MGRFE: Multilayer Recursive Feature Elimination Based on an Embedded Genetic Algorithm for Cancer Classification

• Published in: IEEE/ACM transactions on computational biology and bioinformatics Vol. 18; no. 2; pp. 621 - 632
• Main Authors: Peng, Cheng, Wu, Xinyu, Yuan, Wen, Zhang, Xinran, Zhang, Yu, Li, Ying
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.03.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Bioinformatics; Cancer; cancer classification; Classification; Computational Biology - methods; Databases, Genetic; Datasets; DNA microarrays; Feature extraction; Feature selection; Gene expression; Gene Expression Profiling; Gene selection; Genes; genetic algorithm; Genetic algorithms; Heuristic algorithms; Humans; microarray data; Microwave integrated circuits; Models, Genetic; Multilayers; Neoplasms - classification; Neoplasms - genetics; Neoplasms - metabolism; Nonhomogeneous media; Oligonucleotide Array Sequence Analysis; Phenotypes; Polynomials; recursive feature elimination; Source code; Transcriptome - genetics
• ISSN: 1545-5963; 1557-9964; 1557-9964
• DOI: 10.1109/TCBB.2019.2921961

Microarray gene expression data have become a topic of great interest for cancer classification and for further research in the field of bioinformatics. Nonetheless, due to the "large <inline-formula><tex-math notation="LaTeX">p</tex-math> <mml:math><mml:mi>p</mml:mi></mml:math><inline-graphic xlink:href="li-ieq1-2921961.gif"/> </inline-formula>, small <inline-formula><tex-math notation="LaTeX">n</tex-math> <mml:math><mml:mi>n</mml:mi></mml:math><inline-graphic xlink:href="li-ieq2-2921961.gif"/> </inline-formula>" paradigm of limited biosamples and high-dimensional data, gene selection is becoming a demanding task, which is aimed at selecting a minimal number of discriminatory genes associated closely with a phenotype. Feature or gene selection is still a challenging problem owing to its nondeterministic polynomial time complexity and thus most of the existing feature selection algorithms utilize heuristic rules. A multilayer recursive feature elimination method based on an embedded integer-coded genetic algorithm, MGRFE, is proposed here, which is aimed at selecting the gene combination with minimal size and maximal information. On the basis of 19 benchmark microarray datasets including multiclass and imbalanced datasets, MGRFE outperforms state-of-the-art feature selection algorithms with better cancer classification accuracy and a smaller selected gene number. MGRFE could be regarded as a promising feature selection method for high-dimensional datasets especially gene expression data. Moreover, the genes selected by MGRFE have close biological relevance to cancer phenotypes. The source code of our proposed algorithm and all the 19 datasets used in this paper are available at https://github.com/Pengeace/MGRFE-GaRFE .