Multiple computer-automated structure evaluation study of aquatic toxicity II. Fathead minnow
Gilles Klopman, Roustem Saiakhov, Herbert S. Rosenkranz · Environmental Toxicology and Chemistry · 2000
Abstract An acute toxicity model was constructed on the basis of experimental data for 685 chemicals tested for toxicity for fathead minnow. The multiple computer-automated structure evaluation (M-CASE) program was used for the construction of the model. Based on a comparison between our results and published results, we found that the methodology is able to describe acute toxicity for the fathead minnow with high accuracy. The model incorporates the concept of a baseline activity as one of the parameters for the correlation as well as others parameters such as the presence of biophores, hardness-softness parameters, and other characteristics determined from quantum mechanical calculations. By using its artificial intelligence algorithm, M-CASE chooses automatically the most suitable set of parameters for evaluating the minnow toxicity of any organic molecule. We found that M-CASE can correctly predict acute toxicity for minnow for 80% of organic compounds with an average error of only 0.4 log units of lethal dose. The main toxicophores, corresponding to polar narcosis and to other types of reactive chemicals, were identified.