Display options
Share it on

Commun Stat Simul Comput. 2017;46(7):5070-5084. doi: 10.1080/03610918.2016.1143103. Epub 2017 Feb 28.

An efficient Bayesian approach for Gaussian Bayesian network structure learning.

Communications in statistics: Simulation and computation

Shengtong Han, Hongmei Zhang, Ramin Homayouni, Wilfried Karmaus

Affiliations

  1. School of Public Health, Bioinformatics Program and Center for Translational Informatics, University of Memphis Memphis, TN [email protected].

PMID: 30918419 PMCID: PMC6433420 DOI: 10.1080/03610918.2016.1143103

Abstract

This article proposes a Bayesian computing algorithm to infer Gaussian directed acyclic graphs (DAG's). It has the ability of escaping local modes and maintaining adequate computing speed compared to existing methods. Simulations demonstrated that the proposed algorithm has low false positives and false negatives in comparison to an algorithm applied to DAG's. We applied the algorithm to an epigenetic data set to infer DAG's for smokers and non-smokers.

Keywords: DNA methylation; Gaussian DAG; MCMC

References

  1. J Allergy Clin Immunol. 1992 Aug;90(2):235-41 - PubMed
  2. Biometrika. 2010 Sep;97(3):519-538 - PubMed
  3. Environ Health Perspect. 2012 Oct;120(10):1425-31 - PubMed
  4. Biometrics. 2013 Jun;69(2):478-87 - PubMed
  5. Clin Epigenetics. 2013 Oct 11;5(1):19 - PubMed
  6. PLoS One. 2014 Dec 31;9(12):e115806 - PubMed

Publication Types

Grant support