view gops_merge.py @ 4:381cd27bf67a draft

planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tool_collections/gops/merge commit cae3e05d02e60f595bb8b6d77a84f030e9bd1689
author devteam
date Thu, 22 Jun 2017 18:52:49 -0400
parents 0926c81f382c
children
line wrap: on
line source

#!/usr/bin/env python
"""
Merge overlapping regions.

usage: %prog in_file out_file
    -1, --cols1=N,N,N,N: Columns for start, end, strand in first file
    -m, --mincols=N: Require this much overlap (default 1bp)
    -3, --threecol: Output 3 column bed
"""
from __future__ import print_function

import fileinput
import sys

from bx.cookbook import doc_optparse
from bx.intervals.io import GenomicInterval, NiceReaderWrapper
from bx.intervals.operations.merge import merge
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():
    mincols = 1

    options, args = doc_optparse.parse( __doc__ )
    try:
        chr_col_1, start_col_1, end_col_1, strand_col_1 = parse_cols_arg( options.cols1 )
        if options.mincols:
            mincols = int( options.mincols )
        in_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 )

    out_file = open( out_fname, "w" )

    try:
        for line in merge(g1, mincols=mincols):
            if options.threecol:
                if type( line ) is GenomicInterval:
                    out_file.write( "%s\t%s\t%s\n" % ( line.chrom, str( line.startCol ), str( line.endCol ) ) )
                elif type( line ) is list:
                    out_file.write( "%s\t%s\t%s\n" % ( line[chr_col_1], str( line[start_col_1] ), str( line[end_col_1] ) ) )
                else:
                    out_file.write( "%s\n" % line )
            else:
                if type( line ) is GenomicInterval:
                    out_file.write( "%s\n" % "\t".join( line.fields ) )
                elif type( line ) is list:
                    out_file.write( "%s\n" % "\t".join( line ) )
                else:
                    out_file.write( "%s\n" % line )
    except ParseError as 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 __name__ == "__main__":
    main()