Title
Solving the motif discovery problem by using Differential Evolution with Pareto Tournaments
Abstract
This paper proposes the use of Differential Evolution with Pareto Tournaments (DEPT) to identify common patterns, motifs, in biological sequences. The work is motivated by two fundamental facts: first, the role that bioinformatics problems are taking in computer engineering in recent years, and second, the limited existence of scientific papers that use evolutionary techniques for solving such problems. Although finding motifs in deoxyribonucleic acid (DNA) sequences is one of the classical sequence analysis problems, it has not yet been resolved in an efficient manner. Using evolutionary algorithms we can get nearly optimal solutions in a reasonable time. The Motif Discovery Problem (MDP) aims to maximize conflicting objectives: support, motif length, and similarity. These objectives imply multiobjective optimization (MOO) to obtain motifs in the most efficient way as possible. Moreover, in this work, we incorporate the hypervolume indicator to measure the quality of the solutions to this problem. As we will see, our results surpass the results obtained by other approaches proposed in the literature.
Year
DOI
Venue
2010
10.1109/CEC.2010.5586068
Evolutionary Computation
Keywords
Field
DocType
Pareto optimisation,bioinformatics,evolutionary computation,molecular biophysics,DNA sequences,Pareto tournaments,bioinformatics problems,biological sequences,differential evolution,motif discovery problem,multiobjective optimization,Bioinformatics,evolutionary algorithm,hypervolume,motif discovery,multiobjective optimization
Mathematical optimization,Evolutionary algorithm,Computer science,Evolutionary computation,Motif (music),Multi-objective optimization,Differential evolution,Artificial intelligence,Machine learning,Pareto principle
Conference
ISBN
Citations 
PageRank 
978-1-4244-6909-3
12
0.61
References 
Authors
10
8