Skip to content
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

Will provide a conda install guidelines? Cause docker cannot used #19

Closed
Paulie-ai opened this issue Nov 13, 2024 · 5 comments
Closed
Labels
question Further information is requested setup Problem with installation or setting things up

Comments

@Paulie-ai
Copy link

No description provided.

@Augustin-Zidek Augustin-Zidek added setup Problem with installation or setting things up question Further information is requested labels Nov 13, 2024
@Augustin-Zidek
Copy link
Collaborator

Hi, we are not planning providing AlphaFold 3 on Conda.

If you wish to install this without Docker, you can follow the commands in the Docker container (see https://github.com/google-deepmind/alphafold3/blob/main/docker/Dockerfile) to install AlphaFold 3 directly without Docker.

@Paulie-ai
Copy link
Author

Paulie-ai commented Nov 14, 2024

This is a conda version install step which worked for me.

1. Install HMMER as dockfile describe

2. create conda env and pip packages

conda create -n alphafold3_venv python=3.11
pip3 install -r dev-requirements.txt
mv src/alphafold3/* . -rf
pip3 install --no-deps .
build_data

3. Specify the model, alphafold3 database and hammer's binary_path location. then make prediction using alphafold3

@AlvinAi-cloud
Copy link

@Paulie-ai Thank you very much. Would it be possible for you to provide a more elaborate procedure so that it will help many future people like me who are not familiar with the process?

@Xiaojun928
Copy link

I followed steps by @Paulie-ai, but with some minor changes in the step2. Here are the details

cd alphafold3
conda create -n af3_v_cdbcf41 python=3.11
conda activate af3_v_cdbcf41
### To avoid error below, do some modification here
# 1. using mirror of git
git config --global url."https://githubfast.com/".insteadOf "https://github.com/"

# 2. update the g++ > 9.4
conda install -c conda-forge gcc_linux-64>=9.4 gxx_linux-64>=9.4 cmake make
conda deactivate  
conda activate af3_v_cdbcf41
echo $CONDA_PREFIX  
ln -sf $CONDA_PREFIX/bin/x86_64-conda-linux-gnu-g++ $CONDA_PREFIX/bin/g++
which g++
g++ --version

pip3 install -r dev-requirements.txt
build_data

I first tried this mv src/alphafold3/* . -rf, but got errors when running mv src/alphafold3/* . -rf. So it may be better not to change the original file structure.

@jkosinski
Copy link

Why do you need those mv src/alphafold3/* . -rf or git config --global url."https://githubfast.com/".insteadOf "https://github.com/" steps? For me this worked with mamba (assuming g++ and hmmer installed separately):

git clone https://github.com/google-deepmind/alphafold3.git

mamba create -n alphafold3 python=3.11 -y
source activate alphafold3

cd alphafold3
pip install -r dev-requirements.txt
pip install --no-deps .

build_data

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested setup Problem with installation or setting things up
Projects
None yet
Development

No branches or pull requests

5 participants