search

plger / scDblFinder

Methods for detecting doublets in single-cell sequencing data
https://plger.github.io/scDblFinder/
GNU General Public License v3.0
162 stars 17 forks source link

How to find all features used in training #61

Closed XinyeZhao closed 1 year ago

XinyeZhao commented 2 years ago

Hi scDblFinder team!

It's mentioned in the paper that scDblFinder utilizes multiple features obtained from the Knn network, such as projections on principal components; library size; the number of detected features; and co-expression scores. But I can only find the scDblFinder.weighted and scDblFinder.cxds_score in the output R object. Could you tell me how to obtain all features used in training GDBT tree in the R object?

Thanks

plger commented 2 years ago

Hi, if you use retType="table", the output will be a data.frame containing all the variables for both real cells and artificial doublets. Pierre-Luc