Protocol

Feng pathogenic-versus-common SNP classification

Table 5 pathogenic-versus-common SNP classification; Feng et al. 2025 source-reported protocol.

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.

22 recorded evaluations, 55 metric rows. A comparison chart has not yet been validated for these results. The table retains the individual findings and their sources.

View coverage and remaining gaps across all benchmarks

Results

Results are available, but no reviewed comparison panel is linked in this release.

All evaluations

22 evaluations · 55 results. Different protocols are not a single leaderboard.

Protocol: Feng pathogenic-versus-common SNP classification

Sorted by AUROC (task: pathogenic vs common snp; outer test group 1 only (chromosomes 3, 6, 9, 12, 16, 18, 19, 21), not averaged) (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	Protocol and dataset	AUROC (task: pathogenic vs common snp; outer test group 1 only (chromosomes 3, 6, 9, 12, 16, 18, 19, 21), not averaged)	AUROC (task: pathogenic vs common snp; outer test group 2 only (chromosomes 2, 5, 11, 14, 17, 20, 22, X), not averaged)	AUROC (task: pathogenic vs common snp; outer test group 3 only (chromosomes 1, 4, 7, 8, 10, 13, 15), not averaged)	AUROC (task: pathogenic vs common snp)	Cohen's d (task: pathogenic vs common snp)
NT-v2 (pathogenic/common SNP classification)Evaluation	Feng pathogenic/common SNP short-window dataset	0.731 (best in column)	0.732 (best in column)	0.733 (best in column)	Not reported	Not reported
Enformer, hidden states* (pathogenic/common SNP classification)Evaluation	Feng pathogenic/common SNP long-window dataset	0.715	0.657	0.692	Not reported	Not reported
Caduceus-Ph (pathogenic/common SNP classification)Evaluation	Feng pathogenic/common SNP short-window dataset	0.704	0.688	0.696	Not reported	Not reported
Sei, hidden states* (pathogenic/common SNP classification)Evaluation	Feng pathogenic/common SNP short-window dataset	0.686	0.647	0.646	Not reported	Not reported
Enformer, output tracks* (pathogenic/common SNP classification)Evaluation	Feng pathogenic/common SNP long-window dataset	0.681	0.648	0.67	Not reported	Not reported
Sei, output tracks* (pathogenic/common SNP classification)Evaluation	Feng pathogenic/common SNP short-window dataset	0.675	0.649	0.667	Not reported	Not reported
HyenaDNA-450K, long sequence (pathogenic/common SNP classification)Evaluation	Feng pathogenic/common SNP long-window dataset	0.636	0.622	0.621	Not reported	Not reported
Caduceus-Ph, long sequence (pathogenic/common SNP classification)Evaluation	Feng pathogenic/common SNP long-window dataset	0.63	0.618	0.625	Not reported	Not reported
HyenaDNA (pathogenic/common SNP classification)Evaluation	Feng pathogenic/common SNP short-window dataset	0.624	0.616	0.596	Not reported	Not reported
GROVER (pathogenic/common SNP classification)Evaluation	Feng pathogenic/common SNP short-window dataset	0.606	0.594	0.609	Not reported	Not reported
DNABERT-2 (pathogenic/common SNP classification)Evaluation	Feng pathogenic/common SNP short-window dataset	0.547	0.532	0.535	Not reported	Not reported
Caduceus-Ph (pathogenic/common SNP classification)Evaluation	Feng pathogenic/common SNP short-window dataset	Not reported	Not reported	Not reported	0.696	0.735
Caduceus-Ph, long sequence (pathogenic/common SNP classification)Evaluation	Feng pathogenic/common SNP long-window dataset	Not reported	Not reported	Not reported	0.624	0.462
DNABERT-2 (pathogenic/common SNP classification)Evaluation	Feng pathogenic/common SNP short-window dataset	Not reported	Not reported	Not reported	0.538	0.134
Enformer, hidden states* (pathogenic/common SNP classification)Evaluation	Feng pathogenic/common SNP long-window dataset	Not reported	Not reported	Not reported	0.688	0.727
Enformer, output tracks* (pathogenic/common SNP classification)Evaluation	Feng pathogenic/common SNP long-window dataset	Not reported	Not reported	Not reported	0.666	0.654
GROVER (pathogenic/common SNP classification)Evaluation	Feng pathogenic/common SNP short-window dataset	Not reported	Not reported	Not reported	0.603	0.369
HyenaDNA-450K, long sequence (pathogenic/common SNP classification)Evaluation	Feng pathogenic/common SNP long-window dataset	Not reported	Not reported	Not reported	0.626	0.449
HyenaDNA (pathogenic/common SNP classification)Evaluation	Feng pathogenic/common SNP short-window dataset	Not reported	Not reported	Not reported	0.612	0.395
NT-v2 (pathogenic/common SNP classification)Evaluation	Feng pathogenic/common SNP short-window dataset	Not reported	Not reported	Not reported	0.732 (best in column)	0.881
Sei, hidden states* (pathogenic/common SNP classification)Evaluation	Feng pathogenic/common SNP short-window dataset	Not reported	Not reported	Not reported	0.66	0.557
Sei, output tracks* (pathogenic/common SNP classification)Evaluation	Feng pathogenic/common SNP short-window dataset	Not reported	Not reported	Not reported	0.664	0.605

All 55 result rows with coverage, uncertainty and sources

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
Tested configuration	Protocol and dataset	Finding	Evidence and details
Configuration: Caduceus-Ph (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP short-window dataset	0.696 AUROC (task: pathogenic vs common snp) unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus-Ph pathogenic/common SNP evaluation Table 5, frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 5, Caduceus-Ph row, AUC column (deterministic XML extraction)
Configuration: Caduceus-Ph (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP short-window dataset	0.735 Cohen's d (task: pathogenic vs common snp) unitless · unknown Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus-Ph pathogenic/common SNP evaluation Table 5, frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 5, Caduceus-Ph row, Cohen's d column (deterministic XML extraction). Signed effect size; the source does not state a universal desirable sign/direction, so direction is recorded as unknown rather than assumed higher-is-better.
Configuration: Caduceus-Ph, long sequence (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP long-window dataset	0.624 AUROC (task: pathogenic vs common snp) unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus-Ph, long sequence pathogenic/common SNP evaluation Table 5, frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 5, Caduceus-Ph, long sequence row, AUC column (deterministic XML extraction)
Configuration: Caduceus-Ph, long sequence (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP long-window dataset	0.462 Cohen's d (task: pathogenic vs common snp) unitless · unknown Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus-Ph, long sequence pathogenic/common SNP evaluation Table 5, frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 5, Caduceus-Ph, long sequence row, Cohen's d column (deterministic XML extraction). Signed effect size; the source does not state a universal desirable sign/direction, so direction is recorded as unknown rather than assumed higher-is-better.
Configuration: DNABERT-2 (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP short-window dataset	0.538 AUROC (task: pathogenic vs common snp) unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT-2 pathogenic/common SNP evaluation Table 5, frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 5, DNABERT-2 row, AUC column (deterministic XML extraction)
Configuration: DNABERT-2 (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP short-window dataset	0.134 Cohen's d (task: pathogenic vs common snp) unitless · unknown Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source DNABERT-2 pathogenic/common SNP evaluation Table 5, frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 5, DNABERT-2 row, Cohen's d column (deterministic XML extraction). Signed effect size; the source does not state a universal desirable sign/direction, so direction is recorded as unknown rather than assumed higher-is-better.
Configuration: Enformer, hidden states* (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP long-window dataset	0.688 AUROC (task: pathogenic vs common snp) unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Enformer, hidden states* pathogenic/common SNP evaluation Table 5, frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 5, Enformer, hidden states* row, AUC column (deterministic XML extraction)
Configuration: Enformer, hidden states* (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP long-window dataset	0.727 Cohen's d (task: pathogenic vs common snp) unitless · unknown Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Enformer, hidden states* pathogenic/common SNP evaluation Table 5, frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 5, Enformer, hidden states* row, Cohen's d column (deterministic XML extraction). Signed effect size; the source does not state a universal desirable sign/direction, so direction is recorded as unknown rather than assumed higher-is-better.
Configuration: Enformer, output tracks* (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP long-window dataset	0.666 AUROC (task: pathogenic vs common snp) unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Enformer, output tracks* pathogenic/common SNP evaluation Table 5, frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 5, Enformer, output tracks* row, AUC column (deterministic XML extraction)
Configuration: Enformer, output tracks* (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP long-window dataset	0.654 Cohen's d (task: pathogenic vs common snp) unitless · unknown Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Enformer, output tracks* pathogenic/common SNP evaluation Table 5, frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 5, Enformer, output tracks* row, Cohen's d column (deterministic XML extraction). Signed effect size; the source does not state a universal desirable sign/direction, so direction is recorded as unknown rather than assumed higher-is-better.
Configuration: GROVER (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP short-window dataset	0.603 AUROC (task: pathogenic vs common snp) unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GROVER pathogenic/common SNP evaluation Table 5, frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 5, GROVER row, AUC column (deterministic XML extraction)
Configuration: GROVER (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP short-window dataset	0.369 Cohen's d (task: pathogenic vs common snp) unitless · unknown Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source GROVER pathogenic/common SNP evaluation Table 5, frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 5, GROVER row, Cohen's d column (deterministic XML extraction). Signed effect size; the source does not state a universal desirable sign/direction, so direction is recorded as unknown rather than assumed higher-is-better.
Configuration: HyenaDNA-450K, long sequence (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP long-window dataset	0.626 AUROC (task: pathogenic vs common snp) unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source HyenaDNA-450K, long sequence pathogenic/common SNP evaluation Table 5, frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 5, HyenaDNA-450K, long sequence row, AUC column (deterministic XML extraction)
Configuration: HyenaDNA-450K, long sequence (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP long-window dataset	0.449 Cohen's d (task: pathogenic vs common snp) unitless · unknown Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source HyenaDNA-450K, long sequence pathogenic/common SNP evaluation Table 5, frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 5, HyenaDNA-450K, long sequence row, Cohen's d column (deterministic XML extraction). Signed effect size; the source does not state a universal desirable sign/direction, so direction is recorded as unknown rather than assumed higher-is-better.
Configuration: HyenaDNA (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP short-window dataset	0.612 AUROC (task: pathogenic vs common snp) unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source HyenaDNA pathogenic/common SNP evaluation Table 5, frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 5, HyenaDNA row, AUC column (deterministic XML extraction)
Configuration: HyenaDNA (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP short-window dataset	0.395 Cohen's d (task: pathogenic vs common snp) unitless · unknown Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source HyenaDNA pathogenic/common SNP evaluation Table 5, frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 5, HyenaDNA row, Cohen's d column (deterministic XML extraction). Signed effect size; the source does not state a universal desirable sign/direction, so direction is recorded as unknown rather than assumed higher-is-better.
Configuration: NT-v2 (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP short-window dataset	0.732 AUROC (task: pathogenic vs common snp) unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NT-v2 pathogenic/common SNP evaluation Table 5, frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 5, NT-v2 row, AUC column (deterministic XML extraction)
Configuration: NT-v2 (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP short-window dataset	0.881 Cohen's d (task: pathogenic vs common snp) unitless · unknown Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source NT-v2 pathogenic/common SNP evaluation Table 5, frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 5, NT-v2 row, Cohen's d column (deterministic XML extraction). Signed effect size; the source does not state a universal desirable sign/direction, so direction is recorded as unknown rather than assumed higher-is-better.
Configuration: Sei, hidden states* (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP short-window dataset	0.66 AUROC (task: pathogenic vs common snp) unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Sei, hidden states* pathogenic/common SNP evaluation Table 5, frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 5, Sei, hidden states* row, AUC column (deterministic XML extraction)
Configuration: Sei, hidden states* (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP short-window dataset	0.557 Cohen's d (task: pathogenic vs common snp) unitless · unknown Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Sei, hidden states* pathogenic/common SNP evaluation Table 5, frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 5, Sei, hidden states* row, Cohen's d column (deterministic XML extraction). Signed effect size; the source does not state a universal desirable sign/direction, so direction is recorded as unknown rather than assumed higher-is-better.
Configuration: Sei, output tracks* (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP short-window dataset	0.664 AUROC (task: pathogenic vs common snp) unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Sei, output tracks* pathogenic/common SNP evaluation Table 5, frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 5, Sei, output tracks* row, AUC column (deterministic XML extraction)
Configuration: Sei, output tracks* (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP short-window dataset	0.605 Cohen's d (task: pathogenic vs common snp) unitless · unknown Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Sei, output tracks* pathogenic/common SNP evaluation Table 5, frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks · Table 5, Sei, output tracks* row, Cohen's d column (deterministic XML extraction). Signed effect size; the source does not state a universal desirable sign/direction, so direction is recorded as unknown rather than assumed higher-is-better.
Configuration: Caduceus-Ph (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP short-window dataset	0.704 AUROC (task: pathogenic vs common snp; outer test group 1 only (chromosomes 3, 6, 9, 12, 16, 18, 19, 21), not averaged) unitless · higher Uncertainty: Not reported by the source: Supplementary Data 4 prints one AUC per test group, with no interval. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus-Ph Pathogenic variants vs common per-test-group evaluation Table 5 set-up, AUC reported separately for each outer chromosome test group (Supplementary Data 4); frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks: Supplementary Data 1-6 · Supplementary Data 4 (workbook sheet 'Data 4'), block 'Pathogenic variants vs common', row 'Caduceus-Ph', column 'Test Group 1 AUC' (cell B3). Test group 1 is chromosomes 3, 6, 9, 12, 16, 18, 19, 21 (Methods, 'Variant effect quantification benchmark').
Configuration: Caduceus-Ph (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP short-window dataset	0.688 AUROC (task: pathogenic vs common snp; outer test group 2 only (chromosomes 2, 5, 11, 14, 17, 20, 22, X), not averaged) unitless · higher Uncertainty: Not reported by the source: Supplementary Data 4 prints one AUC per test group, with no interval. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus-Ph Pathogenic variants vs common per-test-group evaluation Table 5 set-up, AUC reported separately for each outer chromosome test group (Supplementary Data 4); frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks: Supplementary Data 1-6 · Supplementary Data 4 (workbook sheet 'Data 4'), block 'Pathogenic variants vs common', row 'Caduceus-Ph', column 'Test Group 2 AUC' (cell C3). Test group 2 is chromosomes 2, 5, 11, 14, 17, 20, 22, X (Methods, 'Variant effect quantification benchmark').
Configuration: Caduceus-Ph (pathogenic/common SNP classification)	Protocol: Feng pathogenic-versus-common SNP classification Dataset: Feng pathogenic/common SNP short-window dataset	0.696 AUROC (task: pathogenic vs common snp; outer test group 3 only (chromosomes 1, 4, 7, 8, 10, 13, 15), not averaged) unitless · higher Uncertainty: Not reported by the source: Supplementary Data 4 prints one AUC per test group, with no interval. Coverage: Not reported scored / Not reported eligible	Independent external evaluation · Source checked Methods, coverage and source Caduceus-Ph Pathogenic variants vs common per-test-group evaluation Table 5 set-up, AUC reported separately for each outer chromosome test group (Supplementary Data 4); frozen embeddings + random forest classifier Aggregation: Not reported Benchmarking DNA foundation models for genomic and genetic tasks: Supplementary Data 1-6 · Supplementary Data 4 (workbook sheet 'Data 4'), block 'Pathogenic variants vs common', row 'Caduceus-Ph', column 'Test Group 3 AUC' (cell D3). Test group 3 is chromosomes 1, 4, 7, 8, 10, 13, 15 (Methods, 'Variant effect quantification benchmark').

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.

Explore all linked results

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.

External evaluations: 22

Literature evidence is not a Rewire measurement. Executed but unpublished runs and private review status are not included.

Null control

Proposed control: requires review

Training-set class prior where supervised fitting is permitted

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

Regularised classifier on simple permitted features, or protocol's conventional reference

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

Claims, original sources and review scope · Release 2026-11-02-a7f03c9e55a5
Property and statement	Original source and location	Review and provenance

No evidence rows match these filters. Choose another scope or clear the search.

How to read the evidence

Sources and history

Release 2026-11-02-a7f03c9e55a5 · Record review: source checked

1 source record and release history

Benchmarking DNA foundation models for genomic and genetic tasks · Original source · PMC12663285.1

Download this release (gzip)

Technical metadata and extraction receipts

Stable ID: amp-feng-20261007-protocol-pathogenic-common-variant-classification

areas: dna-genomes
scope note: Alternate-minus-reference embedding representations scored by a supervised random forest classifier. Three disjoint outer chromosome test groups (3/6/9/12/16/18/19/21; 2/5/11/14/17/20/22/X; 1/4/7/8/10/13/15), each held out in turn with fourfold inner-chromosome cross-validation for hyperparameter tuning. Short and long are separate scored populations by window-size boundary exclusion, never pooled; see each configuration/dataset for its exact window assignment. Exact immutable checkpoints are unreported; configurations retain the printed model name and input representation only.
task: Pathogenic-versus-common SNP discrimination (AUC, Cohen's d)
version: Table 5

Related records

assessment: Caduceus-Ph pathogenic/common SNP evaluation
assessment: Caduceus-Ph, long sequence pathogenic/common SNP evaluation
assessment: DNABERT-2 pathogenic/common SNP evaluation
assessment: Enformer, hidden states* pathogenic/common SNP evaluation
assessment: Enformer, output tracks* pathogenic/common SNP evaluation
assessment: GROVER pathogenic/common SNP evaluation
assessment: HyenaDNA pathogenic/common SNP evaluation
assessment: HyenaDNA-450K, long sequence pathogenic/common SNP evaluation
assessment: NT-v2 pathogenic/common SNP evaluation
assessment: Sei, hidden states* pathogenic/common SNP evaluation
assessment: Sei, output tracks* pathogenic/common SNP evaluation
assessment: Caduceus-Ph Pathogenic variants vs common per-test-group evaluation
assessment: Caduceus-Ph, long sequence Pathogenic variants vs common per-test-group evaluation
assessment: DNABERT-2 Pathogenic variants vs common per-test-group evaluation
assessment: Enformer, hidden states Pathogenic variants vs common per-test-group evaluation
assessment: Enformer, output tracks Pathogenic variants vs common per-test-group evaluation
assessment: GROVER Pathogenic variants vs common per-test-group evaluation
assessment: HyenaDNA-160K Pathogenic variants vs common per-test-group evaluation
assessment: HyenaDNA-450K, long sequence Pathogenic variants vs common per-test-group evaluation
assessment: NT-v2 Pathogenic variants vs common per-test-group evaluation
assessment: Sei, hidden states Pathogenic variants vs common per-test-group evaluation
assessment: Sei, output tracks Pathogenic variants vs common per-test-group evaluation
assessed by: Rank rare-disease variants for review

Suggest a correction