Mercurial > repos > davidvanzessen > experimental_design_igg

comparison igblastmerge.py @ 1:07a23652bc2a draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author davidvanzessen
date Tue, 25 Mar 2014 06:59:26 -0400
parents 03dbb4601b15
children
comparison
equal deleted inserted replaced
0:03dbb4601b15 1:07a23652bc2a
1 import sys 1 import sys
2 # error 2 import pandas as pd
3 def stop_err( msg ):
4 sys.stderr.write( "%s\n" % msg )
5 sys.exit()
6 3
7 # main
8 def main(): 4 def main():
9 args = sys.argv[1:-2] 5 patients = {}
6 files = []
7 sample_id = sys.argv[1]
8 imgt_files = 0
9 blast_files = 0
10 #organize files
11 for arg in sys.argv[2:-2]:
12 if arg.find("/") is -1:
13 patients[sample_id] = files
14 files = []
15 sample_id = arg
16 else:
17 df = pd.read_csv(arg, sep="\t")
18 if "Functionality" in list(df.columns.values):
19 df["VDJ Frame"][df["Functionality"] != "productive"] = "In-frame with stop codon"
20 imgt_files += 1
21 else:
22 blast_files += 1
23 files.append(df)
24 patients[sample_id] = files
25 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']
26 if blast_files is not 0:
27 print "Has a parsed blastn file, using limited columns."
28 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']
10 29
11 try: 30 result = None
12 o = open(sys.argv[-1], 'w') 31 for patient_id, samples in patients.iteritems():
13 i = open(args[1], 'r') 32 count = 1
14 separator = "\t" 33 for sample in samples:
15 newline = "\n" 34 sample['Sample'] = patient_id
16 line = i.readline() 35 sample['Replicate'] = str(count)
17 #write the header 36 count += 1
18 o.write(line[:line.rfind(newline)] + separator + "Sample" + separator + "Replicate" + newline) 37 if result is None:
19 i.close() 38 result = sample[columns]
20 39 else:
21 current = 1 40 result = result.append(sample[columns])
22 sampleID = args[0] 41 result.to_csv(sys.argv[-1], sep="\t", index=False, index_label="index")
23 count = 1
24
25 while True:
26 print str(o)
27 f = open(args[current], 'r')
28 line = f.readline()
29 line = f.readline()
30 while line:
31 o.write(line[:line.rfind(newline)] + separator + sampleID + separator + str(count) + newline)
32 line = f.readline()
33 f.close()
34
35 if current >= (len(args) - 1):
36 break
37 if args[current + 1].find("/") is -1:
38 sampleID = args[current + 1]
39 current += 1
40 count = 1
41 else:
42 count += 1
43 current += 1
44 o.close()
45
46 except Exception, ex:
47 stop_err('Error running new_column.py\n' + str(ex))
48 sys.exit(0)
49 42
50 if __name__ == "__main__": 43 if __name__ == "__main__":
51 print sys.argv
52 main() 44 main()