Exploring the frontiers of condensed-phase chemistry with a general reactive machine learning potential

Zhang, Shuhao; Makoś, Małgorzata Z.; Jadrich, Ryan B.; Kraka, Elfi; Barros, Kipton; Nebgen, Benjamin T.; Tretiak, Sergei; Isayev, Olexandr; Lubbers, Nicholas; Messerly, Richard A.; Smith, Justin S.

doi:10.1038/s41557-023-01427-3

Title: Exploring the frontiers of condensed-phase chemistry with a general reactive machine learning potential

Journal Article · 06 March 2024 · Nature Chemistry

DOI: https://doi.org/10.1038/s41557-023-01427-3 · OSTI ID:2320314

Zhang, Shuhao;

; Jadrich, Ryan B.; Kraka, Elfi; Barros, Kipton;

;

Abstract Atomistic simulation has a broad range of applications from drug design to materials discovery. Machine learning interatomic potentials (MLIPs) have become an efficient alternative to computationally expensive ab initio simulations. For this reason, chemistry and materials science would greatly benefit from a general reactive MLIP, that is, an MLIP that is applicable to a broad range of reactive chemistry without the need for refitting. Here we develop a general reactive MLIP (ANI-1xnr) through automated sampling of condensed-phase reactions. ANI-1xnr is then applied to study five distinct systems: carbon solid-phase nucleation, graphene ring formation from acetylene, biofuel additives, combustion of methane and the spontaneous formation of glycine from early earth small molecules. In all studies, ANI-1xnr closely matches experiment (when available) and/or previous studies using traditional model chemistry methods. As such, ANI-1xnr proves to be a highly general reactive MLIP for C, H, N and O elements in the condensed phase, enabling high-throughput in silico reactive chemistry experimentation.

View Journal Article

Cite

Export

Save

Sponsoring Organization:: USDOE

Grant/Contract Number:: NONE; 89233218CNA000001

OSTI ID:: 2320314

Alternate ID(s):: OSTI ID: 2329239

Journal Information:: Nature Chemistry, Journal Name: Nature Chemistry Journal Issue: 5 Vol. 16; ISSN 1755-4330

Publisher:: Nature Publishing GroupCopyright Statement

Country of Publication:: United Kingdom

Language:: English

References (81)

The TensorMol-0.1 model chemistry: a neural network augmented with long-range physics Yao, Kun; Herr, John E.; Toth, David W. Chemical Science, Vol. 9, Issue 8 https://doi.org/10.1039/C7SC04934J	journal	January 2018
Discovering chemistry with an ab initio nanoreactor Wang, Lee-Ping; Titov, Alexey; McGibbon, Robert Nature Chemistry, Vol. 6, Issue 12 https://doi.org/10.1038/nchem.2099	journal	November 2014
Combustion Mechanisms and Kinetics of Fuel Additives: A ReaxFF Molecular Simulation Chen, Zhuojun; Sun, Weizhen; Zhao, Ling Energy & Fuels, Vol. 32, Issue 11 https://doi.org/10.1021/acs.energyfuels.8b02035	journal	October 2018
Parallel Multistream Training of High-Dimensional Neural Network Potentials Singraber, Andreas; Morawietz, Tobias; Behler, Jörg Journal of Chemical Theory and Computation, Vol. 15, Issue 5 https://doi.org/10.1021/acs.jctc.8b01092	journal	April 2019
The atomic simulation environment—a Python library for working with atoms Hjorth Larsen, Ask; Jørgen Mortensen, Jens; Blomqvist, Jakob Journal of Physics: Condensed Matter, Vol. 29, Issue 27 https://doi.org/10.1088/1361-648X/aa680e	journal	June 2017
Lifelong Machine Learning Potentials Eckhoff, Marco; Reiher, Markus Journal of Chemical Theory and Computation, Vol. 19, Issue 12 https://doi.org/10.1021/acs.jctc.3c00279	journal	June 2023
Constructing high-dimensional neural network potentials: A tutorial review Behler, Jörg International Journal of Quantum Chemistry, Vol. 115, Issue 16 https://doi.org/10.1002/qua.24890	journal	March 2015
Gaussian approximation potentials: A brief tutorial introduction Bartók, Albert P.; Csányi, Gábor International Journal of Quantum Chemistry, Vol. 115, Issue 16 https://doi.org/10.1002/qua.24927	journal	April 2015
Transition1x - a dataset for building generalizable reactive machine learning potentials Schreiner, Mathias; Bhowmik, Arghya; Vegge, Tejs Scientific Data, Vol. 9, Issue 1 https://doi.org/10.1038/s41597-022-01870-w	journal	December 2022
The ReaxFF reactive force-field: development, applications and future directions Senftle, Thomas P.; Hong, Sungwook; Islam, Md Mahbubul npj Computational Materials, Vol. 2, Issue 1 https://doi.org/10.1038/npjcompumats.2015.11	journal	March 2016
First principles reactive simulation for equation of state prediction Jadrich, Ryan B.; Ticknor, Christopher; Leiding, Jeffery A. The Journal of Chemical Physics, Vol. 154, Issue 24 https://doi.org/10.1063/5.0050676	journal	June 2021
E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials Batzner, Simon; Musaelian, Albert; Sun, Lixin Nature Communications, Vol. 13, Issue 1 https://doi.org/10.1038/s41467-022-29939-5	journal	May 2022
Visualization and analysis of atomistic simulation data with OVITO–the Open Visualization Tool Stukowski, Alexander Modelling and Simulation in Materials Science and Engineering, Vol. 18, Issue 1 https://doi.org/10.1088/0965-0393/18/1/015012	journal	December 2009
High-Fidelity Potential Energy Surfaces for Gas-Phase and Gas–Surface Scattering Processes from Machine Learning Jiang, Bin; Li, Jun; Guo, Hua The Journal of Physical Chemistry Letters, Vol. 11, Issue 13 https://doi.org/10.1021/acs.jpclett.0c00989	journal	June 2020
Miller experiments in atomistic computer simulations Saitta, A. M.; Saija, F. Proceedings of the National Academy of Sciences, Vol. 111, Issue 38 https://doi.org/10.1073/pnas.1402894111	journal	September 2014
PubChem 2023 update Kim, Sunghwan; Chen, Jie; Cheng, Tiejun Nucleic Acids Research, Vol. 51, Issue D1 https://doi.org/10.1093/nar/gkac956	journal	October 2022
Learning local equivariant representations for large-scale atomistic dynamics Musaelian, Albert; Batzner, Simon; Johansson, Anders Nature Communications, Vol. 14, Issue 1 https://doi.org/10.1038/s41467-023-36329-y	journal	February 2023
Reactive molecular dynamics for the [Cl–CH ₃ –Br] ⁻ reaction in the gas phase and in solution: a comparative study using empirical and neural network force fields Brickel, Sebastian; Das, Akshaya K.; Unke, Oliver T. Electronic Structure, Vol. 1, Issue 2 https://doi.org/10.1088/2516-1075/ab1edb	journal	May 2019
Exploring chemical and conformational spaces by batch mode deep active learning Zaverkin, Viktor; Holzmüller, David; Steinwart, Ingo Digital Discovery, Vol. 1, Issue 5 https://doi.org/10.1039/D2DD00034B	journal	January 2022
Self-assembly of s p 2 -bonded carbon nanostructures from amorphous precursors Powles, R. C.; Marks, N. A.; Lau, D. W. M. Physical Review B, Vol. 79, Issue 7 https://doi.org/10.1103/PhysRevB.79.075430	journal	February 2009
Reaction prediction via atomistic simulation: from quantum mechanics to machine learning Kang, Pei-Lin; Liu, Zhi-Pan iScience, Vol. 24, Issue 1 https://doi.org/10.1016/j.isci.2020.102013	journal	January 2021
NewtonNet: A Newtonian message passing network for deep learning of interatomic potentials and forces Haghighatlari, Mojtaba; Li, Jie; Guan, Xingyi Digital Discovery https://doi.org/10.1039/D2DD00008C	journal	January 2022
A benchmark dataset for Hydrogen Combustion Guan, Xingyi; Das, Akshaya; Stein, Christopher J. Scientific Data, Vol. 9, Issue 1 https://doi.org/10.1038/s41597-022-01330-5	journal	May 2022
Accurate and transferable multitask prediction of chemical properties with an atoms-in-molecules neural network Zubatyuk, Roman; Smith, Justin S.; Leszczynski, Jerzy Science Advances, Vol. 5, Issue 8 https://doi.org/10.1126/sciadv.aav6490	journal	August 2019
Machine-learned interatomic potentials by active learning: amorphous and liquid hafnium dioxide Sivaraman, Ganesh; Krishnamoorthy, Anand Narayanan; Baur, Matthias npj Computational Materials, Vol. 6, Issue 1 https://doi.org/10.1038/s41524-020-00367-7	journal	July 2020
A critical comparison of neural network potentials for molecular reaction dynamics with exact permutation symmetry Li, Jun; Song, Kaisheng; Behler, Jörg Physical Chemistry Chemical Physics, Vol. 21, Issue 19 https://doi.org/10.1039/C8CP06919K	journal	January 2019
Quantum and quasi-classical dynamics of the OH + CO → H + CO ₂ reaction on a new permutationally invariant neural network potential energy surface Li, Jun; Chen, Jun; Zhang, Dong H. The Journal of Chemical Physics, Vol. 140, Issue 4 https://doi.org/10.1063/1.4863138	journal	January 2014
Simple and efficient algorithms for training machine learning potentials to force data Smith, Justin S.; Lubbers, Nicholas; Thompson, Aidan P. arXiv https://doi.org/10.48550/arXiv.2006.05475	preprint	January 2020
An empirical valence bond approach for comparing reactions in solutions and in enzymes Warshel, Arieh; Weiss, Robert M. Journal of the American Chemical Society, Vol. 102, Issue 20 https://doi.org/10.1021/ja00540a008	journal	September 1980
Automated discovery of a robust interatomic potential for aluminum Smith, Justin S.; Nebgen, Benjamin; Mathew, Nithin Nature Communications, Vol. 12, Issue 1 https://doi.org/10.1038/s41467-021-21376-0	journal	February 2021
SpookyNet: Learning force fields with electronic degrees of freedom and nonlocal effects Unke, Oliver T.; Chmiela, Stefan; Gastegger, Michael Nature Communications, Vol. 12, Issue 1 https://doi.org/10.1038/s41467-021-27504-0	journal	December 2021
Self-Consistent Equations Including Exchange and Correlation Effects Kohn, W.; Sham, L. J. Physical Review, Vol. 140, Issue 4A, p. A1133-A1138 https://doi.org/10.1103/PhysRev.140.A1133	journal	November 1965
Active learning accelerates ab initio molecular dynamics on reactive energy surfaces Ang, Shi Jun; Wang, Wujie; Schwalbe-Koda, Daniel Chem, Vol. 7, Issue 3 https://doi.org/10.1016/j.chempr.2020.12.009	journal	March 2021
ReaxFF: A Reactive Force Field for Hydrocarbons van Duin, Adri C. T.; Dasgupta, Siddharth; Lorant, Francois The Journal of Physical Chemistry A, Vol. 105, Issue 41 https://doi.org/10.1021/jp004368u	journal	October 2001
Determination of modified embedded atom method parameters for nickel Baskes, M. I. Materials Chemistry and Physics, Vol. 50, Issue 2 https://doi.org/10.1016/S0254-0584(97)80252-0	journal	September 1997
Learning Together: Towards foundational models for machine learning interatomic potentials with meta-learning Allen, Alice E. A.; Lubbers, Nicholas; Matin, Sakib arXiv https://doi.org/10.48550/arXiv.2307.04012	preprint	January 2023
A consistent and accurate ab initio parametrization of density functional dispersion correction (DFT-D) for the 94 elements H-Pu Grimme, Stefan; Antony, Jens; Ehrlich, Stephan The Journal of Chemical Physics, Vol. 132, Issue 15 https://doi.org/10.1063/1.3382344	journal	April 2010
Machine learning based interatomic potential for amorphous carbon Deringer, Volker L.; Csányi, Gábor Physical Review B, Vol. 95, Issue 9 https://doi.org/10.1103/PhysRevB.95.094203	journal	March 2017
Query by committee Seung, H. S.; Opper, M.; Sompolinsky, H. Proceedings of the fifth annual workshop on Computational learning theory - COLT '92 https://doi.org/10.1145/130385.130417	conference	January 1992
The Rise of Neural Networks for Materials and Chemical Dynamics Kulichenko, Maksim; Smith, Justin S.; Nebgen, Benjamin The Journal of Physical Chemistry Letters, Vol. 12, Issue 26 https://doi.org/10.1021/acs.jpclett.1c01357	journal	July 2021
Neural network reactive force field for C, H, N, and O systems Yoo, Pilsun; Sakano, Michael; Desai, Saaketh npj Computational Materials, Vol. 7, Issue 1 https://doi.org/10.1038/s41524-020-00484-3	journal	January 2021
Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning Smith, Justin S.; Nebgen, Benjamin T.; Zubatyuk, Roman Nature Communications, Vol. 10, Issue 1 https://doi.org/10.1038/s41467-019-10827-4	journal	July 2019
Separable dual-space Gaussian pseudopotentials Goedecker, S.; Teter, M.; Hutter, J. Physical Review B, Vol. 54, Issue 3 https://doi.org/10.1103/PhysRevB.54.1703	journal	July 1996
On the Opportunities and Risks of Foundation Models Bommasani, Rishi; Hudson, Drew A.; Adeli, Ehsan arXiv https://doi.org/10.48550/arXiv.2108.07258	preprint	January 2021
Amp: A modular approach to machine learning in atomistic simulations Khorshidi, Alireza; Peterson, Andrew A. Computer Physics Communications, Vol. 207 https://doi.org/10.1016/j.cpc.2016.05.010	journal	October 2016
Force Field Development and Nanoreactor Chemistry Wang, Lee-Ping Computational Approaches for Chemistry Under Extreme Conditions https://doi.org/10.1007/978-3-030-05600-1_6	book	February 2019
Complex reaction processes in combustion unraveled by neural network-based molecular dynamics simulation Zeng, Jinzhe; Cao, Liqun; Xu, Mingyuan Nature Communications, Vol. 11, Issue 1 https://doi.org/10.1038/s41467-020-19497-z	journal	November 2020
First Principles Neural Network Potentials for Reactive Simulations of Large Molecular and Condensed Systems Behler, Jörg Angewandte Chemie International Edition, Vol. 56, Issue 42 https://doi.org/10.1002/anie.201703114	journal	August 2017
Mechanism of Graphene Formation via Detonation Synthesis: A DFTB Nanoreactor Approach Lei, Tingyu; Guo, Wenping; Liu, Qingya Journal of Chemical Theory and Computation, Vol. 15, Issue 6 https://doi.org/10.1021/acs.jctc.9b00158	journal	April 2019
Lightweight and effective tensor sensitivity for atomistic neural networks Chigaev, Michael; Smith, Justin S.; Anaya, Steven The Journal of Chemical Physics, Vol. 158, Issue 18 https://doi.org/10.1063/5.0142127	journal	May 2023
Development of the Colle-Salvetti correlation-energy formula into a functional of the electron density Lee, Chengteh; Yang, Weitao; Parr, Robert G. Physical Review B, Vol. 37, Issue 2 https://doi.org/10.1103/PhysRevB.37.785	journal	January 1988
A transferable active-learning strategy for reactive molecular force fields Young, Tom A.; Johnston-Wood, Tristan; Deringer, Volker L. Chemical Science, Vol. 12, Issue 32 https://doi.org/10.1039/D1SC01825F	journal	January 2021
High-pressure ignition delay time measurements of a four-component gasoline surrogate and its high-level blends with ethanol and methyl acetate Cooper, Sean P.; Mathieu, Olivier; Schoegl, Ingmar Fuel, Vol. 275 https://doi.org/10.1016/j.fuel.2020.118016	journal	September 2020
Performance and Cost Assessment of Machine Learning Interatomic Potentials Zuo, Yunxing; Chen, Chi; Li, Xiangguo The Journal of Physical Chemistry A, Vol. 124, Issue 4 https://doi.org/10.1021/acs.jpca.9b08723	journal	October 2019
A neural network potential with rigorous treatment of long-range dispersion Tu, Nguyen Thien Phuc; Rezajooei, Nazanin; Johnson, Erin R. Digital Discovery, Vol. 2, Issue 3 https://doi.org/10.1039/D2DD00150K	journal	January 2023
Gaussian basis sets for accurate calculations on molecular systems in gas and condensed phases VandeVondele, Joost; Hutter, Jürg The Journal of Chemical Physics, Vol. 127, Issue 11 https://doi.org/10.1063/1.2770708	journal	September 2007
Organic Compound Synthes on the Primitive Eart: Several questions about the origin of life have been answered, but much remains to be studied Miller, S. L.; Urey, H. C. Science, Vol. 130, Issue 3370 https://doi.org/10.1126/science.130.3370.245	journal	July 1959
A universal graph deep learning interatomic potential for the periodic table Chen, Chi; Ong, Shyue Ping Nature Computational Science, Vol. 2, Issue 11 https://doi.org/10.1038/s43588-022-00349-3	journal	November 2022
Permutation invariant potential energy surfaces for polyatomic reactions using atomistic neural networks Kolb, Brian; Zhao, Bin; Li, Jun The Journal of Chemical Physics, Vol. 144, Issue 22 https://doi.org/10.1063/1.4953560	journal	June 2016
Towards universal neural network potential for material discovery applicable to arbitrary combination of 45 elements Takamoto, So; Shinagawa, Chikashi; Motoki, Daisuke Nature Communications, Vol. 13, Issue 1 https://doi.org/10.1038/s41467-022-30687-9	journal	May 2022
TeaNet: Universal neural network interatomic potential inspired by iterative electronic relaxations Takamoto, So; Izumi, Satoshi; Li, Ju Computational Materials Science, Vol. 207 https://doi.org/10.1016/j.commatsci.2022.111280	journal	May 2022
First-Principles Monte Carlo Simulations of Reaction Equilibria in Compressed Vapors Fetisov, Evgenii O.; Kuo, I-Feng William; Knight, Chris ACS Central Science, Vol. 2, Issue 6 https://doi.org/10.1021/acscentsci.6b00095	journal	April 2016
Density-functional exchange-energy approximation with correct asymptotic behavior Becke, A. D. Physical Review A, Vol. 38, Issue 6 https://doi.org/10.1103/PhysRevA.38.3098	journal	September 1988
CP2K: An electronic structure and molecular dynamics software package - Quickstep: Efficient and accurate electronic structure calculations Kühne, Thomas D.; Iannuzzi, Marcella; Del Ben, Mauro The Journal of Chemical Physics, Vol. 152, Issue 19 https://doi.org/10.1063/5.0007045	journal	May 2020
The ANI-1ccx and ANI-1x data sets, coupled-cluster and density functional theory properties for molecules Smith, Justin S.; Zubatyuk, Roman; Nebgen, Benjamin Scientific Data, Vol. 7, Issue 1 https://doi.org/10.1038/s41597-020-0473-z	journal	May 2020
A fourth-generation high-dimensional neural network potential with accurate electrostatics including non-local charge transfer Ko, Tsz Wai; Finkler, Jonas A.; Goedecker, Stefan Nature Communications, Vol. 12, Issue 1 https://doi.org/10.1038/s41467-020-20427-2	journal	January 2021
Fitting potential energy surfaces with fundamental invariant neural network. II. Generating fundamental invariants for molecular systems with up to ten atoms Chen, Rongjun; Shao, Kejie; Fu, Bina The Journal of Chemical Physics, Vol. 152, Issue 20 https://doi.org/10.1063/5.0010104	journal	May 2020
Reaction dynamics of Diels–Alder reactions from machine learned potentials Young, Tom A.; Johnston-Wood, Tristan; Zhang, Hanwen Physical Chemistry Chemical Physics, Vol. 24, Issue 35 https://doi.org/10.1039/D2CP02978B	journal	January 2022
Improved long-range reactive bond-order potential for carbon. I. Construction Los, Jan H.; Ghiringhelli, Luca M.; Meijer, Evert Jan Physical Review B, Vol. 72, Issue 21 https://doi.org/10.1103/PhysRevB.72.214102	journal	December 2005
Less is more: Sampling chemical space with active learning Smith, Justin S.; Nebgen, Ben; Lubbers, Nicholas The Journal of Chemical Physics, Vol. 148, Issue 24 https://doi.org/10.1063/1.5023802	journal	June 2018
A deep learning interatomic potential developed for atomistic simulation of carbon materials Wang, Jinjin; Shen, Hong; Yang, Riyi Carbon, Vol. 186 https://doi.org/10.1016/j.carbon.2021.09.062	journal	January 2022
Potential energy surface interpolation with neural networks for instanton rate calculations Cooper, April M.; Hallmen, Philipp P.; Kästner, Johannes The Journal of Chemical Physics, Vol. 148, Issue 9 https://doi.org/10.1063/1.5015950	journal	March 2018
LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales Thompson, Aidan P.; Aktulga, H. Metin; Berger, Richard Computer Physics Communications, Vol. 271 https://doi.org/10.1016/j.cpc.2021.108171	journal	February 2022
A second-generation reactive empirical bond order (REBO) potential energy expression for hydrocarbons Brenner, Donald W.; Shenderova, Olga A.; Harrison, Judith A. Journal of Physics: Condensed Matter, Vol. 14, Issue 4 https://doi.org/10.1088/0953-8984/14/4/312	journal	January 2002
ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost Smith, J. S.; Isayev, O.; Roitberg, A. E. Chemical Science, Vol. 8, Issue 4 https://doi.org/10.1039/C6SC05720A	journal	January 2017
On the limited memory BFGS method for large scale optimization Liu, Dong C.; Nocedal, Jorge Mathematical Programming, Vol. 45, Issue 1-3 https://doi.org/10.1007/BF01589116	journal	August 1989
PACKMOL: A package for building initial configurations for molecular dynamics simulations Martínez, L.; Andrade, R.; Birgin, E. G. Journal of Computational Chemistry, Vol. 30, Issue 13 https://doi.org/10.1002/jcc.21224	journal	October 2009
Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces Behler, Jörg; Parrinello, Michele Physical Review Letters, Vol. 98, Issue 14 https://doi.org/10.1103/PhysRevLett.98.146401	journal	April 2007
Development of a ReaxFF Potential for Carbon Condensed Phases and Its Application to the Thermal Fragmentation of a Large Fullerene Srinivasan, Sriram Goverapet; van Duin, Adri C. T.; Ganesh, P. The Journal of Physical Chemistry A, Vol. 119, Issue 4 https://doi.org/10.1021/jp510274e	journal	January 2015
Extending the Applicability of the ANI Deep Learning Molecular Potential to Sulfur and Halogens Devereux, Christian; Smith, Justin S.; Davis, Kate K. Journal of Chemical Theory and Computation, Vol. 16, Issue 7 https://doi.org/10.1021/acs.jctc.0c00121	journal	June 2020
Graphitization of amorphous carbons: A comparative study of interatomic potentials de Tomas, Carla; Suarez-Martinez, Irene; Marks, Nigel A. Carbon, Vol. 109 https://doi.org/10.1016/j.carbon.2016.08.024	journal	November 2016

Similar Records

Chemistry-mediated Ostwald ripening in carbon-rich C/O systems at extreme conditions

Journal Article · 2022 · Nature Communications · OSTI ID:1855522

Lindsey, Rebecca K.; Goldman, Nir; Fried, Laurence E.; +1 more

ChIMES: A Machine-Learned Interatomic Model Targeting Improved Description of Condensed Phase Chemistry in Energetic Materials

Technical Report · 2020 · OSTI ID:1662036

Lindsey, Rebecca K.; Pham, C. Huy; Fried, Laurence E.; +2 more

Atomistic Simulations of Chemical Reactivity of TATB Under Thermal and Shock Conditions

Conference · 2009 · OSTI ID:977232

Manaa, M R; Reed, E J; Fried, L E

Title: Exploring the frontiers of condensed-phase chemistry with a general reactive machine learning potential

Citation Formats

References (81)

Similar Records

Related Subjects