Sep 2026· Journal of Chemical Theory and Computation· Vol 22, pp. 9274 - 9289· 2 citations· 72 references
Machine Learning in Materials Science
TL;DR
benchmarks demonstrate that GRACE-OFF achieves higher MD performance than comparable MACE-OFF models in both single and double precision, establishing GRACE-OFF as an accurate and computationally efficient foundation potential for routine simulations of organic liquids and biomolecular systems.
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.
External electric fields play a crucial role in chemistry, materials, and biology. However, accurately capturing external field effects remains a challenge for machine learning interatomic potentials (MLIPs). By revealing the limitations of conventional architectures in predicting field-dependent response properties,...
Ke Chen, Sandra Luber· npj Computational Materials· 0 citations
This work presents a physics-informed pretraining strategy that leverages simple empirical potentials to improve the robustness and stability of MLIPs for MD simulations and demonstrates that this physics-informed pretraining consistently improves both prediction accuracy as well as stability in MD.
Qian-Yu Zheng, Victor Fung· Journal of Chemical Informat...· 0 citations
A potential is presented that is universal within the class of water-free solid-state hydrogen-bond network mediated proton conductors rather than across chemistry and a database of 4.4 million first-principles configurations spanning 55 materials, offering a template for other compound classes.
Jonas Hänseroth, Rose von Stackelberg, Christian Dreßler· 0 citations
Molten fluoride salts are critical heat carriers and fuel solvents for advanced molten salt reactors. Yet, their complex atomic interactions and composition-dependent structural evolution remain challenging to characterize over a wide range of temperatures and compositions. Here, we develop a highly transferable and ac...
Yuan Yin, Wen-Shuo Liang, Wen-Tao Zhou et al.· Journal of Chemical Physics· 0 citations
Polyethylene (PE) is one of the most commonly used synthetic polymers. While the synthesis and processing protocols for PE are well established, precise experimental assignment of microscopic structures at atomistic resolution (i.e., the position of each atom) remains largely limited to highly crystalline systems. This...
Bharatha K. Gunawardana, T. Shah, B. Azizova et al.· 1 citation
Atomistic simulations have proven to be a powerful tool in obtaining chemical insights for complex solid–liquid interfaces. However, studying solid–liquid interfaces with first-principles methods is a challenging task due to the underlying computational limitations. Empirical force fields have been extensively applie...
An MIT and Dana-Farber Institute-led team used large language models to examine nearly 4,000 studies and hundreds of code repositories, revealing gaps in the information needed to scrutinize and reuse published research.