Mercurial > repos > davidvanzessen > argalaxy_tools

changeset 24:d5d203d38c8a draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Wed, 01 Feb 2017 09:48:38 -0500
parents e2fbdfacec1d
children 94765af0db1f
files complete.sh report_clonality/RScript.r report_clonality/r_wrapper.sh
diffstat 3 files changed, 166 insertions(+), 53 deletions(-) [+]
line wrap: on
line diff
--- a/complete.sh	Fri Jan 27 04:29:43 2017 -0500
+++ b/complete.sh	Wed Feb 01 09:48:38 2017 -0500
@@ -19,6 +19,10 @@
 #unzip $dir/database.zip -d $PWD/igblastdatabase/
 #export IGDATA=$PWD/igblastdatabase/
 
+echo "python: `which python`"
+echo "R: `which R`"
+echo "Rscript: `which Rscript`"
+
 id=""
 forwardSlash="/"
 mergerInput=()
@@ -39,6 +43,7 @@
 	f=$(file $current)
 	zipType="Zip archive"
 	zxType="XZ compressed data"
+	echo "filetype of ${id}: $f"
   	if [[ "$f" == *"$zipType"* ]] || [[ "$f" == *"$zxType"* ]]
 	then
 		echo "<tr><td>Sample $count of patient $id is an archive file, using IMGT Loader</td></tr>" >> $html
--- a/report_clonality/RScript.r	Fri Jan 27 04:29:43 2017 -0500
+++ b/report_clonality/RScript.r	Wed Feb 01 09:48:38 2017 -0500
@@ -49,6 +49,7 @@
 
 inputdata = read.table(infile, sep="\t", header=TRUE, fill=T, comment.char="", stringsAsFactors=F)
 
+
 print(paste("nrows: ", nrow(inputdata)))
 
 setwd(outdir)
@@ -121,9 +122,6 @@
   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")])
 
@@ -162,6 +160,9 @@
 #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)
 
+print("SAMPLE TABLE:")
+print(table(PRODF$Sample))
+
 #write the samples to a file
 sampleFile <- file("samples.txt")
 un = unique(inputdata$Sample)
@@ -383,7 +384,7 @@
 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)
+write.table(x=CDR3Length, file="CDR3LengthPlot.txt", sep="\t",quote=F,row.names=F,col.names=T)
 
 # ---------------------- Plot the heatmaps ----------------------
 
@@ -412,7 +413,7 @@
     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)
+    write.table(x=acast(dat, Top.V.Gene~Top.D.Gene, value.var="Length"), file=paste("HeatmapVD_", unique(dat[3])[1,1], ".txt", sep=""), sep="\t",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")])
@@ -462,7 +463,7 @@
   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)
+  write.table(x=acast(dat, Top.V.Gene~Top.J.Gene, value.var="Length"), file=paste("HeatmapVJ_", unique(dat[3])[1,1], ".txt", sep=""), sep="\t",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")])
@@ -511,7 +512,7 @@
     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)
+    write.table(x=acast(dat, Top.D.Gene~Top.J.Gene, value.var="Length"), file=paste("HeatmapDJ_", unique(dat[3])[1,1], ".txt", sep=""), sep="\t",quote=F,row.names=T,col.names=NA)
   }
   
   
@@ -701,17 +702,7 @@
 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){
@@ -730,9 +721,12 @@
 	  }
   }
   
+  PRODF.with.D = PRODF[nchar(PRODF$Top.D.Gene, keepNA=F) > 2,]
+  PRODF.no.D = PRODF[nchar(PRODF$Top.D.Gene, keepNA=F) < 4,]
+  
   num_median = function(x, na.rm=T) { as.numeric(median(x, na.rm=na.rm)) }
   
-  newData = data.frame(data.table(PRODF)[,list(unique=.N, 
+  newData = data.frame(data.table(PRODF.with.D)[,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)),
@@ -749,9 +743,9 @@
                                                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)
+  write.table(newData, "junctionAnalysisProd_mean_wD.txt" , sep="\t",quote=F,na="-",row.names=F,col.names=F)
   
-  newData = data.frame(data.table(PRODF)[,list(unique=.N, 
+  newData = data.frame(data.table(PRODF.with.D)[,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)),
@@ -768,9 +762,9 @@
 											   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)
+  write.table(newData, "junctionAnalysisProd_median_wD.txt" , sep="\t",quote=F,na="-",row.names=F,col.names=F)
   
-  newData = data.frame(data.table(UNPROD)[,list(unique=.N, 
+  newData = data.frame(data.table(PRODF.with.D)[,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)),
@@ -787,9 +781,9 @@
                                                 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)
+  write.table(newData, "junctionAnalysisUnProd_mean_wD.txt" , sep="\t",quote=F,na="-",row.names=F,col.names=F)
   
-    newData = data.frame(data.table(UNPROD)[,list(unique=.N, 
+    newData = data.frame(data.table(PRODF.with.D)[,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)),
@@ -805,9 +799,67 @@
                                                 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$CDR3.Length))),
 															by=c("Sample")])
-															
+  newData[,sapply(newData, is.numeric)] = round(newData[,sapply(newData, is.numeric)],1)
+  write.table(newData, "junctionAnalysisUnProd_median_wD.txt" , sep="\t",quote=F,na="-",row.names=F,col.names=F)
+  
+  #---------------- again for no-D
+  
+  newData = data.frame(data.table(PRODF.no.D)[,list(unique=.N, 
+                                               VH.DEL=mean(.SD$X3V.REGION.trimmed.nt.nb, na.rm=T),
+                                               P1=mean(.SD$P3V.nt.nb, na.rm=T),
+                                               N1=mean(rowSums(.SD[,c("N.REGION.nt.nb"), with=F], na.rm=T)),
+                                               P2=mean(.SD$P5J.nt.nb, na.rm=T),
+                                               DEL.JH=mean(.SD$X5J.REGION.trimmed.nt.nb, na.rm=T),
+                                               Total.Del=mean(rowSums(.SD[,c("X3V.REGION.trimmed.nt.nb", "X5J.REGION.trimmed.nt.nb"), with=F], na.rm=T)),
+                                               Total.N=mean(rowSums(.SD[,c("N.REGION.nt.nb"), with=F], na.rm=T)),
+                                               Total.P=mean(rowSums(.SD[,c("P3V.nt.nb", "P5J.nt.nb"), with=F], na.rm=T)),
+                                               Median.CDR3.l=as.double(median(.SD$CDR3.Length))),
+                                         by=c("Sample")])
+  print(newData)
   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)
+  write.table(newData, "junctionAnalysisProd_mean_nD.txt" , sep="\t",quote=F,na="-",row.names=F,col.names=F)
+  
+  newData = data.frame(data.table(PRODF.no.D)[,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"), with=F], na.rm=T)),
+                                               P2=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", "X5J.REGION.trimmed.nt.nb"), with=F], na.rm=T)),
+											   Total.N=num_median(rowSums(.SD[,c("N.REGION.nt.nb"), with=F], na.rm=T)),
+											   Total.P=num_median(rowSums(.SD[,c("P3V.nt.nb", "P5J.nt.nb"), with=F], na.rm=T)),
+											   Median.CDR3.l=as.double(median(.SD$CDR3.Length))),
+                                         by=c("Sample")])
+  newData[,sapply(newData, is.numeric)] = round(newData[,sapply(newData, is.numeric)],1)
+  write.table(newData, "junctionAnalysisProd_median_nD.txt" , sep="\t",quote=F,na="-",row.names=F,col.names=F)
+  
+  newData = data.frame(data.table(PRODF.no.D)[,list(unique=.N, 
+                                                VH.DEL=mean(.SD$X3V.REGION.trimmed.nt.nb, na.rm=T),
+                                                P1=mean(.SD$P3V.nt.nb, na.rm=T),
+                                                N1=mean(rowSums(.SD[,c("N.REGION.nt.nb"), with=F], na.rm=T)),
+                                                P2=mean(.SD$P5J.nt.nb, na.rm=T),
+                                                DEL.JH=mean(.SD$X5J.REGION.trimmed.nt.nb, na.rm=T),
+                                                Total.Del=mean(rowSums(.SD[,c("X3V.REGION.trimmed.nt.nb", "X5J.REGION.trimmed.nt.nb"), with=F], na.rm=T)),
+                                                Total.N=mean(rowSums(.SD[,c("N.REGION.nt.nb"), with=F], na.rm=T)),
+                                                Total.P=mean(rowSums(.SD[,c("P3V.nt.nb", "P5J.nt.nb"), with=F], na.rm=T)),
+                                                Median.CDR3.l=as.double(median(.SD$CDR3.Length))),
+                                          by=c("Sample")])
+  newData[,sapply(newData, is.numeric)] = round(newData[,sapply(newData, is.numeric)],1)
+  write.table(newData, "junctionAnalysisUnProd_mean_nD.txt" , sep="\t",quote=F,na="-",row.names=F,col.names=F)
+  
+    newData = data.frame(data.table(PRODF.no.D)[,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"), with=F], na.rm=T)),
+                                                P2=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", "X5J.REGION.trimmed.nt.nb"), with=F], na.rm=T)),
+                                                Total.N=num_median(rowSums(.SD[,c("N.REGION.nt.nb"), with=F], na.rm=T)),
+                                                Total.P=num_median(rowSums(.SD[,c("P3V.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_nD.txt" , sep="\t",quote=F,na="-",row.names=F,col.names=F)
 }
 
 PRODF = bak
@@ -822,12 +874,18 @@
 	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")])
+D.REGION.reading.frame.1 = data.frame(data.table(D.REGION.reading.frame)[, list(Freq=.N), by=c("Sample", "D.REGION.reading.frame")])
+
+D.REGION.reading.frame.2 = data.frame(data.table(D.REGION.reading.frame)[, list(sample.sum=sum(as.numeric(.SD$D.REGION.reading.frame), na.rm=T)), by=c("Sample")])
 
-write.table(D.REGION.reading.frame, "DReadingFrame.csv" , sep="\t",quote=F,row.names=F,col.names=T)
+D.REGION.reading.frame = merge(D.REGION.reading.frame.1, D.REGION.reading.frame.2, by="Sample")
+
+D.REGION.reading.frame$percentage = round(D.REGION.reading.frame$Freq / D.REGION.reading.frame$sample.sum * 100, 1)
+
+write.table(D.REGION.reading.frame, "DReadingFrame.txt" , 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 + geom_bar(aes( x = D.REGION.reading.frame, y = percentage, 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())
 
@@ -878,6 +936,6 @@
 
 # ---------------------- AA median CDR3 length ----------------------
 
-median.aa.l = data.frame(data.table(PRODF)[, list(median=as.double(median(.SD$CDR3.Length))), by=c("Sample")])
-write.table(median.aa.l, "AAMedianBySample.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F)
+median.aa.l = data.frame(data.table(PRODF)[, list(median=as.double(median(as.numeric(.SD$CDR3.Length, na.rm=T), na.rm=T))), by=c("Sample")])
+write.table(median.aa.l, "AAMedianBySample.txt" , sep="\t",quote=F,na="-",row.names=F,col.names=F)
 
--- a/report_clonality/r_wrapper.sh	Fri Jan 27 04:29:43 2017 -0500
+++ b/report_clonality/r_wrapper.sh	Wed Feb 01 09:48:38 2017 -0500
@@ -72,7 +72,7 @@
 		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
+	if [ -d "/home/galaxy/Anaconda3/bin" ]; then #hopefully temporary fix #or not
 		USECIRCOS="yes"
 		CIRCOSTOOLS="/home/galaxy/circos/circos-tools-0.22/tools"
 		CIRCOSDIR="/home/galaxy/Anaconda3/bin"
@@ -126,7 +126,9 @@
 if [[ "$useD" == "true" ]] ; then
 	echo "<img src='DPlot.png'/>" >> $outputFile
 fi
-echo "<img src='JPlot.png'/>" >> $outputFile
+echo "<img src='JPlot.png'/> <br />" >> $outputFile
+
+echo "<img src='DReadingFrame.png'/>" >> $outputFile
 
 cat $dir/naive_gene_freq.htm >> $outputFile
 
@@ -135,14 +137,14 @@
 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>Donor</th><th>Median CDR3 Length</th></tr></thead>" >> $outputFile
-while IFS=, read Sample median
+while read Sample median
 do
 	echo "<tr><td>$Sample</td><td>$median</td></tr>" >> $outputFile
-done < $outputDir/AAMedianBySample.csv
+done < $outputDir/AAMedianBySample.txt
 echo "</table>" >> $outputFile
 
 cat $dir/naive_cdr3_char.htm >> $outputFile
@@ -278,36 +280,67 @@
 #hasJunctionData="$(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
+if [ -a "$outputDir/junctionAnalysisProd_mean_wD.txt" ] ; then
 	echo "<div class='tabbertab' title='Junction Analysis'>" >> $outputFile
 	echo "<img src='IGH_junctie_analyse.png' />" >> $outputFile
 	
+	echo "<center><p style='font-size: 20;'>Unique rearrangements with a V, D and J gene assigned</p></center>" >> $outputFile
 	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Productive mean</caption><thead><tr><th>Donor</th><th>Number of sequences</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>" >> $outputFile
-	while IFS=, read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP median
+	while read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP median
 	do
 		echo "<tr><td>$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
+	done < $outputDir/junctionAnalysisProd_mean_wD.txt
 	echo "</tbody></table>" >> $outputFile
 	
 	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Unproductive mean</caption><thead><tr><th>Donor</th><th>Number of sequences</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>" >> $outputFile
-	while IFS=, read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP median
+	while read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP median
 	do
 		echo "<tr><td>$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
+	done < $outputDir/junctionAnalysisUnProd_mean_wD.txt
 	echo "</tbody></table>" >> $outputFile
 	
 	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Productive median</caption><thead><tr><th>Donor</th><th>Number of sequences</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>" >> $outputFile
-	while IFS=, read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP median
+	while read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP median
 	do
 		echo "<tr><td>$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
+	done < $outputDir/junctionAnalysisProd_median_wD.txt
 	echo "</tbody></table>" >> $outputFile
 	
 	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Unproductive median</caption><thead><tr><th>Donor</th><th>Number of sequences</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>" >> $outputFile
-	while IFS=, read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP median
+	while read Sample unique VDEL P1 N1 P2 DELD DDEL P3 N2 P4 DELJ TotalDel TotalN TotalP median
 	do
 		echo "<tr><td>$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
+	done < $outputDir/junctionAnalysisUnProd_median_wD.txt
+	echo "</tbody></table>" >> $outputFile
+	
+	# again for no-d
+	echo "<center><p style='font-size: 20;'>Unique rearrangements with only a V and J gene assigned</p></center>" >> $outputFile
+	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Productive mean</caption><thead><tr><th>Donor</th><th>Number of sequences</th><th>V.DEL</th><th>P1</th><th>N</th><th>P2</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>Median.CDR3</th><thead></tr><tbody>" >> $outputFile
+	while read Sample unique VDEL P1 N1 P2 DELJ TotalDel TotalN TotalP median
+	do
+		echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td><td>$median</td></tr>" >> $outputFile
+	done < $outputDir/junctionAnalysisProd_mean_nD.txt
+	echo "</tbody></table>" >> $outputFile
+	
+	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Unproductive mean</caption><thead><tr><th>Donor</th><th>Number of sequences</th><th>V.DEL</th><th>P1</th><th>N</th><th>P2</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>Median.CDR3</th><thead></tr><tbody>" >> $outputFile
+	while read Sample unique VDEL P1 N1 P2 DELJ TotalDel TotalN TotalP median
+	do
+		echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td><td>$median</td></tr>" >> $outputFile
+	done < $outputDir/junctionAnalysisUnProd_mean_nD.txt
+	echo "</tbody></table>" >> $outputFile
+	
+	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Productive median</caption><thead><tr><th>Donor</th><th>Number of sequences</th><th>V.DEL</th><th>P1</th><th>N</th><th>P2</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>Median.CDR3</th><thead></tr><tbody>" >> $outputFile
+	while read Sample unique VDEL P1 N1 P2 DELJ TotalDel TotalN TotalP median
+	do
+		echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td><td>$median</td></tr>" >> $outputFile
+	done < $outputDir/junctionAnalysisProd_median_nD.txt
+	echo "</tbody></table>" >> $outputFile
+	
+	echo "<table class='pure-table pure-table-striped' id='junction_table'> <caption>Unproductive median</caption><thead><tr><th>Donor</th><th>Number of sequences</th><th>V.DEL</th><th>P1</th><th>N</th><th>P2</th><th>DEL.J</th><th>Total.Del</th><th>Total.N</th><th>Total.P</th><th>Median.CDR3</th><thead></tr><tbody>" >> $outputFile
+	while read Sample unique VDEL P1 N1 P2 DELJ TotalDel TotalN TotalP median
+	do
+		echo "<tr><td>$Sample</td><td>$unique</td><td>$VDEL</td><td>$P1</td><td>$N1</td><td>$P2</td><td>$DELJ</td><td>$TotalDel</td><td>$TotalN</td><td>$TotalP</td><td>$median</td></tr>" >> $outputFile
+	done < $outputDir/junctionAnalysisUnProd_median_nD.txt
 	echo "</tbody></table>" >> $outputFile
 	
 	cat $dir/naive_junction.htm >> $outputFile
@@ -319,9 +352,7 @@
 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 filtered dataset</td><td><a href='allUnique.txt'>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.txt'>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 colspan='2' style='background-color:#E0E0E0;'>Gene frequencies</td></tr>" >> $outputFile
 
 echo "<tr><td>The dataset used to generate the distribution of V gene families graph</td><td><a href='VFFrequency.txt'>Download</a></td></tr>" >> $outputFile
 if [[ "$useD" == "true" ]] ; then
@@ -333,19 +364,38 @@
 	echo "<tr><td>The dataset used to generate the relative frequency of D gene usage graph</td><td><a href='DFrequency.txt'>Download</a></td></tr>" >> $outputFile
 fi
 echo "<tr><td>The dataset used to generate the relative frequency of J gene usage graph</td><td><a href='JFrequency.txt'>Download</a></td></tr>" >> $outputFile
+echo "<tr><td>The dataset used to generate the relative frequency of the D reading frame graph</td><td><a href='DReadingFrame.txt'>Download</a></td></tr>" >> $outputFile
+
+echo "<tr><td colspan='2' style='background-color:#E0E0E0;'>CDR3 Characteristics</td></tr>" >> $outputFile
+echo "<tr><td>The dataset used to generate the CDR3 length frequency graph</td><td><a href='CDR3LengthPlot.txt'>Download</a></td></tr>" >> $outputFile
 echo "<tr><td>The dataset used to generate the Amino Acid Composition in the CDR3 graph</td><td><a href='AAComposition.txt'>Download</a></td></tr>" >> $outputFile
 
+echo "<tr><td colspan='2' style='background-color:#E0E0E0;'>Heatmaps</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
+		echo "<tr><td>The data used to generate the VD heatmap for $sample.</td><td><a href='HeatmapVD_$sample.txt'>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
+	echo "<tr><td>The data used to generate the VJ heatmap for $sample.</td><td><a href='HeatmapVJ_$sample.txt'>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
+		echo "<tr><td>The data used to generate the DJ heatmap for $sample.</td><td><a href='HeatmapDJ_$sample.txt'>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 "<tr><td colspan='2' style='background-color:#E0E0E0;'>Circos</td></tr>" >> $outputFile
+for sample in $samples; do
+	if [[ "$useD" == "true" ]] ; then
+		echo "<tr><td>The data used to generate the VD Circos plots for $sample.</td><td><a href='${sample}_VD_circos.txt'>Download</a></td></tr>" >> $outputFile
+	fi
+	echo "<tr><td>The data used to generate the VJ Circos plots for $sample.</td><td><a href='${sample}_VJ_circos.txt'>Download</a></td></tr>" >> $outputFile
+	if [[ "$useD" == "true" ]] ; then
+		echo "<tr><td>The data used to generate the DJ Circos plots for $sample.</td><td><a href='${sample}_DJ_circos.txt'>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 "<tr><td colspan='2' style='background-color:#E0E0E0;'>Clonality</td></tr>" >> $outputFile
+echo "<tr><td>The dataset used to calculate clonality score (Unique based on clonaltype, $clonalType)</td><td><a href='clonalityComplete.txt'>Download</a></td></tr>" >> $outputFile
 
 echo "</table>" >> $outputFile