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

We construct a robust chemistry consisting of a nearsighted neural network potential, TensorMol-0.1, with screened long-range electrostatic and van der Waals physics. It is offered in an open-source Python package and achieves millihartree accuracy and a scalability to tens-of-thousands of atoms on ordinary laptops.

[1]  B. Thole.  Molecular polarizabilities calculated with a modified dipole interaction , 1981 .

[2]  Thomas A. Halgren,et al.  Merck molecular force field. III. Molecular geometries and vibrational frequencies for MMFF94 , 1996, J. Comput. Chem..

[3]  G. Henkelman,et al.  A climbing image nudged elastic band method for finding saddle points and minimum energy paths , 2000 .

[4]  J. D. Gezelter,et al.  Is the Ewald summation still necessary? Pairwise alternatives to the accepted standard for long-range electrostatics. , 2006, The Journal of chemical physics.

[5]  Stefan Grimme,et al.  Semiempirical GGA‐type density functional constructed with a long‐range dispersion correction , 2006, J. Comput. Chem..

[6]  Michele Parrinello,et al.  Generalized neural-network representation of high-dimensional potential-energy surfaces. , 2007, Physical review letters.

[7]  M. Head‐Gordon,et al.  Long-range corrected hybrid density functionals with damped atom-atom dispersion corrections. , 2008, Physical chemistry chemical physics : PCCP.

[8]  M. Parrinello,et al.  Well-tempered metadynamics: a smoothly converging and tunable free-energy method. , 2008, Physical review letters.

[9]  Koichi Yamashita,et al.  Fitting sparse multidimensional data with low-dimensional terms , 2009, Comput. Phys. Commun..

[10]  R. Komanduri,et al.  Input vector optimization of feed-forward neural networks for fitting ab initio potential-energy databases. , 2010, The Journal of chemical physics.

[11]  R. Kondor,et al.  Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons. , 2009, Physical review letters.

[12]  P. Popelier,et al.  Potential energy surfaces fitted by artificial neural networks. , 2010, The journal of physical chemistry. A.

[13]  Nongnuch Artrith,et al.  High-dimensional neural-network potentials for multicomponent systems: Applications to zinc oxide , 2011 .

[14]  Michele Parrinello,et al.  Nucleation mechanism for the direct graphite-to-diamond phase transition. , 2011, Nature materials.

[15]  Alán Aspuru-Guzik,et al.  The Harvard Clean Energy Project: Large-Scale Computational Screening and Design of Organic Photovoltaics on the World Community Grid , 2011 .

[16]  J. Behler.  Neural network potential-energy surfaces in chemistry: a tool for large-scale simulations. , 2011, Physical chemistry chemical physics : PCCP.

[17]  Alán Aspuru-Guzik,et al.  Accelerated computational discovery of high-performance materials for organic photovoltaics by means of cheminformatics , 2011 .

[18]  Klaus-Robert Müller,et al.  Finding Density Functionals with Machine Learning , 2011, Physical review letters.

[19]  A. Tkatchenko,et al.  Accurate and efficient method for many-body van der Waals interactions. , 2012, Physical review letters.

[20]  Jörg Behler,et al.  A neural network potential-energy surface for the water dimer based on environment-dependent atomic energies and charges. , 2012, The Journal of chemical physics.

[21]  K. Müller,et al.  Fast and accurate modeling of molecular atomization energies with machine learning. , 2011, Physical review letters.

[22]  John C. Snyder,et al.  Orbital-free bond breaking via machine learning. , 2013, The Journal of chemical physics.

[23]  T. Morawietz,et al.  A density-functional theory-based neural network potential for water clusters including van der Waals corrections. , 2013, The journal of physical chemistry. A.

[24]  Volodymyr Babin,et al.  A Critical Assessment of Two-Body and Three-Body Interactions in Water. , 2012, Journal of chemical theory and computation.

[25]  Sanguthevar Rajasekaran,et al.  Accelerating materials property predictions using machine learning , 2013, Scientific Reports.

[26]  Corey Oses,et al.  Materials Cartography: Representing and Mining Material Space Using Structural and Electronic Fingerprints , 2014, 1412.4096.

[27]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[28]  Kristof T. Schütt,et al.  How to represent crystal structures for machine learning: Towards fast prediction of electronic properties , 2013, 1307.1266.

[29]  Alán Aspuru-Guzik,et al.  Lead candidates for high-performance organic photovoltaics from high-throughput quantum chemistry – the Harvard Clean Energy Project , 2014 .

[30]  Michele Ceriotti,et al.  i-PI: A Python interface for ab initio path integral molecular dynamics simulations , 2014, Comput. Phys. Commun..

[31]  Zhaojun Zhang,et al.  Effects of reagent rotational excitation on the H + CHD₃ → H₂ + CD₃ reaction: a seven dimensional time-dependent wave packet study. , 2014, The Journal of chemical physics.

[32]  Li Li,et al.  Understanding Machine-learned Density Functionals , 2014, ArXiv.

[33]  O. Anatole von Lilienfeld,et al.  Modeling electronic quantum transport with machine learning , 2014, 1401.8277.

[34]  K. Müller,et al.  Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space , 2015, The journal of physical chemistry letters.

[35]  Jun Li,et al.  A permutationally invariant full-dimensional ab initio potential energy surface for the abstraction and exchange channels of the H + CH4 system. , 2015, The Journal of chemical physics.

[36]  Li Li,et al.  Understanding Kernel Ridge Regression: Common behaviors from simple functions to density functionals , 2015, ArXiv.

[37]  Alán Aspuru-Guzik,et al.  Advances in molecular quantum chemistry contained in the Q-Chem 4 program package , 2014, Molecular Physics.

[38]  Joel M Bowman,et al.  Permutationally Invariant Fitting of Many-Body, Non-covalent Interactions with Application to Three-Body Methane-Water-Water. , 2015, Journal of chemical theory and computation.

[39]  Sergei Manzhos,et al.  Neural network‐based approaches for building high dimensional and quantum dynamics‐friendly potential energy surfaces , 2015 .

[40]  Luke E K Achenie,et al.  Machine-Learning-Augmented Chemisorption Model for CO2 Electroreduction Catalyst Screening. , 2015, The journal of physical chemistry letters.

[41]  Andreas W Götz,et al.  On the representation of many-body interactions in water. , 2015, The Journal of chemical physics.

[42]  Jun Chen,et al.  Communication: Fitting potential energy surfaces with fundamental invariant neural network. , 2016, The Journal of chemical physics.

[43]  Kun Yao,et al.  Kinetic Energy of Hydrocarbons as a Function of Electron Density and Convolutional Neural Networks. , 2015, Journal of chemical theory and computation.

[44]  Czech Republic,et al.  Learning physical descriptors for materials science by compressed sensing , 2016, 1612.04285.

[45]  Alán Aspuru-Guzik,et al.  Neural Networks for the Prediction of Organic Chemistry Reactions , 2016, ACS central science.

[46]  Andrew A Peterson,et al.  Acceleration of saddle-point searches with machine learning. , 2016, The Journal of chemical physics.

[47]  Andreas W Götz,et al.  On the accuracy of the MB-pol many-body potential for water: Interaction energies, vibrational frequencies, and classical thermodynamic and dynamical properties from clusters to liquid water and ice. , 2016, The Journal of chemical physics.

[48]  Kieron Burke,et al.  Pure density functional for strong correlation and the thermodynamic limit from machine learning , 2016, 1609.03705.

[49]  Alireza Khorshidi,et al.  Amp: A modular approach to machine learning in atomistic simulations , 2016, Comput. Phys. Commun..

[50]  Noam Bernstein,et al.  Exploration, Sampling, And Reconstruction of Free Energy Surfaces with Gaussian Process Regression. , 2016, Journal of chemical theory and computation.

[51]  D. Lu,et al.  Supervised Machine-Learning-Based Determination of Three-Dimensional Structure of Metallic Nanoparticles. , 2017, The journal of physical chemistry letters.

[52]  Andreas Verras,et al.  Is Multitask Deep Learning Practical for Pharma? , 2017, J. Chem. Inf. Model..

[53]  Gábor Csányi,et al.  Many-Body Coarse-Grained Interactions Using Gaussian Approximation Potentials. , 2016, The journal of physical chemistry. B.

[54]  Heather J Kulik,et al.  Resolving Transition Metal Chemical Space: Feature Selection for Machine Learning and Structure-Property Relationships. , 2017, The journal of physical chemistry. A.

[55]  Chunjie Luo,et al.  pDeep: Predicting MS/MS Spectra of Peptides with Deep Learning. , 2017, Analytical chemistry.

[56]  Alexandre Tkatchenko,et al.  Quantum-chemical insights from deep tensor neural networks , 2016, Nature Communications.

[57]  Ryosuke Jinnouchi,et al.  Predicting Catalytic Activity of Nanoparticles by a DFT-Aided Machine-Learning Algorithm. , 2017, The journal of physical chemistry letters.

[58]  Li Li,et al.  Bypassing the Kohn-Sham equations with machine learning , 2016, Nature Communications.

[59]  Klaus-Robert Müller,et al.  Machine learning of accurate energy-conserving molecular force fields , 2016, Science Advances.

[60]  E. Weinan,et al.  Deep Potential: a general representation of a many-body potential energy surface , 2017, 1707.01478.

[61]  Mariano Sigman,et al.  The language of geometry: Fast comprehension of geometrical primitives and rules in human adults and preschoolers , 2017, PLoS Comput. Biol..

[62]  Bernard R Brooks,et al.  Machine Learning Force Field Parameters from Ab Initio Data. , 2017, Journal of chemical theory and computation.

[63]  John E Herr,et al.  The many-body expansion combined with neural networks. , 2016, The Journal of chemical physics.

[64]  Cormac Toher,et al.  Universal fragment descriptors for predicting properties of inorganic crystals , 2016, Nature Communications.

[65]  K. Jordan,et al.  Preface: Special Topic: From Quantum Mechanics to Force Fields. , 2017, The Journal of chemical physics.

[66]  Heather J Kulik,et al.  Predicting electronic structure properties of transition metal complexes with neural networks† †Electronic supplementary information (ESI) available. See DOI: 10.1039/c7sc01247k , 2017, Chemical science.

[67]  Olexandr Isayev,et al.  ANI-1, A data set of 20 million calculated off-equilibrium conformations for organic molecules , 2017, Scientific Data.

[68]  Jörg Behler,et al.  Accurate Neural Network Description of Surface Phonons in Reactive Gas–Surface Dynamics: N2 + Ru(0001) , 2017, The journal of physical chemistry letters.

[69]  J. Behler.  First Principles Neural Network Potentials for Reactive Simulations of Large Molecular and Condensed Systems. , 2017, Angewandte Chemie.

[70]  Christoph Kreisbeck,et al.  Machine learning for quantum dynamics: deep learning of excitation energy transfer properties† †Electronic supplementary information (ESI) available. See DOI: 10.1039/c7sc03542j , 2017, Chemical science.

[71]  Artem R Oganov,et al.  Energy-free machine learning force field for aluminum , 2017, Scientific Reports.

[72]  Andrew G. Taube,et al.  Improving the accuracy of Møller-Plesset perturbation theory with neural networks. , 2017, The Journal of chemical physics.

[73]  John E. Herr,et al.  Intrinsic Bond Energies from a Bonds-in-Molecules Neural Network. , 2017, The journal of physical chemistry letters.

[74]  Volker L. Deringer,et al.  Machine learning based interatomic potential for amorphous carbon , 2016, 1611.03277.

[75]  Vijay S. Pande,et al.  OpenMM 7: Rapid development of high performance algorithms for molecular dynamics , 2016, bioRxiv.

[76]  A. W. Götz,et al.  Toward chemical accuracy in the description of ion-water interactions through many-body representations. Alkali-water dimer potential energy surfaces. , 2017, The Journal of chemical physics.

[77]  Ekin D. Cubuk,et al.  Representations in neural network based empirical potentials. , 2017, The Journal of chemical physics.

[78]  Nathan S. Lewis,et al.  Machine-Learning Methods Enable Exhaustive Searches for Active Bimetallic Facets and Reveal Active Site Motifs for CO2 Reduction , 2017 .

[79]  George E. Dahl,et al.  Prediction Errors of Molecular Machine Learning Models Lower than Hybrid DFT Error. , 2017, Journal of chemical theory and computation.

[80]  Francesco Paesani,et al.  Molecular Origin of the Vibrational Structure of Ice Ih. , 2017, The journal of physical chemistry letters.

[81]  Kyle Mills,et al.  Deep learning and the Schrödinger equation , 2017, ArXiv.

[82]  Michael Gastegger,et al.  Machine learning molecular dynamics for the simulation of infrared spectra† †Electronic supplementary information (ESI) available. See DOI: 10.1039/c7sc02267k , 2017, Chemical science.

[83]  Emma Strubell,et al.  Machine-learned and codified synthesis parameters of oxide materials , 2017, Scientific Data.

[84]  J S Smith,et al.  ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost , 2016, Chemical science.

[85]  Weitao Yang,et al.  Internal force corrections with machine learning for quantum mechanics/molecular mechanics simulations. , 2017, The Journal of chemical physics.

[86]  Alexie M. Kolpak,et al.  Discovering charge density functionals and structure-property relationships with PROPhet: A general framework for coupling machine learning and first-principles methods , 2017, Scientific Reports.

[87]  W. Wang,et al.  Machine Learning Approach for Prediction and Understanding of Glass-Forming Ability. , 2017, The journal of physical chemistry letters.

[88]  V. Barone,et al.  Force Field Parametrization of Metal Ions from Statistical Learning Techniques , 2017, Journal of chemical theory and computation.

[89]  Gregory S. Ezra,et al.  Empirical Classification of Trajectory Data: An Opportunity for the Use of Machine Learning in Molecular Dynamics. , 2017, The journal of physical chemistry. B.