biosvd (version 2.8.0)

compute,Eigensystem-method: Compute the eigensystem for a feature by assay matrix

Description

Computes the eigensystem for a feature by assay matrix by applying Singular Value Decomposition.

Usage

"compute"(object, apply = c("data", "variance"))

Arguments

object

object of class matrix, data.frame, Expressionset or Eigensystem, containing the feature x assay expression or intensity data

apply

the actual expression/intensity data (data) or variance in the data (variance) to which to apply the function (default = data)

Value

Object of class Eigensystem

Methods

signature(x = "Eigensystem")

signature(x = "data.frame")

signature(x = "matrix")

signature(x = "ExpressionSet")

Details

Function compute decomposes the input data set from the feature x assay space to the reduced diagonalized "eigenfeatures x eigenassays" space, with the eigenfeatures and eigenassays unique orthonormal superpositions of the features and assays, respectively. This approach allows filtering out eigenfeatures and eigenassays that are inferred to represent noise or experimental artifacts, either at the expression/intensity level or the variance level. The function can be applied to an object of class matrix, data.frame, ExpressionSet, or eigensystem.

References

Alter O, Brown PO and Botstein D. Singular value decomposition for genome-wide expression data processing and modeling. Proc Natl Acad Sci U.S.A. 97(18), 10101-10106 (2000).

See Also

Eigensystem-class

Other X.eigensystem.: exclude, exclude,Eigensystem-method; plot, plot,Eigensystem,EigensystemPlotParam-method; report, report,Eigensystem,EigensystemPlotParam-method

Examples

## Metabolomics starvation data obtained from http://genomics-pubs.princeton.edu/StarvationMetabolomics/Download.shtml
data(StarvationData)

## Computes the eigensystem for the actual expression/intensity data
eigensystem <- compute(StarvationData)
## Computes the eigensystem for the variance in the data
eigensystem <- compute(StarvationData, apply="variance")