[bio] Update biomed property embeddings. (#4721)

Adds:
- mechanismOfAction
- hgncID
- inChIKey

Updates:
- unifiedMedicalLanguageSystemConceptUniqueIdentifier ->
umlsConceptUniqueID
- ncbiTaxonID->ncbiTaxId
- referenceAlleleNCBI -> referenceAllele
- genomicCoordinates -> hasGenomicCoordinates

Deletes:
- diseaseName
- observedAllele
- hg19GenomicPosition
- hg19GenomicLocation
- hg38GenomicPosition
- hg38GenomicLocation
- hasRNATranscript
- ncbiDNASequenceName
- imageUrl
- availableStrength

Example Screenshots

![image](https://github.com/user-attachments/assets/6783a776-48e0-4ceb-aa57-b0276a67d2db)

![image](https://github.com/user-attachments/assets/568b48e8-c6b6-4dce-9e99-af9bf7f0f912)

![image](https://github.com/user-attachments/assets/8f31b18b-3169-4ef0-a67d-a0b6cea3bf71)

deploy/nl/catalog.yaml

@@ -78,7 +78,7 @@ indexes:
   bio_ft:
     store_type: MEMORY
     source_path: ../../tools/nl/embeddings/input/bio
-    embeddings_path: gs://datcom-nl-models/bio_ft_2024_11_05_09_59_39/embeddings.csv
+    embeddings_path: gs://datcom-nl-models/bio_ft_2024_11_08_19_00_38/embeddings.csv
     model: ft-final-v20230717230459-all-MiniLM-L6-v2
     healthcheck_query: "Gene"
   base_uae_lance:

server/integration_tests/explore_test.py

@@ -761,14 +761,17 @@ def test_e2e_triple(self):
     self.run_detect_and_fulfill(
         'e2e_triple',
         [
+            # ----- Context Based Queries -----
             # Should have 'out' properties as answer
             'What strand orientation does FGFR1 have?',
             # Should use context for the entity
-            'what transcripts does it have',
+            'what genomic coordinates does it have',
             # Should use context for the property
-            'how about for P53',
+            'how about for PQLC3',
             # Should not use context because no entity or property found
             'what animal is that found in',
+
+            # ----- Singleton Queries -----
             # Should have 'in' properties as answer
             'What is Betacoronavirus 1 the species of',
             # Should have a chained property in the answer

server/integration_tests/test_data/detection_api_bio/whatisthephylumofvolvox/debug_info.json

@@ -24,7 +24,7 @@
       0.314266,
       0.312765,
       0.312629,
-      0.312504,
+      0.312505,
       0.311774,
       0.310339,
       0.310075,
@@ -75,24 +75,23 @@
       0.31467,
       0.308395,
       0.307941,
-      0.30463,
-      0.282709,
       0.281875,
-      0.280828,
-      0.280453,
-      0.274298,
       0.271505,
       0.270718,
-      0.269547,
       0.259901,
       0.259901,
       0.248279,
+      0.247354,
       0.24662,
-      0.246321,
-      0.246164,
-      0.242123,
+      0.246163,
+      0.238985,
       0.231355,
-      0.229624
+      0.230288,
+      0.229624,
+      0.227736,
+      0.221732,
+      0.21856,
+      0.216932
     ],
     "PROP": [
       "phylum",
@@ -106,24 +105,23 @@
       "ensemblID",
       "simplifiedMolecularInputLineEntrySystem",
       "geneticVariantFunctionalCategory",
-      "imageUrl",
-      "genomicCoordinates",
       "chromosomeSize",
-      "observedAllele",
-      "hg38GenomicPosition",
-      "hg19GenomicPosition",
       "virusHost",
       "strandOrientation",
-      "ncbiDNASequenceName",
       "<-geneID{typeOf:GeneGeneticVariantAssociation}->variantID",
       "<-variantID{typeOf:GeneGeneticVariantAssociation}->geneID",
       "ncbiProteinAccessionNumber",
+      "hgncID",
       "alleleType",
-      "hg38GenomicLocation",
       "ofVirusSpecies",
-      "hg19GenomicLocation",
-      "ncbiTaxonID",
-      "antigenType"
+      "hasGenomicCoordinates",
+      "ncbiTaxId",
+      "umlsConceptUniqueID",
+      "antigenType",
+      "alleleOrigin",
+      "<-diseaseID{typeOf:DiseaseGeneAssociation}->geneID",
+      "antibodyType",
+      "inChIKey"
     ]
   },
   "query_detection_debug_logs": {

server/integration_tests/test_data/detection_api_bio/whattypesofgenesarefgfr1,apoe,andache/debug_info.json

@@ -25,7 +25,7 @@
       0.400638,
       0.398746,
       0.398361,
-      0.390523,
+      0.390524,
       0.389033,
       0.388461,
       0.388382,
@@ -35,7 +35,7 @@
       0.385679,
       0.385434,
       0.385339,
-      0.381842,
+      0.381843,
       0.379705
     ],
     "MultiSV": {},
@@ -77,24 +77,23 @@
       0.65902,
       0.63579,
       0.63404,
-      0.617156,
+      0.617157,
       0.598812,
-      0.595879,
       0.585015,
       0.583271,
       0.581079,
       0.576904,
-      0.543242,
-      0.539973,
-      0.532047,
-      0.530959,
-      0.51427,
+      0.540855,
+      0.538974,
       0.512528,
       0.46106,
       0.444108,
-      0.398229,
-      0.394443,
-      0.39229
+      0.39229,
+      0.384802,
+      0.341795,
+      0.324578,
+      0.32201,
+      0.320837
     ],
     "PROP": [
       "typeOfGene",
@@ -107,22 +106,21 @@
       "<-diseaseID{typeOf:DiseaseGeneAssociation}->geneID",
       "<-compoundID{typeOf:ChemicalCompoundGeneticVariantAssociation}->variantID",
       "<-geneID{typeOf:DiseaseGeneAssociation}->diseaseID",
-      "genomicCoordinates",
       "antigenType",
       "<-variantID{typeOf:ChemicalCompoundGeneticVariantAssociation}->compoundID",
       "alleleType",
       "<-geneticVariantID{typeOf:DiseaseGeneticVariantAssociation}->diseaseID",
-      "hg19GenomicPosition",
-      "hasRNATranscript",
-      "hg19GenomicLocation",
-      "hg38GenomicPosition",
-      "hg38GenomicLocation",
+      "hgncID",
+      "hasGenomicCoordinates",
       "antibodyType",
       "chromosomeSize",
-      "referenceAlleleNCBI",
-      "observedAllele",
-      "ncbiDNASequenceName",
-      "alleleOrigin"
+      "referenceAllele",
+      "alleleOrigin",
+      "specializationOf",
+      "subClassificationOf",
+      "virusGenus",
+      "virusHost",
+      "ncbiProteinAccessionNumber"
     ]
   },
   "query_detection_debug_logs": {