Cover Image

Interpretation, extrapolation and perturbation of single cells

Single-cell analyses have transitioned from descriptive atlasing towards inferring causal effects and mechanistic relationships that capture cellular logic. Technological advances and the growing scale of observational and interventional datasets have fuelled the development of machine learning meth...

Full description

Saved in:
Bibliographic Details
Main Authors: Dimitrov, Daniel (Author) , Schrod, Stefan (Author) , Rohbeck, Martin (Author) , Stegle, Oliver (Author)
Format: Article (Journal)
Language:English
Published: 02 January 2026
In: Nature reviews. Genetics
Year: 2026, Pages: 1-22
ISSN:1471-0064
DOI:10.1038/s41576-025-00920-4
Online Access:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1038/s41576-025-00920-4
Verlag, lizenzpflichtig, Volltext: https://www.nature.com/articles/s41576-025-00920-4
Get full text
Author Notes:Daniel Dimitrov, Stefan Schrod, Martin Rohbeck & Oliver Stegle
Description
Summary:Single-cell analyses have transitioned from descriptive atlasing towards inferring causal effects and mechanistic relationships that capture cellular logic. Technological advances and the growing scale of observational and interventional datasets have fuelled the development of machine learning methods aimed at identifying such dependencies and extrapolating perturbation effects. Here, we review and connect these approaches according to their modelling concepts (including representation learning, causal inference, mechanistic discovery, disentanglement and population tracing), underlying assumptions and downstream tasks. We propose a unifying ontology to guide practitioners in selecting the most suitable methods for a given biological question, with detailed technical descriptions provided in an online resource. Finally, we identify promising computational directions and underexplored data properties that could pave the way for future developments.
Item Description:Veröffentlicht: 02. Januar 2026
Gesehen am 10.03.2026
Physical Description:Online Resource
ISSN:1471-0064
DOI:10.1038/s41576-025-00920-4

Similar Items