Alphafold
Overview
DeepMind: AlphaFold: can accurately predict 3D models of protein structures and has the potential to accelerate research in every field of biology.
Documentation
AlphaFold Protein Structure Database: Developed by DeepMind and EMBL-EBI
AlphaFold Colab: “This Colab notebook allows you to easily predict the structure of a protein using a slightly simplified version of AlphaFold v2.1.0.“
General Articles:
ARCC are NOT domain experts on the science behind using Alphafold. We can best effort support on errors you come across, but not the use of the flags and databases used by Alphafold.
Please share any feedback you have, and we will develop this page for the wider community.
Using
Use the module name alphafold
to discover versions available and to load the application.
Loading the particular alphafold
module version will appropriate set the following environment variables: ALPHADB
and ALPHABIN
and set the associated singularity
module version.
Running Alphafold
Alphafold has been built via a docker image, but has been converted to a Singularity image, so must be run using Singularity.
Flag Help
As versions of alphafold update, available options will change. On loading the alphafold
module, a full list of flags can be found by running:
singularity run -B .:/etc $ALPHABIN/alphafold220.sif --help
singularity run -B .:/etc $ALPHABIN/alphafold220.sif --helpfull
Data Files and Examples
Version | Data Tree | Example |
---|---|---|
2.3.0 |