Genetic Algorithm with New Stochastic Greedy Crossover Operator for Protein Structure Folding Problem

• Main Authors: Leonid Hulianytskyi, Sergii Chornozhuk
• Format: Article
• Language: English
• Published: V.M. Glushkov Institute of Cybernetics 2020-07-01
• Series: Кібернетика та комп'ютерні технології
• Subjects: spatial protein structure; combinatorial optimization; genetic algorithms; crossover operator; stochasticity
• Online Access: http://cctech.org.ua/13-vertikalnoe-menyu-en/128-abstract-20-2-3-arte
• ISSN: 2707-4501; 2707-451X

Introduction. The spatial protein structure folding is an important and actual problem in biology. Considering the mathematical model of the task, we can conclude that it comes down to the combinatorial optimization problem. Therefore, genetic and mimetic algorithms can be used to find a solution. The article proposes a genetic algorithm with a new greedy stochastic crossover operator, which differs from classical approaches with paying attention to qualities of possible ancestors. The purpose of the article is to describe a genetic algorithm with a new greedy stochastic crossover operator, reveal its advantages and disadvantages, compare the proposed algorithm with the best-known implementations of genetic and memetic algorithms for the spatial protein structure prediction, and make conclusions with future steps suggestion afterward. Result. The work of the proposed algorithm is compared with others on the basis of 10 known chains with a length of 48 first proposed in [13]. For each of the chain, a global minimum of free energy was already precalculated. The algorithm found 9 out of 10 spatial structures on which a global minimum of free energy is achieved and also demonstrated a better average value of solutions than the comparing algorithms. Conclusion. The quality of the genetic algorithm with the greedy stochastic crossover operator has been experimentally confirmed. Consequently, its further research is promising. For example, research on the selection of optimal algorithm parameters, improving the speed and quality of solutions found through alternative coding or parallelization. Also, it is worth testing the proposed algorithm on datasets with proteins of other lengths for further checks of the algorithm’s validity.