Machine learning force fields and coarse-grained variables in molecular dynamics: application to materials and biological systems

Abstract

Machine learning encompasses a set of tools and algorithms which are now becoming popular in almost all scientific and technological fields. This is true for molecular dynamics as well, where machine learning offers promises of extracting valuable information from the enormous amounts of data generated by simulation of complex systems. We provide here a review of our current understanding of goals, benefits, and limitations of machine learning techniques for computational studies on atomistic systems, focusing on the construction of empirical force fields from ab-initio databases and the determination of reaction coordinates for free energy computation and enhanced sampling.

References in corpus (41)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• SchNet - a deep learning architecture for molecules and materials
• A Data-Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition
• PLUMED: a portable plugin for free-energy calculations with molecular dynamics
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• String Method for the Study of Rare Events
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Identification of slow molecular order parameters for Markov model construction
• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• Machine Learning Unifies the Modelling of Materials and Molecules
• On-the-fly machine learning force field generation: Application to melting points
• Machine-learning based interatomic potential for amorphous carbon
• Time-lagged autoencoders: Deep learning of slow collective variables for molecular kinetics
• Accelerating crystal structure prediction by machine-learning interatomic potentials with active learning
• Ab initio thermodynamics of liquid and solid water
• A Variational Approach to Enhanced Sampling and Free Energy Calculations
• 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
• Coarse Molecular Dynamics of a Peptide Fragment: Free Energy, Kinetics, and Long-Time Dynamics Computations
• Incorporating long-range physics in atomic-scale machine learning
• Variational Encoding of Complex Dynamics
• Atom-Density Representations for Machine Learning
• Nonlinear Discovery of Slow Molecular Modes using State-Free Reversible VAMPnets
• Variational Koopman models: slow collective variables and molecular kinetics from short off-equilibrium simulations
• Neural networks-based variationally enhanced sampling
• Efficient nonparametric $n$-body force fields from machine learning
• iMapD: intrinsic Map Dynamics exploration for uncharted effective free energy landscapes
• Identification of simple reaction coordinates from complex dynamics
• Effective dynamics using conditional expectations
• Molecular hydrodynamics from memory kernels
• Galerkin Approximation of Dynamical Quantities using Trajectory Data
• Solid Harmonic Wavelet Scattering for Predictions of Molecule Properties
• Navigating at Will on the Water Phase Diagram
• Equation of state of fluid methane from first principles with machine learning potentials
• Learning molecular energies using localized graph kernels
• Girsanov reweighting for path ensembles and Markov state models
• On the determination of probability density functions by using Neural Networks
• Binding Pathway of Opiates to $\mu$ Opioid Receptors Revealed by Unsupervised Machine Learning
• Properties of low-dimensional collective variables in the molecular dynamics of biopolymers

Cited by in corpus (27)

• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Enhanced sampling methods for molecular dynamics simulations
• Perspective on integrating machine learning into computational chemistry and materials science
• Graph Neural Networks for Molecules
• Towards empirical force fields that match experimental observables
• Graph Neural Networks Accelerated Molecular Dynamics
• Multiscale reweighted stochastic embedding (MRSE): Deep learning of collective variables for enhanced sampling
• Learning Mean-Field Equations from Particle Data Using WSINDy
• Contrastive Learning of Coarse-Grained Force Fields
• Soft Metamaterials: Adaptation and Intelligence
• Optimal reaction coordinates and kinetic rates from the projected dynamics of transition paths
• Manifold Learning in Atomistic Simulations: A Conceptual Review
• Solving eigenvalue PDEs of metastable diffusion processes using artificial neural networks
• Machine-Learned Atomic Cluster Expansion Potentials for Fast and Quantum-Accurate Thermal Simulations of Wurtzite AlN
• Autoencoders for dimensionality reduction in molecular dynamics: collective variable dimension, biasing and transition states
• Extending the atomic decomposition and many-body representation, a chemistry-motivated monomer-centered approach for machine learning potentials
• Condensed-phase molecular representation to link structure and thermodynamics in molecular dynamics
• Interpolating many-body wave functions for accelerated molecular dynamics on the near-exact electronic surface
• Predicting Change, Not States: An Alternate Framework for Neural PDE Surrogates
• A neural network potential with self-trained atomic fingerprints: a test with the mW water potential
• Hybrid localized graph kernel for machine learning energy-related properties of molecules and solids
• Maximum Information Extraction Via Clustering and Minimization of Shannon Entropy
• Explaining classifiers to understand coarse-grained models
• Considerations in the use of ML interaction potentials for free energy calculations
• Modeling Brownian Motion as a Timelapse of the Physical, Persistent, Trajectory
• Improving the Efficiency of Variationally Enhanced Sampling with Wavelet-Based Bias Potentials
• Consistent Projection of Langevin Dynamics: Preserving Thermodynamics and Kinetics in Coarse-Grained Models