PageRenderTime 92ms CodeModel.GetById 73ms app.highlight 14ms RepoModel.GetById 1ms app.codeStats 0ms

/tools/new_operations/gops_coverage.py

https://bitbucket.org/cistrome/cistrome-harvard/
Python | 68 lines | 50 code | 9 blank | 9 comment | 6 complexity | b599448b791491cf8f279659003959eb MD5 | raw file
 1#!/usr/bin/env python
 2"""
 3Calculate coverage of one query on another, and append the coverage to
 4the last two columns as bases covered and percent coverage.
 5
 6usage: %prog bed_file_1 bed_file_2 out_file
 7    -1, --cols1=N,N,N,N: Columns for start, end, strand in first file
 8    -2, --cols2=N,N,N,N: Columns for start, end, strand in second file
 9"""
10from galaxy import eggs
11import pkg_resources
12pkg_resources.require( "bx-python" )
13import sys, traceback, fileinput
14from warnings import warn
15from bx.intervals import *
16from bx.intervals.io import *
17from bx.intervals.operations.coverage import *
18from bx.cookbook import doc_optparse
19from galaxy.tools.util.galaxyops import *
20
21assert sys.version_info[:2] >= ( 2, 4 )
22
23def main():
24    upstream_pad = 0
25    downstream_pad = 0
26
27    options, args = doc_optparse.parse( __doc__ )
28    try:
29        chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg( options.cols1 )
30        chr_col_2, start_col_2, end_col_2, strand_col_2 = parse_cols_arg( options.cols2 )      
31        in_fname, in2_fname, out_fname = args
32    except:
33        doc_optparse.exception()
34
35    g1 = NiceReaderWrapper( fileinput.FileInput( in_fname ),
36                            chrom_col=chr_col_1,
37                            start_col=start_col_1,
38                            end_col=end_col_1,
39                            strand_col=strand_col_1,
40                            fix_strand=True )
41    g2 = NiceReaderWrapper( fileinput.FileInput( in2_fname ),
42                            chrom_col=chr_col_2,
43                            start_col=start_col_2,
44                            end_col=end_col_2,
45                            strand_col=strand_col_2,
46                            fix_strand=True )
47
48    out_file = open( out_fname, "w" )
49
50    try:
51        for line in coverage( [g1,g2] ):
52            if type( line ) is GenomicInterval:
53                out_file.write( "%s\n" % "\t".join( line.fields ) )
54            else:
55                out_file.write( "%s\n" % line )
56    except ParseError, exc:
57        out_file.close()
58        fail( "Invalid file format: %s" % str( exc ) )
59
60    out_file.close()
61
62    if g1.skipped > 0:
63        print skipped( g1, filedesc=" of 1st dataset" )
64    if g2.skipped > 0:
65        print skipped( g2, filedesc=" of 2nd dataset" )
66
67if __name__ == "__main__":
68    main()