Guiding Evolutionary Molecular Design: Adding Reinforcement Learning for Mutation Selection
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningSimilar Papers 제목 키워드 기반
Can Molecular Evolution Mechanism Enhance Molecular Representation?
Molecular evolution is the process of simulating the natural evolution of molecules in chemical space to explore potential molecular structures and properties. The relationships between similar molecules are often descri…
Molecular Property Predictionmolecular representationProperty PredictionLearning to grow: control of material self-assembly using evolutionary reinforcement learning
We show that neural networks trained by evolutionary reinforcement learning can enact efficient molecular self-assembly protocols. Presented with molecular simulation trajectories, networks learn to change temperature an…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Deep Evolutionary Learning for Molecular Design
In this paper, we propose a deep evolutionary learning (DEL) process that integrates fragment-based deep generative model and multi-objective evolutionary computation for molecular design. Our approach enables (1) evolut…
Bayesian OptimizationMulti-Constrained Evolutionary Molecular Design Framework: An Interpretable Drug Design Method Combining Rule-Based Evolution and Molecular Crossover
This study proposes MCEMOL (Multi-Constrained Evolutionary Molecular Design Framework), a molecular optimization approach integrating rule-based evolution with molecular crossover. MCEMOL employs dual-layer evolution: op…
Drug DiscoveryDe Novo Molecular Design Enabled by Direct Preference Optimization and Curriculum Learning
De novo molecular design has extensive applications in drug discovery and materials science. The vast chemical space renders direct molecular searches computationally prohibitive, while traditional experimental screening…
Drug DiscoveryReinforcement Learning (RL)