Conditional Latent Space Molecular Scaffold Optimization for Accelerated Molecular Design

TL;DR

CLaSMO is a novel method combining CVAE and Bayesian Optimization to efficiently optimize molecular structures with high applicability and similarity constraints, advancing practical drug discovery.

Contribution

The paper introduces CLaSMO, a new framework that enhances molecular optimization by integrating conditional latent space modeling with Bayesian optimization for better efficiency and applicability.

Findings

CLaSMO achieves state-of-the-art performance across multiple molecular optimization tasks.

The method demonstrates high sample-efficiency, reducing resource requirements.

It maintains molecular similarity and synthetic accessibility in optimized molecules.

Abstract

The rapid discovery of new chemical compounds is essential for advancing global health and developing treatments. While generative models show promise in creating novel molecules, challenges remain in ensuring the real-world applicability of these molecules and finding such molecules efficiently. To address this challenge, we introduce Conditional Latent Space Molecular Scaffold Optimization (CLaSMO), which integrates a Conditional Variational Autoencoder (CVAE) with Latent Space Bayesian Optimization (LSBO) to strategically modify molecules while preserving similarity to the original input, effectively framing the task as constrained optimization. Our LSBO setting improves the sample-efficiency of the molecular optimization, and our modification approach helps us to obtain molecules with higher chances of real-world applicability. CLaSMO explores substructures of molecules in a sample-efficient manner by performing BO in the latent space of a CVAE conditioned on the atomic environment of the molecule to be optimized. Our extensive evaluations across diverse optimization tasks, including rediscovery, docking score, and multi-property optimization, show that CLaSMO efficiently enhances target properties, delivers remarkable sample-efficiency crucial for resource-limited applications while considering molecular similarity constraints, achieves state of the art performance, and maintains practical synthetic accessibility. We also provide an open-source web application that enables chemical experts to apply CLaSMO in a Human-in-the-Loop setting.