Fast protein folding in the hydrophobic-hydrophilic model within three-eights of optimal
STOC '95 Proceedings of the twenty-seventh annual ACM symposium on Theory of computing
SODA '97 Proceedings of the eighth annual ACM-SIAM symposium on Discrete algorithms
A complete and effective move set for simplified protein folding
RECOMB '03 Proceedings of the seventh annual international conference on Research in computational molecular biology
Multimeme Algorithms for Protein Structure Prediction
PPSN VII Proceedings of the 7th International Conference on Parallel Problem Solving from Nature
Software—Practice & Experience
A Local Move Set for Protein Folding in Triangular Lattice Models
WABI '08 Proceedings of the 8th international workshop on Algorithms in Bioinformatics
Novel Memetic Algorithm for Protein Structure Prediction
AI '09 Proceedings of the 22nd Australasian Joint Conference on Advances in Artificial Intelligence
Research frontier: memetic computation-past, present & future
IEEE Computational Intelligence Magazine
An enhanced genetic algorithm for protein structure prediction using the 2d hydrophobic-polar model
EA'05 Proceedings of the 7th international conference on Artificial Evolution
AI'06 Proceedings of the 19th Australian joint conference on Artificial Intelligence: advances in Artificial Intelligence
Hybridization of evolutionary algorithms and local search by means of a clustering method
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Hi-index | 0.00 |
Protein structure prediction (PSP) remains one of the most challenging open problems in structural bioinformatics. Simplified models in terms of lattice structure and energy function have been proposed to ease the computational hardness of this combinatorial optimization problem. In this paper, we describe a clustered meme-based evolutionary approach for PSP using triangular lattice model. Under the framework of memetic algorithm, the proposed method extracts a pool of cultural information from different regions of the search space using data clustering technique. These highly observed local substructures, termed as meme, are then aggregated centrally for further refinements as second stage of evolution. The optimal utilization of ‘explore-and-exploit' feature of evolutionary algorithms is ensured by the inherent parallel architecture of the algorithm and subsequent use of cultural information.