{"id":"https://openalex.org/W7201848212","doi":"https://doi.org/10.5281/zenodo.21839216","title":"ct-validation benchmark data: parsed genetic evidence and clinical trial datasets","display_name":"ct-validation benchmark data: parsed genetic evidence and clinical trial datasets","publication_year":2026,"publication_date":"2026-08-07","ids":{"openalex":"https://openalex.org/W7201848212","doi":"https://doi.org/10.5281/zenodo.21839216"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.21839216","doi":"https://doi.org/10.5281/zenodo.21839216","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21839216","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"volume":null,"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.21839216","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5145956545","display_name":"Klim Kostiuk","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kostiuk, Klim","raw_affiliation_strings":["GERO PTE. LTD., Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GERO PTE. LTD., Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5145947116","display_name":"Daniel Igumnov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Igumnov, Daniel","raw_affiliation_strings":["GERO PTE. LTD., Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GERO PTE. LTD., Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085869644","display_name":"Peter O. Fedichev","orcid":"https://orcid.org/0000-0003-0404-808X","observed_orcids":["https://orcid.org/0000-0003-0404-808X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fedichev, Peter","raw_affiliation_strings":["GERO PTE. LTD., Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GERO PTE. LTD., Singapore","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5145987853","display_name":"Amir Feizi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feizi, Amir","raw_affiliation_strings":["GERO PTE. LTD., Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GERO PTE. LTD., Singapore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.8657000064849854,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.8657000064849854,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.03799999877810478,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.020400000736117363,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/ct-validation","display_name":"CT validation","score":0.921999990940094},{"id":"https://openalex.org/keywords/clinical-trial-results","display_name":"clinical trial results","score":0.7929999828338623},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.6000000238418579},{"id":"https://openalex.org/keywords/genetic-evidence","display_name":"genetic evidence","score":0.6480000019073486},{"id":"https://openalex.org/keywords/clinical-trial-evidence","display_name":"clinical trial evidence","score":0.4269999861717224},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"semantic similarity","score":0.6150000095367432},{"id":"https://openalex.org/keywords/mesh-descriptors","display_name":"MeSH descriptors","score":0.8140000104904175},{"id":"https://openalex.org/keywords/open-targets","display_name":"Open Targets","score":0.5590000152587891},{"id":"https://openalex.org/keywords/gwas-catalog","display_name":"GWAS Catalog","score":0.9079999923706055},{"id":"https://openalex.org/keywords/clinvar","display_name":"ClinVar","score":0.9779999852180481},{"id":"https://openalex.org/keywords/stitch","display_name":"stitches","score":0.9679999947547913},{"id":"https://openalex.org/keywords/chembl","display_name":"ChEMBL","score":0.9869999885559082},{"id":"https://openalex.org/keywords/drug-repurposing","display_name":"drug repurposing","score":0.4480000138282776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6883999705314636},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6567999720573425},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.61080002784729},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4830000102519989},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.47600001096725464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46239998936653137},{"id":"https://openalex.org/C63222358","wikidata":"https://www.wikidata.org/wiki/Q6120337","display_name":"chEMBL","level":3,"score":0.46230000257492065},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42910000681877136},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41280001401901245},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C535046627","wikidata":"https://www.wikidata.org/wiki/Q30612","display_name":"Clinical trial","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3402000069618225},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3395000100135803},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.322299987077713},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C191172861","wikidata":"https://www.wikidata.org/wiki/Q7899321","display_name":"Upstream (networking)","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C106208931","wikidata":"https://www.wikidata.org/wiki/Q1098876","display_name":"Genome-wide association study","level":5,"score":0.2847999930381775},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.2567000091075897}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5281/zenodo.21839216","doi":"https://doi.org/10.5281/zenodo.21839216","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21839216","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.21839217","doi":"https://doi.org/10.5281/zenodo.21839217","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21839217","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.22901451","doi":"https://doi.org/10.5281/zenodo.22901451","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.22901451","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.21839216","doi":"https://doi.org/10.5281/zenodo.21839216","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21839216","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Parsed":[0],"genetic":[1],"evidence":[2,11],"and":[3,34,40,48,94],"clinical":[4,13],"trial":[5,14],"datasets":[6],"used":[7],"to":[8,60,64],"benchmark":[9],"gene\u2013indication":[10],"against":[12],"outcomes":[15],"with":[16],"ct-validation":[17],"v0.4.0.":[18],"Contains":[19],"harmonised":[20],"gene-indication":[21],"tables":[22,53],"derived":[23],"from":[24,54],"Open":[25],"Targets,":[26],"GWAS":[27],"Catalog,":[28],"ClinVar,":[29],"Genebass,":[30],"DGIdb,":[31],"STITCH,":[32],"ChEMBL":[33],"TrialPanorama;":[35],"the":[36,49,73,86],"EFO":[37],"ontology":[38],"mappings":[39],"semantic":[41],"similarity":[42],"lookups":[43],"they":[44],"are":[45,70],"matched":[46],"through;":[47],"processed":[50],"Citeline-derived":[51],"comparator":[52],"Minikel":[55],"et":[56],"al.":[57],"(2024).":[58],"Sufficient":[59],"run":[61],"notebooks/benchmark.py":[62],"end":[63,65],"without":[66],"re-downloading":[67],"upstream":[68,77],"sources.Contents":[69],"redistributed":[71],"under":[72],"terms":[74],"of":[75],"their":[76],"sources,":[78],"which":[79],"differ":[80],"per":[81],"file.":[82],"See":[83],"DATA_SOURCES.md":[84],"in":[85],"accompanying":[87],"code":[88],"repository":[89],"for":[90],"per-source":[91],"licences,":[92],"versions":[93],"download":[95]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2026-08-08T00:00:00"}