Optimization algorithm for improving the prediction accuracy of API solubility in green solvent
Ali Alasiri, Ahmed A. Lahiq, Abdullah A. Alshehri · 2026
Read Optimization algorithm for improving the prediction accuracy of API solubility in green solvent by Ali Alasiri, Ahmed A. Lahiq, Abdullah A. Alshehri (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/PMC13507240.txt.
Description
Ali Alasiri, Ahmed A Lahiq, and Abdullah A Alshehri develop, in 2026 work, a hybrid AI pipeline for drug solubility. It predicts how drug ingredients dissolve in supercritical carbon dioxide, a green solvent used in drug processing. Solubility there depends on tangled links between heat, pressure, and molecular traits, so lab measurement is slow. Their dataset holds more than 350 published measurements.
Two model types, an attention-based tabular network and a gradient boosting method, were tuned by three nature-inspired optimizers. The best pairing reached a fit score near 0.98 on held-out checks, with narrow uncertainty bands. Statistical tests confirmed real gaps between optimizers. Formulators could screen solvent conditions in software before committing bench time.
Catalog record
| CREATOR | Ali Alasiri, Ahmed A. Lahiq, Abdullah A. Alshehri |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 80791 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |