# Classification (supervised learning) of expression data on pathway level

I was wondering if there is any way to apply classification algorithms (e.g random forest) on microarray data but not using the genes as predictors/features but the pathway they belong to.

The thing is that the expressions of the genes that belong to the same pathway should somehow, grouped together and transformed into a new value that will describe that pathway for each specific sample.

Let me give an example.

Assuming that we have g1, g2, g3, g4, g5, g6, g7, g8, g9, g10 as genes and p1, p2, p3 as pathways.

And g1, g2, g3 belong to p1 while g3, g4, g5, g6belong to p2 and g2, g6, g7, g8, g9, g10 belong to p3

One thought is to calculate the mean expression of the above gene groups per sample and then run the classification algorithm on top of these values. But I would like to hear/read your opinion on such an approach and also your suggestions on using a different method to do this.

The final goal would be the extraction of the most significant classification predictors (pathways).

• Do you assume that expression of genes are similar in pathways? Because in a real experiment they are not. – benn Feb 27 '18 at 10:34
• No, I don't want to assume something like that but I mentioned the mean in order to group the genes of each pathway. This approach might be totally wrong but that's why I posted here. To get feedback and different opinions. – J. Doe Feb 27 '18 at 10:59
• My point is, that I haven't seen an algorithm that can transform the expression values of different genes into one value that represents a given pathway. – benn Feb 27 '18 at 11:23
• Oh ok. I see... – J. Doe Feb 27 '18 at 11:32
• IPA is commercial. Isn't it? Can you provide me with free R-based ones to understand what exactly you suggest? – J. Doe Feb 27 '18 at 13:35

Have a look at the GSVA package. It allows to convert a matrix with genes x Samples to a pathways x Samples using several methods ssgsea, gage, gsva...