A summary of the prevalence of Genetic Algorithms in Bioinformatics from 2015 onwards

Abstract

In recent years, machine learning has seen an increasing presencein a large variety of fields, especially in health care and bioinformatics.More specifically, the field where machine learning algorithms have found most applications is Genetic Algorithms.The objective of this paper is to conduct a survey of articles published from 2015 onwards that deal with Genetic Algorithms(GA) and how they are used in bioinformatics.To achieve the objective, a scoping review was conducted that utilized Google Scholar alongside Publish or Perish and the Scimago Journal & CountryRank to search for respectable sources. Upon analyzing 31 articles from the field of bioinformatics, it became apparent that genetic algorithms rarely form a full application, instead they rely on other vital algorithms such as support vector machines.Indeed, support vector machines were the most prevalent algorithms used alongside genetic algorithms; however, while the usage of such algorithms contributes to the heavy focus on accuracy by GA programs, it often sidelines computation times in the process. In fact, most applications employing GAs for classification and feature selectionare nearing or at 100% success rate, and the focus of future GA development should be directed elsewhere. Population-based searches, like GA, are often combined with other machine learning algorithms. In this scoping review, genetic algorithms combined with Support Vector Machines were found to perform best. The performance metric that was evaluated most often was accuracy. Measuring the accuracy avoids measuring the main weakness of GAs, which is computational time. The future of genetic algorithms could be open-ended evolutionary algorithms, which attempt to increase complexity and find diverse solutions, rather than optimize a fitness function and converge to a single best solution from the initial population of solutions.