[bio] Update biomed property embeddings.

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_06_16_50_25/embeddings.csv
     model: ft-final-v20230717230459-all-MiniLM-L6-v2
     healthcheck_query: "Gene"
   base_uae_lance:

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

@@ -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,
       0.246163,
-      0.242122,
       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",
+      "hasGenomicCoordinates",
       "chromosomeSize",
-      "observedAllele",
-      "hg38GenomicPosition",
-      "hg19GenomicPosition",
       "virusHost",
       "strandOrientation",
-      "ncbiDNASequenceName",
       "<-geneID{typeOf:GeneGeneticVariantAssociation}->variantID",
       "<-variantID{typeOf:GeneGeneticVariantAssociation}->geneID",
       "ncbiProteinAccessionNumber",
+      "hgncID",
       "alleleType",
-      "hg38GenomicLocation",
       "ofVirusSpecies",
-      "hg19GenomicLocation",
-      "ncbiTaxonID",
-      "antigenType"
+      "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

@@ -83,17 +83,15 @@
       0.583271,
       0.581079,
       0.576904,
-      0.543242,
-      0.539973,
-      0.532047,
-      0.530959,
-      0.51427,
+      0.540855,
       0.512528,
       0.46106,
       0.444108,
-      0.398229,
-      0.394443,
-      0.39229
+      0.39229,
+      0.384802,
+      0.341795,
+      0.324578,
+      0.32201
     ],
     "PROP": [
       "typeOfGene",
@@ -106,22 +104,20 @@
       "<-diseaseID{typeOf:DiseaseGeneAssociation}->geneID",
       "<-compoundID{typeOf:ChemicalCompoundGeneticVariantAssociation}->variantID",
       "<-geneID{typeOf:DiseaseGeneAssociation}->diseaseID",
-      "genomicCoordinates",
+      "hasGenomicCoordinates",
       "antigenType",
       "<-variantID{typeOf:ChemicalCompoundGeneticVariantAssociation}->compoundID",
       "alleleType",
       "<-geneticVariantID{typeOf:DiseaseGeneticVariantAssociation}->diseaseID",
-      "hg19GenomicPosition",
-      "hasRNATranscript",
-      "hg19GenomicLocation",
-      "hg38GenomicPosition",
-      "hg38GenomicLocation",
+      "hgncID",
       "antibodyType",
       "chromosomeSize",
-      "referenceAlleleNCBI",
-      "observedAllele",
-      "ncbiDNASequenceName",
-      "alleleOrigin"
+      "referenceAllele",
+      "alleleOrigin",
+      "specializationOf",
+      "subClassificationOf",
+      "virusGenus",
+      "virusHost"
     ]
   },
   "query_detection_debug_logs": {

server/integration_tests/test_data/e2e_triple/whattranscriptsdoesithave/chart_config.json

@@ -1,53 +1,15 @@
 {
   "client": "test_detect-and-fulfill",
-  "config": {
-    "categories": [
-      {
-        "blocks": [
-          {
-            "columns": [
-              {
-                "tiles": [
-                  {
-                    "entities": [
-                      "bio/FGFR1"
-                    ],
-                    "type": "ENTITY_OVERVIEW"
-                  }
-                ]
-              }
-            ]
-          }
-        ]
-      }
-    ]
-  },
+  "config": {},
   "context": {},
   "debug": {},
-  "entities": [
-    {
-      "dcid": "bio/FGFR1",
-      "name": "FGFR1",
-      "type": ""
-    }
-  ],
-  "pastSourceContext": "",
-  "place": {},
-  "placeFallback": {},
-  "placeSource": "UNKNOWN",
-  "places": [],
-  "relatedThings": {
-    "childPlaces": {},
-    "childTopics": [],
-    "exploreMore": {},
-    "mainTopics": [],
-    "parentPlaces": [],
-    "parentTopics": [],
-    "peerPlaces": [],
-    "peerTopics": []
+  "failure": "Sorry, could not complete your request. No entity found in the query.",
+  "place": {
+    "dcid": "",
+    "name": "",
+    "place_type": ""
   },
-  "svSource": "UNKNOWN",
   "userMessages": [
-    "See relevant information for FGFR1 based on the previous query."
+    "Sorry, could not complete your request. No entity found in the query."
   ]
 }

tools/nl/embeddings/input/bio/_preindex.csv

@@ -1,5 +1,4 @@
 sentence,dcid
-"""UMLS CUI""",unifiedMedicalLanguageSystemConceptUniqueIdentifier
 A specific organism or taxonomic group of organisms that are susceptible to be infected by a virus,virusHost
 A unique ID for a Medical Subject Heading Descriptor record,medicalSubjectHeadingDescriptorID
 A unique ID for a Medical Subject Heading supplementary record,medicalSubjectHeadingSupplementaryRecordID
@@ -17,51 +16,43 @@ Gene associated with a disease,<-diseaseID{typeOf:DiseaseGeneAssociation}->geneI
 Gene associated with a genetic variant,<-variantID{typeOf:GeneGeneticVariantAssociation}->geneID
 Genetic variant associated with a disease,<-diseaseID{typeOf:DiseaseGeneticVariantAssociation}->geneticVariantID
 GeneticVariantGeneAssociation,<-geneID{typeOf:GeneGeneticVariantAssociation}->variantID;<-variantID{typeOf:GeneGeneticVariantAssociation}->geneID
+HUGO Gene Nomenclature Committee identifier,hgncID
+InChIKey,inChIKey
+International Chemical Identifier (InChI) Key,inChIKey
+MOA,mechanismOfAction
 MeSH descriptor record ID,medicalSubjectHeadingDescriptorID
 MeSH supplementary record ID,medicalSubjectHeadingSupplementaryRecordID
-NCBI Taxonomy database identifier,ncbiTaxonID
-NCBI defined segment of DNA sequence name,ncbiDNASequenceName
+NCBI Taxonomy database identifier,ncbiTaxId
 NCBI protein accession number,ncbiProteinAccessionNumber
-Name used by NIH NCBI to refer to a segment of DNA sequence,ncbiDNASequenceName
 OMIM database identifier,omimID
 Origin of variant allele,alleleOrigin
-RNA transcript that a gene has,hasRNATranscript
-Recorded transcript,hasRNATranscript
-Reference genomic sequence from dbSNP,referenceAlleleNCBI
+Reference genomic sequence from dbSNP,referenceAllele
 Simplified Molecular Input Line Entry System (SMILE),simplifiedMolecularInputLineEntrySystem
 Size of chromosome,chromosomeSize
 Systematiized Nomenclature of Medicine (SNOMED) clinical terms (CT) code,snomedCT
 The allele of a genetic variant observed within a population,alleleType
 "The disease diagnosis code for version 10 of the International Classification of Diseases (ICD), Clinical Modification",icd10CMCode
-The genomic location of a genetic variant using the hg19 assembly,hg19GenomicLocation
-The genomic location of a genetic variant using the hg38 assembly,hg38GenomicLocation
-The genomic position of a genetic variant using the hg19 assembly,hg19GenomicPosition
-The genomic position of a genetic variant using the hg38 assembly,hg38GenomicPosition
 The method by which a drug is administered,administrationRoute
-The name of the disease,diseaseName
 The orientation of the strand on which an annotation is located,strandOrientation
-The sequences of the observed alleles from rs-fasta files.,observedAllele
 The species of a virus isolate,ofVirusSpecies
 The strand on which a given annotation is located,strandOrientation
 The type of gene,typeOfGene
 Type of allele,alleleType
-Unified Medical Language System (UMLS) Concept Unique Identifier (CUI),unifiedMedicalLanguageSystemConceptUniqueIdentifier
+UMLS CUI,umlsConceptUniqueID
+Unified Medical Language System (UMLS) Concept Unique Identifier (CUI),umlsConceptUniqueID
 Variant allele origin,alleleOrigin
 activeIngredient,activeIngredient
 administrationRoute,administrationRoute
 alleleOrigin,alleleOrigin
 alleleType,alleleType
 antibodyType,antibodyType
 antigenType,antigenType
-availableStrength,availableStrength
 chemblID,chemblID
 chemical compound associated with a genetic variant,<-variantID{typeOf:ChemicalCompoundGeneticVariantAssociation}->compoundID
 chromosomeSize,chromosomeSize
 class,class
 "component that provides pharmacological activity or other direct effect in the diagnosis, cure, mitigation, treatment, or prevention of disease, or to affect the structure or any function of the body of man or animals",activeIngredient
-diseaseName,diseaseName
 dosageForm,dosageForm
-dose approved for a drug,availableStrength
 ensemblID,ensemblID
 full name of the gene,fullName
 fullName,fullName
@@ -70,43 +61,36 @@ geneID,geneID
 genetic variant associated with a chemical compound,<-compoundID{typeOf:ChemicalCompoundGeneticVariantAssociation}->variantID
 genetic variant associated with a gene,<-geneID{typeOf:GeneGeneticVariantAssociation}->variantID
 geneticVariantFunctionalCategory,geneticVariantFunctionalCategory
-genomic coordinates,genomicCoordinates
-genomicCoordinates,genomicCoordinates
+genomic coordinates,hasGenomicCoordinates
+genomicCoordinates,hasGenomicCoordinates
 genus of a virus species,virusGenus
-hasRNATranscript,hasRNATranscript
-hg19GenomicLocation,hg19GenomicLocation
-hg19GenomicPosition,hg19GenomicPosition
-hg38GenomicLocation,hg38GenomicLocation
-hg38GenomicPosition,hg38GenomicPosition
+hgncID,hgncID
 host of a virus,virusHost
 icd10CMCode,icd10CMCode
-imageUrl,imageUrl
+mechanismOfAction,mechanismOfAction
 medicalSubjectHeadingDescriptorID,medicalSubjectHeadingDescriptorID
 medicalSubjectHeadingSupplementaryRecordID,medicalSubjectHeadingSupplementaryRecordID
-ncbiDNASequenceName,ncbiDNASequenceName
 ncbiProteinAccessionNumber,ncbiProteinAccessionNumber
-ncbiTaxonID,ncbiTaxonID
+ncbiTaxID,ncbiTaxId
 number of nucleotides in a chromosome,chromosomeSize
-observedAllele,observedAllele
 ofVirusSpecies,ofVirusSpecies
 omimID,omimID
 phylum,phylum
 physical form in which a drug is produced and dispensed,dosageForm
-preferred disease name for the concept specified by disease identifiers,diseaseName
-reference allele,referenceAlleleNCBI
-referenceAlleleNCBI,referenceAlleleNCBI
+reference allele,referenceAllele
+referenceAllele,referenceAllele
+referenceAlleleNCBI,referenceAllele
 simplifiedMolecularInputLineEntrySystem,simplifiedMolecularInputLineEntrySystem
 snomedCT,snomedCT
 specialization of,specializationOf
 specializationOf,specializationOf
 strandOrientation,strandOrientation
 subClassificationOf,subClassificationOf
 subclassification of,subClassificationOf
+the biochemcial interaction through which a drug produces a pharmacological effect,mechanismOfAction
 type of antibody,antibodyType
 type of antigen,antigenType
 typeOfGene,typeOfGene
-unifiedMedicalLanguageSystemConceptUniqueIdentifier,unifiedMedicalLanguageSystemConceptUniqueIdentifier
-url to an image of what the biological specimen looks like,imageUrl
+umlsConceptUniqueID,umlsConceptUniqueID
 virusGenus,virusGenus
 virusHost,virusHost
-what the entity looks like,imageUrl

tools/nl/embeddings/input/bio/sheets_svs.csv

@@ -1,30 +1,26 @@
 dcid,sentence
 ofVirusSpecies,ofVirusSpecies;The species of a virus isolate
 virusHost,virusHost;A specific organism or taxonomic group of organisms that are susceptible to be infected by a virus;host of a virus
-ncbiTaxonID,ncbiTaxonID;NCBI Taxonomy database identifier
-diseaseName,diseaseName;preferred disease name for the concept specified by disease identifiers;The name of the disease
-observedAllele,observedAllele;The sequences of the observed alleles from rs-fasta files.
-referenceAlleleNCBI,referenceAlleleNCBI;Reference genomic sequence from dbSNP;reference allele
+ncbiTaxId,ncbiTaxID;NCBI Taxonomy database identifier
+referenceAllele,referenceAllele;referenceAlleleNCBI;Reference genomic sequence from dbSNP;reference allele
 class,class
 phylum,phylum
 geneticVariantFunctionalCategory,geneticVariantFunctionalCategory;Functional category of the genetic variant
-hg19GenomicPosition,hg19GenomicPosition;The genomic position of a genetic variant using the hg19 assembly
-hg19GenomicLocation,hg19GenomicLocation;The genomic location of a genetic variant using the hg19 assembly
-hg38GenomicPosition,hg38GenomicPosition;The genomic position of a genetic variant using the hg38 assembly
-hg38GenomicLocation,hg38GenomicLocation;The genomic location of a genetic variant using the hg38 assembly
-hasRNATranscript,hasRNATranscript;Recorded transcript;RNA transcript that a gene has
+hgncID,hgncID;HUGO Gene Nomenclature Committee identifier
+inChIKey,InChIKey;International Chemical Identifier (InChI) Key
 strandOrientation,strandOrientation;The strand on which a given annotation is located;The orientation of the strand on which an annotation is located
 typeOfGene,typeOfGene;The type of gene
 omimID,omimID;OMIM database identifier
 icd10CMCode,"icd10CMCode;The disease diagnosis code for version 10 of the International Classification of Diseases (ICD), Clinical Modification"
 subClassificationOf,subClassificationOf;subclassification of
 snomedCT,snomedCT;Systematiized Nomenclature of Medicine (SNOMED) clinical terms (CT) code
-unifiedMedicalLanguageSystemConceptUniqueIdentifier,"unifiedMedicalLanguageSystemConceptUniqueIdentifier;Unified Medical Language System (UMLS) Concept Unique Identifier (CUI);""UMLS CUI"""
+umlsConceptUniqueID,umlsConceptUniqueID;Unified Medical Language System (UMLS) Concept Unique Identifier (CUI);UMLS CUI
 specializationOf,specializationOf;specialization of
 chemblID,chemblID;ChEMBL identifier
 simplifiedMolecularInputLineEntrySystem,simplifiedMolecularInputLineEntrySystem;Simplified Molecular Input Line Entry System (SMILE)
 medicalSubjectHeadingSupplementaryRecordID,medicalSubjectHeadingSupplementaryRecordID;A unique ID for a Medical Subject Heading supplementary record;An ID for a Medical Subject Heading supplementary record;MeSH supplementary record ID
 medicalSubjectHeadingDescriptorID,medicalSubjectHeadingDescriptorID;A unique ID for a Medical Subject Heading Descriptor record;An ID for a Medical Subject Heading descriptor record;MeSH descriptor record ID
+mechanismOfAction,mechanismOfAction;MOA;the biochemcial interaction through which a drug produces a pharmacological effect
 activeIngredient,"activeIngredient;component that provides pharmacological activity or other direct effect in the diagnosis, cure, mitigation, treatment, or prevention of disease, or to affect the structure or any function of the body of man or animals"
 administrationRoute,administrationRoute;The method by which a drug is administered
 dosageForm,dosageForm;physical form in which a drug is produced and dispensed
@@ -37,10 +33,7 @@ geneID,geneID;gene id
 ncbiProteinAccessionNumber,ncbiProteinAccessionNumber;NCBI protein accession number
 alleleOrigin,alleleOrigin;Variant allele origin;Origin of variant allele
 alleleType,alleleType;The allele of a genetic variant observed within a population;Type of allele
-ncbiDNASequenceName,ncbiDNASequenceName;NCBI defined segment of DNA sequence name;Name used by NIH NCBI to refer to a segment of DNA sequence
-imageUrl,imageUrl;url to an image of what the biological specimen looks like;what the entity looks like
-genomicCoordinates,genomicCoordinates;genomic coordinates
-availableStrength,availableStrength;dose approved for a drug
+hasGenomicCoordinates,genomicCoordinates;genomic coordinates
 <-variantID{typeOf:GeneGeneticVariantAssociation}->geneID,GeneticVariantGeneAssociation;Gene associated with a genetic variant
 <-geneID{typeOf:GeneGeneticVariantAssociation}->variantID,GeneticVariantGeneAssociation;genetic variant associated with a gene
 <-diseaseID{typeOf:DiseaseGeneAssociation}->geneID,DiseaseGeneAssociation;Gene associated with a disease