def test_custom_categories(self, graphkb_conn):
category = statement.categorize_relevance(
graphkb_conn, 'x', [('blargh', ['some', 'blargh'])])
assert category == ''
category = statement.categorize_relevance(
graphkb_conn, '1', [('blargh', ['some', 'blargh'])])
assert category == 'blargh'
def test_predisposition_category(self, graphkb_conn):
category = statement.categorize_relevance(graphkb_conn, '8')
assert category == 'cancer predisposition'
def test_no_match(self, graphkb_conn):
category = statement.categorize_relevance(graphkb_conn, 'x')
assert category == ''
def test_third_category(self, graphkb_conn):
category = statement.categorize_relevance(graphkb_conn, '4')
assert category == 'prognostic'
def test_fifth_category(self, graphkb_conn):
category = statement.categorize_relevance(graphkb_conn, '6')
assert category == 'pharmacogenomic'
def test_second_category(self, graphkb_conn):
category = statement.categorize_relevance(graphkb_conn, '3')
assert category == 'diagnostic'
def test_first_match_returns(self, graphkb_conn):
category = statement.categorize_relevance(graphkb_conn, '2')
assert category == 'therapeutic'
def test_default_categories(self, graphkb_conn):
category = statement.categorize_relevance(graphkb_conn, '1')
assert category == 'therapeutic'
def create_section_html(
graphkb_conn: GraphKBConnection,
gene_name: str,
sentences_by_statement_id: Dict[str, str],
statements: Dict[str, Statement],
exp_variants: List[IprVariant],
) -> str:
"""
Generate HTML for a gene section of the comments
"""
output = [f'<h2>{gene_name}</h2>']
sentence_categories: Dict[str, str] = {}
for statement_id, sentence in sentences_by_statement_id.items():
relevance = statements[statement_id]['relevance']['@rid']
category = categorize_relevance(
graphkb_conn, relevance,
RELEVANCE_BASE_TERMS + [('resistance', ['no sensitivity'])])
sentence_categories[sentence] = category
# get the entrez gene description
genes = sorted(
graphkb_conn.query(
{
'target': 'Feature',
'filters': {
'AND': [
{
'source': {
'target': 'Source',
'filters': {
'name': 'entrez gene'
}
}
},
{
'name': gene_name
},
{
'biotype': 'gene'
},
]
},
}, ),
key=generate_ontology_preference_key,
)
variants_text = display_variants(gene_name, exp_variants)
if not variants_text:
# exclude sections where they are not linked to an experimental variant. this can occur when there are co-occurent statements collected
return ''
if genes and genes[0].get('description', ''):
description = '. '.join(genes[0]['description'].split('. ')[:2])
sourceId = genes[0]['sourceId']
output.append(f'''
<blockquote class="entrez_description" cite="{ENTREZ_GENE_URL}/{sourceId}">
{description}.
</blockquote>
<p>
{variants_text}
</p>
''')
sentences_used: Set[str] = set()
for section in [
{s
for (s, v) in sentence_categories.items() if v == 'diagnostic'},
{s
for (s, v) in sentence_categories.items() if v == 'biological'},
{
s
for (s, v) in sentence_categories.items()
if v in ['therapeutic', 'prognostic']
},
{
s
for (s, v) in sentence_categories.items() if v not in [
'diagnostic', 'biological', 'therapeutic', 'prognostic',
'resistance'
]
},
{s
for (s, v) in sentence_categories.items() if v == 'resistance'},
]:
content = '. '.join(sorted(list(section - sentences_used)))
sentences_used.update(section)
output.append(f'<p>{content}</p>')
return '\n'.join(output)
def convert_statements_to_alterations(
graphkb_conn: GraphKBConnection,
statements: List[Statement],
disease_name: str,
variant_matches: Iterable[str],
) -> List[KbMatch]:
"""
Given a set of statements matched from graphkb, convert these into their IPR equivalent representations
Args:
graphkb_conn: the graphkb connection object
statements: list of statement records from graphkb
disease_name: name of the cancer type for the patient being reported on
variant_matches: the list of RIDs the variant matched for these statements
Raises:
ValueError: could not find the disease type in GraphKB
Returns:
IPR graphkb row representations
Notes:
- only report disease matched prognostic markers https://www.bcgsc.ca/jira/browse/GERO-72 and GERO-196
"""
disease_matches = {
r['@rid']
for r in get_term_tree(
graphkb_conn, disease_name, ontology_class='Disease')
}
if not disease_matches:
raise ValueError(
f'failed to match disease ({disease_name}) to graphkb')
rows = []
approved = convert_to_rid_set(get_approved_evidence_levels(graphkb_conn))
for statement in statements:
variants = [
c for c in statement['conditions']
if c['@class'] in VARIANT_CLASSES
]
diseases = [
c for c in statement['conditions'] if c['@class'] == 'Disease'
]
pmid = ';'.join([e['displayName'] for e in statement['evidence']])
relevance_id = statement['relevance']['@rid']
approved_therapy = False
disease_match = len(
diseases) == 1 and diseases[0]['@rid'] in disease_matches
ipr_section = categorize_relevance(graphkb_conn, relevance_id)
if ipr_section == 'therapeutic':
for level in statement['evidenceLevel'] or []:
if level['@rid'] in approved:
approved_therapy = True
break
if ipr_section == 'prognostic' and not disease_match:
continue # GERO-72 / GERO-196
for variant in variants:
if variant['@rid'] not in variant_matches:
continue
row = KbMatch({
'approvedTherapy':
approved_therapy,
'category':
ipr_section or 'unknown',
'context': (statement['subject']['displayName']
if statement['subject'] else None),
'kbContextId': (statement['subject']['@rid']
if statement['subject'] else None),
'disease':
';'.join(sorted(d['displayName'] for d in diseases)),
'evidenceLevel':
display_evidence_levels(statement),
'kbStatementId':
statement['@rid'],
'kbVariant':
variant['displayName'],
'kbVariantId':
variant['@rid'],
'matchedCancer':
disease_match,
'reference':
pmid,
'relevance':
statement['relevance']['displayName'],
'kbRelevanceId':
statement['relevance']['@rid'],
'externalSource':
statement['source']['displayName']
if statement['source'] else None,
'externalStatementId':
statement.get('sourceId'),
})
rows.append(row)
return rows