The genetic microarrays give to researchers a huge amount of data of many diseases represented\nby intensities of gene expression. In genomic medicine gene expression analysis is guided to find\nstrategies for prevention and treatment of diseases with high rate of mortality like the different\ncancers. So, genomic medicine requires the use of complex information technology. The purpose\nof our paper is to present a multi-agent system developed in order to improve gene expression\nanalysis with the automation of tasks about identification of genes involved in a cancer, and classification\nof tumors according to molecular biology. Agents that integrate the system, carry out\nreading files of intensity data of genes from microarrays, pre-processing of this information, and\nwith machine learning methods make groups of genes involved in the process of a disease as well\nas the classification of samples that could propose new subtypes of tumors difficult to identify\nbased on their morphology. Our results we prove that the multi-agent system requires a minimal\nintervention of user, and the agents generate knowledge that reduce the time and complexity of\nthe work of prevention and diagnosis, and thus allow a more effective treatment of tumors.
Loading....