|
0
|
1 #!/usr/bin/env python
|
|
|
2 """
|
|
|
3 Complement regions.
|
|
|
4
|
|
|
5 usage: %prog in_file out_file
|
|
|
6 -1, --cols1=N,N,N,N: Columns for chrom, start, end, strand in file
|
|
|
7 -l, --lengths=N: Filename of .len file for species (chromosome lengths)
|
|
|
8 -a, --all: Complement all chromosomes (Genome-wide complement)
|
|
|
9 """
|
|
|
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.complement import complement
|
|
|
16 from bx.intervals.operations.subtract import subtract
|
|
|
17 from bx.cookbook import doc_optparse
|
|
|
18 from galaxy.tools.util.galaxyops import *
|
|
|
19
|
|
|
20 assert sys.version_info[:2] >= ( 2, 4 )
|
|
|
21
|
|
|
22 def main():
|
|
|
23 allchroms = False
|
|
|
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 lengths = options.lengths
|
|
|
31 if options.all: allchroms = True
|
|
|
32 in_fname, out_fname = args
|
|
|
33 except:
|
|
|
34 doc_optparse.exception()
|
|
|
35
|
|
|
36 g1 = NiceReaderWrapper( fileinput.FileInput( in_fname ),
|
|
|
37 chrom_col=chr_col_1,
|
|
|
38 start_col=start_col_1,
|
|
|
39 end_col=end_col_1,
|
|
|
40 strand_col=strand_col_1,
|
|
|
41 fix_strand=True )
|
|
|
42
|
|
|
43 lens = dict()
|
|
|
44 chroms = list()
|
|
|
45 # dbfile is used to determine the length of each chromosome. The lengths
|
|
|
46 # are added to the lens dict and passed copmlement operation code in bx.
|
|
|
47 dbfile = fileinput.FileInput( lengths )
|
|
|
48
|
|
|
49 if dbfile:
|
|
|
50 if not allchroms:
|
|
|
51 try:
|
|
|
52 for line in dbfile:
|
|
|
53 fields = line.split("\t")
|
|
|
54 lens[fields[0]] = int(fields[1])
|
|
|
55 except:
|
|
|
56 # assume LEN doesn't exist or is corrupt somehow
|
|
|
57 pass
|
|
|
58 elif allchroms:
|
|
|
59 try:
|
|
|
60 for line in dbfile:
|
|
|
61 fields = line.split("\t")
|
|
|
62 end = int(fields[1])
|
|
|
63 chroms.append("\t".join([fields[0],"0",str(end)]))
|
|
|
64 except:
|
|
|
65 pass
|
|
|
66
|
|
|
67 # Safety...if the dbfile didn't exist and we're on allchroms, then
|
|
|
68 # default to generic complement
|
|
|
69 if allchroms and len(chroms) == 0:
|
|
|
70 allchroms = False
|
|
|
71
|
|
|
72 if allchroms:
|
|
|
73 chromReader = GenomicIntervalReader(chroms)
|
|
|
74 generator = subtract([chromReader, g1])
|
|
|
75 else:
|
|
|
76 generator = complement(g1, lens)
|
|
|
77
|
|
|
78 out_file = open( out_fname, "w" )
|
|
|
79
|
|
|
80 try:
|
|
|
81 for interval in generator:
|
|
|
82 if type( interval ) is GenomicInterval:
|
|
|
83 out_file.write( "%s\n" % "\t".join( interval ) )
|
|
|
84 else:
|
|
|
85 out_file.write( "%s\n" % interval )
|
|
|
86 except ParseError, exc:
|
|
|
87 out_file.close()
|
|
|
88 fail( "Invalid file format: %s" % str( exc ) )
|
|
|
89
|
|
|
90 out_file.close()
|
|
|
91
|
|
|
92 if g1.skipped > 0:
|
|
|
93 print skipped( g1, filedesc="" )
|
|
|
94
|
|
|
95 if __name__ == "__main__":
|
|
|
96 main()
|
