将fasta格式参考基因组的每一条染色体都划分成一个一个等长的区

#!/usr/bin/env python
# coding=utf-8

import argparse

def get_parser():
    '''
    Using argpaser to parse the input parameters
    '''
    parser = argparse.ArgumentParser(description='Scattering genome sequence to bins with assigned length')
    parser.add_argument('-i', '--input', type=str, nargs=1,help='input the reference genome file with fasta format')
    parser.add_argument('-b', '--binsize', type=int, nargs=1, help='bin size')
    return parser


def binGenome(fasta, binsize):
    '''Bining the reference to segments head to end with equal length'''
    sequence = {}
    with open(fasta) as fa:
        for line in fa:
            if line.startswith(">"):
                ac = line.strip().split(">")[1]
                seq = ""
            else:
                seq += line.strip()
            sequence[ac] = seq

    for ac, seq in sequence.items():
        seqlen = len(seq)  
        for bin in range(0, seqlen, binsize):
            start, end = bin, bin + binsize
            if bin+binsize > seqlen:
                end = seqlen
            print(">%s_%d-%d"%(ac,start,end))
            print(seq[start:end])