{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T06:48:43Z","timestamp":1775890123875,"version":"3.50.1"},"posted":{"date-parts":[[2025,1,27]]},"group-title":"Bioinformatics","reference-count":26,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T00:00:00Z","timestamp":1737936000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,1,27]]},"abstract":"<jats:title>SUMMARY<\/jats:title>\n                <jats:p>Single-cell technologies have enhanced our knowledge of molecular and cellular heterogeneity underlying disease. As the scale of single-cell datasets expands, linking cell-level phenotypic alterations with clinical outcomes becomes increasingly challenging. To address this, we introduce CellPhenoX, an eXplainable machine learning method to identify cell-specific phenotypes that influence clinical outcomes. CellPhenoX integrates classification models, explainable AI techniques, and a statistical framework to generate interpretable, cell-specific scores that uncover cell populations associated with relevant clinical phenotypes and interaction effects. We demonstrated the performance of CellPhenoX across diverse single-cell designs, including simulations, binary disease-control comparisons, and multi-class studies. Notably, CellPhenoX identified an activated monocyte phenotype in COVID-19, with expansion correlated with disease severity after adjusting for covariates and interactive effects. It also uncovered an inflammation-associated gradient in fibroblasts from ulcerative colitis. We anticipate that CellPhenoX holds the potential to detect clinically relevant phenotypic changes in single-cell data with multiple sources of variation, paving the way for translating single-cell findings into clinical impact.<\/jats:p>","DOI":"10.1101\/2025.01.24.634132","type":"posted-content","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T20:20:20Z","timestamp":1738009220000},"source":"Crossref","is-referenced-by-count":1,"title":["CellPhenoX: An eXplainable Cell-specific machine learning method to predict clinical Phenotypes using single-cell multi-omics"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0887-3319","authenticated-orcid":false,"given":"Jade","family":"Young","sequence":"first","affiliation":[{"name":"Department of Biomedical Informatics, University of Colorado School of Medicine, Aurora, CO, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Inamo","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, University of Colorado School of Medicine, Aurora, CO, USA"},{"name":"Department of Medicine Rheumatology, University of Colorado School of Medicine, Aurora, CO, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zachary","family":"Caterer","sequence":"additional","affiliation":[{"name":"Interdisciplinary Quantitative Biology PhD Program, BioFrontiers Institute, University of Colorado, Boulder, CO, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Revanth","family":"Krishna","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, University of Colorado School of Medicine, Aurora, CO, USA"},{"name":"Department of Medicine Rheumatology, University of Colorado School of Medicine, Aurora, CO, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6102-2970","authenticated-orcid":false,"given":"Fan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, University of Colorado School of Medicine, Aurora, CO, USA"},{"name":"Department of Medicine Rheumatology, University of Colorado School of Medicine, Aurora, CO, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2026041022562958000_2025.01.24.634132v1.1","doi-asserted-by":"publisher","DOI":"10.1038\/nri.2017.76"},{"key":"2026041022562958000_2025.01.24.634132v1.2","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-022-02104-7"},{"key":"2026041022562958000_2025.01.24.634132v1.3","doi-asserted-by":"publisher","DOI":"10.1038\/s41573-023-00688-4"},{"key":"2026041022562958000_2025.01.24.634132v1.4","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.4295"},{"key":"2026041022562958000_2025.01.24.634132v1.5","doi-asserted-by":"crossref","unstructured":"Fonseka, C. Y. et al. Mixed-effects association of single cells identifies an expanded effector CD4+ T cell subset in rheumatoid arthritis. Sci. Transl. Med. 10, (2018).","DOI":"10.1126\/scitranslmed.aaq0305"},{"key":"2026041022562958000_2025.01.24.634132v1.6","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-023-03143-0"},{"key":"2026041022562958000_2025.01.24.634132v1.7","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-020-00803-5"},{"key":"2026041022562958000_2025.01.24.634132v1.8","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-021-01033-z"},{"key":"2026041022562958000_2025.01.24.634132v1.9","doi-asserted-by":"crossref","unstructured":"Reshef, Y. A. et al. Co-varying neighborhood analysis identifies cell populations associated with phenotypes of interest from single-cell transcriptomics. Nat. Biotechnol. 1\u20139 (2021).","DOI":"10.1038\/s41587-021-01066-4"},{"key":"2026041022562958000_2025.01.24.634132v1.10","unstructured":"Lundberg, S. M. & Lee, S.-I. A Unified Approach to Interpreting Model Predictions. In Advances in Neural Information Processing Systems (eds. Guyon, I. et al. ) vol. 30 (Curran Associates, Inc., 2017)."},{"key":"2026041022562958000_2025.01.24.634132v1.11","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00657-x"},{"key":"2026041022562958000_2025.01.24.634132v1.12","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-31384-3"},{"key":"2026041022562958000_2025.01.24.634132v1.13","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-43575-7"},{"key":"2026041022562958000_2025.01.24.634132v1.14","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06708-y"},{"key":"2026041022562958000_2025.01.24.634132v1.15","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-021-01186-x"},{"key":"2026041022562958000_2025.01.24.634132v1.16","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-021-01329-2"},{"key":"2026041022562958000_2025.01.24.634132v1.17","doi-asserted-by":"publisher","DOI":"10.1101\/2023.07.03.547507"},{"key":"2026041022562958000_2025.01.24.634132v1.18","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.4314"},{"key":"2026041022562958000_2025.01.24.634132v1.19","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0619-0"},{"key":"2026041022562958000_2025.01.24.634132v1.20","doi-asserted-by":"publisher","DOI":"10.1007\/s15010-021-01606-9"},{"key":"2026041022562958000_2025.01.24.634132v1.21","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2020.580677"},{"key":"2026041022562958000_2025.01.24.634132v1.22","doi-asserted-by":"publisher","DOI":"10.1038\/s41577-021-00665-1"},{"key":"2026041022562958000_2025.01.24.634132v1.23","doi-asserted-by":"publisher","DOI":"10.1038\/S41586-020-2600-6"},{"key":"2026041022562958000_2025.01.24.634132v1.24","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2019.06.029"},{"key":"2026041022562958000_2025.01.24.634132v1.25","doi-asserted-by":"publisher","DOI":"10.1038\/44565"},{"key":"2026041022562958000_2025.01.24.634132v1.26","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btp616"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.01.24.634132","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T05:56:36Z","timestamp":1775886996000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2025.01.24.634132"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,27]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1101\/2025.01.24.634132","relation":{},"subject":[],"published":{"date-parts":[[2025,1,27]]},"subtype":"preprint"}}