Title: Inference system using softcomputing and mixed data applied in metabolic pathway datamining

Authors: Tomás Arredondo; Diego Candel; Mauricio Leiva; Lioubov Dombrovskaia; Loreine Agulló; Michael Seeger

Addresses: Departamento de Electrónica, Universidad Técnica Federico Santa María, Avda España 1680, Valparaiso, 2340000, Chile. ' Departamento de Informática, Universidad Técnica Federico Santa María, Avda España 1680, Valparaiso, 2340000, Chile. ' Departamento de Informática, Universidad Técnica Federico Santa María, Avda España 1680, Valparaiso, 2340000, Chile. ' Departamento de Informática, Universidad Técnica Federico Santa María, Avda España 1680, Valparaiso, 2340000, Chile. ' Center for Nanotechnology and Systems Biology, Departamento de Química, Universidad Técnica Federico Santa María, Avda España 1680, Valparaiso, 2340000, Chile. ' Center for Nanotechnology and Systems Biology, Departamento de Química, Universidad Técnica Federico Santa María, Avda España 1680, Valparaiso, 2340000, Chile

Abstract: This paper describes the development of an inference system used for the identification of genes that encode enzymes of metabolic pathways. Input sequence alignment values are used to classify the best candidate genes for inclusion in a metabolic pathway map. The system workflow allows the user to provide feedback, which is stored in conjunction with analysed sequences for periodic retraining. The construction of the system involved the study of several different classifiers with various topologies, data sets and parameter normalisation data models. Experimental results show an excellent prediction capability with the classifiers trained with mixed data providing the best results.

Keywords: bioinformatics; data mining; feedforward neural networks; mixed models; metabolic pathways; inference systems; gene identification; enzymes; sequence alignment; classification; soft computing; support vector machines; SVM; genetic algorithms; GAs; fuzzy logic; neural networks.

DOI: 10.1504/IJDMB.2012.045539

International Journal of Data Mining and Bioinformatics, 2012 Vol.6 No.1, pp.61 - 85

Received: 20 Feb 2010
Accepted: 14 Jun 2010
Published online: 17 Dec 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article