pith. sign in

arxiv: 1811.11222 · v1 · pith:DOXWWCYFnew · submitted 2018-11-27 · 💻 cs.LG · physics.chem-ph· stat.ML

Grammars and reinforcement learning for molecule optimization

classification 💻 cs.LG physics.chem-phstat.ML
keywords learningoptimizationreinforcementadditionalcombinationconstraintscontext-freegrammar
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.