A cascading support vector machines system for gene expression data classification

Microarray technology provides the ability of monitoring the gene expression levels of thousands of genes in parallel. Gene expression data classification applies for diseases' diagnosis or prediction. We propose an intelligent system for the classification of multiclass gene expression data. It is based on a cascading support vector machines (SVM) scheme and utilizes Welch's t-test for the detection of differentially expressed genes. The system was applied for the discrimination of normal and lung cancer subtypes' specimens. The overall accuracy achieved was 98.5%. The results show that the proposed system can be efficiently used for microarray data analysis.