Modeling acute toxicity of chemicals to Daphnia magna: A probabilistic neural network approach

A methodology based on probabilistic neural networks (PNNs) is applied to m odel the acute toxicity (48-h LC50) of a set of 700 highly diverse chemical s to Daphnia magna. First, cross-validation experiments confirming the pote ntial use of the PNN as modeling tool for the problem at hand were performe d. Next, various approaches to construct-improved models are presented. The resulting four models are then validated using an external test set of 76 additional compounds. Input to the PNNs is derived solely from simple molec ular descriptors and structural fragments and excludes bulk property parame ters, such as the water solubility or the octanol/water partition coefficie nt.