Machine Learning Force Fields

Published in

Chemical Reviews(2020)

External Links:

Generate Graph DownloadPDF

TL;DR

An overview of applications of ML-FFs and the chemical insights that can be obtained from them is given, and a step-by-step guide for constructing and testing them from scratch is given.

Abstract

In recent years, the use of machine learning (ML) in computational chemistry has enabled numerous advances previously out of reach due to the computational complexity of traditional electronic-structure methods. One of the most promising applications is the construction of ML-based force fields (FFs), with the aim to narrow the gap between the accuracy of ab initio methods and the efficiency of classical FFs. The key idea is to learn the statistical relation between chemical structure and potential energy without relying on a preconceived notion of fixed chemical bonds or knowledge about the relevant interactions. Such universal ML approximations are in principle only limited by the quality and quantity of the reference data used to train them. This review gives an overview of applications of ML-FFs and the chemical insights that can be obtained from them. The core concepts underlying ML-FFs are described in detail, and a step-by-step guide for constructing and testing them from scratch is given. The text concludes with a discussion of the challenges that remain to be overcome by the next generation of ML-FFs.

Authors

A. Tkatchenko

11 papers

Kristof T. Schütt

6 papers

M. Gastegger

4 papers

References329 items

Machine learning of solvent effects on molecular spectra and reactions

Machine Learning in QM/MM Molecular Dynamics Simulations of Condensed-Phase Systems.

Quantum chemical accuracy from density functional approximations via machine learning

Neural Network Potential Energy Surfaces for Small Molecules and Reactions.

A fourth-generation high-dimensional neural network potential with accurate electrostatics including non-local charge transfer

Machine Learning Force Fields

Published in

Chemical Reviews(2020)

External Links:

Generate Graph DownloadPDF

TL;DR

An overview of applications of ML-FFs and the chemical insights that can be obtained from them is given, and a step-by-step guide for constructing and testing them from scratch is given.

Abstract

Authors

A. Tkatchenko

11 papers

Kristof T. Schütt

6 papers

M. Gastegger

4 papers

References329 items

Machine learning of solvent effects on molecular spectra and reactions

Machine Learning in QM/MM Molecular Dynamics Simulations of Condensed-Phase Systems.

Quantum chemical accuracy from density functional approximations via machine learning

Neural Network Potential Energy Surfaces for Small Molecules and Reactions.

A fourth-generation high-dimensional neural network potential with accurate electrostatics including non-local charge transfer

Oliver T. Unke

4 papers

Stefan Chmiela

7 papers

I. Poltavsky

2 papers

K. Müller

12 papers

Quantum machine learning using atom-in-molecule-based fragments selected on the fly

Machine Learning Approaches toward Orbital-free Density Functional Theory: Simultaneous Training on the Kinetic Energy Density Functional and Its Functional Derivative

Molecular force fields with gradient-domain machine learning (GDML): Comparison and synergies with classical force fields.

On the role of gradients for machine learning of molecular energies and forces

Machine learning the ropes: principles, applications and directions in synthetic chemistry.

Machine Learning for Electronically Excited States of Molecules

Dynamical strengthening of covalent and non-covalent molecular interactions by nuclear quantum effects at finite temperature

Comprehensive Investigations of the Cl + CH 3 OH → HCl + CH 3 O/CH 2 OH Reaction: Validation of Experiment and Dynamic Insights

Accurate Many-Body Repulsive Potentials for Density-Functional Tight Binding from Deep Tensor Neural Networks.

Equivariant Flows: exact likelihood generative learning for symmetric densities

A deep neural network for molecular wave functions in quasi-atomic minimal basis representation.

Ensemble learning of coarse-grained molecular dynamics force fields with a kernel approach.

Pushing the Limit of Molecular Dynamics with Ab Initio Accuracy to 100 Million Atoms with Machine Learning

Raman spectrum and polarizability of liquid water from deep neural networks.

Isomerization and decomposition reactions of acetaldehyde relevant to atmospheric processes from dynamics simulations on neural network-based potential energy surfaces.

Directional Message Passing for Molecular Graphs

Reinforcement Learning for Molecular Design Guided by Quantum Mechanics

Combining SchNet and SHARC: The SchNarc Machine Learning Approach for Excited-State Dynamics

Thermal activation of methane by MgO+: temperature dependent kinetics, reactive molecular dynamics simulations and statistical modeling.

Free energy of proton transfer at the water–TiO2 interface from ab initio deep potential molecular dynamics†

Improved protein structure prediction using potentials from deep learning

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Simulating protein–ligand binding with neural network potentials

Exploring chemical compound space with quantum-based machine learning

Machine learning for protein folding and dynamics.

Reactive dynamics and spectroscopy of hydrogen transfer from neural network-based reactive potential energy surfaces

Machine learning for molecular simulation

High-dimensional potential energy surfaces for molecular simulations: from empiricism to machine learning

Generating valid Euclidean distance matrices

Deep-neural-network solution of the electronic Schrödinger equation

Boltzmann generators: Sampling equilibrium states of many-body systems with deep learning

Machine Learning Interatomic Potentials as Emerging Tools for Materials Science

FCHL revisited: Faster and more accurate quantum machine learning.

Embedded Atom Neural Network Potentials: Efficient and Accurate Machine Learning with a Physically Inspired Representation.

Unifying machine learning and quantum chemistry with a deep neural network for molecular wavefunctions

Reactive atomistic simulations of Diels-Alder reactions: The importance of molecular rotations.

High-Resolution Markov State Models for the Dynamics of Trp-Cage Miniprotein Constructed over Slow Folding Modes Identified by State-Free Reversible VAMPnets.

Cormorant: Covariant Molecular Neural Networks

Exhaustive state-to-state cross sections for reactive molecular collisions from importance sampling simulation and a neural network representation.

Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules

Reactive molecular dynamics for the [Cl–CH3–Br]− reaction in the gas phase and in solution: a comparative study using empirical and neural network force fields

DScribe: Library of Descriptors for Machine Learning in Materials Science

Kernel methods for detecting coherent structures in dynamical data.

Coarse-graining molecular systems by spectral matching.

Efficient multi-objective molecular optimization in a continuous latent space

Targeted Adversarial Learning Optimized Sampling.

Machine learning meets quantum physics

Unmasking Clever Hans predictors and assessing what machines really learn

PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments, and Partial Charges.

Sampling reactive regions in phase space by following the minimum dynamic path.

Nonlinear Discovery of Slow Molecular Modes using Hierarchical Dynamics Encoders

Molecular force fields with gradient-domain machine learning: Construction and application to dynamics of small molecules with coupled cluster forces.

Solvation Free Energy Calculations with Quantum Mechanics/Molecular Mechanics and Machine Learning Models.

sGDML: Constructing accurate and data efficient molecular force fields using machine learning

Machine Learning of Coarse-Grained Molecular Dynamics Force Fields

Machine learning enables long time scale molecular photodynamics simulations

Deep Learning for Nonadiabatic Excited-State Dynamics.

Generating equilibrium molecules with deep neural networks

Nuclear Quantum Effects in Sodium Hydroxide Solutions from Neural Network Molecular Dynamics Simulations.

Elucidating the Nuclear Quantum Dynamics of Intramolecular Double Hydrogen Transfer in Porphycene

Accurate molecular polarizabilities with coupled cluster theory and machine learning

Converged Colored Noise Path Integral Molecular Dynamics Study of the Zundel Cation Down to Ultralow Temperatures at Coupled Cluster Accuracy.

SchNetPack: A Deep Learning Toolbox For Atomistic Systems.

A Density Functional Tight Binding Layer for Deep Learning of Chemical Hamiltonians.

i-PI 2.0: A universal force engine for advanced molecular simulations

Operators in quantum machine learning: Response properties in chemical space.

3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data

Quantum-chemical insights from interpretable atomistic neural networks

Predicting molecular properties with covariant compositional networks.

Learning Effective Molecular Models from Experimental Observables.

End-to-end Symmetry Preserving Inter-atomic Potential Energy Model for Finite and Extended Systems

Deep Generative Markov State Models

Machine Learning a General-Purpose Interatomic Potential for Silicon

Machine learning approaches to evaluate correlation patterns in allosteric signaling: A case study of the PDZ2 domain.

A reactive, scalable, and transferable model for molecular energies from a neural network approach based on local information.

Neural networks vs Gaussian process regression for representing potential energy surfaces: A comparative study of fit quality and vibrational spectrum accuracy.

Perturbed path integrals in imaginary time: Efficiently modeling nuclear quantum effects in molecules and materials.

Realistic Atomistic Structure of Amorphous Silicon from Machine-Learning-Driven Molecular Dynamics.

Nuclear quantum effects enter the mainstream

Towards exact molecular dynamics simulations with machine-learned force fields

Gaussian Process Behaviour in Wide Deep Neural Networks

Less is more: sampling chemical space with active learning

Constructing High-Dimensional Neural Network Potential Energy Surfaces for Gas–Surface Scattering and Reactions

Alchemical and structural distribution based representation for universal quantum machine learning.

Metadynamics for training neural network model chemistries: A competitive assessment.

SchNet - A deep learning architecture for molecules and materials.

wACSF-Weighted atom-centered symmetry functions as descriptors in machine learning potentials.

Quantum effects on dislocation motion from ring-polymer molecular dynamics

DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics

Sparse learning of stochastic dynamical equations.

The TensorMol-0.1 model chemistry: a neural network augmented with long-range physics

Deep Neural Networks as Gaussian Processes

DeepLoc: prediction of protein subcellular localization using deep learning

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

100

Quantum and quasiclassical trajectory studies of rotational relaxation in Ar-N2+ collisions.

101

VAMPnets for deep learning of molecular kinetics

102

First Principles Neural Network Potentials for Reactive Simulations of Large Molecular and Condensed Systems.

103

Hierarchical modeling of molecular energies using a deep neural network.

104

Symmetry-Adapted Machine Learning for Tensorial Properties of Atomistic Systems.

105

The Expressive Power of Neural Networks: A View from the Width

106

Proton Network Flexibility Enables Robustness and Large Electric Fields in the Ketosteroid Isomerase Active Site.

107

Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics

108

Minimal distributed charges: Multipolar quality at the cost of point charge electrostatics.

109

Toolkit for the Construction of Reproducing Kernel-Based Representations of Data: Application to Multidimensional Potential Energy Surfaces

110

The "DNA" of chemistry: Scalable quantum machine learning with "amons"

111

The atomic simulation environment-a Python library for working with atoms.

112

Interpolation of intermolecular potentials using Gaussian processes.

113

SchNet: A continuous-filter convolutional neural network for modeling quantum interactions

114

Efficient and accurate machine-learning interpolation of atomic energies in compositions with many species

115

Machine learning molecular dynamics for the simulation of infrared spectra

116

FALKON: An Optimal Large Scale Kernel Method

117

Unified representation of molecules and crystals for machine learning

118

Neural Message Passing for Quantum Chemistry

119

First-Principles Models for van der Waals Interactions in Molecules and Materials: Concepts, Theory, and Applications.

120

A General and Adaptive Robust Loss Function

121

Machine learning of accurate energy-conserving molecular force fields

122

Machine learning based interatomic potential for amorphous carbon

123

Nuclear quantum effect with pure anharmonicity and the anomalous thermal expansion of silicon

124

ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost

125

Machine Learning Force Fields: Construction, Validation, and Outlook

126

Amp: A modular approach to machine learning in atomistic simulations

127

Quantum-chemical insights from deep tensor neural networks

128

An overview of gradient descent optimization algorithms

129

Bypassing the Kohn-Sham equations with machine learning

130

Communication: Understanding molecular representations in machine learning: The role of uniqueness and target similarity.

131

How van der Waals interactions determine the unique properties of water

132

Collision-induced rotational excitation in N2 (+)((2)Σg (+),v=0)-Ar: Comparison of computations and experiment.

133

Solving the quantum many-body problem with artificial neural networks

134

On Valid Optimal Assignment Kernels and Applications to Graph Classification

135

Quantum tunneling of thermal protons through pristine graphene.

136

Wavelet Scattering Regression of Quantum Chemical Energies

137

Molecular graph convolutions: moving beyond fingerprints

138

Preconditioning Kernel Matrices

139

Comparing molecules and solids across structural and alchemical space.

140

The Power of Depth for Feedforward Neural Networks

141

Order Matters: Sequence to sequence for sets

142

Modeling quantum nuclei with perturbed path integral molecular dynamics† †Electronic supplementary information (ESI) available: Heat capacity estimator and first and second-order cumulant expansions of the TI approach. See DOI: 10.1039/c5sc03443d

143

PyEMMA 2: A Software Package for Estimation, Validation, and Analysis of Markov Models.

144

Origin of the highly anisotropic thermal expansion of the semiconducting ZnSb and relations with its thermoelectric applications

145

What Not to Multiply Without Necessity

146

Convolutional Networks on Graphs for Learning Molecular Fingerprints

147

On the Expressive Power of Deep Learning: A Tensor Analysis

148

Machine Learning Energies of 2 Million Elpasolite (ABC_{2}D_{6}) Crystals.

149

Constructing high‐dimensional neural network potentials: A tutorial review

150

Correction: "On-the-fly" coupled cluster path-integral molecular dynamics: impact of nuclear quantum effects on the protonated water dimer.

151

Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

152

Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space

153

How Large Should the QM Region Be in QM/MM Calculations? The Case of Catechol O-Methyltransferase

154

Machine Learning: A Bayesian and Optimization Perspective

155

Crystal structure representations for machine learning models of formation energies

156

On Invariance and Selectivity in Representation Learning

157

Molecular dynamics with on-the-fly machine learning of quantum-mechanical forces.

158

Convolutional LSTM Networks for Subcellular Localization of Proteins

159

Dynamic properties of force fields.

160

Molecular Dynamics, Monte Carlo Simulations, and Langevin Dynamics: A Computational Review

161

Gaussian approximation potentials: A brief tutorial introduction

162

Interatomic potentials for ionic systems with density functional accuracy based on charge densities obtained by a neural network

163

Adam: A Method for Stochastic Optimization

164

Quantum chemistry structures and properties of 134 kilo molecules

165

Deep learning in neural networks: An overview

166

Multisurface Adiabatic Reactive Molecular Dynamics.

167

Computational studies of charge transfer in organic solar photovoltaic cells: A review

168

Force Field for Peptides and Proteins based on the Classical Drude Oscillator.

169

The Polarizable Atomic Multipole-based AMOEBA Force Field for Proteins.

170

Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies.

171

How to represent crystal structures for machine learning: Towards fast prediction of electronic properties

172

Constructive Approximation by Superposition of Sigmoidal Functions

173

Machine learning of molecular electronic properties in chemical compound space

174

Mature HIV-1 capsid structure by cryo-electron microscopy and all-atom molecular dynamics

175

A density-functional theory-based neural network potential for water clusters including van der Waals corrections.

176

Ring-polymer molecular dynamics: quantum effects in chemical dynamics from classical trajectories in an extended phase space.

177

ADADELTA: An Adaptive Learning Rate Method

178

Learning Invariant Representations of Molecules for Atomization Energy Prediction

179

Neural Networks: Tricks of the Trade

180

Enumeration of 166 Billion Organic Small Molecules in the Chemical Universe Database GDB-17

181

On representing chemical environments

182

Practical Bayesian Optimization of Machine Learning Algorithms

183

A neural network potential-energy surface for the water dimer based on environment-dependent atomic energies and charges.

184

Random Search for Hyper-Parameter Optimization

185

Multiconfiguration self-consistent field and multireference configuration interaction methods and applications.

186

Finding Density Functionals with Machine Learning

187

Fast and accurate modeling of molecular atomization energies with machine learning.

188

Molecular docking: a powerful approach for structure-based drug discovery.

189

Introduction to machine learning for brain imaging

190

Atom-centered symmetry functions for constructing high-dimensional neural network potentials.

191

Kernel Analysis of Deep Networks

192

Adaptive Subgradient Methods for Online Learning and Stochastic Optimization

193

Rectified Linear Units Improve Restricted Boltzmann Machines

194

A consistent and accurate ab initio parametrization of density functional dispersion correction (DFT-D) for the 94 elements H-Pu.

195

The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition by Trevor Hastie, Robert Tibshirani, Jerome Friedman

196

Ab initio molecular simulations with numeric atom-centered orbitals

197