基于支持向量机肿瘤分类特征基因选取.pdf

计算机研究与发展 ISSN CN 111777/ TP Journal of Computer Research and Development 42 ( 10) : 1796～1801 , 2005 基于支持向量机的肿瘤分类特征基因选取 李颖新 　　　阮晓钢 (北京工业大学电子信息与控制工程学院 　北京 　100022) (lyxboy @sina com) Feature Selection for Cancer Classif ication Based on Support Vector Machine Li Yingxin and Ruan Xiaogang ( ) School of Elect ronic Inf orm ation and Cont rol Engineering , Beijin g U niversity of Technology , Beijin g 100022 Abstract 　Feature selection is an essential step to perform cancer classification with DNA microarrays , for there are a large number of genes from which to predict classes and a relatively small number of samples This work addresses the problem of selection of a small subset of genes for classification from broad patterns of gene expression profiles by proposing a twostep feature selection method The first step uses a new met ric proposed in this paper as the criteria for class separabilit y to remove the genes irrelevant to the classifica tion task , and then a support vector machine with radial basis function kernel is applied to validate the clas sification performance of the genes selected for distinguishing different tissue types The second step filters out the redundant genes by the sensitivity analysis based on the support vector machine classifier after pair wise redundancy analysis The two steps are applied to the gene expression profiles of human acute leukemi a , and a better and more compact gene subset is obtained in contrast with the baseline method , which shows the feasibility and effectiveness of the method proposed Key words 　feature selection ; support vector machine ; gene expression profiles ; cancer 摘　要