Mutation-based Binary Aquila optimizer for gene selection in cancer classification


Pashaei E.

Computational Biology and Chemistry, vol.101, 2022 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 101
  • Publication Date: 2022
  • Doi Number: 10.1016/j.compbiolchem.2022.107767
  • Journal Name: Computational Biology and Chemistry
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Applied Science & Technology Source, BIOSIS, Biotechnology Research Abstracts, Chemical Abstracts Core, Chimica, Compendex, Computer & Applied Sciences, EMBASE, INSPEC, MEDLINE, zbMATH
  • Keywords: Aquila optimizer, Cancer classification, Feature selection, Mutation, Optimization
  • Istanbul Gelisim University Affiliated: Yes

Abstract

© 2022 Elsevier LtdMicroarray data classification is one of the hottest issues in the field of bioinformatics due to its efficiency in diagnosing patients' ailments. But the difficulty is that microarrays possess a huge number of genes where the majority of which are redundant or irrelevant resulting in the deterioration of classification accuracy. For this issue, mutated binary Aquila Optimizer (MBAO) with a time-varying mirrored S-shaped (TVMS) transfer function is proposed as a new wrapper gene (or feature) selection method to find the optimal subset of informative genes. The suggested hybrid method utilizes Minimum Redundancy Maximum Relevance (mRMR) as a filtering approach to choose top-ranked genes in the first stage and then uses MBAO-TVMS as an efficient wrapper approach to identify the most discriminative genes in the second stage. TVMS is adopted to transform the continuous version of Aquila Optimizer (AO) to binary one and a mutation mechanism is incorporated into binary AO to aid the algorithm to escape local optima and improve its global search capabilities. The suggested method was tested on eleven well-known benchmark microarray datasets and compared to other current state-of-the-art methods. Based on the obtained results, mRMR-MBAO confirms its superiority over the mRMR-BAO algorithm and the other comparative GS approaches on the majority of the medical datasets strategies in terms of classification accuracy and the number of selected genes. R codes of MBAO are available at https://github.com/el-pashaei/MBAO.