Small Molecules' Multi-Metabolic Pathways Prediction Using Physico- Chemical Features and Multi-Task Learning Method.

Title:Small Molecules' Multi-Metabolic Pathways Prediction Using Physico- Chemical Features and Multi-Task Learning Method.

Volume: 8 Issue: 5

Author(s): Bing Niu, Lei Gu, Chunrong Peng, Juan Ding, Xiaochen Yuan and Wencong Lu

Affiliation:

Keywords: KEGG, KNN, metabolic pathway, mRMR, multi-task learning, small molecules.

Abstract: Knowledge of mechanism of small molecules in metabolic pathway is critical to design specific and effective inhibitors for metabolic pathway. As some small molecules are involved in more than one pathway, it is crucial to use an accurate and robust approach to correctly map the small molecule in specific metabolic pathway that it is involved in. In this article, small molecules are studied using the Minimal-Redundancy-Maximal-Relevance-Forward Feature Search (mRMR-FFS) method combined with Multi-task learning method based on K-nearest neighbor (KNN) Algorithms method. Forty-five important chemical features were found based on 10-folds cross validation test from original data set containing 61 features. By applying KNN method with these forty-five selected features, the accuracy rate of prediction model could achieve 68.2% for the 10-folds cross validation test. It is promosing that our two stage scheme can be a useful approach for searching new effective competitive drugs in metabolic pathway.

Cite this article as:

Niu Bing, Gu Lei, Peng Chunrong, Ding Juan, Yuan Xiaochen and Lu Wencong, Small Molecules' Multi-Metabolic Pathways Prediction Using Physico- Chemical Features and Multi-Task Learning Method., Current Bioinformatics 2013; 8 (5) . https://dx.doi.org/10.2174/1574893611308050007