Abstract

The ability to provide thousands of gene expression values simultaneously makes microarray data very useful for phenotype classification. A major constraint in phenotype classification is that the number of genes greatly exceeds the number of samples. We overcame this constraint in two ways; we increased the number of samples by integrating independently generated microarrays that had been designed with the same biological objectives, and reduced the number of genes involved in the classification by selecting a small set of informative genes. We were able to maximally use the abundant microarray data that is being stockpiled by thousands of different research groups while improving classification accuracy. Our goal is to implement a feature (gene) selection method that can be applicable to integrated microarrays as well as to build a highly accurate classifier that permits straightforward biological interpretation. In this paper, we propose a two-stage approach. Firstly, we performed a direct integration of individual microarrays by transforming an expression value into a rank value within a sample and identified informative genes by calculating the number of swaps to reach a perfectly split sequence. Secondly, we built a classifier which is a parameter-free ensemble method using only the pre-selected informative genes. By using our classifier that was derived from large, integrated microarray sample datasets, we achieved high accuracy, sensitivity, and specificity in the classification of an independent test dataset.

Keywords: Data mining; Microarray data analysis; Microarray data integration; Microarray data classification; Informative gene selection

Article Outline

1. Introduction

2. Related work

2.1. Microarray data integration

2.2. Informative gene selection

2.3. Classification

3. System overview

4. System implementation

4.1. Microarray data integration and informative gene selection

4.2. k-GeneTriple classification method

5. Experimental results

5.1. Determining the optimal number of rules (k) by LOOCV

5.2. Accuracy of the informative gene selection method

5.3. Accuracy of the classification method

5.3.1. Accuracy of the classification method using Affymetrix data

5.3.2. Accuracy of the classification method using cDNA microarray

5.4. Run-time comparison of k-GeneTriple and TSP

5.5. Effectiveness of the rank-based microarray data integration in classification

6. Conclusion

Acknowledgements

References