The $p x p$ target Gpos is computed from the
$n x p$ data matrix. It it a modified version
of target G. In particular, it completely ignores negative correlations and
computes the mean correlation $r$ using the positive ones only.
Usage
targetGpos(x, genegroups)
Arguments
x
A $n x p$ data matrix.
genegroups
A list of genes obtained using the database KEGG, where each
entry itself is a list of pathway names this genes belongs to. If a gene does
not belong to any gene functional group, the entry is NA.
Value
A $p x p$ matrix.
References
J. Schaefer and K. Strimmer, 2005. A shrinkage approach to large-scale
covariance matrix estimation and implications for functional genomics.
Statist. Appl. Genet. Mol. Biol. 4:32.
M. Jelizarow, V. Guillemot, A. Tenenhaus, K. Strimmer, A.-L. Boulesteix, 2010.
Over-optimism in bioinformatics: an illustration. Bioinformatics. Accepted.
# A short example on a toy dataset# require(SHIP)data(expl)
attach(expl)
tar <- targetGpos(x,genegroups)
which(tar[upper.tri(tar)]!=0) # not many non zero coefficients !