A Novel Gene Selection Method Based on Sparse Representation and Max-Relevance and Min-Redundancy

Author(s): Min Chen, Xiaoming He, ShaoBin Duan*, YingWei Deng.

Journal Name: Combinatorial Chemistry & High Throughput Screening
Accelerated Technologies for Biotechnology, Bioassays, Medicinal Chemistry and Natural Products Research

Volume 20 , Issue 2 , 2017

Become EABM
Become Reviewer

Abstract:

Aim and Objective: Gene selection method as an important data preprocessing work has been followed. The criteria Maximum relevance and minimum redundancy (MRMR) has been commonly used for gene selection, which has a satisfactory performance in evaluating the correlation between two genes. However, for viewing genes in isolation, it ignores the influence of other genes.

Methods: In this study, we propose a new method based on sparse representation and MRMR algorithm (SRCMRM), using the sparse representation coefficient to represent the relevance of genes and correlation between genes and categories. The SRCMRMR algorithm contains two steps. Firstly, the genes irrelevant to the classification target are removed by using sparse representation coefficient. Secondly, sparse representation coefficient is used to calculate the correlation between genes and the most representative gene with the highest evaluation.

Results: To validate the performance of the SRCMRM, our method is compared with various algorithms. The proposed method achieves better classification accuracy for all datasets.

Conclusion: The effectiveness and stability of our method have been proven through various experiments, which means that our method has practical significance.

Keywords: Sparse representation, MRMR, gene selection.

Rights & PermissionsPrintExport Cite as

Article Details

VOLUME: 20
ISSUE: 2
Year: 2017
Page: [158 - 163]
Pages: 6
DOI: 10.2174/1386207320666170126114051
Price: $58

Article Metrics

PDF: 12
HTML: 1
EPUB: 1
PRC: 1