# RosettaCommons/RFdiffusion

Code for running RFdiffusion

Repository: https://github.com/RosettaCommons/RFdiffusion
Canonical: https://ross.abutalabs.com/products/rfdiffusion
Language: Python
License: NOASSERTION
License Family: other
Last push: 2026-07-15T18:08:01+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 92, release rhythm 8, longevity 89
- inputs: {"age_days": 1254, "days_push": 49, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3026, forks 637 (observed 2026-08-28T04:07:38.677955+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, simulation, data-generation
- domain: bioinformatics, deep-learning, artificial-intelligence
- platform: python
- tags: protein-design, diffusion-models, computational-biology, structural-biology, de-novo-protein-design, binder-design, motif-scaffolding, linux, docker, gpu

## Member repositories
- RosettaCommons/RFdiffusion (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:38.677955+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:29:52.856467+00:00, confidence not recorded.
  - readme: https://github.com/RosettaCommons/RFdiffusion (fetched 2026-08-28T04:07:38.677955+00:00, sha 4b8e2c8d6f5f)
- Data as of 2026-08-30T08:39:29.467469+00:00.