SGE held-out screens pooled, SNVs and indels, AUPRC (AlphaGenome Atlas)
Pool SNVs and indels from the ten held-out SGE screens and separate functionally abnormal from normal variants, scored by AUPRC.
Overview
An explanatory profile has not yet been reviewed for this record.
Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.
5 recorded evaluations, 5 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.
Results
Results are available, but no reviewed comparison panel is linked in this release.
All evaluations
5 evaluations · 5 results. Different protocols are not a single leaderboard.
Protocol: SGE held-out screens pooled, SNVs and indels, AUPRC (AlphaGenome Atlas) · Dataset: Saturation genome editing screens of 13 genes from 14 studies (AlphaGenome Atlas)
Sorted by AUPRC (pooled held-out SGE screens, functionally abnormal vs normal, SNVs and indels) (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.
| Tested configuration | AUPRC (pooled held-out SGE screens, functionally abnormal vs normal, SNVs and indels) |
|---|---|
| AVI six-model ensemble (AlphaGenome Atlas v1)Evaluation | 0.759 (best in column) |
| CADD v1.7 GRCh38, precomputed plus pipeline for missing indels (AlphaGenome Atlas v1)Evaluation | 0.653 |
| Zoonomia Cactus 241-way phyloP (AlphaGenome Atlas v1)Evaluation | 0.408 |
| PhastCons 470-way (AlphaGenome Atlas v1)Evaluation | 0.316 |
| gnomAD v4.1 genome allele frequency, negated (AlphaGenome Atlas v1)Evaluation | 0.2 |
All 5 result rows with coverage, uncertainty and sources
Filter evaluations
Applied filters: All linked evaluations
Source checking is not independent reproduction. Release 2026-11-02-a7f03c9e55a5.
Methods and evaluation design
Procedure, tasks and evaluated configurations
Recorded evaluations
Each evaluation records what was tested and under which conditions.
- AVI on pooled held-out SGE screens, all-variants (AlphaGenome Atlas fig. S7F)
- Cactus 241-way on pooled held-out SGE screens, all-variants (AlphaGenome Atlas fig. S7F)
- CADD v1.7 on pooled held-out SGE screens, all-variants (AlphaGenome Atlas fig. S7F)
- gnomAD allele frequency on pooled held-out SGE screens, all-variants (AlphaGenome Atlas fig. S7F)
- Phastcons 470-way on pooled held-out SGE screens, all-variants (AlphaGenome Atlas fig. S7F)
Baseline coverage
Reference methods help show what a model adds beyond simple controls. We track a null control and a conventional method for each protocol.
0 of 2 active baseline roles have published Rewire measurements in this release. Measurements on a selected protocol do not establish coverage of an entire suite.
No execution recipe linked to this protocol. Recipe availability does not establish a completed evaluation.
- Author-reported evaluations
- 5
Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.
Null control
Proposed control: requires review
Select a task-valid null control after reviewing inputs and metric
Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.
This is a suggested selection rule, not a validated method or a measured score.
Conventional reference
Proposed control: requires review
Select an upstream conventional reference after reviewing the full protocol
Protocol-specific applicability, permitted inputs, access, split, evaluator and execution requirements need review before implementation or execution.
This is a suggested selection rule, not a validated method or a measured score.
Protocol coverage CSV (gzip) · Model evaluation matrix (gzip) · Source table (gzip) · Release and checksums (gzip)
Coverage is derived from release 2026-11-02-a7f03c9e55a5. Source citations describe the original records; they do not validate an unreviewed baseline proposal. No results have been generated by this audit.
Run instructions
No runnable recipe has been reviewed for this protocol. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.
Evidence
Source checking verifies the cited claim or transcription. It does not establish independent reproduction.
Evidence table
Inspect claims, sources and review details
Trace each statement to its source and review. A context-only reference supports the record generally; it does not verify an individual field. Source checking does not reproduce an experiment.
One row per statement and cited source. Multiple citations are not independent evaluations. Shared locators are labelled explicitly.
0 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|
No evidence rows match these filters. Choose another scope or clear the search.
Sources and history
Release 2026-11-02-a7f03c9e55a5 · Record review: source checked
1 source record and release history
- AlphaGenome Atlas: in silico mutagenesis of the entire human genome (Cheng, Taylor, Nicolaisen et al., medRxiv 2026) · Original source · medRxiv preprint version 1, posted 2026-09-20; full-text PDF with supplementary figures and tables (83 pages)
Technical metadata and extraction receipts
Stable ID: ag-atlas-20261019-protocol-sge-pooled-all-variants-auprc
- areas
- dna-genomes
- contexts
- research
- metric
- auprc
- metric direction
- higher
- source locator
- fig. S7F (left) and legend (page 57)
- task link exemption
- No task or benchmark in the store covers saturation genome editing functional classes; left unlinked on purpose so the discrepancy rules treat its scope as unknown rather than guess (#208). Reviewed 2026-11-01.
Related records
- uses data: Saturation genome editing screens of 13 genes from 14 studies (AlphaGenome Atlas)
- assessment: AVI on pooled held-out SGE screens, all-variants (AlphaGenome Atlas fig. S7F)
- assessment: Cactus 241-way on pooled held-out SGE screens, all-variants (AlphaGenome Atlas fig. S7F)
- assessment: CADD v1.7 on pooled held-out SGE screens, all-variants (AlphaGenome Atlas fig. S7F)
- assessment: gnomAD allele frequency on pooled held-out SGE screens, all-variants (AlphaGenome Atlas fig. S7F)
- assessment: Phastcons 470-way on pooled held-out SGE screens, all-variants (AlphaGenome Atlas fig. S7F)