Aplicação de Evolução Diferencial em GPU Para o Problema de Predição de Estrutura de Proteínas com Modelo 3D AB Off-Lattice
Abstract
The function that a protein performs is directly related to its threedimensional structure. However, for most of the proteins currently sequenced, their native structural form is not yet known. This article proposes using the Differential Evolution (DE) algorithm developed on the NVIDIA CUDA platform applied to the 3D AB Off-Lattice model for protein structure prediction. A niche and crowding strategy is added in the DE algorithm combined with parameter self-tuning techniques, routines for resetting the population, two levels of optimization, and local search. Four real proteins were used for experimentation, and the results obtained are competitive with state-of-the-art algorithms. The use of GPU's massive parallelism highlights its applicability to this class of problems, reaching accelerations of 708.78x for the largest protein chain.References
Alberts B, Johnson A, L. J. e. a. (2002). Molecular Biology of the Cell. Garland Science, 4th edition edition.
Boiani, M. and Parpinelli, R. S. (2020). A GPU-based hybrid jDE algorithm applied to the 3d-AB protein structure prediction. Swarm and Evolutionary Computation, 58:100711.
Boškoviíc, B. and Brest, J. (2016). Differential evolution for protein folding optimization based on a three-dimensional AB off-lattice model. Journal of Molecular Modeling, 22(10).
Boškoviíc, B. and Brest, J. (2018). Protein folding optimization using differential evolution extended with local search and component reinitialization. Information Sciences, 454-455:178–199.
Boškoviíc, B. and Brest, J. (2019). Two-level protein folding optimization on a threedimensional ab off-lattice model.
Deng, L., Zhang, L., Sun, H., and Qiao, L. (2019). DSM-DE: a differential evolution with dynamic speciation-based mutation for single-objective optimization. Memetic Computing, 12(1):73–86.
Fraenkel, A. (1993). Complexity of protein folding. Bulletin of Mathematical Biology, 55(6):1199–1210.
Jana, N. D., D. S. and Sil, J. (2018). A Metaheuristic Approach to Protein Structure Prediction. Springer International Publishing.
Li, B., Chiong, R., and Lin, M. (2015). A balance-evolution articial bee colony algorithm for protein structure optimization based on a three-dimensional AB off-lattice model. Computational Biology and Chemistry, 54:1–12.
Li, T., Zhou, C., Wang, B., Xiao, B., and Zheng, X. (2018). A hybrid algorithm based on articial bee colony and pigeon inspired optimization for 3d protein structure prediction. Journal of Bionanoscience, 12(1):100–108.
Opara, K. R. and Arabas, J. (2019). Differential evolution: A survey of theoretical analyses. Swarm and Evolutionary Computation, 44:546 – 558.
Parpinelli, R., Felippe Plichoski, G., Silva, R., and Narloch, P. (2019). A review of techniques for online control of parameters in swarm intelligence and evolutionary computation algorithms. International Journal of Bio-Inspired Computation, 13:1–20.
Siarry, P., editor (2016). Metaheuristics. Springer International Publishing.
Soyata, T. (2018). GPU Parallel Program Development Using CUDA.
Stillinger, F. H., Head-Gordon, T., and Hirshfeld, C. L. (1993). Toy model for protein folding. Physical Review E, 48(2):1469–1477.
Boiani, M. and Parpinelli, R. S. (2020). A GPU-based hybrid jDE algorithm applied to the 3d-AB protein structure prediction. Swarm and Evolutionary Computation, 58:100711.
Boškoviíc, B. and Brest, J. (2016). Differential evolution for protein folding optimization based on a three-dimensional AB off-lattice model. Journal of Molecular Modeling, 22(10).
Boškoviíc, B. and Brest, J. (2018). Protein folding optimization using differential evolution extended with local search and component reinitialization. Information Sciences, 454-455:178–199.
Boškoviíc, B. and Brest, J. (2019). Two-level protein folding optimization on a threedimensional ab off-lattice model.
Deng, L., Zhang, L., Sun, H., and Qiao, L. (2019). DSM-DE: a differential evolution with dynamic speciation-based mutation for single-objective optimization. Memetic Computing, 12(1):73–86.
Fraenkel, A. (1993). Complexity of protein folding. Bulletin of Mathematical Biology, 55(6):1199–1210.
Jana, N. D., D. S. and Sil, J. (2018). A Metaheuristic Approach to Protein Structure Prediction. Springer International Publishing.
Li, B., Chiong, R., and Lin, M. (2015). A balance-evolution articial bee colony algorithm for protein structure optimization based on a three-dimensional AB off-lattice model. Computational Biology and Chemistry, 54:1–12.
Li, T., Zhou, C., Wang, B., Xiao, B., and Zheng, X. (2018). A hybrid algorithm based on articial bee colony and pigeon inspired optimization for 3d protein structure prediction. Journal of Bionanoscience, 12(1):100–108.
Opara, K. R. and Arabas, J. (2019). Differential evolution: A survey of theoretical analyses. Swarm and Evolutionary Computation, 44:546 – 558.
Parpinelli, R., Felippe Plichoski, G., Silva, R., and Narloch, P. (2019). A review of techniques for online control of parameters in swarm intelligence and evolutionary computation algorithms. International Journal of Bio-Inspired Computation, 13:1–20.
Siarry, P., editor (2016). Metaheuristics. Springer International Publishing.
Soyata, T. (2018). GPU Parallel Program Development Using CUDA.
Stillinger, F. H., Head-Gordon, T., and Hirshfeld, C. L. (1993). Toy model for protein folding. Physical Review E, 48(2):1469–1477.
Published
2020-10-21
How to Cite
DIAS, André; BOIANI, Mateus; PARPINELLI, Rafael.
Aplicação de Evolução Diferencial em GPU Para o Problema de Predição de Estrutura de Proteínas com Modelo 3D AB Off-Lattice. In: BRAZILIAN SYMPOSIUM ON HIGH PERFORMANCE COMPUTING SYSTEMS (SSCAD), 21. , 2020, Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2020
.
p. 323-334.
DOI: https://doi.org/10.5753/wscad.2020.14080.
