An entropy-based improved k-top scoring pairs (TSP) method for classifying human cancers

Abstract

Classification and prediction of different cancers based on gene-expression profiles are important for cancer diagnosis, cancer treatment and medication discovery. However, most data in the gene expression profile are not able to make a contribution to cancer classification and prediction. Hence, it is important to find the key genes that are relevant. An entropy-based improved k-top scoring pairs (TSP) (Ik-TSP) method was presented in this study for the classification and prediction of human cancers based on gene-expression data. We compared Ik-TSP classifiers with 5 different machine learning methods and the k-TSP method based on 3 different feature selection methods on 9 binary class gene expression datasets and 10 multi-class gene expression datasets involving human cancers. Experimental results showed that the Ik-TSP method had higher accuracy. The experimental results also showed that the proposed method can effectively find genes that are important for distinguishing different cancer and cancer subtype.

Key words: Cancer classification, gene expression, k-TSP, information entropy, gene selection.