Bayesian neural networks for detecting epistasis in genetic association studies.
Ontology highlight
ABSTRACT:
SUBMITTER: Beam AL
PROVIDER: S-EPMC4256933 | biostudies-literature | 2014 Nov
REPOSITORIES: biostudies-literature
Publications
Bayesian neural networks for detecting epistasis in genetic association studies.
Beam Andrew L AL Motsinger-Reif Alison A Doyle Jon J
BMC bioinformatics 20141121
<h4>Background</h4>Discovering causal genetic variants from large genetic association studies poses many difficult challenges. Assessing which genetic markers are involved in determining trait status is a computationally demanding task, especially in the presence of gene-gene interactions.<h4>Results</h4>A non-parametric Bayesian approach in the form of a Bayesian neural network is proposed for use in analyzing genetic association studies. Demonstrations on synthetic and real data reveal they ar ...[more]
Similar Datasets
Project description:BackgroundEpistasis is recognized ubiquitous in the genetic architecture of complex traits such as disease susceptibility. Experimental studies in model organisms have revealed extensive evidence of biological interactions among genes. Meanwhile, statistical and computational studies in human populations have suggested non-additive effects of genetic variation on complex traits. Although these studies form a baseline for understanding the genetic architecture of complex traits, to date they have only considered interactions among a small number of genetic variants. Our goal here is to use network science to determine the extent to which non-additive interactions exist beyond small subsets of genetic variants. We infer statistical epistasis networks to characterize the global space of pairwise interactions among approximately 1500 Single Nucleotide Polymorphisms (SNPs) spanning nearly 500 cancer susceptibility genes in a large population-based study of bladder cancer.ResultsThe statistical epistasis network was built by linking pairs of SNPs if their pairwise interactions were stronger than a systematically derived threshold. Its topology clearly differentiated this real-data network from networks obtained from permutations of the same data under the null hypothesis that no association exists between genotype and phenotype. The network had a significantly higher number of hub SNPs and, interestingly, these hub SNPs were not necessarily with high main effects. The network had a largest connected component of 39 SNPs that was absent in any other permuted-data networks. In addition, the vertex degrees of this network were distinctively found following an approximate power-law distribution and its topology appeared scale-free.ConclusionsIn contrast to many existing techniques focusing on high main-effect SNPs or models of several interacting SNPs, our network approach characterized a global picture of gene-gene interactions in a population-based genetic data. The network was built using pairwise interactions, and its distinctive network topology and large connected components indicated joint effects in a large set of SNPs. Our observations suggested that this particular statistical epistasis network captured important features of the genetic architecture of bladder cancer that have not been described previously.
| S-EPMC3215301 | biostudies-literature
Project description:Epistasis, commonly defined as the interaction between multiple genes, is an important genetic component underlying phenotypic variation. Many statistical methods have been developed to model and identify epistatic interactions between genetic variants. However, because of the large combinatorial search space of interactions, most epistasis mapping methods face enormous computational challenges and often suffer from low statistical power due to multiple test correction. Here, we present a novel, alternative strategy for mapping epistasis: instead of directly identifying individual pairwise or higher-order interactions, we focus on mapping variants that have non-zero marginal epistatic effects-the combined pairwise interaction effects between a given variant and all other variants. By testing marginal epistatic effects, we can identify candidate variants that are involved in epistasis without the need to identify the exact partners with which the variants interact, thus potentially alleviating much of the statistical and computational burden associated with standard epistatic mapping procedures. Our method is based on a variance component model, and relies on a recently developed variance component estimation method for efficient parameter inference and p-value computation. We refer to our method as the "MArginal ePIstasis Test", or MAPIT. With simulations, we show how MAPIT can be used to estimate and test marginal epistatic effects, produce calibrated test statistics under the null, and facilitate the detection of pairwise epistatic interactions. We further illustrate the benefits of MAPIT in a QTL mapping study by analyzing the gene expression data of over 400 individuals from the GEUVADIS consortium.
| S-EPMC5550000 | biostudies-literature
Project description:Gene-gene epistatic interactions likely play an important role in the genetic basis of many common diseases. Recently, machine-learning and data mining methods have been developed for learning epistatic relationships from data. A well-known combinatorial method that has been successfully applied for detecting epistasis is Multifactor Dimensionality Reduction (MDR). Jiang et al. created a combinatorial epistasis learning method called BNMBL to learn Bayesian network (BN) epistatic models. They compared BNMBL to MDR using simulated data sets. Each of these data sets was generated from a model that associates two SNPs with a disease and includes 18 unrelated SNPs. For each data set, BNMBL and MDR were used to score all 2-SNP models, and BNMBL learned significantly more correct models. In real data sets, we ordinarily do not know the number of SNPs that influence phenotype. BNMBL may not perform as well if we also scored models containing more than two SNPs. Furthermore, a number of other BN scoring criteria have been developed. They may detect epistatic interactions even better than BNMBL.Although BNs are a promising tool for learning epistatic relationships from data, we cannot confidently use them in this domain until we determine which scoring criteria work best or even well when we try learning the correct model without knowledge of the number of SNPs in that model.We evaluated the performance of 22 BN scoring criteria using 28,000 simulated data sets and a real Alzheimer's GWAS data set. Our results were surprising in that the Bayesian scoring criterion with large values of a hyperparameter called ? performed best. This score performed better than other BN scoring criteria and MDR at recall using simulated data sets, at detecting the hardest-to-detect models using simulated data sets, and at substantiating previous results using the real Alzheimer's data set.We conclude that representing epistatic interactions using BN models and scoring them using a BN scoring criterion holds promise for identifying epistatic genetic variants in data. In particular, the Bayesian scoring criterion with large values of a hyperparameter ? appears more promising than a number of alternatives.
| S-EPMC3080825 | biostudies-other
Project description:BackgroundGenome-wide association studies (GWAS) do not provide a full account of the heritability of genetic diseases since gene-gene interactions, also known as epistasis are not considered in single locus GWAS. To address this problem, a considerable number of methods have been developed for identifying disease-associated gene-gene interactions. However, these methods typically fail to identify interacting markers explaining more of the disease heritability over single locus GWAS, since many of the interactions significant for disease are obscured by uninformative marker interactions e.g., linkage disequilibrium (LD).ResultsIn this study, we present a novel SNP interaction prioritization algorithm, named iLOCi (Interacting Loci). This algorithm accounts for marker dependencies separately in case and control groups. Disease-associated interactions are then prioritized according to a novel ranking score calculated from the difference in marker dependencies for every possible pair between case and control groups. The analysis of a typical GWAS dataset can be completed in less than a day on a standard workstation with parallel processing capability. The proposed framework was validated using simulated data and applied to real GWAS datasets using the Wellcome Trust Case Control Consortium (WTCCC) data. The results from simulated data showed the ability of iLOCi to identify various types of gene-gene interactions, especially for high-order interaction. From the WTCCC data, we found that among the top ranked interacting SNP pairs, several mapped to genes previously known to be associated with disease, and interestingly, other previously unreported genes with biologically related roles.ConclusioniLOCi is a powerful tool for uncovering true disease interacting markers and thus can provide a more complete understanding of the genetic basis underlying complex disease. The program is available for download at http://www4a.biotec.or.th/GI/tools/iloci.
| S-EPMC3521387 | biostudies-literature
Project description:Genetic mutations may interact to increase the risk of human complex diseases. Mapping of multiple interacting disease loci in the human genome has recently shown promise in detecting genes with little main effects. The power of interaction association mapping, however, can be greatly influenced by the set of single nucleotide polymorphism (SNP) genotyped in a case-control study. Previous imputation methods only focus on imputation of individual SNPs without considering their joint distribution of possible interactions. We present a new method that simultaneously detects multilocus interaction associations and imputes missing SNPs from a full Bayesian model. Our method treats both the case-control sample and the reference data as random observations. The output of our method is the posterior probabilities of SNPs for their marginal and interacting associations with the disease. Using simulations, we show that the method produces accurate and robust imputation with little overfitting problems. We further show that, with the type I error rate maintained at a common level, SNP imputation can consistently and sometimes substantially improve the power of detecting disease interaction associations. We use a data set of inflammatory bowel disease to demonstrate the application of our method.
| S-EPMC3062153 | biostudies-literature
Project description:MotivationLarge-scale genetic association studies are carried out with the hope of discovering single nucleotide polymorphisms involved in the etiology of complex diseases. There are several existing methods in the literature for performing this kind of analysis for case-control studies, but less work has been done for prospective cohort studies. We present a Bayesian method for linking markers to censored survival outcome by clustering haplotypes using gene trees. Coalescent-based approaches are promising for LD mapping, as the coalescent offers a good approximation to the evolutionary history of mutations.ResultsWe compare the performance of the proposed method in simulation studies to the univariate Cox regression and to dimension reduction methods, and we observe that it performs similarly in localizing the causal site, while offering a clear advantage in terms of false positive associations. Moreover, it offers computational advantages. Applying our method to a real prospective study, we observe potential association between candidate ABC transporter genes and epilepsy treatment outcomes.AvailabilityR codes are available upon request.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC2530885 | biostudies-literature
Project description:BackgroundThe difficulty in elucidating the genetic basis of complex diseases roots in the many factors that can affect the development of a disease. Some of these genetic effects may interact in complex ways, proving undetectable by current single-locus methodology.ResultsWe have developed an analysis tool called Hypothesis Free Clinical Cloning (HFCC) to search for genome-wide epistasis in a case-control design. HFCC combines a relatively fast computing algorithm for genome-wide epistasis detection, with the flexibility to test a variety of different epistatic models in multi-locus combinations. HFCC has good power to detect multi-locus interactions simulated under a variety of genetic models and noise conditions. Most importantly, HFCC can accomplish exhaustive genome-wide epistasis search with large datasets as demonstrated with a 400,000 SNP set typed on a cohort of Parkinson's disease patients and controls.ConclusionWith the current availability of genetic studies with large numbers of individuals and genetic markers, HFCC can have a great impact in the identification of epistatic effects that escape the standard single-locus association analyses.
| S-EPMC2533022 | biostudies-literature
Project description:The conceptual foundation of the genome-wide association study (GWAS) has advanced unchecked since its conception. A revision might seem premature as the potential of GWAS has not been fully realized. Multiple technical and practical limitations need to be overcome before GWAS can be fairly criticized. But with the completion of hundreds of studies and a deeper understanding of the genetic architecture of disease, warnings are being raised. The results compiled to date indicate that risk-associated variants lie predominantly in noncoding regions of the genome. Additionally, alternative methodologies are uncovering large and heterogeneous sets of rare variants underlying disease. The fear is that, even in its fulfillment, the current GWAS paradigm might be incapable of dissecting all kinds of phenotypes. In the following text, we review several initiatives that aim to overcome these limitations. The overarching theme of these studies is the inclusion of biological knowledge to both the analysis and interpretation of genotyping data. GWAS is uninformed of biology by design and although there is some virtue in its simplicity, it is also its most conspicuous deficiency. We propose a framework in which to integrate these novel approaches, both empirical and theoretical, in the form of a genome-wide regulatory network (GWRN). By processing experimental data into networks, emerging data types based on chromatin immunoprecipitation are made computationally tractable. This will give GWAS re-analysis efforts the most current and relevant substrates, and root them firmly on our knowledge of human disease.
| S-EPMC3062944 | biostudies-literature
Project description: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.
| S-EPMC3194240 | biostudies-literature
Project description:MotivationEpistasis may play an etiologic role in complex diseases, but research has been hindered because identification of interactions among sets of single nucleotide polymorphisms (SNPs) requires exploration of immense search spaces. Current approaches using nuclear families accommodate at most several hundred candidate SNPs.ResultsGADGETS detects epistatic SNP-sets by applying a genetic algorithm to case-parent or case-sibling data. To allow for multiple epistatic sets, island subpopulations of SNP-sets evolve separately under selection for evident joint relevance to disease risk. The software evaluates the identified SNP-sets via permutation testing and provides graphical visualization. GADGETS correctly identified epistatic SNP-sets in realistically simulated case-parent triads with 10 000 candidate SNPs, far more SNPs than competitors can handle, and it outperformed competitors in simulations with many fewer SNPs. Applying GADGETS to family-based oral-clefting data from dbGaP identified SNP-sets with possible epistatic effects on risk.Availability and implementationGADGETS is part of the epistasisGA package at https://github.com/mnodzenski/epistasisGA.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC10060691 | biostudies-literature