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.
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?
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?
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?