课件 文献 资料Knowledge-based analysis of microarray gene expression data by using support vector machines.pdfVIP

Knowledge-based analysis of microarray gene expression data by using support vector machines Michael P. S. Brown*, William Noble Grundy庄 David Lin*, Nello Cristianini§, Charles Walsh Sugnetll, Terrence S. Furey*, Manuel Ares, Jr.ll, and David Haussler* Department of Computer Science and 1Center for Molecular Biology of RNA, Department of Biology, University of California, Santa Cruz, Santa Cruz, CA 95064; toepartment of Computer Science, Columbia University, New York, NY 10025; §Department of Engineering Mathematics, University of Bristol, Bristol BSS lTR, United Kingdom Edited by David Botstein, Stanford University School of Medicine, Stanford, CA, and approved November 15, 1999 (received for review August 31, 1999) We introduce a method of functionally classifying genes by using could also be reapplied to the training examples to identify outliers gene expression data from DNA microarray hybridization experi­ that may have previously been assigned to the incorrect class in the ments. The method is based on the theory of support vector training set. Thus, an SVM would use the biological information in machines (SVMs}. SVMs are considered a supervised computer the investigators training set to determine what expression features learning method because they exploit prior knowledge of gene are characteristic of a given functional group and use this infor­ function to identify unknown genes of similar function from rnation to decide whether any given gene is likely to be a member expression data. SVMs avoid several problems associated with of the group. unsupervised clustering methods, such as hierarchical clustering SVMs offer two primary advantages with respect to previously and self-organizing maps. SVMs hav