Evidence claim

Relevance of Cryptic splice site activation by rare GT/AG-creating variants in Genomics England blood RNA-seq (SpliceAI2 paper, auPRC) to use case use-case-patient-rna-splicing-validation

Use case: Select a patient-RNA splicing-variant validation workflow
Assessed by: Cryptic splice site activation by rare GT/AG-creating variants in Genomics England blood RNA-seq (SpliceAI2 paper, auPRC)
Relevance: Proxy evidence
Endpoint: auPRC for separating RNA-seq-confirmed cryptic splice gains from null rare GT/AG-creating variants in 5,435 Genomics England rare-disease participants with WGS and blood RNA-seq, for SpliceAI, Pangolin, AlphaGenome and SpliceAI2 on the same variants

Closest evidence in the paper to this use case: DNA-based predictors scored against splicing observed in rare-disease participants' own RNA-seq, all four tools on the same variants. Proxy, as for Drost et al. 2025: the systems take DNA variants rather than patient RNA, the endpoint is cryptic-site activation by GT/AG-creating variants only, and the authors developed SpliceAI2 and built the benchmark.

5 reviewed evaluations

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.

19 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
Citation locations 3 values source id rna-splicing-20261013-spliceai2-source-article locator Fig. 4g source id rna-splicing-20261013-spliceai2-source-article locator Main 'Contribution to rare genetic disease' paragraph 4 source id rna-splicing-20261013-spliceai2-source-article locator Methods 'Evaluation of competing methods' and 'Variant effect benchmarks' Context-only references	A unified framework for quantitative splicing and transcript prediction (Jaganathan et al., bioRxiv 2026) Original source ↗ rna-splicing-20261013-spliceai2-source-article: Fig. 4g; rna-splicing-20261013-spliceai2-source-article: Main 'Contribution to rare genetic disease' paragraph 4; rna-splicing-20261013-spliceai2-source-article: Methods 'Evaluation of competing methods' and 'Variant effect benchmarks' Version: bioRxiv preprint version 1, posted 2026-10-11; full-text PDF (57 pages) Retrieved: 2026-10-13T12:40:34Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.citation_locators` Source artifact SHA-256: `f8f3db2c3943d4827b670bc2e962e0cec8fbe96e0b1acf9d4a9b9f0c7a78c06b` Hash scope: SHA-256 of one retrieval of the bioRxiv PDF. bioRxiv stamps the PDF when serving it (XMP ModifyDate, MetadataDate, DocumentID, InstanceID, Info ModDate and the second trailer ID), so later retrievals differ. A reviewer retrieval on 2026-10-13 of the same length (2,679,664 bytes) had SHA-256 407f5884427dda0226e0ce1f022e4479d3ff2b243da18bcc691eb345b0e04a6a and ModDate D:20261013063115-07'00'; its bytes differ only in those fields and its pdftotext text layer is identical to the pinned copy. Inspected artifact
Comparison group spliceai2-2026-gel Context-only references	A unified framework for quantitative splicing and transcript prediction (Jaganathan et al., bioRxiv 2026) Original source ↗ rna-splicing-20261013-spliceai2-source-article: Fig. 4g; rna-splicing-20261013-spliceai2-source-article: Main 'Contribution to rare genetic disease' paragraph 4; rna-splicing-20261013-spliceai2-source-article: Methods 'Evaluation of competing methods' and 'Variant effect benchmarks' Version: bioRxiv preprint version 1, posted 2026-10-11; full-text PDF (57 pages) Retrieved: 2026-10-13T12:40:34Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.comparison_group` Source artifact SHA-256: `f8f3db2c3943d4827b670bc2e962e0cec8fbe96e0b1acf9d4a9b9f0c7a78c06b` Hash scope: SHA-256 of one retrieval of the bioRxiv PDF. bioRxiv stamps the PDF when serving it (XMP ModifyDate, MetadataDate, DocumentID, InstanceID, Info ModDate and the second trailer ID), so later retrievals differ. A reviewer retrieval on 2026-10-13 of the same length (2,679,664 bytes) had SHA-256 407f5884427dda0226e0ce1f022e4479d3ff2b243da18bcc691eb345b0e04a6a and ModDate D:20261013063115-07'00'; its bytes differ only in those fields and its pdftotext text layer is identical to the pinned copy. Inspected artifact
Comparison title DNA splice predictors against cryptic splicing in Genomics England rare-disease blood RNA-seq (SpliceAI2 paper, developer-reported) Context-only references	A unified framework for quantitative splicing and transcript prediction (Jaganathan et al., bioRxiv 2026) Original source ↗ rna-splicing-20261013-spliceai2-source-article: Fig. 4g; rna-splicing-20261013-spliceai2-source-article: Main 'Contribution to rare genetic disease' paragraph 4; rna-splicing-20261013-spliceai2-source-article: Methods 'Evaluation of competing methods' and 'Variant effect benchmarks' Version: bioRxiv preprint version 1, posted 2026-10-11; full-text PDF (57 pages) Retrieved: 2026-10-13T12:40:34Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.comparison_title` Source artifact SHA-256: `f8f3db2c3943d4827b670bc2e962e0cec8fbe96e0b1acf9d4a9b9f0c7a78c06b` Hash scope: SHA-256 of one retrieval of the bioRxiv PDF. bioRxiv stamps the PDF when serving it (XMP ModifyDate, MetadataDate, DocumentID, InstanceID, Info ModDate and the second trailer ID), so later retrievals differ. A reviewer retrieval on 2026-10-13 of the same length (2,679,664 bytes) had SHA-256 407f5884427dda0226e0ce1f022e4479d3ff2b243da18bcc691eb345b0e04a6a and ModDate D:20261013063115-07'00'; its bytes differ only in those fields and its pdftotext text layer is identical to the pinned copy. Inspected artifact
Constraints 3 values Inspect every linked evaluation's source locator and configuration before citing a result. Do not combine this mapping's evaluations with any other protocol's results; truth sets, inputs and metrics differ between sources. Compare configurations only within this protocol; the AlphaGenome raw splice site score (0.45) is a separate configuration reported in the Methods, not the paper's chosen AlphaGenome score (0.36). Context-only references	A unified framework for quantitative splicing and transcript prediction (Jaganathan et al., bioRxiv 2026) Original source ↗ rna-splicing-20261013-spliceai2-source-article: Fig. 4g; rna-splicing-20261013-spliceai2-source-article: Main 'Contribution to rare genetic disease' paragraph 4; rna-splicing-20261013-spliceai2-source-article: Methods 'Evaluation of competing methods' and 'Variant effect benchmarks' Version: bioRxiv preprint version 1, posted 2026-10-11; full-text PDF (57 pages) Retrieved: 2026-10-13T12:40:34Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.constraints` Source artifact SHA-256: `f8f3db2c3943d4827b670bc2e962e0cec8fbe96e0b1acf9d4a9b9f0c7a78c06b` Hash scope: SHA-256 of one retrieval of the bioRxiv PDF. bioRxiv stamps the PDF when serving it (XMP ModifyDate, MetadataDate, DocumentID, InstanceID, Info ModDate and the second trailer ID), so later retrievals differ. A reviewer retrieval on 2026-10-13 of the same length (2,679,664 bytes) had SHA-256 407f5884427dda0226e0ce1f022e4479d3ff2b243da18bcc691eb345b0e04a6a and ModDate D:20261013063115-07'00'; its bytes differ only in those fields and its pdftotext text layer is identical to the pinned copy. Inspected artifact
Endpoint auPRC for separating RNA-seq-confirmed cryptic splice gains from null rare GT/AG-creating variants in 5,435 Genomics England rare-disease participants with WGS and blood RNA-seq, for SpliceAI, Pangolin, AlphaGenome and SpliceAI2 on the same variants Context-only references	A unified framework for quantitative splicing and transcript prediction (Jaganathan et al., bioRxiv 2026) Original source ↗ rna-splicing-20261013-spliceai2-source-article: Fig. 4g; rna-splicing-20261013-spliceai2-source-article: Main 'Contribution to rare genetic disease' paragraph 4; rna-splicing-20261013-spliceai2-source-article: Methods 'Evaluation of competing methods' and 'Variant effect benchmarks' Version: bioRxiv preprint version 1, posted 2026-10-11; full-text PDF (57 pages) Retrieved: 2026-10-13T12:40:34Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.endpoint` Source artifact SHA-256: `f8f3db2c3943d4827b670bc2e962e0cec8fbe96e0b1acf9d4a9b9f0c7a78c06b` Hash scope: SHA-256 of one retrieval of the bioRxiv PDF. bioRxiv stamps the PDF when serving it (XMP ModifyDate, MetadataDate, DocumentID, InstanceID, Info ModDate and the second trailer ID), so later retrievals differ. A reviewer retrieval on 2026-10-13 of the same length (2,679,664 bytes) had SHA-256 407f5884427dda0226e0ce1f022e4479d3ff2b243da18bcc691eb345b0e04a6a and ModDate D:20261013063115-07'00'; its bytes differ only in those fields and its pdftotext text layer is identical to the pinned copy. Inspected artifact
Claimed field links:assessed_by:rna-splicing-20261013-spliceai2-protocol-gel-gtag-detection Context-only references	A unified framework for quantitative splicing and transcript prediction (Jaganathan et al., bioRxiv 2026) Original source ↗ rna-splicing-20261013-spliceai2-source-article: Fig. 4g; rna-splicing-20261013-spliceai2-source-article: Main 'Contribution to rare genetic disease' paragraph 4; rna-splicing-20261013-spliceai2-source-article: Methods 'Evaluation of competing methods' and 'Variant effect benchmarks' Version: bioRxiv preprint version 1, posted 2026-10-11; full-text PDF (57 pages) Retrieved: 2026-10-13T12:40:34Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.field` Source artifact SHA-256: `f8f3db2c3943d4827b670bc2e962e0cec8fbe96e0b1acf9d4a9b9f0c7a78c06b` Hash scope: SHA-256 of one retrieval of the bioRxiv PDF. bioRxiv stamps the PDF when serving it (XMP ModifyDate, MetadataDate, DocumentID, InstanceID, Info ModDate and the second trailer ID), so later retrievals differ. A reviewer retrieval on 2026-10-13 of the same length (2,679,664 bytes) had SHA-256 407f5884427dda0226e0ce1f022e4479d3ff2b243da18bcc691eb345b0e04a6a and ModDate D:20261013063115-07'00'; its bytes differ only in those fields and its pdftotext text layer is identical to the pinned copy. Inspected artifact
Headline metric auprc Context-only references	A unified framework for quantitative splicing and transcript prediction (Jaganathan et al., bioRxiv 2026) Original source ↗ rna-splicing-20261013-spliceai2-source-article: Fig. 4g; rna-splicing-20261013-spliceai2-source-article: Main 'Contribution to rare genetic disease' paragraph 4; rna-splicing-20261013-spliceai2-source-article: Methods 'Evaluation of competing methods' and 'Variant effect benchmarks' Version: bioRxiv preprint version 1, posted 2026-10-11; full-text PDF (57 pages) Retrieved: 2026-10-13T12:40:34Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.headline_metric` Source artifact SHA-256: `f8f3db2c3943d4827b670bc2e962e0cec8fbe96e0b1acf9d4a9b9f0c7a78c06b` Hash scope: SHA-256 of one retrieval of the bioRxiv PDF. bioRxiv stamps the PDF when serving it (XMP ModifyDate, MetadataDate, DocumentID, InstanceID, Info ModDate and the second trailer ID), so later retrievals differ. A reviewer retrieval on 2026-10-13 of the same length (2,679,664 bytes) had SHA-256 407f5884427dda0226e0ce1f022e4479d3ff2b243da18bcc691eb345b0e04a6a and ModDate D:20261013063115-07'00'; its bytes differ only in those fields and its pdftotext text layer is identical to the pinned copy. Inspected artifact
Limitations 7 values Developer-reported; the SpliceAI2 authors built the labels and ran SpliceAI, Pangolin and SpliceAI2; AlphaGenome was run by Oxford co-authors. Training overlap: SpliceAI2 was trained on all human genes outside chromosomes 21 and 22; benchmark variants are genome-wide. Blood RNA-seq only, so splicing in genes not expressed in blood is unobserved; GT/AG-creating variants only; the paper does not say whether essential splice variants were excluded from this benchmark. The use case's baseline (FRASER and OUTRIDER on patient RNA, with a legacy splice-site vote such as MaxEntScan on DNA) is not evaluated in this paper; no rule-based motif scorer is compared (see issue #121). Controlled-access data (Genomics England project 754); benchmark variant lists are not released, so the comparison cannot be rerun outside the Research Environment. Single auPRC per model; no uncertainty, strata or thresholds printed. Preprint (bioRxiv v1), not peer reviewed. Context-only references	A unified framework for quantitative splicing and transcript prediction (Jaganathan et al., bioRxiv 2026) Original source ↗ rna-splicing-20261013-spliceai2-source-article: Fig. 4g; rna-splicing-20261013-spliceai2-source-article: Main 'Contribution to rare genetic disease' paragraph 4; rna-splicing-20261013-spliceai2-source-article: Methods 'Evaluation of competing methods' and 'Variant effect benchmarks' Version: bioRxiv preprint version 1, posted 2026-10-11; full-text PDF (57 pages) Retrieved: 2026-10-13T12:40:34Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.limitations` Source artifact SHA-256: `f8f3db2c3943d4827b670bc2e962e0cec8fbe96e0b1acf9d4a9b9f0c7a78c06b` Hash scope: SHA-256 of one retrieval of the bioRxiv PDF. bioRxiv stamps the PDF when serving it (XMP ModifyDate, MetadataDate, DocumentID, InstanceID, Info ModDate and the second trailer ID), so later retrievals differ. A reviewer retrieval on 2026-10-13 of the same length (2,679,664 bytes) had SHA-256 407f5884427dda0226e0ce1f022e4479d3ff2b243da18bcc691eb345b0e04a6a and ModDate D:20261013063115-07'00'; its bytes differ only in those fields and its pdftotext text layer is identical to the pinned copy. Inspected artifact
Pinned records 13 values record id rna-splicing-20261013-spliceai2-eval-gel-gtag-detection-alphagenome-composite-max fields status links attributes.origin attributes.comparison sha256 e58efdf5150e97ebf014a4f0d0c218a87752fe0ecbe3e8d668a2b36bbd5c59bd record id rna-splicing-20261013-spliceai2-eval-gel-gtag-detection-alphagenome-splice-site-max fields status links attributes.origin attributes.comparison sha256 b28e9aded5ea4ad4ab6412fcca12f868b16e406fe1e0b0964e5047c238d7b551 record id rna-splicing-20261013-spliceai2-eval-gel-gtag-detection-pangolin-position-resolved fields status links attributes.origin attributes.comparison sha256 d234e0243e589f54ea0a6ec4732af26e68549712a4f79a151e98ee9a5a3540be record id rna-splicing-20261013-spliceai2-eval-gel-gtag-detection-spliceai-position-resolved fields status links attributes.origin attributes.comparison sha256 45a136877b7e9b535c48aec3cfb95ea58cfb8c87c83567a46907801bce092bb7 record id rna-splicing-20261013-spliceai2-eval-gel-gtag-detection-spliceai2-ensemble fields status links attributes.origin attributes.comparison sha256 578802dc3d65ffd1e2fe220775dd45922e5c424f4995bbf037afe362cc08326a record id rna-splicing-20261013-spliceai2-protocol-gel-gtag-detection fields status name description facets source_ids links attributes sha256 e3b5ab8fb4e1e6711046ac9bccd9b2d6799730e039a342f4064db0f08f1e713d record id rna-splicing-20261013-spliceai2-result-gel-gtag-detection-alphagenome-composite-max-auprc fields status attributes.metric attributes.metric_qualifier attributes.printed_value attributes.numeric_value sha256 a254aed9e733e57d79fb49da6f762ea3669bc5601676695f33e4ed4294b99c19 record id rna-splicing-20261013-spliceai2-result-gel-gtag-detection-alphagenome-splice-site-max-auprc fields status attributes.metric attributes.metric_qualifier attributes.printed_value attributes.numeric_value sha256 e18d63145aabbc3a20444ae3258038c5abfe2fcbeb6998a5d60cdeac89c6e686 record id rna-splicing-20261013-spliceai2-result-gel-gtag-detection-pangolin-position-resolved-auprc fields status attributes.metric attributes.metric_qualifier attributes.printed_value attributes.numeric_value sha256 1c334bbdf20f5e4bbe3b0e0580666ab61ebd8fb2bc329368ac57c0d770cccc3a record id rna-splicing-20261013-spliceai2-result-gel-gtag-detection-spliceai-position-resolved-auprc fields status attributes.metric attributes.metric_qualifier attributes.printed_value attributes.numeric_value sha256 2724caf293a529d790f008ad3a094ca8cb2a2e17454051bc8bb9a1eb06ae3fed record id rna-splicing-20261013-spliceai2-result-gel-gtag-detection-spliceai2-ensemble-auprc fields status attributes.metric attributes.metric_qualifier attributes.printed_value attributes.numeric_value sha256 b100ab826cebb544d8ccb779c6f5edc8963571e5813e555c50c61059e4c6ae17 record id rna-splicing-20261013-spliceai2-source-article fields status attributes.artifact_sha256 sha256 09442cd33f8941b2e764e137cb843ca4a962a185fba4f3d7419d13f1981a5de1 record id use-case-patient-rna-splicing-validation fields status name description facets attributes.question attributes.decision attributes.inputs attributes.output attributes.exclusions attributes.setting attributes.clinical_scope attributes.intended_users sha256 b85cad56e15fbfad66a2e70c3b193ed56c464e5e44b62a19b12f391e409ec897 Context-only references	A unified framework for quantitative splicing and transcript prediction (Jaganathan et al., bioRxiv 2026) Original source ↗ rna-splicing-20261013-spliceai2-source-article: Fig. 4g; rna-splicing-20261013-spliceai2-source-article: Main 'Contribution to rare genetic disease' paragraph 4; rna-splicing-20261013-spliceai2-source-article: Methods 'Evaluation of competing methods' and 'Variant effect benchmarks' Version: bioRxiv preprint version 1, posted 2026-10-11; full-text PDF (57 pages) Retrieved: 2026-10-13T12:40:34Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.pins` Source artifact SHA-256: `f8f3db2c3943d4827b670bc2e962e0cec8fbe96e0b1acf9d4a9b9f0c7a78c06b` Hash scope: SHA-256 of one retrieval of the bioRxiv PDF. bioRxiv stamps the PDF when serving it (XMP ModifyDate, MetadataDate, DocumentID, InstanceID, Info ModDate and the second trailer ID), so later retrievals differ. A reviewer retrieval on 2026-10-13 of the same length (2,679,664 bytes) had SHA-256 407f5884427dda0226e0ce1f022e4479d3ff2b243da18bcc691eb345b0e04a6a and ModDate D:20261013063115-07'00'; its bytes differ only in those fields and its pdftotext text layer is identical to the pinned copy. Inspected artifact
Rationale Closest evidence in the paper to this use case: DNA-based predictors scored against splicing observed in rare-disease participants' own RNA-seq, all four tools on the same variants. Proxy, as for Drost et al. 2025: the systems take DNA variants rather than patient RNA, the endpoint is cryptic-site activation by GT/AG-creating variants only, and the authors developed SpliceAI2 and built the benchmark. Context-only references	A unified framework for quantitative splicing and transcript prediction (Jaganathan et al., bioRxiv 2026) Original source ↗ rna-splicing-20261013-spliceai2-source-article: Fig. 4g; rna-splicing-20261013-spliceai2-source-article: Main 'Contribution to rare genetic disease' paragraph 4; rna-splicing-20261013-spliceai2-source-article: Methods 'Evaluation of competing methods' and 'Variant effect benchmarks' Version: bioRxiv preprint version 1, posted 2026-10-11; full-text PDF (57 pages) Retrieved: 2026-10-13T12:40:34Z	not individually reviewed No individual claim review recorded Audit details Field: `attributes.rationale` Source artifact SHA-256: `f8f3db2c3943d4827b670bc2e962e0cec8fbe96e0b1acf9d4a9b9f0c7a78c06b` Hash scope: SHA-256 of one retrieval of the bioRxiv PDF. bioRxiv stamps the PDF when serving it (XMP ModifyDate, MetadataDate, DocumentID, InstanceID, Info ModDate and the second trailer ID), so later retrievals differ. A reviewer retrieval on 2026-10-13 of the same length (2,679,664 bytes) had SHA-256 407f5884427dda0226e0ce1f022e4479d3ff2b243da18bcc691eb345b0e04a6a and ModDate D:20261013063115-07'00'; its bytes differ only in those fields and its pdftotext text layer is identical to the pinned copy. Inspected artifact

How to read the evidence

Sources and history

Release 2026-10-22-1b7cf027e4f6 · Record review: source checked

1 source record and release history

A unified framework for quantitative splicing and transcript prediction (Jaganathan et al., bioRxiv 2026) · Original source · bioRxiv preprint version 1, posted 2026-10-11; full-text PDF (57 pages)

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: use-case-mapping-rna-splicing-20261013-spliceai2-gel-gtag

field: links:assessed_by:rna-splicing-20261013-spliceai2-protocol-gel-gtag-detection
value: rna-splicing-20261013-spliceai2-protocol-gel-gtag-detection
relevance: proxy
endpoint: auPRC for separating RNA-seq-confirmed cryptic splice gains from null rare GT/AG-creating variants in 5,435 Genomics England rare-disease participants with WGS and blood RNA-seq, for SpliceAI, Pangolin, AlphaGenome and SpliceAI2 on the same variants
rationale: Closest evidence in the paper to this use case: DNA-based predictors scored against splicing observed in rare-disease participants' own RNA-seq, all four tools on the same variants. Proxy, as for Drost et al. 2025: the systems take DNA variants rather than patient RNA, the endpoint is cryptic-site activation by GT/AG-creating variants only, and the authors developed SpliceAI2 and built the benchmark.
constraints: Inspect every linked evaluation's source locator and configuration before citing a result.; Do not combine this mapping's evaluations with any other protocol's results; truth sets, inputs and metrics differ between sources.; Compare configurations only within this protocol; the AlphaGenome raw splice site score (0.45) is a separate configuration reported in the Methods, not the paper's chosen AlphaGenome score (0.36).
limitations: Developer-reported; the SpliceAI2 authors built the labels and ran SpliceAI, Pangolin and SpliceAI2; AlphaGenome was run by Oxford co-authors.; Training overlap: SpliceAI2 was trained on all human genes outside chromosomes 21 and 22; benchmark variants are genome-wide.; Blood RNA-seq only, so splicing in genes not expressed in blood is unobserved; GT/AG-creating variants only; the paper does not say whether essential splice variants were excluded from this benchmark.; The use case's baseline (FRASER and OUTRIDER on patient RNA, with a legacy splice-site vote such as MaxEntScan on DNA) is not evaluated in this paper; no rule-based motif scorer is compared (see issue #121).; Controlled-access data (Genomics England project 754); benchmark variant lists are not released, so the comparison cannot be rerun outside the Research Environment.; Single auPRC per model; no uncertainty, strata or thresholds printed.; Preprint (bioRxiv v1), not peer reviewed.
citation locators: source id: rna-splicing-20261013-spliceai2-source-article; locator: Fig. 4g; source id: rna-splicing-20261013-spliceai2-source-article; locator: Main 'Contribution to rare genetic disease' paragraph 4; source id: rna-splicing-20261013-spliceai2-source-article; locator: Methods 'Evaluation of competing methods' and 'Variant effect benchmarks'
source locator: rna-splicing-20261013-spliceai2-source-article: Fig. 4g; rna-splicing-20261013-spliceai2-source-article: Main 'Contribution to rare genetic disease' paragraph 4; rna-splicing-20261013-spliceai2-source-article: Methods 'Evaluation of competing methods' and 'Variant effect benchmarks'
comparison group: spliceai2-2026-gel
comparison title: DNA splice predictors against cryptic splicing in Genomics England rare-disease blood RNA-seq (SpliceAI2 paper, developer-reported)
stratum label: GT/AG cryptic-site activation, all four models
stratum order: 1
headline metric: auprc
reason: Drafted from the 2026-10-13 SpliceAI2 extraction (data/omics/use-case-coverage-rna-splicing-20261013-spliceai2), issue #127. Independently reviewed in docs/reviews/use-cases/spliceai2-2026-10-13.md.
review: method: scope-review; independent-cell-check; reviewer: claude; reviewer note: Claude (Opus 5.5) research agent, independent reviewer; did not extract this batch; no human review claimed; date: 2026-10-13; artifact sha256: f8f3db2c3943d4827b670bc2e962e0cec8fbe96e0b1acf9d4a9b9f0c7a78c06b; retrieval url: https://www.biorxiv.org/content/10.64898/2026.10.08.757673v1.full.pdf; method note: Judged against the use case's question, inputs and output in data/entities/use-cases.jsonl and the existing judgements for the same use case; endpoint, limitations and every evaluation on the protocol re-read in the pinned PDF.; note: Checked against the pinned source by the independent reviewer; verdict and correction list in docs/reviews/use-cases/spliceai2-2026-10-13.md and this batch's review.json. Developer-reported value, not reproduced. Extraction method: Drafted by the extractor against the use case's question, inputs and output and the existing judgements for the same use case; not a review.
reviewed evaluations: rna-splicing-20261013-spliceai2-eval-gel-gtag-detection-alphagenome-composite-max; rna-splicing-20261013-spliceai2-eval-gel-gtag-detection-alphagenome-splice-site-max; rna-splicing-20261013-spliceai2-eval-gel-gtag-detection-pangolin-position-resolved; rna-splicing-20261013-spliceai2-eval-gel-gtag-detection-spliceai-position-resolved; rna-splicing-20261013-spliceai2-eval-gel-gtag-detection-spliceai2-ensemble
pins: record id: rna-splicing-20261013-spliceai2-eval-gel-gtag-detection-alphagenome-composite-max; fields: status; links; attributes.origin; attributes.comparison; sha256: e58efdf5150e97ebf014a4f0d0c218a87752fe0ecbe3e8d668a2b36bbd5c59bd; record id: rna-splicing-20261013-spliceai2-eval-gel-gtag-detection-alphagenome-splice-site-max; fields: status; links; attributes.origin; attributes.comparison; sha256: b28e9aded5ea4ad4ab6412fcca12f868b16e406fe1e0b0964e5047c238d7b551; record id: rna-splicing-20261013-spliceai2-eval-gel-gtag-detection-pangolin-position-resolved; fields: status; links; attributes.origin; attributes.comparison; sha256: d234e0243e589f54ea0a6ec4732af26e68549712a4f79a151e98ee9a5a3540be; record id: rna-splicing-20261013-spliceai2-eval-gel-gtag-detection-spliceai-position-resolved; fields: status; links; attributes.origin; attributes.comparison; sha256: 45a136877b7e9b535c48aec3cfb95ea58cfb8c87c83567a46907801bce092bb7; record id: rna-splicing-20261013-spliceai2-eval-gel-gtag-detection-spliceai2-ensemble; fields: status; links; attributes.origin; attributes.comparison; sha256: 578802dc3d65ffd1e2fe220775dd45922e5c424f4995bbf037afe362cc08326a; record id: rna-splicing-20261013-spliceai2-protocol-gel-gtag-detection; fields: status; name; description; facets; source_ids; links; attributes; sha256: e3b5ab8fb4e1e6711046ac9bccd9b2d6799730e039a342f4064db0f08f1e713d; record id: rna-splicing-20261013-spliceai2-result-gel-gtag-detection-alphagenome-composite-max-auprc; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: a254aed9e733e57d79fb49da6f762ea3669bc5601676695f33e4ed4294b99c19; record id: rna-splicing-20261013-spliceai2-result-gel-gtag-detection-alphagenome-splice-site-max-auprc; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: e18d63145aabbc3a20444ae3258038c5abfe2fcbeb6998a5d60cdeac89c6e686; record id: rna-splicing-20261013-spliceai2-result-gel-gtag-detection-pangolin-position-resolved-auprc; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 1c334bbdf20f5e4bbe3b0e0580666ab61ebd8fb2bc329368ac57c0d770cccc3a; record id: rna-splicing-20261013-spliceai2-result-gel-gtag-detection-spliceai-position-resolved-auprc; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: 2724caf293a529d790f008ad3a094ca8cb2a2e17454051bc8bb9a1eb06ae3fed; record id: rna-splicing-20261013-spliceai2-result-gel-gtag-detection-spliceai2-ensemble-auprc; fields: status; attributes.metric; attributes.metric_qualifier; attributes.printed_value; attributes.numeric_value; sha256: b100ab826cebb544d8ccb779c6f5edc8963571e5813e555c50c61059e4c6ae17; record id: rna-splicing-20261013-spliceai2-source-article; fields: status; attributes.artifact_sha256; sha256: 09442cd33f8941b2e764e137cb843ca4a962a185fba4f3d7419d13f1981a5de1; record id: use-case-patient-rna-splicing-validation; fields: status; name; description; facets; attributes.question; attributes.decision; attributes.inputs; attributes.output; attributes.exclusions; attributes.setting; attributes.clinical_scope; attributes.intended_users; sha256: b85cad56e15fbfad66a2e70c3b193ed56c464e5e44b62a19b12f391e409ec897

Related records

subject: Select a patient-RNA splicing-variant validation workflow

Suggest a correction