{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T12:42:15Z","timestamp":1785415335208,"version":"3.56.0"},"posted":{"date-parts":[[2025,10,31]]},"group-title":"Bioinformatics","reference-count":50,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T00:00:00Z","timestamp":1761868800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"award":["R01LM013722"],"award-info":[{"award-number":["R01LM013722"]}],"id":[{"id":"https:\/\/ror.org\/0060t0j89","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,10,31]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>\n                  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 the non-coding DNA, particularly in distal promoter regions. Here, we introduce\n                  <jats:italic>\n                    <jats:underline>TSProm<\/jats:underline>\n                  <\/jats:italic>\n                  , a framework that specializes a DNA foundation model (DNABERT2) to decipher the long-range regulatory logic of TSp promoters at the gene isoform level. The contributions of our work are two-fold. First, we propose a novel comparative design that trains two distinct models, A: for general promoter biology and B: for TSp regulation. These models enable the precise isolation of sequence motifs around the transcription start site that uniquely define tissue identity. Second, we introduce a comprehensive explainable AI (xAI) module that integrates attention-based discovery with model-agnostic SHAP analysis to provide robust, cross-validated interpretations of learned features. Applying this framework to human brain, liver, and testis promoters, we identified and validated clinically relevant transcription factors (TFs) in the brain, including\n                  <jats:italic>SP1, MYC<\/jats:italic>\n                  , and\n                  <jats:italic>HES6<\/jats:italic>\n                  , and confirmed their known roles in diseases such as gliomas and neuroblastomas. Our analysis further revealed that\n                  <jats:italic>C2H2<\/jats:italic>\n                  Zinc Finger proteins are a dominant feature of the global landscape of TSp gene regulation. TSProm provides a novel and interpretable framework for identifying TSp gene regulatory elements, offering powerful computational tools for the study of tissue-specific gene regulation in normal and disease conditions.\n                <\/jats:p>","DOI":"10.1101\/2025.10.30.685161","type":"posted-content","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T20:45:11Z","timestamp":1761943511000},"source":"Crossref","is-referenced-by-count":0,"title":["TSProm: Deciphering the Genomic Context of Tissue Specificity"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4241-9181","authenticated-orcid":false,"given":"Pallavi","family":"Surana","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1579-8946","authenticated-orcid":false,"given":"Pratik","family":"Dutta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nimisha","family":"Papineni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5698-1981","authenticated-orcid":false,"given":"Rekha","family":"Sathian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1473-9071","authenticated-orcid":false,"given":"Zhihan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7053-1064","authenticated-orcid":false,"given":"Ramana","family":"Davuluri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2025110401450718000_2025.10.30.685161v1.1","doi-asserted-by":"publisher","DOI":"10.3390\/genes15020252"},{"key":"2025110401450718000_2025.10.30.685161v1.2","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkp335"},{"key":"2025110401450718000_2025.10.30.685161v1.3","doi-asserted-by":"crossref","unstructured":"Y. Barash , G. Bejerano , and N. Friedman . A simple hypergeometric approach for discovering putative transcription factor binding sites. In International Workshop on Algorithms in Bioinformatics, pages 278\u2013293. Springer, 2001.","DOI":"10.1007\/3-540-44696-6_22"},{"key":"2025110401450718000_2025.10.30.685161v1.4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ceb.2020.01.005"},{"key":"2025110401450718000_2025.10.30.685161v1.5","doi-asserted-by":"publisher","DOI":"10.1038\/ng1789"},{"key":"2025110401450718000_2025.10.30.685161v1.6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1411-0"},{"key":"2025110401450718000_2025.10.30.685161v1.7","doi-asserted-by":"publisher","DOI":"10.1016\/j.bbrc.2005.12.068"},{"key":"2025110401450718000_2025.10.30.685161v1.8","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2311.07621"},{"key":"2025110401450718000_2025.10.30.685161v1.9","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-024-02523-z"},{"key":"2025110401450718000_2025.10.30.685161v1.10","doi-asserted-by":"publisher","DOI":"10.1016\/j.tig.2008.01.008"},{"key":"2025110401450718000_2025.10.30.685161v1.11","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1919507117"},{"key":"2025110401450718000_2025.10.30.685161v1.12","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkn782"},{"key":"2025110401450718000_2025.10.30.685161v1.13","doi-asserted-by":"publisher","DOI":"10.1186\/s12864-023-09756-w"},{"key":"2025110401450718000_2025.10.30.685161v1.14","doi-asserted-by":"publisher","DOI":"10.32607\/20758251-2017-9-2-47-58"},{"key":"2025110401450718000_2025.10.30.685161v1.15","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkad1016"},{"key":"2025110401450718000_2025.10.30.685161v1.16","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkae1310"},{"key":"2025110401450718000_2025.10.30.685161v1.17","doi-asserted-by":"publisher","DOI":"10.1101\/gr.1953904"},{"key":"2025110401450718000_2025.10.30.685161v1.18","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1009085"},{"key":"2025110401450718000_2025.10.30.685161v1.19","doi-asserted-by":"publisher","DOI":"10.1126\/science.1262110"},{"key":"2025110401450718000_2025.10.30.685161v1.20","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaz1776"},{"key":"2025110401450718000_2025.10.30.685161v1.21","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwaf028"},{"key":"2025110401450718000_2025.10.30.685161v1.22","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaw3472"},{"key":"2025110401450718000_2025.10.30.685161v1.23","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-017-01203-1"},{"key":"2025110401450718000_2025.10.30.685161v1.24","doi-asserted-by":"publisher","DOI":"10.1186\/s12929-016-0269-9"},{"key":"2025110401450718000_2025.10.30.685161v1.25","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btab083"},{"issue":"7","key":"2025110401450718000_2025.10.30.685161v1.26","doi-asserted-by":"crossref","first-page":"e1005368","DOI":"10.1371\/journal.pgen.1005368","article-title":"Rfx2 is a major transcriptional regulator of spermiogenesis","volume":"11","year":"2015","journal-title":"PLoS genetics"},{"key":"2025110401450718000_2025.10.30.685161v1.27","unstructured":"E. Kokalj , B. \u0160krlj , N. Lavra\u010d , S. Pollak , and M. Robnik-\u0160ikonja . BERT meets shapley: Extending SHAP explanations to transformer-based classifiers. In H. Toivonen and M. Boggia , editors, Proceedings of the EACL Hackashop on News Media Content Analysis and Automated Report Generation, Online, Apr. 2021. Association for Computational Linguistics."},{"key":"2025110401450718000_2025.10.30.685161v1.28","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0237412"},{"key":"2025110401450718000_2025.10.30.685161v1.29","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2018.01.029"},{"key":"2025110401450718000_2025.10.30.685161v1.30","doi-asserted-by":"publisher","DOI":"10.1177\/15330338251334447"},{"key":"2025110401450718000_2025.10.30.685161v1.31","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiolchem.2022.107732"},{"key":"2025110401450718000_2025.10.30.685161v1.32","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-04520-z"},{"key":"2025110401450718000_2025.10.30.685161v1.33","doi-asserted-by":"publisher","DOI":"10.1016\/j.celrep.2025.115901"},{"key":"2025110401450718000_2025.10.30.685161v1.34","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-15334-y"},{"key":"2025110401450718000_2025.10.30.685161v1.35","doi-asserted-by":"publisher","DOI":"10.3390\/cells12091314"},{"key":"2025110401450718000_2025.10.30.685161v1.36","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2020.623679"},{"key":"2025110401450718000_2025.10.30.685161v1.37","unstructured":"Z. Liu , J. Li , S. Li , Z. Zang , C. Tan , Y. Huang , Y. Bai , and S. Z. Li . Genbench: A benchmarking suite for systematic evaluation of genomic foundation models, 2024. URL https:\/\/arxiv.org\/abs\/2406.01627."},{"key":"2025110401450718000_2025.10.30.685161v1.38","unstructured":"S. M. Lundberg and S.-I. Lee . A unified approach to interpreting model predictions. In I. Guyon , U. V. Luxburg , S. Bengio , H. Wallach , R. Fergus , S. Vishwanathan , and R. Garnett , editors, Advances in Neural Information Processing Systems, volume 30. Curran Associates, Inc., 2017. URL https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/8a20a8621978632d76c43dfd28b67767-Paper.pdf."},{"key":"2025110401450718000_2025.10.30.685161v1.39","unstructured":"E. Mosca , F. Szigeti , S. Tragianni , D. Gallagher , and G. Groh . SHAP-based explanation methods: A review for NLP interpretability. In N. Calzolari , C.-R. Huang , H. Kim , J. Pustejovsky , L. Wanner , K.-S. Choi , P.-M. Ryu , H.-H. Chen , L. Donatelli , H. Ji , S. Kurohashi , P. Paggio , N. Xue , S. Kim , Y. Hahm , Z. He , T. K. Lee , E. Santus , F. Bond , and S.-H. Na , editors, Proceedings of the 29th International Conference on Computational Linguistics, Gyeongju, Republic of Korea, Oct. 2022. International Committee on Computational Linguistics."},{"key":"2025110401450718000_2025.10.30.685161v1.40","article-title":"HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution","year":"2023","journal-title":"arXiv preprint"},{"key":"2025110401450718000_2025.10.30.685161v1.41","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkad1059"},{"key":"2025110401450718000_2025.10.30.685161v1.42","doi-asserted-by":"publisher","DOI":"10.1038\/msb4100114"},{"key":"2025110401450718000_2025.10.30.685161v1.43","doi-asserted-by":"publisher","DOI":"10.1016\/j.celrep.2017.10.001"},{"key":"2025110401450718000_2025.10.30.685161v1.44","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.3988"},{"key":"2025110401450718000_2025.10.30.685161v1.45","doi-asserted-by":"publisher","DOI":"10.1186\/s12864-018-4564-6"},{"key":"2025110401450718000_2025.10.30.685161v1.46","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae475"},{"key":"2025110401450718000_2025.10.30.685161v1.47","doi-asserted-by":"publisher","DOI":"10.1109\/SASP.2010.5521145"},{"key":"2025110401450718000_2025.10.30.685161v1.48","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkab1114"},{"key":"2025110401450718000_2025.10.30.685161v1.49","unstructured":"Z. Zhou , Y. Ji , W. Li , P. Dutta , R. Davuluri , and H. Liu . Dnabert-2: Efficient foundation model and benchmark for multi-species genome, 2024. URL https:\/\/arxiv.org\/abs\/2306.15006."},{"key":"2025110401450718000_2025.10.30.685161v1.50","doi-asserted-by":"publisher","DOI":"10.1158\/2159-8290.CD-17-0993"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.10.30.685161","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T09:56:08Z","timestamp":1768470968000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2025.10.30.685161"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,31]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1101\/2025.10.30.685161","relation":{},"subject":[],"published":{"date-parts":[[2025,10,31]]},"subtype":"preprint"}}