AI 2012 - LNAI 7691

A New Genetic Algorithm for Simplified Protein Structure Prediction

Mahmood A. Rashid^{1, 2}, Md. Tamjidul Hoque³, M.A. Hakim Newton^{1, 2}, Duc Nghia Pham^{1, 2}, and Abdul Sattar^{1, 2}

¹Queensland Research Lab, National ICT Australia, Australia

²Institute for Integrated & Intelligent Systems, Griffith University, Australia

³Computer Science, University of New Orleans, USA

Abstract. In this paper, we present a new genetic algorithm for protein structure prediction problem using face-centred cubic lattice and hydrophobic-polar energy model. Our algorithm uses i) an exhaustive generation approach to diversify the search; ii) a novel hydrophobic core-directed macro move to intensify the search; and iii) a random-walk strategy to recover from stagnation. On a set of standard benchmark proteins, our algorithm significantly outperforms the state-of-the-art algorithms for the same models.

Keywords: Protein Structure Prediction, Genetic Algorithms, Local Search, Lattice Models, Energy Models, Random-walk

LNAI 7691, p. 107 ff.

Full article in PDF | BibTeX