def _write_proteins(self, proteins, protein_path):
records = []
for feature in proteins:
translation = feature.extract(self.record.seq).translate()
records.append(
SeqRecord(translation,
util.get_protein_id(feature),
description=''))
SeqIO.write(records, protein_path, 'fasta')
def _write_proteins(self, proteins, protein_path):
records = []
for feature in proteins:
translation_str = feature.qualifiers.get('translation', [None])[0]
if translation_str:
translation = Seq(translation_str)
else:
translation = feature.extract(self.record.seq).translate()
records.append(
SeqRecord(translation,
util.get_protein_id(feature),
description=''))
SeqIO.write(records, protein_path, 'fasta')
def test_integration_prepare_default(tmpdir):
tmpdir = str(tmpdir)
outgbk = os.path.join(tmpdir, 'outfile.gbk')
outtsv = os.path.join(tmpdir, 'outfile.tsv')
run([
'prepare', '--output-gbk', outgbk, '--output-tsv', outtsv,
get_test_file('BGC0000015.fa')
])
records = list(SeqIO.parse(outgbk, 'genbank'))
assert len(records) == 2
record = records[0]
assert_sorted_features(record)
proteins = util.get_protein_features(record)
pfams = util.get_pfam_features(record)
assert len(proteins) == 18
print([util.get_protein_id(f) for f in proteins])
assert len(pfams) == 111
record = records[1]
assert_sorted_features(record)
proteins = util.get_protein_features(record)
pfams = util.get_pfam_features(record)
assert len(proteins) == 27
assert len(pfams) == 36
domains = pd.read_csv(outtsv, sep='\t')
records = domains.groupby('sequence_id')
assert len(records) == 2
record = records.get_group('BGC0000015.1')
print(record['protein_id'].unique())
# some of the proteins do not have any Pfam domains so they are not present
assert len(record['protein_id'].unique()) == 17
assert len(record) == 111
record = records.get_group('BGC0000015.2')
# some of the proteins do not have any Pfam domains so they are not present
assert len(record['protein_id'].unique()) == 11
assert len(record) == 36