{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T23:29:49Z","timestamp":1787009389106,"version":"build-2736575974"},"reference-count":56,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T00:00:00Z","timestamp":1780531200000},"content-version":"vor","delay-in-days":69,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000092","name":"National Library of Medicine","doi-asserted-by":"publisher","award":["R01LM013722"],"award-info":[{"award-number":["R01LM013722"]}],"id":[{"id":"10.13039\/100000092","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,27]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Characterizing tissue-specific (TSp) gene expression is crucial for understanding development and disease; however, traditional expression-based methods often overlook the latent \u201cregulatory grammar\u201d embedded in non-coding DNA, particularly across distal promoter regions. Here, we introduce TSProm, a framework that adapts a DNA foundation model (DNABERT2) to decode the regulatory logic of TSp promoters at the isoform level. Our contributions are two-fold: (i) a comparative design that trains two specialized models: Model A for general promoter biology and Model B for tissue-specific regulation enabling precise isolation of sequence motifs surrounding the transcription start site that uniquely define tissue identity; (ii) we develop an explainable AI module that integrates attention-based motif discovery with model-agnostic SHAP analysis to yield cross-validated interpretations of learned features. Applying TSProm to human brain, liver, and testis promoters, we identified clinically relevant transcription factors (TFs) in the brain, including SP1, MYC, and HES6, whose associations with gliomas and neuroblastomas highlight clinical relevance. Moreover, our results highlight C2H2 zinc finger proteins as a dominant family shaping the global landscape of TSp gene regulation. TSProm provides an interpretable and generalizable framework for identifying tissue-specific regulatory elements, offering powerful computational tools to investigate gene regulation in both normal and disease contexts.<\/jats:p>","DOI":"10.1093\/nargab\/lqag050","type":"journal-article","created":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T11:33:45Z","timestamp":1780400025000},"source":"Crossref","is-referenced-by-count":1,"title":["TSProm: deep learning framework to predict tissue-specific regulatory logic"],"prefix":"10.1093","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4241-9181","authenticated-orcid":false,"given":"Pallavi","family":"Surana","sequence":"first","affiliation":[{"name":"Department of Biomedical Informatics, Stony Brook University, NY 11794 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pratik","family":"Dutta","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Stony Brook University, NY 11794 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nimisha","family":"Papineni","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Stony Brook University, NY 11794 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rekha","family":"Sathian","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Stony Brook University, NY 11794 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Northwestern University, IL 60208 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Northwestern University, 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, NY 11794 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,6,3]]},"reference":[{"key":"2026060321504662700_B1","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.tig.2008.01.008","article-title":"The functional consequences of alternative promoter use in mammalian genomes","volume":"24","author":"Davuluri","year":"2008","journal-title":"Trends Genet"},{"key":"2026060321504662700_B2","doi-asserted-by":"publisher","first-page":"1077","DOI":"10.1016\/j.celrep.2017.10.001","article-title":"Understanding tissue-specific gene regulation","volume":"21","author":"Sonawane","year":"2017","journal-title":"Cell Rep"},{"key":"2026060321504662700_B3","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1038\/s41586-019-1411-0","article-title":"Advances in epigenetics link genetics to the environment and disease","volume":"571","author":"Cavalli","year":"2019","journal-title":"Nature"},{"key":"2026060321504662700_B4","doi-asserted-by":"publisher","first-page":"btae475","DOI":"10.1093\/bioinformatics\/btae475","article-title":"TransTEx: novel tissue-specificity scoring method for grouping human transcriptome into different expression groups","volume":"40","author":"Surana","year":"2024","journal-title":"Bioinformatics"},{"key":"2026060321504662700_B5","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1038\/ng1789","article-title":"Genome-wide analysis of mammalian promoter architecture and evolution","volume":"38","author":"Carninci","year":"2006","journal-title":"Nat Genet"},{"key":"2026060321504662700_B6","doi-asserted-by":"publisher","first-page":"1150","DOI":"10.1126\/science.aaw3472","article-title":"Tissue-specificity in cancer: the rule, not the exception","volume":"363","author":"Haigis","year":"2019","journal-title":"Science"},{"key":"2026060321504662700_B7","doi-asserted-by":"publisher","first-page":"e1009085","DOI":"10.1371\/journal.pcbi.1009085","article-title":"Analyzing cancer gene expression data through the lens of normal tissue-specificity","volume":"17","author":"Frost","year":"2021","journal-title":"PLoS Comput Biol"},{"key":"2026060321504662700_B8","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1038\/msb4100114","article-title":"Tissue-specific regulatory elements in mammalian promoters","volume":"3","author":"Smith","year":"2007","journal-title":"Mol Syst Biol"},{"key":"2026060321504662700_B9","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1038\/s42256-025-01007-9","article-title":"Transformers and genome language models","volume":"7","author":"Consens","year":"2025","journal-title":"Nat Mach Intell"},{"key":"2026060321504662700_B10","doi-asserted-by":"publisher","first-page":"nwaf028","DOI":"10.1093\/nsr\/nwaf028","article-title":"Foundation models in bioinformatics","volume":"12","author":"Guo","year":"2025","journal-title":"Natl Sci Rev"},{"key":"2026060321504662700_B11","doi-asserted-by":"publisher","first-page":"41642","DOI":"10.48550\/arXiv.2306.15006","article-title":"DNABERT-2: Efficient foundation model and benchmark for multi-species genomes","author":"Zhou","year":"2024","journal-title":"ICLR"},{"key":"2026060321504662700_B12","doi-asserted-by":"publisher","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":"2026060321504662700_B13","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1038\/s41592-024-02523-z","article-title":"Nucleotide transformer: building and evaluating robust foundation models for human genomics","volume":"22","author":"Dalla-Torre","year":"2025","journal-title":"Nat Methods"},{"key":"2026060321504662700_B14","doi-asserted-by":"publisher","first-page":"gkae1310","DOI":"10.1093\/nar\/gkae1310","article-title":"GENA-LM: a family of open-source foundational DNA language models for long sequences","volume":"53","author":"Fishman","year":"2025","journal-title":"Nucleic Acids Res"},{"key":"2026060321504662700_B15","first-page":"43177","article-title":"Hyenadna: long-range genomic sequence modeling at single nucleotide resolution","volume":"36","author":"Nguyen","year":"2023","journal-title":"Advances in neural information processing systems"},{"key":"2026060321504662700_B16","doi-asserted-by":"publisher","first-page":"10278","DOI":"10.1093\/nar\/gkac824","article-title":"iPro-WAEL: a comprehensive and robust framework for identifying promoters in multiple species","volume":"50","author":"Zhang","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2026060321504662700_B17","doi-asserted-by":"publisher","first-page":"4200","DOI":"10.1038\/s41598-017-04520-z","article-title":"A comprehensive mouse transcriptomic BodyMap across 17 tissues by RNA-seq","volume":"7","author":"Li","year":"2017","journal-title":"Sci Rep"},{"key":"2026060321504662700_B18","first-page":"4768","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv Neural Inform Process Syst"},{"key":"2026060321504662700_B19","doi-asserted-by":"publisher","first-page":"D174","DOI":"10.1093\/nar\/gkad1059","article-title":"JASPAR 2024: 20th anniversary of the open-access database of transcription factor binding profiles","volume":"52","author":"Rauluseviciute","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2026060321504662700_B20","first-page":"D402","article-title":"TF-Marker: a comprehensive manually curated database for transcription factors and related markers in specific cell and tissue types in human","volume":"50","author":"Xu","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2026060321504662700_B21","doi-asserted-by":"publisher","first-page":"D183","DOI":"10.1093\/nar\/gkad1016","article-title":"KnockTF 2.0: a comprehensive gene expression profile database with knockdown\/knockout of transcription (co-) factors in multiple species","volume":"52","author":"Feng","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2026060321504662700_B22","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1038\/nature11247","article-title":"An integrated encyclopedia of DNA elements in the human genome","volume":"489","author":"Consortium","year":"2012","journal-title":"Nature"},{"key":"2026060321504662700_B23","doi-asserted-by":"publisher","first-page":"107732","DOI":"10.1016\/j.compbiolchem.2022.107732","article-title":"BERT-Promoter: an improved sequence-based predictor of DNA promoter using BERT pre-trained model and SHAP feature selection","volume":"99","author":"Le","year":"2022","journal-title":"Comput Biol Chem"},{"key":"2026060321504662700_B24","doi-asserted-by":"publisher","first-page":"4559","DOI":"10.1109\/JBHI.2023.3292299","article-title":"IChrom-deep: an attention-based deep learning model for identifying chromatin interactions","volume":"27","author":"Zhang","year":"2023","journal-title":"IEEE J Biomed Health Inf"},{"key":"2026060321504662700_B25","article-title":"Genebench: Systematic Evaluation of Genomic Foundation Models and Beyond","volume-title":"NeurIPS","author":"Liu","year":"2024"},{"key":"2026060321504662700_B26","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.1101\/gr.1953904","article-title":"Clustering of DNA sequences in human promoters","volume":"14","author":"FitzGerald","year":"2004","journal-title":"Genome Res"},{"key":"2026060321504662700_B27","doi-asserted-by":"publisher","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":"2026060321504662700_B28","doi-asserted-by":"publisher","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":"2026060321504662700_B29","doi-asserted-by":"publisher","first-page":"e0237412","DOI":"10.1371\/journal.pone.0237412","article-title":"The impact of different negative training data on regulatory sequence predictions","volume":"15","author":"Kr\u00fctzfeldt","year":"2020","journal-title":"PLoS One"},{"key":"2026060321504662700_B30","doi-asserted-by":"crossref","DOI":"10.1007\/3-540-44696-6_22","article-title":"A simple hyper-geometric approach for discovering putative transcription factor binding sites","volume-title":"International Workshop on Algorithms in Bioinformatics","author":"Barash","year":"2001"},{"key":"2026060321504662700_B31","doi-asserted-by":"publisher","DOI":"10.1109\/SASP.2010.5521145","article-title":"Accelerating DNA analysis applications on GPU clusters","volume-title":"2010 IEEE 8th Symposium on Application Specific Processors (SASP)","author":"Tumeo","year":"2010"},{"key":"2026060321504662700_B32","doi-asserted-by":"publisher","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":"2026060321504662700_B33","article-title":"SHAP-based explanation methods: a review for NLP interpretability","volume-title":"Proceedings of the 29th international conference on computational linguistics","author":"Mosca","year":"2022"},{"key":"2026060321504662700_B34","article-title":"BERT meets shapley: extending SHAP explanations to transformer-based classifiers","volume-title":"Proceedings of the EACL hackashop on news media content analysis and automated report generation","author":"Kokalj","year":"2021"},{"key":"2026060321504662700_B35","doi-asserted-by":"publisher","article-title":"XSTREME: comprehensive motif analysis of biological sequence datasets","author":"Grant","DOI":"10.1101\/2021.09.02.458722"},{"key":"2026060321504662700_B36","doi-asserted-by":"publisher","first-page":"1813","DOI":"10.1101\/gr.136184.111","article-title":"ChIP-seq guidelines and practices of the ENCODE and modENCODE consortia","volume":"22","author":"Landt","year":"2012","journal-title":"Genome Res"},{"key":"2026060321504662700_B37","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbae083","article-title":"Enhancer-MDLF: a novel deep learning framework for identifying cell-specific enhancers","volume":"25","author":"Zhang","year":"2024","journal-title":"Brief Bioinf"},{"key":"2026060321504662700_B38","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbaf289","article-title":"A novel deep learning framework with dynamic tokenization for identifying chromatin interactions along with motif importance investigation","volume":"26","author":"Li","year":"2025","journal-title":"Brief Bioinf"},{"key":"2026060321504662700_B39","doi-asserted-by":"publisher","first-page":"252","DOI":"10.3390\/genes15020252","article-title":"Economy of effort or sophisticated programming? The prevalence of bidirectional promoter complexes in the human genome","volume":"15","author":"Anderson","year":"2024","journal-title":"Genes"},{"key":"2026060321504662700_B40","doi-asserted-by":"publisher","first-page":"13457","DOI":"10.1073\/pnas.1919507117","article-title":"MYC protein stability is negatively regulated by BRD4","volume":"117","author":"Devaiah","year":"2020","journal-title":"Proc Natl Acad Sci"},{"key":"2026060321504662700_B41","doi-asserted-by":"publisher","first-page":"11181","DOI":"10.1038\/s41598-022-14751-4","article-title":"Sp1 induced gene TIMP1 is related to immune cell infiltration in glioblastoma","volume":"12","author":"Liu","year":"2022","journal-title":"Sci Rep"},{"key":"2026060321504662700_B42","doi-asserted-by":"publisher","first-page":"13936","DOI":"10.3390\/ijms232213936","article-title":"The bHLH transcription factors in neural development and therapeutic applications for neurodegenerative diseases","volume":"23","author":"Lee","year":"2022","journal-title":"Int J Mol Sci"},{"key":"2026060321504662700_B43","doi-asserted-by":"publisher","first-page":"32","DOI":"10.3389\/fneur.2020.00032","article-title":"C2H2-type zinc finger proteins in brain development, neurodevelopmental, and other neuropsychiatric disorders: systematic literature-based analysis","volume":"11","author":"Al-Naama","year":"2020","journal-title":"Front Neurol"},{"key":"2026060321504662700_B44","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1186\/gb-2004-5-6-226","article-title":"An overview of the basic helix-loop-helix proteins","volume":"5","author":"Jones","year":"2004","journal-title":"Genome Biol"},{"key":"2026060321504662700_B45","first-page":"gkaf779","article-title":"RegNetwork 2025: an integrative data repository for gene regulatory networks in human and mouse","volume":"54","author":"Li","year":"2025","journal-title":"Nucleic Acids Res"},{"key":"2026060321504662700_B46","doi-asserted-by":"publisher","first-page":"e1005368","DOI":"10.1371\/journal.pgen.1005368","article-title":"RFX2 is a major transcriptional regulator of spermiogenesis","volume":"11","author":"Kistler","year":"2015","journal-title":"PLos Genet"},{"key":"2026060321504662700_B47","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1186\/s12864-018-4564-6","article-title":"Characterization of the human RFX transcription factor family by regulatory and target gene analysis","volume":"19","author":"Sugiaman-Trapman","year":"2018","journal-title":"Bmc Genomics [Electronic Resource]"},{"key":"2026060321504662700_B48","doi-asserted-by":"publisher","first-page":"47","DOI":"10.32607\/20758251-2017-9-2-47-58","article-title":"C2H2 zinc finger proteins: the largest but poorly explored family of higher eukaryotic transcription factors","volume":"9","author":"Fedotova","year":"2017","journal-title":"Acta Naturae (\u0430\u043d\u0433\u043b\u043e\u044f\u0437\u044b\u0447\u043d\u0430\u044f \u0432\u0435\u0440\u0441\u0438\u044f)"},{"key":"2026060321504662700_B49","doi-asserted-by":"publisher","first-page":"D267","DOI":"10.1093\/nar\/gkn782","article-title":"SysZNF: the C2H2 zinc finger gene database","volume":"37","author":"Ding","year":"2009","journal-title":"Nucleic Acids Res"},{"key":"2026060321504662700_B50","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1186\/s12929-016-0269-9","article-title":"Zinc finger proteins in cancer progression","volume":"23","author":"Jen","year":"2016","journal-title":"J Biomed Sci"},{"key":"2026060321504662700_B51","doi-asserted-by":"publisher","first-page":"1314","DOI":"10.3390\/cells12091314","article-title":"Zinc finger proteins in the war on gastric cancer: molecular mechanism and clinical potential","volume":"12","author":"Liu","year":"2023","journal-title":"Cells"},{"key":"2026060321504662700_B52","doi-asserted-by":"publisher","first-page":"15330338251334447","DOI":"10.1177\/15330338251334447","article-title":"Zinc finger proteins in colorectal cancer: insights into molecular mechanisms and therapeutic implications","volume":"24","author":"Lan","year":"2025","journal-title":"Technol Cancer Res Treat"},{"key":"2026060321504662700_B53","doi-asserted-by":"publisher","first-page":"1034","DOI":"10.1038\/s41467-017-01203-1","article-title":"The WNT target SP5 negatively regulates WNT transcriptional programs in human pluripotent stem cells","volume":"8","author":"Huggins","year":"2017","journal-title":"Nat Commun"},{"key":"2026060321504662700_B54","doi-asserted-by":"publisher","first-page":"758","DOI":"10.1016\/j.bbrc.2005.12.068","article-title":"Elevated expression and potential roles of human Sp5, a member of Sp transcription factor family, in human cancers","volume":"340","author":"Chen","year":"2006","journal-title":"Biochem Biophys Res Commun"},{"key":"2026060321504662700_B55","doi-asserted-by":"publisher","first-page":"644","DOI":"10.1186\/s12864-023-09756-w","article-title":"Transcriptomic analysis reveals a tissue-specific loss of identity during ageing and cancer","volume":"24","author":"Dos\u00a0Santos","year":"2023","journal-title":"Bmc Genomics [Electronic Resource]"},{"key":"2026060321504662700_B56","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.ceb.2020.01.005","article-title":"Not all cancers are created equal: tissue specificity in cancer genes and pathways","volume":"63","author":"Bianchi","year":"2020","journal-title":"Curr Opin Cell Biol"}],"container-title":["NAR Genomics and Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/nargab\/article-pdf\/8\/2\/lqag050\/68465410\/lqag050.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/nargab\/article-pdf\/8\/2\/lqag050\/68465410\/lqag050.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T01:51:00Z","timestamp":1780537860000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/nargab\/article\/doi\/10.1093\/nargab\/lqag050\/8701108"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,27]]},"references-count":56,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,3,27]]}},"URL":"https:\/\/doi.org\/10.1093\/nargab\/lqag050","relation":{},"ISSN":["2631-9268"],"issn-type":[{"value":"2631-9268","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,6]]},"published":{"date-parts":[[2026,3,27]]},"article-number":"lqag050"}}