Gene selection and classification of microarray data method based on mutual information and moth flame algorithm.

作者：

Highlights：

• The first work to apply the moth flame optimization algorithm to gene selection.

• Hybridization of mutual information and moth flame algorithm for gene selection.

• Performance of our algorithm is evaluated on sixteen benchmark datasets.

• Our proposal obtained the best subset of genes with high classification accuracy.

摘要

•The first work to apply the moth flame optimization algorithm to gene selection.•Hybridization of mutual information and moth flame algorithm for gene selection.•Performance of our algorithm is evaluated on sixteen benchmark datasets.•Our proposal obtained the best subset of genes with high classification accuracy.

论文关键词：Gene expression,Feature selection,Microarray,Cancer classification,Moth Flame Algorithm,Mutual information maximization,Bio-inspired algorithms,Bioinformatics,Optimization algorithms,Evolutionary algorithm,Molecular biology,Swarm intelligence

论文评审过程：Received 21 December 2019, Revised 30 July 2020, Accepted 11 September 2020, Available online 30 September 2020, Version of Record 6 October 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.114012