doiSerbia

Use of GA-ANN and GA-SVM for a QSPR study on the aqueous solubility of pesticides

Bouakkadia Amel (Environmental and Food Safety Laboratory, Department of Chemistry, Badji Mokhtar University - Annaba, Annaba, Algeria + Abbes Laghrour University, Faculty of Sciences and Technology - Khenchela, Route de Batna Khenchela, Algeria), [email protected]
Kertiou Noureddine (Environmental and Food Safety Laboratory, Department of Chemistry, Badji Mokhtar University - Annaba, Annaba, Algeria + Abbes Laghrour University, Faculty of Sciences and Technology - Khenchela, Route de Batna Khenchela, Algeria)
Amiri Rana (Environmental and Food Safety Laboratory, Department of Chemistry, Badji Mokhtar University - Annaba, Annaba, Algeria)
Driouche Youssouf (Environmental and Food Safety Laboratory, Department of Chemistry, Badji Mokhtar University - Annaba, Annaba, Algeria)
Messadi Djelloul (Environmental and Food Safety Laboratory, Department of Chemistry, Badji Mokhtar University - Annaba, Annaba, Algeria)

The partitioning tendency of pesticides, in this study herbicides in particular, into different environmental compartments depends mainly of the physicochemical properties of the pesticides itself. Aqueous solubility (S) indicates the tendency of a pesticide to be removed from soil by runoff or irrigation and to reach surface water. The experimental procedure for determining the aqueous solubility of pesticides is very expensive and difficult. QSPR methods are often used to estimate the aqueous solubility of herbicides. The artificial neural network (ANN) and support vector machine (SVM) methods, always associated with selection of a genetic algorithm (GA) of the most important variable, were used to develop QSPR models to predict the aqueous solubility of a series of 80 herbicides. The values of log S of the studied compounds were well correlated with the descriptors. Considering the pertinent descriptors, a Pearson correlation squared coefficient (R2) of 0.8 was obtained for the ANN model with a structure of 5-3-1 and 0.8 was obtained for the SVM model using the RBF function for the optimal parameters values: C = 11.12; σ = 0.1111 and ε = 0.222.

Keywords: Genetic algorithm, agrochemicals, descriptors, statistical methods