Configuration

LLF (CASP16 and ChEMBL35 evaluation, PLABench)

Configuration of LLF: Retrained by the benchmark authors on the PDBbind v2020 refined set (CASF and CSAR overlaps and censored entries removed; 4,465 training and 497 validation complexes; random 90/10 split with early stopping; longest single chain); applied to CASP16 and ChEMBL35 without further training.

3 evaluations · 19 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

3 evaluations · 19 results. Different protocols are not a single leaderboard.

Sorted by Concordance index (PLABench casp16-L1000) (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 casp16-L1000)	Concordance index (PLABench casp16-L3000)	Concordance index (PLABench chembl35)	Kendall tau (PLABench chembl35)	Modified squared correlation (PLABench casp16-L1000)	Modified squared correlation (PLABench casp16-L3000)	Modified squared correlation (PLABench chembl35)	MSE (PLABench casp16-L1000)	MSE (PLABench casp16-L3000)	MSE (PLABench chembl35)	Pearson (PLABench casp16-L1000)	Pearson (PLABench casp16-L3000)	Pearson (PLABench chembl35)	RMSE (PLABench casp16-L1000)	RMSE (PLABench casp16-L3000)	RMSE (PLABench chembl35)	Spearman (PLABench casp16-L1000)	Spearman (PLABench casp16-L3000)	Spearman (PLABench chembl35)
LLF (CASP16 and ChEMBL35 evaluation, PLABench)Evaluation	PLABench CASP16 L1000 affinity, CASP16 ligand affinity series L1000 (chymase)	0.588	Not reported	Not reported	Not reported	0.02	Not reported	Not reported	0.536	Not reported	Not reported	0.181	Not reported	Not reported	0.732	Not reported	Not reported	0.279	Not reported	Not reported
LLF (CASP16 and ChEMBL35 evaluation, PLABench)Evaluation	PLABench CASP16 L3000 affinity, CASP16 ligand affinity series L3000 (autotaxin)	Not reported	0.667	Not reported	Not reported	Not reported	0.232	Not reported	Not reported	3.38	Not reported	Not reported	0.484	Not reported	Not reported	1.84	Not reported	Not reported	0.467	Not reported
LLF (CASP16 and ChEMBL35 evaluation, PLABench)Evaluation	PLABench ChEMBL35 leakage-controlled affinity, PLABench ChEMBL35 leakage-controlled test set	Not reported	Not reported	0.572	0.144	Not reported	Not reported	0.072	Not reported	Not reported	2.5	Not reported	Not reported	0.212	Not reported	Not reported	1.46	Not reported	Not reported	0.208

All 19 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 (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L1000 affinity Dataset: CASP16 ligand affinity series L1000 (chymase)	0.588 Concordance index (PLABench casp16-L1000) 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 casp16-L1000 lit-interactions-20261011-leakctl-protocol-casp16-l1000 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 3, row 'LLF', series 'L1000', column 'CI' (text-layer line 839)
Configuration: LLF (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L1000 affinity Dataset: CASP16 ligand affinity series L1000 (chymase)	0.536 MSE (PLABench casp16-L1000) 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 casp16-L1000 lit-interactions-20261011-leakctl-protocol-casp16-l1000 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 3, row 'LLF', series 'L1000', column 'MSE' (text-layer line 839)
Configuration: LLF (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L1000 affinity Dataset: CASP16 ligand affinity series L1000 (chymase)	0.181 Pearson (PLABench casp16-L1000) 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 casp16-L1000 lit-interactions-20261011-leakctl-protocol-casp16-l1000 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 3, row 'LLF', series 'L1000', column 'Pearson' (text-layer line 839)
Configuration: LLF (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L1000 affinity Dataset: CASP16 ligand affinity series L1000 (chymase)	0.02 Modified squared correlation (PLABench casp16-L1000) 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 casp16-L1000 lit-interactions-20261011-leakctl-protocol-casp16-l1000 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 3, row 'LLF', series 'L1000', column 'rm2' (text-layer line 839)
Configuration: LLF (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L1000 affinity Dataset: CASP16 ligand affinity series L1000 (chymase)	0.732 RMSE (PLABench casp16-L1000) 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 casp16-L1000 lit-interactions-20261011-leakctl-protocol-casp16-l1000 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 3, row 'LLF', series 'L1000', column 'RMSE' (text-layer line 839)
Configuration: LLF (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L1000 affinity Dataset: CASP16 ligand affinity series L1000 (chymase)	0.279 Spearman (PLABench casp16-L1000) 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 casp16-L1000 lit-interactions-20261011-leakctl-protocol-casp16-l1000 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 3, row 'LLF', series 'L1000', column 'Spearman' (text-layer line 839)
Configuration: LLF (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L3000 affinity Dataset: CASP16 ligand affinity series L3000 (autotaxin)	0.667 Concordance index (PLABench casp16-L3000) 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 casp16-L3000 lit-interactions-20261011-leakctl-protocol-casp16-l3000 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 3, row 'LLF', series 'L3000', column 'CI' (text-layer line 839)
Configuration: LLF (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L3000 affinity Dataset: CASP16 ligand affinity series L3000 (autotaxin)	3.38 MSE (PLABench casp16-L3000) 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 casp16-L3000 lit-interactions-20261011-leakctl-protocol-casp16-l3000 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 3, row 'LLF', series 'L3000', column 'MSE' (text-layer line 839)
Configuration: LLF (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L3000 affinity Dataset: CASP16 ligand affinity series L3000 (autotaxin)	0.484 Pearson (PLABench casp16-L3000) 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 casp16-L3000 lit-interactions-20261011-leakctl-protocol-casp16-l3000 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 3, row 'LLF', series 'L3000', column 'Pearson' (text-layer line 839)
Configuration: LLF (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L3000 affinity Dataset: CASP16 ligand affinity series L3000 (autotaxin)	0.232 Modified squared correlation (PLABench casp16-L3000) 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 casp16-L3000 lit-interactions-20261011-leakctl-protocol-casp16-l3000 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 3, row 'LLF', series 'L3000', column 'rm2' (text-layer line 839)
Configuration: LLF (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L3000 affinity Dataset: CASP16 ligand affinity series L3000 (autotaxin)	1.84 RMSE (PLABench casp16-L3000) 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 casp16-L3000 lit-interactions-20261011-leakctl-protocol-casp16-l3000 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 3, row 'LLF', series 'L3000', column 'RMSE' (text-layer line 839)
Configuration: LLF (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L3000 affinity Dataset: CASP16 ligand affinity series L3000 (autotaxin)	0.467 Spearman (PLABench casp16-L3000) 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 casp16-L3000 lit-interactions-20261011-leakctl-protocol-casp16-l3000 Aggregation: Not reported Leakage-controlled benchmarking reveals generalization limits of deep learning for protein-ligand binding affinity prediction · Table 3, row 'LLF', series 'L3000', column 'Spearman' (text-layer line 839)
Configuration: LLF (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set	0.572 Concordance index (PLABench chembl35) 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 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 'LLF', column 'CI' (text-layer line 1039)
Configuration: LLF (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set	0.144 Kendall tau (PLABench chembl35) 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 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 'LLF', column 'Kendall' (text-layer line 1039)
Configuration: LLF (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set	2.5 MSE (PLABench chembl35) 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 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 'LLF', column 'MSE' (text-layer line 1039)
Configuration: LLF (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set	0.212 Pearson (PLABench chembl35) 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 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 'LLF', column 'Pearson' (text-layer line 1039)
Configuration: LLF (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set	0.072 Modified squared correlation (PLABench chembl35) 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 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 'LLF', column 'rm2' (text-layer line 1039)
Configuration: LLF (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set	1.46 RMSE (PLABench chembl35) 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 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 'LLF', column 'RMSE' (text-layer line 1039)
Configuration: LLF (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set	0.208 Spearman (PLABench chembl35) 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 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 'LLF', column 'Spearman' (text-layer line 1039)

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-casp16-chembl35

areas: molecular-interactions
contexts: research
method types: supervised_machine_learning
reported name: LLF
foundation model eligible: false
parameters: Retrained by the benchmark authors on the PDBbind v2020 refined set (CASF and CSAR overlaps and censored entries removed; 4,465 training and 497 validation complexes; random 90/10 split with early stopping; longest single chain); applied to CASP16 and ChEMBL35 without further training (Methods, 'PDBbind v2020 dataset')
source locator: Table 1; Methods; Tables 3 and 4
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

Suggest a correction