RFdiffusion

RFdiffusion is a protein backbone diffusion project supporting unconditional generation, motif constraints and binder design.

Catalog updated · 2026-10-08

GitHub / Repository ↗Documentation ↗

Public link：https://chemaiatlas.com/models/rfdiffusion/

Claim this resource

Overview

Its inference scripts accept structural conditions such as motifs or targets. Backbone generation is distinct from subsequent sequence design and autonomous agent behavior.

Limitations

The documented environment requires adjustments for GPU, driver and CUDA differences. Generated designs need downstream assessment.

Key Features

Protein backbone generation
Motif-conditioned and binder design

Use Cases

Generate candidate backbones
Study conditional structure generation

How to Use

Follow the README to configure dependencies and obtain checkpoints, inspect an official example, and record the conditions used for inference.

Related resources

AIDDISON Explorer

Platforms

AIDDISON Explorer is a hosted drug-discovery platform that generates and ranks molecular candidates against target profiles, design constraints, predicted properties and synthetic feasibility.

Molecular Generation · Drug Discovery

Updated 2026-10-06

Chemistry42 is a small-molecule discovery platform combining generative design, retrosynthesis, ADMET and selectivity prediction, and physics-based prioritization for hit identification and lead optimization.

Molecular Generation · Drug Discovery

Updated 2026-10-05

Equivariant Diffusion Models

Model

Official research code for E(3)-equivariant diffusion models that generate 3D molecules, with QM9 and GEOM-Drugs training workflows, sample analysis, and property-conditioned generation.

Open sourcePython

Molecular Generation

Updated 2026-10-05

FEgrow

Open Source

FEgrow supports interactive ligand-series construction for free-energy preparation, with documented active-learning examples and Dask-based acceleration for molecular design workflows.

Open source

Molecular Generation · Drug Discovery

Updated 2026-10-05

GeoDiff

Model

GeoDiff is a geometric diffusion model for molecular conformation generation, with official code for GEOM-based training, checkpoint sampling, and conformation and property evaluation.

Open sourcePython

Molecular Generation · Computational Chemistry

Updated 2026-10-05

GEOM

Dataset

GEOM provides 37 million energy- and statistical-weight-annotated molecular conformations for over 450,000 molecules, with MessagePack data, RDKit objects, and loading and analysis tutorials.

Python

Molecular Generation · Computational Chemistry

Updated 2026-10-05

Works with

Used in Recipes

Community

Protein Backbone to Sequence with RFdiffusion and ProteinMPNN

Generate a small monomer backbone with RFdiffusion, pass its PDB coordinates to ProteinMPNN, and retain paired structures, sequences and provenance for later validation.

RFdiffusion + ProteinMPNN

Protein & Drug Research

Level: Advanced Cost: Free Privacy: Local ~90 min

Python

View Setup →

Related guides

Models

Protein Design with AI: Backbone, Sequence, and Prediction

Distinguish RFdiffusion backbone generation, ProteinMPNN sequence design, and Boltz prediction, with explicit handoff and validation boundaries.

Oct 8, 2026 · 3 min read