Merge pull request #107 from bcgsc/feature/KBDEV-1129-add-cancer-gene-flag

Add cancer_gene flag to get_gene_information

Author: mathieulemieux

graphkb/genes.py

@@ -392,7 +392,7 @@ def get_gene_information(
 
     Function is originally from pori_ipr_python::annotate.py
 
-    Gene flags (categories) are: ['cancerRelated', 'knownFusionPartner', 'knownSmallMutation',
+    Gene flags (categories) are: ['cancerGene', 'cancerRelated', 'knownFusionPartner', 'knownSmallMutation',
                                   'oncogene', 'therapeuticAssociated', 'tumourSuppressor']
 
     Args:
@@ -444,6 +444,8 @@ def get_gene_information(
     gene_flags["oncogene"] = convert_to_rid_set(get_oncokb_oncogenes(graphkb_conn))
     logger.info("fetching tumour supressors list")
     gene_flags["tumourSuppressor"] = convert_to_rid_set(get_oncokb_tumour_supressors(graphkb_conn))
+    logger.info("fetching cancerGene list")
+    gene_flags["cancerGene"] = convert_to_rid_set(get_cancer_genes(graphkb_conn))
 
     logger.info("fetching therapeutic associated genes lists")
     gene_flags["therapeuticAssociated"] = convert_to_rid_set(

tests/test_genes.py

@@ -23,7 +23,7 @@
 
 CANONICAL_ONCOGENES = ["kras", "nras", "alk"]
 CANONICAL_TS = ["cdkn2a", "tp53"]
-CANONICAL_CG = ["ercc1", "fanci", "h2bc4", "h2bc17", "acvr1b"]
+CANONICAL_CG = ["alb"]
 CANONICAL_FUSION_GENES = ["alk", "ewsr1", "fli1"]
 CANONICAL_STRUCTURAL_VARIANT_GENES = ["brca1", "dpyd", "pten"]
 CANNONICAL_THERAPY_GENES = ["erbb2", "brca2", "egfr"]
@@ -203,6 +203,7 @@ def test_get_gene_information(conn):
         conn,
         CANONICAL_ONCOGENES
         + CANONICAL_TS
+        + CANONICAL_CG
         + CANONICAL_FUSION_GENES
         + CANONICAL_STRUCTURAL_VARIANT_GENES
         + CANNONICAL_THERAPY_GENES
@@ -247,3 +248,8 @@ def test_get_gene_information(conn):
         assert gene in [
             g["name"] for g in gene_info if g.get("cancerRelated")
         ], f"Missed cancerRelated {gene}"
+
+    for gene in CANONICAL_CG:
+        assert gene in [
+            g["name"] for g in gene_info if g.get("cancerGene")
+        ], f"Missed cancerGene {gene}"