Benchmark
AlphaFold and ESMFold benchmark on PDB structures released 2022 to 2024
Independent benchmark of AlphaFold2, AlphaFold3 and ESMFold on non-redundant PDB entries released between 2022 and 2024 whose sequences have no close homologue among pre-2022 structures.
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. 18 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.
- Predictive-class counts for monomeric predictions, structures in the class whose experimental reference is electron microscopy (Table 1, column 'EM') Protocol · part of this benchmark · 3 evaluations · 12 results
- Predictive-class counts for monomeric predictions, structures in the class whose experimental reference is NMR (Table 1, column 'NMR') Protocol · part of this benchmark · 3 evaluations · 12 results
- Predictive-class counts for monomeric predictions, all structures in the class (Table 1, column 'No.') Protocol · part of this benchmark · 3 evaluations · 12 results
- Predictive-class counts for monomeric predictions, structures in the class whose pLDDT is at least 70 (Table 1, column 'pLDDT ≥ 70') Protocol · part of this benchmark · 3 evaluations · 12 results
- Predictive-class counts for monomeric predictions, structures in the class with template quality 0 (no homologous pre-2022 structure) (Table 1, column 'TQ 0') Protocol · part of this benchmark · 3 evaluations · 12 results
- Predictive-class counts for monomeric predictions, structures in the class with template quality between 1 and 40 (Table 1, column 'TQ 1–40') Protocol · part of this benchmark · 3 evaluations · 12 results
- Predictive-class counts for monomeric predictions, structures in the class with template quality above 40 (Table 1, column 'TQ > 40') Protocol · part of this benchmark · 3 evaluations · 12 results
- Predictive-class counts for monomeric predictions, structures in the class whose experimental reference is X-ray diffraction (Table 1, column 'XRD') Protocol · part of this benchmark · 3 evaluations · 12 results
- Predictive-class counts for dimeric predictions, structures in the class whose experimental reference is electron microscopy (Table 2, column 'EM') Protocol · part of this benchmark · 3 evaluations · 12 results
- Predictive-class counts for dimeric predictions, heterodimeric structures in the class (Table 2, column 'Heterodimer') Protocol · part of this benchmark · 3 evaluations · 12 results
- Predictive-class counts for dimeric predictions, homodimeric structures in the class (Table 2, column 'Homodimer') Protocol · part of this benchmark · 3 evaluations · 12 results
- Predictive-class counts for dimeric predictions, structures in the class whose experimental reference is NMR (Table 2, column 'NMR') Protocol · part of this benchmark · 3 evaluations · 12 results
- Predictive-class counts for dimeric predictions, all structures in the class (Table 2, column 'No.') Protocol · part of this benchmark · 3 evaluations · 12 results
- Predictive-class counts for dimeric predictions, structures in the class whose pLDDT is at least 70 (Table 2, column 'pLDDT ≥ 70') Protocol · part of this benchmark · 3 evaluations · 12 results
- Predictive-class counts for dimeric predictions, structures in the class with template quality 0 (no homologous pre-2022 structure) (Table 2, column 'TQ 0') Protocol · part of this benchmark · 3 evaluations · 12 results
- Predictive-class counts for dimeric predictions, structures in the class with template quality between 1 and 40 (Table 2, column 'TQ 1–40') Protocol · part of this benchmark · 3 evaluations · 12 results
- Predictive-class counts for dimeric predictions, structures in the class with template quality above 40 (Table 2, column 'TQ > 40') Protocol · part of this benchmark · 3 evaluations · 12 results
- Predictive-class counts for dimeric predictions, structures in the class whose experimental reference is X-ray diffraction (Table 2, column 'XRD') Protocol · part of this benchmark · 3 evaluations · 12 results
Methods and evaluation design
Procedure, tasks and evaluated configurations
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 36 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
- Predictive-class counts for monomeric predictions, structures in the class whose experimental reference is electron microscopy (Table 1, column 'EM') · 0/2 roles measured
- Predictive-class counts for monomeric predictions, structures in the class whose experimental reference is NMR (Table 1, column 'NMR') · 0/2 roles measured
- Predictive-class counts for monomeric predictions, all structures in the class (Table 1, column 'No.') · 0/2 roles measured
- Predictive-class counts for monomeric predictions, structures in the class whose pLDDT is at least 70 (Table 1, column 'pLDDT ≥ 70') · 0/2 roles measured
- Predictive-class counts for monomeric predictions, structures in the class with template quality 0 (no homologous pre-2022 structure) (Table 1, column 'TQ 0') · 0/2 roles measured
- Predictive-class counts for monomeric predictions, structures in the class with template quality between 1 and 40 (Table 1, column 'TQ 1–40') · 0/2 roles measured
- Predictive-class counts for monomeric predictions, structures in the class with template quality above 40 (Table 1, column 'TQ > 40') · 0/2 roles measured
- Predictive-class counts for monomeric predictions, structures in the class whose experimental reference is X-ray diffraction (Table 1, column 'XRD') · 0/2 roles measured
- Predictive-class counts for dimeric predictions, structures in the class whose experimental reference is electron microscopy (Table 2, column 'EM') · 0/2 roles measured
- Predictive-class counts for dimeric predictions, heterodimeric structures in the class (Table 2, column 'Heterodimer') · 0/2 roles measured
- Predictive-class counts for dimeric predictions, homodimeric structures in the class (Table 2, column 'Homodimer') · 0/2 roles measured
- Predictive-class counts for dimeric predictions, structures in the class whose experimental reference is NMR (Table 2, column 'NMR') · 0/2 roles measured
- Predictive-class counts for dimeric predictions, all structures in the class (Table 2, column 'No.') · 0/2 roles measured
- Predictive-class counts for dimeric predictions, structures in the class whose pLDDT is at least 70 (Table 2, column 'pLDDT ≥ 70') · 0/2 roles measured
- Predictive-class counts for dimeric predictions, structures in the class with template quality 0 (no homologous pre-2022 structure) (Table 2, column 'TQ 0') · 0/2 roles measured
- Predictive-class counts for dimeric predictions, structures in the class with template quality between 1 and 40 (Table 2, column 'TQ 1–40') · 0/2 roles measured
- Predictive-class counts for dimeric predictions, structures in the class with template quality above 40 (Table 2, column 'TQ > 40') · 0/2 roles measured
- Predictive-class counts for dimeric predictions, structures in the class whose experimental reference is X-ray diffraction (Table 2, column 'XRD') · 0/2 roles measured
Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)
Coverage is derived from release 2026-10-22-1b7cf027e4f6. 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.
Strengths, limitations and unresolved questions
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 2026-10-22-1b7cf027e4f6 · Record review: source checked
1 source record and release history
- Comparative evaluation of the prediction accuracy of AlphaFold and ESMFold for monomeric and dimeric proteins · Original source · Version of record, NAR Genomics and Bioinformatics 2026 (PMC12809598 JATS full text)
Technical metadata and extraction receipts
Stable ID: lit-structure-20261011-afesmfold-benchmark-promodev-2022-2024
- areas
- protein-structure; proteins-complexes
- contexts
- research
- entity level
- suite
- version
- As published 2026
- task
- Predict monomeric and dimeric protein structures from sequence
- scope note
- Targets are PDB entries from 2022 to 2024 with sequence identity below 40% or query coverage below 70% against structures released up to 31 December 2021; CD-HIT at 90% identity removed redundancy and chains shorter than 20 or longer than 2700 residues were excluded.
- source locator
- Materials and methods, 'Collection of benchmarking datasets and structure selection criteria'; Tables 1 and 2
- limitations
- Classification thresholds are the authors' own (RMSD and LDDT for monomers, DockQ for dimers).
Related records
- part of: Predictive-class counts for monomeric predictions, structures in the class whose experimental reference is electron microscopy (Table 1, column 'EM')
- part of: Predictive-class counts for monomeric predictions, structures in the class whose experimental reference is NMR (Table 1, column 'NMR')
- part of: Predictive-class counts for monomeric predictions, all structures in the class (Table 1, column 'No.')
- part of: Predictive-class counts for monomeric predictions, structures in the class whose pLDDT is at least 70 (Table 1, column 'pLDDT ≥ 70')
- part of: Predictive-class counts for monomeric predictions, structures in the class with template quality 0 (no homologous pre-2022 structure) (Table 1, column 'TQ 0')
- part of: Predictive-class counts for monomeric predictions, structures in the class with template quality between 1 and 40 (Table 1, column 'TQ 1–40')
- part of: Predictive-class counts for monomeric predictions, structures in the class with template quality above 40 (Table 1, column 'TQ > 40')
- part of: Predictive-class counts for monomeric predictions, structures in the class whose experimental reference is X-ray diffraction (Table 1, column 'XRD')
- part of: Predictive-class counts for dimeric predictions, structures in the class whose experimental reference is electron microscopy (Table 2, column 'EM')
- part of: Predictive-class counts for dimeric predictions, heterodimeric structures in the class (Table 2, column 'Heterodimer')
- part of: Predictive-class counts for dimeric predictions, homodimeric structures in the class (Table 2, column 'Homodimer')
- part of: Predictive-class counts for dimeric predictions, structures in the class whose experimental reference is NMR (Table 2, column 'NMR')
- part of: Predictive-class counts for dimeric predictions, all structures in the class (Table 2, column 'No.')
- part of: Predictive-class counts for dimeric predictions, structures in the class whose pLDDT is at least 70 (Table 2, column 'pLDDT ≥ 70')
- part of: Predictive-class counts for dimeric predictions, structures in the class with template quality 0 (no homologous pre-2022 structure) (Table 2, column 'TQ 0')
- part of: Predictive-class counts for dimeric predictions, structures in the class with template quality between 1 and 40 (Table 2, column 'TQ 1–40')
- part of: Predictive-class counts for dimeric predictions, structures in the class with template quality above 40 (Table 2, column 'TQ > 40')
- part of: Predictive-class counts for dimeric predictions, structures in the class whose experimental reference is X-ray diffraction (Table 2, column 'XRD')