The use of regression methods for classifying and predicting the mechanisms of toxic action of phenols was investigated in this study. Multiresponse regression was conducted using a total of six linear and nonlinear regression methods: simple linear regression (LinReg), logistic regression (LogReg), generalized additive model (GAM), locally weighted regression scatter plot smoothing (LOWESS), multivariate adaptive regression splines (MARS), and projection pursuit regression (PPR). A database containing phenols acting by four mechanisms (polar narcosis, weak acid respiratory uncoupling, proelectrophilicity, and soft electrophilicity) was used to assess the performances of the six regression methods in the multiresponse regression approach. For comparison purposes, traditional linear discriminant analysis (LDA) was also conducted as a baseline method to study the potential improvement of prediction accuracy by the multiresponse regression approach. Results showed that compared to LDA, the overall mechanism prediction error rate could be reduced to below 10% by multiresponse regression based on PPR. In addition to prediction accuracy, interpretability of the resultant models was discussed.
|Number of pages||5|
|Journal||Journal of Chemical Information and Computer Sciences|
|Publication status||Published - 2003 Nov|
All Science Journal Classification (ASJC) codes
- Information Systems
- Computer Science Applications
- Computational Theory and Mathematics