Limits...
Bayesian neural networks for detecting epistasis in genetic association studies.

Beam AL, Motsinger-Reif A, Doyle J - BMC Bioinformatics (2014)

Bottom Line: By using graphics processing units (GPUs) the time needed to build these models is decreased by several orders of magnitude.In comparison with commonly used approaches for detecting interactions, Bayesian neural networks perform very well across a broad spectrum of possible genetic relationships.The proposed framework is shown to be a powerful method for detecting causal SNPs while being computationally efficient enough to handle large datasets.

View Article: PubMed Central - PubMed

Affiliation: Center for Biomedical Informatics, Harvard Medical School, Boston, MA, USA. Andrew_Beam@hms.harvard.edu.

ABSTRACT

Background: 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.

Results: 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 are able to efficiently and accurately determine which variants are involved in determining case-control status. By using graphics processing units (GPUs) the time needed to build these models is decreased by several orders of magnitude. In comparison with commonly used approaches for detecting interactions, Bayesian neural networks perform very well across a broad spectrum of possible genetic relationships.

Conclusions: The proposed framework is shown to be a powerful method for detecting causal SNPs while being computationally efficient enough to handle large datasets.

Show MeSH
Entropy network for the Top 5 SNPs selected by the BNN.
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
getmorefigures.php?uid=PMC4256933&req=5

Fig7: Entropy network for the Top 5 SNPs selected by the BNN.

Mentions: Here we explore the types of interactions between the top 5 SNPs from the real data analysis using an entropy web. The purpose of the interaction web is to visually display the nature of the interactions (redundant, additive, or synergistic) amongst the 5 SNPs. The colors used comprise a spectrum of colors representing a continuum from Synergy to Redundancy. The colors range from red representing a high degree of synergy (positive information gain), orange a lesser degree, and gold representing the midway point between synergy and redundancy. On the redundancy end of the spectrum, the highest degree is represented by the blue color (negative information gain) with a lesser degree represented by green. The numbers indicate the entropy explained by each of the variables or variable combinations, with the weight of connections proportional to the strength of the signal. Positive numbers indicate synergy between variables, while negative number indicate redundancy. This information is displayed in FigureĀ 7. The figure indicates that several of the SNPs are indeed weakly interacting with one another (rs9327930 with rs1378124 and rs9327930 with rs966414), giving confidence that the method is capable of detecting relevant SNPs in the presence of interactions.Figure 7


Bayesian neural networks for detecting epistasis in genetic association studies.

Beam AL, Motsinger-Reif A, Doyle J - BMC Bioinformatics (2014)

Entropy network for the Top 5 SNPs selected by the BNN.
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
Show All Figures
getmorefigures.php?uid=PMC4256933&req=5

Fig7: Entropy network for the Top 5 SNPs selected by the BNN.
Mentions: Here we explore the types of interactions between the top 5 SNPs from the real data analysis using an entropy web. The purpose of the interaction web is to visually display the nature of the interactions (redundant, additive, or synergistic) amongst the 5 SNPs. The colors used comprise a spectrum of colors representing a continuum from Synergy to Redundancy. The colors range from red representing a high degree of synergy (positive information gain), orange a lesser degree, and gold representing the midway point between synergy and redundancy. On the redundancy end of the spectrum, the highest degree is represented by the blue color (negative information gain) with a lesser degree represented by green. The numbers indicate the entropy explained by each of the variables or variable combinations, with the weight of connections proportional to the strength of the signal. Positive numbers indicate synergy between variables, while negative number indicate redundancy. This information is displayed in FigureĀ 7. The figure indicates that several of the SNPs are indeed weakly interacting with one another (rs9327930 with rs1378124 and rs9327930 with rs966414), giving confidence that the method is capable of detecting relevant SNPs in the presence of interactions.Figure 7

Bottom Line: By using graphics processing units (GPUs) the time needed to build these models is decreased by several orders of magnitude.In comparison with commonly used approaches for detecting interactions, Bayesian neural networks perform very well across a broad spectrum of possible genetic relationships.The proposed framework is shown to be a powerful method for detecting causal SNPs while being computationally efficient enough to handle large datasets.

View Article: PubMed Central - PubMed

Affiliation: Center for Biomedical Informatics, Harvard Medical School, Boston, MA, USA. Andrew_Beam@hms.harvard.edu.

ABSTRACT

Background: 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.

Results: 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 are able to efficiently and accurately determine which variants are involved in determining case-control status. By using graphics processing units (GPUs) the time needed to build these models is decreased by several orders of magnitude. In comparison with commonly used approaches for detecting interactions, Bayesian neural networks perform very well across a broad spectrum of possible genetic relationships.

Conclusions: The proposed framework is shown to be a powerful method for detecting causal SNPs while being computationally efficient enough to handle large datasets.

Show MeSH