The purpose of this study was to develop quantitative structure-activity relationships (QSARs) for the toxicity of 268 aromatic compounds in the Tetrahymena pyriformis growth inhibition assay. The QSARs were developed using the response-surface (or two-parameter) approach, which was also modified using linear free-energy parameters to account for outliers. Subsequently, the data set was analyzed using partial least-squares (PLS). The results of the modeling using different methodologies were compared to the use of a Bayesian regularized neural network (BRANN) trained on the same data. Both response surface approaches, and PLS explained between 75 and 80% of the variance in the data; BRANN gave a higher statistical fit. In terms of the transparency of the approaches, the response surface clearly provides the simplest and easiest to use QSAR, it is readily interpreted in terms of mechanism of toxic action. PLS and BRANN are respectively less transparent. The use of atomistic and fragment-based indexes as descriptors in QSARs is assessed also, these are found not to be as useful as whole molecule parameters for the prediction of toxicity for molecules outside of the training set. The relative merits of the different approaches to the development of QSARs are described.
Available at: http://works.bepress.com/terry_schultz/65/