result · source checked
34.34 RMSD ≤1 Å and PB-valid success
Single best solver · RMSD ≤1 Å and PB-valid success · PoseBusters
- Tested model
- Single best solver
- Task or benchmark
- Physically valid protein–ligand pose selection
- Dataset
- PoseBusters
- Procedure
- Single best solver baseline under the same averaged five-fold selection test.
- Evaluation
- Single best solver: Physically valid protein–ligand pose selection
- Evidence
- Independent external evaluation · source checkedMolecular embedding-based algorithm selection in protein-ligand docking · Table 3, PoseBusters / Mixed / AutoDock row, SBS success column
A source-checked result verifies the numerical transcription, not every model or protocol detail. Evaluation metadata: needs review. Source checked does not mean independently reproduced.
Evaluation results
Release 2026-09-16-d74d282221a9 · 1 evaluation · 1 metric row. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| Single best solver: Physically valid protein–ligand pose selection Model: Single best solver · Benchmark: Physically valid protein–ligand pose selection · Dataset: PoseBusters Single best solver baseline under the same averaged five-fold selection test. Independent external evaluation · Evaluation metadata: needs review | ||
| 34.34 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, SBS success column Source checking is not independent reproduction. |
Sources and history
Release 2026-09-16-d74d282221a9 · Record review: source checked
- Molecular embedding-based algorithm selection in protein-ligand docking · Original source · PMC archival version PMC13104262.1
Technical metadata and extraction receipts
Stable ID: lit-b3-045
- areas
- molecular-interactions
- tasks
- Physically valid protein–ligand pose selection
- printed value
- 34.34
- numeric value
- 34.34
- metric
- RMSD ≤1 Å and PB-valid success
- metric direction
- unknown
- unit
- %
- uncertainty
- Not reported
- source locator
- Table 3, PoseBusters / Mixed / AutoDock row, SBS success column
- review
- method: independent_ai_table_review; reviewer: Codex omics research agent; independent source-table review, not human review; reviewed at: 2026-09-16T10:44:03.435454+00:00; notes: PoseBusters, Mixed, AutoDock row within jointly trained with/without relaxation block. Selected RMSD <=1 Angstrom AND PB-valid group; five-fold average success percentage, not <=2 Angstrom. Inline bold digit nodes joined in original order. Source check verifies central value and table context, not experiment reproduction or all metadata.; evidence: {"table_xml_id": "Tab3", "row_cells": ["PoseBusters", "Mixed", "AutoDock", "34.34", "36.69", "8.90", "51.17", "54.91", "11.87"], "selected_cell_zero_based": 3, "selected_cell_xml": "<td align=\"left\" colspan=\"1\" rowspan=\"1\">34.34</td>", "caption": "Averaged 5-fold MolAS performance v.s. SBS across benchmarks"}; artifact sha256: d556d47e0f7bbdc37eb62374b85ac9092dc7ff438fbae9e42892ac2cc784023f; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC13104262/fullTextXML
- legacy id
- lit-b3-045
- legacy row
- id: lit-b3-045; paper id: molas-2026; domain id: molecular-interactions; task: Physically valid protein–ligand pose selection; model: Single best solver; model version: Not reported; dataset: PoseBusters; dataset version: Not reported; split: Not reported; metric: RMSD ≤1 Å and PB-valid success; value: 34.34; unit: %; uncertainty: Not reported; protocol: Single best solver baseline under the same averaged five-fold selection test.; source locator: Table 3, PoseBusters / Mixed / AutoDock row, SBS success column; source url: https://pmc.ncbi.nlm.nih.gov/articles/PMC13104262/; evaluation origin: independent_paper; reviewed utc: 2026-09-15T23:29:32Z
- missing metadata
- model version: not_reported_in_legacy_extract; dataset version: not_reported_in_legacy_extract; split: not_reported_in_legacy_extract; uncertainty: not_reported_in_legacy_extract