BFEE3: An AI-Assisted, Feature-Rich, and Streamlined Platform for Absolute Binding Free Energy Calculations
Journal of Chemical Information and Modeling · 09.11.2026
DOI: 10.1021/acs.jcim.6c02494 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, online erschienen am 09.11.2026. Verfasst von Mengchen Zhou und 4 weiteren Autor:innen. Die Arbeit nennt 76 Literaturangaben. Gefördert von: Natural Science Foundation of Tianjin Municipality, Fundamental Research Funds for the Central Universities, National Natural Science Foundation of China.
Abstract (Originalsprache)
Absolute binding free energy (ABFE) calculations for protein–ligand and protein–protein complexes, based on molecular simulations, are now established as essential tools in drug design and protein engineering. Nevertheless, both geometrical and alchemical routes require multistage simulation campaigns involving input preparation, postprocessing, and bookkeeping. These complex procedures can introduce preventable errors and limit accessibility for nonexpert practitioners. Therefore, there is a clear need for user-friendly and automated software environments to address these challenges. The Binding Free Energy Estimator (BFEE) is one such tool that has been widely adopted for estimating binding free energies. In this work, we present BFEE3, a release that delivers two major advances. First, it integrates an artificial intelligence (AI) assistant that enables the configuration of binding free energy protocols through natural language and provides on-demand explanations of methodological differences and the roles of individual options. Second, it incorporates recently developed protein–ligand ABFE protocols based on the double-decoupling method (DDM), including lucid DDM (LDDM) and well-tempered metadynamics-λ adaptive biasing force-accelerated DDM (WTM-λABF-DDM). Additional enhancements include support for protein–protein ABFE calculations, GROMACS compatibility for geometrical protein–ligand workflows, one-click simulation setup, and other usability improvements. We demonstrate the main advances of BFEE3 on three representative protein–ligand systems, focusing on natural-language-driven setup, automated input generation, postprocessing, and convergence analysis. We anticipate the use of BFEE3 by both expert and nonexpert users across physical chemistry, biochemistry, and medicinal chemistry.
Förderung
- Natural Science Foundation of Tianjin Municipality
- Fundamental Research Funds for the Central Universities
- National Natural Science Foundation of China
Zitieren
APA
Zhou, M., Bian, H., Shao, X., Cai, W., & Fu, H. (2026). BFEE3: An AI-Assisted, Feature-Rich, and Streamlined Platform for Absolute Binding Free Energy Calculations. Journal of Chemical Information and Modeling. https://doi.org/10.1021/acs.jcim.6c02494
Vancouver
Zhou M, Bian H, Shao X, Cai W, Fu H. BFEE3: An AI-Assisted, Feature-Rich, and Streamlined Platform for Absolute Binding Free Energy Calculations. Journal of Chemical Information and Modeling. 2026. doi:10.1021/acs.jcim.6c02494
BibTeX
@article{Zhou2026,
author = {Zhou, Mengchen and Bian, Hengwei and Shao, Xueguang and Cai, Wensheng and Fu, Haohao},
title = {BFEE3: An AI-Assisted, Feature-Rich, and Streamlined Platform for Absolute Binding Free Energy Calculations},
journal = {Journal of Chemical Information and Modeling},
year = {2026},
doi = {10.1021/acs.jcim.6c02494}
}
EUVIMED