As quantitative structure-property relationship (QSPR) technique provides a suitable tool to predict the critical micelle concentration (CMC) of Gemini surfactants from their structure descriptors. In this study, a comparative work was conducted to model the CMC property of 211 diverse Gemini surfactants based on their structural characteristics using linear and non-linear quantitative structure-property relationship models. Least squares model (OLS) and partial least squares (PLS) against k-nearest neighbours regression model (KNN), artificial neural network (ANN) and support vector regression (SVR) have been developed to model the CMC. Molecular descriptors were calculated and screened to remove unsuitable descriptors and improve the learning. Results indicate that the improved performance of support vector regression when the hyper-parameters are optimized using Dragonfly algorithm (SVR-DA) was highly capable of predicting the pCMC (-logCMC) values with an average absolute relative deviation (AARD) of 0.666 and coefficient of determination (R?) of 0.9971 for the global dataset.

In this work, the solubilities of some anti-inflammatory (nabumetone, phenylbutazone and salicylamide) and statin drugs (fluvastatin, atorvastatin, lovastatin, simvastatin and rosuvastatin) were correlated using the Perturbed-Chain Statistical Associating Fluid Theory (PC-SAFT) with one-parameter mixing rule and commonly used cubic equations of state Peng-Robinson (PR) and Soave-Redlich-Kwong (SRK) combining with van-der Waals-1 parameter (VDW1) and van-der Waals-2 parameters (VDW2) mixing rules. The experimental data for studied compounds were taken from literature at temperature and pressure in ranges (308-348 K) and (100-360 bar) respectively. The critical properties required for the correlation with PR and SRK were estimated using Gani and Noonalol contribution group methods whereas, PC-SAFT pure-component parameters; segment number (m), segment diameter (σ) and energy parameter (ε/k) have been estimated by tihic’s group contribution method for nabumetone. For phenylbutazone and salicylamide those parameters were determined using a linear correlation. For statin drugs, PC-SAFT parameters were fitted to solubility data, and binary interaction parameters (kij and lij) have been obtained by fitting the experimental data. The result was found to be in good agreement with the experimental data and showed that PC-SAFT approach can be used to model solid-SCF equilibrium with better correlation accuracy than cubic equations of state