# Active Learning for Machine Learning Driven Molecular Dynamics Source: [Active Learning for Machine Learning Driven Molecular Dynamics]() Collection index: [llms.txt]() Data updated: 2026-05-30T05:00:04.258Z Authors: Kevin Bachelor, Sanya Murdeshwar, Daniel Sabo, Razvan Marinescu Published: 2025-09-21T19:26:32.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [TICA KDE distribution modeling on Chignolin protein](): TICA KDE distribution modeling; Chignolin protein; W1: 0.00022. - [Bond angle distribution modeling on Chignolin protein](): Bond angle distribution modeling; Chignolin protein; W1: 0.10148. - [Dihedral angle distribution modeling on Chignolin protein](): Dihedral angle distribution modeling; Chignolin protein; W1: 0.36378. - [Reaction coordinate distribution modeling on Chignolin protein](): Reaction coordinate distribution modeling; Chignolin protein; W1: 0.38302. ## Original sources and implementation [Original paper]() [PDF]()