Comparative Assessment of Multiresponse Regression Methods for Predicting the Mechanisms of Toxic Action of Phenols

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.

[1]  S Ren,et al.  Determining the mechanisms of toxic action of phenols to Tetrahymena pyriformis , 2002, Environmental toxicology.

[2]  Yong Wang,et al.  Using Model Trees for Classification , 1998, Machine Learning.

[3]  Ş. Niculescu,et al.  Using probabilistic neural networks to model the toxicity of chemicals to the fathead minnow (Pimephales promelas): a study based on 865 compounds. , 1999, Chemosphere.

[4]  G. Veith,et al.  Rules for distinguishing toxicants that cause type I and type II narcosis syndromes. , 1990, Environmental health perspectives.

[5]  S. Bradbury,et al.  Fish acute toxicity syndromes and their use in the QSAR approach to hazard assessment. , 1987, Environmental health perspectives.

[6]  Ş. Niculescu.  Artificial neural networks and genetic algorithms in QSAR , 2003 .

[7]  Shijin Ren.  Predicting three narcosis mechanisms of aquatic toxicity. , 2002, Toxicology letters.

[8]  John D. Walker,et al.  Quantitative structure–activity relationships (QSARs) in toxicology: a historical perspective , 2003 .

[9]  S. Bradbury,et al.  Predicting modes of toxic action from chemical structure: an overview. , 1994, SAR and QSAR in environmental research.

[10]  Mark T D Cronin,et al.  Comparative assessment of methods to develop QSARs for the prediction of the toxicity of phenols to Tetrahymena pyriformis. , 2002, Chemosphere.

[11]  W. Cleveland,et al.  Locally Weighted Regression: An Approach to Regression Analysis by Local Fitting , 1988 .

[12]  M. Cronin,et al.  Pitfalls in QSAR , 2003 .

[13]  Mark T. D. Cronin,et al.  Multivariate Discrimination between Modes of Toxic Action of Phenols , 2002 .

[14]  J. Friedman.  Multivariate adaptive regression splines , 1990 .

[15]  C. Russom,et al.  Predicting modes of toxic action from chemical structure: Acute toxicity in the fathead minnow (Pimephales promelas) , 1997 .

[16]  J. Friedman,et al.  Projection Pursuit Regression , 1981 .

[17]  Shijin Ren,et al.  Identifying the mechanism of aquatic toxicity of selected compounds by hydrophobicity and electrophilicity descriptors. , 2002, Toxicology letters.

[18]  T. Wayne Schultz,et al.  Structure‐activity relationships for Pimephales and Tetrahymena: A mechanism of action approach , 1997 .