alphafold

Summary

Sources: https://github.com/deepmind/alphafold

License: AlphaFold2 (non-commercial use only)

License: AlphaFold3

Note: Any publication that discloses findings arising from using this source code or the model parameters should cite the AlphaFold paper.

Genetic Databases: /data/dustgroup/ReferenceData/alphafold

Samples: /software/alphafold/

casp14: https://www.predictioncenter.org/casp14/index.cgi (T1050)

This package provides an implementation of the inference pipeline of AlphaFold v2.0. This is a completely new model that was entered in CASP14 and published in Nature. For simplicity, we refer to this model as AlphaFold throughout the rest of this document.

Versions available

• Alphafold 3.0.0 local installation

  • multimer capable
  • no docker or singularity images involved
  • restrictive license!

• Alphafold 2.3.2 for cuda 12.3

  • recommended version
  • multimer capable
  • supports H100 GPUs
  • no docker or singularity images involved

• Alphafold 2.3.2 local installation

  • multimer capable
  • does not support H100 GPUs
  • no docker or singularity images involved

Older versions are meanwhile obsolete.

alphafold simple recipes has some primitive python samples to handle pickled files.