Experimental validation and modeling study on the drug solubility in supercritical solvent: Case study on Exemestane drug

Abstract

Green processing based on supercritical solvents has attracted much attention recently in different fields such as pharmaceutical industry due to its superior characteristics. Comprehensive modeling was performed in this study to analyze the preparation of nanomedicine using green supercritical processing. Computational analysis was performed in order to estimate the solubility at different pressures and temperatures. The model was developed based on the input parameters and can estimate the only output of the process which is drug solubility in the supercritical solvent. In this work, we examined how temperature and pressure affect EXE (Exemestane) drug solubility using different tree-based ensemble methods. The models used in this analysis are the Random Forest (RF), the Extremely Randomized Tree (ET), and the Gradient Boosting (GB). Model optimization and hyper-parameter tuning are also accomplished with the aid of Golden eagle optimizer (GEOA). The R2 values for the test phases of ET, GB, and RF were 0.993, 0.985, and 0.978, respectively. The scores are 0.9945, 0.9758, and 0.9904 in train phases. Specifically, the ET model was chosen since it is the most accurate one. Error rates for this model are 2.317 with MSE, 1.522 with RMSE, and 0.2113 with MAPE.