lint

pori_python/graphkb/genes.py

@@ -185,7 +185,9 @@ def get_genes_from_variant_types(
     return result
 
 
-def get_preferred_gene_source_rid(conn: GraphKBConnection, preferred_source_name=PREFERRED_GENE_SOURCE_NAME):
+def get_preferred_gene_source_rid(
+    conn: GraphKBConnection, preferred_source_name=PREFERRED_GENE_SOURCE_NAME
+):
     """Get the rid of the preferred gene source.
 
     Args:
@@ -196,7 +198,10 @@ def get_preferred_gene_source_rid(conn: GraphKBConnection, preferred_source_name
 
     """
     result = conn.query(
-        {"target": {"target": "Source", "filters": {"name": preferred_source_name}}, "queryType": "similarTo"},
+        {
+            "target": {"target": "Source", "filters": {"name": preferred_source_name}},
+            "queryType": "similarTo",
+        },
     )[0]["@rid"]
     return result
 

pori_python/ipr/connection.py

@@ -13,7 +13,9 @@
 
 
 class IprConnection:
-    def __init__(self, username: str, password: str, url: str = os.environ.get("IPR_URL", DEFAULT_URL)):
+    def __init__(
+        self, username: str, password: str, url: str = os.environ.get("IPR_URL", DEFAULT_URL)
+    ):
         self.token = None
         self.url = url
         self.username = username
@@ -26,7 +28,9 @@ def __init__(self, username: str, password: str, url: str = os.environ.get("IPR_
         self.cache: Dict[str, List[Dict]] = {}
         self.request_count = 0
 
-    def request(self, endpoint: str, method: str = "GET", custom_headers: Dict = None, **kwargs) -> Dict:
+    def request(
+        self, endpoint: str, method: str = "GET", custom_headers: Dict = None, **kwargs
+    ) -> Dict:
         """Request wrapper to handle adding common headers and logging
 
         Args:
@@ -59,7 +63,7 @@ def request(self, endpoint: str, method: str = "GET", custom_headers: Dict = Non
                 pass
 
             raise requests.exceptions.HTTPError(message)
-        if resp.status_code == 204: # TODO: address this in api
+        if resp.status_code == 204:  # TODO: address this in api
             return {'status_code': 204}
         return resp.json()
 

pori_python/ipr/main.py

@@ -72,8 +72,12 @@ def command_interface() -> None:
     )
 
     parser.add_argument('--ipr_url', default=os.environ.get("IPR_URL", DEFAULT_URL))
-    parser.add_argument('--graphkb_username', help='username to use connecting to graphkb if different from ipr')
-    parser.add_argument('--graphkb_password', help='password to use connecting to graphkb if different from ipr')
+    parser.add_argument(
+        '--graphkb_username', help='username to use connecting to graphkb if different from ipr'
+    )
+    parser.add_argument(
+        '--graphkb_password', help='password to use connecting to graphkb if different from ipr'
+    )
     parser.add_argument('--graphkb_url', default=os.environ.get("GRAPHKB_URL", None))
     parser.add_argument('--log_level', default='info', choices=LOG_LEVELS.keys())
     parser.add_argument(

tests/test_graphkb/test_genes.py

@@ -110,6 +110,7 @@ def conn():
     conn.login(os.environ["GRAPHKB_USER"], os.environ["GRAPHKB_PASS"])
     return conn
 
+
 @pytest.mark.skipif(EXCLUDE_ONCOKB_TESTS, reason="excluding tests that depend on oncokb data")
 def test_oncogene(conn):
     result = get_oncokb_oncogenes(conn)
@@ -121,6 +122,7 @@ def test_oncogene(conn):
     for gene in CANONICAL_CG:
         assert gene not in names
 
+
 @pytest.mark.skipif(EXCLUDE_ONCOKB_TESTS, reason="excluding tests that depend on oncokb data")
 def test_tumour_supressors(conn):
     result = get_oncokb_tumour_supressors(conn)
@@ -132,8 +134,11 @@ def test_tumour_supressors(conn):
     for gene in CANONICAL_CG:
         assert gene not in names
 
+
 @pytest.mark.skipif(EXCLUDE_ONCOKB_TESTS, reason="excluding tests that depend on oncokb data")
-@pytest.mark.skipif(EXCLUDE_BCGSC_TESTS, reason="excluding BCGSC-specific tests (tso500 not available)")
+@pytest.mark.skipif(
+    EXCLUDE_BCGSC_TESTS, reason="excluding BCGSC-specific tests (tso500 not available)"
+)
 def test_cancer_genes(conn):
     result = get_cancer_genes(conn)
     names = {row["name"] for row in result}
@@ -144,7 +149,10 @@ def test_cancer_genes(conn):
     for gene in CANONICAL_ONCOGENES:
         assert gene not in names
 
-@pytest.mark.skipif(EXCLUDE_BCGSC_TESTS, reason="excluding BCGSC-specific tests (requires CGL loader))")
+
+@pytest.mark.skipif(
+    EXCLUDE_BCGSC_TESTS, reason="excluding BCGSC-specific tests (requires CGL loader))"
+)
 def test_get_pharmacogenomic_info(conn):
     genes, matches = get_pharmacogenomic_info(conn)
     for gene in PHARMACOGENOMIC_INITIAL_GENES:
@@ -158,7 +166,10 @@ def test_get_pharmacogenomic_info(conn):
                 continue
             assert False, f"No rid found for a pharmacogenomic with {gene}"
 
-@pytest.mark.skipif(EXCLUDE_BCGSC_TESTS, reason="excluding BCGSC-specific tests (requires CGL loader))")
+
+@pytest.mark.skipif(
+    EXCLUDE_BCGSC_TESTS, reason="excluding BCGSC-specific tests (requires CGL loader))"
+)
 def test_get_gene_linked_pharmacogenomic_info(conn):
     genes, matches = get_gene_linked_pharmacogenomic_info(conn)
     for gene in PHARMACOGENOMIC_INITIAL_GENES:
@@ -172,15 +183,19 @@ def test_get_gene_linked_pharmacogenomic_info(conn):
 
 
 @pytest.mark.skipif(EXCLUDE_INTEGRATION_TESTS, reason="excluding long running integration tests")
-@pytest.mark.skipif(EXCLUDE_BCGSC_TESTS, reason="excluding BCGSC-specific tests (requires CGL loader))")
+@pytest.mark.skipif(
+    EXCLUDE_BCGSC_TESTS, reason="excluding BCGSC-specific tests (requires CGL loader))"
+)
 def test_get_cancer_predisposition_info(conn):
     genes, matches = get_cancer_predisposition_info(conn)
     for gene in CANCER_PREDISP_INITIAL_GENES:
         assert gene in genes, f"{gene} not found in get_cancer_predisposition_info"
 
 
 @pytest.mark.skipif(EXCLUDE_INTEGRATION_TESTS, reason="excluding long running integration tests")
-@pytest.mark.skipif(EXCLUDE_BCGSC_TESTS, reason="excluding BCGSC-specific tests (requires CGL loader))")
+@pytest.mark.skipif(
+    EXCLUDE_BCGSC_TESTS, reason="excluding BCGSC-specific tests (requires CGL loader))"
+)
 def test_get_gene_linked_cancer_predisposition_info(conn):
     genes, matches = get_gene_linked_cancer_predisposition_info(conn)
     for gene in CANCER_PREDISP_INITIAL_GENES:
@@ -197,7 +212,9 @@ def test_get_preferred_gene_name_kras(alt_rep, conn):
     ), f"Expected KRAS as preferred gene name for {alt_rep}, not '{gene_name}'"
 
 
-@pytest.mark.skipif(EXCLUDE_BCGSC_TESTS, reason="excluding BCGSC-specific tests (requires CGL loader))")
+@pytest.mark.skipif(
+    EXCLUDE_BCGSC_TESTS, reason="excluding BCGSC-specific tests (requires CGL loader))"
+)
 @pytest.mark.skipif(EXCLUDE_INTEGRATION_TESTS, reason="excluding long running integration tests")
 def test_find_genes_by_variant_type_structural_variant(conn):
     result = get_genes_from_variant_types(conn, ["structural variant"])
@@ -214,6 +231,7 @@ def test_find_no_genes_by_variant_type_with_nonmatching_source_record_id(conn):
     )
     assert not result
 
+
 @pytest.mark.skipif(EXCLUDE_INTEGRATION_TESTS, reason="excluding long running integration tests")
 def test_get_therapeutic_associated_genes(conn):
     gene_list = get_therapeutic_associated_genes(graphkb_conn=conn)
@@ -225,7 +243,11 @@ def test_get_therapeutic_associated_genes(conn):
     for gene in CANNONICAL_THERAPY_GENES + CANONICAL_ONCOGENES + CANONICAL_TS:
         assert gene in names, f"{gene} not found by get_therapeutic_associated_genes"
 
-@pytest.mark.skipif(EXCLUDE_BCGSC_TESTS, reason="excluding BCGSC-specific tests (requires oncokb and other loaders))")
+
+@pytest.mark.skipif(
+    EXCLUDE_BCGSC_TESTS,
+    reason="excluding BCGSC-specific tests (requires oncokb and other loaders))",
+)
 @pytest.mark.skipif(EXCLUDE_INTEGRATION_TESTS, reason="excluding long running integration tests")
 def test_get_gene_information(conn):
     gene_info = get_gene_information(

tests/test_graphkb/test_match.py

@@ -41,12 +41,14 @@ def conn() -> GraphKBConnection:
 def kras(conn):
     return [f["displayName"] for f in match.get_equivalent_features(conn, "kras")]
 
+
 """ 
 version found in the db for ENSG00000133703 will vary depending on which
 version of ensembl was loaded. checking for any . version
  """
 kras_ensg_version = r'ENSG00000133703\..*'
 
+
 class TestGetEquivalentFeatures:
     def test_kras_has_self(self, kras):
         assert "KRAS" in kras
@@ -109,7 +111,10 @@ def test_bad_gene_name(self, conn):
         with pytest.raises(FeatureNotFoundError):
             match.match_copy_variant(conn, "not a real gene name", match.INPUT_COPY_CATEGORIES.AMP)
 
-    @pytest.mark.skipif(EXCLUDE_BCGSC_TESTS, reason="excluding BCGSC-specific tests - no copy loss variants in other data")
+    @pytest.mark.skipif(
+        EXCLUDE_BCGSC_TESTS,
+        reason="excluding BCGSC-specific tests - no copy loss variants in other data",
+    )
     def test_known_loss(self, conn):
         matches = match.match_copy_variant(conn, "CDKN2A", match.INPUT_COPY_CATEGORIES.ANY_LOSS)
         assert matches
@@ -126,7 +131,10 @@ def test_known_loss(self, conn):
         for variant_type in types_selected:
             assert not has_prefix(variant_type, INCREASE_PREFIXES)
 
-    @pytest.mark.skipif(EXCLUDE_BCGSC_TESTS, reason="excluding BCGSC-specific tests - no copy loss variants in other data")
+    @pytest.mark.skipif(
+        EXCLUDE_BCGSC_TESTS,
+        reason="excluding BCGSC-specific tests - no copy loss variants in other data",
+    )
     def test_known_loss_zygosity_filtered(self, conn):
         matches = match.match_copy_variant(
             conn, "CDKN2A", match.INPUT_COPY_CATEGORIES.ANY_LOSS, True
@@ -224,7 +232,9 @@ def test_known_reduced_expression(self, conn):
         for variant_type in types_selected:
             assert not has_prefix(variant_type, INCREASE_PREFIXES)
 
-    @pytest.mark.skipif(EXCLUDE_BCGSC_TESTS, reason="excluding BCGSC-specific tests - no applicable variants")
+    @pytest.mark.skipif(
+        EXCLUDE_BCGSC_TESTS, reason="excluding BCGSC-specific tests - no applicable variants"
+    )
     def test_known_reduced_expression_gene_id(self, conn):
         gene_id = conn.query({"target": "Feature", "filters": [{"name": "PTEN"}]})[0]["@rid"]
         matches = match.match_expression_variant(
@@ -413,7 +423,9 @@ def test_match_explicit_references(self, conn):
             ["EGFR:p.E746_S752delinsI", ["EGFR mutation"], ["EGFR copy variant"]],
         ],
     )
-    @pytest.mark.skipif(EXCLUDE_BCGSC_TESTS, reason='TODO: fix loader for vars ending in X, p.?, copy variant')
+    @pytest.mark.skipif(
+        EXCLUDE_BCGSC_TESTS, reason='TODO: fix loader for vars ending in X, p.?, copy variant'
+    )
     def test_known_variants(self, conn, known_variant, related_variants, unrelated_variants):
         matches = match.match_positional_variant(conn, known_variant)
         names = {m["displayName"] for m in matches}
@@ -424,7 +436,9 @@ def test_known_variants(self, conn, known_variant, related_variants, unrelated_v
         for variant in unrelated_variants:
             assert variant not in names
 
-    @pytest.mark.skipif(EXCLUDE_BCGSC_TESTS, reason="TODO: add nonIPRKB fusion tests; source for these is IPRKB")
+    @pytest.mark.skipif(
+        EXCLUDE_BCGSC_TESTS, reason="TODO: add nonIPRKB fusion tests; source for these is IPRKB"
+    )
     @pytest.mark.parametrize(
         "known_variant,related_variants",
         [

tests/test_graphkb/test_statement.py

@@ -85,7 +85,10 @@ def test_custom_categories(self, graphkb_conn):
         )
         assert category == "blargh"
 
-@pytest.mark.skipif(EXCLUDE_BCGSC_TESTS, reason='db-specific rid; requires Inferred Functional Annotation source')
+
+@pytest.mark.skipif(
+    EXCLUDE_BCGSC_TESTS, reason='db-specific rid; requires Inferred Functional Annotation source'
+)
 @pytest.mark.skipif(EXCLUDE_INTEGRATION_TESTS, reason="excluding long running integration tests")
 class TestStatementMatch:
     def test_truncating_categories(self, conn):  # noqa - pytest fixture, not redefinition

tests/test_ipr/test_main.py

@@ -15,6 +15,7 @@
 EXCLUDE_BCGSC_TESTS = os.environ.get("EXCLUDE_BCGSC_TESTS") == "1"
 EXCLUDE_ONCOKB_TESTS = os.environ.get("EXCLUDE_ONCOKB_TESTS") == "1"
 
+
 def get_test_spec():
     ipr_spec = {"components": {"schemas": {"genesCreate": {"properties": {}}}}}
     ipr_gene_keys = IprGene.__required_keys__ | IprGene.__optional_keys__
@@ -43,20 +44,27 @@ def report_upload_content(tmp_path_factory) -> Dict:
                 ],
                 'patientId': 'PATIENT001',
                 'project': 'TEST',
-                'expressionVariants': json.loads(pd.read_csv(
-                    get_test_file('expression.short.tab'), sep='\t'
-                ).to_json(orient='records')),
-                'smallMutations': json.loads(pd.read_csv(
-                    get_test_file('small_mutations.short.tab'), sep='\t'
-                ).to_json(orient='records')),
-                'copyVariants': json.loads(pd.read_csv(
-                    get_test_file('copy_variants.short.tab'), sep='\t'
-                ).to_json(orient='records')),
-                'structuralVariants': json.loads(pd.read_csv(get_test_file('fusions.tab'), sep='\t').to_json(
-                    orient='records'
-                )),
+                'expressionVariants': json.loads(
+                    pd.read_csv(get_test_file('expression.short.tab'), sep='\t').to_json(
+                        orient='records'
+                    )
+                ),
+                'smallMutations': json.loads(
+                    pd.read_csv(get_test_file('small_mutations.short.tab'), sep='\t').to_json(
+                        orient='records'
+                    )
+                ),
+                'copyVariants': json.loads(
+                    pd.read_csv(get_test_file('copy_variants.short.tab'), sep='\t').to_json(
+                        orient='records'
+                    )
+                ),
+                'structuralVariants': json.loads(
+                    pd.read_csv(get_test_file('fusions.tab'), sep='\t').to_json(orient='records')
+                ),
                 'kbDiseaseMatch': 'colorectal cancer',
-            }, allow_nan=False
+            },
+            allow_nan=False,
         )
     )
     with patch.object(
@@ -108,7 +116,9 @@ def test_main_sections_present(self, report_upload_content: Dict) -> None:
 
     def test_kept_low_quality_fusion(self, report_upload_content: Dict) -> None:
         fusions = [(sv['gene1'], sv['gene2']) for sv in report_upload_content['structuralVariants']]
-        if EXCLUDE_BCGSC_TESTS:  # may be missing statements assoc with SUZ12 if no access to bcgsc data
+        if (
+            EXCLUDE_BCGSC_TESTS
+        ):  # may be missing statements assoc with SUZ12 if no access to bcgsc data
             assert ('SARM1', 'CDKL2') in fusions
         else:
             assert ('SARM1', 'SUZ12') in fusions

tests/test_ipr/test_probe.py

@@ -56,7 +56,9 @@ class TestCreateReport:
     def test_found_probe_small_mutations(self, probe_upload_content: Dict) -> None:
         assert probe_upload_content["smallMutations"]
 
-    @pytest.mark.skipif(EXCLUDE_BCGSC_TESTS, reason="excluding tests that depend on BCGSC-specific data")
+    @pytest.mark.skipif(
+        EXCLUDE_BCGSC_TESTS, reason="excluding tests that depend on BCGSC-specific data"
+    )
     def test_found_probe_small_mutations_match(self, probe_upload_content: Dict) -> None:
         # verify each probe had a KB match
         for sm_probe in probe_upload_content["smallMutations"]: