Skip to main content

AlphaFold

Introduction​

In short AlphaFold is groundbreaking AI system that is making research faster in the field of bioinformatics. To use AlphaFold the system first takes in a sequence of an amino acid and will then predict three dimensional structure of a protein and does so extremely efficiently.

Read more on the AlphaFold official website.

This section on AlphaFold will go through how to use AlphaFold on Elja.

Getting started​

note

Due to Nvidia compatibility issues Elja now requires you to run AlphaFold in a Conda environment.

Setting up the Conda environment​

We start by initializing the conda environment, these are the same steps as seen in Conda:

$ module use /hpcapps/lib-mimir/modules/all 
$ module load Anaconda3/2022.05
$ conda config --add channels defaults
$ conda config --add channels bioconda
$ conda config --add channels conda-forge
$ conda config --set auto_activate_base false
$ conda init
$ bash # You can also log out and in again.

Load AlphaFold​

Once conda is initialized and ready to use we can load AlphaFold module.

$ ml use /hpcapps/libbio-gpu/modules/all
$ ml load AlphaFold/2.3.1

Run AlphaFold on Elja​

To run AlphaFold on Elja you can either run an interactive session or run a batch job.

Starting an interactive session​

You can start an interactive session with the srun command on a GPU node. You can use the screen command or tmux to create a secondary terminal where your interactive session is running in the background.

$ srun --job-name "AlphaFold" --partition gpu-1xA100 --time 01:00:00 --pty bash
$ conda activate $env_path
$ run_alphafold.sh -d /AlphaFoldData/AlphaFold/data -o /hpcapps/source/alphafold_non_docker/dummy_test/ -f /hpcapps/source/alphafold_non_docker/example/query.fasta -t 2020-05-14

Running AlphaFold with SBATCH​

 cat submit.slurm
#!/bin/bash
#SBATCH --mail-type=ALL
#SBATCH --mail-user=<MAIL>         # for example uname@hi.is
#SBATCH --nodes=1                  # number of nodes
#SBATCH --partition=gpu-1xA100
#SBATCH --time=1-00:00:00          # run for 1 day maximum
#SBATCH --output=slurm_job_output.log
#SBATCH --error=slurm_job_errors.log   # Logs if job crashes

module use /hpcapps/libbio-gpu/modules/all
module load AlphaFold/2.3.1
conda activate $env_path

# Run the command

run_alphafold.sh -d /AlphaFoldData/AlphaFold/data -o /hpcapps/source/alphafold_non_docker/dummy_test/ -f /hpcapps/source/alphafold_non_docker/example/query.fasta -t 2020-05-14