Compressing physics with an autoencoder: Creating an atomic species representation to improve machine learning models in the chemical sciences

Accurate Probabilities for Highly Activated Reaction of Polyatomic Molecules on Surfaces Using a High-Dimensional Neural Network Potential: CHD3 + Cu(111)

(2019) Nick Gerrits et al.   Journal of Physical Chemistry Letters

Learning from Failure: Predicting Electronic Structure Calculation Outcomes with Machine Learning Models

(2019) Chenru Duan et al.   Journal of Chemical Theory and Computation

Designing in the Face of Uncertainty: Exploiting Electronic Structure and Machine Learning Models for Discovery in Inorganic Chemistry

(2019) Jon Paul Janet et al.   INORGANIC CHEMISTRY

Parallel Multistream Training of High-Dimensional Neural Network Potentials

(2019) Andreas Singraber et al.   Journal of Chemical Theory and Computation

SchNet – A deep learning architecture for molecules and materials

(2018) K. T. Schütt et al.   JOURNAL OF CHEMICAL PHYSICS

Alchemical and structural distribution based representation for universal quantum machine learning

(2018) Felix A. Faber et al.   JOURNAL OF CHEMICAL PHYSICS

wACSF—Weighted atom-centered symmetry functions as descriptors in machine learning potentials

(2018) M. Gastegger et al.   JOURNAL OF CHEMICAL PHYSICS

Metadynamics for training neural network model chemistries: A competitive assessment

(2018) John E. Herr et al.   JOURNAL OF CHEMICAL PHYSICS

Less is more: Sampling chemical space with active learning

(2018) Justin S. Smith et al.   JOURNAL OF CHEMICAL PHYSICS

Constant size descriptors for accurate machine learning models of molecular properties

(2018) Christopher R. Collins et al.   JOURNAL OF CHEMICAL PHYSICS

Deoxyfluorination with Sulfonyl Fluorides: Navigating Reaction Space with Machine Learning

(2018) Matthew K. Nielsen et al.   JOURNAL OF THE AMERICAN CHEMICAL SOCIETY

Deep Potential Molecular Dynamics: A Scalable Model with the Accuracy of Quantum Mechanics

(2018) Linfeng Zhang et al.   PHYSICAL REVIEW LETTERS

Learning atoms for materials discovery

(2018) Quan Zhou et al.   PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA

Predicting reaction performance in C–N cross-coupling using machine learning

(2018) Derek T. Ahneman et al.   SCIENCE

The TensorMol-0.1 model chemistry: a neural network augmented with long-range physics

(2018) Kun Yao et al.   Chemical Science

“Found in Translation”: predicting outcomes of complex organic chemistry reactions using neural sequence-to-sequence models

(2018) Philippe Schwaller et al.   Chemical Science

Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis

(2018) Matthew Welborn et al.   Journal of Chemical Theory and Computation

Transferable Dynamic Molecular Charge Assignment Using Deep Neural Networks

(2018) Benjamin Nebgen et al.   Journal of Chemical Theory and Computation

Discovering a Transferable Charge Assignment Model Using Machine Learning

(2018) Andrew E. Sifain et al.   Journal of Physical Chemistry Letters

Planning chemical syntheses with deep neural networks and symbolic AI

(2018) Marwin H. S. Segler et al.   NATURE

A Density Functional Tight Binding Layer for Deep Learning of Chemical Hamiltonians

(2018) Haichen Li et al.   Journal of Chemical Theory and Computation

Rational Density Functional Selection Using Game Theory

(2017) Suzanne McAnanama-Brereton et al.   Journal of Chemical Information and Modeling

The many-body expansion combined with neural networks

(2017) Kun Yao et al.   JOURNAL OF CHEMICAL PHYSICS

Prediction Errors of Molecular Machine Learning Models Lower than Hybrid DFT Error

(2017) Felix A. Faber et al.   Journal of Chemical Theory and Computation

Tinker-OpenMM: Absolute and relative alchemical free energies using AMOEBA on GPUs

(2017) Matthew Harger et al.   JOURNAL OF COMPUTATIONAL CHEMISTRY

Impact of domain knowledge on blinded predictions of binding energies by alchemical free energy calculations

(2017) Antonia S. J. S. Mey et al.   JOURNAL OF COMPUTER-AIDED MOLECULAR DESIGN

Free Energy Methods in Drug Design: Prospects of “Alchemical Perturbation” in Medicinal Chemistry

(2017) Billy J. Williams-Noonan et al.   JOURNAL OF MEDICINAL CHEMISTRY

Intrinsic Bond Energies from a Bonds-in-Molecules Neural Network

(2017) Kun Yao et al.   Journal of Physical Chemistry Letters

Machine learning molecular dynamics for the simulation of infrared spectra

(2017) Michael Gastegger et al.   Chemical Science

ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost

(2017) J. S. Smith et al.   Chemical Science

Quantum-chemical insights from deep tensor neural networks

(2017) Kristof T. Schütt et al.   Nature Communications

Bypassing the Kohn-Sham equations with machine learning

(2017) Felix Brockherde et al.   Nature Communications

Fragment optimization for GPCRs by molecular dynamics free energy calculations: Probing druggable subpockets of the A 2A adenosine receptor binding site

(2017) Pierre Matricon et al.   Scientific Reports

Retrosynthetic Reaction Prediction Using Neural Sequence-to-Sequence Models

(2017) Bowen Liu et al.   ACS Central Science

Machine learning unifies the modeling of materials and molecules

(2017) Albert P. Bartók et al.   Science Advances

Machine learning of accurate energy-conserving molecular force fields

(2017) Stefan Chmiela et al.   Science Advances

Communication: Understanding molecular representations in machine learning: The role of uniqueness and target similarity

(2016) Bing Huang et al.   JOURNAL OF CHEMICAL PHYSICS

Kinetic Energy of Hydrocarbons as a Function of Electron Density and Convolutional Neural Networks

(2016) Kun Yao et al.   Journal of Chemical Theory and Computation

Comparing molecules and solids across structural and alchemical space

(2016) Sandip De et al.   PHYSICAL CHEMISTRY CHEMICAL PHYSICS

Machine Learning Energies of 2 Million Elpasolite(ABC2D6)Crystals

(2016) Felix A. Faber et al.   PHYSICAL REVIEW LETTERS

The Chemical Space Project

(2015) Jean-Louis Reymond   ACCOUNTS OF CHEMICAL RESEARCH

Understanding machine-learned density functionals

(2015) Li Li et al.   INTERNATIONAL JOURNAL OF QUANTUM CHEMISTRY

Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space

(2015) Katja Hansen et al.   Journal of Physical Chemistry Letters

Advances in molecular quantum chemistry contained in the Q-Chem 4 program package

(2014) Yihan Shao et al.   MOLECULAR PHYSICS

Orbital-free bond breaking via machine learning

(2013) John C. Snyder et al.   JOURNAL OF CHEMICAL PHYSICS

Machine learning of molecular electronic properties in chemical compound space

(2013) Grégoire Montavon et al.   NEW JOURNAL OF PHYSICS

On representing chemical environments

(2013) Albert P. Bartók et al.   PHYSICAL REVIEW B

Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning

(2012) Matthias Rupp et al.   PHYSICAL REVIEW LETTERS

Atom-centered symmetry functions for constructing high-dimensional neural network potentials

(2011) Jörg Behler   JOURNAL OF CHEMICAL PHYSICS

Neural network potential-energy surfaces in chemistry: a tool for large-scale simulations

(2011) Jörg Behler   PHYSICAL CHEMISTRY CHEMICAL PHYSICS

Potential Energy Surfaces Fitted by Artificial Neural Networks

(2010) Chris M. Handley et al.   JOURNAL OF PHYSICAL CHEMISTRY A

A Survey on Transfer Learning

(2009) Sinno Jialin Pan et al.   IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING

Long-range corrected hybrid density functionals with damped atom–atom dispersion corrections

(2008) Jeng-Da Chai et al.   PHYSICAL CHEMISTRY CHEMICAL PHYSICS