You are here:
PREDICTION OF THE ACUTE TOXICITY OF ORGANIC COMPOUNDS TO THE FATHEAD MINNOW (PIMEPHALES PROMALAS) USING A GROUP CONTRIBUTION METHOD
Citation:
Martin**, T M. AND D M. Young*. PREDICTION OF THE ACUTE TOXICITY OF ORGANIC COMPOUNDS TO THE FATHEAD MINNOW (PIMEPHALES PROMALAS) USING A GROUP CONTRIBUTION METHOD. Marnett, L.J. (ed.), CHEMICAL RESEARCH IN TOXICOLOGY. American Chemical Society, Washington, DC, 14(10):1378-1385, (2001).
Description:
A group contribution method has been developed to correlate the acute toxicity (96 h LC50) to the fathead minnow (Pimephales promelas) for 379 organic chemicals. Multilinear regression and computational neural networks (CNNs) were used for model building. The multilinear linear model had a correlation coefficient (r2) of 0.945 and root mean square error (RMSE) of 0.292. THe CNN model had an r2 of 0.930 and a RMSE of 0.331. When the dataset was broken into a training set and a validation set, the multilinear model again performed slightly better. The CNN model was able to yield virtually the same predictions with or without 4 interaction terms that were included in the multilinear model.