Model type
Study-specific predictive method; this record is the paper-specific evaluated configuration.
Configuration
MolAS
MolAS predicts which docking algorithm is likely to work best for a particular protein–ligand instance.
Sources
Molecular embedding-based algorithm selection in protein-ligand docking · Materials and methods/Scoring function/Physicochemical plausibility (paragraph 2); Discussion/When is MolAS useful in practice? (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
Molecular embedding-based algorithm selection in protein-ligand docking · Introduction (paragraph 5); Materials and methods/Model architecture (paragraph 1)At a glance
Biological inputs
Protein/ligand embeddings for an instance and a fixed candidate-solver set
Sources
Molecular embedding-based algorithm selection in protein-ligand docking · Discussion/When is MolAS useful in practice? (paragraph 1); Discussion/What does MolAS reveal about docking algorithm selection? (paragraph 4)Outputs
Predicted solver performance and a selected docking algorithm
Sources
Molecular embedding-based algorithm selection in protein-ligand docking · Materials and methods/Scoring function/Physicochemical plausibility (paragraph 2); Introduction (paragraph 2)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 |
|---|---|---|
| MolAS: Physically valid protein–ligand pose selection Averaged five-fold algorithm-selection performance on PoseBusters; joint RMSD and validity criterion. Author-reported evaluation · Evaluation metadata: needs review | ||
| 36.69 RMSD ≤1 Å and PB-valid success Unit: % · Direction: unknown | Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported | source checkedMolecular embedding-based algorithm selection in protein-ligand docking · Table 3, PoseBusters / Mixed / AutoDock row, MolAS success column Source checking is not independent reproduction. |
How it works
How the evaluated method works
Pretrained protein and ligand embeddings pass through attentional pooling and a shallow residual decoder that estimates per-algorithm performance.
Sources
Molecular embedding-based algorithm selection in protein-ligand docking · Introduction (paragraph 5); Materials and methods/Model architecture (paragraph 1)What was evaluated
The linked evaluation record identifies MolAS: Physically valid protein–ligand pose selection. Its dataset, split, adaptation and evidence origin remain attached to the reported results.
Sources
Molecular embedding-based algorithm selection in protein-ligand docking · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-lit-b3-044Strengths and limitations
Strengths and considerations
- Evaluates algorithm selection against the single-best and virtual-best solver references.
Sources
Molecular embedding-based algorithm selection in protein-ligand docking · Introduction (paragraph 2); Materials and methods/Scoring function/Physicochemical plausibility (paragraph 2)
Limitations and conditions
- Solver rankings can change under protocol mismatch; the paper positions MolAS as an in-domain selector for fixed pipelines.
Sources
Molecular embedding-based algorithm selection in protein-ligand docking · Discussion/What does MolAS reveal about docking algorithm selection? (paragraph 3); Discussion/When is MolAS useful in practice? (paragraph 1)
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-0eb4b0535b58e3Specifications
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.SourcesMolecular embedding-based algorithm selection in protein-ligand docking · Introduction (paragraph 5); Materials and methods/Model architecture (paragraph 1) |
| Architecture / procedure | Pretrained protein and ligand embeddings pass through attentional pooling and a shallow residual decoder that estimates per-algorithm performance.SourcesMolecular embedding-based algorithm selection in protein-ligand docking · Introduction (paragraph 5); Materials and methods/Model architecture (paragraph 1) |
| Biological inputs | Protein/ligand embeddings for an instance and a fixed candidate-solver setSourcesMolecular embedding-based algorithm selection in protein-ligand docking · Discussion/When is MolAS useful in practice? (paragraph 1); Discussion/What does MolAS reveal about docking algorithm selection? (paragraph 4) |
| Outputs | Predicted solver performance and a selected docking algorithmSourcesMolecular embedding-based algorithm selection in protein-ligand docking · Materials and methods/Scoring function/Physicochemical plausibility (paragraph 2); Introduction (paragraph 2) |
| Parameters | Approximately 638,000 parameters for the MolAS selector. The pretrained protein and ligand feature extractors are separate components.SourcesMolecular embedding-based algorithm selection in protein-ligand docking · Results / Comparison to MC-GNNAS-Dock |
| Known versions / configuration | MolAS is the comparison-table label; that label does not specify an immutable weight revision. · Not reported in inspected sourcesSourcesMolecular embedding-based algorithm selection in protein-ligand docking · Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label. |
| Training data / fitting | Hundreds to a few thousand labelled complexes depending on the benchmark.SourcesMolecular embedding-based algorithm selection in protein-ligand docking · Introduction (paragraph 6); Materials and methods/Datasets and preprocessing/Extra benchmarks (paragraph 6) |
| 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)Molecular embedding-based algorithm selection in protein-ligand docking; BradWangW/MolAS README.md · Materials and methods/Pipeline overview; Materials and methods/Datasets and preprocessing/Dataset; Materials and methods/Datasets and preprocessing/Extra benchmarks; Materials and methods/Datasets and preprocessing/Preprocessing; Materials and methods/Model architecture; Materials and methods/Scoring function/Geometric accuracy; Materials and methods/Scoring function/Physicochemical plausibility; Materials and methods/Training objective; 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/BradWangW/MolAS/blob/a6c417216ddb992f7dc513d511d0429aece4bd61/README.md. This pinned documentation revision is not automatically the evaluated weight revision.SourcesBradWangW/MolAS README.md · README.md; installation, model download and usage instructions |
| Code licence | MIT (study repository code at the cited revision; this does not establish every dependency or historical checkpoint licence).SourcesBradWangW/MolAS 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 sourcesSourcesBradWangW/MolAS 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.
20 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 | Molecular embedding-based algorithm selection in protein-ligand docking Introduction (paragraph 5); Materials and methods/Model architecture (paragraph 1) Version: PMC archival version PMC13104262.1 | 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/ligand embeddings for an instance and a fixed candidate-solver set","MolAS","Predicted solver performance and a selected docking algorithm"] Individual claims | Molecular embedding-based algorithm selection in protein-ligand docking Introduction (paragraph 5); Materials and methods/Model architecture (paragraph 1) Version: PMC archival version PMC13104262.1 | 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 | Molecular embedding-based algorithm selection in protein-ligand docking Introduction (paragraph 5); Materials and methods/Model architecture (paragraph 1) Version: PMC archival version PMC13104262.1 | 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 | Molecular embedding-based algorithm selection in protein-ligand docking Introduction (paragraph 5); Materials and methods/Model architecture (paragraph 1) Version: PMC archival version PMC13104262.1 | 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 Pretrained protein and ligand embeddings pass through attentional pooling and a shallow residual decoder that estimates per-algorithm performance. Individual claims | Molecular embedding-based algorithm selection in protein-ligand docking Introduction (paragraph 5); Materials and methods/Model architecture (paragraph 1) Version: PMC archival version PMC13104262.1 | 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 | BradWangW/MolAS README.md README.md; checkpoint/access documentation and licence scope Version: a6c417216ddb992f7dc513d511d0429aece4bd61 | 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/ligand embeddings for an instance and a fixed candidate-solver set Individual claims | Molecular embedding-based algorithm selection in protein-ligand docking Discussion/When is MolAS useful in practice? (paragraph 1); Discussion/What does MolAS reveal about docking algorithm selection? (paragraph 4) Version: PMC archival version PMC13104262.1 | 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 Predicted solver performance and a selected docking algorithm Individual claims | Molecular embedding-based algorithm selection in protein-ligand docking Materials and methods/Scoring function/Physicochemical plausibility (paragraph 2); Introduction (paragraph 2) Version: PMC archival version PMC13104262.1 | 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 Approximately 638,000 parameters for the MolAS selector. The pretrained protein and ligand feature extractors are separate components. Individual claims | Molecular embedding-based algorithm selection in protein-ligand docking Results / Comparison to MC-GNNAS-Dock Version: PMC archival version PMC13104262.1 | 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 |
| Known versions / configuration MolAS is the comparison-table label; that label does not specify an immutable weight revision. Individual claims | Molecular embedding-based algorithm selection in protein-ligand docking Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label. Version: PMC archival version PMC13104262.1 | 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
- Molecular embedding-based algorithm selection in protein-ligand docking · Original source · PMC archival version PMC13104262.1
- BradWangW/MolAS README.md · Original source · a6c417216ddb992f7dc513d511d0429aece4bd61
- BradWangW/MolAS LICENSE · Original source · a6c417216ddb992f7dc513d511d0429aece4bd61
Technical metadata and extraction receipts
Stable ID: reported-model-0eb4b0535b58e3
- areas
- molecular-interactions
- entity level
- method
- version
- Not reported
- reported name
- MolAS
- 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: molas-2026; source locator: Introduction (paragraph 5); Materials and methods/Model architecture (paragraph 1) | Materials and methods/Scoring function/Physicochemical plausibility (paragraph 2); Discussion/When is MolAS useful in practice? (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.