Configuration

SpliceAI (Drost et al.)

SpliceAI precomputed scores as used by Drost et al.

Overview

SpliceAI precomputed scores as used by Drost et al.

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

Evaluations and results

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

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: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, CAGI6 Splicing VUS subset (Drost et al. Data S1) Dataset: CAGI6 Splicing VUS variants as scored by Drost et al.	0.956 auprc fraction · 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 56 CAGI6 Splicing VUS variants rna-splicing-20261009-protocol-drost2025-cagi6 Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S3 'Stratified datasets', Dataset 'CAGI6', cell I9; row SpliceAI, column AUPRC
Configuration: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, CAGI6 Splicing VUS subset (Drost et al. Data S1) Dataset: CAGI6 Splicing VUS variants as scored by Drost et al.	0.909 auroc fraction · 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 56 CAGI6 Splicing VUS variants rna-splicing-20261009-protocol-drost2025-cagi6 Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S3 'Stratified datasets', Dataset 'CAGI6', cell H9; row SpliceAI, column AUROC
Configuration: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, CAGI6 Splicing VUS subset (Drost et al. Data S1) Dataset: CAGI6 Splicing VUS variants as scored by Drost et al.	0.889 f1-score fraction · 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 56 CAGI6 Splicing VUS variants rna-splicing-20261009-protocol-drost2025-cagi6 Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S4 'CAGI6 dataset', cell F22; row SpliceAI, column F1
Configuration: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, CAGI6 Splicing VUS subset (Drost et al. Data S1) Dataset: CAGI6 Splicing VUS variants as scored by Drost et al.	0.762 negative-predictive-value fraction · 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 56 CAGI6 Splicing VUS variants rna-splicing-20261009-protocol-drost2025-cagi6 Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S4 'CAGI6 dataset', cell H22; row SpliceAI, column Neg Pred Value
Configuration: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, CAGI6 Splicing VUS subset (Drost et al. Data S1) Dataset: CAGI6 Splicing VUS variants as scored by Drost et al.	0.914 precision fraction · 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 56 CAGI6 Splicing VUS variants rna-splicing-20261009-protocol-drost2025-cagi6 Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S4 'CAGI6 dataset', cell G22; row SpliceAI, column Pos Pred Value
Configuration: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, CAGI6 Splicing VUS subset (Drost et al. Data S1) Dataset: CAGI6 Splicing VUS variants as scored by Drost et al.	0.914 precision fraction · 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 56 CAGI6 Splicing VUS variants rna-splicing-20261009-protocol-drost2025-cagi6 Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S4 'CAGI6 dataset', cell E22; row SpliceAI, column Precision
Configuration: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, CAGI6 Splicing VUS subset (Drost et al. Data S1) Dataset: CAGI6 Splicing VUS variants as scored by Drost et al.	0.865 recall fraction · 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 56 CAGI6 Splicing VUS variants rna-splicing-20261009-protocol-drost2025-cagi6 Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S4 'CAGI6 dataset', cell C22; row SpliceAI, column Sensitivity (Recall)
Configuration: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, CAGI6 Splicing VUS subset (Drost et al. Data S1) Dataset: CAGI6 Splicing VUS variants as scored by Drost et al.	0.842 specificity fraction · 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 56 CAGI6 Splicing VUS variants rna-splicing-20261009-protocol-drost2025-cagi6 Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S4 'CAGI6 dataset', cell D22; row SpliceAI, column Specificity
Configuration: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, in-house diagnostic cohort (Drost et al. Data S1) Dataset: Drost et al. in-house RNA-tested diagnostic variants, scorable subset	0.942 auprc fraction · 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 in-house scorable variants (count not printed) rna-splicing-20261009-protocol-drost2025-inhouse Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S3 'Stratified datasets', Dataset 'In House', cell I14; row SpliceAI, column AUPRC
Configuration: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, in-house diagnostic cohort (Drost et al. Data S1) Dataset: Drost et al. in-house RNA-tested diagnostic variants, scorable subset	0.893 auroc fraction · 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 in-house scorable variants (count not printed) rna-splicing-20261009-protocol-drost2025-inhouse Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S3 'Stratified datasets', Dataset 'In House', cell H14; row SpliceAI, column AUROC
Configuration: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, in-house diagnostic cohort (Drost et al. Data S1) Dataset: Drost et al. in-house RNA-tested diagnostic variants, scorable subset	0.858 f1-score fraction · 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 in-house scorable variants (count not printed) rna-splicing-20261009-protocol-drost2025-inhouse Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S4 'In House dataset', cell F35; row SpliceAI, column F1
Configuration: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, in-house diagnostic cohort (Drost et al. Data S1) Dataset: Drost et al. in-house RNA-tested diagnostic variants, scorable subset	0.769 negative-predictive-value fraction · 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 in-house scorable variants (count not printed) rna-splicing-20261009-protocol-drost2025-inhouse Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S4 'In House dataset', cell H35; row SpliceAI, column Neg Pred Value
Configuration: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, in-house diagnostic cohort (Drost et al. Data S1) Dataset: Drost et al. in-house RNA-tested diagnostic variants, scorable subset	0.844 precision fraction · 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 in-house scorable variants (count not printed) rna-splicing-20261009-protocol-drost2025-inhouse Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S4 'In House dataset', cell G35; row SpliceAI, column Pos Pred Value
Configuration: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, in-house diagnostic cohort (Drost et al. Data S1) Dataset: Drost et al. in-house RNA-tested diagnostic variants, scorable subset	0.844 precision fraction · 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 in-house scorable variants (count not printed) rna-splicing-20261009-protocol-drost2025-inhouse Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S4 'In House dataset', cell E35; row SpliceAI, column Precision
Configuration: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, in-house diagnostic cohort (Drost et al. Data S1) Dataset: Drost et al. in-house RNA-tested diagnostic variants, scorable subset	0.873 recall fraction · 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 in-house scorable variants (count not printed) rna-splicing-20261009-protocol-drost2025-inhouse Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S4 'In House dataset', cell C35; row SpliceAI, column Sensitivity (Recall)
Configuration: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, in-house diagnostic cohort (Drost et al. Data S1) Dataset: Drost et al. in-house RNA-tested diagnostic variants, scorable subset	0.725 specificity fraction · 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 in-house scorable variants (count not printed) rna-splicing-20261009-protocol-drost2025-inhouse Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S4 'In House dataset', cell D35; row SpliceAI, column Specificity
Configuration: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, all 243 scorable variants (Drost et al. Data S1) Dataset: Drost et al. RNA-tested clinical variants plus CAGI6 Splicing VUS, 243 scorable	0.943 auprc fraction · 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 243 scorable variants (in-house plus CAGI6) rna-splicing-20261009-protocol-drost2025-merged-243 Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S3 'Entire Dataset', cell D12; row SpliceAI, column AUPRC
Configuration: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, all 243 scorable variants (Drost et al. Data S1) Dataset: Drost et al. RNA-tested clinical variants plus CAGI6 Splicing VUS, 243 scorable	0.895 auroc fraction · 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 243 scorable variants (in-house plus CAGI6) rna-splicing-20261009-protocol-drost2025-merged-243 Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S3 'Entire Dataset', cell C12; row SpliceAI, column AUROC
Configuration: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, all 243 scorable variants (Drost et al. Data S1) Dataset: Drost et al. RNA-tested clinical variants plus CAGI6 Splicing VUS, 243 scorable	0.865 f1-score fraction · 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 243 scorable variants (in-house plus CAGI6) rna-splicing-20261009-protocol-drost2025-merged-243 Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S4 'Entire Dataset', cell F9; row SpliceAI, column F1
Configuration: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, all 243 scorable variants (Drost et al. Data S1) Dataset: Drost et al. RNA-tested clinical variants plus CAGI6 Splicing VUS, 243 scorable	0.767 negative-predictive-value fraction · 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 243 scorable variants (in-house plus CAGI6) rna-splicing-20261009-protocol-drost2025-merged-243 Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S4 'Entire Dataset', cell H9; row SpliceAI, column Neg Pred Value
Configuration: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, all 243 scorable variants (Drost et al. Data S1) Dataset: Drost et al. RNA-tested clinical variants plus CAGI6 Splicing VUS, 243 scorable	0.86 precision fraction · 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 243 scorable variants (in-house plus CAGI6) rna-splicing-20261009-protocol-drost2025-merged-243 Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S4 'Entire Dataset', cell G9; row SpliceAI, column Pos Pred Value
Configuration: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, all 243 scorable variants (Drost et al. Data S1) Dataset: Drost et al. RNA-tested clinical variants plus CAGI6 Splicing VUS, 243 scorable	0.86 precision fraction · 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 243 scorable variants (in-house plus CAGI6) rna-splicing-20261009-protocol-drost2025-merged-243 Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S4 'Entire Dataset', cell E9; row SpliceAI, column Precision
Configuration: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, all 243 scorable variants (Drost et al. Data S1) Dataset: Drost et al. RNA-tested clinical variants plus CAGI6 Splicing VUS, 243 scorable	0.871 recall fraction · 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 243 scorable variants (in-house plus CAGI6) rna-splicing-20261009-protocol-drost2025-merged-243 Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S4 'Entire Dataset', cell C9; row SpliceAI, column Sensitivity (Recall)
Configuration: SpliceAI (Drost et al.)	Protocol: Splice-effect prediction against patient-RNA or exon-trapping results, all 243 scorable variants (Drost et al. Data S1) Dataset: Drost et al. RNA-tested clinical variants plus CAGI6 Splicing VUS, 243 scorable	0.75 specificity fraction · 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 243 scorable variants (in-house plus CAGI6) rna-splicing-20261009-protocol-drost2025-merged-243 Aggregation: Not reported Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools; Drost et al. 2025, Data S1 (Tables S1-S6) · Data S1 Table S4 'Entire Dataset', cell D9; row SpliceAI, column Specificity

Source checking is not independent reproduction. Release 2026-10-09-ba02f2f4a36e.

Use this model

How it works, versions and access

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 2026-10-09-ba02f2f4a36e
Property and statement	Original source and location	Review 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 2026-10-09-ba02f2f4a36e · Record review: source checked

2 source records and release history

Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools · Original source · HGG Advances 7(1):100521, published online 2025-09-22; PMC12547740 full-text XML
Drost et al. 2025, Data S1 (Tables S1-S6) · Original source · mmc2.xlsx (Data S1. Tables S1-S6) inside the Europe PMC supplementaryFiles zip for PMC12547740

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: rna-splicing-20261009-config-drost2025-spliceai

areas: dna-genomes
contexts: clinical_research
method types: supervised_machine_learning
reported name: SpliceAI (Drost et al.)
foundation model eligible: false
missing metadata: version: reason: unreported; note: SpliceAI release not printed; precomputed scores were taken from WGSA version 0.95, with missing annotations filled from the SpliceAI Lookup web page.
parameters: Binary predictions at the literature threshold 0.12
source locator: Methods 'In silico splice predictions'; Results paragraph 3

Related records

configuration of: SpliceAI
system: SpliceAI on 56 CAGI6 Splicing VUS variants
system: SpliceAI on in-house scorable variants (count not printed)
system: SpliceAI on 243 scorable variants (in-house plus CAGI6)

Suggest a correction