1 | #!/usr/bin/env python
|
---|
2 | #Dan Blankenberg
|
---|
3 |
|
---|
4 | import sys
|
---|
5 | from galaxy import eggs
|
---|
6 | import pkg_resources; pkg_resources.require( "bx-python" )
|
---|
7 | import bx.intervals.io
|
---|
8 |
|
---|
9 | assert sys.version_info[:2] >= ( 2, 4 )
|
---|
10 |
|
---|
11 | def stop_err( msg ):
|
---|
12 | sys.stderr.write( msg )
|
---|
13 | sys.exit()
|
---|
14 |
|
---|
15 | def __main__():
|
---|
16 | output_name = sys.argv[1]
|
---|
17 | input_name = sys.argv[2]
|
---|
18 | try:
|
---|
19 | chromCol = int( sys.argv[3] ) - 1
|
---|
20 | except:
|
---|
21 | stop_err( "'%s' is an invalid chrom column, correct the column settings before attempting to convert the data format." % str( sys.argv[3] ) )
|
---|
22 | try:
|
---|
23 | startCol = int( sys.argv[4] ) - 1
|
---|
24 | except:
|
---|
25 | stop_err( "'%s' is an invalid start column, correct the column settings before attempting to convert the data format." % str( sys.argv[4] ) )
|
---|
26 | try:
|
---|
27 | endCol = int( sys.argv[5] ) - 1
|
---|
28 | except:
|
---|
29 | stop_err( "'%s' is an invalid end column, correct the column settings before attempting to convert the data format." % str( sys.argv[5] ) )
|
---|
30 | try:
|
---|
31 | strandCol = int( sys.argv[6] ) - 1
|
---|
32 | except:
|
---|
33 | strandCol = -1
|
---|
34 | try:
|
---|
35 | nameCol = int( sys.argv[7] ) - 1
|
---|
36 | except:
|
---|
37 | nameCol = -1
|
---|
38 | skipped_lines = 0
|
---|
39 | first_skipped_line = 0
|
---|
40 | out = open( output_name,'w' )
|
---|
41 | count = 0
|
---|
42 | for count, region in enumerate( bx.intervals.io.NiceReaderWrapper( open( input_name, 'r' ), chrom_col=chromCol, start_col=startCol, end_col=endCol, strand_col=strandCol, fix_strand=True, return_header=False, return_comments=False ) ):
|
---|
43 | try:
|
---|
44 | if nameCol >= 0:
|
---|
45 | name = region.fields[nameCol]
|
---|
46 | else:
|
---|
47 | raise IndexError
|
---|
48 | except:
|
---|
49 | name = "region_%i" % count
|
---|
50 | try:
|
---|
51 |
|
---|
52 | out.write( "%s\t%i\t%i\t%s\t%i\t%s\n" % ( region.chrom, region.start, region.end, name, 0, region.strand ) )
|
---|
53 | except:
|
---|
54 | skipped_lines += 1
|
---|
55 | if not first_skipped_line:
|
---|
56 | first_skipped_line = count + 1
|
---|
57 | out.close()
|
---|
58 | print "%i regions converted to BED." % ( count + 1 - skipped_lines )
|
---|
59 | if skipped_lines > 0:
|
---|
60 | print "Skipped %d blank or invalid lines starting with line # %d." % ( skipped_lines, first_skipped_line )
|
---|
61 |
|
---|
62 | if __name__ == "__main__": __main__()
|
---|