utils.py 文件源码

def _parse_gff(file, file_name):
    records = []

    with open(file, "r") as infile:

        for i, rec in enumerate(GFF.parse(infile)):

            # Enumerates the contigs (can be chromosome, plasmid and unidentified)
            # based on total number of contigs (not type)
            rec_id = rec.id + "_" + str(i + 1)

            if len(rec_id) > 15:
                rec_id = "contig_" + "_" + str(i + 1)

            seq_record = SeqRecord(Seq(str(rec.seq), IUPAC.unambiguous_dna), id=rec_id,
                                   description=os.path.basename(file_name),
                                   features=rec.features)

            records.append(seq_record)

    return records