zzh
/
gatk-3.8
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Default operating parameters in addition to the parameterized Rscript version. 

git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@6067 348d0f76-0448-11de-a6fe-93d51630548a
This commit is contained in:
droazen 2011-06-22 22:55:53 +00:00
parent 0d07c979e9
commit 3d27e5eb98
1 changed files with 37 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

64
R/exomePreQC.R
View File

@ -2,8 +2,13 @@ args = commandArgs(TRUE)
onCMDLine = ! is.na(args[1])
if ( onCMDLine ) {
inputTSV = args[1]
outputPDF = args[2]
reference_dataset = '/Users/mhanna/metrics.perSample.formatted.table'
inputTSV = args[2]
outputPDF = args[3]
} else {
reference_dataset = '/Users/mhanna/metrics.perSample.formatted.table'
inputTSV = 'GoT2D_exomes_batch_005.tsv'
outputPDF = 'T2D.pdf'
}
require('ggplot2')
@ -11,35 +16,40 @@ require('ggplot2')
inputTSV = "GoT2D_exomes_batch_005.tsv"
data <- read.table(inputTSV,header=T)
fingerprint_lods = list()
for(i in 1:nrow(data)) {
fingerprint_lods[[as.character(data$sample[i])]] <- eval(parse(text=data$FINGERPRINT_LODS[i]))
}
fingerprint_lod_order = order(unlist(lapply(fingerprint_lods,median),use.names=F))
pdf(outputPDF)
boxplot(fingerprint_lods[fingerprint_lod_order],las=3,main='Fingerprint LOD Scores By Sample',xlab='Sample',ylab='LOD Score Distribution',cex.axis=0.65)
complete <- read.table('/Users/mhanna/metrics.perSample.formatted.table',header=T)
complete <- read.table(reference_dataset,header=T)
novel <- subset(complete,exon_intervals == "whole_exome_agilent_1.1_refseq_plus_3_boosters"&Novelty=="novel"&FunctionalClass=="all")
selected_samples <- novel$Sample %in% data$sample
novel_with_highlights <- cbind(novel,selected_samples)
qplot(Sample,Selected_Bases_Pct,data=novel_with_highlights,color=selected_samples) + opts(title='On+Near Bait Bases/PF Bases Aligned per Sample')
qplot(Sample,Mean_Target_Coverage,data=novel_with_highlights,color=selected_samples) + opts(title='Mean Target Coverage per Sample')
qplot(Sample,Zero_Coverage_Targets_Pct,data=novel_with_highlights,color=selected_samples) + opts(title='% of Targets with <2x Coverage per Sample')
qplot(Sample,Fold_80_Base_Penalty,data=novel_with_highlights,color=selected_samples) + opts(title='Fold 80 Base Penalty per Sample')
qplot(Sample,Target_Bases_20x_Pct,data=novel_with_highlights,color=selected_samples) + opts(title='% Target Bases Achieving >20x Coverage per Sample')
qplot(Sample,PF_Reads_Pct,data=novel_with_highlights,color=selected_samples) + opts(title='% PF Reads Aligned per Sample')
qplot(Sample,PF_HQ_Error_Rate,data=novel_with_highlights,color=selected_samples) + opts(title='% HQ Bases mismatching the Reference per Sample')
qplot(Sample,Mean_Read_Length,data=novel_with_highlights,color=selected_samples) + opts(title='Median Read Length per Sample')
qplot(Sample,Bad_Cycles,data=novel_with_highlights,color=selected_samples) + opts(title='# Bad Cycles per Sample')
qplot(Sample,Strand_Balance_Pct,data=novel_with_highlights,color=selected_samples) + opts(title='% PF Reads Aligned to the + Strand per Sample')
qplot(Sample,Total_SNPs,data=novel_with_highlights,color=selected_samples) + opts(title='# SNPs called per Sample')
qplot(Sample,dbSNP_Pct,data=novel_with_highlights,color=selected_samples) + opts(title='% SNPs in dbSNP per Sample')
qplot(PCT_DBSNP,data=data,geom="histogram") + opts(title='% SNPs in dbSNP per Sample')
dev.off()
if(onCMDLine) {
fingerprint_lods = list()
for(i in 1:nrow(data)) {
fingerprint_lods[[as.character(data$sample[i])]] <- eval(parse(text=data$FINGERPRINT_LODS[i]))
}
fingerprint_lod_order = order(unlist(lapply(fingerprint_lods,median),use.names=F))
pdf(outputPDF)
boxplot(fingerprint_lods[fingerprint_lod_order],las=3,main='Fingerprint LOD Scores By Sample',xlab='Sample',ylab='LOD Score Distribution',cex.axis=0.65)
qplot(Sample,Selected_Bases_Pct,data=novel_with_highlights,color=selected_samples) + opts(title='On+Near Bait Bases/PF Bases Aligned per Sample')
qplot(Sample,Mean_Target_Coverage,data=novel_with_highlights,color=selected_samples) + opts(title='Mean Target Coverage per Sample')
qplot(Sample,Zero_Coverage_Targets_Pct,data=novel_with_highlights,color=selected_samples) + opts(title='% of Targets with <2x Coverage per Sample')
qplot(Sample,Fold_80_Base_Penalty,data=novel_with_highlights,color=selected_samples) + opts(title='Fold 80 Base Penalty per Sample')
qplot(Sample,Target_Bases_20x_Pct,data=novel_with_highlights,color=selected_samples) + opts(title='% Target Bases Achieving >20x Coverage per Sample')
qplot(Sample,PF_Reads_Pct,data=novel_with_highlights,color=selected_samples) + opts(title='% PF Reads Aligned per Sample')
qplot(Sample,PF_HQ_Error_Rate,data=novel_with_highlights,color=selected_samples) + opts(title='% HQ Bases mismatching the Reference per Sample')
qplot(Sample,Mean_Read_Length,data=novel_with_highlights,color=selected_samples) + opts(title='Median Read Length per Sample')
qplot(Sample,Bad_Cycles,data=novel_with_highlights,color=selected_samples) + opts(title='# Bad Cycles per Sample')
qplot(Sample,Strand_Balance_Pct,data=novel_with_highlights,color=selected_samples) + opts(title='% PF Reads Aligned to the + Strand per Sample')
qplot(Sample,Total_SNPs,data=novel_with_highlights,color=selected_samples) + opts(title='# SNPs called per Sample')
qplot(Sample,dbSNP_Pct,data=novel_with_highlights,color=selected_samples) + opts(title='% SNPs in dbSNP per Sample')
qplot(PCT_DBSNP,data=data,geom="histogram") + opts(title='% SNPs in dbSNP per Sample')
dev.off()
} else {
print('Plotting command-line arguments')
qplot(Sample,PF_Reads_Pct,data=novel_with_highlights,color=selected_samples) + opts(title='% PF Reads Aligned per Sample')
}
#qplot(Sample,Library_Size_HS,data=novel_with_highlights,color=selected_samples) + opts(title='Hybrid Sequencing Library Size per Sample')
#qplot(Sample,MEDIAN_INSERT_SIZE,data=novel_with_highlights,color=selected_samples) + opts(title='Median Insert Size per Sample')