Protocol

AlphaBind TRA held-out antigen, pairwise accuracy

Pairwise accuracy on antibody pairs against the held-out antigen TRA: the fraction of sampled pairs in which the stronger binder is identified.

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.

4 recorded evaluations, 4 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

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

All evaluations

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

Protocol: AlphaBind TRA held-out antigen, pairwise accuracy · Dataset: AlphaBind TRA antibody variants (held-out antigen)

Sorted by Accuracy (pairwise: stronger binder identified within sampled antibody pairs) (higher 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 configuration	Accuracy (pairwise: stronger binder identified within sampled antibody pairs)
MochiBind (AlphaBind pairwise evaluation)Evaluation	74.27% (p < 0.0001) (best in column)
Graphinity (AlphaBind pairwise evaluation)Evaluation	68.5%
Boltz-2 (AlphaBind pairwise evaluation)Evaluation	60.1%
GeoDock (AlphaBind pairwise evaluation)Evaluation	51.2%

All 4 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: Boltz-2 (AlphaBind pairwise evaluation)	Protocol: AlphaBind TRA held-out antigen, pairwise accuracy Dataset: AlphaBind TRA antibody variants (held-out antigen)	60.1% Accuracy (pairwise: stronger binder identified within sampled antibody pairs) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The Table 2 footnote says "Values denote chi-squared statistics, with significance levels in parentheses", which contradicts the column headers ("Pairwise accuracy (%)", "Graphinity (%)" and so on), the cell contents (percentages between 47.11 and 74.27) and the body text, which places the chi-squared statistics in Table S1. The records read the cells as accuracies with a p-value, which the headers and body support; the footnote is wrong as printed.A systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation · Table 2 footnote Methods, coverage and source Boltz-2 on AlphaBind TRA (pairwise accuracy) lit-interactions-20261011-mochibind-protocol-alphabind-tra-pairwise-accuracy Aggregation: Not reported A systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation · Table 2, row 'TRA', column 'Boltz-2 - iplddt (%)'; STAR Methods, 'Cross-antigen evaluation setup'
Configuration: GeoDock (AlphaBind pairwise evaluation)	Protocol: AlphaBind TRA held-out antigen, pairwise accuracy Dataset: AlphaBind TRA antibody variants (held-out antigen)	51.2% Accuracy (pairwise: stronger binder identified within sampled antibody pairs) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The Table 2 footnote says "Values denote chi-squared statistics, with significance levels in parentheses", which contradicts the column headers ("Pairwise accuracy (%)", "Graphinity (%)" and so on), the cell contents (percentages between 47.11 and 74.27) and the body text, which places the chi-squared statistics in Table S1. The records read the cells as accuracies with a p-value, which the headers and body support; the footnote is wrong as printed.A systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation · Table 2 footnote Methods, coverage and source GeoDock on AlphaBind TRA (pairwise accuracy) lit-interactions-20261011-mochibind-protocol-alphabind-tra-pairwise-accuracy Aggregation: Not reported A systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation · Table 2, row 'TRA', column 'GeoDock (%)'; STAR Methods, 'Cross-antigen evaluation setup'
Configuration: Graphinity (AlphaBind pairwise evaluation)	Protocol: AlphaBind TRA held-out antigen, pairwise accuracy Dataset: AlphaBind TRA antibody variants (held-out antigen)	68.5% Accuracy (pairwise: stronger binder identified within sampled antibody pairs) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Evidence concern: excluded from comparisons The Table 2 footnote says "Values denote chi-squared statistics, with significance levels in parentheses", which contradicts the column headers ("Pairwise accuracy (%)", "Graphinity (%)" and so on), the cell contents (percentages between 47.11 and 74.27) and the body text, which places the chi-squared statistics in Table S1. The records read the cells as accuracies with a p-value, which the headers and body support; the footnote is wrong as printed.A systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation · Table 2 footnote Methods, coverage and source Graphinity on AlphaBind TRA (pairwise accuracy) lit-interactions-20261011-mochibind-protocol-alphabind-tra-pairwise-accuracy Aggregation: Not reported A systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation · Table 2, row 'TRA', column 'Graphinity (%)'; STAR Methods, 'Cross-antigen evaluation setup'
Configuration: MochiBind (AlphaBind pairwise evaluation)	Protocol: AlphaBind TRA held-out antigen, pairwise accuracy Dataset: AlphaBind TRA antibody variants (held-out antigen)	74.27% (p < 0.0001) Accuracy (pairwise: stronger binder identified within sampled antibody pairs) percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Evidence concern: excluded from comparisons The Table 2 footnote says "Values denote chi-squared statistics, with significance levels in parentheses", which contradicts the column headers ("Pairwise accuracy (%)", "Graphinity (%)" and so on), the cell contents (percentages between 47.11 and 74.27) and the body text, which places the chi-squared statistics in Table S1. The records read the cells as accuracies with a p-value, which the headers and body support; the footnote is wrong as printed.A systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation · Table 2 footnote Methods, coverage and source MochiBind on AlphaBind TRA (pairwise accuracy) lit-interactions-20261011-mochibind-protocol-alphabind-tra-pairwise-accuracy Aggregation: Not reported A systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation · Table 2, row 'TRA', column 'MochiBind (%)'; STAR Methods, 'Cross-antigen evaluation setup'

Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.

Methods and evaluation design

Procedure, tasks and evaluated configurations

Recorded evaluations

Each evaluation records what was tested and under which conditions.

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 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.

No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.

Author-reported evaluations: 1
External evaluations: 3

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Select a task-valid null control after reviewing inputs and metric

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

Conventional reference

Proposed control: requires review

Select an upstream conventional reference after reviewing the full protocol

Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.

This is a suggested selection rule, not a validated method or a measured score.

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 protocol. 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

Claims, original sources and review scope · Release 2026-10-22-1b7cf027e4f6
Property and statement	Original source and location	Review and provenance

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

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

1 source record and release history

A systematic evaluation framework for universal antibody-antigen binding affinity prediction and candidate recommendation · Original source · iScience 2026, 116522; PMC13444443 full-text XML

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: lit-interactions-20261011-mochibind-protocol-alphabind-tra-pairwise-accuracy

areas: molecular-interactions; proteins-complexes
contexts: research
protocol: AlphaBind TRA held out; pairwise accuracy (%)
version: iScience 2026, 116522
metric: accuracy
metric direction: higher
unit: percent
metric qualifier: pairwise: stronger binder identified within sampled antibody pairs
limitations: The authors developed MochiBind and ran all baselines.; Boltz-2 and GeoDock are scored through interface confidence (ipLDDT) used as an affinity proxy, not an affinity head.; The p-values printed beside MochiBind are one-sided McNemar tests against the baselines; no uncertainty is printed for the accuracies.; The four columns are not matched on adaptation: the Graphinity column is the authors' own fine-tune of a third-party model, trained on the same rotation, while Boltz-2 and GeoDock are used without any fitting.
source locator: Table 2, row 'TRA'

Related records

part of: Universal antibody-antigen affinity evaluation on AlphaBind (MochiBind study)
uses data: AlphaBind TRA antibody variants (held-out antigen)
assessment: Boltz-2 on AlphaBind TRA (pairwise accuracy)
assessment: GeoDock on AlphaBind TRA (pairwise accuracy)
assessment: Graphinity on AlphaBind TRA (pairwise accuracy)
assessment: MochiBind on AlphaBind TRA (pairwise accuracy)

Suggest a correction