Guided Multi-objective Generative AI to Enhance Structure-based Drug Design

2024-05-20

arXiv.org

AI Summary

Current generative AI models struggle to simultaneously satisfy multiple physicochemical property constraints, limiting their practical utility in structure-based drug design. To address this, we propose IDOLpro—the first framework that end-to-end couples diffusion-based molecular generation with multi-objective differentiable optimization. IDOLpro jointly models binding affinity, synthetic accessibility (SA), and ADME-Tox properties via differentiable scoring functions, enabling gradient-guided, targeted exploration of the latent space. In dual benchmark evaluations, IDOLpro achieves 10–20% improvement in predicted binding affinity and significantly outperforms baselines in SA. Compared to conventional virtual screening, it accelerates lead identification by 100× while substantially reducing computational cost. Most notably, in real experimental protein–ligand complex systems, IDOLpro is the first method to generate novel molecules exhibiting superior activity over known co-crystallized ligands—thereby breaking a longstanding performance bottleneck in de novo drug design.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Natural Language Processing: Generation
• Humans and AI: Game Design — Procedural Content Generation & Storytelling

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

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.

Problem

• Generating molecules with optimized physicochemical properties
• Improving binding affinity and synthetic accessibility
• Accelerating drug discovery with multi-objective AI

Innovation

• Combines diffusion with multi-objective optimization
• Uses differentiable scoring functions for chemical exploration
• Generates ligands with optimized binding and synthetic accessibility