Mercurial > repos > davidvanzessen > complete_immunerepertoire_igg

changeset 5:3287f7b9c47d draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Fri, 05 Sep 2014 04:19:58 -0400
parents 24d5d9120d93
children 8b46fca04595
files complete.sh imgt_loader.py imgt_loader.sh imgtconvert.py imgtconvert.sh
diffstat 5 files changed, 207 insertions(+), 255 deletions(-) [+]
line wrap: on
line diff
--- a/complete.sh	Thu Sep 04 07:59:02 2014 -0400
+++ b/complete.sh	Fri Sep 05 04:19:58 2014 -0400
@@ -1,5 +1,5 @@
 #!/bin/bash
-
+set -e
 inputFiles=($1)
 outputDir=$3
 outputFile=$3/index.html #$1
@@ -31,7 +31,7 @@
 
 function imgtConvert {
 	echo "<tr><td>Starting imgt convert of sample $3 of patient $2</td></tr>" >> $html
-	bash $dir/imgtconvert.sh $1 $2 $3 $4
+	bash $dir/imgt_loader.sh $1 $4 $5
 	echo "<tr><td>Finished conversion of sample $3 of patient $2</td></tr>" >> $html
 	
 }
@@ -59,7 +59,7 @@
 	then
 		echo "<tr><td>Sample $count of patient $id is a zip file, using IMGT Loader</td></tr>" >> $html
 	  fileName=$(basename $current)
-		imgtConvert $current $id $count $parsedFileName &
+		imgtConvert $current $id $count $parsedFileName "${id}_${count}" &
 	else
 		echo "<tr><td>Sample $count of patient $id is not a zip file, using igBLASTn</td></tr>" >> $html
 		blastAndParse $current $id $count $fileName $parsedFileName &
@@ -74,12 +74,14 @@
 echo "<tr><td>-----------------------------------</td></tr>" >> $html
 echo "<tr><td>merging</td></tr>" >> $html
 
-python $dir/experimental_design.py ${mergerInput[*]}  --output $PWD/merged.txt
+python $dir/experimental_design.py ${mergerInput[*]} --output $PWD/merged.txt
 
 echo "<tr><td>done</td></tr>" >> $html
 echo "<tr><td>-----------------------------------</td></tr>" >> $html
 echo "<tr><td>plotting</td></tr>" >> $html
 
+echo "after ED"
+
 if [ "$locus" == "igh" ] || [ "$locus" == "igk" ] || [ "$locus" == "igl" ]; then
 	bash $dir/r_wrapper_b.sh $PWD/merged.txt $2 $outputDir $clonalType $species $locus $selection
 else
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/imgt_loader.py	Fri Sep 05 04:19:58 2014 -0400
@@ -0,0 +1,142 @@
+import pandas as pd
+try:
+	pd.options.mode.chained_assignment = None  # default='warn'
+except:
+	pass
+import re
+import argparse
+import os
+
+def stop_err( msg, ret=1 ):
+    sys.stderr.write( msg )
+    sys.exit( ret )
+
+#docs.python.org/dev/library/argparse.html
+parser = argparse.ArgumentParser()
+parser.add_argument("--summ", help="The 1_Summary file from the imgt output")
+parser.add_argument("--aa", help="The 5_AA-Sequence file from the imgt output")
+parser.add_argument("--junction", help="The 6_Junction file from the imgt output")
+parser.add_argument("--output", help="Output file")
+
+args = parser.parse_args()
+
+old_summary_columns = [u'Sequence ID', u'JUNCTION frame', u'V-GENE and allele', u'D-GENE and allele', u'J-GENE and allele', u'CDR1-IMGT length', u'CDR2-IMGT length', u'CDR3-IMGT length', u'Orientation']
+old_sequence_columns = [u'CDR1-IMGT', u'CDR2-IMGT', u'CDR3-IMGT']
+old_junction_columns = [u'JUNCTION']
+
+added_summary_columns = [u'Functionality', u'V-REGION identity %', u'V-REGION identity nt', u'D-REGION reading frame', u'AA JUNCTION', u'Functionality comment', u'Sequence']
+added_sequence_columns = [u'FR1-IMGT', u'FR2-IMGT', u'FR3-IMGT', u'CDR3-IMGT', u'JUNCTION', u'J-REGION', u'FR4-IMGT']
+added_junction_columns = [u"P3'V-nt nb", u'N1-REGION-nt nb', u"P5'D-nt nb", u"P3'D-nt nb", u'N2-REGION-nt nb', u"P5'J-nt nb", u"3'V-REGION trimmed-nt nb", u"5'D-REGION trimmed-nt nb", u"3'D-REGION trimmed-nt nb", u"5'J-REGION trimmed-nt nb"]
+
+outFile = args.output
+
+#fSummary = pd.read_csv(triplets[0][0], sep="\t", low_memory=False)
+fSummary = pd.read_csv(args.summ, sep="\t", dtype=object)
+#fSequence = pd.read_csv(triplets[0][1], sep="\t", low_memory=False)
+fSequence = pd.read_csv(args.aa, sep="\t", dtype=object)
+#fJunction = pd.read_csv(triplets[0][2], sep="\t", low_memory=False)
+fJunction = pd.read_csv(args.junction, sep="\t", dtype=object)
+tmp = fSummary[["Sequence ID", "JUNCTION frame", "V-GENE and allele", "D-GENE and allele", "J-GENE and allele"]]
+
+tmp["CDR1 Seq"] = fSequence["CDR1-IMGT"]
+tmp["CDR1 Length"] = fSummary["CDR1-IMGT length"]
+
+tmp["CDR2 Seq"] = fSequence["CDR2-IMGT"]
+tmp["CDR2 Length"] = fSummary["CDR2-IMGT length"]
+
+tmp["CDR3 Seq"] = fSequence["CDR3-IMGT"]
+tmp["CDR3 Length"] = fSummary["CDR3-IMGT length"]
+
+tmp["CDR3 Seq DNA"] = fJunction["JUNCTION"]
+tmp["CDR3 Length DNA"] = '1'
+tmp["Strand"] = fSummary["Orientation"]
+tmp["CDR3 Found How"] = 'a'
+
+for col in added_summary_columns:
+    tmp[col] = fSummary[col]
+
+for col in added_sequence_columns:
+    tmp[col] = fSequence[col]
+
+for col in added_junction_columns:
+    tmp[col] = fJunction[col]
+
+outFrame = tmp
+
+outFrame.columns = [u'ID', u'VDJ Frame', u'Top V Gene', u'Top D Gene', u'Top J Gene', u'CDR1 Seq', u'CDR1 Length', u'CDR2 Seq', u'CDR2 Length', u'CDR3 Seq', u'CDR3 Length', u'CDR3 Seq DNA', u'CDR3 Length DNA', u'Strand', u'CDR3 Found How', u'Functionality', 'V-REGION identity %', 'V-REGION identity nt', 'D-REGION reading frame', 'AA JUNCTION', 'Functionality comment', 'Sequence', 'FR1-IMGT', 'FR2-IMGT', 'FR3-IMGT', 'CDR3-IMGT', 'JUNCTION', 'J-REGION', 'FR4-IMGT', 'P3V-nt nb', 'N1-REGION-nt nb', 'P5D-nt nb', 'P3D-nt nb', 'N2-REGION-nt nb', 'P5J-nt nb', '3V-REGION trimmed-nt nb', '5D-REGION trimmed-nt nb', '3D-REGION trimmed-nt nb', '5J-REGION trimmed-nt nb']
+
+"""
+IGHV[0-9]-[0-9ab]+-?[0-9]?D?
+TRBV[0-9]{1,2}-?[0-9]?-?[123]?
+IGKV[0-3]D?-[0-9]{1,2}
+IGLV[0-9]-[0-9]{1,2}
+TRAV[0-9]{1,2}(-[1-46])?(/DV[45678])?
+TRGV[234589]
+TRDV[1-3]
+
+IGHD[0-9]-[0-9ab]+
+TRBD[12]
+TRDD[1-3]
+
+IGHJ[1-6]
+TRBJ[12]-[1-7]
+IGKJ[1-5]
+IGLJ[12367]
+TRAJ[0-9]{1,2}
+TRGJP?[12]
+TRDJ[1-4]
+"""
+
+vPattern = [r"(IGHV[0-9]-[0-9ab]+-?[0-9]?D?)",
+						r"(TRBV[0-9]{1,2}-?[0-9]?-?[123]?)",
+						r"(IGKV[0-3]D?-[0-9]{1,2})",
+						r"(IGLV[0-9]-[0-9]{1,2})",
+						r"(TRAV[0-9]{1,2}(-[1-46])?(/DV[45678])?)",
+						r"(TRGV[234589])",
+						r"(TRDV[1-3])"]
+
+dPattern = [r"(IGHD[0-9]-[0-9ab]+)",
+						r"(TRBD[12])",
+						r"(TRDD[1-3])"]
+						
+jPattern = [r"(IGHJ[1-6])",
+						r"(TRBJ[12]-[1-7])",
+						r"(IGKJ[1-5])",
+						r"(IGLJ[12367])",
+						r"(TRAJ[0-9]{1,2})",
+						r"(TRGJP?[12])",
+						r"(TRDJ[1-4])"]
+
+vPattern = re.compile(r"|".join(vPattern))
+
+dPattern = re.compile(r"|".join(dPattern))
+
+jPattern = re.compile(r"|".join(jPattern))
+
+
+def filterGenes(s, pattern):
+    if type(s) is not str:
+        return "NA"
+    res = pattern.search(s)
+    if res:
+        return res.group(0)
+    return "NA"
+
+
+
+outFrame["Top V Gene"] = outFrame["Top V Gene"].apply(lambda x: filterGenes(x, vPattern))
+outFrame["Top D Gene"] = outFrame["Top D Gene"].apply(lambda x: filterGenes(x, dPattern))
+outFrame["Top J Gene"] = outFrame["Top J Gene"].apply(lambda x: filterGenes(x, jPattern))
+
+print outFrame
+
+tmp = outFrame["VDJ Frame"]
+tmp = tmp.replace("in-frame", "In-frame")
+tmp = tmp.replace("null", "Out-of-frame")
+tmp = tmp.replace("out-of-frame", "Out-of-frame")
+outFrame["VDJ Frame"] = tmp
+outFrame["CDR3 Length DNA"] = outFrame["CDR3 Seq DNA"].map(str).map(len)
+safeLength = lambda x: len(x) if type(x) == str else 0
+outFrame = outFrame[(outFrame["CDR3 Seq DNA"].map(safeLength) > 0) & (outFrame["Top V Gene"] != "NA") & (outFrame["Top J Gene"] != "NA")] #filter out weird rows?
+#outFrame = outFrame[(outFrame["CDR3 Seq DNA"].map(safeLength) > 0) & (outFrame["Top V Gene"] != "NA") & (outFrame["Top D Gene"] != "NA") & (outFrame["Top J Gene"] != "NA")] #filter out weird rows?
+outFrame.to_csv(outFile, sep="\t", index=False, index_label="index")
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/imgt_loader.sh	Fri Sep 05 04:19:58 2014 -0400
@@ -0,0 +1,59 @@
+#!/bin/bash
+input=$1
+output=$2
+name=$3
+dir="$(cd "$(dirname "$0")" && pwd)"
+mkdir -p $PWD/$name/files
+f=$(file $input)
+zip7Type="7-zip archive"
+tarType="tar archive"
+bzip2Type="bzip2 compressed"
+gzipType="gzip compressed"
+zipType="Zip archive"
+rarType="RAR archive"
+
+if [[ "$f" == *"$zip7Type"* ]]; then
+	echo "7-zip"
+	echo "Trying: 7za e $input -o$PWD/files/"
+	7za e $input -o$PWD/$name/files
+fi
+
+if [[ "$f" == *"$tarType"* ]]
+then
+	echo "tar archive"
+	echo "Trying: tar xvf $input -C $PWD/files/"
+	tar xvf $input -C $PWD/$name/files
+fi
+
+if [[ "$f" == *"$bzip2Type"* ]]
+then
+	echo "bzip2 compressed data"
+	echo "Trying: tar jxf $input -C $PWD/files/"
+	tar jxf $input -C $PWD/$name/files
+fi
+
+if [[ "$f" == *"$gzipType"* ]]
+then
+	echo "gzip compressed data"
+	echo "Trying: tar xvzf $input -C $PWD/files/"
+	tar xvzf $input -C $PWD/$name/files
+fi
+
+if [[ "$f" == *"$zipType"* ]]
+then
+	echo "Zip archive"
+	echo "Trying: unzip $input -d $PWD/files/"
+	unzip $input -d $PWD/$name/files > $PWD/unziplog.log
+fi
+
+if [[ "$f" == *"$rarType"* ]]
+then
+	echo "RAR archive"
+	echo "Trying: unrar e $input $PWD/files/"
+	unrar e $input $PWD/$name/files
+fi
+find $PWD/$name/files -iname "1_*" -exec cat {} + > $PWD/$name/summ.txt
+find $PWD/$name/files -iname "5_*" -exec cat {} + > $PWD/$name/aa.txt
+find $PWD/$name/files -iname "6_*" -exec cat {} + > $PWD/$name/junction.txt
+
+python $dir/imgt_loader.py --summ $PWD/$name/summ.txt --aa $PWD/$name/aa.txt --junction $PWD/$name/junction.txt --output $output
--- a/imgtconvert.py	Thu Sep 04 07:59:02 2014 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,194 +0,0 @@
-import pandas as pd
-try:
-	pd.options.mode.chained_assignment = None  # default='warn'
-except:
-	pass
-import re
-import argparse
-import os
-
-def stop_err( msg, ret=1 ):
-    sys.stderr.write( msg )
-    sys.exit( ret )
-
-#docs.python.org/dev/library/argparse.html
-parser = argparse.ArgumentParser()
-parser.add_argument("--input", help="Input folder with files")
-parser.add_argument("--output", help="Output file")
-
-args = parser.parse_args()
-
-old_summary_columns = [u'Sequence ID', u'JUNCTION frame', u'V-GENE and allele', u'D-GENE and allele', u'J-GENE and allele', u'CDR1-IMGT length', u'CDR2-IMGT length', u'CDR3-IMGT length', u'Orientation']
-old_sequence_columns = [u'CDR1-IMGT', u'CDR2-IMGT', u'CDR3-IMGT']
-old_junction_columns = [u'JUNCTION']
-
-added_summary_columns = [u'Functionality', u'V-REGION identity %', u'V-REGION identity nt', u'D-REGION reading frame', u'AA JUNCTION', u'Functionality comment', u'Sequence']
-added_sequence_columns = [u'FR1-IMGT', u'FR2-IMGT', u'FR3-IMGT', u'CDR3-IMGT', u'JUNCTION', u'J-REGION', u'FR4-IMGT']
-added_junction_columns = [u"P3'V-nt nb", u'N1-REGION-nt nb', u"P5'D-nt nb", u"P3'D-nt nb", u'N2-REGION-nt nb', u"P5'J-nt nb", u"3'V-REGION trimmed-nt nb", u"5'D-REGION trimmed-nt nb", u"3'D-REGION trimmed-nt nb", u"5'J-REGION trimmed-nt nb"]
-
-inputFolder = args.input
-
-dirContents = os.listdir(inputFolder)
-if len(dirContents) == 1:
-    inputFolder = os.path.join(inputFolder, dirContents[0])
-    if os.path.isdir(inputFolder):
-        dirContents = os.listdir(inputFolder)
-files = sorted([os.path.join(inputFolder, f) for f in dirContents if os.path.isfile(os.path.join(inputFolder, f))])
-
-if len(files) % 3 is not 0:
-    stop_err("Files in zip not a multiple of 3, it should contain all the 1_, 5_ and 6_ files for a sample")
-    import sys
-    sys.exit()
-
-triplets = []
-step = len(files) / 3
-for i in range(0, step):
-    triplets.append((files[i], files[i + step], files[i + step + step]))
-
-outFile = args.output
-
-#fSummary = pd.read_csv(triplets[0][0], sep="\t", low_memory=False)
-fSummary = pd.read_csv(triplets[0][0], sep="\t", dtype=object)
-#fSequence = pd.read_csv(triplets[0][1], sep="\t", low_memory=False)
-fSequence = pd.read_csv(triplets[0][1], sep="\t", dtype=object)
-#fJunction = pd.read_csv(triplets[0][2], sep="\t", low_memory=False)
-fJunction = pd.read_csv(triplets[0][2], sep="\t", dtype=object)
-tmp = fSummary[["Sequence ID", "JUNCTION frame", "V-GENE and allele", "D-GENE and allele", "J-GENE and allele"]]
-
-tmp["CDR1 Seq"] = fSequence["CDR1-IMGT"]
-tmp["CDR1 Length"] = fSummary["CDR1-IMGT length"]
-
-tmp["CDR2 Seq"] = fSequence["CDR2-IMGT"]
-tmp["CDR2 Length"] = fSummary["CDR2-IMGT length"]
-
-tmp["CDR3 Seq"] = fSequence["CDR3-IMGT"]
-tmp["CDR3 Length"] = fSummary["CDR3-IMGT length"]
-
-tmp["CDR3 Seq DNA"] = fJunction["JUNCTION"]
-tmp["CDR3 Length DNA"] = '1'
-tmp["Strand"] = fSummary["Orientation"]
-tmp["CDR3 Found How"] = 'a'
-
-for col in added_summary_columns:
-    tmp[col] = fSummary[col]
-
-for col in added_sequence_columns:
-    tmp[col] = fSequence[col]
-
-for col in added_junction_columns:
-    tmp[col] = fJunction[col]
-
-outFrame = tmp
-
-
-
-for triple in triplets[1:]:
-    fSummary = pd.read_csv(triple[0], sep="\t", dtype=object)
-    fSequence = pd.read_csv(triple[1], sep="\t", dtype=object)
-    fJunction = pd.read_csv(triple[2], sep="\t", dtype=object)
-
-    tmp = fSummary[["Sequence ID", "JUNCTION frame", "V-GENE and allele", "D-GENE and allele", "J-GENE and allele"]]
-
-    tmp["CDR1 Seq"] = fSequence["CDR1-IMGT"]
-    tmp["CDR1 Length"] = fSummary["CDR1-IMGT length"]
-
-    tmp["CDR2 Seq"] = fSequence["CDR2-IMGT"]
-    tmp["CDR2 Length"] = fSummary["CDR2-IMGT length"]
-
-    tmp["CDR3 Seq"] = fSequence["CDR3-IMGT"]
-    tmp["CDR3 Length"] = fSummary["CDR3-IMGT length"]
-
-    tmp["CDR3 Seq DNA"] = fJunction["JUNCTION"]
-    tmp["CDR3 Length DNA"] = '1'
-    tmp["Strand"] = fSummary["Orientation"]
-    tmp["CDR3 Found How"] = 'a'
-
-    for col in added_summary_columns:
-        tmp[col] = fSummary[col]
-
-    for col in added_sequence_columns:
-        tmp[col] = fSequence[col]
-
-    for col in added_junction_columns:
-        tmp[col] = fJunction[col]
-
-    outFrame = outFrame.append(tmp)
-
-
-outFrame.columns = [u'ID', u'VDJ Frame', u'Top V Gene', u'Top D Gene', u'Top J Gene', u'CDR1 Seq', u'CDR1 Length', u'CDR2 Seq', u'CDR2 Length', u'CDR3 Seq', u'CDR3 Length', u'CDR3 Seq DNA', u'CDR3 Length DNA', u'Strand', u'CDR3 Found How', u'Functionality', 'V-REGION identity %', 'V-REGION identity nt', 'D-REGION reading frame', 'AA JUNCTION', 'Functionality comment', 'Sequence', 'FR1-IMGT', 'FR2-IMGT', 'FR3-IMGT', 'CDR3-IMGT', 'JUNCTION', 'J-REGION', 'FR4-IMGT', 'P3V-nt nb', 'N1-REGION-nt nb', 'P5D-nt nb', 'P3D-nt nb', 'N2-REGION-nt nb', 'P5J-nt nb', '3V-REGION trimmed-nt nb', '5D-REGION trimmed-nt nb', '3D-REGION trimmed-nt nb', '5J-REGION trimmed-nt nb']
-
-"""
-IGHV[0-9]-[0-9ab]+-?[0-9]?D?
-TRBV[0-9]{1,2}-?[0-9]?-?[123]?
-IGKV[0-3]D?-[0-9]{1,2}
-IGLV[0-9]-[0-9]{1,2}
-TRAV[0-9]{1,2}(-[1-46])?(/DV[45678])?
-TRGV[234589]
-TRDV[1-3]
-
-IGHD[0-9]-[0-9ab]+
-TRBD[12]
-TRDD[1-3]
-
-IGHJ[1-6]
-TRBJ[12]-[1-7]
-IGKJ[1-5]
-IGLJ[12367]
-TRAJ[0-9]{1,2}
-TRGJP?[12]
-TRDJ[1-4]
-"""
-
-vPattern = [r"(IGHV[0-9]-[0-9ab]+-?[0-9]?D?)",
-						r"(TRBV[0-9]{1,2}-?[0-9]?-?[123]?)",
-						r"(IGKV[0-3]D?-[0-9]{1,2})",
-						r"(IGLV[0-9]-[0-9]{1,2})",
-						r"(TRAV[0-9]{1,2}(-[1-46])?(/DV[45678])?)",
-						r"(TRGV[234589])",
-						r"(TRDV[1-3])"]
-
-dPattern = [r"(IGHD[0-9]-[0-9ab]+)",
-						r"(TRBD[12])",
-						r"(TRDD[1-3])"]
-						
-jPattern = [r"(IGHJ[1-6])",
-						r"(TRBJ[12]-[1-7])",
-						r"(IGKJ[1-5])",
-						r"(IGLJ[12367])",
-						r"(TRAJ[0-9]{1,2})",
-						r"(TRGJP?[12])",
-						r"(TRDJ[1-4])"]
-
-vPattern = re.compile(r"|".join(vPattern))
-
-dPattern = re.compile(r"|".join(dPattern))
-
-jPattern = re.compile(r"|".join(jPattern))
-
-
-def filterGenes(s, pattern):
-    if type(s) is not str:
-        return "NA"
-    res = pattern.search(s)
-    if res:
-        return res.group(0)
-    return "NA"
-
-
-
-outFrame["Top V Gene"] = outFrame["Top V Gene"].apply(lambda x: filterGenes(x, vPattern))
-outFrame["Top D Gene"] = outFrame["Top D Gene"].apply(lambda x: filterGenes(x, dPattern))
-outFrame["Top J Gene"] = outFrame["Top J Gene"].apply(lambda x: filterGenes(x, jPattern))
-
-print outFrame
-
-tmp = outFrame["VDJ Frame"]
-tmp = tmp.replace("in-frame", "In-frame")
-tmp = tmp.replace("null", "Out-of-frame")
-tmp = tmp.replace("out-of-frame", "Out-of-frame")
-outFrame["VDJ Frame"] = tmp
-outFrame["CDR3 Length DNA"] = outFrame["CDR3 Seq DNA"].map(str).map(len)
-safeLength = lambda x: len(x) if type(x) == str else 0
-outFrame = outFrame[(outFrame["CDR3 Seq DNA"].map(safeLength) > 0) & (outFrame["Top V Gene"] != "NA") & (outFrame["Top J Gene"] != "NA")] #filter out weird rows?
-#outFrame = outFrame[(outFrame["CDR3 Seq DNA"].map(safeLength) > 0) & (outFrame["Top V Gene"] != "NA") & (outFrame["Top D Gene"] != "NA") & (outFrame["Top J Gene"] != "NA")] #filter out weird rows?
-outFrame.to_csv(outFile, sep="\t", index=False, index_label="index")
--- a/imgtconvert.sh	Thu Sep 04 07:59:02 2014 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,57 +0,0 @@
-#!/bin/bash
-dir="$(cd "$(dirname "$0")" && pwd)"
-mkdir $PWD/files
-
-
-#!/bin/bash
-f=$(file $1)
-zip7Type="7-zip archive"
-tarType="tar archive"
-bzip2Type="bzip2 compressed"
-gzipType="gzip compressed"
-zipType="Zip archive"
-rarType="RAR archive"
-
-if [[ "$f" == *"$zip7Type"* ]]; then
-	echo "7-zip"
-	echo "Trying: 7za e $1 -o$PWD/files/"
-	7za e $1 -o$PWD/files/
-fi
-
-if [[ "$f" == *"$tarType"* ]]
-then
-	echo "tar archive"
-	echo "Trying: tar xvf $1 -C $PWD/files/"
-	tar xvf $1 -C $PWD/files/
-fi
-
-if [[ "$f" == *"$bzip2Type"* ]]
-then
-	echo "bzip2 compressed data"
-	echo "Trying: tar jxf $1 -C $PWD/files/"
-	tar jxf $1 -C $PWD/files/
-fi
-
-if [[ "$f" == *"$gzipType"* ]]
-then
-	echo "gzip compressed data"
-	echo "Trying: tar xvzf $1 -C $PWD/files/"
-	tar xvzf $1 -C $PWD/files/
-fi
-
-if [[ "$f" == *"$zipType"* ]]
-then
-	echo "Zip archive"
-	echo "Trying: unzip $1 -d $PWD/files/"
-	unzip $1 -d $PWD/files/ > $PWD/unziplog.log
-fi
-
-if [[ "$f" == *"$rarType"* ]]
-then
-	echo "RAR archive"
-	echo "Trying: unrar e $1 $PWD/files/"
-	unrar e $1 $PWD/files/
-fi
-find $PWD/files/ -type f |  grep -v "1_Summary_\|5_AA-sequences_\|6_Junction_" | xargs rm -f
-python $dir/imgtconvert.py --input $PWD/files --output $2
-