Predicting aqueous solubility by QSPR modeling

Nastaran Meftahi; Michael L Walker; Brian J Smith

doi:10.1016/j.jmgm.2021.107901

Predicting aqueous solubility by QSPR modeling

J Mol Graph Model. 2021 Jul:106:107901. doi: 10.1016/j.jmgm.2021.107901. Epub 2021 Mar 22.

Authors

Nastaran Meftahi¹, Michael L Walker¹, Brian J Smith²

Affiliations

¹ La Trobe Institute for Molecular Science, La Trobe University, Melbourne, Victoria, 3086, Australia.
² La Trobe Institute for Molecular Science, La Trobe University, Melbourne, Victoria, 3086, Australia. Electronic address: brian.smith@latrobe.edu.au.

PMID: 33857890
DOI: 10.1016/j.jmgm.2021.107901

Abstract

The aqueous solubility is predicted here using quantitative structure property relationship (QSPR) models. In this study, we examine whether descriptors that individually yield favorable models for the prediction of the Gibbs energy of solvation and sublimation can be used in combination with octanol-water partition coefficient to produce QSPR models for the prediction of aqueous solubility. Based on this strategy, applied to seven distinct datasets, all models exhibited an R² greater than 0.7 and Q² greater than 0.6 for the estimation of aqueous solubility. We also determined how uncoupling the descriptors used to create QSPR models in the prediction of Gibbs energy of sublimation yielded an improved model. Model refinement using an artificial neural network applying the same descriptors generated significantly better models with improved R² and standard deviation.

Keywords: Aqueous solubility; Machine learning; QSPR.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Neural Networks, Computer
Quantitative Structure-Activity Relationship*
Solubility
Water*

Substances

Water