格式转化 genbank to fasta

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()

https://github.com/combogenomics/regtools/blob/master/gbk2fna