Overview
| Name | Pinal · aliases: Pinal, Denovo-Pinal |
|---|---|
| Full name | No separate expanded name |
| Ambiguous names (not auto-linked) | None |
| Family | Not a family entry. Single-model entry, not a family |
| Organization | Westlake University |
| Organization type | Academic lab |
| Country | China |
| Model class | Text-to-protein generation |
| Domain | Proteins |
| First release | · preprint Basis: bioRxiv v1 preprint source |
| Other milestones | |
| Latest update | · journal Basis: Nature online publication Nature online publication; later GitHub and Hugging Face updates are minor documentation changes source The most recent sourced event, not a claim that nothing changed since. |
| Status | Active · Journal publication within 12 months |
| Openness | Code: Open · Apache-2.0 Weights: Open · Apache-2.0 Weights and code on GitHub and Hugging Face under Apache-2.0; the full training corpus is withheld |
| Benchmarks reported | 0 counted · none of the 44 |
| Wet-lab validation | 4 recorded campaigns |
| Unverified fields | None |
| As of | 2026-11-16 |
What it does
Translates a natural-language function description into structure tokens and then designs a sequence; about 16B parameters trained on 1.7B protein-text pairs. Built on the same team's SaProt.
Benchmarks reported
None of the 44 benchmarks. This model is on the zero-pairing list.
How it evaluates itself: Computational evaluation; Fluorescent protein; Metabolic H protein; PET hydrolase and alcohol dehydrogenase
Other evaluations (outside the 44)
- Computational evaluation (Own task set) Self-reported: Foldability, description-function alignment and sequence diversity versus baselines; no summary number
Developers report: Developers report natural-language descriptions can be turned into functional proteins, with activity seen in four tasks without iterative optimization
Independent evidence: No independent evidence found. No independent evidence found
Training data
Group in Figure 7: Public data + wet lab for validation only.
| Class | Value | Detail |
|---|---|---|
| a. Public databases | Yes | 1.7B synthetic protein-text pairs generated from public sequence, structure, domain and enzyme annotation resources |
| 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 validated four tasks only |
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: 50,000 sequences generated, 29 filtered candidates tested, 1 fluoresced green
Verified against the v9 full text, so the earlier unverifiable flag is lifted; developer-run
Denominator basis: 50,000 initial candidates filtered to ~1,000 and 20 synthesised: 14/20 soluble, 5 active in a reconstituted system
Verified against the v9 full text; developer-run
Denominator basis: 200,000 generated, 2,416 passed filtering, 94 synthesised and screened; no hit rate reported
Previously missing counts are now filled in; developer-run
Denominator basis: 2,500 initial candidates, 1,000 high-confidence, 8 selected, 5 expressed and purified across three subfamilies
Substrate conversion shown chromatographically against a no-enzyme control with no numeric activity; developer-run
Background
- Organization: Academic team at Westlake University with collaborators at several universities, institutes and one biotech company; not a company
- Funding: Funded by Chinese national and provincial research grants
- Products and partnerships: Built on the same team's SaProt; the full corpus is withheld for dual-use reasons
- Related models: SaProt, ProGen3
Reading notes
- All four wet-lab tasks are developer-run at a scale of tens of designs
- All counts are verified in the v9 full text, so figures can be given
Caveats
- No results on any of the 44 benchmarks; on the zero-pairing list under this round's rules
- The full training corpus is withheld, so external reproduction is incomplete
Sources
- bioRxiv preprint (preprint)
- Crossref record 10.1038/s41586-026-11205-z (journal)
- GitHub repository westlake-repl/Denovo-Pinal (repository)
- Hugging Face page westlake-repl/Pinal (repository)
- Journal article DOI 10.1038/s41586-026-11205-z (journal)
- bioRxiv preprint (preprint)
Corrections
None recorded.
Part of the AI for Bio benchmarks survey · all 112 models · open in the explorer. Record as of 2026-11-16.