vsn2trsf {vsn} | R Documentation |
Apply the vsn transformation to data.
## S4 method for signature 'vsn': predict(object, newdata, log2scale=TRUE) vsn2trsf(x, p, strata)
object |
An object of class vsn that
contains transformation parameters and strata information, typically
this is the result of a previous call to vsn2 . |
newdata |
Numeric matrix , vector or
ExpressionSet with the data to which an
existing fit is to be applied to.
A typical use case is when the fit is made to a set of
control features and then the transformation is to be applied to the
full set of data.
If newdata is a vector, it is considered a matrix with one
column and nrow(newdata) rows. |
log2scale |
If TRUE , the data are returned on the glog
scale to base 2, and an overall offset c is added (see Value
section of the vsn2 manual page). If FALSE , the
data are returned on the glog scale to base e, and no offset is
added. |
x |
Numeric matrix. |
p |
An array with the transformation parameters. If strata is
specified, p is expected to be a 3d array, the first
dimension corresponds to the levels of strata ,
the second dimension to the columns of x and the third dimension
must be 2, corresponding to offsets and factors.
If strata is missing, then the first dimension may be omitted
and p can be a 2d array. NA values are not allowed. |
strata |
optional, a factor whose length is nrow(x) . Can
be used for stratified normalization (i.e. separate offsets a and
factors b for each level of strata ). |
For vsn2trsf
, a matrix of the same size as x
.
For predict
, a matrix if newdata
was a matrix, and an
ExpressionSet
, newdata
was an
ExpressionSet
. Dimnames and metadata are preserved.
Wolfgang Huber http://www.ebi.ac.uk/huber
data("kidney") param = array(c(-0.1, -0.1, 0.003, 0.003), dim=c(1,2,2)) tk = vsn2trsf(exprs(kidney), param) plot(tk, pch=".") ## see also the 'subsample' argument of vsn for an easier way to do this: fit = vsn2(kidney[sample(nrow(kidney), 500), ]) tn = predict(fit, newdata=exprs(kidney))