Development of Novel Machine Learning to Optimize the Solubility of Azathioprine as Anticancer Drug in Supercritical Carbon Dioxide

Abstract

Supercritical carbon dioxide (Sc-CO2) has thus been proposed as an appropriate solvent for diluting the pharmaceuticals to increase particle size. The use of supercritical fluids (SCFs) in various industrial applications, such as extraction, chromatography, and particle engineering, has attracted considerable interest. Recognizing the solubility behavior of various drugs is an essential step in the pharmaceutical industry's pursuit of the most effective supercritical approach. In this work, four models were used to predict the solubility of Azathioprine in supercritical carbon dioxide, including Ridge regression (RR), Huber regression (HR), Random forest (RF), and Gaussian process regression (GPR). The R-squared scores of all four models are 0.974, 0.6518, 0.966, and 1.0 for Ridge regression (RR), Huber regression (HR), Random forest (RF), and Gaussian process regression (GPR) models, respectively. The RMSE error rates of 2.843 ×10^-13, 7.036 ×10^-12, 5.673 ×10^-13, and 1.054 ×10^-30 for the RR, HR, RF, and GPR models, respectively. MAE metrics of 1.205 ×10^-6, 2.151  ×10^-6, 5.997 ×10^-7 and 9.419 ×10^-16 errors were also found in the RR, HR, RF, and GPR models, respectively. It was found that Ridge regression (RR), Random forest (RF), and Gaussian process regression (GPR) models can be used to predict any compound's solubility in supercritical carbon dioxide.