EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enabling Biomolecular Simulations with Neural Network Potentials in GROMACS

Lukas Müllender iD, Berk Hess iD, Erik Lindahl iD

Journal of Chemical Theory and Computation · 08.09.2026 · 22 (17) · 9134-9144

DOI: 10.1021/acs.jctc.6c00808 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Chemical Theory and Computation, online erschienen am 20.08.2026. Verfasst von Lukas Müllender und 2 weiteren Autor:innen. Beteiligte Einrichtung: Science for Life Laboratory and Swedish e-Science Research Center, Department of Applied Physics, KTH Royal Institute of Technology, 171 65Solna, Swe…. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 76 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: HORIZON EUROPE Marie Sklodowska-Curie Actions, HORIZON EUROPE Digital, Industry and Space, Swedish Research Council (VR).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neural network potentials (NNPs) are rapidly changing the landscape of state-of-the-art molecular dynamics (MD) simulations. To make full use of this development, the community needs flexible, easy-to-use interfaces firmly integrated with existing methodologies. To address this, we present an interface for hybrid machine learning/molecular mechanics (ML/MM) simulations implemented in the widely used MD code GROMACS. The interface enables NNPs trained in the PyTorch framework to contribute energies and forces during MD simulations, either for selected subsets or entire molecular systems. By defining a flexible set of model inputs and outputs, the interface is agnostic to specific NNP architectures and can accommodate a wide range of descriptor-based and message-passing models. In particular, the design integrates NNP inference seamlessly into the extensive GROMACS molecular simulation ecosystem, providing users with the capability to straightforwardly combine NNPs with existing advanced sampling and free energy workflows. We demonstrate the capabilities of the interface using several representative applications, including enhanced sampling of peptide torsional free energy landscapes, absolute solvation free energy calculations, and protein–ligand simulations. We also run performance benchmarks on water boxes for several different NNP architectures. Our interface is available in recent GROMACS releases, and we believe it will provide a practical foundation for incorporating machine learning potentials into production MD simulations of biomolecular systems.

Autor:innen und Institutionen

  • Science for Life Laboratory and Swedish e-Science Research Center, Department of Applied Physics, KTH Royal Institute of Technology, 171 65Solna, Sweden.
  • Science for Life Laboratory, Department of Biochemistry and Biophysics, Stockholm University, 171 65Solna, Sweden.
  • Department of Physics, Chemistry and Biology, Linköping University, 581 83Linköping, Sweden.
  • Department Chemistry, University of Illinois at Urbana-Champaign, Urbana, Illinois61801, United States.

ORCID-Profile: Lukas Müllender, Berk Hess, Erik Lindahl

Förderung

  • HORIZON EUROPE Marie Sklodowska-Curie Actions
  • HORIZON EUROPE Digital, Industry and Space
  • Swedish Research Council (VR)

Zitieren

APA

Müllender, L., Hess, B., & Lindahl, E. (2026). Enabling Biomolecular Simulations with Neural Network Potentials in GROMACS. Journal of Chemical Theory and Computation, 22(17), 9134-9144. https://doi.org/10.1021/acs.jctc.6c00808

Vancouver

Müllender L, Hess B, Lindahl E. Enabling Biomolecular Simulations with Neural Network Potentials in GROMACS. Journal of Chemical Theory and Computation. 2026;22(17):9134-9144. doi:10.1021/acs.jctc.6c00808

BibTeX
@article{Mllender2026,
  author = {Müllender, Lukas and Hess, Berk and Lindahl, Erik},
  title = {Enabling Biomolecular Simulations with Neural Network Potentials in GROMACS},
  journal = {Journal of Chemical Theory and Computation},
  year = {2026},
  volume = {22},
  number = {17},
  pages = {9134--9144},
  doi = {10.1021/acs.jctc.6c00808}
}
Kostenlos starten →