用强化学习提升分子进化算法的突变选择能力
Guiding Evolutionary Molecular Design: Adding Reinforcement Learning for Mutation Selection
- 基于局部结构上下文和ECFP指纹学习突变策略
- 生成分子更真实，结构错误减少，优化效果更好
- 适合药物设计与分子生成研究者参考
高效探索化学空间仍是核心挑战，许多生成模型仍会产生不稳定或不可合成的化合物。为此，我们提出EvoMol-RL，这是对进化算法EvoMol的重要扩展，通过引入强化学习，根据局部结构上下文指导分子突变。利用扩展连接指纹（ECFPs），EvoMol-RL学习上下文感知的突变策略，优先选择化学上合理的转化。该方法显著提升了生成分子的有效性和真实性，减少了结构缺陷，增强了优化性能。结果表明，EvoMol-RL在分子预筛选真实性方面持续优于基线模型。这证明了将强化学习与分子指纹结合在生成化学相关分子结构方面的有效性。
原文摘要 · Abstract (English)
The efficient exploration of chemical space remains a central challenge, as many generative models still produce unstable or non-synthesizable compounds. To address these limitations, we present EvoMol-RL, a significant extension of the EvoMol evolutionary algorithm that integrates reinforcement learning to guide molecular mutations based on local structural context. By leveraging Extended Connectivity Fingerprints (ECFPs), EvoMol-RL learns context-aware mutation policies that prioritize chemically plausible transformations. This approach significantly improves the generation of valid and realistic molecules, reducing the frequency of structural artifacts and enhancing optimization performance. The results demonstrate that EvoMol-RL consistently outperforms its baseline in molecular pre-filtering realism. These results emphasize the effectiveness of combining reinforcement learning with molecular fingerprints to generate chemically relevant molecular structures.
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。