2026-04-18T03:58:49Zhttps://recercat.cat/oai/request

oai:recercat.cat:2117/194822026-01-21T08:06:58Zcom_2072_1033col_2072_452950

Parsimonious selection of useful genes in microarray gene expression data González Navarro, Félix Fernando Belanche Muñoz, Luis Antonio Universitat Politècnica de Catalunya. Departament de Llenguatges i Sistemes Informàtics Universitat Politècnica de Catalunya. SOCO - Soft Computing Àrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica::Bioinformàtica Computational biology Data mining Cancer -- Research Biological data mining and knowledge discovery Gene expression analysis Tools and methods for computational biology and bioinformatics Cancer informatics Biologia computacional Mineria de dades Càncer -- Investigació Machine Learning methods have of late made significant efforts to solving multidisciplinary problems in the field of cancer classification in microarray gene expression data. These tasks are characterized by a large number of features and a few observations, making the modeling a non-trivial undertaking. In this work we apply entropic filter methods for gene selection, in combination with several off-the-shelf classifiers. The introduction of bootstrap resampling techniques permits the achievement of more stable performance estimates. Our findings show that the proposed methodology permits a drastic reduction in dimension, offering attractive solutions both in terms of prediction accuracy and number of explanatory genes; a dimensionality reduction technique preserving discrimination capabilities is used for visualization of the selected genes. Postprint (author’s final draft) 2011 Part of book or chapter of book González, F.F.; Belanche, Ll. Parsimonious selection of useful genes in microarray gene expression data. A: "Software tools and algorithms for biological systems". Springer, 2011, p. 45-55. 978-1-4419-7046-6 https://hdl.handle.net/2117/19482 10.1007/978-1-4419-7046-6_5 eng https://link.springer.com/book/10.1007/978-1-4419-7046-6 Open Access 11 p. application/pdf Springer