Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces a generalized framework that integrates molecular geometry and directionality into coarse-grained machine-learned potentials using two innovative approaches: anisotropic density-based descriptors (AniSOAP) and symmetry-adapted equivariant message-passing neural networks (MACE-CG). The authors demonstrate that retaining molecular anisotropy significantly enhances the accuracy of energy, force, and torque predictions in coarse-grained simulations, particularly for complex molecules like water. By highlighting the importance of geometric and symmetry information, this work provides a systematic methodology for improving the expressiveness and transferability of coarse-grained models in atomistic simulations.
Retaining molecular anisotropy can dramatically enhance prediction accuracy in coarse-grained simulations, revealing that geometry matters more than previously thought.
Machine-learned interatomic potentials have enabled highly accurate atomistic simulations, but extending these capabilities to coarse-grained systems remains challenging due to the loss of geometric and orientational information during coarse-graining. In this work, we present a generalized framework for incorporating molecular geometry and directionality into coarse-grained machine-learned potentials through two complementary approaches: anisotropic density-based descriptors (AniSOAP) and symmetry-adapted equivariant message-passing neural networks (MACE-CG). Using Gay-Berne particles and coarse-grained representations of benzene, formamide, and water, we demonstrate that explicitly retaining molecular anisotropy substantially improves the prediction of energies, forces, and torques relative to isotropic representations. AniSOAP provides an effective linear baseline when molecular shape is well approximated by ellipsoidal symmetry, while symmetry-adapted MACE-CG enables the incorporation of arbitrary molecular point-group symmetries. For water, whose orientational degrees of freedom are poorly represented by ellipsoidal descriptors alone, symmetry-adapted rigid-body features improve energy, force, and torque prediction by resolving orientational degeneracies inherent to isotropic and moment-of-inertia-based representations. These results show that information loss in coarse-grained modeling is governed not only by mapping resolution but also by the symmetry and geometric information retained in the representation, providing a systematic route toward more expressive and transferable coarse-grained machine-learned potentials.