3D-EDiffMG: 3D equivariant diffusion-driven molecular generation to accelerate drug discovery
Journal of Pharmaceutical Analysis · 2025-06 · 15 (6) · 101257
DOI: 10.1016/j.jpha.2025.101257 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Pharmaceutical Analysis, 2025-06. Verfasst von Chao Xu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Tropical Biological Resources of Ministry of Education, School of Pharmaceutical Sciences, Hainan University, Haikou, 570228, China. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Natural Science Foundation of Guangzhou Municipality, National Natural Science Foundation of China, National Key Research and Development Program of China.
Abstract (Originalsprache)
Structural optimization of lead compounds is a crucial step in drug discovery. One optimization strategy is to modify the molecular structure of a scaffold to improve both its biological activities and absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties. One of the deep molecular generative model approaches preserves the scaffold while generating drug-like molecules, thereby accelerating the molecular optimization process. Deep molecular diffusion generative models simulate a gradual process that creates novel, chemically feasible molecules from noise. However, the existing models lack direct interatomic constraint features and struggle with capturing long-range dependencies in macromolecules, leading to challenges in modifying the scaffold-based molecular structures, and creates limitations in the stability and diversity of the generated molecules. To address these challenges, we propose a deep molecular diffusion generative model, the three-dimensional (3D) equivariant diffusion-driven molecular generation (3D-EDiffMG) model. The dual strong and weak atomic interaction force-based long-range dependency capturing equivariant encoder (dual-SWLEE) is introduced to encode both the bonding and non-bonding information based on strong and weak atomic interactions. Additionally, a gate multilayer perceptron (gMLP) block with tiny attention is incorporated to explicitly model complex long-sequence feature interactions and long-range dependencies. The experimental results show that 3D-EDiffMG effectively generates unique, novel, stable, and diverse drug-like molecules, highlighting its potential for lead optimization and accelerating drug discovery.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Key Laboratory of Tropical Biological Resources of Ministry of Education, School of Pharmaceutical Sciences, Hainan University, Haikou, 570228, China.
- School of Pharmaceutical Sciences, Sun Yat-Sen University, Guangzhou, 510000, China.
Förderung
- Natural Science Foundation of Guangzhou Municipality
- National Natural Science Foundation of China
- National Key Research and Development Program of China
Zitieren
APA
Xu, C., Liu, R., Yao, Y., Huang, W., Li, Z., & Luo, H. B. (2025). 3D-EDiffMG: 3D equivariant diffusion-driven molecular generation to accelerate drug discovery. Journal of Pharmaceutical Analysis, 15(6), 101257. https://doi.org/10.1016/j.jpha.2025.101257
Vancouver
Xu C, Liu R, Yao Y, Huang W, Li Z, Luo HB. 3D-EDiffMG: 3D equivariant diffusion-driven molecular generation to accelerate drug discovery. Journal of Pharmaceutical Analysis. 2025;15(6):101257. doi:10.1016/j.jpha.2025.101257
BibTeX
@article{Xu2025,
author = {Xu, Chao and Liu, Runduo and Yao, Yufen and Huang, Wanyi and Li, Zhe and Luo, Hai-Bin},
title = {3D-EDiffMG: 3D equivariant diffusion-driven molecular generation to accelerate drug discovery},
journal = {Journal of Pharmaceutical Analysis},
year = {2025},
volume = {15},
number = {6},
pages = {101257},
doi = {10.1016/j.jpha.2025.101257}
}
EUVIMED