{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T02:28:41Z","timestamp":1783477721759,"version":"3.55.0"},"reference-count":54,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T00:00:00Z","timestamp":1722902400000},"content-version":"vor","delay-in-days":5,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225209"],"award-info":[{"award-number":["62225209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,8,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Transcription factors are pivotal in the regulation of gene expression, and accurate identification of transcription factor binding sites (TFBSs) at high resolution is crucial for understanding the mechanisms underlying gene regulation. The task of identifying TFBSs from DNA sequences is a significant challenge in the field of computational biology today. To address this challenge, a variety of computational approaches have been developed. However, these methods face limitations in their ability to achieve high-resolution identification and often lack interpretability.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We propose BertSNR, an interpretable deep learning framework for identifying TFBSs at single-nucleotide resolution. BertSNR integrates sequence-level and token-level information by multi-task learning based on pre-trained DNA language models. Benchmarking comparisons show that our BertSNR outperforms the existing state-of-the-art methods in TFBS predictions. Importantly, we enhanced the interpretability of the model through attentional weight visualization and motif analysis, and discovered the subtle relationship between attention weight and motif. Moreover, BertSNR effectively identifies TFBSs in promoter regions, facilitating the study of intricate gene regulation.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The BertSNR source code can be found at https:\/\/github.com\/lhy0322\/BertSNR.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae461","type":"journal-article","created":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T03:49:07Z","timestamp":1723002547000},"source":"Crossref","is-referenced-by-count":3,"title":["BertSNR: an interpretable deep learning framework for single-nucleotide resolution identification of transcription factor binding sites based on DNA language model"],"prefix":"10.1093","volume":"40","author":[{"given":"Hanyu","family":"Luo","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Central South University , Changsha, Hunan 410083, China"},{"name":"School of Computer Science, University of South China , Hengyang, Hunan 421001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University , Changsha, Hunan 410083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1726-0955","authenticated-orcid":false,"given":"Min","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University , Changsha, Hunan 410083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Yin","sequence":"additional","affiliation":[{"name":"Department of Health Outcome and Biomedical Informatics, University of Florida , Gainesville, FL 32611, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2613-2496","authenticated-orcid":false,"given":"Pingjian","family":"Ding","sequence":"additional","affiliation":[{"name":"Center for Artificial Intelligence in Drug Discovery, School of Medicine, Case Western Reserve University , Cleveland, OH 44106, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingyun","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of South China , Hengyang, Hunan 421001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0188-1394","authenticated-orcid":false,"given":"Min","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University , Changsha, Hunan 410083, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,8,6]]},"reference":[{"key":"2024080905565413900_btae461-B1","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1038\/nbt.3300","article-title":"Predicting the sequence specificities of DNA-and RNA-binding proteins by deep learning","volume":"33","author":"Alipanahi","year":"2015","journal-title":"Nat Biotechnol"},{"key":"2024080905565413900_btae461-B2","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1038\/s41576-019-0173-8","article-title":"Determinants of enhancer and promoter activities of regulatory elements","volume":"21","author":"Andersson","year":"2020","journal-title":"Nat Rev Genet"},{"key":"2024080905565413900_btae461-B3","doi-asserted-by":"crossref","first-page":"1196","DOI":"10.1038\/s41592-021-01252-x","article-title":"Effective gene expression prediction from sequence by integrating long-range interactions","volume":"18","author":"Avsec","year":"2021","journal-title":"Nat Methods"},{"key":"2024080905565413900_btae461-B4","doi-asserted-by":"crossref","first-page":"W202","DOI":"10.1093\/nar\/gkp335","article-title":"MEME SUITE: tools for motif discovery and searching","volume":"37","author":"Bailey","year":"2009","journal-title":"Nucleic Acids Res"},{"key":"2024080905565413900_btae461-B5","doi-asserted-by":"crossref","first-page":"W369","DOI":"10.1093\/nar\/gkl198","article-title":"MEME: discovering and analyzing DNA and protein sequence motifs","volume":"34","author":"Bailey","year":"2006","journal-title":"Nucleic Acids Res"},{"key":"2024080905565413900_btae461-B6","author":"Bao"},{"key":"2024080905565413900_btae461-B7","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2024080905565413900_btae461-B8","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1186\/gb-2003-5-1-201","article-title":"Computational prediction of transcription-factor binding site locations","volume":"5","author":"Bulyk","year":"2003","journal-title":"Genome Biol"},{"key":"2024080905565413900_btae461-B9","doi-asserted-by":"crossref","first-page":"D165","DOI":"10.1093\/nar\/gkab1113","article-title":"JASPAR 2022: the 9th release of the open-access database of transcription factor binding profiles","volume":"50","author":"Castro-Mondragon","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2024080905565413900_btae461-B10","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.pharmthera.2015.10.004","article-title":"Targeting transcription factor STAT3 for cancer prevention and therapy","volume":"162","author":"Chai","year":"2016","journal-title":"Pharmacol Ther"},{"key":"2024080905565413900_btae461-B11","first-page":"1","author":"Chang"},{"key":"2024080905565413900_btae461-B12","doi-asserted-by":"crossref","first-page":"6031","DOI":"10.1128\/MCB.25.14.6031-6046.2005","article-title":"Reciprocal transcriptional regulation of Pou5f1 and Sox2 via the Oct4\/Sox2 complex in embryonic stem cells","volume":"25","author":"Chew","year":"2005","journal-title":"Mol Cell Biol"},{"key":"2024080905565413900_btae461-B13","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1124\/pr.117.014753","article-title":"Transcription factor NRF2 as a therapeutic target for chronic diseases: a systems medicine approach","volume":"70","author":"Cuadrado","year":"2018","journal-title":"Pharmacol Rev"},{"key":"2024080905565413900_btae461-B14","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1038\/nature15515","article-title":"Hallmarks of pluripotency","volume":"525","author":"De Los Angeles","year":"2015","journal-title":"Nature"},{"key":"2024080905565413900_btae461-B15","author":"Devlin","year":"2018"},{"key":"2024080905565413900_btae461-B16","doi-asserted-by":"crossref","first-page":"D51","DOI":"10.1093\/nar\/gkw1069","article-title":"The eukaryotic promoter database in its 30th year: focus on non-vertebrate organisms","volume":"45","author":"Dreos","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2024080905565413900_btae461-B17","doi-asserted-by":"crossref","first-page":"791","DOI":"10.1186\/s12885-019-6014-5","article-title":"Oct4 upregulates osteopontin via Egr1 and is associated with poor outcome in human lung cancer","volume":"19","author":"Feng","year":"2019","journal-title":"BMC Cancer"},{"key":"2024080905565413900_btae461-B18","doi-asserted-by":"crossref","first-page":"840","DOI":"10.1038\/nrg3306","article-title":"ChIP\u2013seq and beyond: new and improved methodologies to detect and characterize protein\u2013DNA interactions","volume":"13","author":"Furey","year":"2012","journal-title":"Nat Rev Genet"},{"key":"2024080905565413900_btae461-B19","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1038\/nrm.2017.73","article-title":"Regulation of heat shock transcription factors and their roles in physiology and disease","volume":"19","author":"Gomez-Pastor","year":"2018","journal-title":"Nat Rev Mol Cell Biol"},{"key":"2024080905565413900_btae461-B20","doi-asserted-by":"crossref","first-page":"bbaa229","DOI":"10.1093\/bib\/bbaa229","article-title":"A survey on deep learning in DNA\/RNA motif mining","volume":"22","author":"He","year":"2021","journal-title":"Brief Bioinform"},{"key":"2024080905565413900_btae461-B21","doi-asserted-by":"crossref","first-page":"1037","DOI":"10.1093\/bioinformatics\/btz694","article-title":"Identifying enhancer\u2013promoter interactions with neural network based on pre-trained DNA vectors and attention mechanism","volume":"36","author":"Hong","year":"2020","journal-title":"Bioinformatics"},{"key":"2024080905565413900_btae461-B22","doi-asserted-by":"crossref","first-page":"2154","DOI":"10.1093\/nar\/gkp1180","article-title":"On the detection and refinement of transcription factor binding sites using ChIP-Seq data","volume":"38","author":"Hu","year":"2010","journal-title":"Nucleic Acids Res"},{"key":"2024080905565413900_btae461-B23","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":"2024080905565413900_btae461-B24","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1186\/1471-2105-9-192","article-title":"uShuffle: a useful tool for shuffling biological sequences while preserving the k-let counts","volume":"9","author":"Jiang","year":"2008","journal-title":"BMC Bioinformatics"},{"key":"2024080905565413900_btae461-B25","doi-asserted-by":"crossref","first-page":"3576","DOI":"10.1093\/nar\/gkg585","article-title":"MATCHTM: a tool for searching transcription factor binding sites in DNA sequences","volume":"31","author":"Kel","year":"2003","journal-title":"Nucleic Acids Res"},{"key":"2024080905565413900_btae461-B26","doi-asserted-by":"crossref","first-page":"650","DOI":"10.1016\/j.cell.2018.01.029","article-title":"The human transcription factors","volume":"172","author":"Lambert","year":"2018","journal-title":"Cell"},{"key":"2024080905565413900_btae461-B27","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1109\/TKDE.2020.2981314","article-title":"A survey on deep learning for named entity recognition","volume":"34","author":"Li","year":"2020","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"2024080905565413900_btae461-B28","doi-asserted-by":"crossref","first-page":"164348","DOI":"10.1007\/s11704-021-0548-9","article-title":"Identification and classification of promoters using the attention mechanism based on long short-term memory","volume":"16","author":"Li","year":"2022","journal-title":"Front Comput Sci"},{"key":"2024080905565413900_btae461-B29","first-page":"32","article-title":"Improving language model of human genome for DNA\u2013protein binding prediction based on task-specific pre-training","volume":"15","author":"Luo","year":"2023","journal-title":"Interdiscip Sci"},{"key":"2024080905565413900_btae461-B30","doi-asserted-by":"crossref","first-page":"D1188","DOI":"10.1093\/nar\/gkac1072","article-title":"The UCSC genome browser database: 2023 update","volume":"51","author":"Nassar","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2024080905565413900_btae461-B31","author":"Ng","year":"2017"},{"key":"2024080905565413900_btae461-B32","doi-asserted-by":"crossref","first-page":"984","DOI":"10.1016\/j.bbrc.2014.06.079","article-title":"Transcriptional regulation of OCT4 by the ETS transcription factor ESE-1 in NCCIT human embryonic carcinoma cells","volume":"450","author":"Park","year":"2014","journal-title":"Biochem Biophys Res Commun"},{"key":"2024080905565413900_btae461-B33","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1016\/j.bbagrm.2016.11.002","article-title":"G-quadruplex formation in the Oct4 promoter positively regulates Oct4 expression","volume":"1860","author":"Ren\u010diuk","year":"2017","journal-title":"Biochim Biophys Acta Gene Regul Mech"},{"key":"2024080905565413900_btae461-B34","author":"Ruder","year":"2017"},{"key":"2024080905565413900_btae461-B35","doi-asserted-by":"crossref","first-page":"3446","DOI":"10.1093\/bioinformatics\/bty383","article-title":"Base-pair resolution detection of transcription factor binding site by deep deconvolutional network","volume":"34","author":"Salekin","year":"2018","journal-title":"Bioinformatics"},{"key":"2024080905565413900_btae461-B36","doi-asserted-by":"crossref","first-page":"6097","DOI":"10.1093\/nar\/18.20.6097","article-title":"Sequence logos: a new way to display consensus sequences","volume":"18","author":"Schneider","year":"1990","journal-title":"Nucleic Acids Res"},{"key":"2024080905565413900_btae461-B37","doi-asserted-by":"crossref","first-page":"bbab101","DOI":"10.1093\/bib\/bbab101","article-title":"SAResNet: self-attention residual network for predicting DNA-protein binding","volume":"22","author":"Shen","year":"2021","journal-title":"Brief Bioinform"},{"key":"2024080905565413900_btae461-B38","doi-asserted-by":"crossref","first-page":"11","DOI":"10.26599\/BDMA.2022.9020030","article-title":"A method for bio-sequence analysis algorithm development based on the PAR platform","volume":"6","author":"Shi","year":"2023","journal-title":"Big Data Min Anal"},{"key":"2024080905565413900_btae461-B39","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1038\/nrg3682","article-title":"Transcriptional enhancers: from properties to genome-wide predictions","volume":"15","author":"Shlyueva","year":"2014","journal-title":"Nat Rev Genet"},{"key":"2024080905565413900_btae461-B40","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1038\/cr.2015.6","article-title":"GATA family members as inducers for cellular reprogramming to pluripotency","volume":"25","author":"Shu","year":"2015","journal-title":"Cell Res"},{"key":"2024080905565413900_btae461-B41","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1093\/bioinformatics\/16.1.16","article-title":"DNA binding sites: representation and discovery","volume":"16","author":"Stormo","year":"2000","journal-title":"Bioinformatics"},{"key":"2024080905565413900_btae461-B42","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1101\/gad.311605.118","article-title":"Enhancer transcription: what, where, when, and why?","volume":"32","author":"Tippens","year":"2018","journal-title":"Genes Dev"},{"key":"2024080905565413900_btae461-B43","doi-asserted-by":"crossref","first-page":"71","DOI":"10.31887\/DCNS.2017.19.1\/rpal","article-title":"The potential role of neuroinflammation and transcription factors in Parkinson disease","author":"Tiwari","year":"2017","journal-title":"Dialogues Clin Neurosci"},{"key":"2024080905565413900_btae461-B44","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2024080905565413900_btae461-B45","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1038\/nrg1315","article-title":"Applied bioinformatics for the identification of regulatory elements","volume":"5","author":"Wasserman","year":"2004","journal-title":"Nat Rev Genet"},{"key":"2024080905565413900_btae461-B46","doi-asserted-by":"crossref","first-page":"1431","DOI":"10.1016\/j.cell.2014.08.009","article-title":"Determination and inference of eukaryotic transcription factor sequence specificity","volume":"158","author":"Weirauch","year":"2014","journal-title":"Cell"},{"key":"2024080905565413900_btae461-B47","doi-asserted-by":"crossref","first-page":"176349","DOI":"10.1007\/s11704-023-2689-5","article-title":"Large sequence models for sequential decision-making: a survey","volume":"17","author":"Wen","year":"2023","journal-title":"Front Comput Sci"},{"key":"2024080905565413900_btae461-B48","doi-asserted-by":"crossref","first-page":"881","DOI":"10.1242\/dev.122.3.881","article-title":"Germline regulatory element of oct-4 specific for the totipotent cycle of embryonal cells","volume":"122","author":"Yeom","year":"1996","journal-title":"Development"},{"key":"2024080905565413900_btae461-B49","doi-asserted-by":"crossref","first-page":"D61","DOI":"10.1093\/nar\/gkw951","article-title":"GTRD: a database of transcription factor binding sites identified by ChIP-seq experiments","volume":"45","author":"Yevshin","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2024080905565413900_btae461-B50","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1186\/s13045-015-0119-3","article-title":"Coexpression of gene Oct4 and Nanog initiates stem cell characteristics in hepatocellular carcinoma and promotes epithelial-mesenchymal transition through activation of Stat3\/Snail signaling","volume":"8","author":"Yin","year":"2015","journal-title":"J Hematol Oncol"},{"key":"2024080905565413900_btae461-B51","doi-asserted-by":"crossref","first-page":"vbad001","DOI":"10.1093\/bioadv\/vbad001","article-title":"Applications of transformer-based language models in bioinformatics: a survey","volume":"3","author":"Zhang","year":"2023","journal-title":"Bioinform Adv"},{"key":"2024080905565413900_btae461-B52","doi-asserted-by":"crossref","first-page":"bbab525","DOI":"10.1093\/bib\/bbab525","article-title":"A novel convolution attention model for predicting transcription factor binding sites by combination of sequence and shape","volume":"23","author":"Zhang","year":"2022","journal-title":"Brief Bioinform"},{"key":"2024080905565413900_btae461-B53","doi-asserted-by":"crossref","first-page":"bbab273","DOI":"10.1093\/bib\/bbab273","article-title":"High-resolution transcription factor binding sites prediction improved performance and interpretability by deep learning method","volume":"22","author":"Zhang","year":"2021","journal-title":"Brief Bioinform"},{"key":"2024080905565413900_btae461-B54","doi-asserted-by":"crossref","first-page":"5067","DOI":"10.1093\/bioinformatics\/btz451","article-title":"MTTFsite: cross-cell type TF binding site prediction by using multi-task learning","volume":"35","author":"Zhou","year":"2019","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae461\/58749469\/btae461.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/8\/btae461\/58779100\/btae461.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/8\/btae461\/58779100\/btae461.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,9]],"date-time":"2024-08-09T06:04:48Z","timestamp":1723183488000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae461\/7728457"}},"subtitle":[],"editor":[{"given":"Macha","family":"Nikolski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":54,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,8,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae461","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,8]]},"published":{"date-parts":[[2024,8]]},"article-number":"btae461"}}