rfdiffusion-complex-base

OFoldX pipeline artifact for biomolecular design generation, using the rfdiffusion architecture.

Disclaimer

This model card was generated by the OFoldX team for an OFoldX pipeline artifact. The upstream model authors did not write this card unless explicitly stated otherwise.

OFoldX is pre-alpha research software. Check the source checkpoint, upstream release, and local validation before using the artifact for scientific or operational decisions.

Model Details

RFdiffusion backbone-generation model for protein design and motif scaffolding.

Converted RFdiffusion checkpoint for backbone generation, motif scaffolding, and binder design.

Model Provenance

• Upstream Project: RFdiffusion
• Source Release: https://github.com/RosettaCommons/RFdiffusion/blob/main/scripts/download_models.sh
• Primary Paper: De novo design of protein structure and function with RFdiffusion
• Upstream License: BSD for upstream RFdiffusion code and referenced model weights

Model Specification

Field	Value
Repository	oteam/rfdiffusion-complex-base
Artifact Kind	pipeline
Task	design_generation
Architecture	rfdiffusion
Entrypoint	ofoldx.pipelines.design.DesignPipeline

Links

• Hub repository: oteam/rfdiffusion-complex-base
• Upstream paper: De novo design of protein structure and function with RFdiffusion
• Upstream repository: RFdiffusion
• Source checkpoint release: https://github.com/RosettaCommons/RFdiffusion/blob/main/scripts/download_models.sh
• Code: ofoldx/pipelines/design.py
• Project repository: https://github.com/OTeam-AI4S/OFoldX
• Issues: https://github.com/OTeam-AI4S/OFoldX/issues

Usage

The artifact depends on the ofoldx library. Install it with pip:

pip install ofoldx

Pipeline Usage

Load the artifact from oteam/rfdiffusion-complex-base with the OFoldX task pipeline. Use AutoModel or AutoProcessor only when you need lower-level control:

from ofoldx.pipelines import Pipeline

pipeline = Pipeline.from_pretrained("oteam/rfdiffusion-complex-base")

When a matching processor is available, load it with AutoProcessor.from_pretrained(...) and pass the processed batch to the model.

Interface

• Task: design_generation
• Artifact kind: pipeline
• Architecture: rfdiffusion
• Runtime files: manifest.json, config.json, and model.safetensors when present

Training Details

OFoldX did not train these weights. This repository contains a converted checkpoint and OFoldX runtime metadata for loading it.

Training Data

RFdiffusion fine-tunes a RoseTTAFold-style structure network as a denoising diffusion model over PDB protein structures. OFoldX does not redistribute the training set.

Training Procedure

Upstream RFdiffusion noises residue frames with Gaussian C-alpha translation noise and rotational Brownian motion, trains denoising to true frames with self-conditioning, and uses checkpoint-specific inference configs. OFoldX converts released RFdiffusion checkpoints into model.safetensors; it does not run RFdiffusion training.

Evaluation

OFoldX conversion reports and contract tests validate artifact structure and checkpoint loading. Task-level scientific evaluation should be checked against the corresponding upstream model release or paper.

Limitations

• This artifact is distributed for research use.
• Inputs must match the model-specific processor and expected biomolecular representation.
• OFoldX is pre-alpha, so APIs and artifact metadata may still change before a stable release.

Citation

Please cite the upstream RFdiffusion work for the source checkpoint. If OFoldX supports your work, please also cite or link the OFoldX project repository.

@article{watson2023denovo,
  author = {Watson, Joseph L. and Juergens, David and Bennett, Nathaniel R. and Trippe, Brian L. and Yim, Jason and Eisenach, Helen E. and Ahern, Woody and Borst, Andrew J. and Ragotte, Robert J. and Milles, Lukas F. and others},
  title = {De novo design of protein structure and function with RFdiffusion},
  journal = {Nature},
  volume = {620},
  number = {7976},
  pages = {1089--1100},
  year = {2023},
  doi = {10.1038/s41586-023-06415-8}
}

Contact

Please use OFoldX GitHub issues for questions or comments about this model card.

License

The Hub license metadata, when present, reflects the source checkpoint or upstream project license. The OFoldX project license is not yet finalized. The source checkpoint is associated with the upstream license noted above: BSD for upstream RFdiffusion code and referenced model weights. Review both OFoldX and upstream terms before redistribution or production use.