feat: use all common names provided by ncbi for each assembly taxon (#1431)

app/apis/catalog/brc-analytics-catalog/common/entities.ts

@@ -11,7 +11,7 @@ export interface BRCDataCatalogGenome {
   accession: string;
   annotationStatus: string | null;
   chromosomes: number | null;
-  commonName: string | null;
+  commonNames: string[];
   coverage: string | null;
   galaxyDatacacheUrl: string | null;
   gcPercent: number | null;
@@ -50,7 +50,7 @@ export interface BRCDataCatalogGenome {
 export interface BRCDataCatalogOrganism {
   assemblyCount: number;
   assemblyTaxonomyIds: string[];
-  commonName: string | null;
+  commonNames: string[];
   genomes: BRCDataCatalogGenome[];
   ncbiTaxonomyId: string;
   otherTaxa: string[] | null;

app/viewModelBuilders/catalog/brc-analytics-catalog/common/viewModelBuilders.tsx

@@ -161,15 +161,16 @@ export const buildChromosomes = (
 };
 
 /**
- * Build props for the common name cell.
+ * Build props for the common names cell.
  * @param entity - Organism or genome entity.
- * @returns Props to be used for the cell.
+ * @returns Props for the NTagCell component.
  */
-export const buildCommonName = (
+export const buildCommonNames = (
   entity: BRCDataCatalogOrganism | BRCDataCatalogGenome
-): ComponentProps<typeof BasicCell> => {
+): ComponentProps<typeof NTagCell> => {
   return {
-    value: entity.commonName,
+    label: "common names",
+    values: entity.commonNames,
   };
 };
 

app/views/WorkflowsView/types.ts

@@ -20,7 +20,7 @@ export type BaseWorkflowAssembly = Pick<
  * at runtime but only typed on site-specific WorkflowEntity extensions.
  */
 export type WorkflowAssembly = BaseWorkflowAssembly & {
-  commonName: string;
+  commonNames: string[];
   taxonomicLevelRealm: string;
 };
 

app/views/WorkflowsView/utils.ts

@@ -26,17 +26,18 @@ function findAssemblyByTaxonomyId(
 }
 
 /**
- * Returns the common name of the assembly, or "Any" if the assembly is undefined.
- * `commonName` is only present on BRC assemblies; GA2 assemblies will return "Any".
- * Returns "null" as a string when the assembly exists but commonName is null.
+ * Returns the common names of the assembly, or ["Any"] if the assembly is undefined.
+ * `commonNames` is only present on BRC assemblies; GA2 assemblies will return ["Any"].
+ * Returns ["None"] when the assembly exists but has no common names.
+ * Each name becomes its own filter facet bucket.
  * @param assembly - Assembly.
- * @returns The common name, "null", or "Any".
+ * @returns The list of common names, ["None"], or ["Any"].
  */
-function getCommonName(assembly: AssemblyContract | undefined): string {
-  // A missing commonName field (GA2 assemblies) reads as "Any"; a present-but-
-  // null commonName (BRC) reads as the string "null".
-  if (!assembly || assembly.commonName === undefined) return "Any";
-  return assembly.commonName ?? "null";
+function getCommonNames(assembly: AssemblyContract | undefined): string[] {
+  // A missing commonNames field (GA2 assemblies) reads as ["Any"]; a present-but-
+  // empty commonNames (BRC) reads as ["None"].
+  if (!assembly || assembly.commonNames === undefined) return ["Any"];
+  return assembly.commonNames.length ? assembly.commonNames : ["None"];
 }
 
 /**
@@ -188,15 +189,15 @@ function indexAssemblyByTaxonomyId(
 
 /**
  * Maps an Assembly to the workflow assembly fields.
- * Includes all taxonomy fields plus site-specific fields (commonName, taxonomicLevelRealm)
+ * Includes all taxonomy fields plus site-specific fields (commonNames, taxonomicLevelRealm)
  * which are present at runtime for all sites but only typed on site-specific WorkflowEntity extensions.
  * If the assembly is undefined, returns default values for the properties.
  * @param assembly - The assembly to map.
  * @returns Assembly object for the WorkflowEntity.
  */
 function mapAssembly(assembly: Assembly | undefined): WorkflowAssembly {
   return {
-    commonName: getCommonName(assembly),
+    commonNames: getCommonNames(assembly),
     taxonomicLevelClass: assembly?.taxonomicLevelClass ?? "Any",
     taxonomicLevelDomain: assembly?.taxonomicLevelDomain ?? "Any",
     taxonomicLevelFamily: assembly?.taxonomicLevelFamily ?? "Any",

backend/api/app/services/catalog_data.py

@@ -114,7 +114,7 @@ def search_organisms(self, query: str, limit: int = 10) -> List[Dict[str, Any]]:
                 for field in (
                     "taxonomicLevelSpecies",
                     "taxonomicLevelGenus",
-                    "commonName",
+                    "commonNames",
                     "ncbiTaxonomyId",
                     "taxonomicGroup",
                     "taxonomicLevelStrain",
@@ -137,7 +137,7 @@ def _condense_organism(self, org: Dict[str, Any]) -> Dict[str, Any]:
             "ncbiTaxonomyId": org.get("ncbiTaxonomyId"),
             "species": org.get("taxonomicLevelSpecies"),
             "genus": org.get("taxonomicLevelGenus"),
-            "commonName": org.get("commonName"),
+            "commonNames": org.get("commonNames"),
             "assemblyCount": org.get("assemblyCount"),
             "taxonomicGroup": org.get("taxonomicGroup"),
             "strain": org.get("taxonomicLevelStrain"),

backend/api/app/services/tools/catalog_data.py

@@ -129,11 +129,16 @@ def search_organisms(self, query: str, limit: int = 10) -> List[Dict[str, Any]]:
         results = []
         for org in self.organisms:
             species = (org.get("taxonomicLevelSpecies") or "").lower()
-            common = (org.get("commonName") or "").lower()
+            commons = [(name or "").lower() for name in org.get("commonNames") or []]
             tax_id = str(org.get("ncbiTaxonomyId") or "")
             genus = (org.get("taxonomicLevelGenus") or "").lower()
 
-            if q in species or q in common or q == tax_id or q in genus:
+            if (
+                q in species
+                or any(q in common for common in commons)
+                or q == tax_id
+                or q in genus
+            ):
                 results.append(self._summarize_organism(org))
                 if len(results) >= limit:
                     break
@@ -165,8 +170,8 @@ def find_organism_exact(self, name: Any) -> Optional[Dict[str, Any]]:
         for org in self.organisms:
             candidates = {
                 (org.get("taxonomicLevelSpecies") or "").lower(),
-                (org.get("commonName") or "").lower(),
                 str(org.get("ncbiTaxonomyId") or "").lower(),
+                *((common or "").lower() for common in org.get("commonNames") or []),
             }
             candidates.discard("")
             if q in candidates:
@@ -185,7 +190,7 @@ def _summarize_organism(self, org: Dict[str, Any]) -> Dict[str, Any]:
 
         return {
             "species": org.get("taxonomicLevelSpecies"),
-            "common_name": org.get("commonName"),
+            "common_names": org.get("commonNames"),
             "taxonomy_id": str(org.get("ncbiTaxonomyId")),
             "assembly_count": org.get("assemblyCount", len(genomes)),
             "reference_assembly_count": len(ref_genomes),

backend/api/app/services/tools/catalog_query.py

@@ -136,7 +136,7 @@ def __post_init__(self) -> None:
             "chromosomes": NUMERIC,
             "strainName": SCALAR,
             "coverage": SCALAR,
-            "commonName": SCALAR,
+            "commonNames": LIST,
             "geneModelUrl": SCALAR,
         },
         # ploidy is intentionally omitted from display — it's an organism-level
@@ -163,7 +163,7 @@ def __post_init__(self) -> None:
         source="organisms.json",
         fields={
             "ncbiTaxonomyId": SCALAR,
-            "commonName": SCALAR,
+            "commonNames": LIST,
             "assemblyCount": NUMERIC,
             "priority": SCALAR,
             "priorityPathogenName": SCALAR,
@@ -180,7 +180,7 @@ def __post_init__(self) -> None:
         display=(
             "ncbiTaxonomyId",
             "taxonomicLevelSpecies",
-            "commonName",
+            "commonNames",
             "assemblyCount",
         ),
         # Most relevant first: best-covered organisms (most assemblies), with the

backend/api/tests/test_catalog_data.py

@@ -14,7 +14,7 @@
         "taxonomicLevelSpecies": "Plasmodium falciparum",
         "taxonomicLevelGenus": "Plasmodium",
         "taxonomicLevelFamily": "Plasmodiidae",
-        "commonName": "malaria parasite",
+        "commonNames": ["malaria parasite"],
         "assemblyCount": 2,
         "taxonomicGroup": ["Apicomplexa"],
         "genomes": [
@@ -53,7 +53,7 @@
         "taxonomicLevelSpecies": "Saccharomyces cerevisiae",
         "taxonomicLevelGenus": "Saccharomyces",
         "taxonomicLevelFamily": "Saccharomycetaceae",
-        "commonName": "yeast",
+        "commonNames": ["yeast", "brewer's yeast"],
         "assemblyCount": 1,
         "taxonomicGroup": ["Fungi"],
         "genomes": [
@@ -160,6 +160,12 @@ def test_search_by_common_name(self, catalog):
         assert len(results) == 1
         assert results[0]["taxonomy_id"] == "559292"
 
+    def test_search_by_secondary_common_name(self, catalog):
+        # Matches on a non-primary common name from the full list.
+        results = catalog.search_organisms("brewer")
+        assert len(results) == 1
+        assert results[0]["taxonomy_id"] == "559292"
+
     def test_search_by_taxonomy_id(self, catalog):
         results = catalog.search_organisms("5833")
         assert len(results) == 1
@@ -417,7 +423,7 @@ def test_missing_scope_defaults_to_assembly(self, tmp_path):
         "ncbiTaxonomyId": 562,
         "taxonomicLevelSpecies": "Escherichia coli",
         "taxonomicLevelGenus": "Escherichia",
-        "commonName": "E. coli",
+        "commonNames": ["E. coli"],
         "assemblyCount": 1,
         "taxonomicGroup": ["Bacteria"],
         "genomes": [
@@ -439,7 +445,7 @@ def test_missing_scope_defaults_to_assembly(self, tmp_path):
         "ncbiTaxonomyId": 559292,
         "taxonomicLevelSpecies": "Saccharomyces cerevisiae",
         "taxonomicLevelGenus": "Saccharomyces",
-        "commonName": "yeast",
+        "commonNames": ["yeast"],
         "assemblyCount": 1,
         "taxonomicGroup": ["Fungi"],
         "genomes": [

backend/api/tests/test_catalog_query.py

@@ -476,26 +476,26 @@ def organism_con():
             taxonomicLevelSpecies VARCHAR,
             taxonomicLevelGenus VARCHAR,
             taxonomicLevelDomain VARCHAR,
-            commonName VARCHAR,
+            commonNames VARCHAR[],
             assemblyCount BIGINT,
             taxonomicGroup VARCHAR[]
         )
         """
     )
     rows = [
-        # taxid, species, genus, domain, common, assemblyCount, group
+        # taxid, species, genus, domain, commonNames, assemblyCount, group
         (
             "7165",
             "Anopheles gambiae",
             "Anopheles",
             "Eukaryota",
-            "mosquito",
+            ["mosquito", "African malaria mosquito"],
             12,
             ["Inv"],
         ),
-        ("7173", "Anopheles stephensi", "Anopheles", "Eukaryota", None, 5, ["Inv"]),
-        ("62324", "Anopheles funestus", "Anopheles", "Eukaryota", None, 3, ["Inv"]),
-        ("5476", "Candida albicans", "Candida", "Eukaryota", None, 8, ["Fungi"]),
+        ("7173", "Anopheles stephensi", "Anopheles", "Eukaryota", [], 5, ["Inv"]),
+        ("62324", "Anopheles funestus", "Anopheles", "Eukaryota", [], 3, ["Inv"]),
+        ("5476", "Candida albicans", "Candida", "Eukaryota", [], 8, ["Fungi"]),
     ]
     c.executemany("INSERT INTO organism VALUES (?, ?, ?, ?, ?, ?, ?)", rows)
     yield c
@@ -539,7 +539,7 @@ def test_organism_clade_list_is_bounded(organism_con):
     assert set(out["rows"][0]) == {
         "ncbiTaxonomyId",
         "taxonomicLevelSpecies",
-        "commonName",
+        "commonNames",
         "assemblyCount",
     }
 

backend/tests/test_catalog_data.py

@@ -50,7 +50,7 @@ def test_search_by_genus(self, catalog):
     def test_search_by_common_name(self, catalog):
         results = catalog.search_organisms("malaria")
         assert len(results) > 0
-        names = [r.get("commonName") or "" for r in results]
+        names = [name for r in results for name in (r.get("commonNames") or [])]
         assert any("malaria" in n.lower() for n in names)
 
     def test_search_by_taxonomy_id(self, catalog):