def test_unit_train_classify(tmpdir):
tmpdir = str(tmpdir)
out_path = os.path.join(tmpdir, 'model.pkl')
run([
'train', '--model',
get_test_file('random_forest_test.json'), '--classes',
get_test_file('BGC0000015.classes.csv'), '--output', out_path,
get_test_file('BGC0000015.pfam.csv')
])
assert os.path.exists(out_path)
model = SequenceModelWrapper.load(out_path)
domains = pd.read_csv(get_test_file('BGC0000015.pfam.csv'))
classes = model.predict(
[sample for _, sample in domains.groupby('sequence_id')])
assert isinstance(classes, pd.DataFrame)
assert list(classes.columns) == ['class1', 'class2', 'class3', 'class4']
assert len(classes.index) == 2
assert list(classes.iloc[0] > 0.5) == [True, False, True, False]
assert list(classes.iloc[1] > 0.5) == [False, True, False, True]
def test_unit_train_detect(model, tmpdir):
tmpdir = str(tmpdir)
out_path = os.path.join(tmpdir, 'model.pkl')
run([
'train', '--model',
get_test_file(model), '--config', 'PFAM2VEC',
get_test_file('pfam2vec.test.tsv'), '--output', out_path,
get_test_file('BGC0000015.pfam.csv'),
get_test_file('negative.pfam.csv')
])
assert os.path.exists(out_path)
model = SequenceModelWrapper.load(out_path)
pos_domains = pd.read_csv(get_test_file('BGC0000015.pfam.csv'))
neg_domains = pd.read_csv(get_test_file('negative.pfam.csv'))
pos_prediction = model.predict(pos_domains)
neg_prediction = model.predict(neg_domains)
assert isinstance(pos_prediction, pd.Series)
assert isinstance(neg_prediction, pd.Series)
assert pos_prediction.index.equals(pos_domains.index)
assert neg_prediction.index.equals(neg_domains.index)
assert pos_prediction.mean() > 0.5
assert neg_prediction.mean() < 0.5
def test_integration_train_detect_fail_fasta():
# Should fail due to unprocessed input sequence
with pytest.raises(NotImplementedError):
run([
'train', '--model',
get_test_file('clusterfinder_geneborder_test.json'), '--output',
'bar.pkl',
get_test_file('BGC0000015.fa')
])
def test_integration_pipeline_labelled(tmpdir):
tmpdir = str(tmpdir)
report_dir = os.path.join(tmpdir, 'report')
run(['pipeline', '--output', report_dir, get_test_file('labelled.gbk')])
evaluation_dir = os.path.join(report_dir, 'evaluation')
files = os.listdir(evaluation_dir)
for file in files:
print(file)
assert 'report.bgc.png' in files
assert 'report.score.png' in files
assert 'report.roc.png' in files
assert 'report.pr.png' in files
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
def test_integration_pipeline_default(tmpdir, input_file):
tmpdir = str(tmpdir)
report_dir = os.path.join(tmpdir, 'report')
run(['pipeline', '--output', report_dir, get_test_file(input_file)])
files = os.listdir(report_dir)
for file in files:
print(file)
assert 'README.txt' in files
assert 'report.bgc.gbk' in files
assert 'report.bgc.tsv' in files
assert 'report.full.gbk' in files
assert 'report.pfam.tsv' in files
evaluation_dir = os.path.join(report_dir, 'evaluation')
files = os.listdir(evaluation_dir)
for file in files:
print(file)
assert 'report.bgc.png' in files
assert 'report.score.png' in files
records = list(
SeqIO.parse(os.path.join(report_dir, 'report.full.gbk'), 'genbank'))
assert len(records) == 2
record = records[0]
cluster_features = util.get_cluster_features(record)
assert len(cluster_features) >= 1
record = records[1]
cluster_features = util.get_cluster_features(record)
assert len(cluster_features) >= 1
cluster_records = list(
SeqIO.parse(os.path.join(report_dir, 'report.bgc.gbk'), 'genbank'))
assert len(cluster_records) >= 2
def test_unit_pipeline_default(tmpdir, mocker):
tmpdir = str(tmpdir)
mocker.patch('os.mkdir')
mocker.patch('deepbgc.command.pipeline.logging.FileHandler')
mock_seqio = mocker.patch(
'deepbgc.command.pipeline.deepbgc.util.SequenceParser')
record1 = SeqRecord('ABC')
record2 = SeqRecord('DEF')
mock_seqio_instance = mock_seqio.return_value
mock_seqio_instance.__enter__.return_value = mock_seqio_instance
mock_seqio_instance.parse.return_value = [record1, record2]
mock_annotator = mocker.patch('deepbgc.command.pipeline.DeepBGCAnnotator')
mock_classifier = mocker.patch(
'deepbgc.command.pipeline.DeepBGCClassifier')
mock_detector = mocker.patch('deepbgc.command.pipeline.DeepBGCDetector')
writer_paths = [
'deepbgc.command.pipeline.BGCRegionPlotWriter',
'deepbgc.command.pipeline.ClusterTSVWriter',
'deepbgc.command.pipeline.PfamScorePlotWriter',
'deepbgc.command.pipeline.PfamTSVWriter',
'deepbgc.command.pipeline.GenbankWriter',
'deepbgc.command.pipeline.BGCGenbankWriter',
'deepbgc.command.pipeline.ReadmeWriter'
# Note: We are mocking classes imported in deepbgc.command.pipeline, not at their original location!
]
writers = [mocker.patch(path) for path in writer_paths]
report_dir = os.path.join(tmpdir, 'report')
report_tmp_dir = os.path.join(report_dir, 'tmp')
run([
'pipeline', '--output', report_dir, '--detector', 'mydetector',
'--label', 'mylabel', '--score', '0.1', '--merge-max-protein-gap', '8',
'--merge-max-nucl-gap', '9', '--min-nucl', '10', '--min-proteins',
'20', '--min-domains', '30', '--min-bio-domains', '40', '--classifier',
'myclassifier1', '--classifier', 'myclassifier2', '--classifier-score',
'0.2', 'mySequence.gbk'
])
# Remove logging handlers to avoid affecting other tests
logger = logging.getLogger('')
for handler in logger.handlers[:]:
logger.removeHandler(handler)
os.mkdir.assert_any_call(report_dir)
os.mkdir.assert_any_call(report_tmp_dir)
mock_annotator.assert_called_with(tmp_dir_path=report_tmp_dir,
prodigal_meta_mode=False)
mock_classifier.assert_any_call(classifier='myclassifier1',
score_threshold=0.2)
mock_classifier.assert_any_call(classifier='myclassifier2',
score_threshold=0.2)
mock_detector.assert_called_with(detector='mydetector',
label='mylabel',
score_threshold=0.1,
merge_max_protein_gap=8,
merge_max_nucl_gap=9,
min_nucl=10,
min_proteins=20,
min_domains=30,
min_bio_domains=40)
assert mock_annotator.return_value.run.call_count == 2 # Two records
assert mock_detector.return_value.run.call_count == 2 # Two records
assert mock_classifier.return_value.run.call_count == 4 # Two records for each of the two classifiers
mock_annotator.return_value.print_summary.assert_called_once_with()
mock_detector.return_value.print_summary.assert_called_once_with()
assert mock_classifier.return_value.print_summary.call_count == 2 # For each of the two classifiers
for writer in writers:
assert writer.return_value.write.call_count == 2 # Two records
writer.return_value.close.assert_called_once_with()
def test_unit_main_help():
with pytest.raises(SystemExit) as excinfo:
run(['--help'])
assert excinfo.value.code == 0
def test_unit_main_invalid_command():
with pytest.raises(SystemExit) as excinfo:
run(['invalid'])
assert excinfo.value.code == 2
def test_unit_prepare_help():
with pytest.raises(SystemExit) as excinfo:
run(['prepare', '--help'])
assert excinfo.value.code == 0