{"id":"https://openalex.org/W4412454127","doi":"https://doi.org/10.1093/bioinformatics/btaf188","title":"DNABERT-S: pioneering species differentiation with species-aware DNA embeddings","display_name":"DNABERT-S: pioneering species differentiation with species-aware DNA embeddings","publication_year":2025,"publication_date":"2025-07-01","ids":{"openalex":"https://openalex.org/W4412454127","doi":"https://doi.org/10.1093/bioinformatics/btaf188","pmid":"https://pubmed.ncbi.nlm.nih.gov/40662791"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaf188","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf188","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/41/Supplement_1/i255/63745376/btaf188.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/41/Supplement_1/i255/63745376/btaf188.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101973691","display_name":"Zhihan Zhou","orcid":"https://orcid.org/0000-0002-1473-9071"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]},{"id":"https://openalex.org/I4210128101","display_name":"Northwestern Medical Faculty Foundation","ror":"https://ror.org/036ygzs59","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210128101"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhihan Zhou","raw_affiliation_strings":["Center for Foundation Models and Generative AI, Northwestern University , Evanston, IL 60208,","Department of Computer Science, Northwestern University , Evanston, IL 60208,"],"raw_orcid":"https://orcid.org/0000-0002-1473-9071","affiliations":[{"raw_affiliation_string":"Center for Foundation Models and Generative AI, Northwestern University , Evanston, IL 60208,","institution_ids":["https://openalex.org/I4210128101"]},{"raw_affiliation_string":"Department of Computer Science, Northwestern University , Evanston, IL 60208,","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111264305","display_name":"Weimin Wu","orcid":"https://orcid.org/0009-0004-5901-0219"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]},{"id":"https://openalex.org/I4210128101","display_name":"Northwestern Medical Faculty Foundation","ror":"https://ror.org/036ygzs59","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210128101"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weimin Wu","raw_affiliation_strings":["Center for Foundation Models and Generative AI, Northwestern University , Evanston, IL 60208,","Department of Computer Science, Northwestern University , Evanston, IL 60208,"],"raw_orcid":"https://orcid.org/0009-0004-5901-0219","affiliations":[{"raw_affiliation_string":"Center for Foundation Models and Generative AI, Northwestern University , Evanston, IL 60208,","institution_ids":["https://openalex.org/I4210128101"]},{"raw_affiliation_string":"Department of Computer Science, Northwestern University , Evanston, IL 60208,","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053939738","display_name":"Harrison Ho","orcid":"https://orcid.org/0000-0002-8937-8266"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]},{"id":"https://openalex.org/I196679689","display_name":"Joint Genome Institute","ror":"https://ror.org/04xm1d337","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I196679689","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harrison Ho","raw_affiliation_strings":["Department of Energy Joint Genome Institute, Lawrence Berkeley National Laboratory , Berkeley, CA 94720,","School of Natural Science, University of California at Merced , Merced, CA 95343,"],"raw_orcid":"https://orcid.org/0000-0002-8937-8266","affiliations":[{"raw_affiliation_string":"Department of Energy Joint Genome Institute, Lawrence Berkeley National Laboratory , Berkeley, CA 94720,","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I196679689"]},{"raw_affiliation_string":"School of Natural Science, University of California at Merced , Merced, CA 95343,","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118983749","display_name":"Jiayi Wang","orcid":"https://orcid.org/0009-0009-9174-1667"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]},{"id":"https://openalex.org/I4210128101","display_name":"Northwestern Medical Faculty Foundation","ror":"https://ror.org/036ygzs59","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210128101"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiayi Wang","raw_affiliation_strings":["Center for Foundation Models and Generative AI, Northwestern University , Evanston, IL 60208,","Department of Computer Science, Northwestern University , Evanston, IL 60208,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Foundation Models and Generative AI, Northwestern University , Evanston, IL 60208,","institution_ids":["https://openalex.org/I4210128101"]},{"raw_affiliation_string":"Department of Computer Science, Northwestern University , Evanston, IL 60208,","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051631233","display_name":"Lizhen Shi","orcid":"https://orcid.org/0000-0002-8776-4470"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lizhen Shi","raw_affiliation_strings":["Department of Statistics and Data Science, Northwestern University , Evanston, IL 60208,"],"raw_orcid":"https://orcid.org/0000-0002-8776-4470","affiliations":[{"raw_affiliation_string":"Department of Statistics and Data Science, Northwestern University , Evanston, IL 60208,","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017429478","display_name":"Ramana V. Davuluri","orcid":"https://orcid.org/0000-0002-7053-1064"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramana V Davuluri","raw_affiliation_strings":["Department of Biomedical Informatics, Stony Brook University , Stony Brook, NY 11794,"],"raw_orcid":"https://orcid.org/0000-0002-7053-1064","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Stony Brook University , Stony Brook, NY 11794,","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100781872","display_name":"Zhong Wang","orcid":"https://orcid.org/0000-0002-6307-0458"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]},{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]},{"id":"https://openalex.org/I196679689","display_name":"Joint Genome Institute","ror":"https://ror.org/04xm1d337","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I196679689","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong Wang","raw_affiliation_strings":["Department of Energy Joint Genome Institute, Lawrence Berkeley National Laboratory , Berkeley, CA 94720,","Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory , Berkeley, CA 94720,","School of Natural Science, University of California at Merced , Merced, CA 95343,"],"raw_orcid":"https://orcid.org/0000-0002-6307-0458","affiliations":[{"raw_affiliation_string":"Department of Energy Joint Genome Institute, Lawrence Berkeley National Laboratory , Berkeley, CA 94720,","institution_ids":["https://openalex.org/I148283060","https://openalex.org/I196679689"]},{"raw_affiliation_string":"Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory , Berkeley, CA 94720,","institution_ids":["https://openalex.org/I148283060"]},{"raw_affiliation_string":"School of Natural Science, University of California at Merced , Merced, CA 95343,","institution_ids":["https://openalex.org/I156087764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112180989","display_name":"Han Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]},{"id":"https://openalex.org/I4210128101","display_name":"Northwestern Medical Faculty Foundation","ror":"https://ror.org/036ygzs59","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210128101"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Liu","raw_affiliation_strings":["Center for Foundation Models and Generative AI, Northwestern University , Evanston, IL 60208,","Department of Computer Science, Northwestern University , Evanston, IL 60208,","Department of Statistics and Data Science, Northwestern University , Evanston, IL 60208,"],"raw_orcid":"https://orcid.org/0009-0000-8850-1237","affiliations":[{"raw_affiliation_string":"Center for Foundation Models and Generative AI, Northwestern University , Evanston, IL 60208,","institution_ids":["https://openalex.org/I4210128101"]},{"raw_affiliation_string":"Department of Computer Science, Northwestern University , Evanston, IL 60208,","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Department of Statistics and Data Science, Northwestern University , Evanston, IL 60208,","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":11.6782,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.99115288,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"41","issue":"Supplement_1","first_page":"i255","last_page":"i264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.6110000014305115,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.6110000014305115,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.051500000059604645,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.05000000074505806,"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/cluster-analysis","display_name":"Cluster analysis","score":0.6608096361160278},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5984836220741272},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5655991435050964},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5239301323890686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.433242529630661},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.41840192675590515},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3820822238922119},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.33527690172195435},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32897159457206726},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.16166824102401733},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.13765284419059753}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6608096361160278},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5984836220741272},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5655991435050964},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5239301323890686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.433242529630661},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.41840192675590515},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3820822238922119},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.33527690172195435},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32897159457206726},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.16166824102401733},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.13765284419059753}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D013045","descriptor_name":"Species Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013045","descriptor_name":"Species Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013045","descriptor_name":"Species Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013045","descriptor_name":"Species Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013045","descriptor_name":"Species Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013045","descriptor_name":"Species Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016678","descriptor_name":"Genome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1093/bioinformatics/btaf188","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf188","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/41/Supplement_1/i255/63745376/btaf188.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:40662791","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40662791","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:ark:/13030/qt9kf0s9g0","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:escholarship.org:ark:/13030/qt9kf0s9g0","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/9kf0s9g0","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics, vol 41, iss Supplement_1","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12261423","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12261423","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btaf188","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf188","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/41/Supplement_1/i255/63745376/btaf188.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[{"id":"https://openalex.org/G1286236842","display_name":null,"funder_award_id":"-AC02-05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1657422814","display_name":null,"funder_award_id":"DOE DE-AC02-07CH11359","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2413433374","display_name":null,"funder_award_id":"DE-AC02-07CH11359","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3083819904","display_name":null,"funder_award_id":"05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3944918260","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G4501827968","display_name":null,"funder_award_id":"AC02-05CH11231","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G4565140552","display_name":null,"funder_award_id":"-AC02-05CH11231","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G4813509527","display_name":null,"funder_award_id":"R01LM1372201","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G498139845","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G5507281304","display_name":null,"funder_award_id":"TRIPODS1740735","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5602503670","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320316170","funder_display_name":"Joint Genome Institute"},{"id":"https://openalex.org/G5616713406","display_name":null,"funder_award_id":"DE-AC02-07CH11359","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5687374729","display_name":null,"funder_award_id":"R01 LM013722","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G578688135","display_name":null,"funder_award_id":"CAREER1841569","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G585908603","display_name":null,"funder_award_id":"AC02-07CH11359","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G5962495253","display_name":null,"funder_award_id":"DE-AC02-07CH11359","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G6348972864","display_name":null,"funder_award_id":"AC02-05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6558272803","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7205239661","display_name":null,"funder_award_id":"AC02-05CH11231","funder_id":"https://openalex.org/F4320316170","funder_display_name":"Joint Genome Institute"},{"id":"https://openalex.org/G7233692708","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7538560101","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G89573576","display_name":null,"funder_award_id":"DOE LAB 20-2261","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G969889393","display_name":null,"funder_award_id":"DE-AC02-","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320316170","display_name":"Joint Genome Institute","ror":"https://ror.org/04xm1d337"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412454127.pdf","grobid_xml":"https://content.openalex.org/works/W4412454127.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1584790813","https://openalex.org/W2938868597","https://openalex.org/W2950954328","https://openalex.org/W3120084484","https://openalex.org/W3127238141","https://openalex.org/W3156636935","https://openalex.org/W4223454372","https://openalex.org/W4225258284","https://openalex.org/W4242729757","https://openalex.org/W4281253663","https://openalex.org/W4382631636","https://openalex.org/W4390935732","https://openalex.org/W6794687422"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2037549926","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W2132641928","https://openalex.org/W4310225030"],"abstract_inverted_index":{"SUMMARY:":[0],"We":[1,117],"introduce":[2,82],"DNABERT-S,":[3],"a":[4,65,87,151,178],"tailored":[5],"genome":[6,67],"model":[7,69,105],"that":[8,90],"develops":[9],"species-aware":[10],"embeddings":[11,75],"to":[12,55,76,106],"naturally":[13],"cluster":[14],"and":[15,33,102,108,166,186],"segregate":[16],"DNA":[17,32,79,96],"sequences":[18,30,97],"of":[19,95,153],"different":[20],"species":[21,27,42,57,149,164,174],"in":[22,58,139,163,172],"the":[23,92,104,114,122,158,168],"embedding":[24],"space.":[25],"Differentiating":[26],"from":[28,150],"genomic":[29,155],"(i.e.":[31],"RNA)":[34],"is":[35],"vital":[36],"yet":[37],"challenging,":[38],"since":[39],"many":[40],"real-world":[41],"remain":[43],"uncharacterized,":[44],"lacking":[45],"known":[46],"genomes":[47],"for":[48],"reference.":[49],"Embedding-based":[50],"methods":[51],"are":[52,188],"therefore":[53],"used":[54],"differentiate":[56,109],"an":[59],"unsupervised":[60],"manner.":[61],"DNABERT-S":[62],"builds":[63],"upon":[64],"pre-trained":[66],"foundation":[68],"named":[70],"DNABERT-2.":[71],"To":[72],"encourage":[73],"effective":[74],"error-prone":[77],"long-read":[78],"sequences,":[80,156],"we":[81],"Manifold":[83],"Instance":[84],"Mixup":[85],"(MI-Mix),":[86],"contrastive":[88],"objective":[89],"mixes":[91],"hidden":[93],"representations":[94],"at":[98,113,191],"randomly":[99],"selected":[100],"layers":[101],"trains":[103],"recognize":[107],"these":[110],"mixed":[111],"proportions":[112],"output":[115],"layer.":[116],"further":[118],"enhance":[119],"it":[120,145],"with":[121,176],"proposed":[123],"Curriculum":[124],"Contrastive":[125],"Learning":[126],"(C2LR)":[127],"strategy.":[128],"Empirical":[129],"results":[130],"on":[131],"28":[132],"diverse":[133],"datasets":[134],"show":[135],"DNABERT-S's":[136],"effectiveness,":[137],"especially":[138],"realistic":[140],"label-scarce":[141],"scenarios.":[142],"For":[143],"example,":[144],"identifies":[146],"twice":[147],"more":[148],"mixture":[152],"unlabeled":[154],"doubles":[157],"Adjusted":[159],"Rand":[160],"Index":[161],"(ARI)":[162],"clustering,":[165],"outperforms":[167],"top":[169],"baseline's":[170],"performance":[171],"10-shot":[173],"classification":[175],"just":[177],"2-shot":[179],"training.":[180],"AVAILABILITY":[181],"AND":[182],"IMPLEMENTATION:":[183],"Model,":[184],"codes,":[185],"data":[187],"publically":[189],"available":[190],"https://github.com/MAGICS-LAB/DNABERT_S.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":21},{"year":2025,"cited_by_count":7}],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2025-10-10T00:00:00"}
