Zero-shot enhancer–gene linking: evaluated data subset
ENCODE-rE2G CRISPRi-validated element–gene pairs in K562, filtered for available annotations and GENCODEv46 gene identities.
Subset and evaluation context
This record describes a particular subset or cohort used in an evaluation. Its results do not describe the full dataset.
Evaluation results
Release 2026-09-17-d277315f7d76 · 2 evaluations · 2 metric rows. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| AlphaGenome distilled all-fold student: Zero-shot enhancer–gene linking Configuration: AlphaGenome distilled all-fold studentProtocol: Zero-shot enhancer–gene linking (AlphaGenome paper)Dataset subset: Zero-shot enhancer–gene linking: evaluated data subset Compute expression input-gradient contributions near each candidate element, normalize by gene-context background gradient magnitude and impute zero for elements outside model context. Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.75 auprc Unit: dimensionless · Direction: higher Aggregation: auPRC over labelled element–gene pairs, with separate distance-to-TSS strata in the paper. | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 4 Variant performan'!M17 Source checking is not independent reproduction. |
| borzoi-ensemble (paper Table 4): Zero-shot enhancer–gene linking Configuration: borzoi-ensemble (paper Table 4)Protocol: Zero-shot enhancer–gene linking (AlphaGenome paper)Dataset subset: Zero-shot enhancer–gene linking: evaluated data subset Compute expression input-gradient contributions near each candidate element, normalize by gene-context background gradient magnitude and impute zero for elements outside model context. Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.668 auprc Unit: dimensionless · Direction: higher Aggregation: auPRC over labelled element–gene pairs, with separate distance-to-TSS strata in the paper. | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 4 Variant performan'!L17 Source checking is not 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.
24 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| attributes.entity_level evaluation_subset 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 Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| attributes.entity_level evaluation_subset 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 Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of exact publisher PDF bytes Format: original_pdf |
| attributes.entity_level evaluation_subset 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 Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of exact retrieved original artifact bytes Format: xlsx |
| attributes.exact_manifest 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 Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| attributes.exact_manifest 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 Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of exact publisher PDF bytes Format: original_pdf |
| attributes.exact_manifest 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 Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of exact retrieved original artifact bytes Format: xlsx |
| attributes.reported_dataset_counts [{"positive":471,"total":10353,"count_unit":"enhancer/gene pairs","scope":"complete final evaluation dataset","source_locator":"Supplementary Methods p.39, Enhancer-gene linking"}] 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 Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| attributes.reported_dataset_counts [{"positive":471,"total":10353,"count_unit":"enhancer/gene pairs","scope":"complete final evaluation dataset","source_locator":"Supplementary Methods p.39, Enhancer-gene linking"}] 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 Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of exact publisher PDF bytes Format: original_pdf |
| attributes.reported_dataset_counts [{"positive":471,"total":10353,"count_unit":"enhancer/gene pairs","scope":"complete final evaluation dataset","source_locator":"Supplementary Methods p.39, Enhancer-gene linking"}] 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 Audit detailsField: Source artifact SHA-256: Hash scope: SHA-256 of exact retrieved original artifact bytes Format: xlsx |
| attributes.source_dataset_label ENCODE E2G paper 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 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-d277315f7d76 · Record review: needs review
3 source records and release history
- 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-t4-dataset-15
- areas
- dna-genomes
- entity level
- evaluation_subset
- source dataset label
- ENCODE E2G paper
- source subset scope
- Zero-shot evaluation on the annotated ENCODE-rE2G pairs; do not invent a downstream supervised training split.
- exact manifest
- Not reported
- reported dataset counts
- positive: 471; total: 10353; count unit: enhancer/gene pairs; scope: complete final evaluation dataset; source locator: Supplementary Methods p.39, Enhancer-gene linking
- missing metadata
- split manifest: unextracted; per score denominator: unextracted
- legacy kinds
- dataset
- entity classification
- review date: 2026-09-17; rationale: The record explicitly identifies the source-filtered and split-specific evaluated data population. Preserve it as a dataset subset, including comparator-specific selection, without inferring an unrecorded parent accession or equating differently filtered populations.; source ids: source-alphagenome-nature2026-tables; source-alphagenome-nature2026-supplementary-methods; evidence-official-56e5abfb5f12f1cd3b20; source locator: 'Suppl Table 4 Variant performan'!A17:P17; Supplementary Methods p.30, Chromosome Splits for Variant Benchmarks; Supplementary Methods p.39, Enhancer-gene linking; methods: p.39, Enhancer-gene linking; paper: Fig.4j; Extended Data Fig.7a–d; tables: Suppl Table 4 Variant performan; evaluation index 15; sheet rows 17; ambiguities: None recorded