Overview
| Name | Protenix · aliases: Protenix, Protenix-v1, Protenix-v2 |
|---|---|
| Full name | Official materials use Protenix; the companion tools are named PXDesign and PXMeter |
| Ambiguous names (not auto-linked) | Protenix-Mini |
| Family | Not a family entry. The v0.5 to v2 line is one record; PXDesign and PXMeter are companion tools and SeedFold has its own record |
| Organization | ByteDance Seed, ByteDance Seed AI for Science |
| Organization type | Big-tech lab |
| Country | China |
| Model class | Co-folding (plus the design tool PXDesign) |
| Domain | Structure & co-folding |
| First release | † partly verified · code release Basis: First GitHub release v0.1.0; preprint 2025-01-11; the repository creation date is excluded by policy Note: A possible 2024-11 announcement was not checked this round (partially verified) source |
| Other milestones | |
| Latest update | · new version Basis: GitHub release v2.0.0 v2 released with improved antibody-antigen prediction and proprietary weights not under an open licence; later commits are docs and maintenance source The most recent sourced event, not a claim that nothing changed since. |
| Status | Active · A new version in 2026-04 with maintenance commits since |
| Openness | Code: Partly open · Apache-2.0 Weights: Closed · v1 weights open; v2 weights proprietary, not under an open licence Code is Apache-2.0; v1 weights are open while v2 weights are proprietary and not released under an open licence, so third parties cannot re-check the new version |
| Benchmarks reported | 4 counted (board 1, self 1, modified protocol 1, retrospective 1, unconfirmed 1) |
| Wet-lab validation | 1 recorded campaign |
| Unverified fields | † first_release, release_milestones.weights_release, benchmarks_reported[1], background.products_partnerships |
| As of | 2026-11-16 |
What it does
An open reproduction and extension of AlphaFold 3 aiming to match or beat it under the same data cutoff, with about 368M parameters in v1 and 464M in v2 plus template and RNA alignment features. Unlike OpenFold3 it uses public data only, and unlike Boltz-2 it has no affinity head.
Benchmarks reported
Every row is one pairing from the survey's relation file; a score belongs to the benchmark page's ranking, where it is shown with metric, eval set, source type and date. 4 of 5 pairings are counted.
| Benchmark | Relation | Eval set / protocol | Source type | Note and evidence |
|---|---|---|---|---|
| 31 FoldBench | Official leaderboard or results | maintainer leaderboard | Board | Maintainer leaderboard · evidence |
| 05 PoseBusters | Developer report, official protocol | official set, early version only (via the Mini paper) | Self-reported | Only an early version's table; current versions report no score on this set, so the matrix cell overstated it †unverified · evidence |
| 30 PLINDER / PINDER / Runs N' Poses | Developer report, modified protocol | v1 self-report on the subset where all compared models have results (figure only) | Self-reported | v1 self-report on the subset where all models have results, figure only; plus a third-party figure in the Pearl paper †partly verified · evidence |
| 33 PoseX | Retrospective dataset use | self-docking set, benchmark authors' run | Third-party | PoseX authors ran Protenix under the same protocol †partly verified · evidence |
| 12 DUD-E / LIT-PCBA | Unconfirmed (not counted) | — | Unconfirmed source | Second-hand LIT-PCBA mention, no numbers †disputed · no source link |
Other evaluations (outside the 44)
- Own ligand evaluation set (companion tool) (Own task set) Self-reported: A 623-entry in-house set scored with public validity criteria after manual removal of experimental artefacts; scores are not shown here
- The design-side tool PXDesign (Wet-lab validation) Self-reported: The wet-lab validation belongs to the companion design tool and is not a result of the structure-prediction model
- Third-party tables and second-hand paraphrase (third party evaluation) Third-party: Several third-party tables list v1 alongside the contemporary closed model, partly relayed by second-hand platforms under inconsistent protocols
Developers report: parity with the contemporary closed model under the same data cutoff, clearly improved antibody-antigen prediction in v2, and five seeds achieving what v1 needed a thousand seeds for.
Independent evidence: Third-party re-runs (the benchmark's authors and one comparison paper) place it below the open controls it is compared with, and with v2 weights proprietary later versions cannot be re-checked by third parties.
Training data
Group in Figure 7: Public data + wet lab for validation only.
| Class | Value | Detail |
|---|---|---|
| a. Public databases | Yes | PDB (cutoff 2021-09-30, plus a 2025-06-30 version), alignments and distillation data; the training data and alignment pipeline are open source |
| b. Private or licensed data | No | |
| c. Own wet-lab data used for training | No | |
| d. Wet lab used only for validation | Yes | Wet lab validates only the companion design tool PXDesign; the structure-prediction side has none source |
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.
Denominator basis: Seven targets, six of which yielded nanomolar hits; per-target denominators were not opened in primary material
The range published earlier came from a stale repository README; corrected to the design preprint and cited to the design paper rather than the model repository; developer-reported, not an independent replication
Background
- Organization: It comes from a large internet company's foundation-model research division, whose science agenda spans biological foundation models, quantum chemistry and molecular dynamics, funded from the company's internal budget.
- Funding: Big-tech internal budget, no separate fundraising
- Products and partnerships: The series and its companion design and evaluation tools are open, and the same company also has SeedFold; a 2026-06 report says it is spinning out an AI drug-discovery unit of about 50 people with the structure team joining, without stating whether this series moves (second-hand, unverified).
- Related models: AlphaFold 3, OpenFold3, RF3, Boltz-2, SeedFold
Reading notes
- On the maintainer board v1 sits in the same band as the contemporary closed model under official framing, which supports parity but not superiority.
- With v2 weights closed, later versions rest on official figures alone and cannot be re-checked by third parties.
- The only summary figure available on the site comes from a third-party paper, as the official v1 report gives binned figures only.
- The developers prefer their own off-site evaluations, which sit closer to antibody and RNA use cases and must not be mixed with site entries.
Caveats
- The v2 weights are proprietary, so openness must be read separately for code and weights.
- The public pose-set pairing holds only for an early version and must carry a version qualifier.
- The wet-lab figures belong to the companion design tool, not to the structure-prediction model.
- One pairing rests only on the site's own page (unverified).
- The report on the company's spin-out is second-hand and does not say whether Protenix moves with it (unverified).
Sources
- Official repository (repository)
- Official repository releases (repository)
- The model's preprint (preprint)
- Design tool preprint and project page (preprint)
- The team's own compact-version paper (preprint)
- Third-party re-run paper (third-party paper)
- Re-run paper by the benchmark's authors (third-party paper)
- Coverage of the company's spin-out (second-hand) (second-hand) second-hand
Corrections
4 corrections
| Field | Was | Now | Basis | Found |
|---|---|---|---|---|
| first_release | First release taken as the preprint date 2025-01-11 | Changed to the first code release on 2024-12-12; the repository creation date is excluded by policy | source | 2026-11-16 |
| latest_update | The v2 release was dated 2026-04-08 | Changed to 2026-04-07 per the release page; later commits are documentation | source | 2026-11-16 |
| wetlab_validation | The design-side wet-lab hit-rate range was 20-73%, cited to the model repository | Changed to the design preprint v3 range of 17-82% with nanomolar hits on 6 of 7 targets, cited to the design paper rather than the model repository | source | 2026-11-16 |
| benchmarks_reported | The public pose-set cell was shown as a self-report for the current version | Version-qualified: it holds only for an early version, as neither v1 nor v2 reports on that test set | source | 2026-11-16 |
Part of the AI for Bio benchmarks survey · all 112 models · open in the explorer. Record as of 2026-11-16.