EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Buffer Region Embedding for Hybrid Machine-Learned/Molecular-Mechanical Simulations in Complex Environments

Michael Caspary iD, Radek Crha iD, Edgar Galicia-Andrés iD, Peter Poliak, Chris Oostenbrink iD

Journal of Chemical Information and Modeling · 2026

DOI: 10.1021/acs.jcim.6c00924 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Information and Modeling, 2026. Verfasst von Michael Caspary und 4 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Molecular Modeling and Simulation, BOKU University, 1190Vienna, Austria. Hauptthemen laut MEDLINE: Molecular Dynamics Simulation, Machine Learning. Die Arbeit nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Boehringer Ingelheim, BASF, ?sterreichische Nationalstiftung f?r Forschung, Technologie und Entwicklung.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multiscale approaches combining machine-learned interatomic potentials with classical molecular mechanics force fields are emerging as a scalable alternative to QM/MM approaches, in which a quantum mechanical calculation is embedded in a molecular mechanics environment. They enable quantum-level accuracy for localized chemistry at substantially reduced cost. However, reliable coupling across region boundaries and application in heterogeneous environments remains a central challenge. Here, we extend the buffer region embedding strategy (BuRNN) for hybrid machine-learned interaction potentials/molecular mechanics (MLIP/MM) simulations in complex environments. The buffer region elevates the interactions of the inner region with its immediate surroundings to the MLIP level, whereas the interactions within the buffer region and with the outer region are still described at the MM level. We validate the approach across four test systems of increasing complexity: methanol/water mixtures benchmarked against experimental total X-ray structure factors, a functionalized fullerene designed to describe a covalent boundary between the buffer and outer region, aqueous heme b with an axial cysteine ligand to probe coordinative bond dissociation, and the resting-state of the cytochrome P450 1A2 enzyme. Across these systems, BuRNN reproduces experimental observables or the underlying QM reference data and yields stable dynamics, including challenging metal–ligand interactions. We compare explicit and implicit link-atom treatments at the buffer–outer boundary and find that explicit capping provides more robust uncertainty estimates, which is critical for active-learning model generation. These results establish BuRNN as a practical approach to perform MLIP/MM simulations in biomolecular systems.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Molecular Dynamics SimulationMachine LearningBuffersQuantum MechanicsWaterQuantum Theory

Substanzen

BuffersWater

Autor:innen und Institutionen

  • Institute for Molecular Modeling and Simulation, BOKU University, 1190Vienna, Austria.
  • Christian Doppler Laboratory for Molecular Informatics in the Biosciences, BOKU University, 1190Vienna, Austria.
  • Institute of Physical Chemistry and Chemical Physics, Faculty of Chemical and Food Technology, Slovak University of Technology in Bratislava, Radlinského 9, Bratislava81237, Slovakia.

ORCID-Profile: Michael Caspary, Radek Crha, Edgar Galicia-Andrés, Chris Oostenbrink

Förderung

  • Boehringer Ingelheim
  • BASF
  • ?sterreichische Nationalstiftung f?r Forschung, Technologie und Entwicklung
  • Bundesministerium f?r Arbeit und Wirtschaft
  • Christian Doppler Forschungsgesellschaft

Zitieren

APA

Caspary, M., Crha, R., Galicia-Andrés, E., Poliak, P., & Oostenbrink, C. (2026). Buffer Region Embedding for Hybrid Machine-Learned/Molecular-Mechanical Simulations in Complex Environments. Journal of Chemical Information and Modeling. https://doi.org/10.1021/acs.jcim.6c00924

Vancouver

Caspary M, Crha R, Galicia-Andrés E, Poliak P, Oostenbrink C. Buffer Region Embedding for Hybrid Machine-Learned/Molecular-Mechanical Simulations in Complex Environments. Journal of Chemical Information and Modeling. 2026. doi:10.1021/acs.jcim.6c00924

BibTeX
@article{Caspary2026,
  author = {Caspary, Michael and Crha, Radek and Galicia-Andrés, Edgar and Poliak, Peter and Oostenbrink, Chris},
  title = {Buffer Region Embedding for Hybrid Machine-Learned/Molecular-Mechanical Simulations in Complex Environments},
  journal = {Journal of Chemical Information and Modeling},
  year = {2026},
  doi = {10.1021/acs.jcim.6c00924}
}
Kostenlos starten →