python实现根据序列ID从fasta文件中删除指定的序列

 

001、

[root@pc1 test1]# ls
a.fa  rm.list  test.py
[root@pc1 test1]# cat a.fa                  ## 测试fasta
>chr1
tttcccggg
>chr2
tttgggjjj
cccjjjjjj
>chr3
ccc
>chr4
aaaaatt
[root@pc1 test1]# cat rm.list                ## 删除列表
chr2
chr4
[root@pc1 test1]# cat test.py                ## 删除程序
#!/usr/bin/env python3
# -*- coding: utf-8 -*-

rm_list = []
with open("rm.list", "r") as in_put1:
        for i in in_put1.readlines():
                rm_list.append(i.strip("\n"))
        in_put1.close()

with open("a.fa", "r") as in_put2:
        for i in in_put2:
                if i[0] == ">":
                        for j in rm_list:
                                if j in i:
                                        out = False
                                        break
                                else:
                                        out = True
                if out:
                        print(i.strip())
        in_put2.close()

 

 

[root@pc1 test1]# cat rm.list
chr2
chr4
[root@pc1 test1]# python3 test.py        ## 处理结果
>chr1
tttcccggg
>chr3
ccc

 。