By Topic

Predicting DNA Motifs by Using Evolutionary Multiobjective Optimization

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
David L. Gonzalez-Álvarez ; Department of Technologies of Computers and Communications, University of Extremadura, Cáceres, Spain ; Miguel A. Vega-Rodriguez ; Juan A. Gomez-Pulido ; Juan M. Sanchez-Pérez

Bioinformatics and computational biology include researchers from many areas: biochemists, physicists, mathematicians, and engineers. The scale of the problems that are discussed ranges from small molecules to complex systems, where many organisms coexist. However, among all these issues, we can highlight genomics, which studies the genomes of microorganisms, plants, and animals. Predicting common patterns, i.e., motifs, in a set of deoxyribonucleic acid (DNA) sequences is one of the important sequence analysis problems, and it has not yet been resolved in an efficient manner. In this study, we study the application of evolutionary multiobjective optimization to solve the motif discovery problem, applied to the specific task of discovering novel transcription factor binding sites in DNA sequences. For this, we have designed, adapted, configured, and evaluated several types of multiobjective metaheuristics. After a detailed study, the results indicate that these metaheuristics are appropriate for discovering motifs. To find good approximations to the Pareto front, we use the hypervolume indicator, which has been successfully integrated into evolutionary algorithms. Besides the hypervolume indicator, we also use the coverage relation to ensure: Which is the best Pareto front? New results have been obtained, which significantly improve those published in previous research works.

Published in:

IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews)  (Volume:42 ,  Issue: 6 )