Incorporating biological knowledge to microarray data classification through genomic data fusion

In this paper we propose the utilisation of an evolutionary approach for the task of classifying microarray data by using prior knowledge in the form of existing gene sets. The purpose of the work is to obtain an accurate classification model that uses a biologically relevant, and previously defined, gene set. The proposed algorithm will be integrated within geneCBR, a successful system able to perform data-mining over high-dimensional microarray data. Preliminary results show that the proposal is able to boost the biological relevance of candidate genes while maintaining the classification accuracy of the model.