twilight

Estimation of local false discovery rate

Bioconductor version: Release (2.7)

In a typical microarray setting with gene expression data observed under two conditions, the local false discovery rate describes the probability that a gene is not differentially expressed between the two conditions given its corrresponding observed score or p-value level. The resulting curve of p-values versus local false discovery rate offers an insight into the twilight zone between clear differential and clear non-differential gene expression. Package 'twilight' contains two main functions: Function twilight.pval performs a two-condition test on differences in means for a given input matrix or expression set and computes permutation based p-values. Function twilight performs a stochastic downhill search to estimate local false discovery rates and effect size distributions. The package further provides means to filter for permutations that describe the null distribution correctly. Using filtered permutations, the influence of hidden confounders could be diminished.

Author: Stefanie Scheid

Maintainer: Stefanie Scheid

To install this package, start R and enter:

source("http:///biocLite.R")
biocLite("twilight")    

Documentation

PDF		bcb_logo.pdf
PDF	R Script	Estimation of Local False Discovery Rates
PDF		Rplots.pdf

Reference Manual

Details

biocViews	Microarray, Bioinformatics, DifferentialExpression, MultipleComparisons
Depends	R, splines, stats, Biobase
Imports	Biobase, graphics, grDevices, stats
Suggests	golubEsets, vsn
System Requirements
License	GPL (>= 2)
URL	http://compdiag.molgen.mpg.de/software/twilight.shtml
Depends On Me	OrderedList
Imports Me	OrderedList
Suggests Me
Version	1.26.0

Package Downloads

Package Source	twilight_1.26.0.tar.gz
Windows Binary	twilight_1.26.0.zip (32- & 64-bit)
MacOS 10.5 (Leopard) binary	twilight_1.26.0.tgz
Package Downloads Report	Download Stats