--- a/wrapper.sh	Thu Aug 11 10:35:52 2016 -0400
+++ b/wrapper.sh	Tue Aug 16 09:10:50 2016 -0400
@@ -45,14 +45,6 @@
 cat `find $PWD/files/ -name "8_*"` > $PWD/mutationstats.txt
 cat `find $PWD/files/ -name "10_*"` > $PWD/hotspots.txt
 
-#cat $PWD/files/*/1_* > $PWD/summary.txt
-#cat $PWD/files/*/3_* > $PWD/sequences.txt
-#cat $PWD/files/*/5_* > $PWD/aa.txt
-#cat $PWD/files/*/6_* > $PWD/junction.txt
-#cat $PWD/files/*/7_* > $PWD/mutationanalysis.txt
-#cat $PWD/files/*/8_* > $PWD/mutationstats.txt
-#cat $PWD/files/*/10_* > $PWD/hotspots.txt
-
 if [[ ${#BLASTN_DIR} -ge 5 ]] ; then
 	echo "On server, using BLASTN_DIR env: ${BLASTN_DIR}"
 else
@@ -66,25 +58,11 @@
 if [[ "${method}" == "custom" ]] ; then
 	python $dir/gene_identification.py --input $PWD/summary.txt --output $outdir/identified_genes.txt
 else
-	#ID_index=$(cat $PWD/summary.txt | grep -o -P ".+Sequence ID" | grep -o -P "\t" | wc -l)
-	#ID_index=$((ID_index+1))
-	#sequence_index=$(cat $PWD/summary.txt | grep -o -P ".+\tSequence" | grep -o -P "\t" | wc -l)
-	#sequence_index=$((sequence_index+1))
-	
-	#echo "${ID_index}, ${sequence_index}"
-	
-	#cat $PWD/summary.txt | tail -n+2 | cut -f ${ID_index},${sequence_index} | awk '{print ">" $1 "\n" $2}' > $PWD/sequences.tmp
-	#cat $PWD/summary.txt | tail -n+2 | awk -v id="${ID_index}" -v seq="${sequence_index}" 'BEGIN{FS="\t"} if(NF>10 && length($seq) > 0) {print ">" $id "\n" $seq} {}' > $PWD/sequences.fasta
-	
-	#cat $PWD/sequences.tmp | grep -B1 -vE ">.*|^$" | grep -v "^\-\-$" > sequences.fasta #filter out empty sequences
-	
 	echo "---------------- summary_to_fasta.py ----------------"
 	echo "---------------- summary_to_fasta.py ----------------<br />" >> $log
 	
 	python $dir/summary_to_fasta.py --input $PWD/summary.txt --fasta $PWD/sequences.fasta
 	
-	#rm $PWD/sequences.tmp
-	
 	echo -e "qseqid\tsseqid\tpident\tlength\tmismatch\tgapopen\tqstart\tqend\tsstart\tsend\tevalue\tbitscore" > $outdir/identified_genes.txt
 	${BLASTN_DIR}/blastn -task blastn -db $dir/subclass_definition.db -query $PWD/sequences.fasta -outfmt 6 >> $outdir/identified_genes.txt
 fi
@@ -397,10 +375,6 @@
 echo "<tr><td>Baseline cg data</td><td><a href='baseline_cg.txt'>Download</a></td></tr>" >> $output
 echo "<tr><td>Baseline cm PDF</td><td><a href='baseline_cm.pdf'>Download</a></td></tr>" >> $output
 echo "<tr><td>Baseline cm data</td><td><a href='baseline_cm.txt'>Download</a></td></tr>" >> $output
-#echo "<tr><td></td><td><a href='IgAT.zip'>IgAT zip</a></td></tr>" >> $output
-#echo "<tr><td></td><td><a href='IgAT_ca.zip'>IgAT ca zip</a></td></tr>" >> $output
-#echo "<tr><td></td><td><a href='IgAT_cg.zip'>IgAT cg zip</a></td></tr>" >> $output
-#echo "<tr><td></td><td><a href='IgAT_cm.zip'>IgAT cm zip</a></td></tr>" >> $output
 echo "<tr><td>An IMGT archive with just the matched and filtered sequences</td><td><a href='new_IMGT.txz'>Download</a></td></tr>" >> $output
 echo "<tr><td>An IMGT archive with just the matched and filtered ca sequences</td><td><a href='new_IMGT_ca.txz'>Download</a></td></tr>" >> $output
 echo "<tr><td>An IMGT archive with just the matched and filtered ca1 sequences</td><td><a href='new_IMGT_ca1.txz'>Download</a></td></tr>" >> $output
@@ -411,6 +385,8 @@
 echo "<tr><td>An IMGT archive with just the matched and filtered cg3 sequences</td><td><a href='new_IMGT_cg3.txz'>Download</a></td></tr>" >> $output
 echo "<tr><td>An IMGT archive with just the matched and filtered cg4 sequences</td><td><a href='new_IMGT_cg4.txz'>Download</a></td></tr>" >> $output
 echo "<tr><td>An IMGT archive with just the matched and filtered cm sequences</td><td><a href='new_IMGT_cm.txz'>Download</a></td></tr>" >> $output
+echo "<tr><td>The Change-O DB file with defined clones</td><td><a href='change_o/change-o-db-defined_clones.txt'>Download</a></td></tr>" >> $output
+echo "<tr><td>The Change-O DB defined clones summary file</td><td><a href='change_o/change-o-defined_clones-summary.txt'>Download</a></td></tr>" >> $output
 echo "</table>" >> $output
 
 echo "</div>" >> $output #downloads tab end
@@ -465,15 +441,6 @@
 
 if [[ "$naive_output" != "None" ]]
 then
-	#echo "---------------- imgt_loader.r ----------------"
-	#echo "---------------- imgt_loader.r ----------------<br />" >> $log
-	#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 $outdir/loader_output.txt 2>&1
-
-	#echo "---------------- naive_output.r ----------------"
-	#echo "---------------- naive_output.r ----------------<br />" >> $log
-	#Rscript $dir/naive_output.r $outdir/loader_output.txt $outdir/merged.txt ${naive_output_ca} ${naive_output_cg} ${naive_output_cm} $outdir/ntoverview.txt $outdir/ntsum.txt 2>&1
-	
 	cp $outdir/new_IMGT_ca.txz ${naive_output_ca}
 	cp $outdir/new_IMGT_cg.txz ${naive_output_cg}
 	cp $outdir/new_IMGT_cm.txz ${naive_output_cm}
@@ -481,6 +448,24 @@
 
 echo "</table>" >> $outdir/base_overview.html
 
+echo "---------------- change-o MakeDB ----------------"
+echo "---------------- change-o MakeDB ----------------<br />" >> $log
+
+mkdir $outdir/change_o
+
+tmp="$PWD"
+
+cd $outdir/change_o
+
+bash $dir/change_o/makedb.sh $input false false false $outdir/change_o/change-o-db.txt
+
+echo "---------------- change-o DefineClones ----------------"
+echo "---------------- change-o DefineClones ----------------<br />" >> $log
+
+bash $dir/change_o/define_clones.sh bygroup $outdir/change_o/change-o-db.txt gene first ham none min complete 3.0 $outdir/change_o/change-o-db-defined_clones.txt $outdir/change_o/change-o-defined_clones-summary.txt
+
+PWD="$tmp"
+
 mv $log $outdir/log.html
 
 echo "<html><center><h1><a href='index.html'>Click here for the results</a></h1>Tip: Open it in a new tab (middle mouse button or right mouse button -> 'open in new tab' on the link above)<br />" > $log