Evaluation of descriptors and classification schemes to predict cytochrome substrates in terms of chemical information.

Using a small database of defined substrates in humans for cytochrome P450 mixed function oxidases, a series of descriptors and classification methods were evaluated with respect to how well they correctly classified substrates. The descriptors ranged from structural keys to topological to electronic. A variety of classification schemes were examined in terms of their ability to point out which descriptors are important for predicting the cytochrome P450 specificity for a substrate. Results illustrate the relative effectiveness of the various kinds of descriptors and classification methods, as well as the value of using as well-defined data set as possible.