ShrinkBayes-package: Bayesian analysis of high-dimensional omics data, either...

In markvdwiel/ShrinkBayes: Bayesian analysis of high-dimensional omics data, either Gaussian or counts

Bayesian analysis of high-dimensional omics data, either Gaussian or counts

Description

This package provides differential expression analysis for a variety of omics data, including: RNA-seq, CAGE, miRNA-seq, HT RNAi, mRNA microarray, miRNA microarray. It is particulary useful for relatively small sample sizes, because it applies Empirical Bayes-type estimation of priors for multi-parameter shrinkage to increase power and reproducibility. Mixture and nonparametric priors are accommodated. In addition, it provides Bayesian multiplicity correction, by lfdr and BFDR estimation.

Details

Package:	ShrinkBayes
Type:	Package
Version:	1.0
Date:	2012-10-15
License:	GPL

Functions:
AllComp: Creates all comparisons that do not include the baseline level from a factor object with 3 or more levels
BaselineDef: Defines the baseline level of factor variable.
BFDR: BFDR computation, one-sided, two-sided and multiple comparisons
BFUpdatePosterior:Updates posteriors for testing nested models that differ by more than one variable or simply extracts all posteriors for one particular parameter
CombinePosteriors: Combines posteriors from two models for a given parameter and, possibly, for related linear combinations.
CreateBlocks: Creates blocks of consecutives row indices from the row-dimension of a data set and a block size
FastScreenP: Screens and filters the data set using the data set
FitAllShrink: Applies inla to multiple data rows using shrinkage priors.
MixtureUpdatePrior: Replacing a one-component prior by an optimal mixture prior
MixtureUpdatePosterior: Updates posteriors from a given mixture prior
NonParaUpdatePrior: Replacing a parametric prior by an optimal non-parametric one
NonParaUpdatePosterior: Updates posteriors from a given non-parametric prior
plotPoster: Plots posterior densities
ReDefMiss: Redefines missing variables
ScreenData: Fast p-value computation for simple 2-sample or K-sample designs. To be used as an initial screen.
ShrinkBayesWrap: ShrinkBayes wrapper, apply ShrinkBayes using a one-line command
ShrinkSeq: Simultaneous shrinkage by empirically estimating multiple priors, Poisson and Negative Binomial likelihoods plus zero-inflated versions thereof
ShrinkGauss: Simultaneous shrinkage by empirically estimating multiple priors, Gaussian likelihoods
SummaryTable: Convenience function that produces a summary table
SummaryWrap: Convenience function to compute either posterior null-probabilities (lfdr) or posterior means

Data:
CAGEdata10000: A data set with 10,000 rows containing normalized counts
datsim: A simulated data set (Gaussian) with 1500 rows and 8 columns
HTRNAi: A data set with 960 rows and 6 samples containing normalized High-Throughput RNAi data (Gaussian)
mirseqnorm: A data set with 2060 rows and 55 samples containing normalized counts

Author(s)

Mark A. van de Wiel, [e-mail]

References

Van de Wiel MA, Leday GGR, Pardo L, Rue H, Van der Vaart AW, Van Wieringen WN (2012). Bayesian analysis of RNA sequencing data by estimating multiple shrinkage priors. Biostatistics.

Van de Wiel MA, De Menezes RX, Siebring-van Olst E, Van Beusechem VW (2013). Analysis of small-sample clinical genomics studies using multi-parameter shrinkage: application to high-throughput RNA interference screening. BMC Med Genom.

Van de Wiel MA, Neerincx M, Buffart TE, Sie D, Verheul HMW (2014). ShrinkBayes: a versatile R-package for analysis of count-based sequencing data in complex study designs. BMC Bioinformatics. 15(1):116.

markvdwiel/ShrinkBayes documentation built on March 27, 2022, 7:47 p.m.