Protocol

Share of further OPA1 pathogenic substitutions and VUS called splice-altering (Alavi Table III, extended corpus)

Apply the OPA1-tuned thresholds to 306 pathogenic substitutions and 69 VUS outside the evaluation sets and report the count and share called positive.

12 evaluations · 24 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.

12 recorded evaluations, 24 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

12 evaluations · 24 results. Different protocols are not a single leaderboard.

Protocol: Share of further OPA1 pathogenic substitutions and VUS called splice-altering (Alavi Table III, extended corpus) · Dataset: OPA1 extended LOVD corpus (306 pathogenic substitutions, 69 VUS)

In source order. Decimals are rounded for display; each value links to the printed value and its source.

Tested configuration	Proportion (share of 306 further OPA1 pathogenic substitutions called splice-altering)	Proportion (share of 69 OPA1 VUS substitutions called splice-altering)
AlphaGenome (Either Module) (Alavi 2026)Evaluation	66 (21.6%)	7 (10.1%)
AlphaGenome Junction Scorer (Alavi 2026)Evaluation	54 (17.6%)	4 (5.8%)
AlphaGenome Splice Scorer (Alavi 2026)Evaluation	58 (19.0%)	5 (7.2%)
Borzoi (128-bp) (Alavi 2026)Evaluation	70 (22.9%)	13 (18.8%)
Borzoi (32-bp) (Alavi 2026)Evaluation	86 (28.1%)	7 (10.1%)
Evo2 40B (human identifier) (Alavi 2026)Evaluation	276 (90.2%)	47 (68.1%)
Evo2 40B (without human identifier) (Alavi 2026)Evaluation	280 (91.5%)	46 (66.7%)
Genos 10B ClinVar (Alavi 2026)Evaluation	104 (34.0%)	25 (36.2%)
Genos 10B (Alavi 2026)Evaluation	92 (30.1%)	23 (33.3%)
NTv3 650M Post (Alavi 2026)Evaluation	77 (25.2%)	9 (13.0%)
NTv3 650M Pre (Alavi 2026)Evaluation	212 (69.3%)	23 (33.3%)
SpliceAI (Alavi 2026)Evaluation	75 (24.5%)	6 (8.7%)

All 24 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

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.

External evaluations: 12

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 2026-10-22-1b7cf027e4f6. 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

Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026) · Original source · bioRxiv preprint version 1, posted 2026-10-09; full-text PDF (11 pages)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: rna-splicing-20261011-alavi2026-protocol-opa1-extended-positive-calls

areas: dna-genomes
contexts: clinical_research
protocol: Apply the OPA1-tuned thresholds to 306 pathogenic substitutions and 69 VUS outside the evaluation sets and report the count and share called positive.
version: Table III
source locator: Table III columns 'Positive mutations' and 'Positive VUS'; Results D
limitations: No splicing labels: a positive call rate is not an accuracy measure.; Thresholds were set by one-dimensional grid search on the OPA1 evaluation sets, optimising accuracy and specificity (Methods B).; Single-author preprint; no uncertainty intervals are printed for the tabulated metrics.; Foundation-model scores are zero-shot log-likelihood ratios with author-chosen context windows, aggregation and strand rules (Methods F to H).

Related records

Suggest a correction