Local Variational Graph Coarsening for Machine Learning Coarse-Grained Molecular Dynamics Simulations
- 9 September 2026
- journal article
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 22 (18) , 9655-9665
Abstract
Coarse-grained (CG) molecular dynamics (MD) simulations can simulate large molecular complexes over extended time scales by reducing degrees of freedom. A central challenge in CG modeling is the selection of the CG mapping algorithm, which directly influences both accuracy and the interpretability of the model. Despite significant progress, effective strategies for optimal CG mappings remain a challenging task, highlighting the necessity for a comprehensive computational framework. In this work, we introduce a multilevel graph-coarsening framework for coarse graining, inspired by recent advances in graph reduction with spectral and cut guarantees. CG sites are generated through edge contractions based on a local variational cost metric, while preserving essential spectral properties of the original graph. This construction ensures structural fidelity across scales. To learn the corresponding CG energy functions, we utilize the Message Passing Atomic Cluster Expansion (MACE), yielding efficient yet accurate CG potentials. We demonstrate the generality of the framework across isolated molecules, bulk molecular liquid, and crystal. Our approach provides a data-driven bottom-up computational framework for the development of systematically improvable CG potentials with controlled accuracy and physical interpretability.Keywords
Funding Information
- European Research Council (101077842)
- Indian Institute of Technology Delhi (NA)
This publication has 75 references indexed in Scilit:
- Mapping Still Matters: Coarse-Graining with Machine Learning PotentialsJournal of Chemical Information and Modeling, 2026
- CoarsenConf: Equivariant Coarsening with Aggregated Attention for Molecular Conformer GenerationJournal of Chemical Information and Modeling, 2024
- CGCompiler: Automated Coarse-Grained Molecule Parametrization via Noise-Resistant Mixed-Variable OptimizationJournal of Chemical Theory and Computation, 2023
- Machine learned coarse-grained protein force-fields: Are we there yet?Current Opinion in Structural Biology, 2023
- Automated Coarse-Grained Mapping Algorithm for the Martini Force Field and Benchmarks for Membrane–Water PartitioningJournal of Chemical Theory and Computation, 2021
- An Information-Theory-Based Approach for Optimal Model Reduction of BiomoleculesJournal of Chemical Theory and Computation, 2020
- Coarse-Grained Protein Models and Their ApplicationsChemical Reviews, 2016
- PLUMED 2: New feathers for an old birdComputer Physics Communications, 2014
- Projection of diffusions on submanifolds: Application to mean force computationCommunications on Pure and Applied Mathematics, 2007
- Development and testing of a general amber force fieldJournal of Computational Chemistry, 2004