BioCompass.py 文件源码

def cds_from_gbk(gb_file):
    gb_record = SeqIO.read(open(gb_file,"rU"), "genbank")

    #if strain_id is not None:
    #    gb_record.id = strain_id

    output = pd.DataFrame()
    sign = lambda x: '+' if x > 0 else '-'
    for feature in gb_record.features:
        if feature.type == "CDS":
            tmp = {}
            tmp = {'BGC': gb_record.id,
                    'locus_tag': feature.qualifiers['locus_tag'][0],
                    'start': feature.location.start.position,
                    'stop': feature.location.end.position,
                    'strand': sign(feature.location.strand) }
            if 'note' in feature.qualifiers:
                for note in feature.qualifiers['note']:
                    product = re.search( r"""smCOG: \s (?P<product>.*?) \s+ \(Score: \s* (?P<score>.*); \s* E-value: \s (?P<e_value>.*?)\);""", note, re.VERBOSE)
                    if product is not None:
                        product = product.groupdict()
                        product['score'] = float(product['score'])
                        product['e_value'] = float(product['e_value'])
                        for p in product:
                            tmp[p] = product[p]
            output = output.append(pd.Series(tmp), ignore_index=True)
    return output