Artificial neural networks for the prediction of solvation energies based on experimental and computational data

Yang, Jiyoung; Knape, Matthias J.; Burkert, Oliver; Mazzini, Virginia; Jung, Alexander; Craig, Vincent S. J.; Miranda‐Quintana, Ramón Alain; Bluhmki, Erich; Smiatek, Jens

doi:10.1039/d0cp03701j

Cited by 16 publications

(19 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chemical hardness

and electronegativity

are chemical reactivity descriptors that were applied in an artificial neural network for predicting solvation energies [ 24 ]. They are defined as

and

where

and

denote the energies of the highest occupied (HOMO) and lowest unoccupied molecular orbitals (LUMO), respectively.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Atomistic Descriptors for Machine Learning Models of Solubility Parameters for Small Molecules and Polymers

et al. 2021

View full text Add to dashboard Cite

Descriptors derived from atomic structure and quantum chemical calculations for small molecules representing polymer repeat elements were evaluated for machine learning models to predict the Hildebrand solubility parameters of the corresponding polymers. Since reliable cohesive energy density data and solubility parameters for polymers are difficult to obtain, the experimental heat of vaporization ΔHvap of a set of small molecules was used as a proxy property to evaluate the descriptors. Using the atomistic descriptors, the multilinear regression model showed good accuracy in predicting ΔHvap of the small-molecule set, with a mean absolute error of 2.63 kJ/mol for training and 3.61 kJ/mol for cross-validation. Kernel ridge regression showed similar performance for the small-molecule training set but slightly worse accuracy for the prediction of ΔHvap of molecules representing repeating polymer elements. The Hildebrand solubility parameters of the polymers derived from the atomistic descriptors of the repeating polymer elements showed good correlation with values from the CROW polymer database.

show abstract

“…Chemical hardness

and electronegativity

are chemical reactivity descriptors that were applied in an artificial neural network for predicting solvation energies [ 24 ]. They are defined as

and

where

and

denote the energies of the highest occupied (HOMO) and lowest unoccupied molecular orbitals (LUMO), respectively.…”

Section: Methodsmentioning

confidence: 99%

“…where Q xx , Q yy and Q zz are diagonal elements of the second moment of the charge tensor. Chemical hardness η and electronegativity χ are chemical reactivity descriptors that were applied in an artificial neural network for predicting solvation energies [24]. They are defined as…”

Section: Molecular Descriptorsmentioning

confidence: 99%

Atomistic Descriptors for Machine Learning Models of Solubility Parameters for Small Molecules and Polymers

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Typical applications of RNNs include speech recognition [68] , [67] as well as weather, climate and finance forecasting [69] , [70] , [71] . In principle, RNNs can be regarded as a modified version of standard feed-forward ANNs [56] , [48] , [64] . The basic network structure is represented by one input layer, one or multiple hidden layers and one output layer with a varying number of nodes in each layer.…”

Section: Theoretical Background: Recurrent Neural Networkmentioning

confidence: 99%

“…Often used approaches are artificial neural networks (ANNs) which can be regarded as highdimensional regression methods for connecting input parameters to target variables [56] , [48] . ANNs are nowadays widely used in the field of natural sciences, as can be seen by applications ranging from the calculation of molecular properties, prediction of chemical reactions and drug screening [57] , [58] , [59] , [60] , [61] , [62] , [63] , [64] . Although ANNs are well suited to connect static features, they are often limited for data showing temporal evolution.…”

Section: Introductionmentioning

confidence: 99%

Generic and specific recurrent neural network models: Applications for large and small scale biopharmaceutical upstream processes

Smiatek

Clemens

Montano-Herrera

et al. 2021

Biotechnology Reports

Self Cite

View full text Add to dashboard Cite

Highlights Novel machine learning method based on recurrent neural networks for the accurate prediction of upstream cultivation processes. Insights into the temporal evolution of main upstream parameters and outcomes. High predictive capability, straightforward implementation and broad transferability of the proposed approach. New insights into the influence of parameter changes for process outcomes. Introduction of new analysis methods like autocorrelation functions for the detailed study of experimental and computational data.

show abstract

“…Recently, neural network model (NN) has received new attention for predicting solvation free energy prediction. [23][24][25][26] Some of these architectures operate over fixed molecular fingerprints common akin to traditional QSPR models. [27][28][29] However, due to the incomplete physical understanding of the structure of molecule and emergent properties, the features provided by domain experts may not include all critical design parameters in the material design.…”

Section: Introductionmentioning

confidence: 99%

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

Gao,

Yang,

Tang

et al. 2021

Preprint

View full text Add to dashboard Cite

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 1 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.

show abstract

Artificial neural networks for the prediction of solvation energies based on experimental and computational data

Abstract: The knowledge of thermodynamic properties for novel electrolyte formulations is of fundamental interest for industrial applications as well as academic research. Herewith, we present an artificial neural networks (ANN) approach...

Cited by 16 publications

References 41 publications

Atomistic Descriptors for Machine Learning Models of Solubility Parameters for Small Molecules and Polymers

Atomistic Descriptors for Machine Learning Models of Solubility Parameters for Small Molecules and Polymers

Generic and specific recurrent neural network models: Applications for large and small scale biopharmaceutical upstream processes

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

Contact Info

Product

Resources

About