Answers are grounded in this paper and cite their sources.
Nevirapine is an antiretroviral medication used in the treatment of HIV-1 disease, with primary application as part of combination antiretroviral therapy (ART) to reduce the viral load in the body and improve immune function in people living with HIV. Precise predictions of Nevirapine solubility in different organic solvents allow pharmacists and researchers to identify suitable solvents or solvent combinations to enhance solubility, ensuring that the drug achieves its desired therapeutic concentration. Additionally, accurate models reduce the need for extensive experimental trials, saving time and resources in drug development. This study conducts a comprehensive evaluation of eight artificial intelligence methods for estimating the solubility of Nevirapine in organic solvent mixtures. A dataset comprising 309 solubility measurements in solvents such as methanol, n-propanol, iso-butanol, and toluene was compiled and used in order to train eight machine-learning algorithms: ridge regression, lasso regression, extra trees, ensemble learning, random forest, k-nearest neighbors, adaptive boosting, and decision tree models. The Leverage methodology was applied to evaluate the reliability and accuracy of the dataset, identifying only seven data points as outliers. The performance of formed data-driven models was evaluated with the random forest model emerging as the most precise for solubility prediction. Sensitivity analysis revealed that the mole fraction of iso-butanol had the least impact on solubility, while temperature had the greatest influence. These findings demonstrate the utility of the proposed methods, offering valuable tools for pharmacists working with Nevirapine.
No takes yet. Share an insight, caveat, or question.
Hasan et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: