Leveraging Latent Evolutionary Optimization for Targeted Molecule Generation

TL;DR

This paper introduces LEOMol, a novel generative framework combining evolutionary algorithms and VAEs to efficiently generate optimized molecules with desired properties, outperforming existing models in drug lead optimization tasks.

Contribution

LEOMol is the first to integrate evolutionary algorithms with VAE latent space search for targeted molecule generation, demonstrating superior performance over prior methods.

Findings

LEOMol outperforms state-of-the-art models across multiple property targeting tasks.

Including toxicity in evaluation improves the relevance of generated molecules.

Ablation studies confirm the advantages of evolutionary search over gradient-based methods.

Abstract

Lead optimization is a pivotal task in the drug design phase within the drug discovery lifecycle. The primary objective is to refine the lead compound to meet specific molecular properties for progression to the subsequent phase of development. In this work, we present an innovative approach, Latent Evolutionary Optimization for Molecule Generation (LEOMol), a generative modeling framework for the efficient generation of optimized molecules. LEOMol leverages Evolutionary Algorithms, such as Genetic Algorithm and Differential Evolution, to search the latent space of a Variational AutoEncoder (VAE). This search facilitates the identification of the target molecule distribution within the latent space. Our approach consistently demonstrates superior performance compared to previous state-of-the-art models across a range of constrained molecule generation tasks, outperforming existing models in all four sub-tasks related to property targeting. Additionally, we suggest the importance of including toxicity in the evaluation of generative models. Furthermore, an ablation study underscores the improvements that our approach provides over gradient-based latent space optimization methods. This underscores the effectiveness and superiority of LEOMol in addressing the inherent challenges in constrained molecule generation while emphasizing its potential to propel advancements in drug discovery.