Online Program

Return to main conference page
Friday, May 18
Bioinformatics/Biomedical
Fri, May 18, 10:00 AM - 10:45 AM
Regency Ballroom B
 

A Comparison of Selected Parametric and Non-Parametric Statistical Approaches for Candidate Genes Selection in Transcriptome Data (304688)

Presentation

*Dawit Gezahegn Tadesse, Cincinnati Children's Hospital Medical Center 

Keywords: Atopic Dermatitis, Gene Selection, K-Nearest Neighbor, Linear Discriminant Analysis, Naive Bayes Discriminant Functions, Support Vector Machines, Two-sample T-test, Wilcoxon Mann-Whitney

Gene expression data are usually high-dimensional (there are more genes than sample size). Classical statistical methods don’t work well for high-dimensional data. In this poster, we rigorously compare three gene selection methods, namely the two sample t-test, Wilcoxon Mann-Whitney (WMW) on Atopic Dermatitis data. We create the third gene selection method by the combination of the above two methods. This method chooses the top common genes from both methods. These feature selection methods are compared on four discriminant functions: Support Vector Machine (SVM), Linear Discriminant Analysis (LDA), Naive Bayes Discriminant function (NB) and K-Nearest Neighbor (KNN). We show that we can acheive a 100% accuracy rate for testing data.