Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
| Hi-index | 0.00 |
The determination of the three-dimensional structure of a protein is one of the most challenging problems of modern science. A genetic algorithm (GA) was developed to find low energy conformations under an atomist protein model. A crowding method was used for parental replacement. The comparison criterion between individuals was the absolute RMSD of the Cβ positions' of the residues. The GROMOS96 force field potential energy function was used to evaluate the energy of the conformations. We tested the performance of the GA against poly-alanine sequences of lengths 18 and 23 in a situation where the global minimum was an alpha helix, and also when it was some other compact structure. The GA proved very efficient by having a 100% success ratio in finding both the global minimum and the alpha helix conformation in all situations.