Roll a FASTA file of a circular sequence, changing the starting base of the FASTA sequence

roll_fasta.py

#!/usr/bin/python
# Roll a FASTA file of a circular sequence, changing the starting base of the FASTA sequence to new_startN

from Bio import SeqIO
from Bio.Seq import Seq
from Bio.SeqRecord import SeqRecord

import sys
import os

def roll_fasta(fasta_file, new_startN):
    '''
    roll fasta of circular genome so that new_startN is new start of sequence
    '''
    python_new_startN = new_startN - 1 # change to python index

    SeqRecordObj = SeqIO.read(fasta_file, "fasta") # load fasta

    # Create new record
    new_first_part_fasta = SeqRecordObj.seq[python_new_startN : ]
    new_last_part_fasta = SeqRecordObj.seq[: python_new_startN]
    rolled_sequence = new_first_part_fasta + new_last_part_fasta
    record = SeqRecord(rolled_sequence, '_'.join([SeqRecordObj.id , 'rolled', str(new_startN)]),'','')

    # Create output file name
    (dirName, fileName) = os.path.split(fasta_file)
    (fileBaseName, fileExtension)=os.path.splitext(fileName)
    output_fileName = '_'.join([fileBaseName, 'rolled', str(new_startN)]) + fileExtension
    output_file = os.path.join(dirName, output_fileName)

    # Save new fasta
    output_handle = open(output_file , "w")
    SeqIO.write(record, output_handle, "fasta")
    output_handle.close()


def main(*argv):
    fasta_file = argv[1]
    new_startN = int(argv[2])
    roll_fasta(fasta_file, new_startN)

if __name__ == '__main__':
    sys.exit(main(*sys.argv))