{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:42:14Z","timestamp":1784738534003,"version":"3.55.0"},"reference-count":35,"publisher":"Oxford University Press (OUP)","issue":"Supplement_1","license":[{"start":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T00:00:00Z","timestamp":1752537600000},"content-version":"vor","delay-in-days":14,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["R01LM1372201"],"award-info":[{"award-number":["R01LM1372201"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CAREER1841569"],"award-info":[{"award-number":["CAREER1841569"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["DOE DE-AC02-07CH11359"],"award-info":[{"award-number":["DOE DE-AC02-07CH11359"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["DOE LAB 20-2261"],"award-info":[{"award-number":["DOE LAB 20-2261"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["TRIPODS1740735"],"award-info":[{"award-number":["TRIPODS1740735"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Department of Energy Joint Genome Institute"},{"name":"DOE Office of Science User Facility"},{"DOI":"10.13039\/100006132","name":"Office of Science","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006132","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"Department of Energy","doi-asserted-by":"publisher","award":["DE-AC02-05CH11231"],"award-info":[{"award-number":["DE-AC02-05CH11231"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Summary<\/jats:title>\n                  <jats:p>We introduce DNABERT-S, a tailored genome model that develops species-aware embeddings to naturally cluster and segregate DNA sequences of different species in the embedding space. Differentiating species from genomic sequences (i.e. DNA and RNA) is vital yet challenging, since many real-world species remain uncharacterized, lacking known genomes for reference. Embedding-based methods are therefore used to differentiate species in an unsupervised manner. DNABERT-S builds upon a pre-trained genome foundation model named DNABERT-2. To encourage effective embeddings to error-prone long-read DNA sequences, we introduce Manifold Instance Mixup (MI-Mix), a contrastive objective that mixes the hidden representations of DNA sequences at randomly selected layers and trains the model to recognize and differentiate these mixed proportions at the output layer. We further enhance it with the proposed Curriculum Contrastive Learning (C2LR) strategy. Empirical results on 28 diverse datasets show DNABERT-S\u2019s effectiveness, especially in realistic label-scarce scenarios. For example, it identifies twice more species from a mixture of unlabeled genomic sequences, doubles the Adjusted Rand Index (ARI) in species clustering, and outperforms the top baseline\u2019s performance in 10-shot species classification with just a 2-shot training.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>Model, codes, and data are publically available at https:\/\/github.com\/MAGICS-LAB\/DNABERT_S.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf188","type":"journal-article","created":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T13:02:24Z","timestamp":1752584544000},"page":"i255-i264","source":"Crossref","is-referenced-by-count":33,"title":["DNABERT-S: pioneering species differentiation with species-aware DNA embeddings"],"prefix":"10.1093","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1473-9071","authenticated-orcid":false,"given":"Zhihan","family":"Zhou","sequence":"first","affiliation":[{"name":"Department of Computer Science, Northwestern University , Evanston, IL 60208,","place":["United States"]},{"name":"Center for Foundation Models and Generative AI, Northwestern University , Evanston, IL 60208,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5901-0219","authenticated-orcid":false,"given":"Weimin","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Northwestern University , Evanston, IL 60208,","place":["United States"]},{"name":"Center for Foundation Models and Generative AI, Northwestern University , Evanston, IL 60208,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8937-8266","authenticated-orcid":false,"given":"Harrison","family":"Ho","sequence":"additional","affiliation":[{"name":"School of Natural Science, University of California at Merced , Merced, CA 95343,","place":["United States"]},{"name":"Department of Energy Joint Genome Institute, Lawrence Berkeley National Laboratory , Berkeley, CA 94720,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Northwestern University , Evanston, IL 60208,","place":["United States"]},{"name":"Center for Foundation Models and Generative AI, Northwestern University , Evanston, IL 60208,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8776-4470","authenticated-orcid":false,"given":"Lizhen","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Statistics and Data Science, Northwestern University , Evanston, IL 60208,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7053-1064","authenticated-orcid":false,"given":"Ramana V","family":"Davuluri","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Stony Brook University , Stony Brook, NY 11794,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6307-0458","authenticated-orcid":false,"given":"Zhong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Natural Science, University of California at Merced , Merced, CA 95343,","place":["United States"]},{"name":"Department of Energy Joint Genome Institute, Lawrence Berkeley National Laboratory , Berkeley, CA 94720,","place":["United States"]},{"name":"Environmental Genomics and Systems Biology Division, Lawrence Berkeley National Laboratory , Berkeley, CA 94720,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8850-1237","authenticated-orcid":false,"given":"Han","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Northwestern University , Evanston, IL 60208,","place":["United States"]},{"name":"Center for Foundation Models and Generative AI, Northwestern University , Evanston, IL 60208,","place":["United States"]},{"name":"Department of Statistics and Data Science, Northwestern University , Evanston, IL 60208,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"key":"2025071509021961500_btaf188-B1","doi-asserted-by":"crossref","first-page":"D36","DOI":"10.1093\/nar\/gks1195","article-title":"Genbank","volume":"41","author":"Benson","year":"2013","journal-title":"Nucleic Acids Res"},{"key":"2025071509021961500_btaf188-B2","first-page":"1597","author":"Chen","year":"2020"},{"key":"2025071509021961500_btaf188-B3","first-page":"2300","author":"Chu","year":"2021"},{"key":"2025071509021961500_btaf188-B4","first-page":"287","author":"Dalla-Torre"},{"key":"2025071509021961500_btaf188-B5","article-title":"Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"2025071509021961500_btaf188-B6","first-page":"6894","article-title":"Simcse: simple contrastive learning of sentence embeddings","author":"Gao","year":"2021"},{"key":"2025071509021961500_btaf188-B7","first-page":"2535","author":"Hacohen","year":"2019"},{"key":"2025071509021961500_btaf188-B8","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1186\/s12864-022-08508-6","article-title":"Nucleosome positioning based on DNA sequence embedding and deep learning","volume":"23","author":"Han","year":"2022","journal-title":"BMC Genomics"},{"key":"2025071509021961500_btaf188-B9","doi-asserted-by":"crossref","first-page":"2112","DOI":"10.1093\/bioinformatics\/btab083","article-title":"Dnabert: pre-trained bidirectional encoder representations from transformers model for DNA-language in genome","volume":"37","author":"Ji","year":"2021","journal-title":"Bioinformatics"},{"key":"2025071509021961500_btaf188-B10","doi-asserted-by":"crossref","first-page":"e1165","DOI":"10.7717\/peerj.1165","article-title":"Metabat, an efficient tool for accurately reconstructing single genomes from complex microbial communities","volume":"3","author":"Kang","year":"2015","journal-title":"PeerJ"},{"key":"2025071509021961500_btaf188-B11","doi-asserted-by":"crossref","first-page":"e7359","DOI":"10.7717\/peerj.7359","article-title":"Metabat 2: an adaptive binning algorithm for robust and efficient genome reconstruction from metagenome assemblies","volume":"7","author":"Kang","year":"2019","journal-title":"PeerJ"},{"key":"2025071509021961500_btaf188-B12","author":"Khosla"},{"key":"2025071509021961500_btaf188-B13","author":"Diederik","year":"2014"},{"key":"2025071509021961500_btaf188-B14","author":"Diederik","year":"2013"},{"key":"2025071509021961500_btaf188-B15","first-page":"18471","author":"Lamurias","year":"2023"},{"key":"2025071509021961500_btaf188-B16","author":"Lee","year":"2020"},{"key":"2025071509021961500_btaf188-B17","author":"Li","year":"2020"},{"key":"2025071509021961500_btaf188-B18","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1038\/s41592-022-01431-4","article-title":"Critical assessment of metagenome interpretation: the second round of challenges","volume":"19","author":"Meyer","year":"2022","journal-title":"Nat Methods"},{"key":"2025071509021961500_btaf188-B19","author":"Mikolov","year":"2013"},{"key":"2025071509021961500_btaf188-B20","author":"Ng","year":"2017"},{"key":"2025071509021961500_btaf188-B21","author":"Nguyen","year":"2023"},{"key":"2025071509021961500_btaf188-B22","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1038\/s41587-020-00777-4","article-title":"Improved metagenome binning and assembly using deep variational autoencoders","volume":"39","author":"Nissen","year":"2021","journal-title":"Nat Biotechnol"},{"key":"2025071509021961500_btaf188-B23","doi-asserted-by":"crossref","first-page":"i21","DOI":"10.1093\/bioinformatics\/btad209","article-title":"Semibin2: self-supervised contrastive learning leads to better mags for short-and long-read sequencing","volume":"39","author":"Pan","year":"2023","journal-title":"Bioinformatics"},{"key":"2025071509021961500_btaf188-B24","author":"Peters","year":"2018"},{"key":"2025071509021961500_btaf188-B25","author":"Radford","year":"2019"},{"key":"2025071509021961500_btaf188-B26","author":"Reimers","year":"2019"},{"key":"2025071509021961500_btaf188-B27","doi-asserted-by":"crossref","first-page":"1001","DOI":"10.1089\/cmb.2021.0536","article-title":"kmer2vec: a novel method for comparing DNA sequences by word2vec embedding","volume":"29","author":"Ren","year":"2022","journal-title":"J Comput Biol"},{"key":"2025071509021961500_btaf188-B28","first-page":"1","author":"Roy","year":"2023"},{"key":"2025071509021961500_btaf188-B29","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.1038\/nbt.3988","article-title":"Mmseqs2 enables sensitive protein sequence searching for the analysis of massive data sets","volume":"35","author":"Steinegger","year":"2017","journal-title":"Nat Biotechnol"},{"key":"2025071509021961500_btaf188-B30","first-page":"6438","author":"Verma","year":"2019"},{"key":"2025071509021961500_btaf188-B31","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1038\/s41467-023-44290-z","article-title":"Effective binning of metagenomic contigs using contrastive multi-view representation learning","volume":"15","author":"Wang","year":"2024","journal-title":"Nat Commun"},{"key":"2025071509021961500_btaf188-B32","author":"Ye","year":"2021"},{"key":"2025071509021961500_btaf188-B33","author":"Zhang","year":"2021"},{"key":"2025071509021961500_btaf188-B34","author":"Zhou","year":"2022"},{"key":"2025071509021961500_btaf188-B35","author":"Zhou","year":"2023"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/Supplement_1\/i255\/63745376\/btaf188.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/Supplement_1\/i255\/63745376\/btaf188.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T13:02:26Z","timestamp":1752584546000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/41\/Supplement_1\/i255\/8199363"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,1]]},"references-count":35,"journal-issue":{"issue":"Supplement_1","published-print":{"date-parts":[[2025,7,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf188","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,7]]},"published":{"date-parts":[[2025,7,1]]}}}