Abstract
Predicting the minimum energy protein structure from its amino acid sequence, even under the rather simplified HP lattice model, continues to be an important and challenging problem in computational biology. In this paper, we propose a novel initial population generation strategy for evolutionary algorithm incorporating domain knowledge based on the concept of maximum hydrophobic core formation for Protein structure prediction (PSP) problem. The proposed technique helps the optimization process to commence with diverse seeds and thereby aids in converging to the global solution quickly. The experimental results, conducted on PSP problem using HP benchmark sequences for 2D square and 3D cubic lattice model, demonstrate that the proposed evolutionary algorithm with new core-based population initialization technique is very effective in improving the optimization process in terms of convergence as well as in achieving the optimal energy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Crescenzi, P., Goldman, D., Papadimitriou, C.H., Piccolboni, A., Yannakakis, M.: On the complexity of protein folding. In: RECOMB, pp. 61–62 (1998)
Lau, K., Dill, K.A.: A lattice statistical mechanics model of the conformational and sequence spaces of proteins. Macromolecules 22(10), 3986–3997 (1989)
Nazmul, R., Chetty, M., Samudrala, R., Chalmers, D.: Protein structure prediction based on optimal hydrophobic core formation. In: IEEE Congress on Evolutionary Computation, pp. 1–9 (2012)
Islam, M.K., Chetty, M.: Clustered memetic algorithm with local heuristics for ab initio protein structure prediction. IEEE Trans. Evolutionary Computation 17(4), 558–576 (2013)
Unger, R., Moult, J.: Genetic algorithm for protein folding simulations. Journal of Molecular Biology 231(1), 75–81 (1993)
Islam, M. K., Chetty, M.: Novel memetic algorithm for protein structure prediction. In: Nicholson, A., Li, X. (eds.) AI 2009. LNCS, vol. 5866, pp. 412–421. Springer, Heidelberg (2009)
Shymgelska, A., Hoons, H.H.: An ant colony optimization algorithm for the 2d and 3d hydrophobic polar protein folding problem. BMC Bioinformatics 6(30), 1–22 (2005)
Băutu, A., Luchian, H.: Protein structure prediction in lattice models with particle swarm optimization. In: Dorigo, M., et al. (eds.) ANTS 2010. LNCS, vol. 6234, pp. 512–519. Springer, Heidelberg (2010)
Santana, R., Larranaga, P., Lozano, J.A.: Protein folding in simplified models with estimation of distribution algorithms. IEEE Transactionson on Evolutionary Computation 12(4), 418–438 (2008)
Yue, K., Dill, K.A.: Sequence-structure relationships in proteins and copolymers. Physical Review E 48(3), 2267–2278 (1993)
Beutler, T.C., Dill, K.A.: A fast conformational search strategy for finding low energy structures of model proteins. Protein Science 5(10), 2037–2043 (1996)
Hoque, M. T., Chetty, M., Sattar, A.: Genetic algorithm in ab initio protein structure prediction using low resolution model: A review. In: Sidhu, A.S., Dillon, T.S. (eds.) Biomedical Data and Applications. SCI, vol. 224, pp. 317–342. Springer, Heidelberg (2009)
Hoque, M.T., Chetty, M., Dooley, L.S.: A hybrid genetic algorithm for 2D FCC hydrophobic-hydrophilic lattice model to predict protein folding. In: Sattar, A., Kang, B.-H. (eds.) AI 2006. LNCS (LNAI), vol. 4304, pp. 867–876. Springer, Heidelberg (2006)
Bonissone, P.P., Subbu, R., Eklund, N., Kiehl, R.T.: Evolutionary algorithms+domain knowledge=real-world evolutionary computation. IEEE Trans. on Evolutionary Computation 10(3), 256–280 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Nazmul, R., Chetty, M. (2013). A Knowledge-Based Initial Population Generation in Memetic Algorithm for Protein Structure Prediction. In: Lee, M., Hirose, A., Hou, ZG., Kil, R.M. (eds) Neural Information Processing. ICONIP 2013. Lecture Notes in Computer Science, vol 8227. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-42042-9_68
Download citation
DOI: https://doi.org/10.1007/978-3-642-42042-9_68
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-42041-2
Online ISBN: 978-3-642-42042-9
eBook Packages: Computer ScienceComputer Science (R0)