Pearson (predicted versus observed logit junction usage difference, cerebellum versus blood, 13,770 junctions) of SpliceAI2 tissue-specific fine-tune with a 147-RBP expression signature, 48 GTEx v8 tissues (Jaganathan et al. 2026) on GTEx v8 tissue-specific junction usage differences on held-out chromosomes (Jaganathan et al. 2026)
0.58 Pearson (predicted versus observed logit junction usage difference, cerebellum versus blood, 13,770 junctions)
Methods
- Tested configuration
- SpliceAI2 tissue-specific fine-tune with a 147-RBP expression signature, 48 GTEx v8 tissues (Jaganathan et al. 2026)
- Protocol
- Tissue-specific junction usage differences across GTEx tissue pairs, held-out chromosomes (SpliceAI2 paper, Pearson)
- Dataset
- GTEx v8 tissue-specific junction usage differences on held-out chromosomes (Jaganathan et al. 2026)
- Procedure
- Tissue-specific junction usage differences across GTEx tissue pairs, held-out chromosomes (SpliceAI2 paper, Pearson)
- Evaluation
- SpliceAI2 tissue-specific fine-tune on GTEx tissue-pair junction usage differences
- Coverage
- Not reported scored / Not reported eligible
- Uncertainty
- Not reported by the source
- Evidence
- Author-reported evaluation · source checkedA unified framework for quantitative splicing and transcript prediction (Jaganathan et al., bioRxiv 2026) · Main 'Modeling tissue-specific splicing' paragraph 2 '(13,770 splice junctions, Pearson r = 0.58)'; Fig. 2b panel 'Cerebellum vs blood'
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
- Held-out chromosomes 1, 3, 5, 7 and 9
- Adaptation
- Fine-tuned on chromosomes 2, 4, 6, 8, 10 to 22 and X
- Scoring implementation
- Pearson on logit usage differences
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.
1 evidence row matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Reported result 0.58 Individual claims | A unified framework for quantitative splicing and transcript prediction (Jaganathan et al., bioRxiv 2026) Main 'Modeling tissue-specific splicing' paragraph 2 '(13,770 splice junctions, Pearson r = 0.58)'; Fig. 2b panel 'Cerebellum vs blood' Version: bioRxiv preprint version 1, posted 2026-10-11; full-text PDF (57 pages) | source checked ["pdf-text-parse","independent-cell-check"] · 2026-10-13 author reported Audit detailsChecked 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: Transcribed from the pinned text layer (pdftotext -layout); the sentence is asserted verbatim (whitespace-normalised) by extract/build_batch.py. Field: Source artifact SHA-256: 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. Extraction artifact SHA-256: |
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)
Technical metadata and extraction receipts
Stable ID: rna-splicing-20261013-spliceai2-result-gtex-tissue-specific-spliceai2-tissue-147rbp-pearson-cerebellum-blood
- metric
- pearson-correlation
- metric direction
- higher
- unit
- unitless
- printed value
- 0.58
- numeric value
- 0.58
- source locator
- Main 'Modeling tissue-specific splicing' paragraph 2 '(13,770 splice junctions, Pearson r = 0.58)'; Fig. 2b panel 'Cerebellum vs blood'
- review
- method: pdf-text-parse; 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: Sentence located in the reviewer's own pdftotext output of the pinned PDF; printed value and its context re-read.; 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: Transcribed from the pinned text layer (pdftotext -layout); the sentence is asserted verbatim (whitespace-normalised) by extract/build_batch.py.
- missing metadata
- uncertainty: reason: unreported
- metric qualifier
- predicted versus observed logit junction usage difference, cerebellum versus blood, 13,770 junctions