• Login
    View Item 
    •   Home
    • Research
    • Presentations
    • View Item
    •   Home
    • Research
    • Presentations
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of KAUSTCommunitiesTitleAuthorsKAUST AuthorsIssue DateSubmit DateSubjectsThis CollectionTitleAuthorsKAUST AuthorsIssue DateSubmit DateSubjects

    My Account

    Login

    Quick Links

    Open Access PolicyORCID LibguidePlumX LibguideSubmit an Item

    Statistics

    Display statistics

    Clustering based gene expression feature selection method: A computational approach to enrich the classifier efficiency of differentially expressed genes

    • CSV
    • RefMan
    • EndNote
    • BibTex
    • RefWorks
    Type
    Presentation
    Authors
    Abusamra, Heba
    Bajic, Vladimir B. cc
    KAUST Department
    Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
    Computer Science Program
    Applied Mathematics and Computational Science Program
    Computational Bioscience Research Center (CBRC)
    Date
    2016-07-20
    Permanent link to this record
    http://hdl.handle.net/10754/617533
    
    Metadata
    Show full item record
    Abstract
    The native nature of high dimension low sample size of gene expression data make the classification task more challenging. Therefore, feature (gene) selection become an apparent need. Selecting a meaningful and relevant genes for classifier not only decrease the computational time and cost, but also improve the classification performance. Among different approaches of feature selection methods, however most of them suffer from several problems such as lack of robustness, validation issues etc. Here, we present a new feature selection technique that takes advantage of clustering both samples and genes. Materials and methods We used leukemia gene expression dataset [1]. The effectiveness of the selected features were evaluated by four different classification methods; support vector machines, k-nearest neighbor, random forest, and linear discriminate analysis. The method evaluate the importance and relevance of each gene cluster by summing the expression level for each gene belongs to this cluster. The gene cluster consider important, if it satisfies conditions depend on thresholds and percentage otherwise eliminated. Results Initial analysis identified 7120 differentially expressed genes of leukemia (Fig. 15a), after applying our feature selection methodology we end up with specific 1117 genes discriminating two classes of leukemia (Fig. 15b). Further applying the same method with more stringent higher positive and lower negative threshold condition, number reduced to 58 genes have be tested to evaluate the effectiveness of the method (Fig. 15c). The results of the four classification methods are summarized in Table 11. Conclusions The feature selection method gave good results with minimum classification error. Our heat-map result shows distinct pattern of refines genes discriminating between two classes of leukemia.
    Publisher
    Springer Nature
    Journal
    BMC Genomics
    Conference/Event name
    The 3rd International Genomic Medicine Conference (3rd IGMC 2015)
    DOI
    10.1186/s12864-016-2858-0
    Additional Links
    http://bmcgenomics.biomedcentral.com/articles/10.1186/s12864-016-2858-0
    ae974a485f413a2113503eed53cd6c53
    10.1186/s12864-016-2858-0
    Scopus Count
    Collections
    Applied Mathematics and Computational Science Program; Computer Science Program; Computational Bioscience Research Center (CBRC); Presentations; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

    entitlement

     
    DSpace software copyright © 2002-2019  DuraSpace
    Quick Guide | Contact Us | Send Feedback
    Open Repository is a service hosted by 
    Atmire NV
     

    Export search results

    The export option will allow you to export the current search results of the entered query to a file. Different formats are available for download. To export the items, click on the button corresponding with the preferred download format.

    By default, clicking on the export buttons will result in a download of the allowed maximum amount of items. For anonymous users the allowed maximum amount is 50 search results.

    To select a subset of the search results, click "Selective Export" button and make a selection of the items you want to export. The amount of items that can be exported at once is similarly restricted as the full export.

    After making a selection, click one of the export format buttons. The amount of items that will be exported is indicated in the bubble next to export format.