从fasta文件中提取特定基因序列

# !usr/bin/env python3
# -*- coding:utf-8 -*-
"""
@FileName: 20220220测试
@Time: 2022/2/21,12:00
@NAME: zhang yixing
"""
import argparse


def get_gen(filename, id=None, genid_txt=None):
    id_gen_dict = {}
    with open(filename, 'r') as f:
        for line in f:
            if line.startswith('>'):
                name = line.split()[0]
                id_gen_dict[name] = ''
            else:
                id_gen_dict[name] += line.rstrip()
    if genid_txt==None:
        print(genid_txt==None)
        t = id_gen_dict.get(id,'no found')
        if t == 'no found':
            print('no found')
        else:
            with open('./gen.txt', 'w') as g:
                g.write(id)
                g.write('\n')
                g.write(t)
    else:
        with open(genid_txt, 'r') as id_txt:
            res_dict = {}
            for line in id_txt:
                if id_gen_dict.get(line.strip(),'no found') == 'no found':
                    res_dict[line.strip()] = 'no found'
                else:
                    res_dict[line.strip()] = id_gen_dict[line.strip()]
        with open('./gen.txt', 'w') as g:
            for key, value in res_dict.items():
                g.write(key)
                g.write('\n')
                g.write(value+'\n')


def main():
    parser = argparse.ArgumentParser(usage='程序用法非常简单,出现问题可以评论我', description='从fasta格式中根据基因名字提取基因序列并且生成gen.txt文件')
    parser.add_argument("-i", "--input", help="input filename")  # 输入的基因fasta文件
    parser.add_argument("-g", "--genid",help="gen id")  # 基因ID
    parser.add_argument("-t", "--genid_txt", help="a lot of id in genid.txt")  # TXT文件中有需要的从fasta文件中提取的一批基因ID
    args = parser.parse_args()
    if args.genid:
        get_gen(args.input, args.genid)
        print(args.input, args.genid)
    elif args.genid_txt:
        get_gen(args.input, None, genid_txt=args.genid_txt)
        print(args.input, args.genid_txt)

        # print(args.input, args.genid)


if __name__ == '__main__':
    main()

image.png

用法1

python get_gen.py -i cand.cds -g '>HHKEBNDL_00001'

image.png

用法2

python get_gen.py -i cand.fa -t genid.txt 

以上两种，结果都储存在gen.txt中

image.png

对于没找的基因序列，在基因名字下面用 no found 代替