DocumentCode :
573704
Title :
Network Kernel SVM for microarray classification and gene sets selection
Author :
Yang, Bing ; Tan, Junyan ; Deng, Naiyang ; Jing, Ling
Author_Institution :
Dept. of Appl. Math., China Agric. Univ., Beijing, China
fYear :
2012
fDate :
18-20 Aug. 2012
Firstpage :
101
Lastpage :
105
Abstract :
The importance of network-based approach to identifying biological markers has been increasingly recognized. Lots of papers indicated that genes in a network tend to function together in biological processes, so taking full advantage of the biological observation can improve the performance of microarray classification. However, lots of SVM methods don´t consider this situation during their classifier building. The main idea of this paper intends to embed the information of gene networks into a new SVM learning framework. Based on a new regularization, we propose a novel method, Network Kernel SVM (NK-SVM), for binary classification problem and gene sets selection. By constructing some special kernel matrixes from the prior information of gene network, the new NK-SVM method makes the genes in the same set to be selected (or eliminated) together. The numerical experiments on a real microarray application show that the proposed method tends to provide a better performance than other methods on gene sets selection.
Keywords :
genetics; lab-on-a-chip; support vector machines; NK-SVM method; binary classification problem; biological marker identification; classifier building; gene network; gene sets selection; microarray classification; network based approach; network kernel SVM; Cancer; Colon; Input variables; Kernel; Machine learning; Support vector machines; Vectors; Feature selectio; Gene expressio; Gene networ; Network regularization; Support vector machine;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Systems Biology (ISB), 2012 IEEE 6th International Conference on
Conference_Location :
Xi´an
Print_ISBN :
978-1-4673-4396-1
Electronic_ISBN :
978-1-4673-4397-8
Type :
conf
DOI :
10.1109/ISB.2012.6314120
Filename :
6314120
Link To Document :
بازگشت