Improved Solubility Predictions in scCO2 Using Thermodynamics-Informed Machine Learning Models
- 15 April 2025
- journal article
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 65 (8) , 4043-4056
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 31,975 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 71 references indexed in Scilit:
- State-of-the-art conceptual design of supercritical carbon dioxide as a green technology involved in bioresource conversion processesChemical Engineering Journal, 2024
- GIT-Mol: A multi-modal large language model for molecular science with graph, image, and textComputers in Biology and Medicine, 2024
- A new hybrid quantitative structure property relationships‐support vector regression (QSPR‐SVR) approach for predicting the solubility of drug compounds in supercritical carbon dioxideAIChE Journal, 2023
- 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
- Computation of drug solvation free energy in supercritical CO2: Alternatives to all-atom computer simulationsFluid Phase Equilibria, 2021
- A Deep Learning Approach to Antibiotic DiscoveryCell, 2020
- 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