Configuration

AlphaGenome Splice-Sites (Alavi 2026 v2)

AlphaGenome scored with the splice-sites output and a grid-searched threshold, as configured in Alavi 2026 version 2.

Overview

AlphaGenome: AlphaGenome predicts regulatory activity and variant effects from long DNA sequences, with outputs for expression, splicing, chromatin and contact maps.

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

Evaluations and results

3 evaluations · 14 results. Different protocols are not a single leaderboard.

Sorted by Accuracy (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	Protocol and dataset	Accuracy	False positive rate (type I error: false positives as a share of the benign set)	Precision	Proportion (type II error: false negatives as a share of the splicing set (false-negative rate))	Recall	Specificity	Proportion (share of 306 further OPA1 pathogenic substitutions called splice-altering)	Proportion (share of 69 OPA1 VUS substitutions called splice-altering)
AlphaGenome Splice-Sites (Alavi 2026 v2)Evaluation	Splice-defect classification of OPA1 variants with thresholds tuned on the same sets (Alavi Table III, evaluation sets), OPA1 LOVD evaluation sets (49 splicing, 79 benign)	96.1% (best in column)	2 (2.5%)	95.8%	3 (6.1%) (best in column)	46 (93.9%) (best in column)	77 (97.5%)	Not reported	Not reported
AlphaGenome Splice-Sites (Alavi 2026 v2)Evaluation	Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV), Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)	91.3%	0 (0.0 %) (best in column)	100% (best in column)	16 (21.1%)	60 (78.9%)	107 (100%) (best in column)	Not reported	Not reported
AlphaGenome Splice-Sites (Alavi 2026 v2)Evaluation	Share of further OPA1 pathogenic substitutions and VUS called splice-altering (Alavi Table III, extended corpus), OPA1 extended LOVD corpus (306 pathogenic substitutions, 69 VUS)	Not reported	Not reported	Not reported	Not reported	Not reported	Not reported	74 (24.2%)	3 (4.3%)

All 14 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: AlphaGenome Splice-Sites (Alavi 2026 v2)	Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)	91.3% Accuracy percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AlphaGenome Splice-Sites on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) (Alavi 2026 v2) rna-splicing-20261011-alavi2026-protocol-multigene Aggregation: Not reported Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026, version 2) · Table IV, row 'ALPHAGENOME SPLICE-SITES', column 'Accuracy' (PDF page 9 of 12)
Configuration: AlphaGenome Splice-Sites (Alavi 2026 v2)	Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)	100% Precision percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AlphaGenome Splice-Sites on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) (Alavi 2026 v2) rna-splicing-20261011-alavi2026-protocol-multigene Aggregation: Not reported Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026, version 2) · Table IV, row 'ALPHAGENOME SPLICE-SITES', column 'PPV' (PDF page 9 of 12)
Configuration: AlphaGenome Splice-Sites (Alavi 2026 v2)	Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)	60 (78.9%) Recall percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AlphaGenome Splice-Sites on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) (Alavi 2026 v2) rna-splicing-20261011-alavi2026-protocol-multigene Aggregation: Not reported Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026, version 2) · Table IV, row 'ALPHAGENOME SPLICE-SITES', column 'Sensitivity' (PDF page 9 of 12)
Configuration: AlphaGenome Splice-Sites (Alavi 2026 v2)	Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)	107 (100%) Specificity percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AlphaGenome Splice-Sites on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) (Alavi 2026 v2) rna-splicing-20261011-alavi2026-protocol-multigene Aggregation: Not reported Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026, version 2) · Table IV, row 'ALPHAGENOME SPLICE-SITES', column 'Specificity' (PDF page 9 of 12)
Configuration: AlphaGenome Splice-Sites (Alavi 2026 v2)	Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)	0 (0.0 %) False positive rate (type I error: false positives as a share of the benign set) percent · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AlphaGenome Splice-Sites on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) (Alavi 2026 v2) rna-splicing-20261011-alavi2026-protocol-multigene Aggregation: Not reported Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026, version 2) · Table IV, row 'ALPHAGENOME SPLICE-SITES', column 'Type I error' (PDF page 9 of 12)
Configuration: AlphaGenome Splice-Sites (Alavi 2026 v2)	Protocol: Spliceogenic versus benign classification on an independent 65-gene set with OPA1-derived thresholds (Alavi Table IV) Dataset: Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes)	16 (21.1%) Proportion (type II error: false negatives as a share of the splicing set (false-negative rate)) percent · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AlphaGenome Splice-Sites on Multi-gene spliceogenic test set (76 spliceogenic, 107 benign, 65 genes) (Alavi 2026 v2) rna-splicing-20261011-alavi2026-protocol-multigene Aggregation: Not reported Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026, version 2) · Table IV, row 'ALPHAGENOME SPLICE-SITES', column 'Type II error' (PDF page 9 of 12)
Configuration: AlphaGenome Splice-Sites (Alavi 2026 v2)	Protocol: Splice-defect classification of OPA1 variants with thresholds tuned on the same sets (Alavi Table III, evaluation sets) Dataset: OPA1 LOVD evaluation sets (49 splicing, 79 benign)	96.1% Accuracy percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AlphaGenome Splice-Sites on OPA1 LOVD evaluation sets (49 splicing, 79 benign) (Alavi 2026 v2) rna-splicing-20261011-alavi2026-protocol-opa1-evaluation Aggregation: Not reported Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026, version 2) · Table III, row 'ALPHAGENOME SPLICE-SITES', column 'Accuracy' (PDF page 6 of 12)
Configuration: AlphaGenome Splice-Sites (Alavi 2026 v2)	Protocol: Splice-defect classification of OPA1 variants with thresholds tuned on the same sets (Alavi Table III, evaluation sets) Dataset: OPA1 LOVD evaluation sets (49 splicing, 79 benign)	95.8% Precision percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AlphaGenome Splice-Sites on OPA1 LOVD evaluation sets (49 splicing, 79 benign) (Alavi 2026 v2) rna-splicing-20261011-alavi2026-protocol-opa1-evaluation Aggregation: Not reported Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026, version 2) · Table III, row 'ALPHAGENOME SPLICE-SITES', column 'PPV' (PDF page 6 of 12)
Configuration: AlphaGenome Splice-Sites (Alavi 2026 v2)	Protocol: Splice-defect classification of OPA1 variants with thresholds tuned on the same sets (Alavi Table III, evaluation sets) Dataset: OPA1 LOVD evaluation sets (49 splicing, 79 benign)	46 (93.9%) Recall percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AlphaGenome Splice-Sites on OPA1 LOVD evaluation sets (49 splicing, 79 benign) (Alavi 2026 v2) rna-splicing-20261011-alavi2026-protocol-opa1-evaluation Aggregation: Not reported Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026, version 2) · Table III, row 'ALPHAGENOME SPLICE-SITES', column 'Sensitivity' (PDF page 6 of 12)
Configuration: AlphaGenome Splice-Sites (Alavi 2026 v2)	Protocol: Splice-defect classification of OPA1 variants with thresholds tuned on the same sets (Alavi Table III, evaluation sets) Dataset: OPA1 LOVD evaluation sets (49 splicing, 79 benign)	77 (97.5%) Specificity percent · higher Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AlphaGenome Splice-Sites on OPA1 LOVD evaluation sets (49 splicing, 79 benign) (Alavi 2026 v2) rna-splicing-20261011-alavi2026-protocol-opa1-evaluation Aggregation: Not reported Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026, version 2) · Table III, row 'ALPHAGENOME SPLICE-SITES', column 'Specificity' (PDF page 6 of 12)
Configuration: AlphaGenome Splice-Sites (Alavi 2026 v2)	Protocol: Splice-defect classification of OPA1 variants with thresholds tuned on the same sets (Alavi Table III, evaluation sets) Dataset: OPA1 LOVD evaluation sets (49 splicing, 79 benign)	2 (2.5%) False positive rate (type I error: false positives as a share of the benign set) percent · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AlphaGenome Splice-Sites on OPA1 LOVD evaluation sets (49 splicing, 79 benign) (Alavi 2026 v2) rna-splicing-20261011-alavi2026-protocol-opa1-evaluation Aggregation: Not reported Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026, version 2) · Table III, row 'ALPHAGENOME SPLICE-SITES', column 'Type I error' (PDF page 6 of 12)
Configuration: AlphaGenome Splice-Sites (Alavi 2026 v2)	Protocol: Splice-defect classification of OPA1 variants with thresholds tuned on the same sets (Alavi Table III, evaluation sets) Dataset: OPA1 LOVD evaluation sets (49 splicing, 79 benign)	3 (6.1%) Proportion (type II error: false negatives as a share of the splicing set (false-negative rate)) percent · lower Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AlphaGenome Splice-Sites on OPA1 LOVD evaluation sets (49 splicing, 79 benign) (Alavi 2026 v2) rna-splicing-20261011-alavi2026-protocol-opa1-evaluation Aggregation: Not reported Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026, version 2) · Table III, row 'ALPHAGENOME SPLICE-SITES', column 'Type II error' (PDF page 6 of 12)
Configuration: AlphaGenome Splice-Sites (Alavi 2026 v2)	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)	74 (24.2%) Proportion (share of 306 further OPA1 pathogenic substitutions called splice-altering) percent · unknown Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AlphaGenome Splice-Sites on OPA1 extended LOVD corpus (306 pathogenic substitutions, 69 VUS) (Alavi 2026 v2) rna-splicing-20261011-alavi2026-protocol-opa1-extended-positive-calls Aggregation: Not reported Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026, version 2) · Table III, row 'ALPHAGENOME SPLICE-SITES', column 'Positive mutations' (PDF page 6 of 12)
Configuration: AlphaGenome Splice-Sites (Alavi 2026 v2)	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)	3 (4.3%) Proportion (share of 69 OPA1 VUS substitutions called splice-altering) percent · unknown Uncertainty: Not reported by the source Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source AlphaGenome Splice-Sites on OPA1 extended LOVD corpus (306 pathogenic substitutions, 69 VUS) (Alavi 2026 v2) rna-splicing-20261011-alavi2026-protocol-opa1-extended-positive-calls Aggregation: Not reported Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026, version 2) · Table III, row 'ALPHAGENOME SPLICE-SITES', column 'Positive VUS' (PDF page 6 of 12)

Source checking is not independent reproduction. Release 2026-11-02-a7f03c9e55a5.

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 2026-11-02-a7f03c9e55a5
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 2026-11-02-a7f03c9e55a5 · Record review: source checked

2 source records and release history

Probing Genomic Foundation Models with Splice-Variant Perturbations (Alavi, bioRxiv 2026, version 2) · Original source · bioRxiv preprint version 2, posted 2026-10-31; full-text PDF (12 pages)
Alavi 2026 AlphaGenome scoring scripts at commit 2a3875de (marcel-2c8/splicing-model-eval-2026) · Original source · marcel-2c8/splicing-model-eval-2026 commit 2a3875de6635d3c9b51c71c8018d23df0df98d37 (2026-10-31)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: rna-splicing-20261101-alavi2026-v2-config-alphagenome-splice-sites

areas: dna-genomes
contexts: clinical_research
method types: supervised_machine_learning
reported name: ALPHAGENOME SPLICE-SITES
foundation model eligible: false
version: Google Cloud API (research access), version not printed; scripts at https://github.com/marcel-2c8/splicing-model-eval-2026 commit 2a3875de
parameters: Custom predict_variant routine on the SPLICE_SITES output over a 1,048,576-bp interval: largest loss and gain in splice-site probability per track within ±500 bp of the variant on four strand-specific donor and acceptor tracks; maximum absolute difference across tracks; threshold >= 0.32
access reuse: Google DeepMind Research Access program API
source locator: Methods D 'AlphaGenome'; Tables III and IV row label

Related records

Suggest a correction