Structure-toxicity relationships were studied for a set of 44 herbicides by means of principal component analysis (PCA), multiple regression analysis (MRA), and neural network (NN). The values of log LD50 (lethal dose 50, acute, oral, rat) of the studied compounds were well correlated with the descriptors encoding the chemical structures. Considering the pertinent descriptors, a correlation coefficient of 0.90 (n = 41) was obtained for the NN model with a configuration of 4-3-1 (and 0.92 (n = 41) with a configuration of 4-5-1). To evaluate the contribution of each descriptor on the activity, log LD50 was calculated by removing each descriptor a part. This approach provides the tendency of a descriptor to be favourable (or not) to the activity.

No abstract

Structure-toxicity relationships for 120 insecticidal DDT-type molecules including diaryl nitropropanes (Prolan analogs), diaryl trichloroethane and other DDT isosters, collected from different literature sources, to Musca domestica. were analysed by regression analysis (RA) and a neural network model (NN). The steric factors are extremely important to the toxicity of all the DDT-type analogs. The lipophilicity is also important for the groups, because it facilitates delivery of these neurotoxicants to the site of action in the nerve. On the basis of training results, the NNs proved to give better results than a regression analysis technique and the most accurate predictions. To describe the role of each of the descriptors we suggested a new method based upon the estimation of the connection weights, the identification and the rationalisation of the residuals.