result · source checked
46.8 Success rate, ligand all-atom RMSD <2 Å
DiffDock-L · Success rate, ligand all-atom RMSD <2 Å · LiPP lipid–protein complexes
- Tested model
- DiffDock-L
- Task or benchmark
- Lipid–protein binding pose
- Dataset
- LiPP lipid–protein complexes
- Procedure
- Top-scoring pose; all-atom lipid RMSD below 2 Å.
- Evaluation
- DiffDock-L: Lipid–protein binding pose
- Evidence
- Independent external evaluation · source checkedThe LiPP Benchmark Set for Modeling Lipid–Protein Complexes: Comparison of Co-Folding and Docking Methods · Table 2, DiffDock-L row, LiPP (N=331) % Success Rate 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 |
|---|---|---|
| DiffDock-L: Lipid–protein binding pose Top-scoring pose; all-atom lipid RMSD below 2 Å. Independent external evaluation · Evaluation metadata: needs review | ||
| 46.8 Success rate, ligand all-atom RMSD <2 Å Unit: % · Direction: unknown | Uncertainty: 95% CI 41.3–52.3 Scored: Not reported · Eligible: Not reported | source checkedThe LiPP Benchmark Set for Modeling Lipid–Protein Complexes: Comparison of Co-Folding and Docking Methods · Table 2, DiffDock-L row, LiPP (N=331) % Success Rate column Source checking is not independent reproduction. |
Sources and history
Release 2026-09-16-d74d282221a9 · Record review: source checked
- The LiPP Benchmark Set for Modeling Lipid–Protein Complexes: Comparison of Co-Folding and Docking Methods · Original source · PMC13292216.1
Technical metadata and extraction receipts
Stable ID: lit-042
- areas
- molecular-interactions
- tasks
- Lipid–protein binding pose
- printed value
- 46.8
- numeric value
- 46.8
- metric
- Success rate, ligand all-atom RMSD <2 Å
- metric direction
- unknown
- unit
- %
- uncertainty
- 95% CI 41.3–52.3
- source locator
- Table 2, DiffDock-L row, LiPP (N=331) % Success Rate column
- review
- method: independent_ai_table_review; reviewer: Codex omics research agent; independent source-table review, not human review; reviewed at: 2026-09-16T10:41:16.550691+00:00; notes: JATS label is bare 2, which caused original parser miss. LiPP N=331 full-set column selected, not N=36 test subset. Caption success is lipid all-atom RMSD <2 Angstrom; PB-valid is a separate table. This verifies the central score at its source location, not every metadata field or an experimental reproduction.; evidence: {"table_xml_id": "tbl2", "row_cells": ["DiffDock-L", "46.8 {41.3–52.3}", "30.5 {16.3–48.1}", "-", "50"], "selected_cell_zero_based": 1, "selected_cell_xml": "<td align=\"left\" colspan=\"1\" rowspan=\"1\">46.8 {41.3–52.3}</td>", "caption": "Success Rates (Success Defined Only by Lipid Pose All-Atom RMSD Cutoff Values Less Than 2 Å) of the Five Computational Methods Used in This Study on Lipid–Protein Complexes (via LiPP Benchmark Set) Compared to Protein-Small Molecule Complexes (via PoseBusters Benchmark Set)"}; artifact sha256: 6ff34f2f709a14858a3753abf9f8f6efa1e7e3c351f15c70cf64264193a9414e; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC13292216/fullTextXML
- legacy id
- lit-042
- legacy row
- id: lit-042; paper id: lipp-2026; domain id: molecular-interactions; task: Lipid–protein binding pose; model: DiffDock-L; model version: Not reported; dataset: LiPP lipid–protein complexes; dataset version: 331 complexes; split: Not reported; metric: Success rate, ligand all-atom RMSD <2 Å; value: 46.8; unit: %; uncertainty: 95% CI 41.3–52.3; protocol: Top-scoring pose; all-atom lipid RMSD below 2 Å.; source locator: Table 2, DiffDock-L row, LiPP (N=331) % Success Rate column; source url: https://pmc.ncbi.nlm.nih.gov/articles/PMC13292216/; evaluation origin: independent_paper; reviewed utc: 2026-09-15T23:25:00Z
- missing metadata
- model version: not_reported_in_legacy_extract; split: not_reported_in_legacy_extract