python 中实现将fasta文件的碱基序列以小写字母的形式输出

 

001、

root@PC1:/home/test# ls
a.fasta  test.py
root@PC1:/home/test# 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.lower())

for i,j in dict1.items():
    print(i)
    j = "".join(j)
    for k in range(0, len(j), 5):
        print(j[k:k+5])
in_file.close()
root@PC1:/home/test# cat a.fasta                            ## 测试fasta文件
>gene1 myc
AGCTGCCTAAGC
GGCATAGCTAATCG
>gene2 jun
ACCGAATCGGAGCGATG
GGCATTAAAGATCTAGCT
>gene3 malat1
AGGCTAGCGAG
GCGCGAG
GATTAGGCG
root@PC1:/home/test# python test.py                         ## 执行程序
>gene1 myc
agctg
cctaa
gcggc
atagc
taatc
g
>gene2 jun
accga
atcgg
agcga
tgggc
attaa
agatc
tagct
>gene3 malat1
aggct
agcga
ggcgc
gagga
ttagg
cg

参考：https://www.jianshu.com/p/5ee54bea4cb0