Cancer Classification through Gene Selection Using the Social Spider Optimization Algorithm.

Saved in:

Bibliographic Details
Title:	Cancer Classification through Gene Selection Using the Social Spider Optimization Algorithm.
Authors:	Cherif, Chahira¹ cherif.chahira@univ-oran1.dz, Maiza, Mohammed² maiza.mohammed@univ-oran1.dz, Chouraqui, Samira³ samira.chouraqui@univ-usto.dz, Taleb-Ah, Abdelmalik abdelmalik.taleb-ahmed@uphf.fr
Source:	Informatica (03505596). Oct2025, Vol. 49 Issue 3, p537-550. 14p.
Subjects:	Microarray technology, Feature selection, Machine learning, Tumors, Data management, Swarm intelligence, Classification
Abstract:	Cancer is a leading cause of global mortality, underscoring the need for advanced diagnostic tools to enable early and accurate detection. Microarray technology allows for the simultaneous analysis of thousands of genes, offering valuable insights into cancer biology. However, the high dimensionality of microarray data presents significant challenges for classification tasks. In this study, we propose a novel approach that integrates the Social Spider Optimization (SSO) algorithm with mutual information-based feature selection to identify the most discriminative genes for cancer classification. We evaluate the performance of four machine learning classifiers—Decision Tree (DT), K-Nearest Neighbors (K-NN), Neural Networks (NN), and Support Vector Machines (SVM)—with and without feature selection. Our results demonstrate that the SSO algorithm significantly enhances classification accuracy, with SVM achieving near-perfect performance on leukemia and lymphoma datasets when combined with Max-Relevance Min-Redundancy (MRMR) feature selection. This hybrid approach provides a robust solution for cancer diagnosis by addressing key challenges such as data redundancy and computational complexity. [ABSTRACT FROM AUTHOR]
	Copyright of Informatica (03505596) is the property of Slovene Society Informatika and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	Cancer is a leading cause of global mortality, underscoring the need for advanced diagnostic tools to enable early and accurate detection. Microarray technology allows for the simultaneous analysis of thousands of genes, offering valuable insights into cancer biology. However, the high dimensionality of microarray data presents significant challenges for classification tasks. In this study, we propose a novel approach that integrates the Social Spider Optimization (SSO) algorithm with mutual information-based feature selection to identify the most discriminative genes for cancer classification. We evaluate the performance of four machine learning classifiers—Decision Tree (DT), K-Nearest Neighbors (K-NN), Neural Networks (NN), and Support Vector Machines (SVM)—with and without feature selection. Our results demonstrate that the SSO algorithm significantly enhances classification accuracy, with SVM achieving near-perfect performance on leukemia and lymphoma datasets when combined with Max-Relevance Min-Redundancy (MRMR) feature selection. This hybrid approach provides a robust solution for cancer diagnosis by addressing key challenges such as data redundancy and computational complexity. [ABSTRACT FROM AUTHOR]
ISSN:	03505596
DOI:	10.31449/inf.v49i3.9126