Mercurial > repos > davidvanzessen > complete_immunerepertoire_igg
diff RScript_t.r @ 1:778a9d130904 draft
Uploaded
| author | davidvanzessen |
|---|---|
| date | Thu, 04 Sep 2014 07:46:23 -0400 |
| parents | |
| children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/RScript_t.r Thu Sep 04 07:46:23 2014 -0400 @@ -0,0 +1,499 @@ +#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] +species = args[5] +locus = args[6] +selection = args[7] + +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/") +} +library(ggplot2) +if (!("plyr" %in% rownames(installed.packages()))) { + install.packages("plyr", repos="http://cran.xl-mirror.nl/") +} +library(plyr) + +if (!("data.table" %in% rownames(installed.packages()))) { + install.packages("data.table", repos="http://cran.xl-mirror.nl/") +} +library(data.table) + +if (!("reshape2" %in% rownames(installed.packages()))) { + install.packages("reshape2", repos="http://cran.xl-mirror.nl/") +} +library(reshape2) + + +test = read.table(inFile, sep="\t", header=TRUE, fill=T, comment.char="") + +test = test[test$Sample != "",] + +print("test1\n") + +test$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" , ] +if("Functionality" %in% colnames(test)) { + PROD = test[test$Functionality == "productive" | test$Functionality == "productive (see comment)", ] +} + +NONPROD = test[test$VDJ.Frame == "In-frame with stop codon" | test$VDJ.Frame == "Out-of-frame" | test$CDR3.Found.How == "NOT_FOUND" , ] + +#PRODF = PROD[ -1] + +PRODF = PROD +print("test2\n") +#PRODF = unique(PRODF) +if(any(grepl(pattern="_", x=PRODF$ID))){ #dumb and way to simple + PRODF$freq = gsub("^[0-9]+_", "", PRODF$ID) + PRODF$freq = gsub("_.*", "", PRODF$freq) + PRODF$freq = as.numeric(PRODF$freq) + if(any(is.na(PRODF$freq))){ #fix the dumbness if it fails + PRODF$freq = 1 + if(selection == "unique"){ + PRODF = PRODF[!duplicated(PRODF$VDJCDR3), ] + } + } +} else { + PRODF$freq = 1 + if(selection == "unique"){ + PRODF = PRODF[!duplicated(PRODF$VDJCDR3), ] + } +} + +PRODFV = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.V.Gene")]) +PRODFV$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=sum(freq)), 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$Length))) +PRODFD = merge(PRODFD, Total, by.x='Sample', by.y='Sample', all.x=TRUE) +PRODFD = ddply(PRODFD, c("Sample", "Top.D.Gene"), summarise, relFreq= (Length*100 / Total)) + +PRODFJ = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.J.Gene")]) +PRODFJ$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\n") +D = c("v.name\tchr.orderD\n") +J = c("v.name\tchr.orderJ\n") + +print("test3\n") + +if(species == "human"){ + if(locus == "trb"){ + V = c("v.name\tchr.orderV\nTRBV2\t1\nTRBV3-1\t2\nTRBV4-1\t3\nTRBV5-1\t4\nTRBV6-1\t5\nTRBV4-2\t6\nTRBV6-2\t7\nTRBV4-3\t8\nTRBV6-3\t9\nTRBV7-2\t10\nTRBV6-4\t11\nTRBV7-3\t12\nTRBV9\t13\nTRBV10-1\t14\nTRBV11-1\t15\nTRBV10-2\t16\nTRBV11-2\t17\nTRBV6-5\t18\nTRBV7-4\t19\nTRBV5-4\t20\nTRBV6-6\t21\nTRBV5-5\t22\nTRBV7-6\t23\nTRBV5-6\t24\nTRBV6-8\t25\nTRBV7-7\t26\nTRBV6-9\t27\nTRBV7-8\t28\nTRBV5-8\t29\nTRBV7-9\t30\nTRBV13\t31\nTRBV10-3\t32\nTRBV11-3\t33\nTRBV12-3\t34\nTRBV12-4\t35\nTRBV12-5\t36\nTRBV14\t37\nTRBV15\t38\nTRBV16\t39\nTRBV18\t40\nTRBV19\t41\nTRBV20-1\t42\nTRBV24-1\t43\nTRBV25-1\t44\nTRBV27\t45\nTRBV28\t46\nTRBV29-1\t47\nTRBV30\t48") + D = c("v.name\tchr.orderD\nTRBD1\t1\nTRBD2\t2\n") + J = c("v.name\tchr.orderJ\nTRBJ1-1\t1\nTRBJ1-2\t2\nTRBJ1-3\t3\nTRBJ1-4\t4\nTRBJ1-5\t5\nTRBJ1-6\t6\nTRBJ2-1\t7\nTRBJ2-2\t8\nTRBJ2-3\t9\nTRBJ2-4\t10\nTRBJ2-5\t11\nTRBJ2-6\t12\nTRBJ2-7\t13") + } else if (locus == "tra"){ + V = c("v.name\tchr.orderVTRAV1-1\t1\nTRAV1-2\t2\nTRAV2\t3\nTRAV3\t4\nTRAV4\t5\nTRAV5\t6\nTRAV6\t7\nTRAV7\t8\nTRAV8-1\t9\nTRAV9-1\t10\nTRAV10\t11\nTRAV12-1\t12\nTRAV8-2\t13\nTRAV8-3\t14\nTRAV13-1\t15\nTRAV12-2\t16\nTRAV8-4\t17\nTRAV13-2\t18\nTRAV14/DV4\t19\nTRAV9-2\t20\nTRAV12-3\t21\nTRAV8-6\t22\nTRAV16\t23\nTRAV17\t24\nTRAV18\t25\nTRAV19\t26\nTRAV20\t27\nTRAV21\t28\nTRAV22\t29\nTRAV23/DV6\t30\nTRAV24\t31\nTRAV25\t32\nTRAV26-1\t33\nTRAV27\t34\nTRAV29/DV5\t35\nTRAV30\t36\nTRAV26-2\t37\nTRAV34\t38\nTRAV35\t39\nTRAV36/DV7\t40\nTRAV38-1\t41\nTRAV38-2/DV8\t42\nTRAV39\t43\nTRAV40\t44\nTRAV41\t45\n") + D = c("v.name\tchr.orderD\n") + J = c("v.name\tchr.orderJ\nTRAJ57\t1\nTRAJ56\t2\nTRAJ54\t3\nTRAJ53\t4\nTRAJ52\t5\nTRAJ50\t6\nTRAJ49\t7\nTRAJ48\t8\nTRAJ47\t9\nTRAJ46\t10\nTRAJ45\t11\nTRAJ44\t12\nTRAJ43\t13\nTRAJ42\t14\nTRAJ41\t15\nTRAJ40\t16\nTRAJ39\t17\nTRAJ38\t18\nTRAJ37\t19\nTRAJ36\t20\nTRAJ34\t21\nTRAJ33\t22\nTRAJ32\t23\nTRAJ31\t24\nTRAJ30\t25\nTRAJ29\t26\nTRAJ28\t27\nTRAJ27\t28\nTRAJ26\t29\nTRAJ24\t30\nTRAJ23\t31\nTRAJ22\t32\nTRAJ21\t33\nTRAJ20\t34\nTRAJ18\t35\nTRAJ17\t36\nTRAJ16\t37\nTRAJ15\t38\nTRAJ14\t39\nTRAJ13\t40\nTRAJ12\t41\nTRAJ11\t42\nTRAJ10\t43\nTRAJ9\t44\nTRAJ8\t45\nTRAJ7\t46\nTRAJ6\t47\nTRAJ5\t48\nTRAJ4\t49\nTRAJ3\t50") + } else if (locus == "trg"){ + V = c("v.name\tchr.orderV\nTRGV9\t1\nTRGV8\t2\nTRGV5\t3\nTRGV4\t4\nTRGV3\t5\nTRGV2\t6") + D = c("v.name\tchr.orderD\n") + J = c("v.name\tchr.orderJ\nTRGJ2\t1\nTRGJP2\t2\nTRGJ1\t3\nTRGJP1\t4") + } else if (locus == "trd"){ + V = c("v.name\tchr.orderV\nTRDV1\t1\nTRDV2\t2\nTRDV3\t3") + D = c("v.name\tchr.orderD\nTRDD1\t1\nTRDD2\t2\nTRDD3\t3") + J = c("v.name\tchr.orderJ\nTRDJ1\t1\nTRDJ4\t2\nTRDJ2\t3\nTRDJ3\t4") + } +} else if (species == "mouse"){ + if(locus == "trb"){ + cat("mouse trb not yet implemented") + } else if (locus == "tra"){ + cat("mouse tra not yet implemented") + } else if (locus == "trg"){ + cat("mouse trg not yet implemented") + } else if (locus == "trd"){ + cat("mouse trd not yet implemented") + } +} +useD = TRUE +if(species == "human" && locus == "tra"){ + useD = FALSE + cat("No D Genes in this species/locus") +} + +print("test4\n") + +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) + + +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) + + + +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) + +write.table(PRODF, "allUnique.csv", sep=",",quote=F,row.names=F,col.names=T) + +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") +write.table(x=PRODFV, file="VFrequency.csv", sep=",",quote=F,row.names=F,col.names=T) + +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") +write.table(x=PRODFD, file="DFrequency.csv", sep=",",quote=F,row.names=F,col.names=T) + +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") +write.table(x=PRODFJ, file="JFrequency.csv", sep=",",quote=F,row.names=F,col.names=T) + +png("JPlot.png",width = 800, height = 600) +pJ +dev.off(); + +print("test5\n") + +VGenes = PRODF[,c("Sample", "Top.V.Gene", "freq")] +VGenes$Top.V.Gene = gsub("-.*", "", VGenes$Top.V.Gene) +VGenes = data.frame(data.table(VGenes)[, list(Count=sum(freq)), by=c("Sample", "Top.V.Gene")]) +TotalPerSample = data.frame(data.table(VGenes)[, list(total=sum(.SD$Count)), by=Sample]) +VGenes = merge(VGenes, TotalPerSample, by="Sample") +VGenes$Frequency = VGenes$Count * 100 / VGenes$total +VPlot = ggplot(VGenes) +VPlot = VPlot + geom_bar(aes( x = Top.V.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) + + ggtitle("Distribution of V gene families") + + ylab("Percentage of sequences") +png("VFPlot.png") +VPlot +dev.off(); +write.table(x=VGenes, file="VFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T) + +DGenes = PRODF[,c("Sample", "Top.D.Gene", "freq")] +DGenes$Top.D.Gene = gsub("-.*", "", DGenes$Top.D.Gene) +DGenes = data.frame(data.table(DGenes)[, list(Count=sum(freq)), by=c("Sample", "Top.D.Gene")]) +TotalPerSample = data.frame(data.table(DGenes)[, list(total=sum(.SD$Count)), by=Sample]) +DGenes = merge(DGenes, TotalPerSample, by="Sample") +DGenes$Frequency = DGenes$Count * 100 / DGenes$total +DPlot = ggplot(DGenes) +DPlot = DPlot + geom_bar(aes( x = Top.D.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) + + ggtitle("Distribution of D gene families") + + ylab("Percentage of sequences") +png("DFPlot.png") +DPlot +dev.off(); +write.table(x=DGenes, file="DFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T) + +JGenes = PRODF[,c("Sample", "Top.J.Gene", "freq")] +JGenes$Top.J.Gene = gsub("-.*", "", JGenes$Top.J.Gene) +JGenes = data.frame(data.table(JGenes)[, list(Count=sum(freq)), by=c("Sample", "Top.J.Gene")]) +TotalPerSample = data.frame(data.table(JGenes)[, list(total=sum(.SD$Count)), by=Sample]) +JGenes = merge(JGenes, TotalPerSample, by="Sample") +JGenes$Frequency = JGenes$Count * 100 / JGenes$total +JPlot = ggplot(JGenes) +JPlot = JPlot + geom_bar(aes( x = Top.J.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) + + ggtitle("Distribution of J gene families") + + ylab("Percentage of sequences") +png("JFPlot.png") +JPlot +dev.off(); +write.table(x=JGenes, file="JFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T) + +CDR3Length = data.frame(data.table(PRODF)[, list(Count=sum(freq)), by=c("Sample", "CDR3.Length.DNA")]) +TotalPerSample = data.frame(data.table(CDR3Length)[, list(total=sum(.SD$Count)), by=Sample]) +CDR3Length = merge(CDR3Length, TotalPerSample, by="Sample") +CDR3Length$Frequency = CDR3Length$Count * 100 / CDR3Length$total +CDR3LengthPlot = ggplot(CDR3Length) +CDR3LengthPlot = CDR3LengthPlot + geom_bar(aes( x = CDR3.Length.DNA, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) + + ggtitle("Length distribution of CDR3") + + xlab("CDR3 Length") + + ylab("Percentage of sequences") +png("CDR3LengthPlot.png",width = 1280, height = 720) +CDR3LengthPlot +dev.off() +write.table(x=CDR3Length, file="CDR3LengthPlot.csv", sep=",",quote=F,row.names=F,col.names=T) + +revVchain = Vchain +revDchain = Dchain +revVchain$chr.orderV = rev(revVchain$chr.orderV) +revDchain$chr.orderD = rev(revDchain$chr.orderD) + +print("test6\n") + +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() + write.table(x=acast(dat, Top.V.Gene~Top.D.Gene, value.var="Length"), file=paste("HeatmapVD_", unique(dat[3])[1,1], ".csv", sep=""), sep=",",quote=F,row.names=T,col.names=NA) +} + +VandDCount = data.frame(data.table(PRODF)[, list(Length=sum(freq)), 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() + write.table(x=acast(dat, Top.V.Gene~Top.J.Gene, value.var="Length"), file=paste("HeatmapVJ_", unique(dat[3])[1,1], ".csv", sep=""), sep=",",quote=F,row.names=T,col.names=NA) +} + +VandJCount = data.frame(data.table(PRODF)[, list(Length=sum(freq)), 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() + write.table(x=acast(dat, Top.D.Gene~Top.J.Gene, value.var="Length"), file=paste("HeatmapDJ_", unique(dat[3])[1,1], ".csv", sep=""), sep=",",quote=F,row.names=T,col.names=NA) +} + +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$Sample) +un = paste(un, sep="\n") +writeLines(un, sampleFile) +close(sampleFile) + +print("test7\n") + +if("Replicate" %in% colnames(test)) +{ + clonalityFrame = PROD + clonalityFrame$ReplicateConcat = do.call(paste, c(clonalityFrame[c("VDJCDR3", "Sample", "Replicate")], sep = ":")) + clonalityFrame = clonalityFrame[!duplicated(clonalityFrame$ReplicateConcat), ] + write.table(clonalityFrame, "clonalityComplete.csv", sep=",",quote=F,row.names=F,col.names=T) + + ClonalitySampleReplicatePrint <- function(dat){ + write.table(dat, paste("clonality_", unique(dat$Sample) , "_", unique(dat$Replicate), ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=T) + } + + clonalityFrameSplit = split(clonalityFrame, f=clonalityFrame[,c("Sample", "Replicate")]) + #lapply(clonalityFrameSplit, FUN=ClonalitySampleReplicatePrint) + + ClonalitySamplePrint <- function(dat){ + write.table(dat, paste("clonality_", unique(dat$Sample) , ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=T) + } + + clonalityFrameSplit = split(clonalityFrame, f=clonalityFrame[,"Sample"]) + #lapply(clonalityFrameSplit, FUN=ClonalitySamplePrint) + + 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")]) + clonalFreqCount$Reads = as.numeric(clonalFreqCount$Reads) + ReplicateReads$squared = ReplicateReads$Reads * ReplicateReads$Reads + + ReplicatePrint <- function(dat){ + write.table(dat[-1], paste("ReplicateReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F) + } + + ReplicateSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"]) + lapply(ReplicateSplit, FUN=ReplicatePrint) + + ReplicateReads = data.frame(data.table(ReplicateReads)[, list(ReadsSum=sum(Reads), ReadsSquaredSum=sum(squared)), by=c("Sample")]) + clonalFreqCount = merge(clonalFreqCount, ReplicateReads, by.x="Sample", by.y="Sample", all.x=T) + + + ReplicateSumPrint <- function(dat){ + write.table(dat[-1], paste("ReplicateSumReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F) + } + + ReplicateSumSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"]) + lapply(ReplicateSumSplit, FUN=ReplicateSumPrint) + + writeClonalitySequences <- function(dat){ + for(i in c(2,3,4,5,6)){ + fltr = dat[dat$Type == i,] + if(length(fltr[,1]) == 0){ + next + } + tmp = clonalityFrame[clonalityFrame$Sample == fltr$Sample[1] & clonalityFrame$VDJCDR3 %in% fltr$VDJCDR3,] + tmp = tmp[order(tmp$VDJCDR3),] + write.table(tmp, paste("ClonalitySequences_", unique(dat[1])[1,1] , "_", i, ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=T) + } + } + freqsplt = split(clonalFreq[clonalFreq$Type > 1,], clonalFreq[clonalFreq$Type > 1,]$Sample) + lapply(freqsplt, FUN=writeClonalitySequences) + + 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$ReadsSum = as.numeric(clonalFreqCount$ReadsSum) #prevent integer overflow + 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) +} + +print("test8\n") + +if("Functionality" %in% colnames(test)) +{ + newData = data.frame(data.table(PROD)[,list(unique=.N, + VH.DEL=mean(X3V.REGION.trimmed.nt.nb), + P1=mean(P3V.nt.nb), + N1=mean(N1.REGION.nt.nb), + P2=mean(P5D.nt.nb), + DEL.DH=mean(X5D.REGION.trimmed.nt.nb), + DH.DEL=mean(X3D.REGION.trimmed.nt.nb), + P3=mean(P3D.nt.nb), + N2=mean(N2.REGION.nt.nb), + P4=mean(P5J.nt.nb), + DEL.JH=mean(X5J.REGION.trimmed.nt.nb), + Total.Del=( mean(X3V.REGION.trimmed.nt.nb) + + mean(X5D.REGION.trimmed.nt.nb) + + mean(X3D.REGION.trimmed.nt.nb) + + mean(X5J.REGION.trimmed.nt.nb)), + + Total.N=( mean(N1.REGION.nt.nb) + + mean(N2.REGION.nt.nb)), + + Total.P=( mean(P3V.nt.nb) + + mean(P5D.nt.nb) + + mean(P3D.nt.nb) + + mean(P5J.nt.nb))), + by=c("Sample")]) + write.table(newData, "junctionAnalysis.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F) +} + +print("test9\n")