Enhanced sampling of robust molecular datasets with uncertainty-based collective variables

Abstract

Generating a data set that is representative of the accessible configuration space of a molecular system is crucial for the robustness of machine learned interatomic potentials (MLIP). However, the complexity of molecular systems, characterized by intricate potential energy surfaces (PESs) with numerous local minima and energy barriers, presents a significant challenge. Traditional methods of data generation, such as random sampling or exhaustive exploration, are either intractable or may not capture rare, but highly informative configurations. In this study, we propose a method that leverages uncertainty as the collective variable (CV) to guide the acquisition of chemically-relevant data points, focusing on regions of the configuration space where ML model predictions are most uncertain. This approach employs a Gaussian Mixture Model-based uncertainty metric from a single model as the CV for biased molecular dynamics simulations. The effectiveness of our approach in overcoming energy barriers and exploring unseen energy minima, thereby enhancing the data set in an active learning framework, is demonstrated on the alanine dipeptide benchmark system.

arXiv comment13 pages, 4 figures, 10 pages of Supplementary Information

References in corpus (18)

• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
• Active learning of linearly parametrized interatomic potentials
• MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields
• Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulations
• From ab initio quantum chemistry to molecular dynamics: The delicate case of hydrogen bonding in ammonia
• How to validate machine-learned interatomic potentials
• New fitting scheme to obtain effective potential from Car-Parrinello molecular dynamics simulations: Application to silica
• How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks
• Generative Models for Automatic Chemical Design
• Single-model uncertainty quantification in neural network potentials does not consistently outperform model ensembles
• Differentiable sampling of molecular geometries with uncertainty-based adversarial attacks
• Fast Uncertainty Estimates in Deep Learning Interatomic Potentials
• Uncertainty-biased molecular dynamics for learning uniformly accurate interatomic potentials
• Differentiable Molecular Simulations for Control and Learning
• Transferability of machine learning potentials: Protonated water neural network potential applied to the protonated water hexamer
• Data efficiency and extrapolation trends in neural network interatomic potentials
• Diagnostics of Data-Driven Models: Uncertainty Quantification of PM7 Semi-Empirical Quantum Chemical Method