Bayesian Variable Selection in Structured High-Dimensional Covariate Spaces With Applications in Genomics

Li, Fan; Zhang, Nancy R.

doi:10.1198/jasa.2010.tm08177

Cited by 169 publications

(189 citation statements)

References 29 publications

(36 reference statements)

Supporting

Mentioning

182

Contrasting

Order By: Relevance

“…This work was later extended to consider longitudinal behavior of genes to analyze time course gene expression data 64 . Bayesian linear regression models were developed to use the dependence structure of transcription factors and/or genes in the network to aid gene selection [65][66] . Network-based penalized regression model was developed for subnetwork selection 67 .…”

Section: Testing On the Networkmentioning

confidence: 99%

Analyzing LC/MS Metabolic Profiling Data in the Context of Existing Metabolic Networks

Yu¹,

Bai²

2012

CMB

View full text Add to dashboard Cite

Metabolic profiling is the unbiased detection and quantification of low molecular-weight metabolites in a living system. It is rapidly developing in biological and translational research, contributing to disease mechanism elucidation, environmental chemical surveillance, biomarker detection, and health outcome prediction. Recent developments in experimental and computational technology allow more and more known metabolites to be detected and quantified from complex samples. As the coverage of the metabolic network improves, it has become feasible to examine metabolic profiling data from a systems perspective, i.e. interpreting the data and performing statistical inference in the context of pathways and genome-scale metabolic networks. Recently a number of methods have been developed in this area, and much improvement in algorithms and databases are still needed. In this review, we survey some methods for the analysis of metabolic profiling data based on metabolic networks.

show abstract

Section: Testing On the Networkmentioning

confidence: 99%

Analyzing LC/MS Metabolic Profiling Data in the Context of Existing Metabolic Networks

Yu¹,

Bai²

2012

CMB

View full text Add to dashboard Cite

show abstract

“…Therefore, for a large dataset residing on secondary storage, MCMC processing can be extremely slow. We study how to accelerate the Gibbs sampler, a common MCMC method used to perform variable selection in linear regression [George and McCulloch 1993;Li and Zhang 2010]. With that motivation in mind, we introduce a fast Gibbs sampler for variable selection, based on a combination of Gaussian and noninformative priors, exploiting augmented sufficient statistics, hashing of highly probable variable combinations, and block-based matrices.…”

Section: Introductionmentioning

confidence: 99%

Bayesian Variable Selection in Linear Regression in One Pass for Large Datasets

Ordóñez

Garcia-Alvarado

Baladandayuthapani³

2014

ACM Trans. Knowl. Discov. Data

View full text Add to dashboard Cite

Bayesian models are generally computed with Markov Chain Monte Carlo (MCMC) methods. The main disadvantage of MCMC methods is the large number of iterations they need to sample the posterior distributions of model parameters, especially for large datasets. On the other hand, variable selection remains a challenging problem due to its combinatorial search space, where Bayesian models are a promising solution.In this work, we study how to accelerate Bayesian model computation for variable selection in linear regression. We propose a fast Gibbs sampler algorithm, a widely used MCMC method that incorporates several optimizations. We use a Zellner prior for the regression coefficients, an improper prior on variance, and a conjugate prior Gaussian distribution, which enable dataset summarization in one pass, thus exploiting an augmented set of sufficient statistics. Thereafter, the algorithm iterates in main memory. Sufficient statistics are indexed with a sparse binary vector to efficiently compute matrix projections based on selected variables. Discovered variable subsets probabilities, selecting and discarding each variable, are stored on a hash table for fast retrieval in future iterations. We study how to integrate our algorithm into a Database Management System (DBMS), exploiting aggregate User-Defined Functions for parallel data summarization and stored procedures to manipulate matrices with arrays. An experimental evaluation with real datasets evaluates accuracy and time performance, comparing our DBMS-based algorithm with the R package. Our algorithm is shown to produce accurate results, scale linearly on dataset size, and run orders of magnitude faster than the R package.

show abstract

“…A Markov chain Monte Carlo (MCMC) method for BVS is proposed by George and McCulloch (1993), Ghosal (1999), and Jiang (2007) studied asymptotic properties of the posterior distribution of when the number of covariates diverges, and BVS approaches have been applied to various problems (Li and Zhang, 2010;Richardson et al, 2010).…”

Section: Introductionmentioning

confidence: 99%