| Autor: |
Blazadonakis, Michalis E., Zervakis, Michalis |
| Zdroj: |
Intelligent Techniques & Tools for Novel System Architectures; 2008, p237-258, 22p |
| Abstrakt: |
DNA micro-array analysis allows us to study the expression level of thousands of genes simultaneously on a single experiment. The problem of marker selection has been extensively studied but several aspects need yet to be addressed. In this study we add an important attribute of gene selection by considering the `quality΄ of the selected markers. By the term `quality΄ we refer to the property that a set of selected markers should differentiate its expression between the two possible classes of interest (positive, negative). Thus, we address the problem of selecting a small subset of representative genes that would be adequate enough to discriminate between the two classes of interest in classification, while preserving low intra-cluster and high inter-cluster distance, which eventually leads to better survival prediction. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
