Borzoi (paper Table 3): RNA expression correlation across tracks
Compute per-gene cross-track correlation on normalized, gene-mean-centred expression.
Evaluation procedure
Compute per-gene cross-track correlation on normalized, gene-mean-centred expression.
- Model
- Borzoi (paper Table 3)
- Benchmark
- RNA expression correlation across tracks (AlphaGenome paper)
- Dataset
- RNA expression correlation across tracks: evaluated data subset
- origin
- Author-reported evaluation
- configuration
- Borzoi (paper Table 3)
- protocol id
- alphagenome-2026-t3-protocol-8
- dataset version
- Not reported
- split
- Held-out human genomic intervals under the relevant fold. General training follows Borzoi folds, extending intervals to the AlphaGenome context and removing validation/test windows overlapping training after extension; use the comparison-specific split below rather than the variant chromosome split. Borzoi fold-1 RNA comparison.
- population
- Borzoi-matched RNA-seq coverage aggregated over GENCODE v46 exons with strand matching; retain genes with at least half their exons in a test interval.
- inputs
- Not reported
- adaptation
- Borzoi (paper Table 3)
- metric implementation
- Not reported
- aggregation
- Pearson correlation across tracks. Preserve raw versus normalized Table3 rows; the inspected task paragraph does not specify the weighting used to reduce all correlations to the table scalar.
- 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 |
|---|---|---|
| Borzoi (paper Table 3): RNA expression correlation across tracks Model: Borzoi (paper Table 3) · Benchmark: RNA expression correlation across tracks (AlphaGenome paper) · Dataset: RNA expression correlation across tracks: evaluated data subset Compute per-gene cross-track correlation on normalized, gene-mean-centred expression. Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.497 Gene TPM normalized
(cross-track pearsonr) Unit: correlation · Direction: higher Aggregation: Pearson correlation across tracks. Preserve raw versus normalized Table3 rows; the inspected task paragraph does not specify the weighting used to reduce all correlations to the table scalar. | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 3 Track performance'!J14 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 Borzoi (paper Table 3) 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 Borzoi (paper Table 3) 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 Borzoi (paper Table 3) 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 Pearson correlation across tracks. Preserve raw versus normalized Table3 rows; the inspected task paragraph does not specify the weighting used to reduce all correlations to the table scalar. 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 Pearson correlation across tracks. Preserve raw versus normalized Table3 rows; the inspected task paragraph does not specify the weighting used to reduce all correlations to the table scalar. 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 Pearson correlation across tracks. Preserve raw versus normalized Table3 rows; the inspected task paragraph does not specify the weighting used to reduce all correlations to the table scalar. 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-757d96a97a6fa992
- areas
- dna-genomes
- origin
- author_reported
- protocol
- Compute per-gene cross-track correlation on normalized, gene-mean-centred expression.
- version
- Borzoi (paper Table 3)
- source evaluation index
- 8
- source table
- 3
- comparison
- protocol id: alphagenome-2026-t3-protocol-8; dataset version: Not reported; split: Held-out human genomic intervals under the relevant fold. General training follows Borzoi folds, extending intervals to the AlphaGenome context and removing validation/test windows overlapping training after extension; use the comparison-specific split below rather than the variant chromosome split. Borzoi fold-1 RNA comparison.; population: Borzoi-matched RNA-seq coverage aggregated over GENCODE v46 exons with strand matching; retain genes with at least half their exons in a test interval.; inputs: Not reported; adaptation: Borzoi (paper Table 3); metric implementation: Not reported; aggregation: Pearson correlation across tracks. Preserve raw versus normalized Table3 rows; the inspected task paragraph does not specify the weighting used to reduce all correlations to the table scalar.; budget: Not reported
- context
- allowed inputs: Predicted and observed log-transformed mean exon coverage; normalized endpoints additionally use quantile normalization across genes and subtract each gene’s mean across tracks.; limitations: Whole-gene correlation and cell-type specificity answer different questions. The table’s TPM shorthand must not replace the methods definition of log-transformed exon coverage.
- missing metadata
- dataset version: unextracted; exact input manifest: unextracted; inference budget: unreported; scoring failures: unreported