Strengths and considerations
No source-reviewed explanatory claims are recorded here yet.
Task
protein-protein interaction prediction
Protein-pair interaction classification derives positive and sampled-negative pairs from PINDER structural partitions.
Sources
Multimodal graph, surface, and language-based model for protein protein interaction prediction · Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captionsAt a glance
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 |
|---|---|
| Datasets | Filtered PINDER dimeric systems and negative pairs checked against BioGRID.SourcesMultimodal graph, surface, and language-based model for protein protein interaction prediction · Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captions |
| Splits | The ML-ready PINDER training, validation and test partitions are retained during task construction.SourcesMultimodal graph, surface, and language-based model for protein protein interaction prediction · Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captions |
| Metrics | Accuracy, sensitivity, F1, MCC, AUROC and AUPRC for protein-pair classification.SourcesMultimodal graph, surface, and language-based model for protein protein interaction prediction · Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captions |
| Baselines | ESM-2, ProtT5 and ProstT5 sequence-embedding variants; graph/surface-feature removals are separate ablations.SourcesMultimodal graph, surface, and language-based model for protein protein interaction prediction · Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captions |
| Leakage controls | PINDER uses interface/sequence similarity clustering; sampled negatives are checked against known interactions.SourcesMultimodal graph, surface, and language-based model for protein protein interaction prediction · Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captions |
| Uncertainty | Three-fold cross-validation with different random seeds is reported using means and standard deviations across runs.SourcesMultimodal graph, surface, and language-based model for protein protein interaction prediction · Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captions |
| Entity type | Paper-specific computational evaluation protocol.SourcesMultimodal graph, surface, and language-based model for protein protein interaction prediction · Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captions |
| Organisms | The main task inherits filtered PINDER dimer systems; its Dataset section does not enumerate source organisms. The named human, yeast, bacterial and worm species in the external Baranwal evaluation describe that separate dataset and cannot be assigned as the full PINDER inventory. · Not reported in inspected sourcesSourcesMultimodal graph, surface, and language-based model for protein protein interaction prediction · Methods: Dataset/Sampling; external Baranwal evaluation |
| Assays | PINDER interacting dimers and BioGRID-checked negative pairs.SourcesMultimodal graph, surface, and language-based model for protein protein interaction prediction · Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captions |
| Allowed inputs | Protein-pair representations.SourcesMultimodal graph, surface, and language-based model for protein protein interaction prediction · Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captions |
| Adaptation | Supervised interaction prediction using retained PINDER training/validation/test partitions.SourcesMultimodal graph, surface, and language-based model for protein protein interaction prediction · Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captions |
How it works
How it worksComputational evaluation flow
Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.
Sources
Multimodal graph, surface, and language-based model for protein protein interaction prediction · Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captionsEvaluation methodology
Filtered PINDER dimeric systems and negative pairs checked against BioGRID. The ML-ready PINDER training, validation and test partitions are retained during task construction. Accuracy, sensitivity, F1, MCC, AUROC and AUPRC for protein-pair classification. ESM-2, ProtT5 and ProstT5 sequence-embedding variants; graph/surface-feature removals are separate ablations. PINDER uses interface/sequence similarity clustering; sampled negatives are checked against known interactions. Three-fold cross-validation with different random seeds is reported using means and standard deviations across runs.
Sources
Multimodal graph, surface, and language-based model for protein protein interaction prediction · Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captionsRecorded evaluations
Each evaluation records what was tested and under which conditions.
Tested entities 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 |
|---|---|---|
| GSMFormer-PPI + ProstT5: protein-protein interaction prediction Pipeline: GSMFormer-PPI + ProstT5Task: protein-protein interaction predictionDataset: paper PPI test set ProstT5 embeddings as graph node features Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.988 AUROC Unit: fraction · Direction: unknown | Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported | source checkedMultimodal graph, surface, and language-based model for protein protein interaction prediction · Table 6, ProstT5 embedding row, AUROC column Source checking is not independent reproduction. |
Papers and result coverage
Last literature check: 2026-09-17. Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.
| Paper or primary resource | Version | Reference |
|---|---|---|
| Multimodal graph, surface, and language-based model for protein protein interaction prediction | journal full text in PMC | Read source DOI: 10.1038/s41598-025-34758-x |
What is still missing
- Complete raw tables acquired. Tables 3/4 matched four-method experiments;Table 5 combines different datasets and cannot form a common ranking. Units mix percentaccuracy and fractionalmetrics. Structured extraction pending.
Search and extraction details
source found structured extraction pending
Searches
- Multimodal graph, surface, and language-based model for protein protein interaction prediction primary paper benchmark results
Evidence locations
- Tables3–5; training-validation/test and literature comparisons
Strengths and limitations
Limitations and conditions
- Absence of a sampled protein pair from BioGRID does not prove noninteraction. Random negative construction makes the selected pair lists part of the reproducible protocol.
Sources
Multimodal graph, surface, and language-based model for protein protein interaction prediction · Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captions
Profile review details
Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.
Stable record: reported-task-dfa8f2285dbfa5Evidence 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.
17 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol. Individual claims | Multimodal graph, surface, and language-based model for protein protein interaction prediction Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captions Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram steps ["Input: Protein-pair representations.","Evaluation: Supervised interaction prediction using retained PINDER training/validation/test partitions.","Readout: Accuracy, sensitivity, F1, MCC, AUROC and AUPRC for protein-pair classification."] Individual claims | Multimodal graph, surface, and language-based model for protein protein interaction prediction Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captions Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Computational evaluation flow Individual claims | Multimodal graph, surface, and language-based model for protein protein interaction prediction Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captions Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Datasets Filtered PINDER dimeric systems and negative pairs checked against BioGRID. Individual claims | Multimodal graph, surface, and language-based model for protein protein interaction prediction Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captions Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Splits The ML-ready PINDER training, validation and test partitions are retained during task construction. Individual claims | Multimodal graph, surface, and language-based model for protein protein interaction prediction Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captions Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Adaptation Supervised interaction prediction using retained PINDER training/validation/test partitions. Individual claims | Multimodal graph, surface, and language-based model for protein protein interaction prediction Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captions Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Metrics Accuracy, sensitivity, F1, MCC, AUROC and AUPRC for protein-pair classification. Individual claims | Multimodal graph, surface, and language-based model for protein protein interaction prediction Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captions Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Baselines ESM-2, ProtT5 and ProstT5 sequence-embedding variants; graph/surface-feature removals are separate ablations. Individual claims | Multimodal graph, surface, and language-based model for protein protein interaction prediction Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captions Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Leakage controls PINDER uses interface/sequence similarity clustering; sampled negatives are checked against known interactions. Individual claims | Multimodal graph, surface, and language-based model for protein protein interaction prediction Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captions Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Uncertainty Three-fold cross-validation with different random seeds is reported using means and standard deviations across runs. Individual claims | Multimodal graph, surface, and language-based model for protein protein interaction prediction Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captions Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. 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
2 source records and release history
- Multimodal graph, surface, and language-based model for protein protein interaction prediction · Original source · journal full text in PMC
- Multimodal graph, surface, and language-based model for protein protein interaction prediction · Original source · journal full text in PMC
Technical metadata and extraction receipts
Stable ID: reported-task-dfa8f2285dbfa5
- areas
- proteins-complexes
- tasks
- protein-protein interaction prediction
- entity level
- task
- version
- Not reported
- task
- protein-protein interaction prediction
- scope note
- Paper-specific evaluation task; protocol completeness requires further extraction.
- benchmark research
- review date: 2026-09-17; status: source_found_structured_extraction_pending; primary sources: evidence-expansion-p2-gsmformer-ppi-2026-9b364b5d73d1; inspected locators: Tables3–5; training-validation/test and literature comparisons; searched queries: Multimodal graph, surface, and language-based model for protein protein interaction prediction primary paper benchmark results; gaps: Complete raw tables acquired. Tables 3/4 matched four-method experiments;Table 5 combines different datasets and cannot form a common ranking. Units mix percentaccuracy and fractionalmetrics. Structured extraction pending.; claim scope: Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.
- historical missing metadata
- protocol version: 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
- benchmark
- entity classification
- review date: 2026-09-17; rationale: This source-scoped record identifies the biological prediction task and holds its paper context. Preserve the existing task identity; exact split, model adaptation and scoring remain in linked evaluations or separate protocol records.; source ids: gsmformer-ppi-2026; source locator: Methods: Splits; Sampling; cached text lines 15–21; task metric definitions and corresponding results table; uncertainty/repeat-run/statistical-comparison passages; matching task comparison table/ablation captions; ambiguities: A paper- or suite-specific task may constrain some inputs or metrics; that alone does not make it interchangeable with a complete versioned protocol. No protocol equivalence is inferred.; Some legacy profile Entity type facts use the generic phrase computational evaluation protocol. That boilerplate is not sufficient to establish a single fixed protocol identity or to merge this task with another protocol record.