Version 6.0 • January 2026

DADB-v1.0:
A Therapeutic Decathlon

The first comprehensive benchmark for de novo antibody design that measures what actually matters: binding, structure, developability, and immunogenicity.

📄
Read the Full Scientific Paper

25 pages • 5 platforms • Full methodology

⬇️ Download PDF

The Affinity Trap

Current benchmarks optimize for binding alone, creating a dangerous blind spot. A 1 pM binder that aggregates at 37°C or triggers an immune response is clinically worthless.

🎯

Binding Only

Existing benchmarks measure affinity but ignore the 85% of candidates that fail downstream gates.

🧪

Developability Crisis

Aggregation, poor solubility, and low thermostability kill programs after millions in investment.

⚠️

Immunogenicity Blindspot

25% of late-stage clinical failures are due to anti-drug antibodies—yet no benchmark measures this.

🔒

Proprietary Silos

4 of 5 major platforms are closed-source, preventing fair comparison and reproducibility.

The Therapeutic Decathlon

DADB-v1.0 introduces a composite scoring system that treats antibody design as a multi-event competition—because real drug discovery is never single-metric.

🎪 The Formula

DADB Score = (0.40 × Binding) + (0.25 × Structure) + (0.20 × Developability) + (0.15 × Immunogenicity)

40%
Binding

Affinity, kinetics, specificity

25%
Structure

RMSD, CDR-H3 accuracy

20%
Developability

GATEKEEPER
Tm, aggregation, solubility

15%
Immunogenicity

T-cell assays, cytokine release

🔐 The Gatekeeper Architecture

Developability acts as a binary gate: fail any threshold (Tm < 60°C, aggregation > 5%, solubility < 10 mg/mL, hydrophobicity flag) and receive zero for that component—regardless of picomolar affinity. No more pyrrhic victories.

Five Platforms, One Benchmark

DADB-v1.0 enables fair comparison across both open-source and proprietary platforms through standardized APIs and containerized evaluation.

JAM-2

Nabla Bio

Strength: Highest consistent hit rates (39% VHH-Fc)

⚡ 57% pass all 4 developability criteria

Chai-2

Chai Discovery

Strength: Most extensive cryo-EM validation

🔬 5 structures, 0.41–1.7 Å RMSD

Origin-1

AbSci

Strength: Zero-prior epitope targeting

🎯 4/10 novel epitope successes

RFAntibody

Baker Lab

Strength: Only fully open-source platform

🔓 MIT License, full reproducibility

The Immunogenicity Gap: Despite causing 25% of late-stage failures, Latent-X2 is the only platform with published human immunogenicity data. DADB-v1.0 makes this a scored component for the first time.

Roadmap

From public validation to clinical correlation—a phased approach to benchmark maturity.

Q1 2026

v1.0 Launch

5-platform comparison, immunogenicity track

Q2 2026

v1.5

Bispecifics, Fc engineering

Q4 2026

v2.0

ADC track, linker-payload optimization

2027

v2.5

Cell therapy, TCR design

2028

v3.0

In vivo prediction, clinical correlation

Join the Consortium

DADB's success depends on community participation. Whether you're an academic lab, AI platform, or biopharma partner, there's a role for you.

🏫 Academic Labs

  • Submit open-source models
  • Contribute unpublished structures
  • Validate predictions experimentally
  • Join the Steering Committee

🤖 Platform Providers

  • API-based evaluation (IP-protected)
  • Earn "DADB-Validated" certification
  • Leaderboard recognition
  • Consortium membership

💊 Biopharma Partners

  • Validate predictions vs. clinical outcomes
  • Share developability datasets
  • Early access to benchmark targets
  • Methods paper co-authorship
✉️ Contact the Consortium

Private test set targets are confidential and shared only under NDA

📑

Read the Full Proposal

Download the complete 25-page scientific paper with detailed methodology, platform comparisons, scoring formulas, and benchmark specifications.

📥 Download PDF (341 KB) 👁️ View in Browser

Version 6.0 • Security-reviewed and scientifically corrected • January 2026