# HG changeset patch
# User davidvanzessen
# Date 1456825986 18000
# Node ID 0d5add1a9800f95d7d1a11aa5617dbf088fd1b2c
# Parent d8daf8ed39e1ecd5a2d25c46f28812e899d85a83
Uploaded
diff -r d8daf8ed39e1 -r 0d5add1a9800 wrapper.sh
--- a/wrapper.sh Mon Feb 29 10:55:11 2016 -0500
+++ b/wrapper.sh Tue Mar 01 04:53:06 2016 -0500
@@ -13,6 +13,10 @@
filter_unique=${10}
mkdir $outdir
+echo "---------------- read parameters ----------------"
+
+echo "unpacking IMGT file"
+
type="`file $input`"
if [[ "$type" == *"Zip archive"* ]] ; then
echo "Zip archive"
@@ -39,9 +43,13 @@
echo "identification ($method)"
+echo "blast or custom"
+
if [[ "${method}" == "custom" ]] ; then
+ echo "custom"
python $dir/gene_identification.py --input $PWD/summary.txt --output $outdir/identified_genes.txt
else
+ echo "blast"
ID_index=$(cat $PWD/summary.txt | grep -o -P ".+Sequence ID" | grep -o -P "\t" | wc -l)
ID_index=$((ID_index+1))
sequence_index=$(cat $PWD/summary.txt | grep -o -P ".+\tSequence" | grep -o -P "\t" | wc -l)
@@ -55,11 +63,12 @@
${BLASTN_DIR}/blastn -task blastn -db $dir/subclass_definition.db -query $PWD/sequences.fasta -outfmt 6 >> $outdir/identified_genes.txt
fi
-
+echo "---------------- merge_and_filter.r ----------------"
-echo "merging"
Rscript $dir/merge_and_filter.r $PWD/summary.txt $PWD/sequences.txt $PWD/mutationanalysis.txt $PWD/mutationstats.txt $PWD/hotspots.txt $outdir/identified_genes.txt $outdir/merged.txt $outdir/unmatched.txt $method $functionality $unique ${filter_unique}
+echo "---------------- mutation_analysis.r ----------------"
+
genes="ca,ca1,ca2,cg,cg1,cg2,cg3,cg4,cm"
echo "R mutation analysis"
Rscript $dir/mutation_analysis.r $outdir/merged.txt $genes $outdir ${include_fr1} 2>&1
@@ -67,9 +76,15 @@
#echo "." > $output
#exit 0
-echo "python mutation analysis"
+
+
+echo "---------------- mutation_analysis.py ----------------"
+
python $dir/mutation_analysis.py --input $outdir/merged.txt --genes $genes --includefr1 "${include_fr1}" --output $outdir/hotspot_analysis.txt
echo "R AA histogram"
+
+echo "---------------- aa_histogram.r ----------------"
+
Rscript $dir/aa_histogram.r $outdir/aa_mutations.txt $outdir/aa_histogram.png 2>&1
genes=(ca ca1 ca2 cg cg1 cg2 cg3 cg4 cm)
@@ -78,9 +93,12 @@
echo "$title
" >> $output
-
+echo "---------------- main tables ----------------"
for func in ${funcs[@]}
do
+
+ echo "---------------- $func table ----------------"
+
cat $outdir/mutations_${func}.txt $outdir/hotspot_analysis_${func}.txt > $outdir/result.txt
echo "${func} table
" >> $output
@@ -104,6 +122,8 @@
done
+echo "---------------- download links ----------------"
+
echo "
" >> $output
echo "unmatched
" >> $output
echo "motif per sequence
" >> $output
@@ -112,6 +132,8 @@
echo "AA mutations location by id
" >> $output
echo "Absant AA locations by id
" >> $output
+echo "---------------- images ----------------"
+
echo "
" >> $output
echo "download data
" >> $output
if [ -a $outdir/ca.png ]
@@ -163,11 +185,14 @@
#optional output for naive
+echo "---------------- aa_histogram.r ----------------"
+
if [[ "$naive_output" != "None" ]]
then
- echo "naive_output: $naive_output"
+ echo "---------------- imgt_loader.r ----------------"
#python $dir/imgt_loader.py --summ $PWD/summary.txt --aa $PWD/aa.txt --junction $PWD/junction.txt --output $naive_output
Rscript --verbose $dir/imgt_loader.r $PWD/summary.txt $PWD/aa.txt $PWD/junction.txt ${naive_output} 2>&1
+ echo "---------------- naive_output.r ----------------"
Rscript $dir/naive_output.r $naive_output $outdir/merged.txt $naive_output 2>&1
fi