PuSH - Publikationsserver des Helmholtz Zentrums München

Bahrami, M. ; Richter, T. ; Schmacke, N.A. ; Egea Lavandera, A. ; Theis, F.J.

From modality-specific to compositional foundation models for cell biology.

Cell Syst. 17:101534 (2026)
DOI PMC
Deriving principles governing cell biology from single-cell measurements across modalities, called multimodal modeling, can advance our understanding of cellular states in health and disease. Realizing the full potential of multimodal models requires learning generalizable representations across data types, diseases, and biological contexts. This perspective examines the potential of compositional AI as a modular design approach for constructing multimodal foundation models that unify biological modalities-such as chromatin accessibility, protein abundance, spatial transcriptomics, microscopy imaging, and textual annotations-into cohesive representations of cellular behavior. We present key deep learning modeling approaches, along with transformer-based attention strategies to implement them, while addressing challenges posed by limited data availability and structural differences between modality representations. We also discuss how to connect and align partially overlapping multimodal measurements to build a comprehensive representation space. By synthesizing these technical advancements, we chart a path toward agentic virtual cell models, offering insights into opportunities, limitations, and future directions for leveraging multimodal AI to decode the complexity of cellular systems.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Journalartikel
Dokumenttyp Review
Schlagwörter Compositional Ai ; Single-cell Foundation Models ; Single-cell Multi-omics; Gene-expression; Single; Omics; Genome; Seq; Rna; Chromatin
ISSN (print) / ISBN 2405-4712
e-ISSN 2405-4720
Zeitschrift Cell Systems
Quellenangaben Band: 17, Heft: 2, Seiten: , Artikelnummer: 101534 Supplement: ,
Verlag Elsevier
Verlagsort Maryland Heights, MO
Institut(e) Institute of Computational Biology (ICB)
Förderungen European Union (ERC)
Add-On Fellowship of the Joachim Herz Foundation
Helmholtz Association under the joint research school "Munich School for Data Science"