Prediction of Small Molecules Metabolic Pathways Based on Functional Group Composition

Title: Prediction of Small Molecules Metabolic Pathways Based on Functional Group Composition

Volume: 16 Issue: 8

Author(s): Jin Lu, Bing Niu, Liang Liu, Wen-Cong Lu and Yu-Dong Cai

Affiliation:

Keywords: Adaboost, Jackknife cross-validation test, Independent set test, Metabolism

Abstract: How to correctly and efficiently determine small molecules biological function is a challenge and has a positive effect on further metabonomics analysis. Here, we introduce a computational approach to address this problem. The new approach is based on AdaBoost method and featured by function group composition to the metabolic pathway analysis, which can fast and automatically map the small chemical molecules back to the possible metabolic pathway that they belong to. As a result, jackknife cross validation test and independent set test on the model reached 73.7% and 73.8%, respectively. It can be concluded that the current approach is very promising for mapping some unknown molecules possible metabolic pathway. An online predictor developed by this research is available at http://chemdata.shu.edu.cn/pathway.

Cite this article as:

Lu Jin, Niu Bing, Liu Liang, Lu Wen-Cong and Cai Yu-Dong, Prediction of Small Molecules Metabolic Pathways Based on Functional Group Composition, Protein & Peptide Letters 2009; 16 (8) . https://dx.doi.org/10.2174/092986609788923374