library(gdsfmt)
library(SNPRelate)
## SNPRelate -- supported by Streaming SIMD Extensions 2 (SSE2)
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
Grosmannia clavigera
setwd("/Users/Ryan/Desktop/Missing_Data_Reports")
set.seed(1000)
vcf.fn <- "C:/Users/Ryan/Desktop/Missing_Data_Reports/Gc_HQ.95MissingData.recode.vcf"
snpgdsVCF2GDS(vcf.fn, "Gc_HQ.95MissingData.recode.gds", method="biallelic.only")
## VCF Format ==> SNP GDS Format
## Method: exacting biallelic SNPs
## Number of samples: 243
## Parsing "C:/Users/Ryan/Desktop/Missing_Data_Reports/Gc_HQ.95MissingData.recode.vcf" ...
## import 8116 variants.
## + genotype { Bit2 243x8116, 481.5K } *
## Optimize the access efficiency ...
## Clean up the fragments of GDS file:
## open the file 'Gc_HQ.95MissingData.recode.gds' (523.5K)
## # of fragments: 41
## save to 'Gc_HQ.95MissingData.recode.gds.tmp'
## rename 'Gc_HQ.95MissingData.recode.gds.tmp' (523.3K, reduced: 252B)
## # of fragments: 20
snpgdsSummary("Gc_HQ.95MissingData.recode.gds")
## The file name: C:\Users\Ryan\Desktop\Missing_Data_Reports\Gc_HQ.95MissingData.recode.gds
## The total number of samples: 243
## The total number of SNPs: 8116
## SNP genotypes are stored in SNP-major mode (Sample X SNP).
genofile <- snpgdsOpen("Gc_HQ.95MissingData.recode.gds")
snpset <- snpgdsLDpruning(genofile , ld.threshold = 0.2, autosome.only = FALSE)
## SNP pruning based on LD:
## Excluding 0 SNP (monomorphic: TRUE, MAF: NaN, missing rate: NaN)
## Working space: 243 samples, 8,116 SNPs
## using 1 (CPU) core
## sliding window: 500,000 basepairs, Inf SNPs
## |LD| threshold: 0.2
## method: composite
## Chromosome GCLVSC_067: 33.33%, 1/3
## Chromosome GCLVSC_082: 9.92%, 24/242
## Chromosome GCLVSC_089: 11.26%, 34/302
## Chromosome GCLVSC_097: 11.56%, 75/649
## Chromosome GCLVSC_099: 100.00%, 1/1
## Chromosome GCLVSC_108: 9.02%, 47/521
## Chromosome GCLVSC_113: 8.71%, 85/976
## Chromosome GCLVSC_117: 75.00%, 3/4
## Chromosome GCLVSC_124: 17.65%, 6/34
## Chromosome GCLVSC_132: 8.12%, 28/345
## Chromosome GCLVSC_140: 8.31%, 111/1,335
## Chromosome GCLVSC_142: 16.22%, 12/74
## Chromosome GCLVSC_144: 8.64%, 63/729
## Chromosome GCLVSC_146: 15.05%, 14/93
## Chromosome GCLVSC_156: 7.83%, 34/434
## Chromosome GCLVSC_160: 13.64%, 21/154
## Chromosome GCLVSC_161: 7.17%, 21/293
## Chromosome GCLVSC_162: 66.67%, 2/3
## Chromosome GCLVSC_167: 8.93%, 59/661
## Chromosome GCLVSC_168: 9.55%, 21/220
## Chromosome GCLVSC_173: 10.87%, 69/635
## Chromosome GCLVSC_179: 8.10%, 32/395
## Chromosome GCLVSC_180: 50.00%, 4/8
## Chromosome GCLVSC_200: 100.00%, 1/1
## Chromosome GCLVSC_272: 25.00%, 1/4
## 769 markers are selected in total.
names(snpset)
## [1] "chrGCLVSC_067" "chrGCLVSC_082" "chrGCLVSC_089" "chrGCLVSC_097"
## [5] "chrGCLVSC_099" "chrGCLVSC_108" "chrGCLVSC_113" "chrGCLVSC_117"
## [9] "chrGCLVSC_124" "chrGCLVSC_132" "chrGCLVSC_140" "chrGCLVSC_142"
## [13] "chrGCLVSC_144" "chrGCLVSC_146" "chrGCLVSC_156" "chrGCLVSC_160"
## [17] "chrGCLVSC_161" "chrGCLVSC_162" "chrGCLVSC_167" "chrGCLVSC_168"
## [21] "chrGCLVSC_173" "chrGCLVSC_179" "chrGCLVSC_180" "chrGCLVSC_200"
## [25] "chrGCLVSC_272"
snpset.id <- unlist(snpset)
SampleNames <- read.table(file = "/Users/Ryan/Desktop/Missing_Data_Reports/Gc_HQ_95MissingDataList.txt")
SampleNames <- unlist(SampleNames)
pca <- snpgdsPCA(genofile, snp.id = snpset.id, num.thread = 2, autosome.only = FALSE)
## Principal Component Analysis (PCA) on genotypes:
## Excluding 0 SNP (monomorphic: TRUE, MAF: NaN, missing rate: NaN)
## Working space: 243 samples, 769 SNPs
## using 2 (CPU) cores
## PCA: the sum of all selected genotypes (0,1,2) = 338278
## CPU capabilities: Double-Precision SSE2
## Mon Apr 16 09:43:27 2018 (internal increment: 1464)
##
[..................................................] 0%, ETC: ---
[==================================================] 100%, completed in 0s
## Mon Apr 16 09:43:27 2018 Begin (eigenvalues and eigenvectors)
## Mon Apr 16 09:43:27 2018 Done.
#variance proportion
pc.percent <-pca$varprop*100
head(round(pc.percent, 2))
## [1] 6.92 3.84 2.80 2.21 2.16 2.08
#making a data frame for no prior population information
tab <- data.frame(sample.id = pca$sample.id,
EV1 = pca$eigenvect[,1],
EV2 = pca$eigenvect[,2],
stringsAsFactors = FALSE)
head(tab)
## sample.id EV1
## 1 /mnt/bulleit/arnaud/Plate2_6/ss100_Gc_Plate02_A01.sorted.bam 0.005761784
## 2 /mnt/bulleit/arnaud/Plate2_6/ss139_Gc_Plate02_B01.sorted.bam 0.010247098
## 3 /mnt/bulleit/arnaud/Plate2_6/ss169_Gc_Plate02_D01.sorted.bam 0.006832976
## 4 /mnt/bulleit/arnaud/Plate2_6/ss180_Gc_Plate02_E01.sorted.bam 0.008228574
## 5 /mnt/bulleit/arnaud/Plate2_6/ss205_Gc_Plate02_G01.sorted.bam 0.008302107
## 6 /mnt/bulleit/arnaud/Plate2_6/ss217_Gc_Plate02_A02.sorted.bam 0.007143238
## EV2
## 1 -0.01313856
## 2 -0.02354494
## 3 -0.01265192
## 4 -0.01441839
## 5 -0.01509473
## 6 -0.01173350
#Drawing the pca plot
plot(tab$EV2, tab$EV1, xlab="eigenvector 2", ylab="eigenvector 1")
title(main = "Gc PCA LD Trimmed")
text(x = pca$eigenvect[,2], y = pca$eigenvect[,1], labels = SampleNames, pos = 1 ,cex =0.8, offset = 0.5)
##Describing the Plot
GcLocal <- as_tibble(tab)
GcCluster1 <- filter(GcLocal, EV2 < 0.05 & EV1 > -0.3) %>% arrange(EV2)
GcCluster2 <- filter(GcLocal, EV1 < -0.3) %>% arrange(EV2)
GcCluster3 <- filter(GcLocal, EV2 > 0.05) %>% arrange(EV2)
Leptographium longiclavatum
setwd("/Users/Ryan/Desktop/Missing_Data_Reports")
set.seed(1000)
vcf.fn <- "Ll_HQ.95MissingData.recode.vcf"
snpgdsVCF2GDS(vcf.fn, "Ll_HQ.95MissingData.recode.gds", method="biallelic.only")
## VCF Format ==> SNP GDS Format
## Method: exacting biallelic SNPs
## Number of samples: 165
## Parsing "Ll_HQ.95MissingData.recode.vcf" ...
## import 19301 variants.
## + genotype { Bit2 165x19301, 777.5K } *
## Optimize the access efficiency ...
## Clean up the fragments of GDS file:
## open the file 'Ll_HQ.95MissingData.recode.gds' (863.5K)
## # of fragments: 42
## save to 'Ll_HQ.95MissingData.recode.gds.tmp'
## rename 'Ll_HQ.95MissingData.recode.gds.tmp' (863.2K, reduced: 264B)
## # of fragments: 20
snpgdsSummary("Ll_HQ.95MissingData.recode.gds")
## The file name: C:\Users\Ryan\Desktop\Missing_Data_Reports\Ll_HQ.95MissingData.recode.gds
## The total number of samples: 165
## The total number of SNPs: 19301
## SNP genotypes are stored in SNP-major mode (Sample X SNP).
SampleNames <-
genofile <- snpgdsOpen("Ll_HQ.95MissingData.recode.gds")
SampleNames <- read.table(file = "/Users/Ryan/Desktop/Missing_Data_Reports/Ll_HQ_95MissingDataList.txt")
SampleNames <- unlist(SampleNames)
#next ld-based snp pruning to avoid strong clusters
snpset <- snpgdsLDpruning(genofile , ld.threshold = 0.2, autosome.only = FALSE)
## SNP pruning based on LD:
## Excluding 0 SNP (monomorphic: TRUE, MAF: NaN, missing rate: NaN)
## Working space: 165 samples, 19,301 SNPs
## using 1 (CPU) core
## sliding window: 500,000 basepairs, Inf SNPs
## |LD| threshold: 0.2
## method: composite
## Chromosome lepto_001: 3.02%, 12/397
## Chromosome lepto_002: 5.53%, 14/253
## Chromosome lepto_003: 4.92%, 12/244
## Chromosome lepto_004: 7.06%, 12/170
## Chromosome lepto_005: 5.59%, 8/143
## Chromosome lepto_006: 6.70%, 12/179
## Chromosome lepto_007: 3.06%, 6/196
## Chromosome lepto_008: 6.70%, 12/179
## Chromosome lepto_009: 5.49%, 10/182
## Chromosome lepto_010: 4.95%, 11/222
## Chromosome lepto_011: 6.29%, 10/159
## Chromosome lepto_012: 5.26%, 10/190
## Chromosome lepto_013: 7.14%, 12/168
## Chromosome lepto_014: 6.42%, 7/109
## Chromosome lepto_015: 7.36%, 12/163
## Chromosome lepto_016: 8.40%, 10/119
## Chromosome lepto_017: 7.14%, 11/154
## Chromosome lepto_018: 6.61%, 8/121
## Chromosome lepto_019: 9.35%, 13/139
## Chromosome lepto_020: 5.06%, 9/178
## Chromosome lepto_021: 7.21%, 8/111
## Chromosome lepto_022: 8.70%, 12/138
## Chromosome lepto_023: 9.85%, 13/132
## Chromosome lepto_024: 5.33%, 9/169
## Chromosome lepto_025: 9.91%, 11/111
## Chromosome lepto_026: 6.72%, 8/119
## Chromosome lepto_027: 10.38%, 11/106
## Chromosome lepto_028: 5.23%, 8/153
## Chromosome lepto_029: 7.63%, 9/118
## Chromosome lepto_030: 5.19%, 7/135
## Chromosome lepto_031: 10.43%, 12/115
## Chromosome lepto_032: 7.03%, 9/128
## Chromosome lepto_033: 11.94%, 8/67
## Chromosome lepto_034: 8.18%, 9/110
## Chromosome lepto_035: 7.77%, 8/103
## Chromosome lepto_036: 8.18%, 9/110
## Chromosome lepto_037: 9.47%, 9/95
## Chromosome lepto_038: 10.24%, 17/166
## Chromosome lepto_039: 10.17%, 12/118
## Chromosome lepto_040: 9.88%, 8/81
## Chromosome lepto_041: 14.12%, 12/85
## Chromosome lepto_042: 7.19%, 10/139
## Chromosome lepto_043: 12.33%, 9/73
## Chromosome lepto_044: 7.37%, 7/95
## Chromosome lepto_045: 8.54%, 7/82
## Chromosome lepto_046: 8.92%, 14/157
## Chromosome lepto_047: 8.57%, 9/105
## Chromosome lepto_048: 3.88%, 5/129
## Chromosome lepto_049: 7.63%, 10/131
## Chromosome lepto_050: 20.83%, 5/24
## Chromosome lepto_051: 5.49%, 5/91
## Chromosome lepto_052: 6.35%, 8/126
## Chromosome lepto_053: 8.82%, 9/102
## Chromosome lepto_054: 5.45%, 6/110
## Chromosome lepto_055: 3.70%, 4/108
## Chromosome lepto_056: 12.00%, 9/75
## Chromosome lepto_057: 9.72%, 7/72
## Chromosome lepto_058: 9.52%, 8/84
## Chromosome lepto_059: 9.46%, 7/74
## Chromosome lepto_060: 13.85%, 9/65
## Chromosome lepto_061: 12.86%, 9/70
## Chromosome lepto_062: 4.76%, 4/84
## Chromosome lepto_063: 7.41%, 6/81
## Chromosome lepto_064: 7.48%, 8/107
## Chromosome lepto_065: 7.79%, 6/77
## Chromosome lepto_066: 5.50%, 6/109
## Chromosome lepto_067: 12.12%, 8/66
## Chromosome lepto_068: 9.30%, 12/129
## Chromosome lepto_069: 6.67%, 6/90
## Chromosome lepto_070: 9.47%, 9/95
## Chromosome lepto_071: 8.33%, 8/96
## Chromosome lepto_072: 17.50%, 7/40
## Chromosome lepto_073: 10.61%, 7/66
## Chromosome lepto_074: 8.62%, 5/58
## Chromosome lepto_075: 6.25%, 4/64
## Chromosome lepto_076: 8.11%, 6/74
## Chromosome lepto_077: 6.94%, 5/72
## Chromosome lepto_078: 7.29%, 7/96
## Chromosome lepto_079: 6.52%, 6/92
## Chromosome lepto_080: 12.12%, 12/99
## Chromosome lepto_081: 13.11%, 16/122
## Chromosome lepto_082: 7.50%, 6/80
## Chromosome lepto_083: 12.90%, 4/31
## Chromosome lepto_084: 9.52%, 4/42
## Chromosome lepto_085: 5.71%, 4/70
## Chromosome lepto_086: 8.47%, 5/59
## Chromosome lepto_087: 11.11%, 8/72
## Chromosome lepto_088: 7.69%, 8/104
## Chromosome lepto_089: 8.24%, 7/85
## Chromosome lepto_090: 8.64%, 7/81
## Chromosome lepto_091: 11.46%, 11/96
## Chromosome lepto_092: 7.14%, 5/70
## Chromosome lepto_093: 7.35%, 5/68
## Chromosome lepto_094: 10.00%, 9/90
## Chromosome lepto_095: 4.39%, 5/114
## Chromosome lepto_096: 14.06%, 9/64
## Chromosome lepto_097: 9.33%, 7/75
## Chromosome lepto_098: 12.77%, 6/47
## Chromosome lepto_099: 13.21%, 7/53
## Chromosome lepto_100: 9.09%, 10/110
## Chromosome lepto_101: 14.00%, 7/50
## Chromosome lepto_102: 10.14%, 7/69
## Chromosome lepto_103: 15.07%, 11/73
## Chromosome lepto_104: 10.67%, 8/75
## Chromosome lepto_105: 8.11%, 6/74
## Chromosome lepto_106: 14.58%, 7/48
## Chromosome lepto_107: 16.36%, 9/55
## Chromosome lepto_108: 13.73%, 7/51
## Chromosome lepto_109: 10.71%, 9/84
## Chromosome lepto_110: 14.29%, 6/42
## Chromosome lepto_111: 8.33%, 7/84
## Chromosome lepto_112: 9.52%, 4/42
## Chromosome lepto_113: 5.68%, 5/88
## Chromosome lepto_114: 12.12%, 4/33
## Chromosome lepto_115: 5.26%, 6/114
## Chromosome lepto_116: 8.11%, 6/74
## Chromosome lepto_117: 19.05%, 8/42
## Chromosome lepto_118: 11.11%, 9/81
## Chromosome lepto_119: 21.74%, 5/23
## Chromosome lepto_120: 13.56%, 8/59
## Chromosome lepto_121: 7.46%, 5/67
## Chromosome lepto_122: 7.32%, 3/41
## Chromosome lepto_123: 12.50%, 6/48
## Chromosome lepto_124: 17.02%, 8/47
## Chromosome lepto_125: 11.63%, 5/43
## Chromosome lepto_126: 17.24%, 10/58
## Chromosome lepto_127: 14.63%, 6/41
## Chromosome lepto_128: 11.86%, 7/59
## Chromosome lepto_129: 5.26%, 3/57
## Chromosome lepto_130: 18.92%, 7/37
## Chromosome lepto_131: 17.07%, 7/41
## Chromosome lepto_132: 9.09%, 4/44
## Chromosome lepto_133: 8.70%, 8/92
## Chromosome lepto_134: 7.50%, 3/40
## Chromosome lepto_135: 17.65%, 3/17
## Chromosome lepto_136: 8.16%, 4/49
## Chromosome lepto_137: 10.17%, 6/59
## Chromosome lepto_138: 16.98%, 9/53
## Chromosome lepto_139: 10.00%, 2/20
## Chromosome lepto_140: 6.12%, 3/49
## Chromosome lepto_141: 29.41%, 5/17
## Chromosome lepto_142: 12.90%, 4/31
## Chromosome lepto_143: 8.89%, 4/45
## Chromosome lepto_144: 6.10%, 5/82
## Chromosome lepto_145: 11.90%, 5/42
## Chromosome lepto_146: 11.11%, 5/45
## Chromosome lepto_147: 9.80%, 5/51
## Chromosome lepto_148: 7.27%, 4/55
## Chromosome lepto_149: 11.90%, 5/42
## Chromosome lepto_150: 22.22%, 2/9
## Chromosome lepto_151: 14.29%, 6/42
## Chromosome lepto_152: 11.29%, 7/62
## Chromosome lepto_153: 15.62%, 5/32
## Chromosome lepto_154: 9.84%, 6/61
## Chromosome lepto_155: 9.09%, 4/44
## Chromosome lepto_156: 23.33%, 7/30
## Chromosome lepto_157: 11.90%, 5/42
## Chromosome lepto_158: 10.71%, 6/56
## Chromosome lepto_159: 12.50%, 4/32
## Chromosome lepto_160: 8.62%, 5/58
## Chromosome lepto_161: 10.26%, 4/39
## Chromosome lepto_162: 17.14%, 6/35
## Chromosome lepto_163: 22.22%, 8/36
## Chromosome lepto_164: 11.54%, 6/52
## Chromosome lepto_165: 9.26%, 5/54
## Chromosome lepto_166: 17.86%, 5/28
## Chromosome lepto_167: 12.82%, 5/39
## Chromosome lepto_168: 17.24%, 5/29
## Chromosome lepto_169: 18.37%, 9/49
## Chromosome lepto_170: 17.14%, 6/35
## Chromosome lepto_171: 13.85%, 9/65
## Chromosome lepto_172: 23.81%, 5/21
## Chromosome lepto_173: 15.79%, 6/38
## Chromosome lepto_174: 7.41%, 2/27
## Chromosome lepto_175: 6.98%, 3/43
## Chromosome lepto_176: 10.20%, 5/49
## Chromosome lepto_177: 13.04%, 3/23
## Chromosome lepto_178: 16.67%, 4/24
## Chromosome lepto_179: 20.00%, 6/30
## Chromosome lepto_180: 11.43%, 4/35
## Chromosome lepto_182: 5.13%, 2/39
## Chromosome lepto_183: 9.33%, 7/75
## Chromosome lepto_184: 14.81%, 4/27
## Chromosome lepto_185: 50.00%, 2/4
## Chromosome lepto_186: 7.69%, 3/39
## Chromosome lepto_187: 28.57%, 6/21
## Chromosome lepto_188: 9.76%, 4/41
## Chromosome lepto_189: 14.71%, 5/34
## Chromosome lepto_190: 26.67%, 4/15
## Chromosome lepto_191: 25.00%, 4/16
## Chromosome lepto_192: 30.00%, 9/30
## Chromosome lepto_193: 23.33%, 7/30
## Chromosome lepto_194: 22.22%, 4/18
## Chromosome lepto_195: 7.14%, 5/70
## Chromosome lepto_196: 8.33%, 1/12
## Chromosome lepto_197: 9.09%, 1/11
## Chromosome lepto_198: 9.09%, 3/33
## Chromosome lepto_199: 14.29%, 5/35
## Chromosome lepto_200: 12.12%, 4/33
## Chromosome lepto_201: 10.26%, 4/39
## Chromosome lepto_203: 9.68%, 3/31
## Chromosome lepto_204: 6.45%, 4/62
## Chromosome lepto_205: 11.29%, 7/62
## Chromosome lepto_206: 23.53%, 4/17
## Chromosome lepto_207: 16.00%, 4/25
## Chromosome lepto_208: 25.00%, 4/16
## Chromosome lepto_209: 11.54%, 3/26
## Chromosome lepto_210: 8.16%, 4/49
## Chromosome lepto_211: 8.70%, 2/23
## Chromosome lepto_212: 25.00%, 9/36
## Chromosome lepto_213: 25.00%, 5/20
## Chromosome lepto_214: 10.53%, 4/38
## Chromosome lepto_215: 11.11%, 1/9
## Chromosome lepto_216: 8.70%, 4/46
## Chromosome lepto_217: 14.63%, 6/41
## Chromosome lepto_218: 13.64%, 3/22
## Chromosome lepto_219: 22.58%, 7/31
## Chromosome lepto_220: 16.67%, 3/18
## Chromosome lepto_221: 16.67%, 4/24
## Chromosome lepto_222: 16.67%, 5/30
## Chromosome lepto_223: 14.29%, 1/7
## Chromosome lepto_224: 16.67%, 4/24
## Chromosome lepto_225: 10.00%, 1/10
## Chromosome lepto_226: 9.76%, 4/41
## Chromosome lepto_227: 13.16%, 5/38
## Chromosome lepto_228: 18.75%, 6/32
## Chromosome lepto_229: 15.91%, 7/44
## Chromosome lepto_230: 21.74%, 5/23
## Chromosome lepto_231: 5.88%, 1/17
## Chromosome lepto_232: 11.90%, 5/42
## Chromosome lepto_233: 14.29%, 3/21
## Chromosome lepto_234: 25.00%, 1/4
## Chromosome lepto_235: 15.79%, 3/19
## Chromosome lepto_236: 14.29%, 6/42
## Chromosome lepto_237: 28.57%, 2/7
## Chromosome lepto_238: 8.33%, 3/36
## Chromosome lepto_239: 12.90%, 4/31
## Chromosome lepto_240: 20.00%, 10/50
## Chromosome lepto_241: 8.33%, 7/84
## Chromosome lepto_242: 6.45%, 2/31
## Chromosome lepto_243: 13.04%, 3/23
## Chromosome lepto_244: 20.69%, 6/29
## Chromosome lepto_245: 31.82%, 7/22
## Chromosome lepto_246: 33.33%, 1/3
## Chromosome lepto_247: 15.79%, 3/19
## Chromosome lepto_248: 18.18%, 2/11
## Chromosome lepto_249: 13.04%, 3/23
## Chromosome lepto_250: 17.65%, 3/17
## Chromosome lepto_251: 9.68%, 3/31
## Chromosome lepto_252: 9.09%, 1/11
## Chromosome lepto_253: 8.00%, 2/25
## Chromosome lepto_254: 16.00%, 4/25
## Chromosome lepto_255: 11.76%, 2/17
## Chromosome lepto_256: 20.00%, 3/15
## Chromosome lepto_257: 9.38%, 6/64
## Chromosome lepto_258: 45.45%, 5/11
## Chromosome lepto_259: 14.29%, 5/35
## Chromosome lepto_260: 15.38%, 2/13
## Chromosome lepto_262: 37.50%, 3/8
## Chromosome lepto_263: 11.11%, 3/27
## Chromosome lepto_264: 18.52%, 5/27
## Chromosome lepto_265: 20.83%, 5/24
## Chromosome lepto_266: 29.41%, 5/17
## Chromosome lepto_267: 28.57%, 4/14
## Chromosome lepto_268: 66.67%, 2/3
## Chromosome lepto_269: 12.50%, 2/16
## Chromosome lepto_270: 14.71%, 5/34
## Chromosome lepto_273: 40.00%, 2/5
## Chromosome lepto_274: 35.71%, 5/14
## Chromosome lepto_275: 20.00%, 1/5
## Chromosome lepto_276: 20.00%, 1/5
## Chromosome lepto_277: 14.29%, 4/28
## Chromosome lepto_278: 17.65%, 3/17
## Chromosome lepto_279: 6.45%, 2/31
## Chromosome lepto_280: 25.00%, 1/4
## Chromosome lepto_281: 9.09%, 1/11
## Chromosome lepto_282: 11.76%, 4/34
## Chromosome lepto_283: 3.57%, 1/28
## Chromosome lepto_284: 3.12%, 1/32
## Chromosome lepto_285: 21.05%, 4/19
## Chromosome lepto_286: 19.05%, 4/21
## Chromosome lepto_287: 18.18%, 2/11
## Chromosome lepto_288: 10.00%, 2/20
## Chromosome lepto_289: 37.50%, 3/8
## Chromosome lepto_290: 100.00%, 2/2
## Chromosome lepto_291: 20.00%, 4/20
## Chromosome lepto_292: 20.83%, 5/24
## Chromosome lepto_293: 20.00%, 2/10
## Chromosome lepto_294: 10.53%, 2/19
## Chromosome lepto_295: 16.67%, 1/6
## Chromosome lepto_296: 50.00%, 4/8
## Chromosome lepto_297: 10.53%, 2/19
## Chromosome lepto_298: 40.00%, 2/5
## Chromosome lepto_299: 18.75%, 3/16
## Chromosome lepto_300: 12.50%, 2/16
## Chromosome lepto_301: 28.57%, 2/7
## Chromosome lepto_302: 33.33%, 4/12
## Chromosome lepto_304: 21.43%, 3/14
## Chromosome lepto_306: 33.33%, 2/6
## Chromosome lepto_307: 36.36%, 4/11
## Chromosome lepto_308: 33.33%, 2/6
## Chromosome lepto_310: 18.75%, 3/16
## Chromosome lepto_311: 9.09%, 1/11
## Chromosome lepto_313: 30.77%, 4/13
## Chromosome lepto_315: 66.67%, 2/3
## Chromosome lepto_316: 16.00%, 4/25
## Chromosome lepto_317: 33.33%, 2/6
## Chromosome lepto_318: 20.00%, 2/10
## Chromosome lepto_319: 42.86%, 3/7
## Chromosome lepto_320: 24.00%, 6/25
## Chromosome lepto_321: 12.50%, 1/8
## Chromosome lepto_322: 28.57%, 2/7
## Chromosome lepto_323: 33.33%, 3/9
## Chromosome lepto_324: 12.50%, 1/8
## Chromosome lepto_325: 6.67%, 1/15
## Chromosome lepto_326: 16.67%, 1/6
## Chromosome lepto_327: 17.65%, 3/17
## Chromosome lepto_328: 30.00%, 3/10
## Chromosome lepto_329: 22.22%, 2/9
## Chromosome lepto_330: 11.76%, 2/17
## Chromosome lepto_331: 18.75%, 3/16
## Chromosome lepto_332: 50.00%, 2/4
## Chromosome lepto_333: 11.76%, 4/34
## Chromosome lepto_334: 4.35%, 1/23
## Chromosome lepto_335: 16.67%, 3/18
## Chromosome lepto_336: 4.00%, 1/25
## Chromosome lepto_337: 30.77%, 4/13
## Chromosome lepto_338: 20.00%, 2/10
## Chromosome lepto_340: 14.29%, 1/7
## Chromosome lepto_342: 50.00%, 2/4
## Chromosome lepto_343: 22.22%, 2/9
## Chromosome lepto_344: 100.00%, 1/1
## Chromosome lepto_345: 28.57%, 2/7
## Chromosome lepto_346: 14.81%, 4/27
## Chromosome lepto_347: 60.00%, 3/5
## Chromosome lepto_348: 15.38%, 2/13
## Chromosome lepto_349: 37.50%, 3/8
## Chromosome lepto_350: 9.38%, 3/32
## Chromosome lepto_351: 16.67%, 3/18
## Chromosome lepto_353: 28.57%, 4/14
## Chromosome lepto_354: 44.44%, 4/9
## Chromosome lepto_355: 66.67%, 2/3
## Chromosome lepto_356: 37.50%, 3/8
## Chromosome lepto_358: 25.00%, 4/16
## Chromosome lepto_359: 14.29%, 1/7
## Chromosome lepto_361: 28.57%, 2/7
## Chromosome lepto_362: 33.33%, 3/9
## Chromosome lepto_363: 33.33%, 2/6
## Chromosome lepto_365: 25.00%, 3/12
## Chromosome lepto_367: 33.33%, 3/9
## Chromosome lepto_368: 29.41%, 5/17
## Chromosome lepto_369: 28.57%, 2/7
## Chromosome lepto_370: 37.50%, 6/16
## Chromosome lepto_373: 33.33%, 2/6
## Chromosome lepto_374: 100.00%, 1/1
## Chromosome lepto_375: 33.33%, 3/9
## Chromosome lepto_376: 40.00%, 2/5
## Chromosome lepto_377: 17.65%, 3/17
## Chromosome lepto_378: 100.00%, 1/1
## Chromosome lepto_379: 50.00%, 1/2
## Chromosome lepto_381: 50.00%, 1/2
## Chromosome lepto_382: 22.22%, 2/9
## Chromosome lepto_383: 5.00%, 1/20
## Chromosome lepto_384: 15.38%, 2/13
## Chromosome lepto_385: 100.00%, 1/1
## Chromosome lepto_386: 20.83%, 5/24
## Chromosome lepto_387: 14.29%, 1/7
## Chromosome lepto_388: 10.53%, 2/19
## Chromosome lepto_389: 66.67%, 2/3
## Chromosome lepto_390: 25.00%, 1/4
## Chromosome lepto_392: 18.18%, 2/11
## Chromosome lepto_393: 25.00%, 2/8
## Chromosome lepto_394: 25.00%, 2/8
## Chromosome lepto_395: 20.00%, 1/5
## Chromosome lepto_396: 9.09%, 2/22
## Chromosome lepto_397: 100.00%, 2/2
## Chromosome lepto_398: 33.33%, 1/3
## Chromosome lepto_400: 50.00%, 2/4
## Chromosome lepto_401: 22.22%, 2/9
## Chromosome lepto_402: 50.00%, 1/2
## Chromosome lepto_405: 60.00%, 3/5
## Chromosome lepto_406: 30.00%, 3/10
## Chromosome lepto_407: 100.00%, 1/1
## Chromosome lepto_408: 50.00%, 1/2
## Chromosome lepto_410: 50.00%, 1/2
## Chromosome lepto_411: 18.18%, 2/11
## Chromosome lepto_413: 20.00%, 5/25
## Chromosome lepto_414: 20.00%, 1/5
## Chromosome lepto_415: 18.18%, 2/11
## Chromosome lepto_416: 33.33%, 1/3
## Chromosome lepto_417: 100.00%, 2/2
## Chromosome lepto_418: 12.24%, 6/49
## Chromosome lepto_419: 60.00%, 3/5
## Chromosome lepto_420: 40.00%, 2/5
## Chromosome lepto_422: 12.50%, 1/8
## Chromosome lepto_423: 100.00%, 1/1
## Chromosome lepto_425: 75.00%, 3/4
## Chromosome lepto_426: 14.29%, 1/7
## Chromosome lepto_427: 50.00%, 1/2
## Chromosome lepto_431: 57.14%, 4/7
## Chromosome lepto_432: 50.00%, 1/2
## Chromosome lepto_433: 28.57%, 2/7
## Chromosome lepto_434: 50.00%, 3/6
## Chromosome lepto_435: 100.00%, 1/1
## Chromosome lepto_436: 50.00%, 2/4
## Chromosome lepto_437: 20.00%, 4/20
## Chromosome lepto_441: 66.67%, 2/3
## Chromosome lepto_442: 50.00%, 2/4
## Chromosome lepto_443: 40.00%, 2/5
## Chromosome lepto_444: 20.00%, 1/5
## Chromosome lepto_445: 100.00%, 2/2
## Chromosome lepto_448: 100.00%, 1/1
## Chromosome lepto_452: 57.14%, 4/7
## Chromosome lepto_453: 33.33%, 1/3
## Chromosome lepto_454: 33.33%, 2/6
## Chromosome lepto_456: 50.00%, 1/2
## Chromosome lepto_458: 33.33%, 1/3
## Chromosome lepto_459: 16.67%, 1/6
## Chromosome lepto_460: 20.00%, 1/5
## Chromosome lepto_461: 100.00%, 2/2
## Chromosome lepto_462: 8.33%, 2/24
## Chromosome lepto_463: 33.33%, 1/3
## Chromosome lepto_466: 25.00%, 1/4
## Chromosome lepto_467: 22.22%, 2/9
## Chromosome lepto_468: 33.33%, 1/3
## Chromosome lepto_469: 66.67%, 2/3
## Chromosome lepto_471: 16.67%, 1/6
## Chromosome lepto_477: 80.00%, 4/5
## Chromosome lepto_481: 16.00%, 4/25
## Chromosome lepto_482: 42.86%, 3/7
## Chromosome lepto_483: 31.25%, 5/16
## Chromosome lepto_485: 16.67%, 1/6
## Chromosome lepto_487: 100.00%, 2/2
## Chromosome lepto_490: 12.50%, 2/16
## Chromosome lepto_492: 100.00%, 1/1
## Chromosome lepto_494: 50.00%, 1/2
## Chromosome lepto_501: 100.00%, 1/1
## Chromosome lepto_502: 12.50%, 1/8
## Chromosome lepto_505: 100.00%, 1/1
## Chromosome lepto_511: 75.00%, 3/4
## Chromosome lepto_512: 31.25%, 5/16
## Chromosome lepto_513: 100.00%, 1/1
## Chromosome lepto_516: 33.33%, 1/3
## Chromosome lepto_517: 100.00%, 1/1
## Chromosome lepto_526: 33.33%, 3/9
## Chromosome lepto_527: 100.00%, 1/1
## Chromosome lepto_538: 40.00%, 2/5
## Chromosome lepto_540: 100.00%, 1/1
## Chromosome lepto_541: 14.29%, 1/7
## Chromosome lepto_544: 25.00%, 1/4
## Chromosome lepto_551: 100.00%, 2/2
## Chromosome lepto_562: 100.00%, 1/1
## Chromosome lepto_563: 100.00%, 2/2
## Chromosome lepto_572: 100.00%, 1/1
## Chromosome lepto_576: 33.33%, 1/3
## Chromosome lepto_596: 100.00%, 2/2
## Chromosome lepto_598: 16.67%, 2/12
## Chromosome lepto_599: 18.75%, 3/16
## Chromosome lepto_600: 50.00%, 1/2
## Chromosome lepto_617: 100.00%, 1/1
## Chromosome lepto_628: 25.00%, 1/4
## Chromosome lepto_644: 100.00%, 1/1
## Chromosome lepto_645: 100.00%, 1/1
## Chromosome lepto_648: 66.67%, 2/3
## Chromosome lepto_649: 100.00%, 1/1
## Chromosome lepto_659: 50.00%, 1/2
## Chromosome lepto_705: 100.00%, 2/2
## Chromosome lepto_708: 100.00%, 1/1
## Chromosome lepto_760: 50.00%, 1/2
## 2,084 markers are selected in total.
names(snpset)
## [1] "chrlepto_001" "chrlepto_002" "chrlepto_003" "chrlepto_004"
## [5] "chrlepto_005" "chrlepto_006" "chrlepto_007" "chrlepto_008"
## [9] "chrlepto_009" "chrlepto_010" "chrlepto_011" "chrlepto_012"
## [13] "chrlepto_013" "chrlepto_014" "chrlepto_015" "chrlepto_016"
## [17] "chrlepto_017" "chrlepto_018" "chrlepto_019" "chrlepto_020"
## [21] "chrlepto_021" "chrlepto_022" "chrlepto_023" "chrlepto_024"
## [25] "chrlepto_025" "chrlepto_026" "chrlepto_027" "chrlepto_028"
## [29] "chrlepto_029" "chrlepto_030" "chrlepto_031" "chrlepto_032"
## [33] "chrlepto_033" "chrlepto_034" "chrlepto_035" "chrlepto_036"
## [37] "chrlepto_037" "chrlepto_038" "chrlepto_039" "chrlepto_040"
## [41] "chrlepto_041" "chrlepto_042" "chrlepto_043" "chrlepto_044"
## [45] "chrlepto_045" "chrlepto_046" "chrlepto_047" "chrlepto_048"
## [49] "chrlepto_049" "chrlepto_050" "chrlepto_051" "chrlepto_052"
## [53] "chrlepto_053" "chrlepto_054" "chrlepto_055" "chrlepto_056"
## [57] "chrlepto_057" "chrlepto_058" "chrlepto_059" "chrlepto_060"
## [61] "chrlepto_061" "chrlepto_062" "chrlepto_063" "chrlepto_064"
## [65] "chrlepto_065" "chrlepto_066" "chrlepto_067" "chrlepto_068"
## [69] "chrlepto_069" "chrlepto_070" "chrlepto_071" "chrlepto_072"
## [73] "chrlepto_073" "chrlepto_074" "chrlepto_075" "chrlepto_076"
## [77] "chrlepto_077" "chrlepto_078" "chrlepto_079" "chrlepto_080"
## [81] "chrlepto_081" "chrlepto_082" "chrlepto_083" "chrlepto_084"
## [85] "chrlepto_085" "chrlepto_086" "chrlepto_087" "chrlepto_088"
## [89] "chrlepto_089" "chrlepto_090" "chrlepto_091" "chrlepto_092"
## [93] "chrlepto_093" "chrlepto_094" "chrlepto_095" "chrlepto_096"
## [97] "chrlepto_097" "chrlepto_098" "chrlepto_099" "chrlepto_100"
## [101] "chrlepto_101" "chrlepto_102" "chrlepto_103" "chrlepto_104"
## [105] "chrlepto_105" "chrlepto_106" "chrlepto_107" "chrlepto_108"
## [109] "chrlepto_109" "chrlepto_110" "chrlepto_111" "chrlepto_112"
## [113] "chrlepto_113" "chrlepto_114" "chrlepto_115" "chrlepto_116"
## [117] "chrlepto_117" "chrlepto_118" "chrlepto_119" "chrlepto_120"
## [121] "chrlepto_121" "chrlepto_122" "chrlepto_123" "chrlepto_124"
## [125] "chrlepto_125" "chrlepto_126" "chrlepto_127" "chrlepto_128"
## [129] "chrlepto_129" "chrlepto_130" "chrlepto_131" "chrlepto_132"
## [133] "chrlepto_133" "chrlepto_134" "chrlepto_135" "chrlepto_136"
## [137] "chrlepto_137" "chrlepto_138" "chrlepto_139" "chrlepto_140"
## [141] "chrlepto_141" "chrlepto_142" "chrlepto_143" "chrlepto_144"
## [145] "chrlepto_145" "chrlepto_146" "chrlepto_147" "chrlepto_148"
## [149] "chrlepto_149" "chrlepto_150" "chrlepto_151" "chrlepto_152"
## [153] "chrlepto_153" "chrlepto_154" "chrlepto_155" "chrlepto_156"
## [157] "chrlepto_157" "chrlepto_158" "chrlepto_159" "chrlepto_160"
## [161] "chrlepto_161" "chrlepto_162" "chrlepto_163" "chrlepto_164"
## [165] "chrlepto_165" "chrlepto_166" "chrlepto_167" "chrlepto_168"
## [169] "chrlepto_169" "chrlepto_170" "chrlepto_171" "chrlepto_172"
## [173] "chrlepto_173" "chrlepto_174" "chrlepto_175" "chrlepto_176"
## [177] "chrlepto_177" "chrlepto_178" "chrlepto_179" "chrlepto_180"
## [181] "chrlepto_182" "chrlepto_183" "chrlepto_184" "chrlepto_185"
## [185] "chrlepto_186" "chrlepto_187" "chrlepto_188" "chrlepto_189"
## [189] "chrlepto_190" "chrlepto_191" "chrlepto_192" "chrlepto_193"
## [193] "chrlepto_194" "chrlepto_195" "chrlepto_196" "chrlepto_197"
## [197] "chrlepto_198" "chrlepto_199" "chrlepto_200" "chrlepto_201"
## [201] "chrlepto_203" "chrlepto_204" "chrlepto_205" "chrlepto_206"
## [205] "chrlepto_207" "chrlepto_208" "chrlepto_209" "chrlepto_210"
## [209] "chrlepto_211" "chrlepto_212" "chrlepto_213" "chrlepto_214"
## [213] "chrlepto_215" "chrlepto_216" "chrlepto_217" "chrlepto_218"
## [217] "chrlepto_219" "chrlepto_220" "chrlepto_221" "chrlepto_222"
## [221] "chrlepto_223" "chrlepto_224" "chrlepto_225" "chrlepto_226"
## [225] "chrlepto_227" "chrlepto_228" "chrlepto_229" "chrlepto_230"
## [229] "chrlepto_231" "chrlepto_232" "chrlepto_233" "chrlepto_234"
## [233] "chrlepto_235" "chrlepto_236" "chrlepto_237" "chrlepto_238"
## [237] "chrlepto_239" "chrlepto_240" "chrlepto_241" "chrlepto_242"
## [241] "chrlepto_243" "chrlepto_244" "chrlepto_245" "chrlepto_246"
## [245] "chrlepto_247" "chrlepto_248" "chrlepto_249" "chrlepto_250"
## [249] "chrlepto_251" "chrlepto_252" "chrlepto_253" "chrlepto_254"
## [253] "chrlepto_255" "chrlepto_256" "chrlepto_257" "chrlepto_258"
## [257] "chrlepto_259" "chrlepto_260" "chrlepto_262" "chrlepto_263"
## [261] "chrlepto_264" "chrlepto_265" "chrlepto_266" "chrlepto_267"
## [265] "chrlepto_268" "chrlepto_269" "chrlepto_270" "chrlepto_273"
## [269] "chrlepto_274" "chrlepto_275" "chrlepto_276" "chrlepto_277"
## [273] "chrlepto_278" "chrlepto_279" "chrlepto_280" "chrlepto_281"
## [277] "chrlepto_282" "chrlepto_283" "chrlepto_284" "chrlepto_285"
## [281] "chrlepto_286" "chrlepto_287" "chrlepto_288" "chrlepto_289"
## [285] "chrlepto_290" "chrlepto_291" "chrlepto_292" "chrlepto_293"
## [289] "chrlepto_294" "chrlepto_295" "chrlepto_296" "chrlepto_297"
## [293] "chrlepto_298" "chrlepto_299" "chrlepto_300" "chrlepto_301"
## [297] "chrlepto_302" "chrlepto_304" "chrlepto_306" "chrlepto_307"
## [301] "chrlepto_308" "chrlepto_310" "chrlepto_311" "chrlepto_313"
## [305] "chrlepto_315" "chrlepto_316" "chrlepto_317" "chrlepto_318"
## [309] "chrlepto_319" "chrlepto_320" "chrlepto_321" "chrlepto_322"
## [313] "chrlepto_323" "chrlepto_324" "chrlepto_325" "chrlepto_326"
## [317] "chrlepto_327" "chrlepto_328" "chrlepto_329" "chrlepto_330"
## [321] "chrlepto_331" "chrlepto_332" "chrlepto_333" "chrlepto_334"
## [325] "chrlepto_335" "chrlepto_336" "chrlepto_337" "chrlepto_338"
## [329] "chrlepto_340" "chrlepto_342" "chrlepto_343" "chrlepto_344"
## [333] "chrlepto_345" "chrlepto_346" "chrlepto_347" "chrlepto_348"
## [337] "chrlepto_349" "chrlepto_350" "chrlepto_351" "chrlepto_353"
## [341] "chrlepto_354" "chrlepto_355" "chrlepto_356" "chrlepto_358"
## [345] "chrlepto_359" "chrlepto_361" "chrlepto_362" "chrlepto_363"
## [349] "chrlepto_365" "chrlepto_367" "chrlepto_368" "chrlepto_369"
## [353] "chrlepto_370" "chrlepto_373" "chrlepto_374" "chrlepto_375"
## [357] "chrlepto_376" "chrlepto_377" "chrlepto_378" "chrlepto_379"
## [361] "chrlepto_381" "chrlepto_382" "chrlepto_383" "chrlepto_384"
## [365] "chrlepto_385" "chrlepto_386" "chrlepto_387" "chrlepto_388"
## [369] "chrlepto_389" "chrlepto_390" "chrlepto_392" "chrlepto_393"
## [373] "chrlepto_394" "chrlepto_395" "chrlepto_396" "chrlepto_397"
## [377] "chrlepto_398" "chrlepto_400" "chrlepto_401" "chrlepto_402"
## [381] "chrlepto_405" "chrlepto_406" "chrlepto_407" "chrlepto_408"
## [385] "chrlepto_410" "chrlepto_411" "chrlepto_413" "chrlepto_414"
## [389] "chrlepto_415" "chrlepto_416" "chrlepto_417" "chrlepto_418"
## [393] "chrlepto_419" "chrlepto_420" "chrlepto_422" "chrlepto_423"
## [397] "chrlepto_425" "chrlepto_426" "chrlepto_427" "chrlepto_431"
## [401] "chrlepto_432" "chrlepto_433" "chrlepto_434" "chrlepto_435"
## [405] "chrlepto_436" "chrlepto_437" "chrlepto_441" "chrlepto_442"
## [409] "chrlepto_443" "chrlepto_444" "chrlepto_445" "chrlepto_448"
## [413] "chrlepto_452" "chrlepto_453" "chrlepto_454" "chrlepto_456"
## [417] "chrlepto_458" "chrlepto_459" "chrlepto_460" "chrlepto_461"
## [421] "chrlepto_462" "chrlepto_463" "chrlepto_466" "chrlepto_467"
## [425] "chrlepto_468" "chrlepto_469" "chrlepto_471" "chrlepto_477"
## [429] "chrlepto_481" "chrlepto_482" "chrlepto_483" "chrlepto_485"
## [433] "chrlepto_487" "chrlepto_490" "chrlepto_492" "chrlepto_494"
## [437] "chrlepto_501" "chrlepto_502" "chrlepto_505" "chrlepto_511"
## [441] "chrlepto_512" "chrlepto_513" "chrlepto_516" "chrlepto_517"
## [445] "chrlepto_526" "chrlepto_527" "chrlepto_538" "chrlepto_540"
## [449] "chrlepto_541" "chrlepto_544" "chrlepto_551" "chrlepto_562"
## [453] "chrlepto_563" "chrlepto_572" "chrlepto_576" "chrlepto_596"
## [457] "chrlepto_598" "chrlepto_599" "chrlepto_600" "chrlepto_617"
## [461] "chrlepto_628" "chrlepto_644" "chrlepto_645" "chrlepto_648"
## [465] "chrlepto_649" "chrlepto_659" "chrlepto_705" "chrlepto_708"
## [469] "chrlepto_760"
snpset.id <- unlist(snpset) # all selected snp.id
pca <- snpgdsPCA(genofile, snp.id = snpset.id, num.thread = 2, autosome.only = FALSE)
## Principal Component Analysis (PCA) on genotypes:
## Excluding 0 SNP (monomorphic: TRUE, MAF: NaN, missing rate: NaN)
## Working space: 165 samples, 2,084 SNPs
## using 2 (CPU) cores
## PCA: the sum of all selected genotypes (0,1,2) = 621480
## CPU capabilities: Double-Precision SSE2
## Mon Apr 16 09:43:32 2018 (internal increment: 2156)
##
[..................................................] 0%, ETC: ---
[==================================================] 100%, completed in 0s
## Mon Apr 16 09:43:32 2018 Begin (eigenvalues and eigenvectors)
## Mon Apr 16 09:43:32 2018 Done.
#variance proportion
pc.percent <-pca$varprop*100
head(round(pc.percent, 2))
## [1] 18.11 9.05 5.06 4.45 3.00 2.67
#making a data frame for no prior population information
tab <- data.frame(sample.id = pca$sample.id,
EV1 = pca$eigenvect[,1],
EV2 = pca$eigenvect[,2],
stringsAsFactors = FALSE)
head(tab) #checking if it fille out correctly
## sample.id EV1
## 1 /mnt/bulleit/arnaud/Plate2_6/ss114_Ll_Plate04_C05.sorted.bam -0.02007578
## 2 /mnt/bulleit/arnaud/Plate2_6/ss116_Ll_Plate04_D05.sorted.bam -0.02122900
## 3 /mnt/bulleit/arnaud/Plate2_6/ss121_Ll_Plate06_E06.sorted.bam -0.02103582
## 4 /mnt/bulleit/arnaud/Plate2_6/ss126_Ll_Plate04_E05.sorted.bam -0.02018683
## 5 /mnt/bulleit/arnaud/Plate2_6/ss132_Ll_Plate04_F05.sorted.bam -0.02196045
## 6 /mnt/bulleit/arnaud/Plate2_6/ss136_Ll_Plate04_G05.sorted.bam -0.02196931
## EV2
## 1 0.001308661
## 2 0.001513394
## 3 0.002339123
## 4 0.001642865
## 5 0.001863321
## 6 0.001247673
#Drawing the pca plot
plot(tab$EV2, tab$EV1, xlab="eigenvector 2", ylab="eigenvector 1")
title(main = "Ll PCA LD Trimmed")
text(x = pca$eigenvect[,2], y = pca$eigenvect[,1], labels = SampleNames, pos = 1 ,cex =0.8, offset = 0.5)
LlLocal <- as_tibble(tab)
LlCluster1 <- filter(LlLocal, EV1 > 0.2 & EV2 < -0.1) %>% arrange(EV2)
LlCluster2 <- filter(LlLocal, EV1 < 0) %>% arrange(EV2)
LlCluster3 <- filter(LlLocal, EV2 > 0.4) %>% arrange(EV2)
Ophiostoma montium
setwd("/Users/Ryan/Desktop/Missing_Data_Reports")
set.seed(1000)
vcf.fn <- "C:/Users/Ryan/Desktop/Missing_Data_Reports/Om_HQ.95MissingData.recode.vcf"
snpgdsVCF2GDS(vcf.fn, "Om_HQ.95MissingData.recode.gds", method="biallelic.only")
## VCF Format ==> SNP GDS Format
## Method: exacting biallelic SNPs
## Number of samples: 149
## Parsing "C:/Users/Ryan/Desktop/Missing_Data_Reports/Om_HQ.95MissingData.recode.vcf" ...
## import 28205 variants.
## + genotype { Bit2 149x28205, 1.0M } *
## Optimize the access efficiency ...
## Clean up the fragments of GDS file:
## open the file 'Om_HQ.95MissingData.recode.gds' (1.1M)
## # of fragments: 42
## save to 'Om_HQ.95MissingData.recode.gds.tmp'
## rename 'Om_HQ.95MissingData.recode.gds.tmp' (1.1M, reduced: 264B)
## # of fragments: 20
snpgdsSummary("Om_HQ.95MissingData.recode.gds")
## The file name: C:\Users\Ryan\Desktop\Missing_Data_Reports\Om_HQ.95MissingData.recode.gds
## The total number of samples: 149
## The total number of SNPs: 28205
## SNP genotypes are stored in SNP-major mode (Sample X SNP).
SampleNames <- read.table(file = "/Users/Ryan/Desktop/Missing_Data_Reports/Om_HQ_95MissingDataList.txt")
SampleNames <- unlist(SampleNames)
genofile <- snpgdsOpen("Om_HQ.95MissingData.recode.gds")
snpset <- snpgdsLDpruning(genofile , ld.threshold = 0.2, autosome.only = FALSE)
## SNP pruning based on LD:
## Excluding 0 SNP (monomorphic: TRUE, MAF: NaN, missing rate: NaN)
## Working space: 149 samples, 28,205 SNPs
## using 1 (CPU) core
## sliding window: 500,000 basepairs, Inf SNPs
## |LD| threshold: 0.2
## method: composite
## Chromosome 1060: 26.09%, 6/23
## Chromosome 117621: 50.00%, 1/2
## Chromosome 122858: 44.44%, 4/9
## Chromosome 122870: 50.00%, 4/8
## Chromosome 122880: 40.91%, 9/22
## Chromosome 122895: 50.00%, 5/10
## Chromosome 122896: 10.71%, 33/308
## Chromosome 122903: 15.79%, 27/171
## Chromosome 122910: 12.50%, 20/160
## Chromosome 122911: 13.20%, 26/197
## Chromosome 122919: 15.79%, 36/228
## Chromosome 122929: 62.50%, 10/16
## Chromosome 122946: 13.09%, 25/191
## Chromosome 122947: 37.50%, 15/40
## Chromosome 122950: 11.86%, 37/312
## Chromosome 122968: 19.78%, 18/91
## Chromosome 122974: 29.73%, 11/37
## Chromosome 122980: 22.73%, 15/66
## Chromosome 122990: 21.88%, 7/32
## Chromosome 122993: 11.11%, 18/162
## Chromosome 123014: 32.35%, 11/34
## Chromosome 123039: 27.27%, 21/77
## Chromosome 123046: 19.10%, 17/89
## Chromosome 123068: 85.71%, 6/7
## Chromosome 123075: 16.83%, 17/101
## Chromosome 123085: 85.71%, 6/7
## Chromosome 123088: 22.58%, 7/31
## Chromosome 123094: 11.76%, 12/102
## Chromosome 123116: 39.29%, 11/28
## Chromosome 123130: 50.00%, 2/4
## Chromosome 123139: 50.00%, 9/18
## Chromosome 123203: 28.33%, 17/60
## Chromosome 123226: 9.11%, 52/571
## Chromosome 123237: 37.50%, 9/24
## Chromosome 123239: 60.00%, 6/10
## Chromosome 123247: 17.76%, 19/107
## Chromosome 123260: 43.75%, 7/16
## Chromosome 123282: 29.17%, 7/24
## Chromosome 123308: 21.43%, 12/56
## Chromosome 123309: 25.00%, 11/44
## Chromosome 123351: 24.62%, 16/65
## Chromosome 123353: 23.08%, 18/78
## Chromosome 123373: 12.27%, 33/269
## Chromosome 123375: 19.33%, 23/119
## Chromosome 123385: 27.91%, 12/43
## Chromosome 123398: 7.69%, 35/455
## Chromosome 123399: 29.27%, 12/41
## Chromosome 123435: 27.63%, 21/76
## Chromosome 123460: 34.48%, 10/29
## Chromosome 123467: 14.79%, 21/142
## Chromosome 123493: 50.00%, 6/12
## Chromosome 123511: 25.86%, 15/58
## Chromosome 123513: 9.07%, 37/408
## Chromosome 123514: 17.73%, 25/141
## Chromosome 123516: 13.14%, 18/137
## Chromosome 123527: 25.00%, 9/36
## Chromosome 123528: 17.71%, 17/96
## Chromosome 123529: 16.46%, 13/79
## Chromosome 123530: 66.67%, 2/3
## Chromosome 123546: 26.47%, 18/68
## Chromosome 123547: 50.00%, 4/8
## Chromosome 123550: 36.59%, 15/41
## Chromosome 123587: 27.59%, 8/29
## Chromosome 123610: 33.33%, 1/3
## Chromosome 123616: 27.87%, 17/61
## Chromosome 123642: 12.13%, 37/305
## Chromosome 123652: 45.45%, 5/11
## Chromosome 123658: 26.92%, 7/26
## Chromosome 123664: 25.49%, 13/51
## Chromosome 123666: 48.39%, 15/31
## Chromosome 123672: 14.06%, 27/192
## Chromosome 123697: 27.91%, 12/43
## Chromosome 123698: 64.29%, 9/14
## Chromosome 123720: 25.00%, 4/16
## Chromosome 123733: 37.84%, 14/37
## Chromosome 123736: 80.00%, 8/10
## Chromosome 123737: 12.39%, 28/226
## Chromosome 123744: 80.00%, 4/5
## Chromosome 123781: 23.08%, 12/52
## Chromosome 123782: 13.50%, 22/163
## Chromosome 123788: 10.00%, 1/10
## Chromosome 123791: 14.29%, 1/7
## Chromosome 123807: 14.02%, 23/164
## Chromosome 123859: 53.33%, 8/15
## Chromosome 123869: 50.00%, 9/18
## Chromosome 123871: 22.08%, 17/77
## Chromosome 123900: 60.00%, 3/5
## Chromosome 123928: 28.57%, 8/28
## Chromosome 123929: 16.67%, 12/72
## Chromosome 123952: 17.83%, 23/129
## Chromosome 123956: 80.00%, 4/5
## Chromosome 123984: 45.45%, 10/22
## Chromosome 123985: 23.53%, 8/34
## Chromosome 124002: 17.80%, 21/118
## Chromosome 124012: 11.49%, 44/383
## Chromosome 124031: 50.00%, 3/6
## Chromosome 124053: 18.92%, 21/111
## Chromosome 124054: 44.00%, 11/25
## Chromosome 124063: 19.79%, 19/96
## Chromosome 124083: 13.24%, 27/204
## Chromosome 124130: 26.83%, 11/41
## Chromosome 124133: 36.00%, 9/25
## Chromosome 124159: 11.18%, 19/170
## Chromosome 124163: 26.32%, 20/76
## Chromosome 124172: 36.36%, 4/11
## Chromosome 124174: 32.69%, 17/52
## Chromosome 124177: 14.63%, 24/164
## Chromosome 124179: 23.08%, 12/52
## Chromosome 124203: 27.59%, 16/58
## Chromosome 124207: 20.45%, 18/88
## Chromosome 124215: 75.00%, 6/8
## Chromosome 124219: 21.67%, 26/120
## Chromosome 124220: 12.37%, 36/291
## Chromosome 124223: 16.22%, 6/37
## Chromosome 124240: 15.00%, 3/20
## Chromosome 124270: 14.75%, 32/217
## Chromosome 124275: 15.22%, 21/138
## Chromosome 124288: 53.33%, 8/15
## Chromosome 124306: 28.57%, 18/63
## Chromosome 124333: 13.13%, 34/259
## Chromosome 124339: 22.73%, 10/44
## Chromosome 124407: 8.57%, 12/140
## Chromosome 124414: 33.96%, 18/53
## Chromosome 124420: 71.43%, 5/7
## Chromosome 124428: 24.62%, 16/65
## Chromosome 124440: 12.76%, 25/196
## Chromosome 124484: 36.36%, 8/22
## Chromosome 124489: 100.00%, 2/2
## Chromosome 124497: 23.44%, 15/64
## Chromosome 124503: 21.28%, 10/47
## Chromosome 124504: 16.28%, 14/86
## Chromosome 124545: 13.13%, 26/198
## Chromosome 124546: 37.50%, 9/24
## Chromosome 124562: 9.68%, 42/434
## Chromosome 124600: 11.62%, 23/198
## Chromosome 124632: 14.13%, 26/184
## Chromosome 124639: 18.45%, 19/103
## Chromosome 124645: 100.00%, 5/5
## Chromosome 124655: 66.67%, 2/3
## Chromosome 124681: 5.66%, 57/1,007
## Chromosome 124725: 50.00%, 6/12
## Chromosome 124728: 20.18%, 22/109
## Chromosome 124746: 85.71%, 6/7
## Chromosome 124767: 8.75%, 40/457
## Chromosome 124777: 22.22%, 2/9
## Chromosome 124796: 17.54%, 20/114
## Chromosome 124801: 29.03%, 9/31
## Chromosome 124804: 21.05%, 12/57
## Chromosome 124821: 33.33%, 15/45
## Chromosome 124834: 39.29%, 11/28
## Chromosome 124838: 17.74%, 22/124
## Chromosome 124839: 16.51%, 18/109
## Chromosome 124847: 16.56%, 27/163
## Chromosome 124849: 100.00%, 1/1
## Chromosome 124852: 17.22%, 26/151
## Chromosome 124855: 24.32%, 18/74
## Chromosome 124867: 31.15%, 19/61
## Chromosome 124874: 50.00%, 2/4
## Chromosome 124878: 10.10%, 39/386
## Chromosome 124926: 16.77%, 26/155
## Chromosome 124927: 20.69%, 6/29
## Chromosome 124941: 50.00%, 2/4
## Chromosome 124966: 18.84%, 26/138
## Chromosome 124970: 26.19%, 11/42
## Chromosome 124976: 15.79%, 15/95
## Chromosome 124995: 9.25%, 27/292
## Chromosome 124996: 29.55%, 13/44
## Chromosome 124997: 15.22%, 7/46
## Chromosome 125006: 100.00%, 1/1
## Chromosome 125012: 8.73%, 42/481
## Chromosome 125017: 61.11%, 11/18
## Chromosome 125018: 21.62%, 24/111
## Chromosome 125037: 18.63%, 19/102
## Chromosome 125054: 15.38%, 10/65
## Chromosome 125065: 22.06%, 30/136
## Chromosome 125071: 14.96%, 35/234
## Chromosome 125085: 12.61%, 28/222
## Chromosome 125089: 10.16%, 38/374
## Chromosome 125092: 13.54%, 26/192
## Chromosome 125095: 16.67%, 18/108
## Chromosome 125101: 8.73%, 33/378
## Chromosome 125110: 60.00%, 6/10
## Chromosome 125115: 17.50%, 7/40
## Chromosome 125117: 16.28%, 28/172
## Chromosome 125125: 19.61%, 20/102
## Chromosome 125129: 14.29%, 25/175
## Chromosome 125132: 100.00%, 1/1
## Chromosome 125133: 18.07%, 15/83
## Chromosome 125134: 23.66%, 22/93
## Chromosome 125135: 100.00%, 1/1
## Chromosome 125136: 12.88%, 30/233
## Chromosome 125139: 9.29%, 29/312
## Chromosome 125140: 18.75%, 15/80
## Chromosome 125141: 18.42%, 28/152
## Chromosome 125146: 10.82%, 25/231
## Chromosome 125147: 15.58%, 31/199
## Chromosome 125150: 23.86%, 21/88
## Chromosome 125152: 32.61%, 15/46
## Chromosome 125153: 16.28%, 28/172
## Chromosome 125159: 14.29%, 38/266
## Chromosome 125160: 12.10%, 34/281
## Chromosome 125163: 9.76%, 33/338
## Chromosome 125165: 22.22%, 18/81
## Chromosome 125166: 25.68%, 19/74
## Chromosome 125168: 7.95%, 43/541
## Chromosome 125169: 12.33%, 18/146
## Chromosome 125172: 12.55%, 29/231
## Chromosome 125173: 14.92%, 27/181
## Chromosome 125179: 11.74%, 25/213
## Chromosome 125180: 16.24%, 19/117
## Chromosome 125181: 16.39%, 10/61
## Chromosome 125182: 11.34%, 27/238
## Chromosome 125183: 27.63%, 21/76
## Chromosome 125184: 14.39%, 19/132
## Chromosome 125186: 14.73%, 19/129
## Chromosome 125188: 13.04%, 12/92
## Chromosome 125191: 17.46%, 22/126
## Chromosome 125193: 44.44%, 4/9
## Chromosome 125194: 16.80%, 21/125
## Chromosome 125197: 25.97%, 20/77
## Chromosome 125203: 25.00%, 2/8
## Chromosome 125205: 17.82%, 18/101
## Chromosome 125208: 18.33%, 22/120
## Chromosome 125209: 16.22%, 18/111
## Chromosome 125210: 20.29%, 14/69
## Chromosome 125211: 12.17%, 23/189
## Chromosome 125212: 17.69%, 26/147
## Chromosome 125214: 11.21%, 26/232
## Chromosome 125216: 17.35%, 17/98
## Chromosome 125221: 14.24%, 41/288
## Chromosome 125223: 16.39%, 20/122
## Chromosome 125226: 22.78%, 18/79
## Chromosome 125229: 12.50%, 27/216
## Chromosome 125231: 11.45%, 34/297
## Chromosome 125234: 19.84%, 25/126
## Chromosome 125235: 12.94%, 26/201
## Chromosome 125236: 22.73%, 10/44
## Chromosome 125241: 39.47%, 15/38
## Chromosome 125243: 18.10%, 19/105
## Chromosome 125245: 75.00%, 3/4
## Chromosome 125254: 19.30%, 22/114
## Chromosome 125258: 17.32%, 22/127
## Chromosome 125259: 8.66%, 33/381
## Chromosome 125261: 19.33%, 29/150
## Chromosome 14195: 21.15%, 11/52
## Chromosome 15565: 100.00%, 5/5
## Chromosome 17833: 100.00%, 2/2
## Chromosome 29972: 53.85%, 7/13
## Chromosome 50704: 26.67%, 8/30
## Chromosome 51396: 50.00%, 1/2
## Chromosome 51608: 45.45%, 5/11
## Chromosome 53929: 66.67%, 10/15
## Chromosome 56573: 38.89%, 7/18
## Chromosome 5982: 35.71%, 5/14
## Chromosome 59970: 47.06%, 8/17
## Chromosome 60871: 66.67%, 2/3
## Chromosome 63284: 22.58%, 14/62
## Chromosome 73520: 41.18%, 7/17
## Chromosome 75722: 27.78%, 10/36
## Chromosome 86527: 30.43%, 7/23
## Chromosome 9063: 28.57%, 14/49
## Chromosome 92184: 85.71%, 6/7
## Chromosome 93895: 20.00%, 1/5
## Chromosome 98234: 81.82%, 9/11
## Chromosome 99823: 30.43%, 7/23
## 4,410 markers are selected in total.
names(snpset)
## [1] "chr1060" "chr117621" "chr122858" "chr122870" "chr122880"
## [6] "chr122895" "chr122896" "chr122903" "chr122910" "chr122911"
## [11] "chr122919" "chr122929" "chr122946" "chr122947" "chr122950"
## [16] "chr122968" "chr122974" "chr122980" "chr122990" "chr122993"
## [21] "chr123014" "chr123039" "chr123046" "chr123068" "chr123075"
## [26] "chr123085" "chr123088" "chr123094" "chr123116" "chr123130"
## [31] "chr123139" "chr123203" "chr123226" "chr123237" "chr123239"
## [36] "chr123247" "chr123260" "chr123282" "chr123308" "chr123309"
## [41] "chr123351" "chr123353" "chr123373" "chr123375" "chr123385"
## [46] "chr123398" "chr123399" "chr123435" "chr123460" "chr123467"
## [51] "chr123493" "chr123511" "chr123513" "chr123514" "chr123516"
## [56] "chr123527" "chr123528" "chr123529" "chr123530" "chr123546"
## [61] "chr123547" "chr123550" "chr123587" "chr123610" "chr123616"
## [66] "chr123642" "chr123652" "chr123658" "chr123664" "chr123666"
## [71] "chr123672" "chr123697" "chr123698" "chr123720" "chr123733"
## [76] "chr123736" "chr123737" "chr123744" "chr123781" "chr123782"
## [81] "chr123788" "chr123791" "chr123807" "chr123859" "chr123869"
## [86] "chr123871" "chr123900" "chr123928" "chr123929" "chr123952"
## [91] "chr123956" "chr123984" "chr123985" "chr124002" "chr124012"
## [96] "chr124031" "chr124053" "chr124054" "chr124063" "chr124083"
## [101] "chr124130" "chr124133" "chr124159" "chr124163" "chr124172"
## [106] "chr124174" "chr124177" "chr124179" "chr124203" "chr124207"
## [111] "chr124215" "chr124219" "chr124220" "chr124223" "chr124240"
## [116] "chr124270" "chr124275" "chr124288" "chr124306" "chr124333"
## [121] "chr124339" "chr124407" "chr124414" "chr124420" "chr124428"
## [126] "chr124440" "chr124484" "chr124489" "chr124497" "chr124503"
## [131] "chr124504" "chr124545" "chr124546" "chr124562" "chr124600"
## [136] "chr124632" "chr124639" "chr124645" "chr124655" "chr124681"
## [141] "chr124725" "chr124728" "chr124746" "chr124767" "chr124777"
## [146] "chr124796" "chr124801" "chr124804" "chr124821" "chr124834"
## [151] "chr124838" "chr124839" "chr124847" "chr124849" "chr124852"
## [156] "chr124855" "chr124867" "chr124874" "chr124878" "chr124926"
## [161] "chr124927" "chr124941" "chr124966" "chr124970" "chr124976"
## [166] "chr124995" "chr124996" "chr124997" "chr125006" "chr125012"
## [171] "chr125017" "chr125018" "chr125037" "chr125054" "chr125065"
## [176] "chr125071" "chr125085" "chr125089" "chr125092" "chr125095"
## [181] "chr125101" "chr125110" "chr125115" "chr125117" "chr125125"
## [186] "chr125129" "chr125132" "chr125133" "chr125134" "chr125135"
## [191] "chr125136" "chr125139" "chr125140" "chr125141" "chr125146"
## [196] "chr125147" "chr125150" "chr125152" "chr125153" "chr125159"
## [201] "chr125160" "chr125163" "chr125165" "chr125166" "chr125168"
## [206] "chr125169" "chr125172" "chr125173" "chr125179" "chr125180"
## [211] "chr125181" "chr125182" "chr125183" "chr125184" "chr125186"
## [216] "chr125188" "chr125191" "chr125193" "chr125194" "chr125197"
## [221] "chr125203" "chr125205" "chr125208" "chr125209" "chr125210"
## [226] "chr125211" "chr125212" "chr125214" "chr125216" "chr125221"
## [231] "chr125223" "chr125226" "chr125229" "chr125231" "chr125234"
## [236] "chr125235" "chr125236" "chr125241" "chr125243" "chr125245"
## [241] "chr125254" "chr125258" "chr125259" "chr125261" "chr14195"
## [246] "chr15565" "chr17833" "chr29972" "chr50704" "chr51396"
## [251] "chr51608" "chr53929" "chr56573" "chr5982" "chr59970"
## [256] "chr60871" "chr63284" "chr73520" "chr75722" "chr86527"
## [261] "chr9063" "chr92184" "chr93895" "chr98234" "chr99823"
snpset.id <- unlist(snpset) # all selected snp.id
pca <- snpgdsPCA(genofile, snp.id = snpset.id, num.thread = 2, autosome.only = FALSE)
## Principal Component Analysis (PCA) on genotypes:
## Excluding 0 SNP (monomorphic: TRUE, MAF: NaN, missing rate: NaN)
## Working space: 149 samples, 4,410 SNPs
## using 2 (CPU) cores
## PCA: the sum of all selected genotypes (0,1,2) = 1137542
## CPU capabilities: Double-Precision SSE2
## Mon Apr 16 09:43:38 2018 (internal increment: 2388)
##
[..................................................] 0%, ETC: ---
[==================================================] 100%, completed in 0s
## Mon Apr 16 09:43:38 2018 Begin (eigenvalues and eigenvectors)
## Mon Apr 16 09:43:38 2018 Done.
#variance proportion
pc.percent <-pca$varprop*100
head(round(pc.percent, 2))
## [1] 4.14 3.18 2.52 2.22 2.17 1.76
#making a data frame for no prior population information
tab <- data.frame(sample.id = pca$sample.id,
EV1 = pca$eigenvect[,1],
EV2 = pca$eigenvect[,2],
stringsAsFactors = FALSE)
head(tab) #checking if it fille out correctly
## sample.id EV1
## 1 /mnt/bulleit/arnaud/Plate2_6/ss150_Om_Plate05_C09.sorted.bam 0.03589593
## 2 /mnt/bulleit/arnaud/Plate2_6/ss158_Om_Plate05_E09.sorted.bam 0.04714197
## 3 /mnt/bulleit/arnaud/Plate2_6/ss162_Om_Plate05_F09.sorted.bam 0.04032504
## 4 /mnt/bulleit/arnaud/Plate2_6/ss164_Om_Plate05_G09.sorted.bam 0.05476270
## 5 /mnt/bulleit/arnaud/Plate2_6/ss165_Om_Plate05_H09.sorted.bam 0.04815335
## 6 /mnt/bulleit/arnaud/Plate2_6/ss178_Om_Plate05_A10.sorted.bam 0.05048402
## EV2
## 1 0.009222316
## 2 -0.044016562
## 3 0.014462395
## 4 -0.046060155
## 5 -0.041260811
## 6 -0.028444715
#Drawing the pca plot
plot(tab$EV2, tab$EV1, xlab="eigenvector 2", ylab="eigenvector 1")
title(main = "Om PCA LD Trimmed")
text(x = pca$eigenvect[,2], y = pca$eigenvect[,1], labels = SampleNames, pos = 1 ,cex =0.8, offset = 0.5)
OmLocal <- as_tibble(tab)
OmCluster1 <- filter(OmLocal, EV1 < -0.2) %>% arrange(EV2)
OmCluster2 <- filter(OmLocal, EV2 > 0.15) %>% arrange(EV2)
OmCluster3 <- filter(OmLocal, 0.08 < EV2 & EV2 < 0.15 & EV1 > -0.05) %>% arrange(EV2)
OmCluster4 <- filter(OmLocal, 0.08 < EV2 & EV2 < 0.15 & EV1 < -0.05) %>% arrange(EV2)
OmCluster5 <- filter(OmLocal, -0.016 > EV2 & EV1 > 0.0) %>% arrange(EV2)
OmCluster6 <- filter(OmLocal, -0.016 < EV2 & EV2 < 0.03 & EV1 > 0.0) %>% arrange(EV2)