Graphical Gaussian process regression model for aqueous solvation free energy prediction of organic molecules in redox flow batteries

Gao, Peiyuan; Yang, Xiu; Tang, Yu-Hang; Zheng, Muqing; Andersen, Amity; Murugesan, Vijayakumar; Hollas, Aaron; Wang, Wei

doi:10.1039/d1cp04475c

Title: Graphical Gaussian process regression model for aqueous solvation free energy prediction of organic molecules in redox flow batteries

Journal Article · Thu Oct 28 00:00:00 EDT 2021 · Physical Chemistry Chemical Physics. PCCP

DOI:https://doi.org/10.1039/d1cp04475c· OSTI ID:1833030

Gao, Peiyuan ^[1];

^[2]; Tang, Yu-Hang ^[3]; Zheng, Muqing ^[2]; Andersen, Amity ^[1];

^[1];

^[1]

Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Lehigh Univ., Bethlehem, PA (United States)
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)

The solvation free energy of organic molecules is a critical parameter in determining emergent properties such as solubility, liquid-phase equilibrium constants, and pKa and redox potentials in an organic redox flow battery. In this work, we present a machine learning (ML) model that can learn and predict the aqueous solvation free energy of an organic molecule using Gaussian process regression method based on a new molecular graph kernel. To investigate the performance of the ML model on electrostatic interaction, the nonpolar interaction contribution of solvent and the conformational entropy of solute in solvation free energy, three data sets with implicit or explicit water solvent models, and contribution of conformational entropy of solute are tested. We demonstrate that our ML model can predict the solvation free energy of molecules at chemical accuracy with a mean absolute error of less than 1 kcal/mol for subsets of the QM9 dataset and the Freesolv database. To solve the general data scarcity problem for a graph-based ML model, we propose a dimension reduction algorithm based on the distance between molecular graphs, which can be used to examine the diversity of the molecular data set. It provides a promising way to build a minimum training set to improve prediction for certain test sets where the space of molecular structures is predetermined.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Pacific Northwest National Laboratory (PNNL), Richland, WA (United States); Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)

Sponsoring Organization:: USDOE

Grant/Contract Number:: AC05-76RL01830; AC02-05CH11231; AC02-05CH1123

OSTI ID:: 1833030

Alternate ID(s):: OSTI ID: 1817885; OSTI ID: 1828469

Report Number(s):: PNNL-SA-161057

Journal Information:: Physical Chemistry Chemical Physics. PCCP, Vol. 23, Issue 43; ISSN 1463-9076

Publisher:: Royal Society of ChemistryCopyright Statement

Country of Publication:: United States

Language:: English

References (50)

Deep learning LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey Nature, Vol. 521, Issue 7553 https://doi.org/10.1038/nature14539	journal	May 2015
NWChem: Past, present, and future Aprà, E.; Bylaska, E. J.; de Jong, W. A. The Journal of Chemical Physics, Vol. 152, Issue 18 https://doi.org/10.1063/5.0004997	journal	May 2020
Neural networks vs Gaussian process regression for representing potential energy surfaces: A comparative study of fit quality and vibrational spectrum accuracy Kamath, Aditya; Vargas-Hernández, Rodrigo A.; Krems, Roman V. The Journal of Chemical Physics, Vol. 148, Issue 24 https://doi.org/10.1063/1.5003074	journal	June 2018
Deep Neural Nets as a Method for Quantitative Structure–Activity Relationships Ma, Junshui; Sheridan, Robert P.; Liaw, Andy Journal of Chemical Information and Modeling, Vol. 55, Issue 2 https://doi.org/10.1021/ci500747n	journal	February 2015
Some New Trends in Chemical Graph Theory García-Domenech, Ramón; Gálvez, Jorge; de Julián-Ortiz, Jesus V. Chemical Reviews, Vol. 108, Issue 3 https://doi.org/10.1021/cr0780006	journal	March 2008
Convergence, molecular complexity, and synthetic analysis Bertz, Steven H. Journal of the American Chemical Society, Vol. 104, Issue 21 https://doi.org/10.1021/ja00385a049	journal	October 1982
A review of methods for the calculation of solution free energies and the modelling of systems in solution Skyner, R. E.; McDonagh, J. L.; Groom, C. R. Physical Chemistry Chemical Physics, Vol. 17, Issue 9 https://doi.org/10.1039/C5CP00288E	journal	January 2015
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
Self‐Consistent Molecular‐Orbital Methods. IX. An Extended Gaussian‐Type Basis for Molecular‐Orbital Studies of Organic Molecules Ditchfield, R.; Hehre, W. J.; Pople, J. A. The Journal of Chemical Physics, Vol. 54, Issue 2 https://doi.org/10.1063/1.1674902	journal	January 1971
Compressed graph representation for scalable molecular graph generation Kwon, Youngchun; Lee, Dongseon; Choi, Youn-Suk Journal of Cheminformatics, Vol. 12, Issue 1 https://doi.org/10.1186/s13321-020-00463-2	journal	September 2020
The first general index of molecular complexity Bertz, Steven H. Journal of the American Chemical Society, Vol. 103, Issue 12 https://doi.org/10.1021/ja00402a071	journal	June 1981
Multiscale Cross-Domain Thermochemical Knowledge-Graph Mosbach, Sebastian; Menon, Angiras; Farazi, Feroz Journal of Chemical Information and Modeling, Vol. 60, Issue 12 https://doi.org/10.1021/acs.jcim.0c01145	journal	November 2020
Approaches for Calculating Solvation Free Energies and Enthalpies Demonstrated with an Update of the FreeSolv Database Duarte Ramos Matos, Guilherme; Kyu, Daisy Y.; Loeffler, Hannes H. Journal of Chemical & Engineering Data, Vol. 62, Issue 5 https://doi.org/10.1021/acs.jced.7b00104	journal	April 2017
Battery Lifetime Prognostics Hu, Xiaosong; Xu, Le; Lin, Xianke Joule, Vol. 4, Issue 2 https://doi.org/10.1016/j.joule.2019.11.018	journal	February 2020
Can we predict materials that can be synthesised? Szczypiński, Filip T.; Bennett, Steven; Jelfs, Kim E. Chemical Science, Vol. 12, Issue 3 https://doi.org/10.1039/D0SC04321D	journal	January 2021
Gaussian process regression and conditional polynomial chaos for parameter estimation Li, Jing; Tartakovsky, Alexandre M. Journal of Computational Physics, Vol. 416 https://doi.org/10.1016/j.jcp.2020.109520	journal	September 2020
Quantum Mechanical Continuum Solvation Models Tomasi, Jacopo; Mennucci, Benedetta; Cammi, Roberto Chemical Reviews, Vol. 105, Issue 8 https://doi.org/10.1021/cr9904009	journal	August 2005
A Blind Challenge for Computational Solvation Free Energies: Introduction and Overview Guthrie, J. Peter The Journal of Physical Chemistry B, Vol. 113, Issue 14 https://doi.org/10.1021/jp806724u	journal	April 2009
Improving the Prediction of Absolute Solvation Free Energies Using the Next Generation OPLS Force Field Shivakumar, Devleena; Harder, Edward; Damm, Wolfgang Journal of Chemical Theory and Computation, Vol. 8, Issue 8 https://doi.org/10.1021/ct300203w	journal	July 2012
Predicting Hydration Free Energies of the FreeSolv Database of Drug-like Molecules with Molecular Density Functional Theory Luukkonen, Sohvi; Belloni, Luc; Borgis, Daniel Journal of Chemical Information and Modeling, Vol. 60, Issue 7 https://doi.org/10.1021/acs.jcim.0c00526	journal	June 2020
Aqueous organic and redox-mediated redox flow batteries: a review Gentil, Solène; Reynard, Danick; Girault, Hubert H. Current Opinion in Electrochemistry, Vol. 21 https://doi.org/10.1016/j.coelec.2019.12.006	journal	June 2020
Prediction of octanol-water partition coefficients for the SAMPL6-$$\log P$$logP molecules using molecular dynamics simulations with OPLS-AA, AMBER and CHARMM force fields Fan, Shujie; Iorga, Bogdan I.; Beckstein, Oliver Journal of Computer-Aided Molecular Design, Vol. 34, Issue 5 https://doi.org/10.1007/s10822-019-00267-z	journal	January 2020
Next-generation aqueous flow battery chemistries Narayan, Sri R.; Nirmalchandar, Archith; Murali, Advaith Current Opinion in Electrochemistry, Vol. 18 https://doi.org/10.1016/j.coelec.2019.10.010	journal	December 2019
Inverse molecular design using machine learning: Generative models for matter engineering Sanchez-Lengeling, Benjamin; Aspuru-Guzik, Alán Science, Vol. 361, Issue 6400 https://doi.org/10.1126/science.aat2663	journal	July 2018
Solvent-Specific Featurization for Predicting Free Energies of Solvation through Machine Learning Hutchinson, Samuel T.; Kobayashi, Rika Journal of Chemical Information and Modeling, Vol. 59, Issue 4 https://doi.org/10.1021/acs.jcim.8b00901	journal	January 2019
Multisolvent Models for Solvation Free Energy Predictions Using 3D-RISM Hydration Thermodynamic Descriptors Subramanian, Vigneshwari; Ratkova, Ekaterina; Palmer, David Journal of Chemical Information and Modeling, Vol. 60, Issue 6 https://doi.org/10.1021/acs.jcim.0c00065	journal	April 2020
Convolutional Embedding of Attributed Molecular Graphs for Physical Property Prediction Coley, Connor W.; Barzilay, Regina; Green, William H. Journal of Chemical Information and Modeling, Vol. 57, Issue 8 https://doi.org/10.1021/acs.jcim.6b00601	journal	July 2017
Hydration free energies from kernel-based machine learning: Compound-database bias Rauer, Clemens; Bereau, Tristan The Journal of Chemical Physics, Vol. 153, Issue 1 https://doi.org/10.1063/5.0012230	journal	July 2020
Solvation Free Energy Calculations Using a Continuum Dielectric Model for the Solvent and Gradient-Corrected Density Functional Theory for the Solute Tawa, Gregory J.; Martin, Richard L.; Pratt, Lawrence R. The Journal of Physical Chemistry, Vol. 100, Issue 5 https://doi.org/10.1021/jp951780e	journal	January 1996
Deep learning and knowledge-based methods for computer-aided molecular design—toward a unified approach: State-of-the-art and future directions Alshehri, Abdulelah S.; Gani, Rafiqul; You, Fengqi Computers & Chemical Engineering, Vol. 141 https://doi.org/10.1016/j.compchemeng.2020.107005	journal	October 2020
Conductor-like Screening Model for Real Solvents: A New Approach to the Quantitative Calculation of Solvation Phenomena Klamt, Andreas The Journal of Physical Chemistry, Vol. 99, Issue 7 https://doi.org/10.1021/j100007a062	journal	February 1995
Predicting Single-Substance Phase Diagrams: A Kernel Approach on Graph Representations of Molecules Xiang, Yan; Tang, Yu-Hang; Liu, Hongyi The Journal of Physical Chemistry A, Vol. 125, Issue 20 https://doi.org/10.1021/acs.jpca.1c02391	journal	May 2021
Machinery health prognostics: A systematic review from data acquisition to RUL prediction Lei, Yaguo; Li, Naipeng; Guo, Liang Mechanical Systems and Signal Processing, Vol. 104 https://doi.org/10.1016/j.ymssp.2017.11.016	journal	May 2018
A High-Throughput Solver for Marginalized Graph Kernels on GPU Tang, Yu-Hang; Selvitopi, Oguz; Popovici, Doru Thom 2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS) https://doi.org/10.1109/IPDPS47924.2020.00080	conference	May 2020
Fast and accurate calculation of hydration energies of molecules and ions Voityuk, Alexander A.; Vyboishchikov, Sergei F. Physical Chemistry Chemical Physics, Vol. 22, Issue 26 https://doi.org/10.1039/D0CP02667K	journal	January 2020
Graph Kernels for Molecular Structure−Activity Relationship Analysis with Support Vector Machines Mahé, Pierre; Ueda, Nobuhisa; Akutsu, Tatsuya Journal of Chemical Information and Modeling, Vol. 45, Issue 4 https://doi.org/10.1021/ci050039t	journal	July 2005
Artificial neural networks for the prediction of solvation energies based on experimental and computational data Yang, Jiyoung; Knape, Matthias J.; Burkert, Oliver Physical Chemistry Chemical Physics, Vol. 22, Issue 42 https://doi.org/10.1039/D0CP03701J	journal	January 2020
Enhancing materials property prediction by leveraging computational and experimental data using deep transfer learning Jha, Dipendra; Choudhary, Kamal; Tavazza, Francesca Nature Communications, Vol. 10, Issue 1 https://doi.org/10.1038/s41467-019-13297-w	journal	November 2019
Quantum Interference, Graphs, Walks, and Polynomials Tsuji, Yuta; Estrada, Ernesto; Movassagh, Ramis Chemical Reviews, Vol. 118, Issue 10 https://doi.org/10.1021/acs.chemrev.7b00733	journal	April 2018
OPLS3e: Extending Force Field Coverage for Drug-Like Small Molecules Roos, Katarina; Wu, Chuanjie; Damm, Wolfgang Journal of Chemical Theory and Computation, Vol. 15, Issue 3 https://doi.org/10.1021/acs.jctc.8b01026	journal	January 2019
Molecular Dynamics Fingerprints (MDFP): Machine Learning from MD Data To Predict Free-Energy Differences Riniker, Sereina Journal of Chemical Information and Modeling, Vol. 57, Issue 4 https://doi.org/10.1021/acs.jcim.6b00778	journal	April 2017
A Priori Phase Equilibrium Prediction from a Segment Contribution Solvation Model Lin, Shiang-Tai; Sandler, Stanley I. Industrial & Engineering Chemistry Research, Vol. 41, Issue 5 https://doi.org/10.1021/ie001047w	journal	March 2002
Rationale for mixing exact exchange with density functional approximations Perdew, John P.; Ernzerhof, Matthias; Burke, Kieron The Journal of Chemical Physics, Vol. 105, Issue 22, p. 9982-9985 https://doi.org/10.1063/1.472933	journal	December 1996
A Comprehensive Comparison of the IEFPCM and SS(V)PE Continuum Solvation Methods with the COSMO Approach Klamt, A.; Moya, C.; Palomar, J. Journal of Chemical Theory and Computation, Vol. 11, Issue 9 https://doi.org/10.1021/acs.jctc.5b00601	journal	August 2015
The Structure, Thermodynamics, and Solubility of Organic Crystals from Simulation with a Polarizable Force Field Schnieders, Michael J.; Baltrusaitis, Jonas; Shi, Yue Journal of Chemical Theory and Computation, Vol. 8, Issue 5 https://doi.org/10.1021/ct300035u	journal	April 2012
Evaluating Classical Force Fields against Experimental Cross-Solvation Free Energies Kashefolgheta, Sadra; Oliveira, Marina P.; Rieder, Salomé R. Journal of Chemical Theory and Computation, Vol. 16, Issue 12 https://doi.org/10.1021/acs.jctc.0c00688	journal	November 2020
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
Machine-guided representation for accurate graph-based molecular machine learning Na, Gyoung S.; Chang, Hyunju; Kim, Hyun Woo Physical Chemistry Chemical Physics, Vol. 22, Issue 33 https://doi.org/10.1039/D0CP02709J	journal	January 2020
Electrolyte Lifetime in Aqueous Organic Redox Flow Batteries: A Critical Review Kwabi, David G.; Ji, Yunlong; Aziz, Michael J. Chemical Reviews, Vol. 120, Issue 14 https://doi.org/10.1021/acs.chemrev.9b00599	journal	February 2020
Energies, structures, and electronic properties of molecules in solution with the C-PCM solvation model Cossi, Maurizio; Rega, Nadia; Scalmani, Giovanni Journal of Computational Chemistry, Vol. 24, Issue 6 https://doi.org/10.1002/jcc.10189	journal	April 2003

Similar Records

Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals

Journal Article · Wed Apr 10 00:00:00 EDT 2019 · Chemistry of Materials · OSTI ID:1833030

Chen, Chi; Ye, Weike; Zuo, Yunxing; +2 more

High-Throughput Screening of Promising Redox-Active Molecules with MolGAT

Journal Article · Fri Jun 30 00:00:00 EDT 2023 · ACS Omega · OSTI ID:1833030

Chaka, Mesfin Diro; Geffe, Chernet Amente; Rodriguez, Alex; +3 more

Graph-Based Approaches for Predicting Solvation Energy in Multiple Solvents: Open Datasets and Machine Learning Models

Journal Article · Wed Jun 30 00:00:00 EDT 2021 · Journal of Physical Chemistry. A, Molecules, Spectroscopy, Kinetics, Environment, and General Theory · OSTI ID:1833030

Ward, Logan; Dandu, Naveen; Blaiszik, Ben; +5 more

Related Subjects

25 ENERGY STORAGE
batteries
machine learning

Title: Graphical Gaussian process regression model for aqueous solvation free energy prediction of organic molecules in redox flow batteries

Citation Formats

References (50)

Similar Records

Related Subjects