python 中根据给出的scafflod名称从fasta文件中提取指定的序列

 

001、

root@PC1:/home/test2# ls
a.fasta  scaffold.txt  test.py
root@PC1:/home/test2# cat a.fasta              ## 测试fasta文件
>gene2 myc
AGCTGCCTAAGC
GGCATAGCTAATCG
>gene1 jun
ACCGAATCGGAGCGATG
GGCATTAAAGATCTAGCT
>gene4 malat1
AGGCTAGCGAG
GCGCGAG
GATTAGGCG
>gene3 jun
ACCGAATCGG
GGCATTAAAGATCTAGCT
root@PC1:/home/test2# cat scaffold.txt          ## 给定的scaffold名称
>gene6 yyy
>gene2 myc
>gene4 malat1
>gene8 xxx
root@PC1:/home/test2# cat test.py               ## 测试程序
#!/usr/bin/python
in_file = open("a.fasta", "r")
dict1 = dict()

for i in in_file:
    i = i.strip()
    if i[0] == ">":
        key = i
        dict1[key] = []
    else:
        dict1[key].append(i)
scaffold = open("scaffold.txt", "r")
lines = scaffold.readlines()
for i in dict1.keys():
    if (i+"\n") in lines:
        print(i)
        for j in dict1[i]:
            print(j)

in_file.close()
root@PC1:/home/test2# python test.py           ## 提取结果
>gene2 myc
AGCTGCCTAAGC
GGCATAGCTAATCG
>gene4 malat1
AGGCTAGCGAG
GCGCGAG
GATTAGGCG

 

参考：https://www.jianshu.com/p/403a23fdd7bb