Investigation of Various Dimensionality Reduction and Feature Selection Techniques in Microarray Gene Data for Renal Cancer Diagnosis

Abstract

Renal cancer is among the top 10 cancers in both genders. Microarray gene expression data is one of the effective modalities to diagnose renal cancer. The main objective of this work is to label the gene expression sample as either normal or clear cell renal cell carcinoma. To improve the classification performance and reduce the training time of the above-mentioned supervised classifiers, various feature selection and dimensionality reduction techniques are investigated. Feature selection techniques, namely variance filter, chi-square test, ANOVA test, and mutual information filter, are tested. In addition, principal component analysis, independent component analysis, and linear discriminant analysis are evaluated as dimensionality reduction techniques. Highest balanced accuracy score of 91.6% is attained for support vector machine classifier while it was increased to 94.4% through the usage appropriate dimensionality reduction or feature selection technique.