UpdateKrakenDatabases.py 文件源码

def get_fasta_in_kraken_format(outfile_fasta='sequences.fa'):
    output=open(outfile_fasta,'w')
    for file_name in os.listdir(cwd):
        if file_name.endswith('.gbff'):
            records = SeqIO.parse(file_name, "genbank")
            for seq_record in records:
                seq_id=seq_record.id
                seq=seq_record.seq
                for feature in seq_record.features:
                    if 'source' in feature.type:
                        print(feature.qualifiers)
                        taxid=''.join(feature.qualifiers['db_xref'])
                        taxid=re.sub(r'.*taxon:','kraken:taxid|',taxid)
                        print(''.join(taxid))                        
                        outseq=">"+seq_id+"|"+taxid+"\n"+str(seq)+"\n"
                output.write(outseq)
            os.remove(file_name) 
    output.close()  
    return