Pharmaceutical nanonization by green supercritical processing: Investigation of Exemestane anti-estrogenic medicine solubility using machine learning

Abstract

Oral administration is known as the most prevalently-employed approach of drug delivery because of possessing different benefits like simplicity of use, affordability and negligible sterility restrictions. Despite the noteworthy interests of scientists to manufacture oral therapeutic medicines, poor solubility/bioavailability of orally-administered drugs remains a big challenge in recent years. Therefore, various scientists are trying to develop novel techniques to enhance the solubility of orally-administered therapeutic agents. One of the promising ways, which has recently attracted the global attentions is the use of supercritical fluids (SCFs). This technique could overcome the unfavorable/detrimental influences of organic solvents on the environment due to its environmentally-benign characteristics, non-inflammability and low toxicity. In this research, the solubility of Exemestane (EXE) drug is modeled based on two parameters of temperature and pressure. In order to handle the modeling process, the AdaBoost method with three core models of linear regression (LR), K-Nearest Neighbor (KNN) and Gaussian Process (GPR) are considered, which are tuned by AEO method in terms of their hyper-parameters. Based on the evaluations carried out in this research, ADA GPR, ADA KNN, and ADA LR models showed 0.996, 0.991, and 0.925 values in terms of R-square score. Also, in terms of the error rate, the three models ADA GPR, ADA KNN, and ADA LR have an RMSE error equal to 1.3459, 1.8967, and 5.8875, respectively. Based on these facts and some other analyses, the Gaussian process model optimized and boosted with AdaBoost can be accepted as the most accurate model of this research.