1 | #!/usr/bin/python2.6 |
---|
2 | |
---|
3 | """ |
---|
4 | Find regions of first bed file that overlap regions in a second bed file. This |
---|
5 | program performs a base-by-base intersection, so only runs of bases that are |
---|
6 | covered in both of the inputs will be output. |
---|
7 | |
---|
8 | usage: %prog bed_file_1 bed_file_2 |
---|
9 | """ |
---|
10 | |
---|
11 | import sys |
---|
12 | from warnings import warn |
---|
13 | from bx.bitset import * |
---|
14 | from bx.bitset_builders import * |
---|
15 | from bx.cookbook import doc_optparse |
---|
16 | |
---|
17 | options, args = doc_optparse.parse( __doc__ ) |
---|
18 | try: |
---|
19 | in_fname, in2_fname = args |
---|
20 | except: |
---|
21 | doc_optparse.exit() |
---|
22 | |
---|
23 | bits1 = binned_bitsets_from_file( open( in_fname ) ) |
---|
24 | bits2 = binned_bitsets_from_file( open( in2_fname ) ) |
---|
25 | |
---|
26 | bitsets = dict() |
---|
27 | |
---|
28 | for key in bits1: |
---|
29 | if key in bits2: |
---|
30 | bits1[key].iand( bits2[key] ) |
---|
31 | bitsets[key] = bits1[key] |
---|
32 | |
---|
33 | for chrom in bitsets: |
---|
34 | bits = bitsets[chrom] |
---|
35 | end = 0 |
---|
36 | while 1: |
---|
37 | start = bits.next_set( end ) |
---|
38 | if start == bits.size: break |
---|
39 | end = bits.next_clear( start ) |
---|
40 | print "%s\t%d\t%d" % ( chrom, start, end ) |
---|