Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[bio] Update biomed property embeddings. #4721

Merged
merged 9 commits into from
Nov 11, 2024
Merged

[bio] Update biomed property embeddings. #4721

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
4418038
[NL] Update biomed property embeddings.
clincoln8 Nov 7, 2024
af6fb0b
Merge branch 'datacommonsorg:master' into bio-embeddings
clincoln8 Nov 7, 2024
60628a6
Merge branch 'master' of github.com:clincoln8/datcom-website into bio…
clincoln8 Nov 7, 2024
ad48223
Update golden cosine scores for new embeddings.
clincoln8 Nov 7, 2024
5ffd1e6
Update bio integration tests to request genomic coordinates instead o…
clincoln8 Nov 8, 2024
9c12fcf
Fix embedding nits
clincoln8 Nov 9, 2024
7fc1001
Merge branch 'master' of https://github.com/datacommonsorg/website in…
clincoln8 Nov 9, 2024
3228d0d
Update goldens.
clincoln8 Nov 9, 2024
1a32ea1
Fix trailing whitespace
clincoln8 Nov 11, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion deploy/nl/catalog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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:
Expand Down
7 changes: 5 additions & 2 deletions server/integration_tests/explore_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down
40 changes: 19 additions & 21 deletions server/integration_tests/test_data/detection_api_bio/whatisthephylumofvolvox/debug_info.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@
0.314266,
0.312765,
0.312629,
0.312504,
0.312505,
0.311774,
0.310339,
0.310075,
Expand Down Expand Up @@ -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",
Expand All @@ -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": {
Expand Down
42 changes: 20 additions & 22 deletions ...n_tests/test_data/detection_api_bio/whattypesofgenesarefgfr1,apoe,andache/debug_info.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@
0.400638,
0.398746,
0.398361,
0.390523,
0.390524,
0.389033,
0.388461,
0.388382,
Expand All @@ -35,7 +35,7 @@
0.385679,
0.385434,
0.385339,
0.381842,
0.381843,
0.379705
],
"MultiSV": {},
Expand Down Expand Up @@ -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",
Expand All @@ -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": {
Expand Down
Loading
Loading