comparison fromgtfTobed12.py @ 1:6fd4b3b90220 draft default tip

planemo upload for repository https://github.com/lldelisle/tools-lldelisle/tree/master/tools/fromgtfTobed12 commit 15b8c2cc83708044413a152322bcbfca8a74d29a

0:418e4d0fe0bd

                        "feature in your GTF file. You may want to use the "
                        "`disable_infer_transcripts=True` option to speed up "
                        "database creation")


def convert_gtf_to_bed(fn, fo, useGene, mergeTranscripts,
                       mergeTranscriptsAndOverlappingExons, ucsc):
    db = gffutils.create_db(fn, ':memory:')
    # For each transcript:
    prefered_name = "transcript_name"
    if useGene or mergeTranscripts or mergeTranscriptsAndOverlappingExons:
        prefered_name = "gene_name"
    if mergeTranscripts or mergeTranscriptsAndOverlappingExons:
        all_items = db.features_of_type("gene", order_by='start')
    else:
        all_items = db.features_of_type("transcript", order_by='start')
    for tr in all_items:

argp.add_argument('input', default=None,
                  help="Input gtf file (can be gzip).")
argp.add_argument('--output', default=sys.stdout,
                  type=argparse.FileType('w'),
                  help="Output bed12 file.")
argp.add_argument('--useGene', action="store_true",
                  help="Use the gene name instead of the "
                       "transcript name.")
argp.add_argument('--ucscformat', action="store_true",
                  help="If you want that all chromosome names "
                       "begin with 'chr'.")
group = argp.add_mutually_exclusive_group()
group.add_argument('--mergeTranscripts', action="store_true",
                   help="Merge all transcripts into a single "
                        "entry to have one line per gene.")
group.add_argument('--mergeTranscriptsAndOverlappingExons',

                   help="Merge all transcripts into a single "
                        "entry to have one line per gene and merge"
                        " overlapping exons.")

args = argp.parse_args()
convert_gtf_to_bed(args.input, args.output, args.useGene,
                   args.mergeTranscripts,
                   args.mergeTranscriptsAndOverlappingExons,
                   args.ucscformat)

1:6fd4b3b90220

                        "feature in your GTF file. You may want to use the "
                        "`disable_infer_transcripts=True` option to speed up "
                        "database creation")


def convert_gtf_to_bed(fn, fo, preferedName, mergeTranscripts,
                       mergeTranscriptsAndOverlappingExons, ucsc):
    db = gffutils.create_db(fn, ':memory:')
    # For each transcript:
    if preferedName is not None:
        prefered_name = preferedName
    elif mergeTranscripts or mergeTranscriptsAndOverlappingExons:
        prefered_name = "gene_name"
    else:
        prefered_name = "transcript_name"
    if mergeTranscripts or mergeTranscriptsAndOverlappingExons:
        all_items = db.features_of_type("gene", order_by='start')
    else:
        all_items = db.features_of_type("transcript", order_by='start')
    for tr in all_items:

argp.add_argument('input', default=None,
                  help="Input gtf file (can be gzip).")
argp.add_argument('--output', default=sys.stdout,
                  type=argparse.FileType('w'),
                  help="Output bed12 file.")
argp.add_argument('--ucscformat', action="store_true",
                  help="If you want that all chromosome names "
                       "begin with 'chr'.")
argp.add_argument('--preferedName', default=None,
                  help="Name to use for bed output.")
group = argp.add_mutually_exclusive_group()
group.add_argument('--mergeTranscripts', action="store_true",
                   help="Merge all transcripts into a single "
                        "entry to have one line per gene.")
group.add_argument('--mergeTranscriptsAndOverlappingExons',

                   help="Merge all transcripts into a single "
                        "entry to have one line per gene and merge"
                        " overlapping exons.")

args = argp.parse_args()
convert_gtf_to_bed(args.input, args.output, args.preferedName,
                   args.mergeTranscripts,
                   args.mergeTranscriptsAndOverlappingExons,
                   args.ucscformat)