Accurately predicting solvation free energy in aqueous and organic solvents beyond 298 K by combining deep learning and the 1D reference interaction site model
Fowles, Daniel J. and McHardy, Rose G. and Ahmad, Abdullah and Palmer, David S. (2023) Accurately predicting solvation free energy in aqueous and organic solvents beyond 298 K by combining deep learning and the 1D reference interaction site model. Digital Discovery, 2 (1). pp. 177-188. ISSN 2635-098X (https://doi.org/10.1039/d2dd00103a)
Preview |
Text.
Filename: Fowles_etal_DD_2022_Accurately_predicting_solvation_free_energy_in_aqueous.pdf
Final Published Version License: Download (1MB)| Preview |
Abstract
We report a method to predict the absolute solvation free energy (SFE) of small organic and druglike molecules in water, carbon tetrachloride and chloroform solvents beyond 298 K by combining the 1 Dimensional Reference Interaction Site Model (1D-RISM) and deep learning. RISM is a statistical mechanics based method for modelling molecular solutions that is computationally inexpensive but is too inaccurate for routine SFE calculations in its common form. By replacing the 1D-RISM SFE functional with a 1D convolutional neural network (CNN) trained on RISM correlation functions, we show that predictions approaching chemical accuracy can be obtained for aqueous and non-aqueous solvents at a wide-range of temperatures. This method builds upon the previously reported RISM-MOL-INF procedure which applied RISM to accurately characterise solvation and desolvation processes through solute–solvent correlation functions [Palmer et al., Mol. Pharm., 2015, 12, 3420–3432]. Unlike RISM-MOL-INF however, the newly developed pyRISM-CNN model applied here is capable of rapidly modelling these processes in several different solvents and at a wide-range of temperatures. The pyRISM-CNN functional reduces the predictive error by up to 40-fold as compared to the standard 1D-RISM theory. Prediction errors below 1 kcal mol−1 are obtained for organic solutes in carbon tetrachloride or chloroform solvent systems at 298 K and water solvent systems at 273–373 K. pyRISM-CNN has been implemented in our in-house 1D-RISM solver (pyRISM), which is made freely available as open-source software.
ORCID iDs
Fowles, Daniel J., McHardy, Rose G., Ahmad, Abdullah ORCID: https://orcid.org/0000-0002-6315-749X and Palmer, David S. ORCID: https://orcid.org/0000-0003-4356-9144;-
-
Item type: Article ID code: 83774 Dates: DateEvent1 February 2023Published14 December 2022Published Online8 December 2022Accepted23 September 2022SubmittedSubjects: Science > Chemistry > Organic chemistry Department: Faculty of Science > Pure and Applied Chemistry Depositing user: Pure Administrator Date deposited: 19 Jan 2023 17:09 Last modified: 22 Dec 2024 01:32 URI: https://strathprints.strath.ac.uk/id/eprint/83774