Gene Expression Data Analysis Using Data Mining Algorithms for Colon Cancer

The concept of Data mining is used in various medical applications like tumor classification, protein structure prediction, gene classification, cancer classification based on microarray data, clustering of gene expression data, statistical model of protein-protein interaction etc. Adverse drug events in prediction of medical test effectiveness can be done based on genomics and proteomics through data mining approaches. Cancer detection is one of the hot research topics in the bioinformatics. Data mining techniques, such as pattern recognition, classification and clustering is applied over gene expression data for detection of cancer occurrence and survivability. Classification of colon cancer dataset using weka library, in which Logistics , Ibk, Kstar, NNge, ADTree , Random Forest Algorithms etc had shown 100 % correctly classified instances, followed by Navie Bayes classification and PART with 97.20 % accuracy. Kappa Statistic for Logis t ics , Ibk, Ks tar, NNge, ADTree, Random Forest has shown Maximum. Mean absolute error and Root mean squared error are shown low for Logistics , Ks tar and NNge. Using various Classification algorithms the cancer dataset can be easily analyzed in order to obtain the better results.