Learning collective multicellular dynamics with an interacting mean field neural SDE model
PLOS Computational Biology · 21.01.2026 · 22 (1) · e1013916
DOI: 10.1371/journal.pcbi.1013916 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Computational Biology, online erschienen am 21.01.2026. Verfasst von Qi Jiang und 3 weiteren Autor:innen. Beteiligte Einrichtung: State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China. Hauptthemen laut MEDLINE: Cell Communication, Models, Biological, Neural Networks, Computer. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, Strategic Priority Research Program of the Chinese Academy of Sciences.
Abstract (Originalsprache)
The advent of temporal single-cell RNA sequencing (scRNA-seq) data has enabled in-depth investigation of dynamic processes in heterogeneous multicellular systems. Despite remarkable advancements in computational methods for modeling cellular dynamics, integrating cell-cell interactions (CCIs) into these models remains a major challenge. This is particularly true when dealing with high-dimensional gene expression profiles from large populations of interacting cells, where the intricate interplay between cells can be obscured by data complexity. To address this, we present scIMF, a single-cell deep-generative Interacting Mean Field model that learns collective multicellular dynamics. Leveraging the McKean-Vlasov stochastic differential equation framework, scIMF provides a mathematical foundation for describing interacting multicellular systems, where each cell’s evolution depends on the population’s empirical distribution. By incorporating a cell-wise attention mechanism, the model efficiently captures nonlocal and asymmetric CCIs, enabling realistic reconstruction of complex intercellular relationships in high-dimensional spaces. Benchmarking across diverse temporal scRNA-seq datasets demonstrates that scIMF outperforms state-of-the-art methods in reconstructing gene expression at unobserved time points and in inferring cellular velocities. Furthermore, scIMF uncovers biologically interpretable, non-reciprocal interaction patterns of cells, providing a principled framework for studying complex, particularly non-equilibrium biological systems.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China.
- School of Mathematical Sciences, University of Chinese Academy of Sciences, Beijing, China.
- School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences, Beijing, China.
- Department of Control Science and Engineering, Tongji University, Shanghai, China.
ORCID-Profile: Lin Wan
Förderung
- National Key Research and Development Program of China
- Strategic Priority Research Program of the Chinese Academy of Sciences
Zitieren
APA
Jiang, Q., Li, L., Zhang, L., & Wan, L. (2026). Learning collective multicellular dynamics with an interacting mean field neural SDE model. PLOS Computational Biology, 22(1), e1013916. https://doi.org/10.1371/journal.pcbi.1013916
Vancouver
Jiang Q, Li L, Zhang L, Wan L. Learning collective multicellular dynamics with an interacting mean field neural SDE model. PLOS Computational Biology. 2026;22(1):e1013916. doi:10.1371/journal.pcbi.1013916
BibTeX
@article{Jiang2026,
author = {Jiang, Qi and Li, Longquan and Zhang, Lei and Wan, Lin},
title = {Learning collective multicellular dynamics with an interacting mean field neural SDE model},
journal = {PLOS Computational Biology},
year = {2026},
volume = {22},
number = {1},
pages = {e1013916},
doi = {10.1371/journal.pcbi.1013916}
}
EUVIMED