{"id":"https://openalex.org/W7225611451","doi":"https://doi.org/10.64898/2026.11.05.764758","title":"GeneEmbedLLM: Harnessing Large Language Models for Gene Functional Embedding and Association Prediction","display_name":"GeneEmbedLLM: Harnessing Large Language Models for Gene Functional Embedding and Association Prediction","publication_year":2026,"publication_date":"2026-11-09","ids":{"openalex":"https://openalex.org/W7225611451","doi":"https://doi.org/10.64898/2026.11.05.764758"},"language":"en","primary_location":{"id":"doi:10.64898/2026.11.05.764758","doi":"https://doi.org/10.64898/2026.11.05.764758","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.05.764758","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/09/2026.11.05.764758.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":"submittedVersion","is_accepted":false,"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/2026/11/09/2026.11.05.764758.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019781796","display_name":"Ziyan Zhang","orcid":"https://orcid.org/0009-0006-9254-230X","observed_orcids":["https://orcid.org/0009-0006-9254-230X"]},"institutions":[{"id":"https://openalex.org/I4405252760","display_name":"Guangzhou Laboratory","ror":"https://ror.org/03ybmxt82","country_code":"CN","type":"government","lineage":["https://openalex.org/I4405252760"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"ziyan zhang","raw_affiliation_strings":["Guangzhou National Laboratory;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangzhou National Laboratory;","institution_ids":["https://openalex.org/I4405252760"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161361213","display_name":"liu yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405252760","display_name":"Guangzhou Laboratory","ror":"https://ror.org/03ybmxt82","country_code":"CN","type":"government","lineage":["https://openalex.org/I4405252760"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"liu yang","raw_affiliation_strings":["Guangzhou National Laboratory;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangzhou National Laboratory;","institution_ids":["https://openalex.org/I4405252760"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002744272","display_name":"Zhien He","orcid":"https://orcid.org/0000-0003-4679-7839","observed_orcids":["https://orcid.org/0000-0003-4679-7839"]},"institutions":[{"id":"https://openalex.org/I4405252760","display_name":"Guangzhou Laboratory","ror":"https://ror.org/03ybmxt82","country_code":"CN","type":"government","lineage":["https://openalex.org/I4405252760"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"zhien he","raw_affiliation_strings":["Guangzhou National Laboratory;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangzhou National Laboratory;","institution_ids":["https://openalex.org/I4405252760"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103262689","display_name":"Junxiang Ding","orcid":"https://orcid.org/0000-0003-3782-9966","observed_orcids":["https://orcid.org/0000-0003-3782-9966"]},"institutions":[{"id":"https://openalex.org/I4405252760","display_name":"Guangzhou Laboratory","ror":"https://ror.org/03ybmxt82","country_code":"CN","type":"government","lineage":["https://openalex.org/I4405252760"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"junxiang ding","raw_affiliation_strings":["Guangzhou National Laboratory;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangzhou National Laboratory;","institution_ids":["https://openalex.org/I4405252760"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008280608","display_name":"Yixue Li","orcid":"https://orcid.org/0000-0002-1198-7176","observed_orcids":["https://orcid.org/0000-0002-1198-7176","https://orcid.org/0000-0003-3092-5613"]},"institutions":[{"id":"https://openalex.org/I4405252760","display_name":"Guangzhou Laboratory","ror":"https://ror.org/03ybmxt82","country_code":"CN","type":"government","lineage":["https://openalex.org/I4405252760"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixue Li","raw_affiliation_strings":["Guangzhou Laboratory"],"raw_orcid":"https://orcid.org/0000-0002-1198-7176","affiliations":[{"raw_affiliation_string":"Guangzhou Laboratory","institution_ids":["https://openalex.org/I4405252760"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080082812","display_name":"Rongbo Shen","orcid":"https://orcid.org/0000-0002-2797-0571","observed_orcids":["https://orcid.org/0000-0002-2797-0571"]},"institutions":[{"id":"https://openalex.org/I4405252760","display_name":"Guangzhou Laboratory","ror":"https://ror.org/03ybmxt82","country_code":"CN","type":"government","lineage":["https://openalex.org/I4405252760"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rongbo Shen","raw_affiliation_strings":["Guangzhou National Laboratory;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangzhou National Laboratory;","institution_ids":["https://openalex.org/I4405252760"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5080082812"],"corresponding_institution_ids":["https://openalex.org/I4405252760"],"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":0.8974999785423279,"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":0.8974999785423279,"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":0.0738999992609024,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.009499999694526196,"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":0.8289999961853027},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9110000133514404},{"id":"https://openalex.org/keywords/longformer","display_name":"Longformer","score":0.7940000295639038},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.968999981880188},{"id":"https://openalex.org/keywords/epigenetic-regulation","display_name":"epigenetic regulation","score":0.9789999723434448},{"id":"https://openalex.org/keywords/pathway-annotation","display_name":"pathway annotation","score":0.3070000112056732}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6604999899864197},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6507999897003174},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.573199987411499},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5475000143051147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5450999736785889},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.511900007724762},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.446399986743927},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.42820000648498535},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4083000123500824},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39079999923706055},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37400001287460327},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3441999852657318},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2989000082015991},{"id":"https://openalex.org/C105565629","wikidata":"https://www.wikidata.org/wiki/Q1248292","display_name":"Gene prediction","level":4,"score":0.29010000824928284},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C137866125","wikidata":"https://www.wikidata.org/wiki/Q4299308","display_name":"Modelling biological systems","level":3,"score":0.27950000762939453},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C2991772755","wikidata":"https://www.wikidata.org/wiki/Q751748","display_name":"Gene interaction","level":3,"score":0.2766000032424927},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2761000096797943},{"id":"https://openalex.org/C67339327","wikidata":"https://www.wikidata.org/wiki/Q1502576","display_name":"Gene regulatory network","level":4,"score":0.26600000262260437},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.11.05.764758","doi":"https://doi.org/10.64898/2026.11.05.764758","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.05.764758","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/09/2026.11.05.764758.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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.11.05.764758","doi":"https://doi.org/10.64898/2026.11.05.764758","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.05.764758","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/09/2026.11.05.764758.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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225611451.pdf","grobid_xml":"https://content.openalex.org/works/W7225611451.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W3015468748","https://openalex.org/W4415330695","https://openalex.org/W7140116110"],"related_works":["https://openalex.org/W7160328335","https://openalex.org/W4407057757","https://openalex.org/W7116962943","https://openalex.org/W4393096597","https://openalex.org/W4388465973","https://openalex.org/W7171822642","https://openalex.org/W4409631108","https://openalex.org/W3119457092","https://openalex.org/W4405562247","https://openalex.org/W7225064121"],"abstract_inverted_index":{"\u5c06\u4e0a\u8ff0\u6458\u8981\u63d0\u53d6\u4e3a\u8fde\u7eed\u6587\u672c\u5982\u4e0b\uff1a":[0],"Effective":[1],"and":[2,23,80,87,100,109,144],"high-quality":[3],"gene":[4,43,61,68],"function":[5],"representations":[6],"are":[7],"crucial":[8],"for":[9,57],"bioinformatics":[10],"tasks.":[11],"While":[12],"biological":[13],"knowledge":[14],"about":[15],"genes":[16],"is":[17,118],"inherently":[18],"textual,":[19],"encompassing":[20],"functional":[21],"descriptions":[22],"pathway":[24],"annotations,":[25],"current":[26],"methods":[27],"often":[28],"rely":[29],"on":[30,84,92],"single-source,":[31],"non-textual":[32],"data,":[33],"failing":[34],"to":[35,103],"capture":[36],"the":[37,67,107,127,130],"rich":[38],"semantic":[39],"information":[40],"in":[41],"multi-source":[42,72],"annotations.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48],"propose":[49],"GeneEmbedLLM,":[50],"a":[51],"Large":[52],"Language":[53],"Model":[54],"(LLM)-powered":[55],"framework":[56],"generating":[58],"universal,":[59],"semantically-aware":[60],"embeddings.":[62],"The":[63],"proposed":[64,113],"approach":[65],"advances":[66],"representation":[69],"learning":[70],"through":[71,133],"structured":[73],"text":[74],"integration":[75],"from":[76,97],"five":[77],"authoritative":[78],"databases":[79],"attribute-aware":[81],"attention":[82],"based":[83],"Longformer":[85],"architecture":[86],"contrastive":[88],"learning.":[89],"Experimental":[90],"results":[91],"diverse":[93],"downstream":[94],"tasks,":[95],"ranging":[96],"molecular":[98],"interactions":[99],"phenotypic":[101],"dependencies":[102],"epigenetic":[104],"regulation,":[105],"confirm":[106],"validity":[108],"effectiveness":[110],"of":[111,129],"our":[112],"approach,":[114],"where":[115],"competitive":[116],"performance":[117],"achieved":[119],"across":[120],"all":[121],"evaluated":[122],"benchmarks.":[123],"We":[124],"further":[125],"validate":[126],"quality":[128],"generated":[131],"embeddings":[132],"comprehensive":[134],"analyses,":[135],"including":[136],"embedding":[137],"visualizations,":[138],"intra-pathway":[139],"similarity":[140],"assessments,":[141],"ablation":[142],"study,":[143],"parameter":[145],"analysis.":[146]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}