• How to cite mixOmics?

It depends… See here to cite the paper corresponding to your need.

  • How to extract the names of variables selected when performing sPLS?

We will update a new version to extract theses genes in a most explicit manner. For now it is, for example for component 1 to extract the genes selected from data set X:

comp = 1
which(result$loadings$X[, comp] != 0)

You can do the same for component 2 and 3 and also for the data set Y.
Beware that the absolute value of these loadings indicate the importance of these genes so you can actually sort your list:

loadingsX1 = abs(result$loadings$X[, comp])
names(sort(loadingsX1, decreasing = T)[1:50])

will give you the names of the genes sorted by importance and selected by sPLS.

  • Is there a way the information on genes and metabolites connections can be incorporated in the mixOmics analysis?

mixOmics approaches are entirely data-driven, and we do not include any priori information. However, networks can be inferred by using similarity matrices that are a direct product of the methods RCCA or sPLS. So you can have a look at the network or cim functions (see more details on our website). The web
interface will also be able to give you such outputs.

  • Why does plsda return an error message even though I am using the same code as indicated in the tutorial or the help file?

This is highly likely due to a clash with another package that also provides a plsda function (caret or muma for instance; the spls package provides a splsda function) that was loaded before mixOmics. You can either unload these packages using the function detach() or use the command mixOmics::plsda(…) to be force the plsda function from mixOmics to be run.