EUVIMEDEUVIMED entdecken
Crossref

Beyond the cutoff: Hybrid ML/MM electrostatics for neural network potentials

Shahed Haghiri iD, Andres S Urbina iD, Lyudmila V Slipchenko iD

The Journal of Chemical Physics · 14.03.2026 · 164 (10)

DOI: 10.1063/5.0314507 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of Chemical Physics, online erschienen am 09.03.2026. Verfasst von Shahed Haghiri und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Chemistry, Purdue University, West Lafayette, Indiana 47907, USA. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: Basic Energy Sciences, National Institute of General Medical Sciences.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Atomistic Neural Network Potentials (NNPs) have been developed to predict molecular properties and electronic ground-state energies of small molecules with kcal/mol accuracy. However, despite their excellent scalability and low computational cost, atomistic NNPs are intrinsically local, making them unreliable for modeling long-range interactions in condensed-phase systems relevant to biological, engineering, and pharmaceutical applications. Recently, we demonstrated how to explicitly incorporate information on long-range interactions into the ANI NNP by retraining it in the presence of electrostatic potentials arising from the molecular environment. Effectively, the introduced embedded ANI/MM model is similar in spirit to quantum mechanics/molecular mechanics. Here, we extend this line of work by developing and training the ANI/MM network to predict binding energies for two protein–ligand complexes. We show that this network predicts forces with an error of less than 1 kcal/mol/Å, opening the possibility of using it for geometry optimizations and molecular dynamics. The resulting ANI/MM NNP outperforms the accurate, ab initio–fitted classical force field Q-Force and exhibits good transferability to new solutes, provided that the training set includes relevant structural fragments of the target molecule. Together, these findings demonstrate that hybrid ML/MM neural architectures offer a promising route toward chemically accurate, scalable modeling of complex molecular systems.

Autor:innen und Institutionen

  • Department of Chemistry, Purdue University, West Lafayette, Indiana 47907, USA.

ORCID-Profile: Shahed Haghiri, Andres S Urbina, Lyudmila V Slipchenko

Förderung

  • Basic Energy Sciences
  • National Institute of General Medical Sciences

Zitieren

APA

Haghiri, S., Urbina, A. S., & Slipchenko, L. V. (2026). Beyond the cutoff: Hybrid ML/MM electrostatics for neural network potentials. The Journal of Chemical Physics, 164(10). https://doi.org/10.1063/5.0314507

Vancouver

Haghiri S, Urbina AS, Slipchenko LV. Beyond the cutoff: Hybrid ML/MM electrostatics for neural network potentials. The Journal of Chemical Physics. 2026;164(10). doi:10.1063/5.0314507

BibTeX
@article{Haghiri2026,
  author = {Haghiri, Shahed and Urbina, Andres S and Slipchenko, Lyudmila V},
  title = {Beyond the cutoff: Hybrid ML/MM electrostatics for neural network potentials},
  journal = {The Journal of Chemical Physics},
  year = {2026},
  volume = {164},
  number = {10},
  doi = {10.1063/5.0314507}
}
Kostenlos starten →