{"id":"https://openalex.org/W7127309760","doi":"https://doi.org/10.1080/09540091.2026.2624131","title":"LncRNA-BERT: an RNA language model for classifying coding and long non-coding RNA","display_name":"LncRNA-BERT: an RNA language model for classifying coding and long non-coding RNA","publication_year":2026,"publication_date":"2026-02-03","ids":{"openalex":"https://openalex.org/W7127309760","doi":"https://doi.org/10.1080/09540091.2026.2624131"},"language":"en","primary_location":{"id":"doi:10.1080/09540091.2026.2624131","is_oa":true,"landing_page_url":"https://doi.org/10.1080/09540091.2026.2624131","pdf_url":"https://www.tandfonline.com/doi/pdf/10.1080/09540091.2026.2624131?needAccess=true","source":{"id":"https://openalex.org/S4210188800","display_name":"Connection Science","issn_l":"0954-0091","issn":["0954-0091","1360-0494"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Connection Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.tandfonline.com/doi/pdf/10.1080/09540091.2026.2624131?needAccess=true","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115859706","display_name":"Luuk Romeijn","orcid":null},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]},{"id":"https://openalex.org/I2800006345","display_name":"Leiden University Medical Center","ror":"https://ror.org/05xvt9f17","country_code":"NL","type":"funder","lineage":["https://openalex.org/I2800006345"]},{"id":"https://openalex.org/I4210155092","display_name":"Czech Academy of Sciences, Institute of Computer Science","ror":"https://ror.org/0496n6574","country_code":"CZ","type":"facility","lineage":["https://openalex.org/I202391551","https://openalex.org/I4210155092"]}],"countries":["CZ","NL"],"is_corresponding":false,"raw_author_name":"Luuk Romeijn","raw_affiliation_strings":["Department of Biomedical Data Sciences, Leiden University Medical Center","Leiden Institute of Advanced Computer Science, Leiden University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Data Sciences, Leiden University Medical Center","institution_ids":["https://openalex.org/I2800006345"]},{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science, Leiden University","institution_ids":["https://openalex.org/I121797337","https://openalex.org/I4210155092"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033794718","display_name":"Davy Cats","orcid":"https://orcid.org/0000-0001-9684-220X"},"institutions":[{"id":"https://openalex.org/I2800006345","display_name":"Leiden University Medical Center","ror":"https://ror.org/05xvt9f17","country_code":"NL","type":"funder","lineage":["https://openalex.org/I2800006345"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Davy Cats","raw_affiliation_strings":["Department of Biomedical Data Sciences, Leiden University Medical Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Data Sciences, Leiden University Medical Center","institution_ids":["https://openalex.org/I2800006345"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124954453","display_name":"Katherine Wolstencroft","orcid":null},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]},{"id":"https://openalex.org/I4210155092","display_name":"Czech Academy of Sciences, Institute of Computer Science","ror":"https://ror.org/0496n6574","country_code":"CZ","type":"facility","lineage":["https://openalex.org/I202391551","https://openalex.org/I4210155092"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["CZ","NL"],"is_corresponding":false,"raw_author_name":"Katherine Wolstencroft","raw_affiliation_strings":["Advanced Compute and Data Core, Amsterdam University Medical Center","Leiden Institute of Advanced Computer Science, Leiden University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Compute and Data Core, Amsterdam University Medical Center","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science, Leiden University","institution_ids":["https://openalex.org/I121797337","https://openalex.org/I4210155092"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124948722","display_name":"Hailiang Mei","orcid":null},"institutions":[{"id":"https://openalex.org/I2800006345","display_name":"Leiden University Medical Center","ror":"https://ror.org/05xvt9f17","country_code":"NL","type":"funder","lineage":["https://openalex.org/I2800006345"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Hailiang Mei","raw_affiliation_strings":["Department of Biomedical Data Sciences, Leiden University Medical Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Data Sciences, Leiden University Medical Center","institution_ids":["https://openalex.org/I2800006345"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5124948722"],"corresponding_institution_ids":["https://openalex.org/I2800006345"],"apc_list":{"value":1270,"currency":"USD","value_usd":1270},"apc_paid":{"value":1270,"currency":"USD","value_usd":1270},"fwci":5.2205,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91779854,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"38","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10515","display_name":"Cancer-related molecular mechanisms research","score":0.9746000170707703,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/T10515","display_name":"Cancer-related molecular mechanisms research","score":0.9746000170707703,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/T12610","display_name":"RNA regulation and disease","score":0.00419999985024333,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.003100000089034438,"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/coding","display_name":"Coding (social sciences)","score":0.5910999774932861},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5644999742507935},{"id":"https://openalex.org/keywords/rna","display_name":"RNA","score":0.5356000065803528},{"id":"https://openalex.org/keywords/predictive-coding","display_name":"Predictive coding","score":0.34119999408721924},{"id":"https://openalex.org/keywords/long-non-coding-rna","display_name":"Long non-coding RNA","score":0.3391999900341034},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3167000114917755}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6962000131607056},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5910999774932861},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5644999742507935},{"id":"https://openalex.org/C67705224","wikidata":"https://www.wikidata.org/wiki/Q11053","display_name":"RNA","level":3,"score":0.5356000065803528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5148000121116638},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.504800021648407},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3578999936580658},{"id":"https://openalex.org/C2778061373","wikidata":"https://www.wikidata.org/wiki/Q1315146","display_name":"Predictive coding","level":3,"score":0.34119999408721924},{"id":"https://openalex.org/C62203573","wikidata":"https://www.wikidata.org/wiki/Q15087973","display_name":"Long non-coding RNA","level":4,"score":0.3391999900341034},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C194993378","wikidata":"https://www.wikidata.org/wiki/Q427087","display_name":"Non-coding RNA","level":4,"score":0.2802000045776367},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/09540091.2026.2624131","is_oa":true,"landing_page_url":"https://doi.org/10.1080/09540091.2026.2624131","pdf_url":"https://www.tandfonline.com/doi/pdf/10.1080/09540091.2026.2624131?needAccess=true","source":{"id":"https://openalex.org/S4210188800","display_name":"Connection Science","issn_l":"0954-0091","issn":["0954-0091","1360-0494"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Connection Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1080/09540091.2026.2624131","is_oa":true,"landing_page_url":"https://doi.org/10.1080/09540091.2026.2624131","pdf_url":"https://www.tandfonline.com/doi/pdf/10.1080/09540091.2026.2624131?needAccess=true","source":{"id":"https://openalex.org/S4210188800","display_name":"Connection Science","issn_l":"0954-0091","issn":["0954-0091","1360-0494"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Connection Science","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.43598219752311707,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7127309760.pdf","grobid_xml":"https://content.openalex.org/works/W7127309760.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1998422171","https://openalex.org/W2048194168","https://openalex.org/W2061548680","https://openalex.org/W2075320162","https://openalex.org/W2145931730","https://openalex.org/W2170747616","https://openalex.org/W2173732482","https://openalex.org/W2536860838","https://openalex.org/W2615786037","https://openalex.org/W2788447865","https://openalex.org/W2793097545","https://openalex.org/W2801116223","https://openalex.org/W2805813857","https://openalex.org/W2807607992","https://openalex.org/W2886900083","https://openalex.org/W2951413354","https://openalex.org/W2962784628","https://openalex.org/W2972083913","https://openalex.org/W2999743161","https://openalex.org/W3095979265","https://openalex.org/W3098372957","https://openalex.org/W3102734422","https://openalex.org/W3160510922","https://openalex.org/W3179194243","https://openalex.org/W3187121296","https://openalex.org/W4213095938","https://openalex.org/W4214669263","https://openalex.org/W4290546063","https://openalex.org/W4309908754","https://openalex.org/W4309908782","https://openalex.org/W4319335178","https://openalex.org/W4380488316","https://openalex.org/W4381328026","https://openalex.org/W4385605273","https://openalex.org/W4388237191","https://openalex.org/W4392895925","https://openalex.org/W4396871204","https://openalex.org/W4400329083","https://openalex.org/W4400378440","https://openalex.org/W4400768688","https://openalex.org/W4401668270","https://openalex.org/W4402673179","https://openalex.org/W4404768368","https://openalex.org/W4404821554","https://openalex.org/W4406312067","https://openalex.org/W4406990299","https://openalex.org/W4411886797"],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"(novel)":[1],"RNA":[2,36,65,109,175],"transcripts":[3],"generated":[4],"in":[5,28],"next":[6],"generation":[7],"sequencing":[8],"experiments":[9],"requires":[10],"accurate":[11],"classification,":[12],"given":[13],"the":[14,45,76,96,143,181],"increasing":[15],"evidence":[16],"that":[17,42,50,115,177],"long":[18,107,174],"non-coding":[19,108],"RNAs":[20,73],"(lncRNAs)":[21],"play":[22],"crucial":[23],"regulatory":[24],"roles.":[25],"Recent":[26],"developments":[27],"Large":[29],"Language":[30],"Models":[31],"present":[32,62],"opportunities":[33],"for":[34,171],"classifying":[35],"coding":[37,52,105,116],"potential":[38,53,117],"with":[39,173],"sequence-based":[40],"algorithms":[41],"can":[43],"overcome":[44],"limitations":[46],"of":[47,58],"classical":[48],"approaches":[49],"assess":[51],"based":[54],"on":[55,71,91,130,142],"a":[56,119,152],"set":[57],"predefined":[59],"features.":[60],"We":[61],"lncRNA-BERT,":[63],"an":[64],"language":[66],"model":[67,103],"pre-trained":[68,101,141],"and":[69,79,87,136,162,167],"fine-tuned":[70],"human":[72,131],"collected":[74],"from":[75,106,128,133],"GENCODE,":[77,134],"RefSeq,":[78,135],"NONCODE":[80],"databases":[81],"to":[82,126],"classify":[83],"lncRNAs.":[84],"LncRNA-BERT":[85,122],"matches":[86],"outperforms":[88],"state-of-the-art":[89],"classifiers":[90],"three":[92],"test":[93],"datasets,":[94],"including":[95],"cross-species":[97],"RNAChallenge":[98],"benchmark.":[99],"The":[100],"lncRNA-BERT":[102,186],"distinguishes":[104],"without":[110],"supervised":[111],"learning":[112],"which":[113,158],"confirms":[114],"is":[118,187],"sequence-intrinsic":[120],"characteristic.":[121],"has":[123],"been":[124],"shown":[125],"benefit":[127],"pre-training":[129],"data":[132],"NONCODE,":[137],"improving":[138],"upon":[139],"configurations":[140],"commonly":[144],"used":[145],"RNAcentral":[146],"dataset.":[147],"In":[148],"addition,":[149],"we":[150],"propose":[151],"novel":[153],"Convolutional":[154],"Sequence":[155],"Encoding":[156,170],"method":[157],"demonstrated":[159],"superior":[160],"efficiency":[161],"performance":[163],"than":[164],"K-mer":[165],"Tokenization":[166],"Byte":[168],"Pair":[169],"training":[172],"sequences":[176],"are":[178],"otherwise":[179],"above":[180],"common":[182],"context":[183],"window":[184],"size.":[185],"available":[188],"at":[189],"https://github.com/luukromeijn/lncRNA-Py.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-02-04T00:00:00"}
