Model type
Pretrained splice-site specialist ensemble
Configuration
SpliceAI 1.3.1
This MFASS evaluation uses the official SpliceAI 1.3.1 five-model ensemble in genomic context.
Sources
MFASS v2 run_spliceai.py · run_spliceai.py module documentation and recorded runner configurationHow it worksEvaluated pipeline
Schematic of the pinned MFASS configuration; this does not generalise to every member of the model family.
Sources
MFASS v2 pinned rewire artifacts · benchmarks/mfass/README.md, MFASS-v2 results; results/spliceai-1.3.1.json, description, config and notes at bee9133b83f3aedaf2bbb9013f1875515845607eOverview
Biological inputs
Variant genomic coordinates and GRCh38 reference/annotation
Outputs
Maximum splice acceptor/donor gain/loss delta score
Access
Public pinned benchmark runner with external genome and SpliceAI dependencies.
Sources
MFASS v2 run_spliceai.py · run_spliceai.py; module documentation, main() configuration and scoring procedurelimited source coverage · Automated source review, 2026-09-16. All specifications and missing details
Evaluations and results
1 evaluation · 3 results. Different protocols are not a single leaderboard.
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: SpliceAI 1.3.1 | Protocol: MFASS v2 Dataset: MFASS v2 eligible assay cohort | 0.806 auroc fraction · higher Uncertainty: Not reported Coverage: 8194/8324 | Rewire evaluation · Independently reproducedMethods, coverage and sourceUnchanged specialist run in genomic context with bundled annotation; zero-shot on MFASS assay labels. Point metrics use the scored subset. Aggregation: Not reported MFASS v2 pinned rewire artifacts · benchmarks/mfass/results/spliceai-1.3.1.json :: auroc |
| Configuration: SpliceAI 1.3.1 | Protocol: MFASS v2 Dataset: MFASS v2 eligible assay cohort | 0.299 average_precision fraction · higher Uncertainty: Not reported Coverage: 8194/8324 | Rewire evaluation · Independently reproducedMethods, coverage and sourceUnchanged specialist run in genomic context with bundled annotation; zero-shot on MFASS assay labels. Point metrics use the scored subset. Aggregation: Not reported MFASS v2 pinned rewire artifacts · benchmarks/mfass/results/spliceai-1.3.1.json :: average_precision |
| Configuration: SpliceAI 1.3.1 | Protocol: MFASS v2 Dataset: MFASS v2 eligible assay cohort | 0.64 precision_at_100 fraction · higher Uncertainty: Not reported Coverage: 8194/8324 | Rewire evaluation · Independently reproducedMethods, coverage and sourceUnchanged specialist run in genomic context with bundled annotation; zero-shot on MFASS assay labels. Point metrics use the scored subset. Aggregation: Not reported MFASS v2 pinned rewire artifacts · benchmarks/mfass/results/spliceai-1.3.1.json :: precision_at_100 |
Source checking is not independent reproduction. Release 2026-09-29-06401fd5b220.
Use this model
How it works, versions and access
Related profile: SpliceAI. This page retains the exact record and its evaluation context.
Underlying model: SpliceAI. Results on this page belong to this configuration and its evaluated settings.
How it works
Evaluated procedure
The runner scores variants against GRCh38 with bundled annotations and unmasked outputs. It ranks variants by the largest acceptor/donor gain or loss delta score. Its specialist predictions were retained unchanged for the corrected v2 comparison.
Sources
MFASS v2 pinned rewire artifacts · benchmarks/mfass/README.md, MFASS-v2 results; results/spliceai-1.3.1.json, description, config and notes at bee9133b83f3aedaf2bbb9013f1875515845607eStrengths, limitations and unresolved questions
Strengths and limitations
Strengths and considerations
- Uses a pretrained splice specialist without fitting to MFASS labels.
Sources
MFASS v2 pinned rewire artifacts · benchmarks/mfass/README.md, MFASS-v2 results; results/spliceai-1.3.1.json, description, config and notes at bee9133b83f3aedaf2bbb9013f1875515845607e
Limitations and conditions
- The genomic context differs from the assay construct. Missing predictions and possible exon overlap with specialist training data must be considered.
Sources
MFASS v2 pinned rewire artifacts · benchmarks/mfass/README.md, MFASS-v2 results; results/spliceai-1.3.1.json, description, config and notes at bee9133b83f3aedaf2bbb9013f1875515845607e
Profile review details
Pinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed.
Stable record: rewire-model-spliceai-1-3-1Specifications
Inputs, training, access and other details
Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
| Property | Description and evidence |
|---|---|
| Model type | Pretrained splice-site specialist ensembleSourcesMFASS v2 run_spliceai.py · run_spliceai.py; module documentation, main() configuration and scoring procedure |
| Architecture / procedure | Official five-model SpliceAI ensemble; score is max(DS_AG, DS_AL, DS_DG, DS_DL), with masking disabled.SourcesMFASS v2 run_spliceai.py · run_spliceai.py; module documentation, main() configuration and scoring procedure |
| Biological inputs | Variant genomic coordinates and GRCh38 reference/annotationSourcesMFASS v2 run_spliceai.py · run_spliceai.py; module documentation, main() configuration and scoring procedure |
| Outputs | Maximum splice acceptor/donor gain/loss delta scoreSourcesMFASS v2 run_spliceai.py · run_spliceai.py; module documentation, main() configuration and scoring procedure |
| Parameters | An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sourcesSourcesMFASS v2 run_spliceai.py · Pinned runner configuration and implementation; inspected for aggregate parameter count (component sizes are not added without an exact configuration) |
| Training data / fitting | No MFASS-label fitting by the runner. Upstream transcript overlap with assayed exons remains unchecked.SourcesMFASS v2 run_spliceai.py · run_spliceai.py; module documentation, main() configuration and scoring procedure |
| Context limits | 10,000-bp genomic context; distance_D=50; mask_M=0.SourcesMFASS v2 run_spliceai.py · run_spliceai.py; module documentation, main() configuration and scoring procedure |
| Known versions / configuration | SpliceAI 1.3.1; bundled spliceai1–5.h5 weightsSourcesMFASS v2 run_spliceai.py · run_spliceai.py; module documentation, main() configuration and scoring procedure |
| Access | Public pinned benchmark runner with external genome and SpliceAI dependencies.SourcesMFASS v2 run_spliceai.py · run_spliceai.py; module documentation, main() configuration and scoring procedure |
| Code licence | MIT for the Rewire runner at the reviewed revision. Upstream SpliceAI: PolyForm Strict 1.0.0. These are separate component licences.Sources (2)Rewire benchmark runner licence; github.com/Illumina/SpliceAI LICENSE · LICENSE; complete MIT grant; upstream LICENSE |
| Weights licence | SpliceAI trained models are CC BY-NC 4.0 for academic/non-commercial use; commercial use requires separate Illumina terms.Sourcesgithub.com/Illumina/SpliceAI README.md · README.md; License |
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.
23 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Schematic of the pinned MFASS configuration; this does not generalise to every member of the model family. Individual claims | MFASS v2 pinned rewire artifacts benchmarks/mfass/README.md, MFASS-v2 results; results/spliceai-1.3.1.json, description, config and notes at bee9133b83f3aedaf2bbb9013f1875515845607e Version: bee9133b83f3aedaf2bbb9013f1875515845607e | source checked automated source review · 2026-09-16 Audit detailsPinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed. Field: Source artifact SHA-256: Hash scope: Local imported data/benchmark-runs/mfass-v2.json; not the upstream repository or result-file hash |
Diagram steps
| MFASS v2 pinned rewire artifacts benchmarks/mfass/README.md, MFASS-v2 results; results/spliceai-1.3.1.json, description, config and notes at bee9133b83f3aedaf2bbb9013f1875515845607e Version: bee9133b83f3aedaf2bbb9013f1875515845607e | source checked automated source review · 2026-09-16 Audit detailsPinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed. Field: Source artifact SHA-256: Hash scope: Local imported data/benchmark-runs/mfass-v2.json; not the upstream repository or result-file hash |
| Diagram title Evaluated pipeline Individual claims | MFASS v2 pinned rewire artifacts benchmarks/mfass/README.md, MFASS-v2 results; results/spliceai-1.3.1.json, description, config and notes at bee9133b83f3aedaf2bbb9013f1875515845607e Version: bee9133b83f3aedaf2bbb9013f1875515845607e | source checked automated source review · 2026-09-16 Audit detailsPinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed. Field: Source artifact SHA-256: Hash scope: Local imported data/benchmark-runs/mfass-v2.json; not the upstream repository or result-file hash |
| Model type Pretrained splice-site specialist ensemble Individual claims | MFASS v2 run_spliceai.py run_spliceai.py; module documentation, main() configuration and scoring procedure Version: bee9133b83f3aedaf2bbb9013f1875515845607e | source checked automated source review · 2026-09-16 Audit detailsPinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Architecture / procedure Official five-model SpliceAI ensemble; score is max(DS_AG, DS_AL, DS_DG, DS_DL), with masking disabled. Individual claims | MFASS v2 run_spliceai.py run_spliceai.py; module documentation, main() configuration and scoring procedure Version: bee9133b83f3aedaf2bbb9013f1875515845607e | source checked automated source review · 2026-09-16 Audit detailsPinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Weights licence SpliceAI trained models are CC BY-NC 4.0 for academic/non-commercial use; commercial use requires separate Illumina terms. Individual claims | github.com/Illumina/SpliceAI README.md README.md; License Version: 03f42437aaf56dc5dfd822c4ccee5aec1a705079 | source checked automated source review · 2026-09-16 Audit detailsPinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Biological inputs Variant genomic coordinates and GRCh38 reference/annotation Individual claims | MFASS v2 run_spliceai.py run_spliceai.py; module documentation, main() configuration and scoring procedure Version: bee9133b83f3aedaf2bbb9013f1875515845607e | source checked automated source review · 2026-09-16 Audit detailsPinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Outputs Maximum splice acceptor/donor gain/loss delta score Individual claims | MFASS v2 run_spliceai.py run_spliceai.py; module documentation, main() configuration and scoring procedure Version: bee9133b83f3aedaf2bbb9013f1875515845607e | source checked automated source review · 2026-09-16 Audit detailsPinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Parameters An aggregate parameter total for this exact evaluated configuration is not established by the inspected sources. Individual claims | MFASS v2 run_spliceai.py Pinned runner configuration and implementation; inspected for aggregate parameter count (component sizes are not added without an exact configuration) Version: bee9133b83f3aedaf2bbb9013f1875515845607e | unreported automated source review · 2026-09-16 Audit detailsPinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Training data / fitting No MFASS-label fitting by the runner. Upstream transcript overlap with assayed exons remains unchecked. Individual claims | MFASS v2 run_spliceai.py run_spliceai.py; module documentation, main() configuration and scoring procedure Version: bee9133b83f3aedaf2bbb9013f1875515845607e | source checked automated source review · 2026-09-16 Audit detailsPinned MFASS runner source rechecked at bee9133b83f3aedaf2bbb9013f1875515845607e. Existing numerical records and historical artifacts remain unchanged; no new run was performed. Field: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
View linked audit checks and correction history
Release 2026-09-29-06401fd5b220 · Record review: source checked
5 source records and release history
- MFASS v2 pinned rewire artifacts · Original source · bee9133b83f3aedaf2bbb9013f1875515845607e
- MFASS v2 run_spliceai.py · Original source · bee9133b83f3aedaf2bbb9013f1875515845607e
- Rewire benchmark runner licence · Original source · bee9133b83f3aedaf2bbb9013f1875515845607e
- github.com/Illumina/SpliceAI LICENSE · Original source · 03f42437aaf56dc5dfd822c4ccee5aec1a705079
- github.com/Illumina/SpliceAI README.md · Original source · 03f42437aaf56dc5dfd822c4ccee5aec1a705079
Technical metadata and extraction receipts
Stable ID: rewire-model-spliceai-1-3-1
- areas
- dna-genomes
- entity level
- method
- version
- bee9133b83f3aedaf2bbb9013f1875515845607e
- reported name
- SpliceAI 1.3.1
- historical missing metadata
- None recorded
- metadata review scope
- historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
- legacy kinds
- model
- entity classification
- review date: 2026-09-17; rationale: This source-scoped entry preserves the method/configuration actually named in an evaluation. It is neither a global family identity nor proof of an immutable checkpoint; the linked evaluation retains adaptation, fitting and scoring details.; source ids: evidence-reported-rewire-run-spliceai; source locator: run_spliceai.py; module documentation, main() configuration and scoring procedure | run_spliceai.py module documentation and recorded runner configuration; ambiguities: Configuration means the source-labelled evaluated identity. It does not establish missing checkpoint hashes, default settings or equivalence to same-named records in other papers.
Related records
- uses model: SpliceAI
- family: SpliceAI
- subject: SpliceAI 1.3.1: family SpliceAI
- subject: SpliceAI 1.3.1: uses model SpliceAI
- model: SpliceAI 1.3.1 on MFASS v2