Grammars and reinforcement learning for molecule optimization
We seek to automate the design of molecules based on specific chemical properties. Our primary contributions are a simpler method for generating SMILES strings guaranteed to be chemically valid, using a combination of a new context-free grammar for SMILES and additional masking logic; and casting the molecular property optimization as a reinforcement learning problem, specifically best-of-batch policy gradient applied to a Transformer model architecture. This approach uses substantially fewer model steps per atom than earlier approaches, thus enabling generation of larger molecules, and beats previous state-of-the art baselines by a significant margin. Applying reinforcement learning to a combination of a custom context-free grammar with additional masking to enforce non-local constraints is applicable to any optimization of a graph structure under a mixture of local and nonlocal constraints.
Code (1)
Tasks
reinforcement-learningReinforcement LearningReinforcement Learning (RL)validMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Reinforced Molecular Optimization with Neighborhood-Controlled Grammars
A major challenge in the pharmaceutical industry is to design novel molecules with specific desired properties, especially when the property evaluation is costly. Here, we propose MNCE-RL, a graph convolutional policy ne…
Graph GenerationMolecular Graph GenerationProbabilistic hypergraph grammars for efficient molecular optimization
We present an approach to make molecular optimization more efficient. We infer a hypergraph replacement grammar from the ChEMBL database, count the frequencies of particular rules being used to expand particular nontermi…
GPUreinforcement-learningReinforcement LearningReinforcement Learning (RL)Deep learning for molecular design - a review of the state of the art
In the space of only a few years, deep generative modeling has revolutionized how we think of artificial creativity, yielding autonomous systems which produce original images, music, and text. Inspired by these successes…
Benchmarkingreinforcement-learningReinforcement LearningReinforcement Learning (RL)Representing Molecules as Random Walks Over Interpretable Grammars
Recent research in molecular discovery has primarily been devoted to small, drug-like molecules, leaving many similarly important applications in material design without adequate technology. These applications often rely…
Property PredictionOptimization of Molecules via Deep Reinforcement Learning
We present a framework, which we call Molecule Deep $Q$-Networks (MolDQN), for molecule optimization by combining domain knowledge of chemistry and state-of-the-art reinforcement learning techniques (double $Q$-learning …
Deep Reinforcement LearningMolecular Graph GenerationMulti-Objective Reinforcement LearningQ-Learning+3