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

Now produces an expanded table at the start, as well 

git-svn-id: file:///humgen/gsa-scr1/gsa-engineering/svn_contents/trunk@6017 348d0f76-0448-11de-a6fe-93d51630548a
This commit is contained in:
depristo 2011-06-20 13:45:08 +00:00
parent e8738f95c5
commit a37e9bdbd4
1 changed files with 26 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
R/exomeQC.R
View File

@ -74,6 +74,27 @@ summaryTable <- function(metricsBySites, metricsBySample) {
return(table) return(table)
} }
sampleSummaryTable <- function(metricsBySample) {
# SNP summary statistics
raw <- melt(metricsBySamples, id.vars=c("Novelty", "Sample"), measure.vars=c("nProcessedLoci", "nSNPs", "tiTvRatio", "nIndels", "deletionInsertionRatio"))
table = cast(raw, Novelty ~ variable, mean)
table$nSNPs <- round(table$nSNPs, 0)
table$nIndels <- round(table$nIndels, 0)
table$tiTvRatio <- round(table$tiTvRatio, 2)
table$deletionInsertionRatio <- round(table$deletionInsertionRatio, 2)
colnames(table) <- c("Novelty", "Target size (bp)", "No. SNPs", "Ti/Tv", "No. Indels", "deletion/insertion ratio")
return(table)
}
overallSummaryTable <- function(metricsBySites, metricsBySamples) {
sitesSummary <- as.data.frame(summaryTable(metricsBySites, metricsBySamples))
sitesSummary$Metric.Type <- "Sites"
sampleSummary <- as.data.frame(sampleSummaryTable(metricsBySamples))
sampleSummary$Metric.Type <- "Per-sample avg."
# that last item puts the metric.type second in the list
return(rbind(sitesSummary, sampleSummary)[, c(1,7,2,3,4,5,6)])
}
summaryPlots <- function(metricsBySites) { summaryPlots <- function(metricsBySites) {
name = "SNP and Indel count by novelty and allele frequency" name = "SNP and Indel count by novelty and allele frequency"
molten = melt(subset(metricsBySites$byAC$CountVariants, Novelty != "all" & AC > 0), id.vars=c("Novelty", "AC"), measure.vars=c(c("nSNPs", "nIndels"))) molten = melt(subset(metricsBySites$byAC$CountVariants, Novelty != "all" & AC > 0), id.vars=c("Novelty", "AC"), measure.vars=c(c("nSNPs", "nIndels")))
@ -255,8 +276,10 @@ if ( ! is.na(outputPDF) ) {
} }
# Table of overall counts and quality # Table of overall counts and quality
textplot(as.data.frame(summaryTable(metricsBySites)), show.rownames=F) textplot(overallSummaryTable(metricsBySites), show.rownames=F)
title(paste("Overall summary metrics for project", ProjectName), cex=3) title(paste("Summary metrics for project", ProjectName), cex=3)
# textplot(as.data.frame(sampleSummaryTable(metricsBySamples)), show.rownames=F)
# title(paste("Summary metrics per sample for project", ProjectName), cex=3)
summaryPlots(metricsBySites) summaryPlots(metricsBySites)
perSamplePlots(metricsBySamples) perSamplePlots(metricsBySamples)
@ -265,4 +288,3 @@ if ( ! is.na(outputPDF) ) {
dev.off() dev.off()
} }