flatironinstitute / inferelator

Task-based gene regulatory network inference using single-cell or bulk gene expression data conditioned on a prior network.
BSD 2-Clause "Simplified" License
47 stars 12 forks source link

Is it possible to run it only with expression and metadata? #36

Closed josruirod closed 1 year ago

josruirod commented 3 years ago

Hi, I understood from the readme that this could be run only with the regulators and the expression data, even if the performarnce would be "extremely poor". I would like to test that, but I'm getting the error "No gold standard or priors have been provided". Are these required in all cases? Thanks

asistradition commented 3 years ago

Yep, although it will raise an error (as you've noticed) if you don't set a couple of flags to suppress the error.

from inferelator import inferelator_workflow

worker = inferelator_workflow(regression="elasticnet", workflow="tfa")
worker.set_network_data_flags(use_no_prior=True, use_no_gold_standard=True)

This should work. Let me know if there are any problems.

josruirod commented 3 years ago

Sorry i missed that. It's now working good. Thanks