Bond order predictions using deep neural networks

Magedov, Sergey; Koh, Christopher; Malone, Walter; Lubbers, Nicholas; Nebgen, Benjamin

doi:10.1063/5.0016011

Title: Bond order predictions using deep neural networks

Journal Article · Sun Feb 14 00:00:00 EST 2021 · Journal of Applied Physics

DOI:https://doi.org/10.1063/5.0016011· OSTI ID:1805727

^[1];

^[2];

^[2]

New Mexico Institute of Mining and Technology, Socorro, NM (United States)
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)

Machine learning is an extremely powerful tool for the modern theoretical chemist since it provides a method for bypassing costly algorithms for solving the Schrödinger equation. Already, it has proven able to infer molecular and atomic properties such as charges, enthalpies, dipoles, excited state energies, and others. Most of these machine learning algorithms proceed by inferring properties of individual atoms, even breaking down total molecular energy into individual atomic contributions. In this paper, we introduce a modified version of the Hierarchically Interacting Particle Neural Network (HIP-NN) capable of making predictions on the bonds between atoms rather than on the atoms themselves. We train the modified HIP-NN to infer bond orders for a large number of small organic molecules as computed via the Natural Bond Orbital package. We demonstrate that the trained model is extensible to molecules much larger than those in the training set by studying its performance on the COMP6 dataset. This method has applications in cheminformatics and force field parameterization and opens a promising future for machine learning models to predict other quantities that are defined between atoms such as density matrix elements, Hamiltonian parameters, and molecular reactivities.

View Accepted Manuscript (DOE)

View Accepted Manuscript (Publisher)

Cite

Export

Save

Research Organization:: Los Alamos National Lab. (LANL), Los Alamos, NM (United States)

Sponsoring Organization:: USDOE Laboratory Directed Research and Development (LDRD) Program

Grant/Contract Number:: 89233218CNA000001

OSTI ID:: 1805727

Alternate ID(s):: OSTI ID: 1798549; OSTI ID: 1828728

Report Number(s):: LA-UR-20-26468; LA-UR-21-30590

Journal Information:: Journal of Applied Physics, Vol. 129, Issue 6; ISSN 0021-8979

Publisher:: American Institute of Physics (AIP)Copyright Statement

Country of Publication:: United States

Language:: English

References (56)

Double-slit photoelectron interference in strong-field ionization of the neon dimer Kunitski, Maksim; Eicke, Nicolas; Huber, Pia Nature Communications, Vol. 10, Issue 1 https://doi.org/10.1038/s41467-018-07882-8	journal	January 2019
Charge, bond order and valence in the AB initio SCF theory Mayer, I. Chemical Physics Letters, Vol. 97, Issue 3 https://doi.org/10.1016/0009-2614(83)80005-0	journal	May 1983
High-quality and universal empirical atomic charges for chemoinformatics applications Geidl, Stanislav; Bouchal, Tomáš; Raček, Tomáš Journal of Cheminformatics, Vol. 7, Issue 1 https://doi.org/10.1186/s13321-015-0107-1	journal	December 2015
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
F lex S: A Method for Fast Flexible Ligand Superposition Lemmen, Christian; Lengauer, Thomas; Klebe, Gerhard Journal of Medicinal Chemistry, Vol. 41, Issue 23 https://doi.org/10.1021/jm981037l	journal	November 1998
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
Comparison of atomic charges derived via different procedures Wiberg, Kenneth B.; Rablen, Paul R. Journal of Computational Chemistry, Vol. 14, Issue 12 https://doi.org/10.1002/jcc.540141213	journal	December 1993
The Amber biomolecular simulation programs Case, David A.; Cheatham, Thomas E.; Darden, Tom Journal of Computational Chemistry, Vol. 26, Issue 16 https://doi.org/10.1002/jcc.20290	journal	January 2005
Bond orders and valences from ab initio wave functions Mayer, I. International Journal of Quantum Chemistry, Vol. 29, Issue 3 https://doi.org/10.1002/qua.560290320	journal	March 1986
Correct Bond Order Assignment in a Molecular Framework Using Integer Linear Programming with Application to Molecules Where Only Non-Hydrogen Atom Coordinates Are Available Froeyen, Matheus; Herdewijn, Piet Journal of Chemical Information and Modeling, Vol. 45, Issue 5 https://doi.org/10.1021/ci049645z	journal	June 2005
Approaches to Measure Chemical Similarity - a Review Nikolova, Nina; Jaworska, Joanna QSAR & Combinatorial Science, Vol. 22, Issue 9-10 https://doi.org/10.1002/qsar.200330831	journal	December 2003
Automatic atom type and bond type perception in molecular mechanical calculations Wang, Junmei; Wang, Wei; Kollman, Peter A. Journal of Molecular Graphics and Modelling, Vol. 25, Issue 2 https://doi.org/10.1016/j.jmgm.2005.12.005	journal	October 2006
Chemical Similarity Using Physiochemical Property Descriptors Kearsley, Simon K.; Sallamack, Susan; Fluder, Eugene M. Journal of Chemical Information and Computer Sciences, Vol. 36, Issue 1 https://doi.org/10.1021/ci950274j	journal	January 1996
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
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
Automated simultaneous assignment of bond orders and formal charges Welsh, Ivan D.; Allison, Jane R. Journal of Cheminformatics, Vol. 11, Issue 1 https://doi.org/10.1186/s13321-019-0340-0	journal	March 2019
Extended Hückel tight-binding approach to electronic excitations Rincón, Luis; Hasmy, Anwar; Gonzalez, Carlos A. The Journal of Chemical Physics, Vol. 129, Issue 4 https://doi.org/10.1063/1.2956489	journal	July 2008
Machine learning of molecular electronic properties in chemical compound space Montavon, Grégoire; Rupp, Matthias; Gobre, Vivekanand New Journal of Physics, Vol. 15, Issue 9 https://doi.org/10.1088/1367-2630/15/9/095003	journal	September 2013
A Density Functional Tight Binding Layer for Deep Learning of Chemical Hamiltonians Li, Haichen; Collins, Christopher; Tanha, Matteus Journal of Chemical Theory and Computation, Vol. 14, Issue 11 https://doi.org/10.1021/acs.jctc.8b00873	journal	October 2018
SchNet – A deep learning architecture for molecules and materials Schütt, K. T.; Sauceda, H. E.; Kindermans, P. -J. The Journal of Chemical Physics, Vol. 148, Issue 24 https://doi.org/10.1063/1.5019779	journal	June 2018
DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics Wang, Han; Zhang, Linfeng; Han, Jiequn Computer Physics Communications, Vol. 228 https://doi.org/10.1016/j.cpc.2018.03.016	journal	July 2018
Structure-based virtual screening: an overview Lyne, Paul D. Drug Discovery Today, Vol. 7, Issue 20 https://doi.org/10.1016/S1359-6446(02)02483-2	journal	October 2002
Protein-Based Virtual Screening of Chemical Databases. 1. Evaluation of Different Docking/Scoring Combinations Bissantz, Caterina; Folkers, Gerd; Rognan, Didier Journal of Medicinal Chemistry, Vol. 43, Issue 25 https://doi.org/10.1021/jm001044l	journal	December 2000
Calculation of Intersubstituent Similarity Using R-Group Descriptors Holliday, John D.; Jelfs, Stephen P.; Willett, Peter Journal of Chemical Information and Computer Sciences, Vol. 43, Issue 2 https://doi.org/10.1021/ci025589v	journal	February 2003
Transferable Machine-Learning Model of the Electron Density Grisafi, Andrea; Fabrizio, Alberto; Meyer, Benjamin ACS Central Science, Vol. 5, Issue 1 https://doi.org/10.1021/acscentsci.8b00551	journal	December 2018
NBO 6.0 : Natural bond orbital analysis program Glendening, Eric D.; Landis, Clark R.; Weinhold, Frank Journal of Computational Chemistry, Vol. 34, Issue 16 https://doi.org/10.1002/jcc.23266	journal	March 2013
Development and use of quantum mechanical molecular models. 76. AM1: a new general purpose quantum mechanical molecular model Dewar, Michael J. S.; Zoebisch, Eve G.; Healy, Eamonn F. Journal of the American Chemical Society, Vol. 107, Issue 13 https://doi.org/10.1021/ja00299a024	journal	June 1985
Intrinsic Bond Energies from a Bonds-in-Molecules Neural Network Yao, Kun; Herr, John E.; Brown, Seth N. The Journal of Physical Chemistry Letters, Vol. 8, Issue 12 https://doi.org/10.1021/acs.jpclett.7b01072	journal	June 2017
PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments, and Partial Charges Unke, Oliver T.; Meuwly, Markus Journal of Chemical Theory and Computation, Vol. 15, Issue 6 https://doi.org/10.1021/acs.jctc.9b00181	journal	April 2019
Discovery of antibiotics-derived polymers for gene delivery using combinatorial synthesis and cheminformatics modeling Potta, Thrimoorthy; Zhen, Zhuo; Grandhi, Taraka Sai Pavan Biomaterials, Vol. 35, Issue 6 https://doi.org/10.1016/j.biomaterials.2013.10.069	journal	February 2014
Hierarchical modeling of molecular energies using a deep neural network Lubbers, Nicholas; Smith, Justin S.; Barros, Kipton The Journal of Chemical Physics, Vol. 148, Issue 24 https://doi.org/10.1063/1.5011181	journal	June 2018
LASP: Fast global potential energy surface exploration Huang, Si‐Da; Shang, Cheng; Kang, Pei‐Lin Wiley Interdisciplinary Reviews: Computational Molecular Science, Vol. 9, Issue 6 https://doi.org/10.1002/wcms.1415	journal	March 2019
Discovering a Transferable Charge Assignment Model Using Machine Learning Sifain, Andrew E.; Lubbers, Nicholas; Nebgen, Benjamin T. The Journal of Physical Chemistry Letters, Vol. 9, Issue 16 https://doi.org/10.1021/acs.jpclett.8b01939	journal	July 2018
Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning Rupp, Matthias; Tkatchenko, Alexandre; Müller, Klaus-Robert Physical Review Letters, Vol. 108, Issue 5 https://doi.org/10.1103/PhysRevLett.108.058301	journal	January 2012
Automatic assignment of bond orders based on the analysis of the internal coordinates of molecular structures Lang, Elke; von der Lieth, Claus-Wilhelm; Förster, Thomas Analytica Chimica Acta, Vol. 265, Issue 2 https://doi.org/10.1016/0003-2670(92)85034-4	journal	August 1992
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
Alchemical and structural distribution based representation for universal quantum machine learning Faber, Felix A.; Christensen, Anders S.; Huang, Bing The Journal of Chemical Physics, Vol. 148, Issue 24 https://doi.org/10.1063/1.5020710	journal	June 2018
Blood pressure-lowering efficacy of reserpine for primary hypertension Shamon, Sandy D.; Perez, Marco I. Cochrane Database of Systematic Reviews https://doi.org/10.1002/14651858.CD007655.pub3	journal	December 2016
Optimization of parameters for semiempirical methods I. Method Stewart, James J. P. Journal of Computational Chemistry, Vol. 10, Issue 2 https://doi.org/10.1002/jcc.540100208	journal	March 1989
S66: A Well-balanced Database of Benchmark Interaction Energies Relevant to Biomolecular Structures Řezáč, Jan; Riley, Kevin E.; Hobza, Pavel Journal of Chemical Theory and Computation, Vol. 7, Issue 8 https://doi.org/10.1021/ct2002946	journal	July 2011
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
Transferable Dynamic Molecular Charge Assignment Using Deep Neural Networks Nebgen, Benjamin; Lubbers, Nicholas; Smith, Justin S. Journal of Chemical Theory and Computation, Vol. 14, Issue 9 https://doi.org/10.1021/acs.jctc.8b00524	journal	July 2018
Charge, bond order and valence in the ab initio SCF theory Mayer, I. Chemical Physics Letters, Vol. 117, Issue 4 https://doi.org/10.1016/0009-2614(85)85253-2	journal	June 1985
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
On the Perception of Molecules from 3D Atomic Coordinates Labute, Paul Journal of Chemical Information and Modeling, Vol. 45, Issue 2 https://doi.org/10.1021/ci049915d	journal	January 2005
The OPLS [optimized potentials for liquid simulations] potential functions for proteins, energy minimizations for crystals of cyclic peptides and crambin Jorgensen, William L.; Tirado-Rives, Julian Journal of the American Chemical Society, Vol. 110, Issue 6 https://doi.org/10.1021/ja00214a001	journal	March 1988
Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies Hansen, Katja; Montavon, Grégoire; Biegler, Franziska Journal of Chemical Theory and Computation, Vol. 9, Issue 8 https://doi.org/10.1021/ct400195d	journal	July 2013
BALI: Automatic Assignment of Bond and Atom Types for Protein Ligands in the Brookhaven Protein Databank Hendlich, M.; Rippmann, F.; Barnickel, G. Journal of Chemical Information and Computer Sciences, Vol. 37, Issue 4 https://doi.org/10.1021/ci9603487	journal	July 1997
Application of the pople-santry-segal CNDO method to the cyclopropylcarbinyl and cyclobutyl cation and to bicyclobutane Wiberg, K. B. Tetrahedron, Vol. 24, Issue 3 https://doi.org/10.1016/0040-4020(68)88057-3	journal	January 1968
Ground states of molecules. 38. The MNDO method. Approximations and parameters Dewar, Michael J. S.; Thiel, Walter Journal of the American Chemical Society, Vol. 99, Issue 15 https://doi.org/10.1021/ja00457a004	journal	June 1977
Critical assessment of the automated AutoDock as a new docking tool for virtual screening Park, Hwangseo; Lee, Jinuk; Lee, Sangyoub Proteins: Structure, Function, and Bioinformatics, Vol. 65, Issue 3 https://doi.org/10.1002/prot.21183	journal	November 2006
Automated bond order assignment as an optimization problem Dehof, Anna Katharina; Rurainski, Alexander; Bui, Quang Bao Anh Bioinformatics, Vol. 27, Issue 5 https://doi.org/10.1093/bioinformatics/btq718	journal	January 2011
Principal Components of Ionicity Meister, J.; Schwarz, W. H. E. The Journal of Physical Chemistry, Vol. 98, Issue 33 https://doi.org/10.1021/j100084a048	journal	August 1994
Automatic assignment of chemical connectivity to organic molecules in the Cambridge Structural Database Baber, Jon C.; Hodgkin, Edward E. Journal of Chemical Information and Modeling, Vol. 32, Issue 5 https://doi.org/10.1021/ci00009a001	journal	September 1992
Prediction of atomization energy using graph kernel and active learning Tang, Yu-Hang; de Jong, Wibe A. The Journal of Chemical Physics, Vol. 150, Issue 4 https://doi.org/10.1063/1.5078640	journal	January 2019
Automated conformational analysis and structure generation: algorithms for molecular perception Leach, Andrew R.; Dolata, Daniel P.; Prout, Keith Journal of Chemical Information and Modeling, Vol. 30, Issue 3 https://doi.org/10.1021/ci00067a017	journal	August 1990

Similar Records

Transferable Dynamic Molecular Charge Assignment Using Deep Neural Networks

Journal Article · Tue Jul 31 00:00:00 EDT 2018 · Journal of Chemical Theory and Computation · OSTI ID:1805727

Nebgen, Benjamin Tyler; Lubbers, Nicholas Edward; Smith, Justin Steven; +6 more

Machine Learning Models Capture Plasmon Dynamics in Ag Nanoparticles

Journal Article · Thu Apr 20 00:00:00 EDT 2023 · Journal of Physical Chemistry. A, Molecules, Spectroscopy, Kinetics, Environment, and General Theory · OSTI ID:1805727

Habib, Adela; Lubbers, Nicholas; Tretiak, Sergei; +1 more

Less is more: Sampling chemical space with active learning

Journal Article · Tue May 22 00:00:00 EDT 2018 · Journal of Chemical Physics · OSTI ID:1805727

Smith, Justin Steven; Nebgen, Benjamin Tyler; Lubbers, Nicholas Edward; +2 more

Related Subjects

71 CLASSICAL AND QUANTUM MECHANICS
GENERAL PHYSICS
artificial neural networks
atomic properties
molecular properties
machine learning
excited state energies
proteins
quantum mechanical calculations
density functional theory
Schrodinger equations

Title: Bond order predictions using deep neural networks

Citation Formats

References (56)

Similar Records

Related Subjects