Deep learning of committor and explainable artificial intelligence analysis for identifying reaction coordinates

Abstract

In complex molecular systems, the reaction coordinate (RC) that characterizes transition pathways is essential to understand underlying molecular mechanisms. This review surveys a framework for identifying the RC by applying deep learning to the committor, which provides the most reliable measure of the progress along a transition path. The inputs to the neural network are collective variables (CVs) expressed as functions of atomic coordinates of the system, and the corresponding RC is predicted as the output by training the network on the committor as the learning target. Because deep learning models typically operate in a black-box manner, it is difficult to determine which input variables govern the predictions. The incorporation of eXplainable Artificial Intelligence (XAI) techniques enables quantitative assessment of the contributions of individual input variables to the predictions. This approach allows the identification of CVs that play dominant roles and demonstrates that the committor distribution on the surface using important CVs is separated by well-defined boundaries. The framework provides an explainable deep learning strategy for assigning a molecular mechanism from the RC and is applicable to a wide range of complex molecular systems.

17 pages, 12 figures, to appear in Chem. Phys. Rev

References in corpus (29)

• Escaping free-energy minima
• Accurate determination of crystal structures based on averaged local bond order parameters
• Machine learning for molecular simulation
• VAMPnets: Deep learning of molecular kinetics
• Time-lagged autoencoders: Deep learning of slow collective variables for 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
• State Predictive Information Bottleneck
• Neural network based path collective variables for enhanced sampling of phase transformations
• Identification of simple reaction coordinates from complex dynamics
• Recent Developments in Methods for Identifying Reaction Coordinates
• Computing Committor Functions for the Study of Rare Events Using Deep Learning
• Computing the Committor with the Committor: an Anatomy of the Transition State Ensemble
• Learning reaction coordinates via cross-entropy minimization: Application to alanine dipeptide
• Pathways to self-organization: crystallization via nucleation and growth
• Enhanced Sampling in the Age of Machine Learning: Algorithms and Applications
• Explaining reaction coordinates of alanine dipeptide isomerization obtained from deep neural networks using Explainable Artificial Intelligence (XAI)
• Deep Reinforcement Learning of Transition States
• Descriptors-free Collective Variables From Geometric Graph Neural Networks
• Maximum Likelihood Analysis of Reaction Coordinates during Solidification in Ni
• Data-driven Computation of Molecular Reaction Coordinates
• Identification of a Multi-Dimensional Reaction Coordinate for Crystal Nucleation in ${\text{Ni}}_3\text{Al}$
• Supervised Learning and the Finite-Temperature String Method for Computing Committor Functions and Reaction Rates
• Variational deep learning of equilibrium transition path ensembles
• Unveiling interatomic distances influencing the reaction coordinates in alanine dipeptide isomerization: An explainable deep learning approach
• Investigating the hyperparameter space of deep neural network models for reaction coordinates
• 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