{"id":"https://openalex.org/W7159592703","doi":"https://doi.org/10.48550/arxiv.2604.27269","title":"OptimusKG: Unifying biomedical knowledge in a modern multimodal graph","display_name":"OptimusKG: Unifying biomedical knowledge in a modern multimodal graph","publication_year":2026,"publication_date":"2026-04-29","ids":{"openalex":"https://openalex.org/W7159592703","doi":"https://doi.org/10.48550/arxiv.2604.27269"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.27269","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.27269","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.27269","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120845110","display_name":"Lucas Vittor","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Vittor, Lucas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134975831","display_name":"Ayush Noori","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Noori, Ayush","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134950414","display_name":"I\u00f1aki Arango","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arango, I\u00f1aki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120845111","display_name":"Joaqu\u00edn Polonuer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Polonuer, Joaqu\u00edn","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032358586","display_name":"Sam Rodriques","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rodriques, Sam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134968326","display_name":"Andrew White","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"White, Andrew","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134930540","display_name":"David A. Clifton","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Clifton, David A.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134948961","display_name":"Marinka Zitnik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zitnik, Marinka","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5120845110"],"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":0.8481000065803528,"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":0.8481000065803528,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.0828000009059906,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.03220000118017197,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.690500020980835},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.5795000195503235},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4722999930381775},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.46239998936653137},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.3910999894142151},{"id":"https://openalex.org/keywords/graph-database","display_name":"Graph database","score":0.3425999879837036},{"id":"https://openalex.org/keywords/scientific-literature","display_name":"Scientific literature","score":0.3260999917984009},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.325300008058548}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.690500020980835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.670199990272522},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.5795000195503235},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4722999930381775},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.46239998936653137},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42080000042915344},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3903999924659729},{"id":"https://openalex.org/C176225458","wikidata":"https://www.wikidata.org/wiki/Q595971","display_name":"Graph database","level":3,"score":0.3425999879837036},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.31459999084472656},{"id":"https://openalex.org/C195732255","wikidata":"https://www.wikidata.org/wiki/Q981008","display_name":"Sociology of scientific knowledge","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C137982476","wikidata":"https://www.wikidata.org/wiki/Q7072326","display_name":"Open Biomedical Ontologies","level":5,"score":0.28049999475479126},{"id":"https://openalex.org/C558772884","wikidata":"https://www.wikidata.org/wiki/Q1508564","display_name":"Graph rewriting","level":3,"score":0.27379998564720154},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26989999413490295},{"id":"https://openalex.org/C65603577","wikidata":"https://www.wikidata.org/wiki/Q3427877","display_name":"Web resource","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2639000117778778},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C69075417","wikidata":"https://www.wikidata.org/wiki/Q515701","display_name":"Linked data","level":3,"score":0.2599000036716461},{"id":"https://openalex.org/C147497476","wikidata":"https://www.wikidata.org/wiki/Q54872","display_name":"RDF","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.27269","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.27269","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.27269","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.27269","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"score":0.5287792086601257,"display_name":"Responsible consumption and production","id":"https://metadata.un.org/sdg/12"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Biomedical":[0],"knowledge":[1,186],"graphs":[2,24],"(KGs)":[3],"are":[4,13,29,134],"widely":[5],"used":[6],"in":[7,172,191],"the":[8,125,139,192],"life":[9],"sciences,":[10],"yet":[11],"many":[12],"derived":[14,91,174],"from":[15,26,48,92,138,175],"unstructured":[16],"documents":[17],"and":[18,50,62,79,95,106,108,114,120,177,216],"therefore":[19],"lack":[20],"schema-level":[21],"constrains,":[22],"whereas":[23,156],"assembled":[25],"structured":[27,49],"resources":[28,52],"difficult":[30],"to":[31,53],"harmonize":[32],"into":[33],"a":[34,40,101,143,203],"unified":[35],"representation.":[36],"We":[37,123],"present":[38],"OptimusKG,":[39],"multimodal":[41,144],"biomedical":[42,185,217],"labeled":[43],"property":[44,81,89],"graph":[45,99,132],"(LPG)":[46],"built":[47],"semi-structured":[51],"preserve":[54],"factual,":[55],"type-specific":[56,111],"metadata":[57],"across":[58,69,75,86,116],"molecular,":[59,117],"anatomical,":[60,118],"clinical,":[61,119],"environmental":[63,121],"domains.":[64,122],"OptimusKG":[65,128,183,195],"contains":[66],"190,531":[67],"nodes":[68,105],"10":[70],"entity":[71],"types,":[72,78],"21,813,816":[73],"edges":[74,107,161],"26":[76],"relation":[77],"67,249,863":[80],"instances":[82],"encoding":[83],"110,276,843":[84],"values":[85],"150":[87],"distinct":[88],"keys,":[90],"18":[93],"ontologies":[94],"controlled":[96],"vocabularies.":[97],"The":[98],"enforces":[100],"top-level":[102],"schema":[103],"for":[104,151,206],"retains":[109],"granular,":[110],"properties,":[112],"cross-references,":[113],"provenance":[115],"assessed":[124],"validity":[126],"of":[127,153,158],"by":[129,136],"evaluating":[130],"whether":[131],"relationships":[133],"supported":[135],"evidence":[137,150],"scientific":[140,193],"literature":[141,168],"using":[142],"agent,":[145],"PaperQA3.":[146],"PaperQA3":[147],"identified":[148],"supporting":[149,164],"70.0%":[152],"sampled":[154,159],"edges,":[155],"83.4%":[157],"false":[160],"received":[162],"no":[163],"evidence.":[165],"Edges":[166],"without":[167],"support":[169],"were":[170],"concentrated":[171],"associations":[173],"experimental":[176],"functional":[178],"genomics":[179],"resources,":[180],"suggesting":[181],"that":[182,187],"captures":[184],"may":[188],"precede":[189],"synthesis":[190],"literature.":[194],"is":[196],"distributed":[197],"as":[198,222],"Apache":[199],"Parquet":[200],"files,":[201],"providing":[202],"standardized":[204],"resource":[205],"graph-based":[207],"machine":[208],"learning,":[209],"knowledge-grounded":[210],"retrieval":[211],"with":[212],"large":[213],"language":[214],"models,":[215],"discovery":[218],"use":[219],"cases":[220],"such":[221],"hypothesis":[223],"generation.":[224]},"counts_by_year":[],"updated_date":"2026-05-02T06:10:54.344120","created_date":"2026-05-02T00:00:00"}
