CellFluxRL: Biologically-Constrained Virtual Cell Modeling via Reinforcement Learning
This work addresses the issue of biologically unrealistic virtual cells for drug discovery applications, representing an incremental advancement in the field.
The paper tackles the problem of generating implausible virtual cell images by post-training a state-of-the-art model with reinforcement learning using biologically meaningful rewards, resulting in consistent improvements across all reward categories.
Building virtual cells with generative models to simulate cellular behavior in silico is emerging as a promising paradigm for accelerating drug discovery. However, prior image-based generative approaches can produce implausible cell images that violate basic physical and biological constraints. To address this, we propose to post-train virtual cell models with reinforcement learning (RL), leveraging biologically meaningful evaluators as reward functions. We design seven rewards spanning three categories-biological function, structural validity, and morphological correctness-and optimize the state-of-the-art CellFlux model to yield CellFluxRL. CellFluxRL consistently improves over CellFlux across all rewards, with further performance boosts from test-time scaling. Overall, our results present a virtual cell modeling framework that enforces physically-based constraints through RL, advancing beyond "visually realistic" generations towards "biologically meaningful" ones.