Knowledge-guided diffusion model for 3D ligand-pharmacophore mapping
Jun-Lin Yu, Zhou Cong, Xiang-Li Ning, Jun Mou, Fanbo Meng, Jing-Wei Wu, Yi-Ting Chen, Biao-Dan Tang, X.F. Liu, Guo‐Bo Li · Nature Communications · 2025
Pharmacophores are abstractions of essential chemical interaction patterns, holding an irreplaceable position in drug discovery. Despite the availability of many pharmacophore tools, the adoption of deep learning for pharmacophore-guided drug discovery remains relatively rare. We herein propose a knowledge-guided diffusion framework for ‘on-the-fly’ 3D ligand-pharmacophore mapping, named DiffPhore. It leverages ligand-pharmacophore matching knowledge to guide ligand conformation generation, meanwhile utilizing calibrated sampling to mitigate the exposure bias of the iterative conformation search process. By training on two self-established datasets of 3D ligand-pharmacophore pairs, DiffPhore achieves state-of-the-art performance in predicting ligand binding conformations, surpassing traditional pharmacophore tools and several advanced docking methods. It also manifests superior virtual screening power for lead discovery and target fishing. Using DiffPhore, we successfully identify structurally distinct inhibitors for human glutaminyl cyclases, and their binding modes are further validated through co-crystallographic analysis. We believe this work will advance the AI-enabled pharmacophore-guided drug discovery techniques. The authors develop a deep learning framework for 3D ligand pharmacophore mapping, enabling binding pose prediction, lead discovery, and target fishing. Using this approach, they identify structurally different inhibitors for human glutaminyl cyclases.