Saved in:
Bibliographic Details
Main Authors: Bachelor, Kevin, Murdeshwar, Sanya, Sabo, Daniel, Marinescu, Razvan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.17208
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917541415223296
author Bachelor, Kevin
Murdeshwar, Sanya
Sabo, Daniel
Marinescu, Razvan
author_facet Bachelor, Kevin
Murdeshwar, Sanya
Sabo, Daniel
Marinescu, Razvan
contents Machine-learned coarse-grained (CG) potentials are fast, but degrade over time when simulations reach under-sampled bio-molecular conformations, and generating widespread all-atom (AA) data to combat this is computationally infeasible. We propose a novel active learning (AL) framework for CG neural network potentials in molecular dynamics (MD). Building on the CGSchNet model, our method employs root mean squared deviation (RMSD)-based frame selection from MD simulations in order to generate data on-the-fly by querying an oracle during the training of a neural network potential. This framework preserves CG-level efficiency while correcting the model at precise, RMSD-identified coverage gaps. By training CGSchNet, a coarse-grained neural network potential, we empirically show that our framework explores previously unseen configurations and trains the model on unexplored regions of conformational space. Our active learning framework enables a CGSchNet model trained on the Chignolin protein to achieve a 33.05\% improvement in the Wasserstein-1 (W1) metric in Time-lagged Independent Component Analysis (TICA) space on an in-house benchmark suite.
format Preprint
id arxiv_https___arxiv_org_abs_2509_17208
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Active Learning for Machine Learning Driven Molecular Dynamics
Bachelor, Kevin
Murdeshwar, Sanya
Sabo, Daniel
Marinescu, Razvan
Machine Learning
Atomic and Molecular Clusters
I.6.5; I.2.1
Machine-learned coarse-grained (CG) potentials are fast, but degrade over time when simulations reach under-sampled bio-molecular conformations, and generating widespread all-atom (AA) data to combat this is computationally infeasible. We propose a novel active learning (AL) framework for CG neural network potentials in molecular dynamics (MD). Building on the CGSchNet model, our method employs root mean squared deviation (RMSD)-based frame selection from MD simulations in order to generate data on-the-fly by querying an oracle during the training of a neural network potential. This framework preserves CG-level efficiency while correcting the model at precise, RMSD-identified coverage gaps. By training CGSchNet, a coarse-grained neural network potential, we empirically show that our framework explores previously unseen configurations and trains the model on unexplored regions of conformational space. Our active learning framework enables a CGSchNet model trained on the Chignolin protein to achieve a 33.05\% improvement in the Wasserstein-1 (W1) metric in Time-lagged Independent Component Analysis (TICA) space on an in-house benchmark suite.
title Active Learning for Machine Learning Driven Molecular Dynamics
topic Machine Learning
Atomic and Molecular Clusters
I.6.5; I.2.1
url https://arxiv.org/abs/2509.17208