Bootstrap for the EPoC methods
epoc.bootstrap(Y, U, nboots=100, bthr=NULL, method='epocG',...)
# S3 method for bootsize
plot(x, lambda.boot=NULL, B, range=c(0,1), ...)
epoc.final(epocboot, bthr=0.2, k)mRNA, samples x genes.
CNA, samples x genes.
Number of bootstrap iterations to run.
For epoc.bootstrap method is "epocG" or "epocA".
A sparse network matrix or a list of the same, non-zeros are links. These come from e.g. epoc.final or epoc.bootstrap.
The \(\lambda\)s used to run the bootstrap.
Number of bootstrap iterations ran for 'plot.bootsize'.
Range of bootstrap thresholds to display.
For epoc.final give a list of bootstraped models from epoc.bootstrap.
For epoc.final and epoc.bootplot select the k sparsest model.
Require presence of links in 100*bthr% of the bootstrap iterations.
Parameters passed down to an underlying function. For epoc.bootstrap these are passed down to "epocG" or "epocA" respectively. For epoc.bootplot and plot.bootsize parameters are passed down to the underlying plot command.
epoc.bootstrap returns a list of \(p \times p\) arrays of values in \([0,1]\) where 1 is presence of link in 100% of bootstrap iterations for the \(k\) different \(\lambda\) values for \(p\) different genes.
epoc.final returns a sparse matrix of \(p \times p\) values in \([0,1]\) where 1 is presence of link in 100% of bootstrap iterations, but thresholded such that all values have be greater than or equal to bthr.
epoc.bootstrap run epocA or epocG using bootstrap.
Rebecka J<U+00F6>rnsten, Tobias Abenius, Teresia Kling, Linn<U+00E9>a Schmidt, Erik Johansson, Torbj<U+00F6>rn Nordling, Bodil Nordlander, Chris Sander, Peter Gennemark, Keiko Funa, Bj<U+00F6>rn Nilsson, Linda Lindahl, Sven Nelander. (2011) Network modeling of the transcriptional effects of copy number aberrations in glioblastoma. Molecular Systems Biology 7 (to appear)