[2] | 1 | #!/usr/bin/env python |
---|
| 2 | """ |
---|
| 3 | Merge overlaping regions. |
---|
| 4 | |
---|
| 5 | usage: %prog in_file out_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) |
---|
| 8 | -3, --threecol: Output 3 column bed |
---|
| 9 | """ |
---|
| 10 | from galaxy import eggs |
---|
| 11 | import pkg_resources |
---|
| 12 | pkg_resources.require( "bx-python" ) |
---|
| 13 | import sys, traceback, fileinput |
---|
| 14 | from warnings import warn |
---|
| 15 | from bx.intervals import * |
---|
| 16 | from bx.intervals.io import * |
---|
| 17 | from bx.intervals.operations.merge import * |
---|
| 18 | from bx.cookbook import doc_optparse |
---|
| 19 | from galaxy.tools.util.galaxyops import * |
---|
| 20 | |
---|
| 21 | assert sys.version_info[:2] >= ( 2, 4 ) |
---|
| 22 | |
---|
| 23 | def main(): |
---|
| 24 | mincols = 1 |
---|
| 25 | upstream_pad = 0 |
---|
| 26 | downstream_pad = 0 |
---|
| 27 | |
---|
| 28 | options, args = doc_optparse.parse( __doc__ ) |
---|
| 29 | try: |
---|
| 30 | chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg( options.cols1 ) |
---|
| 31 | if options.mincols: mincols = int( options.mincols ) |
---|
| 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 | out_file = open( out_fname, "w" ) |
---|
| 44 | |
---|
| 45 | try: |
---|
| 46 | for line in merge(g1,mincols=mincols): |
---|
| 47 | if options.threecol: |
---|
| 48 | if type( line ) is GenomicInterval: |
---|
| 49 | out_file.write( "%s\t%s\t%s\n" % ( line.chrom, str( line.startCol ), str( line.endCol ) ) ) |
---|
| 50 | elif type( line ) is list: |
---|
| 51 | out_file.write( "%s\t%s\t%s\n" % ( line[chr_col_1], str( line[start_col_1] ), str( line[end_col_1] ) ) ) |
---|
| 52 | else: |
---|
| 53 | out_file.write( "%s\n" % line ) |
---|
| 54 | else: |
---|
| 55 | if type( line ) is GenomicInterval: |
---|
| 56 | out_file.write( "%s\n" % "\t".join( line.fields ) ) |
---|
| 57 | elif type( line ) is list: |
---|
| 58 | out_file.write( "%s\n" % "\t".join( line ) ) |
---|
| 59 | else: |
---|
| 60 | out_file.write( "%s\n" % line ) |
---|
| 61 | except ParseError, exc: |
---|
| 62 | out_file.close() |
---|
| 63 | fail( "Invalid file format: %s" % str( exc ) ) |
---|
| 64 | |
---|
| 65 | out_file.close() |
---|
| 66 | |
---|
| 67 | if g1.skipped > 0: |
---|
| 68 | print skipped( g1, filedesc=" of 1st dataset" ) |
---|
| 69 | |
---|
| 70 | if __name__ == "__main__": |
---|
| 71 | main() |
---|