A Hybrid Two-Stage Teaching-Learning-Based Optimization Algorithm for Feature Selection in Bioinformatics.

Area of Science:

• Bioinformatics
• Computational Biology
• Machine Learning

Background:

• The curse of dimensionality poses significant challenges for feature selection (FS) in bioinformatics.
• Effective feature selection is crucial for improving classification accuracy in high-dimensional biological datasets.

Purpose of the Study:

• To propose a novel hybrid Two-Stage Teaching-Learning-Based Optimization (TS-TLBO) algorithm for enhanced feature selection.
• To improve the classification performance of bioinformatics data.

Main Methods:

• A hybrid Two-Stage Teaching-Learning-Based Optimization (TS-TLBO) algorithm incorporating selection reduction and comparative self-learning stages.
• Integration of opposition-based learning for initial solution generation.
• Development of a self-adaptive mutation mechanism and integration with differential evolution to enhance search performance.

Main Results:

• The TS-TLBO algorithm effectively reduces the search space by selecting informative and noisy features.
• Comparative experiments on 31 datasets, including 7 bioinformatics datasets, demonstrate superior performance against 11 related methods.
• The algorithm yields a good feature subset, leading to improved classification performance.

Conclusions:

• The proposed TS-TLBO algorithm offers a robust solution for feature selection in high-dimensional data, particularly in bioinformatics.
• The algorithm demonstrates generality and effectiveness in improving classification accuracy and identifying optimal feature subsets.