Journal article · 2023 · Open access

Regularized by Physics: Graph Neural Network Parametrized Potentials for the Description of Intermolecular Interactions

Moritz Thürlemann, Lennard Böselt, Sereina Riniker

Journal of Chemical Theory and Computation, 19(2), 562–579 · Published 12 January 2023 · DOI 10.1021/acs.jctc.2c00661

Free PDFView at the publisherCite this paper

In brief

“Regularized by Physics: Graph Neural Network Parametrized Potentials for the Description of Intermolecular Interactions” is a 2023 journal article by Moritz Thürlemann and 2 co-authors, published in Journal of Chemical Theory and Computation. OpenAlex counts 27 citations as of 16 November 2026, which puts it in the top 3% of works published in 2023 by citations. It is open access under a CC BY-NC-ND licence: the full text is free to read at Journal of Chemical Theory and Computation.

Citations
27
Most cited in
2025 (9)
Field-weighted impact
1.82
References
164
Authors
3

Abstract

Simulations of molecular systems using electronic structure methods are still not feasible for many systems of biological importance.As a result, empirical methods such as force fields (FF) have become an established tool for the simulation of large and complex molecular systems.The parametrization of FF is, however, time-consuming and has traditionally been based on experimental data.Recent years have therefore seen increasing efforts to automatize FF parametrization or to replace FF with machine-learning (ML) based potentials.Here, we propose an alternative strategy to parametrize FF, which makes use of ML and gradient-descent based optimization while retaining a functional form founded in physics.Using a predefined functional form is shown to enable interpretability, robustness, and efficient simulations of large systems over long time scales.To demonstrate the strength of the proposed method, a fixed-charge and a polarizable model are trained on ab initio potential-energy surfaces.Given only information about the constituting elements, the molecular topology, and reference potential energies, the models successfully learn to assign atom types and corresponding FF parameters from scratch.The resulting models and parameters are validated on a wide range of experimentally and computationally derived properties of systems including dimers, pure liquids, and molecular crystals.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Thürlemann, M., Böselt, L., & Riniker, S. (2023). Regularized by Physics: Graph Neural Network Parametrized Potentials for the Description of Intermolecular Interactions. Journal of Chemical Theory and Computation, 19(2), 562–579. https://doi.org/10.1021/acs.jctc.2c00661

MLA 9

Thürlemann, Moritz, et al. “Regularized by Physics: Graph Neural Network Parametrized Potentials for the Description of Intermolecular Interactions.” Journal of Chemical Theory and Computation, vol. 19, no. 2, 2023, pp. 562–579. https://doi.org/10.1021/acs.jctc.2c00661.

Chicago

Thürlemann, Moritz, Lennard Böselt, and Sereina Riniker. 2023. “Regularized by Physics: Graph Neural Network Parametrized Potentials for the Description of Intermolecular Interactions.” Journal of Chemical Theory and Computation 19 (2): 562–579. https://doi.org/10.1021/acs.jctc.2c00661.

Harvard

Thürlemann, M., Böselt, L. and Riniker, S. (2023) ‘Regularized by Physics: Graph Neural Network Parametrized Potentials for the Description of Intermolecular Interactions’, Journal of Chemical Theory and Computation, 19(2), pp. 562–579. doi:10.1021/acs.jctc.2c00661.

IEEE

M. Thürlemann, L. Böselt, and S. Riniker, “Regularized by Physics: Graph Neural Network Parametrized Potentials for the Description of Intermolecular Interactions,” Journal of Chemical Theory and Computation, vol. 19, no. 2, pp. 562–579, 2023, doi: 10.1021/acs.jctc.2c00661.

BibTeX

@article{thurlemann2023regularized,
  title     = {{Regularized by Physics: Graph Neural Network Parametrized Potentials for the Description of Intermolecular Interactions}},
  author    = {Thürlemann, Moritz and Böselt, Lennard and Riniker, Sereina},
  journal   = {Journal of Chemical Theory and Computation},
  year      = {2023},
  volume    = {19},
  number    = {2},
  pages     = {562--579},
  doi       = {10.1021/acs.jctc.2c00661},
  url       = {https://doi.org/10.1021/acs.jctc.2c00661}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202355
202477
202599
202666

Its field-weighted citation impact is 1.82: it has been cited 1.82 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science

  • force field parameterization
  • graph neural networks
  • physics-informed machine learning
  • intermolecular interactions
  • polarizable force field
  • ab initio potential energy surface
  • molecular simulation
  • molecular crystals

Work with this paper

Most-cited papers in Materials Science

All highly cited Materials Science papers

Questions about this paper

How do I cite this paper in APA style?

Thürlemann, M., Böselt, L., & Riniker, S. (2023). Regularized by Physics: Graph Neural Network Parametrized Potentials for the Description of Intermolecular Interactions. Journal of Chemical Theory and Computation, 19(2), 562–579. https://doi.org/10.1021/acs.jctc.2c00661

How many times has this paper been cited?

27 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access: read the free full text at Journal of Chemical Theory and Computation.

Who wrote this paper?

Moritz Thürlemann, Lennard Böselt, Sereina Riniker.

What is the DOI of this paper?

10.1021/acs.jctc.2c00661. The permanent link is https://doi.org/10.1021/acs.jctc.2c00661.

Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.