A Genetic Algorithm for Transposable Elements Hierarchical Classification Rule Induction

Author(s)

Pereira, Gean Trindade ; Santos, Bruna Zamith ; Cerri, Ricardo ; IEEE

• Document type: Journal article
• Source: 2018 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC); v. N/A, p. 8-pg., 2018-01-01.

Abstract

Genomes of animals and plants are crowded with Transposable Elements (TEs), which are DNA sequences capable to move within the genome of a cell. They can modify the functionality of host genes, which makes them extremely important for the genetic variability of species. Therefore, their correct classification is crucial to understand their role in evolution. In this paper, the classification of TEs is treated as a Hierarchical Classification problem making use of Evolutionary Computation. Thus, hierarchical datasets suitable to be used by ML methods are presented, along with a novel hierarchical global rule induction classification strategy using a Genetic Algorithm. To the best of our knowledge, this is the first attempt in the literature to apply a hierarchical global-based rule learner to induce a model which classifies TEs according to a hierarchical taxonomy. We compared our global method with local and homology based methods, and evaluated them using measures specific for hierarchical problems. The experimental results showed that our proposal achieved better or competitive results if compared to state-of-the-art methods from the literature, having the advantage of presenting an interpretable set of classification rules. (AU)

• FAPESP's process: 15/14300-1 - Hierarchical classification of transposable elements using machine learning
• Grantee: Ricardo Cerri
• Support Opportunities: Regular Research Grants
• FAPESP's process: 16/25078-0 - Hierarchical classification of transposable elements and protein functions making use of machine learning
• Grantee: Bruna Zamith Santos
• Support Opportunities: Scholarships in Brazil - Scientific Initiation