DiffDock-L (LiPP evaluation)

Overview

An explanatory profile has not yet been reviewed for this record.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Evaluations and results

5 evaluations · 5 results. Different protocols are not a single leaderboard.

Sorted by Ligand RMSD under 2a rate (ligand pose RMSD below 2 Angstrom, as reported in the cited literature; PoseBusters v2) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	Protocol and dataset	Ligand RMSD under 2a rate (ligand pose RMSD below 2 Angstrom, as reported in the cited literature; PoseBusters v2)	Ligand RMSD under 2a rate (lipid pose all-atom RMSD below 2 Angstrom; Full LiPP set)	Ligand RMSD under 2a rate (lipid pose all-atom RMSD below 2 Angstrom; LiPP test set)	Success rate (RMSD below 2 Angstrom and PoseBusters valid; Full LiPP set)	Success rate (RMSD below 2 Angstrom and PoseBusters valid; LiPP test set)
DiffDock-L (LiPP evaluation)Evaluation	LiPP Table 2: lipid pose all-atom RMSD below 2 Angstrom, PoseBusters v2, PoseBusters v2 (308 protein-small molecule complexes)	50%	Not reported	Not reported	Not reported	Not reported
DiffDock-L (LiPP evaluation)Evaluation	LiPP Table 3: RMSD below 2 Angstrom and PoseBusters valid, Full LiPP set, LiPP benchmark set (331 lipid-protein complexes)	Not reported	Not reported	Not reported	24.1 {19.6–29.1}%	Not reported
DiffDock-L (LiPP evaluation)Evaluation	LiPP Table 3: RMSD below 2 Angstrom and PoseBusters valid, LiPP test set, LiPP test set (36 complexes released after every tool's cutoff)	Not reported	Not reported	Not reported	Not reported	8.3 {1.7–22.4}%
DiffDock-L (LiPP evaluation)Evaluation	LiPP Table 2: lipid pose all-atom RMSD below 2 Angstrom, Full LiPP set, LiPP benchmark set (331 lipid-protein complexes)	Not reported	46.8 {41.3–52.3}%	Not reported	Not reported	Not reported
DiffDock-L (LiPP evaluation)Evaluation	LiPP Table 2: lipid pose all-atom RMSD below 2 Angstrom, LiPP test set, LiPP test set (36 complexes released after every tool's cutoff)	Not reported	Not reported	30.5 {16.3–48.1}%	Not reported	Not reported

All 5 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: DiffDock-L (LiPP evaluation)	Protocol: LiPP Table 3: RMSD below 2 Angstrom and PoseBusters valid, Full LiPP set Dataset: LiPP benchmark set (331 lipid-protein complexes)	24.1 {19.6–29.1}% Success rate (RMSD below 2 Angstrom and PoseBusters valid; Full LiPP set) percent · higher Uncertainty: 95% CI 19.6 to 29.1. Exact binomial interval (table footnote a: 'lower and upper bounds of the 95% confidence intervals calculated with exact binomial distribution') Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DiffDock-L on Full LiPP set (RMSD below 2 Angstrom and PoseBusters valid) lit-structure-20261011-lipp-protocol-pb-valid-lipp-331 Aggregation: Not reported The LiPP Benchmark Set for Modeling Lipid–Protein Complexes: Comparison of Co-Folding and Docking Methods · Table 3, row 'DiffDock-L', column 'LiPP (N = 331) % Success Rate'
Configuration: DiffDock-L (LiPP evaluation)	Protocol: LiPP Table 3: RMSD below 2 Angstrom and PoseBusters valid, LiPP test set Dataset: LiPP test set (36 complexes released after every tool's cutoff)	8.3 {1.7–22.4}% Success rate (RMSD below 2 Angstrom and PoseBusters valid; LiPP test set) percent · higher Uncertainty: 95% CI 1.7 to 22.4. Exact binomial interval (table footnote a: 'lower and upper bounds of the 95% confidence intervals calculated with exact binomial distribution') Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DiffDock-L on LiPP test set (RMSD below 2 Angstrom and PoseBusters valid) lit-structure-20261011-lipp-protocol-pb-valid-lipp-test-36 Aggregation: Not reported The LiPP Benchmark Set for Modeling Lipid–Protein Complexes: Comparison of Co-Folding and Docking Methods · Table 3, row 'DiffDock-L', column 'LiPP test set (N = 36) % Success Rate'
Configuration: DiffDock-L (LiPP evaluation)	Protocol: LiPP Table 2: lipid pose all-atom RMSD below 2 Angstrom, Full LiPP set Dataset: LiPP benchmark set (331 lipid-protein complexes)	46.8 {41.3–52.3}% Ligand RMSD under 2a rate (lipid pose all-atom RMSD below 2 Angstrom; Full LiPP set) percent · higher Uncertainty: 95% CI 41.3 to 52.3. Exact binomial interval (table footnote a: 'lower and upper bounds of the 95% confidence intervals calculated with exact binomial distribution') Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DiffDock-L on Full LiPP set (lipid pose all-atom RMSD below 2 Angstrom) lit-structure-20261011-lipp-protocol-rmsd-lipp-331 Aggregation: Not reported The LiPP Benchmark Set for Modeling Lipid–Protein Complexes: Comparison of Co-Folding and Docking Methods · Table 2, row 'DiffDock-L', column 'LiPP (N = 331) % Success Rate'
Configuration: DiffDock-L (LiPP evaluation)	Protocol: LiPP Table 2: lipid pose all-atom RMSD below 2 Angstrom, LiPP test set Dataset: LiPP test set (36 complexes released after every tool's cutoff)	30.5 {16.3–48.1}% Ligand RMSD under 2a rate (lipid pose all-atom RMSD below 2 Angstrom; LiPP test set) percent · higher Uncertainty: 95% CI 16.3 to 48.1. Exact binomial interval (table footnote a: 'lower and upper bounds of the 95% confidence intervals calculated with exact binomial distribution') Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DiffDock-L on LiPP test set (lipid pose all-atom RMSD below 2 Angstrom) lit-structure-20261011-lipp-protocol-rmsd-lipp-test-36 Aggregation: Not reported The LiPP Benchmark Set for Modeling Lipid–Protein Complexes: Comparison of Co-Folding and Docking Methods · Table 2, row 'DiffDock-L', column 'LiPP test set (N = 36) % Success Rate'
Configuration: DiffDock-L (LiPP evaluation)	Protocol: LiPP Table 2: lipid pose all-atom RMSD below 2 Angstrom, PoseBusters v2 Dataset: PoseBusters v2 (308 protein-small molecule complexes)	50% Ligand RMSD under 2a rate (ligand pose RMSD below 2 Angstrom, as reported in the cited literature; PoseBusters v2) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Result quoted from another source · Source checked Methods, coverage and source DiffDock-L on PoseBusters v2 (lipid pose all-atom RMSD below 2 Angstrom) lit-structure-20261011-lipp-protocol-rmsd-posebusters-v2-308 Aggregation: Not reported The LiPP Benchmark Set for Modeling Lipid–Protein Complexes: Comparison of Co-Folding and Docking Methods · Table 2, row 'DiffDock-L', column 'PoseBusters v2 (N = 308) % Success Rate'

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Use this configuration

How it works, versions and access

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

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.

1 evidence row matching the loaded filters

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance
Facets: method types 1 values supervised_machine_learning Individual claims	The LiPP Benchmark Set for Modeling Lipid–Protein Complexes: Comparison of Co-Folding and Docking Methods Original source ↗ LiPP: "AI-based docking tool", "Trained on complexes in PDBbind before 2019" Version: PMC13292216.1 Retrieved: 2026-09-17T07:56:27.507412+00:00	conflicting claim ["source-hash-verification","automated-source-review"] · 2026-10-12 Audit details Correct the method type from specialist to supervised_machine_learning (use-case baseline review 2026-10-12, table 2). Evidence from docs/reviews/use-cases/baselines-2026-10-12.md. Independent review 2026-10-12: approved. See docs/reviews/2026-10-12-method-type-corrections.md. Conflicting source claim: `"[\"supervised_machine_learning\"]"`. Claim record status: source_checked. Field: `facets.method_types` Claim: metadata-correction-tags-20261012-7a1e3080438e1e4a5863 Source artifact SHA-256: `6ff34f2f709a14858a3753abf9f8f6efa1e7e3c351f15c70cf64264193a9414e` Hash scope: Exact retrieved primary paper artifact bytes. Inspected artifact Extraction artifact SHA-256: `6ff34f2f709a14858a3753abf9f8f6efa1e7e3c351f15c70cf64264193a9414e` Extraction artifact

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

1 source record and release history

The LiPP Benchmark Set for Modeling Lipid–Protein Complexes: Comparison of Co-Folding and Docking Methods · Original source · PMC13292216.1

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: lit-structure-20261011-lipp-config-diffdock-l

areas: protein-structure; molecular-interactions
contexts: research
method types: supervised_machine_learning
reported name: DiffDock-L
method role: AI-based docking
training setting: Trained on complexes in PDBbind before 2019
foundation model eligible: false
source locator: Table 1, row 'DiffDock-L'; Tables 2 and 3 row labels
missing metadata: version: reason: unreported; note: Tool versions are not printed in Tables 1 to 3
provenance note: DiffDock-L as run on the LiPP benchmark set by the LiPP authors.

Related records