# HG changeset patch # User davidvanzessen # Date 1395745166 14400 # Node ID 07a23652bc2a9ebc7c490b4e48741779176e1d5e # Parent 03dbb4601b15135767d473a56f98adb991360676 Uploaded diff -r 03dbb4601b15 -r 07a23652bc2a igblastmerge.py --- a/igblastmerge.py Thu Jan 23 08:14:08 2014 -0500 +++ b/igblastmerge.py Tue Mar 25 06:59:26 2014 -0400 @@ -1,52 +1,44 @@ import sys -# error -def stop_err( msg ): - sys.stderr.write( "%s\n" % msg ) - sys.exit() - -# main -def main(): - args = sys.argv[1:-2] - - try: - o = open(sys.argv[-1], 'w') - i = open(args[1], 'r') - separator = "\t" - newline = "\n" - line = i.readline() - #write the header - o.write(line[:line.rfind(newline)] + separator + "Sample" + separator + "Replicate" + newline) - i.close() - - current = 1 - sampleID = args[0] - count = 1 +import pandas as pd - while True: - print str(o) - f = open(args[current], 'r') - line = f.readline() - line = f.readline() - while line: - o.write(line[:line.rfind(newline)] + separator + sampleID + separator + str(count) + newline) - line = f.readline() - f.close() +def main(): + patients = {} + files = [] + sample_id = sys.argv[1] + imgt_files = 0 + blast_files = 0 + #organize files + for arg in sys.argv[2:-2]: + if arg.find("/") is -1: + patients[sample_id] = files + files = [] + sample_id = arg + else: + df = pd.read_csv(arg, sep="\t") + if "Functionality" in list(df.columns.values): + df["VDJ Frame"][df["Functionality"] != "productive"] = "In-frame with stop codon" + imgt_files += 1 + else: + blast_files += 1 + files.append(df) + patients[sample_id] = files + 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', u'Sample', u'Replicate'] + if blast_files is not 0: + print "Has a parsed blastn file, using limited columns." + 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'Sample', u'Replicate'] - if current >= (len(args) - 1): - break - if args[current + 1].find("/") is -1: - sampleID = args[current + 1] - current += 1 - count = 1 - else: - count += 1 - current += 1 - o.close() - - except Exception, ex: - stop_err('Error running new_column.py\n' + str(ex)) - sys.exit(0) + result = None + for patient_id, samples in patients.iteritems(): + count = 1 + for sample in samples: + sample['Sample'] = patient_id + sample['Replicate'] = str(count) + count += 1 + if result is None: + result = sample[columns] + else: + result = result.append(sample[columns]) + result.to_csv(sys.argv[-1], sep="\t", index=False, index_label="index") if __name__ == "__main__": - print sys.argv main() diff -r 03dbb4601b15 -r 07a23652bc2a igblastmerge.xml --- a/igblastmerge.xml Thu Jan 23 08:14:08 2014 -0500 +++ b/igblastmerge.xml Tue Mar 25 06:59:26 2014 -0400 @@ -3,7 +3,7 @@ igblastmerge.py #for $i, $f in enumerate($patients) - $f.id + "$f.id" #for $j, $g in enumerate($f.samples) ${g.sample} #end for @@ -12,7 +12,7 @@ --output $out_file - +