Configuration

LLF (retrained on Davis and KIBA, PLABench)

Configuration of LLF: Retrained by the benchmark authors on Davis or KIBA under each split (warm: 5-fold CV on an 80/20 split; cold splits: two-stage protocol from MixingDTA, five fold models evaluated on a fixed test set and aggregated).

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.

Evaluations and results

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

Sorted by Concordance index (PLABench Davis-cold-drug) (higher 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	Protocol and dataset	Concordance index (PLABench Davis-cold-drug)	Concordance index (PLABench Davis-cold-target)	Concordance index (PLABench Davis-warm)	Concordance index (PLABench KIBA-cold-drug)	Concordance index (PLABench KIBA-cold-target)	Concordance index (PLABench KIBA-warm)	Modified squared correlation (PLABench Davis-cold-drug)	Modified squared correlation (PLABench Davis-cold-target)	Modified squared correlation (PLABench Davis-warm)	Modified squared correlation (PLABench KIBA-cold-drug)	Modified squared correlation (PLABench KIBA-cold-target)	Modified squared correlation (PLABench KIBA-warm)	MSE (PLABench Davis-cold-drug)	MSE (PLABench Davis-cold-target)	MSE (PLABench Davis-warm)	MSE (PLABench KIBA-cold-drug)	MSE (PLABench KIBA-cold-target)	MSE (PLABench KIBA-warm)	Pearson (PLABench Davis-cold-drug)	Pearson (PLABench Davis-cold-target)	Pearson (PLABench Davis-warm)	Pearson (PLABench KIBA-cold-drug)	Pearson (PLABench KIBA-cold-target)	Pearson (PLABench KIBA-warm)	RMSE (PLABench Davis-cold-drug)	RMSE (PLABench Davis-cold-target)	RMSE (PLABench Davis-warm)	RMSE (PLABench KIBA-cold-drug)	RMSE (PLABench KIBA-cold-target)	RMSE (PLABench KIBA-warm)	Spearman (PLABench Davis-cold-drug)	Spearman (PLABench Davis-cold-target)	Spearman (PLABench Davis-warm)	Spearman (PLABench KIBA-cold-drug)	Spearman (PLABench KIBA-cold-target)	Spearman (PLABench KIBA-warm)
LLF (retrained on Davis and KIBA, PLABench)Evaluation	PLABench Davis, cold-drug split, Davis cold-drug test set (PLABench)	0.663	Not reported	Not reported	Not reported	Not reported	Not reported	0.053	Not reported	Not reported	Not reported	Not reported	Not reported	0.711	Not reported	Not reported	Not reported	Not reported	Not reported	0.278	Not reported	Not reported	Not reported	Not reported	Not reported	0.843	Not reported	Not reported	Not reported	Not reported	Not reported	0.313	Not reported	Not reported	Not reported	Not reported	Not reported
LLF (retrained on Davis and KIBA, PLABench)Evaluation	PLABench Davis, cold-target split, Davis cold-target test set (PLABench)	Not reported	0.756	Not reported	Not reported	Not reported	Not reported	Not reported	0.24	Not reported	Not reported	Not reported	Not reported	Not reported	0.453	Not reported	Not reported	Not reported	Not reported	Not reported	0.514	Not reported	Not reported	Not reported	Not reported	Not reported	0.673	Not reported	Not reported	Not reported	Not reported	Not reported	0.45	Not reported	Not reported	Not reported	Not reported
LLF (retrained on Davis and KIBA, PLABench)Evaluation	PLABench Davis, warm split, Davis warm test set (PLABench)	Not reported	Not reported	0.881	Not reported	Not reported	Not reported	Not reported	Not reported	0.656	Not reported	Not reported	Not reported	Not reported	Not reported	0.224	Not reported	Not reported	Not reported	Not reported	Not reported	0.821	Not reported	Not reported	Not reported	Not reported	Not reported	0.473	Not reported	Not reported	Not reported	Not reported	Not reported	0.669	Not reported	Not reported	Not reported
LLF (retrained on Davis and KIBA, PLABench)Evaluation	PLABench KIBA, cold-drug split, KIBA cold-drug test set (PLABench)	Not reported	Not reported	Not reported	0.715	Not reported	Not reported	Not reported	Not reported	Not reported	0.247	Not reported	Not reported	Not reported	Not reported	Not reported	0.457	Not reported	Not reported	Not reported	Not reported	Not reported	0.548	Not reported	Not reported	Not reported	Not reported	Not reported	0.676	Not reported	Not reported	Not reported	Not reported	Not reported	0.566	Not reported	Not reported
LLF (retrained on Davis and KIBA, PLABench)Evaluation	PLABench KIBA, cold-target split, KIBA cold-target test set (PLABench)	Not reported	Not reported	Not reported	Not reported	0.795	Not reported	Not reported	Not reported	Not reported	Not reported	0.523	Not reported	Not reported	Not reported	Not reported	Not reported	0.343	Not reported	Not reported	Not reported	Not reported	Not reported	0.726	Not reported	Not reported	Not reported	Not reported	Not reported	0.585	Not reported	Not reported	Not reported	Not reported	Not reported	0.735	Not reported
LLF (retrained on Davis and KIBA, PLABench)Evaluation	PLABench KIBA, warm split, KIBA warm test set (PLABench)	Not reported	Not reported	Not reported	Not reported	Not reported	0.883	Not reported	Not reported	Not reported	Not reported	Not reported	0.768	Not reported	Not reported	Not reported	Not reported	Not reported	0.155	Not reported	Not reported	Not reported	Not reported	Not reported	0.882	Not reported	Not reported	Not reported	Not reported	Not reported	0.394	Not reported	Not reported	Not reported	Not reported	Not reported	0.873

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: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench Davis, cold-drug split Dataset: Davis cold-drug test set (PLABench)	0.663 Concordance index (PLABench Davis-cold-drug) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench Davis-cold-drug lit-interactions-20261011-leakctl-protocol-davis-cold-drug Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Cold-drug', dataset 'Davis', column 'CI' (text-layer line 446)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench Davis, cold-drug split Dataset: Davis cold-drug test set (PLABench)	0.711 MSE (PLABench Davis-cold-drug) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench Davis-cold-drug lit-interactions-20261011-leakctl-protocol-davis-cold-drug Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Cold-drug', dataset 'Davis', column 'MSE' (text-layer line 446)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench Davis, cold-drug split Dataset: Davis cold-drug test set (PLABench)	0.278 Pearson (PLABench Davis-cold-drug) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench Davis-cold-drug lit-interactions-20261011-leakctl-protocol-davis-cold-drug Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Cold-drug', dataset 'Davis', column 'Pearson' (text-layer line 446)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench Davis, cold-drug split Dataset: Davis cold-drug test set (PLABench)	0.053 Modified squared correlation (PLABench Davis-cold-drug) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench Davis-cold-drug lit-interactions-20261011-leakctl-protocol-davis-cold-drug Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Cold-drug', dataset 'Davis', column 'rm2' (text-layer line 446)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench Davis, cold-drug split Dataset: Davis cold-drug test set (PLABench)	0.843 RMSE (PLABench Davis-cold-drug) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench Davis-cold-drug lit-interactions-20261011-leakctl-protocol-davis-cold-drug Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Cold-drug', dataset 'Davis', column 'RMSE' (text-layer line 446)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench Davis, cold-drug split Dataset: Davis cold-drug test set (PLABench)	0.313 Spearman (PLABench Davis-cold-drug) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench Davis-cold-drug lit-interactions-20261011-leakctl-protocol-davis-cold-drug Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Cold-drug', dataset 'Davis', column 'Spearman' (text-layer line 446)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench Davis, cold-target split Dataset: Davis cold-target test set (PLABench)	0.756 Concordance index (PLABench Davis-cold-target) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench Davis-cold-target lit-interactions-20261011-leakctl-protocol-davis-cold-target Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Cold-target', dataset 'Davis', column 'CI' (text-layer line 443)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench Davis, cold-target split Dataset: Davis cold-target test set (PLABench)	0.453 MSE (PLABench Davis-cold-target) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench Davis-cold-target lit-interactions-20261011-leakctl-protocol-davis-cold-target Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Cold-target', dataset 'Davis', column 'MSE' (text-layer line 443)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench Davis, cold-target split Dataset: Davis cold-target test set (PLABench)	0.514 Pearson (PLABench Davis-cold-target) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench Davis-cold-target lit-interactions-20261011-leakctl-protocol-davis-cold-target Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Cold-target', dataset 'Davis', column 'Pearson' (text-layer line 443)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench Davis, cold-target split Dataset: Davis cold-target test set (PLABench)	0.24 Modified squared correlation (PLABench Davis-cold-target) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench Davis-cold-target lit-interactions-20261011-leakctl-protocol-davis-cold-target Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Cold-target', dataset 'Davis', column 'rm2' (text-layer line 443)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench Davis, cold-target split Dataset: Davis cold-target test set (PLABench)	0.673 RMSE (PLABench Davis-cold-target) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench Davis-cold-target lit-interactions-20261011-leakctl-protocol-davis-cold-target Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Cold-target', dataset 'Davis', column 'RMSE' (text-layer line 443)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench Davis, cold-target split Dataset: Davis cold-target test set (PLABench)	0.45 Spearman (PLABench Davis-cold-target) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench Davis-cold-target lit-interactions-20261011-leakctl-protocol-davis-cold-target Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Cold-target', dataset 'Davis', column 'Spearman' (text-layer line 443)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench Davis, warm split Dataset: Davis warm test set (PLABench)	0.881 Concordance index (PLABench Davis-warm) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench Davis-warm lit-interactions-20261011-leakctl-protocol-davis-warm Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Warm split', dataset 'Davis', column 'CI' (text-layer line 440)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench Davis, warm split Dataset: Davis warm test set (PLABench)	0.224 MSE (PLABench Davis-warm) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench Davis-warm lit-interactions-20261011-leakctl-protocol-davis-warm Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Warm split', dataset 'Davis', column 'MSE' (text-layer line 440)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench Davis, warm split Dataset: Davis warm test set (PLABench)	0.821 Pearson (PLABench Davis-warm) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench Davis-warm lit-interactions-20261011-leakctl-protocol-davis-warm Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Warm split', dataset 'Davis', column 'Pearson' (text-layer line 440)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench Davis, warm split Dataset: Davis warm test set (PLABench)	0.656 Modified squared correlation (PLABench Davis-warm) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench Davis-warm lit-interactions-20261011-leakctl-protocol-davis-warm Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Warm split', dataset 'Davis', column 'rm2' (text-layer line 440)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench Davis, warm split Dataset: Davis warm test set (PLABench)	0.473 RMSE (PLABench Davis-warm) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench Davis-warm lit-interactions-20261011-leakctl-protocol-davis-warm Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Warm split', dataset 'Davis', column 'RMSE' (text-layer line 440)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench Davis, warm split Dataset: Davis warm test set (PLABench)	0.669 Spearman (PLABench Davis-warm) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench Davis-warm lit-interactions-20261011-leakctl-protocol-davis-warm Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Warm split', dataset 'Davis', column 'Spearman' (text-layer line 440)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench KIBA, cold-drug split Dataset: KIBA cold-drug test set (PLABench)	0.715 Concordance index (PLABench KIBA-cold-drug) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench KIBA-cold-drug lit-interactions-20261011-leakctl-protocol-kiba-cold-drug Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Cold-drug', dataset 'KIBA', column 'CI' (text-layer line 446)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench KIBA, cold-drug split Dataset: KIBA cold-drug test set (PLABench)	0.457 MSE (PLABench KIBA-cold-drug) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench KIBA-cold-drug lit-interactions-20261011-leakctl-protocol-kiba-cold-drug Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Cold-drug', dataset 'KIBA', column 'MSE' (text-layer line 446)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench KIBA, cold-drug split Dataset: KIBA cold-drug test set (PLABench)	0.548 Pearson (PLABench KIBA-cold-drug) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench KIBA-cold-drug lit-interactions-20261011-leakctl-protocol-kiba-cold-drug Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Cold-drug', dataset 'KIBA', column 'Pearson' (text-layer line 446)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench KIBA, cold-drug split Dataset: KIBA cold-drug test set (PLABench)	0.247 Modified squared correlation (PLABench KIBA-cold-drug) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench KIBA-cold-drug lit-interactions-20261011-leakctl-protocol-kiba-cold-drug Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Cold-drug', dataset 'KIBA', column 'rm2' (text-layer line 446)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench KIBA, cold-drug split Dataset: KIBA cold-drug test set (PLABench)	0.676 RMSE (PLABench KIBA-cold-drug) unit-unreported · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench KIBA-cold-drug lit-interactions-20261011-leakctl-protocol-kiba-cold-drug Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Cold-drug', dataset 'KIBA', column 'RMSE' (text-layer line 446)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench KIBA, cold-drug split Dataset: KIBA cold-drug test set (PLABench)	0.566 Spearman (PLABench KIBA-cold-drug) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench KIBA-cold-drug lit-interactions-20261011-leakctl-protocol-kiba-cold-drug Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Cold-drug', dataset 'KIBA', column 'Spearman' (text-layer line 446)
Configuration: LLF (retrained on Davis and KIBA, PLABench)	Protocol: PLABench KIBA, cold-target split Dataset: KIBA cold-target test set (PLABench)	0.795 Concordance index (PLABench KIBA-cold-target) unitless · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source LLF on PLABench KIBA-cold-target lit-interactions-20261011-leakctl-protocol-kiba-cold-target Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 2, row 'LLF', strategy 'Cold-target', dataset 'KIBA', column 'CI' (text-layer line 443)

Source checking is not independent reproduction. Release 2026-10-23-5347695500ed.

Use this configuration

How it works, versions and access

Additional methodological details, versions and access terms have not yet been extracted into a structured profile for this configuration. Consult the linked sources and evaluation records below.

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 2026-10-23-5347695500ed
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 2026-10-23-5347695500ed · Record review: source checked

1 source record and release history

Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Original source · bioRxiv 10.64898/2026.09.17.752433v1 (posted 2026-09-23); 30-page PDF

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: lit-interactions-20261011-leakctl-config-llf-davis-kiba

areas: molecular-interactions
contexts: research
method types: supervised_machine_learning
reported name: LLF
foundation model eligible: false
parameters: Retrained by the benchmark authors on Davis or KIBA under each split (warm: 5-fold CV on an 80/20 split; cold splits: two-stage protocol from MixingDTA, five fold models evaluated on a fixed test set and aggregated)
source locator: Table 1; Methods; Table 2
access reuse: Not stated per model in the source; see each model's release
missing metadata: version: reason: unreported; note: No checkpoint version printed
provenance note: LLF as evaluated in PLABench (sequence-based).

Related records

configuration of: LLF
system: LLF on PLABench Davis-cold-drug
system: LLF on PLABench Davis-cold-target
system: LLF on PLABench Davis-warm
system: LLF on PLABench KIBA-cold-drug
system: LLF on PLABench KIBA-cold-target
system: LLF on PLABench KIBA-warm

Suggest a correction