Title :
Gene Ranking Using R-Metric
Author_Institution :
Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai
Abstract :
Selecting a small number of genes from thousands of genes is useful in disease diagnosis. We propose in this study a new metric termed R-test to analyze how the instances of two classes distribute against each other. We validated the proposed scheme through two well-known benchmarks. R-test outperforms two-well known methods on the two benchmarks
Keywords :
biology computing; genetics; medical diagnostic computing; R-metric; R-test; disease diagnosis; gene ranking; Accuracy; Colon; Computational efficiency; Computer science; Diseases; Gene expression; Support vector machine classification; Support vector machines; Testing;
Conference_Titel :
Computational Intelligence and Security, 2006 International Conference on
Conference_Location :
Guangzhou
Print_ISBN :
1-4244-0605-6
Electronic_ISBN :
1-4244-0605-6
DOI :
10.1109/ICCIAS.2006.294178
