Model type
Pretrained splice-usage specialist ensemble
Configuration
Pangolin · mask=False
This MFASS evaluation uses Pangolin with masking disabled, scoring variants in genomic context.
Sources
MFASS v2 run_pangolin.py · run_pangolin.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/pangolin-maskFalse.json, config and notes at bee9133b83f3aedaf2bbb9013f1875515845607eUnderlying model: Pangolin. Results on this page belong to this configuration and its evaluated settings.
At a glance
Biological inputs
Variant genomic coordinates, GRCh38 reference and GENCODE annotation
Sources
MFASS v2 run_pangolin.py · run_pangolin.py; module documentation, main() configuration and scoring procedureOutputs
Maximum absolute predicted splice-usage change
Sources
MFASS v2 run_pangolin.py · run_pangolin.py; module documentation, main() configuration and scoring procedurelimited source coverage · Automated source review, 2026-09-16. All specifications and missing details
Evaluations and results
Release 2026-09-17-d277315f7d76 · 1 evaluation · 3 metric rows. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| Pangolin · mask=False on MFASS v2 Unchanged specialist run in genomic context with GENCODE v44; zero-shot on MFASS assay labels. Point metrics use the scored subset. Rewire evaluation · Evaluation metadata: reproduced | ||
| 0.8756851300560864 auroc Unit: fraction · Direction: higher | Uncertainty: Point estimate; see paired-comparison artifacts. Coverage (scored/eligible): 8301/8324 | reproducedMFASS v2 pinned rewire artifacts · benchmarks/mfass/results/pangolin-maskFalse.json :: auroc Source checking is not independent reproduction. |
| 0.3887617543064248 average_precision Unit: fraction · Direction: higher | Uncertainty: Point estimate; see paired-comparison artifacts. Coverage (scored/eligible): 8301/8324 | reproducedMFASS v2 pinned rewire artifacts · benchmarks/mfass/results/pangolin-maskFalse.json :: average_precision Source checking is not independent reproduction. |
| 0.65 precision_at_100 Unit: fraction · Direction: higher | Uncertainty: Point estimate; see paired-comparison artifacts. Coverage (scored/eligible): 8301/8324 | reproducedMFASS v2 pinned rewire artifacts · benchmarks/mfass/results/pangolin-maskFalse.json :: precision_at_100 Source checking is not independent reproduction. |
How it works
Evaluated procedure
The runner uses the specified reference and GENCODE annotation to predict changes in splice strength. The mask=False choice retains changes that annotation-based masking would remove. These specialist predictions were retained unchanged in the corrected v2 comparison.
Sources
MFASS v2 pinned rewire artifacts · benchmarks/mfass/README.md, MFASS-v2 results; results/pangolin-maskFalse.json, config and notes at bee9133b83f3aedaf2bbb9013f1875515845607eStrengths and limitations
Strengths and considerations
- Tests a pretrained splice specialist without learning from MFASS assay labels.
Sources
MFASS v2 pinned rewire artifacts · benchmarks/mfass/README.md, MFASS-v2 results; results/pangolin-maskFalse.json, config and notes at bee9133b83f3aedaf2bbb9013f1875515845607e
Limitations and conditions
- Results depend on annotation, masking and scored coverage. This configuration is not interchangeable with Pangolin’s masked default.
Sources
MFASS v2 pinned rewire artifacts · benchmarks/mfass/README.md, MFASS-v2 results; results/pangolin-maskFalse.json, 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-pangolin-maskfalseSpecifications
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-usage specialist ensembleSourcesMFASS v2 run_pangolin.py · run_pangolin.py; module documentation, main() configuration and scoring procedure |
| Architecture / procedure | Official 12-model Pangolin ensemble; use maximum absolute predicted splice-usage change with masking disabled.SourcesMFASS v2 run_pangolin.py · run_pangolin.py; module documentation, main() configuration and scoring procedure |
| Biological inputs | Variant genomic coordinates, GRCh38 reference and GENCODE annotationSourcesMFASS v2 run_pangolin.py · run_pangolin.py; module documentation, main() configuration and scoring procedure |
| Outputs | Maximum absolute predicted splice-usage changeSourcesMFASS v2 run_pangolin.py · run_pangolin.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_pangolin.py · Pinned runner configuration and implementation; inspected for aggregate parameter count (component sizes are not added without an exact configuration) |
| Training data / fitting | No fitting on MFASS assay outcomes in this runner. Upstream training overlap at assayed exons remains unchecked.SourcesMFASS v2 run_pangolin.py · run_pangolin.py; module documentation, main() configuration and scoring procedure |
| Context limits | 10,000-bp genomic context and 50-base scoring distance in the recorded configuration.SourcesMFASS v2 run_pangolin.py · run_pangolin.py; module documentation, main() configuration and scoring procedure |
| Known versions / configuration | Pangolin official final.{1,2,3}.{0,2,4,6}.3.v2 ensemble; mask=FalseSourcesMFASS v2 run_pangolin.py · run_pangolin.py; module documentation, main() configuration and scoring procedure |
| Access | Public pinned runner with external reference, annotation and model dependencies.SourcesMFASS v2 run_pangolin.py · run_pangolin.py; module documentation, main() configuration and scoring procedure |
| Code licence | MIT for the Rewire runner at the reviewed revision. Upstream Pangolin: GPLv3. These are separate component licences.Sources (2)Rewire benchmark runner licence; github.com/tkzeng/Pangolin LICENSE · LICENSE; complete MIT grant; upstream LICENSE |
| Weights licence | A separate grant specifically naming the Pangolin weight files is not stated in the inspected README or repository GPL licence; code and weight scope require clarification. · Not reported in inspected sourcesSourcesgithub.com/tkzeng/Pangolin README.md · README.md; model installation and full repository LICENSE |
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.
21 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/pangolin-maskFalse.json, 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 ["Variant and genomic context","Pangolin predictor","Splice-strength changes","mask=False aggregation","Variant ranking"] Individual claims | MFASS v2 pinned rewire artifacts benchmarks/mfass/README.md, MFASS-v2 results; results/pangolin-maskFalse.json, 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/pangolin-maskFalse.json, 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-usage specialist ensemble Individual claims | MFASS v2 run_pangolin.py run_pangolin.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 12-model Pangolin ensemble; use maximum absolute predicted splice-usage change with masking disabled. Individual claims | MFASS v2 run_pangolin.py run_pangolin.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 A separate grant specifically naming the Pangolin weight files is not stated in the inspected README or repository GPL licence; code and weight scope require clarification. Individual claims | github.com/tkzeng/Pangolin README.md README.md; model installation and full repository LICENSE Version: 5cf94b8db938c658391b4305cd7ce33297d44ff7 | 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 |
| Biological inputs Variant genomic coordinates, GRCh38 reference and GENCODE annotation Individual claims | MFASS v2 run_pangolin.py run_pangolin.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 absolute predicted splice-usage change Individual claims | MFASS v2 run_pangolin.py run_pangolin.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_pangolin.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 fitting on MFASS assay outcomes in this runner. Upstream training overlap at assayed exons remains unchecked. Individual claims | MFASS v2 run_pangolin.py run_pangolin.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
Release 2026-09-17-d277315f7d76 · Record review: source checked
5 source records and release history
- MFASS v2 pinned rewire artifacts · Original source · bee9133b83f3aedaf2bbb9013f1875515845607e
- MFASS v2 run_pangolin.py · Original source · bee9133b83f3aedaf2bbb9013f1875515845607e
- Rewire benchmark runner licence · Original source · bee9133b83f3aedaf2bbb9013f1875515845607e
- github.com/tkzeng/Pangolin LICENSE · Original source · 5cf94b8db938c658391b4305cd7ce33297d44ff7
- github.com/tkzeng/Pangolin README.md · Original source · 5cf94b8db938c658391b4305cd7ce33297d44ff7
Technical metadata and extraction receipts
Stable ID: rewire-model-pangolin-maskfalse
- areas
- dna-genomes
- entity level
- method
- version
- bee9133b83f3aedaf2bbb9013f1875515845607e
- reported name
- Pangolin · mask=False
- historical missing metadata
- 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-pangolin; source locator: run_pangolin.py; module documentation, main() configuration and scoring procedure | run_pangolin.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: Pangolin
- subject: Pangolin · mask=False: uses model Pangolin
- model: Pangolin · mask=False on MFASS v2