bio-modelsBiological Foundation Models
Biological AI Models · Antibody Design

DiffAb

By Tsinghua University (AIR)

Diffusion-based generative model for antibody CDR design and antigen conditioning

DiffAb is an SE(3)-equivariant diffusion model that jointly generates the 3D structure and amino acid sequence of antibody CDR loops conditioned on target antigen epitopes.

Joint structure-sequence diffusion on antibody CDR-H3 and light chain loopsAntigen-conditioned generation with physical clash penaltiesBenchmark evaluations showing higher affinity and diversity than RosettaAntibodyOpen source codebase with PyTorch and PyG implementations
Compare

ℹ️ No direct buying or access link is currently recorded. This product remains available for research and comparison.

Report incorrect information or a broken link →

Overview

DiffAb is an SE(3)-equivariant diffusion model that jointly generates the 3D structure and amino acid sequence of antibody CDR loops conditioned on target antigen epitopes.

Information checked against an official source; not a hands-on test. Source · Last reviewed: 20/09/2026, 11:10:15

Key Features

  • Joint structure-sequence diffusion on antibody CDR-H3 and light chain loops
  • Antigen-conditioned generation with physical clash penalties
  • Benchmark evaluations showing higher affinity and diversity than RosettaAntibody
  • Open source codebase with PyTorch and PyG implementations
Interactive 3D Structure

DiffAb Predicted Complex

Streams real 3D atomic coordinates from RCSB Protein Data Bank
⇄ Drag to rotate · Scroll to zoom
pLDDT / B-Factor:
>90 Very high 70-90 Confident 50-70 Low <50 Very low

Academic Context & Research Evidence

Biological & Workflow Fit

Biological Application
Antibody CDR design, therapeutic optimization, and paratope engineering
Research Workflow
Target antigen PDB -> generate complementary CDR conformations and sequences
Compute & Hardware
1x GPU (>= 16GB VRAM)
Licensing & Academic Use
MIT License
Documented Evidence
View validation publication / source ↗

Cite this Tool

Use this citation format when referencing DiffAb in scientific publications and benchmark papers.

@software{diffab_2026,
  title = {{DiffAb}},
  author = {{Tsinghua University (AIR)}},
  year = {2026},
  url = {https://github.com/luost26/diffab},
  note = {Indexed on aibioatlas - AI for Biology and Drug Discovery}
}

Peer-Reviewed Literature & Preprints

Live scientific citations streamed from Europe PMC and PubMed for DiffAb.

⏳ Fetching real-time literature from Europe PMC & PubMed...

Technical / Product Information

Missing values mean the catalog has no recorded information. They do not mean a feature is absent.

Entry typeAI Model
Access modeOpen Source
AI roleEquivariant Generative Diffusion
Input dataNot recorded
Output dataNot recorded
Licence conditionsMIT License
Commercial eligibilityOpen source release
Compute requirements1x GPU (>= 16GB VRAM)
ValidationNot recorded
TypeEquivariant diffusion model
Intended useNot recorded
CompatibilityNot recorded
ManufacturerTsinghua University
Biological applicationAntibody CDR design, therapeutic optimization, and paratope engineering
Research workflowTarget antigen PDB -> generate complementary CDR conformations and sequences
Evidence levelPeer-reviewed research (ICLR 2023)
Integration evidencehttps://github.com/luost26/diffab
Laboratory handoffCompatible with phage display and high-throughput antibody expression
AvailabilityAvailable on GitHub
Price / accessFree Open Source

Research fit & compatibility

No software–hardware integration has been verified for this entry yet. Explore documented research workflows.

BEFORE YOU CHOOSE

Evaluate Biological AI Models

  • Which input, output and scientific task does the selected version support?
  • Is this a model, supporting tool, commercial platform or research prototype?
  • Verify the code, weights, data licence and independent validation before selecting a workflow.

Alternatives

Similar entries from the same category.

FAQ

Where is this product available?

Available on GitHub

How is pricing handled?

Prices reflect the source at its last check. Confirm current pricing and regional availability on the official site.

Share this entry with your lab or research teamSpread reproducible science across your network
𝕏 Postin LinkedIn

Peer Reviews & Community Ratings

Feedback from researchers and computational biologists evaluating DiffAb.

5.0
★★★★★Based on 0 researcher evaluations
Biological Accuracy
4.8/5
Ease of Installation
4.3/5
Documentation & Code
4.6/5