Improved Solubility Predictions in scCO2 Using Thermodynamics-Informed Machine Learning Models
Preprint
- 10 April 2025
- preprint
- Published by American Chemical Society (ACS) in ChemRxiv
Abstract
Accurate solubility prediction in supercritical carbon dioxide (scCO2) is crucial for optimizing experimental design by eliminating unnecessary and costly trials at an early stage, thereby streamlining the workflow. A comprehensive solubility database containing 31975 records has been compiled, providing a foundation for developing predictive models applicable to a diverse class of chemical compounds, with a particular focus on drug-like substances. In this study, we propose a Domain-Aware Machine Learning approach that incorporates thermodynamic properties governing phase transitions to solubility predictions in scCO2. Predictive models were developed using the CatBoost algorithm and a graph-based architecture employing directed message passing to identify the most effective approach. Furthermore, auxiliary properties of the solute, including melting point, critical parameters, enthalpy of vaporization, and Gibbs free energy of solvation, were predicted as part of this work. The findings underscore the efficacy of incorporating domain-specific thermodynamic features to enhance the predictive accuracy of scCO2 solubility modeling. The interpretation and the applicability domain assessment have confirmed the qualitative selection of the employed descriptors, demonstrating their ability to generalize to unique compounds that fall outside the defined domain.Keywords
All Related Versions
This publication has 54 references indexed in Scilit:
- Solubility of teriflunomide in supercritical carbon dioxide and co-solvent investigationFluid Phase Equilibria, 2024
- Viscosity of deep eutectic solvents: Predictive modeling with experimental validationFluid Phase Equilibria, 2024
- Solubility of Food-Relevant Substances in Pure and Modified Supercritical Carbon Dioxide: Experimental Data (2011–Present), Modeling, and Related ApplicationsFood Engineering Reviews, 2023
- Solubility, Extraction, and Nanoparticles Production in Supercritical Carbon Dioxide: A Mini‐ReviewChemBioEng Reviews, 2022
- QSPR Modelling of the Solubility of Drug and Drug‐like Compounds in Supercritical Carbon DioxideMolecular Informatics, 2022
- CO2 utilization as a supercritical solvent and supercritical antisolvent in production of sertraline hydrochloride nanoparticlesJournal of CO2 Utilization, 2022
- Supercritical CO2 as a green solvent for the circular economy: Extraction of fatty acids from fruit pomaceJournal of CO2 Utilization, 2020
- Thermophysical Properties of Chemicals and Hydrocarbons2014
- Applicability domain for in silico models to achieve accuracy of experimental measurementsJournal of Chemometrics, 2010
- Principles of QSAR models validation: internal and externalQSAR & Combinatorial Science, 2007