Quality Control Vignette

library(gridExtra)
library(knitr)
library(ggplot2)
#install.packages("fastqcr")
library(fastqcr)
#must run this if fastqc is not already installed locally
#fastqc_install()

###ONLY THIS CHUNK REQUIRES MODIFICATION###
###assign your directory locations here:

#specify full path to directory containing a .fastq.gz file for each sample
fq.dir<-"/home/d669d153/work/dia.din/fq"

#specify full path to the output directory where you want 
qc.dir<-"~/Downloads/qc"

#run fastqc on all .fastq.gz files, through r
#only needs to be run once, if tweaking downstream visualizations, comment out this step
#fastqc(fq.dir = fq.dir, # FASTQ files directory
#       qc.dir = qc.dir, # Results directory
#       threads = 4                    # Number of threads
#       )

# List of files in the output directory to ensure fastqc worked
list.files(qc.dir)

[1] “908108_H_diadema_Gatokae_fastqc.html”
[2] “908108_H_diadema_Gatokae_fastqc.zip”
[3] “908150_H_dinops_Guadalcanal_fastqc.html”
[4] “908150_H_dinops_Guadalcanal_fastqc.zip”
[5] “908151_H_diadema_Guadalcanal_fastqc.html”
[6] “908151_H_diadema_Guadalcanal_fastqc.zip”
[7] “908152_H_diadema_Guadalcanal_fastqc.html”
[8] “908152_H_diadema_Guadalcanal_fastqc.zip”
[9] “908153a_H_dinops_Guadalcanal_fastqc.html”
[10] “908153a_H_dinops_Guadalcanal_fastqc.zip”
[11] “908154_H_dinops_Guadalcanal_fastqc.html”
[12] “908154_H_dinops_Guadalcanal_fastqc.zip”
[13] “908155_H_dinops_Guadalcanal_fastqc.html”
[14] “908155_H_dinops_Guadalcanal_fastqc.zip”
[15] “908156_H_diadema_Guadalcanal_fastqc.html”
[16] “908156_H_diadema_Guadalcanal_fastqc.zip”
[17] “908208_H_diadema_Guadalcanal_fastqc.html”
[18] “908208_H_diadema_Guadalcanal_fastqc.zip”
[19] “JM19686_H_diadema_Choiseul_fastqc.html”
[20] “JM19686_H_diadema_Choiseul_fastqc.zip”
[21] “KVO150_H_diadema_Isabel_fastqc.html”
[22] “KVO150_H_diadema_Isabel_fastqc.zip”
[23] “KVO168_H_diadema_Isabel_fastqc.html”
[24] “KVO168_H_diadema_Isabel_fastqc.zip”
[25] “KVO169_H_diadema_Isabel_fastqc.html”
[26] “KVO169_H_diadema_Isabel_fastqc.zip”
[27] “KVO170_H_diadema_Isabel_fastqc.html”
[28] “KVO170_H_diadema_Isabel_fastqc.zip”
[29] “KVO171_H_diadema_Isabel_fastqc.html”
[30] “KVO171_H_diadema_Isabel_fastqc.zip”
[31] “KVO172_H_diadema_Isabel_fastqc.html”
[32] “KVO172_H_diadema_Isabel_fastqc.zip”
[33] “KVO242_H_dinops_Isabel_fastqc.html”
[34] “KVO242_H_dinops_Isabel_fastqc.zip”
[35] “KVO243_H_dinops_Isabel_fastqc.html”
[36] “KVO243_H_dinops_Isabel_fastqc.zip”
[37] “KVO244_H_dinops_Isabel_fastqc.html”
[38] “KVO244_H_dinops_Isabel_fastqc.zip”
[39] “KVO245_H_dinops_Isabel_fastqc.html”
[40] “KVO245_H_dinops_Isabel_fastqc.zip”
[41] “KVO246_H_dinops_Isabel_fastqc.html”
[42] “KVO246_H_dinops_Isabel_fastqc.zip”
[43] “KVO248_H_dinops_Isabel_fastqc.html”
[44] “KVO248_H_dinops_Isabel_fastqc.zip”
[45] “KVO249_Hipposiderous_sp_Isabel_fastqc.html” [46] “KVO249_Hipposiderous_sp_Isabel_fastqc.zip”
[47] “KVO250_Hipposiderous_sp_Isabel_fastqc.html” [48] “KVO250_Hipposiderous_sp_Isabel_fastqc.zip”
[49] “KVO251_Hipposiderous_sp_Rendova_fastqc.html” [50] “KVO251_Hipposiderous_sp_Rendova_fastqc.zip” [51] “THL1048_H_dinops_Guadalcanal_fastqc.html”
[52] “THL1048_H_dinops_Guadalcanal_fastqc.zip”
[53] “THL1120_H_dinops_Gatokae_fastqc.html”
[54] “THL1120_H_dinops_Gatokae_fastqc.zip”
[55] “THL1121_H_dinops_Gatokae_fastqc.html”
[56] “THL1121_H_dinops_Gatokae_fastqc.zip”
[57] “THL1122_H_dinops_Gatokae_fastqc.html”
[58] “THL1122_H_dinops_Gatokae_fastqc.zip”
[59] “THL1154_H_demissus_Makira_fastqc.html”
[60] “THL1154_H_demissus_Makira_fastqc.zip”
[61] “THL1156_H_demissus_Makira_fastqc.html”
[62] “THL1156_H_demissus_Makira_fastqc.zip”
[63] “THL1167_H_diadema_Guadalcanal_fastqc.html”
[64] “THL1167_H_diadema_Guadalcanal_fastqc.zip”
[65] “THL1172_H_dinops_Guadalcanal_fastqc.html”
[66] “THL1172_H_dinops_Guadalcanal_fastqc.zip”
[67] “THL1173_H_dinops_Guadalcanal_fastqc.html”
[68] “THL1173_H_dinops_Guadalcanal_fastqc.zip”
[69] “THL1221_H_diadema_Gatokae_fastqc.html”
[70] “THL1221_H_diadema_Gatokae_fastqc.zip”
[71] “THL1223_H_dinops_Guadalcanal_fastqc.html”
[72] “THL1223_H_dinops_Guadalcanal_fastqc.zip”
[73] “THL17193_H_diadema_Ngella_fastqc.html”
[74] “THL17193_H_diadema_Ngella_fastqc.zip”
[75] “THL17194_H_diadema_Ngella_fastqc.html”
[76] “THL17194_H_diadema_Ngella_fastqc.zip”
[77] “THL17195_H_diadema_Ngella_fastqc.html”
[78] “THL17195_H_diadema_Ngella_fastqc.zip”
[79] “THL17197_H_diadema_Ngella_fastqc.html”
[80] “THL17197_H_diadema_Ngella_fastqc.zip”
[81] “THL17198_H_diadema_Ngella_fastqc.html”
[82] “THL17198_H_diadema_Ngella_fastqc.zip”
[83] “THL17199_H_diadema_Ngella_fastqc.html”
[84] “THL17199_H_diadema_Ngella_fastqc.zip”
[85] “WD1705_H_diadema_E_New_Britain_fastqc.html” [86] “WD1705_H_diadema_E_New_Britain_fastqc.zip”
[87] “WD2047_H_diadema_Simbu_Prov_fastqc.html”
[88] “WD2047_H_diadema_Simbu_Prov_fastqc.zip”
[89] “WD2074_H_diadema_Gulf_Prov_fastqc.html”
[90] “WD2074_H_diadema_Gulf_Prov_fastqc.zip”

#create a character vector where each value is the full path to the .zip created by fastqc() for a given sample
#samps<-list.files("/home/d669d153/work/dia.din/qc", full.names = T, pattern = "*.zip")
samps<-list.files(qc.dir, full.names = T, pattern = "*.zip")

#plot qc test results for each sample
for (i in samps){
  #read info for given sample from the .zip file generated in the previous step
  samp.info <- qc_read(i)
  #open blank list to hold qc visualizations for the given sample
  plot<-list()
  #do qc for the given sample
  plot[[1]]<-qc_plot(samp.info, "Basic statistics")
  plot[[2]]<-qc_plot(samp.info, "Per sequence quality scores")
  plot[[3]]<-qc_plot(samp.info, "Sequence duplication levels")
  #visualize tables
  print(paste0("QC results for sample ", gsub(".*/", "", i)))

  cat('\n')

  print(kable(plot[[1]]))

  cat('\n')

  #visualize plots
  grid.arrange(plot[[2]],plot[[3]],
               ncol=2)
  
  #clear plot to hold info for next sample
  rm(plot)
}

[1] “QC results for sample 908108_H_diadema_Gatokae_fastqc.zip”

Measure	Value
Filename	908108_H_diadema_Gatokae.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	454706
Sequences flagged as poor quality	0
Sequence length	145
%GC	36

[1] “QC results for sample 908150_H_dinops_Guadalcanal_fastqc.zip”

Measure	Value
Filename	908150_H_dinops_Guadalcanal.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	120063
Sequences flagged as poor quality	0
Sequence length	145
%GC	38

[1] “QC results for sample 908151_H_diadema_Guadalcanal_fastqc.zip”

Measure	Value
Filename	908151_H_diadema_Guadalcanal.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	3174216
Sequences flagged as poor quality	0
Sequence length	145
%GC	38

[1] “QC results for sample 908152_H_diadema_Guadalcanal_fastqc.zip”

Measure	Value
Filename	908152_H_diadema_Guadalcanal.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	1388568
Sequences flagged as poor quality	0
Sequence length	145
%GC	37

[1] “QC results for sample 908153a_H_dinops_Guadalcanal_fastqc.zip”

Measure	Value
Filename	908153a_H_dinops_Guadalcanal.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	7300968
Sequences flagged as poor quality	0
Sequence length	145
%GC	37

[1] “QC results for sample 908154_H_dinops_Guadalcanal_fastqc.zip”

Measure	Value
Filename	908154_H_dinops_Guadalcanal.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	519876
Sequences flagged as poor quality	0
Sequence length	145
%GC	37

[1] “QC results for sample 908155_H_dinops_Guadalcanal_fastqc.zip”

Measure	Value
Filename	908155_H_dinops_Guadalcanal.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	989397
Sequences flagged as poor quality	0
Sequence length	145
%GC	37

[1] “QC results for sample 908156_H_diadema_Guadalcanal_fastqc.zip”

Measure	Value
Filename	908156_H_diadema_Guadalcanal.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	4264843
Sequences flagged as poor quality	0
Sequence length	145
%GC	37

[1] “QC results for sample 908208_H_diadema_Guadalcanal_fastqc.zip”

Measure	Value
Filename	908208_H_diadema_Guadalcanal.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	769417
Sequences flagged as poor quality	0
Sequence length	145
%GC	37

[1] “QC results for sample JM19686_H_diadema_Choiseul_fastqc.zip”

Measure	Value
Filename	JM19686_H_diadema_Choiseul.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	1029
Sequences flagged as poor quality	0
Sequence length	145
%GC	34

[1] “QC results for sample KVO150_H_diadema_Isabel_fastqc.zip”

Measure	Value
Filename	KVO150_H_diadema_Isabel.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	34555
Sequences flagged as poor quality	0
Sequence length	145
%GC	36

[1] “QC results for sample KVO168_H_diadema_Isabel_fastqc.zip”

Measure	Value
Filename	KVO168_H_diadema_Isabel.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	262565
Sequences flagged as poor quality	0
Sequence length	145
%GC	36

[1] “QC results for sample KVO169_H_diadema_Isabel_fastqc.zip”

Measure	Value
Filename	KVO169_H_diadema_Isabel.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	499713
Sequences flagged as poor quality	0
Sequence length	145
%GC	36

[1] “QC results for sample KVO170_H_diadema_Isabel_fastqc.zip”

Measure	Value
Filename	KVO170_H_diadema_Isabel.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	825167
Sequences flagged as poor quality	0
Sequence length	145
%GC	36

[1] “QC results for sample KVO171_H_diadema_Isabel_fastqc.zip”

Measure	Value
Filename	KVO171_H_diadema_Isabel.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	271596
Sequences flagged as poor quality	0
Sequence length	145
%GC	36

[1] “QC results for sample KVO172_H_diadema_Isabel_fastqc.zip”

Measure	Value
Filename	KVO172_H_diadema_Isabel.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	98438
Sequences flagged as poor quality	0
Sequence length	145
%GC	36

[1] “QC results for sample KVO242_H_dinops_Isabel_fastqc.zip”

Measure	Value
Filename	KVO242_H_dinops_Isabel.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	1350278
Sequences flagged as poor quality	0
Sequence length	145
%GC	37

[1] “QC results for sample KVO243_H_dinops_Isabel_fastqc.zip”

Measure	Value
Filename	KVO243_H_dinops_Isabel.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	1797464
Sequences flagged as poor quality	0
Sequence length	145
%GC	37

[1] “QC results for sample KVO244_H_dinops_Isabel_fastqc.zip”

Measure	Value
Filename	KVO244_H_dinops_Isabel.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	3002231
Sequences flagged as poor quality	0
Sequence length	145
%GC	36

[1] “QC results for sample KVO245_H_dinops_Isabel_fastqc.zip”

Measure	Value
Filename	KVO245_H_dinops_Isabel.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	4187253
Sequences flagged as poor quality	0
Sequence length	145
%GC	36

[1] “QC results for sample KVO246_H_dinops_Isabel_fastqc.zip”

Measure	Value
Filename	KVO246_H_dinops_Isabel.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	2153670
Sequences flagged as poor quality	0
Sequence length	145
%GC	36

[1] “QC results for sample KVO248_H_dinops_Isabel_fastqc.zip”

Measure	Value
Filename	KVO248_H_dinops_Isabel.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	1799491
Sequences flagged as poor quality	0
Sequence length	145
%GC	36

[1] “QC results for sample KVO249_Hipposiderous_sp_Isabel_fastqc.zip”

Measure	Value
Filename	KVO249_Hipposiderous_sp_Isabel.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	2164473
Sequences flagged as poor quality	0
Sequence length	145
%GC	36

[1] “QC results for sample KVO250_Hipposiderous_sp_Isabel_fastqc.zip”

Measure	Value
Filename	KVO250_Hipposiderous_sp_Isabel.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	215420
Sequences flagged as poor quality	0
Sequence length	145
%GC	36

[1] “QC results for sample KVO251_Hipposiderous_sp_Rendova_fastqc.zip”

Measure	Value
Filename	KVO251_Hipposiderous_sp_Rendova.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	1739541
Sequences flagged as poor quality	0
Sequence length	145
%GC	36

[1] “QC results for sample THL1048_H_dinops_Guadalcanal_fastqc.zip”

Measure	Value
Filename	THL1048_H_dinops_Guadalcanal.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	4848
Sequences flagged as poor quality	0
Sequence length	145
%GC	35

[1] “QC results for sample THL1120_H_dinops_Gatokae_fastqc.zip”

Measure	Value
Filename	THL1120_H_dinops_Gatokae.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	3212
Sequences flagged as poor quality	0
Sequence length	145
%GC	36

[1] “QC results for sample THL1121_H_dinops_Gatokae_fastqc.zip”

Measure	Value
Filename	THL1121_H_dinops_Gatokae.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	6874
Sequences flagged as poor quality	0
Sequence length	145
%GC	35

[1] “QC results for sample THL1122_H_dinops_Gatokae_fastqc.zip”

Measure	Value
Filename	THL1122_H_dinops_Gatokae.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	288
Sequences flagged as poor quality	0
Sequence length	145
%GC	36

[1] “QC results for sample THL1154_H_demissus_Makira_fastqc.zip”

Measure	Value
Filename	THL1154_H_demissus_Makira.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	5201
Sequences flagged as poor quality	0
Sequence length	145
%GC	36

[1] “QC results for sample THL1156_H_demissus_Makira_fastqc.zip”

Measure	Value
Filename	THL1156_H_demissus_Makira.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	819353
Sequences flagged as poor quality	0
Sequence length	145
%GC	36

[1] “QC results for sample THL1167_H_diadema_Guadalcanal_fastqc.zip”

Measure	Value
Filename	THL1167_H_diadema_Guadalcanal.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	1379
Sequences flagged as poor quality	0
Sequence length	145
%GC	37

[1] “QC results for sample THL1172_H_dinops_Guadalcanal_fastqc.zip”

Measure	Value
Filename	THL1172_H_dinops_Guadalcanal.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	173703
Sequences flagged as poor quality	0
Sequence length	145
%GC	38

[1] “QC results for sample THL1173_H_dinops_Guadalcanal_fastqc.zip”

Measure	Value
Filename	THL1173_H_dinops_Guadalcanal.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	979903
Sequences flagged as poor quality	0
Sequence length	145
%GC	37

[1] “QC results for sample THL1221_H_diadema_Gatokae_fastqc.zip”

Measure	Value
Filename	THL1221_H_diadema_Gatokae.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	43
Sequences flagged as poor quality	0
Sequence length	145
%GC	40

[1] “QC results for sample THL1223_H_dinops_Guadalcanal_fastqc.zip”

Measure	Value
Filename	THL1223_H_dinops_Guadalcanal.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	6655
Sequences flagged as poor quality	0
Sequence length	145
%GC	36

[1] “QC results for sample THL17193_H_diadema_Ngella_fastqc.zip”

Measure	Value
Filename	THL17193_H_diadema_Ngella.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	3033643
Sequences flagged as poor quality	0
Sequence length	145
%GC	38

[1] “QC results for sample THL17194_H_diadema_Ngella_fastqc.zip”

Measure	Value
Filename	THL17194_H_diadema_Ngella.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	1210618
Sequences flagged as poor quality	0
Sequence length	145
%GC	37

[1] “QC results for sample THL17195_H_diadema_Ngella_fastqc.zip”

Measure	Value
Filename	THL17195_H_diadema_Ngella.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	1825457
Sequences flagged as poor quality	0
Sequence length	145
%GC	37

[1] “QC results for sample THL17197_H_diadema_Ngella_fastqc.zip”

Measure	Value
Filename	THL17197_H_diadema_Ngella.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	1546118
Sequences flagged as poor quality	0
Sequence length	145
%GC	37

[1] “QC results for sample THL17198_H_diadema_Ngella_fastqc.zip”

Measure	Value
Filename	THL17198_H_diadema_Ngella.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	6607272
Sequences flagged as poor quality	0
Sequence length	145
%GC	37

[1] “QC results for sample THL17199_H_diadema_Ngella_fastqc.zip”

Measure	Value
Filename	THL17199_H_diadema_Ngella.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	1508601
Sequences flagged as poor quality	0
Sequence length	145
%GC	37

[1] “QC results for sample WD1705_H_diadema_E_New_Britain_fastqc.zip”

Measure	Value
Filename	WD1705_H_diadema_E_New_Britain.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	1323647
Sequences flagged as poor quality	0
Sequence length	145
%GC	37

[1] “QC results for sample WD2047_H_diadema_Simbu_Prov_fastqc.zip”

Measure	Value
Filename	WD2047_H_diadema_Simbu_Prov.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	696126
Sequences flagged as poor quality	0
Sequence length	145
%GC	36

[1] “QC results for sample WD2074_H_diadema_Gulf_Prov_fastqc.zip”

Measure	Value
Filename	WD2074_H_diadema_Gulf_Prov.fq.gz
File type	Conventional base calls
Encoding	Sanger / Illumina 1.9
Total Sequences	945453
Sequences flagged as poor quality	0
Sequence length	145
%GC	36

#aggregate the reports by pointing this function to the folder holding output of fastqc()
#qc <- qc_aggregate("/home/d669d153/work/dia.din/qc", progressbar=F)
qc <- qc_aggregate(qc.dir, progressbar = F)

#stats per sample
knitr::kable(qc_stats(qc))

sample	pct.dup	pct.gc	tot.seq	seq.length
908108_H_diadema_Gatokae.fq.gz	84.98	36	454706	145
908150_H_dinops_Guadalcanal.fq.gz	76.29	38	120063	145
908151_H_diadema_Guadalcanal.fq.gz	94.54	38	3174216	145
908152_H_diadema_Guadalcanal.fq.gz	89.86	37	1388568	145
908153a_H_dinops_Guadalcanal.fq.gz	94.82	37	7300968	145
908154_H_dinops_Guadalcanal.fq.gz	84.86	37	519876	145
908155_H_dinops_Guadalcanal.fq.gz	88.96	37	989397	145
908156_H_diadema_Guadalcanal.fq.gz	94.89	37	4264843	145
908208_H_diadema_Guadalcanal.fq.gz	89.66	37	769417	145
JM19686_H_diadema_Choiseul.fq.gz	18.85	34	1029	145
KVO150_H_diadema_Isabel.fq.gz	58.87	36	34555	145
KVO168_H_diadema_Isabel.fq.gz	80.63	36	262565	145
KVO169_H_diadema_Isabel.fq.gz	86.28	36	499713	145
KVO170_H_diadema_Isabel.fq.gz	89.21	36	825167	145
KVO171_H_diadema_Isabel.fq.gz	81.79	36	271596	145
KVO172_H_diadema_Isabel.fq.gz	70.24	36	98438	145
KVO242_H_dinops_Isabel.fq.gz	91.91	37	1350278	145
KVO243_H_dinops_Isabel.fq.gz	92.18	37	1797464	145
KVO244_H_dinops_Isabel.fq.gz	93.16	36	3002231	145
KVO245_H_dinops_Isabel.fq.gz	94.18	36	4187253	145
KVO246_H_dinops_Isabel.fq.gz	91.61	36	2153670	145
KVO248_H_dinops_Isabel.fq.gz	91.09	36	1799491	145
KVO249_Hipposiderous_sp_Isabel.fq.gz	91.67	36	2164473	145
KVO250_Hipposiderous_sp_Isabel.fq.gz	79.87	36	215420	145
KVO251_Hipposiderous_sp_Rendova.fq.gz	91.80	36	1739541	145
THL1048_H_dinops_Guadalcanal.fq.gz	35.68	35	4848	145
THL1120_H_dinops_Gatokae.fq.gz	10.65	36	3212	145
THL1121_H_dinops_Gatokae.fq.gz	9.18	35	6874	145
THL1122_H_dinops_Gatokae.fq.gz	43.75	36	288	145
THL1154_H_demissus_Makira.fq.gz	15.44	36	5201	145
THL1156_H_demissus_Makira.fq.gz	88.94	36	819353	145
THL1167_H_diadema_Guadalcanal.fq.gz	38.43	37	1379	145
THL1172_H_dinops_Guadalcanal.fq.gz	77.77	38	173703	145
THL1173_H_dinops_Guadalcanal.fq.gz	88.50	37	979903	145
THL1221_H_diadema_Gatokae.fq.gz	39.53	40	43	145
THL1223_H_dinops_Guadalcanal.fq.gz	14.46	36	6655	145
THL17193_H_diadema_Ngella.fq.gz	94.40	38	3033643	145
THL17194_H_diadema_Ngella.fq.gz	90.91	37	1210618	145
THL17195_H_diadema_Ngella.fq.gz	92.44	37	1825457	145
THL17197_H_diadema_Ngella.fq.gz	91.87	37	1546118	145
THL17198_H_diadema_Ngella.fq.gz	95.67	37	6607272	145
THL17199_H_diadema_Ngella.fq.gz	91.37	37	1508601	145
WD1705_H_diadema_E_New_Britain.fq.gz	91.09	37	1323647	145
WD2047_H_diadema_Simbu_Prov.fq.gz	86.17	36	696126	145
WD2074_H_diadema_Gulf_Prov.fq.gz	88.42	36	945453	145

solid red line = median sample value

dashed red line = 10% of median sample value

#save stats info as an object
stats.info<-qc_stats(qc)
#make tot.seq numeric
stats.info$tot.seq<-as.numeric(stats.info$tot.seq)

#make histogram of number of sequence reads for each sample
ggplot(stats.info, aes(x=tot.seq))+
              geom_histogram(color="black", fill="white", bins=20)+
              geom_vline(aes(xintercept=median(tot.seq)), color = "red")+
              geom_vline(aes(xintercept=median(tot.seq)*.1), color = "red", lty=14)+
              theme_classic()+
              xlab("Number of sequencing reads")

#solid red line = median sample value
#dashed red line = 10% of median sample value
ggplot(stats.info, aes(x=tot.seq))+
              geom_histogram(color="black", fill="white", bins=200)+
              geom_vline(aes(xintercept=median(tot.seq)), color = "red")+
              geom_vline(aes(xintercept=median(tot.seq)*.1), color = "red", lty=14)+
              theme_classic()+
              xlab("Number of sequencing reads")

#show me the samples that have less than 10% of the number of reads as the median sample from this experiment (these should be dropped immediately)
print(paste("Median sample contains", median(stats.info$tot.seq), "reads. The following samples contain less than", median(stats.info$tot.seq)*.1, "reads (10% of the median), and should likely be dropped"))

[1] “Median sample contains 825167 reads. The following samples contain less than 82516.7 reads (10% of the median), and should likely be dropped”

knitr::kable(stats.info[stats.info$tot.seq < median(stats.info$tot.seq)*.1,])

sample	pct.dup	pct.gc	tot.seq	seq.length
JM19686_H_diadema_Choiseul.fq.gz	18.85	34	1029	145
KVO150_H_diadema_Isabel.fq.gz	58.87	36	34555	145
THL1048_H_dinops_Guadalcanal.fq.gz	35.68	35	4848	145
THL1120_H_dinops_Gatokae.fq.gz	10.65	36	3212	145
THL1121_H_dinops_Gatokae.fq.gz	9.18	35	6874	145
THL1122_H_dinops_Gatokae.fq.gz	43.75	36	288	145
THL1154_H_demissus_Makira.fq.gz	15.44	36	5201	145
THL1167_H_diadema_Guadalcanal.fq.gz	38.43	37	1379	145
THL1221_H_diadema_Gatokae.fq.gz	39.53	40	43	145
THL1223_H_dinops_Guadalcanal.fq.gz	14.46	36	6655	145

Devon DeRaad

24 September 2021

solid red line = median sample value

dashed red line = 10% of median sample value