rewirebio.iobenchmarks
← Back to results
Protocol

MFASS splice-disrupting variant detection, all 27,733 labelled SNVs (Znabu et al. 2026)

Detection of MFASS splice-disrupting variants (exon inclusion reduced by at least 0.50) by sequence-based predictors scored in hg38 genomic context.

5 evaluations · 15 results

Overview

Detection of MFASS splice-disrupting variants (exon inclusion reduced by at least 0.50) by sequence-based predictors scored in hg38 genomic context.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

5 recorded evaluations, 15 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

5 evaluations · 15 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: MMSplice (Znabu et al. 2026)Protocol: MFASS splice-disrupting variant detection, all 27,733 labelled SNVs (Znabu et al. 2026)
Dataset: MFASS v2 eligible assay cohort		0.256 average-precision
unitless · higher

Uncertainty: 95% CI 0.226 to 0.285

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

MMSplice on all labelled MFASS SNVs

splicing-follow-up-20261009-protocol-znabu2026-mfass-full-cohort

Aggregation: Not reported

A Reproducible MFASS Benchmark of Splice-Disruption Predictors Reveals a Shared Exon-Interior Blind Spot · Section 4 'Results' table (page 3), row 'MMSplice', columns 'AP' and 'AP 95% CI'
Configuration: MMSplice (Znabu et al. 2026)Protocol: MFASS splice-disrupting variant detection, all 27,733 labelled SNVs (Znabu et al. 2026)
Dataset: MFASS v2 eligible assay cohort		0.758 auroc
unitless · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

MMSplice on all labelled MFASS SNVs

splicing-follow-up-20261009-protocol-znabu2026-mfass-full-cohort

Aggregation: Not reported

A Reproducible MFASS Benchmark of Splice-Disruption Predictors Reveals a Shared Exon-Interior Blind Spot · Section 4 'Results' table (page 3), row 'MMSplice', column 'AUROC'
Configuration: MMSplice (Znabu et al. 2026)Protocol: MFASS splice-disrupting variant detection, all 27,733 labelled SNVs (Znabu et al. 2026)
Dataset: MFASS v2 eligible assay cohort		27,733 count
count · unknown

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

MMSplice on all labelled MFASS SNVs

splicing-follow-up-20261009-protocol-znabu2026-mfass-full-cohort

Aggregation: Not reported

A Reproducible MFASS Benchmark of Splice-Disruption Predictors Reveals a Shared Exon-Interior Blind Spot · Section 4 'Results' table (page 3), row 'MMSplice', column 'n'
Configuration: Pangolin (Znabu et al. 2026)Protocol: MFASS splice-disrupting variant detection, all 27,733 labelled SNVs (Znabu et al. 2026)
Dataset: MFASS v2 eligible assay cohort		0.421 average-precision
unitless · higher

Uncertainty: 95% CI 0.386 to 0.454

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Pangolin on all labelled MFASS SNVs

splicing-follow-up-20261009-protocol-znabu2026-mfass-full-cohort

Aggregation: Not reported

A Reproducible MFASS Benchmark of Splice-Disruption Predictors Reveals a Shared Exon-Interior Blind Spot · Section 4 'Results' table (page 3), row 'Pangolin', columns 'AP' and 'AP 95% CI'
Configuration: Pangolin (Znabu et al. 2026)Protocol: MFASS splice-disrupting variant detection, all 27,733 labelled SNVs (Znabu et al. 2026)
Dataset: MFASS v2 eligible assay cohort		0.888 auroc
unitless · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Pangolin on all labelled MFASS SNVs

splicing-follow-up-20261009-protocol-znabu2026-mfass-full-cohort

Aggregation: Not reported

A Reproducible MFASS Benchmark of Splice-Disruption Predictors Reveals a Shared Exon-Interior Blind Spot · Section 4 'Results' table (page 3), row 'Pangolin', column 'AUROC'
Configuration: Pangolin (Znabu et al. 2026)Protocol: MFASS splice-disrupting variant detection, all 27,733 labelled SNVs (Znabu et al. 2026)
Dataset: MFASS v2 eligible assay cohort		27,733 count
count · unknown

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

Pangolin on all labelled MFASS SNVs

splicing-follow-up-20261009-protocol-znabu2026-mfass-full-cohort

Aggregation: Not reported

A Reproducible MFASS Benchmark of Splice-Disruption Predictors Reveals a Shared Exon-Interior Blind Spot · Section 4 'Results' table (page 3), row 'Pangolin', column 'n'
Configuration: SPANR (legacy) (Znabu et al. 2026)Protocol: MFASS splice-disrupting variant detection, all 27,733 labelled SNVs (Znabu et al. 2026)
Dataset: MFASS v2 eligible assay cohort		0.228 average-precision
unitless · higher

Uncertainty: 95% CI 0.202 to 0.260

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

SPANR (legacy) on all labelled MFASS SNVs

splicing-follow-up-20261009-protocol-znabu2026-mfass-full-cohort

Aggregation: Not reported

A Reproducible MFASS Benchmark of Splice-Disruption Predictors Reveals a Shared Exon-Interior Blind Spot · Section 4 'Results' table (page 3), row 'SPANR (legacy)', columns 'AP' and 'AP 95% CI'
Configuration: SPANR (legacy) (Znabu et al. 2026)Protocol: MFASS splice-disrupting variant detection, all 27,733 labelled SNVs (Znabu et al. 2026)
Dataset: MFASS v2 eligible assay cohort		0.748 auroc
unitless · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

SPANR (legacy) on all labelled MFASS SNVs

splicing-follow-up-20261009-protocol-znabu2026-mfass-full-cohort

Aggregation: Not reported

A Reproducible MFASS Benchmark of Splice-Disruption Predictors Reveals a Shared Exon-Interior Blind Spot · Section 4 'Results' table (page 3), row 'SPANR (legacy)', column 'AUROC'
Configuration: SPANR (legacy) (Znabu et al. 2026)Protocol: MFASS splice-disrupting variant detection, all 27,733 labelled SNVs (Znabu et al. 2026)
Dataset: MFASS v2 eligible assay cohort		27,663 count
count · unknown

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

SPANR (legacy) on all labelled MFASS SNVs

splicing-follow-up-20261009-protocol-znabu2026-mfass-full-cohort

Aggregation: Not reported

A Reproducible MFASS Benchmark of Splice-Disruption Predictors Reveals a Shared Exon-Interior Blind Spot · Section 4 'Results' table (page 3), row 'SPANR (legacy)', column 'n'
Configuration: SpliceAI (Znabu et al. 2026)Protocol: MFASS splice-disrupting variant detection, all 27,733 labelled SNVs (Znabu et al. 2026)
Dataset: MFASS v2 eligible assay cohort		0.321 average-precision
unitless · higher

Uncertainty: 95% CI 0.293 to 0.353

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

SpliceAI on all labelled MFASS SNVs

splicing-follow-up-20261009-protocol-znabu2026-mfass-full-cohort

Aggregation: Not reported

A Reproducible MFASS Benchmark of Splice-Disruption Predictors Reveals a Shared Exon-Interior Blind Spot · Section 4 'Results' table (page 3), row 'SpliceAI', columns 'AP' and 'AP 95% CI'
Configuration: SpliceAI (Znabu et al. 2026)Protocol: MFASS splice-disrupting variant detection, all 27,733 labelled SNVs (Znabu et al. 2026)
Dataset: MFASS v2 eligible assay cohort		0.819 auroc
unitless · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

SpliceAI on all labelled MFASS SNVs

splicing-follow-up-20261009-protocol-znabu2026-mfass-full-cohort

Aggregation: Not reported

A Reproducible MFASS Benchmark of Splice-Disruption Predictors Reveals a Shared Exon-Interior Blind Spot · Section 4 'Results' table (page 3), row 'SpliceAI', column 'AUROC'
Configuration: SpliceAI (Znabu et al. 2026)Protocol: MFASS splice-disrupting variant detection, all 27,733 labelled SNVs (Znabu et al. 2026)
Dataset: MFASS v2 eligible assay cohort		27,733 count
count · unknown

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

SpliceAI on all labelled MFASS SNVs

splicing-follow-up-20261009-protocol-znabu2026-mfass-full-cohort

Aggregation: Not reported

A Reproducible MFASS Benchmark of Splice-Disruption Predictors Reveals a Shared Exon-Interior Blind Spot · Section 4 'Results' table (page 3), row 'SpliceAI', column 'n'
Configuration: SpliceTransformer (Znabu et al. 2026)Protocol: MFASS splice-disrupting variant detection, all 27,733 labelled SNVs (Znabu et al. 2026)
Dataset: MFASS v2 eligible assay cohort		0.317 average-precision
unitless · higher

Uncertainty: 95% CI 0.285 to 0.352

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

SpliceTransformer on all labelled MFASS SNVs

splicing-follow-up-20261009-protocol-znabu2026-mfass-full-cohort

Aggregation: Not reported

A Reproducible MFASS Benchmark of Splice-Disruption Predictors Reveals a Shared Exon-Interior Blind Spot · Section 4 'Results' table (page 3), row 'SpliceTransformer', columns 'AP' and 'AP 95% CI'
Configuration: SpliceTransformer (Znabu et al. 2026)Protocol: MFASS splice-disrupting variant detection, all 27,733 labelled SNVs (Znabu et al. 2026)
Dataset: MFASS v2 eligible assay cohort		0.786 auroc
unitless · higher

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

SpliceTransformer on all labelled MFASS SNVs

splicing-follow-up-20261009-protocol-znabu2026-mfass-full-cohort

Aggregation: Not reported

A Reproducible MFASS Benchmark of Splice-Disruption Predictors Reveals a Shared Exon-Interior Blind Spot · Section 4 'Results' table (page 3), row 'SpliceTransformer', column 'AUROC'
Configuration: SpliceTransformer (Znabu et al. 2026)Protocol: MFASS splice-disrupting variant detection, all 27,733 labelled SNVs (Znabu et al. 2026)
Dataset: MFASS v2 eligible assay cohort		27,733 count
count · unknown

Uncertainty: Not reported by the source

Coverage: Not reported scored / Not reported eligible

Independent external evaluation · Source checked
Methods, coverage and source

SpliceTransformer on all labelled MFASS SNVs

splicing-follow-up-20261009-protocol-znabu2026-mfass-full-cohort

Aggregation: Not reported

A Reproducible MFASS Benchmark of Splice-Disruption Predictors Reveals a Shared Exon-Interior Blind Spot · Section 4 'Results' table (page 3), row 'SpliceTransformer', column 'n'

Source checking is not independent reproduction. Release 2026-10-10-6e93f504adfc.

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.

External evaluations
5

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

Null control

Proposed control: requires review

Training-set class prior where supervised fitting is permitted

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

Regularised classifier on simple permitted features, or protocol's conventional reference

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 2026-10-10-6e93f504adfc. 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 2026-10-10-6e93f504adfc
Property and statementOriginal source and locationReview and provenance

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

All evidence (JSONL) (gzip)How to read the evidence

Sources and history

Release 2026-10-10-6e93f504adfc · Record review: source checked

1 source records and release historyDownload this release (gzip)
Technical metadata and extraction receipts

Stable ID: splicing-follow-up-20261009-protocol-znabu2026-mfass-full-cohort

areas
dna-genomes
contexts
research
protocol
Score all 28,972 mutant MFASS SNVs; drop variants without a v2 inclusion-change measurement, leaving 27,733 (1,050 SDVs, 3.79%). Report AUROC and average precision per tool, with 1,000-sample bootstrap 95% intervals for average precision.
version
bioRxiv v1, Section 4 Results table
source locator
Section 2 'Data and ground truth'; Section 4 Results table
limitations
Whole labelled MFASS cohort with no held-out split for the single-tool scores; not the rewire matched or v2 held-out populations, so do not pool with those protocols.; Preprint, not peer reviewed.; Tissue-aware tools used tissue-agnostically; genomic context, not the minigene fragment, was scored.; SPANR scores cover 27,663 variants.; SpliceAI returns no score outside annotated genes; those variants were set to 0. On the 12,855 variants SpliceAI scores above zero, the authors report the same order (Pangolin AP 0.468, SpliceTransformer 0.369, SpliceAI 0.365, SPANR 0.302); those values are not extracted.; MMSplice was scored on a reconstructed single-cassette context without a reference-inclusion term, which the authors say likely understates it.; The predictors may have seen the wild-type splice sites of these exons in training (authors' caveat).; Scores for SpliceAI, Pangolin and SpliceTransformer were produced through the Proto tool ecosystem (Merchant et al. 2026), which is not by the benchmark authors; per-tool scores are released.
Related records

Suggest a correction