John Wiley & Sons, Ltd.

Comparative study of biodegradability prediction of chemicals using decision trees, functional trees, and logistic regression

0
Biodegradation is the principal environmental dissipation process of chemicals. As such it is a dominant factor determining the persistence and fate of organic chemicals in the environment, and is therefore of critical importance to chemical management and regulation. In this study, we developed in silico methods assessing biodegradability based on a large heterogeneous set of 825 organic compounds, using the techniques of C4.5 decision tree, functional inner regression tree and logistic regression. External validation was subsequently carried out by two independent test sets of 777 and 27 chemicals. As a result, the functional inner regression tree exhibited the best predictability with predictive accuracies of 81.5% and 81.0% on respective training set (825 chemicals), test set I (777 chemicals). Performance of the developed models on the two test sets was subsequently compared with that of the EPI suite Biowin 5 and Biowin 6 models, which also evidenced a better predictability of the functional inner regression tree model. The model built in our study exhibits a reasonable predictability compared to existing models whilst possesses a transparent algorithm. Interpretation of the mechanisms of biodegradation was also carried out based on the developed models. Environ Toxicol Chem © 2014 SETAC

Customer comments

No comments were found for Comparative study of biodegradability prediction of chemicals using decision trees, functional trees, and logistic regression. Be the first to comment!