Molecular enhanced sampling with autoencoders: On-the-fly collective variable discovery and accelerated free energy landscape exploration

Abstract

Macromolecular and biomolecular folding landscapes typically contain high free energy barriers that impede efficient sampling of configurational space by standard molecular dynamics simulation. Biased sampling can artificially drive the simulation along pre-specified collective variables (CVs), but success depends critically on the availability of good CVs associated with the important collective dynamical motions. Nonlinear machine learning techniques can identify such CVs but typically do not furnish an explicit relationship with the atomic coordinates necessary to perform biased sampling. In this work, we employ auto-associative artificial neural networks ("autoencoders") to learn nonlinear CVs that are explicit and differentiable functions of the atomic coordinates. Our approach offers substantial speedups in exploration of configurational space, and is distinguished from exiting approaches by its capacity to simultaneously discover and directly accelerate along data-driven CVs. We demonstrate the approach in simulations of alanine dipeptide and Trp-cage, and have developed an open-source and freely-available implementation within OpenMM.

References in corpus (1)

• Well-Tempered Metadynamics: A Smoothly Converging and Tunable Free-Energy Method

Cited by in corpus (53)

• Machine learning for molecular simulation
• Data-Driven Collective Variables for Enhanced Sampling
• Machine learning force fields and coarse-grained variables in molecular dynamics: application to materials and biological systems
• Nonlinear Discovery of Slow Molecular Modes using State-Free Reversible VAMPnets
• Inverse methods for design of soft materials
• A unified framework for machine learning collective variables for enhanced sampling simulations: $\text{mlcolvar}$
• Analyzing and biasing simulations with PLUMED
• From enhanced sampling to reaction profiles
• Time-Lagged t-Distributed Stochastic Neighbor Embedding (t-SNE) of Molecular Simulation Trajectories
• 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)
• Multiscale reweighted stochastic embedding (MRSE): Deep learning of collective variables for enhanced sampling
• Predictive Collective Variable Discovery with Deep Bayesian Models
• Reaction Coordinates for Conformational Transitions using Linear Discriminant Analysis on Positions
• Descriptors-free Collective Variables From Geometric Graph Neural Networks
• Local and Global Perspectives on Diffusion Maps in the Analysis of Molecular Systems
• Time Series Forecasting Using Manifold 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
• Data-driven Control of Agent-based Models: an Equation/Variable-free Machine Learning Approach
• Recent advances in describing and driving crystal nucleation using machine learning and artificial intelligence
• PySAGES: flexible, advanced sampling methods accelerated with GPUs
• Unsupervised Diffusion and Volume Maximization-Based Clustering of Hyperspectral Images
• Optimal reaction coordinates and kinetic rates from the projected dynamics of transition paths
• Manifold Learning in Atomistic Simulations: A Conceptual Review
• Deeptime: a Python library for machine learning dynamical models from time series data
• Solving eigenvalue PDEs of metastable diffusion processes using artificial neural networks
• Deep learning the slow modes for rare events sampling
• Slow Invariant Manifolds of Singularly Perturbed Systems via Physics-Informed Machine Learning
• Autoencoders for dimensionality reduction in molecular dynamics: collective variable dimension, biasing and transition states
• Chemistrees: data driven identification of reaction pathways via machine learning
• Metatensor and metatomic: foundational libraries for interoperable atomistic machine learning
• Note: Variational Encoding of Protein Dynamics Benefits from Maximizing Latent Autocorrelation
• A physics-informed neural network method for the approximation of slow invariant manifolds for the general class of stiff systems of ODEs
• Thermodynamically Optimized Machine-learned Reaction Coordinates for Hydrophobic Ligand Dissociation
• WeTICA: A directed search weighted ensemble based enhanced sampling method to estimate rare event kinetics in a reduced dimensional space
• Can molecular dynamics be used to simulate biomolecular recognition?
• 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
• A critical comparison of general-purpose collective variables for crystal nucleation
• On the Correspondence between Gaussian Processes and Geometric Harmonics
• Progress in deep Markov State Modeling: Coarse graining and experimental data restraints
• Understanding ML driven HPC: Applications and Infrastructure
• Machine learning approaches for analyzing and enhancing molecular dynamics simulations
• Exploring the Potential of Parallel Biasing in Flat Histogram Methods
• Improving the Exploration of High Dimensional Free Energy Landscape by a Combination of Temperature Accelerated Sliced Sampling and Parallel Biasing
• Analysis of molecular dynamics simulation data via statistical distances between covariance matrices
• Deep learning of committor and explainable artificial intelligence analysis for identifying reaction coordinates
• Variational embedding of protein folding simulations using gaussian mixture variational autoencoders
• Using data-reduction techniques to analyse biomolecular trajectories
• Adaptive tensor train metadynamics for high-dimensional free energy exploration