Task

protein-ligand binding affinity prediction

Affinity prediction combines refined-set training with core-set and separately filtered general-set evaluations.

Sources

At a glance

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.

Data, procedure and scoring
Property	Description and evidence
Datasets	PDBbind v2020 refined/core collections and BindingDB-trained component models. Sources Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling · Dataset Selection: PDBbind; GeneralSet Benchmark; model training; cached text lines 16, 38, 55–56; task metric definitions and corresponding results table
Splits	CASF2016 core complexes are excluded from refined-set training; a filtered general-set subset excludes refined/core entries. Sources Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling · Dataset Selection: PDBbind; GeneralSet Benchmark; model training; cached text lines 16, 38, 55–56; task metric definitions and corresponding results table
Metrics	RMSE and Pearson correlation coefficient for binding-affinity evaluation; target-specific ranking collections are reported separately. Sources Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling · Dataset Selection: PDBbind; GeneralSet Benchmark; model training; cached text lines 16, 38, 55–56; task metric definitions and corresponding results table
Baselines	Table 4 compares the docking and sequence-model components with HAC-Net, FAST’s pretrained SG-CNN and KDeep. Training sets and affinity units differ: HAC-Net is retrained, SG-CNN retains its original training, and KDeep uses limited retraining or its server default. PerSpect ML is discussed from published results rather than rerun. Sources Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling · Methods: Comparison to Other Tools; Results: Comparison with Structure-Based Tools; Table 4
Leakage controls	PDBbind fine-tuning excludes the CoreSet, and the filtered GeneralSet excludes both RefinedSet and CoreSet. The separate three-target ranking test additionally enforces less than 30% protein similarity. These distinct controls do not establish a BindingDB-overlap audit for the CASF-2016 or GeneralSet rows. Sources Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling · Methods: Fine-Tuning of the BDB-Trained Models Using PDBbind; GeneralSet Benchmark; Ranking Benchmark
Uncertainty	One PDBbind model group uses repeated five-fold cross-validation. Sources Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling · Dataset Selection: PDBbind; GeneralSet Benchmark; model training; cached text lines 16, 38, 55–56; task metric definitions and corresponding results table
Entity type	Paper-specific computational evaluation protocol. Sources Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling · Dataset Selection: PDBbind; GeneralSet Benchmark; model training; cached text lines 16, 38, 55–56; task metric definitions and corresponding results table
Organisms	CASF-2016 and the filtered PDBbind2020 GeneralSet pool protein–ligand complexes. The dataset and benchmark methods do not provide a species census for the scored subsets; target accession identities, rather than an assumed single organism, define their biological context. · Not reported in inspected sources Sources Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling · Methods: GeneralSet Benchmark and data preparation; Table 4
Assays	Protein–ligand affinity and structural labels. Sources Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling · Dataset Selection: PDBbind; GeneralSet Benchmark; model training; cached text lines 16, 38, 55–56; task metric definitions and corresponding results table
Allowed inputs	Protein–ligand representations used by component scoring models. Sources Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling · Dataset Selection: PDBbind; GeneralSet Benchmark; model training; cached text lines 16, 38, 55–56; task metric definitions and corresponding results table
Adaptation	Supervised meta-model/component fitting; CASF core examples are excluded from the refined training collection. Sources Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling · Dataset Selection: PDBbind; GeneralSet Benchmark; model training; cached text lines 16, 38, 55–56; task metric definitions and corresponding results table

How it works

How it worksComputational evaluation flow

Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.

Sources

Evaluation methodology

PDBbind v2020 refined/core collections and BindingDB-trained component models. CASF2016 core complexes are excluded from refined-set training; a filtered general-set subset excludes refined/core entries. RMSE and Pearson correlation coefficient for binding-affinity evaluation; target-specific ranking collections are reported separately. Table 4 compares the docking and sequence-model components with HAC-Net, FAST’s pretrained SG-CNN and KDeep. Training sets and affinity units differ: HAC-Net is retrained, SG-CNN retains its original training, and KDeep uses limited retraining or its server default. PerSpect ML is discussed from published results rather than rerun. PDBbind fine-tuning excludes the CoreSet, and the filtered GeneralSet excludes both RefinedSet and CoreSet. The separate three-target ranking test additionally enforces less than 30% protein similarity. These distinct controls do not establish a BindingDB-overlap audit for the CASF-2016 or GeneralSet rows.

Sources

Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling · Dataset Selection: PDBbind; GeneralSet Benchmark; model training; cached text lines 16, 38, 55–56; task metric definitions and corresponding results table; Methods: Comparison to Other Tools; Results: Comparison with Structure-Based Tools; Table 4; Methods: Fine-Tuning of the BDB-Trained Models Using PDBbind; GeneralSet Benchmark; Ranking Benchmark

Recorded evaluations

Each evaluation records what was tested and under which conditions.

binding-affinity meta-model: protein-ligand binding affinity prediction

Tested entities and results

Release 2026-09-17-d277315f7d76 · 1 evaluation · 1 metric row. Different protocols are not a single leaderboard.

Evaluation setupMetricEvidence origin

Results grouped by the exact reported evaluation
Metric and finding	Coverage and uncertainty	Evidence
binding-affinity meta-model: protein-ligand binding affinity prediction Pipeline: binding-affinity meta-modelTask: protein-ligand binding affinity predictionDataset: CASF-2016 Sequence-or-structure meta-model; predicts ln(Kd/Ki) using docked and deep-learning components Author-reported evaluation · Evaluation metadata: needs review
0.777 Pearson correlation Unit: unitless · Direction: unknown	Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported	source checkedImproved Prediction of Ligand–Protein Binding Affinities by Meta-modeling · Table 4, Meta-models row, CASF-2016 Benchmark > PCC column Source checking is not independent reproduction.

Papers and result coverage

Last literature check: 2026-09-17. Dated primary-source discovery and protocol/table screening. Source checking does not mean experimental reproduction. Only separately extracted and independently reviewed numeric batches are publishable.

Paper or primary resource	Version	Reference
Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling	PMC archival version PMC11632770.1	Read source

What is still missing

complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.

Search and extraction details

primary comparison tables located

Searches

Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling 10.1021/acs.jcim.4c01116

Evidence locations

Table 2; XML table tbl2
Table 3; XML table tbl3
Table 4; XML table tbl4

Strengths and limitations

Strengths and considerations

No source-reviewed explanatory claims are recorded here yet.

Limitations and conditions

Failed docking predictions are excluded from benchmark subsets, changing test coverage. BindingDB-trained and PDBbind-trained models have different training provenance.
Sources
Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling · Dataset Selection: PDBbind; GeneralSet Benchmark; model training; cached text lines 16, 38, 55–56; task metric definitions and corresponding results table

Profile review details

Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change.

Stable record: reported-task-77a32496ce8fe6

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

Claims, original sources and review scope · Release 2026-09-17-d277315f7d76
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	Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling Original source ↗ Dataset Selection: PDBbind; GeneralSet Benchmark; model training; cached text lines 16, 38, 55–56; task metric definitions and corresponding results table Version: PMC archival version PMC11632770.1 Retrieved: 2026-09-16T10:41:06Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `0be25fe75bc0b2eb8065136555763bbae5964ea3a8fdb8c5de79ff96445f6a29` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram steps ["Input: Protein–ligand representations used by component scoring models.","Evaluation: CASF2016 core complexes are excluded from refined-set training; a filtered general-set subset excludes refined/core entries.","Readout: RMSE and Pearson correlation coefficient for binding-affinity evaluation; target-specific ranking collections are reported separately."] Individual claims	Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling Original source ↗ Dataset Selection: PDBbind; GeneralSet Benchmark; model training; cached text lines 16, 38, 55–56; task metric definitions and corresponding results table Version: PMC archival version PMC11632770.1 Retrieved: 2026-09-16T10:41:06Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `0be25fe75bc0b2eb8065136555763bbae5964ea3a8fdb8c5de79ff96445f6a29` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram title Computational evaluation flow Individual claims	Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling Original source ↗ Dataset Selection: PDBbind; GeneralSet Benchmark; model training; cached text lines 16, 38, 55–56; task metric definitions and corresponding results table Version: PMC archival version PMC11632770.1 Retrieved: 2026-09-16T10:41:06Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `0be25fe75bc0b2eb8065136555763bbae5964ea3a8fdb8c5de79ff96445f6a29` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Datasets PDBbind v2020 refined/core collections and BindingDB-trained component models. Individual claims	Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling Original source ↗ Dataset Selection: PDBbind; GeneralSet Benchmark; model training; cached text lines 16, 38, 55–56; task metric definitions and corresponding results table Version: PMC archival version PMC11632770.1 Retrieved: 2026-09-16T10:41:06Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.0.value` Source artifact SHA-256: `0be25fe75bc0b2eb8065136555763bbae5964ea3a8fdb8c5de79ff96445f6a29` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Splits CASF2016 core complexes are excluded from refined-set training; a filtered general-set subset excludes refined/core entries. Individual claims	Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling Original source ↗ Dataset Selection: PDBbind; GeneralSet Benchmark; model training; cached text lines 16, 38, 55–56; task metric definitions and corresponding results table Version: PMC archival version PMC11632770.1 Retrieved: 2026-09-16T10:41:06Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.1.value` Source artifact SHA-256: `0be25fe75bc0b2eb8065136555763bbae5964ea3a8fdb8c5de79ff96445f6a29` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Adaptation Supervised meta-model/component fitting; CASF core examples are excluded from the refined training collection. Individual claims	Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling Original source ↗ Dataset Selection: PDBbind; GeneralSet Benchmark; model training; cached text lines 16, 38, 55–56; task metric definitions and corresponding results table Version: PMC archival version PMC11632770.1 Retrieved: 2026-09-16T10:41:06Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.10.value` Source artifact SHA-256: `0be25fe75bc0b2eb8065136555763bbae5964ea3a8fdb8c5de79ff96445f6a29` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Metrics RMSE and Pearson correlation coefficient for binding-affinity evaluation; target-specific ranking collections are reported separately. Individual claims	Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling Original source ↗ Dataset Selection: PDBbind; GeneralSet Benchmark; model training; cached text lines 16, 38, 55–56; task metric definitions and corresponding results table Version: PMC archival version PMC11632770.1 Retrieved: 2026-09-16T10:41:06Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.2.value` Source artifact SHA-256: `0be25fe75bc0b2eb8065136555763bbae5964ea3a8fdb8c5de79ff96445f6a29` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Baselines Table 4 compares the docking and sequence-model components with HAC-Net, FAST’s pretrained SG-CNN and KDeep. Training sets and affinity units differ: HAC-Net is retrained, SG-CNN retains its original training, and KDeep uses limited retraining or its server default. PerSpect ML is discussed from published results rather than rerun. Individual claims	Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling Original source ↗ Methods: Comparison to Other Tools; Results: Comparison with Structure-Based Tools; Table 4 Version: PMC archival version PMC11632770.1 Retrieved: 2026-09-16T10:41:06Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.3.value` Source artifact SHA-256: `0be25fe75bc0b2eb8065136555763bbae5964ea3a8fdb8c5de79ff96445f6a29` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Leakage controls PDBbind fine-tuning excludes the CoreSet, and the filtered GeneralSet excludes both RefinedSet and CoreSet. The separate three-target ranking test additionally enforces less than 30% protein similarity. These distinct controls do not establish a BindingDB-overlap audit for the CASF-2016 or GeneralSet rows. Individual claims	Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling Original source ↗ Methods: Fine-Tuning of the BDB-Trained Models Using PDBbind; GeneralSet Benchmark; Ranking Benchmark Version: PMC archival version PMC11632770.1 Retrieved: 2026-09-16T10:41:06Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.4.value` Source artifact SHA-256: `0be25fe75bc0b2eb8065136555763bbae5964ea3a8fdb8c5de79ff96445f6a29` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Uncertainty One PDBbind model group uses repeated five-fold cross-validation. Individual claims	Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling Original source ↗ Dataset Selection: PDBbind; GeneralSet Benchmark; model training; cached text lines 16, 38, 55–56; task metric definitions and corresponding results table Version: PMC archival version PMC11632770.1 Retrieved: 2026-09-16T10:41:06Z	source checked automated source review · 2026-09-16 Audit details Targeted full-paper and supplement review of the outstanding task fields, with original dataset metadata checked where accessible. Source-scoped omissions are explicit; no independent benchmark reproduction or numerical-result change. Field: `attributes.profile.facts.5.value` Source artifact SHA-256: `0be25fe75bc0b2eb8065136555763bbae5964ea3a8fdb8c5de79ff96445f6a29` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

All evidence (CSV)All evidence (JSONL)How to read the evidence

Sources and history

Release 2026-09-17-d277315f7d76 · Record review: needs review

2 source records and release history

Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling · Original source · PMC archival version PMC11632770.1
Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling · Original source · PMC archival version PMC11632770.1

Download this release

Technical metadata and extraction receipts

Stable ID: reported-task-77a32496ce8fe6

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: primary_comparison_tables_located; primary sources: evidence-expansion-ligand-affinity-meta-model-2024-0be25fe7; inspected locators: Table 2; XML table tbl2; Table 3; XML table tbl3; Table 4; XML table tbl4; searched queries: Improved Prediction of Ligand–Protein Binding Affinities by Meta-modeling 10.1021/acs.jcim.4c01116; gaps: complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.; exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.; claim scope: Dated primary-source discovery and protocol/table screening. Source checking does not mean experimental reproduction. Only separately extracted and independently reviewed numeric batches are publishable.
historical missing metadata: protocol version: 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: ligand-affinity-meta-model-2024; source locator: Dataset Selection: PDBbind; GeneralSet Benchmark; model training; cached text lines 16, 38, 55–56; task metric definitions and corresponding results table; 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
benchmark: binding-affinity meta-model: protein-ligand binding affinity prediction

Suggest a correction