Manifold Learning in Atomistic Simulations: A Conceptual Review

Abstract

Analyzing large volumes of high-dimensional data requires dimensionality reduction: finding meaningful low-dimensional structures hidden in their high-dimensional observations. Such practice is needed in atomistic simulations of complex systems where even thousands of degrees of freedom are sampled. An abundance of such data makes gaining insight into a specific physical problem strenuous. Our primary aim in this review is to focus on unsupervised machine learning methods that can be used on simulation data to find a low-dimensional manifold providing a collective and informative characterization of the studied process. Such manifolds can be used for sampling long-timescale processes and free-energy estimation. We describe methods that can work on datasets from standard and enhanced sampling atomistic simulations. Unlike recent reviews on manifold learning for atomistic simulations, we consider only methods that construct low-dimensional manifolds based on Markov transition probabilities between high-dimensional samples. We discuss these techniques from a conceptual point of view, including their underlying theoretical frameworks and possible limitations.

References in corpus (56)

• Adam: A Method for Stochastic Optimization
• Scikit-learn: Machine Learning in Python
• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• Escaping free-energy minima
• PLUMED 2: New feathers for an old bird
• Well-Tempered Metadynamics: A Smoothly Converging and Tunable Free-Energy Method
• Parallel Tempering: Theory, Applications, and New Perspectives
• Identification of slow molecular order parameters for Markov model construction
• Machine learning for molecular simulation
• Efficient Algorithms for t-distributed Stochastic Neighborhood Embedding
• VAMPnets: Deep learning of molecular kinetics
• Accurate sampling using Langevin dynamics
• Enhanced Sampling in Molecular Dynamics Using Metadynamics, Replica-Exchange, and Temperature-Acceleration
• Time-lagged autoencoders: Deep learning of slow collective variables for molecular kinetics
• Rethinking Metadynamics: from bias potentials to probability distributions
• Enhanced sampling methods for molecular dynamics simulations
• A Variational Approach to Enhanced Sampling and Free Energy Calculations
• Caliber based spectral gap optimization of order parameters (SGOOP) for sampling complex molecular systems
• Data-driven model reduction and transfer operator approximation
• Molecular enhanced sampling with autoencoders: On-the-fly collective variable discovery and accelerated free energy landscape exploration
• Data-Driven Collective Variables for Enhanced Sampling
• An introduction to the Ginzburg-Landau theory of phase transitions and nonequilibrium patterns
• Variational cross-validation of slow dynamical modes in molecular kinetics
• Machine learning force fields and coarse-grained variables in molecular dynamics: application to materials and biological systems
• Unsupervised machine learning in atomistic simulations, between predictions and understanding
• Optimizing the ensemble for equilibration in broad-histogram Monte Carlo simulations
• A Unified Approach to Enhanced Sampling
• 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
• Autonomous artificial intelligence discovers mechanisms of molecular self-organization in virtual experiments
• Performance Limitations of Flat Histogram Methods and Optimality of Wang-Landau Sampling
• iMapD: intrinsic Map Dynamics exploration for uncharted effective free energy landscapes
• Learning Molecular Dynamics with Simple Language Model built upon Long Short-Term Memory Neural Network
• Spectral Generalized Multi-Dimensional Scaling
• An Analysis of the t-SNE Algorithm for Data Visualization
• Unfolding Hidden Barriers by Active Enhanced Sampling
• Finding Efficient Collective Variables: The Case of Crystallization
• Predicting reaction coordinates in energy landscapes with diffusion anisotropy
• Multiscale reweighted stochastic embedding (MRSE): Deep learning of collective variables for enhanced sampling
• Landmark Diffusion Maps (L-dMaps): Accelerated manifold learning out-of-sample extension
• How wet should be the reaction coordinate for ligand unbinding?
• Unsupervised landmark analysis for jump detection in molecular dynamics simulations
• Local and Global Perspectives on Diffusion Maps in the Analysis of Molecular Systems
• Reaction coordinates and rate constants for liquid droplet nucleation: quantifying the interplay between driving force and memory
• Computing committors via Mahalanobis diffusion maps with enhanced sampling data
• Spectral Map: Embedding Slow Kinetics in Collective Variables
• Visualising energy landscapes through manifold learning
• Reweighted Manifold Learning of Collective Variables from Enhanced Sampling Simulations
• On landmark selection and sampling in high-dimensional data analysis
• On UMAP's true loss function
• Stochastic Neighbor Embedding separates well-separated clusters
• Unsupervised learning of representative local atomic arrangements in molecular dynamics data
• Selecting High-Dimensional Representations of Physical Systems by Reweighted Diffusion Maps
• Enhanced Sampling with Machine Learning: A Review
• From $t$-SNE to UMAP with contrastive learning
• T-SNE Is Not Optimized to Reveal Clusters in Data

Cited by in corpus (2)

• Spectral Map for Slow Collective Variables, Markovian Dynamics, and Transition State Ensembles
• Learning Markovian Dynamics with Spectral Maps