSM647601 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647603 3 0.0000 0.95377 0.000 0.000 1.000
#> GSM647610 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647611 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647612 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647614 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647618 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647629 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647535 3 0.4702 0.72851 0.000 0.212 0.788
#> GSM647563 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647542 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647543 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647548 1 0.0000 0.91595 1.000 0.000 0.000
#> GSM647554 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647555 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647559 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647562 1 0.0000 0.91595 1.000 0.000 0.000
#> GSM647564 3 0.0000 0.95377 0.000 0.000 1.000
#> GSM647571 3 0.0000 0.95377 0.000 0.000 1.000
#> GSM647584 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647585 3 0.0000 0.95377 0.000 0.000 1.000
#> GSM647586 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647587 2 0.0424 0.97932 0.008 0.992 0.000
#> GSM647588 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647596 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647602 3 0.0000 0.95377 0.000 0.000 1.000
#> GSM647609 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647620 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647627 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647628 2 0.0747 0.97208 0.016 0.984 0.000
#> GSM647533 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647536 1 0.0000 0.91595 1.000 0.000 0.000
#> GSM647537 3 0.0000 0.95377 0.000 0.000 1.000
#> GSM647606 1 0.4555 0.73157 0.800 0.200 0.000
#> GSM647621 1 0.6204 0.34286 0.576 0.424 0.000
#> GSM647626 3 0.0000 0.95377 0.000 0.000 1.000
#> GSM647538 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647575 1 0.0000 0.91595 1.000 0.000 0.000
#> GSM647590 1 0.0000 0.91595 1.000 0.000 0.000
#> GSM647605 1 0.0000 0.91595 1.000 0.000 0.000
#> GSM647607 1 0.0000 0.91595 1.000 0.000 0.000
#> GSM647608 1 0.6079 0.42649 0.612 0.388 0.000
#> GSM647622 3 0.0000 0.95377 0.000 0.000 1.000
#> GSM647623 3 0.6309 0.00371 0.000 0.500 0.500
#> GSM647624 1 0.0000 0.91595 1.000 0.000 0.000
#> GSM647625 2 0.6126 0.29642 0.000 0.600 0.400
#> GSM647534 3 0.0000 0.95377 0.000 0.000 1.000
#> GSM647539 1 0.0000 0.91595 1.000 0.000 0.000
#> GSM647566 2 0.0000 0.98622 0.000 1.000 0.000
#> GSM647589 1 0.6204 0.34286 0.576 0.424 0.000
#> GSM647604 1 0.0000 0.91595 1.000 0.000 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 3 0.4866 0.854 0.000 0.000 0.596 0.404
#> GSM647574 3 0.4866 0.854 0.000 0.000 0.596 0.404
#> GSM647577 3 0.4866 0.854 0.000 0.000 0.596 0.404
#> GSM647547 1 0.5150 0.550 0.596 0.008 0.396 0.000
#> GSM647552 3 0.3528 0.717 0.000 0.000 0.808 0.192
#> GSM647553 2 0.4866 0.692 0.000 0.596 0.404 0.000
#> GSM647565 1 0.0000 0.679 1.000 0.000 0.000 0.000
#> GSM647545 2 0.0188 0.794 0.004 0.996 0.000 0.000
#> GSM647549 4 0.5600 0.903 0.376 0.028 0.000 0.596
#> GSM647550 2 0.4866 0.692 0.000 0.596 0.404 0.000
#> GSM647560 3 0.4855 0.852 0.000 0.000 0.600 0.400
#> GSM647617 3 0.4866 0.854 0.000 0.000 0.596 0.404
#> GSM647528 2 0.0000 0.796 0.000 1.000 0.000 0.000
#> GSM647529 4 0.4866 0.933 0.404 0.000 0.000 0.596
#> GSM647531 4 0.4866 0.933 0.404 0.000 0.000 0.596
#> GSM647540 3 0.4866 0.854 0.000 0.000 0.596 0.404
#> GSM647541 2 0.4866 0.692 0.000 0.596 0.404 0.000
#> GSM647546 3 0.0000 0.543 0.000 0.000 1.000 0.000
#> GSM647557 4 0.6862 0.618 0.176 0.228 0.000 0.596
#> GSM647561 4 0.6810 0.726 0.248 0.156 0.000 0.596
#> GSM647567 2 0.2002 0.766 0.044 0.936 0.020 0.000
#> GSM647568 2 0.4866 0.692 0.000 0.596 0.404 0.000
#> GSM647570 2 0.0000 0.796 0.000 1.000 0.000 0.000
#> GSM647573 1 0.0000 0.679 1.000 0.000 0.000 0.000
#> GSM647576 3 0.0000 0.543 0.000 0.000 1.000 0.000
#> GSM647579 3 0.4866 0.854 0.000 0.000 0.596 0.404
#> GSM647580 3 0.4866 0.854 0.000 0.000 0.596 0.404
#> GSM647583 3 0.4866 0.854 0.000 0.000 0.596 0.404
#> GSM647592 2 0.0336 0.795 0.000 0.992 0.008 0.000
#> GSM647593 2 0.0000 0.796 0.000 1.000 0.000 0.000
#> GSM647595 2 0.0000 0.796 0.000 1.000 0.000 0.000
#> GSM647597 4 0.4866 0.933 0.404 0.000 0.000 0.596
#> GSM647598 2 0.0000 0.796 0.000 1.000 0.000 0.000
#> GSM647613 4 0.4866 0.933 0.404 0.000 0.000 0.596
#> GSM647615 2 0.4866 0.692 0.000 0.596 0.404 0.000
#> GSM647616 3 0.4866 0.854 0.000 0.000 0.596 0.404
#> GSM647619 2 0.0000 0.796 0.000 1.000 0.000 0.000
#> GSM647582 2 0.4967 0.639 0.000 0.548 0.452 0.000
#> GSM647591 2 0.0000 0.796 0.000 1.000 0.000 0.000
#> GSM647527 2 0.0000 0.796 0.000 1.000 0.000 0.000
#> GSM647530 4 0.4866 0.933 0.404 0.000 0.000 0.596
#> GSM647532 4 0.4866 0.933 0.404 0.000 0.000 0.596
#> GSM647544 2 0.1557 0.751 0.056 0.944 0.000 0.000
#> GSM647551 2 0.0336 0.795 0.000 0.992 0.008 0.000
#> GSM647556 3 0.4866 0.854 0.000 0.000 0.596 0.404
#> GSM647558 2 0.0000 0.796 0.000 1.000 0.000 0.000
#> GSM647572 2 0.4866 0.692 0.000 0.596 0.404 0.000
#> GSM647578 3 0.4855 0.852 0.000 0.000 0.600 0.400
#> GSM647581 4 0.4866 0.933 0.404 0.000 0.000 0.596
#> GSM647594 4 0.4866 0.933 0.404 0.000 0.000 0.596
#> GSM647599 3 0.4866 0.854 0.000 0.000 0.596 0.404
#> GSM647600 3 0.4866 0.854 0.000 0.000 0.596 0.404
#> GSM647601 2 0.0000 0.796 0.000 1.000 0.000 0.000
#> GSM647603 3 0.4866 0.854 0.000 0.000 0.596 0.404
#> GSM647610 2 0.4866 0.692 0.000 0.596 0.404 0.000
#> GSM647611 2 0.0336 0.795 0.000 0.992 0.008 0.000
#> GSM647612 2 0.4866 0.692 0.000 0.596 0.404 0.000
#> GSM647614 2 0.4866 0.692 0.000 0.596 0.404 0.000
#> GSM647618 2 0.0000 0.796 0.000 1.000 0.000 0.000
#> GSM647629 2 0.4866 0.692 0.000 0.596 0.404 0.000
#> GSM647535 3 0.4215 0.577 0.000 0.072 0.824 0.104
#> GSM647563 2 0.0000 0.796 0.000 1.000 0.000 0.000
#> GSM647542 2 0.4866 0.692 0.000 0.596 0.404 0.000
#> GSM647543 2 0.4866 0.692 0.000 0.596 0.404 0.000
#> GSM647548 1 0.0000 0.679 1.000 0.000 0.000 0.000
#> GSM647554 2 0.4866 0.692 0.000 0.596 0.404 0.000
#> GSM647555 2 0.4866 0.692 0.000 0.596 0.404 0.000
#> GSM647559 2 0.0000 0.796 0.000 1.000 0.000 0.000
#> GSM647562 4 0.4888 0.925 0.412 0.000 0.000 0.588
#> GSM647564 3 0.4866 0.854 0.000 0.000 0.596 0.404
#> GSM647571 3 0.3801 0.739 0.000 0.000 0.780 0.220
#> GSM647584 2 0.0000 0.796 0.000 1.000 0.000 0.000
#> GSM647585 3 0.4866 0.854 0.000 0.000 0.596 0.404
#> GSM647586 2 0.0000 0.796 0.000 1.000 0.000 0.000
#> GSM647587 2 0.0000 0.796 0.000 1.000 0.000 0.000
#> GSM647588 2 0.0000 0.796 0.000 1.000 0.000 0.000
#> GSM647596 2 0.0000 0.796 0.000 1.000 0.000 0.000
#> GSM647602 3 0.4866 0.854 0.000 0.000 0.596 0.404
#> GSM647609 2 0.0000 0.796 0.000 1.000 0.000 0.000
#> GSM647620 2 0.2814 0.766 0.000 0.868 0.132 0.000
#> GSM647627 2 0.0000 0.796 0.000 1.000 0.000 0.000
#> GSM647628 2 0.5376 0.678 0.016 0.588 0.396 0.000
#> GSM647533 2 0.4866 0.692 0.000 0.596 0.404 0.000
#> GSM647536 4 0.4866 0.933 0.404 0.000 0.000 0.596
#> GSM647537 3 0.0000 0.543 0.000 0.000 1.000 0.000
#> GSM647606 1 0.4991 0.555 0.608 0.004 0.388 0.000
#> GSM647621 1 0.5016 0.552 0.600 0.004 0.396 0.000
#> GSM647626 3 0.4866 0.854 0.000 0.000 0.596 0.404
#> GSM647538 2 0.4866 0.692 0.000 0.596 0.404 0.000
#> GSM647575 1 0.0000 0.679 1.000 0.000 0.000 0.000
#> GSM647590 1 0.0000 0.679 1.000 0.000 0.000 0.000
#> GSM647605 1 0.0000 0.679 1.000 0.000 0.000 0.000
#> GSM647607 1 0.0000 0.679 1.000 0.000 0.000 0.000
#> GSM647608 1 0.5016 0.552 0.600 0.004 0.396 0.000
#> GSM647622 3 0.0000 0.543 0.000 0.000 1.000 0.000
#> GSM647623 3 0.2408 0.408 0.000 0.104 0.896 0.000
#> GSM647624 1 0.0000 0.679 1.000 0.000 0.000 0.000
#> GSM647625 3 0.3569 0.211 0.000 0.196 0.804 0.000
#> GSM647534 3 0.4866 0.854 0.000 0.000 0.596 0.404
#> GSM647539 1 0.0000 0.679 1.000 0.000 0.000 0.000
#> GSM647566 2 0.4855 0.692 0.000 0.600 0.400 0.000
#> GSM647589 1 0.4855 0.550 0.600 0.000 0.400 0.000
#> GSM647604 1 0.0000 0.679 1.000 0.000 0.000 0.000
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.0000 0.965 0.000 0.000 1.000 0.000 0.000
#> GSM647574 3 0.0671 0.953 0.000 0.000 0.980 0.016 0.004
#> GSM647577 3 0.0000 0.965 0.000 0.000 1.000 0.000 0.000
#> GSM647547 4 0.0000 0.813 0.000 0.000 0.000 1.000 0.000
#> GSM647552 5 0.0000 0.903 0.000 0.000 0.000 0.000 1.000
#> GSM647553 5 0.2648 0.866 0.000 0.000 0.000 0.152 0.848
#> GSM647565 4 0.3074 0.887 0.196 0.000 0.000 0.804 0.000
#> GSM647545 2 0.0000 0.921 0.000 1.000 0.000 0.000 0.000
#> GSM647549 1 0.3983 0.822 0.784 0.164 0.000 0.052 0.000
#> GSM647550 5 0.1121 0.901 0.000 0.000 0.000 0.044 0.956
#> GSM647560 3 0.2732 0.810 0.000 0.000 0.840 0.000 0.160
#> GSM647617 3 0.0000 0.965 0.000 0.000 1.000 0.000 0.000
#> GSM647528 2 0.0000 0.921 0.000 1.000 0.000 0.000 0.000
#> GSM647529 1 0.0000 0.908 1.000 0.000 0.000 0.000 0.000
#> GSM647531 1 0.0000 0.908 1.000 0.000 0.000 0.000 0.000
#> GSM647540 3 0.0000 0.965 0.000 0.000 1.000 0.000 0.000
#> GSM647541 5 0.0510 0.904 0.000 0.000 0.000 0.016 0.984
#> GSM647546 5 0.2561 0.869 0.000 0.000 0.000 0.144 0.856
#> GSM647557 1 0.2852 0.834 0.828 0.172 0.000 0.000 0.000
#> GSM647561 1 0.2813 0.838 0.832 0.168 0.000 0.000 0.000
#> GSM647567 2 0.0290 0.920 0.000 0.992 0.000 0.008 0.000
#> GSM647568 5 0.2648 0.866 0.000 0.000 0.000 0.152 0.848
#> GSM647570 2 0.0000 0.921 0.000 1.000 0.000 0.000 0.000
#> GSM647573 4 0.3074 0.887 0.196 0.000 0.000 0.804 0.000
#> GSM647576 5 0.0404 0.904 0.000 0.000 0.000 0.012 0.988
#> GSM647579 3 0.0000 0.965 0.000 0.000 1.000 0.000 0.000
#> GSM647580 3 0.0000 0.965 0.000 0.000 1.000 0.000 0.000
#> GSM647583 3 0.0000 0.965 0.000 0.000 1.000 0.000 0.000
#> GSM647592 5 0.1121 0.901 0.000 0.000 0.000 0.044 0.956
#> GSM647593 2 0.3216 0.848 0.000 0.848 0.000 0.044 0.108
#> GSM647595 2 0.0000 0.921 0.000 1.000 0.000 0.000 0.000
#> GSM647597 1 0.0290 0.907 0.992 0.008 0.000 0.000 0.000
#> GSM647598 2 0.0000 0.921 0.000 1.000 0.000 0.000 0.000
#> GSM647613 1 0.2732 0.844 0.840 0.160 0.000 0.000 0.000
#> GSM647615 5 0.1121 0.901 0.000 0.000 0.000 0.044 0.956
#> GSM647616 3 0.0000 0.965 0.000 0.000 1.000 0.000 0.000
#> GSM647619 2 0.3365 0.839 0.000 0.836 0.000 0.044 0.120
#> GSM647582 5 0.0510 0.904 0.000 0.000 0.000 0.016 0.984
#> GSM647591 2 0.0000 0.921 0.000 1.000 0.000 0.000 0.000
#> GSM647527 2 0.0000 0.921 0.000 1.000 0.000 0.000 0.000
#> GSM647530 1 0.0000 0.908 1.000 0.000 0.000 0.000 0.000
#> GSM647532 1 0.0000 0.908 1.000 0.000 0.000 0.000 0.000
#> GSM647544 2 0.0290 0.917 0.000 0.992 0.000 0.008 0.000
#> GSM647551 5 0.1121 0.901 0.000 0.000 0.000 0.044 0.956
#> GSM647556 3 0.1121 0.935 0.000 0.000 0.956 0.000 0.044
#> GSM647558 2 0.0000 0.921 0.000 1.000 0.000 0.000 0.000
#> GSM647572 5 0.2561 0.869 0.000 0.000 0.000 0.144 0.856
#> GSM647578 3 0.3816 0.571 0.000 0.000 0.696 0.000 0.304
#> GSM647581 1 0.0000 0.908 1.000 0.000 0.000 0.000 0.000
#> GSM647594 1 0.0000 0.908 1.000 0.000 0.000 0.000 0.000
#> GSM647599 3 0.1043 0.939 0.000 0.000 0.960 0.000 0.040
#> GSM647600 3 0.0000 0.965 0.000 0.000 1.000 0.000 0.000
#> GSM647601 2 0.0000 0.921 0.000 1.000 0.000 0.000 0.000
#> GSM647603 3 0.0000 0.965 0.000 0.000 1.000 0.000 0.000
#> GSM647610 5 0.0162 0.903 0.000 0.000 0.000 0.004 0.996
#> GSM647611 5 0.1408 0.898 0.000 0.008 0.000 0.044 0.948
#> GSM647612 5 0.1121 0.901 0.000 0.000 0.000 0.044 0.956
#> GSM647614 5 0.3231 0.862 0.000 0.004 0.000 0.196 0.800
#> GSM647618 2 0.0000 0.921 0.000 1.000 0.000 0.000 0.000
#> GSM647629 5 0.0404 0.904 0.000 0.000 0.000 0.012 0.988
#> GSM647535 5 0.0000 0.903 0.000 0.000 0.000 0.000 1.000
#> GSM647563 2 0.1121 0.907 0.000 0.956 0.000 0.044 0.000
#> GSM647542 5 0.2966 0.866 0.000 0.000 0.000 0.184 0.816
#> GSM647543 5 0.3074 0.863 0.000 0.000 0.000 0.196 0.804
#> GSM647548 4 0.3074 0.887 0.196 0.000 0.000 0.804 0.000
#> GSM647554 5 0.1121 0.901 0.000 0.000 0.000 0.044 0.956
#> GSM647555 5 0.1608 0.895 0.000 0.000 0.000 0.072 0.928
#> GSM647559 2 0.1121 0.907 0.000 0.956 0.000 0.044 0.000
#> GSM647562 1 0.2411 0.871 0.884 0.108 0.000 0.008 0.000
#> GSM647564 3 0.0290 0.961 0.000 0.000 0.992 0.000 0.008
#> GSM647571 5 0.2624 0.842 0.000 0.000 0.116 0.012 0.872
#> GSM647584 2 0.3365 0.839 0.000 0.836 0.000 0.044 0.120
#> GSM647585 3 0.0000 0.965 0.000 0.000 1.000 0.000 0.000
#> GSM647586 2 0.0880 0.912 0.000 0.968 0.000 0.032 0.000
#> GSM647587 2 0.0000 0.921 0.000 1.000 0.000 0.000 0.000
#> GSM647588 2 0.2708 0.872 0.000 0.884 0.000 0.044 0.072
#> GSM647596 2 0.0000 0.921 0.000 1.000 0.000 0.000 0.000
#> GSM647602 3 0.0000 0.965 0.000 0.000 1.000 0.000 0.000
#> GSM647609 2 0.3365 0.839 0.000 0.836 0.000 0.044 0.120
#> GSM647620 5 0.1121 0.901 0.000 0.000 0.000 0.044 0.956
#> GSM647627 2 0.3365 0.839 0.000 0.836 0.000 0.044 0.120
#> GSM647628 4 0.3636 0.597 0.000 0.272 0.000 0.728 0.000
#> GSM647533 5 0.2648 0.866 0.000 0.000 0.000 0.152 0.848
#> GSM647536 1 0.0000 0.908 1.000 0.000 0.000 0.000 0.000
#> GSM647537 5 0.6224 0.320 0.000 0.000 0.352 0.152 0.496
#> GSM647606 4 0.0000 0.813 0.000 0.000 0.000 1.000 0.000
#> GSM647621 4 0.0000 0.813 0.000 0.000 0.000 1.000 0.000
#> GSM647626 3 0.0000 0.965 0.000 0.000 1.000 0.000 0.000
#> GSM647538 5 0.3074 0.863 0.000 0.000 0.000 0.196 0.804
#> GSM647575 4 0.3074 0.887 0.196 0.000 0.000 0.804 0.000
#> GSM647590 4 0.3074 0.887 0.196 0.000 0.000 0.804 0.000
#> GSM647605 4 0.3074 0.887 0.196 0.000 0.000 0.804 0.000
#> GSM647607 4 0.3074 0.887 0.196 0.000 0.000 0.804 0.000
#> GSM647608 4 0.0000 0.813 0.000 0.000 0.000 1.000 0.000
#> GSM647622 5 0.5583 0.641 0.000 0.000 0.208 0.152 0.640
#> GSM647623 5 0.0290 0.904 0.000 0.000 0.000 0.008 0.992
#> GSM647624 4 0.3074 0.887 0.196 0.000 0.000 0.804 0.000
#> GSM647625 5 0.0000 0.903 0.000 0.000 0.000 0.000 1.000
#> GSM647534 3 0.0000 0.965 0.000 0.000 1.000 0.000 0.000
#> GSM647539 4 0.3074 0.887 0.196 0.000 0.000 0.804 0.000
#> GSM647566 2 0.6452 0.157 0.000 0.476 0.000 0.196 0.328
#> GSM647589 4 0.0510 0.809 0.000 0.000 0.000 0.984 0.016
#> GSM647604 4 0.3074 0.887 0.196 0.000 0.000 0.804 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.0000 0.937 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647574 3 0.2170 0.855 0.100 0.012 0.888 0.000 0.000 0.000
#> GSM647577 3 0.0000 0.937 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647547 4 0.3390 0.587 0.296 0.000 0.000 0.704 0.000 0.000
#> GSM647552 2 0.1285 0.750 0.004 0.944 0.052 0.000 0.000 0.000
#> GSM647553 1 0.3620 0.553 0.648 0.352 0.000 0.000 0.000 0.000
#> GSM647565 4 0.0000 0.883 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM647545 5 0.0000 0.890 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM647549 6 0.2869 0.802 0.000 0.000 0.000 0.020 0.148 0.832
#> GSM647550 2 0.2260 0.748 0.140 0.860 0.000 0.000 0.000 0.000
#> GSM647560 3 0.2814 0.783 0.008 0.172 0.820 0.000 0.000 0.000
#> GSM647617 3 0.0000 0.937 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647528 5 0.0000 0.890 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM647529 6 0.0000 0.982 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM647531 6 0.0000 0.982 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM647540 3 0.0000 0.937 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647541 2 0.0790 0.777 0.032 0.968 0.000 0.000 0.000 0.000
#> GSM647546 2 0.1714 0.746 0.092 0.908 0.000 0.000 0.000 0.000
#> GSM647557 6 0.0547 0.965 0.000 0.000 0.000 0.000 0.020 0.980
#> GSM647561 6 0.0000 0.982 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM647567 5 0.4011 0.521 0.304 0.000 0.000 0.024 0.672 0.000
#> GSM647568 2 0.3620 0.393 0.352 0.648 0.000 0.000 0.000 0.000
#> GSM647570 5 0.0000 0.890 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM647573 4 0.0000 0.883 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM647576 2 0.1204 0.761 0.056 0.944 0.000 0.000 0.000 0.000
#> GSM647579 3 0.0000 0.937 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647580 3 0.0000 0.937 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647583 3 0.0000 0.937 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647592 2 0.2631 0.722 0.180 0.820 0.000 0.000 0.000 0.000
#> GSM647593 5 0.3712 0.817 0.180 0.052 0.000 0.000 0.768 0.000
#> GSM647595 5 0.2001 0.873 0.040 0.048 0.000 0.000 0.912 0.000
#> GSM647597 6 0.0000 0.982 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM647598 5 0.0000 0.890 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM647613 6 0.0000 0.982 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM647615 2 0.2260 0.748 0.140 0.860 0.000 0.000 0.000 0.000
#> GSM647616 3 0.0000 0.937 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647619 5 0.3771 0.813 0.180 0.056 0.000 0.000 0.764 0.000
#> GSM647582 2 0.0547 0.776 0.020 0.980 0.000 0.000 0.000 0.000
#> GSM647591 5 0.2001 0.873 0.040 0.048 0.000 0.000 0.912 0.000
#> GSM647527 5 0.0000 0.890 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM647530 6 0.0000 0.982 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM647532 6 0.0000 0.982 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM647544 5 0.0713 0.875 0.000 0.000 0.000 0.028 0.972 0.000
#> GSM647551 2 0.2631 0.722 0.180 0.820 0.000 0.000 0.000 0.000
#> GSM647556 3 0.2431 0.825 0.008 0.132 0.860 0.000 0.000 0.000
#> GSM647558 5 0.0000 0.890 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM647572 2 0.3244 0.558 0.268 0.732 0.000 0.000 0.000 0.000
#> GSM647578 3 0.3789 0.523 0.008 0.332 0.660 0.000 0.000 0.000
#> GSM647581 6 0.0000 0.982 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM647594 6 0.0000 0.982 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM647599 3 0.3416 0.770 0.056 0.140 0.804 0.000 0.000 0.000
#> GSM647600 3 0.0000 0.937 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647601 5 0.0937 0.887 0.040 0.000 0.000 0.000 0.960 0.000
#> GSM647603 3 0.0000 0.937 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647610 2 0.0000 0.772 0.000 1.000 0.000 0.000 0.000 0.000
#> GSM647611 2 0.3523 0.681 0.180 0.780 0.000 0.000 0.040 0.000
#> GSM647612 2 0.4122 0.674 0.248 0.704 0.000 0.000 0.048 0.000
#> GSM647614 2 0.3864 0.405 0.480 0.520 0.000 0.000 0.000 0.000
#> GSM647618 5 0.0865 0.888 0.036 0.000 0.000 0.000 0.964 0.000
#> GSM647629 2 0.0458 0.776 0.016 0.984 0.000 0.000 0.000 0.000
#> GSM647535 2 0.1297 0.763 0.040 0.948 0.012 0.000 0.000 0.000
#> GSM647563 5 0.2402 0.852 0.140 0.004 0.000 0.000 0.856 0.000
#> GSM647542 2 0.3851 0.439 0.460 0.540 0.000 0.000 0.000 0.000
#> GSM647543 2 0.4520 0.393 0.448 0.520 0.000 0.000 0.032 0.000
#> GSM647548 4 0.0000 0.883 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM647554 2 0.2300 0.746 0.144 0.856 0.000 0.000 0.000 0.000
#> GSM647555 2 0.2912 0.633 0.216 0.784 0.000 0.000 0.000 0.000
#> GSM647559 5 0.2402 0.852 0.140 0.004 0.000 0.000 0.856 0.000
#> GSM647562 6 0.0260 0.975 0.000 0.000 0.000 0.008 0.000 0.992
#> GSM647564 3 0.1594 0.893 0.052 0.016 0.932 0.000 0.000 0.000
#> GSM647571 2 0.1462 0.759 0.056 0.936 0.008 0.000 0.000 0.000
#> GSM647584 5 0.3712 0.817 0.180 0.052 0.000 0.000 0.768 0.000
#> GSM647585 3 0.0000 0.937 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647586 5 0.1556 0.879 0.080 0.000 0.000 0.000 0.920 0.000
#> GSM647587 5 0.0000 0.890 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM647588 5 0.2772 0.844 0.180 0.004 0.000 0.000 0.816 0.000
#> GSM647596 5 0.0000 0.890 0.000 0.000 0.000 0.000 1.000 0.000
#> GSM647602 3 0.0000 0.937 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647609 5 0.3712 0.817 0.180 0.052 0.000 0.000 0.768 0.000
#> GSM647620 2 0.2300 0.746 0.144 0.856 0.000 0.000 0.000 0.000
#> GSM647627 5 0.2668 0.847 0.168 0.004 0.000 0.000 0.828 0.000
#> GSM647628 4 0.5614 0.310 0.300 0.004 0.000 0.540 0.156 0.000
#> GSM647533 1 0.2631 0.809 0.820 0.180 0.000 0.000 0.000 0.000
#> GSM647536 6 0.0000 0.982 0.000 0.000 0.000 0.000 0.000 1.000
#> GSM647537 1 0.2631 0.809 0.820 0.180 0.000 0.000 0.000 0.000
#> GSM647606 4 0.3817 0.277 0.432 0.000 0.000 0.568 0.000 0.000
#> GSM647621 4 0.2454 0.778 0.160 0.000 0.000 0.840 0.000 0.000
#> GSM647626 3 0.0000 0.937 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647538 1 0.1556 0.706 0.920 0.080 0.000 0.000 0.000 0.000
#> GSM647575 4 0.0000 0.883 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM647590 4 0.0000 0.883 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM647605 4 0.0000 0.883 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM647607 4 0.0000 0.883 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM647608 4 0.1501 0.843 0.076 0.000 0.000 0.924 0.000 0.000
#> GSM647622 1 0.2631 0.809 0.820 0.180 0.000 0.000 0.000 0.000
#> GSM647623 2 0.1204 0.761 0.056 0.944 0.000 0.000 0.000 0.000
#> GSM647624 4 0.0000 0.883 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM647625 2 0.1204 0.761 0.056 0.944 0.000 0.000 0.000 0.000
#> GSM647534 3 0.0000 0.937 0.000 0.000 1.000 0.000 0.000 0.000
#> GSM647539 4 0.0000 0.883 0.000 0.000 0.000 1.000 0.000 0.000
#> GSM647566 1 0.1462 0.696 0.936 0.056 0.000 0.000 0.008 0.000
#> GSM647589 4 0.2378 0.785 0.152 0.000 0.000 0.848 0.000 0.000
#> GSM647604 4 0.0000 0.883 0.000 0.000 0.000 1.000 0.000 0.000
Heatmaps for the consensus matrix. It visualizes the probability of two samples to be in a same group.
consensus_heatmap(res, k = 2)
consensus_heatmap(res, k = 3)
consensus_heatmap(res, k = 4)
consensus_heatmap(res, k = 5)
consensus_heatmap(res, k = 6)
Heatmaps for the membership of samples in all partitions to see how consistent they are:
membership_heatmap(res, k = 2)
membership_heatmap(res, k = 3)
membership_heatmap(res, k = 4)
membership_heatmap(res, k = 5)
membership_heatmap(res, k = 6)
As soon as we have had the classes for columns, we can look for signatures which are significantly different between classes which can be candidate marks for certain classes. Following are the heatmaps for signatures.
Signature heatmaps where rows are scaled:
get_signatures(res, k = 2)
get_signatures(res, k = 3)
get_signatures(res, k = 4)
get_signatures(res, k = 5)
get_signatures(res, k = 6)
Signature heatmaps where rows are not scaled:
get_signatures(res, k = 2, scale_rows = FALSE)
get_signatures(res, k = 3, scale_rows = FALSE)
#> Error in mat[ceiling(1:nr/h_ratio), ceiling(1:nc/w_ratio), drop = FALSE]: subscript out of bounds
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) development.stage(p) other(p) k
#> ATC:pam 101 6.68e-01 0.406 0.179 2
#> ATC:pam 97 3.96e-03 0.195 0.135 3
#> ATC:pam 101 1.17e-07 0.125 0.169 4
#> ATC:pam 101 9.13e-07 0.256 0.218 5
#> ATC:pam 97 6.36e-09 0.347 0.296 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["ATC", "mclust"]
# you can also extract it by
# res = res_list["ATC:mclust"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'ATC' method.
#> Subgroups are detected by 'mclust' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 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 0.483 0.844 0.896 0.4821 0.503 0.503
#> 3 3 0.610 0.814 0.862 0.3118 0.719 0.517
#> 4 4 0.624 0.733 0.808 0.1524 0.816 0.550
#> 5 5 0.553 0.573 0.760 0.0606 0.920 0.711
#> 6 6 0.642 0.336 0.689 0.0506 0.845 0.461
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
#> GSM647569 2 0.7674 0.859 0.224 0.776
#> GSM647574 1 0.0000 0.901 1.000 0.000
#> GSM647577 2 0.7674 0.859 0.224 0.776
#> GSM647547 1 0.0000 0.901 1.000 0.000
#> GSM647552 2 0.7815 0.853 0.232 0.768
#> GSM647553 1 0.0000 0.901 1.000 0.000
#> GSM647565 1 0.0000 0.901 1.000 0.000
#> GSM647545 1 0.8144 0.748 0.748 0.252
#> GSM647549 1 0.5629 0.842 0.868 0.132
#> GSM647550 2 0.2043 0.875 0.032 0.968
#> GSM647560 2 0.7674 0.859 0.224 0.776
#> GSM647617 2 0.7674 0.859 0.224 0.776
#> GSM647528 2 0.0376 0.860 0.004 0.996
#> GSM647529 1 0.5059 0.853 0.888 0.112
#> GSM647531 1 0.5629 0.842 0.868 0.132
#> GSM647540 2 0.7674 0.859 0.224 0.776
#> GSM647541 2 0.2043 0.875 0.032 0.968
#> GSM647546 2 0.7815 0.854 0.232 0.768
#> GSM647557 1 0.7056 0.786 0.808 0.192
#> GSM647561 1 0.7528 0.770 0.784 0.216
#> GSM647567 1 0.0000 0.901 1.000 0.000
#> GSM647568 1 0.8386 0.523 0.732 0.268
#> GSM647570 2 0.2603 0.840 0.044 0.956
#> GSM647573 1 0.0000 0.901 1.000 0.000
#> GSM647576 2 0.7815 0.854 0.232 0.768
#> GSM647579 2 0.7674 0.859 0.224 0.776
#> GSM647580 2 0.7674 0.859 0.224 0.776
#> GSM647583 2 0.7674 0.859 0.224 0.776
#> GSM647592 2 0.4022 0.875 0.080 0.920
#> GSM647593 2 0.2043 0.875 0.032 0.968
#> GSM647595 2 0.2043 0.875 0.032 0.968
#> GSM647597 1 0.5629 0.842 0.868 0.132
#> GSM647598 2 0.0000 0.860 0.000 1.000
#> GSM647613 1 0.6623 0.815 0.828 0.172
#> GSM647615 2 0.3584 0.877 0.068 0.932
#> GSM647616 2 0.7815 0.854 0.232 0.768
#> GSM647619 2 0.2043 0.875 0.032 0.968
#> GSM647582 2 0.5842 0.872 0.140 0.860
#> GSM647591 2 0.2043 0.875 0.032 0.968
#> GSM647527 2 0.0672 0.860 0.008 0.992
#> GSM647530 1 0.5629 0.842 0.868 0.132
#> GSM647532 1 0.0000 0.901 1.000 0.000
#> GSM647544 1 0.6712 0.819 0.824 0.176
#> GSM647551 2 0.2043 0.875 0.032 0.968
#> GSM647556 2 0.7674 0.859 0.224 0.776
#> GSM647558 2 0.0672 0.860 0.008 0.992
#> GSM647572 2 0.7815 0.854 0.232 0.768
#> GSM647578 2 0.7674 0.859 0.224 0.776
#> GSM647581 1 0.5629 0.842 0.868 0.132
#> GSM647594 1 0.5629 0.842 0.868 0.132
#> GSM647599 1 0.6438 0.724 0.836 0.164
#> GSM647600 2 0.7674 0.859 0.224 0.776
#> GSM647601 2 0.0376 0.862 0.004 0.996
#> GSM647603 2 0.7674 0.859 0.224 0.776
#> GSM647610 2 0.2043 0.875 0.032 0.968
#> GSM647611 2 0.2043 0.875 0.032 0.968
#> GSM647612 2 0.2043 0.875 0.032 0.968
#> GSM647614 2 0.8267 0.825 0.260 0.740
#> GSM647618 2 0.0376 0.862 0.004 0.996
#> GSM647629 2 0.2043 0.875 0.032 0.968
#> GSM647535 2 0.7299 0.862 0.204 0.796
#> GSM647563 2 0.0672 0.860 0.008 0.992
#> GSM647542 2 0.7674 0.859 0.224 0.776
#> GSM647543 2 0.7815 0.854 0.232 0.768
#> GSM647548 1 0.0000 0.901 1.000 0.000
#> GSM647554 2 0.2043 0.875 0.032 0.968
#> GSM647555 2 0.7674 0.859 0.224 0.776
#> GSM647559 2 0.0000 0.860 0.000 1.000
#> GSM647562 1 0.5629 0.842 0.868 0.132
#> GSM647564 2 0.7674 0.859 0.224 0.776
#> GSM647571 2 0.7674 0.859 0.224 0.776
#> GSM647584 2 0.2043 0.875 0.032 0.968
#> GSM647585 1 0.9996 -0.273 0.512 0.488
#> GSM647586 2 0.0000 0.860 0.000 1.000
#> GSM647587 2 0.0672 0.860 0.008 0.992
#> GSM647588 2 0.0000 0.860 0.000 1.000
#> GSM647596 1 0.9732 0.511 0.596 0.404
#> GSM647602 2 0.7674 0.859 0.224 0.776
#> GSM647609 2 0.2043 0.875 0.032 0.968
#> GSM647620 2 0.2043 0.875 0.032 0.968
#> GSM647627 2 0.0000 0.860 0.000 1.000
#> GSM647628 1 0.8861 0.431 0.696 0.304
#> GSM647533 1 0.0000 0.901 1.000 0.000
#> GSM647536 1 0.2043 0.889 0.968 0.032
#> GSM647537 1 0.0000 0.901 1.000 0.000
#> GSM647606 1 0.0000 0.901 1.000 0.000
#> GSM647621 1 0.0000 0.901 1.000 0.000
#> GSM647626 2 0.7674 0.859 0.224 0.776
#> GSM647538 1 0.0000 0.901 1.000 0.000
#> GSM647575 1 0.0000 0.901 1.000 0.000
#> GSM647590 1 0.0000 0.901 1.000 0.000
#> GSM647605 1 0.0000 0.901 1.000 0.000
#> GSM647607 1 0.0000 0.901 1.000 0.000
#> GSM647608 1 0.0000 0.901 1.000 0.000
#> GSM647622 1 0.0000 0.901 1.000 0.000
#> GSM647623 1 0.0000 0.901 1.000 0.000
#> GSM647624 1 0.0000 0.901 1.000 0.000
#> GSM647625 1 0.0000 0.901 1.000 0.000
#> GSM647534 2 0.8327 0.818 0.264 0.736
#> GSM647539 1 0.0000 0.901 1.000 0.000
#> GSM647566 1 0.0000 0.901 1.000 0.000
#> GSM647589 1 0.0000 0.901 1.000 0.000
#> GSM647604 1 0.0000 0.901 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 3 0.5397 0.910 0.000 0.280 0.720
#> GSM647574 1 0.0000 0.925 1.000 0.000 0.000
#> GSM647577 3 0.5397 0.910 0.000 0.280 0.720
#> GSM647547 1 0.0000 0.925 1.000 0.000 0.000
#> GSM647552 2 0.0592 0.812 0.000 0.988 0.012
#> GSM647553 1 0.0237 0.923 0.996 0.000 0.004
#> GSM647565 1 0.0000 0.925 1.000 0.000 0.000
#> GSM647545 2 0.5687 0.760 0.020 0.756 0.224
#> GSM647549 2 0.6853 0.721 0.064 0.712 0.224
#> GSM647550 2 0.0000 0.814 0.000 1.000 0.000
#> GSM647560 3 0.6172 0.865 0.012 0.308 0.680
#> GSM647617 3 0.5397 0.910 0.000 0.280 0.720
#> GSM647528 2 0.4842 0.774 0.000 0.776 0.224
#> GSM647529 1 0.4399 0.808 0.812 0.000 0.188
#> GSM647531 1 0.4842 0.779 0.776 0.000 0.224
#> GSM647540 3 0.5397 0.910 0.000 0.280 0.720
#> GSM647541 2 0.0000 0.814 0.000 1.000 0.000
#> GSM647546 3 0.7633 0.751 0.184 0.132 0.684
#> GSM647557 1 0.6673 0.716 0.720 0.056 0.224
#> GSM647561 2 0.6578 0.732 0.052 0.724 0.224
#> GSM647567 1 0.1289 0.919 0.968 0.000 0.032
#> GSM647568 2 0.8624 0.509 0.240 0.596 0.164
#> GSM647570 2 0.4842 0.774 0.000 0.776 0.224
#> GSM647573 1 0.0000 0.925 1.000 0.000 0.000
#> GSM647576 2 0.7361 0.594 0.124 0.704 0.172
#> GSM647579 3 0.5397 0.910 0.000 0.280 0.720
#> GSM647580 3 0.5397 0.910 0.000 0.280 0.720
#> GSM647583 3 0.5397 0.910 0.000 0.280 0.720
#> GSM647592 2 0.0237 0.814 0.000 0.996 0.004
#> GSM647593 2 0.0237 0.814 0.000 0.996 0.004
#> GSM647595 2 0.0237 0.814 0.000 0.996 0.004
#> GSM647597 1 0.3267 0.884 0.884 0.000 0.116
#> GSM647598 2 0.4842 0.774 0.000 0.776 0.224
#> GSM647613 2 0.6276 0.744 0.040 0.736 0.224
#> GSM647615 2 0.0000 0.814 0.000 1.000 0.000
#> GSM647616 3 0.7138 0.815 0.120 0.160 0.720
#> GSM647619 2 0.0237 0.814 0.000 0.996 0.004
#> GSM647582 2 0.0237 0.814 0.000 0.996 0.004
#> GSM647591 2 0.0237 0.814 0.000 0.996 0.004
#> GSM647527 2 0.4842 0.774 0.000 0.776 0.224
#> GSM647530 1 0.4842 0.779 0.776 0.000 0.224
#> GSM647532 1 0.3116 0.868 0.892 0.000 0.108
#> GSM647544 2 0.5874 0.765 0.032 0.760 0.208
#> GSM647551 2 0.0237 0.814 0.000 0.996 0.004
#> GSM647556 3 0.6722 0.868 0.060 0.220 0.720
#> GSM647558 2 0.4842 0.774 0.000 0.776 0.224
#> GSM647572 2 0.7844 0.506 0.120 0.660 0.220
#> GSM647578 2 0.4291 0.624 0.000 0.820 0.180
#> GSM647581 1 0.4842 0.779 0.776 0.000 0.224
#> GSM647594 1 0.4750 0.787 0.784 0.000 0.216
#> GSM647599 3 0.6984 0.504 0.304 0.040 0.656
#> GSM647600 3 0.5397 0.910 0.000 0.280 0.720
#> GSM647601 2 0.2625 0.813 0.000 0.916 0.084
#> GSM647603 3 0.5397 0.910 0.000 0.280 0.720
#> GSM647610 2 0.0000 0.814 0.000 1.000 0.000
#> GSM647611 2 0.0000 0.814 0.000 1.000 0.000
#> GSM647612 2 0.0000 0.814 0.000 1.000 0.000
#> GSM647614 2 0.6918 0.657 0.136 0.736 0.128
#> GSM647618 2 0.4399 0.788 0.000 0.812 0.188
#> GSM647629 2 0.0000 0.814 0.000 1.000 0.000
#> GSM647535 2 0.2878 0.736 0.000 0.904 0.096
#> GSM647563 2 0.4750 0.778 0.000 0.784 0.216
#> GSM647542 2 0.6662 0.667 0.120 0.752 0.128
#> GSM647543 2 0.6597 0.672 0.120 0.756 0.124
#> GSM647548 1 0.0000 0.925 1.000 0.000 0.000
#> GSM647554 2 0.0000 0.814 0.000 1.000 0.000
#> GSM647555 2 0.3482 0.699 0.000 0.872 0.128
#> GSM647559 2 0.2625 0.814 0.000 0.916 0.084
#> GSM647562 2 0.9150 0.537 0.232 0.544 0.224
#> GSM647564 3 0.5397 0.910 0.000 0.280 0.720
#> GSM647571 2 0.4178 0.637 0.000 0.828 0.172
#> GSM647584 2 0.0237 0.814 0.000 0.996 0.004
#> GSM647585 3 0.6597 0.571 0.268 0.036 0.696
#> GSM647586 2 0.4842 0.774 0.000 0.776 0.224
#> GSM647587 2 0.4842 0.774 0.000 0.776 0.224
#> GSM647588 2 0.0592 0.816 0.000 0.988 0.012
#> GSM647596 2 0.5070 0.771 0.004 0.772 0.224
#> GSM647602 3 0.5397 0.910 0.000 0.280 0.720
#> GSM647609 2 0.4062 0.796 0.000 0.836 0.164
#> GSM647620 2 0.0000 0.814 0.000 1.000 0.000
#> GSM647627 2 0.3267 0.808 0.000 0.884 0.116
#> GSM647628 2 0.7026 0.657 0.152 0.728 0.120
#> GSM647533 1 0.1860 0.915 0.948 0.000 0.052
#> GSM647536 1 0.4399 0.808 0.812 0.000 0.188
#> GSM647537 1 0.1860 0.915 0.948 0.000 0.052
#> GSM647606 1 0.1860 0.915 0.948 0.000 0.052
#> GSM647621 1 0.0000 0.925 1.000 0.000 0.000
#> GSM647626 3 0.5397 0.910 0.000 0.280 0.720
#> GSM647538 1 0.1860 0.915 0.948 0.000 0.052
#> GSM647575 1 0.0000 0.925 1.000 0.000 0.000
#> GSM647590 1 0.1860 0.915 0.948 0.000 0.052
#> GSM647605 1 0.0000 0.925 1.000 0.000 0.000
#> GSM647607 1 0.0237 0.924 0.996 0.000 0.004
#> GSM647608 1 0.0000 0.925 1.000 0.000 0.000
#> GSM647622 1 0.1860 0.915 0.948 0.000 0.052
#> GSM647623 1 0.1860 0.915 0.948 0.000 0.052
#> GSM647624 1 0.0237 0.924 0.996 0.000 0.004
#> GSM647625 1 0.1860 0.915 0.948 0.000 0.052
#> GSM647534 2 0.5307 0.693 0.056 0.820 0.124
#> GSM647539 1 0.0000 0.925 1.000 0.000 0.000
#> GSM647566 1 0.1860 0.915 0.948 0.000 0.052
#> GSM647589 1 0.0000 0.925 1.000 0.000 0.000
#> GSM647604 1 0.1860 0.915 0.948 0.000 0.052
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 3 0.0000 0.8815 0.000 0.000 1.000 0.000
#> GSM647574 1 0.2089 0.8532 0.932 0.000 0.020 0.048
#> GSM647577 3 0.0000 0.8815 0.000 0.000 1.000 0.000
#> GSM647547 1 0.0921 0.8588 0.972 0.000 0.000 0.028
#> GSM647552 2 0.5980 0.6001 0.040 0.592 0.364 0.004
#> GSM647553 1 0.2400 0.8496 0.924 0.004 0.028 0.044
#> GSM647565 1 0.1022 0.8587 0.968 0.000 0.000 0.032
#> GSM647545 4 0.0469 0.6875 0.000 0.012 0.000 0.988
#> GSM647549 4 0.5229 -0.2539 0.428 0.008 0.000 0.564
#> GSM647550 4 0.7680 0.1125 0.000 0.324 0.232 0.444
#> GSM647560 3 0.0524 0.8784 0.004 0.008 0.988 0.000
#> GSM647617 3 0.0000 0.8815 0.000 0.000 1.000 0.000
#> GSM647528 4 0.2345 0.6790 0.000 0.100 0.000 0.900
#> GSM647529 1 0.3123 0.8225 0.844 0.000 0.000 0.156
#> GSM647531 1 0.4697 0.6423 0.644 0.000 0.000 0.356
#> GSM647540 3 0.0524 0.8784 0.004 0.000 0.988 0.008
#> GSM647541 2 0.4466 0.9298 0.000 0.784 0.180 0.036
#> GSM647546 3 0.0895 0.8723 0.020 0.004 0.976 0.000
#> GSM647557 1 0.5285 0.4548 0.524 0.008 0.000 0.468
#> GSM647561 4 0.3810 0.4818 0.188 0.008 0.000 0.804
#> GSM647567 1 0.1545 0.8515 0.952 0.040 0.008 0.000
#> GSM647568 4 0.7299 0.4486 0.184 0.004 0.260 0.552
#> GSM647570 4 0.0592 0.6884 0.000 0.016 0.000 0.984
#> GSM647573 1 0.1022 0.8584 0.968 0.000 0.000 0.032
#> GSM647576 3 0.2266 0.7989 0.004 0.084 0.912 0.000
#> GSM647579 3 0.0000 0.8815 0.000 0.000 1.000 0.000
#> GSM647580 3 0.0000 0.8815 0.000 0.000 1.000 0.000
#> GSM647583 3 0.0000 0.8815 0.000 0.000 1.000 0.000
#> GSM647592 2 0.3969 0.9386 0.000 0.804 0.180 0.016
#> GSM647593 2 0.3852 0.9374 0.000 0.808 0.180 0.012
#> GSM647595 2 0.3852 0.9374 0.000 0.808 0.180 0.012
#> GSM647597 1 0.4095 0.7893 0.792 0.016 0.000 0.192
#> GSM647598 4 0.4728 0.5963 0.000 0.216 0.032 0.752
#> GSM647613 4 0.3498 0.5307 0.160 0.008 0.000 0.832
#> GSM647615 2 0.4808 0.8793 0.000 0.736 0.236 0.028
#> GSM647616 3 0.0188 0.8798 0.004 0.000 0.996 0.000
#> GSM647619 2 0.3852 0.9374 0.000 0.808 0.180 0.012
#> GSM647582 2 0.4079 0.9386 0.000 0.800 0.180 0.020
#> GSM647591 2 0.3852 0.9374 0.000 0.808 0.180 0.012
#> GSM647527 4 0.2345 0.6790 0.000 0.100 0.000 0.900
#> GSM647530 1 0.4522 0.6889 0.680 0.000 0.000 0.320
#> GSM647532 1 0.2704 0.8354 0.876 0.000 0.000 0.124
#> GSM647544 4 0.2262 0.6886 0.016 0.012 0.040 0.932
#> GSM647551 2 0.3725 0.9360 0.000 0.812 0.180 0.008
#> GSM647556 3 0.0524 0.8784 0.004 0.000 0.988 0.008
#> GSM647558 4 0.0592 0.6884 0.000 0.016 0.000 0.984
#> GSM647572 3 0.4746 0.4910 0.004 0.008 0.712 0.276
#> GSM647578 3 0.0524 0.8784 0.004 0.000 0.988 0.008
#> GSM647581 1 0.4697 0.6423 0.644 0.000 0.000 0.356
#> GSM647594 1 0.4624 0.6609 0.660 0.000 0.000 0.340
#> GSM647599 3 0.6844 0.4270 0.260 0.152 0.588 0.000
#> GSM647600 3 0.0000 0.8815 0.000 0.000 1.000 0.000
#> GSM647601 2 0.5771 0.8156 0.000 0.712 0.144 0.144
#> GSM647603 3 0.0000 0.8815 0.000 0.000 1.000 0.000
#> GSM647610 2 0.4079 0.9386 0.000 0.800 0.180 0.020
#> GSM647611 2 0.4079 0.9386 0.000 0.800 0.180 0.020
#> GSM647612 4 0.6919 0.4127 0.000 0.120 0.352 0.528
#> GSM647614 4 0.5355 0.3628 0.004 0.008 0.408 0.580
#> GSM647618 2 0.6289 0.6631 0.000 0.648 0.116 0.236
#> GSM647629 2 0.4121 0.9377 0.000 0.796 0.184 0.020
#> GSM647535 3 0.2115 0.8400 0.004 0.024 0.936 0.036
#> GSM647563 4 0.2924 0.6775 0.000 0.100 0.016 0.884
#> GSM647542 4 0.5524 0.3133 0.004 0.012 0.432 0.552
#> GSM647543 4 0.5400 0.3226 0.004 0.008 0.428 0.560
#> GSM647548 1 0.0921 0.8588 0.972 0.000 0.000 0.028
#> GSM647554 2 0.4079 0.9386 0.000 0.800 0.180 0.020
#> GSM647555 3 0.5837 0.0518 0.000 0.036 0.564 0.400
#> GSM647559 4 0.6572 0.4209 0.000 0.272 0.120 0.608
#> GSM647562 1 0.4916 0.5426 0.576 0.000 0.000 0.424
#> GSM647564 3 0.0188 0.8805 0.004 0.000 0.996 0.000
#> GSM647571 3 0.2123 0.8398 0.004 0.028 0.936 0.032
#> GSM647584 2 0.3969 0.9382 0.000 0.804 0.180 0.016
#> GSM647585 3 0.6635 0.4804 0.228 0.152 0.620 0.000
#> GSM647586 4 0.5003 0.4997 0.000 0.308 0.016 0.676
#> GSM647587 4 0.1211 0.6890 0.000 0.040 0.000 0.960
#> GSM647588 4 0.7333 0.1604 0.000 0.332 0.172 0.496
#> GSM647596 4 0.0469 0.6875 0.000 0.012 0.000 0.988
#> GSM647602 3 0.0000 0.8815 0.000 0.000 1.000 0.000
#> GSM647609 2 0.4655 0.8521 0.000 0.796 0.116 0.088
#> GSM647620 2 0.4553 0.9266 0.000 0.780 0.180 0.040
#> GSM647627 4 0.5993 0.4440 0.000 0.308 0.064 0.628
#> GSM647628 4 0.5263 0.5588 0.032 0.004 0.260 0.704
#> GSM647533 1 0.3444 0.8237 0.816 0.184 0.000 0.000
#> GSM647536 1 0.2868 0.8311 0.864 0.000 0.000 0.136
#> GSM647537 1 0.3123 0.8303 0.844 0.156 0.000 0.000
#> GSM647606 1 0.3539 0.8259 0.820 0.176 0.000 0.004
#> GSM647621 1 0.0921 0.8588 0.972 0.000 0.000 0.028
#> GSM647626 3 0.0592 0.8722 0.016 0.000 0.984 0.000
#> GSM647538 1 0.3486 0.8223 0.812 0.188 0.000 0.000
#> GSM647575 1 0.1022 0.8584 0.968 0.000 0.000 0.032
#> GSM647590 1 0.3448 0.8278 0.828 0.168 0.000 0.004
#> GSM647605 1 0.1724 0.8606 0.948 0.020 0.000 0.032
#> GSM647607 1 0.1833 0.8601 0.944 0.024 0.000 0.032
#> GSM647608 1 0.0921 0.8588 0.972 0.000 0.000 0.028
#> GSM647622 1 0.3444 0.8237 0.816 0.184 0.000 0.000
#> GSM647623 1 0.5395 0.7584 0.736 0.172 0.092 0.000
#> GSM647624 1 0.1833 0.8601 0.944 0.024 0.000 0.032
#> GSM647625 1 0.5229 0.7718 0.748 0.168 0.084 0.000
#> GSM647534 3 0.6310 0.1963 0.060 0.428 0.512 0.000
#> GSM647539 1 0.0921 0.8588 0.972 0.000 0.000 0.028
#> GSM647566 1 0.3486 0.8223 0.812 0.188 0.000 0.000
#> GSM647589 1 0.1356 0.8581 0.960 0.000 0.008 0.032
#> GSM647604 1 0.3626 0.8234 0.812 0.184 0.000 0.004
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.1270 0.7807 0.000 0.000 0.948 0.000 0.052
#> GSM647574 4 0.6648 0.4232 0.052 0.088 0.056 0.668 0.136
#> GSM647577 3 0.0703 0.7832 0.000 0.000 0.976 0.000 0.024
#> GSM647547 4 0.3311 0.7196 0.048 0.064 0.004 0.868 0.016
#> GSM647552 5 0.6141 0.1882 0.248 0.000 0.172 0.004 0.576
#> GSM647553 4 0.8645 0.0708 0.124 0.088 0.160 0.488 0.140
#> GSM647565 4 0.1285 0.7600 0.036 0.004 0.004 0.956 0.000
#> GSM647545 2 0.0867 0.6225 0.008 0.976 0.000 0.008 0.008
#> GSM647549 2 0.4028 0.4616 0.040 0.768 0.000 0.192 0.000
#> GSM647550 5 0.5929 0.1893 0.004 0.308 0.116 0.000 0.572
#> GSM647560 3 0.4122 0.5807 0.004 0.004 0.688 0.000 0.304
#> GSM647617 3 0.0703 0.7832 0.000 0.000 0.976 0.000 0.024
#> GSM647528 2 0.2074 0.6156 0.000 0.896 0.000 0.000 0.104
#> GSM647529 4 0.3689 0.7222 0.092 0.076 0.000 0.828 0.004
#> GSM647531 4 0.5691 0.6193 0.128 0.236 0.000 0.632 0.004
#> GSM647540 3 0.1608 0.7738 0.000 0.000 0.928 0.000 0.072
#> GSM647541 5 0.2393 0.7393 0.004 0.016 0.080 0.000 0.900
#> GSM647546 3 0.3449 0.7175 0.004 0.008 0.832 0.016 0.140
#> GSM647557 4 0.5068 0.5219 0.040 0.388 0.000 0.572 0.000
#> GSM647561 2 0.3691 0.5199 0.040 0.804 0.000 0.156 0.000
#> GSM647567 4 0.5184 0.3670 0.348 0.020 0.004 0.612 0.016
#> GSM647568 2 0.7892 0.2612 0.040 0.448 0.324 0.044 0.144
#> GSM647570 2 0.0404 0.6261 0.000 0.988 0.000 0.000 0.012
#> GSM647573 4 0.0324 0.7570 0.000 0.004 0.004 0.992 0.000
#> GSM647576 3 0.4438 0.5085 0.004 0.004 0.648 0.004 0.340
#> GSM647579 3 0.1270 0.7807 0.000 0.000 0.948 0.000 0.052
#> GSM647580 3 0.0703 0.7832 0.000 0.000 0.976 0.000 0.024
#> GSM647583 3 0.0703 0.7832 0.000 0.000 0.976 0.000 0.024
#> GSM647592 5 0.2293 0.6833 0.016 0.000 0.084 0.000 0.900
#> GSM647593 5 0.2966 0.6943 0.136 0.016 0.000 0.000 0.848
#> GSM647595 5 0.2966 0.6943 0.136 0.016 0.000 0.000 0.848
#> GSM647597 4 0.6308 0.4544 0.352 0.144 0.000 0.500 0.004
#> GSM647598 2 0.4398 0.5031 0.040 0.720 0.000 0.000 0.240
#> GSM647613 2 0.3731 0.5141 0.040 0.800 0.000 0.160 0.000
#> GSM647615 5 0.3618 0.6342 0.004 0.012 0.196 0.000 0.788
#> GSM647616 3 0.0290 0.7688 0.000 0.000 0.992 0.008 0.000
#> GSM647619 5 0.2753 0.6984 0.136 0.008 0.000 0.000 0.856
#> GSM647582 5 0.2170 0.6783 0.004 0.004 0.088 0.000 0.904
#> GSM647591 5 0.3554 0.7017 0.136 0.016 0.020 0.000 0.828
#> GSM647527 2 0.2074 0.6156 0.000 0.896 0.000 0.000 0.104
#> GSM647530 4 0.4690 0.6804 0.092 0.160 0.000 0.744 0.004
#> GSM647532 4 0.1731 0.7576 0.000 0.060 0.004 0.932 0.004
#> GSM647544 2 0.2170 0.6091 0.004 0.904 0.088 0.004 0.000
#> GSM647551 5 0.1116 0.7015 0.028 0.004 0.004 0.000 0.964
#> GSM647556 3 0.3317 0.7126 0.004 0.004 0.804 0.000 0.188
#> GSM647558 2 0.0703 0.6273 0.000 0.976 0.000 0.000 0.024
#> GSM647572 2 0.7569 0.2621 0.052 0.452 0.332 0.012 0.152
#> GSM647578 3 0.3715 0.6702 0.004 0.000 0.736 0.000 0.260
#> GSM647581 4 0.5731 0.6180 0.132 0.236 0.000 0.628 0.004
#> GSM647594 4 0.5033 0.6820 0.124 0.156 0.000 0.716 0.004
#> GSM647599 3 0.7674 0.0950 0.256 0.000 0.468 0.092 0.184
#> GSM647600 3 0.1608 0.7718 0.000 0.000 0.928 0.000 0.072
#> GSM647601 5 0.7438 0.1528 0.136 0.328 0.080 0.000 0.456
#> GSM647603 3 0.1270 0.7807 0.000 0.000 0.948 0.000 0.052
#> GSM647610 5 0.2295 0.7386 0.004 0.008 0.088 0.000 0.900
#> GSM647611 5 0.4612 0.7041 0.136 0.016 0.080 0.000 0.768
#> GSM647612 2 0.7182 0.2834 0.024 0.416 0.224 0.000 0.336
#> GSM647614 2 0.7541 0.2659 0.052 0.456 0.332 0.012 0.148
#> GSM647618 2 0.7453 0.1548 0.136 0.448 0.080 0.000 0.336
#> GSM647629 5 0.2984 0.7209 0.004 0.016 0.124 0.000 0.856
#> GSM647535 3 0.7031 0.3669 0.012 0.188 0.488 0.012 0.300
#> GSM647563 2 0.2984 0.6155 0.000 0.860 0.032 0.000 0.108
#> GSM647542 2 0.7541 0.2659 0.052 0.456 0.332 0.012 0.148
#> GSM647543 2 0.7541 0.2659 0.052 0.456 0.332 0.012 0.148
#> GSM647548 4 0.1285 0.7600 0.036 0.004 0.004 0.956 0.000
#> GSM647554 5 0.2177 0.7409 0.004 0.008 0.080 0.000 0.908
#> GSM647555 3 0.6930 0.1164 0.024 0.328 0.472 0.000 0.176
#> GSM647559 2 0.7057 0.2878 0.136 0.512 0.056 0.000 0.296
#> GSM647562 2 0.6229 -0.1006 0.132 0.504 0.000 0.360 0.004
#> GSM647564 3 0.2890 0.7254 0.004 0.000 0.836 0.000 0.160
#> GSM647571 3 0.6727 0.3087 0.024 0.260 0.536 0.000 0.180
#> GSM647584 5 0.4181 0.7059 0.136 0.016 0.052 0.000 0.796
#> GSM647585 3 0.7239 -0.1602 0.364 0.000 0.452 0.084 0.100
#> GSM647586 2 0.7187 0.2812 0.136 0.508 0.068 0.000 0.288
#> GSM647587 2 0.1121 0.6271 0.000 0.956 0.000 0.000 0.044
#> GSM647588 2 0.7487 0.0844 0.136 0.424 0.080 0.000 0.360
#> GSM647596 2 0.0162 0.6201 0.004 0.996 0.000 0.000 0.000
#> GSM647602 3 0.0880 0.7826 0.000 0.000 0.968 0.000 0.032
#> GSM647609 5 0.5380 0.6798 0.136 0.056 0.080 0.000 0.728
#> GSM647620 5 0.2393 0.7393 0.004 0.016 0.080 0.000 0.900
#> GSM647627 2 0.7262 0.2339 0.136 0.484 0.068 0.000 0.312
#> GSM647628 2 0.7501 0.3813 0.020 0.488 0.296 0.156 0.040
#> GSM647533 1 0.5757 0.8788 0.640 0.000 0.008 0.216 0.136
#> GSM647536 4 0.3574 0.7254 0.088 0.072 0.000 0.836 0.004
#> GSM647537 1 0.5810 0.8724 0.632 0.000 0.008 0.224 0.136
#> GSM647606 4 0.4015 0.3773 0.348 0.000 0.000 0.652 0.000
#> GSM647621 4 0.1862 0.7492 0.048 0.000 0.004 0.932 0.016
#> GSM647626 3 0.0992 0.7814 0.000 0.000 0.968 0.008 0.024
#> GSM647538 1 0.5079 0.9011 0.700 0.000 0.000 0.164 0.136
#> GSM647575 4 0.0162 0.7562 0.000 0.000 0.004 0.996 0.000
#> GSM647590 4 0.3274 0.6031 0.220 0.000 0.000 0.780 0.000
#> GSM647605 4 0.1357 0.7489 0.048 0.000 0.004 0.948 0.000
#> GSM647607 4 0.0162 0.7563 0.004 0.000 0.000 0.996 0.000
#> GSM647608 4 0.1525 0.7531 0.036 0.000 0.004 0.948 0.012
#> GSM647622 1 0.5184 0.8988 0.688 0.000 0.000 0.176 0.136
#> GSM647623 1 0.6220 0.8416 0.616 0.000 0.028 0.132 0.224
#> GSM647624 4 0.1121 0.7497 0.044 0.000 0.000 0.956 0.000
#> GSM647625 1 0.6669 0.7485 0.596 0.000 0.108 0.072 0.224
#> GSM647534 5 0.7090 -0.2137 0.324 0.000 0.224 0.020 0.432
#> GSM647539 4 0.1041 0.7589 0.032 0.000 0.004 0.964 0.000
#> GSM647566 1 0.5079 0.9011 0.700 0.000 0.000 0.164 0.136
#> GSM647589 4 0.2204 0.7496 0.048 0.000 0.016 0.920 0.016
#> GSM647604 4 0.4227 0.2170 0.420 0.000 0.000 0.580 0.000
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.3717 -0.20878 0.000 0.000 0.616 0.000 0.000 0.384
#> GSM647574 1 0.7283 0.48360 0.440 0.020 0.128 0.108 0.000 0.304
#> GSM647577 3 0.3737 -0.21483 0.000 0.000 0.608 0.000 0.000 0.392
#> GSM647547 1 0.5736 0.42542 0.440 0.004 0.000 0.144 0.000 0.412
#> GSM647552 3 0.5475 -0.15194 0.056 0.000 0.516 0.004 0.400 0.024
#> GSM647553 1 0.8143 0.03170 0.360 0.064 0.360 0.104 0.032 0.080
#> GSM647565 4 0.4232 0.68320 0.116 0.000 0.000 0.736 0.000 0.148
#> GSM647545 2 0.0260 0.74980 0.000 0.992 0.000 0.000 0.000 0.008
#> GSM647549 2 0.4619 0.31409 0.000 0.600 0.000 0.348 0.000 0.052
#> GSM647550 3 0.6016 -0.29968 0.000 0.244 0.404 0.000 0.352 0.000
#> GSM647560 3 0.1176 0.25551 0.000 0.000 0.956 0.000 0.024 0.020
#> GSM647617 3 0.3737 -0.21483 0.000 0.000 0.608 0.000 0.000 0.392
#> GSM647528 2 0.1075 0.73450 0.000 0.952 0.000 0.000 0.048 0.000
#> GSM647529 4 0.0632 0.70344 0.000 0.024 0.000 0.976 0.000 0.000
#> GSM647531 4 0.2542 0.67077 0.000 0.080 0.000 0.876 0.000 0.044
#> GSM647540 3 0.4206 -0.20645 0.000 0.000 0.620 0.000 0.024 0.356
#> GSM647541 5 0.4482 0.41695 0.000 0.036 0.384 0.000 0.580 0.000
#> GSM647546 3 0.0622 0.26284 0.000 0.000 0.980 0.000 0.008 0.012
#> GSM647557 4 0.6372 0.23801 0.000 0.332 0.000 0.464 0.168 0.036
#> GSM647561 2 0.4606 0.32458 0.000 0.604 0.000 0.344 0.000 0.052
#> GSM647567 1 0.4031 0.52706 0.772 0.008 0.000 0.124 0.000 0.096
#> GSM647568 1 0.8367 0.19234 0.328 0.108 0.252 0.008 0.056 0.248
#> GSM647570 2 0.0260 0.75118 0.000 0.992 0.000 0.000 0.008 0.000
#> GSM647573 4 0.3740 0.69224 0.096 0.000 0.000 0.784 0.000 0.120
#> GSM647576 3 0.2673 0.25792 0.000 0.004 0.852 0.000 0.132 0.012
#> GSM647579 3 0.3684 -0.19960 0.000 0.000 0.628 0.000 0.000 0.372
#> GSM647580 3 0.3737 -0.21483 0.000 0.000 0.608 0.000 0.000 0.392
#> GSM647583 3 0.3737 -0.21483 0.000 0.000 0.608 0.000 0.000 0.392
#> GSM647592 5 0.2009 0.58446 0.000 0.008 0.084 0.000 0.904 0.004
#> GSM647593 5 0.1897 0.60659 0.000 0.084 0.004 0.000 0.908 0.004
#> GSM647595 5 0.1949 0.60440 0.000 0.088 0.004 0.000 0.904 0.004
#> GSM647597 4 0.5259 0.48657 0.212 0.036 0.000 0.676 0.064 0.012
#> GSM647598 2 0.2378 0.60362 0.000 0.848 0.000 0.000 0.152 0.000
#> GSM647613 2 0.4619 0.31768 0.000 0.600 0.000 0.348 0.000 0.052
#> GSM647615 5 0.4229 0.33838 0.000 0.016 0.436 0.000 0.548 0.000
#> GSM647616 3 0.3747 -0.22295 0.000 0.000 0.604 0.000 0.000 0.396
#> GSM647619 5 0.1843 0.60793 0.000 0.080 0.004 0.000 0.912 0.004
#> GSM647582 5 0.4063 0.34293 0.000 0.004 0.420 0.000 0.572 0.004
#> GSM647591 5 0.1806 0.60525 0.000 0.088 0.004 0.000 0.908 0.000
#> GSM647527 2 0.1075 0.73450 0.000 0.952 0.000 0.000 0.048 0.000
#> GSM647530 4 0.1010 0.70145 0.000 0.036 0.000 0.960 0.000 0.004
#> GSM647532 4 0.2186 0.71136 0.056 0.024 0.000 0.908 0.000 0.012
#> GSM647544 2 0.1480 0.73437 0.000 0.940 0.040 0.000 0.000 0.020
#> GSM647551 5 0.3516 0.53572 0.000 0.016 0.220 0.000 0.760 0.004
#> GSM647556 3 0.2207 0.30153 0.000 0.016 0.900 0.000 0.076 0.008
#> GSM647558 2 0.0260 0.75118 0.000 0.992 0.000 0.000 0.008 0.000
#> GSM647572 3 0.5034 0.27764 0.004 0.120 0.724 0.000 0.076 0.076
#> GSM647578 3 0.1956 0.30019 0.000 0.008 0.908 0.000 0.080 0.004
#> GSM647581 4 0.4212 0.44427 0.000 0.264 0.000 0.688 0.000 0.048
#> GSM647594 4 0.1492 0.69717 0.000 0.036 0.000 0.940 0.000 0.024
#> GSM647599 3 0.5670 -0.02997 0.204 0.000 0.640 0.004 0.052 0.100
#> GSM647600 3 0.3684 -0.19960 0.000 0.000 0.628 0.000 0.000 0.372
#> GSM647601 5 0.3969 0.41100 0.000 0.312 0.020 0.000 0.668 0.000
#> GSM647603 3 0.3684 -0.19960 0.000 0.000 0.628 0.000 0.000 0.372
#> GSM647610 5 0.4209 0.41632 0.000 0.020 0.384 0.000 0.596 0.000
#> GSM647611 5 0.1334 0.61435 0.000 0.020 0.032 0.000 0.948 0.000
#> GSM647612 3 0.6422 -0.11128 0.000 0.380 0.436 0.000 0.132 0.052
#> GSM647614 2 0.8024 0.00594 0.328 0.332 0.188 0.000 0.076 0.076
#> GSM647618 5 0.3927 0.36866 0.000 0.344 0.012 0.000 0.644 0.000
#> GSM647629 5 0.4318 0.32539 0.000 0.020 0.448 0.000 0.532 0.000
#> GSM647535 3 0.3475 0.30370 0.000 0.020 0.812 0.000 0.140 0.028
#> GSM647563 2 0.1500 0.72904 0.000 0.936 0.012 0.000 0.052 0.000
#> GSM647542 3 0.6256 0.13945 0.004 0.328 0.516 0.000 0.076 0.076
#> GSM647543 3 0.6301 0.09358 0.004 0.348 0.496 0.000 0.076 0.076
#> GSM647548 4 0.5353 0.47037 0.116 0.000 0.000 0.516 0.000 0.368
#> GSM647554 5 0.4199 0.42113 0.000 0.020 0.380 0.000 0.600 0.000
#> GSM647555 3 0.5016 0.29424 0.004 0.100 0.728 0.000 0.092 0.076
#> GSM647559 5 0.4175 0.11069 0.000 0.464 0.012 0.000 0.524 0.000
#> GSM647562 4 0.4876 0.15503 0.000 0.368 0.000 0.564 0.000 0.068
#> GSM647564 3 0.0458 0.25628 0.000 0.000 0.984 0.000 0.000 0.016
#> GSM647571 3 0.3167 0.30269 0.000 0.000 0.832 0.000 0.096 0.072
#> GSM647584 5 0.2060 0.60921 0.000 0.084 0.016 0.000 0.900 0.000
#> GSM647585 6 0.6646 0.00000 0.200 0.000 0.308 0.000 0.048 0.444
#> GSM647586 5 0.4169 0.13676 0.000 0.456 0.012 0.000 0.532 0.000
#> GSM647587 2 0.0260 0.75118 0.000 0.992 0.000 0.000 0.008 0.000
#> GSM647588 5 0.4219 0.28361 0.000 0.388 0.020 0.000 0.592 0.000
#> GSM647596 2 0.0458 0.74761 0.000 0.984 0.000 0.000 0.000 0.016
#> GSM647602 3 0.3737 -0.21483 0.000 0.000 0.608 0.000 0.000 0.392
#> GSM647609 5 0.2432 0.60294 0.000 0.100 0.024 0.000 0.876 0.000
#> GSM647620 5 0.5438 0.37923 0.000 0.124 0.380 0.000 0.496 0.000
#> GSM647627 5 0.4169 0.13676 0.000 0.456 0.012 0.000 0.532 0.000
#> GSM647628 2 0.7553 0.08529 0.340 0.400 0.148 0.052 0.004 0.056
#> GSM647533 1 0.1313 0.54828 0.952 0.000 0.028 0.016 0.000 0.004
#> GSM647536 4 0.0777 0.70325 0.000 0.024 0.000 0.972 0.000 0.004
#> GSM647537 1 0.1577 0.54817 0.940 0.000 0.036 0.016 0.000 0.008
#> GSM647606 1 0.3503 0.51034 0.788 0.000 0.000 0.180 0.012 0.020
#> GSM647621 1 0.5774 0.41442 0.440 0.000 0.000 0.176 0.000 0.384
#> GSM647626 3 0.3747 -0.22320 0.000 0.000 0.604 0.000 0.000 0.396
#> GSM647538 1 0.2349 0.48797 0.892 0.000 0.020 0.008 0.000 0.080
#> GSM647575 4 0.5219 0.51590 0.116 0.000 0.000 0.568 0.000 0.316
#> GSM647590 4 0.4378 0.58897 0.280 0.000 0.000 0.676 0.012 0.032
#> GSM647605 4 0.4085 0.67989 0.128 0.000 0.000 0.752 0.000 0.120
#> GSM647607 4 0.4180 0.68351 0.116 0.000 0.000 0.764 0.012 0.108
#> GSM647608 1 0.5948 0.37742 0.440 0.000 0.000 0.232 0.000 0.328
#> GSM647622 1 0.1167 0.53749 0.960 0.000 0.020 0.008 0.000 0.012
#> GSM647623 1 0.6532 -0.03542 0.452 0.000 0.372 0.004 0.080 0.092
#> GSM647624 4 0.4180 0.68351 0.116 0.000 0.000 0.764 0.012 0.108
#> GSM647625 3 0.6435 -0.04764 0.388 0.000 0.448 0.004 0.084 0.076
#> GSM647534 3 0.5677 0.09054 0.256 0.000 0.576 0.004 0.156 0.008
#> GSM647539 4 0.3977 0.69007 0.096 0.000 0.000 0.760 0.000 0.144
#> GSM647566 1 0.2349 0.48797 0.892 0.000 0.020 0.008 0.000 0.080
#> GSM647589 1 0.5718 0.41927 0.440 0.000 0.000 0.164 0.000 0.396
#> GSM647604 1 0.4165 -0.26346 0.536 0.000 0.000 0.452 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)
#> Error in mat[ceiling(1:nr/h_ratio), ceiling(1:nc/w_ratio), drop = FALSE]: subscript out of bounds
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) development.stage(p) other(p) k
#> ATC:mclust 101 2.13e-06 0.3473 0.3170 2
#> ATC:mclust 103 2.65e-09 0.0837 0.0967 3
#> ATC:mclust 85 3.02e-07 0.6551 0.1009 4
#> ATC:mclust 74 3.56e-08 0.5827 0.1779 5
#> ATC:mclust 38 6.76e-04 0.4448 0.2872 6
If matrix rows can be associated to genes, consider to use functional_enrichment(res,
...) to perform function enrichment for the signature genes. See this vignette for more detailed explanations.
The object with results only for a single top-value method and a single partition method can be extracted as:
res = res_list["ATC", "NMF"]
# you can also extract it by
# res = res_list["ATC:NMF"]
A summary of res and all the functions that can be applied to it:
res
#> A 'ConsensusPartition' object with k = 2, 3, 4, 5, 6.
#> On a matrix with 51941 rows and 103 columns.
#> Top rows (1000, 2000, 3000, 4000, 5000) are extracted by 'ATC' method.
#> Subgroups are detected by 'NMF' method.
#> Performed in total 1250 partitions by row resampling.
#> Best k for subgroups seems to be 2.
#>
#> Following methods can be applied to this 'ConsensusPartition' object:
#> [1] "cola_report" "collect_classes" "collect_plots"
#> [4] "collect_stats" "colnames" "compare_signatures"
#> [7] "consensus_heatmap" "dimension_reduction" "functional_enrichment"
#> [10] "get_anno_col" "get_anno" "get_classes"
#> [13] "get_consensus" "get_matrix" "get_membership"
#> [16] "get_param" "get_signatures" "get_stats"
#> [19] "is_best_k" "is_stable_k" "membership_heatmap"
#> [22] "ncol" "nrow" "plot_ecdf"
#> [25] "rownames" "select_partition_number" "show"
#> [28] "suggest_best_k" "test_to_known_factors"
collect_plots() function collects all the plots made from res for all k (number of partitions)
into one single page to provide an easy and fast comparison between different k.
collect_plots(res)
The plots are:
k and the heatmap of
predicted classes for each k.k.k.k.All the plots in panels can be made by individual functions and they are plotted later in this section.
select_partition_number() produces several plots showing different
statistics for choosing “optimized” k. There are following statistics:
k;k, the area increased is defined as \(A_k - A_{k-1}\).The detailed explanations of these statistics can be found in the cola vignette.
Generally speaking, lower PAC score, higher mean silhouette score or higher
concordance corresponds to better partition. Rand index and Jaccard index
measure how similar the current partition is compared to partition with k-1.
If they are too similar, we won't accept k is better than k-1.
select_partition_number(res)
The numeric values for all these statistics can be obtained by get_stats().
get_stats(res)
#> k 1-PAC mean_silhouette concordance area_increased Rand Jaccard
#> 2 2 0.863 0.895 0.959 0.4380 0.560 0.560
#> 3 3 0.867 0.863 0.941 0.4229 0.728 0.548
#> 4 4 0.734 0.712 0.855 0.1265 0.882 0.700
#> 5 5 0.633 0.601 0.787 0.0818 0.884 0.650
#> 6 6 0.569 0.501 0.688 0.0455 0.913 0.690
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
#> GSM647569 2 0.0000 0.9633 0.000 1.000
#> GSM647574 2 0.0000 0.9633 0.000 1.000
#> GSM647577 2 0.0000 0.9633 0.000 1.000
#> GSM647547 2 0.9996 -0.0362 0.488 0.512
#> GSM647552 2 0.0000 0.9633 0.000 1.000
#> GSM647553 2 0.0000 0.9633 0.000 1.000
#> GSM647565 1 0.0000 0.9351 1.000 0.000
#> GSM647545 1 0.6438 0.8142 0.836 0.164
#> GSM647549 1 0.0000 0.9351 1.000 0.000
#> GSM647550 2 0.0000 0.9633 0.000 1.000
#> GSM647560 2 0.0000 0.9633 0.000 1.000
#> GSM647617 2 0.0000 0.9633 0.000 1.000
#> GSM647528 2 0.9286 0.4329 0.344 0.656
#> GSM647529 1 0.0000 0.9351 1.000 0.000
#> GSM647531 1 0.0000 0.9351 1.000 0.000
#> GSM647540 2 0.0000 0.9633 0.000 1.000
#> GSM647541 2 0.0000 0.9633 0.000 1.000
#> GSM647546 2 0.0000 0.9633 0.000 1.000
#> GSM647557 1 0.0000 0.9351 1.000 0.000
#> GSM647561 1 0.0000 0.9351 1.000 0.000
#> GSM647567 2 0.9963 0.0609 0.464 0.536
#> GSM647568 2 0.0000 0.9633 0.000 1.000
#> GSM647570 1 0.7376 0.7637 0.792 0.208
#> GSM647573 1 0.0000 0.9351 1.000 0.000
#> GSM647576 2 0.0000 0.9633 0.000 1.000
#> GSM647579 2 0.0000 0.9633 0.000 1.000
#> GSM647580 2 0.0000 0.9633 0.000 1.000
#> GSM647583 2 0.0000 0.9633 0.000 1.000
#> GSM647592 2 0.0000 0.9633 0.000 1.000
#> GSM647593 2 0.0000 0.9633 0.000 1.000
#> GSM647595 2 0.0000 0.9633 0.000 1.000
#> GSM647597 1 0.0000 0.9351 1.000 0.000
#> GSM647598 2 0.6623 0.7595 0.172 0.828
#> GSM647613 1 0.0000 0.9351 1.000 0.000
#> GSM647615 2 0.0000 0.9633 0.000 1.000
#> GSM647616 2 0.0000 0.9633 0.000 1.000
#> GSM647619 2 0.0000 0.9633 0.000 1.000
#> GSM647582 2 0.0000 0.9633 0.000 1.000
#> GSM647591 2 0.0000 0.9633 0.000 1.000
#> GSM647527 1 0.9970 0.1657 0.532 0.468
#> GSM647530 1 0.0000 0.9351 1.000 0.000
#> GSM647532 1 0.0000 0.9351 1.000 0.000
#> GSM647544 1 0.7139 0.7792 0.804 0.196
#> GSM647551 2 0.0000 0.9633 0.000 1.000
#> GSM647556 2 0.0000 0.9633 0.000 1.000
#> GSM647558 2 0.9993 -0.0199 0.484 0.516
#> GSM647572 2 0.0000 0.9633 0.000 1.000
#> GSM647578 2 0.0000 0.9633 0.000 1.000
#> GSM647581 1 0.0000 0.9351 1.000 0.000
#> GSM647594 1 0.0000 0.9351 1.000 0.000
#> GSM647599 2 0.0000 0.9633 0.000 1.000
#> GSM647600 2 0.0000 0.9633 0.000 1.000
#> GSM647601 2 0.0000 0.9633 0.000 1.000
#> GSM647603 2 0.0000 0.9633 0.000 1.000
#> GSM647610 2 0.0000 0.9633 0.000 1.000
#> GSM647611 2 0.0000 0.9633 0.000 1.000
#> GSM647612 2 0.0000 0.9633 0.000 1.000
#> GSM647614 2 0.0000 0.9633 0.000 1.000
#> GSM647618 2 0.0000 0.9633 0.000 1.000
#> GSM647629 2 0.0000 0.9633 0.000 1.000
#> GSM647535 2 0.0000 0.9633 0.000 1.000
#> GSM647563 2 0.0376 0.9596 0.004 0.996
#> GSM647542 2 0.0000 0.9633 0.000 1.000
#> GSM647543 2 0.0000 0.9633 0.000 1.000
#> GSM647548 1 0.0000 0.9351 1.000 0.000
#> GSM647554 2 0.0000 0.9633 0.000 1.000
#> GSM647555 2 0.0000 0.9633 0.000 1.000
#> GSM647559 2 0.0000 0.9633 0.000 1.000
#> GSM647562 1 0.0000 0.9351 1.000 0.000
#> GSM647564 2 0.0000 0.9633 0.000 1.000
#> GSM647571 2 0.0000 0.9633 0.000 1.000
#> GSM647584 2 0.0000 0.9633 0.000 1.000
#> GSM647585 2 0.0000 0.9633 0.000 1.000
#> GSM647586 2 0.0000 0.9633 0.000 1.000
#> GSM647587 1 0.2948 0.9070 0.948 0.052
#> GSM647588 2 0.0000 0.9633 0.000 1.000
#> GSM647596 1 0.7056 0.7840 0.808 0.192
#> GSM647602 2 0.0000 0.9633 0.000 1.000
#> GSM647609 2 0.0000 0.9633 0.000 1.000
#> GSM647620 2 0.0000 0.9633 0.000 1.000
#> GSM647627 2 0.0000 0.9633 0.000 1.000
#> GSM647628 2 0.8861 0.5250 0.304 0.696
#> GSM647533 2 0.0000 0.9633 0.000 1.000
#> GSM647536 1 0.0000 0.9351 1.000 0.000
#> GSM647537 2 0.0000 0.9633 0.000 1.000
#> GSM647606 1 0.2948 0.9070 0.948 0.052
#> GSM647621 1 0.8443 0.6650 0.728 0.272
#> GSM647626 2 0.0000 0.9633 0.000 1.000
#> GSM647538 2 0.0000 0.9633 0.000 1.000
#> GSM647575 1 0.0000 0.9351 1.000 0.000
#> GSM647590 1 0.0000 0.9351 1.000 0.000
#> GSM647605 1 0.0000 0.9351 1.000 0.000
#> GSM647607 1 0.0000 0.9351 1.000 0.000
#> GSM647608 1 0.4562 0.8750 0.904 0.096
#> GSM647622 2 0.0000 0.9633 0.000 1.000
#> GSM647623 2 0.0000 0.9633 0.000 1.000
#> GSM647624 1 0.0000 0.9351 1.000 0.000
#> GSM647625 2 0.0000 0.9633 0.000 1.000
#> GSM647534 2 0.0000 0.9633 0.000 1.000
#> GSM647539 1 0.0000 0.9351 1.000 0.000
#> GSM647566 2 0.1843 0.9361 0.028 0.972
#> GSM647589 1 0.8016 0.7117 0.756 0.244
#> GSM647604 1 0.0000 0.9351 1.000 0.000
cbind(get_classes(res, k = 3), get_membership(res, k = 3))
#> class entropy silhouette p1 p2 p3
#> GSM647569 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647574 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647577 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647547 1 0.6295 0.169 0.528 0.000 0.472
#> GSM647552 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647553 3 0.0237 0.939 0.004 0.000 0.996
#> GSM647565 1 0.0000 0.899 1.000 0.000 0.000
#> GSM647545 2 0.0237 0.935 0.000 0.996 0.004
#> GSM647549 2 0.0000 0.932 0.000 1.000 0.000
#> GSM647550 3 0.0892 0.932 0.000 0.020 0.980
#> GSM647560 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647617 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647528 2 0.0892 0.940 0.000 0.980 0.020
#> GSM647529 1 0.1031 0.896 0.976 0.024 0.000
#> GSM647531 1 0.2448 0.859 0.924 0.076 0.000
#> GSM647540 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647541 3 0.1289 0.924 0.000 0.032 0.968
#> GSM647546 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647557 2 0.3038 0.835 0.104 0.896 0.000
#> GSM647561 2 0.0000 0.932 0.000 1.000 0.000
#> GSM647567 1 0.6260 0.245 0.552 0.000 0.448
#> GSM647568 3 0.0424 0.939 0.000 0.008 0.992
#> GSM647570 2 0.0237 0.935 0.000 0.996 0.004
#> GSM647573 1 0.0000 0.899 1.000 0.000 0.000
#> GSM647576 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647579 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647580 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647583 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647592 3 0.1163 0.927 0.000 0.028 0.972
#> GSM647593 2 0.6204 0.256 0.000 0.576 0.424
#> GSM647595 2 0.2066 0.911 0.000 0.940 0.060
#> GSM647597 1 0.0892 0.897 0.980 0.020 0.000
#> GSM647598 2 0.0892 0.940 0.000 0.980 0.020
#> GSM647613 2 0.0000 0.932 0.000 1.000 0.000
#> GSM647615 3 0.0747 0.934 0.000 0.016 0.984
#> GSM647616 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647619 3 0.2796 0.870 0.000 0.092 0.908
#> GSM647582 3 0.0237 0.940 0.000 0.004 0.996
#> GSM647591 2 0.1163 0.938 0.000 0.972 0.028
#> GSM647527 2 0.0747 0.939 0.000 0.984 0.016
#> GSM647530 1 0.1031 0.896 0.976 0.024 0.000
#> GSM647532 1 0.1031 0.896 0.976 0.024 0.000
#> GSM647544 2 0.0237 0.935 0.000 0.996 0.004
#> GSM647551 3 0.0747 0.934 0.000 0.016 0.984
#> GSM647556 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647558 2 0.0892 0.940 0.000 0.980 0.020
#> GSM647572 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647578 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647581 1 0.5591 0.560 0.696 0.304 0.000
#> GSM647594 1 0.1031 0.896 0.976 0.024 0.000
#> GSM647599 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647600 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647601 2 0.1031 0.940 0.000 0.976 0.024
#> GSM647603 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647610 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647611 3 0.6204 0.274 0.000 0.424 0.576
#> GSM647612 3 0.4291 0.766 0.000 0.180 0.820
#> GSM647614 3 0.5733 0.532 0.000 0.324 0.676
#> GSM647618 2 0.1163 0.938 0.000 0.972 0.028
#> GSM647629 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647535 3 0.0747 0.935 0.000 0.016 0.984
#> GSM647563 2 0.1031 0.940 0.000 0.976 0.024
#> GSM647542 3 0.6079 0.386 0.000 0.388 0.612
#> GSM647543 3 0.6079 0.385 0.000 0.388 0.612
#> GSM647548 1 0.1031 0.896 0.976 0.024 0.000
#> GSM647554 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647555 3 0.0892 0.932 0.000 0.020 0.980
#> GSM647559 2 0.1031 0.940 0.000 0.976 0.024
#> GSM647562 2 0.0000 0.932 0.000 1.000 0.000
#> GSM647564 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647571 3 0.0747 0.935 0.000 0.016 0.984
#> GSM647584 2 0.5988 0.416 0.000 0.632 0.368
#> GSM647585 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647586 2 0.1031 0.940 0.000 0.976 0.024
#> GSM647587 2 0.0000 0.932 0.000 1.000 0.000
#> GSM647588 2 0.1643 0.926 0.000 0.956 0.044
#> GSM647596 2 0.0237 0.935 0.000 0.996 0.004
#> GSM647602 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647609 2 0.2448 0.894 0.000 0.924 0.076
#> GSM647620 3 0.6045 0.398 0.000 0.380 0.620
#> GSM647627 2 0.1289 0.935 0.000 0.968 0.032
#> GSM647628 2 0.0892 0.940 0.000 0.980 0.020
#> GSM647533 3 0.2878 0.853 0.096 0.000 0.904
#> GSM647536 1 0.0892 0.897 0.980 0.020 0.000
#> GSM647537 3 0.0424 0.936 0.008 0.000 0.992
#> GSM647606 1 0.2537 0.847 0.920 0.000 0.080
#> GSM647621 1 0.5254 0.650 0.736 0.000 0.264
#> GSM647626 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647538 3 0.1860 0.899 0.052 0.000 0.948
#> GSM647575 1 0.0000 0.899 1.000 0.000 0.000
#> GSM647590 1 0.0000 0.899 1.000 0.000 0.000
#> GSM647605 1 0.0000 0.899 1.000 0.000 0.000
#> GSM647607 1 0.0000 0.899 1.000 0.000 0.000
#> GSM647608 1 0.0747 0.892 0.984 0.000 0.016
#> GSM647622 3 0.0424 0.936 0.008 0.000 0.992
#> GSM647623 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647624 1 0.0000 0.899 1.000 0.000 0.000
#> GSM647625 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647534 3 0.0000 0.942 0.000 0.000 1.000
#> GSM647539 1 0.0000 0.899 1.000 0.000 0.000
#> GSM647566 3 0.3752 0.793 0.144 0.000 0.856
#> GSM647589 1 0.4346 0.752 0.816 0.000 0.184
#> GSM647604 1 0.0000 0.899 1.000 0.000 0.000
cbind(get_classes(res, k = 4), get_membership(res, k = 4))
#> class entropy silhouette p1 p2 p3 p4
#> GSM647569 3 0.0000 0.9168 0.000 0.000 1.000 0.000
#> GSM647574 3 0.0000 0.9168 0.000 0.000 1.000 0.000
#> GSM647577 3 0.0000 0.9168 0.000 0.000 1.000 0.000
#> GSM647547 3 0.5389 0.4388 0.032 0.000 0.660 0.308
#> GSM647552 1 0.5766 0.3051 0.564 0.032 0.404 0.000
#> GSM647553 3 0.0000 0.9168 0.000 0.000 1.000 0.000
#> GSM647565 4 0.1792 0.7724 0.068 0.000 0.000 0.932
#> GSM647545 2 0.1211 0.8427 0.040 0.960 0.000 0.000
#> GSM647549 2 0.0376 0.8473 0.004 0.992 0.000 0.004
#> GSM647550 3 0.0937 0.9096 0.012 0.012 0.976 0.000
#> GSM647560 3 0.0657 0.9131 0.012 0.004 0.984 0.000
#> GSM647617 3 0.0000 0.9168 0.000 0.000 1.000 0.000
#> GSM647528 2 0.0188 0.8475 0.004 0.996 0.000 0.000
#> GSM647529 4 0.2530 0.7862 0.112 0.000 0.000 0.888
#> GSM647531 4 0.2048 0.7893 0.064 0.008 0.000 0.928
#> GSM647540 3 0.0000 0.9168 0.000 0.000 1.000 0.000
#> GSM647541 3 0.0895 0.9058 0.004 0.020 0.976 0.000
#> GSM647546 3 0.0592 0.9115 0.016 0.000 0.984 0.000
#> GSM647557 2 0.4920 0.5248 0.368 0.628 0.000 0.004
#> GSM647561 2 0.0672 0.8481 0.008 0.984 0.000 0.008
#> GSM647567 1 0.7456 0.1937 0.460 0.000 0.180 0.360
#> GSM647568 3 0.1706 0.8853 0.016 0.000 0.948 0.036
#> GSM647570 2 0.1635 0.8359 0.044 0.948 0.000 0.008
#> GSM647573 4 0.1022 0.7862 0.032 0.000 0.000 0.968
#> GSM647576 3 0.0592 0.9115 0.016 0.000 0.984 0.000
#> GSM647579 3 0.0188 0.9160 0.004 0.000 0.996 0.000
#> GSM647580 3 0.0000 0.9168 0.000 0.000 1.000 0.000
#> GSM647583 3 0.0000 0.9168 0.000 0.000 1.000 0.000
#> GSM647592 1 0.7042 0.4615 0.572 0.188 0.240 0.000
#> GSM647593 2 0.5498 0.4147 0.404 0.576 0.020 0.000
#> GSM647595 2 0.5080 0.4170 0.420 0.576 0.004 0.000
#> GSM647597 1 0.5028 0.1280 0.596 0.004 0.000 0.400
#> GSM647598 2 0.1716 0.8348 0.064 0.936 0.000 0.000
#> GSM647613 2 0.2363 0.8217 0.056 0.920 0.000 0.024
#> GSM647615 3 0.1610 0.8855 0.032 0.016 0.952 0.000
#> GSM647616 3 0.0000 0.9168 0.000 0.000 1.000 0.000
#> GSM647619 1 0.7023 0.3471 0.564 0.272 0.164 0.000
#> GSM647582 3 0.6355 0.2156 0.348 0.076 0.576 0.000
#> GSM647591 2 0.4643 0.5585 0.344 0.656 0.000 0.000
#> GSM647527 2 0.0336 0.8470 0.008 0.992 0.000 0.000
#> GSM647530 4 0.1557 0.7864 0.056 0.000 0.000 0.944
#> GSM647532 4 0.2760 0.7798 0.128 0.000 0.000 0.872
#> GSM647544 2 0.3239 0.7969 0.068 0.880 0.000 0.052
#> GSM647551 1 0.6098 0.5394 0.676 0.124 0.200 0.000
#> GSM647556 3 0.0000 0.9168 0.000 0.000 1.000 0.000
#> GSM647558 2 0.1545 0.8372 0.040 0.952 0.000 0.008
#> GSM647572 3 0.0000 0.9168 0.000 0.000 1.000 0.000
#> GSM647578 3 0.0000 0.9168 0.000 0.000 1.000 0.000
#> GSM647581 4 0.6133 0.4131 0.088 0.268 0.000 0.644
#> GSM647594 4 0.2647 0.7831 0.120 0.000 0.000 0.880
#> GSM647599 3 0.1022 0.9023 0.032 0.000 0.968 0.000
#> GSM647600 3 0.0188 0.9160 0.004 0.000 0.996 0.000
#> GSM647601 2 0.2216 0.8214 0.092 0.908 0.000 0.000
#> GSM647603 3 0.0188 0.9160 0.004 0.000 0.996 0.000
#> GSM647610 3 0.0336 0.9142 0.008 0.000 0.992 0.000
#> GSM647611 2 0.6574 0.1545 0.084 0.532 0.384 0.000
#> GSM647612 3 0.0336 0.9140 0.000 0.008 0.992 0.000
#> GSM647614 3 0.2558 0.8601 0.008 0.036 0.920 0.036
#> GSM647618 2 0.2589 0.8066 0.116 0.884 0.000 0.000
#> GSM647629 3 0.0188 0.9157 0.000 0.004 0.996 0.000
#> GSM647535 3 0.0336 0.9141 0.000 0.008 0.992 0.000
#> GSM647563 2 0.1854 0.8337 0.048 0.940 0.000 0.012
#> GSM647542 3 0.0707 0.9044 0.000 0.000 0.980 0.020
#> GSM647543 3 0.0657 0.9108 0.000 0.012 0.984 0.004
#> GSM647548 4 0.1824 0.7513 0.060 0.004 0.000 0.936
#> GSM647554 3 0.4595 0.6600 0.176 0.044 0.780 0.000
#> GSM647555 3 0.0000 0.9168 0.000 0.000 1.000 0.000
#> GSM647559 2 0.0336 0.8482 0.008 0.992 0.000 0.000
#> GSM647562 2 0.1854 0.8343 0.048 0.940 0.000 0.012
#> GSM647564 3 0.0000 0.9168 0.000 0.000 1.000 0.000
#> GSM647571 3 0.0188 0.9157 0.000 0.004 0.996 0.000
#> GSM647584 2 0.5069 0.5703 0.320 0.664 0.016 0.000
#> GSM647585 3 0.0592 0.9115 0.016 0.000 0.984 0.000
#> GSM647586 2 0.1302 0.8415 0.044 0.956 0.000 0.000
#> GSM647587 2 0.0188 0.8478 0.004 0.996 0.000 0.000
#> GSM647588 2 0.1724 0.8399 0.032 0.948 0.020 0.000
#> GSM647596 2 0.3301 0.7946 0.076 0.876 0.000 0.048
#> GSM647602 3 0.0000 0.9168 0.000 0.000 1.000 0.000
#> GSM647609 2 0.2704 0.8012 0.124 0.876 0.000 0.000
#> GSM647620 3 0.5546 0.4411 0.052 0.268 0.680 0.000
#> GSM647627 2 0.0469 0.8472 0.012 0.988 0.000 0.000
#> GSM647628 2 0.4313 0.7436 0.064 0.824 0.004 0.108
#> GSM647533 1 0.5963 0.5265 0.688 0.000 0.196 0.116
#> GSM647536 4 0.2647 0.7831 0.120 0.000 0.000 0.880
#> GSM647537 3 0.5167 -0.1092 0.488 0.000 0.508 0.004
#> GSM647606 1 0.5112 -0.0816 0.560 0.000 0.004 0.436
#> GSM647621 4 0.5050 0.1349 0.004 0.000 0.408 0.588
#> GSM647626 3 0.0000 0.9168 0.000 0.000 1.000 0.000
#> GSM647538 1 0.3211 0.5436 0.892 0.012 0.040 0.056
#> GSM647575 4 0.1022 0.7845 0.032 0.000 0.000 0.968
#> GSM647590 1 0.4994 -0.2198 0.520 0.000 0.000 0.480
#> GSM647605 4 0.3311 0.7603 0.172 0.000 0.000 0.828
#> GSM647607 4 0.3172 0.7513 0.160 0.000 0.000 0.840
#> GSM647608 4 0.3351 0.7764 0.148 0.000 0.008 0.844
#> GSM647622 3 0.1940 0.8636 0.076 0.000 0.924 0.000
#> GSM647623 3 0.4382 0.5349 0.296 0.000 0.704 0.000
#> GSM647624 4 0.2647 0.7874 0.120 0.000 0.000 0.880
#> GSM647625 1 0.4948 0.2416 0.560 0.000 0.440 0.000
#> GSM647534 3 0.5040 0.3121 0.364 0.008 0.628 0.000
#> GSM647539 4 0.3266 0.7135 0.168 0.000 0.000 0.832
#> GSM647566 1 0.3468 0.5510 0.880 0.012 0.052 0.056
#> GSM647589 4 0.4978 0.1833 0.004 0.000 0.384 0.612
#> GSM647604 1 0.3486 0.4121 0.812 0.000 0.000 0.188
cbind(get_classes(res, k = 5), get_membership(res, k = 5))
#> class entropy silhouette p1 p2 p3 p4 p5
#> GSM647569 3 0.1399 0.8463 0.020 0.000 0.952 0.000 0.028
#> GSM647574 3 0.1012 0.8500 0.020 0.000 0.968 0.000 0.012
#> GSM647577 3 0.0798 0.8490 0.008 0.000 0.976 0.000 0.016
#> GSM647547 1 0.5844 0.3532 0.640 0.000 0.140 0.208 0.012
#> GSM647552 5 0.4470 0.5843 0.036 0.012 0.208 0.000 0.744
#> GSM647553 3 0.1628 0.8377 0.056 0.000 0.936 0.000 0.008
#> GSM647565 1 0.4798 0.1078 0.512 0.004 0.000 0.472 0.012
#> GSM647545 2 0.2068 0.8208 0.004 0.904 0.000 0.000 0.092
#> GSM647549 2 0.5141 0.6924 0.036 0.736 0.000 0.152 0.076
#> GSM647550 3 0.2573 0.8379 0.104 0.000 0.880 0.000 0.016
#> GSM647560 3 0.3921 0.7798 0.072 0.000 0.800 0.000 0.128
#> GSM647617 3 0.1168 0.8486 0.032 0.000 0.960 0.000 0.008
#> GSM647528 2 0.0451 0.8539 0.008 0.988 0.000 0.000 0.004
#> GSM647529 4 0.0794 0.6097 0.028 0.000 0.000 0.972 0.000
#> GSM647531 4 0.2283 0.5917 0.036 0.040 0.000 0.916 0.008
#> GSM647540 3 0.1216 0.8462 0.020 0.000 0.960 0.000 0.020
#> GSM647541 3 0.3690 0.7964 0.052 0.008 0.828 0.000 0.112
#> GSM647546 3 0.2677 0.8255 0.112 0.000 0.872 0.000 0.016
#> GSM647557 5 0.6981 0.0837 0.032 0.396 0.000 0.148 0.424
#> GSM647561 2 0.1854 0.8432 0.008 0.936 0.000 0.020 0.036
#> GSM647567 4 0.6079 0.3564 0.108 0.000 0.136 0.676 0.080
#> GSM647568 1 0.5935 0.1241 0.580 0.020 0.324 0.000 0.076
#> GSM647570 2 0.2561 0.8228 0.144 0.856 0.000 0.000 0.000
#> GSM647573 4 0.4173 0.3002 0.300 0.000 0.000 0.688 0.012
#> GSM647576 3 0.4410 0.7583 0.112 0.000 0.764 0.000 0.124
#> GSM647579 3 0.2409 0.8341 0.032 0.000 0.900 0.000 0.068
#> GSM647580 3 0.0912 0.8507 0.012 0.000 0.972 0.000 0.016
#> GSM647583 3 0.1211 0.8472 0.016 0.000 0.960 0.000 0.024
#> GSM647592 5 0.5650 0.6219 0.068 0.100 0.120 0.000 0.712
#> GSM647593 5 0.5071 0.5191 0.016 0.272 0.040 0.000 0.672
#> GSM647595 5 0.4557 0.4292 0.012 0.324 0.008 0.000 0.656
#> GSM647597 4 0.5336 0.3325 0.084 0.000 0.000 0.628 0.288
#> GSM647598 2 0.2338 0.8016 0.004 0.884 0.000 0.000 0.112
#> GSM647613 2 0.2122 0.8454 0.036 0.924 0.000 0.032 0.008
#> GSM647615 3 0.5878 0.1665 0.068 0.012 0.504 0.000 0.416
#> GSM647616 3 0.1282 0.8443 0.044 0.000 0.952 0.000 0.004
#> GSM647619 5 0.4449 0.6241 0.020 0.140 0.060 0.000 0.780
#> GSM647582 5 0.5704 0.5584 0.056 0.048 0.232 0.000 0.664
#> GSM647591 5 0.4747 0.3366 0.008 0.376 0.012 0.000 0.604
#> GSM647527 2 0.0162 0.8535 0.004 0.996 0.000 0.000 0.000
#> GSM647530 4 0.1704 0.5892 0.068 0.000 0.000 0.928 0.004
#> GSM647532 4 0.0404 0.6080 0.012 0.000 0.000 0.988 0.000
#> GSM647544 2 0.2806 0.8112 0.152 0.844 0.000 0.000 0.004
#> GSM647551 5 0.3651 0.6279 0.004 0.060 0.108 0.000 0.828
#> GSM647556 3 0.1557 0.8356 0.052 0.000 0.940 0.000 0.008
#> GSM647558 2 0.1831 0.8479 0.076 0.920 0.000 0.000 0.004
#> GSM647572 3 0.2077 0.8304 0.084 0.000 0.908 0.000 0.008
#> GSM647578 3 0.1197 0.8486 0.048 0.000 0.952 0.000 0.000
#> GSM647581 4 0.5859 0.2467 0.144 0.220 0.000 0.628 0.008
#> GSM647594 4 0.0671 0.6099 0.016 0.000 0.000 0.980 0.004
#> GSM647599 3 0.5575 0.6293 0.212 0.000 0.640 0.000 0.148
#> GSM647600 3 0.2735 0.8263 0.036 0.000 0.880 0.000 0.084
#> GSM647601 2 0.2763 0.7649 0.004 0.848 0.000 0.000 0.148
#> GSM647603 3 0.2491 0.8331 0.036 0.000 0.896 0.000 0.068
#> GSM647610 3 0.1357 0.8463 0.048 0.000 0.948 0.000 0.004
#> GSM647611 3 0.7684 -0.3032 0.052 0.256 0.356 0.000 0.336
#> GSM647612 3 0.1774 0.8510 0.052 0.000 0.932 0.000 0.016
#> GSM647614 3 0.6858 0.1113 0.412 0.064 0.444 0.000 0.080
#> GSM647618 2 0.5034 0.3644 0.016 0.616 0.020 0.000 0.348
#> GSM647629 3 0.1195 0.8469 0.028 0.000 0.960 0.000 0.012
#> GSM647535 3 0.1648 0.8491 0.040 0.000 0.940 0.000 0.020
#> GSM647563 2 0.2891 0.8019 0.176 0.824 0.000 0.000 0.000
#> GSM647542 3 0.3466 0.8227 0.076 0.040 0.856 0.000 0.028
#> GSM647543 3 0.4198 0.8052 0.068 0.044 0.816 0.000 0.072
#> GSM647548 4 0.4470 0.1987 0.328 0.008 0.000 0.656 0.008
#> GSM647554 3 0.2157 0.8404 0.036 0.004 0.920 0.000 0.040
#> GSM647555 3 0.1168 0.8519 0.032 0.000 0.960 0.000 0.008
#> GSM647559 2 0.1557 0.8543 0.052 0.940 0.000 0.000 0.008
#> GSM647562 2 0.2976 0.8189 0.132 0.852 0.000 0.012 0.004
#> GSM647564 3 0.2077 0.8327 0.084 0.000 0.908 0.000 0.008
#> GSM647571 3 0.3297 0.8226 0.084 0.000 0.848 0.000 0.068
#> GSM647584 5 0.5370 0.4918 0.024 0.296 0.040 0.000 0.640
#> GSM647585 3 0.3339 0.8135 0.124 0.000 0.836 0.000 0.040
#> GSM647586 2 0.1478 0.8350 0.000 0.936 0.000 0.000 0.064
#> GSM647587 2 0.0880 0.8544 0.032 0.968 0.000 0.000 0.000
#> GSM647588 2 0.2053 0.8296 0.004 0.924 0.048 0.000 0.024
#> GSM647596 2 0.2136 0.8365 0.088 0.904 0.000 0.000 0.008
#> GSM647602 3 0.0290 0.8497 0.008 0.000 0.992 0.000 0.000
#> GSM647609 2 0.4959 0.4402 0.020 0.652 0.020 0.000 0.308
#> GSM647620 3 0.6392 0.4903 0.052 0.200 0.624 0.000 0.124
#> GSM647627 2 0.0968 0.8532 0.012 0.972 0.004 0.000 0.012
#> GSM647628 2 0.4013 0.7380 0.224 0.756 0.008 0.008 0.004
#> GSM647533 5 0.8175 0.0960 0.164 0.000 0.172 0.260 0.404
#> GSM647536 4 0.1216 0.6080 0.020 0.000 0.000 0.960 0.020
#> GSM647537 3 0.6697 0.3610 0.104 0.000 0.576 0.064 0.256
#> GSM647606 4 0.5770 0.3478 0.256 0.000 0.000 0.604 0.140
#> GSM647621 4 0.6724 -0.2415 0.380 0.000 0.208 0.408 0.004
#> GSM647626 3 0.1251 0.8420 0.036 0.000 0.956 0.000 0.008
#> GSM647538 5 0.3053 0.5153 0.128 0.000 0.008 0.012 0.852
#> GSM647575 4 0.4801 0.1618 0.372 0.004 0.000 0.604 0.020
#> GSM647590 4 0.6212 0.1638 0.324 0.000 0.000 0.516 0.160
#> GSM647605 4 0.2659 0.5782 0.060 0.000 0.000 0.888 0.052
#> GSM647607 1 0.5504 0.1153 0.488 0.000 0.000 0.448 0.064
#> GSM647608 4 0.2153 0.6058 0.040 0.000 0.000 0.916 0.044
#> GSM647622 3 0.6359 0.3892 0.220 0.000 0.520 0.000 0.260
#> GSM647623 5 0.6054 0.4153 0.172 0.000 0.260 0.000 0.568
#> GSM647624 4 0.3555 0.5336 0.124 0.000 0.000 0.824 0.052
#> GSM647625 5 0.5057 0.5219 0.072 0.000 0.240 0.004 0.684
#> GSM647534 5 0.4584 0.4941 0.028 0.000 0.312 0.000 0.660
#> GSM647539 1 0.5869 0.2790 0.588 0.016 0.000 0.316 0.080
#> GSM647566 5 0.3742 0.5008 0.188 0.000 0.020 0.004 0.788
#> GSM647589 4 0.6290 -0.0437 0.148 0.000 0.332 0.516 0.004
#> GSM647604 5 0.6468 -0.1632 0.188 0.000 0.000 0.360 0.452
cbind(get_classes(res, k = 6), get_membership(res, k = 6))
#> class entropy silhouette p1 p2 p3 p4 p5 p6
#> GSM647569 3 0.2655 0.74008 0.004 0.000 0.848 0.000 0.140 0.008
#> GSM647574 3 0.2066 0.74842 0.000 0.000 0.908 0.000 0.040 0.052
#> GSM647577 3 0.3032 0.75389 0.012 0.000 0.852 0.000 0.096 0.040
#> GSM647547 4 0.6640 0.01466 0.088 0.008 0.076 0.556 0.016 0.256
#> GSM647552 5 0.5114 0.51430 0.048 0.004 0.144 0.000 0.708 0.096
#> GSM647553 3 0.3905 0.63694 0.012 0.000 0.780 0.004 0.044 0.160
#> GSM647565 4 0.4151 0.37748 0.052 0.012 0.000 0.744 0.000 0.192
#> GSM647545 2 0.6089 0.50290 0.000 0.592 0.008 0.076 0.244 0.080
#> GSM647549 4 0.7476 0.11662 0.004 0.188 0.000 0.412 0.172 0.224
#> GSM647550 3 0.5600 0.58155 0.024 0.048 0.672 0.000 0.072 0.184
#> GSM647560 3 0.5186 0.43345 0.020 0.000 0.548 0.000 0.380 0.052
#> GSM647617 3 0.2113 0.74939 0.004 0.000 0.908 0.000 0.028 0.060
#> GSM647528 2 0.0547 0.82238 0.000 0.980 0.000 0.000 0.020 0.000
#> GSM647529 4 0.4284 0.48454 0.232 0.004 0.000 0.716 0.008 0.040
#> GSM647531 4 0.4034 0.53072 0.128 0.000 0.000 0.784 0.028 0.060
#> GSM647540 3 0.2555 0.75511 0.008 0.000 0.876 0.000 0.096 0.020
#> GSM647541 3 0.4874 0.54085 0.004 0.024 0.620 0.000 0.324 0.028
#> GSM647546 3 0.2414 0.74988 0.012 0.000 0.896 0.000 0.036 0.056
#> GSM647557 5 0.8241 0.11359 0.068 0.108 0.000 0.248 0.340 0.236
#> GSM647561 2 0.6124 0.56444 0.000 0.608 0.000 0.140 0.108 0.144
#> GSM647567 1 0.7415 0.22298 0.420 0.000 0.256 0.224 0.020 0.080
#> GSM647568 6 0.8377 0.17578 0.056 0.052 0.308 0.152 0.060 0.372
#> GSM647570 2 0.3935 0.77668 0.000 0.792 0.000 0.056 0.028 0.124
#> GSM647573 4 0.4102 0.47952 0.116 0.004 0.000 0.760 0.000 0.120
#> GSM647576 3 0.4615 0.53663 0.004 0.000 0.612 0.000 0.340 0.044
#> GSM647579 3 0.3950 0.64471 0.004 0.000 0.708 0.000 0.264 0.024
#> GSM647580 3 0.1578 0.75715 0.004 0.000 0.936 0.000 0.048 0.012
#> GSM647583 3 0.2673 0.73856 0.004 0.000 0.852 0.000 0.132 0.012
#> GSM647592 5 0.6655 0.42210 0.140 0.052 0.192 0.000 0.576 0.040
#> GSM647593 5 0.6564 0.49678 0.032 0.164 0.040 0.000 0.568 0.196
#> GSM647595 5 0.6498 0.31930 0.052 0.248 0.000 0.000 0.504 0.196
#> GSM647597 1 0.6938 0.06404 0.424 0.000 0.000 0.332 0.124 0.120
#> GSM647598 2 0.3469 0.74328 0.000 0.808 0.000 0.000 0.104 0.088
#> GSM647613 2 0.5991 0.58483 0.004 0.604 0.000 0.216 0.056 0.120
#> GSM647615 5 0.5410 0.13958 0.016 0.012 0.348 0.000 0.568 0.056
#> GSM647616 3 0.1367 0.74093 0.000 0.000 0.944 0.000 0.012 0.044
#> GSM647619 5 0.6334 0.53587 0.052 0.080 0.076 0.000 0.632 0.160
#> GSM647582 5 0.4122 0.48754 0.028 0.016 0.196 0.000 0.752 0.008
#> GSM647591 5 0.6297 0.32642 0.024 0.252 0.004 0.000 0.512 0.208
#> GSM647527 2 0.0508 0.82377 0.000 0.984 0.000 0.000 0.012 0.004
#> GSM647530 4 0.2462 0.55917 0.132 0.004 0.000 0.860 0.000 0.004
#> GSM647532 4 0.2955 0.54314 0.172 0.000 0.000 0.816 0.008 0.004
#> GSM647544 2 0.2154 0.80225 0.004 0.908 0.004 0.020 0.000 0.064
#> GSM647551 5 0.5385 0.52728 0.044 0.024 0.092 0.000 0.704 0.136
#> GSM647556 3 0.3266 0.64870 0.008 0.000 0.824 0.000 0.036 0.132
#> GSM647558 2 0.1410 0.82317 0.000 0.944 0.000 0.008 0.004 0.044
#> GSM647572 3 0.3461 0.63633 0.008 0.000 0.804 0.000 0.036 0.152
#> GSM647578 3 0.1624 0.74299 0.008 0.000 0.936 0.000 0.012 0.044
#> GSM647581 4 0.3089 0.52496 0.020 0.104 0.000 0.848 0.000 0.028
#> GSM647594 4 0.3568 0.51342 0.212 0.000 0.000 0.764 0.008 0.016
#> GSM647599 3 0.6416 0.29929 0.088 0.000 0.472 0.000 0.352 0.088
#> GSM647600 3 0.4253 0.60071 0.008 0.000 0.664 0.000 0.304 0.024
#> GSM647601 2 0.3845 0.71595 0.000 0.772 0.000 0.000 0.140 0.088
#> GSM647603 3 0.4193 0.63353 0.008 0.000 0.688 0.000 0.276 0.028
#> GSM647610 3 0.2716 0.71578 0.008 0.000 0.868 0.000 0.028 0.096
#> GSM647611 5 0.6766 0.45361 0.004 0.212 0.208 0.000 0.504 0.072
#> GSM647612 3 0.4251 0.71175 0.004 0.024 0.776 0.000 0.084 0.112
#> GSM647614 3 0.8780 -0.32316 0.028 0.080 0.312 0.116 0.164 0.300
#> GSM647618 5 0.6828 0.32621 0.016 0.272 0.028 0.004 0.472 0.208
#> GSM647629 3 0.3579 0.73882 0.008 0.000 0.808 0.000 0.120 0.064
#> GSM647535 3 0.3054 0.75138 0.004 0.000 0.840 0.000 0.116 0.040
#> GSM647563 2 0.2260 0.78568 0.000 0.860 0.000 0.000 0.000 0.140
#> GSM647542 3 0.4889 0.63986 0.004 0.132 0.732 0.000 0.060 0.072
#> GSM647543 3 0.5223 0.62713 0.004 0.044 0.668 0.004 0.232 0.048
#> GSM647548 4 0.3161 0.51135 0.040 0.020 0.000 0.848 0.000 0.092
#> GSM647554 3 0.2579 0.74811 0.008 0.000 0.884 0.000 0.060 0.048
#> GSM647555 3 0.2781 0.75247 0.004 0.016 0.880 0.000 0.040 0.060
#> GSM647559 2 0.1536 0.82326 0.000 0.940 0.004 0.000 0.016 0.040
#> GSM647562 2 0.2876 0.78234 0.004 0.860 0.000 0.056 0.000 0.080
#> GSM647564 3 0.3194 0.65827 0.008 0.000 0.828 0.000 0.032 0.132
#> GSM647571 3 0.4757 0.62494 0.008 0.016 0.672 0.000 0.264 0.040
#> GSM647584 5 0.6151 0.54243 0.004 0.152 0.072 0.000 0.604 0.168
#> GSM647585 3 0.3821 0.72078 0.028 0.000 0.804 0.000 0.108 0.060
#> GSM647586 2 0.1890 0.80888 0.000 0.916 0.000 0.000 0.060 0.024
#> GSM647587 2 0.0725 0.82365 0.000 0.976 0.000 0.000 0.012 0.012
#> GSM647588 2 0.2589 0.79207 0.000 0.888 0.060 0.000 0.028 0.024
#> GSM647596 2 0.1706 0.81340 0.004 0.936 0.004 0.032 0.000 0.024
#> GSM647602 3 0.1578 0.75739 0.004 0.000 0.936 0.000 0.048 0.012
#> GSM647609 2 0.6267 0.05283 0.008 0.444 0.016 0.000 0.376 0.156
#> GSM647620 3 0.6683 0.12251 0.008 0.192 0.452 0.000 0.312 0.036
#> GSM647627 2 0.1555 0.81658 0.000 0.940 0.008 0.000 0.040 0.012
#> GSM647628 2 0.3931 0.75272 0.012 0.808 0.004 0.040 0.020 0.116
#> GSM647533 1 0.5247 0.42359 0.728 0.000 0.100 0.028 0.076 0.068
#> GSM647536 4 0.4870 0.29155 0.380 0.004 0.000 0.572 0.012 0.032
#> GSM647537 1 0.6094 0.24565 0.584 0.000 0.268 0.016 0.064 0.068
#> GSM647606 1 0.3996 0.28269 0.760 0.000 0.000 0.180 0.012 0.048
#> GSM647621 4 0.5808 0.19989 0.060 0.000 0.156 0.628 0.000 0.156
#> GSM647626 3 0.2838 0.69393 0.004 0.000 0.852 0.000 0.028 0.116
#> GSM647538 1 0.4934 0.28455 0.576 0.000 0.016 0.004 0.372 0.032
#> GSM647575 4 0.6037 0.26506 0.244 0.012 0.000 0.532 0.004 0.208
#> GSM647590 1 0.5801 0.06667 0.564 0.000 0.000 0.284 0.028 0.124
#> GSM647605 1 0.4987 0.00159 0.584 0.000 0.000 0.352 0.016 0.048
#> GSM647607 4 0.5908 -0.01186 0.248 0.000 0.000 0.468 0.000 0.284
#> GSM647608 4 0.5100 0.36077 0.380 0.000 0.000 0.556 0.036 0.028
#> GSM647622 1 0.7239 -0.06260 0.368 0.000 0.288 0.000 0.248 0.096
#> GSM647623 5 0.6575 0.27100 0.168 0.000 0.260 0.000 0.504 0.068
#> GSM647624 4 0.4648 0.42311 0.340 0.000 0.000 0.604 0.000 0.056
#> GSM647625 5 0.6254 0.29425 0.220 0.000 0.260 0.000 0.496 0.024
#> GSM647534 5 0.5048 0.21582 0.068 0.000 0.344 0.000 0.580 0.008
#> GSM647539 6 0.6851 -0.15779 0.264 0.016 0.000 0.316 0.020 0.384
#> GSM647566 1 0.5834 0.19569 0.492 0.000 0.004 0.016 0.380 0.108
#> GSM647589 4 0.6396 0.20924 0.056 0.004 0.196 0.608 0.028 0.108
#> GSM647604 1 0.3912 0.42455 0.796 0.000 0.000 0.072 0.108 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) development.stage(p) other(p) k
#> ATC:NMF 98 1.48e-02 0.605 0.351 2
#> ATC:NMF 95 2.96e-05 0.224 0.126 3
#> ATC:NMF 83 3.47e-06 0.356 0.282 4
#> ATC:NMF 72 2.24e-04 0.114 0.478 5
#> ATC:NMF 61 8.20e-01 0.322 0.473 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