Explaining reaction coordinates of alanine dipeptide isomerization obtained from deep neural networks using Explainable Artificial Intelligence (XAI)

TL;DR

This paper introduces an explainable AI framework using LIME and SHAP to interpret reaction coordinates derived from deep neural networks for alanine dipeptide isomerization, enhancing understanding of collective variable contributions.

Contribution

The study applies XAI methods to elucidate how deep learning models determine reaction coordinates, addressing the challenge of interpretability in complex molecular systems.

Findings

XAI methods identify key collective variables influencing reaction coordinates.

LIME and SHAP results align with previous committor test analyses.

Framework is effective for systems with increasing degrees of freedom.

Abstract

A method for obtaining appropriate reaction coordinates is required to identify transition states distinguishing product and reactant in complex molecular systems. Recently, abundant research has been devoted to obtaining reaction coordinates using artificial neural networks from deep learning literature, where many collective variables are typically utilized in the input layer. However, it is difficult to explain the details of which collective variables contribute to the predicted reaction coordinates owing to the complexity of the nonlinear functions in deep neural networks. To overcome this limitation, we used Explainable Artificial Intelligence (XAI) methods of the Local Interpretable Model-agnostic Explanation (LIME) and the game theory-based framework known as Shapley Additive exPlanations (SHAP). We demonstrated that XAI enables us to obtain the degree of contribution of each collective variable to reaction coordinates that is determined by nonlinear regressions with deep learning for the committor of the alanine dipeptide isomerization in vacuum. In particular, both LIME and SHAP provide important features to the predicted reaction coordinates, which are characterized by appropriate dihedral angles consistent with those previously reported from the committor test analysis. The present study offers an AI-aided framework to explain the appropriate reaction coordinates, which acquires considerable significance when the number of degrees of freedom increases.