Time-lagged autoencoders: Deep learning of slow collective variables for molecular kinetics

Abstract

Inspired by the success of deep learning techniques in the physical and chemical sciences, we apply a modification of an autoencoder type deep neural network to the task of dimension reduction of molecular dynamics data. We can show that our time-lagged autoencoder reliably finds low-dimensional embeddings for high-dimensional feature spaces which capture the slow dynamics of the underlying stochastic processes - beyond the capabilities of linear dimension reduction techniques.

References in corpus (19)

• Adam: A Method for Stochastic Optimization
• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Automatic chemical design using a data-driven continuous representation of molecules
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• A Data-Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition
• On Dynamic Mode Decomposition: Theory and Applications
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Identification of slow molecular order parameters for Markov model construction
• VAMPnets: Deep learning of molecular kinetics
• Data-driven model reduction and transfer operator approximation
• Variational cross-validation of slow dynamical modes in molecular kinetics
• Variational Koopman models: slow collective variables and molecular kinetics from short off-equilibrium simulations
• A variational conformational dynamics approach to the selection of collective variables in metadynamics
• Statistically optimal analysis of state-discretized trajectory data from multiple thermodynamic states
• A Kernel-Based Approach to Data-Driven Koopman Spectral Analysis
• Markov State Models from short non-Equilibrium Simulations - Analysis and Correction of Estimation Bias
• Variational approach for learning Markov processes from time series data
• xTRAM: Estimating equilibrium expectations from time-correlated simulation data at multiple thermodynamic states
• Spectral rate theory for projected two-state kinetics

Cited by in corpus (87)

• Machine Learning for Fluid Mechanics
• Machine learning and the physical sciences
• Machine Learning Force Fields
• Deep learning for universal linear embeddings of nonlinear dynamics
• Machine learning for molecular simulation
• Data-driven discovery of coordinates and governing equations
• SINDy-PI: A Robust Algorithm for Parallel Implicit Sparse Identification of Nonlinear Dynamics
• Data-Driven Collective Variables for Enhanced Sampling
• Machine learning force fields and coarse-grained variables in molecular dynamics: application to materials and biological systems
• Variational Encoding of Complex Dynamics
• Deep learning of dynamics and signal-noise decomposition with time-stepping constraints
• Coarse-Graining Auto-Encoders for Molecular Dynamics
• Robust flow field reconstruction from limited measurements via sparse representation
• Discovery of Nonlinear Multiscale Systems: Sampling Strategies and Embeddings
• Nonlinear Discovery of Slow Molecular Modes using State-Free Reversible VAMPnets
• Sparse Identification of Nonlinear Dynamics for Rapid Model Recovery
• Neural networks-based variationally enhanced sampling
• Physics-Informed Probabilistic Learning of Linear Embeddings of Non-linear Dynamics With Guaranteed Stability
• Graph Dynamical Networks for Unsupervised Learning of Atomic Scale Dynamics in Materials
• Guest Editorial: Special Topic on Data-enabled Theoretical Chemistry
• Physics-constrained, low-dimensional models for MHD: First-principles and data-driven approaches
• A unified framework for machine learning collective variables for enhanced sampling simulations: $\text{mlcolvar}$
• Learning Parameters and Constitutive Relationships with Physics Informed Deep Neural Networks
• From enhanced sampling to reaction profiles
• Kernel Learning for Robust Dynamic Mode Decomposition: Linear and Nonlinear Disambiguation Optimization (LANDO)
• Ensemble Learning of Coarse-Grained Molecular Dynamics Force Fields with a Kernel Approach
• Deep Learning Collective Variables from Transition Path Ensemble
• Time-Lagged t-Distributed Stochastic Neighbor Embedding (t-SNE) of Molecular Simulation Trajectories
• Simulations meet Machine Learning in Structural Biology
• From Fourier to Koopman: Spectral Methods for Long-term Time Series Prediction
• 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 Learning Models for Global Coordinate Transformations that Linearize PDEs
• Multiscale reweighted stochastic embedding (MRSE): Deep learning of collective variables for enhanced sampling
• Targeted free energy perturbation revisited: Accurate free energies from mapped reference potentials
• Predictive Collective Variable Discovery with Deep Bayesian Models
• Extracting Interpretable Physical Parameters from Spatiotemporal Systems using Unsupervised Learning
• Reaction Coordinates for Conformational Transitions using Linear Discriminant Analysis on Positions
• Capabilities and Limitations of Time-lagged Autoencoders for Slow Mode Discovery in Dynamical Systems
• PySINDy: A Python package for the Sparse Identification of Nonlinear Dynamics from Data
• Differentiable Molecular Simulations for Control and Learning
• Hydration free energies from kernel-based machine learning: Compound-database bias
• Exploring particle dynamics during self-organization processes via rotationally invariant latent representations
• Identification of MIMO Wiener-type Koopman Models for Data-Driven Model Reduction using Deep Learning
• A Deep Autoencoder Framework for Discovery of Metastable Ensembles in Biomacromolecules
• Temporally coherent backmapping of molecular trajectories from coarse-grained to atomistic resolution
• Adding alchemical variables to metadynamics to enhance sampling in free energy calculations
• Contour forward flux sampling: Sampling rare events along multiple collective variables
• Neural Canonical Transformation with Symplectic Flows
• Recent advances in describing and driving crystal nucleation using machine learning and artificial intelligence
• Predicting rare events using neural networks and short-trajectory data
• Data-driven Modeling of Rotating Detonation Waves
• Dimensionality reduction to maximize prediction generalization capability
• PySAGES: flexible, advanced sampling methods accelerated with GPUs
• Fast conformational clustering of extensive molecular dynamics simulation data
• Manifold Learning in Atomistic Simulations: A Conceptual Review
• Deeptime: a Python library for machine learning dynamical models from time series data
• Understanding the role of predictive time delay and biased propagator in RAVE
• Deep learning the slow modes for rare events sampling
• Deflation reveals dynamical structure in nondominant reaction coordinates
• Inexact iterative numerical linear algebra for neural network-based spectral estimation and rare-event prediction
• Deep Learning of Conjugate Mappings
• Information-driven transitions in projections of underdamped dynamics
• Multiresolution Convolutional Autoencoders
• Spectral Map for Slow Collective Variables, Markovian Dynamics, and Transition State Ensembles
• Note: Variational Encoding of Protein Dynamics Benefits from Maximizing Latent Autocorrelation
• Thermodynamically Optimized Machine-learned Reaction Coordinates for Hydrophobic Ligand Dissociation
• Learning Markovian Dynamics with Spectral Maps
• Identifying the leading dynamics of ubiquitin: a comparison between the tICA and the LE4PD slow fluctuations in amino acids' position
• Discovering time-varying aeroelastic models of a long-span suspension bridge from field measurements by sparse identification of nonlinear dynamical systems
• Hierarchical deep learning-based adaptive time-stepping scheme for multiscale simulations
• Unveiling interatomic distances influencing the reaction coordinates in alanine dipeptide isomerization: An explainable deep learning approach
• Effective equations for reaction coordinates in polymer transport
• Learning Interpretable Collective Variables for Spreading Processes on Networks
• Collective variables between large-scale states in turbulent convection
• Progress in deep Markov State Modeling: Coarse graining and experimental data restraints
• Kinematically consistent recurrent neural networks for learning inverse problems in wave propagation
• Intrinsic Dimensionality of Fermi-Pasta-Ulam-Tsingou High-Dimensional Trajectories Through Manifold Learning: A Linear Approach
• Exploring the Potential of Parallel Biasing in Flat Histogram Methods
• Operator Autoencoders: Learning Physical Operations on Encoded Molecular Graphs
• A purely data-driven framework for prediction, optimization, and control of networked processes: application to networked SIS epidemic model
• Deep learning of committor and explainable artificial intelligence analysis for identifying reaction coordinates
• Improving the Exploration of High Dimensional Free Energy Landscape by a Combination of Temperature Accelerated Sliced Sampling and Parallel Biasing
• Neural Network Surrogates for Free Energy Computation of Complex Chemical Systems
• A deep learning approach to the structural analysis of proteins
• Ligand dissociation mechanisms from all-atom simulations: Are we there yet?
• Variational embedding of protein folding simulations using gaussian mixture variational autoencoders