Gene Selection for Tumor Cell Classification

Katti FaceliAndré C. P. L. F. de CarvalhoWilson A. Silva Jr.

Gene expression profiles contain the expression level of thousands of genes. Depending on the issue under investigation, this large amount of data makes the analysis impractical. Thus, it is important to select subsets of relevant genes to work with. This paper investigates different metrics for gene selection. The metrics are evaluated based in their ability in selecting predictive genes. This evaluation is made by constructing classifiers using the genes selected by each metric and then comparing the performance of these classifiers. The classifiers are generated using Support Vector Machines (SVMs) and MultiLayer Perceptrons (MLPs) networks. Clique no link abaixo para buscar o texto completo deste trabalho na Web: Buscar na Web

Biblioteca Digital Brasileira de Computação - Contato:
     Mantida por: