Microarray Classification and Gene Selection with FS-NEAT

摘要: The analysis of microarrays has the potential to identify and predict diseases predisposition, such as cancer, opening a new path better diagnosis improved treatments. Additionally, can help find genetic biomarkers, which are genes whose expressions related specific disease stage or condition. But due huge number present in microarray experiments, small available samples, computational methods that deal with techniques need overcome difficulties both classification feature selection tasks. This paper presents adaptations for use FS-NEAT, an evolutionary algorithm creates optimizes neural networks through algorithms, tool satisfactorily perform tasks simultaneously automatically. method is tested Leukemia dataset containing six imbalanced classes, compared other classifiers, selected biologically validated.