Critical Gene Selection by a Modified Particle Swarm Optimization Approach
Abstract
Gene selection is an eminent area of research in computational biology. Identifying disease critical genes analysing large gene expression dataset is a challenging problem in computational biology. Application of meta-heuristics is considered to be efficient to attempt such problem. Particle Swarm Optimization (PSO) is a meta-heuristic technique based on swarm intelligence. An improved version of PSO, namely, New Variant Repository and Mutation based PSO (NVRMPSO) combined with kNN (NVRMPSO-kNN) has been applied here to find the subset of genes (disease critical) from gene expression dataset. The modification has been done on a recent PSO version, referred as, Repository and Mutation based PSO (RMPSO). The kNN algorithm has been used for sample classification. The performance of proposed NVRMPSO-kNN has been compared with RMPSO incorporated with kNN (RMPSO-kNN) in gene selection problem. The RMPSO-kNN and proposed NVRMPSO-kNN have been applied to three different sizes of datasets, numbered as, E-MEXP-1050, GSE60438 and GSE10588 of preeclampsia disease. The experimental results reveal that the efficacy of NVRMPSO-kNN is better than that of RMPSO-kNN when Classification Accuracy is considered. Furthermore, the performance of proposed NVRMPSO-kNN has been validated with the state-of-the-art observations.
Keywords
Gene selection Gene expression PSO RMPSO kNNReferences
- 1.Heller, M.J.: DNA microarray technology: devices, systems, and applications. Annu. Rev. Biomed. Eng. 4(1), 129–153 (2002)CrossRefGoogle Scholar
- 2.Biswas, S., Dutta, S., Acharyya, S.: Identification of disease critical genes using collective meta-heuristic approaches: an application to preeclampsia. Interdisc. Sci. Comput. Life Sci. 1–16 (2017)Google Scholar
- 3.Saha, S., Biswas, S., Acharyya, S.: Gene selection by sample classification using k nearest neighbor and meta-heuristic algorithms. In: 2016 IEEE 6th International Conference on Advanced Computing (IACC), pp. 250–255. IEEE, February 2016Google Scholar
- 4.Chen, X.W.: Gene selection for cancer classification using bootstrapped genetic algorithms and support vector machines. In: Proceedings of the 2003 IEEE Bioinformatics Conference. CSB 2003 on Computational Systems Bioinformatics, CSB 2003, pp. 504–505. IEEE, August 2003Google Scholar
- 5.Alba, E., Garcia-Nieto, J., Jourdan, L., Talbi, E.G.: Gene selection in cancer classification using PSO/SVM and GA/SVM hybrid algorithms. In: 2007 IEEE Congress on Evolutionary Computation, pp. 284–290. IEEE, September 2007Google Scholar
- 6.Alomari, O.A., Khader, A.T., Al-Betar, M.A., Abualigah, L.M.: Gene selection for cancer classification by combining minimum redundancy maximum relevancy and bat-inspired algorithm. Int. J. Data Min. Bioinform. 19(1), 32–51 (2017)CrossRefGoogle Scholar
- 7.Moosa, J.M., Shakur, R., Kaykobad, M., Rahman, M.S.: Gene selection for cancer classification with the help of bees. BMC Med. Genomics 9(2), 47 (2016)CrossRefGoogle Scholar
- 8.Kar, S., Sharma, K.D., Maitra, M.: Gene selection from microarray gene expression data for classification of cancer subgroups employing PSO and adaptive K-nearest neighborhood technique. Expert Syst. Appl. 42(1), 612–627 (2015)CrossRefGoogle Scholar
- 9.Dashtban, M., Balafar, M., Suravajhala, P.: Gene selection for tumor classification using a novel bio-inspired multi-objective approach. Genomics 110(1), 10–17 (2018)CrossRefGoogle Scholar
- 10.Pyingkodi, M., Thangarajan, R.: Informative gene selection for cancer classification with microarray data using a metaheuristic framework. Asian Pac. J. Cancer Prev. APJCP 19(2), 561 (2018)Google Scholar
- 11.Jana, B., Mitra, S., Acharyya, S.: Repository and Mutation based Particle Swarm Optimization (RMPSO): a new PSO variant applied to reconstruction of Gene Regulatory Network. Appl. Soft Comput. 74, 330–355 (2019)CrossRefGoogle Scholar
- 12.Ching, T., et al.: Genome-wide hypermethylation coupled with promoter hypomethylation in the chorioamniotic membranes of early onset pre-eclampsia. Mol. Hum. Reprod. 20(9), 885–904 (2014)CrossRefGoogle Scholar
- 13.Vaiman, D., Miralles, F.: An integrative analysis of preeclampsia based on the construction of an extended composite network featuring protein-protein physical interactions and transcriptional relationships. PLoS ONE 11(11), e0165849 (2016)CrossRefGoogle Scholar