用强化学习让虚拟细胞更符合生物规律，提升药物研发效率
CellFluxRL: Biologically-Constrained Virtual Cell Modeling via Reinforcement Learning
- 用强化学习优化虚拟细胞生成模型，引入七种生物相关奖励函数
- 在结构、形态和功能上均优于原模型，测试时缩放进一步提升性能
- 适合生物模拟、药物筛选领域研究者，推动生成结果从视觉真实转向生物可信
构建可模拟细胞行为的虚拟细胞生成模型，正成为加速药物发现的新兴范式。然而，以往基于图像的生成方法常产生违反基本物理与生物约束的不真实细胞图像。为此，我们提出对虚拟细胞模型进行强化学习后训练，利用具有生物学意义的评估器作为奖励函数。设计了涵盖生物功能、结构有效性与形态正确性的七项奖励，并优化了最先进的CellFlux模型，得到CellFluxRL。CellFluxRL在所有奖励上均持续优于原模型，且测试时缩放进一步提升表现。结果表明，该框架通过强化学习强制施加物理基础约束，使虚拟细胞生成从“视觉逼真”迈向“生物有意义”。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。