Datasets
LIT-PCBA is the virtual-screening collection; CASF and MerckFEP are separate scoring evaluations.
Task
Protein–ligand virtual screening
Virtual screening evaluates enrichment when candidate ligands are ranked using the paper’s docking/scoring workflow.
Sources
Normalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening · Results/Conclusion: virtual screening; cached text lines 97–110, 147Overview
Metrics
Top-one-percent enrichment factor, summarized across the virtual-screening evaluation.
Allowed inputs
Ligands, target proteins and docking/scoring outputs.
Sources
Normalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening · Results/Conclusion: virtual screening; cached text lines 97–110, 147Evaluation procedure diagram
How it worksComputational evaluation flow
Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.
Sources
Normalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening · Results/Conclusion: virtual screening; cached text lines 97–110, 147limited source coverage · Automated source review, 2026-09-16. All specifications and missing details
Results
Results are available, but no reviewed comparison panel is linked in this release.
All evaluations
2 evaluations · 2 results. Different protocols are not a single leaderboard.
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Pipeline: DiffDock-NMDN | Task: Protein–ligand virtual screening Dataset: CASF-2016 blind docked poses | 66.7 Forward-screening success rate % · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceDiffDock-NMDN: Protein–ligand virtual screening NMDN scoring on DiffDock-NMDN blind docked poses; not ligand-pose RMSD. Aggregation: Not reported Normalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening · Table 2, DiffDock-NMDN / NMDN row, success rate (%) column |
| Configuration: Vina | Task: Protein–ligand virtual screening Dataset: CASF-2016 blind docked poses | 42.1 Forward-screening success rate % · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceVina: Protein–ligand virtual screening Vina scoring on the same DiffDock-NMDN blind docked poses; not ligand-pose RMSD. Aggregation: Not reported Normalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening · Table 2, Vina scoring row, success rate (%) column |
Source checking is not independent reproduction. Release 2026-09-29-06401fd5b220.
Methods and evaluation design
Procedure, tasks and evaluated configurations
How it works
Evaluation methodology
LIT-PCBA is the virtual-screening collection; CASF and MerckFEP are separate scoring evaluations. Top-one-percent enrichment factor, summarized across the virtual-screening evaluation. DiffDock combined with NMDN scoring is the assessed workflow.
Sources
Normalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening · Results/Conclusion: virtual screening; cached text lines 97–110, 147Recorded evaluations
Each evaluation records what was tested and under which conditions.
Run instructions
No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.
A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.
Strengths, limitations and unresolved questions
Strengths and limitations
Strengths and considerations
No source-reviewed explanatory claims are recorded here yet.
Limitations and conditions
- Blind-docked screening and screening supplied with known binder information are different settings. Many LIT-PCBA actives arise from phenotypic assays and are not validated against the nominal target.
Sources
Normalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening · Results/Conclusion: virtual screening; cached text lines 97–110, 147
Profile review details
Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.
Stable record: reported-task-a7803ecf7708ccSpecifications
Inputs, training, access and other details
Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
| Property | Description and evidence |
|---|---|
| Datasets | LIT-PCBA is the virtual-screening collection; CASF and MerckFEP are separate scoring evaluations.SourcesNormalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening · Results/Conclusion: virtual screening; cached text lines 97–110, 147 |
| Splits | Models are fitted on the first RTMScore random PDBbind training/validation allocation. LIT-PCBA is a separate external screening collection, evaluated target by target; its compounds are not partitioned into a new supervised screening training set in the described experiment.SourcesNormalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening · §4.1.1 Binder Data Set; LIT-PCBA screening description and Table 4 |
| Metrics | Top-one-percent enrichment factor, summarized across the virtual-screening evaluation.SourcesNormalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening · Results/Conclusion: virtual screening; cached text lines 97–110, 147 |
| Baselines | DiffDock combined with NMDN scoring is the assessed workflow.SourcesNormalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening · Results/Conclusion: virtual screening; cached text lines 97–110, 147 |
| Leakage controls | The binder-training filters remove PDB entries in the test sets. The weak-binder collection is reported to have no overlap with the adopted benchmarks. LIT-PCBA pose generation and scoring do not use known binder information for the evaluated target; the paper does not claim a universal protein-family or scaffold-disjoint test.SourcesNormalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening · §4.1.1–4.1.2 including list items omitted from paragraph-only cache; LIT-PCBA screening discussion before Table 4 |
| Uncertainty | The LIT-PCBA table reports per-target enrichment factors, an across-target average and counts above enrichment thresholds. It does not report confidence intervals or repeated-run dispersion for these screening estimates; sampling variability reported for the PDBbind docking experiment is a different endpoint. · Not reported in inspected sourcesSourcesNormalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening · LIT-PCBA screening results, Table 4 and its footnotes; contrast Table 1 |
| Entity type | Paper-specific computational evaluation protocol.SourcesNormalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening · Results/Conclusion: virtual screening; cached text lines 97–110, 147 |
| Organisms | The LIT-PCBA table identifies molecular targets, with many activity labels derived from cell-based phenotypic assays. The screening description and target table do not give a per-assay organism or cell-line inventory; target identity alone does not establish assay provenance. · Not reported in inspected sourcesSourcesNormalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening · LIT-PCBA screening description, Table 4 and reference to Table S6 |
| Assays | Active/inactive compound screening labels.SourcesNormalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening · Results/Conclusion: virtual screening; cached text lines 97–110, 147 |
| Allowed inputs | Ligands, target proteins and docking/scoring outputs.SourcesNormalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening · Results/Conclusion: virtual screening; cached text lines 97–110, 147 |
| Adaptation | DiffDock pose generation combined with NMDN scoring; the screen is separate from CASF affinity evaluation.SourcesNormalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening · Results/Conclusion: virtual screening; cached text lines 97–110, 147 |
Evidence
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Papers and result coverage
Last literature check: 2026-09-17. Primary-paper discovery and source inspection. Source-checked results are not independently reproduced experiments.
| Paper or primary resource | Version | Reference |
|---|---|---|
| Normalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening | version of record | Read source DOI: 10.1021/acs.jcim.4c01014 |
Historical gaps recorded on 2026-09-17
The catalogue now holds 2 result rows for this benchmark. A note below about pending extraction describes the state on 2026-09-17 and may since have been answered by a later batch. The result rows and their sources are the current record.
- Target-level EF, mean EF and counts above EF cutoffs are separate metrics.
- Do not describe pKd-score or pKd-screen as experimentally calibrated affinity from the EF metric.
- All table scores are conditional on the stated docked poses.
Search and extraction details
primary comparison table screened
Searches
- "PMC11815853"
Evidence locations
- Table 4 caption and footnotes
- Results: virtual screening
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.
17 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol. Individual claims | Normalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening Results/Conclusion: virtual screening; cached text lines 97–110, 147 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Diagram steps
| Normalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening Results/Conclusion: virtual screening; cached text lines 97–110, 147 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Computational evaluation flow Individual claims | Normalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening Results/Conclusion: virtual screening; cached text lines 97–110, 147 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Datasets LIT-PCBA is the virtual-screening collection; CASF and MerckFEP are separate scoring evaluations. Individual claims | Normalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening Results/Conclusion: virtual screening; cached text lines 97–110, 147 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Splits Models are fitted on the first RTMScore random PDBbind training/validation allocation. LIT-PCBA is a separate external screening collection, evaluated target by target; its compounds are not partitioned into a new supervised screening training set in the described experiment. Individual claims | Normalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening §4.1.1 Binder Data Set; LIT-PCBA screening description and Table 4 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Adaptation DiffDock pose generation combined with NMDN scoring; the screen is separate from CASF affinity evaluation. Individual claims | Normalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening Results/Conclusion: virtual screening; cached text lines 97–110, 147 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Metrics Top-one-percent enrichment factor, summarized across the virtual-screening evaluation. Individual claims | Normalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening Results/Conclusion: virtual screening; cached text lines 97–110, 147 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Baselines DiffDock combined with NMDN scoring is the assessed workflow. Individual claims | Normalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening Results/Conclusion: virtual screening; cached text lines 97–110, 147 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Leakage controls The binder-training filters remove PDB entries in the test sets. The weak-binder collection is reported to have no overlap with the adopted benchmarks. LIT-PCBA pose generation and scoring do not use known binder information for the evaluated target; the paper does not claim a universal protein-family or scaffold-disjoint test. Individual claims | Normalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening §4.1.1–4.1.2 including list items omitted from paragraph-only cache; LIT-PCBA screening discussion before Table 4 Version: version of record | source checked automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Uncertainty The LIT-PCBA table reports per-target enrichment factors, an across-target average and counts above enrichment thresholds. It does not report confidence intervals or repeated-run dispersion for these screening estimates; sampling variability reported for the PDBbind docking experiment is a different endpoint. Individual claims | Normalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening LIT-PCBA screening results, Table 4 and its footnotes; contrast Table 1 Version: version of record | unreported automated source review · 2026-09-16 Audit detailsRelevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
View linked audit checks and correction history
Release 2026-09-29-06401fd5b220 · Record review: needs review
2 source records and release history
- Normalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening · Original source · version of record
- Normalized Protein–Ligand Distance Likelihood Score for End-to-End Blind Docking and Virtual Screening · Original source · version of record
Technical metadata and extraction receipts
Stable ID: reported-task-a7803ecf7708cc
- areas
- molecular-interactions
- tasks
- Protein–ligand virtual screening
- entity level
- task
- version
- Not reported
- task
- Protein–ligand virtual screening
- scope note
- Paper-specific evaluation task; protocol completeness requires further extraction.
- benchmark research
- review date: 2026-09-17; status: primary_comparison_table_screened; primary sources: expansion-p3-nmdn-2025; inspected locators: Table 4 caption and footnotes; Results: virtual screening; searched queries: "PMC11815853"; gaps: Target-level EF, mean EF and counts above EF cutoffs are separate metrics.; Do not describe pKd-score or pKd-screen as experimentally calibrated affinity from the EF metric.; All table scores are conditional on the stated docked poses.; claim scope: Primary-paper discovery and source inspection. Source-checked results are not independently reproduced experiments.
- historical missing metadata
- protocol version: not_reported_in_legacy_extract; split: not_reported_in_legacy_extract
- metadata review scope
- historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
- legacy kinds
- benchmark
- entity classification
- review date: 2026-09-17; rationale: This source-scoped record identifies the biological prediction task and holds its paper context. Preserve the existing task identity; exact split, model adaptation and scoring remain in linked evaluations or separate protocol records.; source ids: nmdn-2025; source locator: Results/Conclusion: virtual screening; cached text lines 97–110, 147; ambiguities: A paper- or suite-specific task may constrain some inputs or metrics; that alone does not make it interchangeable with a complete versioned protocol. No protocol equivalence is inferred.; Some legacy profile Entity type facts use the generic phrase computational evaluation protocol. That boilerplate is not sufficient to establish a single fixed protocol identity or to merge this task with another protocol record.
Related records
- dataset: CASF-2016 blind docked poses
- benchmark: DiffDock-NMDN: Protein–ligand virtual screening
- benchmark: Vina: Protein–ligand virtual screening