An Eigengene-Based Classifier Committee Learning Algorithm for Tumor Classification
This paper presents a tumor classification approach by using eigengene and support vector machine (SVM) based classifier committee learning (CCL) algorithm. In this method, first, multiple sample feature subspaces of gene expression data are extracted by random subspace method. Then, the gene expression data constructed by these subspaces are modeled by independent component analysis (ICA), respectively. And the corresponding eigengene sets are extracted by the ICA algorithm. Finally, Bayesian sum rule (BSR) based SVM CCL algorithm is applied on these feature sets and the unknown labels are predicted. Experimental results on two DNA microarray datasets demonstrate that the proposed method is efficient and feasible for the tumor classification.
KeywordsGene expression data tumor classification independent component analysis Bayesian sum rule classifier committee learning
Unable to display preview. Download preview PDF.
- 5.Chang, C.C., Lin, C.J.: LIBSVM: A Library for Support Vector Machines (2001), http://www.csie.ntu.edu.tw/~cjlin/libsvm
- 9.Alon, U., Barkai, N., Notterman, D.A., et al.: Broad Patterns of Gene Expression Revealed by Clustering Analysis of Tumor and Normal Colon Tissues Probed by Oligonucleotide Arrays. Proceedings of the National Academy of Sciences of the United States of America 96, 6745–6750 (1999)CrossRefGoogle Scholar