International Journal of Intelligence Science, 2015, 5, 158-172 Published Online April 2015 in SciRes. http://www.scirp.org/journal/ijis http://dx.doi.org/10.4236/ijis.2015.53014 How to cite this paper: Márquez, E., et al. (2015) A Decision Support System Based on Multi-Agent Technology for Gene Expression Analysis. International Journal of Intelligence Science, 5, 158-172. http://dx.doi.org/10.4236/ijis.2015.53014 A Decision Support System Based on Multi-Agent Technology for Gene Expression Analysis Edna Márquez 1 , Jesús Savage 1 , Jaime Berumen 2 , Christian Lemaitre 3 , Ana Lilia Laureano-Cruces 4 , Ana Espinosa 2 , Ron Leder 1 , Alfredo Weitzenfeld 5 1 Facultad de Ingeniería, Universidad Nacional Autónoma de México, México D.F., México 2 Unidad de Medicina Genómica, Hospital General de México, México D.F., México 3 Departamento de Ciencias de la Comunicación, Universidad Autónoma Metropolitana, México D.F., México 4 Departamento de Sistemas, Universidad Autónoma Metropolitana, México D.F., México 5 Department of Computer Science and Engineering, University of South Florida, Tampa, FL, USA Email: cednam@gmail.com , robotssavage@gmail.com , jaimeberumen@hotmail.com , lemaitre@gmail.com , clc@azc.uam.mx , anaesga@hotmail.com , rleder@ieee.org , aweitzenfeld@usf.edu Received 13 March 2015; accepted 21 April 2015; published 27 April 2015 Copyright © 2015 by authors and Scientific Research Publishing Inc. This work is licensed under the Creative Commons Attribution International License (CC BY). http://creativecommons.org/licenses/by/4.0/ Abstract The genetic microarrays give to researchers a huge amount of data of many diseases represented by intensities of gene expression. In genomic medicine gene expression analysis is guided to find strategies for prevention and treatment of diseases with high rate of mortality like the different cancers. So, genomic medicine requires the use of complex information technology. The purpose of our paper is to present a multi-agent system developed in order to improve gene expression analysis with the automation of tasks about identification of genes involved in a cancer, and classi- fication of tumors according to molecular biology. Agents that integrate the system, carry out reading files of intensity data of genes from microarrays, pre-processing of this information, and with machine learning methods make groups of genes involved in the process of a disease as well as the classification of samples that could propose new subtypes of tumors difficult to identify based on their morphology. Our results we prove that the multi-agent system requires a minimal intervention of user, and the agents generate knowledge that reduce the time and complexity of the work of prevention and diagnosis, and thus allow a more effective treatment of tumors. Keywords Multi-Agent Systems, Machine Learning, Bioinformatics, Gene Expression Analysis