biopython：基因genbank格式转核酸或氨基酸fasta格式

genbank to fasta 核酸

from Bio import SeqIO
gbk_filename = "c00079_GUT_GEN...region001.gbk"
faa_filename = "c00079_GUT_GEN...region001.fna"
input_handle  = open(gbk_filename, "r")
output_handle = open(faa_filename, "w")

for seq_record in SeqIO.parse(input_handle, "genbank") :
    print("Dealing with GenBank record %s" % seq_record.id)
    output_handle.write(">%s %s\n%s\n" % (
           seq_record.id,
           seq_record.description,
           seq_record.seq))

output_handle.close()
input_handle.close()

genbank to fasta 氨基酸

from Bio import SeqIO
gbk_filename = "NC_005213.gbk"
faa_filename = "NC_005213_converted.faa"
input_handle  = open(gbk_filename, "r")
output_handle = open(faa_filename, "w")

for seq_record in SeqIO.parse(input_handle, "genbank") :
    print("Dealing with GenBank record %s" % seq_record.id)
    for seq_feature in seq_record.features :
        if seq_feature.type=="CDS" :
            assert len(seq_feature.qualifiers['translation'])==1
            output_handle.write(">%s from %s\n%s\n" % (
                   seq_feature.qualifiers['locus_tag'][0],
                   seq_record.name,
                   seq_feature.qualifiers['translation'][0]))

output_handle.close()
input_handle.close()

参考官方手册