Issue No. 03 - May-June (2013 vol. 10)
ISSN: 1545-5963
pp: 593-604
Hsi-Che Liu , Mackay Medical College and Division of Pediatric Hematology-Oncology, Mackay Memorial Hospital, New Taipei
Pei-Chen Peng , National Taiwan University, Taipei
Tzung-Chien Hsieh , National Taiwan University, Taipei
Ting-Chi Yeh , Mackay Medical College and Division of Pediatric Hematology-Oncology, Mackay Memorial Hospital, New Taipei
Chih-Jen Lin , National Taiwan University, Taipei
Chien-Yu Chen , National Taiwan University, Taipei
Jen-Yin Hou , Mackay Medical College and Division of Pediatric Hematology-Oncology, Mackay Memorial Hospital, New Taipei
Lee-Yung Shih , Chang Gung Memorial Hospital, Taipei, and Chang Gung University, Taoyuan
Der-Cherng Liang , Mackay Medical College and Division of Pediatric Hematology-Oncology, Mackay Memorial Hospital, New Taipei
ABSTRACT
The amount of gene expression data of microarray has grown exponentially. To apply them for extensive studies, integrated analysis of cross-laboratory (cross-lab) data becomes a trend, and thus, choosing an appropriate feature selection method is an essential issue. This paper focuses on feature selection for Affymetrix (Affy) microarray studies across different labs. We investigate four feature selection methods: $(t)$-test, significance analysis of microarrays (SAM), rank products (RP), and random forest (RF). The four methods are applied to acute lymphoblastic leukemia, acute myeloid leukemia, breast cancer, and lung cancer Affy data which consist of three cross-lab data sets each. We utilize a rank-based normalization method to reduce the bias from cross-lab data sets. Training on one data set or two combined data sets to test the remaining data set(s) are both considered. Balanced accuracy is used for prediction evaluation. This study provides comprehensive comparisons of the four feature selection methods in cross-lab microarray analysis. Results show that SAM has the best classification performance. RF also gets high classification accuracy, but it is not as stable as SAM. The most naive method is $(t)$-test, but its performance is the worst among the four methods. In this study, we further discuss the influence from the number of training samples, the number of selected genes, and the issue of unbalanced data sets.
INDEX TERMS
cross-laboratory experiment, Microarray data analysis, feature selection, cancer,
CITATION
Hsi-Che Liu, Pei-Chen Peng, Tzung-Chien Hsieh, Ting-Chi Yeh, Chih-Jen Lin, Chien-Yu Chen, Jen-Yin Hou, Lee-Yung Shih, Der-Cherng Liang, "Comparison of Feature Selection Methods for Cross-Laboratory Microarray Analysis", IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 10, no. , pp. 593-604, May-June 2013, doi:10.1109/TCBB.2013.70
CITATIONS
SHARE
99 ms
(Ver 3.1 (10032016))