search

AntonioDeFalco / SCEVAN

R package that automatically classifies the cells in the scRNA data by segregating non-malignant cells of tumor microenviroment from the malignant cells. It also infers the copy number profile of malignant cells, identifies subclonal structures and analyses the specific and shared alterations of each subpopulation.
https://www.nature.com/articles/s41467-023-36790-9
GNU General Public License v3.0
90 stars 25 forks source link

Correlation number of genes/counts #123

Open Ilarius opened 1 week ago

Ilarius commented 1 week ago

I noticed a correlation between counts and tumor/healthy prediction. (I am using all non-epithelial cells as reference). Any tips on how to avoid this?

Screenshot 2024-09-18 at 12 26 46

AntonioDeFalco commented 1 week ago

Hello @Ilarius, Could you explain why you consider this correlation to be an issue? It’s well established in the literature that cancer cells express a large number of genes due to various factors, isn’t it?

Regards.