A gene selection algorithm for microarray cancer classification using an improved particle swarm optimization.

Area of Science:

• Bioinformatics
• Computational Biology
• Machine Learning

Background:

• Gene selection is critical for accurate cancer classification from microarray data.
• Traditional Particle Swarm Optimization (PSO) methods face challenges with redundancy and complexity in gene selection.
• Developing efficient algorithms is crucial for analyzing complex gene expression patterns.

Purpose of the Study:

• To propose a novel Self-Inertia Weight Adaptive Particle Swarm Optimization (SIW-APSO) algorithm for enhanced gene selection.
• To improve the prediction accuracy of cancer classification using microarray data.
• To balance exploration and exploitation in particle swarm optimization for gene selection.

Main Methods:

• A new variant of PSO, SIW-APSO, was developed to optimize gene selection.
• The Extreme Learning Machine (ELM) was integrated for the gene selection procedure.
• The proposed SIW-APSO-ELM algorithm was applied to cancer microarray datasets.

Main Results:

• The SIW-APSO-ELM algorithm achieved high prediction accuracies in cancer gene selection.
• The proposed method demonstrated superior performance compared to existing state-of-the-art techniques.
• Effective identification of prognostic genes with reduced redundancy was achieved.

Conclusions:

• The SIW-APSO-ELM algorithm offers an effective approach for gene selection in cancer classification.
• This method enhances the accuracy and efficiency of analyzing gene expression data.
• The study highlights the potential of adaptive PSO variants in bioinformatics applications.