◎aibioatlasExplore · Compare · Discover
Home›Biological AI Models›AntiFold
bio-modelsBiological Foundation Models
Biological AI Models · Antibody Design

AntiFold

By University of Oxford (OPIG) →

Antibody-specific inverse folding and sequence optimization

AntiFold is an inverse folding model fine-tuned specifically on antibody variable domain structures, providing superior sequence recovery and natural humanness scores for CDR design.

Specialized inverse folding model for antibody heavy and light chainsTrained on non-redundant experimental structures from SAbDab and AlphaFold-Multimer predictionsGenerates antibody sequence libraries with high stability and developability profilesFast inference suitable for screening millions of candidate CDR loops
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

AntiFold is an inverse folding model fine-tuned specifically on antibody variable domain structures, providing superior sequence recovery and natural humanness scores for CDR design.

Information checked against an official source; not a hands-on test. Source · Last reviewed: 20/09/2026, 11:09:40

Key Features

  • Specialized inverse folding model for antibody heavy and light chains
  • Trained on non-redundant experimental structures from SAbDab and AlphaFold-Multimer predictions
  • Generates antibody sequence libraries with high stability and developability profiles
  • Fast inference suitable for screening millions of candidate CDR loops
Interactive 3D Structure

AntiFold 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 humanization, CDR affinity maturation, and de novo paratope design
Research Workflow
Input antibody backbone structure -> output high-affinity, humanized sequence candidates
Compute & Hardware
1x GPU or multi-core CPU
Licensing & Academic Use
BSD-3-Clause
Documented Evidence
View validation publication / source ↗

Cite this Tool

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

@software{antifold_2026,
  title = {{AntiFold}},
  author = {{University of Oxford (OPIG)}},
  year = {2026},
  url = {https://github.com/oxpig/AntiFold},
  note = {Indexed on aibioatlas - AI for Biology and Drug Discovery}
}

Peer-Reviewed Literature & Preprints

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

⏳ 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 roleAntibody Optimization
Input dataNot recorded
Output dataNot recorded
Licence conditionsBSD-3-Clause
Commercial eligibilityOpen source permissive
Compute requirements1x GPU or multi-core CPU
ValidationNot recorded
TypeAntibody inverse folding model
Intended useNot recorded
CompatibilityNot recorded
ManufacturerUniversity of Oxford
Biological applicationAntibody humanization, CDR affinity maturation, and de novo paratope design
Research workflowInput antibody backbone structure -> output high-affinity, humanized sequence candidates
Evidence levelPeer-reviewed publication (Nature Communications 2024)
Integration evidencehttps://github.com/oxpig/AntiFold
Laboratory handoffCandidates compatible with high-throughput antibody expression and SPR binding assays
AvailabilityAvailable on GitHub and PyPI
Price / accessFree Open Source

Research fit & compatibility

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

Gallery & resources

No licensed product photograph recorded for AntiFold yet. Visit the official resource below for manufacturer imagery.

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.
Selection guide →Find alternatives →

Alternatives

Similar entries from the same category.

FAQ

Where is this product available?

Available on GitHub and PyPI

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 AntiFold.

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