Global and local integrated gradient-based diffusion model for de novo drug design.

ABSTRACT: In de novo drug design, deep learning-based approaches have become essential to efficiently navigate the vast chemical space of drug-like molecules. Recently, diffusion-based models have attracted significant attention in the generation of target-binding molecules. However, these models have difficulty in simultaneously optimizing the binding affinity and drug-like properties and require high computational costs because of the long and sequential denoising process. To address these limitations, we propose the Global and local integrated gradient-based Diffusion Model (GlintDM). GlintDM introduces a significantly faster denoising process, namely skip transition, by leveraging global gradients and local gradients. Due to the fast denoising process, GlintDM can perform the following three pha

SUBMITTER: Park S 

PROVIDER: S-EPMC12874906 | biostudies-literature | 2026 Jan

REPOSITORIES: biostudies-literature