{"id":"https://openalex.org/W4417062606","doi":"https://doi.org/10.1145/3768322.3769100","title":"Uncertainty-Aware Fine-Tuning in Genomic Language Models","display_name":"Uncertainty-Aware Fine-Tuning in Genomic Language Models","publication_year":2025,"publication_date":"2025-10-11","ids":{"openalex":"https://openalex.org/W4417062606","doi":"https://doi.org/10.1145/3768322.3769100"},"language":null,"primary_location":{"id":"doi:10.1145/3768322.3769100","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3768322.3769100","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3768322.3769100","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"conference-abstract","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3768322.3769100","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5098975021","display_name":"Gavin Hearne","orcid":"https://orcid.org/0009-0006-9193-4264"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gavin Hearne","raw_affiliation_strings":["Drexel University, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0009-0006-9193-4264","affiliations":[{"raw_affiliation_string":"Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023224900","display_name":"Gail Rosen","orcid":"https://orcid.org/0000-0003-1763-5750"},"institutions":[{"id":"https://openalex.org/I72816309","display_name":"Drexel University","ror":"https://ror.org/04bdffz58","country_code":"US","type":"education","lineage":["https://openalex.org/I72816309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gail Rosen","raw_affiliation_strings":["Drexel University, Philadelphia, PA, USA"],"raw_orcid":"https://orcid.org/0000-0003-1763-5750","affiliations":[{"raw_affiliation_string":"Drexel University, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I72816309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I72816309"],"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":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.2533999979496002,"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"}},"topics":[{"id":"https://openalex.org/T11642","display_name":"Genomics and Rare Diseases","score":0.2533999979496002,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.09160000085830688,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.0885000005364418,"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/scalability","display_name":"Scalability","score":0.6935999989509583},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4731000065803528},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.43689998984336853},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.38920000195503235},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.3765000104904175},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.34610000252723694},{"id":"https://openalex.org/keywords/genomic-sequencing","display_name":"Genomic sequencing","score":0.3352000117301941},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3100000023841858}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7142999768257141},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6935999989509583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4918999969959259},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4731000065803528},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4690000116825104},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.43689998984336853},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.38920000195503235},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.3765000104904175},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3686000108718872},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C2994067223","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"Genomic sequencing","level":4,"score":0.3352000117301941},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32600000500679016},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2913999855518341},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.2750000059604645},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C40993552","wikidata":"https://www.wikidata.org/wiki/Q514654","display_name":"Gold standard (test)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3768322.3769100","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3768322.3769100","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3768322.3769100","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3768322.3769100","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3768322.3769100","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3768322.3769100","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the 16th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417062606.pdf","grobid_xml":"https://content.openalex.org/works/W4417062606.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Transformer-based":[0],"Genomic":[1],"Language":[2],"Models":[3],"(GLMs),":[4],"such":[5],"as":[6],"DNABERT":[7],"and":[8,54,86],"the":[9,106],"Nucleotide":[10],"Transformer,":[11],"have":[12],"achieved":[13],"strong":[14],"performance":[15],"on":[16,32],"a":[17,39,72],"wide":[18],"range":[19],"of":[20,92,100,102,108],"genomic":[21,88],"prediction":[22],"tasks.":[23],"However":[24],"their":[25,42,77],"tendency":[26],"to":[27,41],"produce":[28],"overconfident":[29],"predictions,":[30],"particularly":[31],"noisy":[33],"or":[34],"out-of-distribution":[35],"(OOD)":[36],"data,":[37],"remains":[38],"barrier":[40],"reliable":[43],"use":[44],"in":[45],"practice.":[46],"In":[47],"genomics,":[48],"where":[49,90],"unknown":[50],"species,":[51],"novel":[52],"variants,":[53],"heterogeneous":[55],"sequencing":[56],"data":[57],"are":[58,69],"common,":[59],"robust":[60],"uncertainty":[61],"quantification":[62],"(UQ)":[63],"is":[64],"essential.":[65],"While":[66],"deep":[67],"ensembles":[68],"often":[70],"considered":[71],"gold":[73],"standard":[74],"for":[75,83],"UQ,":[76],"computational":[78],"overhead":[79],"makes":[80],"them":[81],"impractical":[82],"large":[84],"GLMs":[85],"large-scale":[87],"datasets,":[89],"billions":[91,101],"sequences":[93],"may":[94],"be":[95],"processed":[96],"through":[97],"models":[98],"consisting":[99],"parameters.":[103],"This":[104],"motivates":[105],"exploration":[107],"lighter-weight":[109],"approaches":[110],"that":[111],"preserve":[112],"scalability":[113],"without":[114],"sacrificing":[115],"predictive":[116],"reliability.":[117]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-05T00:00:00"}