Prediction of Interatomic Potentials Combining Empirical Potential and Graph Neural Networks

Main Article Content

Tao Ming
Guochao Wan

Keywords

molecular dynamics simulation, graph neural network, ZBL potential, machine learning interatomic potential

Abstract

Molecular dynamics (MD) simulation is constrained by the time and spatial scales as well as computational efficiency of traditional methods. While machine learning interatomic potentials (MLIPs) based on graph neural networks (GNNs) improve modeling accuracy, they suffer from insufficient short-range interaction modeling and lack of physical constraints. This paper proposes the DimezblNet model, which explicitly embeds the ZBL empirical potential function into the DimeNet framework. Through physically guided hybrid potential modeling, the description of short-range repulsive interactions is strengthened. On the MD17 dataset, the model reduces the mean absolute error (MAE) of energy and atomic force predictions for molecules like aspirin by 3.7%-5.3% compared to DimeNet. In the QM9 molecular property prediction task, the MAE of polarizability (α) is 0.0452 ų, outperforming DimeNet (0.0469 ų, a 3.6% improvement), and the MAE of dipole moment (μ) is 0.0273 D. Experiments show that combining physical priors with data-driven strategies significantly enhances the model's generalization ability and interpretability in complex molecular systems.

Abstract 8 | PDF Downloads 15

References

  • Alder, B. J., & Wainwright, T. E. (1957). Phase transition for a hard sphere system. The Journal of Chemical Physics, 27(5), 1208-1209. https://doi.org/10.1063/1.1743957
  • Anderson, B., Hy, T. S., & Kondor, R. (2019). Cormorant: Covariant molecular neural networks [Paper presentation]. 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada.
  • Bartók, A. P., Payne, M. C., Kondor, R., & Csányi, G. (2010). Gaussian approximation potentials: The accuracy of quantum mechanics, without the electrons. Physical Review Letters, 104(13), Article 136403. https://doi.org/10.1103/PHYSREVLETT.104.136403
  • Batzner, S., Musaelian, A., Sun, L., Geiger, M., Mailoa, J. P., Kornbluth, M., Molinari, N., Smidt, T. E., & Kozinsky, B. (2022). E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials. Nature Communications, 13(1), Article 2453. https://doi.org/10.1038/S41467-022-29939-5
  • Chmiela, S., Sauceda, H. E., Poltavsky, I., Müller, K. R., & Tkatchenko, A. (2019). sGDML: Constructing accurate and data efficient molecular force fields using machine learning. Computer Physics Communications, 240, 38-45. https://doi.org/10.1016/J.CPC.2019.02.007
  • Chmiela, S., Tkatchenko, A., Sauceda, H. E., Poltavsky, I., Schütt, K. T., & Müller, K. R. (2017). Machine learning of accurate energy-conserving molecular force fields. Science Advances, 3(5), Article e1603015. https://doi.org/10.1126/SCIADV.1603015
  • Gasteiger, J., Becker, F., & Günnemann, S. (2021). Gemnet: Universal directional graph neural networks for molecules [Paper presentation]. 35th Conference on Neural Information Processing Systems (NeurIPS 2021). Virtual.
  • Gasteiger, J., Groß, J., & Günnemann, S. (2020). Directional message passing for molecular graphs. arXiv preprint, arXiv:2003.03123. https://doi.org/10.48550/arXiv.2003.03123
  • Gilmer, J., Schoenholz, S. S., Riley, P. F., Vinyals, O., & Dahl, G. E. (2017). Neural message passing for quantum chemistry [Paper presentation]. Proceedings of the 34th International Conference on Machine Learning, Sydney, NSW, Australia.
  • Huang, B., & Von Lilienfeld, O. A. (2021). Ab initio machine learning in chemical compound space. Chemical Reviews, 121(16), 10001-10036. https://doi.org/10.1021/ACS.CHEMREV.0C01303
  • Keretsu, S., Bhujbal, S. P., & Cho, S. J. (2020). Rational approach toward COVID-19 main protease inhibitors via molecular docking, molecular dynamics simulation and free energy calculation. Scientific Reports, 10(1), Article 17716. https://doi.org/10.1038/S41598-020-74468-0
  • Maron, H., Ben-Hamu, H., Serviansky, H., & Lipman, Y. (2019). Provably powerful graph networks [Paper presentation]. 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada.
  • Ramakrishnan, R., Dral, P. O., Rupp, M., & Von Lilienfeld, O. A. (2014). Quantum chemistry structures and properties of 134 kilo molecules. Scientific Data, 1, 1-7. https://doi.org/10.1038/SDATA.2014.22
  • Ruddigkeit, L., Van Deursen, R., Blum, L. C., & Reymond, J. L. (2012). Enumeration of 166 billion organic small molecules in the chemical universe database GDB-17. Journal of Chemical Information and Modeling, 52(11), 2864-2875. https://doi.org/10.1021/CI300415D
  • Schütt, K., Kindermans, P.-J., Sauceda Felix, H. E., Chmiela, S., Tkatchenko, A., & Müller, K.-R. (2017). Schnet: A continuous-filter convolutional neural network for modeling quantum interactions [Paper presentation]. 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA.
  • Unke, O. T., & Meuwly, M. (2019). PhysNet: A neural network for predicting energies, forces, dipole moments, and partial charges. Journal of Chemical Theory and Computation, 15(6), 3678-3693. https://doi.org/10.1021/ACS.JCTC.9B00181
  • Zhang, L., Han, J., Wang, H., Saidi, W., & Car, R. (2018). End-to-end symmetry preserving inter-atomic potential energy model for finite and extended systems [Paper presentation]. Proceedings of the 32nd International Conference on Neural Information Processing Systems, Montréal, Canada.
  • Ziegler, J. F., & Biersack, J. P. (1985). The stopping and range of ions in matter. In D. A. Bromley (Ed.), Treatise on heavy-ion science: Volume 6: Astrophysics, chemistry, and condensed matter (pp. 93-129). Springer. https://doi.org/10.1007/978-1-4615-8103-1_3

Similar Articles

1-10 of 11

You may also start an advanced similarity search for this article.