Protocol

Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5)

Measure the average wall-clock time per compound to co-fold a protein-ligand pair on one NVIDIA H100, for five DEKOIS 2.0 targets with 400 decoys each.

6 evaluations · 36 results

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.

6 recorded evaluations, 36 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

6 evaluations · 36 results. Different protocols are not a single leaderboard.

Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) · Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each

Sorted by Runtime (Average total time per compound on one NVIDIA H100 80 GB, averaged over the five targets) (lower 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	Runtime (Average total time per compound on one NVIDIA H100 80 GB, averaged over the five targets)	Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target a2a)	Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target ar)	Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target cdk2)	Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target ctsk)	Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target hdac2)
Boltz-2 (without affinity module), 1 sample, timed per compoundEvaluation	7.79 (best in column)	10.8 (best in column)	6.14 (best in column)	7.11 (best in column)	6.05 (best in column)	8.79 (best in column)
Protenix, 1 sample, timed per compoundEvaluation	12.4	20.1	9.46	10.5	8.49	13.4
AF3, 1 sample, timed per compoundEvaluation	13	19.1	10.6	12.8	6.7	15.7
Boltz-2, 1 sample, timed per compoundEvaluation	17.8	21.5	15.4	16.8	16.2	18.9
AF3, 5 samples, timed per compoundEvaluation	18.4	26.3	15.4	17.5	10.3	22.6
Protenix, 5 samples, timed per compoundEvaluation	34.6	45.8	29.7	31.8	30	35.6

All 36 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: AF3, 1 sample, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	19.1 Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target a2a) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Continued row with 1 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row '(row continued, sample count 1)' (Number of samples = 1), column 'a2a'
Configuration: AF3, 1 sample, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	10.6 Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target ar) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Continued row with 1 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row '(row continued, sample count 1)' (Number of samples = 1), column 'ar'
Configuration: AF3, 1 sample, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	13 Runtime (Average total time per compound on one NVIDIA H100 80 GB, averaged over the five targets) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Continued row with 1 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row '(row continued, sample count 1)' (Number of samples = 1), column 'Average'
Configuration: AF3, 1 sample, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	12.8 Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target cdk2) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Continued row with 1 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row '(row continued, sample count 1)' (Number of samples = 1), column 'cdk2'
Configuration: AF3, 1 sample, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	6.7 Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target ctsk) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Continued row with 1 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row '(row continued, sample count 1)' (Number of samples = 1), column 'ctsk'
Configuration: AF3, 1 sample, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	15.7 Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target hdac2) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Continued row with 1 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row '(row continued, sample count 1)' (Number of samples = 1), column 'hdac2'
Configuration: AF3, 5 samples, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	26.3 Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target a2a) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source AF3 with 5 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row 'AF3' (Number of samples = 5), column 'a2a'
Configuration: AF3, 5 samples, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	15.4 Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target ar) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source AF3 with 5 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row 'AF3' (Number of samples = 5), column 'ar'
Configuration: AF3, 5 samples, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	18.4 Runtime (Average total time per compound on one NVIDIA H100 80 GB, averaged over the five targets) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source AF3 with 5 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row 'AF3' (Number of samples = 5), column 'Average'
Configuration: AF3, 5 samples, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	17.5 Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target cdk2) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source AF3 with 5 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row 'AF3' (Number of samples = 5), column 'cdk2'
Configuration: AF3, 5 samples, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	10.3 Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target ctsk) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source AF3 with 5 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row 'AF3' (Number of samples = 5), column 'ctsk'
Configuration: AF3, 5 samples, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	22.6 Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target hdac2) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source AF3 with 5 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row 'AF3' (Number of samples = 5), column 'hdac2'
Configuration: Boltz-2, 1 sample, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	21.5 Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target a2a) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Boltz-2 with 1 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row 'Boltz-2' (Number of samples = 1), column 'a2a'
Configuration: Boltz-2, 1 sample, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	15.4 Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target ar) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Boltz-2 with 1 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row 'Boltz-2' (Number of samples = 1), column 'ar'
Configuration: Boltz-2, 1 sample, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	17.8 Runtime (Average total time per compound on one NVIDIA H100 80 GB, averaged over the five targets) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Boltz-2 with 1 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row 'Boltz-2' (Number of samples = 1), column 'Average'
Configuration: Boltz-2, 1 sample, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	16.8 Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target cdk2) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Boltz-2 with 1 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row 'Boltz-2' (Number of samples = 1), column 'cdk2'
Configuration: Boltz-2, 1 sample, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	16.2 Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target ctsk) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Boltz-2 with 1 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row 'Boltz-2' (Number of samples = 1), column 'ctsk'
Configuration: Boltz-2, 1 sample, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	18.9 Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target hdac2) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Boltz-2 with 1 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row 'Boltz-2' (Number of samples = 1), column 'hdac2'
Configuration: Boltz-2 (without affinity module), 1 sample, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	10.8 Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target a2a) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Boltz-2 (without affinity module) with 1 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row 'Boltz-2 (without affinity module)' (Number of samples = 1), column 'a2a'
Configuration: Boltz-2 (without affinity module), 1 sample, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	6.14 Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target ar) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Boltz-2 (without affinity module) with 1 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row 'Boltz-2 (without affinity module)' (Number of samples = 1), column 'ar'
Configuration: Boltz-2 (without affinity module), 1 sample, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	7.79 Runtime (Average total time per compound on one NVIDIA H100 80 GB, averaged over the five targets) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Boltz-2 (without affinity module) with 1 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row 'Boltz-2 (without affinity module)' (Number of samples = 1), column 'Average'
Configuration: Boltz-2 (without affinity module), 1 sample, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	7.11 Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target cdk2) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Boltz-2 (without affinity module) with 1 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row 'Boltz-2 (without affinity module)' (Number of samples = 1), column 'cdk2'
Configuration: Boltz-2 (without affinity module), 1 sample, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	6.05 Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target ctsk) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Boltz-2 (without affinity module) with 1 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row 'Boltz-2 (without affinity module)' (Number of samples = 1), column 'ctsk'
Configuration: Boltz-2 (without affinity module), 1 sample, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	8.79 Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target hdac2) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Boltz-2 (without affinity module) with 1 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row 'Boltz-2 (without affinity module)' (Number of samples = 1), column 'hdac2'
Configuration: Protenix, 1 sample, timed per compound	Protocol: Co-folding time per compound on five DEKOIS 2.0 targets (Shen et al. 2025 Table 5) Dataset: DEKOIS 2.0 speed subset, five targets with 400 decoys each	20.1 Runtime (Average total time per compound on one NVIDIA H100 80 GB, DEKOIS 2.0 target a2a) second · lower Uncertainty: Not reported by the source: The source prints no interval or spread for this value Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Continued row with 1 sample(s): time per compound (Shen et al. 2025 Table 5) hitdisc-20261022-protocol-shen-speed Aggregation: Not reported Shen et al. 2025, Chemical Science (Europe PMC full text) · Table 5, row '(row continued, sample count 1)' (Number of samples = 1), column 'a2a'

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: 6

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

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

How to read the evidence

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)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: hitdisc-20261022-protocol-shen-speed

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: runtime
metric direction: lower
unit: second
unit detail: seconds per compound, the total time for a target averaged over its compounds
metric definition: The overall computational efficiency calculated by averaging the total time per compound, with pre-computed MSAs and ligand SMILES as input.
protocol: Five representative DEKOIS 2.0 targets, each with 400 randomly selected decoys, run on a single NVIDIA H100 with 80 GB of memory.
denominator: 5
version: Shen et al. 2025, Table 5
source locator: Table 5 and its caption
limitations: MSA construction is excluded: pre-computed MSAs were fed as input, so the figures are inference time only.; The authors note that runtimes vary substantially across targets with token length and other factors, so the average over five targets is not a per-compound cost for an arbitrary target.; No docking tool was timed, so this table does not compare co-folding cost with docking cost.; Timings are single measurements; no repeats or uncertainty are reported.
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: DEKOIS 2.0 speed subset, five targets with 400 decoys each
assessment: Continued row with 1 sample(s): time per compound (Shen et al. 2025 Table 5)
assessment: AF3 with 5 sample(s): time per compound (Shen et al. 2025 Table 5)
assessment: Boltz-2 with 1 sample(s): time per compound (Shen et al. 2025 Table 5)
assessment: Boltz-2 (without affinity module) with 1 sample(s): time per compound (Shen et al. 2025 Table 5)
assessment: Continued row with 1 sample(s): time per compound (Shen et al. 2025 Table 5)
assessment: Protenix with 5 sample(s): time per compound (Shen et al. 2025 Table 5)
assessed by: Find hits for a target by virtual screening

Suggest a correction