Pangolin (paper Table 4): Splice-site-region variants splicing-based classification
Score each variant from its predicted splicing changes and compare with the selected ClinVar pathogenicity labels.
Evaluation procedure
Score each variant from its predicted splicing changes and compare with the selected ClinVar pathogenicity labels.
- Model
- Pangolin (paper Table 4)
- Benchmark
- Splice-site-region variants splicing-based classification (AlphaGenome paper)
- Dataset
- Splice-site-region variants splicing-based classification: evaluated data subset
- origin
- Author-reported evaluation
- configuration
- Pangolin (paper Table 4)
- protocol id
- alphagenome-2026-t4-protocol-3
- dataset version
- Not reported
- split
- Zero-shot scorer development uses validation chromosomes 1,2,4,5,7,8,10,11,13,14,15,17,20,22,X; final test chromosomes are 3,6,9,12,16,18,19,21. This partitions variant evaluation labels; the distilled model’s teachers were trained on all reference-genome folds.
- population
- ClinVar GRCh38 release 2025-03-23. ClinVar intronic/synonymous/missense variants near splice sites, using the paper’s exonic/intronic distance definitions.
- inputs
- Not reported
- adaptation
- Pangolin (paper Table 4)
- metric implementation
- Not reported
- aggregation
- auPRC in the category, retaining its own class prevalence and sampling scheme.
- budget
- Not reported
Metadata review: needs review. Unreported conditions prevent automatic comparisons.
Evaluation results
Release 2026-09-17-a757f4af4277 · 1 evaluation · 1 metric row. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| Pangolin (paper Table 4): Splice-site-region variants splicing-based classification Model: Pangolin (paper Table 4) · Benchmark: Splice-site-region variants splicing-based classification (AlphaGenome paper) · Dataset: Splice-site-region variants splicing-based classification: evaluated data subset Score each variant from its predicted splicing changes and compare with the selected ClinVar pathogenicity labels. Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.553822 auprc_max_abs_track_aggregation Unit: dimensionless · Direction: higher Aggregation: auPRC in the category, retaining its own class prevalence and sampling scheme. | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 4 Variant performan'!L4 Source checking is not independent reproduction. |
Evidence table
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.
63 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| attributes.comparison.adaptation Pangolin (paper Table 4) Context-only references | alphagenome: Journal full-text XML No field-specific location recorded Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Retrieved page snapshot; no immutable publisher revision supplied | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| attributes.comparison.adaptation Pangolin (paper Table 4) Context-only references | AlphaGenome Nature 2026 supplementary methods No field-specific location recorded Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Supplement to Nature version of record, 28 January 2026; content hash pinned | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of exact publisher PDF bytes Format: original_pdf |
| attributes.comparison.adaptation Pangolin (paper Table 4) Context-only references | AlphaGenome Nature 2026 supplementary comparison tables No field-specific location recorded Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nature version of record, 28 January 2026 | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of exact retrieved original artifact bytes Format: xlsx |
| attributes.comparison.aggregation auPRC in the category, retaining its own class prevalence and sampling scheme. Context-only references | alphagenome: Journal full-text XML No field-specific location recorded Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Retrieved page snapshot; no immutable publisher revision supplied | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| attributes.comparison.aggregation auPRC in the category, retaining its own class prevalence and sampling scheme. Context-only references | AlphaGenome Nature 2026 supplementary methods No field-specific location recorded Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Supplement to Nature version of record, 28 January 2026; content hash pinned | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of exact publisher PDF bytes Format: original_pdf |
| attributes.comparison.aggregation auPRC in the category, retaining its own class prevalence and sampling scheme. Context-only references | AlphaGenome Nature 2026 supplementary comparison tables No field-specific location recorded Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nature version of record, 28 January 2026 | not individually reviewed No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of exact retrieved original artifact bytes Format: xlsx |
| attributes.comparison.budget No value recorded Context-only references | alphagenome: Journal full-text XML No field-specific location recorded Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Retrieved page snapshot; no immutable publisher revision supplied | missing or unspecified No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| attributes.comparison.budget No value recorded Context-only references | AlphaGenome Nature 2026 supplementary methods No field-specific location recorded Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Supplement to Nature version of record, 28 January 2026; content hash pinned | missing or unspecified No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of exact publisher PDF bytes Format: original_pdf |
| attributes.comparison.budget No value recorded Context-only references | AlphaGenome Nature 2026 supplementary comparison tables No field-specific location recorded Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nature version of record, 28 January 2026 | missing or unspecified No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of exact retrieved original artifact bytes Format: xlsx |
| attributes.comparison.dataset_version No value recorded Context-only references | alphagenome: Journal full-text XML No field-specific location recorded Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Retrieved page snapshot; no immutable publisher revision supplied | missing or unspecified No individual claim review recorded author reported Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
Sources and history
Release 2026-09-17-a757f4af4277 · Record review: needs review
- AlphaGenome Nature 2026 supplementary comparison tables · Original source · Nature version of record, 28 January 2026
- AlphaGenome Nature 2026 supplementary methods · Original source · Supplement to Nature version of record, 28 January 2026; content hash pinned
- alphagenome: Journal full-text XML · Original source · Retrieved page snapshot; no immutable publisher revision supplied
Technical metadata and extraction receipts
Stable ID: alphagenome-2026-evaluation-f3c06cfe6a884f62
- areas
- dna-genomes
- origin
- author_reported
- protocol
- Score each variant from its predicted splicing changes and compare with the selected ClinVar pathogenicity labels.
- version
- Pangolin (paper Table 4)
- source evaluation index
- 3
- source table
- 4
- comparison
- protocol id: alphagenome-2026-t4-protocol-3; dataset version: Not reported; split: Zero-shot scorer development uses validation chromosomes 1,2,4,5,7,8,10,11,13,14,15,17,20,22,X; final test chromosomes are 3,6,9,12,16,18,19,21. This partitions variant evaluation labels; the distilled model’s teachers were trained on all reference-genome folds.; population: ClinVar GRCh38 release 2025-03-23. ClinVar intronic/synonymous/missense variants near splice sites, using the paper’s exonic/intronic distance definitions.; inputs: Not reported; adaptation: Pangolin (paper Table 4); metric implementation: Not reported; aggregation: auPRC in the category, retaining its own class prevalence and sampling scheme.; budget: Not reported
- context
- allowed inputs: REF/ALT sequence, gene annotations and composite splice-site/site-usage/junction scores; the table uses maximum absolute track aggregation.; limitations: ClinVar pathogenicity is not an experimentally isolated splicing label. Boundary text differs in strict/inclusive wording between methods and Fig3h; use the released category labels rather than inventing edge-case membership.
- missing metadata
- dataset version: unextracted; exact input manifest: unextracted; inference budget: unreported; scoring failures: unreported
Related records
- model: Pangolin (paper Table 4)
- benchmark: Splice-site-region variants splicing-based classification (AlphaGenome paper)
- dataset: Splice-site-region variants splicing-based classification: evaluated data subset
- evaluation: Pangolin (paper Table 4): Splice-site-region variants splicing-based classification, auprc max abs track aggregation