Descriptors-free Collective Variables From Geometric Graph Neural Networks

Abstract

Enhanced sampling simulations make the computational study of rare events feasible. A large family of such methods crucially depends on the definition of some collective variables (CVs) that could provide a low-dimensional representation of the relevant physics of the process. Recently, many methods have been proposed to semi-automatize the CV design by using machine learning tools to learn the variables directly from the simulation data. However, most methods are based on feed-forward neural networks and require as input some user-defined physical descriptors. Here, we propose to bypass this step using a graph neural network to directly use the atomic coordinates as input for the CV model. This way, we achieve a fully automatic approach to CV determination that provides variables invariant under the relevant symmetries, especially the permutational one. Furthermore, we provide different analysis tools to favor the physical interpretation of the final CV. We prove the robustness of our approach using different methods from the literature for the optimization of the CV, and we prove its efficacy on several systems, including a small peptide, an ion dissociation in explicit solvent, and a simple chemical reaction.

References in corpus (10)

• Nonlinear Discovery of Slow Molecular Modes using State-Free Reversible VAMPnets
• A unified framework for machine learning collective variables for enhanced sampling simulations: $\text{mlcolvar}$
• Computing the Committor with the Committor: an Anatomy of the Transition State Ensemble
• Deep Learning Collective Variables from Transition Path Ensemble
• GraphVAMPNet, using graph neural networks and variational approach to markov processes for dynamical modeling of biomolecules
• Equivariant Graph Neural Networks for 3D Macromolecular Structure
• A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems
• Characterizing metastable states with the help of machine learning
• Advanced simulations with PLUMED: OPES and Machine Learning Collective Variables
• Rare Event Sampling using Smooth Basin Classification

Cited by in corpus (5)

• Enhanced Sampling in the Age of Machine Learning: Algorithms and Applications
• Everything everywhere all at once: a probability-based enhanced sampling approach to rare events
• 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