Protein Design Containers

Singularity/Apptainer packaging for open-source protein design tools. Each tool lives in its own directory with a definition file, launcher, and README.

This repository provides container definitions and convenience launchers only. The scientific methods, model weights, and primary documentation belong to the original authors (see Attribution).

Tools

Tool	Directory	Docs	Weights in SIF?	Sylabs pull
RFdiffusion (original)	rfdiffusion/	rfdiffusion/README.md	Yes (baked in)	library://rfdiffusion/repo/rfdiffusion:amd64
RFdiffusion3 / Foundry	rfd3/	rfd3/README.md	No (host ./models)	library://rfd3/default/rfd3_x86:slim
BoltzGen	boltzgen/	boltzgen/README.md	No (host ./models)	library://boltzgen/default/boltzgen_x86:latest

Repository layout

ProteinDesign-Containers/
├── README.md                 # This overview
├── keys/                     # Public keys for Sylabs image verification
├── build_container.slurm     # Optional SLURM helper (RFdiffusion build)
├── rfdiffusion/              # Original RFdiffusion
├── rfd3/                     # Foundry slim image (RFD3, RF3, MPNN, …)
└── boltzgen/                 # BoltzGen

Quick start

Pick a tool and follow its README:

# RFdiffusion3 / Foundry (slim, no weights in the SIF)
cd rfd3
singularity pull library://rfd3/default/rfd3_x86:slim
./download_models.sh
python run_foundry_launcher.py --out_dir ./out --inputs ./design.json --ckpt_path rfd3

# Original RFdiffusion
cd ../rfdiffusion
# see rfdiffusion/README.md

# BoltzGen
cd ../boltzgen
# see boltzgen/README.md

Prerequisites: Singularity or Apptainer; NVIDIA drivers for GPU runs; Python 3 with absl-py for the Python launchers (spython also for the RFdiffusion launcher).

Attribution & citation

If you use these containers in research, cite the upstream tools, not only this packaging repo.

RFdiffusion (original)

Watson et al., Nature (2023). Paper · GitHub · Baker Lab / Institute for Protein Design, University of Washington.

@article{watson2023rfdiffusion,
  title={De novo design of protein structure and function with {RFdiffusion}},
  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 Wicky, Basile I. M. and Hanikel, Nikita and Pellock, Samuel J. and Courbet, Alexis and Sheffler, William and Wang, Jue and Venkatesh, Preetham and Sappington, Isaac and Torres, Susana V{\'a}zquez and Lauko, Anna and De Bortoli, Valentin and Mathieu, Emile and Ovchinnikov, Sergey and Barzilay, Regina and Jaakkola, Tommi S. and DiMaio, Frank and Baek, Minkyung and Baker, David},
  journal={Nature},
  volume={620},
  pages={1089--1100},
  year={2023},
  doi={10.1038/s41586-023-06415-8}
}

RFdiffusion3 / Foundry (RFD3, RF3, MPNN)

Butcher et al. (RFdiffusion3); Corley et al. (AtomWorks / RF3); Dauparas et al. (ProteinMPNN / LigandMPNN). Foundry · RFD3 preprint · Institute for Protein Design / RosettaCommons.

@article{butcher2025_rfdiffusion3,
  author  = {Butcher, Jasper and Krishna, Rohith and Mitra, Raktim and Brent, Rafael Isaac and Li, Yanjing and Corley, Nathaniel and Kim, Paul T and Funk, Jonathan and Mathis, Simon Valentin and Salike, Saman and Muraishi, Aiko and Eisenach, Helen and Thompson, Tuscan Rock and Chen, Jie and Politanska, Yuliya and Sehgal, Enisha and Coventry, Brian and Zhang, Odin and Qiang, Bo and Didi, Kieran and Kazman, Maxwell and DiMaio, Frank and Baker, David},
  title   = {De novo Design of All-atom Biomolecular Interactions with {RFdiffusion3}},
  year    = {2025},
  doi     = {10.1101/2025.09.18.676967},
  journal = {bioRxiv}
}

@article{corley2025accelerating,
  title   = {Accelerating biomolecular modeling with atomworks and rf3},
  author  = {Corley, Nathaniel and Mathis, Simon and Krishna, Rohith and Bauer, Magnus S and Thompson, Tuscan R and Ahern, Woody and Kazman, Maxwell W and Brent, Rafael I and Didi, Kieran and Kubaney, Andrew and others},
  journal = {bioRxiv},
  year    = {2025}
}

@article{dauparas2022robust,
  title   = {Robust deep learning--based protein sequence design using {ProteinMPNN}},
  author  = {Dauparas, Justas and Anishchenko, Ivan and Bennett, Nathaniel and Bai, Hua and Ragotte, Robert J and Milles, Lukas F and Wicky, Basile IM and Courbet, Alexis and de Haas, Rob J and Bethel, Neville and others},
  journal = {Science},
  volume  = {378},
  number  = {6615},
  pages   = {49--56},
  year    = {2022}
}

BoltzGen

Stark et al. GitHub · Paper

@article{stark2025boltzgen,
  author  = {Stark, Hannes and Faltings, Felix and Choi, MinGyu and others},
  title   = {{BoltzGen}: Toward Universal Binder Design},
  year    = {2025},
  journal = {bioRxiv}
}

Acknowledgements (packaging)

Container packaging and launchers in this repository are maintained for HPC / Singularity workflows. Funding and computational support for the packaging effort include Cornell University BRC Epigenomics Core Facility (RRID:SCR_021287), Penn State Institute for Computational and Data Sciences (RRID:SCR_025154), Penn State AIMI (RRID:SCR_022867), a gift to AIMI research from Dell Technologies, and NSF ACCESS (BIO230041) to William KM Lai and Gretta Kellogg.

Upstream software remains under the licenses of the original projects (e.g. BSD for Foundry; see each upstream repository).