rewire.itbenchmarks
Task

Antibody loop structure prediction

Antibody loop structure assessment uses public ImmuneBuilder tests and a separate private structural collection.

SourcesConformation-aware structure prediction of antigen-recognizing immune proteins · Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28

2 evaluations · 2 results

Overview

Datasets

ImmuneBuilder antibody, nanobody and TCR tests; an additional private antibody-structure dataset.

Metrics

Mean region-specific RMSD; private-set loop RMSD is also stratified by sequence edit distance.

Allowed inputs

Immune-protein sequence for loop/structure prediction.

SourcesConformation-aware structure prediction of antigen-recognizing immune proteins · Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28
Evaluation procedure diagram
How it worksComputational evaluation flow
Computational evaluation flow1. Input: Immune-protein sequence for loop/structure prediction.. Then: 2. Evaluation: Structure prediction trained with clusters containing public test examples excluded.. Then: 3. Readout: Mean region-specific RMSD; private-set loop RMSD is also stratified by sequence edit distance.Computational evaluation flow1. Input: Immune-protein sequence for loop/structure prediction.. Then: 2. Evaluation: Structure prediction trained with clusters containing public test examples excluded.. Then: 3. Readout: Mean region-specific RMSD; private-set loop RMSD is also stratified by sequence edit distance.Computational evaluation flow1. Input: Immune-protein sequence for loop/structure prediction.. Then: 2. Evaluation: Structure prediction trained with clusters containing public test examples excluded.. Then: 3. Readout: Mean region-specific RMSD; private-set loop RMSD is also stratified by sequence edit distance.

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

SourcesConformation-aware structure prediction of antigen-recognizing immune proteins · Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28

limited source coverage · Automated source review, 2026-09-16. All specifications and missing details

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

2 evaluations · 2 results. Different protocols are not a single leaderboard.

Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: IbexTask: Antibody loop structure prediction
Dataset: ImmuneBuilder antibody test set
2.72 Mean CDR H3 RMSD
Å · unknown

Uncertainty: Not reported

Coverage: Not reported scored / Not reported eligible

Author-reported evaluation · Source checked
Methods, coverage and source

Ibex: Antibody loop structure prediction

Backbone RMSD after framework alignment; average over antibody test structures.

Aggregation: Not reported

Conformation-aware structure prediction of antigen-recognizing immune proteins · Table 1, Antibodies / Ibex row, CDR H3 column
Configuration: Chai-1Task: Antibody loop structure prediction
Dataset: ImmuneBuilder antibody test set
2.65 Mean CDR H3 RMSD
Å · unknown

Uncertainty: Not reported

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Chai-1: Antibody loop structure prediction

Backbone RMSD after framework alignment; one seed and one diffusion trajectory.

Aggregation: Not reported

Conformation-aware structure prediction of antigen-recognizing immune proteins · Table 1, Antibodies / Chai-1 row, CDR H3 column

Source checking is not independent reproduction. Release 2026-09-29-06401fd5b220.

Methods and evaluation design

Procedure, tasks and evaluated configurations

How it works

Evaluation methodology

ImmuneBuilder antibody, nanobody and TCR tests; an additional private antibody-structure dataset. Training excludes clusters containing public test structures; the private set is characterized by loop distance to public structures. Mean region-specific RMSD; private-set loop RMSD is also stratified by sequence edit distance. ESMFold, Chai-1, Boltz-1 and specialized immune-protein structure models. Boltz-2 is excluded from the public test comparison because its later training cutoff includes much of that test set. Chai-1 and Boltz-1 use one seed/trajectory in the public comparison; this is not a repeated-sampling uncertainty analysis.

SourcesConformation-aware structure prediction of antigen-recognizing immune proteins · Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Run instructions

No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.

Strengths, limitations and unresolved questions

Strengths and limitations

Profile review details

Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.

Stable record: reported-task-f3a12dbc0e0439

Specifications

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
DatasetsImmuneBuilder antibody, nanobody and TCR tests; an additional private antibody-structure dataset.
SourcesConformation-aware structure prediction of antigen-recognizing immune proteins · Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28
SplitsTraining excludes clusters containing public test structures; the private set is characterized by loop distance to public structures.
SourcesConformation-aware structure prediction of antigen-recognizing immune proteins · Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28
MetricsMean region-specific RMSD; private-set loop RMSD is also stratified by sequence edit distance.
SourcesConformation-aware structure prediction of antigen-recognizing immune proteins · Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28
BaselinesESMFold, Chai-1, Boltz-1 and specialized immune-protein structure models.
SourcesConformation-aware structure prediction of antigen-recognizing immune proteins · Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28
Leakage controlsBoltz-2 is excluded from the public test comparison because its later training cutoff includes much of that test set.
SourcesConformation-aware structure prediction of antigen-recognizing immune proteins · Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28
UncertaintyChai-1 and Boltz-1 use one seed/trajectory in the public comparison; this is not a repeated-sampling uncertainty analysis.
SourcesConformation-aware structure prediction of antigen-recognizing immune proteins · Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28
Entity typePaper-specific computational evaluation protocol.
SourcesConformation-aware structure prediction of antigen-recognizing immune proteins · Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28
OrganismsAntibody, nanobody and T-cell receptor collections.
SourcesConformation-aware structure prediction of antigen-recognizing immune proteins · Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28
AssaysExperimentally determined immune-protein structures.
SourcesConformation-aware structure prediction of antigen-recognizing immune proteins · Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28
Allowed inputsImmune-protein sequence for loop/structure prediction.
SourcesConformation-aware structure prediction of antigen-recognizing immune proteins · Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28
AdaptationStructure prediction trained with clusters containing public test examples excluded.
SourcesConformation-aware structure prediction of antigen-recognizing immune proteins · Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28

Evidence

Source checking verifies the cited claim or transcription. It does not establish independent reproduction.

Papers and result coverage

Last literature check: 2026-09-17. Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.

Paper or primary resourceVersionReference
Conformation-aware structure prediction of antigen-recognizing immune proteinsPMC archival version PMC12710905.1Read source
DOI: 10.1080/19420862.2025.2602217
Historical gaps recorded on 2026-09-17

The catalogue now holds 2 result rows for this benchmark. A note below about pending extraction describes the state on 2026-09-17 and may since have been answered by a later batch. The result rows and their sources are the current record.

  • Complete raw table acquired. Antibodyloops cannot be pooled withnanobody/TCR cohorts orframeworkRMSD; sixloopregions separate. LowerÅRMSD; nanobodylight-chain N/A retained. Structured extraction pending.
Search and extraction details

source found structured extraction pending

Searches

  • Conformation-aware structure prediction of antigen-recognizing immune proteins primary paper benchmark results

Evidence locations

  • Table1 region-specific RMSD; antibody/nanobody/TCR blocks

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 2026-09-29-06401fd5b220
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
Conformation-aware structure prediction of antigen-recognizing immune proteins

Original source ↗

Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28

Version: PMC archival version PMC12710905.1
Retrieved: 2026-09-16T10:44:03.426811+00:00

source checked

automated source review · 2026-09-16

Audit details

Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.

Field: attributes.profile.diagram.caption

Source artifact SHA-256: caa1109bd5fe7f6be703aa9d4afd6f4f1522bcbce6b7361650eb59618c2a9e14

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

Inspected artifact

Diagram steps
  • Input: Immune-protein sequence for loop/structure prediction.
  • Evaluation: Structure prediction trained with clusters containing public test examples excluded.
  • Readout: Mean region-specific RMSD; private-set loop RMSD is also stratified by sequence edit distance.
Individual claims
Conformation-aware structure prediction of antigen-recognizing immune proteins

Original source ↗

Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28

Version: PMC archival version PMC12710905.1
Retrieved: 2026-09-16T10:44:03.426811+00:00

source checked

automated source review · 2026-09-16

Audit details

Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.

Field: attributes.profile.diagram.steps

Source artifact SHA-256: caa1109bd5fe7f6be703aa9d4afd6f4f1522bcbce6b7361650eb59618c2a9e14

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

Inspected artifact

Diagram title
Computational evaluation flow
Individual claims
Conformation-aware structure prediction of antigen-recognizing immune proteins

Original source ↗

Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28

Version: PMC archival version PMC12710905.1
Retrieved: 2026-09-16T10:44:03.426811+00:00

source checked

automated source review · 2026-09-16

Audit details

Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.

Field: attributes.profile.diagram.title

Source artifact SHA-256: caa1109bd5fe7f6be703aa9d4afd6f4f1522bcbce6b7361650eb59618c2a9e14

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

Inspected artifact

Datasets
ImmuneBuilder antibody, nanobody and TCR tests; an additional private antibody-structure dataset.
Individual claims
Conformation-aware structure prediction of antigen-recognizing immune proteins

Original source ↗

Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28

Version: PMC archival version PMC12710905.1
Retrieved: 2026-09-16T10:44:03.426811+00:00

source checked

automated source review · 2026-09-16

Audit details

Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.

Field: attributes.profile.facts.0.value

Source artifact SHA-256: caa1109bd5fe7f6be703aa9d4afd6f4f1522bcbce6b7361650eb59618c2a9e14

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

Inspected artifact

Splits
Training excludes clusters containing public test structures; the private set is characterized by loop distance to public structures.
Individual claims
Conformation-aware structure prediction of antigen-recognizing immune proteins

Original source ↗

Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28

Version: PMC archival version PMC12710905.1
Retrieved: 2026-09-16T10:44:03.426811+00:00

source checked

automated source review · 2026-09-16

Audit details

Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.

Field: attributes.profile.facts.1.value

Source artifact SHA-256: caa1109bd5fe7f6be703aa9d4afd6f4f1522bcbce6b7361650eb59618c2a9e14

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

Inspected artifact

Adaptation
Structure prediction trained with clusters containing public test examples excluded.
Individual claims
Conformation-aware structure prediction of antigen-recognizing immune proteins

Original source ↗

Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28

Version: PMC archival version PMC12710905.1
Retrieved: 2026-09-16T10:44:03.426811+00:00

source checked

automated source review · 2026-09-16

Audit details

Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.

Field: attributes.profile.facts.10.value

Source artifact SHA-256: caa1109bd5fe7f6be703aa9d4afd6f4f1522bcbce6b7361650eb59618c2a9e14

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

Inspected artifact

Metrics
Mean region-specific RMSD; private-set loop RMSD is also stratified by sequence edit distance.
Individual claims
Conformation-aware structure prediction of antigen-recognizing immune proteins

Original source ↗

Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28

Version: PMC archival version PMC12710905.1
Retrieved: 2026-09-16T10:44:03.426811+00:00

source checked

automated source review · 2026-09-16

Audit details

Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.

Field: attributes.profile.facts.2.value

Source artifact SHA-256: caa1109bd5fe7f6be703aa9d4afd6f4f1522bcbce6b7361650eb59618c2a9e14

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

Inspected artifact

Baselines
ESMFold, Chai-1, Boltz-1 and specialized immune-protein structure models.
Individual claims
Conformation-aware structure prediction of antigen-recognizing immune proteins

Original source ↗

Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28

Version: PMC archival version PMC12710905.1
Retrieved: 2026-09-16T10:44:03.426811+00:00

source checked

automated source review · 2026-09-16

Audit details

Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.

Field: attributes.profile.facts.3.value

Source artifact SHA-256: caa1109bd5fe7f6be703aa9d4afd6f4f1522bcbce6b7361650eb59618c2a9e14

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

Inspected artifact

Leakage controls
Boltz-2 is excluded from the public test comparison because its later training cutoff includes much of that test set.
Individual claims
Conformation-aware structure prediction of antigen-recognizing immune proteins

Original source ↗

Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28

Version: PMC archival version PMC12710905.1
Retrieved: 2026-09-16T10:44:03.426811+00:00

source checked

automated source review · 2026-09-16

Audit details

Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.

Field: attributes.profile.facts.4.value

Source artifact SHA-256: caa1109bd5fe7f6be703aa9d4afd6f4f1522bcbce6b7361650eb59618c2a9e14

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

Inspected artifact

Uncertainty
Chai-1 and Boltz-1 use one seed/trajectory in the public comparison; this is not a repeated-sampling uncertainty analysis.
Individual claims
Conformation-aware structure prediction of antigen-recognizing immune proteins

Original source ↗

Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28

Version: PMC archival version PMC12710905.1
Retrieved: 2026-09-16T10:44:03.426811+00:00

source checked

automated source review · 2026-09-16

Audit details

Task-specific computational methodology and field context checked in the cited primary-source artifact. Source-backed fields, inapplicable evaluator dimensions and unresolved details are distinguished. Numerical results were not reproduced.

Field: attributes.profile.facts.5.value

Source artifact SHA-256: caa1109bd5fe7f6be703aa9d4afd6f4f1522bcbce6b7361650eb59618c2a9e14

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

Inspected artifact

Sources and history

View linked audit checks and correction history

Release 2026-09-29-06401fd5b220 · Record review: needs review

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

Stable ID: reported-task-f3a12dbc0e0439

areas
molecular-interactions
tasks
Antibody loop structure prediction
entity level
task
version
Not reported
task
Antibody loop structure prediction
scope note
Paper-specific evaluation task; protocol completeness requires further extraction.
benchmark research
review date: 2026-09-17; status: source_found_structured_extraction_pending; primary sources: evidence-expansion-p2-ibex-2025-caa1109bd5fe; inspected locators: Table1 region-specific RMSD; antibody/nanobody/TCR blocks; searched queries: Conformation-aware structure prediction of antigen-recognizing immune proteins primary paper benchmark results; gaps: Complete raw table acquired. Antibodyloops cannot be pooled withnanobody/TCR cohorts orframeworkRMSD; sixloopregions separate. LowerÅRMSD; nanobodylight-chain N/A retained. Structured extraction pending.; claim scope: Primary-source discovery and table/protocol screening; source checked is not independently reproduced. Raw acquisitions not automatically numerical publication approval.
historical missing metadata
protocol version: not_reported_in_legacy_extract; split: 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: ibex-2025; source locator: Results: Benchmarking on the ImmuneBuilder test set; Benchmarking on a private dataset; cached text lines 22–28; 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