Model type
Study-specific predictive method; this record is the paper-specific evaluated configuration.
Configuration
PST
PST adds structural adapters to a pretrained protein sequence transformer.
Sources
Endowing protein language models with structural knowledge · 1 Introduction (paragraph 4); 5 Discussion (paragraph 1)How it worksEvaluated procedure (conceptual)
Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings.
Sources
Endowing protein language models with structural knowledge · 1 Introduction (paragraph 4); 3 Methods/3.2 Protein structure transformer/3.2.2 Protein structure transformer construction (paragraph 1)At a glance
Biological inputs
Protein sequence and structural information
Sources
Endowing protein language models with structural knowledge · 1 Introduction (paragraph 7); 3 Methods (paragraph 1)Outputs
Joint sequence/structure representations for downstream tasks
Sources
Endowing protein language models with structural knowledge · 4 Experiments/4.4 Ablation studies/4.4.3 Pretraining only structure extractors almost matches full-model pretraining performance (paragraph 2); 1 Introduction (paragraph 5)limited source coverage · Automated source review, 2026-09-16. All specifications and missing details
Evaluations and results
Release 2026-09-17-d277315f7d76 · 1 evaluation · 1 metric row. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| PST: Zero-shot variant effect prediction Zero-shot VEP; paper averages absolute Spearman correlations. Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.501 Mean |Spearman rho| Unit: unitless · Direction: unknown | Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported | source checkedEndowing protein language models with structural knowledge · Table 2, PST row, Zero-shot VEP Mean |ρ| column Source checking is not independent reproduction. |
How it works
How the evaluated method works
Specialised structural adapters modify self-attention to combine sequence and structure embeddings, while retaining the pretrained language-model backbone.
Sources
Endowing protein language models with structural knowledge · 1 Introduction (paragraph 4); 3 Methods/3.2 Protein structure transformer/3.2.2 Protein structure transformer construction (paragraph 1)What was evaluated
The linked evaluation record identifies PST: Zero-shot variant effect prediction. Its dataset, split, adaptation and evidence origin remain attached to the reported results.
Sources
Endowing protein language models with structural knowledge · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-lit-023Strengths and limitations
Strengths and considerations
- Tests a lightweight way to incorporate structure without training an entirely new large protein model.
Sources
Endowing protein language models with structural knowledge · 2 Related work (paragraph 1); 4 Experiments/4.4 Ablation studies/4.4.1 Simpler structural inputs yield better performance (paragraph 1)
Limitations and conditions
- The extra structural inputs and adaptation data must be preserved when comparing with the sequence-only ESM-2 baseline.
Sources
Endowing protein language models with structural knowledge · 3 Methods (paragraph 1); 5 Discussion (paragraph 3)
Profile review details
Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction.
Stable record: reported-model-7dd5992188a868Specifications
Inputs, training, access and other details
Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
| Property | Description and evidence |
|---|---|
| Model type | Study-specific predictive method; this record is the paper-specific evaluated configuration.SourcesEndowing protein language models with structural knowledge · 1 Introduction (paragraph 4); 3 Methods/3.2 Protein structure transformer/3.2.2 Protein structure transformer construction (paragraph 1) |
| Architecture / procedure | Specialised structural adapters modify self-attention to combine sequence and structure embeddings, while retaining the pretrained language-model backbone.SourcesEndowing protein language models with structural knowledge · 1 Introduction (paragraph 4); 3 Methods/3.2 Protein structure transformer/3.2.2 Protein structure transformer construction (paragraph 1) |
| Biological inputs | Protein sequence and structural informationSourcesEndowing protein language models with structural knowledge · 1 Introduction (paragraph 7); 3 Methods (paragraph 1) |
| Outputs | Joint sequence/structure representations for downstream tasksSourcesEndowing protein language models with structural knowledge · 4 Experiments/4.4 Ablation studies/4.4.3 Pretraining only structure extractors almost matches full-model pretraining performance (paragraph 2); 1 Introduction (paragraph 5) |
| Parameters | An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sourcesSources (2)Endowing protein language models with structural knowledge; BorgwardtLab/PST README.md · 3 Methods; 3 Methods/3.1 Evolutionary scale modeling; 3 Methods/3.1 Evolutionary scale modeling/3.1.1 ESM-2 model architecture; 3 Methods/3.2 Protein structure transformer; 3 Methods/3.2 Protein structure transformer/3.2.1 Protein graph representation; 3 Methods/3.2 Protein structure transformer/3.2.2 Protein structure transformer construction; 3 Methods/3.2 Protein structure transformer/3.2.3 Pretraining the PST; 4 Experiments/4.1 Experimental setup/4.1.4 Pretraining; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision |
| Known versions / configuration | PST is the comparison-table label; that label does not specify an immutable weight revision. · Not reported in inspected sourcesSourcesEndowing protein language models with structural knowledge · Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label. |
| Training data / fitting | 542,000 protein structures with a masked-language objective for the added structural integration.SourcesEndowing protein language models with structural knowledge · 3 Methods/3.2 Protein structure transformer/3.2.3 Pretraining the PST (paragraph 1); 3 Methods/3.1 Evolutionary scale modeling (paragraph 2) |
| Context limits | A maximum input/context length for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sourcesSources (2)Endowing protein language models with structural knowledge; BorgwardtLab/PST README.md · 3 Methods; 3 Methods/3.1 Evolutionary scale modeling; 3 Methods/3.1 Evolutionary scale modeling/3.1.1 ESM-2 model architecture; 3 Methods/3.2 Protein structure transformer; 3 Methods/3.2 Protein structure transformer/3.2.1 Protein graph representation; 3 Methods/3.2 Protein structure transformer/3.2.2 Protein structure transformer construction; 3 Methods/3.2 Protein structure transformer/3.2.3 Pretraining the PST; 4 Experiments/4.1 Experimental setup/4.1.4 Pretraining; inspected for explicit maximum input length (dataset lengths and family-wide limits are not substituted); README.md at pinned repository revision |
| Access | Official study implementation and usage documentation: https://github.com/BorgwardtLab/PST/blob/57d9dcd8200900504a19de459450e137867262d7/README.md. This pinned documentation revision is not automatically the evaluated weight revision.SourcesBorgwardtLab/PST README.md · README.md; installation, model download and usage instructions |
| Code licence | BSD 3-Clause (study repository code at the cited revision; this does not establish every dependency or historical checkpoint licence).SourcesBorgwardtLab/PST LICENSE · LICENSE; complete licence text |
| Weights licence | The inspected model-access documentation does not explicitly identify terms for this exact evaluated checkpoint or fitted head; repository code terms are shown separately. · Not reported in inspected sourcesSourcesBorgwardtLab/PST README.md · README.md; checkpoint/access documentation and licence scope |
Evidence table
Inspect claims, sources and review details
Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
21 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings. Individual claims | Endowing protein language models with structural knowledge 1 Introduction (paragraph 4); 3 Methods/3.2 Protein structure transformer/3.2.2 Protein structure transformer construction (paragraph 1) Version: PMC12603367.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram steps ["Protein sequence and structural information","PST","Joint sequence/structure representations for downstream tasks"] Individual claims | Endowing protein language models with structural knowledge 1 Introduction (paragraph 4); 3 Methods/3.2 Protein structure transformer/3.2.2 Protein structure transformer construction (paragraph 1) Version: PMC12603367.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Evaluated procedure (conceptual) Individual claims | Endowing protein language models with structural knowledge 1 Introduction (paragraph 4); 3 Methods/3.2 Protein structure transformer/3.2.2 Protein structure transformer construction (paragraph 1) Version: PMC12603367.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Model type Study-specific predictive method; this record is the paper-specific evaluated configuration. Individual claims | Endowing protein language models with structural knowledge 1 Introduction (paragraph 4); 3 Methods/3.2 Protein structure transformer/3.2.2 Protein structure transformer construction (paragraph 1) Version: PMC12603367.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Architecture / procedure Specialised structural adapters modify self-attention to combine sequence and structure embeddings, while retaining the pretrained language-model backbone. Individual claims | Endowing protein language models with structural knowledge 1 Introduction (paragraph 4); 3 Methods/3.2 Protein structure transformer/3.2.2 Protein structure transformer construction (paragraph 1) Version: PMC12603367.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Weights licence The inspected model-access documentation does not explicitly identify terms for this exact evaluated checkpoint or fitted head; repository code terms are shown separately. Individual claims | BorgwardtLab/PST README.md README.md; checkpoint/access documentation and licence scope Version: 57d9dcd8200900504a19de459450e137867262d7 | unreported automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Biological inputs Protein sequence and structural information Individual claims | Endowing protein language models with structural knowledge 1 Introduction (paragraph 7); 3 Methods (paragraph 1) Version: PMC12603367.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Outputs Joint sequence/structure representations for downstream tasks Individual claims | Endowing protein language models with structural knowledge 4 Experiments/4.4 Ablation studies/4.4.3 Pretraining only structure extractors almost matches full-model pretraining performance (paragraph 2); 1 Introduction (paragraph 5) Version: PMC12603367.1 | source checked automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Parameters An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. Individual claims | BorgwardtLab/PST README.md 3 Methods; 3 Methods/3.1 Evolutionary scale modeling; 3 Methods/3.1 Evolutionary scale modeling/3.1.1 ESM-2 model architecture; 3 Methods/3.2 Protein structure transformer; 3 Methods/3.2 Protein structure transformer/3.2.1 Protein graph representation; 3 Methods/3.2 Protein structure transformer/3.2.2 Protein structure transformer construction; 3 Methods/3.2 Protein structure transformer/3.2.3 Pretraining the PST; 4 Experiments/4.1 Experimental setup/4.1.4 Pretraining; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 57d9dcd8200900504a19de459450e137867262d7 | unreported automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Parameters An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. Individual claims | Endowing protein language models with structural knowledge 3 Methods; 3 Methods/3.1 Evolutionary scale modeling; 3 Methods/3.1 Evolutionary scale modeling/3.1.1 ESM-2 model architecture; 3 Methods/3.2 Protein structure transformer; 3 Methods/3.2 Protein structure transformer/3.2.1 Protein graph representation; 3 Methods/3.2 Protein structure transformer/3.2.2 Protein structure transformer construction; 3 Methods/3.2 Protein structure transformer/3.2.3 Pretraining the PST; 4 Experiments/4.1 Experimental setup/4.1.4 Pretraining; inspected for aggregate parameter count (component sizes are not added without an exact configuration); README.md at pinned repository revision Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: PMC12603367.1 | unreported automated source review · 2026-09-16 Audit detailsPrimary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
Release 2026-09-17-d277315f7d76 · Record review: needs review
3 source records and release history
- Endowing protein language models with structural knowledge · Original source · PMC12603367.1
- BorgwardtLab/PST README.md · Original source · 57d9dcd8200900504a19de459450e137867262d7
- BorgwardtLab/PST LICENSE · Original source · 57d9dcd8200900504a19de459450e137867262d7
Technical metadata and extraction receipts
Stable ID: reported-model-7dd5992188a868
- areas
- proteins-complexes
- entity level
- method
- version
- Not reported
- reported name
- PST
- historical missing metadata
- version: not_reported_in_legacy_extract; checkpoint revision: not_reported_in_legacy_extract; training data: not_reported_in_legacy_extract; licence: not_reported_in_legacy_extract
- metadata review scope
- historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
- legacy kinds
- model
- entity classification
- review date: 2026-09-17; rationale: This source-scoped entry preserves the method/configuration actually named in an evaluation. It is neither a global family identity nor proof of an immutable checkpoint; the linked evaluation retains adaptation, fitting and scoring details.; source ids: pst-2025; source locator: 1 Introduction (paragraph 4); 3 Methods/3.2 Protein structure transformer/3.2.2 Protein structure transformer construction (paragraph 1) | 1 Introduction (paragraph 4); 5 Discussion (paragraph 1); ambiguities: Configuration means the source-labelled evaluated identity. It does not establish missing checkpoint hashes, default settings or equivalence to same-named records in other papers.