GPCRrecent screening (the six targets whose first structures postdate the Boltz-2 training cutoff) (Shen et al. 2025 Table 3)
Rank the actives and TocoDecoy-generated decoys of the six targets whose first structures postdate the Boltz-2 training cutoff in the GPCRrecent set with a co-folding confidence score, a rescoring function or a docking baseline, and report AUROC, BEDROC and enrichment factors averaged over targets.
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.
2 recorded evaluations, 20 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
2 evaluations · 20 results. Different protocols are not a single leaderboard.
Protocol: GPCRrecent screening (the six targets whose first structures postdate the Boltz-2 training cutoff) (Shen et al. 2025 Table 3) · Dataset: GPCRrecent, six targets after the Boltz-2 training cutoff
Sorted by AUROC (AUROC, mean over the 6 GPCRrecent targets) (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 (AUROC, mean over the 6 GPCRrecent targets) | AUROC (AUROC, median over the 6 GPCRrecent targets) | Bedroc (BEDROC with alpha = 80.5, mean over the 6 GPCRrecent targets) | Bedroc (BEDROC with alpha = 80.5, median over the 6 GPCRrecent targets) | Enrichment factor (EF at the top 0.5% of the ranked library, mean over the 6 GPCRrecent targets) | Enrichment factor (EF at the top 0.5% of the ranked library, median over the 6 GPCRrecent targets) | Enrichment factor (EF at the top 1% of the ranked library, mean over the 6 GPCRrecent targets) | Enrichment factor (EF at the top 1% of the ranked library, median over the 6 GPCRrecent targets) | Enrichment factor (EF at the top 5% of the ranked library, mean over the 6 GPCRrecent targets) | Enrichment factor (EF at the top 5% of the ranked library, median over the 6 GPCRrecent targets) |
|---|---|---|---|---|---|---|---|---|---|---|
| Boltz-2 (min-iPAE) as a screening scoreEvaluation | 0.764 (best in column) | 0.74 (best in column) | 0.287 (best in column) | 0.245 (best in column) | 19 (best in column) | 17.6 (best in column) | 14.3 (best in column) | 12.5 (best in column) | 6.83 (best in column) | 5.87 (best in column) |
| Boltz-2 (ipTM) as a screening scoreEvaluation | 0.717 | 0.699 | 0.23 | 0.201 | 15.8 | 13.6 | 12.6 | 10.9 | 5.17 | 4.84 |
All 20 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
- 2
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
- Shen et al. 2025, Chemical Science (Europe PMC full text) · Original source · PMC12704515 (Chem Sci, published 2025-12-11)
Technical metadata and extraction receipts
Stable ID: hitdisc-20261022-protocol-shen-gpcrrecent-6
- 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: 11a4cee97057d9e72f9393024d22fdd169e3134f493367eee2f7869facf9ccf8; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC12704515/fullTextXML; receipt: data/omics/use-case-coverage-hitdisc-20261022/review.json
- metric
- enrichment-factor
- metric direction
- higher
- unit
- unitless
- metric qualifier
- mean and median over the GPCRrecent targets
- metric definition
- AUROC, BEDROC with alpha = 80.5 (the top 2% of the ranked list contributes 80% of the score), and enrichment factors at 0.5%, 1% and 5%, each reported as the mean and the median over targets. EFx% is the ratio of true positives found in the top x% of the ranked compounds relative to random selection.
- protocol
- Receptor structures retrieved from the PDB and prepared with the Protein Preparation Wizard; ligands prepared with LigPrep; co-folding, rescoring and docking all applied to the same compounds.
- denominator
- 6
- version
- Shen et al. 2025, Table 3
- source locator
- Table 3 (rows marked 'subset' and footnote a)
- control
- Targets whose first crystal structure was released after 2022, chosen so that the structural inputs postdate the co-folding models' training data.
- limitations
- Enrichment factors depend on the actives-to-inactives ratio and on how the negatives were built, which differ by more than an order of magnitude between the benchmarks in this store (1:30 for DEKOIS 2.0, 1:50 for GPCRrecent, and from about 1:43 to about 1:200 across the five LIT-PCBA targets scored here, reaching about 1:18000 for LIT-PCBA ADRB2). Values from different protocols are not comparable.; The decoys are generated by a conditional recurrent neural network (TocoDecoy) at 1:50, not assayed inactives.; The temporal control covers crystal structures only. The authors exclude Boltz-2's affinity module from this analysis because its binding-data training sources overlap the benchmark, and say the set cannot reflect the generalisation of affinity predictors.; AF3 was not run on this set; Protenix and Boltz-2 were used as representatives because of their lower memory requirements.; Only the two Boltz-2 rows marked 'subset' in Table 3 were computed on these six targets; the other rows in the table cover all 16.
- 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: GPCRrecent, six targets after the Boltz-2 training cutoff
- part of: GPCRrecent
- assessment: Boltz-2 (ipTM) subset on GPCRrecent (Shen et al. 2025 Table 3)
- assessment: Boltz-2 (min-iPAE) subset on GPCRrecent (Shen et al. 2025 Table 3)
- assessed by: Find hits for a target by virtual screening