Paper Info
Title
Comparing multiobjective artificial bee colony adaptations for discovering DNA motifs
Abstract
Multiobjective optimization is successfully applied in many biological problems. Currently, most biological problems require to optimize more than one single objective at the same time, resulting in Multiobjective Optimization Problems (MOP). In the last years, multiple metaheuristics have been successfully used to solve optimization problems. However, many of them are designed to solve problems with only one objective function. In this work, we study several multiobjective adaptations to solve one of the most important biological problems, the Motif Discovery Problem (MDP). MDP aims to discover novel Transcription Factor Binding Sites (TFBS) in DNA sequences, maximizing three conflicting objectives: motif length, support, and similarity. For this purpose, we have used the Artificial Bee Colony algorithm, a novel Swarm Intelligence algorithm based on the intelligent behavior of honey bees. As we will see, the use of one or another multiobjective adaptation causes significant differences in the results.
Year
DOI
Venue
2012
10.1007/978-3-642-29066-4_10
EvoBIO
Keywords
Field
DocType
novel transcription factor,artificial bee colony algorithm,dna motif,multiobjective artificial bee colony,conflicting objective,important biological problem,multiobjective adaptation,multiobjective optimization problems,objective function,novel swarm intelligence algorithm,multiobjective optimization,biological problem,swarm intelligence,dna
Artificial bee colony algorithm,Honey Bees,DNA binding site,Computer science,Swarm intelligence,Multi-objective optimization,Artificial intelligence,Bioinformatics,Single objective,Optimization problem,Machine learning,Metaheuristic
Conference
Citations 
PageRank 
References 
2
0.36
11
Authors
4
Name
Order
Citations
PageRank
David L. González-Álvarez110712.72
Miguel A. Vega-Rodríguez2741113.05
Juan A. Gómez-Pulido320221.36
Juan Manuel Sánchez-Pérez427830.84