AlphaGenome fold-1 ensemble, splice-junction head: Human splice-junction classification and count prediction
For classification, contrast read-supported junctions with unobserved donor–acceptor pairs. For count prediction, correlate log(1+x)-transformed predicted and observed counts only on nonzero observed junctions.
Evaluation procedure
For classification, contrast read-supported junctions with unobserved donor–acceptor pairs. For count prediction, correlate log(1+x)-transformed predicted and observed counts only on nonzero observed junctions.
- Model
- AlphaGenome fold-1 ensemble, splice-junction head
- Benchmark
- Human splice-junction classification and count prediction (AlphaGenome paper)
- Dataset
- Human splice-junction classification and count prediction: evaluated data subset
- origin
- Author-reported evaluation
- configuration
- AlphaGenome fold-1 ensemble, splice-junction head
- protocol id
- alphagenome-2026-t3-protocol-4
- dataset version
- Not reported
- split
- Held-out intervals of fold-1 evaluated with a model ensemble trained on fold-1 training data.
- population
- Filtered RNA-seq junctions on fold-1 held-out intervals; observed splice sites define candidate pairings.
- inputs
- Not reported
- adaptation
- AlphaGenome fold-1 ensemble, splice-junction head
- metric implementation
- Not reported
- aggregation
- Classification: auPRC per tissue averaged across tissues. Quantitative endpoint: Pearson correlation of log-transformed counts; do not pool these two metric rows.
- budget
- Not reported
Metadata review: needs review. Unreported conditions prevent automatic comparisons.
Evaluation results
Release 2026-09-17-a757f4af4277 · 1 evaluation · 2 metric rows. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| AlphaGenome fold-1 ensemble, splice-junction head: Human splice-junction classification and count prediction Model: AlphaGenome fold-1 ensemble, splice-junction head · Benchmark: Human splice-junction classification and count prediction (AlphaGenome paper) · Dataset: Human splice-junction classification and count prediction: evaluated data subset For classification, contrast read-supported junctions with unobserved donor–acceptor pairs. For count prediction, correlate log(1+x)-transformed predicted and observed counts only on nonzero observed junctions. Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.82 pearsonr Unit: correlation · Direction: higher Aggregation: Classification: auPRC per tissue averaged across tissues. Quantitative endpoint: Pearson correlation of log-transformed counts; do not pool these two metric rows. | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 3 Track performance'!K8 Source checking is not independent reproduction. |
| 0.82 auPRC Unit: dimensionless · Direction: higher Aggregation: Classification: auPRC per tissue averaged across tissues. Quantitative endpoint: Pearson correlation of log-transformed counts; do not pool these two metric rows. | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 3 Track performance'!K9 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 AlphaGenome fold-1 ensemble, splice-junction head 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 AlphaGenome fold-1 ensemble, splice-junction head 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 AlphaGenome fold-1 ensemble, splice-junction head 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 Classification: auPRC per tissue averaged across tissues. Quantitative endpoint: Pearson correlation of log-transformed counts; do not pool these two metric rows. 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 Classification: auPRC per tissue averaged across tissues. Quantitative endpoint: Pearson correlation of log-transformed counts; do not pool these two metric rows. 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 Classification: auPRC per tissue averaged across tissues. Quantitative endpoint: Pearson correlation of log-transformed counts; do not pool these two metric rows. 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-5d9680277b54b879
- areas
- dna-genomes
- origin
- author_reported
- protocol
- For classification, contrast read-supported junctions with unobserved donor–acceptor pairs. For count prediction, correlate log(1+x)-transformed predicted and observed counts only on nonzero observed junctions.
- version
- AlphaGenome fold-1 ensemble, splice-junction head
- source evaluation index
- 4
- source table
- 3
- comparison
- protocol id: alphagenome-2026-t3-protocol-4; dataset version: Not reported; split: Held-out intervals of fold-1 evaluated with a model ensemble trained on fold-1 training data.; population: Filtered RNA-seq junctions on fold-1 held-out intervals; observed splice sites define candidate pairings.; inputs: Not reported; adaptation: AlphaGenome fold-1 ensemble, splice-junction head; metric implementation: Not reported; aggregation: Classification: auPRC per tissue averaged across tissues. Quantitative endpoint: Pearson correlation of log-transformed counts; do not pool these two metric rows.; budget: Not reported
- context
- allowed inputs: Predicted junction counts; Splam comparison scores each pair using the smaller donor/acceptor probability.; limitations: The PSI3/PSI5 analyses on chromosome2 are a separate analysis, not the Table3 auPRC/count endpoints. Unobserved junctions are assay-derived negative labels, not proof of biological impossibility.
- missing metadata
- dataset version: unextracted; exact input manifest: unextracted; inference budget: unreported; scoring failures: unreported
Related records
- model: AlphaGenome fold-1 ensemble, splice-junction head
- benchmark: Human splice-junction classification and count prediction (AlphaGenome paper)
- dataset: Human splice-junction classification and count prediction: evaluated data subset
- evaluation: AlphaGenome fold-1 ensemble, splice-junction head: Human splice-junction classification and count prediction, pearsonr
- evaluation: AlphaGenome fold-1 ensemble, splice-junction head: Human splice-junction classification and count prediction, auPRC