info presentación miembros líneas investigación publicaciones investigación tesis docencia
[Articulos Revista] [Articulos Congreso] [Reports] [Libros] [Capitulos Libro] [Todo] [Resumen]

Autores
Categoria WoS
Area
Titulo: A Random Forest proximity matrix as a new measure for gene annotation
Tipo: congreso internacional
Congreso: European Symposium on Artificial Neural Netwoks, Computational Intelligence and Machine Learning
Fecha: 23-25/4/2014
Lugar celebracion: Brugges (Belgium)
ISBN: 978-287419095-7
Libro: ESANN 2014 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium), 23-25 April 2014

Abstract:

In this paper we present a new score for gene annotation. This new score is based on the proximity matrix obtained from a trained Random Forest (RF) model. As an example application, we built this model using the association p-values of genotype with blood phenotype as input and the association of genotype data with coronary heart disease as output. This new score has been validated by comparing the Gene Ontology (GO) annotation using this score versus the score obtained from the gene annotation “String” tool. Using the new proximity based measure results in more accurate annotation, especially in the GO categories Molecular Function and Biological Process
SABIA
    .: SABIA :.  Sistemas Adaptativos y Bioinspirados en Inteligencia Artificial