Configuration

MFE (CASP16 and ChEMBL35 evaluation, PLABench)

Configuration of MFE: Published checkpoint applied without retraining; given AlphaFold3-predicted complex structures.

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)
MFE (CASP16 and ChEMBL35 evaluation, PLABench)Evaluation	PLABench CASP16 L1000 affinity, CASP16 ligand affinity series L1000 (chymase)	0.632	Not reported	Not reported	Not reported	0.037	Not reported	Not reported	1.52	Not reported	Not reported	0.332	Not reported	Not reported	1.24	Not reported	Not reported	0.485	Not reported	Not reported
MFE (CASP16 and ChEMBL35 evaluation, PLABench)Evaluation	PLABench CASP16 L3000 affinity, CASP16 ligand affinity series L3000 (autotaxin)	Not reported	0.705	Not reported	Not reported	Not reported	0.345	Not reported	Not reported	1.32	Not reported	Not reported	0.613	Not reported	Not reported	1.15	Not reported	Not reported	0.574	Not reported
MFE (CASP16 and ChEMBL35 evaluation, PLABench)Evaluation	PLABench ChEMBL35 leakage-controlled affinity, PLABench ChEMBL35 leakage-controlled test set	Not reported	Not reported	0.556	0.111	Not reported	Not reported	0.048	Not reported	Not reported	1.63	Not reported	Not reported	0.177	Not reported	Not reported	1.21	Not reported	Not reported	0.162

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: MFE (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L1000 affinity Dataset: CASP16 ligand affinity series L1000 (chymase)	0.632 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 MFE 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 'MFE', series 'L1000', column 'CI' (text-layer line 837)
Configuration: MFE (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L1000 affinity Dataset: CASP16 ligand affinity series L1000 (chymase)	1.52 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 MFE 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 'MFE', series 'L1000', column 'MSE' (text-layer line 837)
Configuration: MFE (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L1000 affinity Dataset: CASP16 ligand affinity series L1000 (chymase)	0.332 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 MFE 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 'MFE', series 'L1000', column 'Pearson' (text-layer line 837)
Configuration: MFE (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L1000 affinity Dataset: CASP16 ligand affinity series L1000 (chymase)	0.037 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 MFE 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 'MFE', series 'L1000', column 'rm2' (text-layer line 837)
Configuration: MFE (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L1000 affinity Dataset: CASP16 ligand affinity series L1000 (chymase)	1.24 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 MFE 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 'MFE', series 'L1000', column 'RMSE' (text-layer line 837)
Configuration: MFE (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L1000 affinity Dataset: CASP16 ligand affinity series L1000 (chymase)	0.485 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 MFE 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 'MFE', series 'L1000', column 'Spearman' (text-layer line 837)
Configuration: MFE (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L3000 affinity Dataset: CASP16 ligand affinity series L3000 (autotaxin)	0.705 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 MFE 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 'MFE', series 'L3000', column 'CI' (text-layer line 837)
Configuration: MFE (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L3000 affinity Dataset: CASP16 ligand affinity series L3000 (autotaxin)	1.32 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 MFE 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 'MFE', series 'L3000', column 'MSE' (text-layer line 837)
Configuration: MFE (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L3000 affinity Dataset: CASP16 ligand affinity series L3000 (autotaxin)	0.613 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 MFE 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 'MFE', series 'L3000', column 'Pearson' (text-layer line 837)
Configuration: MFE (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L3000 affinity Dataset: CASP16 ligand affinity series L3000 (autotaxin)	0.345 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 MFE 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 'MFE', series 'L3000', column 'rm2' (text-layer line 837)
Configuration: MFE (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L3000 affinity Dataset: CASP16 ligand affinity series L3000 (autotaxin)	1.15 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 MFE 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 'MFE', series 'L3000', column 'RMSE' (text-layer line 837)
Configuration: MFE (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench CASP16 L3000 affinity Dataset: CASP16 ligand affinity series L3000 (autotaxin)	0.574 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 MFE 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 'MFE', series 'L3000', column 'Spearman' (text-layer line 837)
Configuration: MFE (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set	0.556 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 MFE 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 'MFE', column 'CI' (text-layer line 1037)
Configuration: MFE (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set	0.111 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 MFE 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 'MFE', column 'Kendall' (text-layer line 1037)
Configuration: MFE (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set	1.63 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 MFE 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 'MFE', column 'MSE' (text-layer line 1037)
Configuration: MFE (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set	0.177 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 MFE 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 'MFE', column 'Pearson' (text-layer line 1037)
Configuration: MFE (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set	0.048 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 MFE 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 'MFE', column 'rm2' (text-layer line 1037)
Configuration: MFE (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set	1.21 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 MFE 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 'MFE', column 'RMSE' (text-layer line 1037)
Configuration: MFE (CASP16 and ChEMBL35 evaluation, PLABench)	Protocol: PLABench ChEMBL35 leakage-controlled affinity Dataset: PLABench ChEMBL35 leakage-controlled test set	0.162 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 MFE 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 'MFE', column 'Spearman' (text-layer line 1037)

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-mfe-casp16-chembl35

areas: molecular-interactions
contexts: research
method types: supervised_machine_learning
reported name: MFE
foundation model eligible: false
parameters: Published checkpoint applied without retraining; given AlphaFold3-predicted complex structures. Results (lines 78-80) say structure-based models used official pretrained checkpoints; Data availability (line 542) lists retrained MFE checkpoints
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: MFE as evaluated in PLABench (structure-based).

Related records

Suggest a correction