Mercurial > repos > davidvanzessen > complete_immunerepertoire_igg
diff RScript_b.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_b.r Thu Sep 04 07:46:23 2014 -0400 @@ -0,0 +1,462 @@ +#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$Sample != "",] + +test$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$CDR3.Found.How == "NOT_FOUND" , ] + +#PRODF = PROD[ -1] + +PRODF = PROD + +#PRODF = unique(PRODF) + + + +if(selection == "unique"){ + PRODF = PRODF[!duplicated(PRODF$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") +D = c("v.name\tchr.orderD") +J = c("v.name\tchr.orderJ") + +if(species == "human"){ + if(locus == "igh"){ + V = c("v.name\tchr.orderV\nIGHV3-74\t1\nIGHV3-73\t2\nIGHV3-72\t3\nIGHV2-70\t4\nIGHV1-69D\t5\nIGHV1-69-2\t6\nIGHV2-70D\t7\nIGHV1-69\t8\nIGHV3-66\t9\nIGHV3-64\t10\nIGHV4-61\t11\nIGHV4-59\t12\nIGHV1-58\t13\nIGHV3-53\t14\nIGHV5-51\t15\nIGHV3-49\t16\nIGHV3-48\t17\nIGHV1-46\t18\nIGHV1-45\t19\nIGHV3-43\t20\nIGHV4-39\t21\nIGHV3-43D\t22\nIGHV4-38-2\t23\nIGHV4-34\t24\nIGHV3-33\t25\nIGHV4-31\t26\nIGHV3-30-5\t27\nIGHV4-30-4\t28\nIGHV3-30-3\t29\nIGHV4-30-2\t30\nIGHV4-30-1\t31\nIGHV3-30\t32\nIGHV4-28\t33\nIGHV2-26\t34\nIGHV1-24\t35\nIGHV3-23D\t36\nIGHV3-23\t37\nIGHV3-21\t38\nIGHV3-20\t39\nIGHV1-18\t40\nIGHV3-15\t41\nIGHV3-13\t42\nIGHV3-11\t43\nIGHV5-10-1\t44\nIGHV3-9\t45\nIGHV1-8\t46\nIGHV3-64D\t47\nIGHV3-7\t48\nIGHV2-5\t49\nIGHV7-4-1\t50\nIGHV4-4\t51\nIGHV1-3\t52\nIGHV1-2\t53\nIGHV6-1\t54") + D = c("v.name\tchr.orderD\nIGHD1-7\t1\nIGHD2-8\t2\nIGHD3-9\t3\nIGHD3-10\t4\nIGHD5-12\t5\nIGHD6-13\t6\nIGHD2-15\t7\nIGHD3-16\t8\nIGHD4-17\t9\nIGHD5-18\t10\nIGHD6-19\t11\nIGHD1-20\t12\nIGHD2-21\t13\nIGHD3-22\t14\nIGHD5-24\t15\nIGHD6-25\t16\nIGHD1-26\t17\nIGHD7-27\t18") + J = c("v.name\tchr.orderJ\nIGHJ1\t1\nIGHJ2\t2\nIGHJ3\t3\nIGHJ4\t4\nIGHJ5\t5\nIGHJ6\t6") + } else if (locus == "igk"){ + V = c("v.name\tchr.orderV\nIGKV3D-7\t1\nIGKV1D-8\t2\nIGKV1D-43\t3\nIGKV3D-11\t4\nIGKV1D-12\t5\nIGKV1D-13\t6\nIGKV3D-15\t7\nIGKV1D-16\t8\nIGKV1D-17\t9\nIGKV3D-20\t10\nIGKV2D-26\t11\nIGKV2D-28\t12\nIGKV2D-29\t13\nIGKV2D-30\t14\nIGKV1D-33\t15\nIGKV1D-39\t16\nIGKV2D-40\t17\nIGKV2-40\t18\nIGKV1-39\t19\nIGKV1-33\t20\nIGKV2-30\t21\nIGKV2-29\t22\nIGKV2-28\t23\nIGKV1-27\t24\nIGKV2-24\t25\nIGKV3-20\t26\nIGKV1-17\t27\nIGKV1-16\t28\nIGKV3-15\t29\nIGKV1-13\t30\nIGKV1-12\t31\nIGKV3-11\t32\nIGKV1-9\t33\nIGKV1-8\t34\nIGKV1-6\t35\nIGKV1-5\t36\nIGKV5-2\t37\nIGKV4-1\t38") + D = c("v.name\tchr.orderD\n") + J = c("v.name\tchr.orderJ\nIGKJ1\t1\nIGKJ2\t2\nIGKJ3\t3\nIGKJ4\t4\nIGKJ5\t5") + } else if (locus == "igl"){ + V = c("v.name\tchr.orderV\nIGLV4-69\t1\nIGLV8-61\t2\nIGLV4-60\t3\nIGLV6-57\t4\nIGLV5-52\t5\nIGLV1-51\t6\nIGLV9-49\t7\nIGLV1-47\t8\nIGLV7-46\t9\nIGLV5-45\t10\nIGLV1-44\t11\nIGLV7-43\t12\nIGLV1-41\t13\nIGLV1-40\t14\nIGLV5-39\t15\nIGLV5-37\t16\nIGLV1-36\t17\nIGLV3-27\t18\nIGLV3-25\t19\nIGLV2-23\t20\nIGLV3-22\t21\nIGLV3-21\t22\nIGLV3-19\t23\nIGLV2-18\t24\nIGLV3-16\t25\nIGLV2-14\t26\nIGLV3-12\t27\nIGLV2-11\t28\nIGLV3-10\t29\nIGLV3-9\t30\nIGLV2-8\t31\nIGLV4-3\t32\nIGLV3-1\t33") + D = c("v.name\tchr.orderD\n") + J = c("v.name\tchr.orderJ\nIGLJ1\t1\nIGLJ2\t2\nIGLJ3\t3\nIGLJ6\t4\nIGLJ7\t5") + } +} else if (species == "mouse"){ + if(locus == "igh"){ + cat("mouse igh not yet implemented") + } else if (locus == "igk"){ + cat("mouse igk not yet implemented") + } else if (locus == "igl"){ + cat("mouse igl not yet implemented") + } +} + +useD = TRUE +if(species == "human" && (locus == "igk" || locus == "igl")){ + useD = FALSE +} + +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(); + +if(useD){ + 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) + print(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(); + +VGenes = PRODF[,c("Sample", "Top.V.Gene")] +VGenes$Top.V.Gene = gsub("-.*", "", VGenes$Top.V.Gene) +VGenes = data.frame(data.table(VGenes)[, list(Count=.N), by=c("Sample", "Top.V.Gene")]) +TotalPerSample = data.frame(data.table(VGenes)[, list(total=sum(.SD$Count)), by=Sample]) +VGenes = merge(VGenes, TotalPerSample, by="Sample") +VGenes$Frequency = VGenes$Count * 100 / VGenes$total +VPlot = ggplot(VGenes) +VPlot = VPlot + geom_bar(aes( x = Top.V.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) + + ggtitle("Distribution of V gene families") + + ylab("Percentage of sequences") +png("VFPlot.png") +VPlot +dev.off(); +write.table(x=VGenes, file="VFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T) + +if(useD){ + DGenes = PRODF[,c("Sample", "Top.D.Gene")] + DGenes$Top.D.Gene = gsub("-.*", "", DGenes$Top.D.Gene) + DGenes = data.frame(data.table(DGenes)[, list(Count=.N), by=c("Sample", "Top.D.Gene")]) + TotalPerSample = data.frame(data.table(DGenes)[, list(total=sum(.SD$Count)), by=Sample]) + DGenes = merge(DGenes, TotalPerSample, by="Sample") + DGenes$Frequency = DGenes$Count * 100 / DGenes$total + DPlot = ggplot(DGenes) + DPlot = DPlot + geom_bar(aes( x = Top.D.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) + + ggtitle("Distribution of D gene families") + + ylab("Percentage of sequences") + png("DFPlot.png") + print(DPlot) + dev.off(); + write.table(x=DGenes, file="DFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T) +} + +JGenes = PRODF[,c("Sample", "Top.J.Gene")] +JGenes$Top.J.Gene = gsub("-.*", "", JGenes$Top.J.Gene) +JGenes = data.frame(data.table(JGenes)[, list(Count=.N), by=c("Sample", "Top.J.Gene")]) +TotalPerSample = data.frame(data.table(JGenes)[, list(total=sum(.SD$Count)), by=Sample]) +JGenes = merge(JGenes, TotalPerSample, by="Sample") +JGenes$Frequency = JGenes$Count * 100 / JGenes$total +JPlot = ggplot(JGenes) +JPlot = JPlot + geom_bar(aes( x = Top.J.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) + + ggtitle("Distribution of J gene families") + + ylab("Percentage of sequences") +png("JFPlot.png") +JPlot +dev.off(); +write.table(x=JGenes, file="JFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T) + +CDR3Length = data.frame(data.table(PRODF)[, list(Count=.N), by=c("Sample", "CDR3.Length.DNA")]) +TotalPerSample = data.frame(data.table(CDR3Length)[, list(total=sum(.SD$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$chr.orderD) + +if(useD){ + plotVD <- function(dat){ + if(length(dat[,1]) == 0){ + return() + } + img = ggplot() + + geom_tile(data=dat, aes(x=factor(reorder(Top.D.Gene, chr.orderD)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) + + theme(axis.text.x = element_text(angle = 90, hjust = 1)) + + scale_fill_gradient(low="gold", high="blue", na.value="white") + + ggtitle(paste(unique(dat$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$v.name))) + print(img) + dev.off() + write.table(x=acast(dat, Top.V.Gene~Top.D.Gene, value.var="Length"), file=paste("HeatmapVD_", unique(dat[3])[1,1], ".csv", sep=""), sep=",",quote=F,row.names=T,col.names=NA) + } + + VandDCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.D.Gene", "Sample")]) + + VandDCount$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$Sample)) + + completeVD = merge(VandDCount, cartegianProductVD, all.y=TRUE) + completeVD = merge(completeVD, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE) + completeVD = merge(completeVD, Dchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE) + VDList = split(completeVD, f=completeVD[,"Sample"]) + + lapply(VDList, FUN=plotVD) +} + +plotVJ <- function(dat){ + if(length(dat[,1]) == 0){ + return() + } + cat(paste(unique(dat[3])[1,1])) + img = ggplot() + + geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) + + theme(axis.text.x = element_text(angle = 90, hjust = 1)) + + scale_fill_gradient(low="gold", high="blue", na.value="white") + + ggtitle(paste(unique(dat$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$v.name))) + print(img) + dev.off() + write.table(x=acast(dat, Top.V.Gene~Top.J.Gene, value.var="Length"), file=paste("HeatmapVJ_", unique(dat[3])[1,1], ".csv", sep=""), sep=",",quote=F,row.names=T,col.names=NA) +} + +VandJCount = data.frame(data.table(PRODF)[, list(Length=.N), by=c("Top.V.Gene", "Top.J.Gene", "Sample")]) + +VandJCount$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$Sample)) + +completeVJ = merge(VandJCount, cartegianProductVJ, all.y=TRUE) +completeVJ = merge(completeVJ, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE) +completeVJ = merge(completeVJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE) +VJList = split(completeVJ, f=completeVJ[,"Sample"]) +lapply(VJList, FUN=plotVJ) + +if(useD){ + plotDJ <- function(dat){ + if(length(dat[,1]) == 0){ + return() + } + img = ggplot() + + geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.D.Gene, chr.orderD)), fill=relLength)) + + theme(axis.text.x = element_text(angle = 90, hjust = 1)) + + scale_fill_gradient(low="gold", high="blue", na.value="white") + + ggtitle(paste(unique(dat$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) + + +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) + + 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) +} + +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) +}