{"id":"https://openalex.org/W4414881761","doi":"https://doi.org/10.1186/s12859-025-06262-6","title":"Knowledge-augmented pre-trained language models for biomedical relation extraction","display_name":"Knowledge-augmented pre-trained language models for biomedical relation extraction","publication_year":2025,"publication_date":"2025-10-07","ids":{"openalex":"https://openalex.org/W4414881761","doi":"https://doi.org/10.1186/s12859-025-06262-6","pmid":"https://pubmed.ncbi.nlm.nih.gov/41057775"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-025-06262-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06262-6","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-025-06262-6","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-025-06262-6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017484078","display_name":"Mario S\u00e4nger","orcid":"https://orcid.org/0000-0002-2950-2587"},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]},{"id":"https://openalex.org/I4210149424","display_name":"AstraZeneca (Spain)","ror":"https://ror.org/05qqrnb63","country_code":"ES","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210149424"]}],"countries":["DE","ES"],"is_corresponding":false,"raw_author_name":"Mario S\u00e4nger","raw_affiliation_strings":["Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin, Unter den Linden 6, 10099, Berlin, Germany","Enterprise AI Platforms & Services, AstraZeneca, Av. Diagonal, 615, 08028, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin, Unter den Linden 6, 10099, Berlin, Germany","institution_ids":["https://openalex.org/I39343248"]},{"raw_affiliation_string":"Enterprise AI Platforms & Services, AstraZeneca, Av. Diagonal, 615, 08028, Barcelona, Spain","institution_ids":["https://openalex.org/I4210149424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055236937","display_name":"Ulf Leser","orcid":"https://orcid.org/0000-0003-2166-9582"},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ulf Leser","raw_affiliation_strings":["Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin, Unter den Linden 6, 10099, Berlin, Germany. leser@informatik.hu-berlin.de","Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin, Unter den Linden 6, 10099, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin, Unter den Linden 6, 10099, Berlin, Germany. leser@informatik.hu-berlin.de","institution_ids":["https://openalex.org/I39343248"]},{"raw_affiliation_string":"Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin, Unter den Linden 6, 10099, Berlin, Germany","institution_ids":["https://openalex.org/I39343248"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":3.2774,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93068081,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"26","issue":"1","first_page":"240","last_page":"240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9991999864578247,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.992900013923645,"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/generalizability-theory","display_name":"Generalizability theory","score":0.7156000137329102},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6419000029563904},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.571399986743927},{"id":"https://openalex.org/keywords/relationship-extraction","display_name":"Relationship extraction","score":0.5644999742507935},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5335000157356262},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5044000148773193},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.4936999976634979}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7405999898910522},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.7156000137329102},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6419000029563904},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.571399986743927},{"id":"https://openalex.org/C153604712","wikidata":"https://www.wikidata.org/wiki/Q7310755","display_name":"Relationship extraction","level":3,"score":0.5644999742507935},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.536300003528595},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5335000157356262},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5116999745368958},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5044000148773193},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.4936999976634979},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.486299991607666},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36880001425743103},{"id":"https://openalex.org/C66153294","wikidata":"https://www.wikidata.org/wiki/Q899291","display_name":"CASP","level":4,"score":0.35190001130104065},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31610000133514404},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.31189998984336853},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2572999894618988},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.2556999921798706}],"mesh":[{"descriptor_ui":"D000098342","descriptor_name":"Large Language Models","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":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1186/s12859-025-06262-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06262-6","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-025-06262-6","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41057775","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41057775","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:europepmc.org:11310438","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12502496","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12502496/pdf/12859_2025_Article_6262.pdf","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:doaj.org/article:bcd5d6b4e8ed47df859d92dc0b444bd5","is_oa":true,"landing_page_url":"https://doaj.org/article/bcd5d6b4e8ed47df859d92dc0b444bd5","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 26, Iss 1, Pp 1-25 (2025)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12502496","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12502496/","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":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-025-06262-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06262-6","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-025-06262-6","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320323700","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414881761.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W90362830","https://openalex.org/W1601495365","https://openalex.org/W1975147762","https://openalex.org/W1983610905","https://openalex.org/W2024862171","https://openalex.org/W2027482274","https://openalex.org/W2052250375","https://openalex.org/W2096541451","https://openalex.org/W2107580398","https://openalex.org/W2119412782","https://openalex.org/W2142153593","https://openalex.org/W2170189740","https://openalex.org/W2346452181","https://openalex.org/W2899070097","https://openalex.org/W2911489562","https://openalex.org/W2946690328","https://openalex.org/W2970771982","https://openalex.org/W3009295847","https://openalex.org/W3045642779","https://openalex.org/W3046375318","https://openalex.org/W3093844547","https://openalex.org/W3093891978","https://openalex.org/W3100452049","https://openalex.org/W3112376646","https://openalex.org/W3184553911","https://openalex.org/W3185341429","https://openalex.org/W3208785685","https://openalex.org/W4221153690","https://openalex.org/W4226118422","https://openalex.org/W4297458751","https://openalex.org/W4309659061","https://openalex.org/W4309728330","https://openalex.org/W4327722639","https://openalex.org/W4362601037","https://openalex.org/W4381573137","https://openalex.org/W4386320945","https://openalex.org/W4387223206","https://openalex.org/W4393936594","https://openalex.org/W4400127918","https://openalex.org/W4401040924","https://openalex.org/W4401857142"],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"relationship":[1],"extraction":[2,163],"(RE)":[3],"from":[4,133],"biomedical":[5],"literature":[6],"is":[7],"critical":[8],"for":[9,48,59,160,181],"managing":[10],"the":[11,30,53,56,75,118,143,147,150],"vast":[12],"amount":[13],"of":[14,77,145,149,167],"scientific":[15],"knowledge":[16,134],"produced":[17],"each":[18],"year.":[19],"In":[20],"recent":[21],"years,":[22],"utilizing":[23],"pre-trained":[24],"language":[25,152],"models":[26],"(PLMs)":[27],"has":[28],"become":[29],"prevalent":[31],"approach":[32],"in":[33,52],"RE.":[34,49],"Several":[35],"studies":[36,70],"report":[37],"improved":[38],"performance":[39],"when":[40,184],"incorporating":[41],"additional":[42,125],"context":[43,168],"information":[44,92,132,169],"while":[45],"fine-tuning":[46],"PLMs":[47,54,88,109,183],"However,":[50],"variations":[51],"applied,":[55],"databases":[57],"used":[58],"augmentation,":[60],"hyper-parameter":[61],"optimization,":[62],"and":[63,71,110,136,154],"evaluation":[64,103],"methods":[65],"complicate":[66],"direct":[67],"comparisons":[68],"between":[69],"raise":[72],"questions":[73],"about":[74],"generalizability":[76],"these":[78],"findings.":[79],"Our":[80,140],"study":[81,177],"addresses":[82],"this":[83],"research":[84],"gap":[85],"by":[86],"evaluating":[87],"enhanced":[89],"with":[90,124],"contextual":[91],"on":[93],"five":[94],"datasets":[95],"spanning":[96],"four":[97],"relation":[98],"scenarios":[99],"within":[100],"a":[101,156],"consistent":[102],"framework.":[104],"We":[105],"evaluate":[106],"three":[107],"baseline":[108],"first":[111],"conduct":[112],"extensive":[113],"hyperparameter":[114,158],"optimization.":[115],"After":[116],"selecting":[117],"top-performing":[119],"model,":[120],"we":[121],"enhance":[122],"it":[123],"data,":[126],"including":[127],"textual":[128],"entity":[129],"descriptions,":[130],"relational":[131],"graphs,":[135],"molecular":[137],"structure":[138],"encodings.":[139],"findings":[141],"illustrate":[142],"importance":[144],"(1)":[146],"choice":[148],"underlying":[151],"model":[153],"(2)":[155],"comprehensive":[157],"optimization":[159],"achieving":[161],"strong":[162],"performance.":[164],"Although":[165],"inclusion":[166],"yield":[170],"only":[171],"minor":[172],"overall":[173],"improvements,":[174],"an":[175],"ablation":[176],"reveals":[178],"substantial":[179],"benefits":[180],"smaller":[182],"such":[185],"external":[186],"data":[187],"was":[188],"included":[189],"during":[190],"fine-tuning.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-28T08:01:55.173337","created_date":"2025-10-10T00:00:00"}