# HG changeset patch # User davidvanzessen # Date 1464265093 14400 # Node ID 07f7da724a77bd04d87b74ab68432b44c2fd4cf6 # Parent 041f94f50b34495f90ec08085af66fd8e8310906 Uploaded diff -r 041f94f50b34 -r 07f7da724a77 merge_and_filter.r diff -r 041f94f50b34 -r 07f7da724a77 mutation_analysis.py --- a/mutation_analysis.py Tue May 24 03:59:44 2016 -0400 +++ b/mutation_analysis.py Thu May 26 08:18:13 2016 -0400 @@ -49,8 +49,8 @@ fr2Index = linesplt.index("FR2.IMGT") cdr2Index = linesplt.index("CDR2.IMGT") fr3Index = linesplt.index("FR3.IMGT") - cdr1LengthIndex = linesplt.index("CDR1.IMGT.Nb.of.nucleotides") - cdr2LengthIndex = linesplt.index("CDR2.IMGT.Nb.of.nucleotides") + cdr1LengthIndex = linesplt.index("CDR1.IMGT.length") + cdr2LengthIndex = linesplt.index("CDR2.IMGT.length") first = False continue linecount += 1 @@ -73,9 +73,9 @@ cdr1Length = linesplt[cdr1LengthIndex] cdr2Length = linesplt[cdr2LengthIndex] - cdr1LengthDic[ID] = int(cdr1Length) / 3 - cdr2LengthDic[ID] = int(cdr2Length) / 3 - + cdr1LengthDic[ID] = int(cdr1Length) if cdr1Length != "X" else 0 + cdr2LengthDic[ID] = int(cdr2Length) if cdr2Length != "X" else 0 + IDlist += [ID] AALength = (int(max(mutationList, key=lambda i: int(i[4]) if i[4] else 0)[4]) + 1) # [4] is the position of the AA mutation, None if silent diff -r 041f94f50b34 -r 07f7da724a77 wrapper.sh --- a/wrapper.sh Tue May 24 03:59:44 2016 -0400 +++ b/wrapper.sh Thu May 26 08:18:13 2016 -0400 @@ -90,10 +90,6 @@ echo "R mutation analysis" Rscript $dir/mutation_analysis.r $outdir/merged.txt $classes $outdir ${include_fr1} 2>&1 -#echo "." > $output -#exit 0 - - echo "---------------- mutation_analysis.py ----------------" echo "---------------- mutation_analysis.py ----------------
" >> $output @@ -119,7 +115,7 @@ while read ID class seq A C G T do - echo "$ID$class$A$C$G$T" >> $outdir/base_overview.html + echo "$ID$seq$class$A$C$G$T" >> $outdir/base_overview.html done < $outdir/sequence_overview/ntoverview.txt