Machine Learning Unifies the Modelling of Materials and Molecules

Abstract

Determining the stability of molecules and condensed phases is the cornerstone of atomistic modelling, underpinning our understanding of chemical and materials properties and transformations. Here we show that a machine learning model, based on a local description of chemical environments and Bayesian statistical learning, provides a unified framework to predict atomic-scale properties. It captures the quantum mechanical effects governing the complex surface reconstructions of silicon, predicts the stability of different classes of molecules with chemical accuracy, and distinguishes active and inactive protein ligands with more than 99% reliability. The universality and the systematic nature of our framework provides new insight into the potential energy surface of materials and molecules.

References in corpus (16)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• On representing chemical environments
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Moment Tensor Potentials: a class of systematically improvable interatomic potentials
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• Comparing molecules and solids across structural and alchemical space
• Machine learning prediction errors better than DFT accuracy
• Machine-learning based interatomic potential for amorphous carbon
• Finding Density Functionals with Machine Learning
• Machine Learning of Molecular Electronic Properties in Chemical Compound Space
• AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery
• Machine Learning Energies of 2 M Elpasolite (ABC${}_2$D${}_6$) Crystals
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• Defect Formation Energies without the Band-Gap Problem: Combining DFT and GW for the Silicon Self-Interstitial
• Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances

Cited by in corpus (198)

• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Machine Learning Force Fields
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• SISSO: a compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates
• Data-driven materials science: status, challenges and perspectives
• Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields
• Machine learning prediction errors better than DFT accuracy
• On-the-fly machine learning force field generation: Application to melting points
• Phase transitions of hybrid perovskites simulated by machine-learning force fields trained on-the-fly with Bayesian inference
• Big-Data Science in Porous Materials: Materials Genomics and Machine Learning
• Physics-inspired structural representations for molecules and materials
• Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation
• Deep neural network solution of the electronic Schrödinger equation
• Opportunities and Challenges for Machine Learning in Materials Science
• Machine learning a general purpose interatomic potential for silicon
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• Machine learning for electronically excited states of molecules
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• Alchemical and structural distribution based representation for improved QML
• Symmetry-Adapted Machine-Learning for Tensorial Properties of Atomistic Systems
• Automatic Selection of Atomic Fingerprints and Reference Configurations for Machine-Learning Potentials
• Chemical Shifts in Molecular Solids by Machine Learning
• An Accurate and Transferable Machine Learning Potential for Carbon
• A Transferable Machine-Learning Model of the Electron Density
• Applying machine learning techniques to predict the properties of energetic materials
• sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning
• Machine learning force fields and coarse-grained variables in molecular dynamics: application to materials and biological systems
• De novo exploration and self-guided learning of potential-energy surfaces
• Incorporating long-range physics in atomic-scale machine learning
• Machine learning enables long time scale molecular photodynamics simulations
• 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
• Coarse Graining Molecular Dynamics with Graph Neural Networks
• Committee neural network potentials control generalization errors and enable active learning
• Inclusion of machine learning kernel ridge regression potential energy surfaces in on-the-fly nonadiabatic molecular dynamics simulation
• Atom-Density Representations for Machine Learning
• Unsupervised machine learning in atomistic simulations, between predictions and understanding
• Comparison of permutationally invariant polynomials, neural networks, and Gaussian approximation potentials in representing water interactions through many-body expansions
• Fast and Accurate Uncertainty Estimation in Chemical Machine Learning
• End-to-end Symmetry Preserving Inter-atomic Potential Energy Model for Finite and Extended Systems
• Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning
• Machine Learning for Quantum Matter
• 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
• Automated Fitting of Neural Network Potentials at Coupled Cluster Accuracy: Protonated Water Clusters as Testing Ground
• Autonomous artificial intelligence discovers mechanisms of molecular self-organization in virtual experiments
• Neural Network Potentials for Chemistry: Concepts, Applications and Prospects
• Ab initio vibrational free energies including anharmonicity for multicomponent alloys
• Predicting molecular dipole moments by combining atomic partial charges and atomic dipoles
• Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces
• Training neural nets to learn reactive potential energy surfaces using interactive quantum chemistry in virtual reality
• Discriminative Cooperative Networks for Detecting Phase Transitions
• Uncertainty estimation for molecular dynamics and sampling
• Informing Geometric Deep Learning with Electronic Interactions to Accelerate Quantum Chemistry
• Transfer learning for materials informatics using crystal graph convolutional neural network
• Physically Motivated Recursively Embedded Atom Neural Networks: Incorporating Local Completeness and Nonlocality
• Graph convolutional neural networks as "general-purpose" property predictors: the universality and limits of applicability
• A local Bayesian optimizer for atomic structures
• Artificial Intelligent Atomic Force Microscope Enabled by Machine Learning
• High-Dimensional Neural Network Potentials for Magnetic Systems Using Spin-Dependent Atom-Centered Symmetry Functions
• Error-Controlled Exploration of Chemical Reaction Networks with Gaussian Processes
• Graph Neural Networks for Molecules
• Tutorial: How to Train a Neural Network Potential
• PubChemQC PM6: A dataset of 221 million molecules with optimized molecular geometries and electronic properties
• Ephemeral data derived potentials for random structure search
• Differentiable sampling of molecular geometries with uncertainty-based adversarial attacks
• Chemical diversity in molecular orbital energy predictions with kernel ridge regression
• Recursive evaluation and iterative contraction of $N$-body equivariant features
• PiNN: A Python Library for Building Atomic Neural Networks of Molecules and Materials
• BIGDML: Towards Exact Machine Learning Force Fields for Materials
• Optimizing Molecules using Efficient Queries from Property Evaluations
• Quantum Machine Learning Framework for Virtual Screening in Drug Discovery: a Prospective Quantum Advantage
• Equation of state of fluid methane from first principles with machine learning potentials
• i-PI 3.0: a flexible and efficient framework for advanced atomistic simulations
• A Bayesian approach to NMR crystal structure determination
• Phase Transitions of Zirconia: Machine-Learned Force Fields Beyond Density Functional Theory
• Real space mapping of topological invariants using artificial neural networks
• Graph Neural Networks Accelerated Molecular Dynamics
• Ensemble Learning of Coarse-Grained Molecular Dynamics Force Fields with a Kernel Approach
• Ranking the information content of distance measures
• Towards Electronic Structure-Based Ab-Initio Molecular Dynamics Simulations with Hundreds of Millions of Atoms
• Machine learning force fields based on local parametrization of dispersion interactions: Application to the phase diagram of C${}_{60}$
• A Perspective on Deep Learning for Molecular Modeling and Simulations
• An Experimentally Driven Automated Machine Learned lnter-Atomic Potential for a Refractory Oxide
• Molecular Force Fields with Gradient-Domain Machine Learning (GDML): Comparison and Synergies with Classical Force Fields
• Insights into lithium manganese oxide-water interfaces using machine learning potentials
• Ab-initio Structure and Thermodynamics of the RPBE-D3 Water/Vapor Interface by Neural-Network Molecular Dynamics
• Atomic Permutationally Invariant Polynomials for Fitting Molecular Force Fields
• Challenges for Machine Learning Force Fields in Reproducing Potential Energy Surfaces of Flexible Molecules
• Combining Machine Learning and Many-Body Calculations: Coverage-Dependent Adsorption of CO on Rh(111)
• Group-theoretical high-order rotational invariants for structural representations: Application to linearized machine learning interatomic potential
• Quantifying Chemical Structure and Atomic Energies in Amorphous Silicon Networks
• A deep neural network for molecular wave functions in quasi-atomic minimal basis representation
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Relevance of Rotationally Equivariant Convolutions for Predicting Molecular Properties
• Lifelong Machine Learning Potentials
• On Machine Learning Force Fields for Metallic Nanoparticles
• Machine learning the computational cost of quantum chemistry
• Machine learning for molecular dynamics with strongly correlated electrons
• Generalized convex hull construction for materials discovery
• A New Kind of Atlas of Zeolite Building Blocks
• Machine Learning - Driven Materials Discovery: Unlocking Next-Generation Functional Materials - A review
• Self-Parametrizing System-Focused Atomistic Models
• Predicting the phase diagram of titanium dioxide with random search and pattern recognition
• Sensitivity and Dimensionality of Atomic Environment Representations used for Machine Learning Interatomic Potentials
• 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
• Predicting Gas-Particle Partitioning Coefficients of Atmospheric Molecules with Machine Learning
• Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectorie
• Transferability of machine learning potentials: Protonated water neural network potential applied to the protonated water hexamer
• ænet-PyTorch: a GPU-supported implementation for machine learning atomic potentials training
• Detecting dynamic domains and local fluctuations in complex molecular systems via timelapse neighbors shuffling
• Machine learning the DFT potential energy surface for inorganic halide perovskite CsPbBr${}_3$
• Denoise Pretraining on Nonequilibrium Molecules for Accurate and Transferable Neural Potentials
• Inverse molecular design from first principles: tailoring organic chromophore spectra for optoelectronic applications
• UV-Visible Absorption Spectra of Solvated Molecules by Quantum Chemical Machine Learning
• Scalable neural networks for the efficient learning of disordered quantum systems
• Atomistic structure search using local surrogate mode
• Linear Jacobi-Legendre expansion of the charge density for machine learning-accelerated electronic structure calculations
• Controlled exploration of chemical space by machine learning of coarse-grained representations
• Neural Network Potential with Multi-Resolution Approach Enables Accurate Prediction of Reaction Free Energies in Solution
• Measuring transferability issues in machine-learning force fields: The example of Gold-Iron interactions with linearized potentials
• Prediction of stable Li-Sn compounds: boosting ab initio searches with neural network potentials
• Optimal radial basis for density-based atomic representations
• Atomic structure optimization with machine-learning enabled interpolation between chemical elements
• Data efficiency and extrapolation trends in neural network interatomic potentials
• Hybrid Classical/Machine-Learning Force Fields for the Accurate Description of Molecular Condensed-Phase Systems
• Representations and Strategies for Transferable Machine Learning Models in Chemical Discovery
• Free energy calculation of crystalline solids using normalizing flow
• Quantum chemical roots of machine-learning molecular similarity descriptors
• Chemical Bonding in Metallic Glasses from Machine Learning and Crystal Orbital Hamilton Population
• The fundamentals of quantum machine learning
• Grain Boundary Segregation Predicted by Quantum-Accurate Segregation Spectra but not by Classical Models
• Infrared spectra of neutral polycyclic aromatic hydrocarbons by machine learning
• A machine learning potential for simulating infrared spectra of nanosilicate clusters
• Wasserstein metric for improved QML with adjacency matrix representations
• Learning the energy curvature versus particle number in approximate density functionals
• Assessing the persistence of chalcogen bonds in solution with neural network potentials
• Mean-Field Density Matrix Decompositions
• Learning on-top: regressing the on-top pair density for real-space visualization of electron correlation
• Interactive Human-Machine Learning Framework for Modelling of Ferroelectric-Dielectric Composites
• Heterogeneous Molecular Graph Neural Networks for Predicting Molecule Properties
• Machine-learning of atomic-scale properties based on physical principles
• Improved decision making with similarity based machine learning: Applications in chemistry
• Proper Orthogonal Descriptors for Efficient and Accurate Interatomic Potentials
• Supervised learning of few dirty bosons with variable particle number
• Construction of Machine Learned Force Fields with Quantum Chemical Accuracy: Applications and Chemical Insights
• Machine learning forces trained by Gaussian process in liquid states: Transferability to temperature and pressure
• Unsupervised learning-based structural analysis: Search for a characteristic low-dimensional space by local structures in atomistic simulations
• The Conformational Space of a Flexible Amino Acid at Metallic Surfaces
• Accurate prediction of structural and mechanical properties on amorphous materials enabled through machine-learning potentials: a case study of silicon nitride
• Machine Learning Inference of Molecular Dipole Moment in Liquid Water
• Extending the reach of quantum computing for materials science with machine learning potentials
• CoRe Optimizer: An All-in-One Solution for Machine Learning
• Accurate Molecular Dynamics Enabled by Efficient Physically-Constrained Machine Learning Approaches
• Compressing physical properties of atomic species for improving predictive chemistry
• Machine learning at the atomic-scale
• Discovery of structure-property relations for molecules via hypothesis-driven active learning over the chemical space
• Fast proper orthogonal descriptors for many-body interatomic potentials
• Accelerating the theoretical study of Li-polysulphide adsorption on single-atom catalysts via machine learning approaches
• Advancing descriptor search in materials science: feature engineering and selection strategies
• Efficient Generation of Stable Linear Machine-Learning Force Fields with Uncertainty-Aware Active Learning
• Exploring the energy landscape of aluminas through machine learning interatomic potential
• Locally Spontaneous Dynamic Oxygen Migration on Biphenylene: A DFT Study
• Molecular Dipole Moment Learning via Rotationally Equivariant Gaussian Process Regression with Derivatives in Molecular-orbital-based Machine Learning
• Electronic Descriptors for Supervised Spectroscopic Predictions
• Physics-guided descriptors for prediction of structural polymorphs
• Learning intermolecular forces at liquid-vapor interfaces
• Compressing and forecasting atomic material simulations with descriptors
• Hierarchical quantum embedding by machine learning for large molecular assemblies
• Superconductor discovery in the emerging paradigm of Materials Informatics
• The impact of static distortion waves on superlubricity
• Modeling Chemical Exfoliation of Non-van der Waals Chromium Sulfides by Machine Learning Interatomic Potentials and Monte Carlo Simulations
• Accelerating structure search using atomistic graph-based classifiers
• A Fuzzy Classification Framework to Identify Equivalent Atoms in Complex Materials and Molecules
• Machine-learning Based Extraction of the Short-Range Part of the Interaction in Non-contact Atomic Force Microscopy
• Lifelong Machine Learning Potentials for Chemical Reaction Network Explorations
• Investigating 3D Atomic Environments for Enhanced QSAR
• Machine Learning S-Wave Scattering Phase Shifts Bypassing the Radial Schrödinger Equation
• Ab initio machine learning in chemical compound space
• Towards Commodity, Web-Based Augmented Reality Applications for Research and Education in Chemistry and Structural Biology
• Surrogate-Based Black-Box Optimization Method for Costly Molecular Properties
• Structure-Driven Prediction of Magnetic Order in Uranium Compounds
• Predicting band gaps and band-edge positions of oxide perovskites using DFT and machine learning
• Deep-learning atomistic semi-empirical pseudopotential model for nanomaterials
• Scalable Training of Neural Network Potentials for Complex Interfaces Through Data Augmentation
• A Kernel-based Machine Learning Approach to Computing Quasiparticle Energies within Many-Body Green's Functions Theory
• Efficiency of neural-network state representations of one-dimensional quantum spin systems
• Anharmonic infrared spectra of cationic pyrene and superhydrogenated derivatives
• Representing spherical tensors with scalar-based machine-learning models
• Integer linear programming for unsupervised training set selection in molecular machine learning
• Thermal transport and phase transitions of zirconia by on-the-fly machine-learned interatomic potentials
• Learning Atomic Multipoles: Prediction of the Electrostatic Potential with Equivariant Graph Neural Networks
• Accelerated Simulations of Molecular Systems through Learning of their Effective Dynamics
• Improving Molecular Force Fields Across Configurational Space by Combining Supervised and Unsupervised Machine Learning
• Combining DFT with ML to study size specific interactions between metal clusters and adsorbates
• Compressing local atomic neighbourhood descriptors