# HG changeset patch
# User davidvanzessen
# Date 1438344485 14400
# Node ID edbf4fba5fc72ae254a9fa77d72ad3d07d33bbc4
# Parent 079eed22fdb66ae9c9636873a21d347787d2a2fa
Uploaded
diff -r 079eed22fdb6 -r edbf4fba5fc7 complete.sh
--- a/complete.sh Thu Jul 30 10:00:08 2015 -0400
+++ b/complete.sh Fri Jul 31 08:08:05 2015 -0400
@@ -35,8 +35,8 @@
fi
echo "working on $current"
fileName=$(basename $current)
- parsedFileName="${fileName%.*}"
- parsedFileName="$PWD/$parsedFileName.parsed"
+ fileName="${fileName%.*}"
+ parsedFileName="$PWD/$fileName.parsed"
f=$(file $current)
zipType="Zip archive"
zxType="XZ compressed data"
@@ -44,7 +44,7 @@
then
echo "| Sample $count of patient $id is an archive file, using IMGT Loader |
" >> $html
fileName=$(basename $current)
- bash ${dir}/imgt_loader/imgt_loader.sh $current $parsedFileName $count $parsedFileName "tmp"
+ bash ${dir}/imgt_loader/imgt_loader.sh $current $parsedFileName "${fileName}"
else
echo "| Sample $count of patient $id is not a zip file, using igBLASTn |
" >> $html
#blastAndParse $current $id $count $fileName $parsedFileName &
diff -r 079eed22fdb6 -r edbf4fba5fc7 report_clonality/RScript.r
--- a/report_clonality/RScript.r Thu Jul 30 10:00:08 2015 -0400
+++ b/report_clonality/RScript.r Fri Jul 31 08:08:05 2015 -0400
@@ -101,7 +101,8 @@
#write the complete dataset that is left over, will be the input if 'none' for clonaltype and 'no' for filterproductive
-write.table(PRODF, "allUnique.csv", sep=",",quote=F,row.names=F,col.names=T)
+write.table(PRODF, "allUnique.txt", sep=",",quote=F,row.names=F,col.names=T)
+write.table(PRODF, "allUnique.csv", sep="\t",quote=F,row.names=F,col.names=T)
write.table(UNPROD, "allUnproductive.csv", sep=",",quote=F,row.names=F,col.names=T)
#write the samples to a file
@@ -554,55 +555,59 @@
imgtcolumns = c("X3V.REGION.trimmed.nt.nb","P3V.nt.nb", "N1.REGION.nt.nb", "P5D.nt.nb", "X5D.REGION.trimmed.nt.nb", "X3D.REGION.trimmed.nt.nb", "P3D.nt.nb", "N2.REGION.nt.nb", "P5J.nt.nb", "X5J.REGION.trimmed.nt.nb", "X3V.REGION.trimmed.nt.nb", "X5D.REGION.trimmed.nt.nb", "X3D.REGION.trimmed.nt.nb", "X5J.REGION.trimmed.nt.nb", "N1.REGION.nt.nb", "N2.REGION.nt.nb", "P3V.nt.nb", "P5D.nt.nb", "P3D.nt.nb", "P5J.nt.nb")
if(all(imgtcolumns %in% colnames(inputdata)))
{
+ print("MEAN P3V.nt.nb:")
+ print(PRODF$P3V.nt.nb)
+ print(mean(PRODF$P3V.nt.nb, na.rm=T))
+ print(head(PRODF))
newData = data.frame(data.table(PRODF)[,list(unique=.N,
- VH.DEL=mean(X3V.REGION.trimmed.nt.nb, na.rm=T),
- P1=mean(P3V.nt.nb, na.rm=T),
- N1=mean(N1.REGION.nt.nb, na.rm=T),
- P2=mean(P5D.nt.nb, na.rm=T),
- DEL.DH=mean(X5D.REGION.trimmed.nt.nb, na.rm=T),
- DH.DEL=mean(X3D.REGION.trimmed.nt.nb, na.rm=T),
- P3=mean(P3D.nt.nb, na.rm=T),
- N2=mean(N2.REGION.nt.nb, na.rm=T),
- P4=mean(P5J.nt.nb, na.rm=T),
- DEL.JH=mean(X5J.REGION.trimmed.nt.nb, na.rm=T),
- Total.Del=( mean(X3V.REGION.trimmed.nt.nb, na.rm=T) +
- mean(X5D.REGION.trimmed.nt.nb, na.rm=T) +
- mean(X3D.REGION.trimmed.nt.nb, na.rm=T) +
- mean(X5J.REGION.trimmed.nt.nb, na.rm=T)),
+ VH.DEL=mean(.SD$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$X5J.REGION.trimmed.nt.nb, na.rm=T)),
- Total.N=( mean(N1.REGION.nt.nb, na.rm=T) +
- mean(N2.REGION.nt.nb, na.rm=T)),
+ Total.N=( mean(.SD$N1.REGION.nt.nb, na.rm=T) +
+ mean(.SD$N2.REGION.nt.nb, na.rm=T)),
- Total.P=( mean(P3V.nt.nb, na.rm=T) +
- mean(P5D.nt.nb, na.rm=T) +
- mean(P3D.nt.nb, na.rm=T) +
- mean(P5J.nt.nb, na.rm=T))),
+ Total.P=( mean(.SD$P3V.nt.nb, na.rm=T) +
+ mean(.SD$P5D.nt.nb, na.rm=T) +
+ mean(.SD$P3D.nt.nb, na.rm=T) +
+ mean(.SD$P5J.nt.nb, na.rm=T))),
by=c("Sample")])
write.table(newData, "junctionAnalysisProd.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F)
newData = data.frame(data.table(UNPROD)[,list(unique=.N,
- VH.DEL=mean(X3V.REGION.trimmed.nt.nb, na.rm=T),
- P1=mean(P3V.nt.nb, na.rm=T),
- N1=mean(N1.REGION.nt.nb, na.rm=T),
- P2=mean(P5D.nt.nb, na.rm=T),
- DEL.DH=mean(X5D.REGION.trimmed.nt.nb, na.rm=T),
- DH.DEL=mean(X3D.REGION.trimmed.nt.nb, na.rm=T),
- P3=mean(P3D.nt.nb, na.rm=T),
- N2=mean(N2.REGION.nt.nb, na.rm=T),
- P4=mean(P5J.nt.nb, na.rm=T),
- DEL.JH=mean(X5J.REGION.trimmed.nt.nb, na.rm=T),
- Total.Del=( mean(X3V.REGION.trimmed.nt.nb, na.rm=T) +
- mean(X5D.REGION.trimmed.nt.nb, na.rm=T) +
- mean(X3D.REGION.trimmed.nt.nb, na.rm=T) +
- mean(X5J.REGION.trimmed.nt.nb, na.rm=T)),
+ VH.DEL=mean(.SD$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$X5J.REGION.trimmed.nt.nb, na.rm=T)),
- Total.N=( mean(N1.REGION.nt.nb, na.rm=T) +
- mean(N2.REGION.nt.nb, na.rm=T)),
+ Total.N=( mean(.SD$N1.REGION.nt.nb, na.rm=T) +
+ mean(.SD$N2.REGION.nt.nb, na.rm=T)),
- Total.P=( mean(P3V.nt.nb, na.rm=T) +
- mean(P5D.nt.nb, na.rm=T) +
- mean(P3D.nt.nb, na.rm=T) +
- mean(P5J.nt.nb, na.rm=T))),
+ Total.P=( mean(.SD$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")])
write.table(newData, "junctionAnalysisUnProd.csv" , sep=",",quote=F,na="-",row.names=F,col.names=F)
}