[bio] update multi-hop properties (datacommonsorg#4712)

- Add multi-hop properties needed for the hero queries - Update multi-hop properties where naming has changed from data cleanup - Update entity overview tile to link to the browser page for ease of testing
gmechali · Nov 5, 2024 · cf2ed57 · cf2ed57
1 parent 454b21f
commit cf2ed57
Show file tree

Hide file tree

Showing 13 changed files with 380 additions and 325 deletions.
diff --git a/deploy/nl/catalog.yaml b/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_06_24_23_40_05/embeddings.csv
+    embeddings_path: gs://datcom-nl-models/bio_ft_2024_11_05_09_59_39/embeddings.csv
     model: ft-final-v20230717230459-all-MiniLM-L6-v2
     healthcheck_query: "Gene"
   base_uae_lance:

diff --git a/server/config/nl_page/prop_titles.json b/server/config/nl_page/prop_titles.json
@@ -1,19 +1,35 @@
 {
-  "<-referenceSNPClusterID{typeOf:GeneticVariantGeneAssociation}->geneSymbol": {
+  "<-variantID{typeOf:GeneGeneticVariantAssociation}->geneID": {
     "displayName": "associated gene",
     "titleFormat": "The associated genes for {entity} are"
   }, 
-  "<-geneSymbol{typeOf:GeneticVariantGeneAssociation}->referenceSNPClusterID": {
+  "<-geneID{typeOf:GeneGeneticVariantAssociation}->variantID": {
     "displayName": "associated genetic variant",
     "titleFormat": "The associated genetic variants for {entity} are"
   }, 
-  "<-diseaseOntologyID{typeOf:DiseaseGeneAssociation}->geneID": {
+  "<-diseaseID{typeOf:DiseaseGeneAssociation}->geneID": {
     "displayName": "associated gene",
     "titleFormat": "The associated genes for {entity} are"
   }, 
-  "<-geneID{typeOf:DiseaseGeneAssociation}->diseaseOntologyID": {
+  "<-geneID{typeOf:DiseaseGeneAssociation}->diseaseID": {
     "displayName": "associated disease",
     "titleFormat": "The associated diseases for {entity} are"
+  }, 
+  "<-diseaseID{typeOf:DiseaseGeneticVariantAssociation}->geneticVariantID": {
+    "displayName": "associated genetic variant",
+    "titleFormat": "The associated genetic variants for {entity} are"
+  }, 
+  "<-geneticVariantID{typeOf:DiseaseGeneticVariantAssociation}->diseaseID": {
+    "displayName": "associated disease",
+    "titleFormat": "The associated diseases for {entity} are"
+  },
+  "<-compoundID{typeOf:ChemicalCompoundGeneticVariantAssociation}->variantID": {
+    "displayName": "associated genetic variant",
+    "titleFormat": "The associated genetic variants for {entity} are"
+  }, 
+  "<-variantID{typeOf:ChemicalCompoundGeneticVariantAssociation}->compoundID": {
+    "displayName": "associated chemical compound",
+    "titleFormat": "The associated chemical compounds for {entity} are"
   },
   "->mRNA": {
     "displayName": "mRNA"

diff --git a/server/integration_tests/test_data/detection_api_bio/whatisthephylumofvolvox/debug_info.json b/server/integration_tests/test_data/detection_api_bio/whatisthephylumofvolvox/debug_info.json
@@ -11,28 +11,28 @@
   "sv_matching": {
     "CosineScore": [
       0.35510897636413574,
-      0.3460872769355774,
+      0.3460870683193207,
       0.3452577292919159,
-      0.344845712184906,
-      0.34113651514053345,
-      0.3384983241558075,
-      0.3349902033805847,
-      0.3316609561443329,
-      0.3260059356689453,
-      0.32424432039260864,
-      0.3206062316894531,
+      0.34484589099884033,
+      0.3411366045475006,
+      0.3384982645511627,
+      0.3349902629852295,
+      0.3316609263420105,
+      0.32600605487823486,
+      0.3242444694042206,
+      0.32060620188713074,
       0.31426557898521423,
-      0.3127653896808624,
-      0.31262922286987305,
-      0.31250447034835815,
-      0.31177398562431335,
-      0.31033921241760254,
-      0.31007489562034607,
-      0.30988338589668274,
-      0.3080539405345917,
-      0.30745869874954224,
-      0.30719631910324097,
-      0.3039420247077942
+      0.3127654492855072,
+      0.3126293420791626,
+      0.31250452995300293,
+      0.31177404522895813,
+      0.3103388845920563,
+      0.3100748658180237,
+      0.3098835051059723,
+      0.3080541491508484,
+      0.3074587285518646,
+      0.3071962296962738,
+      0.30394214391708374
     ],
     "MultiSV": {},
     "Query": "what is the phylum of",
@@ -64,39 +64,42 @@
   },
   "props_matching": {
     "CosineScore": [
-      0.9999998807907104,
-      0.4752839505672455,
-      0.36154165863990784,
-      0.34200993180274963,
-      0.3293309211730957,
-      0.31845176219940186,
-      0.31466981768608093,
-      0.3083951473236084,
-      0.3079407513141632,
-      0.30463001132011414,
-      0.28270864486694336,
-      0.28187549114227295,
-      0.2808278203010559,
-      0.2804529666900635,
-      0.27429836988449097,
-      0.27150505781173706,
-      0.2707182466983795,
-      0.26954683661460876,
-      0.2599008083343506,
-      0.2599008083343506,
-      0.24827907979488373,
-      0.24662044644355774,
-      0.24632112681865692,
-      0.24616354703903198,
-      0.24212250113487244,
-      0.23135541379451752,
-      0.2296244502067566,
-      0.22773587703704834
+      1.0000001192092896,
+      0.47528401017189026,
+      0.3615417182445526,
+      0.34543079137802124,
+      0.34543079137802124,
+      0.3420097231864929,
+      0.3293308615684509,
+      0.318451464176178,
+      0.31466978788375854,
+      0.308395117521286,
+      0.30794060230255127,
+      0.3046301007270813,
+      0.2827085852622986,
+      0.281875342130661,
+      0.28082770109176636,
+      0.2804528772830963,
+      0.2742983400821686,
+      0.2715050280094147,
+      0.27071818709373474,
+      0.2695467472076416,
+      0.25990068912506104,
+      0.25990068912506104,
+      0.24827904999256134,
+      0.24662022292613983,
+      0.24632100760936737,
+      0.2461635172367096,
+      0.24212227761745453,
+      0.23135530948638916,
+      0.2296244353055954
     ],
     "PROP": [
       "phylum",
       "chemblID",
       "geneID",
+      "<-compoundID{typeOf:ChemicalCompoundGeneticVariantAssociation}->variantID",
+      "<-variantID{typeOf:ChemicalCompoundGeneticVariantAssociation}->compoundID",
       "virusGenus",
       "typeOfGene",
       "fullName",
@@ -112,16 +115,15 @@
       "virusHost",
       "strandOrientation",
       "ncbiDNASequenceName",
-      "<-geneSymbol{typeOf:GeneticVariantGeneAssociation}->referenceSNPClusterID",
-      "<-referenceSNPClusterID{typeOf:GeneticVariantGeneAssociation}->geneSymbol",
+      "<-geneID{typeOf:GeneGeneticVariantAssociation}->variantID",
+      "<-variantID{typeOf:GeneGeneticVariantAssociation}->geneID",
       "ncbiProteinAccessionNumber",
       "alleleType",
       "hg38GenomicLocation",
       "ofVirusSpecies",
       "hg19GenomicLocation",
       "ncbiTaxonID",
-      "antigenType",
-      "alleleOrigin"
+      "antigenType"
     ]
   },
   "query_detection_debug_logs": {

diff --git a/...n_tests/test_data/detection_api_bio/whattypesofgenesarefgfr1,apoe,andache/debug_info.json b/...n_tests/test_data/detection_api_bio/whattypesofgenesarefgfr1,apoe,andache/debug_info.json
@@ -12,30 +12,30 @@
   "query_with_places_removed": "what types of genes are and",
   "sv_matching": {
     "CosineScore": [
-      0.5237788558006287,
-      0.44518929719924927,
-      0.4198145568370819,
+      0.5237791538238525,
+      0.4451894760131836,
+      0.4198145866394043,
       0.41922125220298767,
-      0.4136667251586914,
-      0.4096524715423584,
-      0.4066111147403717,
-      0.40137141942977905,
-      0.40101921558380127,
+      0.41366666555404663,
+      0.4096527099609375,
+      0.4066110849380493,
+      0.4013715386390686,
+      0.4010191559791565,
       0.40063756704330444,
-      0.3987462520599365,
-      0.3983607292175293,
-      0.39052334427833557,
-      0.3890331983566284,
-      0.38846108317375183,
+      0.39874646067619324,
+      0.39836058020591736,
+      0.39052361249923706,
+      0.38903331756591797,
+      0.3884609639644623,
       0.3883824050426483,
-      0.3873300850391388,
-      0.3864220678806305,
-      0.38589635491371155,
-      0.385678768157959,
-      0.3854341208934784,
-      0.38533875346183777,
-      0.3818424642086029,
-      0.37970471382141113
+      0.3873301148414612,
+      0.38642188906669617,
+      0.3858962655067444,
+      0.3856789469718933,
+      0.3854343295097351,
+      0.38533878326416016,
+      0.38184264302253723,
+      0.37970495223999023
     ],
     "MultiSV": {},
     "Query": "what types of genes are and",
@@ -68,42 +68,49 @@
   },
   "props_matching": {
     "CosineScore": [
-      0.9086108803749084,
-      0.7445291876792908,
-      0.7330227494239807,
-      0.7175889611244202,
-      0.6834693551063538,
+      0.9086110591888428,
+      0.7445294260978699,
+      0.7330226898193359,
+      0.7175887823104858,
+      0.6834690570831299,
       0.6590196490287781,
-      0.6340398192405701,
-      0.5988121628761292,
-      0.595878541469574,
-      0.5850147604942322,
-      0.5810789465904236,
+      0.6357895731925964,
+      0.6340402364730835,
+      0.6171568036079407,
+      0.5988123416900635,
+      0.5958784818649292,
+      0.5850145220756531,
+      0.5832706689834595,
+      0.5810792446136475,
+      0.576904296875,
       0.5432419776916504,
-      0.5399730205535889,
+      0.5399729013442993,
       0.5320467948913574,
-      0.5309585928916931,
-      0.5142701268196106,
-      0.5125278830528259,
-      0.4610598683357239,
-      0.4441079795360565,
-      0.3982292413711548,
-      0.3944430947303772,
-      0.3922898471355438,
-      0.38480237126350403
+      0.5309585332870483,
+      0.5142703056335449,
+      0.5125279426574707,
+      0.46105992794036865,
+      0.4441080689430237,
+      0.39822953939437866,
+      0.3944427967071533,
+      0.39229002594947815
     ],
     "PROP": [
       "typeOfGene",
       "geneticVariantFunctionalCategory",
-      "<-referenceSNPClusterID{typeOf:GeneticVariantGeneAssociation}->geneSymbol",
-      "<-geneSymbol{typeOf:GeneticVariantGeneAssociation}->referenceSNPClusterID",
+      "<-variantID{typeOf:GeneGeneticVariantAssociation}->geneID",
+      "<-geneID{typeOf:GeneGeneticVariantAssociation}->variantID",
       "fullName",
       "geneID",
-      "<-diseaseOntologyID{typeOf:DiseaseGeneAssociation}->geneID",
-      "<-geneID{typeOf:DiseaseGeneAssociation}->diseaseOntologyID",
+      "<-diseaseID{typeOf:DiseaseGeneticVariantAssociation}->geneticVariantID",
+      "<-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",
@@ -114,8 +121,7 @@
       "referenceAlleleNCBI",
       "observedAllele",
       "ncbiDNASequenceName",
-      "alleleOrigin",
-      "specializationOf"
+      "alleleOrigin"
     ]
   },
   "query_detection_debug_logs": {