{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T05:54:34Z","timestamp":1787032474414,"version":"build-2736575974"},"posted":{"date-parts":[[2026,4,22]]},"group-title":"Bioinformatics","reference-count":41,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T00:00:00Z","timestamp":1776816000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100015326","name":"NIH Common Fund","doi-asserted-by":"crossref","award":["R01AG082730"],"award-info":[{"award-number":["R01AG082730"]}],"id":[{"id":"10.13039\/100015326","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,6,27]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Single-cell transcriptomics resolves cellular heterogeneity within individuals, but connecting molecular states to individual-level phenotypes requires frameworks that explicitly bridge these scales. We present scVIP, a generative model that links gene expression, cell-type composition, and phenotypic measurements within a single probabilistic model, which enables accurate phenotype prediction and interpretable trajectory inference. A cell-type-aware multi-instance learning architecture learns donor embeddings that capture progression while localizing phenotype-associated signals to specific cell populations. Applied across four settings, scVIP accurately predicts cortical developmental age (Pearson r = 0.95), characterizes Huntington\u2019s disease progression (concordance correlation coefficient = 0.90), integrates two Alzheimer\u2019s disease cohorts recovering disease-relevant microglial and astrocytic programs, and distinguishes healthy from ACPA-positive individuals and non-progressors from early RA individuals, identifying inflammatory T cell programs associated with disease. scVIP enables principled analysis of how cellular states collectively shape organism-level phenotypes across development and disease.<\/jats:p>","DOI":"10.64898\/2026.04.20.717759","type":"posted-content","created":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:00:12Z","timestamp":1776927612000},"source":"Crossref","is-referenced-by-count":1,"title":["scVIP: personalized modeling of single-cell transcriptomes for developmental and disease phenotypes"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5783-3156","authenticated-orcid":false,"given":"Hsin-Yu","family":"Lai","sequence":"first","affiliation":[{"name":"Allen Institute, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yehchan","family":"Yoo","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0064-1791","authenticated-orcid":false,"given":"Andreas","family":"Tj\u00e4rnberg","sequence":"additional","affiliation":[{"name":"Allen Institute, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruoxin","family":"Li","sequence":"additional","affiliation":[{"name":"Allen Institute, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyuan","family":"He","sequence":"additional","affiliation":[{"name":"Allen Institute, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3164-6448","authenticated-orcid":false,"given":"Kyle J.","family":"Travaglini","sequence":"additional","affiliation":[{"name":"Allen Institute, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Qiao","sequence":"additional","affiliation":[{"name":"University of Kentucky, Lexington, KY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1213-2321","authenticated-orcid":false,"given":"Anamika","family":"Agrawal","sequence":"additional","affiliation":[{"name":"Allen Institute, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7772-4694","authenticated-orcid":false,"given":"Omar","family":"Kana","sequence":"additional","affiliation":[{"name":"Allen Institute, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5120-4546","authenticated-orcid":false,"given":"Cindy","family":"van Velthoven","sequence":"additional","affiliation":[{"name":"Allen Institute, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1711-8868","authenticated-orcid":false,"given":"Jeff","family":"Carroll","sequence":"additional","affiliation":[{"name":"Allen Institute, Seattle, WA, USA"},{"name":"University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Gillespie","sequence":"additional","affiliation":[{"name":"Allen Institute, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2522-2884","authenticated-orcid":false,"given":"Shubhabrata","family":"Mukherjee","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7207-4696","authenticated-orcid":false,"given":"David W.","family":"Fardo","sequence":"additional","affiliation":[{"name":"University of Kentucky, Lexington, KY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojun","family":"Li","sequence":"additional","affiliation":[{"name":"Allen Institute, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9012-6552","authenticated-orcid":false,"given":"Ed","family":"Lein","sequence":"additional","affiliation":[{"name":"Allen Institute, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6911-344X","authenticated-orcid":false,"given":"Mariano Ignacio","family":"Gabitto","sequence":"additional","affiliation":[{"name":"Allen Institute, Seattle, WA, USA"},{"name":"University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026063005401325000_2026.04.20.717759v2.1","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.2859"},{"key":"2026063005401325000_2026.04.20.717759v2.2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2015.05.002"},{"key":"2026063005401325000_2026.04.20.717759v2.3","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-25680-7"},{"key":"2026063005401325000_2026.04.20.717759v2.4","doi-asserted-by":"publisher","DOI":"10.1186\/s13059-015-0844-5"},{"key":"2026063005401325000_2026.04.20.717759v2.5","doi-asserted-by":"crossref","unstructured":"Litinetskaya, A. , Hediyeh-zadeh, S. , Moinfar, A. A. , Lotfollahi, M. & Theis, F. J. Weakly supervised learning uncovers phenotypic signatures in single-cell data. bioRxiv (2025). URL https:\/\/www.biorxiv.org\/content\/early\/2025\/12\/16\/2024.07.29.605625.","DOI":"10.1101\/2024.07.29.605625"},{"key":"2026063005401325000_2026.04.20.717759v2.6","doi-asserted-by":"publisher","DOI":"10.1038\/s44320-023-00003-8"},{"key":"2026063005401325000_2026.04.20.717759v2.7","unstructured":"Green, G. S. et al. Cellular dynamics across aged human brains uncover a multicellular cascade leading to alzheimer\u2019s disease. bioRxiv (2023). URL https:\/\/www.biorxiv.org\/content\/early\/2023\/03\/09\/2023.03.07.531493."},{"key":"2026063005401325000_2026.04.20.717759v2.8","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-024-01774-5"},{"key":"2026063005401325000_2026.04.20.717759v2.9","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1195-2"},{"key":"2026063005401325000_2026.04.20.717759v2.10","doi-asserted-by":"publisher","DOI":"10.1007\/BF00308809"},{"key":"2026063005401325000_2026.04.20.717759v2.11","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1016\/j.jalz.2018.02.018","article-title":"NIA-AA research framework: Toward a biological definition of Alzheimer\u2019s disease","volume":"14","year":"2018","journal-title":"Alzheimer\u2019s & Dementia"},{"key":"2026063005401325000_2026.04.20.717759v2.12","doi-asserted-by":"crossref","first-page":"e70404","DOI":"10.1002\/alz.70404","article-title":"An integrated view of the relationships between amyloid, tau, and inflammatory pathophysiology in alzheimer\u2019s disease","volume":"21","year":"2025","journal-title":"Alzheimer\u2019s & Dementia"},{"key":"2026063005401325000_2026.04.20.717759v2.13","doi-asserted-by":"crossref","first-page":"i96","DOI":"10.1093\/bioinformatics\/btaf241","article-title":"Incorporating hierarchical information into multiple instance learning for patient phenotype prediction with single-cell rna-sequencing data","volume":"41","year":"2025","journal-title":"Bioinformatics"},{"key":"2026063005401325000_2026.04.20.717759v2.14","doi-asserted-by":"crossref","first-page":"101570","DOI":"10.1016\/j.cels.2026.101570","article-title":"Learning multi-cellular representations of single-cell transcriptomics data enables characterization of patient-level disease states","volume":"17","year":"2026","journal-title":"Cell Systems"},{"key":"2026063005401325000_2026.04.20.717759v2.15","doi-asserted-by":"crossref","unstructured":"Pang, K. et al. Pulsar: a foundation model for multi-scale and multi-cellular biology. bioRxiv 2025.11.24.685470 (2025). Preprint.","DOI":"10.1101\/2025.11.24.685470"},{"key":"2026063005401325000_2026.04.20.717759v2.16","doi-asserted-by":"crossref","unstructured":"Jiang, L. et al. Reconstructing developmental and disease progression with sample-level embeddings. bioRxiv 2025.12.10.693462 (2025). Preprint.","DOI":"10.64898\/2025.12.10.693462"},{"key":"2026063005401325000_2026.04.20.717759v2.17","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-018-0229-21"},{"key":"2026063005401325000_2026.04.20.717759v2.18","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-021-01206-w"},{"key":"2026063005401325000_2026.04.20.717759v2.19","first-page":"1222","article-title":"Multivi: deep generative model for the integration of multimodal data","volume":"0","year":"2023","journal-title":"Nature Methods"},{"key":"2026063005401325000_2026.04.20.717759v2.20","year":"2018","journal-title":"Attention-based deep multiple instance learning"},{"key":"2026063005401325000_2026.04.20.717759v2.21","doi-asserted-by":"publisher","DOI":"10.1038\/nn1172"},{"key":"2026063005401325000_2026.04.20.717759v2.22","doi-asserted-by":"publisher","DOI":"10.1126\/science.aav2522"},{"key":"2026063005401325000_2026.04.20.717759v2.23","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09644-1"},{"key":"2026063005401325000_2026.04.20.717759v2.24","doi-asserted-by":"publisher","DOI":"10.1002\/ajmg.b.31232"},{"key":"2026063005401325000_2026.04.20.717759v2.25","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2024.11.038"},{"key":"2026063005401325000_2026.04.20.717759v2.26","doi-asserted-by":"publisher","DOI":"10.1038\/nn.3668"},{"key":"2026063005401325000_2026.04.20.717759v2.27","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.aaw8546"},{"key":"2026063005401325000_2026.04.20.717759v2.28","doi-asserted-by":"publisher","DOI":"10.1016\/j.nbd.2019.104646"},{"key":"2026063005401325000_2026.04.20.717759v2.29","doi-asserted-by":"publisher","DOI":"10.1006\/exnr.1999.7170"},{"key":"2026063005401325000_2026.04.20.717759v2.30","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02566-3"},{"key":"2026063005401325000_2026.04.20.717759v2.31","doi-asserted-by":"publisher","DOI":"10.1016\/j.freeradbiomed.2013.04.016"},{"key":"2026063005401325000_2026.04.20.717759v2.32","doi-asserted-by":"publisher","DOI":"10.1083\/jcb.201709069"},{"key":"2026063005401325000_2026.04.20.717759v2.33","unstructured":"Gillespie, M. A. et al. Progression to rheumatoid arthritis in at-risk individuals is defined by systemic inflammation and by T and B cell dysregulation. Science Translational Medicine 17 (2025)."},{"key":"2026063005401325000_2026.04.20.717759v2.34","unstructured":"Gong, Q. et al. Longitudinal multi-omic immune profiling reveals age-related immune cell dynamics in healthy adults. bioRxiv (2024)."},{"key":"2026063005401325000_2026.04.20.717759v2.35","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-27150-6"},{"key":"2026063005401325000_2026.04.20.717759v2.36","doi-asserted-by":"crossref","unstructured":"Shi, X. , Cao, W. & Raschka, S. Deep neural networks for rank-consistent ordinal regression based on conditional probabilities. Pattern Analysis and Applications 26 (2023).","DOI":"10.1007\/s10044-023-01181-9"},{"key":"2026063005401325000_2026.04.20.717759v2.37","doi-asserted-by":"publisher","DOI":"10.2307\/1909582"},{"key":"2026063005401325000_2026.04.20.717759v2.38","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4076(86)90002-3"},{"key":"2026063005401325000_2026.04.20.717759v2.39","doi-asserted-by":"publisher","DOI":"10.15252\/msb.20209620"},{"key":"2026063005401325000_2026.04.20.717759v2.40","doi-asserted-by":"publisher","DOI":"10.1561\/2200000056"},{"key":"2026063005401325000_2026.04.20.717759v2.41","unstructured":"Tj\u00e4rnberg, A. LSP-score (2025). URL https:\/\/github.com\/Xparx\/LSP-score."}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.04.20.717759","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T13:03:57Z","timestamp":1782824637000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.04.20.717759"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,22]]},"references-count":41,"URL":"https:\/\/doi.org\/10.64898\/2026.04.20.717759","relation":{},"subject":[],"published":{"date-parts":[[2026,4,22]]},"subtype":"preprint"}}