PATCHR Logo
v1.0.0 Released — Open Source (MIT)

PATCHR

Diffusion-based molecular structure inpainting

for Protein, RNA, DNA, and multi-chain complexes

1.78 Å
Backbone RMSD
99.4%
Connectivity Pass
All-atom
Full Resolution
Key Capabilities

Complete Molecular Inpainting Platform

PATCHR uses synchronized rigid template tracking and local refinement denoising to achieve state-of-the-art accuracy while preserving your experimental coordinates exactly as-is.

End-to-End Workflow

From PDB structure to completed model in Patchr Studio

Loading demo...

Structure Inpainting

Fill in missing residues and atoms using diffusion-based generative models with template conditioning.

Protein, DNA, RNA & Complexes

Works with proteins, nucleic acids, protein-ligand complexes, and multi-chain assemblies.

All-Atom Resolution

Generates complete all-atom structures, not just backbone traces. 1.78 Å Cα RMSD on benchmarks.

Simulation-Ready Output

Direct export to GROMACS, AMBER, and OpenMM for molecular dynamics simulations.

Dual Backend Support

Choose between Boltz-2 and Protenix backends. ~10s inference for 200-residue proteins.

CLI + Desktop GUI

Full command-line interface and Patchr Studio desktop app with Mol* 3D viewer integration.

Performance

Benchmark Results

Evaluated on 940 PDB40 structures with artificially introduced gaps mirroring real PDB missing-region statistics.

Method Comparison

RMSD (Å) on missing residues — lower is better

MethodTypeCα RMSDAll-atom
PATCHR (full)All-atom1.782.54
Boltz-2 (unmodified)All-atom11.1911.93
Boltz-2 + template + steeringAll-atom3.223.89
RFdiffusion2All-atom9.1910.20
RFdiffusionBackbone2.04

Structural Context Accuracy

Cα RMSD by secondary structure and solvent accessibility

Helix0.30 Å
Strand0.26 Å
Loop0.85 Å
Buried0.39 Å
Intermediate0.65 Å
Surface1.01 Å
1.78 Å
Backbone Cα RMSD
2.54 Å
All-atom RMSD
99.4%
Connectivity Pass Rate
940
Benchmark Structures
v1.0.0 Available Now

Get PATCHR

Free and open source under the MIT license. Download the desktop app, install via pip, or run on Google Colab.

Quick Start

$git clone https://github.com/DeepFoldProtein/patchr.git
$cd patchr && pip install -e .
$patchr template 1TON all
$patchr predict examples/inpainting/1ton_AB.yaml --out_dir results