Q: I did not understand when you say we cannot make the regulatory connections using the 84 genes and take the best 20 genes having the highest connectivity.
A: This would actually be equivalent to using all 84 genes.
Created by Thomas Yu thomas.yu Correct! Just want to double check, we cannot use the 84 in situs data (the bdtnp file) to select the 20 features(genes), but we are allowed to use the RNASeq file, either dge_raw, normalized, or binarized file, to run feature selection to pick the 20 features(genes)? Thanks! Just to be clear, you cannot extract features from the 84 in situs in an exhaustive way, you have to pre-select the 20,40 or 60 genes and consider as if the rest did not exist. ok then this is fine... Q: But I am using the RNA-seq for the 84 genes not the _in-situ_ data?