ChEMBL v35 test set curated by Shimizu et al., with ligands of ECFP4 Tanimoto similarity >= 0.85 to any training molecule of the nine models removed and targets with at least 10 compounds kept.
9 evaluations · 63 results. Different protocols are not a single leaderboard.
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: Boltz2 (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 0.606 Concordance index (PLABench chembl35) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourcelit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'Boltz2', column 'CI' (text-layer line 1032) |
| Configuration: Boltz2 (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 0.211 Kendall tau (PLABench chembl35) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourcelit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'Boltz2', column 'Kendall' (text-layer line 1032) |
| Configuration: Boltz2 (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 1.69 MSE (PLABench chembl35) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourcelit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'Boltz2', column 'MSE' (text-layer line 1032) |
| Configuration: Boltz2 (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 0.321 Pearson (PLABench chembl35) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourcelit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'Boltz2', column 'Pearson' (text-layer line 1032) |
| Configuration: Boltz2 (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 0.098 Modified squared correlation (PLABench chembl35) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourcelit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'Boltz2', column 'rm2' (text-layer line 1032) |
| Configuration: Boltz2 (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 1.25 RMSE (PLABench chembl35) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourcelit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'Boltz2', column 'RMSE' (text-layer line 1032) |
| Configuration: Boltz2 (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 0.302 Spearman (PLABench chembl35) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourcelit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'Boltz2', column 'Spearman' (text-layer line 1032) |
| Configuration: DeepDTA (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 0.551 Concordance index (PLABench chembl35) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourcelit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'DeepDTA', column 'CI' (text-layer line 1038) |
| Configuration: DeepDTA (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 0.103 Kendall tau (PLABench chembl35) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourcelit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'DeepDTA', column 'Kendall' (text-layer line 1038) |
| Configuration: DeepDTA (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 2.17 MSE (PLABench chembl35) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourcelit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'DeepDTA', column 'MSE' (text-layer line 1038) |
| Configuration: DeepDTA (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 0.153 Pearson (PLABench chembl35) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourcelit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'DeepDTA', column 'Pearson' (text-layer line 1038) |
| Configuration: DeepDTA (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 0.045 Modified squared correlation (PLABench chembl35) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourcelit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'DeepDTA', column 'rm2' (text-layer line 1038) |
| Configuration: DeepDTA (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 1.39 RMSE (PLABench chembl35) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourcelit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'DeepDTA', column 'RMSE' (text-layer line 1038) |
| Configuration: DeepDTA (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 0.151 Spearman (PLABench chembl35) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourcelit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'DeepDTA', column 'Spearman' (text-layer line 1038) |
| Configuration: FlowDock (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 0.56 Concordance index (PLABench chembl35) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourcelit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'FlowDock', column 'CI' (text-layer line 1033) |
| Configuration: FlowDock (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 0.12 Kendall tau (PLABench chembl35) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourcelit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'FlowDock', column 'Kendall' (text-layer line 1033) |
| Configuration: FlowDock (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 2.22 MSE (PLABench chembl35) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourcelit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'FlowDock', column 'MSE' (text-layer line 1033) |
| Configuration: FlowDock (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 0.188 Pearson (PLABench chembl35) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourcelit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'FlowDock', column 'Pearson' (text-layer line 1033) |
| Configuration: FlowDock (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 0.051 Modified squared correlation (PLABench chembl35) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourcelit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'FlowDock', column 'rm2' (text-layer line 1033) |
| Configuration: FlowDock (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 1.37 RMSE (PLABench chembl35) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourcelit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'FlowDock', column 'RMSE' (text-layer line 1033) |
| Configuration: FlowDock (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 0.173 Spearman (PLABench chembl35) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourcelit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'FlowDock', column 'Spearman' (text-layer line 1033) |
| Configuration: FLOWR.ROOT (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 0.632 Concordance index (PLABench chembl35) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceFLOWR.ROOT on PLABench chembl35 lit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'FLOWR.ROOT', column 'CI' (text-layer line 1034) |
| Configuration: FLOWR.ROOT (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 0.264 Kendall tau (PLABench chembl35) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceFLOWR.ROOT on PLABench chembl35 lit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'FLOWR.ROOT', column 'Kendall' (text-layer line 1034) |
| Configuration: FLOWR.ROOT (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 0.931 MSE (PLABench chembl35) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceFLOWR.ROOT on PLABench chembl35 lit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'FLOWR.ROOT', column 'MSE' (text-layer line 1034) |
| Configuration: FLOWR.ROOT (CASP16 and ChEMBL35 evaluation, PLABench) | Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set | 0.392 Pearson (PLABench chembl35) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible | Independent external evaluation · Source checkedMethods, coverage and sourceFLOWR.ROOT on PLABench chembl35 lit-interactions-20261011-leakctl-protocol-chembl35 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 4, row 'FLOWR.ROOT', column 'Pearson' (text-layer line 1034) |
Source checking is not independent reproduction. Release 2026-10-23-5347695500ed.
0 of 4 readiness checks met. These checks assess whether the evidence supports a reproducible investigation; a source-checked score alone does not meet them.
Release 2026-10-23-5347695500ed · Evidence verified: Not verified
Exact outcomes, predictions, identifiers and evaluator are connected.
Missing or unresolved evidence
Verified: Not verified
Replay evidence includes annotations and an assessment of dependence. Unknown independence permits descriptive analysis only.
Missing or unresolved evidence
Verified: Not verified
A pinned recipe describes the inputs, environment and resource requirements.
Missing or unresolved evidence
Verified: Not verified
Separate data and exposure records support an independent test.
Missing or unresolved evidence
Verified: Not verified
Readiness describes the evidence in this release. Availability on your computer is checked separately when an investigation runs. Existing data exposure can prevent independent validation even when files are available.
No verified artifact manifest is connected to this record yet. The gaps above identify what is needed before analysis can begin.
A dataset supplies biological observations. The evaluation protocol defines how those observations are split, used and scored.
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
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.
6 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Population 4,862 complexes across 71 target proteins Context-only references | Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction Results 'Large-scale pretraining...'; Table 4 Version: bioRxiv 10.64898/2026.09.17.752433v1 (posted 2026-09-23); 30-page PDF | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Source location Results 'Large-scale pretraining...'; Table 4 Context-only references | Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction Results 'Large-scale pretraining...'; Table 4 Version: bioRxiv 10.64898/2026.09.17.752433v1 (posted 2026-09-23); 30-page PDF | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Split Held-out test set Context-only references | Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction Results 'Large-scale pretraining...'; Table 4 Version: bioRxiv 10.64898/2026.09.17.752433v1 (posted 2026-09-23); 30-page PDF | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Version ChEMBL v35 (PLABench filter) Context-only references | Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction Results 'Large-scale pretraining...'; Table 4 Version: bioRxiv 10.64898/2026.09.17.752433v1 (posted 2026-09-23); 30-page PDF | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Description ChEMBL v35 test set curated by Shimizu et al., with ligands of ECFP4 Tanimoto similarity >= 0.85 to any training molecule of the nine models removed and targets with at least 10 compounds kept. Context-only references | Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction Results 'Large-scale pretraining...'; Table 4 Version: bioRxiv 10.64898/2026.09.17.752433v1 (posted 2026-09-23); 30-page PDF | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Name PLABench ChEMBL35 leakage-controlled test set Context-only references | Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction Results 'Large-scale pretraining...'; Table 4 Version: bioRxiv 10.64898/2026.09.17.752433v1 (posted 2026-09-23); 30-page PDF | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Release 2026-10-23-5347695500ed · Record review: source checked
Stable ID: lit-interactions-20261011-leakctl-data-chembl35