A quantitative structure property relationship for prediction of solubilization of hazardous compounds using GA-based...

QSPR studies for estimating the incorporation organic hazardous compounds in cationic surfactant (CTAB) were developed by application of the structural descriptors and multiple linear regression (MLR) method. Various structure-related descriptors were studied in order to derive information on hydrophobic, electronic and steric properties of solute molecules. Theoretical molecular descriptors selected by genetic algorithms-procedure were followed to predict logKs values by a stepwise-MLR method. A simple model with low standard errors and high correlation coefficients was selected. It was also found that MLR method could model the relationship between solubility and structural descriptors perfectly. The proposed methodology was validated using full cross validation and external validation using division of the available data set into training and test sets. The squared regression coefficient of prediction for the MLR model was 0.9624. The results illustrated that the linear techniques such as MLR combined with a successful variable selection procedure are capable to generate an efficient QSPR model for predicting the solubility of different compounds. The proposed model can be used adequately for the prediction and description of the solubility of organic compounds in micellar solutions.