Human-level molecular optimization driven by mol-gene evolution

TL;DR

This paper presents DGMM, a novel deep learning-based genetic algorithm that encodes molecules as mol-gene to optimize drug-like compounds while balancing structural novelty and pharmacological properties.

Contribution

Introduces DGMM, combining D-VAE and genetic algorithms for flexible, structure-level molecular optimization akin to medicinal chemists' work.

Findings

DGMM effectively discovers pharmacologically similar, structurally distinct compounds.

DGMM reveals trade-offs in structural optimization during drug discovery.

Demonstrates success in multiple molecular optimization applications.

Abstract

De novo molecule generation allows the search for more drug-like hits across a vast chemical space. However, lead optimization is still required, and the process of optimizing molecular structures faces the challenge of balancing structural novelty with pharmacological properties. This study introduces the Deep Genetic Molecular Modification Algorithm (DGMM), which brings structure modification to the level of medicinal chemists. A discrete variational autoencoder (D-VAE) is used in DGMM to encode molecules as quantization code, mol-gene, which incorporates deep learning into genetic algorithms for flexible structural optimization. The mol-gene allows for the discovery of pharmacologically similar but structurally distinct compounds, and reveals the trade-offs of structural optimization in drug discovery. We demonstrate the effectiveness of the DGMM in several applications.