Guided Multi-objective Generative AI to Enhance Structure-based Drug Design
Abstract
Generative AI has the potential to revolutionize drug discovery. Yet, despite recent advances in deep learning, existing models cannot generate molecules that satisfy all desired physicochemical properties. Herein, we describe IDOLpro, a generative chemistry AI combining diffusion with multi-objective optimization for structure-based drug design. Differentiable scoring functions guide the latent variables of the diffusion model to explore uncharted chemical space and generate novel ligands in silico, optimizing a plurality of target physicochemical properties. We demonstrate our platform's effectiveness by generating ligands with optimized binding affinity and synthetic accessibility on two benchmark sets. IDOLpro produces ligands with binding affinities over 10%-20% better than the next best state-of-the-art method on each test set, producing more drug-like molecules with generally better synthetic accessibility scores than other methods. We do a head-to-head comparison of IDOLpro against a classic virtual screen of a large database of drug-like molecules. We show that IDOLpro can generate molecules for a range of important disease-related targets with better binding affinity and synthetic accessibility than any molecule found in the virtual screen while being over 100x faster and less expensive to run. On a test set of experimental complexes, IDOLpro is the first to produce molecules with better binding affinities than experimentally observed ligands. IDOLpro can accommodate other scoring functions (e.g. ADME-Tox) to accelerate hit-finding, hit-to-lead, and lead optimization for drug discovery.
AI-Generated Overview
Here's a brief overview of the provided text from the scientific paper with the requested bullet points:
-
Research Focus: The paper presents IDOLpro, a novel generative AI framework aimed at enhancing structure-based drug design by generating novel ligands that optimize multiple desired physicochemical properties, such as binding affinity and synthetic accessibility.
-
Methodology: IDOLpro integrates a generative model based on diffusion and employs multi-objective optimization by using differentiable scoring functions to explore chemical space and produce drug-like molecules. It iteratively modifies latent vectors to maximize target properties.
-
Results: IDOLpro demonstrated superior performance, producing ligands with 10%-20% higher binding affinities and better synthetic accessibility scores than existing state-of-the-art methods. It significantly outperformed traditional virtual screening, achieving improvements in both speed and cost-effectiveness.
-
Key Contribution(s): The framework is notable for its ability to co-optimize multiple objectives in ligand design and for generating high-quality ligands that surpass both existing ML models and experimentally validated reference molecules.
-
Significance: IDOLpro represents a significant advancement in the field of computational drug discovery, providing a faster, less costly, and more effective approach for the identification of promising drug candidates compared to conventional methods.
-
Broader Applications: The tool has broad potential applications, not only in drug discovery but also in materials science, where similar inverse design problems exist. It can be adapted to optimize other properties important in drug development, such as toxicity and solubility.