vcf_clustering
EPermina
15 April 2018
if(!require(tidyverse)){
install.packages("tidyverse")
}## Loading required package: tidyverse## ── Attaching packages ────────────────────────────────── tidyverse 1.2.1 ──## ✔ ggplot2 2.2.1 ✔ purrr 0.2.4
## ✔ tibble 1.4.2 ✔ dplyr 0.7.4
## ✔ tidyr 0.8.0 ✔ stringr 1.3.0
## ✔ readr 1.1.1 ✔ forcats 0.3.0## ── Conflicts ───────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()if(!require(SNPRelate)){
source("https://bioconductor.org/biocLite.R")
biocLite("SNPRelate")
}## Loading required package: SNPRelate## Loading required package: gdsfmt## SNPRelate -- supported by Streaming SIMD Extensions 2 (SSE2)set.seed(1680) # for reproducibility
if(!require(ISLR)) {
install.packages("ISLR")
}## Loading required package: ISLRif(!require(cluster)) {
install.packages("cluster")
}## Loading required package: clusterif(!require(Rtsne)) {
install.packages("Rtsne")
}## Loading required package: Rtsnelibrary(cluster) # for gower similarity and pam
library(Rtsne) # for t-SNE plot
library(tidyverse)
library(SNPRelate)
library(reshape2)##
## Attaching package: 'reshape2'## The following object is masked from 'package:tidyr':
##
## smithsset.seed(1680) # for reproducibilityData manipulation, reading in
first_analysis/populations.snps.vcf.filtered.for.non-presence.presumed.0.samplesOnly.txt is a modified populations.snps.vcf file
- all samples with no coverage of SNPs (./. only columns) were removed
- vcf header has also been removed
- ./. is replaced with 0/0:0:0,0
# cat first info columns
# get rid of "single" in the col names (sample names)
cat populations.snps.vcf | sed 's/.single//g' | tail -n +16 | cut -f10- | tr ":" "\t" | sed 's#0/1#0.5#g' | sed 's#0/0#0#g' | sed 's#1/1#1#g' > genotypes_and_coverage.01.txt # # convert genotypes from 0/1 format to 0.5 format
cat populations.snps.vcf | sed 's/.single//g' | tail -n +15 | cut -f10- | head -1 > sampleNames.txt # read in bash-splitted file
genotypes_and_coverage<-read.delim("genotypes_and_coverage.01.txt", header = F, sep = '\t')
sample_names<-read.delim("sampleNames.txt", sep = "\t", header = TRUE, nrows=2)
names<-names(sample_names)
genotype_names_in_split <- paste(names, ".1.geno", sep="") # genotype names in split
coverage_names_in_split <- paste(names, ".2.cover", sep="") # coverage names in split
support_reads_names<- paste(names, ".3.support", sep="") # coverage supporting reads names in split
#bind 3 vectors
names_split <- sort(as.vector(rbind(genotype_names_in_split,coverage_names_in_split,support_reads_names))) # collate
names(genotypes_and_coverage)<-names_split
coverage_cols<-grepl("2.cover", names(genotypes_and_coverage))
genotype_cols<-grepl("1.geno", names(genotypes_and_coverage))
coverage<-genotypes_and_coverage[coverage_cols]
genotype<-genotypes_and_coverage[genotype_cols]
#genotype<- read.delim("genotype.01.txt", sep = "\t", header = TRUE)
t.coverage<-t(as.matrix(coverage))
t.genotype<-t(as.matrix(genotype))Clustering - - coverage and genotype
# Applying Ward Hierarchical Clustering
d_coverage <- dist(t.coverage, method="euclidean")
ward_fit_coverage <- hclust(d_coverage, method="ward")## The "ward" method has been renamed to "ward.D"; note new "ward.D2"g4_ward_coverage <- cutree(ward_fit_coverage, k = c(4))
g8_ward_coverage <- cutree(ward_fit_coverage, k = c(8))
#using Gower via daisy
gower_dist_genotype <- daisy(t.genotype,
metric = "gower",
type = list(logratio = 3))## Warning in daisy(t.genotype, metric = "gower", type = list(logratio = 3)):
## binary variable(s) 2, 4, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 17, 18, 19,
## 20, 21, 22, 23, 24, 25, 26 treated as interval scaledgower_mat_genotype <- as.matrix(gower_dist_genotype)
tsne_obj_genotype <- Rtsne(gower_dist_genotype, is_distance = TRUE)
pam_fit_genotype <- pam(gower_dist_genotype, diss = TRUE, k = 3)
tsne_data_genotype <- tsne_obj_genotype$Y %>%
data.frame() %>%
setNames(c("X", "Y")) %>%
mutate(cluster = factor(pam_fit_genotype$clustering),
name = row.names(t.genotype))
# Gower clusters for coverage:
gower_dist_coverage <- daisy(t.coverage,
metric = "gower",
type = list(logratio = 3))
gower_mat_coverage <- as.matrix(gower_dist_coverage)
tsne_obj_coverage <- Rtsne(gower_dist_coverage, is_distance = TRUE)
pam_fit_coverage <- pam(gower_dist_coverage, diss = TRUE, k = 3)
tsne_data_coverage <- tsne_obj_coverage$Y %>%
data.frame() %>%
setNames(c("X", "Y")) %>%
mutate(cluster = factor(pam_fit_coverage$clustering),
name = row.names(t.coverage))Writing data out
write.table(tsne_data_genotype, file="genotype_clusters.csv", quote = FALSE, sep = ",")
write.table(g8_ward_coverage, file="coverage_groups.csv", quote = FALSE, sep = ",")
#write.table()Plots: Ward clustered dendrogram for coverage:
plot(ward_fit_coverage)
Genotype clusters:
ggplot(aes(x = X, y = Y), data = tsne_data_genotype) +
geom_point(aes(color = cluster))
Samples in genotype clusters:
tsne_data_genotype## X Y cluster name
## 1 -9.0275969 -6.24022771 1 P1_A01.1.geno
## 2 -8.5733970 -4.96771651 1 P1_A02.1.geno
## 3 2.9268395 -0.15391249 2 P1_A03.1.geno
## 4 3.6549049 2.75365209 2 P1_A04.1.geno
## 5 2.5982498 -0.83326148 2 P1_A05.1.geno
## 6 4.8746777 2.46090491 2 P1_A06.1.geno
## 7 4.1394616 1.04698684 2 P1_A07.1.geno
## 8 -3.6982637 -0.84295930 3 P1_A08.1.geno
## 9 -3.6982637 -0.84295930 3 P1_A09.1.geno
## 10 -8.5804480 -4.79813955 1 P1_A10.1.geno
## 11 3.1491796 3.92601472 2 P1_A11.1.geno
## 12 -3.6905131 -1.06522763 3 P1_A12.1.geno
## 13 -9.0256390 -6.23994384 1 P1_B01.1.geno
## 14 0.9942077 2.20661849 2 P1_B02.1.geno
## 15 1.3313714 -0.58053000 2 P1_B03.1.geno
## 16 -3.6905887 -1.06546154 3 P1_B04.1.geno
## 17 4.1349555 1.54191831 2 P1_B05.1.geno
## 18 1.2295602 2.70242443 2 P1_B06.1.geno
## 19 4.0070159 2.19271063 2 P1_B07.1.geno
## 20 1.5648114 0.37355042 2 P1_B08.1.geno
## 21 3.7217895 3.82947266 2 P1_B09.1.geno
## 22 3.7217895 3.82947266 2 P1_B10.1.geno
## 23 3.3431274 3.07648052 2 P1_B11.1.geno
## 24 3.9702056 2.27716388 2 P1_B12.1.geno
## 25 3.1376562 -0.95601103 2 P1_C01.1.geno
## 26 -9.0266415 -6.24052710 1 P1_C02.1.geno
## 27 0.7649760 3.37527338 2 P1_C03.1.geno
## 28 0.9872588 2.17177043 2 P1_C04.1.geno
## 29 2.8293319 -1.01990655 2 P1_C05.1.geno
## 30 -9.0260767 -6.24097859 1 P1_C06.1.geno
## 31 3.9788116 2.26280689 2 P1_C07.1.geno
## 32 -3.6660938 -0.89296383 3 P1_C08.1.geno
## 33 -9.0280735 -6.24084313 1 P1_C09.1.geno
## 34 2.3685632 1.91336634 2 P1_C10.1.geno
## 35 1.2263342 3.69217034 2 P1_C11.1.geno
## 36 1.3373933 2.80618602 2 P1_C12.1.geno
## 37 -9.0273296 -6.24062574 1 P1_D01.1.geno
## 38 -9.0275712 -6.24024982 1 P1_D02.1.geno
## 39 3.1114720 -0.16090742 2 P1_D03.1.geno
## 40 2.7847014 3.16177606 2 P1_D04.1.geno
## 41 2.5525417 3.98594002 2 P1_D05.1.geno
## 42 0.8795029 1.35354054 2 P1_D06.1.geno
## 43 2.1650138 3.96485462 2 P1_D07.1.geno
## 44 -9.3112805 -6.53371156 1 P1_D08.1.geno
## 45 0.9232555 -0.07103359 2 P1_D09.1.geno
## 46 -9.0273519 -6.24033613 1 P1_D11.1.geno
## 47 -8.5801521 -4.79810013 1 P1_D12.1.geno
## 48 4.6184305 -0.08891616 2 P1_E01.1.geno
## 49 2.2158735 -1.09501306 2 P1_E02.1.geno
## 50 1.5689882 2.95338811 2 P1_E03.1.geno
## 51 4.2704512 2.87709581 2 P1_E04.1.geno
## 52 1.7296677 -0.88897380 2 P1_E05.1.geno
## 53 -8.5762420 -4.96768769 1 P1_E06.1.geno
## 54 3.3055005 -0.12261126 2 P1_E07.1.geno
## 55 0.7499287 0.55361308 2 P1_E08.1.geno
## 56 -8.5735173 -4.96691769 1 P1_E09.1.geno
## 57 3.7310858 -0.76954903 2 P1_E11.1.geno
## 58 1.0489636 -0.16696390 2 P1_E12.1.geno
## 59 1.8737307 3.18954825 2 P1_F01.1.geno
## 60 -8.0880411 -6.24614431 1 P1_F02.1.geno
## 61 1.3146887 -0.40600607 2 P1_F03.1.geno
## 62 2.3346109 -0.07658695 2 P1_F04.1.geno
## 63 0.4630021 2.87624960 2 P1_F05.1.geno
## 64 2.1188688 3.14858559 2 P1_F06.1.geno
## 65 2.5579782 -0.14518007 2 P1_F07.1.geno
## 66 -7.8278075 -5.54217765 1 P1_F08.1.geno
## 67 2.0677735 1.58309762 2 P1_F09.1.geno
## 68 4.1397925 1.55229791 2 P1_F10.1.geno
## 69 2.7224988 -0.26913181 2 P1_F11.1.geno
## 70 0.3131316 1.94944681 2 P1_F12.1.geno
## 71 -8.9373169 -6.42994699 1 P1_G02.1.geno
## 72 4.3219183 3.47435494 2 P1_G03.1.geno
## 73 4.0429056 2.10404789 2 P1_G04.1.geno
## 74 -9.0247932 -6.23955247 1 P1_G05.1.geno
## 75 -3.9515518 -1.89563858 3 P1_G06.1.geno
## 76 4.3575570 3.48407411 2 P1_G07.1.geno
## 77 3.7314779 -0.76938854 2 P1_G08.1.geno
## 78 1.8774086 0.10978213 2 P1_G09.1.geno
## 79 4.3300604 0.87076909 2 P1_G10.1.geno
## 80 -9.0277630 -6.24046365 1 P1_G11.1.geno
## 81 4.3154816 -0.38037783 2 P1_G12.1.geno
## 82 1.6369589 0.33722983 2 P1_H01.1.geno
## 83 4.0202323 2.15109055 2 P1_H02.1.geno
## 84 2.0255979 0.01666963 2 P1_H03.1.geno
## 85 4.1487730 1.51988551 2 P1_H04.1.geno
## 86 4.6797385 2.59496588 2 P1_H05.1.geno
## 87 5.0076614 2.33669893 2 P1_H06.1.geno
## 88 -9.0270988 -6.24036010 1 P1_H07.1.geno
## 89 2.5639875 1.95336536 2 P1_H08.1.geno
## 90 3.6552628 2.75425953 2 P1_H09.1.geno
## 91 4.1497818 1.53310848 2 P1_H10.1.geno
## 92 3.2088069 -0.14482005 2 P1_H11.1.geno
## 93 2.7217290 3.17275003 2 P1_H12.1.geno
## 94 4.7029228 0.09445591 2 P2_A01.1.geno
## 95 2.6144339 3.12398529 2 P2_A02.1.geno
## 96 3.7762785 -0.01382083 2 P2_A03.1.geno
## 97 2.7475669 3.12306632 2 P2_A04.1.geno
## 98 -8.6287420 -4.76269251 1 P2_A05.1.geno
## 99 1.4802740 3.85705300 2 P2_A07.1.geno
## 100 0.7416349 1.77484588 2 P2_A08.1.geno
## 101 5.0896634 1.55863219 2 P2_A09.1.geno
## 102 2.0079887 3.15781604 2 P2_A10.1.geno
## 103 1.2648344 0.66580522 2 P2_A11.1.geno
## 104 2.5279215 -0.09189322 2 P2_A12.1.geno
## 105 -8.5728273 -4.96809034 1 P2_B01.1.geno
## 106 1.4263310 2.79706384 2 P2_B02.1.geno
## 107 0.8375271 1.49463950 2 P2_B06.1.geno
## 108 -3.6905474 -1.06551905 3 P2_B07.1.geno
## 109 1.0686268 2.30991037 2 P2_B08.1.geno
## 110 5.1579755 0.91296430 2 P2_B09.1.geno
## 111 2.9717290 1.44468930 2 P2_B10.1.geno
## 112 2.9240073 1.80293333 2 P2_B11.1.geno
## 113 3.1477670 1.52029401 2 P2_B12.1.geno
## 114 1.4096462 0.51150246 2 P2_C02.1.geno
## 115 -0.7491210 0.37500260 2 P2_C03.1.geno
## 116 -1.0776133 0.24301716 3 P2_C05.1.geno
## 117 -0.8751639 0.32482837 2 P2_C07.1.geno
## 118 2.9696054 1.74972021 2 P2_C08.1.geno
## 119 2.8801045 1.85067619 2 P2_C09.1.geno
## 120 3.1079887 1.57243056 2 P2_C12.1.geno
## 121 3.0500855 1.61074713 2 P2_D03.1.geno
## 122 3.0240369 1.67103113 2 P2_D04.1.geno
## 123 2.8801044 1.85067633 2 P2_D05.1.geno
## 124 -9.0270405 -6.24018859 1 P2_D06.1.geno
## 125 -9.0281172 -6.24009170 1 P2_D07.1.geno
## 126 -9.0274075 -6.23958213 1 P2_D08.1.geno
## 127 3.0500855 1.61074713 2 P2_D09.1.geno
## 128 -9.0264096 -6.24011622 1 P2_E01.1.geno
## 129 2.2744632 1.83348594 2 P2_E02.1.geno
## 130 2.8801044 1.85067633 2 P2_E03.1.geno
## 131 -3.6905787 -1.06555795 3 P2_E05.1.geno
## 132 0.3703816 1.41633192 2 P2_E06.1.geno
## 133 -9.3140770 -6.57432986 1 P2_E09.1.geno
## 134 2.8586769 1.62368343 2 P2_E11.1.geno
## 135 2.7507631 1.91377530 2 P2_E12.1.geno
## 136 -9.0282985 -6.24013499 1 P2_F02.1.geno
## 137 2.8083848 1.89093691 2 P2_F03.1.geno
## 138 -3.6905787 -1.06555798 3 P2_F04.1.geno
## 139 2.5510461 1.95719568 2 P2_F05.1.geno
## 140 2.8759021 1.28507992 2 P2_F06.1.geno
## 141 2.5239082 1.94794736 2 P2_F08.1.geno
## 142 2.8069071 1.22124777 2 P2_F09.1.geno
## 143 2.8759021 1.28507992 2 P2_G03.1.geno
## 144 4.1341917 2.96918304 2 P2_G05.1.geno
## 145 2.3072956 1.65591711 2 P2_G06.1.geno
## 146 -9.0279052 -6.23964932 1 P2_G09.1.geno
## 147 2.4155908 1.15556826 2 P2_H01.1.geno
## 148 2.4097797 1.15128897 2 P2_H02.1.geno
## 149 2.3056422 1.65361846 2 P2_H04.1.geno
## 150 2.3225646 1.52098758 2 P2_H05.1.geno
## 151 2.5658402 1.94999778 2 P2_H06.1.geno
## 152 2.3685634 1.91336642 2 P2_H07.1.geno
## 153 2.7899187 1.20341811 2 P2_H08.1.geno
## 154 2.0691820 1.57483365 2 P2_H09.1.geno
## 155 -8.5735094 -4.96780277 1 P3_A01.1.geno
## 156 -7.9330737 -4.25241156 3 P3_A02.1.geno
## 157 2.8016030 1.21507996 2 P3_A03.1.geno
## 158 -9.0277258 -6.24036628 1 P3_A04.1.geno
## 159 2.7916814 1.20607991 2 P3_A05.1.geno
## 160 2.0611301 1.53768271 2 P3_A06.1.geno
## 161 2.0617646 1.57769428 2 P3_A07.1.geno
## 162 2.7963708 1.21031253 2 P3_A08.1.geno
## 163 2.5196929 1.94290661 2 P3_A09.1.geno
## 164 -9.0327126 -6.24055727 1 P3_A10.1.geno
## 165 2.4872640 1.93737460 2 P3_A11.1.geno
## 166 2.0604123 1.51662385 2 P3_A12.1.geno
## 167 2.7900810 1.20355151 2 P3_B01.1.geno
## 168 2.7912845 1.20574883 2 P3_B02.1.geno
## 169 -9.0279131 -6.24066640 1 P3_B03.1.geno
## 170 2.3780718 1.18039530 2 P3_B04.1.geno
## 171 2.3802405 1.17681375 2 P3_B05.1.geno
## 172 2.3011277 1.65867205 2 P3_B06.1.geno
## 173 2.3940047 1.16786437 2 P3_B07.1.geno
## 174 2.3041390 1.67022258 2 P3_B08.1.geno
## 175 2.3828779 1.17491536 2 P3_B09.1.geno
## 176 2.7911646 1.20579015 2 P3_B10.1.geno
## 177 2.3984600 1.16567284 2 P3_B11.1.geno
## 178 2.1028964 1.58480396 2 P3_B12.1.geno
## 179 -8.5746671 -4.96724385 1 P3_C01.1.geno
## 180 -8.5736302 -4.96765507 1 P3_C02.1.geno
## 181 2.3778296 1.17853690 2 P3_C03.1.geno
## 182 2.7897206 1.20324511 2 P3_C04.1.geno
## 183 2.3726923 1.18570770 2 P3_C05.1.geno
## 184 -9.0273011 -6.24008951 1 P3_C06.1.geno
## 185 2.3110630 1.70095964 2 P3_C07.1.geno
## 186 2.4934746 1.93886644 2 P3_C08.1.geno
## 187 2.7885075 1.20212452 2 P3_C09.1.geno
## 188 2.5017396 1.93889452 2 P3_C10.1.geno
## 189 2.4025124 1.16264517 2 P3_D01.1.geno
## 190 2.3752404 1.18019721 2 P3_D02.1.geno
## 191 2.7883642 1.20219369 2 P3_D03.1.geno
## 192 2.4101002 1.15785168 2 P3_D05.1.geno
## 193 2.3044205 1.64603358 2 P3_D06.1.geno
## 194 2.7881881 1.20193354 2 P3_D07.1.geno
## 195 2.3750859 1.90939091 2 P3_D08.1.geno
## 196 2.0677735 1.58309763 2 P3_D09.1.geno
## 197 2.3788172 1.17765871 2 P3_D11.1.geno
## 198 2.0605935 1.51482458 2 P3_D12.1.geno
## 199 0.4989277 0.88597621 2 P3_E02.1.geno
## 200 2.0677735 1.58309763 2 P3_E03.1.geno
## 201 -8.4019993 -6.27575317 1 P3_E04.1.geno
## 202 2.0558517 1.49582135 2 P3_E05.1.geno
## 203 2.3773102 1.17891834 2 P3_E06.1.geno
## 204 2.7904144 1.20513854 2 P3_E07.1.geno
## 205 -7.6445891 -5.43026810 1 P3_F01.1.geno
## 206 -9.0278578 -6.24037685 1 P3_F04.1.geno
## 207 2.7900810 1.20355151 2 P3_F05.1.geno
## 208 2.7921867 1.20792339 2 P3_F08.1.geno
## 209 2.3072956 1.65591711 2 P3_F12.1.geno
## 210 2.7967705 1.21113663 2 P3_G02.1.geno
## 211 2.7938769 1.20784580 2 P3_G03.1.geno
## 212 2.3685412 1.91335675 2 P3_G04.1.geno
## 213 2.8202966 1.88060830 2 P3_G05.1.geno
## 214 2.3782135 1.18147777 2 P3_G06.1.geno
## 215 2.9057950 1.82422912 2 P3_H05.1.geno
## 216 -8.5743118 -4.96743109 1 P4_A01.1.geno
## 217 -3.6906417 -1.06553534 3 P4_A02.1.geno
## 218 3.0500855 1.61074713 2 P4_A03.1.geno
## 219 -8.5745503 -4.96773118 1 P4_A07.1.geno
## 220 -0.6263837 1.62647795 1 P4_A08.1.geno
## 221 -8.5745524 -4.96785098 1 P4_A09.1.geno
## 222 2.9626916 1.75981460 2 P4_A10.1.geno
## 223 -3.9513876 -1.89613851 3 P4_A11.1.geno
## 224 2.8415762 1.86822298 2 P4_A12.1.geno
## 225 -3.6905950 -1.06553352 3 P4_B01.1.geno
## 226 -8.5739543 -4.96756009 1 P4_B02.1.geno
## 227 -8.5734954 -4.96735406 1 P4_B03.1.geno
## 228 -3.6905765 -1.06559958 3 P4_B05.1.geno
## 229 3.0500855 1.61074713 2 P4_B06.1.geno
## 230 2.8586769 1.62368343 2 P4_B07.1.geno
## 231 3.0500855 1.61074713 2 P4_B08.1.geno
## 232 2.9595015 1.76359907 2 P4_B09.1.geno
## 233 2.3056435 1.65362293 2 P4_B11.1.geno
## 234 4.9702665 1.10859804 2 P4_B12.1.geno
## 235 1.7749188 0.17313048 2 P4_C03.1.geno
## 236 -9.0275579 -6.24041697 1 P4_C04.1.geno
## 237 0.8787586 1.35096512 2 P4_C05.1.geno
## 238 -0.7491210 0.37500260 2 P4_C06.1.geno
## 239 -3.6904313 -1.06555768 3 P4_C07.1.geno
## 240 0.7552745 0.64838149 2 P4_C08.1.geno
## 241 5.0236349 0.64998647 2 P4_C10.1.geno
## 242 -3.6904160 -1.06571476 3 P4_C11.1.geno
## 243 3.5771857 -0.08810084 2 P4_D01.1.geno
## 244 1.9019138 -0.66659642 2 P4_D02.1.geno
## 245 1.2091785 0.83097429 2 P4_D03.1.geno
## 246 -8.5751149 -4.96763257 1 P4_D04.1.geno
## 247 2.8020909 3.16361634 2 P4_D05.1.geno
## 248 -3.6660946 -0.89296444 3 P4_D06.1.geno
## 249 2.0569492 0.01530520 2 P4_D07.1.geno
## 250 -3.6905787 -1.06555795 3 P4_D08.1.geno
## 251 4.2385135 0.87073660 2 P4_D09.1.geno
## 252 -3.6905787 -1.06555795 3 P4_D11.1.geno
## 253 -9.0269296 -6.24022086 1 P4_D12.1.geno
## 254 4.2385175 0.87084449 2 P4_E01.1.geno
## 255 -8.5735148 -4.96710751 1 P4_E02.1.geno
## 256 -3.6906666 -1.06556599 3 P4_E03.1.geno
## 257 -3.5817761 -1.67893252 3 P4_E04.1.geno
## 258 1.8618528 3.09287285 2 P4_E05.1.geno
## 259 -3.8635711 -1.98807280 3 P4_E06.1.geno
## 260 -3.6906665 -1.06556600 3 P4_E07.1.geno
## 261 1.0247974 2.43430961 2 P4_E08.1.geno
## 262 -3.6886429 -1.06615687 3 P4_E09.1.geno
## 263 1.3668937 2.75336571 2 P4_E11.1.geno
## 264 1.8162512 3.18445138 2 P4_E12.1.geno
## 265 1.2054666 0.80991627 2 P4_F01.1.geno
## 266 -3.6905787 -1.06555798 3 P4_F02.1.geno
## 267 -3.9513908 -1.89646382 3 P4_F03.1.geno
## 268 5.1095536 1.72668421 2 P4_F04.1.geno
## 269 0.3165625 2.43321308 2 P4_F05.1.geno
## 270 -8.5740386 -4.96785630 1 P4_F06.1.geno
## 271 -3.5817834 -1.67893295 3 P4_F07.1.geno
## 272 0.8090803 0.48165025 2 P4_F08.1.geno
## 273 2.2746997 3.91637675 2 P4_F09.1.geno
## 274 0.9803535 1.39106430 2 P4_F10.1.geno
## 275 4.4735213 1.72886380 2 P4_F12.1.geno
## 276 3.9009319 0.41285273 2 P4_G01.1.geno
## 277 0.9462675 2.07131684 2 P4_G07.1.geno
## 278 3.0255228 3.98400414 2 P4_G09.1.geno
## 279 0.8333512 1.49901766 2 P4_G11.1.geno
## 280 3.6503445 2.79681279 2 P4_H01.1.geno
## 281 3.3376689 3.07181055 2 P4_H06.1.geno
## 282 3.3376689 3.07181055 2 P4_H07.1.geno
## 283 3.9008000 0.41264478 2 P4_H09.1.geno
## 284 3.9007959 0.41263820 2 P4_H10.1.geno
## 285 3.9007959 0.41263820 2 P4_H11.1.geno
## 286 2.3768538 1.91415786 2 P4_H12.1.genoCoverage Gower clusters:
ggplot(aes(x = X, y = Y), data = tsne_data_coverage) +
geom_point(aes(color = cluster))
Samples and coverage clusters:
tsne_data_coverage## X Y cluster name
## 1 2.321135808 -2.7608904 1 P1_A01.2.cover
## 2 3.526319455 -3.6701296 1 P1_A02.2.cover
## 3 -0.304493267 8.0936922 2 P1_A03.2.cover
## 4 1.906156900 5.5102565 2 P1_A04.2.cover
## 5 2.204881296 6.4435140 2 P1_A05.2.cover
## 6 1.823113474 7.0934428 2 P1_A06.2.cover
## 7 0.906990417 -1.1471230 2 P1_A07.2.cover
## 8 3.501086312 -0.6044907 2 P1_A08.2.cover
## 9 -1.372189768 -7.2863522 2 P1_A09.2.cover
## 10 3.970247812 -2.4124510 2 P1_A10.2.cover
## 11 -0.511700897 -7.0082746 2 P1_A11.2.cover
## 12 3.157686623 -0.7141103 2 P1_A12.2.cover
## 13 0.678915099 -6.4289555 3 P1_B01.2.cover
## 14 -1.647758862 1.9869954 2 P1_B02.2.cover
## 15 -1.064203919 -7.0420491 2 P1_B03.2.cover
## 16 0.666344473 -8.0640674 3 P1_B04.2.cover
## 17 -2.636081774 -0.4598821 2 P1_B05.2.cover
## 18 1.099813180 6.6060573 2 P1_B06.2.cover
## 19 -1.085868884 6.9687945 2 P1_B07.2.cover
## 20 -1.189898668 7.5906013 2 P1_B08.2.cover
## 21 0.345613796 1.8874242 2 P1_B09.2.cover
## 22 -7.758437585 -1.1134272 2 P1_B10.2.cover
## 23 -1.112694860 1.7951857 2 P1_B11.2.cover
## 24 0.860834285 2.1879836 2 P1_B12.2.cover
## 25 -0.684918926 4.7954035 2 P1_C01.2.cover
## 26 0.803717781 -6.4293236 1 P1_C02.2.cover
## 27 1.954666864 0.2104642 2 P1_C03.2.cover
## 28 -1.905704210 7.4314508 2 P1_C04.2.cover
## 29 -0.841211762 -7.1821594 2 P1_C05.2.cover
## 30 3.027152973 -6.0494523 1 P1_C06.2.cover
## 31 -2.613197469 -0.4682609 2 P1_C07.2.cover
## 32 2.161462284 -8.2635364 3 P1_C08.2.cover
## 33 0.688867832 -2.7057058 2 P1_C09.2.cover
## 34 -1.754615187 6.6926100 2 P1_C10.2.cover
## 35 1.323288290 2.5018145 2 P1_C11.2.cover
## 36 1.947532133 0.2111850 2 P1_C12.2.cover
## 37 2.765247062 -6.6289434 1 P1_D01.2.cover
## 38 1.890069002 -2.8121306 2 P1_D02.2.cover
## 39 -2.621614422 -0.4681622 2 P1_D03.2.cover
## 40 1.859462967 2.8269876 2 P1_D04.2.cover
## 41 -2.162372636 2.2923544 2 P1_D05.2.cover
## 42 0.789700931 -5.9769077 2 P1_D06.2.cover
## 43 -0.813057620 -6.2270641 2 P1_D07.2.cover
## 44 0.688899961 -2.7057331 2 P1_D08.2.cover
## 45 -1.299532410 -6.9379705 2 P1_D09.2.cover
## 46 0.599022729 -2.6036229 2 P1_D11.2.cover
## 47 1.797900303 -6.5485186 1 P1_D12.2.cover
## 48 -0.320646172 3.0565131 2 P1_E01.2.cover
## 49 -1.111558461 4.5327546 2 P1_E02.2.cover
## 50 0.854715380 -2.8478152 2 P1_E03.2.cover
## 51 0.599022729 -2.6036229 2 P1_E04.2.cover
## 52 -0.338006653 5.7762591 2 P1_E05.2.cover
## 53 4.311341910 -3.9429290 1 P1_E06.2.cover
## 54 4.526726526 -0.7538916 2 P1_E07.2.cover
## 55 4.865761003 -1.0268600 2 P1_E08.2.cover
## 56 3.597382874 -2.5319809 2 P1_E09.2.cover
## 57 -1.308150440 5.1810599 2 P1_E11.2.cover
## 58 0.863284223 4.8814355 2 P1_E12.2.cover
## 59 -1.006530100 5.5466317 2 P1_F01.2.cover
## 60 3.141676748 -6.4841634 1 P1_F02.2.cover
## 61 1.795794781 -9.1072089 3 P1_F03.2.cover
## 62 0.563255522 -2.5399608 2 P1_F04.2.cover
## 63 -0.056163904 5.6481575 2 P1_F05.2.cover
## 64 -1.389072780 5.1080784 2 P1_F06.2.cover
## 65 0.925757684 4.4894900 2 P1_F07.2.cover
## 66 3.769908747 -3.7954007 1 P1_F08.2.cover
## 67 -1.215468523 5.2520286 2 P1_F09.2.cover
## 68 4.531526866 -0.7067873 2 P1_F10.2.cover
## 69 -1.255071615 4.5983421 2 P1_F11.2.cover
## 70 2.037420041 0.0821602 2 P1_F12.2.cover
## 71 3.968131305 -3.3494962 1 P1_G02.2.cover
## 72 -0.347948225 -8.3738984 3 P1_G03.2.cover
## 73 0.549447213 4.3421509 2 P1_G04.2.cover
## 74 0.751212210 -6.4843162 3 P1_G05.2.cover
## 75 3.267288067 -3.4840352 1 P1_G06.2.cover
## 76 -7.571272298 -1.2803511 2 P1_G07.2.cover
## 77 0.951168239 -1.5347746 2 P1_G08.2.cover
## 78 1.406855043 -8.8355559 3 P1_G09.2.cover
## 79 -1.641001597 4.4388198 2 P1_G10.2.cover
## 80 0.627137759 -6.5477911 3 P1_G11.2.cover
## 81 0.401116174 5.3317578 2 P1_G12.2.cover
## 82 -1.680189184 3.8088080 2 P1_H01.2.cover
## 83 0.009611071 4.5765861 2 P1_H02.2.cover
## 84 4.517078707 -1.7442236 2 P1_H03.2.cover
## 85 0.282804513 4.0629617 2 P1_H04.2.cover
## 86 0.730885544 3.6037739 2 P1_H05.2.cover
## 87 -0.769916005 4.0922723 2 P1_H06.2.cover
## 88 0.782921799 -6.0694511 1 P1_H07.2.cover
## 89 -0.841211762 -7.1821594 2 P1_H08.2.cover
## 90 -0.836597798 4.5839672 2 P1_H09.2.cover
## 91 -2.640185111 -0.4674640 2 P1_H10.2.cover
## 92 -2.638516129 -0.4641206 2 P1_H11.2.cover
## 93 -1.643830100 3.8821907 2 P1_H12.2.cover
## 94 0.395565499 3.4065407 2 P2_A01.2.cover
## 95 -0.274238889 1.5541598 2 P2_A02.2.cover
## 96 -1.443627030 3.6075169 2 P2_A03.2.cover
## 97 1.958488106 0.2131681 2 P2_A04.2.cover
## 98 4.258177623 -3.9274588 1 P2_A05.2.cover
## 99 -0.904909633 3.1199899 2 P2_A07.2.cover
## 100 -2.638439516 -0.4641671 2 P2_A08.2.cover
## 101 -1.067269315 3.9479990 2 P2_A09.2.cover
## 102 -0.531273646 4.0355613 2 P2_A10.2.cover
## 103 -0.466861931 4.0096596 2 P2_A11.2.cover
## 104 -0.928262608 3.1582377 2 P2_A12.2.cover
## 105 1.713819332 -6.8217929 3 P2_B01.2.cover
## 106 -2.633156532 -0.4678006 2 P2_B02.2.cover
## 107 -0.553028293 4.8060244 2 P2_B06.2.cover
## 108 4.696143570 -1.8131258 2 P2_B07.2.cover
## 109 0.424948184 3.3810940 2 P2_B08.2.cover
## 110 0.645120691 -2.6572138 2 P2_B09.2.cover
## 111 -0.180675524 2.9331727 2 P2_B10.2.cover
## 112 -1.405984658 3.4936793 2 P2_B11.2.cover
## 113 -0.290145711 4.2041360 2 P2_B12.2.cover
## 114 0.262470099 4.3386082 2 P2_C02.2.cover
## 115 -7.831665261 -1.0381231 2 P2_C03.2.cover
## 116 1.985013665 -8.8241810 3 P2_C05.2.cover
## 117 -1.510251722 -7.0383614 2 P2_C07.2.cover
## 118 -0.418120283 5.0318927 2 P2_C08.2.cover
## 119 -0.861785800 4.1586807 2 P2_C09.2.cover
## 120 -0.071228167 3.9549265 2 P2_C12.2.cover
## 121 -0.984305143 3.5743174 2 P2_D03.2.cover
## 122 -0.923532813 3.1631168 2 P2_D04.2.cover
## 123 -7.353633241 -1.4551700 2 P2_D05.2.cover
## 124 2.385058560 -2.7933243 1 P2_D06.2.cover
## 125 0.599022729 -2.6036229 2 P2_D07.2.cover
## 126 0.429068346 -4.9558022 2 P2_D08.2.cover
## 127 0.688899961 -2.7057331 2 P2_D09.2.cover
## 128 1.624938010 -5.9992277 1 P2_E01.2.cover
## 129 2.190286469 -0.6455248 2 P2_E02.2.cover
## 130 -1.212810685 3.3163018 2 P2_E03.2.cover
## 131 2.287028719 -8.5256313 3 P2_E05.2.cover
## 132 1.858864847 -7.8871059 3 P2_E06.2.cover
## 133 2.231152193 -2.8305272 1 P2_E09.2.cover
## 134 -0.024322061 3.1997285 2 P2_E11.2.cover
## 135 -0.467146826 3.9896287 2 P2_E12.2.cover
## 136 0.974504623 -3.0736739 2 P2_F02.2.cover
## 137 -0.626300210 4.8431420 2 P2_F03.2.cover
## 138 1.925243845 -8.7449478 3 P2_F04.2.cover
## 139 0.674440278 -5.3289569 1 P2_F05.2.cover
## 140 1.954666864 0.2104642 2 P2_F06.2.cover
## 141 4.922750245 -0.9981700 2 P2_F08.2.cover
## 142 -7.831665261 -1.0381231 2 P2_F09.2.cover
## 143 0.055651882 4.5230883 2 P2_G03.2.cover
## 144 -0.001337382 7.4985241 2 P2_G05.2.cover
## 145 -7.311041041 -1.5349120 2 P2_G06.2.cover
## 146 3.243965434 -7.3871159 1 P2_G09.2.cover
## 147 -2.815071366 5.2049257 2 P2_H01.2.cover
## 148 2.591801727 5.8561331 2 P2_H02.2.cover
## 149 -7.831665261 -1.0381231 2 P2_H04.2.cover
## 150 2.788524043 3.6115980 2 P2_H05.2.cover
## 151 -3.242815073 3.7269274 2 P2_H06.2.cover
## 152 -0.443080587 7.0071192 2 P2_H07.2.cover
## 153 -7.673750469 -1.1956287 2 P2_H08.2.cover
## 154 2.054299503 3.3381049 2 P2_H09.2.cover
## 155 4.188255864 -4.6404490 1 P3_A01.2.cover
## 156 1.097574108 -7.7443875 1 P3_A02.2.cover
## 157 0.582485988 3.6184525 2 P3_A03.2.cover
## 158 1.923555626 -2.8471908 2 P3_A04.2.cover
## 159 1.079120265 7.6590678 2 P3_A05.2.cover
## 160 -2.682481769 3.0396274 2 P3_A06.2.cover
## 161 -0.326614384 5.7443451 2 P3_A07.2.cover
## 162 -0.470047085 5.7329112 2 P3_A08.2.cover
## 163 -1.536276662 4.4757395 2 P3_A09.2.cover
## 164 0.705595980 -6.5146896 1 P3_A10.2.cover
## 165 -1.679072818 4.7114490 2 P3_A11.2.cover
## 166 1.928882681 0.2149269 2 P3_A12.2.cover
## 167 -7.353633241 -1.4551700 2 P3_B01.2.cover
## 168 -0.901134087 3.3552713 2 P3_B02.2.cover
## 169 0.688911167 -2.7057523 2 P3_B03.2.cover
## 170 0.066848246 4.6171414 2 P3_B04.2.cover
## 171 0.346672978 3.3463484 2 P3_B05.2.cover
## 172 0.649171840 3.5112414 2 P3_B06.2.cover
## 173 -0.470191680 2.9650357 2 P3_B07.2.cover
## 174 -0.564388379 3.8795569 2 P3_B08.2.cover
## 175 0.137727727 3.4008502 2 P3_B09.2.cover
## 176 0.731692476 5.0692159 2 P3_B10.2.cover
## 177 -0.035920744 3.1683376 2 P3_B11.2.cover
## 178 -0.299011225 2.9620135 2 P3_B12.2.cover
## 179 3.547737471 -8.0549063 3 P3_C01.2.cover
## 180 1.605601242 -6.5511072 3 P3_C02.2.cover
## 181 0.264852879 3.5809131 2 P3_C03.2.cover
## 182 0.685692394 4.3575913 2 P3_C04.2.cover
## 183 -0.210367888 4.9918243 2 P3_C05.2.cover
## 184 0.688833462 -2.7056786 2 P3_C06.2.cover
## 185 0.109955006 5.1606346 2 P3_C07.2.cover
## 186 0.014605621 5.0865860 2 P3_C08.2.cover
## 187 -1.031198346 4.0944428 2 P3_C09.2.cover
## 188 -0.282669830 4.1308575 2 P3_C10.2.cover
## 189 0.531598230 5.2069516 2 P3_D01.2.cover
## 190 -2.633336417 -0.4525126 2 P3_D02.2.cover
## 191 0.921017769 4.1543390 2 P3_D03.2.cover
## 192 0.936519824 4.1501419 2 P3_D05.2.cover
## 193 -0.515832940 3.4743553 2 P3_D06.2.cover
## 194 -1.455625440 3.6453424 2 P3_D07.2.cover
## 195 0.871357682 4.0372284 2 P3_D08.2.cover
## 196 0.329323287 4.6152519 2 P3_D09.2.cover
## 197 -7.831665261 -1.0381231 2 P3_D11.2.cover
## 198 -0.767422705 4.9075337 2 P3_D12.2.cover
## 199 -1.628579356 4.1166996 2 P3_E02.2.cover
## 200 -0.856592428 -7.3956066 2 P3_E03.2.cover
## 201 2.096626485 -1.5593516 1 P3_E04.2.cover
## 202 -0.409480898 4.9519151 2 P3_E05.2.cover
## 203 0.862031589 4.8505265 2 P3_E06.2.cover
## 204 -1.530643637 4.4260906 2 P3_E07.2.cover
## 205 3.749094680 -3.7561043 1 P3_F01.2.cover
## 206 4.091527824 -4.0699451 1 P3_F04.2.cover
## 207 -1.384804513 5.1243791 2 P3_F05.2.cover
## 208 -1.553696453 4.4819464 2 P3_F08.2.cover
## 209 0.372206663 5.3990392 2 P3_F12.2.cover
## 210 -1.374158898 5.1766933 2 P3_G02.2.cover
## 211 -0.873864903 5.5188804 2 P3_G03.2.cover
## 212 -0.347268689 5.0703958 2 P3_G04.2.cover
## 213 -0.065879072 5.7151065 2 P3_G05.2.cover
## 214 0.363568669 5.4536998 2 P3_G06.2.cover
## 215 -1.050752064 5.5314945 2 P3_H05.2.cover
## 216 2.934752660 -6.3495238 1 P4_A01.2.cover
## 217 2.779643915 -8.5190919 3 P4_A02.2.cover
## 218 -7.353588577 -1.4552001 2 P4_A03.2.cover
## 219 3.475660469 -2.7349111 2 P4_A07.2.cover
## 220 0.481398838 -5.9874971 2 P4_A08.2.cover
## 221 3.261447852 -7.9954863 3 P4_A09.2.cover
## 222 -0.751644788 -7.6434117 2 P4_A10.2.cover
## 223 2.696902202 -7.3736888 1 P4_A11.2.cover
## 224 -1.071825560 5.5494477 2 P4_A12.2.cover
## 225 1.523443813 -8.6422740 3 P4_B01.2.cover
## 226 1.807229060 -6.8760777 3 P4_B02.2.cover
## 227 3.359792972 -7.7880820 3 P4_B03.2.cover
## 228 3.237507800 -0.8532339 1 P4_B05.2.cover
## 229 -3.308167810 6.0443123 2 P4_B06.2.cover
## 230 4.529133141 -0.8119465 2 P4_B07.2.cover
## 231 3.068487552 5.0148975 2 P4_B08.2.cover
## 232 -1.276504671 -6.7962811 2 P4_B09.2.cover
## 233 0.066875519 -7.1589750 3 P4_B11.2.cover
## 234 -3.435611757 3.0014339 2 P4_B12.2.cover
## 235 2.160247581 5.1054682 2 P4_C03.2.cover
## 236 3.218808885 -3.4240702 1 P4_C04.2.cover
## 237 -2.478900770 2.5632862 2 P4_C05.2.cover
## 238 -7.831665261 -1.0381231 2 P4_C06.2.cover
## 239 3.229347993 -0.6244680 2 P4_C07.2.cover
## 240 -7.572952941 -1.2888724 2 P4_C08.2.cover
## 241 0.709854379 6.7656756 2 P4_C10.2.cover
## 242 2.201811407 -8.7351986 3 P4_C11.2.cover
## 243 0.736151315 -8.0357950 3 P4_D01.2.cover
## 244 -0.467769875 5.7811579 2 P4_D02.2.cover
## 245 3.628650525 -3.5623973 1 P4_D03.2.cover
## 246 2.604063891 -5.0100582 1 P4_D04.2.cover
## 247 0.497986405 -2.5039683 2 P4_D05.2.cover
## 248 4.384333615 -1.9646056 2 P4_D06.2.cover
## 249 -1.166713517 -6.9643958 2 P4_D07.2.cover
## 250 2.292279194 -9.2400300 3 P4_D08.2.cover
## 251 1.523576617 6.1050974 2 P4_D09.2.cover
## 252 5.144619343 -1.9097402 1 P4_D11.2.cover
## 253 1.878818948 -2.8360334 2 P4_D12.2.cover
## 254 -3.018590683 6.9117389 2 P4_E01.2.cover
## 255 3.886388645 -4.1104979 1 P4_E02.2.cover
## 256 0.359360272 -8.0283572 3 P4_E03.2.cover
## 257 1.433038767 -7.1440362 3 P4_E04.2.cover
## 258 0.588713831 -6.6319443 3 P4_E05.2.cover
## 259 5.286880485 -1.5161597 2 P4_E06.2.cover
## 260 1.195286101 -8.3403477 3 P4_E07.2.cover
## 261 -6.454246287 -1.4974640 2 P4_E08.2.cover
## 262 4.572338929 -0.8873005 2 P4_E09.2.cover
## 263 -0.607556171 -7.5064632 2 P4_E11.2.cover
## 264 -3.017364549 3.8142714 2 P4_E12.2.cover
## 265 0.412426378 7.1260637 2 P4_F01.2.cover
## 266 2.234044014 -8.6175908 3 P4_F02.2.cover
## 267 3.975856508 -3.1020318 1 P4_F03.2.cover
## 268 -7.758516096 -1.1133699 2 P4_F04.2.cover
## 269 -7.179736795 -1.9521758 2 P4_F05.2.cover
## 270 1.247096828 -6.8129322 3 P4_F06.2.cover
## 271 -0.113909003 -7.7541552 2 P4_F07.2.cover
## 272 2.192815584 -8.7418282 3 P4_F08.2.cover
## 273 1.815132681 -8.9922606 3 P4_F09.2.cover
## 274 -7.673490950 -1.1954763 2 P4_F10.2.cover
## 275 -2.395258493 6.9915644 2 P4_F12.2.cover
## 276 -2.382633033 6.1683224 2 P4_G01.2.cover
## 277 -2.571127253 5.8769224 2 P4_G07.2.cover
## 278 -3.817388578 5.4309519 2 P4_G09.2.cover
## 279 -7.670582044 -1.1956385 2 P4_G11.2.cover
## 280 2.318958141 4.2928427 2 P4_H01.2.cover
## 281 2.318958141 4.2928427 2 P4_H06.2.cover
## 282 -3.864879563 4.3702219 2 P4_H07.2.cover
## 283 -7.758361718 -1.1134740 2 P4_H09.2.cover
## 284 -2.967260483 4.7425440 2 P4_H10.2.cover
## 285 -2.967260483 4.7425440 2 P4_H11.2.cover
## 286 -7.353633241 -1.4551700 2 P4_H12.2.cover