view @ 0:2b42545705fa draft

Uploaded Python Script
author curtisross
date Thu, 23 Sep 2021 16:24:09 +0000
line wrap: on
line source

#!/usr/bin/env python
import sys
import argparse
import logging
from Bio import SeqIO

log = logging.getLogger()

def drop_id(fasta_file=None):
    for rec in SeqIO.parse(fasta_file, "fasta"):
        rec.description = ""
        ind = str(rec.seq).find("##")
        if (
            ind != -1
        ):  # This method causes mid-file comments (such as from Apollo sequences) to be appended to the end of the previous sequence
            rec.seq = rec.seq[0:ind]
        yield rec

if __name__ == "__main__":
    parser = argparse.ArgumentParser(description="Identify shine-dalgarno sequences")
    parser.add_argument("fasta_file", type=argparse.FileType("r"), help="Genbank file")

    args = parser.parse_args()
    for rec in drop_id(**vars(args)):
        SeqIO.write([rec], sys.stdout, "fasta")