Deep reinforcement learning as an interaction agent to steer fragment-based 3D molecular generation for protein pockets
Briefings in Bioinformatics · 2025
DOI: 10.1093/bib/bbae531 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Xudong Zhang und 8 weiteren Autor:innen. Beteiligte Einrichtung: Shanghai Key Laboratory of Maternal Fetal Medicine, Clinical and Translational Research Center of Shanghai First Maternity and Infant Hospital, Schoo…. Hauptthemen laut MEDLINE: Deep Learning, Proteins. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, Shanghai Rising Star Program.
Abstract (Originalsprache)
Designing high-affinity molecules for protein targets (especially novel protein families) is a crucial yet challenging task in drug discovery. Recently, there has been tremendous progress in structure-based 3D molecular generative models that incorporate structural information of protein pockets. However, the capacity for molecular representation learning and the generalization for capturing interaction patterns need substantial further developments. Here, we propose AMG, a framework that leverages deep reinforcement learning as a pocket–ligand interaction agent (IA) to gradually steer fragment-based 3D molecular generation targeting protein pockets. AMG is trained using a two-stage strategy to capture interaction features and explicitly optimize the IA. The framework also introduces a pair of separate encoders for pockets and ligands, coupled with a dedicated pre-training strategy. This enables AMG to enhance its generalization ability by leveraging a vast repository of undocked pockets and molecules, thus mitigating the constraints posed by the limited quantity and quality of available datasets. Extensive evaluations demonstrate that AMG significantly outperforms five state-of-the-art baselines in affinity performance while maintaining proper drug-likeness properties. Furthermore, visual analysis confirms the superiority of AMG at capturing 3D molecular geometrical features and interaction patterns within pocket–ligand complexes, indicating its considerable promise for various structure-based downstream tasks.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Shanghai Key Laboratory of Maternal Fetal Medicine, Clinical and Translational Research Center of Shanghai First Maternity and Infant Hospital, School of Computer Science and Technology, Tongji University, Shanghai 2000…
- School of Computer Science and Technology, Tongji University, Shanghai 200092, China.
- School of Chemical Science and Engineering, Tongji University, Shanghai 200092, China.
- School of Computation, Information and Technology, Technical University of Munich, 85748, Garching b. München.
- Shanghai Key Laboratory of Maternal Fetal Medicine, Clinical and Translational Research Center of Shanghai First Maternity and Infant Hospital, Frontier Science Center for Stem Cell Research, School of Life Sciences and…
Förderung
- National Natural Science Foundation of China
- National Key Research and Development Program of China
- Shanghai Rising Star Program
- Xiaomi Young Talents Program and the European Union' s Horizon 2020 Framework Programme for Research and Innovation
Zitieren
APA
Zhang, X., Hou, J., Qu, S., Lu, F., Tian, Z., Knoll, A., Chen, G., Gao, S., & Zhang, Y. (2025). Deep reinforcement learning as an interaction agent to steer fragment-based 3D molecular generation for protein pockets. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbae531
Vancouver
Zhang X, Hou J, Qu S, Lu F, Tian Z, Knoll A, et al. Deep reinforcement learning as an interaction agent to steer fragment-based 3D molecular generation for protein pockets. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbae531
BibTeX
@article{Zhang2025,
author = {Zhang, Xudong and Hou, Jing and Qu, Sanqing and Lu, Fan and Tian, Zhixin and Knoll, Alois and Chen, Guang and Gao, Shaorong and Zhang, Yanping},
title = {Deep reinforcement learning as an interaction agent to steer fragment-based 3D molecular generation for protein pockets},
journal = {Briefings in Bioinformatics},
year = {2025},
doi = {10.1093/bib/bbae531}
}
EUVIMED