A hybrid genetic algorithm for 2d FCC hydrophobic-hydrophilic lattice model to predict protein folding

Authors:
Md Tamjidul Hoque;Madhu Chetty;Laurence S. Dooley
Affiliations:
Gippsland School of Information Technology, Monash University, Churchill, VIC, Australia;Gippsland School of Information Technology, Monash University, Churchill, VIC, Australia;Gippsland School of Information Technology, Monash University, Churchill, VIC, Australia
Venue:
AI'06 Proceedings of the 19th Australian joint conference on Artificial Intelligence: advances in Artificial Intelligence
Year:
2006

Citing 9
Cited 5

Genetic algorithms for protein folding simulations

Genetic algorithms for protein folding simulations
On the complexity of protein folding (extended abstract)

STOC '98 Proceedings of the thirtieth annual ACM symposium on Theory of computing
Protein folding in the hydrophobic-hydrophilic (HP) is NP-complete

RECOMB '98 Proceedings of the second annual international conference on Computational molecular biology
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
Genetic Algorithm for 3D Protein Folding Simulations

Proceedings of the 5th International Conference on Genetic Algorithms
Optimally Compact Finite Sphere Packings - Hydrophobic Cores in the FCC

CPM '01 Proceedings of the 12th Annual Symposium on Combinatorial Pattern Matching
Blue Gene: a vision for protein science using a petaflop supercomputer

IBM Systems Journal - Deep computing for the life sciences
Search for folding nuclei in native protein structures

Bioinformatics
A Constraint-Based Approach to Fast and Exact Structure Prediction in Three-Dimensional Protein Models

Constraints

A Local Move Set for Protein Folding in Triangular Lattice Models

WABI '08 Proceedings of the 8th international workshop on Algorithms in Bioinformatics
DFS Based Partial Pathways in GA for Protein Structure Prediction

PRIB '08 Proceedings of the Third IAPR International Conference on Pattern Recognition in Bioinformatics
Novel Memetic Algorithm for Protein Structure Prediction

AI '09 Proceedings of the 22nd Australasian Joint Conference on Advances in Artificial Intelligence
DFS-generated pathways in GA crossover for protein structure prediction

Neurocomputing
A memetic approach to protein structure prediction in triangular lattices

ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a Hybrid Genetic Algorithm (HGA) for the protein folding prediction (PFP) applications using the 2D face-centred-cube (FCC) Hydrophobic-Hydrophilic (HP) lattice model. This approach enhances the optimal core formation concept and develops effective and efficient strategies to implement generalized short pull moves to embed highly probable short motifs or building blocks and hence forms the hybridized GA for FCC model. Building blocks containing Hydrophobic (H) – Hydrophilic (P or Polar) covalent bonds are utilized such a way as to help form a core that maximizes the |fitness|. The HGA helps overcome the ineffective crossover and mutation operations that traditionally lead to the stuck condition, especially when the core becomes compact. PFP has been strategically translated into a multi-objective optimization problem and implemented using a swing function, with the HGA providing improved performance in the 2D FCC model compared with the Simple GA.