Mercurial > repos > davidvanzessen > argalaxy_tools
changeset 28:798b62942b4b draft
Uploaded
| author | davidvanzessen |
|---|---|
| date | Wed, 01 Mar 2017 10:41:30 -0500 |
| parents | b539aeb75980 |
| children | 1f83e14f173b |
| files | imgt_loader/imgt_loader.r imgt_loader/imgt_loader.sh report_clonality/RScript.r.old report_clonality/RScript.r~ report_clonality/r_wrapper.sh.old report_clonality/r_wrapper.sh~ |
| diffstat | 6 files changed, 7 insertions(+), 2057 deletions(-) [+] |
line wrap: on
line diff
--- a/imgt_loader/imgt_loader.r Tue Feb 28 08:10:34 2017 -0500 +++ b/imgt_loader/imgt_loader.r Wed Mar 01 10:41:30 2017 -0500 @@ -4,11 +4,13 @@ sequences.file = args[2] aa.file = args[3] junction.file = args[4] -out.file = args[5] +gapped.aa.file = args[5] +out.file = args[6] summ = read.table(summ.file, sep="\t", header=T, quote="", fill=T) sequences = read.table(sequences.file, sep="\t", header=T, quote="", fill=T) aa = read.table(aa.file, sep="\t", header=T, quote="", fill=T) +gapped.aa = read.table(gapped.aa.file, sep="\t", header=T, quote="", fill=T) junction = read.table(junction.file, sep="\t", header=T, quote="", fill=T) old_summary_columns=c('Sequence.ID','JUNCTION.frame','V.GENE.and.allele','D.GENE.and.allele','J.GENE.and.allele','CDR1.IMGT.length','CDR2.IMGT.length','CDR3.IMGT.length','Orientation') @@ -32,8 +34,8 @@ out[,"CDR3.Seq"] = aa[,"CDR3.IMGT"] out[,"CDR3.Length"] = summ[,"CDR3.IMGT.length"] -out[,"CDR3.Seq.DNA"] = sequences[,"CDR3.IMGT"] -out[,"CDR3.Length.DNA"] = nchar(as.character(sequences[,"CDR3.IMGT"])) +out[,"CDR3.Seq.DNA"] = gapped.aa[,"CDR3.IMGT"] +out[,"CDR3.Length.DNA"] = nchar(as.character(out[,"CDR3.Seq.DNA"])) out[,"Strand"] = summ[,"Orientation"] out[,"CDR3.Found.How"] = "a"
--- a/imgt_loader/imgt_loader.sh Tue Feb 28 08:10:34 2017 -0500 +++ b/imgt_loader/imgt_loader.sh Wed Mar 01 10:41:30 2017 -0500 @@ -62,9 +62,10 @@ fi find $PWD/$name/files -iname "1_*" -exec cat {} + > $PWD/$name/summ.txt find $PWD/$name/files -iname "3_*" -exec cat {} + > $PWD/$name/sequences.txt +find $PWD/$name/files -iname "4_*" -exec cat {} + > $PWD/$name/gapped_aa.txt find $PWD/$name/files -iname "5_*" -exec cat {} + > $PWD/$name/aa.txt find $PWD/$name/files -iname "6_*" -exec cat {} + > $PWD/$name/junction.txt #python $dir/imgt_loader.py --summ $PWD/$name/summ.txt --aa $PWD/$name/aa.txt --junction $PWD/$name/junction.txt --output $output -Rscript --verbose $dir/imgt_loader.r $PWD/$name/summ.txt $PWD/$name/sequences.txt $PWD/$name/aa.txt $PWD/$name/junction.txt $output 2>&1 +Rscript --verbose $dir/imgt_loader.r $PWD/$name/summ.txt $PWD/$name/sequences.txt $PWD/$name/aa.txt $PWD/$name/junction.txt $PWD/$name/gapped_aa.txt $output 2>&1
--- a/report_clonality/RScript.r.old Tue Feb 28 08:10:34 2017 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,877 +0,0 @@ -# ---------------------- load/install packages ---------------------- - -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) - -if (!("lymphclon" %in% rownames(installed.packages()))) { - install.packages("lymphclon", repos="http://cran.xl-mirror.nl/") -} -library(lymphclon) - -# ---------------------- parameters ---------------------- - -args <- commandArgs(trailingOnly = TRUE) - -infile = args[1] #path to input file -outfile = args[2] #path to output file -outdir = args[3] #path to output folder (html/images/data) -clonaltype = args[4] #clonaltype definition, or 'none' for no unique filtering -ct = unlist(strsplit(clonaltype, ",")) -species = args[5] #human or mouse -locus = args[6] # IGH, IGK, IGL, TRB, TRA, TRG or TRD -filterproductive = ifelse(args[7] == "yes", T, F) #should unproductive sequences be filtered out? (yes/no) -clonality_method = args[8] - - -# ---------------------- Data preperation ---------------------- - -print("Report Clonality - Data preperation") - -inputdata = read.table(infile, sep="\t", header=TRUE, fill=T, comment.char="", stringsAsFactors=F) - -print(paste("nrows: ", nrow(inputdata))) - -setwd(outdir) - -# remove weird rows -inputdata = inputdata[inputdata$Sample != "",] - -print(paste("nrows: ", nrow(inputdata))) - -#remove the allele from the V,D and J genes -inputdata$Top.V.Gene = gsub("[*]([0-9]+)", "", inputdata$Top.V.Gene) -inputdata$Top.D.Gene = gsub("[*]([0-9]+)", "", inputdata$Top.D.Gene) -inputdata$Top.J.Gene = gsub("[*]([0-9]+)", "", inputdata$Top.J.Gene) - -print(paste("nrows: ", nrow(inputdata))) - -#filter uniques -inputdata.removed = inputdata[NULL,] - -print(paste("nrows: ", nrow(inputdata))) - -inputdata$clonaltype = 1:nrow(inputdata) - -#keep track of the count of sequences in samples or samples/replicates for the front page overview -input.sample.count = data.frame(data.table(inputdata)[, list(All=.N), by=c("Sample")]) -input.rep.count = data.frame(data.table(inputdata)[, list(All=.N), by=c("Sample", "Replicate")]) - -PRODF = inputdata -UNPROD = inputdata -if(filterproductive){ - if("Functionality" %in% colnames(inputdata)) { # "Functionality" is an IMGT column - #PRODF = inputdata[inputdata$Functionality == "productive" | inputdata$Functionality == "productive (see comment)", ] - PRODF = inputdata[inputdata$Functionality %in% c("productive (see comment)","productive"),] - - PRODF.count = data.frame(data.table(PRODF)[, list(count=.N), by=c("Sample")]) - - UNPROD = inputdata[inputdata$Functionality %in% c("unproductive (see comment)","unproductive"), ] - } else { - PRODF = inputdata[inputdata$VDJ.Frame != "In-frame with stop codon" & inputdata$VDJ.Frame != "Out-of-frame" & inputdata$CDR3.Found.How != "NOT_FOUND" , ] - UNPROD = inputdata[!(inputdata$VDJ.Frame != "In-frame with stop codon" & inputdata$VDJ.Frame != "Out-of-frame" & inputdata$CDR3.Found.How != "NOT_FOUND" ), ] - } -} - -for(i in 1:nrow(UNPROD)){ - if(!is.numeric(UNPROD[i,"CDR3.Length"])){ - UNPROD[i,"CDR3.Length"] = 0 - } -} - -prod.sample.count = data.frame(data.table(PRODF)[, list(Productive=.N), by=c("Sample")]) -prod.rep.count = data.frame(data.table(PRODF)[, list(Productive=.N), by=c("Sample", "Replicate")]) - -unprod.sample.count = data.frame(data.table(UNPROD)[, list(Unproductive=.N), by=c("Sample")]) -unprod.rep.count = data.frame(data.table(UNPROD)[, list(Unproductive=.N), by=c("Sample", "Replicate")]) - -clonalityFrame = PRODF - -#remove duplicates based on the clonaltype -if(clonaltype != "none"){ - clonaltype = paste(clonaltype, ",Sample", sep="") #add sample column to clonaltype, unique within samples - PRODF$clonaltype = do.call(paste, c(PRODF[unlist(strsplit(clonaltype, ","))], sep = ":")) - PRODF = PRODF[!duplicated(PRODF$clonaltype), ] - - UNPROD$clonaltype = do.call(paste, c(UNPROD[unlist(strsplit(clonaltype, ","))], sep = ":")) - UNPROD = UNPROD[!duplicated(UNPROD$clonaltype), ] - - #again for clonalityFrame but with sample+replicate - clonalityFrame$clonaltype = do.call(paste, c(clonalityFrame[unlist(strsplit(clonaltype, ","))], sep = ":")) - clonalityFrame$clonality_clonaltype = do.call(paste, c(clonalityFrame[unlist(strsplit(paste(clonaltype, ",Replicate", sep=""), ","))], sep = ":")) - clonalityFrame = clonalityFrame[!duplicated(clonalityFrame$clonality_clonaltype), ] -} - -print("SAMPLE TABLE:") -print(table(PRODF$Sample)) - -prod.unique.sample.count = data.frame(data.table(PRODF)[, list(Productive_unique=.N), by=c("Sample")]) -prod.unique.rep.count = data.frame(data.table(PRODF)[, list(Productive_unique=.N), by=c("Sample", "Replicate")]) - -unprod.unique.sample.count = data.frame(data.table(UNPROD)[, list(Unproductive_unique=.N), by=c("Sample")]) -unprod.unique.rep.count = data.frame(data.table(UNPROD)[, list(Unproductive_unique=.N), by=c("Sample", "Replicate")]) - -PRODF$freq = 1 - -if(any(grepl(pattern="_", x=PRODF$ID))){ #the frequency can be stored in the ID with the pattern ".*_freq_.*" - PRODF$freq = gsub("^[0-9]+_", "", PRODF$ID) - PRODF$freq = gsub("_.*", "", PRODF$freq) - PRODF$freq = as.numeric(PRODF$freq) - if(any(is.na(PRODF$freq))){ #if there was an "_" in the ID, but not the frequency, go back to frequency of 1 for every sequence - PRODF$freq = 1 - } -} - -#make a names list with sample -> color -naive.colors = c('blue4', 'darkred', 'olivedrab3', 'red', 'gray74', 'darkviolet', 'lightblue1', 'gold', 'chartreuse2', 'pink', 'Paleturquoise3', 'Chocolate1', 'Yellow', 'Deeppink3', 'Mediumorchid1', 'Darkgreen', 'Blue', 'Gray36', 'Hotpink', 'Yellow4') -unique.samples = unique(PRODF$Sample) - -if(length(unique.samples) <= length(naive.colors)){ - sample.colors = naive.colors[1:length(unique.samples)] -} else { - sample.colors = rainbow(length(unique.samples)) -} - -names(sample.colors) = unique.samples - -print("Sample.colors") -print(sample.colors) - - -#write the complete dataset that is left over, will be the input if 'none' for clonaltype and 'no' for filterproductive -write.table(PRODF, "allUnique.txt", sep="\t",quote=F,row.names=F,col.names=T) -write.table(PRODF, "allUnique.csv", sep=",",quote=F,row.names=F,col.names=T) -write.table(UNPROD, "allUnproductive.csv", sep=",",quote=F,row.names=F,col.names=T) - -#write the samples to a file -sampleFile <- file("samples.txt") -un = unique(inputdata$Sample) -un = paste(un, sep="\n") -writeLines(un, sampleFile) -close(sampleFile) - -# ---------------------- Counting the productive/unproductive and unique sequences ---------------------- - -print("Report Clonality - counting productive/unproductive/unique") - -#create the table on the overview page with the productive/unique counts per sample/replicate -#first for sample -sample.count = merge(input.sample.count, prod.sample.count, by="Sample", all.x=T) -sample.count$perc_prod = round(sample.count$Productive / sample.count$All * 100) -sample.count = merge(sample.count, prod.unique.sample.count, by="Sample", all.x=T) -sample.count$perc_prod_un = round(sample.count$Productive_unique / sample.count$All * 100) - -sample.count = merge(sample.count , unprod.sample.count, by="Sample", all.x=T) -sample.count$perc_unprod = round(sample.count$Unproductive / sample.count$All * 100) -sample.count = merge(sample.count, unprod.unique.sample.count, by="Sample", all.x=T) -sample.count$perc_unprod_un = round(sample.count$Unproductive_unique / sample.count$All * 100) - -#then sample/replicate -rep.count = merge(input.rep.count, prod.rep.count, by=c("Sample", "Replicate"), all.x=T) -rep.count$perc_prod = round(rep.count$Productive / rep.count$All * 100) -rep.count = merge(rep.count, prod.unique.rep.count, by=c("Sample", "Replicate"), all.x=T) -rep.count$perc_prod_un = round(rep.count$Productive_unique / rep.count$All * 100) - -rep.count = merge(rep.count, unprod.rep.count, by=c("Sample", "Replicate"), all.x=T) -rep.count$perc_unprod = round(rep.count$Unproductive / rep.count$All * 100) -rep.count = merge(rep.count, unprod.unique.rep.count, by=c("Sample", "Replicate"), all.x=T) -rep.count$perc_unprod_un = round(rep.count$Unproductive_unique / rep.count$All * 100) - -rep.count$Sample = paste(rep.count$Sample, rep.count$Replicate, sep="_") -rep.count = rep.count[,names(rep.count) != "Replicate"] - -count = rbind(sample.count, rep.count) - - - -write.table(x=count, file="productive_counting.txt", sep=",",quote=F,row.names=F,col.names=F) - -# ---------------------- V+J+CDR3 sequence count ---------------------- - -VJCDR3.count = data.frame(table(clonalityFrame$Top.V.Gene, clonalityFrame$Top.J.Gene, clonalityFrame$CDR3.Seq.DNA)) -names(VJCDR3.count) = c("Top.V.Gene", "Top.J.Gene", "CDR3.Seq.DNA", "Count") - -VJCDR3.count = VJCDR3.count[VJCDR3.count$Count > 0,] -VJCDR3.count = VJCDR3.count[order(-VJCDR3.count$Count),] - -write.table(x=VJCDR3.count, file="VJCDR3_count.txt", sep="\t",quote=F,row.names=F,col.names=T) - -# ---------------------- Frequency calculation for V, D and J ---------------------- - -print("Report Clonality - frequency calculation V, D and J") - -PRODFV = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.V.Gene")]) -Total = ddply(PRODFV, .(Sample), function(x) data.frame(Total = sum(x$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")]) -Total = ddply(PRODFD, .(Sample), function(x) data.frame(Total = sum(x$Length))) -PRODFD = merge(PRODFD, Total, by.x='Sample', by.y='Sample', all.x=TRUE) -PRODFD = ddply(PRODFD, c("Sample", "Top.D.Gene"), summarise, relFreq= (Length*100 / Total)) - -PRODFJ = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.J.Gene")]) -Total = ddply(PRODFJ, .(Sample), function(x) data.frame(Total = sum(x$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)) - -# ---------------------- Setting up the gene names for the different species/loci ---------------------- - -print("Report Clonality - getting genes for species/loci") - -Vchain = "" -Dchain = "" -Jchain = "" - -if(species == "custom"){ - print("Custom genes: ") - splt = unlist(strsplit(locus, ";")) - print(paste("V:", splt[1])) - print(paste("D:", splt[2])) - print(paste("J:", splt[3])) - - Vchain = unlist(strsplit(splt[1], ",")) - Vchain = data.frame(v.name = Vchain, chr.orderV = 1:length(Vchain)) - - Dchain = unlist(strsplit(splt[2], ",")) - if(length(Dchain) > 0){ - Dchain = data.frame(v.name = Dchain, chr.orderD = 1:length(Dchain)) - } else { - Dchain = data.frame(v.name = character(0), chr.orderD = numeric(0)) - } - - Jchain = unlist(strsplit(splt[3], ",")) - Jchain = data.frame(v.name = Jchain, chr.orderJ = 1:length(Jchain)) - -} else { - genes = read.table("genes.txt", sep="\t", header=TRUE, fill=T, comment.char="") - - Vchain = genes[grepl(species, genes$Species) & genes$locus == locus & genes$region == "V",c("IMGT.GENE.DB", "chr.order")] - colnames(Vchain) = c("v.name", "chr.orderV") - Dchain = genes[grepl(species, genes$Species) & genes$locus == locus & genes$region == "D",c("IMGT.GENE.DB", "chr.order")] - colnames(Dchain) = c("v.name", "chr.orderD") - Jchain = genes[grepl(species, genes$Species) & genes$locus == locus & genes$region == "J",c("IMGT.GENE.DB", "chr.order")] - colnames(Jchain) = c("v.name", "chr.orderJ") -} -useD = TRUE -if(nrow(Dchain) == 0){ - useD = FALSE - cat("No D Genes in this species/locus") -} -print(paste(nrow(Vchain), "genes in V")) -print(paste(nrow(Dchain), "genes in D")) -print(paste(nrow(Jchain), "genes in J")) - -# ---------------------- merge with the frequency count ---------------------- - -PRODFV = merge(PRODFV, Vchain, by.x='Top.V.Gene', by.y='v.name', all.x=TRUE) - -PRODFD = merge(PRODFD, Dchain, by.x='Top.D.Gene', by.y='v.name', all.x=TRUE) - -PRODFJ = merge(PRODFJ, Jchain, by.x='Top.J.Gene', by.y='v.name', all.x=TRUE) - -# ---------------------- Create the V, D and J frequency plots and write the data.frame for every plot to a file ---------------------- - -print("Report Clonality - V, D and J frequency plots") - -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") + scale_fill_manual(values=sample.colors) -pV = pV + theme(panel.background = element_rect(fill = "white", colour="black"),text = element_text(size=15, colour="black"), axis.text.x = element_text(angle = 45, hjust = 1), panel.grid.major.y = element_line(colour = "black"), panel.grid.major.x = element_blank()) -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") + scale_fill_manual(values=sample.colors) - pD = pD + theme(panel.background = element_rect(fill = "white", colour="black"),text = element_text(size=15, colour="black"), axis.text.x = element_text(angle = 45, hjust = 1), panel.grid.major.y = element_line(colour = "black"), panel.grid.major.x = element_blank()) - 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") + scale_fill_manual(values=sample.colors) -pJ = pJ + theme(panel.background = element_rect(fill = "white", colour="black"),text = element_text(size=15, colour="black"), axis.text.x = element_text(angle = 45, hjust = 1), panel.grid.major.y = element_line(colour = "black"), panel.grid.major.x = element_blank()) -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(); - -# ---------------------- Now the frequency plots of the V, D and J families ---------------------- - -print("Report Clonality - V, D and J family plots") - -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$total -VPlot = ggplot(VGenes) -VPlot = VPlot + geom_bar(aes( x = Top.V.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) + - ggtitle("Distribution of V gene families") + - ylab("Percentage of sequences") + - scale_fill_manual(values=sample.colors) + - theme(panel.background = element_rect(fill = "white", colour="black"),text = element_text(size=15, colour="black"), axis.text.x = element_text(angle = 45, hjust = 1), panel.grid.major.y = element_line(colour = "black"), panel.grid.major.x = element_blank()) -png("VFPlot.png") -VPlot -dev.off(); -write.table(x=VGenes, file="VFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T) - -if(useD){ - DGenes = PRODF[,c("Sample", "Top.D.Gene")] - DGenes$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$total - DPlot = ggplot(DGenes) - DPlot = DPlot + geom_bar(aes( x = Top.D.Gene, y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) + - ggtitle("Distribution of D gene families") + - ylab("Percentage of sequences") + - scale_fill_manual(values=sample.colors) + - theme(panel.background = element_rect(fill = "white", colour="black"),text = element_text(size=15, colour="black"), axis.text.x = element_text(angle = 45, hjust = 1), panel.grid.major.y = element_line(colour = "black"), panel.grid.major.x = element_blank()) - png("DFPlot.png") - print(DPlot) - dev.off(); - write.table(x=DGenes, file="DFFrequency.csv", sep=",",quote=F,row.names=F,col.names=T) -} - -# ---------------------- Plotting the cdr3 length ---------------------- - -print("Report Clonality - CDR3 length plot") - -CDR3Length = data.frame(data.table(PRODF)[, list(Count=.N), by=c("Sample", "CDR3.Length")]) -TotalPerSample = data.frame(data.table(CDR3Length)[, list(total=sum(.SD$Count)), by=Sample]) -CDR3Length = merge(CDR3Length, TotalPerSample, by="Sample") -CDR3Length$Frequency = CDR3Length$Count * 100 / CDR3Length$total -CDR3LengthPlot = ggplot(CDR3Length) -CDR3LengthPlot = CDR3LengthPlot + geom_bar(aes( x = factor(reorder(CDR3.Length, as.numeric(CDR3.Length))), y = Frequency, fill = Sample), stat='identity', position='dodge' ) + theme(axis.text.x = element_text(angle = 90, hjust = 1)) + - ggtitle("Length distribution of CDR3") + - xlab("CDR3 Length") + - ylab("Percentage of sequences") + - scale_fill_manual(values=sample.colors) + - theme(panel.background = element_rect(fill = "white", colour="black"),text = element_text(size=15, colour="black"), axis.text.x = element_text(angle = 45, hjust = 1), panel.grid.major.y = element_line(colour = "black"), panel.grid.major.x = element_blank()) -png("CDR3LengthPlot.png",width = 1280, height = 720) -CDR3LengthPlot -dev.off() -write.table(x=CDR3Length, file="CDR3LengthPlot.csv", sep=",",quote=F,row.names=F,col.names=T) - -# ---------------------- Plot the heatmaps ---------------------- - -#get the reverse order for the V and D genes -revVchain = Vchain -revDchain = Dchain -revVchain$chr.orderV = rev(revVchain$chr.orderV) -revDchain$chr.orderD = rev(revDchain$chr.orderD) - -if(useD){ - print("Report Clonality - Heatmaps VD") - plotVD <- function(dat){ - if(length(dat[,1]) == 0){ - return() - } - - img = ggplot() + - geom_tile(data=dat, aes(x=factor(reorder(Top.D.Gene, chr.orderD)), y=factor(reorder(Top.V.Gene, chr.orderV)), fill=relLength)) + - theme(axis.text.x = element_text(angle = 90, hjust = 1)) + - scale_fill_gradient(low="gold", high="blue", na.value="white") + - ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) + - xlab("D genes") + - ylab("V Genes") + - theme(panel.background = element_rect(fill = "white", colour="black"),text = element_text(size=15, colour="black"), panel.grid.major = element_line(colour = "gainsboro")) - - png(paste("HeatmapVD_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Dchain$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 - check = is.nan(VandDCount$relLength) - if(any(check)){ - VandDCount[check,"relLength"] = 0 - } - - cartegianProductVD = expand.grid(Top.V.Gene = Vchain$v.name, Top.D.Gene = Dchain$v.name) - - completeVD = merge(VandDCount, cartegianProductVD, by.x=c("Top.V.Gene", "Top.D.Gene"), by.y=c("Top.V.Gene", "Top.D.Gene"), all=TRUE) - - completeVD = merge(completeVD, revVchain, by.x="Top.V.Gene", by.y="v.name", all.x=TRUE) - - completeVD = merge(completeVD, Dchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE) - - fltr = is.nan(completeVD$relLength) - if(all(fltr)){ - completeVD[fltr,"relLength"] = 0 - } - - VDList = split(completeVD, f=completeVD[,"Sample"]) - lapply(VDList, FUN=plotVD) -} - -print("Report Clonality - Heatmaps VJ") - -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") + - theme(panel.background = element_rect(fill = "white", colour="black"),text = element_text(size=15, colour="black"), panel.grid.major = element_line(colour = "gainsboro")) - - 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$max - -check = is.nan(VandJCount$relLength) -if(any(check)){ - VandJCount[check,"relLength"] = 0 -} - -cartegianProductVJ = expand.grid(Top.V.Gene = Vchain$v.name, Top.J.Gene = Jchain$v.name) - -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) - -fltr = is.nan(completeVJ$relLength) -if(any(fltr)){ - completeVJ[fltr,"relLength"] = 1 -} - -VJList = split(completeVJ, f=completeVJ[,"Sample"]) -lapply(VJList, FUN=plotVJ) - - - -if(useD){ - print("Report Clonality - Heatmaps DJ") - plotDJ <- function(dat){ - if(length(dat[,1]) == 0){ - return() - } - img = ggplot() + - geom_tile(data=dat, aes(x=factor(reorder(Top.J.Gene, chr.orderJ)), y=factor(reorder(Top.D.Gene, chr.orderD)), fill=relLength)) + - theme(axis.text.x = element_text(angle = 90, hjust = 1)) + - scale_fill_gradient(low="gold", high="blue", na.value="white") + - ggtitle(paste(unique(dat$Sample), " (N=" , sum(dat$Length, na.rm=T) ,")", sep="")) + - xlab("J genes") + - ylab("D Genes") + - theme(panel.background = element_rect(fill = "white", colour="black"),text = element_text(size=15, colour="black"), panel.grid.major = element_line(colour = "gainsboro")) - - png(paste("HeatmapDJ_", unique(dat[3])[1,1] , ".png", sep=""), width=150+(15*length(Jchain$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 - - check = is.nan(DandJCount$relLength) - if(any(check)){ - DandJCount[check,"relLength"] = 0 - } - - cartegianProductDJ = expand.grid(Top.D.Gene = Dchain$v.name, Top.J.Gene = Jchain$v.name) - - completeDJ = merge(DandJCount, cartegianProductDJ, all.y=TRUE) - completeDJ = merge(completeDJ, revDchain, by.x="Top.D.Gene", by.y="v.name", all.x=TRUE) - completeDJ = merge(completeDJ, Jchain, by.x="Top.J.Gene", by.y="v.name", all.x=TRUE) - - fltr = is.nan(completeDJ$relLength) - if(any(fltr)){ - completeDJ[fltr, "relLength"] = 1 - } - - DJList = split(completeDJ, f=completeDJ[,"Sample"]) - lapply(DJList, FUN=plotDJ) -} - - -# ---------------------- output tables for the circos plots ---------------------- - -print("Report Clonality - Circos data") - -for(smpl in unique(PRODF$Sample)){ - PRODF.sample = PRODF[PRODF$Sample == smpl,] - - fltr = PRODF.sample$Top.V.Gene == "" - if(any(fltr, na.rm=T)){ - PRODF.sample[fltr, "Top.V.Gene"] = "NA" - } - - fltr = PRODF.sample$Top.D.Gene == "" - if(any(fltr, na.rm=T)){ - PRODF.sample[fltr, "Top.D.Gene"] = "NA" - } - - fltr = PRODF.sample$Top.J.Gene == "" - if(any(fltr, na.rm=T)){ - PRODF.sample[fltr, "Top.J.Gene"] = "NA" - } - - v.d = table(PRODF.sample$Top.V.Gene, PRODF.sample$Top.D.Gene) - v.j = table(PRODF.sample$Top.V.Gene, PRODF.sample$Top.J.Gene) - d.j = table(PRODF.sample$Top.D.Gene, PRODF.sample$Top.J.Gene) - - write.table(v.d, file=paste(smpl, "_VD_circos.txt", sep=""), sep="\t", quote=F, row.names=T, col.names=NA) - write.table(v.j, file=paste(smpl, "_VJ_circos.txt", sep=""), sep="\t", quote=F, row.names=T, col.names=NA) - write.table(d.j, file=paste(smpl, "_DJ_circos.txt", sep=""), sep="\t", quote=F, row.names=T, col.names=NA) -} - -# ---------------------- calculating the clonality score ---------------------- - -if("Replicate" %in% colnames(inputdata)) #can only calculate clonality score when replicate information is available -{ - print("Report Clonality - Clonality") - write.table(clonalityFrame, "clonalityComplete.csv", sep=",",quote=F,row.names=F,col.names=T) - if(clonality_method == "boyd"){ - samples = split(clonalityFrame, clonalityFrame$Sample, drop=T) - - for (sample in samples){ - res = data.frame(paste=character(0)) - sample_id = unique(sample$Sample)[[1]] - for(replicate in unique(sample$Replicate)){ - tmp = sample[sample$Replicate == replicate,] - clone_table = data.frame(table(tmp$clonaltype)) - clone_col_name = paste("V", replicate, sep="") - colnames(clone_table) = c("paste", clone_col_name) - res = merge(res, clone_table, by="paste", all=T) - } - - res[is.na(res)] = 0 - infer.result = infer.clonality(as.matrix(res[,2:ncol(res)])) - - #print(infer.result) - - write.table(data.table(infer.result[[12]]), file=paste("lymphclon_clonality_", sample_id, ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=F) - - res$type = rowSums(res[,2:ncol(res)]) - - coincidence.table = data.frame(table(res$type)) - colnames(coincidence.table) = c("Coincidence Type", "Raw Coincidence Freq") - write.table(coincidence.table, file=paste("lymphclon_coincidences_", sample_id, ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=T) - } - } else { - clonalFreq = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "clonaltype")]) - - #write files for every coincidence group of >1 - samples = unique(clonalFreq$Sample) - for(sample in samples){ - clonalFreqSample = clonalFreq[clonalFreq$Sample == sample,] - if(max(clonalFreqSample$Type) > 1){ - for(i in 2:max(clonalFreqSample$Type)){ - clonalFreqSampleType = clonalFreqSample[clonalFreqSample$Type == i,] - clonalityFrame.sub = clonalityFrame[clonalityFrame$clonaltype %in% clonalFreqSampleType$clonaltype,] - clonalityFrame.sub = clonalityFrame.sub[order(clonalityFrame.sub$clonaltype),] - write.table(clonalityFrame.sub, file=paste("coincidences_", sample, "_", i, ".txt", sep=""), sep="\t",quote=F,row.names=F,col.names=T) - } - } - } - - 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", "clonaltype")]) - ReplicateReads = data.frame(data.table(ReplicateReads)[, list(Reads=.N), by=c("Sample", "Replicate")]) - clonalFreqCount$Reads = as.numeric(clonalFreqCount$Reads) - ReplicateReads$Reads = as.numeric(ReplicateReads$Reads) - ReplicateReads$squared = as.numeric(ReplicateReads$Reads * ReplicateReads$Reads) - - ReplicatePrint <- function(dat){ - write.table(dat[-1], paste("ReplicateReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F) - } - - ReplicateSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"]) - lapply(ReplicateSplit, FUN=ReplicatePrint) - - ReplicateReads = data.frame(data.table(ReplicateReads)[, list(ReadsSum=sum(as.numeric(Reads)), ReadsSquaredSum=sum(as.numeric(squared))), by=c("Sample")]) - clonalFreqCount = merge(clonalFreqCount, ReplicateReads, by.x="Sample", by.y="Sample", all.x=T) - - ReplicateSumPrint <- function(dat){ - write.table(dat[-1], paste("ReplicateSumReads_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F) - } - - ReplicateSumSplit = split(ReplicateReads, f=ReplicateReads[,"Sample"]) - lapply(ReplicateSumSplit, FUN=ReplicateSumPrint) - - clonalFreqCountSum = data.frame(data.table(clonalFreqCount)[, list(Numerator=sum(WeightedCount, na.rm=T)), by=c("Sample")]) - clonalFreqCount = merge(clonalFreqCount, clonalFreqCountSum, by.x="Sample", by.y="Sample", all.x=T) - clonalFreqCount$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$Result, paste("ClonalityScore_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F) - } - - clonalityScore = clonalFreqCount[c("Sample", "Result")] - clonalityScore = unique(clonalityScore) - - clonalityScoreSplit = split(clonalityScore, f=clonalityScore[,"Sample"]) - lapply(clonalityScoreSplit, FUN=ClonalityScorePrint) - - clonalityOverview = clonalFreqCount[c("Sample", "Type", "Count", "Weight", "WeightedCount")] - - - - ClonalityOverviewPrint <- function(dat){ - dat = dat[order(dat[,2]),] - write.table(dat[-1], paste("ClonalityOverView_", unique(dat[1])[1,1] , ".csv", sep=""), sep=",",quote=F,na="-",row.names=F,col.names=F) - } - - clonalityOverviewSplit = split(clonalityOverview, f=clonalityOverview$Sample) - lapply(clonalityOverviewSplit, FUN=ClonalityOverviewPrint) - } -} - -bak = PRODF - -imgtcolumns = c("X3V.REGION.trimmed.nt.nb","P3V.nt.nb", "N1.REGION.nt.nb", "P5D.nt.nb", "X5D.REGION.trimmed.nt.nb", "X3D.REGION.trimmed.nt.nb", "P3D.nt.nb", "N2.REGION.nt.nb", "P5J.nt.nb", "X5J.REGION.trimmed.nt.nb", "X3V.REGION.trimmed.nt.nb", "X5D.REGION.trimmed.nt.nb", "X3D.REGION.trimmed.nt.nb", "X5J.REGION.trimmed.nt.nb", "N1.REGION.nt.nb", "N2.REGION.nt.nb", "P3V.nt.nb", "P5D.nt.nb", "P3D.nt.nb", "P5J.nt.nb") -if(all(imgtcolumns %in% colnames(inputdata))) -{ - print("found IMGT columns, running junction analysis") - - if(locus %in% c("IGK","IGL", "TRA", "TRG")){ - print("VJ recombination, no filtering on absent D") - } else { - print("VDJ recombination, using N column for junction analysis") - fltr = nchar(PRODF$Top.D.Gene) < 4 - print(paste("Removing", sum(fltr), "sequences without a identified D")) - PRODF = PRODF[!fltr,] - } - - - #ensure certain columns are in the data (files generated with older versions of IMGT Loader) - col.checks = c("N.REGION.nt.nb", "N1.REGION.nt.nb", "N2.REGION.nt.nb", "N3.REGION.nt.nb", "N4.REGION.nt.nb") - for(col.check in col.checks){ - if(!(col.check %in% names(PRODF))){ - print(paste(col.check, "not found adding new column")) - if(nrow(PRODF) > 0){ #because R is anoying... - PRODF[,col.check] = 0 - } else { - PRODF = cbind(PRODF, data.frame(N3.REGION.nt.nb=numeric(0), N4.REGION.nt.nb=numeric(0))) - } - if(nrow(UNPROD) > 0){ - UNPROD[,col.check] = 0 - } else { - UNPROD = cbind(UNPROD, data.frame(N3.REGION.nt.nb=numeric(0), N4.REGION.nt.nb=numeric(0))) - } - } - } - - num_median = function(x, na.rm=T) { as.numeric(median(x, na.rm=na.rm)) } - - newData = data.frame(data.table(PRODF)[,list(unique=.N, - VH.DEL=mean(.SD$X3V.REGION.trimmed.nt.nb, na.rm=T), - P1=mean(.SD$P3V.nt.nb, na.rm=T), - N1=mean(rowSums(.SD[,c("N.REGION.nt.nb", "N1.REGION.nt.nb"), with=F], na.rm=T)), - P2=mean(.SD$P5D.nt.nb, na.rm=T), - DEL.DH=mean(.SD$X5D.REGION.trimmed.nt.nb, na.rm=T), - DH.DEL=mean(.SD$X3D.REGION.trimmed.nt.nb, na.rm=T), - P3=mean(.SD$P3D.nt.nb, na.rm=T), - N2=mean(rowSums(.SD[,c("N2.REGION.nt.nb", "N3.REGION.nt.nb", "N4.REGION.nt.nb"), with=F], na.rm=T)), - P4=mean(.SD$P5J.nt.nb, na.rm=T), - DEL.JH=mean(.SD$X5J.REGION.trimmed.nt.nb, na.rm=T), - Total.Del=mean(rowSums(.SD[,c("X3V.REGION.trimmed.nt.nb", "X5D.REGION.trimmed.nt.nb", "X3D.REGION.trimmed.nt.nb", "X5J.REGION.trimmed.nt.nb"), with=F], na.rm=T)), - Total.N=mean(rowSums(.SD[,c("N.REGION.nt.nb", "N1.REGION.nt.nb", "N2.REGION.nt.nb", "N3.REGION.nt.nb", "N4.REGION.nt.nb"), with=F], na.rm=T)), - Total.P=mean(rowSums(.SD[,c("P3V.nt.nb", "P5D.nt.nb", "P3D.nt.nb", "P5J.nt.nb"), with=F], na.rm=T)), - Median.CDR3.l=as.double(median(.SD$CDR3.Length))), - by=c("Sample")]) - newData[,sapply(newData, is.numeric)] = round(newData[,sapply(newData, is.numeric)],1) - write.table(newData, "junctionAnalysisProd_mean.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F) - - newData = data.frame(data.table(PRODF)[,list(unique=.N, - VH.DEL=num_median(.SD$X3V.REGION.trimmed.nt.nb, na.rm=T), - P1=num_median(.SD$P3V.nt.nb, na.rm=T), - N1=num_median(rowSums(.SD[,c("N.REGION.nt.nb", "N1.REGION.nt.nb"), with=F], na.rm=T)), - P2=num_median(.SD$P5D.nt.nb, na.rm=T), - DEL.DH=num_median(.SD$X5D.REGION.trimmed.nt.nb, na.rm=T), - DH.DEL=num_median(.SD$X3D.REGION.trimmed.nt.nb, na.rm=T), - P3=num_median(.SD$P3D.nt.nb, na.rm=T), - N2=num_median(rowSums(.SD[,c("N2.REGION.nt.nb", "N3.REGION.nt.nb", "N4.REGION.nt.nb"), with=F], na.rm=T)), - P4=num_median(.SD$P5J.nt.nb, na.rm=T), - DEL.JH=num_median(.SD$X5J.REGION.trimmed.nt.nb, na.rm=T), - Total.Del=num_median(rowSums(.SD[,c("X3V.REGION.trimmed.nt.nb", "X5D.REGION.trimmed.nt.nb", "X3D.REGION.trimmed.nt.nb", "X5J.REGION.trimmed.nt.nb"), with=F], na.rm=T)), - Total.N=num_median(rowSums(.SD[,c("N.REGION.nt.nb", "N1.REGION.nt.nb", "N2.REGION.nt.nb", "N3.REGION.nt.nb", "N4.REGION.nt.nb"), with=F], na.rm=T)), - Total.P=num_median(rowSums(.SD[,c("P3V.nt.nb", "P5D.nt.nb", "P3D.nt.nb", "P5J.nt.nb"), with=F], na.rm=T)), - Median.CDR3.l=as.double(median(.SD$CDR3.Length))), - by=c("Sample")]) - newData[,sapply(newData, is.numeric)] = round(newData[,sapply(newData, is.numeric)],1) - write.table(newData, "junctionAnalysisProd_median.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F) - - newData = data.frame(data.table(UNPROD)[,list(unique=.N, - VH.DEL=mean(.SD$X3V.REGION.trimmed.nt.nb, na.rm=T), - P1=mean(.SD$P3V.nt.nb, na.rm=T), - N1=mean(rowSums(.SD[,c("N.REGION.nt.nb", "N1.REGION.nt.nb"), with=F], na.rm=T)), - P2=mean(.SD$P5D.nt.nb, na.rm=T), - DEL.DH=mean(.SD$X5D.REGION.trimmed.nt.nb, na.rm=T), - DH.DEL=mean(.SD$X3D.REGION.trimmed.nt.nb, na.rm=T), - P3=mean(.SD$P3D.nt.nb, na.rm=T), - N2=mean(rowSums(.SD[,c("N2.REGION.nt.nb", "N3.REGION.nt.nb", "N4.REGION.nt.nb"), with=F], na.rm=T)), - P4=mean(.SD$P5J.nt.nb, na.rm=T), - DEL.JH=mean(.SD$X5J.REGION.trimmed.nt.nb, na.rm=T), - Total.Del=mean(rowSums(.SD[,c("X3V.REGION.trimmed.nt.nb", "X5D.REGION.trimmed.nt.nb", "X3D.REGION.trimmed.nt.nb", "X5J.REGION.trimmed.nt.nb"), with=F], na.rm=T)), - Total.N=mean(rowSums(.SD[,c("N.REGION.nt.nb", "N1.REGION.nt.nb", "N2.REGION.nt.nb", "N3.REGION.nt.nb", "N4.REGION.nt.nb"), with=F], na.rm=T)), - Total.P=mean(rowSums(.SD[,c("P3V.nt.nb", "P5D.nt.nb", "P3D.nt.nb", "P5J.nt.nb"), with=F], na.rm=T)), - Median.CDR3.l=as.double(median(.SD$CDR3.Length))), - by=c("Sample")]) - newData[,sapply(newData, is.numeric)] = round(newData[,sapply(newData, is.numeric)],1) - write.table(newData, "junctionAnalysisUnProd_mean.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F) - - newData = data.frame(data.table(UNPROD)[,list(unique=.N, - VH.DEL=num_median(.SD$X3V.REGION.trimmed.nt.nb, na.rm=T), - P1=num_median(.SD$P3V.nt.nb, na.rm=T), - N1=num_median(rowSums(.SD[,c("N.REGION.nt.nb", "N1.REGION.nt.nb"), with=F], na.rm=T)), - P2=num_median(.SD$P5D.nt.nb, na.rm=T), - DEL.DH=num_median(.SD$X5D.REGION.trimmed.nt.nb, na.rm=T), - DH.DEL=num_median(.SD$X3D.REGION.trimmed.nt.nb, na.rm=T), - P3=num_median(.SD$P3D.nt.nb, na.rm=T), - N2=num_median(rowSums(.SD[,c("N2.REGION.nt.nb", "N3.REGION.nt.nb", "N4.REGION.nt.nb"), with=F], na.rm=T)), - P4=num_median(.SD$P5J.nt.nb, na.rm=T), - DEL.JH=num_median(.SD$X5J.REGION.trimmed.nt.nb, na.rm=T), - Total.Del=num_median(rowSums(.SD[,c("X3V.REGION.trimmed.nt.nb", "X5D.REGION.trimmed.nt.nb", "X3D.REGION.trimmed.nt.nb", "X5J.REGION.trimmed.nt.nb"), with=F], na.rm=T)), - Total.N=num_median(rowSums(.SD[,c("N.REGION.nt.nb", "N1.REGION.nt.nb", "N2.REGION.nt.nb", "N3.REGION.nt.nb", "N4.REGION.nt.nb"), with=F], na.rm=T)), - Total.P=num_median(rowSums(.SD[,c("P3V.nt.nb", "P5D.nt.nb", "P3D.nt.nb", "P5J.nt.nb"), with=F], na.rm=T)), - Median.CDR3.l=as.double(median(.SD$CDR3.Length))), - by=c("Sample")]) - - newData[,sapply(newData, is.numeric)] = round(newData[,sapply(newData, is.numeric)],1) - write.table(newData, "junctionAnalysisUnProd_median.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F) -} - -PRODF = bak - - -# ---------------------- D reading frame ---------------------- - -D.REGION.reading.frame = PRODF[,c("Sample", "D.REGION.reading.frame")] - -chck = is.na(D.REGION.reading.frame$D.REGION.reading.frame) -if(any(chck)){ - D.REGION.reading.frame[chck,"D.REGION.reading.frame"] = "No D" -} - -D.REGION.reading.frame = data.frame(data.table(D.REGION.reading.frame)[, list(Freq=.N), by=c("Sample", "D.REGION.reading.frame")]) - -write.table(D.REGION.reading.frame, "DReadingFrame.csv" , sep="\t",quote=F,row.names=F,col.names=T) - -D.REGION.reading.frame = ggplot(D.REGION.reading.frame) -D.REGION.reading.frame = D.REGION.reading.frame + geom_bar(aes( x = D.REGION.reading.frame, y = Freq, fill=Sample), stat='identity', position='dodge' ) + ggtitle("D reading frame") + xlab("Frequency") + ylab("Frame") -D.REGION.reading.frame = D.REGION.reading.frame + scale_fill_manual(values=sample.colors) -D.REGION.reading.frame = D.REGION.reading.frame + theme(panel.background = element_rect(fill = "white", colour="black"),text = element_text(size=15, colour="black"), axis.text.x = element_text(angle = 45, hjust = 1), panel.grid.major.y = element_line(colour = "black"), panel.grid.major.x = element_blank()) - -png("DReadingFrame.png") -D.REGION.reading.frame -dev.off() - - - - -# ---------------------- AA composition in CDR3 ---------------------- - -AACDR3 = PRODF[,c("Sample", "CDR3.Seq")] - -TotalPerSample = data.frame(data.table(AACDR3)[, list(total=sum(nchar(as.character(.SD$CDR3.Seq)))), by=Sample]) - -AAfreq = list() - -for(i in 1:nrow(TotalPerSample)){ - sample = TotalPerSample$Sample[i] - AAfreq[[i]] = data.frame(table(unlist(strsplit(as.character(AACDR3[AACDR3$Sample == sample,c("CDR3.Seq")]), "")))) - AAfreq[[i]]$Sample = sample -} - -AAfreq = ldply(AAfreq, data.frame) -AAfreq = merge(AAfreq, TotalPerSample, by="Sample", all.x = T) -AAfreq$freq_perc = as.numeric(AAfreq$Freq / AAfreq$total * 100) - - -AAorder = read.table(sep="\t", header=TRUE, text="order.aa\tAA\n1\tR\n2\tK\n3\tN\n4\tD\n5\tQ\n6\tE\n7\tH\n8\tP\n9\tY\n10\tW\n11\tS\n12\tT\n13\tG\n14\tA\n15\tM\n16\tC\n17\tF\n18\tL\n19\tV\n20\tI") -AAfreq = merge(AAfreq, AAorder, by.x='Var1', by.y='AA', all.x=TRUE) - -AAfreq = AAfreq[!is.na(AAfreq$order.aa),] - -AAfreqplot = ggplot(AAfreq) -AAfreqplot = AAfreqplot + geom_bar(aes( x=factor(reorder(Var1, order.aa)), y = freq_perc, fill = Sample), stat='identity', position='dodge' ) -AAfreqplot = AAfreqplot + annotate("rect", xmin = 0.5, xmax = 2.5, ymin = 0, ymax = Inf, fill = "red", alpha = 0.2) -AAfreqplot = AAfreqplot + annotate("rect", xmin = 3.5, xmax = 4.5, ymin = 0, ymax = Inf, fill = "blue", alpha = 0.2) -AAfreqplot = AAfreqplot + annotate("rect", xmin = 5.5, xmax = 6.5, ymin = 0, ymax = Inf, fill = "blue", alpha = 0.2) -AAfreqplot = AAfreqplot + annotate("rect", xmin = 6.5, xmax = 7.5, ymin = 0, ymax = Inf, fill = "red", alpha = 0.2) -AAfreqplot = AAfreqplot + ggtitle("Amino Acid Composition in the CDR3") + xlab("Amino Acid, from Hydrophilic (left) to Hydrophobic (right)") + ylab("Percentage") + scale_fill_manual(values=sample.colors) -AAfreqplot = AAfreqplot + theme(panel.background = element_rect(fill = "white", colour="black"),text = element_text(size=15, colour="black"), axis.text.x = element_text(angle = 45, hjust = 1), panel.grid.major.y = element_line(colour = "black"), panel.grid.major.x = element_blank()) - -png("AAComposition.png",width = 1280, height = 720) -AAfreqplot -dev.off() -write.table(AAfreq, "AAComposition.csv" , sep=",",quote=F,na="-",row.names=F,col.names=T) - -# ---------------------- AA median CDR3 length ---------------------- - -median.aa.l = data.frame(data.table(PRODF)[, list(median=as.double(median(.SD$CDR3.Length))), by=c("Sample")]) -write.table(median.aa.l, "AAMedianBySample.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F) -
--- a/report_clonality/RScript.r~ Tue Feb 28 08:10:34 2017 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,658 +0,0 @@ -# ---------------------- load/install packages ---------------------- - -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) - -if (!("lymphclon" %in% rownames(installed.packages()))) { - install.packages("lymphclon", repos="http://cran.xl-mirror.nl/") -} -library(lymphclon) - -# ---------------------- parameters ---------------------- - -args <- commandArgs(trailingOnly = TRUE) - -infile = args[1] #path to input file -outfile = args[2] #path to output file -outdir = args[3] #path to output folder (html/images/data) -clonaltype = args[4] #clonaltype definition, or 'none' for no unique filtering -ct = unlist(strsplit(clonaltype, ",")) -species = args[5] #human or mouse -locus = args[6] # IGH, IGK, IGL, TRB, TRA, TRG or TRD -filterproductive = ifelse(args[7] == "yes", T, F) #should unproductive sequences be filtered out? (yes/no) -clonality_method = args[8] - -# ---------------------- Data preperation ---------------------- - -inputdata = read.table(infile, sep="\t", header=TRUE, fill=T, comment.char="") - -setwd(outdir) - -# remove weird rows -inputdata = inputdata[inputdata$Sample != "",] - -#remove the allele from the V,D and J genes -inputdata$Top.V.Gene = gsub("[*]([0-9]+)", "", inputdata$Top.V.Gene) -inputdata$Top.D.Gene = gsub("[*]([0-9]+)", "", inputdata$Top.D.Gene) -inputdata$Top.J.Gene = gsub("[*]([0-9]+)", "", inputdata$Top.J.Gene) - -inputdata$clonaltype = 1:nrow(inputdata) - -PRODF = inputdata -UNPROD = inputdata -if(filterproductive){ - if("Functionality" %in% colnames(inputdata)) { # "Functionality" is an IMGT column - PRODF = inputdata[inputdata$Functionality == "productive" | inputdata$Functionality == "productive (see comment)", ] - UNPROD = inputdata[!(inputdata$Functionality == "productive" | inputdata$Functionality == "productive (see comment)"), ] - } else { - PRODF = inputdata[inputdata$VDJ.Frame != "In-frame with stop codon" & inputdata$VDJ.Frame != "Out-of-frame" & inputdata$CDR3.Found.How != "NOT_FOUND" , ] - UNPROD = inputdata[!(inputdata$VDJ.Frame != "In-frame with stop codon" & inputdata$VDJ.Frame != "Out-of-frame" & inputdata$CDR3.Found.How != "NOT_FOUND" ), ] - } -} - -clonalityFrame = PRODF - -#remove duplicates based on the clonaltype -if(clonaltype != "none"){ - clonaltype = paste(clonaltype, ",Sample", sep="") #add sample column to clonaltype, unique within samples - PRODF$clonaltype = do.call(paste, c(PRODF[unlist(strsplit(clonaltype, ","))], sep = ":")) - PRODF = PRODF[!duplicated(PRODF$clonaltype), ] - - UNPROD$clonaltype = do.call(paste, c(UNPROD[unlist(strsplit(clonaltype, ","))], sep = ":")) - UNPROD = UNPROD[!duplicated(UNPROD$clonaltype), ] - - #again for clonalityFrame but with sample+replicate - clonalityFrame$clonaltype = do.call(paste, c(clonalityFrame[unlist(strsplit(clonaltype, ","))], sep = ":")) - clonalityFrame$clonality_clonaltype = do.call(paste, c(clonalityFrame[unlist(strsplit(paste(clonaltype, ",Replicate", sep=""), ","))], sep = ":")) - clonalityFrame = clonalityFrame[!duplicated(clonalityFrame$clonality_clonaltype), ] -} - -PRODF$freq = 1 - -if(any(grepl(pattern="_", x=PRODF$ID))){ #the frequency can be stored in the ID with the pattern ".*_freq_.*" - PRODF$freq = gsub("^[0-9]+_", "", PRODF$ID) - PRODF$freq = gsub("_.*", "", PRODF$freq) - PRODF$freq = as.numeric(PRODF$freq) - if(any(is.na(PRODF$freq))){ #if there was an "_" in the ID, but not the frequency, go back to frequency of 1 for every sequence - PRODF$freq = 1 - } -} - - - -#write the complete dataset that is left over, will be the input if 'none' for clonaltype and 'no' for filterproductive -write.table(PRODF, "allUnique.txt", sep=",",quote=F,row.names=F,col.names=T) -write.table(PRODF, "allUnique.csv", sep="\t",quote=F,row.names=F,col.names=T) -write.table(UNPROD, "allUnproductive.csv", sep=",",quote=F,row.names=F,col.names=T) - -#write the samples to a file -sampleFile <- file("samples.txt") -un = unique(inputdata$Sample) -un = paste(un, sep="\n") -writeLines(un, sampleFile) -close(sampleFile) - -# ---------------------- Counting the productive/unproductive and unique sequences ---------------------- - -if(!("Functionality" %in% inputdata)){ #add a functionality column to the igblast data - inputdata$Functionality = "unproductive" - search = (inputdata$VDJ.Frame != "In-frame with stop codon" & inputdata$VDJ.Frame != "Out-of-frame" & inputdata$CDR3.Found.How != "NOT_FOUND") - if(sum(search) > 0){ - inputdata[search,]$Functionality = "productive" - } -} - -inputdata.dt = data.table(inputdata) #for speed - -if(clonaltype == "none"){ - ct = c("clonaltype") -} - -inputdata.dt$samples_replicates = paste(inputdata.dt$Sample, inputdata.dt$Replicate, sep="_") -samples_replicates = c(unique(inputdata.dt$samples_replicates), unique(as.character(inputdata.dt$Sample))) -frequency_table = data.frame(ID = samples_replicates[order(samples_replicates)]) - - -sample_productive_count = inputdata.dt[, list(All=.N, - Productive = nrow(.SD[.SD$Functionality == "productive" | .SD$Functionality == "productive (see comment)",]), - perc_prod = 1, - Productive_unique = nrow(.SD[.SD$Functionality == "productive" | .SD$Functionality == "productive (see comment)",list(count=.N),by=ct]), - perc_prod_un = 1, - Unproductive= nrow(.SD[.SD$Functionality != "productive" & .SD$Functionality != "productive (see comment)",]), - perc_unprod = 1, - Unproductive_unique =nrow(.SD[.SD$Functionality != "productive" & .SD$Functionality != "productive (see comment)",list(count=.N),by=ct]), - perc_unprod_un = 1), - by=c("Sample")] - -sample_productive_count$perc_prod = round(sample_productive_count$Productive / sample_productive_count$All * 100) -sample_productive_count$perc_prod_un = round(sample_productive_count$Productive_unique / sample_productive_count$All * 100) - -sample_productive_count$perc_unprod = round(sample_productive_count$Unproductive / sample_productive_count$All * 100) -sample_productive_count$perc_unprod_un = round(sample_productive_count$Unproductive_unique / sample_productive_count$All * 100) - - -sample_replicate_productive_count = inputdata.dt[, list(All=.N, - Productive = nrow(.SD[.SD$Functionality == "productive" | .SD$Functionality == "productive (see comment)",]), - perc_prod = 1, - Productive_unique = nrow(.SD[.SD$Functionality == "productive" | .SD$Functionality == "productive (see comment)",list(count=.N),by=ct]), - perc_prod_un = 1, - Unproductive= nrow(.SD[.SD$Functionality != "productive" & .SD$Functionality != "productive (see comment)",]), - perc_unprod = 1, - Unproductive_unique =nrow(.SD[.SD$Functionality != "productive" & .SD$Functionality != "productive (see comment)",list(count=.N),by=ct]), - perc_unprod_un = 1), - by=c("samples_replicates")] - -sample_replicate_productive_count$perc_prod = round(sample_replicate_productive_count$Productive / sample_replicate_productive_count$All * 100) -sample_replicate_productive_count$perc_prod_un = round(sample_replicate_productive_count$Productive_unique / sample_replicate_productive_count$All * 100) - -sample_replicate_productive_count$perc_unprod = round(sample_replicate_productive_count$Unproductive / sample_replicate_productive_count$All * 100) -sample_replicate_productive_count$perc_unprod_un = round(sample_replicate_productive_count$Unproductive_unique / sample_replicate_productive_count$All * 100) - -setnames(sample_replicate_productive_count, colnames(sample_productive_count)) - -counts = rbind(sample_replicate_productive_count, sample_productive_count) -counts = counts[order(counts$Sample),] - -write.table(x=counts, file="productive_counting.txt", sep=",",quote=F,row.names=F,col.names=F) - -# ---------------------- Frequency calculation for V, D and J ---------------------- - -PRODFV = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.V.Gene")]) -Total = ddply(PRODFV, .(Sample), function(x) data.frame(Total = sum(x$Length))) -PRODFV = merge(PRODFV, Total, by.x='Sample', by.y='Sample', all.x=TRUE) -PRODFV = ddply(PRODFV, c("Sample", "Top.V.Gene"), summarise, relFreq= (Length*100 / Total)) - -PRODFD = data.frame(data.table(PRODF)[, list(Length=sum(freq)), by=c("Sample", "Top.D.Gene")]) -Total = ddply(PRODFD, .(Sample), function(x) data.frame(Total = sum(x$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")]) -Total = ddply(PRODFJ, .(Sample), function(x) data.frame(Total = sum(x$Length))) -PRODFJ = merge(PRODFJ, Total, by.x='Sample', by.y='Sample', all.x=TRUE) -PRODFJ = ddply(PRODFJ, c("Sample", "Top.J.Gene"), summarise, relFreq= (Length*100 / Total)) - -# ---------------------- Setting up the gene names for the different species/loci ---------------------- - -Vchain = "" -Dchain = "" -Jchain = "" - -if(species == "custom"){ - print("Custom genes: ") - splt = unlist(strsplit(locus, ";")) - print(paste("V:", splt[1])) - print(paste("D:", splt[2])) - print(paste("J:", splt[3])) - - Vchain = unlist(strsplit(splt[1], ",")) - Vchain = data.frame(v.name = Vchain, chr.orderV = 1:length(Vchain)) - - Dchain = unlist(strsplit(splt[2], ",")) - if(length(Dchain) > 0){ - Dchain = data.frame(v.name = Dchain, chr.orderD = 1:length(Dchain)) - } else { - Dchain = data.frame(v.name = character(0), chr.orderD = numeric(0)) - } - - Jchain = unlist(strsplit(splt[3], ",")) - Jchain = data.frame(v.name = Jchain, chr.orderJ = 1:length(Jchain)) - -} else { - genes = read.table("genes.txt", sep="\t", header=TRUE, fill=T, comment.char="") - - Vchain = genes[grepl(species, genes$Species) & genes$locus == locus & genes$region == "V",c("IMGT.GENE.DB", "chr.order")] - colnames(Vchain) = c("v.name", "chr.orderV") - Dchain = genes[grepl(species, genes$Species) & genes$locus == locus & genes$region == "D",c("IMGT.GENE.DB", "chr.order")] - colnames(Dchain) = c("v.name", "chr.orderD") - Jchain = genes[grepl(species, genes$Species) & genes$locus == locus & genes$region == "J",c("IMGT.GENE.DB", "chr.order")] - colnames(Jchain) = c("v.name", "chr.orderJ") -} -useD = TRUE -if(nrow(Dchain) == 0){ - useD = FALSE - cat("No D Genes in this species/locus") -} -print(paste("useD:", useD)) - -# ---------------------- merge with the frequency count ---------------------- - -PRODFV = merge(PRODFV, Vchain, by.x='Top.V.Gene', by.y='v.name', all.x=TRUE) - -PRODFD = merge(PRODFD, Dchain, by.x='Top.D.Gene', by.y='v.name', all.x=TRUE) - -PRODFJ = merge(PRODFJ, Jchain, by.x='Top.J.Gene', by.y='v.name', all.x=TRUE) - -# ---------------------- Create the V, D and J frequency plots and write the data.frame for every plot to a file ---------------------- - -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(); - -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(); - -# ---------------------- Now the frequency plots of the V, D and J families ---------------------- - -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) - -# ---------------------- Plotting the cdr3 length ---------------------- - -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) - -# ---------------------- Plot the heatmaps ---------------------- - - -#get the reverse order for the V and D genes -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$v.name, Sample = unique(inputdata$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$v.name, Sample = unique(inputdata$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$v.name, Sample = unique(inputdata$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) -} - - -# ---------------------- calculating the clonality score ---------------------- - -if("Replicate" %in% colnames(inputdata)) #can only calculate clonality score when replicate information is available -{ - if(clonality_method == "boyd"){ - samples = split(clonalityFrame, clonalityFrame$Sample, drop=T) - - for (sample in samples){ - res = data.frame(paste=character(0)) - sample_id = unique(sample$Sample)[[1]] - for(replicate in unique(sample$Replicate)){ - tmp = sample[sample$Replicate == replicate,] - clone_table = data.frame(table(tmp$clonaltype)) - clone_col_name = paste("V", replicate, sep="") - colnames(clone_table) = c("paste", clone_col_name) - res = merge(res, clone_table, by="paste", all=T) - } - - res[is.na(res)] = 0 - infer.result = infer.clonality(as.matrix(res[,2:ncol(res)])) - - write.table(data.table(infer.result[[12]]), file=paste("lymphclon_clonality_", sample_id, ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=F) - - res$type = rowSums(res[,2:ncol(res)]) - - coincidence.table = data.frame(table(res$type)) - colnames(coincidence.table) = c("Coincidence Type", "Raw Coincidence Freq") - write.table(coincidence.table, file=paste("lymphclon_coincidences_", sample_id, ".csv", sep=""), sep=",",quote=F,row.names=F,col.names=T) - } - } else { - write.table(clonalityFrame, "clonalityComplete.csv", sep=",",quote=F,row.names=F,col.names=T) - - clonalFreq = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "clonaltype")]) - clonalFreqCount = data.frame(data.table(clonalFreq)[, list(Count=.N), by=c("Sample", "Type")]) - clonalFreqCount$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$Weight - - ReplicateReads = data.frame(data.table(clonalityFrame)[, list(Type=.N), by=c("Sample", "Replicate", "clonaltype")]) - ReplicateReads = data.frame(data.table(ReplicateReads)[, list(Reads=.N), by=c("Sample", "Replicate")]) - clonalFreqCount$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(as.numeric(Reads)), ReadsSquaredSum=sum(as.numeric(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$Sample) - lapply(clonalityOverviewSplit, FUN=ClonalityOverviewPrint) - } -} - -imgtcolumns = c("X3V.REGION.trimmed.nt.nb","P3V.nt.nb", "N1.REGION.nt.nb", "P5D.nt.nb", "X5D.REGION.trimmed.nt.nb", "X3D.REGION.trimmed.nt.nb", "P3D.nt.nb", "N2.REGION.nt.nb", "P5J.nt.nb", "X5J.REGION.trimmed.nt.nb", "X3V.REGION.trimmed.nt.nb", "X5D.REGION.trimmed.nt.nb", "X3D.REGION.trimmed.nt.nb", "X5J.REGION.trimmed.nt.nb", "N1.REGION.nt.nb", "N2.REGION.nt.nb", "P3V.nt.nb", "P5D.nt.nb", "P3D.nt.nb", "P5J.nt.nb") -if(all(imgtcolumns %in% colnames(inputdata))) -{ - print("found IMGT columns, running junction analysis") - newData = data.frame(data.table(PRODF)[,list(unique=.N, - VH.DEL=mean(.SD$X3V.REGION.trimmed.nt.nb, na.rm=T), - P1=mean(.SD$P3V.nt.nb, na.rm=T), - N1=mean(.SD$N1.REGION.nt.nb, na.rm=T), - P2=mean(.SD$P5D.nt.nb, na.rm=T), - DEL.DH=mean(.SD$X5D.REGION.trimmed.nt.nb, na.rm=T), - DH.DEL=mean(.SD$X3D.REGION.trimmed.nt.nb, na.rm=T), - P3=mean(.SD$P3D.nt.nb, na.rm=T), - N2=mean(.SD$N2.REGION.nt.nb, na.rm=T), - P4=mean(.SD$P5J.nt.nb, na.rm=T), - DEL.JH=mean(.SD$X5J.REGION.trimmed.nt.nb, na.rm=T), - Total.Del=( mean(.SD$X3V.REGION.trimmed.nt.nb, na.rm=T) + - mean(.SD$X5D.REGION.trimmed.nt.nb, na.rm=T) + - mean(.SD$X3D.REGION.trimmed.nt.nb, na.rm=T) + - mean(.SD$X5J.REGION.trimmed.nt.nb, na.rm=T)), - - Total.N=( mean(.SD$N1.REGION.nt.nb, na.rm=T) + - mean(.SD$N2.REGION.nt.nb, na.rm=T)), - - Total.P=( mean(.SD$P3V.nt.nb, na.rm=T) + - mean(.SD$P5D.nt.nb, na.rm=T) + - mean(.SD$P3D.nt.nb, na.rm=T) + - mean(.SD$P5J.nt.nb, na.rm=T))), - by=c("Sample")]) - print(newData) - newData[,sapply(newData, is.numeric)] = round(newData[,sapply(newData, is.numeric)],1) - write.table(newData, "junctionAnalysisProd.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F) - - newData = data.frame(data.table(UNPROD)[,list(unique=.N, - VH.DEL=mean(.SD$X3V.REGION.trimmed.nt.nb, na.rm=T), - P1=mean(.SD$P3V.nt.nb, na.rm=T), - N1=mean(.SD$N1.REGION.nt.nb, na.rm=T), - P2=mean(.SD$P5D.nt.nb, na.rm=T), - DEL.DH=mean(.SD$X5D.REGION.trimmed.nt.nb, na.rm=T), - DH.DEL=mean(.SD$X3D.REGION.trimmed.nt.nb, na.rm=T), - P3=mean(.SD$P3D.nt.nb, na.rm=T), - N2=mean(.SD$N2.REGION.nt.nb, na.rm=T), - P4=mean(.SD$P5J.nt.nb, na.rm=T), - DEL.JH=mean(.SD$X5J.REGION.trimmed.nt.nb, na.rm=T), - Total.Del=(mean(.SD$X3V.REGION.trimmed.nt.nb, na.rm=T) + - mean(.SD$X5D.REGION.trimmed.nt.nb, na.rm=T) + - mean(.SD$X3D.REGION.trimmed.nt.nb, na.rm=T) + - mean(.SD$X5J.REGION.trimmed.nt.nb, na.rm=T)), - Total.N=( mean(.SD$N1.REGION.nt.nb, na.rm=T) + - mean(.SD$N2.REGION.nt.nb, na.rm=T)), - Total.P=( mean(.SD$P3V.nt.nb, na.rm=T) + - mean(.SD$P5D.nt.nb, na.rm=T) + - mean(.SD$P3D.nt.nb, na.rm=T) + - mean(.SD$P5J.nt.nb, na.rm=T))), - by=c("Sample")]) - newData[,sapply(newData, is.numeric)] = round(newData[,sapply(newData, is.numeric)],1) - write.table(newData, "junctionAnalysisUnProd.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F) -} - -# ---------------------- AA composition in CDR3 ---------------------- - -AACDR3 = PRODF[,c("Sample", "CDR3.Seq")] - -TotalPerSample = data.frame(data.table(AACDR3)[, list(total=sum(nchar(as.character(.SD$CDR3.Seq)))), by=Sample]) - -AAfreq = list() - -for(i in 1:nrow(TotalPerSample)){ - sample = TotalPerSample$Sample[i] - AAfreq[[i]] = data.frame(table(unlist(strsplit(as.character(AACDR3[AACDR3$Sample == sample,c("CDR3.Seq")]), "")))) - AAfreq[[i]]$Sample = sample -} - -AAfreq = ldply(AAfreq, data.frame) -AAfreq = merge(AAfreq, TotalPerSample, by="Sample", all.x = T) -AAfreq$freq_perc = as.numeric(AAfreq$Freq / AAfreq$total * 100) - - -AAorder = read.table(sep="\t", header=TRUE, text="order.aa\tAA\n1\tR\n2\tK\n3\tN\n4\tD\n5\tQ\n6\tE\n7\tH\n8\tP\n9\tY\n10\tW\n11\tS\n12\tT\n13\tG\n14\tA\n15\tM\n16\tC\n17\tF\n18\tL\n19\tV\n20\tI") -AAfreq = merge(AAfreq, AAorder, by.x='Var1', by.y='AA', all.x=TRUE) - -AAfreq = AAfreq[!is.na(AAfreq$order.aa),] - -AAfreqplot = ggplot(AAfreq) -AAfreqplot = AAfreqplot + geom_bar(aes( x=factor(reorder(Var1, order.aa)), y = freq_perc, fill = Sample), stat='identity', position='dodge' ) -AAfreqplot = AAfreqplot + annotate("rect", xmin = 0.5, xmax = 2.5, ymin = 0, ymax = Inf, fill = "red", alpha = 0.2) -AAfreqplot = AAfreqplot + annotate("rect", xmin = 3.5, xmax = 4.5, ymin = 0, ymax = Inf, fill = "blue", alpha = 0.2) -AAfreqplot = AAfreqplot + annotate("rect", xmin = 5.5, xmax = 6.5, ymin = 0, ymax = Inf, fill = "blue", alpha = 0.2) -AAfreqplot = AAfreqplot + annotate("rect", xmin = 6.5, xmax = 7.5, ymin = 0, ymax = Inf, fill = "red", alpha = 0.2) -AAfreqplot = AAfreqplot + ggtitle("Amino Acid Composition in the CDR3") + xlab("Amino Acid, from Hydrophilic (left) to Hydrophobic (right)") + ylab("Percentage") - -png("AAComposition.png",width = 1280, height = 720) -AAfreqplot -dev.off() -write.table(AAfreq, "AAComposition.csv" , sep=",",quote=F,na="-",row.names=F,col.names=T) - -
--- a/report_clonality/r_wrapper.sh.old Tue Feb 28 08:10:34 2017 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,315 +0,0 @@ -#!/bin/bash - -inputFile=$1 -outputDir=$3 -outputFile=$3/index.html #$2 -clonalType=$4 -species=$5 -locus=$6 -filterproductive=$7 -clonality_method=$8 - -dir="$(cd "$(dirname "$0")" && pwd)" -useD="false" -if grep -q "$species.*${locus}D" "$dir/genes.txt" ; then - echo "species D region in reference db" - useD="true" -fi -echo "$species" -if [[ "$species" == *"custom"* ]] ; then - loci=(${locus//;/ }) - useD="true" - echo "${loci[@]}" - if [[ "${#loci[@]}" -eq "2" ]] ; then - useD="false" - fi -fi -mkdir $3 -cp $dir/genes.txt $outputDir -Rscript --verbose $dir/RScript.r $inputFile $outputDir $outputDir $clonalType "$species" "$locus" $filterproductive ${clonality_method} 2>&1 -cp $dir/tabber.js $outputDir -cp $dir/style.css $outputDir -cp $dir/script.js $outputDir -cp $dir/jquery-1.11.0.min.js $outputDir -cp $dir/pure-min.css $outputDir -samples=`cat $outputDir/samples.txt` - -echo "<html><center><h1><a href='index.html'>Click here for the results</a></h1>Tip: Open it in a new tab (middle mouse button or right mouse button -> 'open in new tab' on the link above)<br />" > $2 -echo "<table border = 1>" >> $2 -echo "<thead><tr><th>Sample/Replicate</th><th>All</th><th>Productive</th><th>Unique Productive</th><th>Unproductive</th><th>Unique Unproductive</th></tr></thead>" >> $2 -while IFS=, read sample all productive perc_prod productive_unique perc_prod_un unproductive perc_unprod unproductive_unique perc_unprod_un - do - echo "<tr><td>$sample</td>" >> $2 - echo "<td>$all</td>" >> $2 - echo "<td>$productive (${perc_prod}%)</td>" >> $2 - echo "<td>$productive_unique (${perc_prod_un}%)</td>" >> $2 - echo "<td>$unproductive (${perc_unprod}%)</td>" >> $2 - echo "<td>$unproductive_unique (${perc_unprod_un}%)</td></tr>" >> $2 -done < $outputDir/productive_counting.txt -echo "</table border></center></html>" >> $2 - -echo "<html><head><title>Report on:" >> $outputFile - -mkdir $outputDir/circos -cp $dir/circos/* $outputDir/circos/ -#CIRCOSTOOLS="/data/galaxy/galaxy-dist/toolsheddependencies/circos/0.64/saskia-hiltemann/cg_circos_plots/bbfdd52d64fd/circos-tools-0.21/tools" -#CIRCOSDIR="/data/galaxy/galaxy-dist/toolsheddependencies/circos/0.64/saskia-hiltemann/cg_circos_plots/bbfdd52d64fd/bin/" - -#CIRCOSTOOLS="/home/galaxy/circos/circos-tools-0.22/tools" -#CIRCOSDIR="/home/galaxy/Anaconda3/bin" - -USECIRCOS="no" -if [ -d "$CIRCOSDIR" ]; then - USECIRCOS="yes" -else - if [ -d "/data/galaxy/galaxy-dist/toolsheddependencies/circos/0.64/saskia-hiltemann/cg_circos_plots/bbfdd52d64fd/bin/" ]; then #hopefully temporary fix - USECIRCOS="yes" - CIRCOSTOOLS="/data/galaxy/galaxy-dist/toolsheddependencies/circos/0.64/saskia-hiltemann/cg_circos_plots/bbfdd52d64fd/circos-tools-0.21/tools" - CIRCOSDIR="/data/galaxy/galaxy-dist/toolsheddependencies/circos/0.64/saskia-hiltemann/cg_circos_plots/bbfdd52d64fd/bin/" - fi - - if [ -d "/home/galaxy/Anaconda3/bin" ]; then #hopefully temporary fix - USECIRCOS="yes" - CIRCOSTOOLS="/home/galaxy/circos/circos-tools-0.22/tools" - CIRCOSDIR="/home/galaxy/Anaconda3/bin" - fi -fi - -echo "Using Circos: $USECIRCOS" -sed -i "s%DATA_DIR%$outputDir/circos%" $outputDir/circos/circos.conf -for sample in $samples; do #output the samples to a file and create the circos plots with the R script output - echo " $sample" >> $outputFile - - if [[ "$USECIRCOS" != "yes" ]]; then - continue - fi - - circos_file="$outputDir/${sample}_VJ_circos.txt" - echo -e -n "labels$(cat ${circos_file})" > ${circos_file} - cat "${circos_file}" | $CIRCOSTOOLS/tableviewer/bin/parse-table -configfile $dir/circos/parse-table.conf 2>&1 | $CIRCOSTOOLS/tableviewer/bin/make-conf -dir $outputDir/circos/ - $CIRCOSDIR/circos -conf $outputDir/circos/circos.conf 2>&1 - mv $outputDir/circos/circos.png $outputDir/circosVJ_${sample}.png - - - if [[ "$useD" == "true" ]] ; then - circos_file="$outputDir/${sample}_VD_circos.txt" - echo -e -n "labels$(cat ${circos_file})" > ${circos_file} - cat "${circos_file}" | $CIRCOSTOOLS/tableviewer/bin/parse-table -configfile $dir/circos/parse-table.conf 2>&1 | $CIRCOSTOOLS/tableviewer/bin/make-conf -dir $outputDir/circos/ - $CIRCOSDIR/circos -conf $outputDir/circos/circos.conf 2>&1 - mv $outputDir/circos/circos.png $outputDir/circosVD_${sample}.png - - circos_file="$outputDir/${sample}_DJ_circos.txt" - echo -e -n "labels$(cat ${circos_file})" > ${circos_file} - cat "${circos_file}" | $CIRCOSTOOLS/tableviewer/bin/parse-table -configfile $dir/circos/parse-table.conf 2>&1 | $CIRCOSTOOLS/tableviewer/bin/make-conf -dir $outputDir/circos/ - $CIRCOSDIR/circos -conf $outputDir/circos/circos.conf 2>&1 - mv $outputDir/circos/circos.png $outputDir/circosDJ_${sample}.png - - fi -done -echo "</title><script type='text/javascript' src='jquery-1.11.0.min.js'></script>" >> $outputFile -echo "<link rel='stylesheet' type='text/css' href='pure-min.css'>" >> $outputFile -echo "<script type='text/javascript' src='tabber.js'></script>" >> $outputFile -echo "<script type='text/javascript' src='script.js'></script>" >> $outputFile -echo "<link rel='stylesheet' type='text/css' href='style.css'></head>" >> $outputFile -echo "<div class='tabber'><div class='tabbertab' title='Gene frequencies'>" >> $outputFile - - -echo "<img src='VFPlot.png'/>" >> $outputFile -if [[ "$useD" == "true" ]] ; then - echo "<img src='DFPlot.png'/>" >> $outputFile -fi -echo "<img src='VPlot.png'/>" >> $outputFile -if [[ "$useD" == "true" ]] ; then - echo "<img src='DPlot.png'/>" >> $outputFile -fi -echo "<img src='JPlot.png'/>" >> $outputFile -echo "</div>" >> $outputFile - -echo "<div class='tabbertab' title='CDR3 Characteristics'>" >> $outputFile -echo "<img src='CDR3LengthPlot.png'/><br />" >> $outputFile -echo "<img src='AAComposition.png'/>" >> $outputFile -echo "<img src='DReadingFrame.png'/>" >> $outputFile - -echo "<table class='pure-table pure-table-striped'>" >> $outputFile -echo "<thead><tr><th>Sample</th><th>Median CDR3 Length</th></tr></thead>" >> $outputFile -while IFS=, read Sample median -do - echo "<tr><td>$Sample</td><td>$median</td></tr>" >> $outputFile -done < $outputDir/AAMedianBySample.csv -echo "</table>" >> $outputFile - -echo "</div>" >> $outputFile - -#Heatmaps - -count=1 -echo "<div class='tabbertab' title='Heatmaps'><div class='tabber'>" >> $outputFile -for sample in $samples; do - echo "<div class='tabbertab' title='$sample'><table border='1'><tr>" >> $outputFile - if [[ "$useD" == "true" ]] ; then - echo "<td><img src='HeatmapVD_$sample.png'/></td>" >> $outputFile - fi - echo "<td><img src='HeatmapVJ_$sample.png'/></td>" >> $outputFile - if [[ "$useD" == "true" ]] ; then - echo "<td><img src='HeatmapDJ_$sample.png'/></td>" >> $outputFile - fi - echo "</tr></table></div>" >> $outputFile - count=$((count+1)) -done -echo "</div></div>" >> $outputFile - -#circos - -if [[ "$USECIRCOS" == "yes" ]]; then - - echo "<div class='tabbertab' title='Circos'><div class='tabber'>" >> $outputFile - for sample in $samples; do - echo "<div class='tabbertab' title='$sample'><table border='1'><center>" >> $outputFile - if [[ "$useD" == "true" ]] ; then - echo "<tr><td>V-D</td><td><img src='circosVD_${sample}.png' width='700' height='700'/></td></tr>" >> $outputFile - fi - echo "<tr><td>V-J</td><td><img src='circosVJ_${sample}.png' width='700' height='700'/></td></tr>" >> $outputFile - if [[ "$useD" == "true" ]] ; then - echo "<tr><td>D-J</td><td><img src='circosDJ_${sample}.png' width='700' height='700'/></td></tr>" >> $outputFile - fi - echo "<center></table></div>" >> $outputFile - count=$((count+1)) - done - echo "</div></div>" >> $outputFile -fi -#echo "<div class='tabbertab' title='Interactive'><svg class='chart'></svg><script src='http://d3js.org/d3.v3.min.js'></script></div>" >> $outputFile - -hasReplicateColumn="$(if head -n 1 $inputFile | grep -q 'Replicate'; then echo 'Yes'; else echo 'No'; fi)" -echo "$hasReplicateColumn" -#if its a 'new' merged file with replicate info -if [[ "$hasReplicateColumn" == "Yes" ]] ; then - echo "<div class='tabbertab' title='Clonality'><div class='tabber'>" >> $outputFile - for sample in $samples; do - echo "${clonality_method}" - if [[ "${clonality_method}" == "old" ]] ; then - echo "in old" - clonalityScore="$(cat $outputDir/ClonalityScore_$sample.csv)" - echo "<div class='tabbertab' title='$sample'><table class='pure-table pure-table-striped'>" >> $outputFile - echo "<thead><tr><th colspan='4'>Clonality Score: $clonalityScore</th></tr></thead>" >> $outputFile - - #replicate,reads,squared - echo "<tr><td>Replicate ID</td><td>Number of Reads</td></tr>" >> $outputFile - while IFS=, read replicate reads squared - do - echo "<tr><td>$replicate</td><td>$reads</td></tr>" >> $outputFile - done < $outputDir/ReplicateReads_$sample.csv - - #sum of reads and reads squared - while IFS=, read readsSum squaredSum - do - echo "<tr><td>Sum</td><td>$readsSum</td></tr>" >> $outputFile - done < $outputDir/ReplicateSumReads_$sample.csv - - #overview - echo "<tr><td>Coincidence Type</td><td>Raw Coincidence Freq</td></tr>" >> $outputFile - while IFS=, read type count weight weightedCount - do - if [[ "$type" -eq "1" ]]; then - echo "<tr><td>$type</td><td>$count</td></tr>" >> $outputFile - else - echo "<tr><td><a href='coincidences_${sample}_${type}.txt'>$type</a></td><td>$count</td></tr>" >> $outputFile - fi - - done < $outputDir/ClonalityOverView_$sample.csv - echo "</table></div>" >> $outputFile - else - echo "in new" - clonalityScore="$(cat $outputDir/lymphclon_clonality_${sample}.csv)" - echo "<div class='tabbertab' title='$sample'>" >> $outputFile - echo "Lymphclon clonality score: <br />$clonalityScore<br /><br />" >> $outputFile - echo "<table border = 1>" >> $outputFile - while IFS=, read type count - do - echo "<tr><td>$type</td><td>$count</td></tr>" >> $outputFile - done < $outputDir/lymphclon_coincidences_$sample.csv - echo "</table></div>" >> $outputFile - fi - done - echo "</div></div>" >> $outputFile -fi - -#hasJunctionData="$(if head -n 1 $inputFile | grep -qE '3V.REGION.trimmed.nt.nb'; then echo 'Yes'; else echo 'No'; fi)" - -#if [[ "$hasJunctionData" == "Yes" ]] ; then -if [ -a "$outputDir/junctionAnalysisProd_mean.csv" ] ; then - echo "<div class='tabbertab' title='Junction Analysis'>" >> $outputFile - echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Productive mean</caption><thead><tr><th>Sample</th><th>count</th><th>V.DEL</th><th>P1</th><th>N1</th><th>P2</th><th>DEL.D</th><th>D.DEL</th><th>P3</th><th>N2</th><th>P4</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>Median.CDR3</th><thead></tr><tbody>" >> $outputFile - while IFS=, read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP median - do - echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELD</td><td>$DDEL</td><td>$P3</td><td>$N2</td><td>$P4</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td><td>$median</td></tr>" >> $outputFile - done < $outputDir/junctionAnalysisProd_mean.csv - echo "</tbody></table>" >> $outputFile - - echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Unproductive mean</caption><thead><tr><th>Sample</th><th>count</th><th>V.DEL</th><th>P1</th><th>N1</th><th>P2</th><th>DEL.D</th><th>D.DEL</th><th>P3</th><th>N2</th><th>P4</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>Median.CDR3</th><thead></tr><tbody>" >> $outputFile - while IFS=, read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP median - do - echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELD</td><td>$DDEL</td><td>$P3</td><td>$N2</td><td>$P4</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td><td>$median</td></tr>" >> $outputFile - done < $outputDir/junctionAnalysisUnProd_mean.csv - echo "</tbody></table>" >> $outputFile - - echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Productive median</caption><thead><tr><th>Sample</th><th>count</th><th>V.DEL</th><th>P1</th><th>N1</th><th>P2</th><th>DEL.D</th><th>D.DEL</th><th>P3</th><th>N2</th><th>P4</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>Median.CDR3</th><thead></tr><tbody>" >> $outputFile - while IFS=, read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP median - do - echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELD</td><td>$DDEL</td><td>$P3</td><td>$N2</td><td>$P4</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td><td>$median</td></tr>" >> $outputFile - done < $outputDir/junctionAnalysisProd_median.csv - echo "</tbody></table>" >> $outputFile - - echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Unproductive median</caption><thead><tr><th>Sample</th><th>count</th><th>V.DEL</th><th>P1</th><th>N1</th><th>P2</th><th>DEL.D</th><th>D.DEL</th><th>P3</th><th>N2</th><th>P4</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>Median.CDR3</th><thead></tr><tbody>" >> $outputFile - while IFS=, read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP median - do - echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELD</td><td>$DDEL</td><td>$P3</td><td>$N2</td><td>$P4</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td><td>$median</td></tr>" >> $outputFile - done < $outputDir/junctionAnalysisUnProd_median.csv - echo "</tbody></table>" >> $outputFile - - echo "</div>" >> $outputFile -fi - -echo "<div class='tabbertab' title='Comparison'><table class='pure-table pure-table-striped'><thead><tr><th>ID</th><th>Include</th></tr></thead>" >> $outputFile -for sample in $samples; do - echo "<tr><td>$sample</td><td><input type='checkbox' onchange=\"javascript:compareAdd('$sample')\" id='compare_checkbox_$sample'/></td></tr>" >> $outputFile -done -echo "</table><div name='comparisonarea'>" >> $outputFile -echo "<table><tr id='comparison_table_vd'></tr></table>" >> $outputFile -echo "<table><tr id='comparison_table_vj'></tr></table>" >> $outputFile -echo "<table><tr id='comparison_table_dj'></tr></table>" >> $outputFile -echo "</div></div>" >> $outputFile - -echo "<div class='tabbertab' title='Downloads'>" >> $outputFile -echo "<table class='pure-table pure-table-striped'>" >> $outputFile -echo "<thead><tr><th>Description</th><th>Link</th></tr></thead>" >> $outputFile -echo "<tr><td>The dataset used to generate the frequency graphs and the heatmaps (Unique based on clonaltype, $clonalType)</td><td><a href='allUnique.csv'>Download</a></td></tr>" >> $outputFile -echo "<tr><td>The dataset used to calculate clonality score (Unique based on clonaltype, $clonalType)</td><td><a href='clonalityComplete.csv'>Download</a></td></tr>" >> $outputFile - -echo "<tr><td>The dataset used to generate the CDR3 length frequency graph</td><td><a href='CDR3LengthPlot.csv'>Download</a></td></tr>" >> $outputFile - -echo "<tr><td>The dataset used to generate the V gene family frequency graph</td><td><a href='VFFrequency.csv'>Download</a></td></tr>" >> $outputFile -if [[ "$useD" == "true" ]] ; then - echo "<tr><td>The dataset used to generate the D gene family frequency graph</td><td><a href='DFFrequency.csv'>Download</a></td></tr>" >> $outputFile -fi - -echo "<tr><td>The dataset used to generate the V gene frequency graph</td><td><a href='VFrequency.csv'>Download</a></td></tr>" >> $outputFile -if [[ "$useD" == "true" ]] ; then - echo "<tr><td>The dataset used to generate the D gene frequency graph</td><td><a href='DFrequency.csv'>Download</a></td></tr>" >> $outputFile -fi -echo "<tr><td>The dataset used to generate the J gene frequency graph</td><td><a href='JFrequency.csv'>Download</a></td></tr>" >> $outputFile -echo "<tr><td>The dataset used to generate the AA composition graph</td><td><a href='AAComposition.csv'>Download</a></td></tr>" >> $outputFile - -for sample in $samples; do - if [[ "$useD" == "true" ]] ; then - echo "<tr><td>The data used to generate the VD heatmap for $sample.</td><td><a href='HeatmapVD_$sample.csv'>Download</a></td></tr>" >> $outputFile - fi - echo "<tr><td>The data used to generate the VJ heatmap for $sample.</td><td><a href='HeatmapVJ_$sample.csv'>Download</a></td></tr>" >> $outputFile - if [[ "$useD" == "true" ]] ; then - echo "<tr><td>The data used to generate the DJ heatmap for $sample.</td><td><a href='HeatmapDJ_$sample.csv'>Download</a></td></tr>" >> $outputFile - fi -done - -echo "<tr><td>A frequency count of V Gene + J Gene + CDR3</td><td><a href='VJCDR3_count.txt'>Download</a></td></tr>" >> $outputFile - -echo "</table>" >> $outputFile -echo "</div></html>" >> $outputFile
--- a/report_clonality/r_wrapper.sh~ Tue Feb 28 08:10:34 2017 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,203 +0,0 @@ -#!/bin/bash - -inputFile=$1 -outputDir=$3 -outputFile=$3/index.html #$2 -clonalType=$4 -species=$5 -locus=$6 -filterproductive=$7 -clonality_method=$8 -dir="$(cd "$(dirname "$0")" && pwd)" -useD="false" -if grep -q "$species.*${locus}D" "$dir/genes.txt" ; then - echo "species D region in reference db" - useD="true" -fi -echo "$species" -if [[ "$species" == *"custom"* ]] ; then - loci=(${locus//;/ }) - useD="true" - echo "${loci[@]}" - if [[ "${#loci[@]}" -eq "2" ]] ; then - useD="false" - fi -fi -mkdir $3 -cp $dir/genes.txt $outputDir -Rscript --verbose $dir/RScript.r $inputFile $outputDir $outputDir $clonalType "$species" "$locus" $filterproductive ${clonality_method} 2>&1 -cp $dir/tabber.js $outputDir -cp $dir/style.css $outputDir -cp $dir/script.js $outputDir -cp $dir/jquery-1.11.0.min.js $outputDir -samples=`cat $outputDir/samples.txt` -echo "<html><center><h1><a href='index.html'>Click here for the results</a></h1>Tip: Open it in a new tab (middle mouse button or right mouse button -> 'open in new tab' on the link above)<br />" > $2 -echo "<table border = 1>" >> $2 -echo "<thead><tr><th>Sample/Replicate</th><th>All</th><th>Productive</th><th>Unique Productive</th><th>Unproductive</th><th>Unique Unproductive</th></tr></thead>" >> $2 -while IFS=, read sample all productive perc_prod productive_unique perc_prod_un unproductive perc_unprod unproductive_unique perc_unprod_un - do - echo "<tr><td>$sample</td>" >> $2 - echo "<td>$all</td>" >> $2 - echo "<td>$productive (${perc_prod}%)</td>" >> $2 - echo "<td>$productive_unique (${perc_prod_un}%)</td>" >> $2 - echo "<td>$unproductive (${perc_unprod}%)</td>" >> $2 - echo "<td>$unproductive_unique (${perc_unprod_un}%)</td></tr>" >> $2 -done < $outputDir/productive_counting.txt -echo "</table border></center></html>" >> $2 - -echo "productive_counting.txt" -echo "<html><head><title>Report on:" >> $outputFile -for sample in $samples; do - echo " $sample" >> $outputFile -done -echo "</title><script type='text/javascript' src='jquery-1.11.0.min.js'></script>" >> $outputFile -echo "<script type='text/javascript' src='tabber.js'></script>" >> $outputFile -echo "<script type='text/javascript' src='script.js'></script>" >> $outputFile -echo "<link rel='stylesheet' type='text/css' href='style.css'></head>" >> $outputFile -echo "<div class='tabber'><div class='tabbertab' title='Gene frequencies'>" >> $outputFile - -echo "<img src='CDR3LengthPlot.png'/><br />" >> $outputFile -echo "<img src='VFPlot.png'/>" >> $outputFile -if [[ "$useD" == "true" ]] ; then - echo "<img src='DFPlot.png'/>" >> $outputFile -fi -echo "<img src='JFPlot.png'/>" >> $outputFile -echo "<img src='VPlot.png'/>" >> $outputFile -if [[ "$useD" == "true" ]] ; then - echo "<img src='DPlot.png'/>" >> $outputFile -fi -echo "<img src='JPlot.png'/>" >> $outputFile -echo "<img src='AAComposition.png'/></div>" >> $outputFile - -count=1 -echo "<div class='tabbertab' title='Heatmaps'><div class='tabber'>" >> $outputFile -for sample in $samples; do - echo "<div class='tabbertab' title='$sample'><table border='1'><tr>" >> $outputFile - if [[ "$useD" == "true" ]] ; then - echo "<td><img src='HeatmapVD_$sample.png'/></td>" >> $outputFile - fi - echo "<td><img src='HeatmapVJ_$sample.png'/></td>" >> $outputFile - if [[ "$useD" == "true" ]] ; then - echo "<td><img src='HeatmapDJ_$sample.png'/></td>" >> $outputFile - fi - echo "</tr></table></div>" >> $outputFile - count=$((count+1)) -done -echo "</div></div>" >> $outputFile - -#echo "<div class='tabbertab' title='Interactive'><svg class='chart'></svg><script src='http://d3js.org/d3.v3.min.js'></script></div>" >> $outputFile - -hasReplicateColumn="$(if head -n 1 $inputFile | grep -q 'Replicate'; then echo 'Yes'; else echo 'No'; fi)" -echo "$hasReplicateColumn" -#if its a 'new' merged file with replicate info -if [[ "$hasReplicateColumn" == "Yes" && "$clonalType" != "none" ]] ; then - echo "<div class='tabbertab' title='Clonality'><div class='tabber'>" >> $outputFile - for sample in $samples; do - echo "${clonality_method}" - if [[ "${clonality_method}" == "old" ]] ; then - echo "in old" - clonalityScore="$(cat $outputDir/ClonalityScore_$sample.csv)" - echo "<div class='tabbertab' title='$sample'><table border='1'>" >> $outputFile - echo "<tr><td colspan='4'>Clonality Score: $clonalityScore</td></tr>" >> $outputFile - - #replicate,reads,squared - echo "<tr><td>Replicate ID</td><td>Number of Reads</td><td>Reads Squared</td><td></td></tr>" >> $outputFile - while IFS=, read replicate reads squared - do - - echo "<tr><td>$replicate</td><td>$reads</td><td>$squared</td><td></td></tr>" >> $outputFile - done < $outputDir/ReplicateReads_$sample.csv - - #sum of reads and reads squared - while IFS=, read readsSum squaredSum - do - echo "<tr><td>Sum</td><td>$readsSum</td><td>$squaredSum</td></tr>" >> $outputFile - done < $outputDir/ReplicateSumReads_$sample.csv - - #overview - echo "<tr><td>Coincidence Type</td><td>Raw Coincidence Freq</td><td>Coincidence Weight</td><td>Coincidences, Weighted</td></tr>" >> $outputFile - while IFS=, read type count weight weightedCount - do - echo "<tr><td>$type</td><td>$count</td><td>$weight</td><td>$weightedCount</td></tr>" >> $outputFile - done < $outputDir/ClonalityOverView_$sample.csv - echo "</table></div>" >> $outputFile - else - echo "in new" - clonalityScore="$(cat $outputDir/lymphclon_clonality_${sample}.csv)" - echo "<div class='tabbertab' title='$sample'>" >> $outputFile - echo "Lymphclon clonality score: <br />$clonalityScore<br /><br />" >> $outputFile - echo "<table border = 1>" >> $outputFile - while IFS=, read type count - do - echo "<tr><td>$type</td><td>$count</td></tr>" >> $outputFile - done < $outputDir/lymphclon_coincidences_$sample.csv - echo "</table></div>" >> $outputFile - fi - done - echo "</div></div>" >> $outputFile -fi - -hasJunctionData="$(if head -n 1 $inputFile | grep -q '3V-REGION trimmed-nt'; then echo 'Yes'; else echo 'No'; fi)" - -if [[ "$hasJunctionData" == "Yes" ]] ; then - echo "<div class='tabbertab' title='Junction Analysis'>" >> $outputFile - echo "<table border='1' id='junction_table'> <caption>Productive</caption><thead><tr><th>Sample</th><th>count</th><th>VH.DEL</th><th>P1</th><th>N1</th><th>P2</th><th>DEL.DH</th><th>DH.DEL</th><th>P3</th><th>N2</th><th>P4</th><th>DEL.JH</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><thead></tr><tbody>" >> $outputFile - while IFS=, read Sample unique VHDEL P1 N1 P2 DELDH DHDEL P3 N2 P4 DELJH TotalDel TotalN TotalP - do - echo "<tr><td>$Sample</td><td>$unique</td><td>$VHDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELDH</td><td>$DHDEL</td><td>$P3</td><td>$N2</td><td>$P4</td><td>$DELJH</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td></tr>" >> $outputFile - done < $outputDir/junctionAnalysisProd.csv - echo "</tbody></table>" >> $outputFile - - echo "<table border='1' id='junction_table'> <caption>Unproductive</caption><thead><tr><th>Sample</th><th>count</th><th>VH.DEL</th><th>P1</th><th>N1</th><th>P2</th><th>DEL.DH</th><th>DH.DEL</th><th>P3</th><th>N2</th><th>P4</th><th>DEL.JH</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><thead></tr><tbody>" >> $outputFile - while IFS=, read Sample unique VHDEL P1 N1 P2 DELDH DHDEL P3 N2 P4 DELJH TotalDel TotalN TotalP - do - echo "<tr><td>$Sample</td><td>$unique</td><td>$VHDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELDH</td><td>$DHDEL</td><td>$P3</td><td>$N2</td><td>$P4</td><td>$DELJH</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td></tr>" >> $outputFile - done < $outputDir/junctionAnalysisUnProd.csv - echo "</tbody></table>" >> $outputFile - - echo "</div>" >> $outputFile -fi - -echo "<div class='tabbertab' title='Comparison'><table border='1'><tr><th>ID</th><th>Include</th></tr>" >> $outputFile -for sample in $samples; do - echo "<tr><td>$sample</td><td><input type='checkbox' onchange=\"javascript:compareAdd('$sample')\" id='compare_checkbox_$sample'/></td></tr>" >> $outputFile -done -echo "</table><div name='comparisonarea'>" >> $outputFile -echo "<table><tr id='comparison_table_vd'></tr></table>" >> $outputFile -echo "<table><tr id='comparison_table_vj'></tr></table>" >> $outputFile -echo "<table><tr id='comparison_table_dj'></tr></table>" >> $outputFile -echo "</div></div>" >> $outputFile - -echo "<div class='tabbertab' title='Downloads'>" >> $outputFile -echo "<table border='1'>" >> $outputFile -echo "<tr><th>Description</th><th>Link</th></tr>" >> $outputFile -echo "<tr><td>The dataset used to generate the frequency graphs and the heatmaps (Unique based on clonaltype, $clonalType)</td><td><a href='allUnique.csv'>Download</a></td></tr>" >> $outputFile -echo "<tr><td>The dataset used to calculate clonality score (Unique based on clonaltype, $clonalType)</td><td><a href='clonalityComplete.csv'>Download</a></td></tr>" >> $outputFile - -echo "<tr><td>The dataset used to generate the CDR3 length frequency graph</td><td><a href='CDR3LengthPlot.csv'>Download</a></td></tr>" >> $outputFile - -echo "<tr><td>The dataset used to generate the V gene family frequency graph</td><td><a href='VFFrequency.csv'>Download</a></td></tr>" >> $outputFile -if [[ "$useD" == "true" ]] ; then - echo "<tr><td>The dataset used to generate the D gene family frequency graph</td><td><a href='DFFrequency.csv'>Download</a></td></tr>" >> $outputFile -fi -echo "<tr><td>The dataset used to generate the J gene family frequency graph</td><td><a href='JFFrequency.csv'>Download</a></td></tr>" >> $outputFile - -echo "<tr><td>The dataset used to generate the V gene frequency graph</td><td><a href='VFrequency.csv'>Download</a></td></tr>" >> $outputFile -if [[ "$useD" == "true" ]] ; then - echo "<tr><td>The dataset used to generate the D gene frequency graph</td><td><a href='DFrequency.csv'>Download</a></td></tr>" >> $outputFile -fi -echo "<tr><td>The dataset used to generate the J gene frequency graph</td><td><a href='JFrequency.csv'>Download</a></td></tr>" >> $outputFile -echo "<tr><td>The dataset used to generate the AA composition graph</td><td><a href='AAComposition.csv'>Download</a></td></tr>" >> $outputFile - -for sample in $samples; do - if [[ "$useD" == "true" ]] ; then - echo "<tr><td>The data used to generate the VD heatmap for $sample.</td><td><a href='HeatmapVD_$sample.csv'>Download</a></td></tr>" >> $outputFile - fi - echo "<tr><td>The data used to generate the VJ heatmap for $sample.</td><td><a href='HeatmapVJ_$sample.csv'>Download</a></td></tr>" >> $outputFile - if [[ "$useD" == "true" ]] ; then - echo "<tr><td>The data used to generate the DJ heatmap for $sample.</td><td><a href='HeatmapDJ_$sample.csv'>Download</a></td></tr>" >> $outputFile - fi -done - -echo "</table>" >> $outputFile -echo "</div></html>" >> $outputFile