Protocol

ATAC prediction on held-out peaks (AlphaGenome paper)

Can reference sequence predict local ATAC profile shape and total signal at held-out peaks?

Sources (3)

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

2 evaluations · 6 metric rows

At a glance

Inputs, training, access and other details

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.

Data, procedure and scoring
Property	Description and evidence
Dataset and biological context	ChromBPNet test peak regions, fold 0. Only directly matching ENCODE experiment accessions are used. Sources (3) 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. Sources (3) 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. Sources (3) 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 jsd Sources (3) 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
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. Sources (3) 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 sources Sources (3) 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
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

How it worksATAC prediction on held-out peaks: evaluation procedure

Conceptual summary of the cited procedure; model-specific conditions are given below.

Sources (3)

What is tested

Can reference sequence predict local ATAC profile shape and total signal at held-out peaks?

Sources (3)

Procedure

Evaluate signal correlation, log-total-count correlation and profile JSD as separate metrics; retain only endpoints actually listed for this evaluation in Table3.

Sources (3)

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Published comparisons

Explore the results reported under one evaluation protocol. Each figure keeps its source, dataset and metric together; it is not a ranking across studies.

Comparison and metric

ATAC prediction on held-out peaks (AlphaGenome paper)

profile jsd (dimensionless) · Lower values are better for this metric.

Can reference sequence predict local ATAC profile shape and total signal at held-out peaks?

Evaluation protocol · ATAC prediction on held-out peaks: evaluated data subset

ChromBPNet (paper Table 3) · Configuration · Author-reported evaluation0.467
AlphaGenome fold-0 track model on comparator-matched test peaks · Configuration · Author-reported evaluation0.46

Source order is preserved. Plotted marks show point estimates; uncertainty, where reported, is retained in the printed values and table. Differences do not establish statistical significance.

AlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 3 Track performance'!J30; 'Suppl Table 3 Track performance'!K30

Values, uncertainty and evidence

profile jsd: original source values
Tested entity	Printed value	Uncertainty	Evidence
ChromBPNet (paper Table 3) · Configuration	0.467 dimensionless	Not reported	Author-reported evaluation · source checkedAlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 3 Track performance'!J30
AlphaGenome fold-0 track model on comparator-matched test peaks · Configuration	0.46 dimensionless	Not reported	Author-reported evaluation · source checkedAlphaGenome Nature 2026 supplementary comparison tables · 'Suppl Table 3 Track performance'!K30

Scope and limitations

This is the AlphaGenome paper’s comparison. Source-checked scores are not independent reproductions.
Model inputs, training and inference budgets differ or remain partly unextracted. This figure does not establish a controlled architectural advantage.
Superseded and quarantined score conflicts are excluded; comparator-specific subsets remain separate.

Source transcription and grouping reviewed by automated source review on 2026-09-17. These experiments were not independently reproduced by rewire.

Tested entities and results

Release 2026-09-17-d277315f7d76 · 2 evaluations · 6 metric rows. Different protocols are not a single leaderboard.

Evaluation setupMetricEvidence origin

Results grouped by the exact reported evaluation
Metric and finding	Coverage and uncertainty	Evidence
ChromBPNet (paper Table 3): ATAC prediction on held-out peaks Configuration: ChromBPNet (paper Table 3)Protocol: ATAC prediction on held-out peaks (AlphaGenome paper)Dataset subset: 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 Configuration: AlphaGenome fold-0 track model on comparator-matched test peaksProtocol: ATAC prediction on held-out peaks (AlphaGenome paper)Dataset subset: 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.

Papers and result coverage

Last literature check: 2026-09-17. Original Nature paper comparison; numerical source transcription was separately reviewed. No independent model execution.

Paper or primary resource	Version	Reference
alphagenome: Journal full-text XML	Retrieved page snapshot; no immutable publisher revision supplied	Read source
AlphaGenome Nature 2026 supplementary comparison tables	Nature version of record, 28 January 2026	Read source DOI: 10.1038/s41586-025-10014-0
AlphaGenome Nature 2026 supplementary methods	Supplement to Nature version of record, 28 January 2026; content hash pinned	Read source

What is still missing

Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.
Subsequent studies use different datasets and are not pooled with this paper.

Search and extraction details

complete comparison extracted

Searches

AlphaGenome benchmark evaluation Nature 2026 supplementary Tables 3 4 regulatory variant prediction
AlphaGenome independent evaluation benchmark 2026 variant effects

Evidence locations

'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

Strengths and limitations

Strengths and considerations

No source-reviewed explanatory claims are recorded here yet.

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.
Sources (3)
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.
Sources (3)
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-16

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.

42 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-17-d277315f7d76
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 Original source ↗ '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 Retrieved: 2026-09-16T19:53:03.009088+00:00	source checked automated source review · 2026-09-17 Audit details Primary-source transcription and separate automated source review. No human sign-off or independent experimental reproduction. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `d159b791fc6cb7b679c151727b7b05a6e5b6388b08a89b675014983d85b6df36` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram caption Conceptual summary of the cited procedure; model-specific conditions are given below. Individual claims	AlphaGenome Nature 2026 supplementary methods Original source ↗ '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 Retrieved: 2026-09-17T06:37:01.778972+00:00	source checked automated source review · 2026-09-17 Audit details Primary-source transcription and separate automated source review. No human sign-off or independent experimental reproduction. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `86b2e6a07543e3c201e2e157a3e9c6eb5235ff13eb8a5224f6fcb6fe1808d4c0` Hash scope: SHA-256 of exact publisher PDF bytes Format: original_pdf Inspected artifact
Diagram caption Conceptual summary of the cited procedure; model-specific conditions are given below. Individual claims	AlphaGenome Nature 2026 supplementary comparison tables Original source ↗ '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 Retrieved: 2026-09-17T06:31:06.887921+00:00	source checked automated source review · 2026-09-17 Audit details Primary-source transcription and separate automated source review. No human sign-off or independent experimental reproduction. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `833cb78b6ae6fe39415cfff296ac00c48d800326139f13eb307531a1cc133154` Hash scope: SHA-256 of exact retrieved original artifact bytes Format: xlsx Inspected artifact
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 Original source ↗ '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 Retrieved: 2026-09-16T19:53:03.009088+00:00	source checked automated source review · 2026-09-17 Audit details Primary-source transcription and separate automated source review. No human sign-off or independent experimental reproduction. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `d159b791fc6cb7b679c151727b7b05a6e5b6388b08a89b675014983d85b6df36` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected 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 Original source ↗ '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 Retrieved: 2026-09-17T06:37:01.778972+00:00	source checked automated source review · 2026-09-17 Audit details Primary-source transcription and separate automated source review. No human sign-off or independent experimental reproduction. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `86b2e6a07543e3c201e2e157a3e9c6eb5235ff13eb8a5224f6fcb6fe1808d4c0` Hash scope: SHA-256 of exact publisher PDF bytes Format: original_pdf Inspected 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 comparison tables Original source ↗ '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 Retrieved: 2026-09-17T06:31:06.887921+00:00	source checked automated source review · 2026-09-17 Audit details Primary-source transcription and separate automated source review. No human sign-off or independent experimental reproduction. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `833cb78b6ae6fe39415cfff296ac00c48d800326139f13eb307531a1cc133154` Hash scope: SHA-256 of exact retrieved original artifact bytes Format: xlsx Inspected artifact
Diagram title ATAC prediction on held-out peaks: evaluation procedure Individual claims	alphagenome: Journal full-text XML Original source ↗ '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 Retrieved: 2026-09-16T19:53:03.009088+00:00	source checked automated source review · 2026-09-17 Audit details Primary-source transcription and separate automated source review. No human sign-off or independent experimental reproduction. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `d159b791fc6cb7b679c151727b7b05a6e5b6388b08a89b675014983d85b6df36` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram title ATAC prediction on held-out peaks: evaluation procedure Individual claims	AlphaGenome Nature 2026 supplementary methods Original source ↗ '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 Retrieved: 2026-09-17T06:37:01.778972+00:00	source checked automated source review · 2026-09-17 Audit details Primary-source transcription and separate automated source review. No human sign-off or independent experimental reproduction. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `86b2e6a07543e3c201e2e157a3e9c6eb5235ff13eb8a5224f6fcb6fe1808d4c0` Hash scope: SHA-256 of exact publisher PDF bytes Format: original_pdf Inspected artifact
Diagram title ATAC prediction on held-out peaks: evaluation procedure Individual claims	AlphaGenome Nature 2026 supplementary comparison tables Original source ↗ '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 Retrieved: 2026-09-17T06:31:06.887921+00:00	source checked automated source review · 2026-09-17 Audit details Primary-source transcription and separate automated source review. No human sign-off or independent experimental reproduction. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `833cb78b6ae6fe39415cfff296ac00c48d800326139f13eb307531a1cc133154` Hash scope: SHA-256 of exact retrieved original artifact bytes Format: xlsx Inspected artifact
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 Original source ↗ '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 Retrieved: 2026-09-16T19:53:03.009088+00:00	source checked automated source review · 2026-09-17 Audit details Primary-source transcription and separate automated source review. No human sign-off or independent experimental reproduction. Field: `attributes.profile.facts.0.value` Source artifact SHA-256: `d159b791fc6cb7b679c151727b7b05a6e5b6388b08a89b675014983d85b6df36` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact

All evidence (CSV)All evidence (JSONL)How to read the evidence

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

Download this release

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.
comparison panels: id: paper-figure-cc960d3b44baddbf7c; title: ATAC prediction on held-out peaks (AlphaGenome paper); protocol id: alphagenome-2026-t3-protocol-16; dataset id: alphagenome-2026-t3-dataset-16; metric: profile jsd; unit: dimensionless; direction: lower; result ids: alphagenome-2026-result-270237f434fc9d2a; alphagenome-2026-result-c858347ce602e204; source ids: source-alphagenome-nature2026-tables; source locator: 'Suppl Table 3 Track performance'!J30; 'Suppl Table 3 Track performance'!K30; context: Can reference sequence predict local ATAC profile shape and total signal at held-out peaks?; caveats: This is the AlphaGenome paper’s comparison. Source-checked scores are not independent reproductions.; Model inputs, training and inference budgets differ or remain partly unextracted. This figure does not establish a controlled architectural advantage.; Superseded and quarantined score conflicts are excluded; comparator-specific subsets remain separate.; review: method: automated_source_review; date: 2026-09-17; id: paper-figure-68e7f1e69758f8dfb4; title: ATAC prediction on held-out peaks (AlphaGenome paper); protocol id: alphagenome-2026-t3-protocol-16; dataset id: alphagenome-2026-t3-dataset-16; metric: pearsonr; unit: correlation; direction: higher; result ids: alphagenome-2026-result-3b25512692b45cae; alphagenome-2026-result-aca65e3609d76bef; source ids: source-alphagenome-nature2026-tables; source locator: 'Suppl Table 3 Track performance'!K28; 'Suppl Table 3 Track performance'!J28; context: Can reference sequence predict local ATAC profile shape and total signal at held-out peaks?; caveats: This is the AlphaGenome paper’s comparison. Source-checked scores are not independent reproductions.; Model inputs, training and inference budgets differ or remain partly unextracted. This figure does not establish a controlled architectural advantage.; Superseded and quarantined score conflicts are excluded; comparator-specific subsets remain separate.; review: method: automated_source_review; date: 2026-09-17; id: paper-figure-339d0791039294fb6d; title: ATAC prediction on held-out peaks (AlphaGenome paper); protocol id: alphagenome-2026-t3-protocol-16; dataset id: alphagenome-2026-t3-dataset-16; metric: log1p_count_pearsonr; unit: correlation; direction: higher; result ids: alphagenome-2026-result-6436c97f2f91b1f2; alphagenome-2026-result-9e659109fec02018; source ids: source-alphagenome-nature2026-tables; source locator: 'Suppl Table 3 Track performance'!K29; 'Suppl Table 3 Track performance'!J29; context: Can reference sequence predict local ATAC profile shape and total signal at held-out peaks?; caveats: This is the AlphaGenome paper’s comparison. Source-checked scores are not independent reproductions.; Model inputs, training and inference budgets differ or remain partly unextracted. This figure does not establish a controlled architectural advantage.; Superseded and quarantined score conflicts are excluded; comparator-specific subsets remain separate.; review: method: automated_source_review; date: 2026-09-17
benchmark research: review date: 2026-09-17; status: complete_comparison_extracted; primary sources: evidence-official-56e5abfb5f12f1cd3b20; source-alphagenome-nature2026-tables; source-alphagenome-nature2026-supplementary-methods; inspected locators: '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; searched queries: AlphaGenome benchmark evaluation Nature 2026 supplementary Tables 3 4 regulatory variant prediction; AlphaGenome independent evaluation benchmark 2026 variant effects; gaps: Individual protocol input manifests, scoring counts and uncertainty remain unextracted where explicitly marked.; Subsequent studies use different datasets and are not pooled with this paper.; claim scope: Original Nature paper comparison; numerical source transcription was separately reviewed. No independent model execution.
legacy kinds: benchmark
entity classification: review date: 2026-09-17; rationale: The source-backed record identifies a specified evaluated procedure and its dataset/split/scoring context. Classify it as a protocol while preserving version and comparison restrictions.; source ids: source-alphagenome-nature2026-tables; source-alphagenome-nature2026-supplementary-methods; evidence-official-56e5abfb5f12f1cd3b20; source locator: '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; ambiguities: None recorded

Related records

Suggest a correction