Manifold-Constrained Nucleus-Level Denoising Diffusion Model for Structure-Based Drug Design

TL;DR

NucleusDiff is a novel AI model for structure-based drug design that enforces physical distance constraints between atoms, significantly reducing violations and improving binding affinity compared to existing models.

Contribution

The paper introduces NucleusDiff, a manifold-constrained diffusion model that incorporates physical atom distance constraints to improve drug design accuracy.

Findings

Reduces separation violation rate by up to 100%

Enhances binding affinity by up to 22.16%

Outperforms state-of-the-art models in evaluations

Abstract

Artificial intelligence models have shown great potential in structure-based drug design, generating ligands with high binding affinities. However, existing models have often overlooked a crucial physical constraint: atoms must maintain a minimum pairwise distance to avoid separation violation, a phenomenon governed by the balance of attractive and repulsive forces. To mitigate such separation violations, we propose NucleusDiff. It models the interactions between atomic nuclei and their surrounding electron clouds by enforcing the distance constraint between the nuclei and manifolds. We quantitatively evaluate NucleusDiff using the CrossDocked2020 dataset and a COVID-19 therapeutic target, demonstrating that NucleusDiff reduces violation rate by up to 100.00% and enhances binding affinity by up to 22.16%, surpassing state-of-the-art models for structure-based drug design. We also provide qualitative analysis through manifold sampling, visually confirming the effectiveness of NucleusDiff in reducing separation violations and improving binding affinities.