Strengths and considerations
No source-reviewed explanatory claims are recorded here yet.
benchmark · protocol
Zero-shot CAGI5 MPRA activity-effect prediction (borzoi-ensemble-matched comparison) (AlphaGenome paper)
Can native-sequence predictions recover measured reporter-assay variant effects across CAGI5 loci?
AlphaGenome Nature 2026 supplementary comparison tables; AlphaGenome Nature 2026 supplementary methods; alphagenome: Journal full-text XML · 'Suppl Table 4 Variant performan'!A11:P11; Supplementary Methods p.30, Chromosome Splits for Variant Benchmarks; Supplementary Methods p.40, Benchmarking on CAGI5 MPRA; Table10 cell-type matching; ExtendedDataFig8 caption; methods: p.40, Benchmarking on the CAGI5 MPRA challenge; paper: Extended Data Fig.8a; tables: Suppl Table 4 Variant performan; evaluation index 9; sheet rows 10, 11At a glance
Explanatory profile: limited source coverage · Automated source review, 2026-09-17. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.
| Property | Description and evidence |
|---|---|
| Dataset and biological context | CAGI5 challenge effects with hg19 sequence and GENCODEv19 annotations; comparator-specific locus/context sets.AlphaGenome Nature 2026 supplementary comparison tables; AlphaGenome Nature 2026 supplementary methods; alphagenome: Journal full-text XML · 'Suppl Table 4 Variant performan'!A11:P11; Supplementary Methods p.30, Chromosome Splits for Variant Benchmarks; Supplementary Methods p.40, Benchmarking on CAGI5 MPRA; Table10 cell-type matching; ExtendedDataFig8 caption; methods: p.40, Benchmarking on the CAGI5 MPRA challenge; paper: Extended Data Fig.8a; tables: Suppl Table 4 Variant performan; evaluation index 9; sheet rows 10, 11 |
| Split | Use the challenge’s evaluation data and reported locus exclusions. Do not replace this locus-based protocol with the generic variant chromosome split.AlphaGenome Nature 2026 supplementary comparison tables; AlphaGenome Nature 2026 supplementary methods; alphagenome: Journal full-text XML · 'Suppl Table 4 Variant performan'!A11:P11; Supplementary Methods p.30, Chromosome Splits for Variant Benchmarks; Supplementary Methods p.40, Benchmarking on CAGI5 MPRA; Table10 cell-type matching; ExtendedDataFig8 caption; methods: p.40, Benchmarking on the CAGI5 MPRA challenge; paper: Extended Data Fig.8a; tables: Suppl Table 4 Variant performan; evaluation index 9; sheet rows 10, 11 |
| Allowed inputs and adaptation | REF/ALT native genomic sequence and DNase scores averaged across cell-type-matched tracks; mappings differ by comparator strategy.AlphaGenome Nature 2026 supplementary comparison tables; AlphaGenome Nature 2026 supplementary methods; alphagenome: Journal full-text XML · 'Suppl Table 4 Variant performan'!A11:P11; Supplementary Methods p.30, Chromosome Splits for Variant Benchmarks; Supplementary Methods p.40, Benchmarking on CAGI5 MPRA; Table10 cell-type matching; ExtendedDataFig8 caption; methods: p.40, Benchmarking on the CAGI5 MPRA challenge; paper: Extended Data Fig.8a; tables: Suppl Table 4 Variant performan; evaluation index 9; sheet rows 10, 11 |
| Metrics as reported | mean_pearsonr_allAlphaGenome Nature 2026 supplementary comparison tables; AlphaGenome Nature 2026 supplementary methods; alphagenome: Journal full-text XML · 'Suppl Table 4 Variant performan'!A11:P11; Supplementary Methods p.30, Chromosome Splits for Variant Benchmarks; Supplementary Methods p.40, Benchmarking on CAGI5 MPRA; Table10 cell-type matching; ExtendedDataFig8 caption; methods: p.40, Benchmarking on the CAGI5 MPRA challenge; paper: Extended Data Fig.8a; tables: Suppl Table 4 Variant performan; evaluation index 9; sheet rows 10, 11 |
| Aggregation | Mean Pearson correlation over the included locus/context comparisons; Table4 rows10 and11 have different AlphaGenome scalars and must remain separate.AlphaGenome Nature 2026 supplementary comparison tables; AlphaGenome Nature 2026 supplementary methods; alphagenome: Journal full-text XML · 'Suppl Table 4 Variant performan'!A11:P11; Supplementary Methods p.30, Chromosome Splits for Variant Benchmarks; Supplementary Methods p.40, Benchmarking on CAGI5 MPRA; Table10 cell-type matching; ExtendedDataFig8 caption; methods: p.40, Benchmarking on the CAGI5 MPRA challenge; paper: Extended Data Fig.8a; tables: Suppl Table 4 Variant performan; evaluation index 9; sheet rows 10, 11 |
| Uncertainty | Not reported for these summary-table scores. · Not reported in inspected sourcesAlphaGenome Nature 2026 supplementary comparison tables; AlphaGenome Nature 2026 supplementary methods; alphagenome: Journal full-text XML · 'Suppl Table 4 Variant performan'!A11:P11; Supplementary Methods p.30, Chromosome Splits for Variant Benchmarks; Supplementary Methods p.40, Benchmarking on CAGI5 MPRA; Table10 cell-type matching; ExtendedDataFig8 caption; methods: p.40, Benchmarking on the CAGI5 MPRA challenge; paper: Extended Data Fig.8a; tables: Suppl Table 4 Variant performan; evaluation index 9; sheet rows 10, 11 |
| Entity type | protocol |
| Organisms | Not extracted or verified for this record. |
| Assays | Not extracted or verified for this record. |
| Baselines | Not extracted or verified for this record. |
How it works
Conceptual summary of the cited procedure; model-specific conditions are given below.
Read the diagram as text
- Select comparison-specific CAGI5 loci
- Match DNase tracks
- Score REF/ALT sequence effects
- Average locus correlations
What is tested
Can native-sequence predictions recover measured reporter-assay variant effects across CAGI5 loci?
AlphaGenome Nature 2026 supplementary comparison tables; AlphaGenome Nature 2026 supplementary methods; alphagenome: Journal full-text XML · 'Suppl Table 4 Variant performan'!A11:P11; Supplementary Methods p.30, Chromosome Splits for Variant Benchmarks; Supplementary Methods p.40, Benchmarking on CAGI5 MPRA; Table10 cell-type matching; ExtendedDataFig8 caption; methods: p.40, Benchmarking on the CAGI5 MPRA challenge; paper: Extended Data Fig.8a; tables: Suppl Table 4 Variant performan; evaluation index 9; sheet rows 10, 11Procedure
Compute locus/context Pearson correlations between predicted and observed effects. The Borzoi strategy uses its reported scoring windows and modified matching; the ChromBPNet comparison excludes the unavailable TERT-GBM context.
AlphaGenome Nature 2026 supplementary comparison tables; AlphaGenome Nature 2026 supplementary methods; alphagenome: Journal full-text XML · 'Suppl Table 4 Variant performan'!A11:P11; Supplementary Methods p.30, Chromosome Splits for Variant Benchmarks; Supplementary Methods p.40, Benchmarking on CAGI5 MPRA; Table10 cell-type matching; ExtendedDataFig8 caption; methods: p.40, Benchmarking on the CAGI5 MPRA challenge; paper: Extended Data Fig.8a; tables: Suppl Table 4 Variant performan; evaluation index 9; sheet rows 10, 11Tested models and results
Release 2026-09-17-a757f4af4277 · 2 evaluations · 2 metric rows. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| AlphaGenome distilled cell-type-matched DNase scorer, Borzoi-matched locus subset: Zero-shot CAGI5 MPRA activity-effect prediction (borzoi-ensemble-matched comparison) Model: AlphaGenome distilled cell-type-matched DNase scorer, Borzoi-matched locus subset · Benchmark: Zero-shot CAGI5 MPRA activity-effect prediction (borzoi-ensemble-matched comparison) (AlphaGenome paper) · Dataset: Zero-shot CAGI5 MPRA activity-effect prediction (borzoi-ensemble-matched comparison): evaluated data subset Compute locus/context Pearson correlations between predicted and observed effects. The Borzoi strategy uses its reported scoring windows and modified matching; the ChromBPNet comparison excludes the unavailable TERT-GBM context. Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.56 mean_pearsonr_all Unit: correlation · Direction: higher Aggregation: Mean Pearson correlation over the included locus/context comparisons; Table4 rows10 and11 have different AlphaGenome scalars and must remain separate. | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 4 Variant performan'!M11 Source checking is not independent reproduction. |
| borzoi-ensemble (paper Table 4): Zero-shot CAGI5 MPRA activity-effect prediction (borzoi-ensemble-matched comparison) Model: borzoi-ensemble (paper Table 4) · Benchmark: Zero-shot CAGI5 MPRA activity-effect prediction (borzoi-ensemble-matched comparison) (AlphaGenome paper) · Dataset: Zero-shot CAGI5 MPRA activity-effect prediction (borzoi-ensemble-matched comparison): evaluated data subset Compute locus/context Pearson correlations between predicted and observed effects. The Borzoi strategy uses its reported scoring windows and modified matching; the ChromBPNet comparison excludes the unavailable TERT-GBM context. Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.55 mean_pearsonr_all Unit: correlation · Direction: higher Aggregation: Mean Pearson correlation over the included locus/context comparisons; Table4 rows10 and11 have different AlphaGenome scalars and must remain separate. | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 4 Variant performan'!L11 Source checking is not independent reproduction. |
Strengths and limitations
Limitations and conditions
- Native genomic prediction is compared with an MPRA measurement. Track proxies and context exclusions affect comparability; do not merge the two same-index rows into one evaluation population.AlphaGenome Nature 2026 supplementary comparison tables; AlphaGenome Nature 2026 supplementary methods; alphagenome: Journal full-text XML · 'Suppl Table 4 Variant performan'!A11:P11; Supplementary Methods p.30, Chromosome Splits for Variant Benchmarks; Supplementary Methods p.40, Benchmarking on CAGI5 MPRA; Table10 cell-type matching; ExtendedDataFig8 caption; methods: p.40, Benchmarking on the CAGI5 MPRA challenge; paper: Extended Data Fig.8a; tables: Suppl Table 4 Variant performan; evaluation index 9; sheet rows 10, 11
- This is an author-reported protocol, not a rewire rerun. Different datasets, processing and adaptations cannot support an unrestricted leaderboard.AlphaGenome Nature 2026 supplementary comparison tables; AlphaGenome Nature 2026 supplementary methods; alphagenome: Journal full-text XML · 'Suppl Table 4 Variant performan'!A11:P11; Supplementary Methods p.30, Chromosome Splits for Variant Benchmarks; Supplementary Methods p.40, Benchmarking on CAGI5 MPRA; Table10 cell-type matching; ExtendedDataFig8 caption; methods: p.40, Benchmarking on the CAGI5 MPRA challenge; paper: Extended Data Fig.8a; tables: Suppl Table 4 Variant performan; evaluation index 9; sheet rows 10, 11
Profile review details
Primary-source transcription and separate automated source review. No human sign-off or independent experimental reproduction.
Stable record: alphagenome-2026-t4-protocol-9-row11Evidence 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.
42 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Diagram caption Conceptual summary of the cited procedure; model-specific conditions are given below. Individual claims | alphagenome: Journal full-text XML 'Suppl Table 4 Variant performan'!A11:P11; Supplementary Methods p.30, Chromosome Splits for Variant Benchmarks; Supplementary Methods p.40, Benchmarking on CAGI5 MPRA; Table10 cell-type matching; ExtendedDataFig8 caption; methods: p.40, Benchmarking on the CAGI5 MPRA challenge; paper: Extended Data Fig.8a; tables: Suppl Table 4 Variant performan; evaluation index 9; sheet rows 10, 11 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Retrieved page snapshot; no immutable publisher revision supplied | source checked automated source review · 2026-09-17 Audit detailsPrimary-source transcription and separate automated source review. No human sign-off or independent experimental reproduction. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Diagram caption Conceptual summary of the cited procedure; model-specific conditions are given below. Individual claims | AlphaGenome Nature 2026 supplementary methods 'Suppl Table 4 Variant performan'!A11:P11; Supplementary Methods p.30, Chromosome Splits for Variant Benchmarks; Supplementary Methods p.40, Benchmarking on CAGI5 MPRA; Table10 cell-type matching; ExtendedDataFig8 caption; methods: p.40, Benchmarking on the CAGI5 MPRA challenge; paper: Extended Data Fig.8a; tables: Suppl Table 4 Variant performan; evaluation index 9; sheet rows 10, 11 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 | source checked automated source review · 2026-09-17 Audit detailsPrimary-source transcription and separate automated source review. No human sign-off or independent experimental reproduction. Field: Source artifact SHA-256: Hash scope: SHA-256 of exact publisher PDF bytes Format: original_pdf |
| Diagram caption Conceptual summary of the cited procedure; model-specific conditions are given below. Individual claims | AlphaGenome Nature 2026 supplementary comparison tables 'Suppl Table 4 Variant performan'!A11:P11; Supplementary Methods p.30, Chromosome Splits for Variant Benchmarks; Supplementary Methods p.40, Benchmarking on CAGI5 MPRA; Table10 cell-type matching; ExtendedDataFig8 caption; methods: p.40, Benchmarking on the CAGI5 MPRA challenge; paper: Extended Data Fig.8a; tables: Suppl Table 4 Variant performan; evaluation index 9; sheet rows 10, 11 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nature version of record, 28 January 2026 | source checked automated source review · 2026-09-17 Audit detailsPrimary-source transcription and separate automated source review. No human sign-off or independent experimental reproduction. Field: Source artifact SHA-256: Hash scope: SHA-256 of exact retrieved original artifact bytes Format: xlsx |
| Diagram steps ["Select comparison-specific CAGI5 loci","Match DNase tracks","Score REF/ALT sequence effects","Average locus correlations"] Individual claims | alphagenome: Journal full-text XML 'Suppl Table 4 Variant performan'!A11:P11; Supplementary Methods p.30, Chromosome Splits for Variant Benchmarks; Supplementary Methods p.40, Benchmarking on CAGI5 MPRA; Table10 cell-type matching; ExtendedDataFig8 caption; methods: p.40, Benchmarking on the CAGI5 MPRA challenge; paper: Extended Data Fig.8a; tables: Suppl Table 4 Variant performan; evaluation index 9; sheet rows 10, 11 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Retrieved page snapshot; no immutable publisher revision supplied | source checked automated source review · 2026-09-17 Audit detailsPrimary-source transcription and separate automated source review. No human sign-off or independent experimental reproduction. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Diagram steps ["Select comparison-specific CAGI5 loci","Match DNase tracks","Score REF/ALT sequence effects","Average locus correlations"] Individual claims | AlphaGenome Nature 2026 supplementary methods 'Suppl Table 4 Variant performan'!A11:P11; Supplementary Methods p.30, Chromosome Splits for Variant Benchmarks; Supplementary Methods p.40, Benchmarking on CAGI5 MPRA; Table10 cell-type matching; ExtendedDataFig8 caption; methods: p.40, Benchmarking on the CAGI5 MPRA challenge; paper: Extended Data Fig.8a; tables: Suppl Table 4 Variant performan; evaluation index 9; sheet rows 10, 11 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 | source checked automated source review · 2026-09-17 Audit detailsPrimary-source transcription and separate automated source review. No human sign-off or independent experimental reproduction. Field: Source artifact SHA-256: Hash scope: SHA-256 of exact publisher PDF bytes Format: original_pdf |
| Diagram steps ["Select comparison-specific CAGI5 loci","Match DNase tracks","Score REF/ALT sequence effects","Average locus correlations"] Individual claims | AlphaGenome Nature 2026 supplementary comparison tables 'Suppl Table 4 Variant performan'!A11:P11; Supplementary Methods p.30, Chromosome Splits for Variant Benchmarks; Supplementary Methods p.40, Benchmarking on CAGI5 MPRA; Table10 cell-type matching; ExtendedDataFig8 caption; methods: p.40, Benchmarking on the CAGI5 MPRA challenge; paper: Extended Data Fig.8a; tables: Suppl Table 4 Variant performan; evaluation index 9; sheet rows 10, 11 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nature version of record, 28 January 2026 | source checked automated source review · 2026-09-17 Audit detailsPrimary-source transcription and separate automated source review. No human sign-off or independent experimental reproduction. Field: Source artifact SHA-256: Hash scope: SHA-256 of exact retrieved original artifact bytes Format: xlsx |
| Diagram title Zero-shot CAGI5 MPRA activity-effect prediction (borzoi-ensemble-matched comparison): evaluation procedure Individual claims | alphagenome: Journal full-text XML 'Suppl Table 4 Variant performan'!A11:P11; Supplementary Methods p.30, Chromosome Splits for Variant Benchmarks; Supplementary Methods p.40, Benchmarking on CAGI5 MPRA; Table10 cell-type matching; ExtendedDataFig8 caption; methods: p.40, Benchmarking on the CAGI5 MPRA challenge; paper: Extended Data Fig.8a; tables: Suppl Table 4 Variant performan; evaluation index 9; sheet rows 10, 11 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Retrieved page snapshot; no immutable publisher revision supplied | source checked automated source review · 2026-09-17 Audit detailsPrimary-source transcription and separate automated source review. No human sign-off or independent experimental reproduction. Field: Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
| Diagram title Zero-shot CAGI5 MPRA activity-effect prediction (borzoi-ensemble-matched comparison): evaluation procedure Individual claims | AlphaGenome Nature 2026 supplementary methods 'Suppl Table 4 Variant performan'!A11:P11; Supplementary Methods p.30, Chromosome Splits for Variant Benchmarks; Supplementary Methods p.40, Benchmarking on CAGI5 MPRA; Table10 cell-type matching; ExtendedDataFig8 caption; methods: p.40, Benchmarking on the CAGI5 MPRA challenge; paper: Extended Data Fig.8a; tables: Suppl Table 4 Variant performan; evaluation index 9; sheet rows 10, 11 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 | source checked automated source review · 2026-09-17 Audit detailsPrimary-source transcription and separate automated source review. No human sign-off or independent experimental reproduction. Field: Source artifact SHA-256: Hash scope: SHA-256 of exact publisher PDF bytes Format: original_pdf |
| Diagram title Zero-shot CAGI5 MPRA activity-effect prediction (borzoi-ensemble-matched comparison): evaluation procedure Individual claims | AlphaGenome Nature 2026 supplementary comparison tables 'Suppl Table 4 Variant performan'!A11:P11; Supplementary Methods p.30, Chromosome Splits for Variant Benchmarks; Supplementary Methods p.40, Benchmarking on CAGI5 MPRA; Table10 cell-type matching; ExtendedDataFig8 caption; methods: p.40, Benchmarking on the CAGI5 MPRA challenge; paper: Extended Data Fig.8a; tables: Suppl Table 4 Variant performan; evaluation index 9; sheet rows 10, 11 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Nature version of record, 28 January 2026 | source checked automated source review · 2026-09-17 Audit detailsPrimary-source transcription and separate automated source review. No human sign-off or independent experimental reproduction. Field: Source artifact SHA-256: Hash scope: SHA-256 of exact retrieved original artifact bytes Format: xlsx |
| Dataset and biological context CAGI5 challenge effects with hg19 sequence and GENCODEv19 annotations; comparator-specific locus/context sets. Individual claims | alphagenome: Journal full-text XML 'Suppl Table 4 Variant performan'!A11:P11; Supplementary Methods p.30, Chromosome Splits for Variant Benchmarks; Supplementary Methods p.40, Benchmarking on CAGI5 MPRA; Table10 cell-type matching; ExtendedDataFig8 caption; methods: p.40, Benchmarking on the CAGI5 MPRA challenge; paper: Extended Data Fig.8a; tables: Suppl Table 4 Variant performan; evaluation index 9; sheet rows 10, 11 Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Retrieved page snapshot; no immutable publisher revision supplied | source checked automated source review · 2026-09-17 Audit detailsPrimary-source transcription and separate automated source review. No human sign-off or independent experimental reproduction. Field: 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-t4-protocol-9-row11
- areas
- dna-genomes
- entity level
- protocol
- version
- Nature version of record, 28 January 2026
- source evaluation index
- 9
- source table
- 4
- reference levels
- metric: mean_pearsonr_all; printed value: 0; numeric value: 0; source locator: Suppl Table 4 Variant performan!J11; note: Source reference quantity for relative-performance calculation, not a measured baseline run.
Related records
- benchmark: borzoi-ensemble (paper Table 4): Zero-shot CAGI5 MPRA activity-effect prediction (borzoi-ensemble-matched comparison)
- benchmark: AlphaGenome distilled cell-type-matched DNase scorer, Borzoi-matched locus subset: Zero-shot CAGI5 MPRA activity-effect prediction (borzoi-ensemble-matched comparison)
- benchmark: Zero-shot CAGI5 MPRA activity-effect prediction (borzoi-ensemble-matched comparison): evaluated data subset