comparison sRbowtieParser.py @ 0:b996480cd604 draft

planemo upload for repository https://bitbucket.org/drosofff/gedtools/
author drosofff
date Wed, 27 May 2015 17:19:15 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:b996480cd604
1 #!/usr/bin/python
2 # python parser module to analyse sRbowtie alignments
3 # version 1.0.2 - argparse implementation
4 # Usage sRbowtieParser.py <1:index source> <2:extraction directive> <3:outputL> <4:polarity> <5:6:7 filePath:FileExt:FileLabel> <.. ad lib>
5
6 import sys, argparse
7 from smRtools import *
8
9 def masterListGenerator(data_source):
10 for filePath, FileExt, FileLabel in data_source:
11 yield HandleSmRNAwindows (filePath, FileExt, IndexSource, genomeRefFormat)
12
13 def Parser():
14 the_parser = argparse.ArgumentParser()
15 the_parser.add_argument('--IndexSource', action="store", type=str, help="Path to the index source")
16 the_parser.add_argument('--ExtractDirective', action="store", type=str, choices=["fastaSource", "bowtieIndex"], help="Extract info from fasta or bowtie index")
17 the_parser.add_argument('--output', action="store", type=str, help="path to the output")
18 the_parser.add_argument('--polarity', choices=["forward", "reverse", "both"], help="forward, reverse or both forward an reverse reads are counted")
19 the_parser.add_argument('--alignmentSource',nargs='+', help="paths to alignments files")
20 the_parser.add_argument('--alignmentFormat',nargs='+', help="Format of the bowtie alignment (tabular, sam or bam)")
21 the_parser.add_argument('--alignmentLabel',nargs='+', help="Label of the alignment")
22 args = the_parser.parse_args()
23 return args
24
25 args = Parser()
26
27 IndexSource = args.IndexSource
28 genomeRefFormat = args.ExtractDirective
29 Output = args.output
30 Polarity = args.polarity
31 header = ["gene"]
32
33
34 FileLabelList=[label for label in args.alignmentLabel]
35 header.extend(FileLabelList)
36 assert (len(FileLabelList)==len(set(FileLabelList))),"You have supplied a non-unique label. Please make sure that your input files have unique names"
37
38 data_source=zip (args.alignmentSource, args.alignmentFormat, args.alignmentLabel)
39 master_generator=masterListGenerator(data_source)
40
41 for i,window in enumerate(master_generator):
42 window=window
43 if i==0:
44 gene_count_dict={gene:[str(item.readcount(polarity=Polarity))] for gene,item in window.instanceDict.items()}
45 else:
46 [gene_count_dict[gene].append(str(item.readcount(polarity=Polarity))) for gene,item in window.instanceDict.items()]
47
48
49 F = open (args.output, "w")
50 # print >>F, args
51 print >> F, "\t".join(header)
52
53 for item in sorted(gene_count_dict.keys()):
54 line=[item]
55 line.extend(gene_count_dict[item])
56 print >> F, "\t".join(line )
57 F.close()