alterlab-rfdiffusion

RFdiffusion (de-novo backbone generation)

Overview

RFdiffusion (Watson et al., Nature 2023; RosettaCommons/RFdiffusion) is a diffusion model that generates protein backbones — new 3D structures, not sequences. It supports unconditional generation, motif scaffolding (build a fold around a fixed functional motif), binder design (generate a backbone that binds a target surface), and symmetric assemblies. It is the structure-generation step that starts the de-novo design pipeline; alterlab-proteinmpnn then designs sequences for the backbone and alterlab-alphafold validates them.

When to Use This Skill

Use this skill when the user wants to:

• Generate a novel protein backbone from scratch (unconditional).
• Scaffold a functional motif (e.g. a binding loop / catalytic geometry) into a new fold.
• Design a binder backbone against a given target protein surface / hotspots.
• Build symmetric oligomers (cyclic/dihedral) as backbones.

Does NOT Trigger

Scenario	Use instead
Design the sequence for an existing backbone	alterlab-proteinmpnn
Design a pocket sequence with a ligand/metal present	alterlab-ligandmpnn
Fold a known sequence into a structure	alterlab-alphafold
Generative multimodal (sequence+structure) design	alterlab-esm

Core Capabilities

1. Unconditional generation

# RosettaCommons/RFdiffusion — run_inference.py drives generation (Hydra config).
# It lives in the repo's scripts directory; TODO(verify) config keys/version.
python run_inference.py \
  'contigmap.contigs=[100-100]' \
  inference.output_prefix=out/uncond \
  inference.num_designs=10

contigmap.contigs specifies what to build (here, a 100-residue monomer). Outputs backbone PDBs with no sequence.

2. Motif scaffolding

Fix a functional motif (residues from an input PDB) and let RFdiffusion build a supporting fold around it — the way to transplant a binding/catalytic geometry into a new, stable scaffold. Contig syntax mixes fixed motif ranges with generated segments (TODO(verify) the exact contig grammar for your version).