Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems

Abstract

Machine learning models are poised to make a transformative impact on chemical sciences by dramatically accelerating computational algorithms and amplifying insights available from computational chemistry methods. However, achieving this requires a confluence and coaction of expertise in computer science and physical sciences. This review is written for new and experienced researchers working at the intersection of both fields. We first provide concise tutorials of computational chemistry and machine learning methods, showing how insights involving both can be achieved. We then follow with a critical review of noteworthy applications that demonstrate how computational chemistry and machine learning can be used together to provide insightful (and useful) predictions in molecular and materials modeling, retrosyntheses, catalysis, and drug design.

arXiv comment169 pages, 24 figures

References in corpus (157)

• Efficient Estimation of Word Representations in Vector Space
• Deep Learning in Neural Networks: An Overview
• DeepWalk: Online Learning of Social Representations
• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• Separable Dual Space Gaussian Pseudo-potentials
• Improving neural networks by preventing co-adaptation of feature detectors
• Escaping free-energy minima
• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Neural Message Passing for Quantum Chemistry
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Automatic chemical design using a data-driven continuous representation of molecules
• Global Optimization by Basin-Hopping and the Lowest Energy Structures of Lennard-Jones Clusters Containing up to 110 Atoms
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• 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
• Solving the Quantum Many-Body Problem with Artificial Neural Networks
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Learning to Plan Chemical Syntheses
• Pseudopotentials for high-throughput DFT calculations
• Machine Learning Force Fields
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
• Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• Deep Reinforcement Learning for De-Novo Drug Design
• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Unmasking Clever Hans Predictors and Assessing What Machines Really Learn
• A Performance and Cost Assessment of Machine Learning Interatomic Potentials
• Progress in Time-Dependent Density-Functional Theory
• Molecular Transformer - A Model for Uncertainty-Calibrated Chemical Reaction Prediction
• Big Data of Materials Science - Critical Role of the Descriptor
• Machine learning for molecular simulation
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• A Unifying Review of Deep and Shallow Anomaly Detection
• Comparing molecules and solids across structural and alchemical space
• Machine Learning Unifies the Modelling of Materials and Molecules
• W4 theory for computational thermochemistry: in pursuit of confident sub-kJ/mol predictions
• How to Explain Individual Classification Decisions
• By-passing the Kohn-Sham equations with machine learning
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Active learning of linearly parametrized interatomic potentials
• Machine learning prediction errors better than DFT accuracy
• Strong scaling of general-purpose molecular dynamics simulations on GPUs
• Machine-learning based interatomic potential for amorphous carbon
• Universal Fragment Descriptors for Predicting Electronic Properties of Inorganic Crystals
• Finding Density Functionals with Machine Learning
• Machine Learning of Molecular Electronic Properties in Chemical Compound Space
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• A Fourth-Generation High-Dimensional Neural Network Potential with Accurate Electrostatics Including Non-local Charge Transfer
• How van der Waals interactions determine the unique properties of water
• Deep neural network solution of the electronic Schrödinger equation
• Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
• Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks
• How to represent crystal structures for machine learning: towards fast prediction of electronic properties
• MolGAN: An implicit generative model for small molecular graphs
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• Learning Deep Generative Models of Graphs
• Density-functional tight-binding for beginners
• Correlated metals and the LDA+U method
• Neural networks for the prediction organic chemistry reactions
• Ab initio thermodynamics of liquid and solid water
• ANI-1: A data set of 20M off-equilibrium DFT calculations for organic molecules
• FCHL revisited: faster and more accurate quantum machine learning
• Physically-informed artificial neural networks for atomistic modeling of materials
• Alchemical and structural distribution based representation for improved QML
• Autonomous discovery in the chemical sciences part I: Progress
• Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
• Interatomic potentials for ionic systems with density functional accuracy based on charge densities obtained by a neural network
• AiiDA 1.0, a scalable computational infrastructure for automated reproducible workflows and data provenance
• The Lennard-Jones potential: when (not) to use it
• Hierarchical modeling of molecular energies using a deep neural network
• Automatic Selection of Atomic Fingerprints and Reference Configurations for Machine-Learning Potentials
• Materials Cartography: Representing and Mining Material Space Using Structural and Electronic Fingerprints
• WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials
• Quantum embedding theories
• Embedded Atom Neural Network Potentials: Efficient and Accurate Machine Learning with a Physically Inspired Representation
• Developing an improved Crystal Graph Convolutional Neural Network framework for accelerated materials discovery
• Autonomous discovery in the chemical sciences part II: Outlook
• An Accurate and Transferable Machine Learning Potential for Carbon
• A Transferable Machine-Learning Model of the Electron Density
• Mol-CycleGAN - a generative model for molecular optimization
• Deep Potential: a general representation of a many-body potential energy surface
• Rungs 1 to 4 of DFT Jacob's ladder: extensive test on the lattice constant, bulk modulus, and cohesive energy of solids
• sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
• Data-Driven Collective Variables for Enhanced Sampling
• Sparse learning of stochastic dynamic equations
• Syntax-Directed Variational Autoencoder for Structured Data
• Machine learning force fields and coarse-grained variables in molecular dynamics: application to materials and biological systems
• Resonant catalysis of thermally-activated chemical reactions via vibrational polaritons
• De novo exploration and self-guided learning of potential-energy surfaces
• Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
• Incorporating long-range physics in atomic-scale machine learning
• Extending the Accuracy of the SNAP Interatomic Potential Form
• Accurate molecular polarizabilities with coupled-cluster theory and machine learning
• Low-Scaling Algorithm for Nudged Elastic Band Calculations Using a Surrogate Machine Learning Model
• On the Completeness of Atomic Structure Representations
• DeePCG: constructing coarse-grained models via deep neural networks
• Unsupervised machine learning in atomistic simulations, between predictions and understanding
• Atom-Density Representations for Machine Learning
• Evidence for supercritical behavior of high-pressure liquid hydrogen
• Efficient global structure optimization with a machine learned surrogate model
• Structure-based Sampling and Self-correcting Machine Learning for Accurate Calculations of Potential Energy Surfaces and Vibrational Levels
• The Ground State Electronic Energy of Benzene
• Learning Multimodal Graph-to-Graph Translation for Molecular Optimization
• Neural networks-based variationally enhanced sampling
• Metrics for measuring distances in configuration spaces
• Orbital-free Bond Breaking via Machine Learning
• Feature Optimization for Atomistic Machine Learning Yields A Data-Driven Construction of the Periodic Table of the Elements
• QM7-X: A comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules
• Molecular geometry prediction using a deep generative graph neural network
• The Interplay of Structure and Dynamics in the Raman Spectrum of Liquid Water over the Full Frequency and Temperature Range
• Quantifying Density Errors in DFT
• iMapD: intrinsic Map Dynamics exploration for uncharted effective free energy landscapes
• Transferable atomic multipole machine learning models for small organic molecules
• Linking the Neural Machine Translation and the Prediction of Organic Chemistry Reactions
• Combining simulations and solution experiments as a paradigm for RNA force field refinement
• Operators in Machine Learning: Response Properties in Chemical Space
• Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces
• Machine Learning Configuration Interaction
• Machine Learning the Physical Non-Local Exchange-Correlation Functional of Density-Functional Theory
• A Universal Density Matrix Functional from Molecular Orbital-Based Machine Learning: Transferability across Organic Molecules
• Neural network based path collective variables for enhanced sampling of phase transformations
• Perspective: Energy Landscapes for Machine Learning
• Relation of centroid molecular dynamics and ring-polymer molecular dynamics to exact quantum dynamics
• Quasi-chemical Theories of Associated Liquids
• A local Bayesian optimizer for atomic structures
• Nonlocal Kinetic Energy Functionals By Functional Integration
• Quantum fluctuations and isotope effects in ab initio descriptions of water
• PubChemQC PM6: A dataset of 221 million molecules with optimized molecular geometries and electronic properties
• Real-space density functional theory on graphical processing units: computational approach and comparison to Gaussian basis set methods
• Neural-network Kohn-Sham exchange-correlation potential and its out-of-training transferability
• PiNN: A Python Library for Building Atomic Neural Networks of Molecules and Materials
• Autonomous robotic nanofabrication with reinforcement learning
• Isotope Effects in Liquid Water via Deep Potential Molecular Dynamics
• Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials
• Quantum-mechanical exploration of the phase diagram of water
• Functional Form of the Superconducting Critical Temperature from Machine Learning
• ATLAS: A Real-Space Finite-Difference Implementation of Orbital-Free Density Functional Theory
• Ensemble Learning of Coarse-Grained Molecular Dynamics Force Fields with a Kernel Approach
• Gaussian Mixture Based Enhanced Sampling
• Dynamical Strengthening of Covalent and Non-Covalent Molecular Interactions by Nuclear Quantum Effects at Finite Temperature
• A Novel Approach to Describe Chemical Environments in High Dimensional Neural Network Potentials
• On the Inductive Bias of Neural Tangent Kernels
• Machine learning enhanced global optimization by clustering local environments to enable bundled atomic energies
• Product Kernel Interpolation for Scalable Gaussian Processes
• Ionic and electronic transport properties in dense plasmas by orbital-free density functional theory
• Predicting the phase diagram of titanium dioxide with random search and pattern recognition
• Atoms in molecules from alchemical perturbation density functional theory
• Generating equilibrium molecules with deep neural networks
• An Introduction to Electrocatalyst Design using Machine Learning for Renewable Energy Storage
• Wasserstein metric for improved QML with adjacency matrix representations
• Extracting ice phases from liquid water: why a machine-learning water model generalizes so well

Cited by in corpus (58)

• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• SELFIES and the future of molecular string representations
• Higher-Order Explanations of Graph Neural Networks via Relevant Walks
• Inverse design of 3d molecular structures with conditional generative neural networks
• Neural Network Potentials for Chemistry: Concepts, Applications and Prospects
• Toward Explainable AI for Regression Models
• SchNetPack 2.0: A neural network toolbox for atomistic machine learning
• BIGDML: Towards Exact Machine Learning Force Fields for Materials
• Natural Language Processing Models That Automate Programming Will Transform Chemistry Research and Teaching
• Accurate large-scale simulations of siliceous zeolites by neural network potentials
• Benchmarking Basis Sets for Density Functional Theory Thermochemistry Calculations: Why unpolarised basis sets and the polarised 6-311G family should be avoided
• Adsorption at Nanoconfined Solid-Water Interfaces
• A reactive neural network framework for water-loaded acidic zeolites
• Imaginary components of out-of-time correlators and information scrambling for navigating the learning landscape of a quantum machine learning model
• Towards Linearly Scaling and Chemically Accurate Global Machine Learning Force Fields for Large Molecules
• Exploring the robust extrapolation of high-dimensional machine learning potentials
• ArcaNN: automated enhanced sampling generation of training sets for chemically reactive machine learning interatomic potentials
• Towards fully ab initio simulation of atmospheric aerosol nucleation
• Ligand additivity relationships enable efficient exploration of transition metal chemical space
• Transfer-Learned Potential Energy Surfaces: Towards Microsecond-Scale Molecular Dynamics Simulations in the Gas Phase at CCSD(T) Quality
• Collective Variables for Conformational Polymorphism in Molecular Crystals
• Neural Network Potential with Multi-Resolution Approach Enables Accurate Prediction of Reaction Free Energies in Solution
• Data efficiency and extrapolation trends in neural network interatomic potentials
• Spiers Memorial Lecture: How to do impactful research in artificial intelligence for chemistry and materials science
• Stress and heat flux via automatic differentiation
• Ab initio machine learning of phase space averages
• Unified Deep Learning Framework for Many-Body Quantum Chemistry via Green's Functions
• Analyzing Atomic Interactions in Molecules as Learned by Neural Networks
• Automatic feature selection and weighting in molecular systems using Differentiable Information Imbalance
• Algorithmic Differentiation for Automated Modeling of Machine Learned Force Fields
• Alchemical geometry relaxation
• Analyzing drop coalescence in microfluidic device with a deep learning generative model
• Super-resolution in Molecular Dynamics Trajectory Reconstruction with Bi-Directional Neural Networks
• SPA${}^{\mathrm{H}}$M(a,b): encoding the density information from guess Hamiltonian in quantum machine learning representations
• Machine learning for accuracy in density functional approximations
• Farthest Point Sampling in Property Designated Chemical Feature Space as a General Strategy for Enhancing the Machine Learning Model Performance for Small Scale Chemical Dataset
• Neural Quantum Propagators for Driven-Dissipative Quantum Dynamics
• Enhanced sampling of robust molecular datasets with uncertainty-based collective variables
• Efficient Generation of Stable Linear Machine-Learning Force Fields with Uncertainty-Aware Active Learning
• Integrated workflows and interfaces for data-driven semi-empirical electronic structure calculations
• Molecular Hessian matrices from a machine learning random forest regression algorithm
• Equivariant Electronic Hamiltonian Prediction with Many-Body Message Passing
• Enhancing lattice kinetic schemes for fluid dynamics with Lattice-Equivariant Neural Networks
• Deep quantum Monte Carlo approach for polaritonic chemistry
• Machine-Learned Potentials for Solvation Modeling
• Operator-induced structural variable selection for identifying materials genes
• Extending the definition of atomic basis sets to atoms with fractional nuclear charge
• Determinant- and Derivative-Free Quantum Monte Carlo Within the Stochastic Representation of Wavefunctions
• Excited-State Response Theory Within the Context of the Coupled-Cluster Formalism
• Lost Data in Electron Microscopy
• Orbital Mixer: Using Atomic Orbital Features for Basis Dependent Prediction of Molecular Wavefunctions
• Reconstructing Kernel-based Machine Learning Force Fields with Super-linear Convergence
• Deep-learning atomistic semi-empirical pseudopotential model for nanomaterials
• Transfer learning of many-body electronic correlation entropy from local measurements
• How to use Machine Learning to improve the discrimination between signal and background at particle colliders
• Optimal Sampling Density for Nonparametric Regression
• The informativeness of the gradient revisited
• A charge-density machine-learning workflow for computing the infrared spectrum of molecules