SEE: a novel multi-objective evolutionary algorithm for identifying SNP epistasis in genome-wide association studies

Abstract

Although genome-wide association studies play an increasingly important role in identifying causes of complex diseases, detecting SNP epistasis in these studies is a computational challenge. The existing methods are usually based on a single-correlation model between SNP combinations and phenotype and their performance is often unsatisfactory. The highest average power of the existing methods is 0.58 on DME models and 0.97 on DNME models. The highest average F-measure of the existing methods is 0.44 on DME models and 0.90 on DNME models. The lowest average computation time (second) of the existing methods is 2.12 on DME models and 2.09 on DNME models. In this work, a novel multi-objective evolutionary algorithm named SEE is presented for identifying SNP epistasis. In SEE, eight evolution objectives are successfully integrated to measure the association between SNP combinations and phenotype. SEE uses a novel evolutionary strategy based on sort, exploration and exploitation. SEE was compared with other existing methods using 72 simulated datasets. The average power of SEE is 0.71 with DME models and 0.99 with DNME models. The average F-measure of SEE is 0.68 with DME models and 0.99 with DNME models. The average computation time of SEE is 0.21 with DME models and 0.40 with DNME models. It is indicated that SEE outperforms other algorithms in both F-measure and computation time. It was then utilized to analyze real data obtained from the Wellcome Trust Case Control Consortium. Availability and Implementation: SEE is freely available at https://github.com/sunliyan0000/SEE.

SHEIB-AGM: A Novel Stochastic Approach for Detecting High-Order Epistatic Interactions Using Bioinformation With Automatic Gene Matrix in Genome-Wide Association Studies

“…The computation complexity seems to be very high, but most of the operations are Boolean logic operations, so the speed is very fast. The speed improvement of the storage structure and Boolean operation has been proved in other studies [29], [30], [33].…”

“…In recent years, numerous methods have been proposed for detecting epistatic interactions [21]- [30]. MDR (multifactordimensionality reduction) [21] is a method for reducing the dimensionality of multilocus information to improve the identification of polymorphism combinations associated with disease risk.…”

“…It uses harmony search with five objective functions. SEE [30] is a multi-objective evolutionary algorithm that uses eight evolution objectives. Four of these objectives are widely used to measure the relationship between SNP combinations and phenotype in GWAS.…”

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

“…In recent years, multi-objective optimization algorithms that are used to enhance the identification power of the SNP interaction have been adopted to detect various SNP interactions [24], [57]; however, for disease models without marginal effects, the performance of these algorithms is still not satisfactory. The goal of a multi-objective algorithm is to find a set of Pareto-optimal solutions (nondominated solutions), each of which satisfies the objectives at an acceptable level without being dominated by any other solution.…”

“…It uses MDR as an objective function, conducts the search based on an opportunistic evolution strategy to maximize the efficiency, evolves candidate solutions on distributed computing nodes, and can adopt expert knowledge from any source to guide the search. Sun et al presented a multi-objective evolution algorithm (SEE) to detect SNP epistasis [57]. In SEE, eight objective functions are integrated to measure the association between SNP combinations and phenotype.…”