twostepsva.build: A function for estimating surrogate variables with the two...
In sva: Surrogate Variable Analysis

Description Usage Arguments Value Examples

This function is the implementation of the two step approach for estimating surrogate variables proposed by Leek and Storey 2007 PLoS Genetics. This function is primarily included for backwards compatibility. Newer versions of the sva algorithm are available through sva, svaseq, with low level functionality available through irwsva.build and ssva.

1	twostepsva.build(dat, mod, n.sv)

`dat`	The transformed data matrix with the variables in rows and samples in columns
`mod`	The model matrix being used to fit the data
`n.sv`	The number of surogate variables to estimate

sv The estimated surrogate variables, one in each column

pprob.gam: A vector of the posterior probabilities each gene is affected by heterogeneity

pprob.b A vector of the posterior probabilities each gene is affected by mod (this is always null for the two-step approach)

n.sv The number of significant surrogate variables

library(bladderbatch)
library(limma)
data(bladderdata)
dat <- bladderEset

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

n.sv = num.sv(edata,mod,method="leek")
svatwostep <- twostepsva.build(edata,mod,n.sv)