{"id":"https://openalex.org/W7125419375","doi":"https://doi.org/10.1093/bioinformatics/btag037","title":"<i>BioTriplex</i> : a full-text annotated corpus for fine-tuning language models in gene-disease relation extraction tasks","display_name":"<i>BioTriplex</i> : a full-text annotated corpus for fine-tuning language models in gene-disease relation extraction tasks","publication_year":2026,"publication_date":"2026-01-03","ids":{"openalex":"https://openalex.org/W7125419375","doi":"https://doi.org/10.1093/bioinformatics/btag037","pmid":"https://pubmed.ncbi.nlm.nih.gov/41564323"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btag037","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag037","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1093/bioinformatics/btag037","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123576489","display_name":"Charlotte Collins","orcid":null},"institutions":[{"id":"https://openalex.org/I1344076864","display_name":"Center for Applied Linguistics","ror":"https://ror.org/020pekv35","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1344076864"]},{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB","US"],"is_corresponding":true,"raw_author_name":"Charlotte Collins","raw_affiliation_strings":["Centre for Human Inspired Artificial Intelligence, Institute for Technology and Humanity, University of Cambridge , Cambridge CB2 1SB,","Language Technology Laboratory, Theoretical and Applied Linguistics, Faculty of Modern and Medieval Languages and Linguistics, University of Cambridge , Cambridge CB3 9DA,"],"raw_orcid":"https://orcid.org/0000-0002-8715-9035","affiliations":[{"raw_affiliation_string":"Centre for Human Inspired Artificial Intelligence, Institute for Technology and Humanity, University of Cambridge , Cambridge CB2 1SB,","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Language Technology Laboratory, Theoretical and Applied Linguistics, Faculty of Modern and Medieval Languages and Linguistics, University of Cambridge , Cambridge CB3 9DA,","institution_ids":["https://openalex.org/I1344076864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033949287","display_name":"Panagiotis Fytas","orcid":null},"institutions":[{"id":"https://openalex.org/I1344076864","display_name":"Center for Applied Linguistics","ror":"https://ror.org/020pekv35","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1344076864"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Panagiotis Fytas","raw_affiliation_strings":["Language Technology Laboratory, Theoretical and Applied Linguistics, Faculty of Modern and Medieval Languages and Linguistics, University of Cambridge , Cambridge CB3 9DA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Laboratory, Theoretical and Applied Linguistics, Faculty of Modern and Medieval Languages and Linguistics, University of Cambridge , Cambridge CB3 9DA,","institution_ids":["https://openalex.org/I1344076864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072888371","display_name":"\u0130lknur Karaden\u0131z","orcid":"https://orcid.org/0000-0002-7097-6143"},"institutions":[{"id":"https://openalex.org/I1344076864","display_name":"Center for Applied Linguistics","ror":"https://ror.org/020pekv35","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1344076864"]},{"id":"https://openalex.org/I44925452","display_name":"\u00d6zye\u011fin University","ror":"https://ror.org/01jjhfr75","country_code":"TR","type":"education","lineage":["https://openalex.org/I44925452"]}],"countries":["TR","US"],"is_corresponding":true,"raw_author_name":"\u0130lknur Karadeniz","raw_affiliation_strings":["Department of Artificial Intelligence and Data Engineering, \u00d6zye\u011fin University , Istanbul 34794, T\u00fcrkiye","Language Technology Laboratory, Theoretical and Applied Linguistics, Faculty of Modern and Medieval Languages and Linguistics, University of Cambridge , Cambridge CB3 9DA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence and Data Engineering, \u00d6zye\u011fin University , Istanbul 34794, T\u00fcrkiye","institution_ids":["https://openalex.org/I44925452"]},{"raw_affiliation_string":"Language Technology Laboratory, Theoretical and Applied Linguistics, Faculty of Modern and Medieval Languages and Linguistics, University of Cambridge , Cambridge CB3 9DA,","institution_ids":["https://openalex.org/I1344076864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101412040","display_name":"Huiyuan Zheng","orcid":"https://orcid.org/0000-0003-1431-1590"},"institutions":[{"id":"https://openalex.org/I28166907","display_name":"Karolinska Institutet","ror":"https://ror.org/056d84691","country_code":"SE","type":"education","lineage":["https://openalex.org/I28166907"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Huiyuan Zheng","raw_affiliation_strings":["Institute of Environmental Medicine, Karolinska Institutet , Stockholm 171 77,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Environmental Medicine, Karolinska Institutet , Stockholm 171 77,","institution_ids":["https://openalex.org/I28166907"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103341517","display_name":"Simon Baker","orcid":null},"institutions":[{"id":"https://openalex.org/I1344076864","display_name":"Center for Applied Linguistics","ror":"https://ror.org/020pekv35","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1344076864"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simon Baker","raw_affiliation_strings":["Language Technology Laboratory, Theoretical and Applied Linguistics, Faculty of Modern and Medieval Languages and Linguistics, University of Cambridge , Cambridge CB3 9DA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Laboratory, Theoretical and Applied Linguistics, Faculty of Modern and Medieval Languages and Linguistics, University of Cambridge , Cambridge CB3 9DA,","institution_ids":["https://openalex.org/I1344076864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036940014","display_name":"Ulla Stenius","orcid":null},"institutions":[{"id":"https://openalex.org/I28166907","display_name":"Karolinska Institutet","ror":"https://ror.org/056d84691","country_code":"SE","type":"education","lineage":["https://openalex.org/I28166907"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Ulla Stenius","raw_affiliation_strings":["Institute of Environmental Medicine, Karolinska Institutet , Stockholm 171 77,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Environmental Medicine, Karolinska Institutet , Stockholm 171 77,","institution_ids":["https://openalex.org/I28166907"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108840344","display_name":"Anna Korhonen","orcid":null},"institutions":[{"id":"https://openalex.org/I1344076864","display_name":"Center for Applied Linguistics","ror":"https://ror.org/020pekv35","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1344076864"]},{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Anna Korhonen","raw_affiliation_strings":["Centre for Human Inspired Artificial Intelligence, Institute for Technology and Humanity, University of Cambridge , Cambridge CB2 1SB,","Language Technology Laboratory, Theoretical and Applied Linguistics, Faculty of Modern and Medieval Languages and Linguistics, University of Cambridge , Cambridge CB3 9DA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Human Inspired Artificial Intelligence, Institute for Technology and Humanity, University of Cambridge , Cambridge CB2 1SB,","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Language Technology Laboratory, Theoretical and Applied Linguistics, Faculty of Modern and Medieval Languages and Linguistics, University of Cambridge , Cambridge CB3 9DA,","institution_ids":["https://openalex.org/I1344076864"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072888371","https://openalex.org/A5123576489"],"corresponding_institution_ids":["https://openalex.org/I1344076864","https://openalex.org/I241749","https://openalex.org/I44925452"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07121221,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"42","issue":"2","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":0.8615000247955322,"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":0.8615000247955322,"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/T10028","display_name":"Topic Modeling","score":0.04149999842047691,"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"}},{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.02280000038444996,"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/relation","display_name":"Relation (database)","score":0.6895999908447266},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.6190000176429749},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46070000529289246},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.39579999446868896},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.34389999508857727},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.34049999713897705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8500999808311462},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7404000163078308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6973999738693237},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.6895999908447266},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.6190000176429749},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46070000529289246},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.39579999446868896},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.2759999930858612}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004194","descriptor_name":"Disease","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D004194","descriptor_name":"Disease","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D004194","descriptor_name":"Disease","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D004194","descriptor_name":"Disease","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D004194","descriptor_name":"Disease","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D004194","descriptor_name":"Disease","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D004194","descriptor_name":"Disease","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D004194","descriptor_name":"Disease","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1093/bioinformatics/btag037","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag037","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41564323","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41564323","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:europepmc.org:11690549","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12883087","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:12883087","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12883087/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/397839","is_oa":true,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/397839","pdf_url":null,"source":{"id":"https://openalex.org/S4306401777","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"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":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btag037","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag037","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5788038969039917,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G8487615369","display_name":null,"funder_award_id":"EP/Y031350/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2035352268","https://openalex.org/W2040298461","https://openalex.org/W2055032581","https://openalex.org/W2479527281","https://openalex.org/W2791951321","https://openalex.org/W2911489562","https://openalex.org/W2956934712","https://openalex.org/W3046375318","https://openalex.org/W3127972566","https://openalex.org/W3178755335","https://openalex.org/W3200735940","https://openalex.org/W4221128994","https://openalex.org/W4283318325","https://openalex.org/W4376274483","https://openalex.org/W4381573137","https://openalex.org/W4393094733","https://openalex.org/W4393936594","https://openalex.org/W4400021004","https://openalex.org/W4401413215","https://openalex.org/W4407219056","https://openalex.org/W4407913993","https://openalex.org/W4411119577"],"related_works":[],"abstract_inverted_index":{"MOTIVATION:":[0],"Automatic":[1],"information":[2,22],"extraction":[3,82],"from":[4,54],"biomedical":[5,14,41,76,100,196],"texts":[6,44],"requires":[7],"machine":[8],"learning":[9],"methodology":[10],"that":[11,66],"can":[12,67],"recognize":[13],"entities,":[15],"characterize":[16],"inter-entity":[17],"relationships,":[18],"and":[19,51,89,113,139,148,155,159,167,183],"relate":[20],"extracted":[21],"to":[23,70,122],"specific":[24],"research":[25,101],"topics.":[26],"Large":[27],"language":[28,72,128,192],"models":[29,73,193],"(LLMs)":[30],"excel":[31],"in":[32,39,130,190],"general":[33,55],"tasks":[34],"but":[35],"perform":[36],"less":[37],"reliably":[38],"the":[40,84,124,144,150,185],"domain,":[42],"where":[43],"are":[45],"characterized":[46],"by":[47],"extensive":[48],"technical":[49],"terminology":[50],"semantic":[52],"variations":[53],"literature.":[56],"There":[57],"is":[58],"an":[59],"unmet":[60],"need":[61],"for":[62,74,194],"annotated":[63,108],"full-text":[64,180],"datasets":[65,189],"be":[68],"used":[69],"fine-tune":[71],"significant":[75],"applications.":[77],"Here,":[78],"we":[79],"focus":[80],"on":[81],"of":[83,97,116,187],"complex":[85],"relationships":[86],"between":[87],"genes":[88],"diseases.":[90],"RESULTS:":[91],"We":[92,119],"present":[93],"BioTriplex,":[94],"a":[95,178],"corpus":[96],"100":[98],"full-length":[99],"articles":[102],"(comprising":[103],"604":[104],"subsection":[105],"texts)":[106],"manually":[107],"with":[109,164],"disease":[110],"names,":[111],"genes,":[112],"21":[114],"subtypes":[115],"disease-gene":[117],"relationships.":[118],"employ":[120],"BioTriplex":[121,176],"train":[123],"LLaMA":[125,145],"3.1":[126,146],"8B":[127],"model":[129,136],"gene-disease":[131,161],"relation":[132,162],"extraction.":[133],"Our":[134],"fine-tuned":[135],"outperforms":[137],"zero-shot":[138],"few-shot":[140],"approaches,":[141],"both":[142],"within":[143],"architecture":[147],"across":[149],"larger":[151],"state-of-the-art":[152],"LLMs":[153],"GPT-4":[154],"Claude":[156],"Sonnet":[157],"3.7,":[158],"classifies":[160],"types":[163],"broader":[165],"scope":[166],"greater":[168],"granularity":[169],"than":[170],"previously":[171],"described.":[172],"These":[173],"results":[174],"validate":[175],"as":[177],"useful":[179],"data":[181],"resource":[182],"underscore":[184],"value":[186],"specialized":[188],"fine-tuning":[191],"important":[195],"tasks.":[197],"AVAILABILITY":[198],"AND":[199],"IMPLEMENTATION:":[200],"https://github.com/PanagiotisFytas/BioTriplex.":[201]},"counts_by_year":[],"updated_date":"2026-06-29T08:53:18.405633","created_date":"2026-01-23T00:00:00"}
