An OpenMM-Based ML/MM–MMGBSA Workflow for End-point Protein–Ligand Binding Energy Ranking
Journal of Chemical Information and Modeling · 2026
DOI: 10.1021/acs.jcim.6c01539 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, 2026. Verfasst von Chenchen Wang und 7 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences, Macao Polytechnic University, Macao999078, China. Hauptthemen laut MEDLINE: Proteins, Molecular Dynamics Simulation. Die Arbeit nennt 53 Literaturangaben. Gefördert von: Fundo para o Desenvolvimento das Ci?ncias e da Tecnologia.
Abstract (Originalsprache)
Machine-learning force fields provide a practical route to introduce quantum-derived potential-energy surfaces into molecular dynamics simulations, but their value in end-point protein–ligand binding energy workflows remains unclear. Here, we developed an OpenMM-based ML/MM–MMGBSA workflow by combining ligand-only mechanically embedded ML/MM hybrid simulations and MMPBSA.py analysis, and evaluated it on 199 protein–ligand complexes from eight targets in the JACS benchmark set. The results showed that the effect of ML/MM sampling on MM/GBSA ranking was strongly target-, MLFF-, and sampling-time-dependent; selected improvements were observed in several systems, but simply extending the production length did not consistently improve end-point ranking. Pairwise sign accuracy analysis further showed that trajectory-based MM/GBSA provided useful ranking performance relative to single-structure Prime MMGBSA, although alchemical RBFE methods remained more robust. Overall, this workflow provides a practical and reproducible framework for integrating ML/MM conformational sampling with end-point binding free-energy estimations, while highlighting the need for MLFFs compatible with broader chemical space and explicit-solvent biomolecular environments, improved hybrid simulation embedding schemes such as electrostatic or polarizable embedding, and better consistency between sampling and scoring models.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Centre for Artificial Intelligence Driven Drug Discovery, Faculty of Applied Sciences, Macao Polytechnic University, Macao999078, China.
- Department of Integrative Biotechnology, Yonsei University, Incheon21983, Republic of Korea.
ORCID-Profile: Chenchen Wang, Huanxiang Liu, Xiaojun Yao
Förderung
- Fundo para o Desenvolvimento das Ci?ncias e da Tecnologia
Zitieren
APA
Wang, C., Wang, S., Zhai, S., Qin, L., Xu, K., Wang, J., Liu, H., & Yao, X. (2026). An OpenMM-Based ML/MM–MMGBSA Workflow for End-point Protein–Ligand Binding Energy Ranking. Journal of Chemical Information and Modeling. https://doi.org/10.1021/acs.jcim.6c01539
Vancouver
Wang C, Wang S, Zhai S, Qin L, Xu K, Wang J, et al. An OpenMM-Based ML/MM–MMGBSA Workflow for End-point Protein–Ligand Binding Energy Ranking. Journal of Chemical Information and Modeling. 2026. doi:10.1021/acs.jcim.6c01539
BibTeX
@article{Wang2026,
author = {Wang, Chenchen and Wang, Shihang and Zhai, Silong and Qin, Li and Xu, Kai and Wang, Jianmin and Liu, Huanxiang and Yao, Xiaojun},
title = {An OpenMM-Based ML/MM–MMGBSA Workflow for End-point Protein–Ligand Binding Energy Ranking},
journal = {Journal of Chemical Information and Modeling},
year = {2026},
doi = {10.1021/acs.jcim.6c01539}
}
EUVIMED