Problem
Research questions and friction points this paper is trying to address.
Cellular perturbation prediction
Continuous dose control
Generative modeling
Dose-conditioned cell morphing
Joint Flow Matching Enables Continuous Dose-Conditioned Cell Morphing
🤖 AI Summary
This study addresses the limitations of existing cellular perturbation prediction methods in achieving continuous dose control and morphological transformation. We propose a dual-time-step joint flow matching framework that simultaneously models cellular latent variables and drug concentrations. Leveraging the invertibility of flow matching, this approach enables single-cell morphology generation under continuous dosing and inverse estimation of concentrations from observed morphologies. Experimental results demonstrate that the proposed model matches or exceeds baseline performance on two compounds and successfully generalizes to unseen doses. Consequently, this work provides an effective generative solution for modeling continuous drug responses, bridging the gap between discrete experimental observations and continuous pharmacological dynamics in single-cell perturbation studies.
📝 Abstract
Generative modeling has shown increasing promise for predicting cellular perturbation effects under chemical compound treatments. Existing approaches either model perturbation as a distribution-to-distribution mapping without explicit concentration handling, or treat concentration as a discrete class label, precluding continuous dose control. We introduce a joint flow matching approach that simultaneously models cell latents and drug concentration via a dual-timestep formulation, enabling dose-conditioned single-cell morphing through the invertibility of flow matching. The joint formulation induces a monotonic dose-response geometry in latent space and additionally supports concentration estimation from cell morphology. As proof of concept, we further demonstrate generalization to an unseen dose held out during training. Empirically, our method achieves competitive or improved per-concentration metrics on two compounds compared with representative baselines, while enabling capabilities structurally unavailable to discrete-class methods.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Joint Flow Matching
Continuous Dose Conditioning
Dual-timestep Formulation
Monotonic Dose-response Geometry
Single-cell Morphing
🔎 Similar Papers
No similar papers found.
