| name | rfdiffusion |
| description | Generate de novo protein backbones with RFdiffusion for protein-target binders, hotspot-conditioned interfaces, motif scaffolding, partial diffusion, or symmetric assemblies. Use this skill when a design workflow needs reproducible RFdiffusion contigs, residue mappings, checkpoints, seeds, batch execution, and handoff to ProteinMPNN plus independent structure validation. RFdiffusion generates backbones; it does not validate folding or binding.
|
| license | MIT |
| origin | openai4s |
| category | biomodels |
| requirements | ["gpu"] |
| capabilities | {"network":{"mode":"raw_required","domains":[]}} |
| metadata | {"display-name":"RFdiffusion","third_party":[{"kind":"recipe","name":"Adaptyv protein-design-skills RFdiffusion recipe","license":"MIT","terms_url":"https://github.com/adaptyvbio/protein-design-skills/blob/b231232025e3db41e9c637abc1e8082e915f6cb1/LICENSE"},{"kind":"code-and-weights","name":"RFdiffusion","license":"BSD-3-Clause","terms_url":"https://github.com/RosettaCommons/RFdiffusion/blob/main/LICENSE"}]} |
RFdiffusion
Use RFdiffusion for the backbone-generation stage of a protein-design
workflow. Treat its output as a structural proposal, not as evidence that a
sequence folds or binds. Design sequences afterward with proteinmpnn (or
ligandmpnn when non-protein atoms must be visible), then validate both the
isolated design and the target–design complex with an independent predictor
such as boltz, chai1, or alphafold2.
The adapted recipe is MIT-licensed. The upstream RFdiffusion code and the
model weights referenced by its README are BSD-3-Clause; record the exact
upstream commit and checkpoint digest used by each run.
Preflight: freeze the design contract
Before inference:
- Preserve the original chain IDs and residue numbers. Write an explicit map
if the input is renumbered, cropped, or has insertion codes.
- Audit missing residues/atoms, alternate locations, non-standard residues,
and biological assembly choice. Do not silently remove cofactors or chains.
- For binder design, confirm proposed hotspot residues are surface-accessible
and belong to the intended target chain. A typical pilot uses 3–6 spatially
coherent hotspots, but the biological interface determines the final set.
- Freeze the target PDB digest, RFdiffusion commit, checkpoint digest,
contig string, hotspot list, seed policy, number of designs, and output
prefix in a machine-readable manifest.
- Keep target-only coordinates separate from any withheld reference binder.
Do not leak a reference complex into generation or validation.
Do not trim a target merely to make inference cheaper unless the retained
construct is biologically justified and the residue map is preserved.
Install and invoke the official runner
RFdiffusion is a source repository rather than an OpenAI4S sidecar. Prepare a
pinned GPU environment, clone a fixed revision of the official repository,
install it there, and download the documented checkpoint. Verify every
download before starting a campaign. Follow the upstream CUDA/PyTorch/DGL
compatibility instructions for the selected revision; do not improvise a
version matrix from this recipe.
Do not install RFdiffusion into OpenAI4S's shared struct environment. That
environment intentionally targets portable Python 3.13 with a CPU PyTorch
build, whereas upstream RFdiffusion publishes a Python 3.9, CUDA-specific
PyTorch/DGL stack. Use a pinned dedicated conda environment or the official
RFdiffusion Docker image pinned by digest. openai4s setup --profile full
creates the shared struct environment; it does not provision RFdiffusion,
GPU drivers, model weights, or a container image.
Run scripts from the RFdiffusion repository root. The official inference entry
point is :
