Result

0.909 auroc

drost2025-cagi6-spliceai-auroc auroc

Tested 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.
Procedure: rna-splicing-20261009-protocol-drost2025-cagi6
Evaluation: SpliceAI on 56 CAGI6 Splicing VUS variants
Coverage: Not reported scored / Not reported eligible
Uncertainty: Not reported by the source
Evidence: Independent external evaluation · source checkedRoutine 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

A source-checked result verifies the numerical transcription, not every model or protocol detail. Evaluation metadata: source checked. Source checked does not mean independently reproduced.

Reproduction

Split: No training split
Adaptation: None; pretrained predictors with literature thresholds
Scoring implementation: R: plotROC 2.3.1 (ROC), yardstick 1.2.0 (PR), caret 6.0.94 (binary statistics)

No execution recipe has been verified for this exact configuration and evaluation. A benchmark's general instructions may use different inputs, splits or model settings.

Reproducing this published result requires matching its model configuration, data, split and scorer. Source checking or a successful smoke test does not establish score reproduction.

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.

2 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
Reported result 0.90896159317212 Individual claims	Routine RNA-based analysis of potential splicing variants facilitates genomic diagnostics and reveals limitations of in silico prediction tools Original source ↗ Data S1 Table S3 'Stratified datasets', Dataset 'CAGI6', cell H9; row SpliceAI, column AUROC Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: HGG Advances 7(1):100521, published online 2025-09-22; PMC12547740 full-text XML Retrieved: 2026-10-09T20:30:41Z	source checked ["source-hash-verification","deterministic-table-parse","independent-cell-check"] · 2026-10-09 independent paper Audit details Deterministic parse of the pinned XLSX cell XML (extract/extract_rna_splicing.py) with sheet title, block titles, column headers and row labels asserted; printed_value is the shortest round-trip decimal of the stored double, raw_xml_value keeps the stored text. Pending independent review. Independent review 2026-10-09: value and identity match the source. Field: `attributes.printed_value` Source artifact SHA-256: `2a2e970526e4348d505d26356b830d96da9e32688c4de84841ac8137b62d5d32` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact Extraction artifact SHA-256: `a3a69202b8f0d9ecb7fa22a16991d5e4d583b5ae72fd598206ea5c2b4c5c14ca` Extraction artifact
Reported result 0.90896159317212 Individual claims	Drost et al. 2025, Data S1 (Tables S1-S6) Original source ↗ Data S1 Table S3 'Stratified datasets', Dataset 'CAGI6', cell H9; row SpliceAI, column AUROC Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: mmc2.xlsx (Data S1. Tables S1-S6) inside the Europe PMC supplementaryFiles zip for PMC12547740 Retrieved: 2026-10-09T20:31:37Z	source checked ["source-hash-verification","deterministic-table-parse","independent-cell-check"] · 2026-10-09 independent paper Audit details Deterministic parse of the pinned XLSX cell XML (extract/extract_rna_splicing.py) with sheet title, block titles, column headers and row labels asserted; printed_value is the shortest round-trip decimal of the stored double, raw_xml_value keeps the stored text. Pending independent review. Independent review 2026-10-09: value and identity match the source. Field: `attributes.printed_value` Source artifact SHA-256: `a3a69202b8f0d9ecb7fa22a16991d5e4d583b5ae72fd598206ea5c2b4c5c14ca` Hash scope: SHA-256 of mmc2.xlsx as extracted from the supplementaryFiles zip (zip SHA-256 1c89a7ebc0bf686c6087d0fee86ba6f364a6d754d5bc7eb9c446b7db017f1ebc; the zip is re-built by Europe PMC on each request, so only the member hash is stable). Inspected artifact Extraction artifact SHA-256: `a3a69202b8f0d9ecb7fa22a16991d5e4d583b5ae72fd598206ea5c2b4c5c14ca` Extraction artifact

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-result-drost2025-cagi6-spliceai-auroc

metric: auroc
metric direction: higher
unit: fraction
printed value: 0.90896159317212
numeric value: 0.90896159317212
source locator: Data S1 Table S3 'Stratified datasets', Dataset 'CAGI6', cell H9; row SpliceAI, column AUROC
missing metadata: uncertainty: reason: unreported
review: method: source-hash-verification; deterministic-table-parse; independent-cell-check; reviewer: claude; reviewer note: Separate Claude review agent, independent of the extractor; no human review claimed; date: 2026-10-09; artifact sha256: a3a69202b8f0d9ecb7fa22a16991d5e4d583b5ae72fd598206ea5c2b4c5c14ca; retrieval url: https://www.ebi.ac.uk/europepmc/webservices/rest/PMC12547740/supplementaryFiles; method note: Re-downloaded the artifact and matched its SHA-256. Read Drost Data S1 Table S3 with a separate reader written for this review (the extractor's scripts were not run). Checked printed and numeric value, locator, metric, unit and direction, and the evaluation's configuration, protocol and dataset.; note: Deterministic parse of the pinned XLSX cell XML (extract/extract_rna_splicing.py) with sheet title, block titles, column headers and row labels asserted; printed_value is the shortest round-trip decimal of the stored double, raw_xml_value keeps the stored text. Pending independent review. Independent review 2026-10-09: value and identity match the source.
metric qualifier: continuous score
raw xml value: 0.90896159317212

Related records

evaluation: SpliceAI on 56 CAGI6 Splicing VUS variants

Suggest a correction