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.
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.
Click to jump to each section.
Our method represents a significant advancement in computational biology, providing researchers with powerful tools for virtual cell modeling, drug discovery, and understanding cellular dynamics. The open-source implementation enables the community to build upon this work and accelerate progress in this field.
Our method aims to predict changes in cell morphology induced by chemical or gene perturbations in silico. The approach addresses the fundamental challenge of distinguishing true biological effects from experimental artifacts through innovative distribution-to-distribution modeling.
Key components of CellFlux include:
Our key innovation lies in formulating cellular morphology prediction as a distribution-to-distribution learning problem. Traditional methods often ignore control cells or treat perturbation prediction as a simple image-to-image translation. In contrast, our approach recognizes that:
This approach enables our method to generate more accurate and biologically meaningful cellular responses while maintaining robustness across diverse experimental conditions.
Our method leverages flow matching to learn continuous transformations between cellular states. The algorithm is designed to handle the complexity of biological data while maintaining computational efficiency.
During training, our model learns a velocity field by fitting trajectories between control cell images (x₀ ~ p₀) and perturbed cell images (x₁ ~ p₁). At each training step, intermediate states are sampled along linear interpolations, and the network minimizes the difference between predicted and true velocities.
At inference, the trained velocity field guides the transformation of control cell states into perturbed states by solving an ordinary differential equation iteratively using numerical integration steps.
Key Technical Components include:
Our method achieves superior performance across multiple cellular imaging datasets, demonstrating significant improvements in both image generation quality and biological relevance.
Our results demonstrate significant improvements:
Our method unlocks unprecedented capabilities that advance the field toward a true virtual cell, enabling researchers to study cellular dynamics in ways previously impossible.
Key capabilities include:
These capabilities significantly advance our understanding of cellular behavior and provide powerful tools for drug discovery and personalized therapy development.
Our method represents a significant advancement in computational biology, providing researchers with powerful tools for virtual cell modeling, drug discovery, and understanding cellular dynamics. The distribution-to-distribution approach addresses fundamental challenges in biological data analysis, while flow matching enables unprecedented capabilities in cellular morphology simulation. We hope our work will strengthen the computational biology community and accelerate progress toward truly predictive virtual cell models.
@inproceedings{CellFlux,
title={{CellFlux: Simulating Cellular Morphology Changes via Flow Matching}},
author={Zhang, Yuhui and Su, Yuchang and Wang, Chenyu and Li, Tianhong and Wefers, Zoe and Nirschl, Jeffrey and Burgess, James and Ding, Daisy and Lozano, Alejandro and Lundberg, Emma and Yeung-Levy, Serena},
booktitle={International Conference on Machine Learning (ICML)},
year={2025}
}