A Hybrid Tumor Gene Selection Method with Laplacian Score and Correlation Analysis
In the proposed method, Laplacian criteria is firstly introduced to sort the genes as their descending scores. And then, correlation analysis is applied to select those pathogenic genes from the sorted sequence to reduce the redundancy. At last, SVM classifier is used to predict the class labels of the optimal gene subset. Compared to some other related gene selection methods such as Fisher score and Laplacian score, Experimental results on four standard datasets have shown the stability and efficiency of the proposed method.
KeywordsCorrelation analysis Laplacian score Tumor gene expressive data Gene selection
This work was partly supported by the grants of Natural Science Foundation of China (61273303, 61273225, 61373109 and 61572381), China Postdoctoral Science Foundation (20100470613 and 201104173), Natural Science Foundation of Hubei Province (2010CDB03302), the Research Foundation of Education Bureau of Hubei Province (Q20121115).
- 8.Pillati, M., Viroli, C.: Supervised locally linear embedding for classification: an application to gene expression data analysis. In: 29th Annual Conference of the German Classification Society (GfKl 2005), pp. 15–18 (2005)Google Scholar
- 13.He, X., Cai, D., Niyogi, P.: Laplacian score for feature selection. In: Advances in Neural Information Processing Systems, pp. 507–514 (2005)Google Scholar
- 15.Nie, F., Huang, H., Cai, X., Ding, C.H.: Efficient and robust feature selection via joint l2, 1-norms minimization. In: Advances in Neural Information Processing Systems, pp. 1813–1821 (2010)Google Scholar