GRACE-OFF: A Machine-Learned Interatomic Potential for Organic Liquids Using the GRACE Architecture.
4 affiliations
- 1Faculty of Chemistry, Institute of Computational Biological Chemistry, University of Vienna, 1090Vienna, Austria.
- 2Vienna Doctoral School of Chemistry (DosChem), University of Vienna, 1090Vienna, Austria.
- 3Institute of Materials Chemistry, TU Wien, A-1060Vienna, Austria.
- 4Interdisciplinary Centre for Advanced Materials Simulation (ICAMS), Ruhr-University Bochum, 44780Bochum, Germany.
Abstract
Machine-learned interatomic potentials (MLIPs) have become an increasingly important tool for molecular dynamics (MD) simulations, enabling near quantum-mechanical accuracy at significantly reduced computational cost. Recent studies indicate that the Graph Atomic Cluster Expansion (GRACE) neural network architecture delivers strong performance in materials chemistry. In this work, we assess the GRACE architecture for the prediction of potential energy surfaces for organic molecules and introduce GRACE-OFF (GRACE Organic Force Field). GRACE models of varying depth (one-layer and two-layer) and size (small, medium, large) are trained on the SPICE v2.0 data set. We validate the resulting models using a variety of benchmarks. These include single-point energy and force predictions, torsional energy profiles, condensed phase properties of organic liquids and water (thermodynamic properties, self-diffusion coefficients, radial distribution functions, and temperature-dependent water density), as well as the stability of biomolecular MD simulations for gas-phase Ala15 and solvated crambin. For the single-molecule benchmarks (single point energies and forces, torsional energy profiles), the one-layer models showed only mediocre performance, whereas the two-layer models outperformed the MACE-OFF models to which we compare. For the condensed phase properties, the two-layer models gave consistently better results than the MACE-OFF family of MLIPs. For water and hexane, the GRACE-OFF models also beat the much more expensive small UMA/OMol25 (S) model. The two-layer GRACE-OFF models accurately reproduce experimental water radial distribution functions and predict water densities in close agreement with experimental data over a temperature range from 270 to 330 K. Benchmarks demonstrate that GRACE-OFF achieves higher MD performance than comparable MACE-OFF models in both single and double precision. This establishes GRACE-OFF as an accurate and computationally efficient foundation potential for routine simulations of organic liquids and biomolecular systems.
Related
- Six Open Questions in Machine-Learned Interatomic Potential Foundation Models
- A Machine-Learned Interatomic Potential Free-Energy Surface for the First Step of MIL-101(Cr) Secondary Building Unit Formation
- Accurate and Rapid Vibrational Spectra of Molecular Crystals from Machine-Learned Interatomic Potentials
- Neural Constrained Charge Equilibration for Extracting Charge Transport Parameters from Machine Learned Interatomic Potentials
- FACTO: fast atom-centered tensor operator for accurate and efficient foundational machine-learned interatomic potentials
BibTeX
@article{picha2026graceoff,
title = {{GRACE-OFF: A Machine-Learned Interatomic Potential for Organic Liquids Using the GRACE Architecture.}},
author = {Anna Katharina Picha and Johannes Karwounopoulos and Linus C Erhard and Stefan Boresch and Esther Heid},
journal = {Journal of chemical theory and computation},
year = {2026},
month = sep,
doi = {10.1021/acs.jctc.6c01169},
url = {https://europepmc.org/article/MED/42917463},
note = {CC BY},
}
RIS
TY - JOUR
TI - GRACE-OFF: A Machine-Learned Interatomic Potential for Organic Liquids Using the GRACE Architecture.
AU - Anna Katharina Picha
AU - Johannes Karwounopoulos
AU - Linus C Erhard
AU - Stefan Boresch
AU - Esther Heid
PY - 2026
DA - 2026/09/01
JO - Journal of chemical theory and computation
DO - 10.1021/acs.jctc.6c01169
UR - https://europepmc.org/article/MED/42917463
AB - Machine-learned interatomic potentials (MLIPs) have become an increasingly important tool for molecular dynamics (MD) simulations, enabling near quantum-mechanical accuracy at significantly reduced computational cost. Recent studies indicate that the Graph Atomic Cluster Expansion (GRACE) neural network architecture delivers strong performance in materials chemistry. In this work, we assess the GRACE architecture for the prediction of potential energy surfaces for organic molecules and introduce GRACE-OFF (GRACE Organic Force Field). GRACE models of varying depth (one-layer and two-layer) and size (small, medium, large) are trained on the SPICE v2.0 data set. We validate the resulting models using a variety of benchmarks. These include single-point energy and force predictions, torsional energy profiles, condensed phase properties of organic liquids and water (thermodynamic properties, self-diffusion coefficients, radial distribution functions, and temperature-dependent water density), as well as the stability of biomolecular MD simulations for gas-phase Ala15 and solvated crambin. For the single-molecule benchmarks (single point energies and forces, torsional energy profiles), the one-layer models showed only mediocre performance, whereas the two-layer models outperformed the MACE-OFF models to which we compare. For the condensed phase properties, the two-layer models gave consistently better results than the MACE-OFF family of MLIPs. For water and hexane, the GRACE-OFF models also beat the much more expensive small UMA/OMol25 (S) model. The two-layer GRACE-OFF models accurately reproduce experimental water radial distribution functions and predict water densities in close agreement with experimental data over a temperature range from 270 to 330 K. Benchmarks demonstrate that GRACE-OFF achieves higher MD performance than comparable MACE-OFF models in both single and double precision. This establishes GRACE-OFF as an accurate and computationally efficient foundation potential for routine simulations of organic liquids and biomolecular systems.
SN - 1549-9618
SN - 1549-9626
ER -