Document Detail


Prediction of interaction between enzymes and small molecules in metabolic pathways through integrating multiple classifiers.
MedLine Citation:
PMID:  20937036     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
Information about interactions between enzymes and small molecules is important for understanding various metabolic bioprocesses. In this article we applied a majority voting system to predict the interactions between enzymes and small molecules in the metabolic pathways, by combining several classifiers including AdaBoost, Bagging and KNN together. The advantage of such a strategy is based on the principle that a predictor based majority voting systems usually provide more reliable results than any single classifier. The prediction accuracies thus obtained on a training dataset and an independent testing dataset were 82.8% and 84.8%, respectively. The prediction accuracy for the networking couples in the independent testing dataset was 75.5%, which is about 4% higher than that reported in a previous study. The web-server for the prediction method presented in this paper is available at http://chemdata.shu.edu.cn/small-enz.
Authors:
Jin Lu; Yubei Zhu; Yajun Li; Wencong Lu; Lele Hu; Bing Niu; Pengfei Qing; Lei Gu
Related Documents :
22141926 - A fully-automatic caudate nucleus segmentation of brain mri: application in volumetric ...
12967966 - Pathminer: predicting metabolic pathways by heuristic search.
512846 - A pharmacokinetic model to differentiate preabsorptive, gut epithelial, and hepatic fir...
12673766 - Optimization-based framework for inferring and testing hypothesized metabolic objective...
22675526 - What ecological factors shape species-area curves in neutral models?
7846316 - On the exact hazard and survival functions of the mvk stochastic carcinogenesis model.
Publication Detail:
Type:  Journal Article; Research Support, Non-U.S. Gov't    
Journal Detail:
Title:  Protein and peptide letters     Volume:  17     ISSN:  1875-5305     ISO Abbreviation:  Protein Pept. Lett.     Publication Date:  2010 Dec 
Date Detail:
Created Date:  2010-11-25     Completed Date:  2011-02-25     Revised Date:  2011-03-31    
Medline Journal Info:
Nlm Unique ID:  9441434     Medline TA:  Protein Pept Lett     Country:  Netherlands    
Other Details:
Languages:  eng     Pagination:  1536-41     Citation Subset:  IM    
Affiliation:
School of Materials Science and Engineering, Shanghai University, 149 Yan-Chang Road, Shanghai 200444, China.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Algorithms
Computer Simulation*
Enzymes / chemistry*
Metabolic Networks and Pathways*
Models, Biological
Models, Chemical
Protein Binding
Chemical
Reg. No./Substance:
0/Enzymes

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Nucleolar localization signals of LIM kinase 2 function as a cell-penetrating peptide.
Next Document:  Analysis of the conformations corresponding to hexapeptide and large sequences characterized by cont...