view gops_coverage.py @ 2:bc9c66c1e9c9 draft

planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tool_collections/gops/coverage commit a1517c9d22029095120643bbe2c8fa53754dd2b7
author devteam
date Wed, 11 Nov 2015 12:48:05 -0500
parents 1e864693a1c0
children 4ef9819dc7fb
line wrap: on
line source

#!/usr/bin/env python
"""
Calculate coverage of one query on another, and append the coverage to
the last two columns as bases covered and percent coverage.

usage: %prog bed_file_1 bed_file_2 out_file
    -1, --cols1=N,N,N,N: Columns for start, end, strand in first file
    -2, --cols2=N,N,N,N: Columns for start, end, strand in second file
"""
import fileinput
import sys
from bx.intervals.io import GenomicInterval, NiceReaderWrapper
from bx.intervals.operations.coverage import coverage
from bx.cookbook import doc_optparse
from bx.tabular.io import ParseError
from galaxy.tools.util.galaxyops import fail, parse_cols_arg, skipped

assert sys.version_info[:2] >= ( 2, 4 )


def main():
    options, args = doc_optparse.parse( __doc__ )
    try:
        chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg( options.cols1 )
        chr_col_2, start_col_2, end_col_2, strand_col_2 = parse_cols_arg( options.cols2 )
        in_fname, in2_fname, out_fname = args
    except:
        doc_optparse.exception()

    g1 = NiceReaderWrapper( fileinput.FileInput( in_fname ),
                            chrom_col=chr_col_1,
                            start_col=start_col_1,
                            end_col=end_col_1,
                            strand_col=strand_col_1,
                            fix_strand=True )
    g2 = NiceReaderWrapper( fileinput.FileInput( in2_fname ),
                            chrom_col=chr_col_2,
                            start_col=start_col_2,
                            end_col=end_col_2,
                            strand_col=strand_col_2,
                            fix_strand=True )

    out_file = open( out_fname, "w" )

    try:
        for line in coverage( [g1, g2] ):
            if type( line ) is GenomicInterval:
                out_file.write( "%s\n" % "\t".join( line.fields ) )
            else:
                out_file.write( "%s\n" % line )
    except ParseError, exc:
        out_file.close()
        fail( "Invalid file format: %s" % str( exc ) )

    out_file.close()

    if g1.skipped > 0:
        print skipped( g1, filedesc=" of 1st dataset" )
    if g2.skipped > 0:
        print skipped( g2, filedesc=" of 2nd dataset" )

if __name__ == "__main__":
    main()