Feature Selection for Detecting Gene-Gene Interactions in Genome-Wide Association Studies
Disease association studies aim at finding the genetic variations underlying complex human diseases in order to better understand the etiology of the disease and to provide better diagnoses, treatment, and even prevention. The non-linear interactions among multiple genetic factors play an important role in finding those genetic variations, but have not always been taken fully into account. This is due to the fact that searching combinations of interacting genetic factors becomes inhibitive as its complexity grows exponentially with the size of data. It is especially challenging for genome-wide association studies (GWAS) where typically more than a million single-nucleotide polymorphisms (SNPs) are under consideration. Dimensionality reduction is thus needed to allow us to investigate only a subset of genetic attributes that most likely have interaction effects. In this article, we conduct a comprehensive study by examining six widely used feature selection methods in machine learning for filtering interacting SNPs rather than the ones with strong individual main effects. Those six feature selection methods include chi-square, logistic regression, odds ratio, and three Relief-based algorithms. By applying all six feature selection methods to both a simulated and a real GWAS datasets, we report that Relief-based methods perform the best in filtering SNPs associated with a disease in terms of strong interaction effects.
KeywordsFeature selection Relief algorithms Information gain Gene-gene interactions Genome-wide association studies
This research was supported by Newfoundland and Labrador Research and Development Corporation (RDC) Ignite Grant 5404.1942.101 and the Natural Science and Engineering Research Council (NSERC) of Canada Discovery Grant RGPIN-2016-04699 to TH.
- 1.Wellcome Trust Case Control Consortium, et al.: Genome-wide association study of 14,000 cases of seven common diseases and 3,000 shared controls. Nature 447(7145), 661 (2007)Google Scholar
- 3.The 1000 Genomes Project Consortium, et al.: A map of human genome variation from population scale sequencing. Nature 467(7319), 1061 (2010)Google Scholar
- 5.Hu, T., Andrew, A.S., Karagas, M.R., Moore, J.H.: Statistical epistasis networks reduce the computational complexity of searching three-locus genetic models. Proc. Pac. Symp. Biocomput. 18, 397–408 (2013)Google Scholar
- 8.Yu, L., Liu, H.: Feature selection for high-dimensional data: a fast correlation-based filter solution. ICML 3, 856–863 (2003)Google Scholar
- 11.Freitas, A.A.: Data Mining and Knowledge Discovery with Evolutionary Algorithms. Springer Science & Business Media, Heidelberg (2013)Google Scholar
- 23.Fan, R., Zhong, M., Wang, S., Zhang, Y., Andrew, A., Karagas, M., Chen, H., Amos, C.I., Xiong, M., Moore, J.H.: Entropy-based information gain approaches to detect and to characterize gene-gene and gene-environment interactions/correlations of complex diseases. Genet. Epidemiol. 35(7), 706–721 (2011)CrossRefGoogle Scholar
- 28.Kira, K., Rendell, L.A.: A practical approach to feature selection. In: Proceedings of the Ninth International Workshop on Machine Learning, pp. 249–256 (1992)Google Scholar
- 34.Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)MathSciNetzbMATHGoogle Scholar