Spectral Map: Embedding Slow Kinetics in Collective Variables

Abstract

The dynamics of physical systems that require high-dimensional representation can often be captured in a few meaningful degrees of freedom called collective variables (CVs). However, identifying CVs is challenging and constitutes a fundamental problem in physical chemistry. This problem is even more pronounced when CVs information about slow kinetics related to rare transitions between long-lived metastable states. To address this issue, we propose an unsupervised deep-learning method called spectral map. Our method constructs slow CVs by maximizing the spectral gap between slow and fast eigenvalues of a transition matrix estimated by an anisotropic diffusion kernel. We demonstrate our method in several high-dimensional reversible folding processes.

arXiv commentPublished version

References in corpus (11)

• VAMPnets: Deep learning of molecular kinetics
• Caliber based spectral gap optimization of order parameters (SGOOP) for sampling complex molecular systems
• Data-Driven Collective Variables for Enhanced Sampling
• Unsupervised machine learning in atomistic simulations, between predictions and understanding
• Autonomous artificial intelligence discovers mechanisms of molecular self-organization in virtual experiments
• iMapD: intrinsic Map Dynamics exploration for uncharted effective free energy landscapes
• Effective dynamics using conditional expectations
• Unfolding Hidden Barriers by Active Enhanced Sampling
• Multiscale reweighted stochastic embedding (MRSE): Deep learning of collective variables for enhanced sampling
• Reweighted Manifold Learning of Collective Variables from Enhanced Sampling Simulations
• Selecting High-Dimensional Representations of Physical Systems by Reweighted Diffusion Maps

Cited by in corpus (5)

• Enhanced Sampling in the Age of Machine Learning: Algorithms and Applications
• Manifold Learning in Atomistic Simulations: A Conceptual Review
• Spectral Map for Slow Collective Variables, Markovian Dynamics, and Transition State Ensembles
• Learning Markovian Dynamics with Spectral Maps
• Unraveling the Mechanism of Drug Binding to SARS-CoV-2 RNA Pseudoknot with Thermodynamics-Driven Machine Learning