rewire.itbenchmarks
← Back to results
Task

BEND CPG: CpG methylation

CpG methylation. Scored with AUROC on ENCODE CpG methylation. A downstream head trained on frozen embeddings, except for the expert methods and the fully supervised baselines, which are trained end to end. Metric and splits are from Table 1.

15 evaluations · 15 results

Overview

CpG methylation. Scored with AUROC on ENCODE CpG methylation. A downstream head trained on frozen embeddings, except for the expert methods and the fully supervised baselines, which are trained end to end. Metric and splits are from Table 1.

Consult the linked sources for architecture or protocol details. Missing evidence is not evidence of a missing capability.

Results

Each comparison retains its reviewed evaluation scope, dataset and metric. Results are shown without a pooled ranking.

BEND CPG: CpG methylation

auroc (fraction) · Higher values are better.

BEND CPG: CpG methylation · ENCODE CpG methylation (BEND split)

Evidence origin: Author-reported evaluation.

BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 1, row(CpG methylation)
  • The expert entries are specialist published models, each compared on one task only.
  • The metric differs by task, taken from Table 1, so these figures cannot be averaged into one score.
Comparison details and limitations

Every method BEND reports on CpG methylation, scored with AUROC on ENCODE CpG methylation.

  • Author-reported numbers, source checked but not independently reproduced.

Automated source review: 2026-09-18. Numerical source review does not establish independent reproduction.

Dots show point estimates. Whiskers show only explicitly defined uncertainty (standard deviation, standard error or a labelled interval); their definitions remain in Table. Unresolved uncertainty is not plotted. Differences do not establish statistical significance.

Showing 12 of 15 matching rows.

Tested configuration
00.250.50.751
Reported score
  1. BASSET0.93
  2. NT-MS0.92
  3. NT-V20.91
  4. DNABERT0.91
  5. GENA-LM BERT0.91
  6. GENA-LM BigBird0.91
  7. HyenaDNA large0.91
  8. DNABERT-20.9
  9. NT-1000G0.89
  10. GROVER0.89
  11. NT-H0.88
  12. ResNet-LM0.87

Methods and evaluation design

Procedure, tasks and evaluated configurations

Evaluation design

Benchmarks bring together tasks and protocols. A task describes the biological question; a protocol defines a particular test.

Benchmarks

These source-backed links do not make different protocols or scores interchangeable.

Recorded evaluations

Each evaluation records what was tested and under which conditions.

Explore all linked results

Run instructions

No runnable recipe has been reviewed for this task. Dataset access, model requirements, licences and compute requirements must be checked against its sources before execution.

A task describes a biological question. Choose a linked protocol to obtain concrete split and scoring instructions.

Strengths, limitations and unresolved questions

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.

1 evidence row matching the loaded filters

Claims, original sources and review scope · Release 2026-09-29-06401fd5b220
Property and statementOriginal source and locationReview and provenance
Relationship: part of
discovery-benchmark-bend
Individual claims		BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks

Original source ↗

Table 1, row(CpG methylation)

Version: Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256
Retrieved: 2026-09-17T08:06:28.183228+00:00

source checked

automated source review · 2026-09-18

Audit details

Primary-source transcription with no human sign-off and no independent reproduction.

Field: links:part_of:discovery-benchmark-bend

Claim: bend-association-cpg

Source artifact SHA-256: f709b6bef3120eb979c0a0e02d2582475c49410f29850ed7601ba7a700ca379d

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

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

Sources and history

View linked audit checks and correction history

Release 2026-09-29-06401fd5b220 · Record review: source checked

1 source records and release historyDownload this release
Technical metadata and extraction receipts

Stable ID: bend-task-cpg

areas
dna-genomes
tasks
CpG methylation
metric
AUROC
metric direction
higher
dataset
ENCODE CpG methylation
protocol
A downstream head trained on frozen embeddings, except for the expert methods and the fully supervised baselines, which are trained end to end. Metric and splits are from Table 1.
source locator
Table 1, row(CpG methylation)
comparison panels
id: bend-panel-cpg; title: BEND CPG: CpG methylation; protocol id: bend-task-cpg; dataset id: bend-dataset-encode-cpg-methylation; metric: auroc; unit: fraction; direction: higher; result ids: bend-result-basset-cpg-auroc; bend-result-cnn-cpg-auroc; bend-result-resnet-lm-cpg-auroc; bend-result-awd-lstm-cpg-auroc; bend-result-nt-h-cpg-auroc; bend-result-nt-ms-cpg-auroc; bend-result-nt-1000g-cpg-auroc; bend-result-nt-v2-cpg-auroc; bend-result-dnabert-cpg-auroc; bend-result-dnabert-2-cpg-auroc; bend-result-gena-lm-bert-cpg-auroc; bend-result-gena-lm-bigbird-cpg-auroc; bend-result-hyenadna-large-cpg-auroc; bend-result-hyenadna-tiny-cpg-auroc; bend-result-grover-cpg-auroc; source ids: evidence-expansion-bend-final-f709b6be; source locator: Table 1, row(CpG methylation); context: Every method BEND reports on CpG methylation, scored with AUROC on ENCODE CpG methylation.; caveats: Author-reported numbers, source checked but not independently reproduced.; The expert entries are specialist published models, each compared on one task only.; The metric differs by task, taken from Table 1, so these figures cannot be averaged into one score.; review: method: automated_source_review; date: 2026-09-18
Related records

Suggest a correction