Latent Chemical Space Searching for Plug-in Multi-objective Molecule Generation

TL;DR

This paper introduces a versatile plug-in molecular generation model utilizing an improved Particle Swarm Optimization method, enhancing multi-objective drug molecule design by integrating target affinity, drug-likeness, and synthesizability.

Contribution

The study develops a novel plug-in molecular generation framework with an optimized PSO variant and a new affinity predictor, advancing multi-objective drug discovery tools.

Findings

PSO-ENP identified as the best optimization variant.

The model effectively generates drug-like natural products.

Case studies demonstrate practical applicability in drug discovery.

Abstract

Molecular generation, an essential method for identifying new drug structures, has been supported by advancements in machine learning and computational technology. However, challenges remain in multi-objective generation, model adaptability, and practical application in drug discovery. In this study, we developed a versatile 'plug-in' molecular generation model that incorporates multiple objectives related to target affinity, drug-likeness, and synthesizability, facilitating its application in various drug development contexts. We improved the Particle Swarm Optimization (PSO) in the context of drug discoveries, and identified PSO-ENP as the optimal variant for multi-objective molecular generation and optimization through comparative experiments. The model also incorporates a novel target-ligand affinity predictor, enhancing the model's utility by supporting three-dimensional information and improving synthetic feasibility. Case studies focused on generating and optimizing drug-like big marine natural products were performed, underscoring PSO-ENP's effectiveness and demonstrating its considerable potential for practical drug discovery applications.