OpenSplice MPRA delta PSI prediction for 283,121 single-nucleotide substitutions in 599 exons (SpliceAI2 paper, Spearman)
Rank correlation between predicted and measured exon-inclusion change in the OpenSplice reporter assay.
Overview
An explanatory profile has not yet been reviewed for this record.
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
4 recorded evaluations, 12 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.
Results
Results are available, but no reviewed comparison panel is linked in this release.
All evaluations
4 evaluations · 12 results. Different protocols are not a single leaderboard.
Protocol: OpenSplice MPRA delta PSI prediction for 283,121 single-nucleotide substitutions in 599 exons (SpliceAI2 paper, Spearman) · Dataset: OpenSplice MPRA single-nucleotide substitutions with measured delta PSI (as used by Jaganathan et al. 2026)
Sorted by Spearman (all variants; essential splice variants excluded) (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 | Spearman (all variants; essential splice variants excluded) | Spearman (exonic variants; essential splice variants excluded) | Spearman (intronic variants; essential splice variants excluded) |
|---|---|---|---|
| SpliceAI2 two-model multispecies ensemble (Jaganathan et al. 2026)Evaluation | 0.59 (best in column) | 0.62 (best in column) | 0.52 (best in column) |
| SpliceAI scores released with the OpenSplice dataset (Jaganathan et al. 2026)Evaluation | 0.55 | 0.57 | 0.5 |
| Pangolin scores released with the OpenSplice dataset (Jaganathan et al. 2026)Evaluation | 0.53 | 0.54 | 0.49 |
| AlphaGenome scores released with the OpenSplice dataset (Jaganathan et al. 2026)Evaluation | 0.49 | 0.52 | 0.44 |
All 12 result rows with coverage, uncertainty and sources
Filter evaluations
Applied filters: All linked evaluations
Source checking is not independent reproduction. Release 2026-10-22-1b7cf027e4f6.
Methods and evaluation design
Procedure, tasks and evaluated configurations
Recorded evaluations
Each evaluation records what was tested and under which conditions.
Baseline coverage
Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.
0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.
No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.
- Author-reported evaluations
- 4
Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.
Null control
Proposed control: requires review
Training-set class prior where supervised fitting is permitted
Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.
This is a suggested selection rule, not a validated method or a measured score.
Conventional reference
Proposed control: requires review
Regularised classifier on simple permitted features, or protocol's conventional reference
Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.
This is a suggested selection rule, not a validated method or a measured score.
Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)
Coverage is derived from release 2026-10-22-1b7cf027e4f6. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.
Run instructions
No runnable recipe has been reviewed for this protocol. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.
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
| Property and statement | Original source and location | Review and provenance |
|---|
No evidence rows match these filters. Choose another scope or clear the search.
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-protocol-opensplice-mpra
- areas
- dna-genomes; rna-transcriptomes
- contexts
- research
- protocol
- SpliceAI2 effect = mean of the donor usage change at the downstream donor and the acceptor usage change at the upstream acceptor of the measured exon; SpliceAI, Pangolin and AlphaGenome use the scores released with OpenSplice. Spearman against measured delta PSI, overall and by exonic or intronic position.
- version
- bioRxiv v1 Extended Data Fig. 2 and Fig. 1d
- metric
- spearman-correlation
- metric direction
- higher
- source locator
- Methods 'Variant effect benchmarks', OpenSplice MPRA paragraph; Extended Data Fig. 2 panel 'OpenSplice MPRA (ρ)'
- limitations
- Comparator scores are those released with OpenSplice, not rescored by the authors, while SpliceAI2 was scored by its developers with an exon-skipping formula; settings therefore differ between systems.; The OpenSplice paragraph of the Methods says released SpliceAI, Pangolin and AlphaGenome scores were used. The AlphaGenome paragraph says the raw composite score was chosen across 'eight evaluations' and used 'for all evaluations'; the paper has eight other analyses with AlphaGenome (four GTEx panels in Fig. 1d and Figs. 3c, 3f, 4b and 4g), so the reviewer reads the OpenSplice scores as the released ones. The settings of the released scores are not described in this paper.; Reporter exon inclusion in a minigene context, not endogenous or patient splicing.; Developer-reported: the SpliceAI2 authors (Illumina) scored SpliceAI2 and computed every correlation; the SpliceAI, Pangolin and AlphaGenome scores are those released with the OpenSplice dataset (reference 23).; Training overlap: SpliceAI2 was trained on all human genes except those on chromosomes 21 and 22; the paper does not say how many of the 599 OpenSplice exons lie in training genes.; Essential splice variants are excluded, so results do not cover canonical GT/AG disruption.; No confidence intervals or resampling uncertainty are printed.; Preprint (bioRxiv v1), not peer reviewed.
Related records
- uses data: OpenSplice MPRA single-nucleotide substitutions with measured delta PSI (as used by Jaganathan et al. 2026)
- assessment: AlphaGenome on OpenSplice MPRA (spearman-correlation, SpliceAI2 paper)
- assessment: Pangolin on OpenSplice MPRA (spearman-correlation, SpliceAI2 paper)
- assessment: SpliceAI on OpenSplice MPRA (spearman-correlation, SpliceAI2 paper)
- assessment: SpliceAI2 on OpenSplice MPRA (spearman-correlation, SpliceAI2 paper)
- assessed by: Prioritise variants for splicing experiments