2D and 3D-QSAR study on the fish embryo Toxicity test of EC₅₀

Quantitative structure-toxicity relationships were developed for the prediction of the fish embryo toxicity test, based on the linear heuristic method (HM) and support vector machines (SVM). Each kind of compound was represented by several calculated structural descriptors, derived for a diverse set of 30 compounds using DFT-B3LYP/6-31+G (d) level of the theory. A seven-parameter correlation was found to be the most important descriptor affecting the toxicity. In the HM method, the value of square of the correlation coefficient R² is 0.761, in the SVM method, the value of the R ² is 0.867 in the training set. We report 3D-QSAR analyses using CoMFA and CoMSIA in order to have a better understanding of the mechanism of action and structure-activity relationship of these compounds. In the CoMFA method, the value of square of the correlation coefficient r² is 0.964, in the CoMSIA method, the value of the r² is 0.912 in the training set. The steric and hydrophobic play relatively important roles on the toxicity.