prep-genome.py 文件源码

def main(args):
    for record in SeqIO.parse(args.infile, 'fasta'):
        if args.discard:
            if sum([1 for rx in args.discard if re.match(rx, record.id)]) > 0:
                continue

        subseqcounter = 0
        printlog(args.debug, "DEBUG: convert to upper case", record.id)
        sequence = str(record.seq).upper()
        printlog(args.debug, "DEBUG: split seq by Ns", record.id)
        subseqs = [ss for ss in re.split('[^ACGT]+', sequence) if len(ss) > args.minlength]
        printlog(args.debug, "DEBUG: print subseqs", record.id)
        for subseq in subseqs:
            subseqcounter += 1
            subid = '{:s}_chunk_{:d}'.format(record.id, subseqcounter)
            subrecord = SeqRecord(Seq(subseq), subid, '', '')
            SeqIO.write(subrecord, args.outfile, 'fasta')