利用python将gbk格式转换为fasta &&

将gbk格式文件转换成fasta格式文件

flag=0
fasta = open ('/mnt/f/biopython/AY810830.fasta','w')
with open ('/mnt/f/biopython/AY810830.gbk','r') as f:
    for line in f:
        if line[0:9] =='ACCESSION':
            fasta.writelines('>'+line.split()[1]+'\n')
        elif line[0:6] =='ORIGIN':
            flag = 1
        elif flag == 1:
            s = line.split()
            if s != []:
                print(s)
                seq=''.join(s[1:])
                fasta.writelines(seq.upper()+'\n')
fasta.close()

将多个fasta序列中提取含有'Homo sapiens'的序列

fasta_file=open('multi.fasta','r')
out_file=open('human.fasta','w')
seq = ''
for line in fasta_file:
    if line[0]=='>' and seq =='':
        header = line
    elif line[0] != '>':
        seq=seq+line
    elif line[0] =='>' and seq !='':
        if "Homo sapiens" in header:
            out_file.write(header+seq)
        seq = ''
        header = line
if "Homo sapiens" in header :
    out_file.write(header+seq)
out_file.close()

请关注我的公众号----生信栈，不定期分享实用的生物信息干货！！！