isvaFn: Main engine function for inference of independent surrogate...

In isva: Independent Surrogate Variable Analysis

Description

This is the main engine function which infers the statistically independent surrogate variables (ISVs) by performing Independent Component Analysis (ICA) on the residual variation matrix. It uses either the ICA implementation of JADE or the one from the fastICA R-package. The residual variation matrix reflects the variation orthogonal to that of a phenotype of interest and is inferred using a linear model.

Usage

isvaFn(data.m, pheno.v, ncomp = NULL,icamethod)

Arguments

data.m	Data matrix. Rows label features. Columns label samples.
pheno.v	Numeric vector encoding phenotype of interest.
ncomp	Optionally specify number of ISVs to look for. By default will use Approximate Random Matrix Theory to infer this number.
icamethod	The ICA method to be used. Input value is taken from DoISVA.

Value

A list with following entries:

n.isv	Number of inferred ISVs.
isv	Matrix of inferred ISVs.

Author(s)

Andrew E Teschendorff

References

Independent Surrogate Variable Analysis to deconvolve confounding factors in large-scale microarray profiling studies. Teschendorff AE, Zhuang JJ, Widschwendter M. Bioinformatics. 2011 Jun 1;27(11):1496-505.

Examples

## see example for DoISVA

Example output

Loading required package: qvalue
Loading required package: fastICA
Loading required package: JADE

isva documentation built on May 1, 2019, 6:49 p.m.