Mercurial > repos > davidvanzessen > mutation_analysis

view wrapper.sh @ 0:8a5a2abbb870 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Mon, 29 Aug 2016 05:36:10 -0400
parents
children
line wrap: on
line source

#!/bin/bash
#set -e
dir="$(cd "$(dirname "$0")" && pwd)"
input=$1
method=$2
log=$3 #becomes the main html page at the end
outdir=$4
output="$outdir/index.html" #copied to $log location at the end
title=$5
include_fr1=$6
functionality=$7
unique=$8
naive_output_ca=$9
naive_output_cg=${10}
naive_output_cm=${11}
filter_unique=${12}
class_filter=${13}
empty_region_filter=${14}
mkdir $outdir

tar -xzf $dir/style.tar.gz -C $outdir

echo "---------------- read parameters ----------------"
echo "---------------- read parameters ----------------<br />" > $log

echo "unpacking IMGT file"

type="`file $input`"
if [[ "$type" == *"Zip archive"* ]] ; then
	echo "Zip archive"
	echo "unzip $input -d $PWD/files/"
	unzip $input -d $PWD/files/
elif [[ "$type" == *"XZ compressed data"* ]] ; then
	echo "ZX archive"
	echo "tar -xJf $input -C $PWD/files/"
	mkdir -p $PWD/files/$title
	tar -xJf $input -C $PWD/files/$title
fi

cat `find $PWD/files/ -name "1_*"` > $PWD/summary.txt
cat `find $PWD/files/ -name "3_*"` > $PWD/sequences.txt
cat `find $PWD/files/ -name "5_*"` > $PWD/aa.txt
cat `find $PWD/files/ -name "6_*"` > $PWD/junction.txt
cat `find $PWD/files/ -name "7_*"` > $PWD/mutationanalysis.txt
cat `find $PWD/files/ -name "8_*"` > $PWD/mutationstats.txt
cat `find $PWD/files/ -name "10_*"` > $PWD/hotspots.txt

if [[ ${#BLASTN_DIR} -ge 5 ]] ; then
	echo "On server, using BLASTN_DIR env: ${BLASTN_DIR}"
else
	BLASTN_DIR="/home/galaxy/Downloads/ncbi-blast-2.4.0+/bin"
	echo "Dev Galaxy set BLASTN_DIR to: ${BLASTN_DIR}"
fi

echo "---------------- identification ($method) ----------------"
echo "---------------- identification ($method) ----------------<br />" >> $log

if [[ "${method}" == "custom" ]] ; then
	python $dir/gene_identification.py --input $PWD/summary.txt --output $outdir/identified_genes.txt
else
	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
	
	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

echo "---------------- merge_and_filter.r ----------------"
echo "---------------- merge_and_filter.r ----------------<br />" >> $log

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/before_unique_filter.txt $outdir/unmatched.txt $method $functionality $unique ${filter_unique} ${class_filter} ${empty_region_filter} 2>&1

echo "---------------- creating new IMGT zip ----------------"
echo "---------------- creating new IMGT zip ----------------<br />" >> $log

mkdir $outdir/new_IMGT

cat `find $PWD/files/ -name "1_*"` > "$outdir/new_IMGT/1_Summary.txt"
cat `find $PWD/files/ -name "2_*"` > "$outdir/new_IMGT/2_IMGT-gapped-nt-sequences.txt"
cat `find $PWD/files/ -name "3_*"` > "$outdir/new_IMGT/3_Nt-sequences.txt"
cat `find $PWD/files/ -name "4_*"` > "$outdir/new_IMGT/4_IMGT-gapped-AA-sequences.txt"
cat `find $PWD/files/ -name "5_*"` > "$outdir/new_IMGT/5_AA-sequences.txt"
cat `find $PWD/files/ -name "6_*"` > "$outdir/new_IMGT/6_Junction.txt"
cat `find $PWD/files/ -name "7_*"` > "$outdir/new_IMGT/7_V-REGION-mutation-and-AA-change-table.txt"
cat `find $PWD/files/ -name "8_*"` > "$outdir/new_IMGT/8_V-REGION-nt-mutation-statistics.txt"
cat `find $PWD/files/ -name "9_*"` > "$outdir/new_IMGT/9_V-REGION-AA-change-statistics.txt"
cat `find $PWD/files/ -name "10_*"` > "$outdir/new_IMGT/10_V-REGION-mutation-hotspots.txt"

mkdir $outdir/new_IMGT_ca
cp $outdir/new_IMGT/* $outdir/new_IMGT_ca

mkdir $outdir/new_IMGT_ca1
cp $outdir/new_IMGT/* $outdir/new_IMGT_ca1

mkdir $outdir/new_IMGT_ca2
cp $outdir/new_IMGT/* $outdir/new_IMGT_ca2

mkdir $outdir/new_IMGT_cg
cp $outdir/new_IMGT/* $outdir/new_IMGT_cg

mkdir $outdir/new_IMGT_cg1
cp $outdir/new_IMGT/* $outdir/new_IMGT_cg1

mkdir $outdir/new_IMGT_cg2
cp $outdir/new_IMGT/* $outdir/new_IMGT_cg2

mkdir $outdir/new_IMGT_cg3
cp $outdir/new_IMGT/* $outdir/new_IMGT_cg3

mkdir $outdir/new_IMGT_cg4
cp $outdir/new_IMGT/* $outdir/new_IMGT_cg4

mkdir $outdir/new_IMGT_cm
cp $outdir/new_IMGT/* $outdir/new_IMGT_cm

Rscript $dir/new_imgt.r $outdir/new_IMGT/ $outdir/merged.txt "-" 2>&1

Rscript $dir/new_imgt.r $outdir/new_IMGT_ca/ $outdir/merged.txt "ca" 2>&1
Rscript $dir/new_imgt.r $outdir/new_IMGT_ca1/ $outdir/merged.txt "ca1" 2>&1
Rscript $dir/new_imgt.r $outdir/new_IMGT_ca2/ $outdir/merged.txt "ca2" 2>&1

Rscript $dir/new_imgt.r $outdir/new_IMGT_cg/ $outdir/merged.txt "cg" 2>&1
Rscript $dir/new_imgt.r $outdir/new_IMGT_cg1/ $outdir/merged.txt "cg1" 2>&1
Rscript $dir/new_imgt.r $outdir/new_IMGT_cg2/ $outdir/merged.txt "cg2" 2>&1
Rscript $dir/new_imgt.r $outdir/new_IMGT_cg3/ $outdir/merged.txt "cg3" 2>&1
Rscript $dir/new_imgt.r $outdir/new_IMGT_cg4/ $outdir/merged.txt "cg4" 2>&1

Rscript $dir/new_imgt.r $outdir/new_IMGT_cm/ $outdir/merged.txt "cm" 2>&1


tmp="$PWD"
cd $outdir/new_IMGT/ #tar weirdness...
tar -cJf ../new_IMGT.txz *

cd $outdir/new_IMGT_ca/
tar -cJf ../new_IMGT_ca.txz *

cd $outdir/new_IMGT_ca1/
tar -cJf ../new_IMGT_ca1.txz *

cd $outdir/new_IMGT_ca2/
tar -cJf ../new_IMGT_ca2.txz *

cd $outdir/new_IMGT_cg/
tar -cJf ../new_IMGT_cg.txz *

cd $outdir/new_IMGT_cg1/
tar -cJf ../new_IMGT_cg1.txz *

cd $outdir/new_IMGT_cg2/
tar -cJf ../new_IMGT_cg2.txz *

cd $outdir/new_IMGT_cg3/
tar -cJf ../new_IMGT_cg3.txz *

cd $outdir/new_IMGT_cg4/
tar -cJf ../new_IMGT_cg4.txz *

cd $outdir/new_IMGT_cm/
tar -cJf ../new_IMGT_cm.txz *

cd $tmp

echo "---------------- mutation_analysis.r ----------------"
echo "---------------- mutation_analysis.r ----------------<br />" >> $log

classes="ca,ca1,ca2,cg,cg1,cg2,cg3,cg4,cm,unmatched"
echo "R mutation analysis"
Rscript $dir/mutation_analysis.r $outdir/merged.txt $classes $outdir ${include_fr1} 2>&1


echo "---------------- mutation_analysis.py ----------------"
echo "---------------- mutation_analysis.py ----------------<br />" >> $log

python $dir/mutation_analysis.py --input $outdir/merged.txt --genes $classes --includefr1 "${include_fr1}" --output $outdir/hotspot_analysis.txt

echo "---------------- aa_histogram.r ----------------"
echo "---------------- aa_histogram.r ----------------<br />" >> $log

Rscript $dir/aa_histogram.r $outdir/aa_id_mutations.txt $outdir/absent_aa_id.txt "ca,cg,cm" $outdir/ 2>&1
if [ -e "$outdir/aa_histogram_.png" ]; then
        mv $outdir/aa_histogram_.png $outdir/aa_histogram.png
        mv $outdir/aa_histogram_.txt $outdir/aa_histogram.txt
fi

genes=(ca ca1 ca2 cg cg1 cg2 cg3 cg4 cm)

funcs=(sum mean median)
funcs=(sum)

echo "---------------- sequence_overview.r ----------------"
echo "---------------- sequence_overview.r ----------------<br />" >> $log

mkdir $outdir/sequence_overview

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 "<table border='1'>" > $outdir/base_overview.html

while IFS=$'\t' read ID class seq A C G T
do
	echo "<tr><td>$ID</td><td>$seq</td><td>$class</td><td>$A</td><td>$C</td><td>$G</td><td>$T</td></tr>" >> $outdir/base_overview.html
done < $outdir/sequence_overview/ntoverview.txt

echo "<html><center><h1>$title</h1></center>" > $output
echo "<meta name='viewport' content='width=device-width, initial-scale=1'>" >> $output
echo "<script type='text/javascript' src='jquery-1.11.0.min.js'></script>" >> $output
echo "<script type='text/javascript' src='tabber.js'></script>" >> $output
echo "<script type='text/javascript' src='script.js'></script>" >> $output
echo "<link rel='stylesheet' type='text/css' href='style.css'>" >> $output
echo "<link rel='stylesheet' type='text/css' href='pure-min.css'>" >> $output

matched_count="`cat $outdir/merged.txt | grep -v 'unmatched' | tail -n +2 | wc -l`"
unmatched_count="`cat $outdir/unmatched.txt | tail -n +2 | wc -l`"
total_count=$((matched_count + unmatched_count))
perc_count=$((unmatched_count / total_count * 100))
perc_count=`bc -l <<< "scale=2; ${unmatched_count} / ${total_count} * 100"`
perc_count=`bc -l <<< "scale=2; (${unmatched_count} / ${total_count} * 100 ) / 1"`

echo "<center><h2>Total: ${total_count}</h2></center>" >> $output
echo "<center><h2>Matched: ${matched_count} Unmatched: ${unmatched_count}</h2></center>" >> $output
echo "<center><h2>Percentage unmatched: ${perc_count}</h2></center>" >> $output

echo "---------------- main tables ----------------"
echo "---------------- main tables ----------------<br />" >> $log

echo "<div class='tabber'>" >> $output
echo "<div class='tabbertab' title='SHM Overview'>" >> $output

for func in ${funcs[@]}
do

	echo "---------------- $func table ----------------"
	echo "---------------- $func table ----------------<br />" >> $log
	
	cat $outdir/mutations_${func}.txt $outdir/hotspot_analysis_${func}.txt > $outdir/data_${func}.txt
	
	echo "---------------- pattern_plots.r ----------------"
	echo "---------------- pattern_plots.r ----------------<br />" >> $log

	Rscript $dir/pattern_plots.r $outdir/data_${func}.txt $outdir/plot1 $outdir/plot2 $outdir/plot3 2>&1
	
	echo "<table class='pure-table pure-table-striped'>" >> $output
	echo "<thead><tr><th>info</th>" >> $output
	for gene in ${genes[@]}
	do
		tmp=`cat $outdir/${gene}_${func}_n.txt`
		echo "<th><a href='matched_${gene}_${func}.txt'>${gene} (N = $tmp)</a></th>" >> $output
	done
	
	tmp=`cat $outdir/all_${func}_n.txt`
	echo "<th><a href='matched_all_${func}.txt'>all (N = $tmp)</a></th>" >> $output
	tmp=`cat $outdir/unmatched_${func}_n.txt`
	echo "<th><a href='unmatched.txt'>unmatched (N = ${unmatched_count})</a></th><tr></thead>" >> $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
		if [ "$name" == "FR S/R (ratio)" ] || [ "$name" == "CDR S/R (ratio)" ] ; then #meh
			echo "<tr><td>$name</td><td>${cax}/${cay} (${caz})</td><td>${ca1x}/${ca1y} (${ca1z})</td><td>${ca2x}/${ca2y} (${ca2z})</td><td>${cgx}/${cgy} (${cgz})</td><td>${cg1x}/${cg1y} (${cg1z})</td><td>${cg2x}/${cg2y} (${cg2z})</td><td>${cg3x}/${cg3y} (${cg3z})</td><td>${cg4x}/${cg4y} (${cg4z})</td><td>${cmx}/${cmy} (${cmz})</td><td>${allx}/${ally} (${allz})</td></tr>" >> $output
		else
			echo "<tr><td>$name</td><td>${cax}/${cay} (${caz}%)</td><td>${ca1x}/${ca1y} (${ca1z}%)</td><td>${ca2x}/${ca2y} (${ca2z}%)</td><td>${cgx}/${cgy} (${cgz}%)</td><td>${cg1x}/${cg1y} (${cg1z}%)</td><td>${cg2x}/${cg2y} (${cg2z}%)</td><td>${cg3x}/${cg3y} (${cg3z}%)</td><td>${cg4x}/${cg4y} (${cg4z}%)</td><td>${cmx}/${cmy} (${cmz}%)</td><td>${allx}/${ally} (${allz}%)</td><td>${unx}/${uny} (${unz}%)</td></tr>" >> $output
		fi
	done < $outdir/data_${func}.txt
	echo "</table>" >> $output
	#echo "<a href='data_${func}.txt'>Download data</a>" >> $output
done

echo "<img src='plot1.png' /><br />" >> $output
echo "<img src='plot2.png' /><br />" >> $output
echo "<img src='plot3.png' /><br />" >> $output

echo "</div>" >> $output #SHM overview tab end

echo "---------------- images ----------------"
echo "---------------- images ----------------<br />" >> $log

echo "<div class='tabbertab' title='SHM Frequency'>" >> $output

if [ -a $outdir/scatter.png ]
then
	echo "<img src='scatter.png'/><br />" >> $output
	echo "<a href='scatter.txt'>download data</a><br />" >> $output
fi
if [ -a $outdir/frequency_ranges.png ]
then
	echo "<img src='frequency_ranges.png'/><br />" >> $output
	echo "<a href='frequency_ranges_classes.txt'>download class data</a><br />" >> $output
	echo "<a href='frequency_ranges_subclasses.txt'>download subclass data</a><br />" >> $output
fi

echo "</div>" >> $output #SHM frequency tab end

echo "<div class='tabbertab' title='Transition tables'>" >> $output

echo "<table border='0'>" >> $output

for gene in ${genes[@]}
do
	echo "<tr>" >> $output
	echo "<td><h1>${gene}</h1></td>" >> $output
	echo "<td><img src='transitions_heatmap_${gene}.png' /></td>" >> $output
	echo "<td><img src='transitions_stacked_${gene}.png' /></td>" >> $output
	echo "<td><table class='pure-table transition-table pure-table-bordered'>" >> $output
	while IFS=, read from a c g t
		do
			echo "<tr><td>$from</td><td>$a</td><td>$c</td><td>$g</td><td>$t</td></tr>" >> $output
	done < $outdir/transitions_${gene}_sum.txt
	echo "</table></td>" >> $output
	
	echo "</tr>" >> $output
done

echo "<tr>" >> $output
echo "<td><h1>All</h1></td>" >> $output
echo "<td><img src='transitions_heatmap_all.png' /></td>" >> $output
echo "<td><img src='transitions_stacked_all.png' /></td>" >> $output
echo "<td><table class='pure-table transition-table pure-table-bordered'>" >> $output
while IFS=, read from a c g t
	do
		echo "<tr><td>$from</td><td>$a</td><td>$c</td><td>$g</td><td>$t</td></tr>" >> $output
done < $outdir/transitions_all_sum.txt
echo "</table></td>" >> $output

echo "</tr>" >> $output

echo "</table>" >> $output

echo "</div>" >> $output #transition tables tab end

echo "<div class='tabbertab' title='Antigen Selection'>" >> $output

if [ -a $outdir/aa_histogram.png ]
then
	echo "<img src='aa_histogram.png'/><br />" >> $output
	echo "<a href='aa_histogram.txt'>download data</a><br />" >> $output
	echo "<img src='aa_histogram_ca.png'/><br />" >> $output
	echo "<a href='aa_histogram_ca.txt'>download data</a><br />" >> $output
	echo "<img src='aa_histogram_cg.png'/><br />" >> $output
	echo "<a href='aa_histogram_cg.txt'>download data</a><br />" >> $output
	echo "<img src='aa_histogram_cm.png'/><br />" >> $output
	echo "<a href='aa_histogram_cm.txt'>download data</a><br />" >> $output
fi

echo "<embed src='baseline_ca.pdf' width='700px' height='1000px'>" >> $output
echo "<embed src='baseline_cg.pdf' width='700px' height='1000px'>" >> $output
echo "<embed src='baseline_cm.pdf' width='700px' height='1000px'>" >> $output

echo "</div>" >> $output #antigen selection tab end

echo "<div class='tabbertab' title='CSR'>" >> $output #CSR tab

if [ -a $outdir/ca.png ] 
then
	echo "<img src='ca.png'/><br />" >> $output
	echo "<a href='ca.txt'>download data</a><br />" >> $output
fi
if [ -a $outdir/cg.png ]
then
	echo "<img src='cg.png'/><br />" >> $output
	echo "<a href='cg.txt'>download data</a><br />" >> $output
fi

echo "</div>" >> $output #CSR tab end

echo "---------------- change-o MakeDB ----------------"

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
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

Rscript $dir/merge.r $outdir/change_o/change-o-db-defined_clones.txt $outdir/merged.txt "all" "Sequence.ID,best_match" "SEQUENCE_ID" "Sequence.ID" $outdir/change_o/change-o-db-defined_clones.txt 2>&1

echo "Rscript $dir/merge.r $outdir/change_o/change-o-db-defined_clones.txt $outdir/$outdir/merged.txt 'all' 'Sequence.ID,best_match' 'Sequence.ID' 'Sequence.ID' '\t' $outdir/change_o/change-o-db-defined_clones.txt 2>&1"

if [[ $(wc -l < $outdir/new_IMGT_ca/1_Summary.txt) -gt "1" ]]; then
	bash $dir/change_o/makedb.sh $outdir/new_IMGT_ca.txz false false false $outdir/change_o/change-o-db-ca.txt
	bash $dir/change_o/define_clones.sh bygroup $outdir/change_o/change-o-db-ca.txt gene first ham none min complete 3.0 $outdir/change_o/change-o-db-defined_clones-ca.txt $outdir/change_o/change-o-defined_clones-summary-ca.txt
else
	echo "No ca sequences" > "$outdir/change_o/change-o-db-defined_clones-ca.txt"	
	echo "No ca sequences" > "$outdir/change_o/change-o-defined_clones-summary-ca.txt"	
fi

if [[ $(wc -l < $outdir/new_IMGT_cg/1_Summary.txt) -gt "1" ]]; then
	bash $dir/change_o/makedb.sh $outdir/new_IMGT_cg.txz false false false $outdir/change_o/change-o-db-cg.txt
	bash $dir/change_o/define_clones.sh bygroup $outdir/change_o/change-o-db-cg.txt gene first ham none min complete 3.0 $outdir/change_o/change-o-db-defined_clones-cg.txt $outdir/change_o/change-o-defined_clones-summary-cg.txt
else
	echo "No cg sequences" > "$outdir/change_o/change-o-db-defined_clones-cg.txt"	
	echo "No cg sequences" > "$outdir/change_o/change-o-defined_clones-summary-cg.txt"	
fi

if [[ $(wc -l < $outdir/new_IMGT_cm/1_Summary.txt) -gt "1" ]]; then
	bash $dir/change_o/makedb.sh $outdir/new_IMGT_cm.txz false false false $outdir/change_o/change-o-db-cm.txt
	bash $dir/change_o/define_clones.sh bygroup $outdir/change_o/change-o-db-cm.txt gene first ham none min complete 3.0 $outdir/change_o/change-o-db-defined_clones-cm.txt $outdir/change_o/change-o-defined_clones-summary-cm.txt
else
	echo "No cm sequences" > "$outdir/change_o/change-o-db-defined_clones-cm.txt"	
	echo "No cm sequences" > "$outdir/change_o/change-o-defined_clones-summary-cm.txt"	
fi

PWD="$tmp"

echo "<div class='tabbertab' title='Clonality'>" >> $output #clonality tab

function clonality_table {
	local infile=$1
	local outfile=$2
	
	echo "<table class='pure-table pure-table-striped'>" >> $outfile
	echo "<thead><tr><th>Clone size</th><th>Nr of clones</th><th>Nr of sequences</th></tr></thead>" >> $outfile
	
	first='true'
	
	while read size clones seqs
	do
		if [[ "$first" == "true" ]]; then
			first="false"
			continue
		fi
		echo "<tr><td>$size</td><td>$clones</td><td>$seqs</td></tr>" >> $outfile
	done < $infile
	
	echo "</table>" >> $outfile
}
echo "<div class='tabber'>" >> $output

echo "<div class='tabbertab' title='All'>" >> $output
clonality_table $outdir/change_o/change-o-defined_clones-summary.txt $output
echo "</div>" >> $output

echo "<div class='tabbertab' title='Ca'>" >> $output
clonality_table $outdir/change_o/change-o-defined_clones-summary-ca.txt $output
echo "</div>" >> $output

echo "<div class='tabbertab' title='Cg'>" >> $output
clonality_table $outdir/change_o/change-o-defined_clones-summary-cg.txt $output
echo "</div>" >> $output

echo "<div class='tabbertab' title='Cm'>" >> $output
clonality_table $outdir/change_o/change-o-defined_clones-summary-cm.txt $output
echo "</div>" >> $output

echo "</div>" >> $output #clonality tabber end

echo "</div>" >> $output #clonality tab end

echo "<div class='tabbertab' title='Downloads'>" >> $output

echo "<table class='pure-table pure-table-striped'>" >> $output
echo "<thead><tr><th>info</th><th>link</th></tr></thead>" >> $output
echo "<tr><td>The complete dataset</td><td><a href='merged.txt'>Download</a></td></tr>" >> $output
echo "<tr><td>The SHM Overview table as a dataset</td><td><a href='data_sum.txt'>Download</a></td></tr>" >> $output
echo "<tr><td>The data used to generate the first SHM Overview plot</td><td><a href='plot1.txt'>Download</a></td></tr>" >> $output
echo "<tr><td>The data used to generate the sexond SHM Overview plot</td><td><a href='plot2.txt'>Download</a></td></tr>" >> $output
echo "<tr><td>The data used to generate the third SHM Overview plot</td><td><a href='plot3.txt'>Download</a></td></tr>" >> $output
echo "<tr><td>The alignment info on the unmatched sequences</td><td><a href='unmatched.txt'>Download</a></td></tr>" >> $output

echo "<tr><td>Motif data per sequence ID</td><td><a href='motif_per_seq.txt'>Download</a></td></tr>" >> $output
echo "<tr><td>Mutation data per sequence ID</td><td><a href='mutation_by_id.txt'>Download</a></td></tr>" >> $output
echo "<tr><td>AA mutation data per sequence ID</td><td><a href='aa_id_mutations.txt'>Download</a></td></tr>" >> $output
echo "<tr><td>Absent AA location data per sequence ID</td><td><a href='absent_aa_id.txt'>Download</a></td></tr>" >> $output
echo "<tr><td>CDR1+FR2+CDR2+FR3+CDR3 sequences that show up more than once</td><td><a href='sequence_overview/index.html'>Download</a></td></tr>" >> $output

echo "<tr><td>Base count for every sequence</td><td><a href='base_overview.html'>Download</a></td></tr>" >> $output

echo "<tr><td>Baseline PDF (<a href='http://selection.med.yale.edu/baseline/'>http://selection.med.yale.edu/baseline/</a>)</td><td><a href='baseline.pdf'>Download</a></td></tr>" >> $output
echo "<tr><td>Baseline data</td><td><a href='baseline.txt'>Download</a></td></tr>" >> $output
echo "<tr><td>Baseline ca PDF</td><td><a href='baseline_ca.pdf'>Download</a></td></tr>" >> $output
echo "<tr><td>Baseline ca data</td><td><a href='baseline_ca.txt'>Download</a></td></tr>" >> $output
echo "<tr><td>Baseline cg PDF</td><td><a href='baseline_cg.pdf'>Download</a></td></tr>" >> $output
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>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
echo "<tr><td>An IMGT archive with just the matched and filtered ca2 sequences</td><td><a href='new_IMGT_ca2.txz'>Download</a></td></tr>" >> $output
echo "<tr><td>An IMGT archive with just the matched and filtered cg sequences</td><td><a href='new_IMGT_cg.txz'>Download</a></td></tr>" >> $output
echo "<tr><td>An IMGT archive with just the matched and filtered cg1 sequences</td><td><a href='new_IMGT_cg1.txz'>Download</a></td></tr>" >> $output
echo "<tr><td>An IMGT archive with just the matched and filtered cg2 sequences</td><td><a href='new_IMGT_cg2.txz'>Download</a></td></tr>" >> $output
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 and subclass annotation</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 "<tr><td>The Change-O DB file with defined clones of ca</td><td><a href='change_o/change-o-db-defined_clones-ca.txt'>Download</a></td></tr>" >> $output
echo "<tr><td>The Change-O DB defined clones summary file of ca</td><td><a href='change_o/change-o-defined_clones-summary-ca.txt'>Download</a></td></tr>" >> $output
echo "<tr><td>The Change-O DB file with defined clones of cg</td><td><a href='change_o/change-o-db-defined_clones-cg.txt'>Download</a></td></tr>" >> $output
echo "<tr><td>The Change-O DB defined clones summary file of cg</td><td><a href='change_o/change-o-defined_clones-summary-cg.txt'>Download</a></td></tr>" >> $output
echo "<tr><td>The Change-O DB file with defined clones of cm</td><td><a href='change_o/change-o-db-defined_clones-cm.txt'>Download</a></td></tr>" >> $output
echo "<tr><td>The Change-O DB defined clones summary file of cm</td><td><a href='change_o/change-o-defined_clones-summary-cm.txt'>Download</a></td></tr>" >> $output

echo "</table>" >> $output

echo "</div>" >> $output #downloads tab end

echo "</div>" >> $output #tabs end 

echo "</html>" >> $output

echo "---------------- baseline ----------------"
echo "---------------- baseline ----------------<br />" >> $log
tmp="$PWD"

mkdir $outdir/baseline


mkdir $outdir/baseline/ca_cg_cm
if [[ $(wc -l < $outdir/new_IMGT/1_Summary.txt) -gt "1" ]]; then
	cd $outdir/baseline/ca_cg_cm
	bash $dir/baseline/wrapper.sh 1 1 1 1 0 0 "25:26:38:55:65:104:-" $outdir/new_IMGT.txz "ca_cg_cm" "$dir/baseline/IMGT-reference-seqs-IGHV-2015-11-05.fa" "$outdir/baseline.pdf" "Sequence.ID" "$outdir/baseline.txt"	
else
	echo "No sequences" > "$outdir/baseline.txt"	
fi

mkdir $outdir/baseline/ca
if [[ $(wc -l < $outdir/new_IMGT_ca/1_Summary.txt) -gt "1" ]]; then
	cd $outdir/baseline/ca
	bash $dir/baseline/wrapper.sh 1 1 1 1 0 0 "25:26:38:55:65:104:-" $outdir/new_IMGT_ca.txz "ca" "$dir/baseline/IMGT-reference-seqs-IGHV-2015-11-05.fa" "$outdir/baseline_ca.pdf" "Sequence.ID" "$outdir/baseline_ca.txt"
else
	echo "No ca sequences" > "$outdir/baseline_ca.txt"	
fi

mkdir $outdir/baseline/cg
if [[ $(wc -l < $outdir/new_IMGT_cg/1_Summary.txt) -gt "1" ]]; then
	cd $outdir/baseline/cg
	bash $dir/baseline/wrapper.sh 1 1 1 1 0 0 "25:26:38:55:65:104:-" $outdir/new_IMGT_cg.txz "cg" "$dir/baseline/IMGT-reference-seqs-IGHV-2015-11-05.fa" "$outdir/baseline_cg.pdf" "Sequence.ID" "$outdir/baseline_cg.txt"
else
	echo "No cg sequences" > "$outdir/baseline_cg.txt"	
fi

mkdir $outdir/baseline/cm
if [[ $(wc -l < $outdir/new_IMGT_cm/1_Summary.txt) -gt "1" ]]; then
	cd $outdir/baseline/cm
	bash $dir/baseline/wrapper.sh 1 1 1 1 0 0 "25:26:38:55:65:104:-" $outdir/new_IMGT_cm.txz "cm" "$dir/baseline/IMGT-reference-seqs-IGHV-2015-11-05.fa" "$outdir/baseline_cm.pdf" "Sequence.ID" "$outdir/baseline_cm.txt"
else
	echo "No cm sequences" > "$outdir/baseline_cm.txt"	
fi

cd $tmp

echo "---------------- naive_output.r ----------------"
echo "---------------- naive_output.r ----------------<br />" >> $log

if [[ "$naive_output" != "None" ]]
then
	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}
fi

echo "</table>" >> $outdir/base_overview.html

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
echo "<table border = 1>" >> $log
echo "<thead><tr><th>Info</th><th>Sequences</th><th>Percentage</th></tr></thead>" >> $log
tIFS="$TMP"
IFS=$'\t'
while read step seq perc
	do
		echo "<tr>" >> $log
		echo "<td>$step</td>" >> $log
		echo "<td>$seq</td>" >> $log
		echo "<td>${perc}%</td>" >> $log
		echo "</tr>" >> $log
done < $outdir/filtering_steps.txt
echo "</table border></center></html>" >> $log

IFS="$tIFS"


echo "---------------- Done! ----------------"
echo "---------------- Done! ----------------<br />" >> $outdir/log.html