Microarray cancer feature selection: Review, challenges and research directions

Abstract

Microarray technology has become an emerging trend in the domain of genetic research in which many researchers employ to study and investigate the levels of genes’ expression in a given organism. Microarray experiments have lots of application areas in the health sector such as diseases prediction and diagnosis, cancer study and soon. The enormous quantity of raw gene expression data usually results in analytical and computational complexities which include feature selection and classification of the datasets into the correct class or group. To achieve satisfactory cancer classification accuracy with the complete set of genes remains a great challenge, due to the high dimensions, small sample size, and presence of noise in gene expression data. Feature reduction is critical and sensitive in the classification task. Therefore, this paper presents a comprehensive survey of studies on microarray cancer classification with a focus on feature selection methods. In this paper, the taxonomy of the various feature selection methods used for microarray cancer classification and open research issues have been extensively discussed.

Keywords

• Feature selection
• Filter
• Wrapper
• Embedded
• Microarray technology
• Microarray data