AlphaFold

Description

AlphaFold can predict protein structures with atomic accuracy even where no similar structure is known

More information

- Homepage: https://deepmind.com/research/case-studies/alphafold

Available Versions of AlphaFold

Version	Module	Available on

Version	Module	Available on
2.2.2-foss-2021a-CUDA-11.3.1	bio/AlphaFold/2.2.2-foss-2021a-CUDA-11.3.1	Noctua 2

This table is generated automatically. If you need other versions please click pc2-support@uni-paderborn.de.

Usage Hints for AlphaFold

If you need support in using this software or example job scripts please click pc2-support@uni-paderborn.de.

Example for Noctua 2

The following example shows the usage of Alphafold for t1050.fasta, which can be downloaded from https://predictioncenter.org/casp14/target.cgi?target=T1050&view=sequence.

It uses one Nvidia A100 GPU (40 GB) and runs for about 40 minutes.

#!/bin/bash
#SBATCH -t 1:00:00
#SBATCH -N 1
#SBATCH -n 1
#SBATCH --cpus-per-task=32
#SBATCH -p gpu
#SBATCH --gres=gpu:a100:1

module reset
module load bio/AlphaFold/2.2.2-foss-2021a-CUDA-11.3.1
rm -rf out
mkdir out

alphafold --data_dir=/scratch/data-repos/bio/AlphaFold/full_databases --fasta_paths=t1050.fasta --output_dir=out --max_template_date=2020-05-14 --model_preset=monomer --db_preset=reduced_dbs