def test_load_tab(self):
result = load_annotations(self.tab, warn=print)
self.assertEqual(12, len(result.keys()))
domains = []
for gene in result['12']:
for t in gene.spliced_transcripts:
print(t)
if t.unspliced_transcript.name == 'ENST00000550458':
tl = t.translations[0]
domains = tl.domains
break
if domains:
break
for d in domains:
print(d.name, d.regions)
self.assertEqual(2, len(domains))
result = load_annotations(REFERENCE_ANNOTATIONS_FILE, warn=print)
self.assertEqual(1, len(result.keys()))
def test_load_tab(self):
result = load_annotations(self.tab, warn=print)
self.assertEqual(12, len(result.keys()))
domains = []
for gene in result['12']:
for t in gene.spliced_transcripts:
print(t)
if t.unspliced_transcript.name == 'ENST00000550458':
tl = t.translations[0]
domains = tl.domains
break
if domains:
break
for d in domains:
print(d.name, d.regions)
self.assertEqual(2, len(domains))
result = load_annotations(get_data('mock_reference_annotations.tsv'),
warn=print)
self.assertEqual(1, len(result.keys()))
def set_example_genes():
result = {}
genes = load_annotations(os.path.join(DATA_DIR, 'example_genes.json'))
seqs = load_reference_genome(os.path.join(DATA_DIR, 'example_genes.fa'))
for chr_genes in genes.values():
for gene in chr_genes:
if gene.name in seqs:
gene.seq = str(seqs[gene.name].seq)
result[gene.name] = gene
if gene.aliases:
for alias in gene.aliases:
result[alias] = gene
print(result.keys())
return result
def test_trans_bam_stats(self):
bamfh = BamCache(get_data('mock_trans_reads_for_events.sorted.bam'))
annotations = load_annotations(get_data('mock_annotations.json'))
stats = compute_transcriptome_bam_stats(
bamfh,
annotations,
100,
min_mapping_quality=1,
stranded=True,
sample_cap=10000,
distribution_fraction=0.99,
)
assert abs(stats.median_fragment_size - 185) < 5
assert stats.read_length == 75
assert stats.stdev_fragment_size < 50
bamfh.close()
def test_load_json(self):
result = load_annotations(self.json, warn=print)
self.assertEqual(12, len(result.keys()))
def test_tab_equivalent_to_json(self):
tab_result = load_annotations(self.tab, warn=print)
json_result = load_annotations(self.json, warn=print)
self.assertEqual(sorted(tab_result.keys()), sorted(json_result.keys()))
def test_min_genes_error(annotations, error_message_include, tmp_path):
filename = tmp_path / "annotations.json"
filename.write_text(json.dumps(annotations))
with pytest.raises(AssertionError) as exc:
load_annotations(str(filename))
assert error_message_include in str(exc.value)
def test_load_json(self):
result = load_annotations(JSON)
assert len(result.keys()) == 12