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

A methodology based on probabilistic neural networks (PNNs) is applied to model the acute toxicity (48-h LC50) of a set of 700 highly diverse chemicals to Daphnia magna. First, cross-validation experiments confirming the potential use of the PNN as modeling tool for the problem at hand were performed. 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 molecular descriptors and structural fragments and excludes bulk property parameters, such as the water solubility or the octanol/water partition coefficient.