An Ant Colony Optimization and Tabu List Approach to the Detection of Gene-Gene Interactions in Genome-Wide Association Studies [Research Frontier]

Abstract

In this paper, a novel ant colony optimisation and tabu list approach for the discovery of gene-gene interactions in genome-wide association study data is proposed. The method is tested on a number of diseases drawn from the large established database, the Wellcome Trust Case Control Consortium which contains hundreds of thousands of small DNA changes known as single nucleotide polymorphisms. To analyse full scale genome-wide association study data, the standard ant colony optimisation algorithm has been adapted, with tournament path selection, a subset based approach, and tabu list included in the algorithm. These modifications, in addition to the use of a statistical test of significance of single nucleotide polymorphism interactions as a fitness function, greatly increase execution speeds and permit the discovery of combinations of single nucleotide polymorphisms that can discriminate cases and controls. The methodology is applied to several large-scale genome-wide association study disease datasets namely, inflammatory bowel disease, rheumatoid arthritis, type I diabetes and type II diabetes patients to discover putative gene-gene interactions in reasonable time on modest hardware.

A Review of Ant Colony Optimization Based Methods for Detecting Epistatic Interactions

“…2) TABU SEARCH Sapin et al [34] incorporated tabu search into path selection strategy to prevent the modified ACO algorithm from continually selecting SNPs displaying strong main effects. The modification of this ACO_Tabu method can be described as follows.…”

“…However, for large scale data sets, especially those in GWAS, the roulette wheel selection strategy slows down the convergence speed since each SNP only owns a very small segment of the roulette wheel, resulting in this strategy tending to a random selection. In order to overcome this limitation, Sapin et al [34]- [38] adopted tournament selection strategy to guide ants selecting SNPs. Firstly, nts SNPs are randomly selected to form a tournament, where nts is the tournament size specified by users, which can be adjusted to alter the convergence speed.…”

“…As a matter of fact, this variant, as well as another frequently used variant in methods [34]- [39], which was defined as…”

A Survey on Swarm Intelligence Search Methods Dedicated to Detection of High-Order SNP Interactions

“…Sapin et al employed the ACO algorithm to discover small numbers of SNPs on a genome-wide scale and then evaluated the association of these SNPs with phenotype using a decision tree or contingency table model [35]. In addition, they incorporated the tournament path selection and tabu list into ACO for the analysis of GWAS [36]. Yuan et al introduced a fast adoptive ACO algorithm (FAACOSE) to detect SNP interactions [37].…”

DualWMDR: Detecting epistatic interaction with dual screening and multifactor dimensionality reduction

“…Filter-based methods aim to select a subset of SNPs as a candidate set for interaction tests on the basis of existing biological knowledge (i.e., databases of pathways and protein-protein interactions; Ritchie, 2011;Turner et al, 2011), statistical features (i.e., marginal effects; Ma et al, 2012; and genotype frequencies; Ackermann & Beyer, 2012;Guo, Meng, Yu, & Pan, 2014;Xie et al, 2011) or fast algorithms (Cao, Yu, Liu, Jia, & Wang, 2018;Liu, Yu, Jiang, & Wang, 2017;Yang et al, 2008). Wrapper-based methods apply random sampling procedures (i.e., Markov chain Monte Carlo, MCMC; Zhang & Liu, 2007) and the Gibbs sampling; Tang, Wu, Jiang, & Li, 2009), heuristic algorithms (i.e., ant colony optimization, ACO; Sapin, Keedwell, & Frayling, 2015;Wang, Liu, Robbins, & Rekaya, 2010) and differential evolution, DE; C.-H. Yang et al, 2017) or machine learning algorithm (i.e., random forest, RF; Schwarz, König, & Ziegler, 2010;Yoshida & Koike, 2011), support vector machine (SVM; Chen et al, 2008;Marvel & Motsinger-Reif, 2012) and neural network (NN; Uppu et al, 2016) to search the space of interactions. Compared to wrapper-based methods, besides the apparent advantage of speed, filter-based methods have greater power and improved biological interpretation (Wei, Hemani, & Haley, 2014).…”