AI for Bio · Model

tFold

Antibody structure and design system: MSA-free structure prediction plus epitope-specific de novo design

AntibodiesBig-tech labChinaActive中文

Overview

NametFold · aliases: tFold, tFold-Ab, tFold-Ag
Full nameNo separate expanded name
Ambiguous names (not auto-linked)None
FamilyNot a family entry. Single-model entry, not a family
OrganizationTencent AI for Life Sciences Lab
Organization typeBig-tech lab
CountryChina
Model classAntibody structure and design system
DomainAntibodies
First release · preprint
Basis: bioRxiv v1 preprint (repository creation date not used) source
Other milestones
  • Preprint v1: · bioRxiv v1 source
  • Journal online: · Journal online publication (design pipeline) source
  • Code release: · GitHub v1.0 packaging release source
Latest update · journal
Basis: Journal online publication of the design pipeline
The design-pipeline paper was published; the last GitHub push is the 2025-03-14 packaging release source
The most recent sourced event, not a claim that nothing changed since.
StatusActive · Journal publication within 12 months
OpennessCode: Partly open
Weights: On request
GitHub states source and weights are provided but declares no standard open-source licence
Benchmarks reported0 counted · none of the 44
Wet-lab validation1 recorded campaign
Unverified fieldsNone
As of2026-11-16

What it does

An antibody structure and design system: predicts antibody structure without MSA, predicts antibody-antigen complexes, and combines virtual screening with epitope-specific de novo design; the online service sits on the company's drug-discovery platform.

Benchmarks reported

None of the 44 benchmarks. This model is on the zero-pairing list.

How it evaluates itself: SAbDab-22H2-Ab structure test (n=169); SAbDab-22H2-AbAg (n=99); Virtual screening; De novo design, 4 targets

Other evaluations (outside the 44)

  • Time-split antibody structure test (Own task set) Self-reported: 169 time-split antibody structures compared with general folding and antibody-specific models
  • Antibody-antigen docking test (Own task set) Self-reported: Docking success on 99 complexes; alone it trails a general co-folding model, and improves with ensembling or epitope input
  • Virtual screening (Own task set) Self-reported: Candidate pools for two targets ranked, with enrichment metrics reported by the developers

Developers report: Developers report MSA-free antibody structure prediction better than general folding models on antibody regions, and SPR-confirmed de novo binders on four targets

Independent evidence: No independent evidence found. No independent evaluation found

Training data

Group in Figure 7: Public data + wet lab for validation only.

ClassValueDetail
a. Public databasesYesPublic antibody structure data (2022-07 time split) and public sequences for the language model
b. Private or licensed dataNo
c. Own wet-lab data used for trainingNot disclosedOwn wet-lab training data not disclosed
d. Wet lab used only for validationYesPhage display and SPR validated four targets

Wet-lab validation

Every rate carries its numerator and denominator. Claims that could not be verified are shown as unverified, without numbers; different paper versions are separate entries.

De novo design, four targets (Nature Communications paper)
Targets 4 · Designs tested 10 · Hits — · Success approximate success rate 1.5-4.4% (no per-target breakdown) · Best affinity best PD-L1 KD 45 pM; best PD-1 KD 81.6 nM

Denominator basis: 10,000 Fab pairs synthesised per target, with 10 Fc-fusion antibodies finally measured by SPR; success about 1.5%–4.4% with no per-target breakdown
Verified in the published paper, lifting the earlier unverified flag; the site's old "~82 nM" should read 81.6 nM. The preprint previously cited as a tFold source actually belongs to IgGM, whose figures must not be attributed here

Self-reported · No sourced date · verified · source

Background

  • Organization: An in-house lab in Shenzhen funded by the company, with no separate funding
  • Funding: Not disclosed or not applicable
  • Products and partnerships: The online service sits on the company's drug-discovery platform; the sister system IgGM shares authors
  • Related models: IgGM / IgGM-FM, RFantibody, AlphaFold 3

Reading notes

  1. The site once listed the IgGM preprint as a source here; the figures must be kept apart
  2. Only the overall 1.5%–4.4% range exists, with no per-target numbers
  3. No results reported on any of the 44 benchmarks

Caveats

  1. No standard open-source licence is declared and the weight terms are unclear
  2. Structure and docking evaluations are self-built time-split sets

Sources

  1. PubMed/PMC record (journal)
  2. bioRxiv preprint (preprint)
  3. Crossref record 10.1038/s41467-025-67361-9 (journal)
  4. GitHub repository TencentAI4S/tfold (repository)
  5. Journal article DOI 10.1038/s41467-025-67361-9 (journal)

Corrections

2 corrections
FieldWasNowBasisFound
sourcesListed the IgGM preprint as a tFold sourceChanged to this model's journal paper; IgGM figures must not be attributed heresource2026-11-16
wetlab_validationBest PD-1 KD about 82 nM81.6 nM (published paper)source2026-11-16

Part of the AI for Bio benchmarks survey · all 112 models · open in the explorer. Record as of 2026-11-16.