Toward Predicting Solubility of Arbitrary Solutes in Arbitrary Solvents: Prediction of Density and Refractive Index Using Machine Learning Algorithms with Global Sensitivity Analysis
Brian Hu, Jingchen Zhai, Xiguang Qi, Xibing He, Nick X. Wang, Junmei Wang · 2026
Read Toward Predicting Solubility of Arbitrary Solutes in Arbitrary Solvents: Prediction of Density and Refractive Index Using Machine Learning Algorithms with Global Sensitivity Analysis by Brian Hu, Jingchen Zhai, Xiguang Qi, Xibing He, Nick X. Wang, Junmei Wang (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13386533.txt.
Description
Brian Hu and colleagues train machine learning models to predict liquid density and refractive index in 2026 work. Both measures guide solvent choice and mixture work in process chemistry, and both tie to molecular energy terms. Data covered roughly 5,000 compounds for density and 4,000 for refractive index values.
Two descriptor families fed several learning algorithms, and both yielded sturdy models with low errors. One family edged ahead slightly on both properties in their tests. Sensitivity and Shapley analyses then ranked which features carried the predictions, a step toward the larger goal of predicting solubility for any solute-solvent pairing.
Catalog record
| CREATOR | Brian Hu, Jingchen Zhai, Xiguang Qi, Xibing He, Nick X. Wang, Junmei Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 50355 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |