RosettaCommons/RFdiffusion

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

3026 stars · 637 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

RFdiffusion is an open-source method for de novo protein structure generation using diffusion models, with or without conditional information such as motifs or targets. It supports a range of protein design challenges including motif scaffolding, symmetric oligomer generation, and binder design.

Use cases

• generate novel protein structures from scratch
• scaffold a functional motif into a new protein backbone
• design binders to a target protein
• generate symmetric protein oligomers like cyclic or dihedral assemblies
• sample variations around an existing design with partial diffusion
• design macrocyclic peptides

When to choose

• you need de novo protein backbones for a design campaign
• you have a functional motif that needs a supporting scaffold
• you want to design binders or symmetric assemblies computationally

When to avoid

• you need general-purpose image or audio diffusion models
• you lack GPU resources or bioinformatics background
• you need a polished GUI application rather than scripts and notebooks

Facets

library · maturity active

machine-learning deep-learning simulation data-generation bioinformatics deep-learning artificial-intelligence python protein-design diffusion-models computational-biology structural-biology de-novo-protein-design binder-design motif-scaffolding linux docker gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="RosettaCommons/RFdiffusion")