Investigating the hyperparameter space of deep neural network models for reaction coordinates

Abstract

Identifying reaction coordinates (RCs) is a key to understanding the mechanism of reactions in complex systems. Deep neural network (DNN) and machine learning approaches have become a powerful tool to find the RC. On the other hand, the hyperparameters that determine the DNN model structure can be highly flexible and are often selected intuitively and in a non-trivial and tedious manner. Furthermore, how the hyperparameter choice affects the RC quality remains obscure. Here, we explore the hyperparameter space by developing the hyperparameter tuning approach for the DNN model for RC and investigate how the parameter set affects the RC quality. The DNN model is built to predict the committor along the RC from various collective variables by minimizing the cross-entropy function; the hyperparameters are automatically determined using the Bayesian optimization method. The approach is applied to study the isomerization of alanine dipeptide in vacuum and in water, and the features that characterize the RC are extracted using the explainable AI (XAI) tools. The results show that the DNN models with diverse structures can describe the RC with similar accuracy, and furthermore, the features analyzed by XAI are highly similar. This indicates that the hyperparameter space is multimodal. The electrostatic potential from the solvent to the hydrogen H18 plays an important role in the RC in water. The current study shows that the structure of the DNN models can be rather flexible, while the suitably optimized models share the same features; therefore, a common mechanism from the RC can be extracted.

11 pages, 11 figures, 2 table for main text, 12 pages for supplementary material

References in corpus (12)

• A Unified Approach to Interpreting Model Predictions
• VAMPnets: Deep learning of molecular kinetics
• Molecular enhanced sampling with autoencoders: On-the-fly collective variable discovery and accelerated free energy landscape exploration
• Data-Driven Collective Variables for Enhanced Sampling
• Autonomous artificial intelligence discovers mechanisms of molecular self-organization in virtual experiments
• Neural network based path collective variables for enhanced sampling of phase transformations
• Learning reaction coordinates via cross-entropy minimization: Application to alanine dipeptide
• Deep Learning Collective Variables from Transition Path Ensemble
• Explaining reaction coordinates of alanine dipeptide isomerization obtained from deep neural networks using Explainable Artificial Intelligence (XAI)
• Deep Reinforcement Learning of Transition States
• Variational deep learning of equilibrium transition path ensembles
• Unveiling interatomic distances influencing the reaction coordinates in alanine dipeptide isomerization: An explainable deep learning approach

Cited by in corpus (3)

• Deep learning of committor for ion dissociation and interpretable analysis of solvent effects using atom-centered symmetry functions
• Revealing the Atomistic Mechanism of Rare Events in Molecular Dynamics
• Deep learning of committor and explainable artificial intelligence analysis for identifying reaction coordinates