# HG changeset patch # User davidvanzessen # Date 1471433432 14400 # Node ID 31cca6d3722a56e5e45da0d79bfd0deea0c0b182 # Parent 613278c1bde0a1d2a95a0b42061e6188a90dee6b Uploaded diff -r 613278c1bde0 -r 31cca6d3722a mutation_analysis.xml --- a/mutation_analysis.xml Tue Aug 16 09:10:50 2016 -0400 +++ b/mutation_analysis.xml Wed Aug 17 07:30:32 2016 -0400 @@ -61,6 +61,11 @@ naive_output_cond['naive_output'] == "yes" + + 10.1093/nar/gks457 + 10.1093/bioinformatics/btv359 + 10.1186/1471-2105-10-421 + Takes an IMGT zip (http://www.imgt.org/HighV-QUEST/search.action) file and creates a summarization of the mutation analysis. diff -r 613278c1bde0 -r 31cca6d3722a wrapper.sh --- a/wrapper.sh Tue Aug 16 09:10:50 2016 -0400 +++ b/wrapper.sh Wed Aug 17 07:30:32 2016 -0400 @@ -195,7 +195,6 @@ mkdir $outdir/sequence_overview -#Rscript $dir/sequence_overview.r $outdir/identified_genes.txt $PWD/sequences.txt $outdir/merged.txt $outdir/sequence_overview $classes $outdir/hotspot_analysis_sum.txt 2>&1 Rscript $dir/sequence_overview.r $outdir/before_unique_filter.txt $outdir/merged.txt $outdir/sequence_overview $classes $outdir/hotspot_analysis_sum.txt 2>&1 echo "" > $outdir/base_overview.html @@ -206,12 +205,12 @@ done < $outdir/sequence_overview/ntoverview.txt echo "

$title

" > $output +echo "" >> $output echo "" >> $output echo "" >> $output echo "" >> $output echo "" >> $output - -#display the matched/unmatched for clearity +echo "" >> $output matched_count="`cat $outdir/merged.txt | grep -v 'unmatched' | tail -n +2 | wc -l`" unmatched_count="`cat $outdir/unmatched.txt | tail -n +2 | wc -l`" @@ -238,8 +237,8 @@ cat $outdir/mutations_${func}.txt $outdir/hotspot_analysis_${func}.txt > $outdir/data_${func}.txt - echo "
" >> $output - echo "" >> $output + echo "

${func} table

info
" >> $output + echo "" >> $output for gene in ${genes[@]} do tmp=`cat $outdir/${gene}_${func}_n.txt` @@ -249,7 +248,7 @@ tmp=`cat $outdir/all_${func}_n.txt` echo "" >> $output tmp=`cat $outdir/unmatched_${func}_n.txt` - echo "" >> $output + echo "" >> $output while IFS=, read name cax cay caz ca1x ca1y ca1z ca2x ca2y ca2z cgx cgy cgz cg1x cg1y cg1z cg2x cg2y cg2z cg3x cg3y cg3z cg4x cg4y cg4z cmx cmy cmz unx uny unz allx ally allz do @@ -294,7 +293,7 @@ echo "" >> $output echo "" >> $output echo "" >> $output - echo "
infoall (N = $tmp)unmatched (N = ${unmatched_count})unmatched (N = ${unmatched_count})

${gene}

" >> $output + echo "
" >> $output while IFS=, read from a c g t do echo "" >> $output @@ -308,7 +307,7 @@ echo "" >> $output echo "" >> $output echo "" >> $output -echo "
$from$a$c$g$t

All

" >> $output +echo "
" >> $output while IFS=, read from a c g t do echo "" >> $output @@ -358,7 +357,8 @@ echo "
" >> $output -echo "
$from$a$c$g$t
" >> $output +echo "
" >> $output +echo "" >> $output echo "" >> $output echo "" >> $output echo "" >> $output @@ -367,7 +367,7 @@ echo "" >> $output echo "" >> $output echo "" >> $output -echo "" >> $output +echo "" >> $output echo "" >> $output echo "" >> $output echo "" >> $output
infolink
The complete datasetDownload
The alignment info on the unmatched sequencesDownload
Motif data per sequence IDDownload
Absent AA location data per sequence IDDownload
CDR1+FR2+CDR2+FR3+CDR3 sequences that show up more than onceDownload
Base count for every sequenceDownload
Baseline PDF (http://selection.med.yale.edu/baseline/)Download
Baseline PDF (http://selection.med.yale.edu/baseline/)Download
Baseline dataDownload
Baseline ca PDFDownload
Baseline ca dataDownload