{"id":"https://openalex.org/W7123764788","doi":"https://doi.org/10.1021/acs.jcim.5c02747","title":"DNACSE: Enhancing Genomic LLMs with Contrastive Learning for DNA Barcode Identification","display_name":"DNACSE: Enhancing Genomic LLMs with Contrastive Learning for DNA Barcode Identification","publication_year":2026,"publication_date":"2026-01-13","ids":{"openalex":"https://openalex.org/W7123764788","doi":"https://doi.org/10.1021/acs.jcim.5c02747","pmid":"https://pubmed.ncbi.nlm.nih.gov/41528854"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.5c02747","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c02747","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100663490","display_name":"Jiadong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"government","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiadong Wang","raw_affiliation_strings":["Dalian University","The Key Laboratory of Advanced Design and Intelligent Computing, Ministry of Education, School of Software Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University","institution_ids":["https://openalex.org/I4210092944"]},{"raw_affiliation_string":"The Key Laboratory of Advanced Design and Intelligent Computing, Ministry of Education, School of Software Engineering","institution_ids":["https://openalex.org/I1327237609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122969510","display_name":"Bin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"government","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bin Wang","raw_affiliation_strings":["Dalian University","The Key Laboratory of Advanced Design and Intelligent Computing, Ministry of Education, School of Software Engineering"],"raw_orcid":"https://orcid.org/0000-0002-8800-000X","affiliations":[{"raw_affiliation_string":"Dalian University","institution_ids":["https://openalex.org/I4210092944"]},{"raw_affiliation_string":"The Key Laboratory of Advanced Design and Intelligent Computing, Ministry of Education, School of Software Engineering","institution_ids":["https://openalex.org/I1327237609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056678444","display_name":"Shihua Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"government","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shihua Zhou","raw_affiliation_strings":["Dalian University","The Key Laboratory of Advanced Design and Intelligent Computing, Ministry of Education, School of Software Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University","institution_ids":["https://openalex.org/I4210092944"]},{"raw_affiliation_string":"The Key Laboratory of Advanced Design and Intelligent Computing, Ministry of Education, School of Software Engineering","institution_ids":["https://openalex.org/I1327237609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122937510","display_name":"Ben Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]},{"id":"https://openalex.org/I4390039265","display_name":"PRG S&Tech (South Korea)","ror":"https://ror.org/02sr2ee22","country_code":null,"type":"company","lineage":["https://openalex.org/I4390039265"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ben Cao","raw_affiliation_strings":["Dalian University of Technology","School of Computer Science and Technology"],"raw_orcid":"https://orcid.org/0000-0003-1503-6009","affiliations":[{"raw_affiliation_string":"Dalian University of Technology","institution_ids":["https://openalex.org/I27357992"]},{"raw_affiliation_string":"School of Computer Science and Technology","institution_ids":["https://openalex.org/I4390039265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122962692","display_name":"Wei Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090724","display_name":"State Key Laboratory of Building Safety and Built Environment","ror":"https://ror.org/00g8d1q08","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210090724"]},{"id":"https://openalex.org/I877107187","display_name":"University of Roehampton","ror":"https://ror.org/043071f54","country_code":"GB","type":"education","lineage":["https://openalex.org/I877107187"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["School of Computing, Engineering and the Built Environment (CEBE)","University of Roehampton"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Engineering and the Built Environment (CEBE)","institution_ids":["https://openalex.org/I4210090724"]},{"raw_affiliation_string":"University of Roehampton","institution_ids":["https://openalex.org/I877107187"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122924556","display_name":"Pan Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I185492890","display_name":"University of Canterbury","ror":"https://ror.org/03y7q9t39","country_code":"NZ","type":"education","lineage":["https://openalex.org/I185492890"]},{"id":"https://openalex.org/I4210165760","display_name":"College of Accounting","ror":"https://ror.org/01e5pnf26","country_code":"SI","type":"education","lineage":["https://openalex.org/I4210165760"]}],"countries":["NZ","SI"],"is_corresponding":false,"raw_author_name":"Pan Zheng","raw_affiliation_strings":["Department of Accounting and Information Systems","University of Canterbury"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Accounting and Information Systems","institution_ids":["https://openalex.org/I4210165760"]},{"raw_affiliation_string":"University of Canterbury","institution_ids":["https://openalex.org/I185492890"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5056678444","https://openalex.org/A5122937510","https://openalex.org/A5122969510"],"corresponding_institution_ids":["https://openalex.org/I1327237609","https://openalex.org/I27357992","https://openalex.org/I4210092944","https://openalex.org/I4390039265"],"apc_list":null,"apc_paid":null,"fwci":44.9601,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.99580728,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"66","issue":"2","first_page":"976","last_page":"993"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12640","display_name":"Environmental DNA in Biodiversity Studies","score":0.7325999736785889,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12640","display_name":"Environmental DNA in Biodiversity Studies","score":0.7325999736785889,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12388","display_name":"Identification and Quantification in Food","score":0.11140000075101852,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.1023000031709671,"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/barcode","display_name":"Barcode","score":0.8528000116348267},{"id":"https://openalex.org/keywords/dna-barcoding","display_name":"DNA barcoding","score":0.711899995803833},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5076000094413757},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.5055000185966492},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.46480000019073486},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.436599999666214},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.4343000054359436},{"id":"https://openalex.org/keywords/genomic-dna","display_name":"genomic DNA","score":0.4203000068664551},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4016999900341034}],"concepts":[{"id":"https://openalex.org/C2776841711","wikidata":"https://www.wikidata.org/wiki/Q856","display_name":"Barcode","level":2,"score":0.8528000116348267},{"id":"https://openalex.org/C141732470","wikidata":"https://www.wikidata.org/wiki/Q1154642","display_name":"DNA barcoding","level":2,"score":0.711899995803833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6431000232696533},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5370000004768372},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5076000094413757},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.5055000185966492},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.46480000019073486},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.436599999666214},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4343000054359436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4307999908924103},{"id":"https://openalex.org/C17757408","wikidata":"https://www.wikidata.org/wiki/Q4135516","display_name":"genomic DNA","level":3,"score":0.4203000068664551},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4165000021457672},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.36629998683929443},{"id":"https://openalex.org/C24586158","wikidata":"https://www.wikidata.org/wiki/Q27075","display_name":"Mitochondrial DNA","level":3,"score":0.36550000309944153},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.35109999775886536},{"id":"https://openalex.org/C49105822","wikidata":"https://www.wikidata.org/wiki/Q176996","display_name":"Polymerase chain reaction","level":3,"score":0.34700000286102295},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3319000005722046},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.31679999828338623},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.3158999979496002},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2937999963760376},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28769999742507935},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C199185054","wikidata":"https://www.wikidata.org/wiki/Q552299","display_name":"Chain (unit)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C3020077223","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomic information","level":4,"score":0.25949999690055847},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.25679999589920044}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058893","descriptor_name":"DNA Barcoding, Taxonomic","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D058893","descriptor_name":"DNA Barcoding, Taxonomic","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.5c02747","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c02747","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:41528854","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41528854","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":"Journal of chemical information and modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5227066278457642}],"awards":[{"id":"https://openalex.org/G1708588729","display_name":null,"funder_award_id":"2024-BS-267","funder_id":"https://openalex.org/F4320323086","funder_display_name":"Natural Science Foundation of Liaoning Province"},{"id":"https://openalex.org/G3412151233","display_name":null,"funder_award_id":"2024JH2/102600064","funder_id":"https://openalex.org/F4320327473","funder_display_name":"Department of Science and Technology of Liaoning Province"},{"id":"https://openalex.org/G4457078305","display_name":null,"funder_award_id":"62572088","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4765741851","display_name":null,"funder_award_id":"D20240244","funder_id":"https://openalex.org/F4320336644","funder_display_name":"High-end Foreign Experts Recruitment Plan of China"},{"id":"https://openalex.org/G49595074","display_name":null,"funder_award_id":"D23006","funder_id":"https://openalex.org/F4320327912","funder_display_name":"Higher Education Discipline Innovation Project"},{"id":"https://openalex.org/G503759827","display_name":null,"funder_award_id":"LJ222411258005","funder_id":"https://openalex.org/F4320324560","funder_display_name":"Department of Education of Liaoning Province"},{"id":"https://openalex.org/G5121078275","display_name":null,"funder_award_id":"2024-MSLH-009","funder_id":"https://openalex.org/F4320327473","funder_display_name":"Department of Science and Technology of Liaoning Province"},{"id":"https://openalex.org/G5664334659","display_name":null,"funder_award_id":"2024-MS-212","funder_id":"https://openalex.org/F4320323086","funder_display_name":"Natural Science Foundation of Liaoning Province"},{"id":"https://openalex.org/G6419423173","display_name":null,"funder_award_id":"62502063","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G769293279","display_name":null,"funder_award_id":"XLYC2403039","funder_id":"https://openalex.org/F4320329895","funder_display_name":"Liaoning Revitalization Talents Program"},{"id":"https://openalex.org/G8610243087","display_name":null,"funder_award_id":"62272079","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323086","display_name":"Natural Science Foundation of Liaoning Province","ror":null},{"id":"https://openalex.org/F4320324560","display_name":"Department of Education of Liaoning Province","ror":"https://ror.org/0022v2454"},{"id":"https://openalex.org/F4320327473","display_name":"Department of Science and Technology of Liaoning Province","ror":"https://ror.org/02f09cx53"},{"id":"https://openalex.org/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null},{"id":"https://openalex.org/F4320329895","display_name":"Liaoning Revitalization Talents Program","ror":null},{"id":"https://openalex.org/F4320336644","display_name":"High-end Foreign Experts Recruitment Plan of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2005536918","https://openalex.org/W2055043387","https://openalex.org/W2086996637","https://openalex.org/W2097793126","https://openalex.org/W2099901798","https://openalex.org/W2110375946","https://openalex.org/W2113054345","https://openalex.org/W2138621090","https://openalex.org/W2161005004","https://openalex.org/W2171571559","https://openalex.org/W2212552901","https://openalex.org/W2774661702","https://openalex.org/W2912959159","https://openalex.org/W2949676527","https://openalex.org/W2987322729","https://openalex.org/W2990774200","https://openalex.org/W3086141885","https://openalex.org/W3156636935","https://openalex.org/W3159259047","https://openalex.org/W3197054356","https://openalex.org/W4226086088","https://openalex.org/W4283797513","https://openalex.org/W4285602451","https://openalex.org/W4292477917","https://openalex.org/W4323046456","https://openalex.org/W4327977343","https://openalex.org/W4367597910","https://openalex.org/W4368617968","https://openalex.org/W4386065844","https://openalex.org/W4391682965","https://openalex.org/W4391693688","https://openalex.org/W4392044970","https://openalex.org/W4399138230","https://openalex.org/W4402353554","https://openalex.org/W4404821554","https://openalex.org/W4406290930","https://openalex.org/W4406457580","https://openalex.org/W4411090134","https://openalex.org/W4412030743","https://openalex.org/W4412454127","https://openalex.org/W4412663299","https://openalex.org/W4413025787","https://openalex.org/W4413140665","https://openalex.org/W4414404547","https://openalex.org/W4417165014"],"related_works":[],"abstract_inverted_index":{"DNA":[0,10,22,31,38,47,58,63,88,110,114,177,192,204],"barcoding":[1,64],"is":[2,51,220],"a":[3,26,208],"powerful":[4],"tool":[5],"for":[6,76],"exploring":[7],"biodiversity,":[8],"and":[9,18,32,40,120,130,140,164,203,214],"language":[11,48,59,89,111,178],"models":[12,60,112,179],"have":[13],"significantly":[14],"facilitated":[15],"its":[16],"construction":[17],"identification.":[19],"However,":[20],"since":[21],"barcodes":[23,39],"come":[24],"from":[25],"specific":[27],"region":[28],"of":[29,96,109,128,158,176,200],"mitochondrial":[30],"there":[33],"are":[34,168],"structural":[35],"differences":[36],"between":[37],"reference":[41],"genomes":[42],"used":[43],"to":[44,53,61,85,154,211],"train":[45],"existing":[46,57],"models,":[49],"it":[50,124,146],"difficult":[52],"directly":[54],"apply":[55],"the":[56,62,87,94,97,106,134,148,174],"task.":[65],"To":[66],"address":[67],"this,":[68],"this":[69],"paper":[70],"introduces":[71],"DNACSE":[72,104,172,186],"(DNA":[73],"Contrastive":[74],"Learning":[75],"Sequence":[77],"Embeddings),":[78],"an":[79,156],"unsupervised":[80],"noise-contrastive":[81],"learning":[82],"framework":[83],"designed":[84],"fine-tune":[86],"foundation":[90],"model":[91],"while":[92],"enhancing":[93],"distribution":[95],"embedding":[98],"space.":[99],"The":[100,217],"results":[101],"demonstrate":[102],"that":[103,171],"outperforms":[105],"direct":[107],"usage":[108],"in":[113,118,180,191],"barcoding-related":[115],"tasks.":[116,183],"Specifically,":[117],"fine-tuning":[119],"linear":[121],"probe":[122],"tasks,":[123,145],"achieves":[125],"accuracy":[126],"rates":[127],"99.17":[129],"98.31%,":[131],"respectively,":[132],"surpassing":[133],"current":[135],"state-of-the-art":[136],"BarcodeBERT":[137],"by":[138,196],"6.44":[139],"6.44%.":[141],"In":[142,160,184],"zero-shot":[143,162],"clustering":[144],"raises":[147],"adjusted":[149],"mutual":[150],"information":[151,202],"(AMI)":[152],"score":[153],"92.25%,":[155],"improvement":[157],"8.36%.":[159],"addition,":[161],"benchmarking":[163,166],"genomic":[165,182],"tests":[167],"evaluated,":[169],"indicating":[170],"enhances":[173],"performance":[175,190],"generalized":[181],"summary,":[185],"has":[187],"demonstrated":[188],"excellent":[189],"barcode":[193,205],"species":[194],"classification":[195],"making":[197],"full":[198],"use":[199],"multispecies":[201],"information,":[206],"providing":[207],"feasible":[209],"way":[210],"further":[212],"explore":[213],"protect":[215],"biodiversity.":[216],"code":[218],"repository":[219],"available":[221],"at":[222],"https://github.com/Kavicy/DNACSE.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2026-01-14T00:00:00"}