CellFlux: Simulating Cellular Morphology Changes via Flow Matching

Yuhui Zhang, Yuchang Su, Chenyu Wang, Tianhong Li, Zoe Wefers, Jeffrey J Nirschl, James Burgess, Daisy Ding, Alejandro Lozano, Emma Lundberg, Serena Yeung-Levy
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:76111-76138, 2025.

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/.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-zhang25bt, title = {{C}ell{F}lux: 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 J and Burgess, James and Ding, Daisy and Lozano, Alejandro and Lundberg, Emma and Yeung-Levy, Serena}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {76111--76138}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/zhang25bt/zhang25bt.pdf}, url = {https://proceedings.mlr.press/v267/zhang25bt.html}, 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/.} }
Endnote
%0 Conference Paper %T CellFlux: Simulating Cellular Morphology Changes via Flow Matching %A Yuhui Zhang %A Yuchang Su %A Chenyu Wang %A Tianhong Li %A Zoe Wefers %A Jeffrey J Nirschl %A James Burgess %A Daisy Ding %A Alejandro Lozano %A Emma Lundberg %A Serena Yeung-Levy %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-zhang25bt %I PMLR %P 76111--76138 %U https://proceedings.mlr.press/v267/zhang25bt.html %V 267 %X 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/.
APA
Zhang, Y., Su, Y., Wang, C., Li, T., Wefers, Z., Nirschl, J.J., Burgess, J., Ding, D., Lozano, A., Lundberg, E. & Yeung-Levy, S.. (2025). CellFlux: Simulating Cellular Morphology Changes via Flow Matching. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:76111-76138 Available from https://proceedings.mlr.press/v267/zhang25bt.html.

Related Material