Microarray Classification and Rule Based Cancer Identification

Microarray analysis creates a clear scenario for the complete transcription profile of cells that facilitate drug and therapeutics development, disease diagnosis and enable us to take an in depth look at cell biology. One of the key challenges in microarray analysis, especially in cancerous gene expression profiles, is to identify genes or groups of genes that are highly responsible for the existence of a tumor in a cell. Our proposed modified algorithm support vector machine (SVM) is used to classify cancer related 5 microarray data and observed improved performance than previously used Interesting rule group (IRG), classification based on associations (CBA), and even a different version of SVM algorithm. Finally we use entropy measure through rule based learning algorithm to extract the responsible genes causes for cancer for each microarray problem. The rules are generated with higher acceptability.