vahuynh / GENIE3

Machine learning-based approach for the inference of gene regulatory networks from expression data.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

A question

opened this issue · comments

Hello,
I recently read a paper from you, Inferring Regulatory Networks from Expression Data
Using Tree-Based Methods
, but I have a trouble, if we have calculated weights, how choose an appropriate threshold to get the relationships between genes.

Thank you for you time.

GENIE3 only provides a ranking of the network edges and not a network topology. The weights returned by GENIE3 are not statistically interpretable and thus choosing an appropriate threshold remains an open problem so far.