--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/immunerepertoirecombined_imgt/RScript.r	Mon Dec 09 03:45:21 2013 -0500
@@ -0,0 +1,295 @@
+#options( show.error.messages=F, error = function () { cat( geterrmessage(), file=stderr() ); q( "no", 1, F ) } )
+
+args <- commandArgs(trailingOnly = TRUE)
+
+inFile = args[1]
+outFile = args[2]
+outDir = args[3]
+clonalType = args[4]
+
+if (!("gridExtra" %in% rownames(installed.packages()))) {
+	install.packages("gridExtra", repos="http://cran.xl-mirror.nl/") 
+}
+library(gridExtra)
+if (!("ggplot2" %in% rownames(installed.packages()))) {
+	install.packages("ggplot2", repos="http://cran.xl-mirror.nl/") 
+}
+require(ggplot2)
+if (!("plyr" %in% rownames(installed.packages()))) {
+	install.packages("plyr", repos="http://cran.xl-mirror.nl/") 
+}			
+require(plyr)
+
+if (!("data.table" %in% rownames(installed.packages()))) {
+	install.packages("data.table", repos="http://cran.xl-mirror.nl/") 
+}
+library(data.table)
+
+
+test = read.table(inFile, sep="\t", header=TRUE, fill=T)
+
+test = test[test$Sample != "",]
+
+test$Top.V.Gene = gsub("[*]([0-9]+)", "", test$Top.V.Gene)
+test$Top.D.Gene = gsub("[*]([0-9]+)", "", test$Top.D.Gene)
+test$Top.J.Gene = gsub("[*]([0-9]+)", "", test$Top.J.Gene)
+
+#test$VDJCDR3 = do.call(paste, c(test[c("Top.V.Gene", "Top.D.Gene", "Top.J.Gene","CDR3.Seq.DNA")], sep = ":"))
+test$VDJCDR3 = do.call(paste, c(test[unlist(strsplit(clonalType, ","))], sep = ":"))
+
+PROD = test[test$VDJ.Frame != "In-frame with stop codon" & test$VDJ.Frame != "Out-of-frame" & test$CDR3.Found.How != "NOT_FOUND" , ]
+
+NONPROD = test[test$VDJ.Frame == "In-frame with stop codon" | test$VDJ.Frame == "Out-of-frame" | test$CDR3.Found.How == "NOT_FOUND" , ]
+
+#PRODF = PROD[ -1]
+
+PRODF = PROD
+
+#PRODF = unique(PRODF)
+PRODF = PRODF[!duplicated(PRODF$VDJCDR3), ]
+
+PRODFV = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Sample", "Top.V.Gene")])
+PRODFV$Length = as.numeric(PRODFV$Length)
+Total = 0
+Total = ddply(PRODFV, .(Sample), function(x) data.frame(Total = sum(x$Length)))
+PRODFV = merge(PRODFV, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
+PRODFV = ddply(PRODFV, c("Sample", "Top.V.Gene"), summarise, relFreq= (Length*100 / Total))
+
+PRODFD = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Sample", "Top.D.Gene")])
+PRODFD$Length = as.numeric(PRODFD$Length)
+Total = 0
+Total = ddply(PRODFD, .(Sample), function(x) data.frame(Total = sum(x$Length)))
+PRODFD = merge(PRODFD, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
+PRODFD = ddply(PRODFD, c("Sample", "Top.D.Gene"), summarise, relFreq= (Length*100 / Total))
+
+PRODFJ = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Sample", "Top.J.Gene")])
+PRODFJ$Length = as.numeric(PRODFJ$Length)
+Total = 0
+Total = ddply(PRODFJ, .(Sample), function(x) data.frame(Total = sum(x$Length)))
+PRODFJ = merge(PRODFJ, Total, by.x='Sample', by.y='Sample', all.x=TRUE)
+PRODFJ = ddply(PRODFJ, c("Sample", "Top.J.Gene"), summarise, relFreq= (Length*100 / Total))
+
+V = c("v.name\tchr.orderV\nIGHV7-81\t1\nIGHV3-74\t2\nIGHV3-73\t3\nIGHV3-72\t4\nIGHV2-70\t6\nIGHV1-69\t7\nIGHV3-66\t8\nIGHV3-64\t9\nIGHV4-61\t10\nIGHV4-59\t11\nIGHV1-58\t12\nIGHV3-53\t13\nIGHV5-a\t15\nIGHV5-51\t16\nIGHV3-49\t17\nIGHV3-48\t18\nIGHV1-46\t20\nIGHV1-45\t21\nIGHV3-43\t22\nIGHV4-39\t23\nIGHV3-35\t24\nIGHV4-34\t25\nIGHV3-33\t26\nIGHV4-31\t27\nIGHV4-30-4\t28\nIGHV4-30-2\t29\nIGHV3-30-3\t30\nIGHV3-30\t31\nIGHV4-28\t32\nIGHV2-26\t33\nIGHV1-24\t34\nIGHV3-23\t35\nIGHV3-21\t37\nIGHV3-20\t38\nIGHV1-18\t40\nIGHV3-15\t41\nIGHV3-13\t42\nIGHV3-11\t43\nIGHV3-9\t44\nIGHV1-8\t45\nIGHV3-7\t46\nIGHV2-5\t47\nIGHV7-4-1\t48\nIGHV4-4\t49\nIGHV4-b\t50\nIGHV1-3\t51\nIGHV1-2\t52\nIGHV6-1\t53")
+tcV = textConnection(V)
+Vchain = read.table(tcV, sep="\t", header=TRUE)
+PRODFV = merge(PRODFV, Vchain, by.x='Top.V.Gene', by.y='v.name', all.x=TRUE)
+close(tcV)
+
+D = c("v.name\tchr.orderD\nIGHD1-1\t1\nIGHD2-2\t2\nIGHD3-3\t3\nIGHD6-6\t4\nIGHD1-7\t5\nIGHD2-8\t6\nIGHD3-9\t7\nIGHD3-10\t8\nIGHD4-11\t9\nIGHD5-12\t10\nIGHD6-13\t11\nIGHD1-14\t12\nIGHD2-15\t13\nIGHD3-16\t14\nIGHD4-17\t15\nIGHD5-18\t16\nIGHD6-19\t17\nIGHD1-20\t18\nIGHD2-21\t19\nIGHD3-22\t20\nIGHD4-23\t21\nIGHD5-24\t22\nIGHD6-25\t23\nIGHD1-26\t24\nIGHD7-27\t25")
+tcD = textConnection(D)
+Dchain = read.table(tcD, sep="\t", header=TRUE)
+PRODFD = merge(PRODFD, Dchain, by.x='Top.D.Gene', by.y='v.name', all.x=TRUE)
+close(tcD)
+
+
+J = c("v.name\tchr.orderJ\nIGHJ1\t1\nIGHJ2\t2\nIGHJ3\t3\nIGHJ4\t4\nIGHJ5\t5\nIGHJ6\t6")
+tcJ = textConnection(J)
+Jchain = read.table(tcJ, sep="\t", header=TRUE)
+PRODFJ = merge(PRODFJ, Jchain, by.x='Top.J.Gene', by.y='v.name', all.x=TRUE)
+close(tcJ)
+
+setwd(outDir)
+
+pV = ggplot(PRODFV)
+pV = pV + geom_bar( aes( x=factor(reorder(Top.V.Gene, chr.orderV)), y=relFreq, fill=Sample), stat='identity', position="dodge") + theme(axis.text.x = element_text(angle = 90, hjust = 1))
+pV = pV + xlab("Summary of V gene") + ylab("Frequency") + ggtitle("Relative frequency of V gene usage")
+
+png("VPlot.png",width = 1280, height = 720)
+pV
+dev.off();
+
+pD = ggplot(PRODFD)
+pD = pD + geom_bar( aes( x=factor(reorder(Top.D.Gene, chr.orderD)), y=relFreq, fill=Sample), stat='identity', position="dodge") + theme(axis.text.x = element_text(angle = 90, hjust = 1))
+pD = pD + xlab("Summary of D gene") + ylab("Frequency") + ggtitle("Relative frequency of D gene usage")
+
+png("DPlot.png",width = 800, height = 600)
+pD
+dev.off();
+
+pJ = ggplot(PRODFJ)
+pJ = pJ + geom_bar( aes( x=factor(reorder(Top.J.Gene, chr.orderJ)), y=relFreq, fill=Sample), stat='identity', position="dodge") + theme(axis.text.x = element_text(angle = 90, hjust = 1))
+pJ = pJ + xlab("Summary of J gene") + ylab("Frequency") + ggtitle("Relative frequency of J gene usage")
+
+png("JPlot.png",width = 800, height = 600)
+pJ
+dev.off();
+
+revVchain = Vchain
+revDchain = Dchain
+revVchain$chr.orderV = rev(revVchain$chr.orderV)
+revDchain$chr.orderD = rev(revDchain$chr.orderD)
+
+plotVD <- function(dat){
+	if(length(dat[,1]) == 0){
+		return()
+	}
+	img = ggplot() + 
+	geom_tile(data=dat, aes(x=factor(reorder(Top.D.Gene, chr.orderD)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) + 
+	theme(axis.text.x = element_text(angle = 90, hjust = 1)) + 
+	scale_fill_gradient(low="gold", high="blue", na.value="white") + 
+	ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) + 
+	xlab("D genes") + 
+	ylab("V Genes")
+	
+	png(paste("HeatmapVD_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Dchain$v.name)), height=100+(15*length(Vchain$v.name)))
+	print(img)
+	dev.off()
+}
+
+VandDCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.D.Gene", "Sample")])
+
+VandDCount$l = log(VandDCount$Length)
+maxVD = data.frame(data.table(VandDCount)[, list(max=max(l)), by=c("Sample")])
+VandDCount = merge(VandDCount, maxVD, by.x="Sample", by.y="Sample", all.x=T)
+VandDCount$relLength = VandDCount$l / VandDCount$max
+
+cartegianProductVD = expand.grid(Top.V.Gene = Vchain$v.name, Top.D.Gene = Dchain$v.name, Sample = unique(test$Sample))
+
+completeVD = merge(VandDCount, cartegianProductVD, all.y=TRUE)
+completeVD = merge(completeVD, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
+completeVD = merge(completeVD, Dchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
+VDList = split(completeVD, f=completeVD[,"Sample"])
+
+lapply(VDList, FUN=plotVD)
+
+
+
+plotVJ <- function(dat){
+	if(length(dat[,1]) == 0){
+		return()
+	}
+	img = ggplot() + 
+	geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) + 
+	theme(axis.text.x = element_text(angle = 90, hjust = 1)) + 
+	scale_fill_gradient(low="gold", high="blue", na.value="white") + 
+	ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) + 
+	xlab("J genes") + 
+	ylab("V Genes")
+	
+	png(paste("HeatmapVJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Vchain$v.name)))
+	print(img)
+	dev.off()
+}
+
+VandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.J.Gene", "Sample")])
+
+VandJCount$l = log(VandJCount$Length)
+maxVJ = data.frame(data.table(VandJCount)[, list(max=max(l)), by=c("Sample")])
+VandJCount = merge(VandJCount, maxVJ, by.x="Sample", by.y="Sample", all.x=T)
+VandJCount$relLength = VandJCount$l / VandJCount$max
+
+cartegianProductVJ = expand.grid(Top.V.Gene = Vchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(test$Sample))
+
+completeVJ = merge(VandJCount, cartegianProductVJ, all.y=TRUE)
+completeVJ = merge(completeVJ, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE)
+completeVJ = merge(completeVJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
+VJList = split(completeVJ, f=completeVJ[,"Sample"])
+lapply(VJList, FUN=plotVJ)
+
+plotDJ <- function(dat){
+	if(length(dat[,1]) == 0){
+		return()
+	}
+	img = ggplot() + 
+	geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.D.Gene, chr.orderD)), fill=relLength)) + 
+	theme(axis.text.x = element_text(angle = 90, hjust = 1)) + 
+	scale_fill_gradient(low="gold", high="blue", na.value="white") + 
+	ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) + 
+	xlab("J genes") + 
+	ylab("D Genes")
+	
+	png(paste("HeatmapDJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$v.name)), height=100+(15*length(Dchain$v.name)))
+	print(img)
+	dev.off()
+}
+
+DandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.D.Gene", "Top.J.Gene", "Sample")])
+
+DandJCount$l = log(DandJCount$Length)
+maxDJ = data.frame(data.table(DandJCount)[, list(max=max(l)), by=c("Sample")])
+DandJCount = merge(DandJCount, maxDJ, by.x="Sample", by.y="Sample", all.x=T)
+DandJCount$relLength = DandJCount$l / DandJCount$max
+
+cartegianProductDJ = expand.grid(Top.D.Gene = Dchain$v.name, Top.J.Gene = Jchain$v.name, Sample = unique(test$Sample))
+
+completeDJ = merge(DandJCount, cartegianProductDJ, all.y=TRUE)
+completeDJ = merge(completeDJ, revDchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE)
+completeDJ = merge(completeDJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE)
+DJList = split(completeDJ, f=completeDJ[,"Sample"])
+lapply(DJList, FUN=plotDJ)
+
+
+sampleFile <- file("samples.txt")
+un = unique(test$Sample)
+un = paste(un, sep="\n")
+writeLines(un, sampleFile)
+close(sampleFile)
+
+
+if("Replicate" %in% colnames(test))
+{
+	clonalityFrame = PROD
+	clonalityFrame$ReplicateConcat = do.call(paste, c(clonalityFrame[c("VDJCDR3", "Sample", "Replicate")], sep = ":"))
+	clonalityFrame = clonalityFrame[!duplicated(clonalityFrame$ReplicateConcat), ]
+	clonalFreq = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "VDJCDR3")])
+	clonalFreqCount = data.frame(data.table(clonalFreq)[, list(Count=.N), by=c("Sample", "Type")])
+	clonalFreqCount$realCount = clonalFreqCount$Type * clonalFreqCount$Count
+	clonalSum = data.frame(data.table(clonalFreqCount)[, list(Reads=sum(realCount)), by=c("Sample")])
+	clonalFreqCount = merge(clonalFreqCount, clonalSum, by.x="Sample", by.y="Sample")
+
+	ct = c('Type\tWeight\n2\t1\n3\t3\n4\t6\n5\t10\n6\t15')
+	tcct = textConnection(ct)
+	CT  = read.table(tcct, sep="\t", header=TRUE)
+	close(tcct)
+	clonalFreqCount = merge(clonalFreqCount, CT, by.x="Type", by.y="Type", all.x=T)
+	clonalFreqCount$WeightedCount = clonalFreqCount$Count * clonalFreqCount$Weight
+
+	ReplicateReads = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "Replicate", "VDJCDR3")])
+	ReplicateReads = data.frame(data.table(ReplicateReads)[, list(Reads=.N), by=c("Sample", "Replicate")])
+	ReplicateReads$squared = ReplicateReads$Reads * ReplicateReads$Reads
+
+	ReplicatePrint <- function(dat){
+		write.table(dat[-1], paste("ReplicateReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
+	}
+
+	ReplicateSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
+	lapply(ReplicateSplit, FUN=ReplicatePrint)
+
+	ReplicateReads = data.frame(data.table(ReplicateReads)[, list(ReadsSum=sum(Reads), ReadsSquaredSum=sum(squared)), by=c("Sample")])
+	clonalFreqCount = merge(clonalFreqCount, ReplicateReads, by.x="Sample", by.y="Sample", all.x=T)
+
+
+	ReplicateSumPrint <- function(dat){
+		write.table(dat[-1], paste("ReplicateSumReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
+	}
+
+	ReplicateSumSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"])
+	lapply(ReplicateSumSplit, FUN=ReplicateSumPrint)
+
+	clonalFreqCountSum = data.frame(data.table(clonalFreqCount)[, list(Numerator=sum(WeightedCount, na.rm=T)), by=c("Sample")])
+	clonalFreqCount = merge(clonalFreqCount, clonalFreqCountSum, by.x="Sample", by.y="Sample", all.x=T)
+
+	clonalFreqCount$Denominator = (((clonalFreqCount$ReadsSum * clonalFreqCount$ReadsSum) - clonalFreqCount$ReadsSquaredSum) / 2)
+	clonalFreqCount$Result = (clonalFreqCount$Numerator + 1) / (clonalFreqCount$Denominator + 1)
+
+	ClonalityScorePrint <- function(dat){
+		write.table(dat$Result, paste("ClonalityScore_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
+	}
+
+	clonalityScore = clonalFreqCount[c("Sample", "Result")]
+	clonalityScore = unique(clonalityScore)
+
+	clonalityScoreSplit = split(clonalityScore, f=clonalityScore[,"Sample"])
+	lapply(clonalityScoreSplit, FUN=ClonalityScorePrint)
+
+	clonalityOverview = clonalFreqCount[c("Sample", "Type", "Count", "Weight", "WeightedCount")]
+
+
+
+	ClonalityOverviewPrint <- function(dat){
+		write.table(dat[-1], paste("ClonalityOverView_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F)
+	}
+
+	clonalityOverviewSplit = split(clonalityOverview, f=clonalityOverview$Sample)
+	lapply(clonalityOverviewSplit, FUN=ClonalityOverviewPrint)
+}