Abstract
Genetic Algorithm (GA) is an evolutionary meta-heuristic approach, motivated by the principle of Genetics and natural selection. The goal of GA is to produce better offspring by genetic operations including selection, crossover, and mutation. In GA, parent selection is essential as the optimization results directly depend on the fitness of next generation (off-springs). In this paper, an improved version of GA, named Elitist Twin Removal Genetic Algorithm (ETRGA) has been proposed to enhance the performance of crossover operator during parent selection. This is to ensure that the best gene template will never be lost. In addition, Twin Removal (TR) operator efficiently balances the intensification (exploitation) and diversification (exploration) of the search process. Proposed ETRGA has been applied to 15 well-known benchmark functions as well as gene selection problem to find critical gene. Here, common disease gene obtained by three algorithms is termed as a critical gene. The performance of ETRGA has been compared with Simple Genetic Algorithm (SGA) and Twin Removal Genetic Algorithm (TRGA). The experimental results confirm that the proposed ETRGA outperforms SGA and TRGA in terms of statistical metrics taken care in the account in benchmark functions and real-life problem. The convergence graph of ETRGA shows that it has better exploration and does not suffer from premature convergence.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Lim TY (2014) Structured population genetic algorithms: a literature survey. Artif Intell Rev 41(3):385–399
Yang XS (2010) Nature inspired meta-heuristic algorithm. 2ndedn. Luniver Press, United Kingdom
Biswas S, Acharyya S (2016) Neural model of gene regulatory network: a survey on supportive meta-heuristic. Theory Biosci 135(1–2):1–19
Hoque MT, Chetty M, Dolley LS (2007) Generalized schemata theorem incorporating twin removal for protein structure prediction. In: International workshop on pattern recognition in bioinformatics, pp 84–87
Iqbal S, Hoque T (2017) hGRGA: a scalable genetic algorithm using homologous gene schema replacement. Swarm Evol Comput 34:33–49
Saha S, Biswas S, Acharyya S (2016) Gene selection by sample classification using k nearest neighbor and meta-heuristic algorithms. In: Proceedings of 2016 IEEE 6th international conference on advanced computing (IACC), pp 250–255
Saha S, Biswas S, Acharyya S (2017) Identification of disease critical gene using collective meta-heuristic approaches: an application to Preeclamsia. Interdiscip Sci: Comput Life Sci 1–16
Lockhart DJ, Winzeler EA (2000) Genomics, gene expression and DNA arrays. Nature 405(6788):827
Liang JJ, Qu BY, Suganthan PN (2013) Problem definitions and evaluation criteria for the CEC 2014 special session and competition on single objective real-parameter numerical optimization, Computational Intelligence Laboratory, Zhengzhou University, Zhengzhou China and Technical Report, Nanyang Technological University, Singapore
Jamil M, Yang XS (2013) A literature survey of benchmark functions for global optimisation problems. Int J Math Model Numeric Optim 4(2):150–194
Gulesserian T, Seidl R, Hardmeier R, Cairns N, Lubec G (2001) Superoxide Dismutase SOD1, encoded on Chromosome 21, but not SOD2 is overexpressed in brains of patients with down syndrome. J Investig Med 49:41–46
Fuentes JJ, Genesca L, Kingsbury TJ, Cunningham KW, Perez-Riba M, Estivill X, Luna S (2000) DSCR1, overexpressed in down syndrome, is an inhibitor of calcineurin-mediated signaling pathways. Hum Mol Genet 9(11):1681–1690
Halevy T, Biancotti JC, Yanuka O, Golan-Lev T, Benvenisty N (2016) Molecular characterization of down syndrome embryonic stem cells reveals a role for RUNX1 in neural differentiation. Stem Cell Rep 7(4):777–786
Gao X, Li H, Wei JX (2018) MiR-4421 regulates the progression of preeclampsia by regulating CYP11B2. Europ Rev Med Pharmacol Sci 22(6):1533–1540
Deng CL, Ling ST, Liu XQ, Zhao YJ, Lv YF (2015) Decreased expression of matrix metalloproteinase-1 in the maternal umbilical serum, trophoblasts and decidua leads to preeclampsia. Exp Therap Med 9(3):992–998
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Das, P., Jana, B., Acharyya, S. (2021). A New Variant of Genetic Algorithm for Solving Gene Selection Problem. In: Giri, D., Buyya, R., Ponnusamy, S., De, D., Adamatzky, A., Abawajy, J.H. (eds) Proceedings of the Sixth International Conference on Mathematics and Computing. Advances in Intelligent Systems and Computing, vol 1262. Springer, Singapore. https://doi.org/10.1007/978-981-15-8061-1_25
Download citation
DOI: https://doi.org/10.1007/978-981-15-8061-1_25
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-8060-4
Online ISBN: 978-981-15-8061-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)