rewirebio.iobenchmarks
Configuration

TorchCraft minibinder design, raw output

A TorchCraft setting that optimises a complete minibinder sequence against a fixed protein target template and returns the sequence without any inverse-folding redesign.

4 evaluations · 4 results

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.

Model Capabilities & Hardware Requirements

Deployment facts recorded for TorchCraft minibinder design, raw output. Fields the record does not carry are marked not recorded.

ParametersNot recorded
Minimum VRAMNot recorded
Inference LatencyNot recorded
Context WindowNot recorded
AccessNot recorded
LicenseNot recorded

Evaluated Checkpoint: As published in arXiv:2609.19770v1, on pretrained AlphaFold 3 weights through TorchFold

Evaluations and results

4 evaluations · 4 results. Different protocols are not a single leaderboard.

Protocol: Apparent dissociation constant of a selected minibinder design by biolayer interferometry

Sorted by Dissociation constant (apparent KD of a de novo minibinder, measured by biolayer interferometry with the binder immobilised and fitted with a 1:1 binding model, for one displayed representative design from a filtered and ranked pool, not a campaign hit rate) (lower 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 configurationProtocol and datasetDissociation constant (apparent KD of a de novo minibinder, measured by biolayer interferometry with the binder immobilised and fitted with a 1:1 binding model, for one displayed representative design from a filtered and ranked pool, not a campaign hit rate)
TorchCraft minibinder design, raw outputEvaluationPDGFRb measurements of the minibinder validation campaign2.04 (best in column)
TorchCraft minibinder design, raw outputEvaluationIL-7Ra measurements of the minibinder validation campaign8.55
TorchCraft minibinder design, raw outputEvaluationPD-L1 measurements of the minibinder validation campaign23.3
TorchCraft minibinder design, raw outputEvaluationIFNAR2 measurements of the minibinder validation campaign60.2
All 4 result rows with coverage, uncertainty and sources
Filter evaluations

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configurationProtocol and datasetFindingEvidence and details
Configuration: TorchCraft minibinder design, raw outputProtocol: Apparent dissociation constant of a selected minibinder design by biolayer interferometry
Dataset subset: IFNAR2 measurements of the minibinder validation campaign
60.2 Dissociation constant (apparent KD of a de novo minibinder, measured by biolayer interferometry with the binder immobilised and fitted with a 1:1 binding model, for one displayed representative design from a filtered and ranked pool, not a campaign hit rate)
nanomolar · lower

Uncertainty: Not reported by the source: No error, interval or replicate spread is printed for the KD values.

Coverage: 1 displayed designs scored (One representative design; the tested denominator is not stated.)

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

Measured binding of a selected TorchCraft minibinder to IFNAR2

Not reported

Aggregation: Not reported

TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1) · Figure 2a caption (page 4), sentence "Apparent dissociation constants of the displayed binders were 60.2, 8.55, 2.04, and 23.3 nM, respectively."; value for IFNAR2. The same number is printed in Section 2.2 and in the Figure 2a panel label "KD: 60.2nM".
Configuration: TorchCraft minibinder design, raw outputProtocol: Apparent dissociation constant of a selected minibinder design by biolayer interferometry
Dataset subset: IL-7Ra measurements of the minibinder validation campaign
8.55 Dissociation constant (apparent KD of a de novo minibinder, measured by biolayer interferometry with the binder immobilised and fitted with a 1:1 binding model, for one displayed representative design from a filtered and ranked pool, not a campaign hit rate)
nanomolar · lower

Uncertainty: Not reported by the source: No error, interval or replicate spread is printed for the KD values.

Coverage: 1 displayed designs scored (One representative design; the tested denominator is not stated.)

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

Measured binding of a selected TorchCraft minibinder to IL-7Ra

Not reported

Aggregation: Not reported

TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1) · Figure 2a caption (page 4), sentence "Apparent dissociation constants of the displayed binders were 60.2, 8.55, 2.04, and 23.3 nM, respectively."; value for IL-7Ra. The same number is printed in Section 2.2 and in the Figure 2a panel label "KD: 8.55nM".
Configuration: TorchCraft minibinder design, raw outputProtocol: Apparent dissociation constant of a selected minibinder design by biolayer interferometry
Dataset subset: PDGFRb measurements of the minibinder validation campaign
2.04 Dissociation constant (apparent KD of a de novo minibinder, measured by biolayer interferometry with the binder immobilised and fitted with a 1:1 binding model, for one displayed representative design from a filtered and ranked pool, not a campaign hit rate)
nanomolar · lower

Uncertainty: Not reported by the source: No error, interval or replicate spread is printed for the KD values.

Coverage: 1 displayed designs scored (One representative design; the tested denominator is not stated.)

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

Measured binding of a selected TorchCraft minibinder to PDGFRb

Not reported

Aggregation: Not reported

TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1) · Figure 2a caption (page 4), sentence "Apparent dissociation constants of the displayed binders were 60.2, 8.55, 2.04, and 23.3 nM, respectively."; value for PDGFRb. The same number is printed in Section 2.2 and in the Figure 2a panel label "KD: 2.04nM".
Configuration: TorchCraft minibinder design, raw outputProtocol: Apparent dissociation constant of a selected minibinder design by biolayer interferometry
Dataset subset: PD-L1 measurements of the minibinder validation campaign
23.3 Dissociation constant (apparent KD of a de novo minibinder, measured by biolayer interferometry with the binder immobilised and fitted with a 1:1 binding model, for one displayed representative design from a filtered and ranked pool, not a campaign hit rate)
nanomolar · lower

Uncertainty: Not reported by the source: No error, interval or replicate spread is printed for the KD values.

Coverage: 1 displayed designs scored (One representative design; the tested denominator is not stated.)

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

Measured binding of a selected TorchCraft minibinder to PD-L1

Not reported

Aggregation: Not reported

TorchCraft: Unified binder design by inverting an all-atom structure predictor (arXiv:2609.19770v1) · Figure 2a caption (page 4), sentence "Apparent dissociation constants of the displayed binders were 60.2, 8.55, 2.04, and 23.3 nM, respectively."; value for PD-L1. The same number is printed in Section 2.2 and in the Figure 2a panel label "KD: 23.3nM".

Source checking is not independent reproduction. Release 2026-11-21-c8bea25e5abb.

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 2026-11-21-c8bea25e5abb
Property and statementOriginal source and locationReview and provenance

No evidence rows match these filters. Choose another scope or clear the search.

Sources and history

Release 2026-11-21-c8bea25e5abb · Record review: source checked

1 source record and release historyDownload this release (gzip)
Technical metadata and record identifiers

Technical metadata for this record is tracked under stable ID torchcraft-20261115-config-minibinder-raw.

Source locator: Supplementary Table S1 row 'Minibinder'; Appendix A.1.3 and A.2.1; Section 2.2

Related records

How to cite

TorchCraft minibinder design, raw output. Rewire biological model benchmark database, release 2026-11-21-c8bea25e5abb. https://benchmarks.rewirebio.io/database/configuration/torchcraft-20261115-config-minibinder-raw/

Release 2026-11-21-c8bea25e5abb. Rankings and values change between releases, so keep the release id in the citation. Cite the original publication as well for any value you reuse: each result links its source.

The compilation and annotations made by Rewire in this release are offered under CC BY 4.0; values and text taken from cited sources stay under the terms of those sources and are not covered by this licence. Data licence

Suggest a correction