Learn R Programming

SigCheck (version 2.4.0)

Check a gene signature's prognostic performance against random signatures, known signatures, and permuted data/metadata

Description

While gene signatures are frequently used to predict phenotypes (e.g. predict prognosis of cancer patients), it it not always clear how optimal or meaningful they are (cf David Venet, Jacques E. Dumont, and Vincent Detours' paper "Most Random Gene Expression Signatures Are Significantly Associated with Breast Cancer Outcome"). Based on suggestions in that paper, SigCheck accepts a data set (as an ExpressionSet) and a gene signature, and compares its performance on survival and/or classification tasks against a) random gene signatures of the same length; b) known, related and unrelated gene signatures; and c) permuted data and/or metadata.

Copy Link

Version

Version

2.4.0

License

Artistic-2.0

Maintainer

Rory Stark

Last Published

February 15th, 2017

Functions in SigCheck (2.4.0)

SigCheck-package

Check a gene signature's survival and/or classification performance against random signatures, known signatures, and permuted data/metadata.
sigCheckPermuted

Check signature performance against performance on randomly permuted data.
knownSignatures

sigCheckRandom

Check signature performance against signatures composed of randomly selected features
sigCheckPlot

Plot results of a signature check or set of checks
nkiResults

Precomputed list of results for a call to sigCheckAll using the breastCancerNKI dataset.
classifyResults

sigCheck

Create a SigCheckObject and establish baseline performance.
sigCheckAll

Run a default set of checks on a gene signature.
SigCheckObject-class

Class "SigCheckObject"
sigCheckKnown

Check signature performance against a panel of known signatures.