Protein Structure Prediction on the Face Centered Cubic Lattice by Local Search

Abstract

Ab initio protein structure prediction is an important problem for which several algorithms have been developed. Algorithms differ by how they represent 3D protein conformations (on-lattice, off-lattice, coarse-grain or fine-grain model), by the energy model they consider, and whether they are heuristic or exact algorithms. This paper presents a local search algorithm to find the native state for the Hydrophobic-Polar (HP) model on the Face Centered Cubic (FCC) lattice; i.e. a self-avoiding walk on the FCC lattice with maximum number of H-H contacts. The algorithm relies on a randomized, structured initialization, a novel fitness function to guide the search, and efficient data structures to obtain self-avoiding walks. Experimental results on benchmark instances show the efficiency and excellent performance of our algorithm, and illustrate the biological pertinence of the FCC lattice.