Strengths and considerations
No source-reviewed explanatory claims are recorded here yet.
benchmark · protocol
ATAC prediction on held-out peaks (AlphaGenome paper)
Can reference sequence predict local ATAC profile shape and total signal at held-out peaks?
AlphaGenome Nature 2026 supplementary comparison tables; AlphaGenome Nature 2026 supplementary methods; alphagenome: Journal full-text XML · 'Suppl Table 3 Track performance'!A28:N28; 'Suppl Table 3 Track performance'!A29:N29; 'Suppl Table 3 Track performance'!A30:N30; Supplementary Methods p.21, Benchmarking Against Existing Methods; Main paper Extended Data Fig.3f,g caption; paper: Extended Data Fig.3f,g caption; methods: p.21, Benchmarking Against Existing Methods; tables: Suppl Table 3 Track performance; evaluation index 16; sheet rows 28, 29, 30At 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 | ChromBPNet test peak regions, fold 0. Only directly matching ENCODE experiment accessions are used.AlphaGenome Nature 2026 supplementary comparison tables; AlphaGenome Nature 2026 supplementary methods; alphagenome: Journal full-text XML · 'Suppl Table 3 Track performance'!A28:N28; 'Suppl Table 3 Track performance'!A29:N29; 'Suppl Table 3 Track performance'!A30:N30; Supplementary Methods p.21, Benchmarking Against Existing Methods; Main paper Extended Data Fig.3f,g caption; paper: Extended Data Fig.3f,g caption; methods: p.21, Benchmarking Against Existing Methods; tables: Suppl Table 3 Track performance; evaluation index 16; sheet rows 28, 29, 30 |
| Split | Intersect ChromBPNet fold-0 test peaks with regions that do not overlap AlphaGenome fold-0 training intervals.AlphaGenome Nature 2026 supplementary comparison tables; AlphaGenome Nature 2026 supplementary methods; alphagenome: Journal full-text XML · 'Suppl Table 3 Track performance'!A28:N28; 'Suppl Table 3 Track performance'!A29:N29; 'Suppl Table 3 Track performance'!A30:N30; Supplementary Methods p.21, Benchmarking Against Existing Methods; Main paper Extended Data Fig.3f,g caption; paper: Extended Data Fig.3f,g caption; methods: p.21, Benchmarking Against Existing Methods; tables: Suppl Table 3 Track performance; evaluation index 16; sheet rows 28, 29, 30 |
| Allowed inputs and adaptation | Reference DNA; predicted and observed base-resolution profiles on matched assay peaks.AlphaGenome Nature 2026 supplementary comparison tables; AlphaGenome Nature 2026 supplementary methods; alphagenome: Journal full-text XML · 'Suppl Table 3 Track performance'!A28:N28; 'Suppl Table 3 Track performance'!A29:N29; 'Suppl Table 3 Track performance'!A30:N30; Supplementary Methods p.21, Benchmarking Against Existing Methods; Main paper Extended Data Fig.3f,g caption; paper: Extended Data Fig.3f,g caption; methods: p.21, Benchmarking Against Existing Methods; tables: Suppl Table 3 Track performance; evaluation index 16; sheet rows 28, 29, 30 |
| Metrics as reported | log1p_count_pearsonr; pearsonr; profile jsdAlphaGenome Nature 2026 supplementary comparison tables; AlphaGenome Nature 2026 supplementary methods; alphagenome: Journal full-text XML · 'Suppl Table 3 Track performance'!A28:N28; 'Suppl Table 3 Track performance'!A29:N29; 'Suppl Table 3 Track performance'!A30:N30; Supplementary Methods p.21, Benchmarking Against Existing Methods; Main paper Extended Data Fig.3f,g caption; paper: Extended Data Fig.3f,g caption; methods: p.21, Benchmarking Against Existing Methods; tables: Suppl Table 3 Track performance; evaluation index 16; sheet rows 28, 29, 30 |
| Aggregation | Table3 reports task summary scalars; Extended Data Fig.3 shows per-cell-line comparisons. The inspected caption does not fully specify pooling across peaks/cell lines.AlphaGenome Nature 2026 supplementary comparison tables; AlphaGenome Nature 2026 supplementary methods; alphagenome: Journal full-text XML · 'Suppl Table 3 Track performance'!A28:N28; 'Suppl Table 3 Track performance'!A29:N29; 'Suppl Table 3 Track performance'!A30:N30; Supplementary Methods p.21, Benchmarking Against Existing Methods; Main paper Extended Data Fig.3f,g caption; paper: Extended Data Fig.3f,g caption; methods: p.21, Benchmarking Against Existing Methods; tables: Suppl Table 3 Track performance; evaluation index 16; sheet rows 28, 29, 30 |
| 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 3 Track performance'!A28:N28; 'Suppl Table 3 Track performance'!A29:N29; 'Suppl Table 3 Track performance'!A30:N30; Supplementary Methods p.21, Benchmarking Against Existing Methods; Main paper Extended Data Fig.3f,g caption; paper: Extended Data Fig.3f,g caption; methods: p.21, Benchmarking Against Existing Methods; tables: Suppl Table 3 Track performance; evaluation index 16; sheet rows 28, 29, 30 |
| 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
- Peer-model test peaks
- Remove AlphaGenome training overlap
- Align assay predictions and observations
- Evaluate count and shape metrics
What is tested
Can reference sequence predict local ATAC profile shape and total signal at held-out peaks?
AlphaGenome Nature 2026 supplementary comparison tables; AlphaGenome Nature 2026 supplementary methods; alphagenome: Journal full-text XML · 'Suppl Table 3 Track performance'!A28:N28; 'Suppl Table 3 Track performance'!A29:N29; 'Suppl Table 3 Track performance'!A30:N30; Supplementary Methods p.21, Benchmarking Against Existing Methods; Main paper Extended Data Fig.3f,g caption; paper: Extended Data Fig.3f,g caption; methods: p.21, Benchmarking Against Existing Methods; tables: Suppl Table 3 Track performance; evaluation index 16; sheet rows 28, 29, 30Procedure
Evaluate signal correlation, log-total-count correlation and profile JSD as separate metrics; retain only endpoints actually listed for this evaluation in Table3.
AlphaGenome Nature 2026 supplementary comparison tables; AlphaGenome Nature 2026 supplementary methods; alphagenome: Journal full-text XML · 'Suppl Table 3 Track performance'!A28:N28; 'Suppl Table 3 Track performance'!A29:N29; 'Suppl Table 3 Track performance'!A30:N30; Supplementary Methods p.21, Benchmarking Against Existing Methods; Main paper Extended Data Fig.3f,g caption; paper: Extended Data Fig.3f,g caption; methods: p.21, Benchmarking Against Existing Methods; tables: Suppl Table 3 Track performance; evaluation index 16; sheet rows 28, 29, 30Tested models and results
Release 2026-09-17-a757f4af4277 · 2 evaluations · 6 metric rows. Different protocols are not a single leaderboard.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| ChromBPNet (paper Table 3): ATAC prediction on held-out peaks Model: ChromBPNet (paper Table 3) · Benchmark: ATAC prediction on held-out peaks (AlphaGenome paper) · Dataset: ATAC prediction on held-out peaks: evaluated data subset Evaluate signal correlation, log-total-count correlation and profile JSD as separate metrics; retain only endpoints actually listed for this evaluation in Table3. Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.467 profile jsd Unit: dimensionless · Direction: lower Aggregation: Table3 reports task summary scalars; Extended Data Fig.3 shows per-cell-line comparisons. The inspected caption does not fully specify pooling across peaks/cell lines. | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 3 Track performance'!J30 Source checking is not independent reproduction. |
| 0.780 log1p_count_pearsonr Unit: correlation · Direction: higher Aggregation: Table3 reports task summary scalars; Extended Data Fig.3 shows per-cell-line comparisons. The inspected caption does not fully specify pooling across peaks/cell lines. | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 3 Track performance'!J29 Source checking is not independent reproduction. |
| 0.786 pearsonr Unit: correlation · Direction: higher Aggregation: Table3 reports task summary scalars; Extended Data Fig.3 shows per-cell-line comparisons. The inspected caption does not fully specify pooling across peaks/cell lines. | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 3 Track performance'!J28 Source checking is not independent reproduction. |
| AlphaGenome fold-0 track model on comparator-matched test peaks: ATAC prediction on held-out peaks Model: AlphaGenome fold-0 track model on comparator-matched test peaks · Benchmark: ATAC prediction on held-out peaks (AlphaGenome paper) · Dataset: ATAC prediction on held-out peaks: evaluated data subset Evaluate signal correlation, log-total-count correlation and profile JSD as separate metrics; retain only endpoints actually listed for this evaluation in Table3. Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.86 pearsonr Unit: correlation · Direction: higher Aggregation: Table3 reports task summary scalars; Extended Data Fig.3 shows per-cell-line comparisons. The inspected caption does not fully specify pooling across peaks/cell lines. | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 3 Track performance'!K28 Source checking is not independent reproduction. |
| 0.85 log1p_count_pearsonr Unit: correlation · Direction: higher Aggregation: Table3 reports task summary scalars; Extended Data Fig.3 shows per-cell-line comparisons. The inspected caption does not fully specify pooling across peaks/cell lines. | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 3 Track performance'!K29 Source checking is not independent reproduction. |
| 0.46 profile jsd Unit: dimensionless · Direction: lower Aggregation: Table3 reports task summary scalars; Extended Data Fig.3 shows per-cell-line comparisons. The inspected caption does not fully specify pooling across peaks/cell lines. | Uncertainty: unreported Scored: Not reported · Eligible: Not reported | source checkedAlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 3 Track performance'!K30 Source checking is not independent reproduction. |
Strengths and limitations
Limitations and conditions
- JSD is lower-is-better. The article calls it both Jensen–Shannon distance and divergence; the precise implementation is not resolved by these descriptions. Matching held-out intervals does not establish external pretraining decontamination.AlphaGenome Nature 2026 supplementary comparison tables; AlphaGenome Nature 2026 supplementary methods; alphagenome: Journal full-text XML · 'Suppl Table 3 Track performance'!A28:N28; 'Suppl Table 3 Track performance'!A29:N29; 'Suppl Table 3 Track performance'!A30:N30; Supplementary Methods p.21, Benchmarking Against Existing Methods; Main paper Extended Data Fig.3f,g caption; paper: Extended Data Fig.3f,g caption; methods: p.21, Benchmarking Against Existing Methods; tables: Suppl Table 3 Track performance; evaluation index 16; sheet rows 28, 29, 30
- 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 3 Track performance'!A28:N28; 'Suppl Table 3 Track performance'!A29:N29; 'Suppl Table 3 Track performance'!A30:N30; Supplementary Methods p.21, Benchmarking Against Existing Methods; Main paper Extended Data Fig.3f,g caption; paper: Extended Data Fig.3f,g caption; methods: p.21, Benchmarking Against Existing Methods; tables: Suppl Table 3 Track performance; evaluation index 16; sheet rows 28, 29, 30
Profile review details
Primary-source transcription and separate automated source review. No human sign-off or independent experimental reproduction.
Stable record: alphagenome-2026-t3-protocol-16Evidence 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 3 Track performance'!A28:N28; 'Suppl Table 3 Track performance'!A29:N29; 'Suppl Table 3 Track performance'!A30:N30; Supplementary Methods p.21, Benchmarking Against Existing Methods; Main paper Extended Data Fig.3f,g caption; paper: Extended Data Fig.3f,g caption; methods: p.21, Benchmarking Against Existing Methods; tables: Suppl Table 3 Track performance; evaluation index 16; sheet rows 28, 29, 30 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 3 Track performance'!A28:N28; 'Suppl Table 3 Track performance'!A29:N29; 'Suppl Table 3 Track performance'!A30:N30; Supplementary Methods p.21, Benchmarking Against Existing Methods; Main paper Extended Data Fig.3f,g caption; paper: Extended Data Fig.3f,g caption; methods: p.21, Benchmarking Against Existing Methods; tables: Suppl Table 3 Track performance; evaluation index 16; sheet rows 28, 29, 30 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 3 Track performance'!A28:N28; 'Suppl Table 3 Track performance'!A29:N29; 'Suppl Table 3 Track performance'!A30:N30; Supplementary Methods p.21, Benchmarking Against Existing Methods; Main paper Extended Data Fig.3f,g caption; paper: Extended Data Fig.3f,g caption; methods: p.21, Benchmarking Against Existing Methods; tables: Suppl Table 3 Track performance; evaluation index 16; sheet rows 28, 29, 30 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 ["Peer-model test peaks","Remove AlphaGenome training overlap","Align assay predictions and observations","Evaluate count and shape metrics"] Individual claims | alphagenome: Journal full-text XML 'Suppl Table 3 Track performance'!A28:N28; 'Suppl Table 3 Track performance'!A29:N29; 'Suppl Table 3 Track performance'!A30:N30; Supplementary Methods p.21, Benchmarking Against Existing Methods; Main paper Extended Data Fig.3f,g caption; paper: Extended Data Fig.3f,g caption; methods: p.21, Benchmarking Against Existing Methods; tables: Suppl Table 3 Track performance; evaluation index 16; sheet rows 28, 29, 30 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 ["Peer-model test peaks","Remove AlphaGenome training overlap","Align assay predictions and observations","Evaluate count and shape metrics"] Individual claims | AlphaGenome Nature 2026 supplementary methods 'Suppl Table 3 Track performance'!A28:N28; 'Suppl Table 3 Track performance'!A29:N29; 'Suppl Table 3 Track performance'!A30:N30; Supplementary Methods p.21, Benchmarking Against Existing Methods; Main paper Extended Data Fig.3f,g caption; paper: Extended Data Fig.3f,g caption; methods: p.21, Benchmarking Against Existing Methods; tables: Suppl Table 3 Track performance; evaluation index 16; sheet rows 28, 29, 30 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 ["Peer-model test peaks","Remove AlphaGenome training overlap","Align assay predictions and observations","Evaluate count and shape metrics"] Individual claims | AlphaGenome Nature 2026 supplementary comparison tables 'Suppl Table 3 Track performance'!A28:N28; 'Suppl Table 3 Track performance'!A29:N29; 'Suppl Table 3 Track performance'!A30:N30; Supplementary Methods p.21, Benchmarking Against Existing Methods; Main paper Extended Data Fig.3f,g caption; paper: Extended Data Fig.3f,g caption; methods: p.21, Benchmarking Against Existing Methods; tables: Suppl Table 3 Track performance; evaluation index 16; sheet rows 28, 29, 30 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 ATAC prediction on held-out peaks: evaluation procedure Individual claims | alphagenome: Journal full-text XML 'Suppl Table 3 Track performance'!A28:N28; 'Suppl Table 3 Track performance'!A29:N29; 'Suppl Table 3 Track performance'!A30:N30; Supplementary Methods p.21, Benchmarking Against Existing Methods; Main paper Extended Data Fig.3f,g caption; paper: Extended Data Fig.3f,g caption; methods: p.21, Benchmarking Against Existing Methods; tables: Suppl Table 3 Track performance; evaluation index 16; sheet rows 28, 29, 30 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 ATAC prediction on held-out peaks: evaluation procedure Individual claims | AlphaGenome Nature 2026 supplementary methods 'Suppl Table 3 Track performance'!A28:N28; 'Suppl Table 3 Track performance'!A29:N29; 'Suppl Table 3 Track performance'!A30:N30; Supplementary Methods p.21, Benchmarking Against Existing Methods; Main paper Extended Data Fig.3f,g caption; paper: Extended Data Fig.3f,g caption; methods: p.21, Benchmarking Against Existing Methods; tables: Suppl Table 3 Track performance; evaluation index 16; sheet rows 28, 29, 30 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 ATAC prediction on held-out peaks: evaluation procedure Individual claims | AlphaGenome Nature 2026 supplementary comparison tables 'Suppl Table 3 Track performance'!A28:N28; 'Suppl Table 3 Track performance'!A29:N29; 'Suppl Table 3 Track performance'!A30:N30; Supplementary Methods p.21, Benchmarking Against Existing Methods; Main paper Extended Data Fig.3f,g caption; paper: Extended Data Fig.3f,g caption; methods: p.21, Benchmarking Against Existing Methods; tables: Suppl Table 3 Track performance; evaluation index 16; sheet rows 28, 29, 30 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 ChromBPNet test peak regions, fold 0. Only directly matching ENCODE experiment accessions are used. Individual claims | alphagenome: Journal full-text XML 'Suppl Table 3 Track performance'!A28:N28; 'Suppl Table 3 Track performance'!A29:N29; 'Suppl Table 3 Track performance'!A30:N30; Supplementary Methods p.21, Benchmarking Against Existing Methods; Main paper Extended Data Fig.3f,g caption; paper: Extended Data Fig.3f,g caption; methods: p.21, Benchmarking Against Existing Methods; tables: Suppl Table 3 Track performance; evaluation index 16; sheet rows 28, 29, 30 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-t3-protocol-16
- areas
- dna-genomes
- entity level
- protocol
- version
- Nature version of record, 28 January 2026
- source evaluation index
- 16
- source table
- 3
- reference levels
- metric: pearsonr; printed value: 0; numeric value: 0; source locator: Suppl Table 3 Track performance!H28; note: Source reference quantity for relative-performance calculation, not a measured baseline run.; metric: log1p_count_pearsonr; printed value: 0; numeric value: 0; source locator: Suppl Table 3 Track performance!H29; note: Source reference quantity for relative-performance calculation, not a measured baseline run.; metric: profile jsd; printed value: 0; numeric value: 0; source locator: Suppl Table 3 Track performance!H30; note: Source reference quantity for relative-performance calculation, not a measured baseline run.