bga.suppl performs a bga between group analysis with projection
of supplementary points using suppl
bga.suppl(dataset, supdata, classvec, supvec = NULL, suponly = FALSE, type="coa", ...)matrix, data.frame,
ExpressionSet or
marrayRaw-class.
If the input is gene expression data in a matrix or data.frame. The
rows and columns are expected to contain the variables (genes) and cases (array samples)
respectively.matrix, data.frame,
ExpressionSet or
marrayRaw-class.
If the input is gene expression data in a matrix or data.frame. The
rows and columns are expected to contain the variables (genes) and cases (array samples)
respectively. The test dataset supdata and the training dataset dataset must contain
the same number of variables (genes).factor or vector which describes the classes in the
training data dataset.factor or vector which describes the classes in the
test dataset supdata.FALSE, that
is the training coordinates, test coordinates and class assignments
will all be returned.suponly is FALSE (the default option) bga.suppl returns a list of length 4 containing
the results of the bga of the training dataset and the results of the projection of the test dataset onto the bga axes-
dudi). dudi),"between" (see bca),and
"dudi.bga"(see bga)supplsuponly is TRUE only the results from suppl will be returned.
bga.suppl calls bga to perform between group analysis (bga) on the training dataset,
then it calls suppl to project the test dataset onto the bga axes.
It returns the coordinates and class assignment of the cases (microarray samples) in the test dataset as
described by Culhane et al., 2002. The test dataset must contain the same number of variables (genes) as the training dataset.
The input format of both the training dataset and test dataset are verified using array2ade4.
Use plot.bga to plot results from bga.
bga,
suppl, bca,
plot.bga, bga.jackknife data(khan)
#khan.bga<-bga(khan$train, khan$train.classes)
if (require(ade4, quiet = TRUE)) {
khan.bga<-bga.suppl(khan$train, supdata=khan$test,
classvec=khan$train.classes, supvec=khan$test.classes)
khan.bga
plot.bga(khan.bga, genelabels=khan$annotation$Symbol)
khan.bga$suppl
}
Run the code above in your browser using DataLab