From cf2ed57452e85821188a55afe1b299f1e378b0f6 Mon Sep 17 00:00:00 2001 From: chejennifer <69875368+chejennifer@users.noreply.github.com> Date: Tue, 5 Nov 2024 13:18:35 -0800 Subject: [PATCH] [bio] update multi-hop properties (#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 --- deploy/nl/catalog.yaml | 2 +- server/config/nl_page/prop_titles.json | 24 +++- .../whatisthephylumofvolvox/debug_info.json | 106 ++++++++------- .../debug_info.json | 100 +++++++------- .../debug_info.json | 90 ++++++------ .../compareobesityvs.poverty/debug_info.json | 64 ++++----- .../debug_info.json | 84 ++++++------ .../debug_info.json | 128 +++++++++--------- .../debug_info.json | 54 ++++---- .../chart_config.json | 18 +++ .../components/tiles/entity_overview_tile.tsx | 5 +- tools/nl/embeddings/input/bio/_preindex.csv | 18 ++- tools/nl/embeddings/input/bio/sheets_svs.csv | 12 +- 13 files changed, 380 insertions(+), 325 deletions(-) diff --git a/deploy/nl/catalog.yaml b/deploy/nl/catalog.yaml index de54d5294c..9cb901f293 100644 --- 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 index 4a7e7e3257..3cf8c9cbc0 100644 --- 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 index 88264f8460..e434859d40 100644 --- 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/server/integration_tests/test_data/detection_api_bio/whattypesofgenesarefgfr1,apoe,andache/debug_info.json b/server/integration_tests/test_data/detection_api_bio/whattypesofgenesarefgfr1,apoe,andache/debug_info.json index 0d288676b2..4f8acbe246 100644 --- a/server/integration_tests/test_data/detection_api_bio/whattypesofgenesarefgfr1,apoe,andache/debug_info.json +++ b/server/integration_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": { diff --git a/server/integration_tests/test_data/detection_api_multivar/comparemalepopulationwithfemalepopulation/debug_info.json b/server/integration_tests/test_data/detection_api_multivar/comparemalepopulationwithfemalepopulation/debug_info.json index 6911e00711..9c720a8739 100644 --- a/server/integration_tests/test_data/detection_api_multivar/comparemalepopulationwithfemalepopulation/debug_info.json +++ b/server/integration_tests/test_data/detection_api_multivar/comparemalepopulationwithfemalepopulation/debug_info.json @@ -8,43 +8,43 @@ "query_with_places_removed": "compare male population with female population", "sv_matching": { "CosineScore": [ - 0.9187589883804321, - 0.8590542674064636, + 0.9187595844268799, + 0.8590543866157532, 0.8354092836380005, - 0.7823135852813721, - 0.7773193120956421, + 0.7823134660720825, + 0.7773187756538391, 0.7762894630432129, 0.7663271427154541, - 0.7661072611808777, - 0.7614185810089111, - 0.7606043219566345, - 0.7595799565315247, - 0.7573726773262024, - 0.757302463054657, - 0.7572974562644958, - 0.7553005814552307, - 0.753344714641571, - 0.7532935738563538, - 0.7509563565254211, - 0.7482579350471497, - 0.7451451420783997, - 0.7443950176239014, - 0.7431556582450867, - 0.7426689267158508, - 0.7396599650382996, - 0.7371536493301392, - 0.7365996241569519, - 0.7347152829170227, - 0.7336517572402954, - 0.7326081991195679, - 0.7325156927108765, - 0.7302993535995483, - 0.729926347732544, + 0.766107439994812, + 0.7614184617996216, + 0.7606041431427002, + 0.7595797181129456, + 0.7573733329772949, + 0.7573024034500122, + 0.757297158241272, + 0.7553009390830994, + 0.7533451318740845, + 0.7532937526702881, + 0.7509560585021973, + 0.7482578754425049, + 0.7451456785202026, + 0.7443947792053223, + 0.7431552410125732, + 0.7426693439483643, + 0.7396597862243652, + 0.7371534109115601, + 0.7366002798080444, + 0.7347153425216675, + 0.733651876449585, + 0.732607901096344, + 0.7325160503387451, + 0.7302997708320618, + 0.7299268841743469, 0.7289118766784668, - 0.728903591632843, - 0.7280725836753845, - 0.7259583473205566, - 0.7259331345558167 + 0.7289034724235535, + 0.7280722260475159, + 0.7259584665298462, + 0.7259330153465271 ], "MultiSV": { "Candidates": [ @@ -54,7 +54,7 @@ "Parts": [ { "CosineScore": [ - 0.9257851839065552 + 0.9257858991622925 ], "QueryPart": "male population", "SV": [ @@ -63,8 +63,8 @@ }, { "CosineScore": [ - 0.92969810962677, - 0.8847430348396301 + 0.9296979904174805, + 0.884743332862854 ], "QueryPart": "female population", "SV": [ @@ -80,7 +80,7 @@ "Parts": [ { "CosineScore": [ - 0.9117769002914429 + 0.911777138710022 ], "QueryPart": "male population female", "SV": [ @@ -89,8 +89,8 @@ }, { "CosineScore": [ - 0.8982371687889099, - 0.8723466992378235 + 0.8982378840446472, + 0.8723467588424683 ], "QueryPart": "population", "SV": [ @@ -106,10 +106,10 @@ "Parts": [ { "CosineScore": [ - 0.8088874816894531, - 0.8034244179725647, - 0.8017649054527283, - 0.7751561999320984 + 0.808887243270874, + 0.8034241199493408, + 0.8017654418945312, + 0.775155782699585 ], "QueryPart": "male", "SV": [ @@ -121,8 +121,8 @@ }, { "CosineScore": [ - 0.9170326590538025, - 0.8730189204216003 + 0.9170327186584473, + 0.873018741607666 ], "QueryPart": "population female population", "SV": [ diff --git a/server/integration_tests/test_data/detection_api_multivar/compareobesityvs.poverty/debug_info.json b/server/integration_tests/test_data/detection_api_multivar/compareobesityvs.poverty/debug_info.json index 2717973e61..83ff52431b 100644 --- a/server/integration_tests/test_data/detection_api_multivar/compareobesityvs.poverty/debug_info.json +++ b/server/integration_tests/test_data/detection_api_multivar/compareobesityvs.poverty/debug_info.json @@ -8,35 +8,35 @@ "query_with_places_removed": "compare obesity vs poverty", "sv_matching": { "CosineScore": [ - 0.8778440952301025, - 0.7967696785926819, - 0.7624966502189636, - 0.7499464750289917, - 0.7484046220779419, - 0.744289755821228, - 0.7357544302940369, - 0.7350348830223083, - 0.7310351729393005, - 0.7289621829986572, - 0.7266256213188171, - 0.7264258861541748, - 0.7264258861541748, - 0.7253912091255188, + 0.8778442740440369, + 0.7967699766159058, + 0.762496829032898, + 0.7499465942382812, + 0.7484047412872314, + 0.7442895174026489, + 0.7357541918754578, + 0.7350349426269531, + 0.7310354709625244, + 0.7289618253707886, + 0.7266261577606201, + 0.7264261841773987, + 0.7264261841773987, + 0.7253916263580322, 0.7230079174041748, - 0.713947594165802, - 0.7126947641372681, - 0.7094854116439819, - 0.7085545659065247, - 0.7085544466972351, - 0.7078820466995239, - 0.7077706456184387, - 0.7045392394065857, - 0.7024305462837219, - 0.7004537582397461, - 0.6994994878768921, - 0.695670485496521, - 0.6947909593582153, - 0.6913240551948547 + 0.7139475345611572, + 0.7126950621604919, + 0.7094853520393372, + 0.7085550427436829, + 0.7085551023483276, + 0.7078822255134583, + 0.7077707052230835, + 0.7045387029647827, + 0.7024303078651428, + 0.7004534602165222, + 0.6994997262954712, + 0.6956704258918762, + 0.6947906613349915, + 0.6913242936134338 ], "MultiSV": { "Candidates": [ @@ -46,10 +46,10 @@ "Parts": [ { "CosineScore": [ - 0.8467828035354614, - 0.8316561579704285, - 0.8201544284820557, - 0.8177065253257751 + 0.8467836380004883, + 0.8316553831100464, + 0.8201552033424377, + 0.8177061080932617 ], "QueryPart": "obesity", "SV": [ diff --git a/server/integration_tests/test_data/detection_api_multivar/howarefactorslikeobesity,bloodpressureandasthmaimpactedbyclimatechange/debug_info.json b/server/integration_tests/test_data/detection_api_multivar/howarefactorslikeobesity,bloodpressureandasthmaimpactedbyclimatechange/debug_info.json index fdb51b9dd8..bef680e6ec 100644 --- a/server/integration_tests/test_data/detection_api_multivar/howarefactorslikeobesity,bloodpressureandasthmaimpactedbyclimatechange/debug_info.json +++ b/server/integration_tests/test_data/detection_api_multivar/howarefactorslikeobesity,bloodpressureandasthmaimpactedbyclimatechange/debug_info.json @@ -8,34 +8,34 @@ "query_with_places_removed": "how are factors like obesity , blood pressure and asthma impacted by climate change", "sv_matching": { "CosineScore": [ - 0.7864788770675659, - 0.7135568261146545, - 0.691805899143219, - 0.6740916967391968, - 0.6734588742256165, - 0.670462429523468, - 0.6635114550590515, - 0.6593927145004272, - 0.6520175337791443, - 0.6484816074371338, + 0.7864793539047241, + 0.7135567665100098, + 0.691805362701416, + 0.6740915179252625, + 0.6734591722488403, + 0.6704620718955994, + 0.6635113954544067, + 0.6593924760818481, + 0.6520178318023682, + 0.6484817266464233, 0.6461696624755859, - 0.6459028124809265, - 0.6435540914535522, + 0.6459026336669922, + 0.6435545682907104, 0.6410900354385376, - 0.640523374080658, - 0.6402111649513245, - 0.6384206414222717, - 0.6380341053009033, - 0.6376466751098633, - 0.6346374154090881, - 0.6341455578804016, + 0.6405231952667236, + 0.6402113437652588, + 0.6384210586547852, + 0.6380343437194824, + 0.6376464366912842, + 0.6346377730369568, + 0.6341456174850464, 0.6338476538658142, - 0.632270336151123, - 0.6322208046913147, - 0.6304947137832642, - 0.6302966475486755, - 0.6298351287841797, - 0.6295675039291382 + 0.6322696805000305, + 0.6322205662727356, + 0.6304948925971985, + 0.6302965879440308, + 0.6298357844352722, + 0.6295678019523621 ], "MultiSV": { "Candidates": [ @@ -45,7 +45,7 @@ "Parts": [ { "CosineScore": [ - 0.7997785806655884 + 0.7997788786888123 ], "QueryPart": "factors like obesity blood pressure asthma impacted", "SV": [ @@ -54,7 +54,7 @@ }, { "CosineScore": [ - 1.000000238418579 + 1.0 ], "QueryPart": "climate change", "SV": [ @@ -69,11 +69,11 @@ "Parts": [ { "CosineScore": [ - 0.7588625550270081, - 0.7463639974594116, - 0.740165114402771, - 0.7351229190826416, - 0.7130995392799377 + 0.7588618993759155, + 0.7463642954826355, + 0.740165650844574, + 0.7351235151290894, + 0.7130995988845825 ], "QueryPart": "factors like obesity", "SV": [ @@ -86,7 +86,7 @@ }, { "CosineScore": [ - 1.0000003576278687 + 0.9999995827674866 ], "QueryPart": "blood pressure", "SV": [ @@ -95,8 +95,8 @@ }, { "CosineScore": [ - 0.8255704641342163, - 0.802787184715271 + 0.8255698084831238, + 0.8027870655059814 ], "QueryPart": "asthma impacted climate change", "SV": [ @@ -112,9 +112,9 @@ "Parts": [ { "CosineScore": [ - 0.7768431305885315, - 0.7495043873786926, - 0.7342660427093506, + 0.7768431901931763, + 0.7495046257972717, + 0.7342654466629028, 0.7325114011764526 ], "QueryPart": "factors like obesity blood pressure asthma", @@ -127,7 +127,7 @@ }, { "CosineScore": [ - 0.9056915044784546 + 0.9056921005249023 ], "QueryPart": "impacted climate change", "SV": [ @@ -142,7 +142,7 @@ "Parts": [ { "CosineScore": [ - 0.8207898736000061 + 0.8207905888557434 ], "QueryPart": "factors like obesity blood pressure", "SV": [ @@ -151,8 +151,8 @@ }, { "CosineScore": [ - 0.8255704641342163, - 0.802787184715271 + 0.8255698084831238, + 0.8027870655059814 ], "QueryPart": "asthma impacted climate change", "SV": [ diff --git a/server/integration_tests/test_data/detection_api_multivar/numberofpoorhispanicwomenwithphd/debug_info.json b/server/integration_tests/test_data/detection_api_multivar/numberofpoorhispanicwomenwithphd/debug_info.json index 88431aa490..9732c39707 100644 --- a/server/integration_tests/test_data/detection_api_multivar/numberofpoorhispanicwomenwithphd/debug_info.json +++ b/server/integration_tests/test_data/detection_api_multivar/numberofpoorhispanicwomenwithphd/debug_info.json @@ -8,46 +8,46 @@ "query_with_places_removed": "number of poor hispanic women with phd", "sv_matching": { "CosineScore": [ - 0.7985790967941284, - 0.788325846195221, - 0.7763473391532898, - 0.7740628719329834, - 0.741028904914856, - 0.7334664463996887, - 0.7228288054466248, - 0.7225687503814697, - 0.6995472311973572, - 0.6995018720626831, - 0.6976181268692017, - 0.6974342465400696, - 0.6960033774375916, - 0.6953437924385071, - 0.6945170760154724, - 0.6939643025398254, - 0.693536639213562, - 0.6908403635025024, - 0.690697431564331, - 0.6896734833717346, - 0.6889524459838867, - 0.6886194348335266, - 0.686329185962677, + 0.7985796332359314, + 0.7883262634277344, + 0.776346743106842, + 0.77406245470047, + 0.7410296201705933, + 0.7334667444229126, + 0.7228284478187561, + 0.722568929195404, + 0.6995474100112915, + 0.6995023488998413, + 0.697618305683136, + 0.6974341869354248, + 0.696003794670105, + 0.6953426003456116, + 0.6945168972015381, + 0.6939643621444702, + 0.6935360431671143, + 0.6908406019210815, + 0.6906974911689758, + 0.6896734237670898, + 0.6889521479606628, + 0.6886201500892639, + 0.6863292455673218, 0.6859177947044373, - 0.6827537417411804, - 0.6822136044502258, - 0.6815626621246338, - 0.6798743009567261, - 0.6768563985824585, - 0.6763087511062622, - 0.6751545071601868, - 0.6744989156723022, - 0.6725670695304871, - 0.6717979907989502, - 0.6691677570343018, - 0.6690006852149963, - 0.6682180166244507, - 0.6678112149238586, - 0.665069043636322, - 0.6648703813552856 + 0.6827540397644043, + 0.6822139620780945, + 0.6815624237060547, + 0.67987459897995, + 0.676856517791748, + 0.6763089299201965, + 0.6751540303230286, + 0.6744991540908813, + 0.6725671291351318, + 0.6717973947525024, + 0.6691675186157227, + 0.6690007448196411, + 0.6682180762290955, + 0.6678104400634766, + 0.6650688052177429, + 0.6648702621459961 ], "MultiSV": { "Candidates": [ @@ -57,17 +57,17 @@ "Parts": [ { "CosineScore": [ - 0.831177294254303, - 0.8310007452964783, - 0.8255155086517334, - 0.8195511698722839, - 0.8145607709884644, - 0.8090665936470032, - 0.8086387515068054, - 0.8074401021003723, - 0.8002946972846985, - 0.798579752445221, - 0.7878183722496033 + 0.8311771750450134, + 0.8310011029243469, + 0.8255152702331543, + 0.8195514678955078, + 0.8145602345466614, + 0.8090661764144897, + 0.8086389303207397, + 0.8074402809143066, + 0.8002950549125671, + 0.7985796332359314, + 0.787818193435669 ], "QueryPart": "number of poor hispanic", "SV": [ @@ -86,8 +86,8 @@ }, { "CosineScore": [ - 0.8318256139755249, - 0.8029921650886536 + 0.8318259119987488, + 0.8029923439025879 ], "QueryPart": "women phd", "SV": [ @@ -103,8 +103,8 @@ "Parts": [ { "CosineScore": [ - 0.836671769618988, - 0.7972695827484131 + 0.8366719484329224, + 0.7972691059112549 ], "QueryPart": "number of poor", "SV": [ @@ -114,10 +114,10 @@ }, { "CosineScore": [ - 0.8151502013206482, - 0.7885994911193848, - 0.7775559425354004, - 0.7752048969268799 + 0.8151505589485168, + 0.7885995507240295, + 0.7775554656982422, + 0.7752053141593933 ], "QueryPart": "hispanic women phd", "SV": [ @@ -135,8 +135,8 @@ "Parts": [ { "CosineScore": [ - 0.8495932221412659, - 0.8335015177726746 + 0.8495935201644897, + 0.8335005044937134 ], "QueryPart": "number of poor hispanic women", "SV": [ @@ -146,11 +146,11 @@ }, { "CosineScore": [ - 0.7646967172622681, + 0.7646968960762024, 0.7476688027381897, - 0.7377063632011414, - 0.7362765669822693, - 0.7305881977081299 + 0.7377066612243652, + 0.7362767457962036, + 0.7305882573127747 ], "QueryPart": "phd", "SV": [ diff --git a/server/integration_tests/test_data/detection_api_multivar/showmetheimpactofclimatechangeondrought/debug_info.json b/server/integration_tests/test_data/detection_api_multivar/showmetheimpactofclimatechangeondrought/debug_info.json index faec85fed8..6a9d2ab9e5 100644 --- a/server/integration_tests/test_data/detection_api_multivar/showmetheimpactofclimatechangeondrought/debug_info.json +++ b/server/integration_tests/test_data/detection_api_multivar/showmetheimpactofclimatechangeondrought/debug_info.json @@ -8,30 +8,30 @@ "query_with_places_removed": "show me the impact of climate change on drought", "sv_matching": { "CosineScore": [ - 0.8393685817718506, - 0.7931121587753296, - 0.7699977159500122, - 0.7208102941513062, - 0.7175307869911194, + 0.8393681645393372, + 0.79311203956604, + 0.7699974775314331, + 0.7208107709884644, + 0.7175306081771851, 0.6995436549186707, - 0.6863453984260559, - 0.674246072769165, - 0.673050582408905, - 0.6703541874885559, - 0.6652891635894775, - 0.6644605398178101, - 0.6353793740272522, - 0.6349935531616211, - 0.6347004175186157, - 0.6308181285858154, + 0.6863456964492798, + 0.674246609210968, + 0.6730499267578125, + 0.6703540682792664, + 0.6652892827987671, + 0.6644606590270996, + 0.6353792548179626, + 0.6349931359291077, + 0.6347004771232605, + 0.630818247795105, 0.6290862560272217, - 0.6256593465805054, - 0.6180377006530762, - 0.6162121891975403, - 0.6141721606254578, - 0.6139706969261169, - 0.6138609051704407, - 0.6123875379562378 + 0.6256592273712158, + 0.6180376410484314, + 0.6162123084068298, + 0.6141720414161682, + 0.6139707565307617, + 0.6138609647750854, + 0.6123877167701721 ], "MultiSV": { "Candidates": [ @@ -41,7 +41,7 @@ "Parts": [ { "CosineScore": [ - 0.8787480592727661 + 0.8787487149238586 ], "QueryPart": "show climate change", "SV": [ @@ -50,7 +50,7 @@ }, { "CosineScore": [ - 1.000000238418579 + 1.0 ], "QueryPart": "drought", "SV": [ @@ -65,8 +65,8 @@ "Parts": [ { "CosineScore": [ - 0.7942371964454651, - 0.7929015159606934 + 0.7942370176315308, + 0.7929013967514038 ], "QueryPart": "show climate", "SV": [ @@ -76,7 +76,7 @@ }, { "CosineScore": [ - 0.866513192653656 + 0.866512656211853 ], "QueryPart": "change drought", "SV": [ diff --git a/server/integration_tests/test_data/e2e_triple/whatgenesareassociatedwiththegeneticvariantrs13317andrs7903146/chart_config.json b/server/integration_tests/test_data/e2e_triple/whatgenesareassociatedwiththegeneticvariantrs13317andrs7903146/chart_config.json index a5f832efe9..a1d256de8f 100644 --- a/server/integration_tests/test_data/e2e_triple/whatgenesareassociatedwiththegeneticvariantrs13317andrs7903146/chart_config.json +++ b/server/integration_tests/test_data/e2e_triple/whatgenesareassociatedwiththegeneticvariantrs13317andrs7903146/chart_config.json @@ -4,6 +4,24 @@ "categories": [ { "blocks": [ + { + "columns": [ + { + "tiles": [ + { + "answerMessageTileSpec": { + "propertyExpr": "<-geneticVariantID{typeOf:DiseaseGeneticVariantAssociation}->diseaseID" + }, + "entities": [ + "bio/rs7903146" + ], + "title": "The associated diseases for rs7903146 are", + "type": "ANSWER_MESSAGE" + } + ] + } + ] + }, { "columns": [ { diff --git a/static/js/components/tiles/entity_overview_tile.tsx b/static/js/components/tiles/entity_overview_tile.tsx index 19dcac9e88..09fe9320db 100644 --- a/static/js/components/tiles/entity_overview_tile.tsx +++ b/static/js/components/tiles/entity_overview_tile.tsx @@ -20,6 +20,8 @@ import React from "react"; +import { URI_PREFIX } from "../../browser/constants"; + interface EntityOverviewTilePropType { entity: string; } @@ -34,7 +36,8 @@ export function EntityOverviewTile( return ( <>
- Entity overview tile for {props.entity} + Entity overview tile for  + {props.entity}
); diff --git a/tools/nl/embeddings/input/bio/_preindex.csv b/tools/nl/embeddings/input/bio/_preindex.csv index 909c5a0988..0dde4b2383 100644 --- a/tools/nl/embeddings/input/bio/_preindex.csv +++ b/tools/nl/embeddings/input/bio/_preindex.csv @@ -6,13 +6,17 @@ A unique ID for a Medical Subject Heading supplementary record,medicalSubjectHea An ID for a Medical Subject Heading descriptor record,medicalSubjectHeadingDescriptorID An ID for a Medical Subject Heading supplementary record,medicalSubjectHeadingSupplementaryRecordID ChEMBL identifier,chemblID -Disease associated with a gene,<-geneID{typeOf:DiseaseGeneAssociation}->diseaseOntologyID -DiseaseGeneAssociation,<-diseaseOntologyID{typeOf:DiseaseGeneAssociation}->geneID;<-geneID{typeOf:DiseaseGeneAssociation}->diseaseOntologyID +ChemicalCompoundGeneticVariantAssociation,<-compoundID{typeOf:ChemicalCompoundGeneticVariantAssociation}->variantID;<-variantID{typeOf:ChemicalCompoundGeneticVariantAssociation}->compoundID +Disease associated with a gene,<-geneID{typeOf:DiseaseGeneAssociation}->diseaseID +Disease associated with a genetic variant,<-geneticVariantID{typeOf:DiseaseGeneticVariantAssociation}->diseaseID +DiseaseGeneAssociation,<-diseaseID{typeOf:DiseaseGeneAssociation}->geneID;<-geneID{typeOf:DiseaseGeneAssociation}->diseaseID +DiseaseGeneticVariantAssociation,<-diseaseID{typeOf:DiseaseGeneticVariantAssociation}->geneticVariantID;<-geneticVariantID{typeOf:DiseaseGeneticVariantAssociation}->diseaseID Ensembl ID,ensemblID Functional category of the genetic variant,geneticVariantFunctionalCategory -Gene associated with a disease,<-diseaseOntologyID{typeOf:DiseaseGeneAssociation}->geneID -Gene associated with a genetic variant,<-referenceSNPClusterID{typeOf:GeneticVariantGeneAssociation}->geneSymbol -GeneticVariantGeneAssociation,<-geneSymbol{typeOf:GeneticVariantGeneAssociation}->referenceSNPClusterID;<-referenceSNPClusterID{typeOf:GeneticVariantGeneAssociation}->geneSymbol +Gene associated with a disease,<-diseaseID{typeOf:DiseaseGeneAssociation}->geneID +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 MeSH descriptor record ID,medicalSubjectHeadingDescriptorID MeSH supplementary record ID,medicalSubjectHeadingSupplementaryRecordID NCBI Taxonomy database identifier,ncbiTaxonID @@ -51,6 +55,7 @@ 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 @@ -62,7 +67,8 @@ full name of the gene,fullName fullName,fullName gene id,geneID geneID,geneID -genetic variant associated with a gene,<-geneSymbol{typeOf:GeneticVariantGeneAssociation}->referenceSNPClusterID +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 diff --git a/tools/nl/embeddings/input/bio/sheets_svs.csv b/tools/nl/embeddings/input/bio/sheets_svs.csv index 3d7d78e87c..7042de0db2 100644 --- a/tools/nl/embeddings/input/bio/sheets_svs.csv +++ b/tools/nl/embeddings/input/bio/sheets_svs.csv @@ -41,8 +41,12 @@ ncbiDNASequenceName,ncbiDNASequenceName;NCBI defined segment of DNA sequence nam 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 -<-referenceSNPClusterID{typeOf:GeneticVariantGeneAssociation}->geneSymbol,GeneticVariantGeneAssociation;Gene associated with a genetic variant -<-geneSymbol{typeOf:GeneticVariantGeneAssociation}->referenceSNPClusterID,GeneticVariantGeneAssociation;genetic variant associated with a gene -<-diseaseOntologyID{typeOf:DiseaseGeneAssociation}->geneID,DiseaseGeneAssociation;Gene associated with a disease -<-geneID{typeOf:DiseaseGeneAssociation}->diseaseOntologyID,DiseaseGeneAssociation;Disease associated with a gene +<-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 +<-geneID{typeOf:DiseaseGeneAssociation}->diseaseID,DiseaseGeneAssociation;Disease associated with a gene +<-diseaseID{typeOf:DiseaseGeneticVariantAssociation}->geneticVariantID,DiseaseGeneticVariantAssociation;Genetic variant associated with a disease +<-geneticVariantID{typeOf:DiseaseGeneticVariantAssociation}->diseaseID,DiseaseGeneticVariantAssociation;Disease associated with a genetic variant +<-compoundID{typeOf:ChemicalCompoundGeneticVariantAssociation}->variantID,ChemicalCompoundGeneticVariantAssociation;genetic variant associated with a chemical compound +<-variantID{typeOf:ChemicalCompoundGeneticVariantAssociation}->compoundID,ChemicalCompoundGeneticVariantAssociation;chemical compound associated with a genetic variant virusGenus,virusGenus;genus of a virus species