New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Scores not output to output file when running containerized Gnina #235
Comments
I have not seen that before. If you can share your docker container I can look into it. |
Ok, thanks. The dockerfile is as follows: ARG OSVERSION "ubuntu2204" ENV PROJECT_DIR=${ENVNAME} WORKDIR /home/nas RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone RUN apt-key adv --fetch-keys https://developer.download.nvidia.com/compute/cuda/repos/${OSVERSION}/${ARCH}/${NVIDIA_PUBKEY} RUN apt -y update && RUN git clone https://github.com/gnina/gnina.git && COPY environment_gnina.yml ../environment.yml RUN wget https://repo.anaconda.com/miniconda/Miniconda3-py39_4.12.0-Linux-x86_64.sh && CMD bash` and the environment.yml files is:
|
Before I go to the trouble of trying to reproduce this - can you try adding |
Unfortunately, no. Reverting to this release version gives the same result. |
I've built a container using your docker file and run it:
The scores are present in the output file:
Can you provide your input files so I can see if that's the problem? |
Issue summary
I previously ran Gnina outside of a docker container and scores and minimzed affinity and CNN scores as comments were appended directly below the SDF block for each pose. I have since moved Gnina into a docker container and now I find only a single comment for minimzed affinity at 0 and no CNN scores, i.e.:
0.00000
However, scores are output to the terminal, e.g.:
mode | affinity | CNN | CNN
| (kcal/mol) | pose score | affinity
-----+------------+------------+----------
1 -7.11 0.7744 6.065
Gnina otherwise seems to run normally, generating plausible poses. Is there a setting in Gnina which might result in this behavior?
Steps to reproduce
I have run Gnina within a docker container as follows:
docker run --gpus all --name name1 -v /home/roc/dir_name/:/home/src/dir_name/ --shm-size 8gb pardela gnina -r /home/src/dir_name/temp/temp_gnina_receptor.pdb --ligand /home/src/dir_name/temp/temp_gnina_ligand.sdf --autobox_ligand /home/src/dir_name/temp/temp_gnina_receptor.pdb -o /home/src/dir_name/temp/temp_gnina_poses.sdf --exhaustiveness 64 --num_modes 10 --device 0 --cnn_scoring "rescore" --pose_sort_order CNNscore --min_rmsd_filter 1.0
Your system configuration
Operating system: Windows 11
Compiler: 11.4.0
CUDA version (if applicable): 12.3
CUDNN version (if applicable): 8.8.0.121
Python version: 3.11
The text was updated successfully, but these errors were encountered: