In this paper, a quantitative structure-retention relationship (QSRR) model was developed for predicting the retention indices (log RI) of 36 constituents of essential oils. First, the chemical structure of each compound was sketched using HyperChem software. Then, molecular descriptors covering different information of molecular structures were calculated by Dragon software. The results illustrated that linear techniques, such as multiple linear regression (MLR), combined with a successful variable selection procedure are capable of generating an efficient QSRR model for predicting the retention indices of different compounds. This model, with high statistical significance (R 2 = 0.9781, Q 2 LOO = 0.9691, Q 2 ext = 0.9546, Q 2 L(5)O = 0.9667, F = 245.27), could be used adequately for the prediction and description of the retention indices of other essential oil compounds. The reliability of the proposed model was further illustrated using various evaluation techniques: leave-5-out cross-validation, bootstrap, randomization test and validation through the test set.

The partitioning tendency of pesticides, in these study herbicides in particular, into different environmental compartments depends mainly of the physic-chemical 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 determining 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, every time associated with genetic algorithm (GA) selection of the most important variable, were used to develop QSPR models to predict the aqueous solubility of a series 80 herbicides. The values of log S of the studied compounds were well correlated with de descriptors. Considering the pertinent descriptors, a Pearson Correlation Squared (R2) coefficient 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; ? = 0.1111 and ? = 0.222.

Pesticide use in agriculture can cause undesirable effects on humans and the natural environment. Physicochemical properties of pesticides play an important role in determining its distribution and fate in the environment. Chemometric methods can be used to describe how the physicochemical properties vary according to the characteristics of the molecular structure expressed in terms of appropriate molecular descriptors. Quantitative Structure-Property Relationship (QSPR) models can also provide a general overview of the molecular structure that influences these properties. Henry's law constant (H) is an important property for predicting the solubility and vapor-liquid equilibrium of pesticides. Genetic algorithm/ multi-linear hybrid approach was used to model the log H of 48 pesticides belonging to four chemical classes: ureas, triazines, carbamates and aryloxyalkanoic acids. The 5 explanatory variables model selected is robust and has good fitness and good predictive ability. Two influential points which reinforce the model and an outlier were highlighted. The model can be used to predict the Henry's law constant of pesticides falling in the applicability domain of our model.

The search for new larvicides suited for vector control of mosquitoes requires considerable time, an enormous budget, and several analytical setups. Fortunately, the use of quantitative structure–activity relationship (QSAR) modeling allows the prediction of the larvicidal activity of structurally diverse chemicals against mosquitoes in a way quick and costless. This approach can be helpful to study for making biolarvicide with highest ability to destroy mosquito larvae. We propose a quantitative structure-activity relationship model using two different statistical methods, multiple linear regression (MLR) and Support vector machine (SVM) for predicting the larvicidal activity of 30 compounds of essential oils (EOs) isolated from the root of Asarum heterotropoides against Culex pipiens pallens. A model with four theoretical descriptors derived from Dragon software was developed applying the genetic algorithm (GA)-variable subset selection (VSS) procedure. The statistical parameters, R2 = 0.9716, Q2LOO = 0.9595, s = 0.1690 of the model developed by MLR showed a good predictive capability for log LC50 values. The comparison between the results of MLR and SVM models showed that the SVM model present a good alternative to construct a QSAR model for the prediction of the larvicidal activity.

No abstract