How to use RFdiffusion: what you can do with it

3 use cases

• Generate new protein backbones from scratch

  Run unconditional diffusion to design monomers of a chosen length.

  • REPO RosettaCommons/RFdiffusion
  • Claude Code
  • Codex
  • Cursor
  • Gemini CLI
  • Security and science
  • Advanced
  View prompt

  Using RosettaCommons/RFdiffusion, set up the SE3nv environment and run `./scripts/run_inference.py 'contigmap.contigs=[150-150]' inference.output_prefix=test_outputs/test inference.num_designs=10`, then summarize what each output file contains.

  Share Email me this

• Design a binder against a target protein

  Diffuse a binder against a target chain, using hotspot residues to aim it at the right surface.

  • REPO RosettaCommons/RFdiffusion
  • Claude Code
  • Codex
  • Cursor
  • Gemini CLI
  • Security and science
  • Advanced
  View prompt

  With RosettaCommons/RFdiffusion, design 10 binders to residues 1-100 of chain B in <my target pdb> with hotspot residues <my hotspots>, and explain how to pick the hotspots from the structure.

  Share Email me this

• Scaffold a functional motif into a new protein

  Hold a motif from an input PDB fixed and let diffusion build the protein around it.

  • REPO RosettaCommons/RFdiffusion
  • Claude Code
  • Codex
  • Cursor
  • Gemini CLI
  • Security and science
  • Advanced
  View prompt

  Using RosettaCommons/RFdiffusion, scaffold residues <my motif range> of <my pdb> with contigs like 'contigmap.contigs=[5-15/A10-25/30-40]' and tell me how to check the motif stayed in place.

  Share Email me this

Quick start with RFdiffusion

1. Check you have what it needs: A clone of the repo plus the model weights downloaded into its models folder; Anaconda or Miniconda, and NVIDIA's SE(3)-Transformer installed from the env folder; An NVIDIA GPU; the provided environment file targets CUDA 11.1 and may need adapting.
2. Open RosettaCommons/RFdiffusion on GitHub and read the README and license.
3. Clone the repo with git clone https://github.com/RosettaCommons/RFdiffusion.git and download the weights into models as the README lists
4. Create the environment with conda env create -f env/SE3nv.yml and conda activate SE3nv, then install SE3Transformer and pip install -e . from the repo root
5. Run ./scripts/run_inference.py 'contigmap.contigs=[150-150]' inference.output_prefix=test_outputs/test inference.num_designs=10
6. Look at the .pdb outputs and the .trb metadata file for each design

These steps come from our top use case, Generate new protein backbones from scratch, which also has a copy-paste agent prompt.

Using the Deduped MCP, get the setup steps for RosettaCommons/RFdiffusion

claude mcp add --transport http deduped https://dedupedai.com/mcp

Best AI repos for Security and science

About this repo

• Who it is forProtein designers and computational biology teams exploring de novo backbones and binders.
• Why it is hot3.1k stars, picked up by one AI source we track
• Sourcegithub.com/RosettaCommons/RFdiffusion · Back to Hot repos

Requirements

• A clone of the repo plus the model weights downloaded into its models folder
• Anaconda or Miniconda, and NVIDIA's SE(3)-Transformer installed from the env folder
• An NVIDIA GPU; the provided environment file targets CUDA 11.1 and may need adapting
• Docker as an alternative to the conda setup, using the provided docker/Dockerfile

Related repos

• Trended earlier REPO huggingface/diffusers Diffusers Diffusers is Hugging Face's Python library for pretrained diffusion models that generate images, audio and even 3D molecule structures. It offers ready pipelines that run in a few lines of code, interchangeable noise schedulers that trade speed for quality, and pretrained model building blocks for your own diffusion systems, with access to more than 30,000 checkpoints on the Hub and guides for optimization and training.
• Trended earlier REPO worldbench/DiffusionOPSD DiffusionOPSD DiffusionOPSD is an external Python implementation of an on-policy self-distillation method for reward-guided post-training of diffusion models such as SD3.5-M and Z-Image-Turbo.
• Trended earlier REPO Biohub/esm Esm The esm package from Biohub (EvolutionaryScale) ships ESMC, a protein language model trained on billions of protein sequences, ESMFold2, a structure prediction model built on ESMC 6B that predicts all atom 3D structures from sequence, and sparse autoencoders that decompose ESMC representations into interpretable features. Models run locally from Hugging Face weights or through the Biohub Platform with an API token.