Clustering with activity matrix

[IsabWu]

Hello !

I used PISCES pipeline and I have obtained interesting predictions of Masters Regulators when I applied this method to my own data however but I didn't succeed to obtain an activity matrix that cluster properly my different cell populations like yours in the acticle "Single-cell protein activity analysis identifies recurrence-associated renal tumor macrophages" while there is no problem to cluster my cell populations with the normalized gene expression matrix (generated with the seurat function SCTransform).
I have tried using the code in your git (code below) and I also use Seurat to do the UMAP and the clustering.

Do you have any suggestions about what can explain this kind of problems.

Thanks in advance.