Machine learning for molecular simulation

Abstract

Machine learning (ML) is transforming all areas of science. The complex and time-consuming calculations in molecular simulations are particularly suitable for a machine learning revolution and have already been profoundly impacted by the application of existing ML methods. Here we review recent ML methods for molecular simulation, with particular focus on (deep) neural networks for the prediction of quantum-mechanical energies and forces, coarse-grained molecular dynamics, the extraction of free energy surfaces and kinetics and generative network approaches to sample molecular equilibrium structures and compute thermodynamics. To explain these methods and illustrate open methodological problems, we review some important principles of molecular physics and describe how they can be incorporated into machine learning structures. Finally, we identify and describe a list of open challenges for the interface between ML and molecular simulation.

References in corpus (46)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Automatic chemical design using a data-driven continuous representation of molecules
• Methods for Interpreting and Understanding Deep Neural Networks
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• SchNet - a deep learning architecture for molecules and materials
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• On Dynamic Mode Decomposition: Theory and Applications
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Deep Reinforcement Learning for De-Novo Drug Design
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Identification of slow molecular order parameters for Markov model construction
• Unmasking Clever Hans Predictors and Assessing What Machines Really Learn
• By-passing the Kohn-Sham equations with machine learning
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra
• VAMPnets: Deep learning of molecular kinetics
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• Extended dynamic mode decomposition with dictionary learning: a data-driven adaptive spectral decomposition of the Koopman operator
• Time-lagged autoencoders: Deep learning of slow collective variables for molecular kinetics
• A Variational Approach to Enhanced Sampling and Free Energy Calculations
• ANI-1: A data set of 20M off-equilibrium DFT calculations for organic molecules
• Molecular enhanced sampling with autoencoders: On-the-fly collective variable discovery and accelerated free energy landscape exploration
• sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
• Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis
• Variational cross-validation of slow dynamical modes in molecular kinetics
• DeePCG: constructing coarse-grained models via deep neural networks
• Variational Encoding of Complex Dynamics
• Coarse-Graining Auto-Encoders for Molecular Dynamics
• Non-covalent interactions across organic and biological subsets of chemical space: Physics-based potentials parametrized from machine learning
• Nonlinear Discovery of Slow Molecular Modes using State-Free Reversible VAMPnets
• Structure-based Sampling and Self-correcting Machine Learning for Accurate Calculations of Potential Energy Surfaces and Vibrational Levels
• Variational Koopman models: slow collective variables and molecular kinetics from short off-equilibrium simulations
• Neural networks-based variationally enhanced sampling
• A variational conformational dynamics approach to the selection of collective variables in metadynamics
• Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces
• A Universal Density Matrix Functional from Molecular Orbital-Based Machine Learning: Transferability across Organic Molecules
• Learning Free Energy Landscapes Using Artificial Neural Networks
• Variational Selection of Features for Molecular Kinetics
• Free energy surface reconstruction from umbrella samples using Gaussian process regression
• Adversarial-Residual-Coarse-Graining: Applying machine learning theory to systematic molecular coarse-graining
• Coarse-graining Molecular Systems by Spectral Matching
• Optimal data-driven estimation of generalized Markov state models for non-equilibrium dynamics
• Accurate structure-based coarse-graining leads to consistent barrier-crossing dynamics

Cited by in corpus (136)

• Machine Learning Force Fields
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Big-Data Science in Porous Materials: Materials Genomics and Machine Learning
• DeePMD-kit v2: A software package for Deep Potential models
• Enhancing Computational Fluid Dynamics with Machine Learning
• A Fourth-Generation High-Dimensional Neural Network Potential with Accurate Electrostatics Including Non-local Charge Transfer
• GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations
• Machine learning for electronically excited states of molecules
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• Higher-Order Explanations of Graph Neural Networks via Relevant Walks
• 14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon
• Perspective on integrating machine learning into computational chemistry and materials science
• General-purpose machine-learned potential for 16 elemental metals and their alloys
• A practical guide to machine learning interatomic potentials -- Status and future
• Coarse Graining Molecular Dynamics with Graph Neural Networks
• Deep Learning with Coherent VCSEL Neural Networks
• Machine Learning in QM/MM Molecular Dynamics Simulations of Condensed-Phase Systems
• Autonomous artificial intelligence discovers mechanisms of molecular self-organization in virtual experiments
• Neural Network Potentials for Chemistry: Concepts, Applications and Prospects
• How to validate machine-learned interatomic potentials
• Ab-initio quantum chemistry with neural-network wavefunctions
• Toward Explainable AI for Regression Models
• Learning neural network potentials from experimental data via Differentiable Trajectory Reweighting
• DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials
• Strategies for the Construction of Machine-Learning Potentials for Accurate and Efficient Atomic-Scale Simulations
• High-Dimensional Neural Network Potentials for Magnetic Systems Using Spin-Dependent Atom-Centered Symmetry Functions
• Liquid-liquid transition in water from first principles
• SchNetPack 2.0: A neural network toolbox for atomistic machine learning
• A unified framework for machine learning collective variables for enhanced sampling simulations: $\text{mlcolvar}$
• Machine learning driven simulated deposition of carbon films: from low-density to diamondlike amorphous carbon
• Graph Neural Networks for Molecules
• Nonlinear stochastic modeling with Langevin regression
• Tutorial: How to Train a Neural Network Potential
• Thermodynamics and dielectric response of ${\text{BaTiO}}_3$ by data-driven modeling
• BIGDML: Towards Exact Machine Learning Force Fields for Materials
• Towards empirical force fields that match experimental observables
• Machine Learning Implicit Solvation for Molecular Dynamics
• Machine Learning Directed Optimization of Classical Molecular Modeling Force Fields
• Machine learning and excited-state molecular dynamics
• Learning reaction coordinates via cross-entropy minimization: Application to alanine dipeptide
• Graph Neural Networks Accelerated Molecular Dynamics
• Ensemble Learning of Coarse-Grained Molecular Dynamics Force Fields with a Kernel Approach
• Adsorption at Nanoconfined Solid-Water Interfaces
• Insights into lithium manganese oxide-water interfaces using machine learning potentials
• Molecular Force Fields with Gradient-Domain Machine Learning (GDML): Comparison and Synergies with Classical Force Fields
• Dynamical Strengthening of Covalent and Non-Covalent Molecular Interactions by Nuclear Quantum Effects at Finite Temperature
• Lifelong Machine Learning Potentials
• A Prompt-Engineered Large Language Model, Deep Learning Workflow for Materials Classification
• Multiscale reweighted stochastic embedding (MRSE): Deep learning of collective variables for enhanced sampling
• Learning to Simulate High Energy Particle Collisions from Unlabeled Data
• Targeted free energy perturbation revisited: Accurate free energies from mapped reference potentials
• Recipes for when Physics Fails: Recovering Robust Learning of Physics Informed Neural Networks
• Predicting Oxidation and Spin States by High-Dimensional Neural Networks: Applications to Lithium Manganese Oxide Spinels
• Reaction Coordinates for Conformational Transitions using Linear Discriminant Analysis on Positions
• Ligand-induced protein dynamics differences correlate with protein-ligand binding affinities: An unsupervised deep learning approach
• On the design space between molecular mechanics and machine learning force fields
• Towards fully ab initio simulation of atmospheric aerosol nucleation
• Thirty years of molecular dynamics simulations on posttranslational modifications of proteins
• DeepQMC: an open-source software suite for variational optimization of deep-learning molecular wave functions
• Impact of the characteristics of quantum chemical databases on machine learning predictions of tautomerization energies
• Nucleating a Different Coordination in a Crystal under Pressure: A Study of the B1-B2 Transition in NaCl by Metadynamics
• An experimentally validated neural-network potential energy surface for H atoms on free-standing graphene in full dimensionality
• Indirect Learning of Interatomic Potentials for Accelerated Materials Simulations
• High-dimensional neural network potentials for accurate vibrational frequencies: The formic acid dimer benchmark
• Accelerating the prediction of inorganic surfaces with machine learning interatomic potentials
• Geometry-enhanced Pre-training on Interatomic Potentials
• Accelerating discrete dislocation dynamics simulations with graph neural networks
• Accelerating fourth-generation machine learning potentials by quasi-linear scaling particle mesh charge equilibration
• A data-driven approach to determine dipole moments of diatomic molecules
• Accuracy of Charge Densities in Electronic Structure Calculations
• Free energy calculation of crystalline solids using normalizing flow
• Anomalous phase separation dynamics in a correlated electron system: machine-learning enabled large-scale kinetic Monte Carlo simulations
• Stress and heat flux via automatic differentiation
• Manifold Learning in Atomistic Simulations: A Conceptual Review
• Machine learning understands knotted polymers
• Analyzing Atomic Interactions in Molecules as Learned by Neural Networks
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• A machine learning potential for simulating infrared spectra of nanosilicate clusters
• Predicting the Electronic Density Response of Condensed-Phase Systems to Electric Field Perturbations
• Sampling Rare Conformational Transitions with a Quantum Computer
• Wasserstein metric for improved QML with adjacency matrix representations
• Wavelet Scattering Networks for Atomistic Systems with Extrapolation of Material Properties
• Random sampling versus active learning algorithms for machine learning potentials of quantum liquid water
• Machine learning predictions for local electronic properties of disordered correlated electron systems
• Efficient Composite Infrared Spectroscopy: Combining the Doubly-Harmonic Approximation with Machine Learning Potentials
• Anisotropic molecular coarse-graining by force and torque matching with neural networks
• Algorithmic Differentiation for Automated Modeling of Machine Learned Force Fields
• Counterfactual Learning on Graphs: A Survey
• Super-resolution in Molecular Dynamics Trajectory Reconstruction with Bi-Directional Neural Networks
• Neural Thermodynamic Integration: Free Energies from Energy-based Diffusion Models
• A Hessian-Based Assessment of Atomic Forces for Training Machine Learning Interatomic Potentials
• Size and Quality of Quantum Mechanical Data Sets for Training Neural Network Force Fields for Liquid Water
• Shadow molecular dynamics and atomic cluster expansions for flexible charge models
• Extending the reach of quantum computing for materials science with machine learning potentials
• Machine learning for structure-property relationships: Scalability and limitations
• CoRe Optimizer: An All-in-One Solution for Machine Learning
• Neural Quantum Propagators for Driven-Dissipative Quantum Dynamics
• Machine learning assisted coarse-grained molecular dynamics modeling of meso-scale interfacial fluids
• Discovery of structure-property relations for molecules via hypothesis-driven active learning over the chemical space
• Machine learning glass caging order parameters with an artificial nested neural network
• Iterative charge equilibration for fourth-generation high-dimensional neural network potentials
• Adaptive energy reference for machine-learning models of the electronic density of states
• Pre-training, fine-tuning, and distillation (PFD): Automatically generating machine learning force fields from universal models
• AMARO: All Heavy-Atom Transferable Neural Network Potentials of Protein Thermodynamics
• Efficient Generation of Stable Linear Machine-Learning Force Fields with Uncertainty-Aware Active Learning
• Building Robust Machine Learning Models for Small Chemical Science Data: The Case of Shear Viscosity
• Morphological Symmetries in Robotics
• Aqueous Solution Chemistry In Silico and the Role of Data Driven Approaches
• Learning intermolecular forces at liquid-vapor interfaces
• Melting curves of ice polymorphs in the vicinity of the liquid-liquid critical point
• Hierarchical quantum embedding by machine learning for large molecular assemblies
• Molecular relaxation by reverse diffusion with time step prediction
• ImmunoLingo: Linguistics-based formalization of the antibody language
• Atomistic Simulations of Oxide-Water Interfaces using Machine Learning Potentials
• Lifelong Machine Learning Potentials for Chemical Reaction Network Explorations
• Predicting trajectory behaviour via machine-learned invariant manifolds
• Free energy profiles for chemical reactions in solution from high-dimensional neural network potentials: The case of the Strecker synthesis
• Investigating Data Hierarchies in Multifidelity Machine Learning for Excitation Energies
• Hybrid localized graph kernel for machine learning energy-related properties of molecules and solids
• Predicting electronic screening for fast Koopmans spectral functional calculations
• A Bond-Based Machine Learning Model for Molecular Polarizabilities and A Priori Raman Spectra
• JaxSGMC: Modular stochastic gradient MCMC in JAX
• Finding Thermodynamically Favorable Pathways in Chemical Reaction Networks Using Flows in Hypergraphs and Mixed-Integer Linear Programming
• Translational eigenstates of He@C${}_{60}$ from four-dimensional \textit{ab initio} Potential Energy Surfaces interpolated using Gaussian Process Regression
• Machine-Learned Potentials for Solvation Modeling
• Reconstructing Kernel-based Machine Learning Force Fields with Super-linear Convergence
• Recovering Hidden Degrees of Freedom Using Gaussian Processes
• Atomistic Global Optimization X: A Python package for optimization of atomistic structures
• Self-consistency error correction for accurate machine learning potentials from variational Monte Carlo
• Uncertainty in AI-driven Monte Carlo simulations
• Active Learning of a Neural Network Potential for Large-Scale Atomistic Simulations of Polymer Electrolyte Membranes
• Phase classification using neural networks: application to supercooled, polymorphic core-softened mixtures
• Integer linear programming for unsupervised training set selection in molecular machine learning
• Deep learning of committor and explainable artificial intelligence analysis for identifying reaction coordinates
• Improving the Efficiency of Variationally Enhanced Sampling with Wavelet-Based Bias Potentials
• Improving Molecular Force Fields Across Configurational Space by Combining Supervised and Unsupervised Machine Learning