{"id":"https://openalex.org/W4417251048","doi":"https://doi.org/10.1109/bibe66822.2025.00113","title":"Large Language Models for Genomic Sequence Understanding: Classifying Introns/Exons and Translating DNA to Protein","display_name":"Large Language Models for Genomic Sequence Understanding: Classifying Introns/Exons and Translating DNA to Protein","publication_year":2025,"publication_date":"2025-11-06","ids":{"openalex":"https://openalex.org/W4417251048","doi":"https://doi.org/10.1109/bibe66822.2025.00113"},"language":null,"primary_location":{"id":"doi:10.1109/bibe66822.2025.00113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibe66822.2025.00113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 25th International Conference on Bioinformatics and Bioengineering (BIBE)","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/A5103135534","display_name":"Gustavo Cruz","orcid":"https://orcid.org/0000-0003-1438-2284"},"institutions":[{"id":"https://openalex.org/I4210092022","display_name":"Heart Foundation","ror":"https://ror.org/00h4cdy24","country_code":"US","type":"other","lineage":["https://openalex.org/I4210092022"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gustavo Cruz","raw_affiliation_strings":["Heart Institute (InCor) - HCFMUSP,Informatics Postgraduate Program, UFPR, R&D,São Paulo,Brazil"],"affiliations":[{"raw_affiliation_string":"Heart Institute (InCor) - HCFMUSP,Informatics Postgraduate Program, UFPR, R&D,São Paulo,Brazil","institution_ids":["https://openalex.org/I4210092022"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007123533","display_name":"Aurora Pozo","orcid":"https://orcid.org/0000-0001-5808-3919"},"institutions":[{"id":"https://openalex.org/I52418104","display_name":"Universidade Federal do Paran\u00e1","ror":"https://ror.org/05syd6y78","country_code":"BR","type":"education","lineage":["https://openalex.org/I52418104"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Aurora Trinidad Ramirez Pozo","raw_affiliation_strings":["Department of Informatics - UFPR,Curitiba,Brazil"],"affiliations":[{"raw_affiliation_string":"Department of Informatics - UFPR,Curitiba,Brazil","institution_ids":["https://openalex.org/I52418104"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103135534"],"corresponding_institution_ids":["https://openalex.org/I4210092022"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35279742,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"653","last_page":"657"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9047999978065491,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9047999978065491,"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":0.024800000712275505,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.020099999383091927,"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":0.571399986743927},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5317999720573425},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5031999945640564},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.4729999899864197},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4551999866962433},{"id":"https://openalex.org/keywords/coding-region","display_name":"Coding region","score":0.44040000438690186},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.39480000734329224},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.36010000109672546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5985000133514404},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.571399986743927},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5658000111579895},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5317999720573425},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5031999945640564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48010000586509705},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4729999899864197},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4551999866962433},{"id":"https://openalex.org/C91779695","wikidata":"https://www.wikidata.org/wiki/Q3780824","display_name":"Coding region","level":3,"score":0.44040000438690186},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.39480000734329224},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38040000200271606},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C17757408","wikidata":"https://www.wikidata.org/wiki/Q4135516","display_name":"genomic DNA","level":3,"score":0.3571000099182129},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.35690000653266907},{"id":"https://openalex.org/C149034497","wikidata":"https://www.wikidata.org/wiki/Q1384835","display_name":"Expressed sequence tag","level":4,"score":0.35109999775886536},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.3379000127315521},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.3375000059604645},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.31380000710487366},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.2930999994277954},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.29010000824928284},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.2851000130176544},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.28369998931884766},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2824000120162964}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibe66822.2025.00113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibe66822.2025.00113","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 25th International Conference on Bioinformatics and Bioengineering (BIBE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7528236091","display_name":null,"funder_award_id":"407644/2021-0,04515/2022-1","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"}],"funders":[{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2809442901","https://openalex.org/W2809541759","https://openalex.org/W2906125480","https://openalex.org/W2909194804","https://openalex.org/W2956257472","https://openalex.org/W2996771978","https://openalex.org/W3025307178","https://openalex.org/W3127238141","https://openalex.org/W4405005386"],"related_works":[],"abstract_inverted_index":{"This":[0],"work":[1],"explores":[2],"the":[3,58],"application":[4],"of":[5,38,60],"Transformerbased":[6],"architectures":[7],"for":[8,62],"genomic":[9,64],"sequence":[10,67],"analysis,":[11],"focusing":[12],"on":[13,46],"intron-exon":[14],"classification":[15,65],"and":[16,33,44,53,66],"DNA-to-protein":[17],"translation.":[18],"We":[19],"evaluate":[20],"three":[21],"models:":[22],"GPT":[23],"(Generative":[24],"Pre-trained":[25],"Transformer),":[26],"BERT":[27],"(Bidirectional":[28],"Encoder":[29],"Representations":[30],"from":[31,48],"Transformers),":[32],"DNABERT,":[34],"a":[35],"DNA-specific":[36],"variant":[37],"BERT.":[39],"The":[40],"models":[41],"are":[42],"trained":[43],"tested":[45],"datasets":[47],"GenBank,":[49],"covering":[50],"entire":[51],"sequences":[52],"sliding-window":[54],"approaches.":[55],"Results":[56],"demonstrate":[57],"potential":[59],"Transformers":[61],"accurate":[63],"translation,":[68],"highlighting":[69],"their":[70],"applicability":[71],"in":[72],"coding":[73],"regions":[74],"identification":[75],"tasks.":[76]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-12-11T00:00:00"}