Graph-Coarsening for Machine Learning Coarse-grained Molecular Dynamics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mondal, Soumya, Halder, Subhanu, Basu, Debarchan, Kumar, Sandeep, Karmakar, Tarak
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909699124756480
author Mondal, Soumya
Halder, Subhanu
Basu, Debarchan
Kumar, Sandeep
Karmakar, Tarak
author_facet Mondal, Soumya
Halder, Subhanu
Basu, Debarchan
Kumar, Sandeep
Karmakar, Tarak
contents Coarse-grained (CG) molecular dynamics (MD) simulations can simulate large molecular complexes over extended timescales by reducing degrees of freedom. A critical step in CG modeling is the selection of the CG mapping algorithm, which directly influences both accuracy and interpretability of the model. Despite progress, the optimal strategy for coarse-graining remains a challenging task, highlighting the necessity for a comprehensive theoretical framework. In this work, we present a graph-based coarsening approach to develop CG models. Coarse-grained sites are obtained through edge contractions, where nodes are merged based on a local variational cost metric while preserving key spectral properties of the original graph. Furthermore, we illustrate how Message Passing Atomic Cluster Expansion (MACE) can be applied to generate ML-CG potentials that are not only highly efficient but also accurate. Our approach provides a bottom-up, theoretically grounded computational method for the development of systematically improvable CG potentials.
format Preprint
id arxiv_https___arxiv_org_abs_2507_16531
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Graph-Coarsening for Machine Learning Coarse-grained Molecular Dynamics
Mondal, Soumya
Halder, Subhanu
Basu, Debarchan
Kumar, Sandeep
Karmakar, Tarak
Soft Condensed Matter
Coarse-grained (CG) molecular dynamics (MD) simulations can simulate large molecular complexes over extended timescales by reducing degrees of freedom. A critical step in CG modeling is the selection of the CG mapping algorithm, which directly influences both accuracy and interpretability of the model. Despite progress, the optimal strategy for coarse-graining remains a challenging task, highlighting the necessity for a comprehensive theoretical framework. In this work, we present a graph-based coarsening approach to develop CG models. Coarse-grained sites are obtained through edge contractions, where nodes are merged based on a local variational cost metric while preserving key spectral properties of the original graph. Furthermore, we illustrate how Message Passing Atomic Cluster Expansion (MACE) can be applied to generate ML-CG potentials that are not only highly efficient but also accurate. Our approach provides a bottom-up, theoretically grounded computational method for the development of systematically improvable CG potentials.
title Graph-Coarsening for Machine Learning Coarse-grained Molecular Dynamics
topic Soft Condensed Matter
url https://arxiv.org/abs/2507.16531