把文件内容按照染色体分开写出

测试序列如下，text.txt:

chr2    43995310    43995986

chr17   49788603    49789067

chr17   59565573    59566163

chr19   8390308 8390745

chr12   49188033    49189033

chr7    974903  975570

chr7    98878532    98879500

chr7    44044672    44045322

chr1    153634052   153634772

chr11   60905850    60906575

 

直接看代码：

#encoding = utf-8

import sys
from collections import OrderedDict

 7 
def readfasta(filename):

    tmp_dict = OrderedDict()

    with open(filename) as f:

        for line in f:
            line = line.rstrip().split(' ',1)

            chr_id = line[0]

            if chr_id not in tmp_dict:
                tmp_dict[chr_id] = line[1]

            else:
                tmp_dict[chr_id] += line[1]

    return tmp_dict

def seperatefile(filename,outfile):

    data = readfasta(filename)

    for chr_id,features in data.items():
        import os
        (name,ext) = os.path.splitext(outfile)

        with open('%s_%s%s' %(name,chr_id,ext),'w') as f_out:
            f_out.write('%s\n' %chr_id)
            f_out.write('%s\n' %features)

seperatefile('test.txt','output.txt')

 推荐论坛：生信技能树，http://biotrainee.com/forum.php/