String Matching Based Correlated Gene Selection and ANN Based Classification of Leukemia Gene Expression Data Set: A Review

Data mining algorithms play a vital role to classify Gene expression data, for the prediction of diseases. With the help of gene expression data obtained from microarray technology, heterogeneous cancers can be classified into appropriate subtypes but accurate Cancer classification based on the DNA microarray data is still a difficult problem because there are huge numbers of genes relative to the number of training samples and it is a difficult task to create an optimal classifier for DNA analysis that deals with only a few samples with large number noisy features. Since it become difficult to human to see all those parameter in a short type of time span. The failure in diagnosing of right type of cancer, become inevitable to avoid, that may cause delay in treatment. It may cause causality also. We can use AI to sort out the problem. Here we reestablish the fact that a string matching based feature selection technique for finding most informative genes then we test the effectiveness of the proposed approach using a neural network based classifier on leukemia benchmark gene expression data sets. The obtained results are encouraging.