OpenFold3-preview is a biomolecular structure prediction model aiming to be a bitwise reproduction of DeepMind's AlphaFold3, developed by the AlQuraishi Lab at Columbia University and the OpenFold consortium. This research preview is intended to gather community feedback and allow developers to start building on top of the OpenFold ecosystem. The OpenFold project is committed to long-term maintenance and open source support, and our repository is freely available for academic and commercial use under the Apache 2.0 license.

For our reproduction of AlphaFold2, please refer to the original OpenFold repository.

Please visit our full documentation at https://openfold-3.readthedocs.io/en/latest/

OpenFold3-preview replicates the input features described in the AlphaFold3 publication, as well as batch job support and efficient kernel-accelerated inference.

A summary of our supported features includes:

• Structure prediction of standard and non-canonical protein, RNA, and DNA chains, and small molecules
• Pipelines for generating MSAs using the ColabFold server or using JackHMMER / hhblits following the AlphaFold3 protocol
• Structure templates for protein monomers
• Kernel acceleration through cuEquivariance and DeepSpeed4Science kernels - more details here
• Support for multi-query jobs with distributed predictions across multiple GPUs
• Custom settings for memory constrained GPU resources

Make your first predictions with OpenFold3-preview in a few easy steps:

1. Install OpenFold3-preview using our pip package

pip install openfold3 
mamba install kalign2 -c bioconda

2. Setup your installation of OpenFold3-preview and download model parameters:

setup_openfold

3. Run your first prediction using the ColabFold MSA server with the run_openfold binary

run_openfold predict --query_json=examples/example_inference_inputs/query_ubiquitin.json

More information on how to customize your inference prediction can be found at our documentation home at https://openfold-3.readthedocs.io/en/latest/. More examples for inputs and outputs can be found in our HuggingFace examples.

OpenFold3-preview performs competitively with the state of the art in open source biomolecular structure prediction, while being the only model to match AlphaFold3's performance on monomeric RNA structures.

Preliminary results:

Performance of OF3p and other models on a diverse set of benchmarks:

• Protein and RNA monomers from CASP16 and Ludaic et al
• Proein-protein complexes from CASP16 and FoldBench
• Protein-ligand complexes from the Runs and Poses

For more details on inferences procedures and benchmarking methods, please refer to our whitepaper.

The final OpenFold3 model is still in development, and we are actively working on the following features:

• Full parity on all modalities with AlphaFold3
• Training documentation & dataset release
• Workflows for training on custom non-PDB data

If you encounter problems using OpenFold3-preview, feel free to create an issue! We also welcome pull requests from the community.

If you use OpenFold3-preview in your research, please cite the following:

@software{openfold3-preview,
  title = {OpenFold3-preview},
  author = {{The OpenFold3 Team}},
  year = {2025},
  version = {0.1.0},
  doi = {10.5281/zenodo.1234567},
  url = {https://github.com/aqlaboratory/openfold-3},
  abstract = {OpenFold3-preview is a biomolecular structure prediction model aiming to be a bitwise reproduction of DeepMind's AlphaFold3, developed by the AlQuraishi Lab at Columbia University and the OpenFold consortium.}
}

Any work that cites OpenFold3-preview should also cite AlphaFold3.