MorphoDiff: Cellular Morphology Painting with Diffusion Models
Zeinab Navidi, Jun Ma, Esteban Miglietta, Le Liu, Anne E Carpenter, Beth A Cimini, Benjamin Haibe-Kains, BO WANG
Abstract
Understanding cellular responses to external stimuli is critical for parsing biological mechanisms and advancing therapeutic development. High-content image-based assays provide a cost-effective approach to examine cellular phenotypes induced by diverse interventions, which offers valuable insights into biological processes and cellular states. We introduce MorphoDiff, a generative pipeline to predict high-resolution cell morphological responses under different conditions based on perturbation encoding. To the best of our knowledge, MorphoDiff is the first framework capable of producing guided, high-resolution predictions of cell morphology that generalize across both chemical and genetic interventions. The model integrates perturbation embeddings as guiding signals within a 2D latent diffusion model. The comprehensive computational, biological, and visual validations across three open-source Cell Painting datasets show that MorphoDiff can generate high-fidelity images and produce meaningful biology signals under various interventions. We envision the model will facilitate efficient in silico exploration of perturbational landscapes towards more effective drug discovery studies.
BibTeX
@inproceedings{
navidi2025morphodiff,
title={MorphoDiff: Cellular Morphology Painting with Diffusion Models},
author={Zeinab Navidi and Jun Ma and Esteban Miglietta and Le Liu and Anne E Carpenter and Beth A Cimini and Benjamin Haibe-Kains and BO WANG},
booktitle={The Thirteenth International Conference on Learning Representations},
year={2025},
url={https://openreview.net/forum?id=PstM8YfhvI}
}