Pith. sign in

REVIEW 1 cited by

Grammars and reinforcement learning for molecule optimization

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1811.11222 v1 pith:DOXWWCYF submitted 2018-11-27 cs.LG physics.chem-phstat.ML

classification cs.LGphysics.chem-phstat.ML
keywords learningoptimizationreinforcementadditionalcombinationconstraintscontext-freegrammar
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Efficient design of rna sequences with desired properties, structure, and motifs using a grammar variational autoencoder

    q-bio.QM 2025-07 reject novelty 3.0 of 10

    RGVAE, a stochastic-context-free-grammar VAE for RNA, can generate sequences satisfying design constraints, but the claimed outperformance over baselines is not convincingly demonstrated.

Pith tools