Ab initio machine learning in chemical compound space

Abstract

Chemical compound space (CCS), the set of all theoretically conceivable combinations of chemical elements and (meta-)stable geometries that make up matter, is colossal. The first principles based virtual sampling of this space, for example in search of novel molecules or materials which exhibit desirable properties, is therefore prohibitive for all but the smallest sub-sets and simplest properties. We review studies aimed at tackling this challenge using modern machine learning techniques based on (i) synthetic data, typically generated using quantum mechanics based methods, and (ii) model architectures inspired by quantum mechanics. Such Quantum mechanics based Machine Learning (QML) approaches combine the numerical efficiency of statistical surrogate models with an {\em ab initio} view on matter. They rigorously reflect the underlying physics in order to reach universality and transferability across CCS. While state-of-the-art approximations to quantum problems impose severe computational bottlenecks, recent QML based developments indicate the possibility of substantial acceleration without sacrificing the predictive power of quantum mechanics.

References in corpus (83)

• Neural Message Passing for Quantum Chemistry
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• SchNet - a deep learning architecture for molecules and materials
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Learning to Plan Chemical Syntheses
• Two-dimensional materials from high-throughput computational exfoliation of experimentally known compounds
• On Calibration of Modern Neural Networks
• Machine Learning Force Fields
• AFLOW: An automatic framework for high-throughput materials discovery
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Machine learning phases of matter
• Machine Learning of Accurate Energy-Conserving Molecular Force Fields
• 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
• Big Data of Materials Science - Critical Role of the Descriptor
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• Less is more: sampling chemical space with active learning
• The Open Catalyst 2020 (OC20) Dataset and Community Challenges
• Machine Learning Unifies the Modelling of Materials and Molecules
• Active learning of linearly parametrized interatomic potentials
• Machine learning prediction errors better than DFT accuracy
• Finding Density Functionals with Machine Learning
• Nearsightedness of Electronic Matter
• How to represent crystal structures for machine learning: towards fast prediction of electronic properties
• Machine Learning Energies of 2 M Elpasolite (ABC${}_2$D${}_6$) Crystals
• Ab initio thermodynamics of liquid and solid water
• Machine learning quantum phases of matter beyond the fermion sign problem
• ANI-1: A data set of 20M off-equilibrium DFT calculations for organic molecules
• FCHL revisited: faster and more accurate quantum machine learning
• Resolving transition metal chemical space: feature selection for machine learning and structure-property relationships
• Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
• Reconstructing quantum states with generative models
• Interatomic potentials for ionic systems with density functional accuracy based on charge densities obtained by a neural network
• Achieving DFT accuracy with a machine-learning interatomic potential: thermomechanics and defects in bcc ferromagnetic iron
• Chemical Shifts in Molecular Solids by Machine Learning
• Deep Neural Networks for Accurate Predictions of Garnet Stability
• The discontinuous nature of the exchange-correlation functional -- critical for strongly correlated systems
• sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
• Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis
• Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
• Machine Learning for Quantum Mechanical Properties of Atoms in Molecules
• Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics
• Accurate molecular polarizabilities with coupled-cluster theory and machine learning
• On the Completeness of Atomic Structure Representations
• Atom-Density Representations for Machine Learning
• Evidence for supercritical behavior of high-pressure liquid hydrogen
• Fast and Accurate Uncertainty Estimation in Chemical Machine Learning
• Structure-based Sampling and Self-correcting Machine Learning for Accurate Calculations of Potential Energy Surfaces and Vibrational Levels
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• Machine learning for many-body physics: The case of the Anderson impurity model
• Transferable atomic multipole machine learning models for small organic molecules
• Deep Confidence: A Computationally Efficient Framework for Calculating Reliable Errors for Deep Neural Networks
• Guest Editorial: Special Topic on Data-enabled Theoretical Chemistry
• A local Bayesian optimizer for atomic structures
• Error-Controlled Exploration of Chemical Reaction Networks with Gaussian Processes
• Efficient and Accurate Simulations of Vibrational and Electronic Spectra with Symmetry-Preserving Neural Network Models for Tensorial Properties
• Solid Harmonic Wavelet Scattering for Predictions of Molecule Properties
• Modeling Electronic Quantum Transport with Machine Learning
• Extrapolating quantum observables with machine learning: Inferring multiple phase transitions from properties of a single phase
• Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models
• Gaussian Process-Based Refinement of Dispersion Corrections
• Gaussian Process Model for Collision Dynamics of Complex Molecules
• Molecular Force Fields with Gradient-Domain Machine Learning (GDML): Comparison and Synergies with Classical Force Fields
• Fast and accurate predictions of covalent bonds in chemical space
• Exploring water adsorption on isoelectronically doped graphene using alchemical derivatives
• Simulating solvation and acidity in complex mixtures with first-principles accuracy: the case of CH${}_3$SO${}_3$H and H${}_2$O${}_2$ in phenol
• ML Models of Vibrating H${}_2$CO: Comparing Reproducing Kernels, FCHL and PhysNet
• Machine Learned Hückel Theory: Interfacing Physics and Deep Neural Networks
• Nonempirical definition of the Mendeleev numbers: Organizing the chemical space
• Machine learning for many-body physics: efficient solution of dynamical mean-field theory
• Atoms in molecules from alchemical perturbation density functional theory
• 3DMolNet: A Generative Network for Molecular Structures
• Controlled exploration of chemical space by machine learning of coarse-grained representations
• A community-powered search of machine learning strategy space to find NMR property prediction models
• Large yet bounded: Spin gap ranges in carbenes
• Machine Learning with bond information for local structure optimizations in surface science
• The fundamentals of quantum machine learning
• Wasserstein metric for improved QML with adjacency matrix representations
• Dictionary of 140k GDB and ZINC derived AMONs
• AI Discovering a Coordinate System of Chemical Elements: Dual Representation by Variational Autoencoders

Cited by in corpus (1)

• Towards the design of chemical reactions: Machine learning barriers of competing mechanisms in reactant space