Overview
| Name | ProSST · aliases: ProSST, ProSST-2048 |
|---|---|
| Full name | Paper and repository use the short name only |
| Ambiguous names (not auto-linked) | None |
| Family | Not a family entry. Different structure-vocabulary sizes (K) are configurations of one model, not members |
| Organization | Shanghai Jiao Tong University, Shanghai AI Laboratory |
| Organization type | Academic lab |
| Country | China |
| Model class | Protein language model (quantized structure tokens) |
| Domain | Proteins (also: Structure & co-folding) |
| First release | † partly verified · preprint Basis: bioRxiv preprint v1 (the conference version came later) Note: The preprint DOI is inferred from a title match (unverified); the site previously used the conference publication as first release source |
| Other milestones | |
| Latest update | † partly verified · conference paper Basis: Publication at a 2024 machine-learning conference Formal conference publication; the 2026-07 and 2026-09 README items are project news, not model updates Note: The exact publication day is not pinned, so it is kept to the month (unverified) source The most recent sourced event, not a claim that nothing changed since. |
| Status | Maintained only · Repository maintained with project news, no new ProSST version |
| Openness | Code: Open Weights: Open Code and weights public in the official repository; licence text not retrieved this round, so terms are left empty |
| Benchmarks reported | 2 counted (board 2) |
| Wet-lab validation | None recorded |
| Unverified fields | † first_release, latest_update, benchmarks_reported[1], release_milestones.official_announcement, open_status.weights_license, open_status.code_license |
| As of | 2026-11-16 |
What it does
A quantization module maps each residue's local 3D environment to a discrete structure token, then sequence-structure disentangled attention is pretrained for zero-shot mutation-effect prediction. It is the base model of VenusREM; unlike SaProt the structure vocabulary is learned rather than taken from an off-the-shelf alignment tool.
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. 2 of 2 pairings are counted.
| Benchmark | Relation | Eval set / protocol | Source type | Note and evidence |
|---|---|---|---|---|
| 02 ProteinGym | Official leaderboard or results | zero-shot substitution DMS summary table, several structure-vocabulary sizes | Board | Entry on the official summary table · evidence |
| 34 AbBiBench | Official leaderboard or results | antibody binding-affinity correlation, structure-aware LM category | Board | Benchmark-registered score †unverified · no source link |
Other evaluations (outside the 44)
- Inherited weakness on viral proteins (Public benchmark not among the 44) Third-party: A board maintainer post notes that models inheriting existing embeddings drop on viral-protein subsets, this one included
- Retrieval-augmented successor as a control (Comparison against baselines only) Self-reported: Used repeatedly as the control for VenusREM, a comparison by the same group
Developers report: Developers report that learned quantized structure tokens plus disentangled attention put a roughly 110M-parameter model in the top tier for zero-shot mutation-effect prediction.
Independent evidence: No independent evidence found. No independent re-evaluation or third-party re-run found
Training data
Group in Figure 7: Public data only.
| Class | Value | Detail |
|---|---|---|
| a. Public databases | Yes | About 18.8M public structures source |
| b. Private or licensed data | No | No private or licensed data reported |
| c. Own wet-lab data used for training | No | |
| d. Wet lab used only for validation | No |
Wet-lab validation
None. The developers report no wet-lab validation.
Background
- Organization: An academic team with no separate company: Shanghai Jiao Tong University working with the Shanghai AI Laboratory and further university partners. The work appeared at a 2024 machine-learning conference and grew into a protein-engineering toolchain.
- Funding: Paper acknowledgements not retrieved; funding left blank
- Products and partnerships: The same group's Venus line adds retrieval augmentation on top of it to form VenusREM, alongside a protein-engineering system and a mining tool; it shares the structure-aware route with SaProt.
- Related models: VenusREM, SaProt, PoET-2
Reading notes
- It leads the sequence-plus-structure category on the official board, but time-stamped "first open model past a threshold" claims are not carried here.
- It depends on predicted structures, and models inheriting existing embeddings generally drop on viral proteins.
- No wet lab: it speaks to DMS ranking, not to designability.
- The latest update is the conference publication; later repository notes are project news, not a new version.
Caveats
- The AbBiBench pairing rests only on this site's page (unverified).
- The conference date is month-precision and the preprint DOI is inferred from a title match (unverified).
- Retrieval and structure inputs raise scores, so it is not directly comparable with sequence-only models.
Sources
- Official repository (repository)
- ProSST preprint (DOI inferred from title match) (preprint)
- ProteinGym official summary table (leaderboard)
- Board maintainer blog post (second-hand) (second-hand) second-hand
Corrections
3 corrections
| Field | Was | Now | Basis | Found |
|---|---|---|---|---|
| latest_update.event_kind | Recorded as none-since-release | Changed to conference publication (2024-12) | source | 2026-11-16 |
| latest_update.description | Said the repository only had README news and no new version, contradicting the recorded date's event | States that 2024-12 is the conference publication and that the 2026 README items are project news, not model updates | source | 2026-11-16 |
| first_release | Used the conference publication as first release | Changed to the 2024-04-17 preprint v1, the earlier provable public evidence | 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.