{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T13:33:38Z","timestamp":1785418418521,"version":"3.56.0"},"posted":{"date-parts":[[2025,7,25]]},"group-title":"Bioinformatics","reference-count":74,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T00:00:00Z","timestamp":1753401600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"award":["R01 DK087694"],"award-info":[{"award-number":["R01 DK087694"]}],"id":[{"id":"https:\/\/ror.org\/01cwqze88","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,7,25]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>Single cell multi-omic investigation opens-up new opportunities to understand mechanisms of gene regulation. Existing methods for inferring transcript abundance from chromatin accessibility fail to prioritize the most relevant peaks and tend to assume positive associations between ATAC peaks and RNA counts. We hypothesize that gene regulation can be modeled as a function of combined positive and negative interactions among peaks and that causal regulatory variants are enriched in the vicinity of the most critical peaks.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>A machine learning pipeline leveraging single nuclear multiomic transcriptome and chromatin accessibility data is developed to model gene expression as a function of ATAC peak intensity. Multiome data was available for 18 immune cell types from 29 donors, 19 with Crohn\u2019s disease. The pipeline aggregates results from three machine learning approaches (random forest regression, XGBoost, and Light GBM) as well as linear regression to identify which ATAC peaks contribute to explaining variation among donors and cell types in pseudobulk gene expression. The coefficient of determination with cross-validation was used to identify robust models which typically explain between 5% and 40% of transcript abundance, utilizing on average 47% of the ATAC peaks, representing a significant gain in predictive accuracy. The most important peaks are enriched in GWAS variants for inflammatory bowel disease and the autoimmune disease systemic lupus erythematosus, but not for rheumatoid arthritis.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>Atlanta Plots visualize the proportion of ATAC peaks contributing to a predictive model of gene expression as well as the proportion of variance explained by the model. Software implementing our pipeline, \u201csnATAC-Express\u201d, is freely available on GitHub.<\/jats:p>\n                <\/jats:sec>","DOI":"10.1101\/2025.07.25.666784","type":"posted-content","created":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T04:15:17Z","timestamp":1753503317000},"source":"Crossref","is-referenced-by-count":0,"title":["snATAC-Express infers Gene Expression from Prioritized Chromatin Accessibility Peaks using Machine Learning"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6737-3504","authenticated-orcid":false,"given":"Margaret","family":"Brown","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandro","family":"Ferrari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anne","family":"Dodd","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6919-3765","authenticated-orcid":false,"given":"Vasantha L.","family":"Kolachala","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8686-4189","authenticated-orcid":false,"given":"Subra","family":"Kugathasan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8575-0537","authenticated-orcid":false,"given":"Russell D.","family":"Wolfinger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5352-5877","authenticated-orcid":false,"given":"Greg","family":"Gibson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2025072808150452000_2025.07.25.666784v1.1","first-page":"100063","article-title":"From GWAS variant to function: A study of approximately 148,000 variants for blood cell traits","volume":"3","year":"2022","journal-title":"HGG Adv"},{"key":"2025072808150452000_2025.07.25.666784v1.2","doi-asserted-by":"publisher","DOI":"10.1016\/J.AJHG.2022.12.011"},{"key":"2025072808150452000_2025.07.25.666784v1.3","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.1315"},{"key":"2025072808150452000_2025.07.25.666784v1.4","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.2764"},{"key":"2025072808150452000_2025.07.25.666784v1.5","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-26530-2"},{"key":"2025072808150452000_2025.07.25.666784v1.6","doi-asserted-by":"publisher","DOI":"10.1186\/s13072-019-0260-2"},{"key":"2025072808150452000_2025.07.25.666784v1.7","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.2688"},{"key":"2025072808150452000_2025.07.25.666784v1.8","doi-asserted-by":"publisher","DOI":"10.1038\/nature13835"},{"key":"2025072808150452000_2025.07.25.666784v1.9","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-022-01341-y"},{"key":"2025072808150452000_2025.07.25.666784v1.10","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-38637-9"},{"key":"2025072808150452000_2025.07.25.666784v1.11","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btw024"},{"key":"2025072808150452000_2025.07.25.666784v1.12","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaa516"},{"key":"2025072808150452000_2025.07.25.666784v1.13","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.4463"},{"key":"2025072808150452000_2025.07.25.666784v1.14","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms6795"},{"key":"2025072808150452000_2025.07.25.666784v1.15","doi-asserted-by":"publisher","DOI":"10.1126\/science.1256271"},{"key":"2025072808150452000_2025.07.25.666784v1.16","doi-asserted-by":"publisher","DOI":"10.1186\/s12864-016-3428-1"},{"key":"2025072808150452000_2025.07.25.666784v1.17","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-021-00790-6"},{"key":"2025072808150452000_2025.07.25.666784v1.18","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-021-01282-5"},{"key":"2025072808150452000_2025.07.25.666784v1.19","doi-asserted-by":"publisher","DOI":"10.1016\/J.MOLCEL.2018.06.044"},{"key":"2025072808150452000_2025.07.25.666784v1.20","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-024-01682-1"},{"key":"2025072808150452000_2025.07.25.666784v1.21","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-024-01689-8"},{"key":"2025072808150452000_2025.07.25.666784v1.22","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-16106-x"},{"key":"2025072808150452000_2025.07.25.666784v1.23","doi-asserted-by":"publisher","DOI":"10.1080\/19491034.2022.2143106"},{"key":"2025072808150452000_2025.07.25.666784v1.24","doi-asserted-by":"crossref","first-page":"100640","DOI":"10.1016\/j.tbs.2023.100640","article-title":"Machine learning techniques for evaluating the nonlinear link between built-environment characteristics and travel behaviors: A systematic review","volume":"33","year":"2023","journal-title":"Travel Behav Society"},{"key":"2025072808150452000_2025.07.25.666784v1.25","doi-asserted-by":"crossref","first-page":"652771","DOI":"10.3389\/fimmu.2021.652771","article-title":"Metabolic control of autoimmunity and tissue inflammation in rheumatoid arthritis","volume":"12","year":"2021","journal-title":"Front Immunol"},{"key":"2025072808150452000_2025.07.25.666784v1.26","first-page":"806560","article-title":"The Role of Immunometabolism in the Pathogenesis of Systemic Lupus Erythematosus","volume":"12","year":"2021","journal-title":"Front Immunol"},{"key":"2025072808150452000_2025.07.25.666784v1.27","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2020.04.074"},{"key":"2025072808150452000_2025.07.25.666784v1.28","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1186\/s13073-018-0558-x","article-title":"Disease-specific regulation of gene expression in a comparative analysis of juvenile idiopathic arthritis and inflammatory bowel disease","volume":"10","year":"2018","journal-title":"Genome Med"},{"key":"2025072808150452000_2025.07.25.666784v1.29","doi-asserted-by":"crossref","first-page":"655","DOI":"10.1038\/ja.2009.98","article-title":"Chemical biology of inflammatory cytokine signaling","volume":"62","year":"2009","journal-title":"J Antibiot (Tokyo"},{"key":"2025072808150452000_2025.07.25.666784v1.30","doi-asserted-by":"publisher","DOI":"10.1196\/annals.1443.021"},{"key":"2025072808150452000_2025.07.25.666784v1.31","doi-asserted-by":"publisher","DOI":"10.1093\/intimm\/dxaa078"},{"key":"2025072808150452000_2025.07.25.666784v1.32","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2017.00873"},{"issue":"Suppl 2","key":"2025072808150452000_2025.07.25.666784v1.33","doi-asserted-by":"crossref","first-page":"S4","DOI":"10.1186\/ar1703","article-title":"The role of the T cell in autoimmune inflammation","volume":"7","year":"2005","journal-title":"Arthritis Res Ther"},{"key":"2025072808150452000_2025.07.25.666784v1.34","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1038\/hdy.2010.54","article-title":"Epigenetics and gene expression","volume":"105","year":"2010","journal-title":"Heredity (Edinb"},{"key":"2025072808150452000_2025.07.25.666784v1.35","doi-asserted-by":"publisher","DOI":"10.1038\/s41590-019-0378-1"},{"key":"2025072808150452000_2025.07.25.666784v1.36","doi-asserted-by":"publisher","DOI":"10.1038\/onc.2011.320"},{"key":"2025072808150452000_2025.07.25.666784v1.37","first-page":"4768","article-title":"A unified approach to interpreting model predictions","volume":"30","year":"2017","journal-title":"NIPS"},{"key":"2025072808150452000_2025.07.25.666784v1.38","doi-asserted-by":"crossref","first-page":"647","DOI":"10.1007\/s10115-013-0679-x","article-title":"Explaining prediction models and individual predictions with feature contributions","volume":"41","year":"2014","journal-title":"Knowl Info Syst"},{"key":"2025072808150452000_2025.07.25.666784v1.39","first-page":"1","article-title":"An efficient explanation of individual classifications using game theory","volume":"11","year":"2010","journal-title":"J Mach Learn Res"},{"key":"2025072808150452000_2025.07.25.666784v1.40","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms16021"},{"key":"2025072808150452000_2025.07.25.666784v1.41","doi-asserted-by":"publisher","DOI":"10.1038\/ng.233"},{"key":"2025072808150452000_2025.07.25.666784v1.42","doi-asserted-by":"publisher","DOI":"10.1038\/nature12873"},{"key":"2025072808150452000_2025.07.25.666784v1.43","doi-asserted-by":"publisher","DOI":"10.1038\/ng.3359"},{"key":"2025072808150452000_2025.07.25.666784v1.44","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkad781"},{"key":"2025072808150452000_2025.07.25.666784v1.45","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btv402"},{"key":"2025072808150452000_2025.07.25.666784v1.46","doi-asserted-by":"publisher","DOI":"10.1101\/2021.03.13.21249938"},{"key":"2025072808150452000_2025.07.25.666784v1.47","doi-asserted-by":"publisher","DOI":"10.1186\/s13073-021-00996-7"},{"key":"2025072808150452000_2025.07.25.666784v1.48","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2019.00772"},{"key":"2025072808150452000_2025.07.25.666784v1.49","doi-asserted-by":"publisher","DOI":"10.3390\/ijms23020905"},{"key":"2025072808150452000_2025.07.25.666784v1.50","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-48620-7"},{"key":"2025072808150452000_2025.07.25.666784v1.51","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-023-01577-7"},{"key":"2025072808150452000_2025.07.25.666784v1.52","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2017.11.019"},{"key":"2025072808150452000_2025.07.25.666784v1.53","doi-asserted-by":"publisher","DOI":"10.1038\/S41576-018-0089-8"},{"key":"2025072808150452000_2025.07.25.666784v1.54","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-08443-4"},{"key":"2025072808150452000_2025.07.25.666784v1.55","doi-asserted-by":"publisher","DOI":"10.1002\/bies.201900188"},{"key":"2025072808150452000_2025.07.25.666784v1.56","doi-asserted-by":"publisher","DOI":"10.1016\/j.exphem.2017.01.003"},{"key":"2025072808150452000_2025.07.25.666784v1.57","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pgen.1009719"},{"key":"2025072808150452000_2025.07.25.666784v1.58","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-23007-0"},{"key":"2025072808150452000_2025.07.25.666784v1.59","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pgen.1000888"},{"key":"2025072808150452000_2025.07.25.666784v1.60","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-023-01529-1"},{"key":"2025072808150452000_2025.07.25.666784v1.61","doi-asserted-by":"crossref","first-page":"1939","DOI":"10.1093\/ecco-jcc\/jjae055","article-title":"Concordant B and T cell heterogeneity inferred from the multiomic landscape of peripheral blood mononuclear cells in a Crohn\u2019s disease cohort","volume":"18","year":"2024","journal-title":"J Crohns Colitis"},{"key":"2025072808150452000_2025.07.25.666784v1.62","doi-asserted-by":"crossref","unstructured":"Pan YD , Tian R , Lee C , Bao G , Gibson G . Fine-mapping within eQTL credible intervals by expression CROP-seq. Biol Methods Protoc. 2020;5:bpa008.","DOI":"10.1093\/biomethods\/bpaa008"},{"key":"2025072808150452000_2025.07.25.666784v1.63","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-0837-5"},{"key":"2025072808150452000_2025.07.25.666784v1.64","doi-asserted-by":"publisher","DOI":"10.1093\/bfgp\/ely002"},{"key":"2025072808150452000_2025.07.25.666784v1.65","doi-asserted-by":"crossref","first-page":"874525","DOI":"10.3389\/fcell.2022.874525","article-title":"Effects of the Zbtb1 gene on chromatin spatial structure and lymphatic development: combined analysis of Hi-C, ATAC-Seq and RNA-Seq","volume":"10","year":"2022","journal-title":"Front Cell Dev Biol"},{"key":"2025072808150452000_2025.07.25.666784v1.66","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms14049"},{"key":"2025072808150452000_2025.07.25.666784v1.67","doi-asserted-by":"publisher","DOI":"10.1186\/gb-2008-9-9-r137"},{"key":"2025072808150452000_2025.07.25.666784v1.68","doi-asserted-by":"publisher","DOI":"10.1093\/NAR\/GKAC1010"},{"key":"2025072808150452000_2025.07.25.666784v1.69","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkac1071"},{"key":"2025072808150452000_2025.07.25.666784v1.70","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2010.04.018"},{"key":"2025072808150452000_2025.07.25.666784v1.71","first-page":"785","article-title":"XGBoost: A Scalable Tree Boosting System","volume":"16","year":"2016","journal-title":"KDD"},{"key":"2025072808150452000_2025.07.25.666784v1.72","first-page":"3149","article-title":"LightGBM: a highly efficient gradient boosting decision tree","volume":"30","year":"2017","journal-title":"NIPS"},{"key":"2025072808150452000_2025.07.25.666784v1.73","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkp427"},{"key":"2025072808150452000_2025.07.25.666784v1.74","doi-asserted-by":"crossref","unstructured":"McKinney W . Data Structures for Statistical Computing in Python. Proc 9th Python in Science Conf. 2010;9:56\u201361.","DOI":"10.25080\/Majora-92bf1922-00a"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.07.25.666784","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T09:11:50Z","timestamp":1768468310000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2025.07.25.666784"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,25]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1101\/2025.07.25.666784","relation":{},"subject":[],"published":{"date-parts":[[2025,7,25]]},"subtype":"preprint"}}