Overview
| Name | Ginkgo GDPa1 · aliases: GDPa1, Ginkgo GDPa1, AbDev competition |
|---|---|
| Full name | GDPa1 antibody developability dataset and the AbDev competition |
| Ambiguous names (not auto-linked) | AbDev |
| Family | Not a family entry. One dataset plus a one-off competition; no family members. |
| Domain | Antibodies (also: Proteins) |
| Inclusion | Supplementary entry |
| Type | A B · Public dataset plus a private held-out blind test |
| Evidence level | L4 · Blind test with hidden truth, but the held-out antibodies are existing clinical antibodies, not prospectively synthesised |
| Publisher | Ginkgo Datapoints, Ginkgo Bioworks, Hugging Face (Platform company) |
| First release | † partly verified Basis: Official announcement of the public dataset and the competition (2025-09-08); the 2025-06-13 dataset-object creation date is a gated object and is not used as a first release Note: Day precision still rests on the announcement page and stays flagged. source |
| Other milestones | |
| Latest update | † partly verified · data Basis: Dataset card changelog and the platform's last-modified time Dataset card updated to v1.4; before that: results paper 2026-02-22, competition closed 2025-11-18. Note: The dataset is gated and the changelog unreadable, so the v1.4 label is carried from an existing record. source The most recent sourced event, not a claim that nothing changed since. |
| Next expected | The organizers have announced no date for a next round. |
| Status | ◐ Low-frequency · Low frequency: the competition closed (2025-09-08 to 2025-11-18); the public leaderboard still runs and the dataset is at v1.4. |
| Scale | 246 public clinical antibodies with 10 assays; 80 private held-out antibodies; 5 properties predicted; 113 teams.
|
| Wet-lab refresh | Fresh experiments each round · The 80 held-out antibodies were measured specifically for the competition, once only; not a standing round. |
| Own wet lab needed to evaluate a new model | No, run it as a download |
| Models reported | 0 counted |
| Unverified fields | † first_release, latest_update, release_milestones.first_public_evidence, scale.items[2], scale.items[4], ranking.entries[2], ranking.entries[3] |
| As of | 2026-11-16 |
What it measures
- Task: Predict five developability properties from sequence, scored on 80 private held-out antibodies.
- Truth: Experimental measurements from one laboratory under uniform assays: hydrophobicity, polyreactivity, self-association, thermostability and titer.
- Primary metric: Spearman correlation per property
- Secondary metrics: Per-property prize standings
- Version traps: Distinguish GDPa1 cross-validation from the competition's private held-out protocol; the paper shows the two differ systematically.
Current ranking
Board
| Metric | Spearman correlation per property on the private held-out set |
|---|---|
| Eval set | AbDev competition 2025, 80 private held-out antibodies, 5 properties |
| Snapshot | |
| Board | https://huggingface.co/spaces/ginkgo-datapoints/abdev-leaderboard |
| Retrieved | 2026-11-16 |
Caveat. The competition closed 2025-11-18 and standings come from the results paper; the leaderboard Space errored on 2026-11-16 and was not loaded; no site model appears among the winners.
Shown in the overview table: Board
| Rank | Model | Score (verbatim) | Metric · eval set / protocol | Source type · date | Source and note |
|---|---|---|---|---|---|
| 1 | Anonymous | 0.708 | Spearman correlation per property on the private held-out set AbDev competition 2025, 80 private held-out antibodies, 5 properties | Board | source Not a site model; top-1 on hydrophobicity (HIC). |
| 1 | microcrisprtm2 | 0.392 | Spearman correlation per property on the private held-out set AbDev competition 2025, 80 private held-out antibodies, 5 properties | Board | source Not a site model; top-1 on thermostability (Tm2). |
| 1 | PR_CHO_NOV | 0.356 | Spearman correlation per property on the private held-out set AbDev competition 2025, 80 private held-out antibodies, 5 properties | Board | source Not a site model; top-1 on polyreactivity (abstract 0.356, Results 0.337; swapped with self-association between the two). |
| 1 | AbDevelop | 0.337 | Spearman correlation per property on the private held-out set AbDev competition 2025, 80 private held-out antibodies, 5 properties | Board | source Not a site model; top-1 on self-association (abstract 0.337, Results 0.356). |
| 1 | meta2 | 0.310 | Spearman correlation per property on the private held-out set AbDev competition 2025, 80 private held-out antibodies, 5 properties | Board | source Not a site model; top-1 on titer. |
Models reported
Grouped by relation type; each line shows its source type. Counted relations add up to 0. A pairing whose evidence rests only on this survey's own page is shown as unverified.
None. No model among the 112 has a recorded pairing with this entry.
Caveats
- The key negative result of the blind test: cross-validation correlations are systematically higher than held-out correlations.
- Only 246 training and 80 test antibodies, all clinical-stage, so extrapolation to early-stage or designed antibodies is untested.
- A one-off competition: the held-out set is exposed once it closes, so later work can only compare cross-validation scores.
- Winning methods differ by property; no single architecture wins across the board.
- Not a prospective synthesis test; the held-out antibodies are existing clinical antibodies.
How to use it
Request GDPa1 from the data platform (terms must be accepted), use the recommended stratified cross-validation split, and report Spearman per property for all five. The private held-out set was consumed by the competition and cannot be submitted to again; a real blind test needs new antibodies measured under the same assays, or joining the related consortium. State whether a number is cross-validation or the competition held-out set.
Pairs well with: AbBiBench · FLAb / FLAb2 · AIntibody · Polaris / ASAP / OpenADMET
Sources
- Competition and dataset announcement (official site) ·
- Competition results paper (mAbs 18(1)) (journal) ·
- GDPa1 dataset card (gated) (official site) ·
- Public leaderboard (leaderboard)
Corrections
5 corrections
| Field | Was | Now | Basis | Found |
|---|---|---|---|---|
| first_release | 2025-06-13 (dataset on HF); competition announced 2025-09-08 | 2025-09-08 | source | 2026-11-16 |
| first_release_basis | HF blog/competition launch with public GDPa1 data (HF repo object created 2025-06-13, likely private/gated earlier) | official announcement of the public GDPa1 dataset and AbDev competition, 2025-09-08. HF dataset object created 2025-06-13 (creation date, gated, not displayed as release). | source | 2026-11-16 |
| first_release | 2025-09-08 | 2025-06-13 (dataset on HF); competition announced 2025-09-08 | source | 2026-11-16 |
| scale | 246 public antibodies, 10 assays; 80 private holdout; 113 teams (presented as fully verified) | same figures, but 246/10 are verified on the dataset card while 80 and 113 come from the results paper abstract | source | 2026-11-16 |
| ranking.entries | polyreactivity 0.337 and self-association 0.356 | polyreactivity 0.356 and self-association 0.337 per the abstract; the Results section swaps the two | source | 2026-11-16 |
Part of the AI for Bio benchmarks survey · all 44 benchmarks · open in the explorer. Record as of 2026-11-16.