Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Graphical Gaussian Process Regression Model for Aqueous Solvation Free Energy Prediction of Organic Molecules in Redox Flow Battery

Journal Article · · Physical Chemistry Chemical Physics. PCCP
DOI:https://doi.org/10.1039/D1CP04475C· OSTI ID:1817885
; ; ; ; ; ; ;
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.
Research Organization:
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States); Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
Sponsoring Organization:
USDOE
Grant/Contract Number:
AC02-05CH11231; AC05-76RL01830
OSTI ID:
1817885
Alternate ID(s):
OSTI ID: 1828469
OSTI ID: 1833030
Report Number(s):
PNNL-SA--161057; ark:/13030/qt4v85j39p
Journal Information:
Physical Chemistry Chemical Physics. PCCP, Journal Name: Physical Chemistry Chemical Physics. PCCP Journal Issue: 43 Vol. 23; ISSN 1463-9076
Country of Publication:
United States
Language:
English

References (52)

Energies, structures, and electronic properties of molecules in solution with the C-PCM solvation model journal April 2003
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 journal January 2020
Next-generation aqueous flow battery chemistries journal December 2019
Aqueous organic and redox-mediated redox flow batteries: a review journal June 2020
Deep learning and knowledge-based methods for computer-aided molecular design—toward a unified approach: State-of-the-art and future directions journal October 2020
Gaussian process regression and conditional polynomial chaos for parameter estimation journal September 2020
Battery Lifetime Prognostics journal February 2020
Machinery health prognostics: A systematic review from data acquisition to RUL prediction journal May 2018
Quantum Interference, Graphs, Walks, and Polynomials journal April 2018
Electrolyte Lifetime in Aqueous Organic Redox Flow Batteries: A Critical Review journal February 2020
Approaches for Calculating Solvation Free Energies and Enthalpies Demonstrated with an Update of the FreeSolv Database journal April 2017
Multisolvent Models for Solvation Free Energy Predictions Using 3D-RISM Hydration Thermodynamic Descriptors journal April 2020
Predicting Hydration Free Energies of the FreeSolv Database of Drug-like Molecules with Molecular Density Functional Theory journal June 2020
Multiscale Cross-Domain Thermochemical Knowledge-Graph journal November 2020
Convolutional Embedding of Attributed Molecular Graphs for Physical Property Prediction journal July 2017
Molecular Dynamics Fingerprints (MDFP): Machine Learning from MD Data To Predict Free-Energy Differences journal April 2017
Solvent-Specific Featurization for Predicting Free Energies of Solvation through Machine Learning journal January 2019
Evaluating Classical Force Fields against Experimental Cross-Solvation Free Energies journal November 2020
A Comprehensive Comparison of the IEFPCM and SS(V)PE Continuum Solvation Methods with the COSMO Approach journal August 2015
OPLS3e: Extending Force Field Coverage for Drug-Like Small Molecules journal January 2019
Predicting Single-Substance Phase Diagrams: A Kernel Approach on Graph Representations of Molecules journal May 2021
Graph Kernels for Molecular Structure−Activity Relationship Analysis with Support Vector Machines journal July 2005
Deep Neural Nets as a Method for Quantitative Structure–Activity Relationships journal February 2015
Some New Trends in Chemical Graph Theory journal March 2008
Quantum Mechanical Continuum Solvation Models journal August 2005
The Structure, Thermodynamics, and Solubility of Organic Crystals from Simulation with a Polarizable Force Field journal April 2012
Improving the Prediction of Absolute Solvation Free Energies Using the Next Generation OPLS Force Field journal July 2012
A Priori Phase Equilibrium Prediction from a Segment Contribution Solvation Model journal March 2002
Conductor-like Screening Model for Real Solvents: A New Approach to the Quantitative Calculation of Solvation Phenomena journal February 1995
Convergence, molecular complexity, and synthetic analysis journal October 1982
The first general index of molecular complexity journal June 1981
A Blind Challenge for Computational Solvation Free Energies: Introduction and Overview journal April 2009
Solvation Free Energy Calculations Using a Continuum Dielectric Model for the Solvent and Gradient-Corrected Density Functional Theory for the Solute journal January 1996
Deep learning journal May 2015
Enhancing materials property prediction by leveraging computational and experimental data using deep transfer learning journal November 2019
A review of methods for the calculation of solution free energies and the modelling of systems in solution journal January 2015
MoleculeNet: a benchmark for molecular machine learning journal January 2018
Delfos: deep learning model for prediction of solvation free energies in generic organic solvents journal January 2019
Fast and accurate calculation of hydration energies of molecules and ions journal January 2020
Machine-guided representation for accurate graph-based molecular machine learning journal January 2020
Artificial neural networks for the prediction of solvation energies based on experimental and computational data journal January 2020
Can we predict materials that can be synthesised? journal January 2021
Self‐Consistent Molecular‐Orbital Methods. IX. An Extended Gaussian‐Type Basis for Molecular‐Orbital Studies of Organic Molecules journal January 1971
Rationale for mixing exact exchange with density functional approximations journal December 1996
Neural networks vs Gaussian process regression for representing potential energy surfaces: A comparative study of fit quality and vibrational spectrum accuracy journal June 2018
Prediction of atomization energy using graph kernel and active learning journal January 2019
NWChem: Past, present, and future journal May 2020
Hydration free energies from kernel-based machine learning: Compound-database bias journal July 2020
A High-Throughput Solver for Marginalized Graph Kernels on GPU conference May 2020
Accurate and transferable multitask prediction of chemical properties with an atoms-in-molecules neural network journal August 2019
Inverse molecular design using machine learning: Generative models for matter engineering journal July 2018
Compressed graph representation for scalable molecular graph generation journal September 2020

Similar Records

Solvation thermodynamics of neutral and charged solutes using the solvation‐layer interface condition continuum dielectric model
Journal Article · Thu Oct 11 20:00:00 EDT 2018 · International Journal of Quantum Chemistry · OSTI ID:1479564

Related Subjects

25 ENERGY STORAGE
batteries
machine learning