gprege

Gaussian Process Ranking and Estimation of Gene Expression time-series

Bioconductor version: Release (2.12)

The gprege package implements the methodology described in Kalaitzis & Lawrence (2011) "A simple approach to ranking differentially expressed gene expression time-courses through Gaussian process regression". The software fits two GPs with the an RBF (+ noise diagonal) kernel on each profile. One GP kernel is initialised wih a short lengthscale hyperparameter, signal variance as the observed variance and a zero noise variance. It is optimised via scaled conjugate gradients (netlab). A second GP has fixed hyperparameters: zero inverse-width, zero signal variance and noise variance as the observed variance. The log-ratio of marginal likelihoods of the two hypotheses acts as a score of differential expression for the profile. Comparison via ROC curves is performed against BATS (Angelini et.al, 2007). A detailed discussion of the ranking approach and dataset used can be found in the paper (http://www.biomedcentral.com/1471-2105/12/180).

Author: Alfredo Kalaitzis <a.kalaitzis at ucl.ac.uk>

Maintainer: Alfredo Kalaitzis <a.kalaitzis at ucl.ac.uk>

To install this package, start R and enter:

    source("http://bioconductor.org/biocLite.R")
    biocLite("gprege")

To cite this package in a publication, start R and enter:

    citation("gprege")

Documentation

PDF R Script gprege Quick Guide
PDF   Reference Manual
Text   NEWS

Details

biocViews Bioinformatics, DifferentialExpression, Microarray, Preprocessing, Software, TimeCourse
Version 1.4.1
In Bioconductor since BioC 2.10 (R-2.15)
License AGPL-3
Depends R (>= 2.8.0), gptk
Imports
Suggests spam
System Requirements
URL
Depends On Me
Imports Me
Suggests Me

Package Downloads

Package Source gprege_1.4.1.tar.gz
Windows Binary gprege_1.4.1.zip (32- & 64-bit)
Mac OS X 10.6 (Snow Leopard) gprege_1.4.1.tgz
Package Downloads Report Download Stats

Mailing Lists »

Post questions about Bioconductor packages to our mailing lists. Read the posting guide before posting!

Fred Hutchinson Cancer Research Center