Mercurial > repos > devteam > join

comparison gops_join.py @ 0:e56b47dce68a

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Imported from capsule None
author devteam
date Tue, 01 Apr 2014 10:54:03 -0400
parents
children ffbd1de29c28
comparison
equal deleted inserted replaced
-1:000000000000 0:e56b47dce68a
1 #!/usr/bin/env python
2 """
3 Join two sets of intervals using their overlap as the key.
4
5 usage: %prog bed_file_1 bed_file_2 out_file
6 -1, --cols1=N,N,N,N: Columns for start, end, strand in first file
7 -2, --cols2=N,N,N,N: Columns for start, end, strand in second file
8 -m, --mincols=N: Require this much overlap (default 1bp)
9 -f, --fill=N: none, right, left, both
10 """
11 import sys, traceback, fileinput
12 from warnings import warn
13 from bx.intervals import *
14 from bx.intervals.io import *
15 from bx.intervals.operations.join import *
16 from bx.cookbook import doc_optparse
17 from galaxy.tools.util.galaxyops import *
18
19 assert sys.version_info[:2] >= ( 2, 4 )
20
21 def main():
22 mincols = 1
23 upstream_pad = 0
24 downstream_pad = 0
25 leftfill = False
26 rightfill = False
27
28 options, args = doc_optparse.parse( __doc__ )
29 try:
30 chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg( options.cols1 )
31 chr_col_2, start_col_2, end_col_2, strand_col_2 = parse_cols_arg( options.cols2 )
32 if options.mincols: mincols = int( options.mincols )
33 if options.fill:
34 if options.fill == "both":
35 rightfill = leftfill = True
36 else:
37 rightfill = options.fill == "right"
38 leftfill = options.fill == "left"
39 in_fname, in2_fname, out_fname = args
40 except:
41 doc_optparse.exception()
42
43 g1 = NiceReaderWrapper( fileinput.FileInput( in_fname ),
44 chrom_col=chr_col_1,
45 start_col=start_col_1,
46 end_col=end_col_1,
47 strand_col=strand_col_1,
48 fix_strand=True )
49 g2 = NiceReaderWrapper( fileinput.FileInput( in2_fname ),
50 chrom_col=chr_col_2,
51 start_col=start_col_2,
52 end_col=end_col_2,
53 strand_col=strand_col_2,
54 fix_strand=True )
55
56 out_file = open( out_fname, "w" )
57
58 try:
59 for outfields in join(g1, g2, mincols=mincols, rightfill=rightfill, leftfill=leftfill):
60 if type( outfields ) is list:
61 out_file.write( "%s\n" % "\t".join( outfields ) )
62 else:
63 out_file.write( "%s\n" % outfields )
64 except ParseError, exc:
65 out_file.close()
66 fail( "Invalid file format: %s" % str( exc ) )
67 except MemoryError:
68 out_file.close()
69 fail( "Input datasets were too large to complete the join operation." )
70
71 out_file.close()
72
73 if g1.skipped > 0:
74 print skipped( g1, filedesc=" of 1st dataset" )
75 if g2.skipped > 0:
76 print skipped( g2, filedesc=" of 2nd dataset" )
77
78 if __name__ == "__main__":
79 main()