Learning multi-cellular representations of single-cell transcriptomics data enables characterization of patient-level disease states
Cell Systems · 2026-05 · 17 (5) · 101570
DOI: 10.1016/j.cels.2026.101570 ↗Kurz gefasst
Fachartikel in der Zeitschrift Cell Systems, 2026-05. Verfasst von Tianyu Liu und 12 weiteren Autor:innen. Beteiligte Einrichtung: Research & Early Development, Genentech, South San Francisco, CA 94080, USA; Interdepartmental Program in Computational Biology & Bioinformatics, Yal…. Hauptthemen laut MEDLINE: Single-Cell Analysis, Transcriptome. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Genentech.
Abstract (Originalsprache)
Single-cell RNA sequencing (scRNA-seq) is a prominent tool for studying human disease biology. The availability of massive scRNA-seq datasets and advanced machine learning has driven the development of single-cell foundation models that provide versatile cell representations based on expression. To understand disease states, we need to account for entire tissue ecosystems, simultaneously considering many different interacting cells. Here, we tackle this challenge by generating patient-level representations derived from multi-cellular expression contexts measured with scRNA-seq of tissues. We develop PaSCient, a machine learning model that employs a multi-level representation learning paradigm and provides importance scores at the cell and gene levels for fine-grained analysis of disease characteristics. We apply PaSCient to a large-scale scRNA-seq atlas of 12.5 million cells from over 2,700 patients. Comprehensive benchmarking demonstrates the superiority of PaSCient in disease classification and multiple downstream applications, including dimensionality reduction, feature prioritization, and patient subgroup discovery.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Research & Early Development, Genentech, South San Francisco, CA 94080, USA; Interdepartmental Program in Computational Biology & Bioinformatics, Yale University, New Haven, CT 06511, USA.
- Research & Early Development, Genentech, South San Francisco, CA 94080, USA.
- Research & Early Development, Genentech, South San Francisco, CA 94080, USA; Roche Informatics, F. Hoffmann-La Roche Ltd., Mississauga, ON, Canada.
- Research & Early Development, Genentech, South San Francisco, CA 94080, USA; Department of Computer Science, Stanford University, Palo Alto, CA 94035, USA.
- Research & Early Development, Genentech, South San Francisco, CA 94080, USA; MOE Key Laboratory of Bioinformatics and Bioinformatics Division, BNRIST, Department of Automation, Tsinghua University, Beijing, China.
- Research & Early Development, Genentech, South San Francisco, CA 94080, USA. Electronic address: scaliag@gene.com.
Förderung
- Genentech
Zitieren
APA
Liu, T., De Brouwer, E., Verma, A., Missarova, A., Kuo, T., Diamant, N., Wang, H., Hao, M., Biancalani, T., Bravo, H. C., Scalia, G., Regev, A., & Heimberg, G. (2026). Learning multi-cellular representations of single-cell transcriptomics data enables characterization of patient-level disease states. Cell Systems, 17(5), 101570. https://doi.org/10.1016/j.cels.2026.101570
Vancouver
Liu T, De Brouwer E, Verma A, Missarova A, Kuo T, Diamant N, et al. Learning multi-cellular representations of single-cell transcriptomics data enables characterization of patient-level disease states. Cell Systems. 2026;17(5):101570. doi:10.1016/j.cels.2026.101570
BibTeX
@article{Liu2026,
author = {Liu, Tianyu and De Brouwer, Edward and Verma, Archit and Missarova, Alsu and Kuo, Tony and Diamant, Nathaniel and Wang, Hanchen and Hao, Minsheng and Biancalani, Tommaso and Bravo, Hector Corrada and Scalia, Gabriele and Regev, Aviv and Heimberg, Graham},
title = {Learning multi-cellular representations of single-cell transcriptomics data enables characterization of patient-level disease states},
journal = {Cell Systems},
year = {2026},
volume = {17},
number = {5},
pages = {101570},
doi = {10.1016/j.cels.2026.101570}
}
EUVIMED