rewire.it
Task

CATH superfamily annotation

CATH superfamily annotation evaluates protein-domain classification with stringent sequence-identity separation.

SourcesCATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets · Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages

1 evaluation · 1 metric row

At a glance

Inputs, training, access and other details

Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.

Data, procedure and scoring
PropertyDescription and evidence
DatasetsCATHe-derived large and small superfamily datasets based on CATH v4.3 and CATH-Gene3D.
SourcesCATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets · Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages
SplitsTraining, validation and test domain sets are retained from CATHe where structural-token availability permits.
SourcesCATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets · Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages
MetricsF1 is emphasized for class imbalance; balanced accuracy and MCC are also computed.
SourcesCATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets · Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages
BaselinesCATHe and alternative embeddings from ProtT5, ProstT5, ESM2, Ankh and TM-Vec; domain availability and input dimensionality differ.
SourcesCATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets · Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages
Leakage controlsThe source reports less than 20% sequence identity within and between the original partitions.
SourcesCATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets · Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages
UncertaintyBootstrap resampling of the test set supplies interval estimates.
SourcesCATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets · Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages
Entity typePaper-specific computational evaluation protocol.
SourcesCATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets · Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages
OrganismsThe benchmark spans CATH superfamilies using PDB and AlphaFold-database domains. Data and datasets specifies structural-domain and superfamily coverage, but does not provide a species inventory; superfamily classes are not organism labels. · Not reported in inspected sources
SourcesCATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets · Data and datasets; 3Di processing
AssaysCATH domain superfamily annotations and structural-alphabet representations.
SourcesCATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets · Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages
Allowed inputsAmino-acid embeddings, 3Di embeddings, or their concatenation.
SourcesCATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets · Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages
AdaptationFrozen protein-model embeddings feed a supervised feed-forward classifier; classifier/data-filter hyperparameters are selected in the study.
SourcesCATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets · Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages

How it works

How it worksComputational evaluation flow
Computational evaluation flow1. Input: Amino-acid embeddings, 3Di embeddings, or their concatenation.. Then: 2. Evaluation: Frozen protein-model embeddings feed a supervised feed-forward classifier; classifier/data-filter hyperparameters are selected in the study.. Then: 3. Readout: F1 is emphasized for class imbalance; balanced accuracy and MCC are also computed.Computational evaluation flow1. Input: Amino-acid embeddings, 3Di embeddings, or their concatenation.. Then: 2. Evaluation: Frozen protein-model embeddings feed a supervised feed-forward classifier; classifier/data-filter hyperparameters are selected in the study.. Then: 3. Readout: F1 is emphasized for class imbalance; balanced accuracy and MCC are also computed.Computational evaluation flow1. Input: Amino-acid embeddings, 3Di embeddings, or their concatenation.. Then: 2. Evaluation: Frozen protein-model embeddings feed a supervised feed-forward classifier; classifier/data-filter hyperparameters are selected in the study.. Then: 3. Readout: F1 is emphasized for class imbalance; balanced accuracy and MCC are also computed.

Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.

SourcesCATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets · Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages
Evaluation methodology

CATHe-derived large and small superfamily datasets based on CATH v4.3 and CATH-Gene3D. Training, validation and test domain sets are retained from CATHe where structural-token availability permits. F1 is emphasized for class imbalance; balanced accuracy and MCC are also computed. CATHe and alternative embeddings from ProtT5, ProstT5, ESM2, Ankh and TM-Vec; domain availability and input dimensionality differ. The source reports less than 20% sequence identity within and between the original partitions. Bootstrap resampling of the test set supplies interval estimates.

SourcesCATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets · Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Tested entities and results

Release 2026-09-17-d277315f7d76 · 1 evaluation · 1 metric row. Different protocols are not a single leaderboard.

Results grouped by the exact reported evaluation
Metric and findingCoverage and uncertaintyEvidence
CATHe2 + ProstT5: CATH superfamily annotation

amino-acid and structural alphabet embedding classifier

Author-reported evaluation · Evaluation metadata: needs review

82.3% F1

Unit: percent · Direction: unknown

Uncertainty: ± 1.3 percentage points

Scored: Not reported · Eligible: Not reported

source checkedCATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets · Table 3, ProstT5 full row, F1 score column

Source checking is not independent reproduction.

Papers and result coverage

Last literature check: 2026-09-17. Dated primary-source discovery and protocol/table screening. Source checking does not mean experimental reproduction. Only separately extracted and independently reviewed numeric batches are publishable.

Paper or primary resourceVersionReference
CATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabetsjournal full text in PMCRead source

What is still missing

  • complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.
  • exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.
Search and extraction details

primary comparison tables located

Searches

  • CATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets 10.1093/biomethods/bpaf080

Evidence locations

  • Table 1.; XML table bpaf080-T1
  • Table 3.; XML table bpaf080-T3

Strengths and limitations

Profile review details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Stable record: reported-task-c98e91ffc7247d

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.

18 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-17-d277315f7d76
Property and statementOriginal source and locationReview and provenance
Diagram caption

Conceptual summary of the cited evaluation; exact task configuration and source version remain part of the protocol.

Individual claims
CATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets

Original source ↗

Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.366Z

source checked

automated source review · 2026-09-16

Audit details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Field: attributes.profile.diagram.caption

Source artifact SHA-256: 713dbfb6ec1cc1aa85c0543eb93aafa0b45b8873df28053b765dd0a1b6d9b563

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Diagram steps

["Input: Amino-acid embeddings, 3Di embeddings, or their concatenation.","Evaluation: Frozen protein-model embeddings feed a supervised feed-forward classifier; classifier/data-filter hyperparameters are selected in the study.","Readout: F1 is emphasized for class imbalance; balanced accuracy and MCC are also computed."]

Individual claims
CATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets

Original source ↗

Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.366Z

source checked

automated source review · 2026-09-16

Audit details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Field: attributes.profile.diagram.steps

Source artifact SHA-256: 713dbfb6ec1cc1aa85c0543eb93aafa0b45b8873df28053b765dd0a1b6d9b563

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Diagram title

Computational evaluation flow

Individual claims
CATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets

Original source ↗

Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.366Z

source checked

automated source review · 2026-09-16

Audit details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Field: attributes.profile.diagram.title

Source artifact SHA-256: 713dbfb6ec1cc1aa85c0543eb93aafa0b45b8873df28053b765dd0a1b6d9b563

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Datasets

CATHe-derived large and small superfamily datasets based on CATH v4.3 and CATH-Gene3D.

Individual claims
CATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets

Original source ↗

Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.366Z

source checked

automated source review · 2026-09-16

Audit details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Field: attributes.profile.facts.0.value

Source artifact SHA-256: 713dbfb6ec1cc1aa85c0543eb93aafa0b45b8873df28053b765dd0a1b6d9b563

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Splits

Training, validation and test domain sets are retained from CATHe where structural-token availability permits.

Individual claims
CATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets

Original source ↗

Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.366Z

source checked

automated source review · 2026-09-16

Audit details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Field: attributes.profile.facts.1.value

Source artifact SHA-256: 713dbfb6ec1cc1aa85c0543eb93aafa0b45b8873df28053b765dd0a1b6d9b563

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Adaptation

Frozen protein-model embeddings feed a supervised feed-forward classifier; classifier/data-filter hyperparameters are selected in the study.

Individual claims
CATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets

Original source ↗

Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.366Z

source checked

automated source review · 2026-09-16

Audit details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Field: attributes.profile.facts.10.value

Source artifact SHA-256: 713dbfb6ec1cc1aa85c0543eb93aafa0b45b8873df28053b765dd0a1b6d9b563

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Metrics

F1 is emphasized for class imbalance; balanced accuracy and MCC are also computed.

Individual claims
CATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets

Original source ↗

Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.366Z

source checked

automated source review · 2026-09-16

Audit details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Field: attributes.profile.facts.2.value

Source artifact SHA-256: 713dbfb6ec1cc1aa85c0543eb93aafa0b45b8873df28053b765dd0a1b6d9b563

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Baselines

CATHe and alternative embeddings from ProtT5, ProstT5, ESM2, Ankh and TM-Vec; domain availability and input dimensionality differ.

Individual claims
CATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets

Original source ↗

Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.366Z

source checked

automated source review · 2026-09-16

Audit details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Field: attributes.profile.facts.3.value

Source artifact SHA-256: 713dbfb6ec1cc1aa85c0543eb93aafa0b45b8873df28053b765dd0a1b6d9b563

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Leakage controls

The source reports less than 20% sequence identity within and between the original partitions.

Individual claims
CATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets

Original source ↗

Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.366Z

source checked

automated source review · 2026-09-16

Audit details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Field: attributes.profile.facts.4.value

Source artifact SHA-256: 713dbfb6ec1cc1aa85c0543eb93aafa0b45b8873df28053b765dd0a1b6d9b563

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Uncertainty

Bootstrap resampling of the test set supplies interval estimates.

Individual claims
CATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets

Original source ↗

Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages

Version: journal full text in PMC
Retrieved: 2026-09-16T10:33:38.366Z

source checked

automated source review · 2026-09-16

Audit details

Relevant full-paper computational evaluation sections, tables/captions and cited supplementary task passages were reviewed. Reporting omissions are scoped to the inspected sources. Original numerical results are unchanged.

Field: attributes.profile.facts.5.value

Source artifact SHA-256: 713dbfb6ec1cc1aa85c0543eb93aafa0b45b8873df28053b765dd0a1b6d9b563

Hash scope: Hash scope not separately documented; inspect source record

Inspected artifact

Sources and history

Release 2026-09-17-d277315f7d76 · Record review: needs review

2 source records and release historyDownload this release
Technical metadata and extraction receipts

Stable ID: reported-task-c98e91ffc7247d

areas
proteins-complexes
tasks
CATH superfamily annotation
entity level
task
version
Not reported
task
CATH superfamily annotation
scope note
Paper-specific evaluation task; protocol completeness requires further extraction.
benchmark research
review date: 2026-09-17; status: primary_comparison_tables_located; primary sources: evidence-expansion-cathe2-2025-713dbfb6; inspected locators: Table 1.; XML table bpaf080-T1; Table 3.; XML table bpaf080-T3; searched queries: CATHe2: Enhanced CATH superfamily detection using ProstT5 and structural alphabets 10.1093/biomethods/bpaf080; gaps: complete numerical transcription and independent cell review: Full primary artifact and table inventory preserved; no new numeric row is published from this audit alone.; exact checkpoint hashes and per-method scored denominators: Table labels alone do not establish these fields; do not infer checkpoint or scored count from model name or dataset size.; claim scope: Dated primary-source discovery and protocol/table screening. Source checking does not mean experimental reproduction. Only separately extracted and independently reviewed numeric batches are publishable.
historical missing metadata
protocol version: not_reported_in_legacy_extract
metadata review scope
historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
legacy kinds
benchmark
entity classification
review date: 2026-09-17; rationale: This source-scoped record identifies the biological prediction task and holds its paper context. Preserve the existing task identity; exact split, model adaptation and scoring remain in linked evaluations or separate protocol records.; source ids: cathe2-2025; source locator: Methods: Data and datasets; Results; cached text lines 11–14, 30; comparative evaluation and ablation passages; ambiguities: A paper- or suite-specific task may constrain some inputs or metrics; that alone does not make it interchangeable with a complete versioned protocol. No protocol equivalence is inferred.; Some legacy profile Entity type facts use the generic phrase computational evaluation protocol. That boilerplate is not sufficient to establish a single fixed protocol identity or to merge this task with another protocol record.
Related records

Suggest a correction