Protein structure prediction with co-evolving memetic algorithms

We present a coevolutionary learning-optimisation approach to protein structure prediction which uses a memetic algorithm as its underlying search method. Instance-specific knowledge can be learned, stored and applied by the system in the form of a population of rules. These rules determine the neighbourhoods used by the local search process, which is applied to each member of the coevolving population of candidate solutions. A generic coevolutionary framework is proposed for this approach, and then the implementation of a simple self-adaptive instantiation is described. A rule defining the local search's move operator is encoded as a {condition : action} pair and added to the genotype of each individual. It is demonstrated that the action of mutation and crossover on the patterns encoded in these rules, coupled with the action of selection on the resultant phenotypes is sufficient to permit the discovery and propagation of knowledge about the instance being optimised. The algorithm is benchmarked against a simple genetic algorithm, a memetic algorithm using a fixed neighbourhood function, and a similar memetic algorithm which uses random (rather than evolved) rules and shows significant improvements in terms of the ability to locate optimum configurations using Dill's HP model. It is shown that this "metalearning" of problem features provides a means of creating highly scaleable algorithms.

[1]  Jim Smith,et al.  A Memetic Algorithm With Self-Adaptive Local Search: TSP as a case study , 2000, GECCO.

[2]  Tim Jones.  Evolutionary Algorithms, Fitness Landscapes and Search , 1995 .

[3]  J. Skolnick,et al.  Assembly of protein structure from sparse experimental data: An efficient Monte Carlo model , 1998, Proteins.

[4]  Natalio Krasnogor,et al.  Studies on the theory and design space of memetic algorithms , 2002 .

[5]  Nenad Mladenović,et al.  An Introduction to Variable Neighborhood Search , 1997 .

[6]  Natalio Krasnogor,et al.  Toward truly "memetic" memetic algorithms: discussion and proof of concepts , 2002 .

[7]  Bernd Freisleben,et al.  Fitness landscape analysis and memetic algorithms for the quadratic assignment problem , 2000, IEEE Trans. Evol. Comput..

[8]  Frank Thomson Leighton,et al.  Protein folding in the hydrophobic-hydrophilic (HP) is NP-complete , 1998, RECOMB '98.

[9]  Ron Unger,et al.  On the applicability of genetic algorithms to protein folding , 1993, [1993] Proceedings of the Twenty-sixth Hawaii International Conference on System Sciences.

[10]  Edmund K. Burke,et al.  Multimeme Algorithms for Protein Structure Prediction , 2002, PPSN.

[11]  W. Hart.  Adaptive global optimization with local search , 1994 .

[12]  K. Dill.  Theory for the folding and stability of globular proteins. , 1985, Biochemistry.

[13]  William E. Hart,et al.  Protein structure prediction with evolutionary algorithms , 1999 .

[14]  Ron Unger,et al.  Genetic Algorithm for 3D Protein Folding Simulations , 1993, ICGA.

[15]  J. E. Smith,et al.  Co-evolving memetic algorithms: a learning approach to robust scalable optimisation , 2003, The 2003 Congress on Evolutionary Computation, 2003. CEC '03..

[16]  M Feig,et al.  Accurate reconstruction of all‐atom protein representations from side‐chain‐based low‐resolution models , 2000, Proteins.

[17]  Bernd Freisleben,et al.  Fitness landscapes and memetic algorithm design , 1999 .

[18]  Silvano Martello,et al.  Meta-Heuristics: Advances and Trends in Local Search Paradigms for Optimization , 2012 .

[19]  Natalio Krasnogor,et al.  Emergence of profitable search strategies based on a simple inheritance mechanism , 2001 .

[20]  Jim Smith,et al.  Study of fitness landscapes for the HP model of protein structure prediction , 2003, The 2003 Congress on Evolutionary Computation, 2003. CEC '03..