Predicting subcellular locations of eukaryotic proteins using Bayesian and k-nearest neighbor classifiers

ASIAIR > College of Computer Science > Department of Biomedical informatics > Journal Article > Item 310904400/8167

Please use this identifier to cite or link to this item: http://asiair.asia.edu.tw/ir/handle/310904400/8167

Title:	Predicting subcellular locations of eukaryotic proteins using Bayesian and k-nearest neighbor classifiers
Authors:	Han C.W. Hsiao;S.H. Chen;P.C. Chang;Jeffrey J.P. Tsai
Contributors:	Department of Bioinformatics
Keywords:	subcellular location prediction;na?ve Bayesian classifier;k-nearest neighbor classifier;functional domain;feature reduction
Date:	2008-09
Issue Date:	2010-03-19 08:25:07 (UTC+0)
Publisher:	Asia University
Abstract:	Biologically, the function of a protein is highly related to its subcellular location. It is of necessity to develop a reliable method for protein subcellular location prediction, especially when a large amount of proteins are to be analyzed. Various methods have been proposed to perform the task. The results, however, are not satisfactory in terms of effectiveness and efficiency. A hybrid approach combining na?ve Bayesian classifier and k-nearest neighbor classifier is proposed to classify eukaryotic proteins represented as a combination of amino acid composition, dipeptide composition, and functional domain composition. Experimental results show that the total accuracy of a set of 17,655 proteins can reach up to 91.5%.
Relation:	Journal of Information Science and Engineering 24 (5): 1361-1375
Appears in Collections:	[Department of Biomedical informatics ] Journal Article

Files in This Item:

File	Description	Size	Format
		0Kb	Unknown	394	View/Open
310904400-8167.doc		37Kb	Microsoft Word	251	View/Open