Datasets
RCSB PDB-derived chain–ligand pairs with binding-affinity labels, refined to pocket–ligand examples.
Task
Protein–ligand binding affinity prediction
Protein–ligand affinity regression uses curated structural complexes and a held-out fraction of the assembled dataset.
Sources
DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity · Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captionsOverview
Metrics
Mean absolute error and root mean squared error for affinity prediction.
Allowed inputs
Pocket–ligand structural features.
Sources
DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity · Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captionsEvaluation 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
DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity · Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captionslimited 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 |
|---|---|---|---|
| Configuration: DEELIG | Task: Protein–ligand binding affinity prediction Dataset: PDBbind core v2016 | 0.889 Pearson R unitless · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceDEELIG: Protein–ligand binding affinity prediction Source paper reports DEELIG on PDBbind core set. Aggregation: Not reported DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity · Table 2, DEELIG row, PDBbind v2016 column |
| Configuration: TOPBP (Complex) | Task: Protein–ligand binding affinity prediction Dataset: PDBbind core v2016 | 0.861 Pearson R unitless · unknown Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Result quoted from another source · Source checkedMethods, coverage and sourceTOPBP (Complex): Protein–ligand binding affinity prediction Source table compiles a previously published comparator; protocol equivalence is not established. Aggregation: Not reported DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity · Table 2, TOPBP (Complex) row, PDBbind v2016 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
RCSB PDB-derived chain–ligand pairs with binding-affinity labels, refined to pocket–ligand examples. The feature dataset is divided into training, validation and test partitions in an 80:10:10 ratio. Mean absolute error and root mean squared error for affinity prediction. Atomic versus composite feature models; the PDBbind-core comparison also lists AutoDock Vina, RF::VinaElem, TOPBP and AGL Score. The checked dataset section gives partition proportions but no scaffold- or protein-target-disjoint assignment rule. The reported SD describes dispersion associated with real/predicted values. It is not identified as a confidence interval or independent retraining uncertainty.
Sources
DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity · Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captionsRecorded 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
- Random pair splitting does not establish scaffold- or target-disjoint generalization; chain-level examples may share protein or ligand information.
Sources
DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity · Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captions
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-d81be76396e644Specifications
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 | RCSB PDB-derived chain–ligand pairs with binding-affinity labels, refined to pocket–ligand examples.SourcesDEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity · Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captions |
| Splits | The feature dataset is divided into training, validation and test partitions in an 80:10:10 ratio.SourcesDEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity · Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captions |
| Metrics | Mean absolute error and root mean squared error for affinity prediction.SourcesDEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity · Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captions |
| Baselines | Atomic versus composite feature models; the PDBbind-core comparison also lists AutoDock Vina, RF::VinaElem, TOPBP and AGL Score.SourcesDEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity · Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captions |
| Leakage controls | The checked dataset section gives partition proportions but no scaffold- or protein-target-disjoint assignment rule. · Not reported in inspected sourcesSourcesDEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity · Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captions |
| Uncertainty | The reported SD describes dispersion associated with real/predicted values. It is not identified as a confidence interval or independent retraining uncertainty.SourcesDEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity · Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captions |
| Entity type | Paper-specific computational evaluation protocol.SourcesDEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity · Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captions |
| Organisms | The PDB query selects protein–ligand structures with measured affinity and crystallographic criteria. The raw-data and refinement sections specify no taxonomic selection or organism-count table for the retained chain–ligand pairs. · Not reported in inspected sourcesSourcesDEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity · Novel data set: raw data; Data set refinement |
| Assays | Protein–ligand structural and binding-affinity labels.SourcesDEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity · Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captions |
| Allowed inputs | Pocket–ligand structural features.SourcesDEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity · Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captions |
| Adaptation | Supervised affinity regression on the training partition.SourcesDEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity · Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captions |
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-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.
| Paper or primary resource | Version | Reference |
|---|---|---|
| DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity | PMC archival version PMC8274096.1 | Read source DOI: 10.1177/11779322211030364 |
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.
- Complete raw tables acquired. Table 1PCC footnote sayspercentcorrectclassification whileTable 2 labelsPearson; ambiguity quarantined. Literature comparison rows have different training histories. Structured extraction pending.
Search and extraction details
source found structured extraction pending
Searches
- DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity primary paper benchmark results
Evidence locations
- Tables1–3; novel test and PDBbind2013/2016 comparisons
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 | DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captions Version: PMC archival version PMC8274096.1 | 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
| DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captions Version: PMC archival version PMC8274096.1 | 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 | DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captions Version: PMC archival version PMC8274096.1 | 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 RCSB PDB-derived chain–ligand pairs with binding-affinity labels, refined to pocket–ligand examples. Individual claims | DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captions Version: PMC archival version PMC8274096.1 | 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 The feature dataset is divided into training, validation and test partitions in an 80:10:10 ratio. Individual claims | DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captions Version: PMC archival version PMC8274096.1 | 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 Supervised affinity regression on the training partition. Individual claims | DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captions Version: PMC archival version PMC8274096.1 | 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 Mean absolute error and root mean squared error for affinity prediction. Individual claims | DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captions Version: PMC archival version PMC8274096.1 | 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 Atomic versus composite feature models; the PDBbind-core comparison also lists AutoDock Vina, RF::VinaElem, TOPBP and AGL Score. Individual claims | DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captions Version: PMC archival version PMC8274096.1 | 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 checked dataset section gives partition proportions but no scaffold- or protein-target-disjoint assignment rule. Individual claims | DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captions Version: PMC archival version PMC8274096.1 | 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 |
| Uncertainty The reported SD describes dispersion associated with real/predicted values. It is not identified as a confidence interval or independent retraining uncertainty. Individual claims | DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captions Version: PMC archival version PMC8274096.1 | 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 |
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
- DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity · Original source · PMC archival version PMC8274096.1
- DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity · Original source · PMC archival version PMC8274096.1
Technical metadata and extraction receipts
Stable ID: reported-task-d81be76396e644
- areas
- molecular-interactions
- tasks
- Protein–ligand binding affinity prediction
- entity level
- task
- version
- Not reported
- task
- Protein–ligand binding affinity prediction
- scope note
- Paper-specific evaluation task; protocol completeness requires further extraction.
- benchmark research
- review date: 2026-09-17; status: source_found_structured_extraction_pending; primary sources: evidence-expansion-p2-deelig-2021-5a7620c18d06; inspected locators: Tables1–3; novel test and PDBbind2013/2016 comparisons; searched queries: DEELIG: A Deep Learning Approach to Predict Protein-Ligand Binding Affinity primary paper benchmark results; gaps: Complete raw tables acquired. Table 1PCC footnote sayspercentcorrectclassification whileTable 2 labelsPearson; ambiguity quarantined. Literature comparison rows have different training histories. Structured extraction pending.; claim scope: Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.
- 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: deelig-2021; source locator: Methods: Novel data set; Data set refinement; model input construction; cached text lines 10–17, 41; task metric definitions and corresponding results table; matching task comparison table/ablation captions; 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.