|
1
|
1 #!/usr/bin/python
|
|
|
2 # python parser module for pre-mir and mature miRNAs, guided by mirbase.org GFF3
|
|
|
3 # version 0.0.9 (1-6-2014)
|
|
|
4 # Usage MirParser.py <1:index source> <2:extraction directive> <3:output pre-mir> <4: output mature miRs> <5:mirbase GFF3>
|
|
|
5 # <6:pathToLatticeDataframe or "dummy_dataframe_path"> <7:Rcode or "dummy_plotCode"> <8:latticePDF or "dummy_latticePDF">
|
|
|
6 # <9:10:11 filePath:FileExt:FileLabel> <.. ad lib>
|
|
|
7
|
|
|
8 import sys, subprocess
|
|
|
9 from smRtools import *
|
|
|
10
|
|
|
11 IndexSource = sys.argv[1]
|
|
|
12 ExtractionDirective = sys.argv[2]
|
|
|
13 if ExtractionDirective == "--do_not_extract_index":
|
|
|
14 genomeRefFormat = "fastaSource"
|
|
|
15 elif ExtractionDirective == "--extract_index":
|
|
|
16 genomeRefFormat = "bowtieIndex"
|
|
|
17 OutputPre_mirs = sys.argv[3]
|
|
|
18 OutputMature_Mirs = sys.argv[4]
|
|
|
19 GFF3_file = sys.argv[5]
|
|
|
20 lattice = sys.argv[6]
|
|
|
21 Rcode = sys.argv[7]
|
|
|
22 latticePDF = sys.argv[8]
|
|
|
23 Triplets = [sys.argv[9:][i:i+3] for i in xrange(0, len(sys.argv[9:]), 3)]
|
|
|
24 MasterListOfGenomes = {}
|
|
|
25
|
|
|
26 for [filePath, FileExt, FileLabel] in Triplets:
|
|
|
27 print FileLabel
|
|
|
28 MasterListOfGenomes[FileLabel] = HandleSmRNAwindows (alignmentFile=filePath, alignmentFileFormat=FileExt, genomeRefFile=IndexSource, genomeRefFormat=genomeRefFormat, biosample=FileLabel)
|
|
|
29
|
|
|
30 header = ["gene"]
|
|
|
31 for [filePath, FileExt, FileLabel] in Triplets:
|
|
|
32 header.append(FileLabel)
|
|
|
33
|
|
|
34 hit_table = ["\t".join(header)] # table header: gene, sample1, sample2, sample3, etc. separated by tabulation
|
|
|
35
|
|
|
36 ## read GFF3 to subinstantiate
|
|
|
37 gff3 = open (GFF3_file, "r")
|
|
|
38 lattice_dataframe = []
|
|
|
39 for line in gff3:
|
|
|
40 if line[0] == "#": continue
|
|
|
41 gff_fields = line[:-1].split("\t")
|
|
|
42 chrom = gff_fields[0]
|
|
|
43 gff_name = gff_fields[-1].split("Name=")[-1].split(";")[0] # to isolate the GFF Name
|
|
|
44 item_upstream_coordinate = int(gff_fields[3])
|
|
|
45 item_downstream_coordinate = int(gff_fields[4])
|
|
|
46 if gff_fields[6] == "+":
|
|
|
47 item_polarity = "forward"
|
|
|
48 else:
|
|
|
49 item_polarity = "reverse"
|
|
|
50 item_line = [gff_name]
|
|
|
51 for sample in header[1:]:
|
|
|
52 count = MasterListOfGenomes[sample].instanceDict[chrom].readcount(upstream_coord=item_upstream_coordinate, downstream_coord=item_downstream_coordinate, polarity=item_polarity)
|
|
|
53 item_line.append(str(count))
|
|
|
54 ## subtreatement for lattice
|
|
|
55 if lattice != "dummy_dataframe_path":
|
|
|
56 if ("5p" not in gff_name) and ("3p" not in gff_name):
|
|
|
57 lattice_dataframe.append(MasterListOfGenomes[sample].instanceDict[chrom].readcoverage(upstream_coord=item_upstream_coordinate, downstream_coord=item_downstream_coordinate, windowName=gff_name+"_"+sample) )
|
|
|
58 ## end of subtreatement for lattice
|
|
|
59 hit_table.append("\t".join(item_line) )
|
|
|
60 gff3.close()
|
|
|
61
|
|
|
62 Fpremirs = open (OutputPre_mirs, "w")
|
|
|
63 print >> Fpremirs, hit_table[0]
|
|
|
64 finalPreList = [ i for i in sorted(hit_table[1:]) if ("5p" not in i) and ("3p" not in i)]
|
|
|
65 print >> Fpremirs, "\n".join(finalPreList )
|
|
|
66 Fpremirs.close()
|
|
|
67
|
|
|
68 Fmaturemires = open (OutputMature_Mirs, "w")
|
|
|
69 print >> Fmaturemires, hit_table[0]
|
|
|
70 finalMatureList = [ i for i in sorted(hit_table[1:]) if ("5p" in i) or ("3p" in i)]
|
|
|
71 print >> Fmaturemires, "\n".join(finalMatureList )
|
|
|
72 Fmaturemires.close()
|
|
|
73
|
|
|
74 if lattice != "dummy_dataframe_path":
|
|
|
75 Flattice = open(lattice, "w")
|
|
|
76 print >> Flattice, "%s\t%s\t%s\t%s\t%s\t%s\t%s" % ("sample", "mir", "offset", "offsetNorm", "counts","countsNorm", "polarity")
|
|
|
77 print >> Flattice, "\n".join(lattice_dataframe)
|
|
|
78 Flattice.close()
|
|
|
79 R_command="Rscript "+ Rcode
|
|
|
80 process = subprocess.Popen(R_command.split())
|
|
|
81 process.wait()
|
