{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T20:00:51Z","timestamp":1790193651407,"version":"4.1.0"},"posted":{"date-parts":[[2026,9,20]]},"group-title":"Bioinformatics","reference-count":41,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T00:00:00Z","timestamp":1789862400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"award":["R35GM154862"],"award-info":[{"award-number":["R35GM154862"]}],"id":[{"id":"https:\/\/ror.org\/04q48ey07","id-type":"ROR","asserted-by":"publisher"}]},{"award":["SES-2619578"],"award-info":[{"award-number":["SES-2619578"]}],"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,9,20]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>\n                  Single-cell DNA methylation profiling technology captures novel epigenetic data modality but are challenging to analyze because of their heterogeneity, high dimensionality, and ultra-sparsity. Here we present SMORE (\n                  <jats:italic>S<\/jats:italic>\n                  ingle-cell\n                  <jats:italic>M<\/jats:italic>\n                  ethyl\n                  <jats:italic>O<\/jats:italic>\n                  me\n                  <jats:italic>R<\/jats:italic>\n                  eduction and\n                  <jats:italic>E<\/jats:italic>\n                  mbedding), a computational method for joint dimensionality reduction and cell population discovery dedicated to single cell DNA methylation data. SMORE operates on a Bayesian framework that converts methylation proportions into ordered methylation states and jointly infers a low-dimensional representation, cell populations and their number. By using low-rank latent Gaussian factorization and adopting a mixture-of-finite-mixtures prior on latent cell scores, SMORE infers cell assignments without requiring a prespecified cluster number, and propagates uncertainty from methylation measurements to cell assignments. Across simulations spanning varying sample sizes, population imbalance, signal strengths and model misspecification,\n                  <jats:italic>SMORE<\/jats:italic>\n                  accurately recovered latent population structure and outperformed existing methods. Applied to human single-cell methylation datasets from lung, peripheral blood and primary motor cortex,\n                  <jats:italic>SMORE<\/jats:italic>\n                  recovered biologically supported cell population structures.\n                  <jats:italic>SMORE<\/jats:italic>\n                  provides an uncertainty-aware framework for dimension reduction and population discovery for single-cell methylomes.\n                <\/jats:p>","DOI":"10.64898\/2026.09.14.751514","type":"posted-content","created":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T04:20:16Z","timestamp":1789964416000},"source":"Crossref","is-referenced-by-count":0,"title":["SMORE: joint dimension reduction and cell population discovery on single-cell methylome data"],"prefix":"10.64898","author":[{"given":"Jingwen","family":"Deng","sequence":"first","affiliation":[{"name":"Department of Biostatistics and Data Science, School of Public Health, The University of Texas Health Science Center at Houston, Houston, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Data Science, School of Public Health, The University of Texas Health Science Center at Houston, Houston, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3710-9029","authenticated-orcid":false,"given":"Wen","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Data Science, School of Public Health, The University of Texas Health Science Center at Houston, Houston, TX, USA"},{"name":"Center for Spatial-Temporal Modeling for Applications in Population Sciences, School of Public Health, The University of Texas Health Science Center at Houston, Houston, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanyu","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Statistics and Probability, Michigan State University, East Lansing, MI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2243-9949","authenticated-orcid":false,"given":"Hao","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Data Science, School of Public Health, The University of Texas Health Science Center at Houston, Houston, TX, USA"},{"name":"Center for Spatial-Temporal Modeling for Applications in Population Sciences, School of Public Health, The University of Texas Health Science Center at Houston, Houston, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026092312102259000_2026.09.14.751514v1.1","doi-asserted-by":"publisher","DOI":"10.2307\/2290350"},{"key":"2026092312102259000_2026.09.14.751514v1.2","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.3728"},{"key":"2026092312102259000_2026.09.14.751514v1.3","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-017-1189-z"},{"key":"2026092312102259000_2026.09.14.751514v1.4","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-020-02015-1"},{"key":"2026092312102259000_2026.09.14.751514v1.5","doi-asserted-by":"publisher","DOI":"10.1007\/s12564-010-9096-y"},{"key":"2026092312102259000_2026.09.14.751514v1.6","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-03149-4"},{"key":"2026092312102259000_2026.09.14.751514v1.7","first-page":"201","article-title":"Model-based clustering for expression data via a dirichlet process mixture model","volume":"4","year":"2006","journal-title":"Bayesian Inference for Gene Expression and Proteomics"},{"key":"2026092312102259000_2026.09.14.751514v1.8","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-25131-3"},{"key":"2026092312102259000_2026.09.14.751514v1.9","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1008270"},{"key":"2026092312102259000_2026.09.14.751514v1.10","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-026-70523-y"},{"key":"2026092312102259000_2026.09.14.751514v1.11","doi-asserted-by":"publisher","DOI":"10.1016\/j.celrep.2015.02.001"},{"key":"2026092312102259000_2026.09.14.751514v1.12","doi-asserted-by":"publisher","DOI":"10.1093\/rfs\/9.2.557"},{"issue":"1","key":"2026092312102259000_2026.09.14.751514v1.13","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1038\/s43586-022-00184-w","article-title":"Principal component analysis","volume":"2","year":"2022","journal-title":"Nature Reviews Methods Primers"},{"key":"2026092312102259000_2026.09.14.751514v1.14","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-12293-4"},{"key":"2026092312102259000_2026.09.14.751514v1.15","doi-asserted-by":"publisher","DOI":"10.1016\/j.stemcr.2018.07.003"},{"key":"2026092312102259000_2026.09.14.751514v1.16","doi-asserted-by":"publisher","DOI":"10.1016\/j.gpb.2022.05.007"},{"key":"2026092312102259000_2026.09.14.751514v1.17","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-021-00926-8"},{"key":"2026092312102259000_2026.09.14.751514v1.18","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-021-02329-8"},{"key":"2026092312102259000_2026.09.14.751514v1.19","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-019-1665-8"},{"key":"2026092312102259000_2026.09.14.751514v1.20","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-9473(97)00038-8"},{"key":"2026092312102259000_2026.09.14.751514v1.21","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-024-02347-x"},{"key":"2026092312102259000_2026.09.14.751514v1.22","doi-asserted-by":"publisher","DOI":"10.1038\/44565"},{"key":"2026092312102259000_2026.09.14.751514v1.23","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0547-z"},{"key":"2026092312102259000_2026.09.14.751514v1.24","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06805-y"},{"key":"2026092312102259000_2026.09.14.751514v1.25","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03182-8"},{"key":"2026092312102259000_2026.09.14.751514v1.26","doi-asserted-by":"publisher","DOI":"10.1126\/science.aan3351"},{"key":"2026092312102259000_2026.09.14.751514v1.27","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-06355-2"},{"key":"2026092312102259000_2026.09.14.751514v1.28","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861"},{"issue":"521","key":"2026092312102259000_2026.09.14.751514v1.29","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1080\/01621459.2016.1255636","article-title":"Mixture models with a prior on the number of components","volume":"113","year":"2018","journal-title":"Journal of the American Statistical Association"},{"key":"2026092312102259000_2026.09.14.751514v1.30","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.4112"},{"issue":"2","key":"2026092312102259000_2026.09.14.751514v1.31","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1080\/10618600.2000.10474879","article-title":"Markov chain sampling methods for dirichlet process mixture models","volume":"9","year":"2000","journal-title":"Journal of computational and graphical statistics"},{"key":"2026092312102259000_2026.09.14.751514v1.32","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-22859-w"},{"key":"2026092312102259000_2026.09.14.751514v1.33","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.3035"},{"key":"2026092312102259000_2026.09.14.751514v1.34","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-026-73171-4"},{"key":"2026092312102259000_2026.09.14.751514v1.35","doi-asserted-by":"publisher","DOI":"10.3389\/fbioe.2022.842019"},{"key":"2026092312102259000_2026.09.14.751514v1.36","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9868.00293"},{"key":"2026092312102259000_2026.09.14.751514v1.37","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-026-01225-9"},{"key":"2026092312102259000_2026.09.14.751514v1.38","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-017-1269-0"},{"key":"2026092312102259000_2026.09.14.751514v1.39","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2019.05.006"},{"key":"2026092312102259000_2026.09.14.751514v1.40","doi-asserted-by":"publisher","DOI":"10.1126\/science.adx0673"},{"key":"2026092312102259000_2026.09.14.751514v1.41","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-017-0007-6"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.09.14.751514","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T19:10:27Z","timestamp":1790190627000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.09.14.751514"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,20]]},"references-count":41,"URL":"https:\/\/doi.org\/10.64898\/2026.09.14.751514","relation":{},"subject":[],"published":{"date-parts":[[2026,9,20]]},"subtype":"preprint"}}