Merge branch 'develop' of https://github.com/bcgsc/pori_python into f…

…eat/update-readme

.github/workflows/gkb_workflows/pytest.yml

@@ -12,7 +12,7 @@ jobs:
     strategy:
       max-parallel: 4
       matrix:
-        python-version: ['3.7', '3.8', '3.9', '3.10']
+        python-version: ['3.9', '3.10']
 
     steps:
     - uses: actions/checkout@v3

.github/workflows/pytest.yml

@@ -16,7 +16,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ['3.8', '3.9', '3.10', '3.11', '3.12']
+        python-version: ['3.9', '3.10', '3.11', '3.12']
 
     steps:
     - uses: actions/checkout@v3
@@ -32,15 +32,15 @@ jobs:
       run: |
         pip install flake8
         # stop the build if there are Python syntax errors or undefined names
-        flake8 ipr graphkb --count --select=E9,F63,F7,F82 --show-source --statistics
+        flake8 pori_python --count --select=E9,F63,F7,F82 --show-source --statistics
     - name: Check with black
       run: |
         pip install black
-        black --check -S -l 100 ipr graphkb tests
+        black --check -S -l 100 pori_python tests
     - name: Full Tests with pytest
       run: |
         pip list
-        pytest --junitxml=junit/test-results-${{ matrix.python-version }}.xml --cov ipr --cov-report term --cov-report xml
+        pytest --junitxml=junit/test-results-${{ matrix.python-version }}.xml --cov pori_python --cov-report term --cov-report xml
       env:
         IPR_USER: ${{ secrets.IPR_TEST_USER }}
         IPR_PASS: ${{ secrets.IPR_TEST_PASSWORD }}

.github/workflows/quick-pytest.yml

@@ -13,7 +13,7 @@ jobs:
     strategy:
       max-parallel: 4
       matrix:
-        python-version: ['3.7', '3.8', '3.9', '3.10', '3.11', '3.12']
+        python-version: ['3.9', '3.10', '3.11', '3.12']
 
     steps:
     - uses: actions/checkout@v3
@@ -29,11 +29,11 @@ jobs:
       run: |
         pip install flake8
         # stop the build if there are Python syntax errors or undefined names
-        flake8 ipr graphkb --count --select=E9,F63,F7,F82 --show-source --statistics
+        flake8 pori_python --count --select=E9,F63,F7,F82 --show-source --statistics
     - name: Check with black
       run: |
         pip install black
-        black --check -S -l 100 ipr graphkb tests
+        black --check -S -l 100 pori_python tests
     - name: Short Tests with pytest
       run: pytest --junitxml=junit/test-results-${{ matrix.python-version }}.xml --cov ipr --cov-report term --cov-report xml
       env:

pori_python/graphkb/genes.py

@@ -229,6 +229,16 @@ def get_preferred_gene_name(
 def get_cancer_predisposition_info(
     conn: GraphKBConnection, source: str = PREFERRED_GENE_SOURCE
 ) -> Tuple[List[str], Dict[str, str]]:
+    newval = get_gene_linked_cancer_predisposition_info(conn, source)
+    genes = newval[0]
+    allvardata = newval[1]
+    variants = {key: allvardata[key][0] for key in allvardata.keys()}
+    return newval[0], variants
+
+
+def get_gene_linked_cancer_predisposition_info(
+    conn: GraphKBConnection, source: str = PREFERRED_GENE_SOURCE
+) -> Tuple[List[str], Dict[str, Tuple[str, List[str]]]]:
     """
     Return two lists from GraphKB, one of cancer predisposition genes and one of associated variants.
 
@@ -241,6 +251,8 @@ def get_cancer_predisposition_info(
 
     Example: https://graphkb.bcgsc.ca/view/Statement/155:11616
 
+
+
     Returns:
         genes: list of cancer predisposition genes
         variants: dictionary mapping pharmacogenomic variant IDs to variant display names
@@ -283,21 +295,24 @@ def get_cancer_predisposition_info(
     ):
         for condition in record["conditions"]:  # type: ignore
             if condition["@class"] == "PositionalVariant":
-                variants[condition["@rid"]] = condition["displayName"]
+                assoc_gene_list = []
                 for reference in ["reference1", "reference2"]:
                     name = (condition.get(reference) or {}).get("displayName", "")
                     biotype = (condition.get(reference) or {}).get("biotype", "")
                     if name and biotype == "gene":
                         genes.add(name)
+                        assoc_gene_list.append(name)
                     elif name:
                         gene = get_preferred_gene_name(conn, name, source)
                         if gene:
                             infer_genes.add((gene, name, biotype))
+                            assoc_gene_list.append(gene)
                         else:
                             non_genes.add((name, biotype))
                             logger.error(
                                 f"Non-gene cancer predisposition {biotype}: {name} for {condition['displayName']}"
                             )
+                variants[condition["@rid"]] = [condition["displayName"], assoc_gene_list]
 
     for gene, name, biotype in infer_genes:
         logger.debug(f"Found gene '{gene}' for '{name}' ({biotype})")
@@ -312,6 +327,16 @@ def get_cancer_predisposition_info(
 def get_pharmacogenomic_info(
     conn: GraphKBConnection, source: str = PREFERRED_GENE_SOURCE
 ) -> Tuple[List[str], Dict[str, str]]:
+    newval = get_gene_linked_pharmacogenomic_info(conn, source)
+    genes = newval[0]
+    allvardata = newval[1]
+    variants = {key: allvardata[key][0] for key in allvardata.keys()}
+    return newval[0], variants
+
+
+def get_gene_linked_pharmacogenomic_info(
+    conn: GraphKBConnection, source: str = PREFERRED_GENE_SOURCE
+) -> Tuple[List[str], Dict[str, Tuple[str, List[str]]]]:
     """
     Return two lists from GraphKB, one of pharmacogenomic genes and one of associated variants.
 
@@ -360,22 +385,24 @@ def get_pharmacogenomic_info(
 
         for condition in record["conditions"]:  # type: ignore
             if condition["@class"] == "PositionalVariant":
-                variants[condition["@rid"]] = condition["displayName"]
+                assoc_gene_list = []
                 for reference in ["reference1", "reference2"]:
                     name = (condition.get(reference) or {}).get("displayName", "")
                     biotype = (condition.get(reference) or {}).get("biotype", "")
                     if name and biotype == "gene":
                         genes.add(name)
+                        assoc_gene_list.append(name)
                     elif name:
                         gene = get_preferred_gene_name(conn, name, source)
                         if gene:
                             infer_genes.add((gene, name, biotype))
+                            assoc_gene_list.append(gene)
                         else:
                             non_genes.add((name, biotype))
                             logger.error(
                                 f"Non-gene pharmacogenomic {biotype}: {name} for {condition['displayName']}"
                             )
-
+                variants[condition["@rid"]] = [condition["displayName"], assoc_gene_list]
     for gene, name, biotype in infer_genes:
         logger.debug(f"Found gene '{gene}' for '{name}' ({biotype})")
         genes.add(gene)

setup.cfg

@@ -27,7 +27,7 @@ long_description_content_type = text/markdown
 
 [options]
 packages = find:
-python_requires = >=3.7
+python_requires = >=3.9
 dependency_links = []
 include_package_data = True
 install_requires =

tests/test_graphkb/test_genes.py

@@ -10,11 +10,13 @@
 from pori_python.graphkb.genes import (
     get_cancer_genes,
     get_cancer_predisposition_info,
+    get_gene_linked_cancer_predisposition_info,
     get_gene_information,
     get_genes_from_variant_types,
     get_oncokb_oncogenes,
     get_oncokb_tumour_supressors,
     get_pharmacogenomic_info,
+    get_gene_linked_pharmacogenomic_info,
     get_preferred_gene_name,
     get_therapeutic_associated_genes,
 )
@@ -148,6 +150,21 @@ def test_get_pharmacogenomic_info(conn):
         for rid, variant_display in matches.items():
             if variant_display.startswith(gene):
                 break
+        else:  # no break called
+            # failing on this version of the func; addressed in 'new' version
+            if gene == 'ACYP2':
+                continue
+            assert False, f"No rid found for a pharmacogenomic with {gene}"
+
+
+def test_get_gene_linked_pharmacogenomic_info(conn):
+    genes, matches = get_gene_linked_pharmacogenomic_info(conn)
+    for gene in PHARMACOGENOMIC_INITIAL_GENES:
+        assert gene in genes, f"{gene} not found in get_pharmacogenomic_info"
+        for rid, variant_info in matches.items():
+            variant_gene_assoc = variant_info[1]
+            if gene in variant_gene_assoc:
+                break
         else:  # no break called
             assert False, f"No rid found for a pharmacogenomic with {gene}"
 
@@ -159,6 +176,13 @@ def test_get_cancer_predisposition_info(conn):
         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")
+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:
+        assert gene in genes, f"{gene} not found in get_cancer_predisposition_info"
+
+
 @pytest.mark.parametrize(
     "alt_rep", ("NM_033360.4", "NM_033360", "ENSG00000133703.11", "ENSG00000133703")
 )

tests/test_graphkb/test_graphkb.py

@@ -18,6 +18,7 @@ def conn():
     conn.login(os.environ["GRAPHKB_USER"], os.environ["GRAPHKB_PASS"])
     return conn
 
+
 class TestPaginate:
     @mock.patch("pori_python.graphkb.GraphKBConnection.request")
     def test_does_not_paginate_when_false(self, graphkb_request, conn):

tests/test_graphkb/test_match.py

@@ -7,7 +7,10 @@
 
 import pori_python.graphkb
 from pori_python.graphkb import GraphKBConnection, match
-from pori_python.graphkb.constants import DEFAULT_NON_STRUCTURAL_VARIANT_TYPE, STRUCTURAL_VARIANT_SIZE_THRESHOLD
+from pori_python.graphkb.constants import (
+    DEFAULT_NON_STRUCTURAL_VARIANT_TYPE,
+    STRUCTURAL_VARIANT_SIZE_THRESHOLD,
+)
 from pori_python.graphkb.util import FeatureNotFoundError
 
 # Test datasets
@@ -500,6 +503,7 @@ def test_filling_cache(self):
         assert "alice" in match.FEATURES_CACHE
         match.FEATURES_CACHE = None
 
+
 class TestTypeScreening:
     # Types as class variables
     default_type = DEFAULT_NON_STRUCTURAL_VARIANT_TYPE

tests/test_ipr/test_annotate.py

@@ -47,6 +47,7 @@ def graphkb_conn():
     graphkb_conn.login(username, password)
     return graphkb_conn
 
+
 class TestAnnotation:
     def test_annotate_nonsense_vs_missense(self, graphkb_conn):
         """Verify missense (point mutation) is not mistaken for a nonsense (stop codon) mutation."""
@@ -58,7 +59,6 @@ def test_annotate_nonsense_vs_missense(self, graphkb_conn):
             assert not nonsense, f"nonsense matched to {key}: {TP53_MUT_DICT[key]}"
             assert matched, f"should have matched in {key}: {TP53_MUT_DICT[key]}"
 
-
     def test_annotate_nonsense_vs_missense_protein(self, graphkb_conn):
         """Verify missense (point mutation) is not mistaken for a nonsense (stop codon) mutation."""
         disease = 'cancer'
@@ -69,7 +69,6 @@ def test_annotate_nonsense_vs_missense_protein(self, graphkb_conn):
             assert not nonsense, f"nonsense matched to {key}: {TP53_MUT_DICT[key]}"
             assert matched, f"should have matched in {key}: {TP53_MUT_DICT[key]}"
 
-
     def test_annotate_structural_variants_tp53(self, graphkb_conn):
         """Verify alternate TP53 variants match."""
         disease = 'cancer'

tests/test_ipr/test_summary.py

@@ -1,6 +1,10 @@
 from unittest.mock import MagicMock
 
-from pori_python.ipr.summary import GRAPHKB_GUI, get_preferred_drug_representation, substitute_sentence_template
+from pori_python.ipr.summary import (
+    GRAPHKB_GUI,
+    get_preferred_drug_representation,
+    substitute_sentence_template,
+)
 
 
 class TestGetPreferredDrugRepresentation: