Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2015 Dec;9(6):218-25.
doi: 10.1049/iet-syb.2015.0017.

Ant colony optimisation of decision tree and contingency table models for the discovery of gene-gene interactions

Emmanuel Sapin  1 , Ed Keedwell  2 , Tim Frayling  3
Affiliations
Review

Ant colony optimisation of decision tree and contingency table models for the discovery of gene-gene interactions

Emmanuel Sapin et al. IET Syst Biol. 2015 Dec.

Abstract

In this study, ant colony optimisation (ACO) algorithm is used to derive near-optimal interactions between a number of single nucleotide polymorphisms (SNPs). This approach is used to discover small numbers of SNPs that are combined into a decision tree or contingency table model. The ACO algorithm is shown to be very robust as it is proven to be able to find results that are discriminatory from a statistical perspective with logical interactions, decision tree and contingency table models for various numbers of SNPs considered in the interaction. A large number of the SNPs discovered here have been already identified in large genome-wide association studies to be related to type II diabetes in the literature, lending additional confidence to the results.

PubMed Disclaimer

Figures

Fig. 1
Fig. 1
The ACO algorithm described in [28]
Fig. 2
Fig. 2
Decision tree created with four SNPs (snp1anti, snp2anti, snp3anti and snp4anti)
Fig. 3
Fig. 3
Best decision trees the ACO algorithm has discovered on the dataset of the WTCCC over a set of 100 runs. The controls and cases are represented next to each other with the controls (cases) to the right (left). The values and expected values of positive and negative are represented next to each other with these values (expected values) to the right (left)
Fig. 4
Fig. 4
Distribution of the values of the Chi‐squared of the best association that has been discovered for each run of a set of 100 representative runs of the algorithm
Fig. 5
Fig. 5
Distribution of cases and controls for each genotype combination from two SNPs leading to the best result of the ACO algorithm. The controls and cases are represented next to each other with the controls (cases) to the right (left). The values of positive and negative are darkly shaded, whereas the expected values are lightly shaded
Fig. 6
Fig. 6
Distribution of cases and controls for each genotype combination from two SNPs leading to the best result of the ACO algorithm. The controls and cases are represented next to each other with the controls (cases) to the right (left). The values of positive and negative are darkly shaded, whereas the expected values are lightly shaded
See this image and copyright information in PMC

References

    1. Klein, R. , Zeiss, C. , Chew, E. , et al.: ‘Complement factor h polymorphism in age‐related macular degeneration’, Sci. 15 April 2005, 2005, 308, pp. 385–389 - PMC - PubMed
    1. Johnson, A. , O'Donnell, C. : ‘An open access database of genome‐wide association results’, BMC Med. Genet., 2009, 10, (1), 6 (doi: 10.1186/1471-2350-10-6) - DOI - PMC - PubMed
    1. Wright, S. : ‘Genic and organismic selection’, Evolution, 1980, 34, pp. 825–843 (doi: 10.2307/2407990) - DOI - PubMed
    1. Oki, N. : ‘On considering epistasis in genome wide association studies’ (North Carolina State University, North Carolina, USA: 2012)
    1. The Wellcome Trust Case Control Consortium : ‘Genome‐wide association study of 14,000 cases of seven common diseases and 3000 shared controls’, Nature, 2007, 447, pp. 661–978 (doi: 10.1038/nature05911) - DOI - PMC - PubMed

Publication types

LinkOut - more resources