Mercurial > repos > devteam > merge

comparison gops_merge.py @ 3:b9c97d3233bb draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 33927a87ba2eee9bf0ecdd376a66241b17b3d734
author devteam
date Tue, 13 Oct 2015 12:51:07 -0400
parents 10ac6097acdb
children dfbbc0291b36
comparison
equal deleted inserted replaced
2:1e9d95cae35f 3:b9c97d3233bb
5 usage: %prog in_file out_file 5 usage: %prog in_file out_file
6 -1, --cols1=N,N,N,N: Columns for start, end, strand in first file 6 -1, --cols1=N,N,N,N: Columns for start, end, strand in first file
7 -m, --mincols=N: Require this much overlap (default 1bp) 7 -m, --mincols=N: Require this much overlap (default 1bp)
8 -3, --threecol: Output 3 column bed 8 -3, --threecol: Output 3 column bed
9 """ 9 """
10 import sys, traceback, fileinput 10 import fileinput
11 from warnings import warn 11 import sys
12 from bx.intervals import * 12 from bx.intervals.io import GenomicInterval, NiceReaderWrapper
13 from bx.intervals.io import * 13 from bx.intervals.operations.merge import merge
14 from bx.intervals.operations.merge import *
15 from bx.cookbook import doc_optparse 14 from bx.cookbook import doc_optparse
16 from galaxy.tools.util.galaxyops import * 15 from bx.tabular.io import ParseError
16 from galaxy.tools.util.galaxyops import fail, parse_cols_arg, skipped
17 17
18 assert sys.version_info[:2] >= ( 2, 4 ) 18 assert sys.version_info[:2] >= ( 2, 4 )
19 19
20
20 def main(): 21 def main():
21 mincols = 1 22 mincols = 1
22 upstream_pad = 0
23 downstream_pad = 0
24 23
25 options, args = doc_optparse.parse( __doc__ ) 24 options, args = doc_optparse.parse( __doc__ )
26 try: 25 try:
27 chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg( options.cols1 ) 26 chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg( options.cols1 )
28 if options.mincols: mincols = int( options.mincols ) 27 if options.mincols:
28 mincols = int( options.mincols )
29 in_fname, out_fname = args 29 in_fname, out_fname = args
30 except: 30 except:
31 doc_optparse.exception() 31 doc_optparse.exception()
32 32
33 g1 = NiceReaderWrapper( fileinput.FileInput( in_fname ), 33 g1 = NiceReaderWrapper( fileinput.FileInput( in_fname ),
34 chrom_col=chr_col_1, 34 chrom_col=chr_col_1,
35 start_col=start_col_1, 35 start_col=start_col_1,
36 end_col=end_col_1, 36 end_col=end_col_1,
37 strand_col = strand_col_1, 37 strand_col=strand_col_1,
38 fix_strand=True ) 38 fix_strand=True )
39 39
40 out_file = open( out_fname, "w" ) 40 out_file = open( out_fname, "w" )
41 41
42 try: 42 try:
43 for line in merge(g1,mincols=mincols): 43 for line in merge(g1, mincols=mincols):
44 if options.threecol: 44 if options.threecol:
45 if type( line ) is GenomicInterval: 45 if type( line ) is GenomicInterval:
46 out_file.write( "%s\t%s\t%s\n" % ( line.chrom, str( line.startCol ), str( line.endCol ) ) ) 46 out_file.write( "%s\t%s\t%s\n" % ( line.chrom, str( line.startCol ), str( line.endCol ) ) )
47 elif type( line ) is list: 47 elif type( line ) is list:
48 out_file.write( "%s\t%s\t%s\n" % ( line[chr_col_1], str( line[start_col_1] ), str( line[end_col_1] ) ) ) 48 out_file.write( "%s\t%s\t%s\n" % ( line[chr_col_1], str( line[start_col_1] ), str( line[end_col_1] ) ) )