David L. González-Álvarez
Miguel A. Vega-Rodríguez
ABSTRACT
In this paper we present a novel local search for improving the ability of multiobjective evolutionary algorithms when finding repeated patterns -motifs- in DNA sequences. In the metaheuristic design, two competing goals must be taken into account: exploration and exploitation. Exploration is needed to cover most of the optimization problem search space and provide a reliable estimation of the global optimum. In turn, exploitation is also important since normally the solutions refinement allows the achievement of better results. In this work we take advantage of both concepts by combining the exploration capabilities of a population-based evolutionary algorithm and the power of a local search, especially designed to optimize the Motif Discovery Problem (MDP). For doing this, we have implemented a new hybrid multiobjective metaheuristic based on Artificial Bee Colony (ABC). After analyzing the results achieved by this algorithm, named Hybrid-MOABC (H-MOABC), and comparing them with those achieved by three multiobjective evolutionary algorithms and thirteen well-known biological tools, we prove that the hybridization computes accurate biological predictions on real genetic instances in an optimum way. In fact, to the best of our knowledge, the results presented in this paper improve those presented in the literature.
- Che, D. Song, Y., and Rashedd, K. MDGA: Motif discovery using a genetic algorithm. Proceedings of the 2005 Conference on Genetic and Evolutionary Computation (GECCO'05) (2005), 447--452. Google Scholar
Digital Library
- Deb, K., Pratap, A., Agarwal, S., and Meyarivan, T. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation 6, 2 (2002), 182--197. Google ScholarDigital Library
- D'haeseleer, P. What are DNA sequence motifs? Nature Biotechnology 24, 4 (2006), 423--425.Google ScholarCross Ref
- Fogel, G. B., Porto, V. W., Varga, G., Dow, E. R., Crave, A. M., Powers, D. M., Harlow, H. B., Su, E. W., Onyia, J. E., and Su, C. Evolutionary computation for discovery of composite transcription factor binding sites. Nucleic Acids Research 36, 21 (2008), e142, 1--14.Google ScholarCross Ref
- Fogel, G. B., Weekes, D. G., Varga, G., Dow, E. R., Harlow, H. B., Onyia, J. E., and Su, C. Discovery of sequence motifs related to coexpression of genes using evolutionary computation. Nucleic Acids Research 32, 13 (2004), 3826--3835.Google ScholarCross Ref
- González-Álvarez, D. L., Vega-Rodríguez, M. A., Gómez-Pulido, J. A., and Sánchez-Pérez, J. M. Comparing multiobjective swarm intelligence metaheuristics for DNA motif discovery. Engineering Applications of Artificial Intelligence 26, 1 (2012), 341--326. Google ScholarDigital Library
- Karaboga, D. An idea based on honey bee swarm for numerical optimization. Technical report-tr06, Erciyes University, Turkey (2005).Google Scholar
- Kaya, M. MOGAMOD: Multi-objective genetic algorithm for motif discovery. Expert Systems with Applications 36, 2 (2009), 1039--1047. Google ScholarDigital Library
- Liu, F. F. M., Tsai, J. J. P., Chen, R. M., Chen, S. N., and Shih, S. H. FMGA: finding motifs by genetic algorithm. Fourth IEEE Symposium on Bioinformatics and Bioengineering (BIBE'04) (2004), 459--466. Google ScholarDigital Library
- Lones, M. A., and Tyrrell, A. M. Regulatory motif discovery using a population clustering evolutionary algorithm. IEEE/ACM Transactions on Computational Biology and Bioinformatics 4, 3 (2007), 403--414. Google ScholarDigital Library
- Shao, L., and Chen, Y. Bacterial foraging optimization algorithm integrating tabu search for motif discovery. IEEE International Conference on Bioinformatics and Biomedicine (BIBM'09) (2009), 415--418. Google ScholarDigital Library
- Shao, L., Chen, Y., and Abraham, A. Motif discovery using evolutionary algorithms. International Conference of Soft Computing and Pattern Recognition (SOCPAR'09) (2009), 420--425. Google ScholarDigital Library
- Sheskin, D. J. Handbook of parametric and nonparametric statistical procedures. 4th ed. New York: Chapman & Hall/CRC Press (2007). Google ScholarDigital Library
- Stine, M., Dasgupta, D., and Mukatira, S. Motif discovery in upstream sequences of coordinately expressed genes. The 2003 Congress on Evolutionary Computation (CEC'03) (2003), 1596--1603.Google ScholarCross Ref
- Talbi, E.-G. A taxonomy of hybrid metaheuristics. Journal of Heuristics 8 (2002), 541--564. Google ScholarDigital Library
- Talbi, E.-G. Metaheuristics: From Design to Implementation. John Wiley & Sons (2009). Google ScholarDigital Library
- Tompa, M., Li, N., Bailey, T. L., Church, G. M., De Moor, B., Eskin, E., Favorov, A. V., Frith, M. C., Fu, Y., Kent, W. J., Makeev, V. J., Mironov, A. A., Noble, W. S., Pavesi, G., Pesole, G., Régnier, M., Simonis, N., Sinha, S. Thijs, G., Van Helden, J., Vandenbogaert, M., Weng, Z., Workman, C., Ye, C., and Zhu, Z. Assessing computational tools for the discovery of transcription factor binding sites. Nature Biotechnology 23, 1 (2005), 137--144.Google ScholarCross Ref
- Wei, Z., and Jensen, S. GAME: detecting cis-regulatory elements using a genetic algorithm. Bioinformatics 22, 13 (2006), 1577--1584. Google ScholarDigital Library
- Zare-Mirakabad, F., Ahrabian, H., Sadeghi, M., Hashemifar, S., Nowzari-Dalini, A., and Goliaei, B. Genetic algorithm for dyad pattern finding in DNA sequences. Genes & Genetic Systems 84, 1 (2009), 81--93.Google ScholarCross Ref
- Zitzler, E., Laumanns, M., and Thiele, L. SPEA2: Improving the strength pareto evolutionary algorithm. Technical report tik-report 103, Swiss Federal Institute of Technology Zurich, Switzeland (2001).Google Scholar
- Zitzler, E., and Thiele, L. Multiobjective evolutionary algorithms: A comparative case study and the strength pareto approach. IEEE Transactions on Evolutionary Computation 3, 4 (1999), 257--271. Google ScholarDigital Library
Index Terms
- Designing a novel hybrid swarm based multiobjective evolutionary algorithm for finding DNA motifs
Recommendations
Hybrid multiobjective artificial bee colony with differential evolution applied to motif finding
EvoBIO'13: Proceedings of the 11th European conference on Evolutionary Computation, Machine Learning and Data Mining in BioinformaticsThe Multiobjective Artificial Bee Colony with Differential Evolution (MO-ABC/DE) is a new hybrid multiobjective evolutionary algorithm proposed for solving optimization problems. One important optimization problem in Bioinformatics is the Motif ...
Comparing multiobjective artificial bee colony adaptations for discovering DNA motifs
EvoBIO'12: Proceedings of the 10th European conference on Evolutionary Computation, Machine Learning and Data Mining in BioinformaticsMultiobjective 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 ...
Finding motifs in DNA sequences applying a multiobjective artificial bee colony (MOABC) algorithm
EvoBIO'11: Proceedings of the 9th European conference on Evolutionary computation, machine learning and data mining in bioinformaticsIn this work we propose the application of a Swarm Intelligence (SI) algorithm to solve the Motif Discovery Problem (MDP), applied to the specific task of discovering novel Transcription Factor Binding Sites (TFBS) in DNA sequences. In the last years ...
Comments