AlphaFold 2.1.1-foss-2021a-CUDA-11.3.1

There is a newer install of AlphaFold

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

Accessing AlphaFold 2.1.1-foss-2021a-CUDA-11.3.1

To load the module for AlphaFold 2.1.1-foss-2021a-CUDA-11.3.1 please use this command on the BEAR systems (BlueBEAR and BEAR Cloud VMs):

📋 module load AlphaFold/2.1.1-foss-2021a-CUDA-11.3.1

There is a CPU version of this module: AlphaFold 2.1.1-foss-2021a

BEAR Apps Version

2021a

Architectures

EL8-icelake (GPUs: NVIDIA A100, NVIDIA A30) — EL8-sapphirerapids

The listed architectures consist of two part: OS-CPU. The OS used is represented by EL and there are several different processor (CPU) types available on BlueBEAR. More information about the processor types on BlueBEAR is available on the BlueBEAR Job Submission page.

AlphaFold Databases

The AlphaFold databases, include both the full and reduced versions, are available in ${BB_APPS_DATA}/AlphaFold. Inside that folder you will find folder(s) dated by download date. Each dated folder contains all of the databases that can be downloaded with the download_all_data.sh script and was downloaded on the date as indicated by the folder name.

Running AlphaFold

For convenience a symbolic link named alphafold points to the run_alphafold.py script. So, once the AlphaFold module is loaded, you can just use alphafold instead of run_alphafold.py or python run_alphafold.py.

The run_alphafold.py script has been modified so that it is sufficient to define the $ALPHAFOLD_DATA_DIR environment variable for it to pick up all the data provided in that location. We provide several database downloads from different dates in ${BB_APPS_DATA}/AlphaFold. Select one of these centrally downloaded databases to use and add the following to your jobscript (replacing YYYYMMDD with the relevant database date):

export ALPHAFOLD_DATA_DIR=${BB_APPS_DATA}/AlphaFold/YYYYMMDD

Extensions

  • chex 0.0.8
  • contextlib2 21.6.0
  • dm-haiku-0.0.4
  • dm-tree-0.1.6
  • docker 5.0.0
  • immutabledict 2.1.0
  • ml_collections 0.1.0
  • PDBFixer 1.7
  • tabulate 0.8.9
  • toolz 0.11.1
  • websocket-client-1.2.1

More Information

For more information visit the AlphaFold website.

Dependencies

This version of AlphaFold has a direct dependency on: Biopython/1.79-foss-2021a CUDA/11.3.1 cuDNN/8.2.1.32-CUDA-11.3.1 foss/2021a HH-suite/3.3.0-gompi-2021a HMMER/3.3.2-gompi-2021a jax/0.2.24-foss-2021a-CUDA-11.3.1 Kalign/3.3.1-GCCcore-10.3.0 NCCL/2.10.3-GCCcore-10.3.0-CUDA-11.3.1 Python/3.9.5-GCCcore-10.3.0 PyYAML/5.4.1-GCCcore-10.3.0 SciPy-bundle/2021.05-foss-2021a TensorFlow/2.6.0-foss-2021a-CUDA-11.3.1

Other Versions

These versions of AlphaFold are available on the BEAR systems (BlueBEAR and BEAR Cloud VMs). These will be retained in accordance with our Applications Support and Retention Policy.

Last modified on 2nd December 2021