{"id":"https://openalex.org/W7225064121","doi":"https://doi.org/10.64898/2026.10.29.762818","title":"Gene Embedding Hub: a standardized resource for human gene representations","display_name":"Gene Embedding Hub: a standardized resource for human gene representations","publication_year":2026,"publication_date":"2026-11-01","ids":{"openalex":"https://openalex.org/W7225064121","doi":"https://doi.org/10.64898/2026.10.29.762818"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.29.762818","doi":"https://doi.org/10.64898/2026.10.29.762818","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.29.762818","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/01/2026.10.29.762818.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/01/2026.10.29.762818.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160320019","display_name":"Daniel Tabares","orcid":"https://orcid.org/0009-0000-2436-3402","observed_orcids":["https://orcid.org/0009-0000-2436-3402"]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Daniel Tabares","raw_affiliation_strings":["ETH Zurich, Department of Computer Science, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0009-0000-2436-3402","affiliations":[{"raw_affiliation_string":"ETH Zurich, Department of Computer Science, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140159957","display_name":"Michael Bohl","orcid":"https://orcid.org/0009-0007-4084-6560","observed_orcids":["https://orcid.org/0009-0007-4084-6560"]},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Michael Bohl","raw_affiliation_strings":["ETH Zurich, Department of Computer Science, Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0009-0007-4084-6560","affiliations":[{"raw_affiliation_string":"ETH Zurich, Department of Computer Science, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074876525","display_name":"Valentina Boeva","orcid":"https://orcid.org/0000-0002-4382-7185","observed_orcids":["https://orcid.org/0000-0002-4382-7185"]},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]},{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Valentina Boeva","raw_affiliation_strings":["AI Center Zurich","ETH Zurich, Department of Computer Science, Zurich, Switzerland","Swiss Institute of Bioinformatics"],"raw_orcid":"https://orcid.org/0000-0002-4382-7185","affiliations":[{"raw_affiliation_string":"AI Center Zurich","institution_ids":[]},{"raw_affiliation_string":"ETH Zurich, Department of Computer Science, Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Swiss Institute of Bioinformatics","institution_ids":["https://openalex.org/I12708293"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5074876525"],"corresponding_institution_ids":["https://openalex.org/I12708293","https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.8422999978065491,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.8422999978065491,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.030700000002980232,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.027699999511241913,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/gene-embeddings","display_name":"gene embeddings","score":0.9959999918937683},{"id":"https://openalex.org/keywords/human-genes","display_name":"human genes","score":0.7730000019073486},{"id":"https://openalex.org/keywords/gene-representation","display_name":"gene representation","score":0.6809999942779541},{"id":"https://openalex.org/keywords/regulatory-genomics","display_name":"regulatory genomics","score":0.7730000019073486},{"id":"https://openalex.org/keywords/biological-networks","display_name":"biological networks","score":0.7149999737739563},{"id":"https://openalex.org/keywords/knowledge-graphs","display_name":"knowledge graphs","score":0.9639999866485596},{"id":"https://openalex.org/keywords/biomedical-text","display_name":"biomedical text","score":0.5350000262260437},{"id":"https://openalex.org/keywords/gene-identifiers","display_name":"gene identifiers","score":0.4749999940395355}],"concepts":[{"id":"https://openalex.org/C141674004","wikidata":"https://www.wikidata.org/wiki/Q1344256","display_name":"Ensembl","level":5,"score":0.8870999813079834},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6808000206947327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6122999787330627},{"id":"https://openalex.org/C62177273","wikidata":"https://www.wikidata.org/wiki/Q5531556","display_name":"Gene nomenclature","level":4,"score":0.6025999784469604},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5971999764442444},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5616999864578247},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5389000177383423},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.49309998750686646},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.447299987077713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4447999894618988},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4083000123500824},{"id":"https://openalex.org/C161078062","wikidata":"https://www.wikidata.org/wiki/Q1068690","display_name":"Functional genomics","level":5,"score":0.4043000042438507},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.3953999876976013},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3610000014305115},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34470000863075256},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.30320000648498535},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2847000062465668},{"id":"https://openalex.org/C2780330800","wikidata":"https://www.wikidata.org/wiki/Q7884647","display_name":"UniGene","level":5,"score":0.28130000829696655},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.27320000529289246},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2685000002384186},{"id":"https://openalex.org/C165864922","wikidata":"https://www.wikidata.org/wiki/Q411391","display_name":"Regulation of gene expression","level":3,"score":0.2630999982357025},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C2778473407","wikidata":"https://www.wikidata.org/wiki/Q1459574","display_name":"Compendium","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.25690001249313354},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2540000081062317},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.29.762818","doi":"https://doi.org/10.64898/2026.10.29.762818","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.29.762818","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/01/2026.10.29.762818.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.29.762818","doi":"https://doi.org/10.64898/2026.10.29.762818","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.29.762818","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/01/2026.10.29.762818.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225064121.pdf","grobid_xml":"https://content.openalex.org/works/W7225064121.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W2047940964","https://openalex.org/W2111864076","https://openalex.org/W2143965359","https://openalex.org/W2156564520","https://openalex.org/W2198606573","https://openalex.org/W2342249984","https://openalex.org/W2347037915","https://openalex.org/W2556519015","https://openalex.org/W2767232866","https://openalex.org/W2798361766","https://openalex.org/W2909194804","https://openalex.org/W2911489562","https://openalex.org/W2949311246","https://openalex.org/W2951422523","https://openalex.org/W2953263404","https://openalex.org/W2979826702","https://openalex.org/W3017463390","https://openalex.org/W3035965352","https://openalex.org/W3042669608","https://openalex.org/W3046375318","https://openalex.org/W3203588026","https://openalex.org/W3214315533","https://openalex.org/W4200497629","https://openalex.org/W4210659358","https://openalex.org/W4220991280","https://openalex.org/W4224014283","https://openalex.org/W4318983406","https://openalex.org/W4327550249","https://openalex.org/W4378838672","https://openalex.org/W4392168151","https://openalex.org/W4403174218","https://openalex.org/W4404225843","https://openalex.org/W4404458588","https://openalex.org/W4404511387","https://openalex.org/W4404535307","https://openalex.org/W4405095064","https://openalex.org/W4405114593","https://openalex.org/W4407057757","https://openalex.org/W4409484936","https://openalex.org/W4411081036","https://openalex.org/W4416608069","https://openalex.org/W4416704614","https://openalex.org/W7125967877","https://openalex.org/W7129078377","https://openalex.org/W7130512363","https://openalex.org/W7167668826"],"related_works":["https://openalex.org/W4407057757","https://openalex.org/W4409631108","https://openalex.org/W4388465973","https://openalex.org/W4393096597","https://openalex.org/W7204941501","https://openalex.org/W2952631022","https://openalex.org/W4402220357","https://openalex.org/W4405562247","https://openalex.org/W2910809191","https://openalex.org/W4396966059"],"abstract_inverted_index":{"Abstract":[0],"Gene":[1],"embeddings":[2,87,143,161],"are":[3],"vector":[4],"representations":[5,89,155],"of":[6,27,43,153],"gene":[7,114,154],"identity":[8],"that":[9,144],"provide":[10],"machine-learning":[11],"models":[12,96],"with":[13],"information":[14],"from":[15,49,93],"diverse":[16],"biological":[17,65,98],"sources.":[18],"However,":[19],"their":[20],"use":[21],"is":[22,103,138],"hindered":[23],"by":[24,125],"a":[25,40,106],"lack":[26],"standardization:":[28],"inconsistent":[29],"identifiers,":[30,115],"formats,":[31],"and":[32,52,71,88,97,118,128,133,148,158,164],"preprocessing":[33],"conventions.":[34],"In":[35],"this":[36],"work,":[37],"we":[38],"present":[39],"unified":[41],"resource":[42,124],"67":[44],"human":[45],"gene-embedding":[46],"sets":[47],"derived":[48],"protein,":[50],"DNA":[51],"RNA":[53],"sequences,":[54],"biomedical":[55],"text,":[56],"bulk":[57],"expression":[58,61],"data,":[59,64],"single-cell":[60],"models,":[62,73],"functional":[63],"networks,":[66],"knowledge":[67],"graphs,":[68],"regulatory":[69],"genomics":[70],"multimodal":[72],"covering":[74],"up":[75],"to":[76,140],"20,097":[77],"GENCODE-annotated":[78],"protein-coding":[79],"genes.":[80],"The":[81,136],"collection":[82,137],"includes":[83],"both":[84],"published":[85],"precomputed":[86],"generated":[90],"or":[91],"extracted":[92],"publicly":[94],"available":[95],"data.":[99],"Each":[100],"embedding":[101,110],"set":[102],"organized":[104],"in":[105],"folder":[107],"containing":[108],"the":[109,112,123],"matrix,":[111],"Ensembl":[113],"machine-readable":[116],"metadata,":[117],"processing":[119],"documentation.":[120],"We":[121],"validate":[122],"measuring":[126],"global":[127],"local":[129],"similarity,":[130],"cross-embedding":[131,134],"consensus,":[132],"predictability.":[135],"designed":[139],"allow":[141],"community-contributed":[142],"meet":[145],"predefined":[146],"technical":[147],"documentation":[149],"requirements,":[150],"enables":[151],"comparison":[152],"across":[156],"modalities":[157],"provides":[159],"standardized":[160],"for":[162],"training":[163],"downstream":[165],"applications.":[166]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-02T00:00:00"}
