ssva: A function for estimating surrogate variables using a...

Description Usage Arguments Value Examples

View source: R/ssva.R

Description

This function implements a supervised surrogate variable analysis approach where genes/probes known to be affected by artifacts but not by the biological variables of interest are assumed to be known in advance. This supervised sva approach can be called through the sva and svaseq functions by specifying controls.

Usage

1
ssva(dat, controls, n.sv)

Arguments

dat

The transformed data matrix with the variables in rows and samples in columns

controls

A vector of probabilities (between 0 and 1, inclusive) that each gene is a control. A value of 1 means the gene is certainly a control and a value of 0 means the gene is certainly not a control.

n.sv

The number of surogate variables to estimate

Value

sv The estimated surrogate variables, one in each column

pprob.gam: A vector of the posterior probabilities each gene is affected by heterogeneity (exactly equal to controls for ssva)

pprob.b A vector of the posterior probabilities each gene is affected by mod (always null for ssva)

n.sv The number of significant surrogate variables

Examples

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
library(bladderbatch)
data(bladderdata)
dat <- bladderEset[1:5000,]

pheno = pData(dat)
edata = exprs(dat)
mod = model.matrix(~as.factor(cancer), data=pheno)

n.sv = num.sv(edata,mod,method="leek")
set.seed(1234)
controls <- runif(nrow(edata))
ssva_res <- ssva(edata,controls,n.sv)

Bioconductor-mirror/sva documentation built on June 23, 2017, 6:27 p.m.