{"id":"https://openalex.org/W7126015404","doi":"https://doi.org/10.1109/bibm66473.2025.11357206","title":"Exploratory Analysis of the Regulation of Long Non-Coding RNA Transcription with Nucleotide Large Language Models","display_name":"Exploratory Analysis of the Regulation of Long Non-Coding RNA Transcription with Nucleotide Large Language Models","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126015404","doi":"https://doi.org/10.1109/bibm66473.2025.11357206"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11357206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11357206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124208098","display_name":"Wei Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Meta Platform Inc.,Menlo Park,CA,USA"],"affiliations":[{"raw_affiliation_string":"Meta Platform Inc.,Menlo Park,CA,USA","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124216453","display_name":"Zhichao Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhichao Hou","raw_affiliation_strings":["North Carolina State University,Department of Computer Science,Raleigh,NC,USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University,Department of Computer Science,Raleigh,NC,USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111287829","display_name":"Tianfu Matt Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianfu Wu","raw_affiliation_strings":["North Carolina State University,Department of Electrical and Computer Engineering,Raleigh,NC,USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University,Department of Electrical and Computer Engineering,Raleigh,NC,USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009156496","display_name":"Dage Liu","orcid":"https://orcid.org/0000-0002-5412-2535"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaorui Liu","raw_affiliation_strings":["North Carolina State University,Department of Computer Science,Raleigh,NC,USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University,Department of Computer Science,Raleigh,NC,USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076553823","display_name":"Xinxia Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinxia Peng","raw_affiliation_strings":["North Carolina State University,Bioinformatics Research Center,Department of Molecular Biomedical Sciences,Raleigh,NC,USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University,Bioinformatics Research Center,Department of Molecular Biomedical Sciences,Raleigh,NC,USA","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5124208098"],"corresponding_institution_ids":["https://openalex.org/I4210114444"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68675961,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7764","last_page":"7771"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10515","display_name":"Cancer-related molecular mechanisms research","score":0.8507999777793884,"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":0.8507999777793884,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.049800001084804535,"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/T12610","display_name":"RNA regulation and disease","score":0.03180000185966492,"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/interpretability","display_name":"Interpretability","score":0.7243000268936157},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4584999978542328},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4431000053882599},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.41280001401901245},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4043000042438507},{"id":"https://openalex.org/keywords/biomedicine","display_name":"Biomedicine","score":0.382999986410141},{"id":"https://openalex.org/keywords/regulatory-sequence","display_name":"Regulatory sequence","score":0.36890000104904175},{"id":"https://openalex.org/keywords/systems-biology","display_name":"Systems biology","score":0.36410000920295715},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.35409998893737793}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7243000268936157},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5706999897956848},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4584999978542328},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4431000053882599},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43209999799728394},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4268999993801117},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.41280001401901245},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4043000042438507},{"id":"https://openalex.org/C66782513","wikidata":"https://www.wikidata.org/wiki/Q864601","display_name":"Biomedicine","level":2,"score":0.382999986410141},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3808000087738037},{"id":"https://openalex.org/C21592294","wikidata":"https://www.wikidata.org/wiki/Q3238407","display_name":"Regulatory sequence","level":4,"score":0.36890000104904175},{"id":"https://openalex.org/C152662350","wikidata":"https://www.wikidata.org/wiki/Q815297","display_name":"Systems biology","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.3314000070095062},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.3086000084877014},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.2992999851703644},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.2924000024795532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29179999232292175},{"id":"https://openalex.org/C3018260909","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory analysis","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C27153228","wikidata":"https://www.wikidata.org/wiki/Q3787274","display_name":"Transcriptional regulation","level":4,"score":0.2597000002861023},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.25850000977516174},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm66473.2025.11357206","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11357206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1988581590","https://openalex.org/W2030479443","https://openalex.org/W2037363723","https://openalex.org/W2144211451","https://openalex.org/W2145931730","https://openalex.org/W2147380886","https://openalex.org/W2157399331","https://openalex.org/W2767184075","https://openalex.org/W2890017579","https://openalex.org/W2903950532","https://openalex.org/W2971451528","https://openalex.org/W3115880421","https://openalex.org/W3127238141","https://openalex.org/W3133859624","https://openalex.org/W3171835979","https://openalex.org/W3203588026","https://openalex.org/W4213095938","https://openalex.org/W4223547475","https://openalex.org/W4297243391","https://openalex.org/W4313488537","https://openalex.org/W4327550249","https://openalex.org/W4391035666","https://openalex.org/W4392168151","https://openalex.org/W4396871204","https://openalex.org/W4400729643","https://openalex.org/W4401966068","https://openalex.org/W4407820212","https://openalex.org/W4408811547"],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,62,76,111,165,175],"(LLMs)":[3],"have":[4],"emerged":[5],"as":[6],"powerful":[7],"tools":[8],"for":[9,170],"biological":[10,70,103],"sequence":[11,131,142],"analysis.":[12,179],"However,":[13],"their":[14,41],"applicability":[15],"to":[16,28,67,86],"the":[17,29,89,126,158],"transcriptional":[18],"regulation":[19,178],"of":[20,33,40,59,80,91,133,162,173],"long":[21],"non-coding":[22],"RNAs":[23],"(IncRNAs)":[24],"remains":[25,138],"underexplored":[26],"due":[27],"complexity":[30,98],"and":[31,44,55,102,119,148,160,166],"diversity":[32],"IncRNA":[34,92,134,177],"sequences,":[35],"combined":[36],"with":[37],"limited":[38,139],"knowledge":[39],"regulatory":[42],"mechanisms":[43],"functional":[45],"characteristics.":[46],"In":[47],"this":[48,152],"study,":[49],"we":[50,94],"systematically":[51],"evaluate":[52],"both":[53],"singletask":[54],"multi-task":[56],"fine-tuning":[57,73],"strategies":[58],"genome":[60,74],"foundation":[61,75,110,169],"across":[63],"four":[64],"tasks":[65],"designed":[66,85],"capture":[68,112],"increasing":[69],"complexity.":[71],"By":[72],"on":[77],"a":[78,168],"series":[79],"progressively":[81],"complex":[82],"tasks,":[83],"each":[84],"closely":[87],"mimic":[88],"complexities":[90],"classification,":[93],"explore":[95],"how":[96],"task":[97,115],"impacts":[99],"model":[100],"performance":[101,146],"interpretability.":[104],"Our":[105],"findings":[106],"reveal":[107],"that":[108],"while":[109],"promoter-specific":[113],"signals,":[114],"complexity,":[116],"input":[117],"length,":[118],"data":[120],"quality":[121],"significantly":[122],"influence":[123],"performance.":[124],"Notably,":[125],"most":[127],"challenging":[128],"task,":[129],"promoter":[130],"classification":[132],"from":[135],"coding":[136],"genes,":[137],"by":[140],"primary":[141],"features":[143],"alone.":[144],"Through":[145],"evaluation":[147],"attentionbased":[149],"interpretability":[150],"analysis,":[151],"work":[153],"provides":[154],"key":[155],"insights":[156],"into":[157],"potential":[159],"limitations":[161],"current":[163],"LLM-based":[164],"offers":[167],"future":[171],"development":[172],"integrative":[174],"in":[176],"The":[180],"dataset":[181],"is":[182],"available":[183],"at":[184],"https://github.com/wangwe90/IncRNA-promoter-sequence-detection-dataset":[185]},"counts_by_year":[],"updated_date":"2026-02-01T03:34:12.195049","created_date":"2026-01-30T00:00:00"}
