Supported Applications


  • Description

    a trainable, memory-efficient, and GPU-friendly PyTorch reproduction of DeepMind's AlphaFold 2.

  • Usage Notes

    SBGrid/BioGrids OpenFold provides the following directly callable programs:

    build_deepspeed_config.py data_dir_to_fasta.py generate_chain_data_cache.py generate_mmcif_cache.py precompute_alignments.py precompute_alignments_mmseqs.py prep_proteinnet_msas.py python.openfold run_pretrained_openfold.py train_openfold.py unpack_proteinnet.py

  • Installation

    Use the following command to install this title with the CLI client: $ sbgrid-cli install openfold Copy to clipboard Available operating systems: Linux 64
  • Primary Citation*

    G. Ahdritz, N. Bouatta, S. Kadyan, Q. Xia, W. Gerecke, and M. AlQuraishi. 2021. OpenFold. Zenodo. https://doi.org/10.5281/zenodo.5709539.

    • *Full citation information available through

  • Citation Note

    Any work that cites OpenFold should also cite AlphaFold.

  • Webinars

    Topic: Retraining AlphaFold2 yields new insights into its learning mechanism and capacity for generalization.

    Presenter: Gustaf Ahdritz, Ph.D. Student, AlQuraishi Laboratory Columbia University.

    Host: Jason Key
    Recorded on April 11, 2023

    For more information on OpenFold: