Interest in the prediction of toxicity without the use of experimental data
is growing, and quantitative structure-activity relationship (QSAR) method
s are valuable for such predictions. A QSAR study of acute aqueous toxicity
of 375 diverse organic compounds has been developed using only calculated
structural features as independent variables. Toxicity is expressed as -log
(LD50) with the units -log(millimoles per liter) and ranges from -3 to 6. M
ultiple linear regression and computational neural networks (CNNs) are util
ized for model building. The best model is a nonlinear CNN model based on e
ight calculated molecular structure descriptors. The root-mean-square log(L
D50) errors for the training, cross-validation, and prediction sets of this
CNN model are 0.71, 0.77, and 0.74 -log(mmol/L), respectively. These resul
ts are compared to a previous study with the same data set which included m
any more descriptors and used experimental data in the descriptor pool.