Quantitative Structure–Activity Relationship (QSAR) model is presented for the estimation of the toxicity of 28 nitroaromatic compounds including some well-known explosives. This work was conducted using the principal component analysis (PCA) method, the multiple linear regression method (MLR), the multiple non-linear regressions (MNLR) and the artificial neural network (ANN). The predicted results of various nitro-aromatic compounds afford reliable prediction of LD50 with respect to experimental data. Density functional theory (DFT) calculations have been carried out in order to get insights into the structure, chemical reactivity and property information for the series of study compounds. This study shows that the MLR and ANN have served also to predict activities, but when compared with the results given by the RNLM, we realized that the predictions fulfilled by this latter were more effective.
