Claim Missing Document
Check
Articles

Found 1 Documents
Search

Feature Selection Methods of Gene Expression Based on Machine Learning: A Review Karwan Jameel Merceedi; Adnan Mohsin Abdulazeez
International Journal of Research and Applied Technology Vol. 5 No. 1 (2025): Vol 5 No 1 (2025)
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/injuratech.v5i1.16828

Abstract

This paper presents a comprehensive review of machine learning-driven feature selection strategies applied to gene expression data. The rapid expansion of high-dimensional genomic datasets necessitates advanced analytical techniques to extract meaningful biological insights. In this context, feature selection is pivotal for identifying key biomarker genes that significantly influence the predictive performance of machine learning models. This review examines diverse feature selection paradigms—categorized into filter, wrapper, and embedded approaches—evaluating their respective strengths and limitations. Furthermore, it underscores the role of gene expression data in elucidating the molecular mechanisms underlying complex diseases and biological processes, while addressing the challenges posed by high-dimensionality to enhance model interpretability, reduce computational complexity, and improve predictive accuracy. To elucidate their underlying principles and practical applications, prominent algorithms—such as Mutual Information, Relief, and Recursive Feature Elimination (RFE)—are critically analyzed across diverse datasets and experimental frameworks, with particular emphasis on scalability, interpretability, and robustness. Finally, the article surveys emerging paradigms, including deep learning architectures, ensemble methods, and domain knowledge integration, before concluding with current open challenges and prospective future directions. Ultimately, this review serves as a valuable resource for bioinformaticians, researchers, and practitioners navigating machine learning-based feature selection in genomic analysis.