Feature Selection For Genomic Data By Combining Filter And Wrapper Approaches

Gene expression data usually contains a large number of genes, but a small number of samples. Feature selection for gene expression data aims at finding a set of genes that best discriminate biological samples of different types. In this paper, we propose a two-stage selection algorithm for genomic...

ver descrição completa

Detalhes bibliográficos
Autores: Akadi, Ali El, Amine, Aouatif, El Ouardighi, Abdeljalil, Aboutajdine, Driss
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2009
País:Brasil
Recursos:Universidade Federal de Lavras (UFLA)
Repositorio:INFOCOMP: Jornal de Ciência da Computação
Idioma:inglés
OAI Identifier:oai:infocomp.dcc.ufla.br:article/279
Acesso em linha:https://infocomp.dcc.ufla.br/index.php/infocomp/article/view/279
Access Level:acceso abierto
Palavra-chave:Feature selection
Genetic algorithm
MRMR
Support Vector Machine
Naïve Bayes classi- fier
LOOCV
Descrição
Resumo:Gene expression data usually contains a large number of genes, but a small number of samples. Feature selection for gene expression data aims at finding a set of genes that best discriminate biological samples of different types. In this paper, we propose a two-stage selection algorithm for genomic data by combining MRMR (Minimum Redundancy Maximum Relevance) and GA (Genetic Algorithm): In the first stage, MRMR is used to filter noisy and redundant genes in high dimensional microarray data. In the second stage, the GA uses the classifier accuracy as a fitness function to select the highly discriminating genes. The proposed method is tested on five open datasets: NCI, Lymphoma, Lung, Leukemia and Colon using Support Vector Machine and Naïve Bayes classifiers. The comparison of the MRMR-GA with MRMR filter and GA wrapper shows that our method is able to find the smallest gene subset that gives the most classification accuracy in leave-one-out cross-validation (LOOCV).