[2] | 1 | #!/usr/bin/env python |
---|
| 2 | import sys |
---|
| 3 | |
---|
| 4 | assert sys.version_info[:2] >= ( 2, 4 ) |
---|
| 5 | |
---|
| 6 | def __main__(): |
---|
| 7 | input_name = sys.argv[1] |
---|
| 8 | output_name = sys.argv[2] |
---|
| 9 | skipped_lines = 0 |
---|
| 10 | first_skipped_line = 0 |
---|
| 11 | out = open( output_name, 'w' ) |
---|
| 12 | i = 0 |
---|
| 13 | for i, line in enumerate( file( input_name ) ): |
---|
| 14 | line = line.rstrip( '\r\n' ) |
---|
| 15 | if line and not line.startswith( '#' ): |
---|
| 16 | try: |
---|
| 17 | elems = line.split( '\t' ) |
---|
| 18 | start = str( int( elems[3] ) - 1 ) |
---|
| 19 | strand = elems[6] |
---|
| 20 | if strand not in ['+', '-']: |
---|
| 21 | strand = '+' |
---|
| 22 | # GFF format: chrom source, name, chromStart, chromEnd, score, strand |
---|
| 23 | # Bed format: chrom, chromStart, chromEnd, name, score, strand |
---|
| 24 | # |
---|
| 25 | # Replace any spaces in the name with underscores so UCSC will not complain |
---|
| 26 | name = elems[2].replace(" ", "_") |
---|
| 27 | out.write( "%s\t%s\t%s\t%s\t0\t%s\n" %( elems[0], start, elems[4], name, strand ) ) |
---|
| 28 | except: |
---|
| 29 | skipped_lines += 1 |
---|
| 30 | if not first_skipped_line: |
---|
| 31 | first_skipped_line = i + 1 |
---|
| 32 | else: |
---|
| 33 | skipped_lines += 1 |
---|
| 34 | if not first_skipped_line: |
---|
| 35 | first_skipped_line = i + 1 |
---|
| 36 | out.close() |
---|
| 37 | info_msg = "%i lines converted to BED. " % ( i + 1 - skipped_lines ) |
---|
| 38 | if skipped_lines > 0: |
---|
| 39 | info_msg += "Skipped %d blank/comment/invalid lines starting with line #%d." %( skipped_lines, first_skipped_line ) |
---|
| 40 | print info_msg |
---|
| 41 | |
---|
| 42 | if __name__ == "__main__": __main__() |
---|