Giters

RosettaCommons / RoseTTAFold

This package contains deep learning models and related scripts for RoseTTAFold

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Activating conda environments

Joseph-Vineland opened this issue · comments

commented

I am following the instructions to install RoseTTAFold.

# create conda environment for RoseTTAFold
# If your NVIDIA driver compatible with cuda11
conda env create -f RoseTTAFold-linux.yml
# create conda environment for pyRosetta folding & running DeepAccNet
conda env create -f folding-linux.yml

At what point do you activate these conda environments? ( conda activate env_name )
What is the correct procedure for activating them?

Do you create and activate the the RoseTTAFold environemnt, then create and activate the folding environment from within it? Which environemnt should be activated when performing step 4 Download and install third-party software?

Thanks for the amazing tool, it is very exciting to be able to use something like this.

commented

Once you have followed the instructions to successully install RoseTTAFold, the correct procedure is to activate the RoseTTAFold conda environment ( conda activate RoseTTAFold ) and use the run_e2e_ver.sh or run_pyrosetta_ver.sh scripts within there.

Side Note: Like many other users have experienced, for me the run_e2e_ver.sh scripts fails with a 'RuntimeError: CUDA out of memory'. I hope someone can find a solution.