Mercurial > repos > devteam > concat

comparison gops_concat.py @ 0:8aa939ace6ba

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 10:53:46 -0400
parents
children d491589307e7
comparison
equal deleted inserted replaced
-1:000000000000 0:8aa939ace6ba
1 #!/usr/bin/env python
2 """
3 Concatenate two bed files. The concatenated files are returned in the
4 same format as the first. If --sameformat is specified, then all
5 columns will be treated as the same, and all fields will be saved,
6 although the output will be trimmed to match the primary input. In
7 addition, if --sameformat is specified, missing fields will be padded
8 with a period(.).
9
10 usage: %prog in_file_1 in_file_2 out_file
11 -1, --cols1=N,N,N,N: Columns for chrom, start, end, strand in first file
12 -2, --cols2=N,N,N,N: Columns for chrom, start, end, strand in second file
13 -s, --sameformat: All files are precisely the same format.
14 """
15
16 import sys, traceback, fileinput
17 from warnings import warn
18 from bx.intervals import *
19 from bx.intervals.io import *
20 from bx.intervals.operations.concat import *
21 from bx.cookbook import doc_optparse
22 from galaxy.tools.util.galaxyops import *
23
24 assert sys.version_info[:2] >= ( 2, 4 )
25
26 def main():
27 sameformat=False
28 upstream_pad = 0
29 downstream_pad = 0
30
31 options, args = doc_optparse.parse( __doc__ )
32 try:
33 chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg( options.cols1 )
34 chr_col_2, start_col_2, end_col_2, strand_col_2 = parse_cols_arg( options.cols2 )
35 if options.sameformat: sameformat = True
36 in_file_1, in_file_2, out_fname = args
37 except:
38 doc_optparse.exception()
39
40 g1 = NiceReaderWrapper( fileinput.FileInput( in_file_1 ),
41 chrom_col=chr_col_1,
42 start_col=start_col_1,
43 end_col=end_col_1,
44 strand_col=strand_col_1,
45 fix_strand=True )
46
47 g2 = NiceReaderWrapper( fileinput.FileInput( in_file_2 ),
48 chrom_col=chr_col_2,
49 start_col=start_col_2,
50 end_col=end_col_2,
51 strand_col=strand_col_2,
52 fix_strand=True )
53
54 out_file = open( out_fname, "w" )
55
56 try:
57 for line in concat( [g1, g2], sameformat=sameformat ):
58 if type( line ) is GenomicInterval:
59 out_file.write( "%s\n" % "\t".join( line.fields ) )
60 else:
61 out_file.write( "%s\n" % line )
62 except ParseError, exc:
63 out_file.close()
64 fail( "Invalid file format: %s" % str( exc ) )
65
66 out_file.close()
67
68 if g1.skipped > 0:
69 print skipped( g1, filedesc=" of 1st dataset" )
70 if g2.skipped > 0:
71 print skipped( g2, filedesc=" of 2nd dataset" )
72
73 if __name__ == "__main__":
74 main()