Novel mathematical and polypharmacology predictions of salicylsalicylic acid: Solubility enhancement through SCCO₂ system

Over the last decades, significant drawbacks of organic solvents such as high toxicity have motivated the scientists to find more eco-friendly solvents. Supercritical fluids (SCFs), especially SCCO₂, are known as a promising class of solvent, which have shown their indisputable potential of application in industrial-based pharmaceutical activities due to possessing various advantages such as high abundancy, low cost, and insignificant toxicity. Machine Learning (ML) is considered as a numerical approach to estimate drug solubility in pharmaceutical industry. The purpose of this manuscript is to estimate the solubility of salicylsalicylic acid in SCCO₂ and compare it with experimental data using machine learning (ML) approach. A regression problem with 32 input vectors is the subject of this study, which is being conducted. This dataset contains two input features (P and T) and one output feature. We utilized Decision Tree (DT), K-nearest neighbor (KNN), and Multilayer perceptron (MLP) regression models as the first time for salicylsalicylic acid, which had error rates of 1.10E-01, 1.07E-01, and 7.13E-01, respectively, when using the MAPE measure. In addition, the R-squared scores for the DT, KNN, and MLP models are 0.974, 0.996, and 0.809, respectively. The third statistic is MAE, in which the error rates of models are 5.27E-05 for DT, 5.53E-05 for KNN, and 2.61E-04 for MLP. The error rates of DT, KNN, and MLP are all 5.27E-05. Finally, KNN was the most general model, with optimal values of P = 400, T = 338.0, and Y = 0.00388 being obtained.