PLABench
Leakage-controlled, target-centric benchmark of protein-ligand binding affinity prediction: Davis and KIBA under warm, cold-target and cold-drug splits, CASP16 ligand series L1000 and L3000, and a ChEMBL35 test set filtered against the training data of the evaluated models.
Results are recorded on the linked protocols, tasks or configurations listed below. Their settings and evaluations are kept separate.
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.
Results on linked records
This benchmark has no results of its own in this release. 9 linked records have results. They are not assigned to the underlying benchmark: each record keeps its own settings and evaluations, and its scores are on its own page.
- PLABench CASP16 L1000 affinity Protocol · part of this benchmark · 9 evaluations · 54 results
- PLABench CASP16 L3000 affinity Protocol · part of this benchmark · 9 evaluations · 54 results
- PLABench ChEMBL35 leakage-controlled affinity Protocol · part of this benchmark · 9 evaluations · 63 results
- PLABench Davis, cold-drug split Protocol · part of this benchmark · 3 evaluations · 18 results
- PLABench Davis, cold-target split Protocol · part of this benchmark · 3 evaluations · 18 results
- PLABench Davis, warm split Protocol · part of this benchmark · 3 evaluations · 18 results
- PLABench KIBA, cold-drug split Protocol · part of this benchmark · 3 evaluations · 18 results
- PLABench KIBA, cold-target split Protocol · part of this benchmark · 3 evaluations · 18 results
- PLABench KIBA, warm split Protocol · part of this benchmark · 3 evaluations · 18 results
Methods and evaluation design
Procedure, tasks and evaluated configurations
Additional methodological details, tasks and evaluated configurations have not yet been extracted into a structured profile for this benchmark. Consult the linked sources and evaluation records below.
Baseline coverage
Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.
0 of 18 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.
Baseline status by linked protocol
- PLABench CASP16 L1000 affinity · 0/2 roles measured
- PLABench CASP16 L3000 affinity · 0/2 roles measured
- PLABench ChEMBL35 leakage-controlled affinity · 0/2 roles measured
- PLABench Davis, cold-drug split · 0/2 roles measured
- PLABench Davis, cold-target split · 0/2 roles measured
- PLABench Davis, warm split · 0/2 roles measured
- PLABench KIBA, cold-drug split · 0/2 roles measured
- PLABench KIBA, cold-target split · 0/2 roles measured
- PLABench KIBA, warm split · 0/2 roles measured
Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)
Coverage is derived from release 2026-10-23-5347695500ed. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.
Run instructions
No runnable recipe has been reviewed for this benchmark. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.
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
| Property and statement | Original source and location | Review and provenance |
|---|
No evidence rows match these filters. Choose another scope or clear the search.
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
Technical metadata and extraction receipts
Stable ID: lit-interactions-20261011-leakctl-benchmark-plabench
- areas
- molecular-interactions
- contexts
- research
- entity level
- suite
- version
- bioRxiv v1 (2026-09-23)
- task
- Protein-ligand binding affinity prediction and target-centric ligand ranking
- scope note
- Tables 2-4 extracted. Figure-only analyses (input pose accuracy ladder, interaction counts, per-target Kendall tau) not extracted.
- source locator
- Abstract; Figure 1; Tables 1-4
Related records
- part of: PLABench CASP16 L1000 affinity
- part of: PLABench CASP16 L3000 affinity
- part of: PLABench ChEMBL35 leakage-controlled affinity
- part of: PLABench Davis, cold-drug split
- part of: PLABench Davis, cold-target split
- part of: PLABench Davis, warm split
- part of: PLABench KIBA, cold-drug split
- part of: PLABench KIBA, cold-target split
- part of: PLABench KIBA, warm split