Artificial Bee Colony for Bioinformatics Applications: Review

The Artificial Bee Colony (ABC) algorithm has emerged as a robust swarm intelligence-based optimization method, inspired by the foraging behavior of honey bees. Due to its simplicity, adaptability, and ability to escape local optima, ABC has attracted several researchers to tackle complex optimization problems in different fields. This review explores the application of the ABC algorithm within the domain of bioinformatics, emphasizing its effectiveness in addressing key computational challenges, including gene selection, protein structure prediction, sequence alignment, clustering of biological data, and Biological feature selection in genomics and proteomics. By examining recent advances and variations of the ABC algorithm tailored for bioinformatics, we highlight the strengths, limitations, and potential areas of improvement for the algorithm’s application to large-scale biological datasets. The review begins by analyzing the growth of the ABC algorithm in terms of research fields, publication numbers, and leading researchers. Thereafter, the theoretical background of the basic version of ABC is illustrated. The review thoroughly examines the utilization of ABC variants in more than ten bioinformatics applications. A critical analysis is also provided to show the main research gaps and limitations of the existing works. Finally, the conclusion and the possible future directions to fill the research gaps in this domain are recommended. This review serves as a comprehensive reference, aimed at researchers and practitioners seeking insights into how ABC can be applied or further developed to meet the growing computational demands of the bioinformatics domain.