CellFlux: Simulating Cellular Morphology Changes via Flow Matching

TL;DR

CellFlux is a novel image-generative model that accurately simulates cellular morphology changes under various perturbations, distinguishing true biological effects from experimental artifacts, and enabling continuous state interpolation for biomedical research.

Contribution

It introduces flow matching for distribution-wise transformation modeling, improving biological fidelity and artifact separation in cellular morphology simulation.

Findings

Achieves 35% better FID scores than previous methods.

Increases mode-of-action prediction accuracy by 12%.

Enables continuous interpolation between cellular states.

Abstract

Building a virtual cell capable of accurately simulating cellular behaviors in silico has long been a dream in computational biology. We introduce CellFlux, an image-generative model that simulates cellular morphology changes induced by chemical and genetic perturbations using flow matching. Unlike prior methods, CellFlux models distribution-wise transformations from unperturbed to perturbed cell states, effectively distinguishing actual perturbation effects from experimental artifacts such as batch effects -- a major challenge in biological data. Evaluated on chemical (BBBC021), genetic (RxRx1), and combined perturbation (JUMP) datasets, CellFlux generates biologically meaningful cell images that faithfully capture perturbation-specific morphological changes, achieving a 35% improvement in FID scores and a 12% increase in mode-of-action prediction accuracy over existing methods. Additionally, CellFlux enables continuous interpolation between cellular states, providing a potential tool for studying perturbation dynamics. These capabilities mark a significant step toward realizing virtual cell modeling for biomedical research. Project page: https://yuhui-zh15.github.io/CellFlux/.