Re-ranking the Sigma-2 receptor docking hit list by co-folding and docking scores (Kim, Correy, Hall et al. 2026)
Rank the compounds of a tested ultra-large docking hit list by DOCK3.7 energy, AlphaFold3 L-pLDDT or Boltz-2 pIC50, and report the area under the ROC curve for separating measured binders from high-ranking docking false positives.
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.
3 recorded evaluations, 3 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.
Results
Results are available, but no reviewed comparison panel is linked in this release.
All evaluations
3 evaluations · 3 results. Different protocols are not a single leaderboard.
Protocol: Re-ranking the Sigma-2 receptor docking hit list by co-folding and docking scores (Kim, Correy, Hall et al. 2026) · Dataset: Sigma-2 receptor docking hit list, 506 tested compounds
Sorted by AUROC (Discrimination of measured binders from high-ranking docking false positives in the tested sigma-2 receptor hit list) (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 | AUROC (Discrimination of measured binders from high-ranking docking false positives in the tested sigma-2 receptor hit list) |
|---|---|
| Boltz-2 pIC50 (Kim, Correy, Hall et al. 2026 hit-list re-ranking)Evaluation | AUC = 83.8 (best in column) |
| DOCK3.7 (Kim, Correy, Hall et al. 2026 hit-list re-ranking)Evaluation | AUC = 78.8 |
| AF3 L-pLDDT (Kim, Correy, Hall et al. 2026 hit-list re-ranking)Evaluation | AUC = 56.1 |
All 3 result rows with coverage, uncertainty and sources
Filter evaluations
Applied filters: All linked evaluations
Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.
Methods and evaluation design
Procedure, tasks and evaluated configurations
Recorded evaluations
Each evaluation records what was tested and under which conditions.
Baseline coverage
Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.
0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.
No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.
- Author-reported evaluations
- 3
Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.
Null control
Proposed control: requires review
Protocol-specific valid geometric or structural control
Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.
This is a suggested selection rule, not a validated method or a measured score.
Conventional reference
Proposed control: requires review
Upstream conventional structural reference with matched templates and cutoffs
Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.
This is a suggested selection rule, not a validated method or a measured score.
Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)
Coverage is derived from release 2026-10-22-1b7cf027e4f6. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.
Run instructions
No runnable recipe has been reviewed for this protocol. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.
Strengths, limitations and unresolved questions
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.
0 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|
No evidence rows match these filters. Choose another scope or clear the search.
Sources and history
Release 2026-10-22-1b7cf027e4f6 · Record review: source checked
1 source record and release history
- Kim, Correy, Hall et al. 2026, eLife 15:RP110475 (Europe PMC full text) · Original source · PMC13657626 (eLife 2026;15:RP110475, version of record published 2026-10-12)
Technical metadata and extraction receipts
Stable ID: hitdisc-20261022-protocol-kim-sigma2
- areas
- molecular-interactions
- contexts
- research
- task
- Protein-ligand virtual screening (library ranking)
- publication status
- peer_reviewed
- review
- method: scope-review; automated-source-review; reviewer: claude; reviewer note: Claude review agent, independent of the extraction agent; no human review claimed; date: 2026-10-22; method note: Read the record against the pinned sources and against docs/use-cases.md and docs/record-contract.md.; note: Record checked against the pinned source and the record contract. Transcription checked; not reproduced and not reviewed by a human scientist.; artifact sha256: 9be510b7b0cc152ff56a03c96877bf06b6a6bdeffdb4baecf8e999a6bf155aa6; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC13657626/fullTextXML; receipt: data/omics/use-case-coverage-hitdisc-20261022/review.json
- metric
- auroc
- metric direction
- higher
- unit
- unitless
- unit detail
- printed as a percentage on a 0-100 scale
- metric qualifier
- discrimination of measured binders from high-ranking docking false positives in a tested hit list
- metric definition
- Area under the receiver operating characteristic curve for separating true hits from non-binders, printed in the body text as a percentage.
- protocol
- Every compound in the list was synthesised and assayed in the original screening campaign. The three scores are then computed for those same compounds and their ranking compared; the comparison itself is a retrospective re-ranking of a prospectively tested set.
- denominator
- 506
- version
- Kim, Correy, Hall et al. 2026, Results 'Co-folding struggles to reliably re-rank docking hit lists'
- source locator
- Results 'Co-folding struggles to reliably re-rank docking hit lists'; Methods 'Benchmarking co-folding on experimentally validated compounds'
- control
- DOCK3.7, the engine that produced the hit list, is scored on the same compounds.
- limitations
- The negatives are compounds a docking screen already ranked highly, which is a far harder and more realistic negative set than property-matched decoys; these AUC values are not comparable with enrichment on decoy benchmarks.; The list is a biased sample of the library: only high-ranking docked molecules were synthesised, so neither the AUC nor any hit rate derived from it estimates performance over a whole library.; No training-overlap control is stated for this arm. Training cutoffs are given for the separate Mac1 pose benchmark, and Supplementary file 2 reports pairwise similarity between the datasets, but neither was extracted here.; The hit-rate curves, the semi-logarithmic ROC curves and the early-enrichment values for these sets are published only as figures (Figure 5 and its supplements 3 and 4) and were not read.; Only three scores were compared on these sets: DOCK3.7 energy, AF3 L-pLDDT and Boltz-2 pIC50. Chai-1 was used on the Mac1 pose arm only.
- scope note
- Retrospective: the method ranks a curated set of actives and negatives that were assembled before the evaluation, not compounds selected and then tested.
Related records
- evaluates task: Protein–ligand virtual screening
- uses data: Sigma-2 receptor docking hit list, 506 tested compounds
- assessment: AF3 L-pLDDT re-ranking the sigma-2 receptor docking hit list (Kim, Correy, Hall et al. 2026)
- assessment: Boltz-2 pIC50 re-ranking the sigma-2 receptor docking hit list (Kim, Correy, Hall et al. 2026)
- assessment: DOCK3.7 energy re-ranking the sigma-2 receptor docking hit list (Kim, Correy, Hall et al. 2026)
- assessed by: Find hits for a target by virtual screening