A Generalized Approach for Incorporating Geometry and Directionality into Coarse-Grained Machine-Learned…

Abstract

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.

Exchange-Correlation Potentials and Energies from Inverse Generalized Kohn-Sham Calculations
Vishal Subramanian, Bikash Kanungo, Vaibhav Khanna +2
arXiv14 Sep 2026PreprintCC BY 4.0Full textPhysical chemistry Computational physicsarXiv
Can Universal Machine-Learning Interatomic Potentials Capture Small Polarons? A Geometry-Based Benchmark in Transition-Metal Oxides
Vladislav Korostelev, Pjotrs Žguns, Konstantin Klyukin
arXiv12 Oct 2026PreprintarXiv licenceFull textPhysical chemistry Computational physicsarXiv
Effective Directionality in Electron-Transfer-Driven Reactions on Bifurcating Multidimensional Potential Energy Surfaces
Linh M. Le
ChemRxiv21 Oct 2026PreprintCC BYFull textPhysical chemistryChemRxiv
How Chemical Evidence Shapes Mechanistic Reasoning and Prediction by Large Language Models: Fine-Grained Inference in Nucleoside-Derived Supramolecular Gelation
Ying Wang, Xi Yu
ChemRxiv3 Nov 2026PreprintLicence not statedGeneral chemistryChemRxiv
Coarse‐Grained Simulations Rationalize Thermosensitivity and Hydrolytic Degradation of Vinyl Copolymers Obtained by Radical Ring‐Opening Polymerization
Ping Gao, Yingmin Jiang, Tâp Ha-Duong +1
Angewandte Chemie International Edition10 Sep 2026Peer-reviewedPublisher termsFull textMaterials & polymersHAL

Cite

BibTeX RIS

BibTeX

@misc{lin2026generalized,
  title = {{A Generalized Approach for Incorporating Geometry and Directionality into Coarse-Grained Machine-Learned Potentials}},
  author = {Arthur Y. Lin and Tejas Dahiya and Rose K. Cersonsky},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.01911},
  eprint = {2609.01911},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.01911},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - A Generalized Approach for Incorporating Geometry and Directionality into Coarse-Grained Machine-Learned Potentials
AU  - Arthur Y. Lin
AU  - Tejas Dahiya
AU  - Rose K. Cersonsky
PY  - 2026
DA  - 2026/09/01
PB  - arXiv
DO  - 10.48550/arxiv.2609.01911
UR  - https://arxiv.org/abs/2609.01911
AB  - 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.
ER  -

Abstract

Related

Cite