Bridging Molecular Scales with Implicit Score Matching for Bottom-Up Coarse Graining
Abstract
Molecular dynamics simulations provide a computational microscope for atomic scale processes but remain restricted to relatively small spatial and temporal scales. Coarse-grained models extend their reach by representing groups of atoms as effective interaction sites. The number of particles is systematically reduced by embedding the collective behavior of groups of atoms into coarse-grained sites governed by effective potentials. However, constructing accurate, highly coarsened potentials, even with the assistance of modern machine-learning methods, is a grand challenge because coarse grained forces depend on a statistical distribution of composite atomic configurations making direct calculation computationally prohibitive. Here, we introduce an alternative framework based on implicit score matching that directly avoids the need for explicit coarse-grained forces. This approach both substantially reduces the training data required relative to conventional force-matching methods and enables high-fidelity models in which each coarse-grained site represents hundreds to thousands of atoms. We demonstrate the method's versatility and effectiveness across a diverse range of chemical systems and phenomena, developing bottom-up, machine-learned models. These enable efficient modeling at micrometer and millimeter length scales, while retaining significant amounts of the atomic scale fidelity. These results establish implicit score matching as a practical route towards chemically accurate simulations that bridge molecular and mesoscopic scales.
Related
- A simple time coarse graining method for molecular dynamics simulations of liquids
- MATCHERS: a ‘chemistry-infused’ representation bridging molecular graphs and strings
- An unlearnable target: diagnosing the orientation gauge in PXRD-conditioned molecular-crystal flow matching
- Tailoring Reactivity of Molecular Gallium Hydroxides via Chalcogen Bridging.
- Bridging Chemical Literature and Molecular Graphs: LLM-Augmented Enantioselectivity Prediction for Iridium-Catalyzed Asymmetric C-H Borylation.
BibTeX
@misc{sahrmann2026bridging,
title = {{Bridging Molecular Scales with Implicit Score Matching for Bottom-Up Coarse Graining}},
author = {Patrick G. Sahrmann and Nicholas Lubbers and Benjamin T. Nebgen and Emily Shinkle and Sergei Tretiak and Kipton Barros and Brenden W. Hamilton},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.32040},
eprint = {2609.32040},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.32040},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Bridging Molecular Scales with Implicit Score Matching for Bottom-Up Coarse Graining
AU - Patrick G. Sahrmann
AU - Nicholas Lubbers
AU - Benjamin T. Nebgen
AU - Emily Shinkle
AU - Sergei Tretiak
AU - Kipton Barros
AU - Brenden W. Hamilton
PY - 2026
DA - 2026/09/25
PB - arXiv
DO - 10.48550/arxiv.2609.32040
UR - https://arxiv.org/abs/2609.32040
AB - Molecular dynamics simulations provide a computational microscope for atomic scale processes but remain restricted to relatively small spatial and temporal scales. Coarse-grained models extend their reach by representing groups of atoms as effective interaction sites. The number of particles is systematically reduced by embedding the collective behavior of groups of atoms into coarse-grained sites governed by effective potentials. However, constructing accurate, highly coarsened potentials, even with the assistance of modern machine-learning methods, is a grand challenge because coarse grained forces depend on a statistical distribution of composite atomic configurations making direct calculation computationally prohibitive. Here, we introduce an alternative framework based on implicit score matching that directly avoids the need for explicit coarse-grained forces. This approach both substantially reduces the training data required relative to conventional force-matching methods and enables high-fidelity models in which each coarse-grained site represents hundreds to thousands of atoms. We demonstrate the method's versatility and effectiveness across a diverse range of chemical systems and phenomena, developing bottom-up, machine-learned models. These enable efficient modeling at micrometer and millimeter length scales, while retaining significant amounts of the atomic scale fidelity. These results establish implicit score matching as a practical route towards chemically accurate simulations that bridge molecular and mesoscopic scales.
ER -