/rfdiffusion

name: rfdiffusion
description: >
  Generate protein backbones using RFdiffusion, a diffusion-based generative
  model for de novo protein structure generation. Use this skill when:
  (1) Designing binder scaffolds for a target protein,
  (2) Generating novel protein backbones from scratch,
  (3) Scaffolding functional motifs into new proteins,
  (4) Specifying hotspot residues for interface design,
  (5) Creating symmetric oligomers.

  For sequence design after backbone generation, use proteinmpnn.
  For structure validation, use alphafold or chai.
  For QC thresholds, use protein-qc.
license: MIT
category: design-tools
tags: [structure-design, diffusion, backbone, binder]
proteinbase_slug: rfdiffusion
proteinbase_url: https://proteinbase.com/design-methods/rfdiffusion

RFdiffusion Backbone Generation

Prerequisites

| Requirement | Minimum | Recommended | |-------------|---------|-------------| | Python | 3.9+ | 3.10 | | CUDA | 11.7+ | 12.0+ | | GPU VRAM | 16GB | 24GB (A10G) | | RAM | 16GB | 32GB |

How to run

RFdiffusion is not in biomodals, so run it from the official RosettaCommons repo or its Docker image, not through Modal.

Local installation (official repo)

git clone https://github.com/RosettaCommons/RFdiffusion.git
cd RFdiffusion

# Conda env including the required NVIDIA SE(3)-Transformer
conda env create -f env/SE3nv.yml
conda activate SE3nv
cd env/SE3Transformer && pip install . && cd ../..
pip install -e .

# Download weights (per-file hashed paths; see the repo README for the full list)
mkdir -p models
wget -P models http://files.ipd.uw.edu/pub/RFdiffusion/e29311f6f1bf1af907f9ef9f44b8328b/Complex_base_ckpt.pt

# Binder design run; single-quote the hydra args so the shell does not split [] or ,
./scripts/run_inference.py \
  inference.input_pdb=target.pdb \
  'contigmap.contigs=[A1-150/0 70-100]' \
  'ppi.hotspot_res=[A45,A67,A89]' \
  inference.num_designs=100

A RosettaCommons-maintained Docker image is also available from the repo README. After backbone generation, design sequences with `proteinmpnn`.

Config Schema (Hydra)

Contigmap Syntax

# De novo single chain (50-100 residues)
contigmap.contigs=[50-100]

# Binder + target (A = target chain, fixed with /0)
contigmap.contigs=[A1-150/0 70-100]

# Motif scaffolding (preserve residues, /0 = fixed)
contigmap.contigs=[20-40/0 A10-30/0 20-40]

# Multi-chain binder
contigmap.contigs=[A1-100/0 B1-100/0 60-80]

# Variable length ranges
contigmap.contigs=[A1-150/0 50-100]  # Binder 50-100 AA

Hotspot Specification

# Residues for interface (chain + resnum, no spaces)
ppi.hotspot_res=[A45,A67,A89]

Common mistakes

Contig Syntax

✅ **Correct**:

'contigmap.contigs=[A1-150/0 70-100]'  # Target fixed (/0), binder variable

Single-quote the whole argument so the shell does not split on the space inside the brackets.

❌ **Wrong**:

contigmap.contigs=[A1-150 70-100]     # Missing /0 - target will move!
contigmap.contigs=[A1-150/0 70-100]   # Unquoted: shell splits on the space
contigmap.contigs=[A1-150/0, 70-100]  # Extra comma changes the contig string

Hotspot Residues

✅ **Correct**:

'ppi.hotspot_res=[A45,A67,A89]'      # Chain letter + residue number, whole arg quoted

❌ **Wrong**:

ppi.hotspot_res=[45,67,89]           # Missing chain letter
'ppi.hotspot_res=[A45, A67, A89]'    # Spaces inside the list break parsing

Complete Parameter Reference

Core Parameters

| Parameter | Default | Range | Description | |-----------|---------|-------|-------------| | `inference.num_designs` | 10 | 1-10000 | Number of designs to generate | | `inference.input_pdb` | - | path | Target structure file | | `inference.output_prefix` | output | string | Output filename prefix | | `diffuser.T` | 50 | 20-200 | Diffusion timesteps | | `denoiser.noise_scale_ca` | 1.0 | 0.0-2.0 | CA atom noise (0.5-0.8 = conservative) | | `denoiser.noise_scale_frame` | 1.0 | 0.0-2.0 | Frame noise | | `inference.ckpt_override_path` | - | path | Model checkpoint | | `potentials.guide_scale` | 1.0 | 0.1-10 | Guidance strength | | `potentials.guide_decay` | constant | string | Decay type |

Advanced Parameters

| Parameter | Default | Description | |-----------|---------|-------------| | `diffuser.partial_T` | None | Start diffusion from timestep T (partial diffusion) | | `contigmap.inpaint_str` | None | Sequence positions to inpaint | | `scaffoldguided.scaffoldguided` | false | Enable scaffold-guided generation | | `scaffoldguided.target_pdb` | None | Scaffold template PDB | | `ppi.binderlen` | None | Specify exact binder length |

Symmetry Parameters

| Parameter | Default | Description | |-----------|---------|-------------| | `symmetry.symmetry` | None | Symmetry type (C2, C3, C4, D2, etc.) | | `symmetry.recenter` | true | Recenter symmetric assembly | | `symmetry.radius` | None | Radius constraint for symmetric assembly |

Fold Conditioning

| Parameter | Default | Description | |-----------|---------|-------------| | `contigmap.provide_seq` | None | Provide sequence for fold conditioning | | `contigmap.inpaint_seq` | None | Positions for sequence inpainting |

Model Checkpoints

| Checkpoint | Use Case | |------------|----------| | `Complex_base_ckpt.pt` | Binder design (default) | | `Base_ckpt.pt` | De novo monomers | | `ActiveSite_ckpt.pt` | Active site scaffolding | | `InpaintSeq_ckpt.pt` | Sequence inpainting |

Common workflows

Binder Design

1. Prepare target PDB (trim to binding region + 10A buffer) 2. Identify 3-6 hotspot residues (exposed, conserved) 3. Generate 100-500 backbones 4. Pass to proteinmpnn for sequence design

Motif Scaffolding

1. Extract motif coordinates 2. Use `/0` to fix motif in contigmap 3. Generate surrounding scaffold 4. Validate motif preservation (RMSD < 1.5A)

Symmetric Oligomers

# C3 symmetric trimer
python run_inference.py \
  symmetry.symmetry=C3 \
  contigmap.contigs=[