Protein–ligand pose assessment distinguishes geometric accuracy from stereochemical validity and examines temporal distribution shift.
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 | PLINDER and PDBbind2020 complexes; PLINDER subsets use ligand-similarity filtering.SourcesImproving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Methods: Benchmark Dataset; Evaluation Metrics; Results: Table 1; cached text lines 8–14, 41–44 |
| Splits | Before/After subsets are separated by the structure-prediction training cutoff; stricter subsets additionally filter protein and ligand similarity.SourcesImproving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Methods: Benchmark Dataset; Evaluation Metrics; Results: Table 1; cached text lines 8–14, 41–44 |
| Metrics | Protein and ligand RMSD, chirality reproduction, bond-length RMSD and bond-angle RMSD; aggregate definitions vary by metric.SourcesImproving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Methods: Benchmark Dataset; Evaluation Metrics; Results: Table 1; cached text lines 8–14, 41–44 |
| Baselines | AlphaFold3, Boltz-1 and restraint variants; AutoDock Vina and DiffDock for applicable ligand metrics.SourcesImproving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Methods: Benchmark Dataset; Evaluation Metrics; Results: Table 1; cached text lines 8–14, 41–44 |
| Leakage controls | Temporal and similarity-based subsets are examined separately; Before-set scores include structures potentially seen in training.SourcesImproving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Methods: Benchmark Dataset; Evaluation Metrics; Results: Table 1; cached text lines 8–14, 41–44 |
| Uncertainty | The cited text-accessible evaluation sections give no confidence-interval, resampling or repeat-run error-bar specification. Image-only tables and uninspected supplements are outside this absence claim. · Not reported in inspected sourcesSourcesImproving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Methods: Benchmark Dataset; Evaluation Metrics; Results: Table 1; cached text lines 8–14, 41–44 |
| Entity type | Paper-specific computational evaluation protocol.SourcesImproving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Methods: Benchmark Dataset; Evaluation Metrics; Results: Table 1; cached text lines 8–14, 41–44 |
| Organisms | PLINDER and PDBbind subsets are filtered by structure, time and similarity for the broad benchmark. Their curation section does not tabulate species coverage. The separately described human MDM2 case is not the organism scope of the full benchmark. · Not reported in inspected sourcesSourcesImproving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Dataset selection; separate MDM2 case-study setup |
| Assays | Protein–ligand structures with stereochemical and pose references.SourcesImproving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Methods: Benchmark Dataset; Evaluation Metrics; Results: Table 1; cached text lines 8–14, 41–44 |
| Allowed inputs | Complex prediction inputs; restraint-conditioned variants are explicitly separate comparisons.SourcesImproving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Methods: Benchmark Dataset; Evaluation Metrics; Results: Table 1; cached text lines 8–14, 41–44 |
| Adaptation | Pretrained structure predictors evaluated across cutoff-defined subsets and restraint variants.SourcesImproving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Methods: Benchmark Dataset; Evaluation Metrics; Results: Table 1; cached text lines 8–14, 41–44 |
Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.
PLINDER and PDBbind2020 complexes; PLINDER subsets use ligand-similarity filtering. Before/After subsets are separated by the structure-prediction training cutoff; stricter subsets additionally filter protein and ligand similarity. Protein and ligand RMSD, chirality reproduction, bond-length RMSD and bond-angle RMSD; aggregate definitions vary by metric. AlphaFold3, Boltz-1 and restraint variants; AutoDock Vina and DiffDock for applicable ligand metrics. Temporal and similarity-based subsets are examined separately; Before-set scores include structures potentially seen in training. The cited text-accessible evaluation sections give no confidence-interval, resampling or repeat-run error-bar specification. Image-only tables and uninspected supplements are outside this absence claim.
Each evaluation records what was tested and under which conditions.
Release 2026-09-17-d277315f7d76 · 2 evaluations · 2 metric rows. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| Boltz-1: Protein–ligand pose prediction All entries; authors note this dataset contains structures seen during model training. Independent external evaluation · Evaluation metadata: needs review | ||
| 1.393 Median ligand RMSD Unit: Å · Direction: unknown | Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported | source checkedImproving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Table 1, Boltz-1 row, Ligand RMSD (Å) column Source checking is not independent reproduction. |
| DiffDock: Protein–ligand pose prediction All entries; rigid-protein docking comparator; authors note this dataset contains structures seen during model training. Independent external evaluation · Evaluation metadata: needs review | ||
| 1.342 Median ligand RMSD Unit: Å · Direction: unknown | Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported | source checkedImproving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction · Table 1, DiffDock row, Ligand RMSD (Å) column Source checking is not independent reproduction. |
Last literature check: 2026-09-17. Dated primary-source discovery and protocol/table screening. Source checking does not mean experimental reproduction. Only separately extracted and independently reviewed numeric batches are publishable.
| Paper or primary resource | Version | Reference |
|---|---|---|
| Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction | version of record | Read source |
primary comparison tables located
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-bf513ed6db92c5Trace 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.
18 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 | Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction Methods: Benchmark Dataset; Evaluation Metrics; Results: Table 1; cached text lines 8–14, 41–44 Version: version of record | 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: Complex prediction inputs; restraint-conditioned variants are explicitly separate comparisons.","Evaluation: Pretrained structure predictors evaluated across cutoff-defined subsets and restraint variants.","Readout: Protein and ligand RMSD, chirality reproduction, bond-length RMSD and bond-angle RMSD; aggregate definitions vary by metric."] Individual claims | Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction Methods: Benchmark Dataset; Evaluation Metrics; Results: Table 1; cached text lines 8–14, 41–44 Version: version of record | 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 | Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction Methods: Benchmark Dataset; Evaluation Metrics; Results: Table 1; cached text lines 8–14, 41–44 Version: version of record | 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 PLINDER and PDBbind2020 complexes; PLINDER subsets use ligand-similarity filtering. Individual claims | Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction Methods: Benchmark Dataset; Evaluation Metrics; Results: Table 1; cached text lines 8–14, 41–44 Version: version of record | 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 Before/After subsets are separated by the structure-prediction training cutoff; stricter subsets additionally filter protein and ligand similarity. Individual claims | Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction Methods: Benchmark Dataset; Evaluation Metrics; Results: Table 1; cached text lines 8–14, 41–44 Version: version of record | 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 Pretrained structure predictors evaluated across cutoff-defined subsets and restraint variants. Individual claims | Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction Methods: Benchmark Dataset; Evaluation Metrics; Results: Table 1; cached text lines 8–14, 41–44 Version: version of record | 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 Protein and ligand RMSD, chirality reproduction, bond-length RMSD and bond-angle RMSD; aggregate definitions vary by metric. Individual claims | Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction Methods: Benchmark Dataset; Evaluation Metrics; Results: Table 1; cached text lines 8–14, 41–44 Version: version of record | 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 AlphaFold3, Boltz-1 and restraint variants; AutoDock Vina and DiffDock for applicable ligand metrics. Individual claims | Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction Methods: Benchmark Dataset; Evaluation Metrics; Results: Table 1; cached text lines 8–14, 41–44 Version: version of record | 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 Temporal and similarity-based subsets are examined separately; Before-set scores include structures potentially seen in training. Individual claims | Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction Methods: Benchmark Dataset; Evaluation Metrics; Results: Table 1; cached text lines 8–14, 41–44 Version: version of record | 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 The cited text-accessible evaluation sections give no confidence-interval, resampling or repeat-run error-bar specification. Image-only tables and uninspected supplements are outside this absence claim. Individual claims | Improving Stereochemical Limitations in Protein–Ligand Complex Structure Prediction Methods: Benchmark Dataset; Evaluation Metrics; Results: Table 1; cached text lines 8–14, 41–44 Version: version of record | unreported 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 |
Release 2026-09-17-d277315f7d76 · Record review: needs review
Stable ID: reported-task-bf513ed6db92c5