bNEAT: a Bayesian network method for detecting epistatic interactions in genome-wide association studies

Abstract

BackgroundDetecting epistatic interactions plays a significant role in improving pathogenesis, prevention, diagnosis and treatment of complex human diseases. A recent study in automatic detection of epistatic interactions shows that Markov Blanket-based methods are capable of finding genetic variants strongly associated with common diseases and reducing false positives when the number of instances is large. Unfortunately, a typical dataset from genome-wide association studies consists of very limited number of examples, where current methods including Markov Blanket-based method may perform poorly.ResultsTo address small sample problems, we propose a Bayesian network-based approach (bNEAT) to detect epistatic interactions. The proposed method also employs a Branch-and-Bound technique for learning. We apply the proposed method to simulated datasets based on four disease models and a real dataset. Experimental results show that our method outperforms Markov Blanket-based methods and other commonly-used methods, especially when the number of samples is small.ConclusionsOur results show bNEAT can obtain a strong power regardless of the number of samples and is especially suitable for detecting epistatic interactions with slight or no marginal effects. The merits of the proposed approach lie in two aspects: a suitable score for Bayesian network structure learning that can reflect higher-order epistatic interactions and a heuristic Bayesian network structure learning method.

Large-scale gene network analysis reveals the significance of extracellular matrix pathway and homeobox genes in acute myeloid leukemia: an introduction to the Pigengene package and its applications

“…We hypothesized that gene network analysis addresses both of the above challenges because it models the interactions between genes in a comprehensive structure [20, 21] (Additional file 1: Note S1). Recently, Liu reviewed the computational methods that employ a gene network approach to identify biomarkers from high-throughput data [22].…”

A PLSPM-Based Test Statistic for Detecting Gene-Gene Co-Association in Genome-Wide Association Study with Case-Control Design

“…Many methods have been developed for constructing the genetic network, such as Bayesian network [36], Gaussian network [37], and Boolean network [38]. In these genetic networks for GWAS with case-control design, an ‘edge’ between any two nodes indicates that the joint effects of the two genes on target trait or phenotype would be different between controls and cases, which implies the co-association (or interaction) between the two genes.…”

Verification of Three-Phase Dependency Analysis Bayesian Network Learning Method for Maize Carotenoid Gene Mining

“…( 2) Mathematical and Statistical Methods . In recent years, some mathematical and statistical methods are used to study the genetic loci for specific phenotypic traits, such as using linear regression method for the detection of cancer sites [ 5 ], using structural equation model to detect the effects of body size and obesity in mice [ 6 ], using ordinal regression for the detection of multiple phenotypic loci [ 7 ], and using logistic regression to detect the interaction between SNP (Single Nucleotide Polymorphism) loci associated with diseases [ 8 , 9 ]. Dimensionality Reduction Multifactor (MDR) can detect the interaction between multiple genetic loci and their association with phenotypic traits [ 10 ].…”