Autonomous discovery in the chemical sciences part I: Progress

Abstract

This two-part review examines how automation has contributed to different aspects of discovery in the chemical sciences. In this first part, we describe a classification for discoveries of physical matter (molecules, materials, devices), processes, and models and how they are unified as search problems. We then introduce a set of questions and considerations relevant to assessing the extent of autonomy. Finally, we describe many case studies of discoveries accelerated by or resulting from computer assistance and automation from the domains of synthetic chemistry, drug discovery, inorganic chemistry, and materials science. These illustrate how rapid advancements in hardware automation and machine learning continue to transform the nature of experimentation and modelling. Part two reflects on these case studies and identifies a set of open challenges for the field.

Revised version available at 10.1002/anie.201909987

References in corpus (40)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Automatic chemical design using a data-driven continuous representation of molecules
• To Explain or to Predict?
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Learning to Plan Chemical Syntheses
• High-throughput electronic band structure calculations: challenges and tools
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Deep Reinforcement Learning for De-Novo Drug Design
• Explainable Machine Learning for Scientific Insights and Discoveries
• Less is more: sampling chemical space with active learning
• Deep learning for molecular design - a review of the state of the art
• Data-driven materials science: status, challenges and perspectives
• Active learning of linearly parametrized interatomic potentials
• Finding Density Functionals with Machine Learning
• Machine Learning of Molecular Electronic Properties in Chemical Compound Space
• Machine Learning Molecular Dynamics for the Simulation of Infrared Spectra
• VAMPnets: Deep learning of molecular kinetics
• Discovery of low thermal conductivity compounds with first-principles anharmonic lattice dynamics calculations and Bayesian optimization
• Prediction and accelerated laboratory discovery of previously unknown 18-electron ABX compounds
• Predicting Crystal Structures with Data Mining of Quantum Calculations
• Competitive Fragmentation Modeling of ESI-MS/MS spectra for putative metabolite identification
• Neural networks for the prediction organic chemistry reactions
• Boosting Docking-based Virtual Screening with Deep Learning
• Insightful classification of crystal structures using deep learning
• Accelerating Photovoltaic Materials Development via High-Throughput Experiments and Machine-Learning-Assisted Diagnosis
• Machine learning with systematic density-functional theory calculations: Application to melting temperatures of single and binary component solids
• Autonomous discovery in the chemical sciences part II: Outlook
• Exploration of Reaction Pathways and Chemical Transformation Networks
• Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis
• Automated Discovery of Elementary Chemical Reaction Steps Using Freezing String and Berny Optimization Methods
• Fast machine-learning online optimization of ultra-cold-atom experiments
• Rapid Prediction of Electron-Ionization Mass Spectrometry using Neural Networks
• The Exploration of Chemical Reaction Networks
• Coarse-Graining Auto-Encoders for Molecular Dynamics
• Modelling Chemical Reasoning to Predict Reactions
• Constructing first-principles phase diagrams of amorphous LixSi using machine-learning-assisted sampling with an evolutionary algorithm
• A Universal Density Matrix Functional from Molecular Orbital-Based Machine Learning: Transferability across Organic Molecules
• Error-Controlled Exploration of Chemical Reaction Networks with Gaussian Processes
• Machine Learning for Novel Thermal-Materials Discovery: Early Successes, Opportunities, and Challenges

Cited by in corpus (13)

• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Gryffin: An algorithm for Bayesian optimization of categorical variables informed by expert knowledge
• Bayesian optimization with known experimental and design constraints for chemistry applications
• Inverse methods for design of soft materials
• Towards the design of chemical reactions: Machine learning barriers of competing mechanisms in reactant space
• Olympus: a benchmarking framework for noisy optimization and experiment planning
• On-the-fly Autonomous Control of Neutron Diffraction via Physics-Informed Bayesian Active Learning
• Quantifying the performance of machine learning models in materials discovery
• Golem: An algorithm for robust experiment and process optimization
• Graph Machine Learning for Design of High-Octane Fuels
• Predicting Gas-Particle Partitioning Coefficients of Atmospheric Molecules with Machine Learning
• Spiers Memorial Lecture: How to do impactful research in artificial intelligence for chemistry and materials science
• Autonomous Drug Design with Multi-Armed Bandits