ASIA unversity:Item 310904400/8653
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 94286/110023 (86%)
Visitors : 21699472      Online Users : 519
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
    •  Adv. Search
    Home ‧ Login ‧ Upload ‧ Help ‧ About ‧ Administer Goto mobile version


    Please use this identifier to cite or link to this item: http://asiair.asia.edu.tw/ir/handle/310904400/8653


    Title: Predicting subcellular locations of eukaryotic proteins using bayesian and k-nearest neighbor classifiers
    Authors: Hsiao, Han C. W.;Chen, Shih-Hao;Chang, Judson Pei-Chun;Tsai, Jeffrey J. P.
    Contributors: Department of Bioinformatics
    Keywords: Amines;Amino acids;Bayesian networks;Classifiers;Forecasting;Location;Organic acids;Proteins;Amino acid compositions;Bayesian;Bayesian classifiers;Dipeptide compositions;Eukaryotic proteins;Feature reduction;Functional domain;Functional domains;Hybrid approaches;k-nearest neighbor classifier;K-nearest neighbor classifiers;Protein subcellular locations;Reliable methods;Subcellular location prediction;Subcellular locations
    Date: 2008
    Issue Date: 2010-04-07 13:21:20 (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 nai¨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 24:1361-1375
    Appears in Collections:[Department of Biomedical informatics  ] Journal Article

    Files in This Item:

    File Description SizeFormat
    157.doc30KbMicrosoft Word298View/Open


    All items in ASIAIR are protected by copyright, with all rights reserved.

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback