EUVIMEDEUVIMED entdecken
Crossref

From QM/MM to ML/MM: A new era in multiscale modeling

Juan Santiago Grassano, Ignacio Pickering, Adrian E. Roitberg, Dario A. Estrin, Jonathan A. Semelak

Chemical Physics Reviews · 01.12.2025 · 6 (4)

DOI: 10.1063/5.0260078 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Chemical Physics Reviews, online erschienen am 10.11.2025. Verfasst von Juan Santiago Grassano und 4 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 159 Literaturangaben. Gefördert von: Agencia Nacional de Promoción de la Investigación, el Desarrollo Tecnológico y la Innovación, Secretaría de Ciencia y Técnica, Universidad de Buenos Aires, Consejo Nacional de Investigaciones Científicas y Técnicas.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hybrid machine-learning/molecular-mechanics (ML/MM) methods extend the classical QM/MM paradigm by replacing the quantum description with neural network interatomic potentials trained to reproduce accurately quantum-mechanical (QM) results. By describing only the chemically active region with ML and the surrounding environment with molecular mechanics (MM), ML/MM models achieve near-QM/MM fidelity at a fraction of the computational cost, enabling routine simulation of reaction mechanisms, vibrational spectra, and binding free energies in complex biological or condensed-phase environments. The key challenge lies in coupling the ML and MM regions, a task addressed through three main strategies: (1) mechanical embedding (ME), where ML regions interact with fixed MM charges via classical electrostatics; (2) polarization-corrected mechanical embedding (PCME), where a vacuum-trained ML potential is supplemented post hoc with electrostatic corrections; and (3) environment-integrated embedding (EIE), where ML potentials are trained with explicit inclusion of MM-derived fields, enhancing accuracy but requiring specialized data. Since ML/MM builds on the scaffolding of QM/MM, most proposed coupling strategies rely heavily on electrostatics, polarization, and other physicochemical concepts, and the development and analysis of ML/MM schemes sits naturally at the intersection of physical chemistry and modern data science. This review surveys the conceptual foundations of ML/MM schemes, classifies existing implementations, and highlights key applications and open challenges, providing a critical snapshot of the current state-of-the-art and positioning ML/MM not merely as a computational alternative but as the natural evolution of QM/MM toward data-driven, scalable multiscale modeling.

Förderung

  • Agencia Nacional de Promoción de la Investigación, el Desarrollo Tecnológico y la Innovación
  • Secretaría de Ciencia y Técnica, Universidad de Buenos Aires
  • Consejo Nacional de Investigaciones Científicas y Técnicas
  • National Science Foundation

Zitieren

APA

Grassano, J. S., Pickering, I., Roitberg, A. E., Estrin, D. A., & Semelak, J. A. (2025). From QM/MM to ML/MM: A new era in multiscale modeling. Chemical Physics Reviews, 6(4). https://doi.org/10.1063/5.0260078

Vancouver

Grassano JS, Pickering I, Roitberg AE, Estrin DA, Semelak JA. From QM/MM to ML/MM: A new era in multiscale modeling. Chemical Physics Reviews. 2025;6(4). doi:10.1063/5.0260078

BibTeX
@article{Grassano2025,
  author = {Grassano, Juan Santiago and Pickering, Ignacio and Roitberg, Adrian E. and Estrin, Dario A. and Semelak, Jonathan A.},
  title = {From QM/MM to ML/MM: A new era in multiscale modeling},
  journal = {Chemical Physics Reviews},
  year = {2025},
  volume = {6},
  number = {4},
  doi = {10.1063/5.0260078}
}
Kostenlos starten →