ENCODE chromatin accessibility (BEND split)
The split of ENCODE chromatin accessibility that BEND evaluated on. The upstream dataset release is not catalogued here, so no claim is made that this matches its original splits.
Subset and evaluation context
This record describes a particular subset or cohort used in an evaluation. Its results do not describe the full dataset.
Evaluation results
Release 2026-09-17-134cd1815de8 · 15 evaluations · 15 metric rows. Different protocols are not a single leaderboard. Where several source tables report the same metric, the published comparisons above offer a pooled view that names what it does not hold constant.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| AWD-LSTM on BEND CHROMATIN: Chromatin accessibility Method: AWD-LSTMTask: BEND CHROMATIN: Chromatin accessibilityDataset subset: ENCODE chromatin accessibility (BEND split) 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. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.69 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(AWD-LSTM), column(Chromatin accessibility) Source checking is not independent reproduction. |
| BASSET on BEND CHROMATIN: Chromatin accessibility Configuration: BASSETTask: BEND CHROMATIN: Chromatin accessibilityDataset subset: ENCODE chromatin accessibility (BEND split) 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. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.85 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(Expert method), column(Chromatin accessibility) Source checking is not independent reproduction. |
| CNN on BEND CHROMATIN: Chromatin accessibility Method: CNNTask: BEND CHROMATIN: Chromatin accessibilityDataset subset: ENCODE chromatin accessibility (BEND split) 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. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.75 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(CNN), column(Chromatin accessibility) Source checking is not independent reproduction. |
| DNABERT-2 on BEND CHROMATIN: Chromatin accessibility Configuration: DNABERT-2Task: BEND CHROMATIN: Chromatin accessibilityDataset subset: ENCODE chromatin accessibility (BEND split) 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. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.81 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(DNABERT-2), column(Chromatin accessibility) Source checking is not independent reproduction. |
| DNABERT on BEND CHROMATIN: Chromatin accessibility Configuration: DNABERTTask: BEND CHROMATIN: Chromatin accessibilityDataset subset: ENCODE chromatin accessibility (BEND split) 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. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.85 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(DNABERT), column(Chromatin accessibility) Source checking is not independent reproduction. |
| GENA-LM BERT on BEND CHROMATIN: Chromatin accessibility Configuration: GENA-LM BERTTask: BEND CHROMATIN: Chromatin accessibilityDataset subset: ENCODE chromatin accessibility (BEND split) 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. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.76 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(GENA-LM BERT), column(Chromatin accessibility) Source checking is not independent reproduction. |
| GENA-LM BigBird on BEND CHROMATIN: Chromatin accessibility Configuration: GENA-LM BigBirdTask: BEND CHROMATIN: Chromatin accessibilityDataset subset: ENCODE chromatin accessibility (BEND split) 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. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.82 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(GENA-LM BigBird), column(Chromatin accessibility) Source checking is not independent reproduction. |
| GROVER on BEND CHROMATIN: Chromatin accessibility Configuration: GROVERTask: BEND CHROMATIN: Chromatin accessibilityDataset subset: ENCODE chromatin accessibility (BEND split) 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. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.82 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(GROVER), column(Chromatin accessibility) Source checking is not independent reproduction. |
| HyenaDNA large on BEND CHROMATIN: Chromatin accessibility Configuration: HyenaDNA largeTask: BEND CHROMATIN: Chromatin accessibilityDataset subset: ENCODE chromatin accessibility (BEND split) 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. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.84 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(HyenaDNA large), column(Chromatin accessibility) Source checking is not independent reproduction. |
| HyenaDNA tiny on BEND CHROMATIN: Chromatin accessibility Configuration: HyenaDNA tinyTask: BEND CHROMATIN: Chromatin accessibilityDataset subset: ENCODE chromatin accessibility (BEND split) 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. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.78 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(HyenaDNA tiny), column(Chromatin accessibility) Source checking is not independent reproduction. |
| NT-1000G on BEND CHROMATIN: Chromatin accessibility Configuration: NT-1000GTask: BEND CHROMATIN: Chromatin accessibilityDataset subset: ENCODE chromatin accessibility (BEND split) 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. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.77 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(NT-1000G), column(Chromatin accessibility) Source checking is not independent reproduction. |
| NT-H on BEND CHROMATIN: Chromatin accessibility Method: NT-HTask: BEND CHROMATIN: Chromatin accessibilityDataset subset: ENCODE chromatin accessibility (BEND split) 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. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.74 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(NT-H), column(Chromatin accessibility) Source checking is not independent reproduction. |
| NT-MS on BEND CHROMATIN: Chromatin accessibility Method: NT-MSTask: BEND CHROMATIN: Chromatin accessibilityDataset subset: ENCODE chromatin accessibility (BEND split) 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. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.79 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(NT-MS), column(Chromatin accessibility) Source checking is not independent reproduction. |
| NT-V2 on BEND CHROMATIN: Chromatin accessibility Configuration: NT-V2Task: BEND CHROMATIN: Chromatin accessibilityDataset subset: ENCODE chromatin accessibility (BEND split) 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. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.80 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(NT-V2), column(Chromatin accessibility) Source checking is not independent reproduction. |
| ResNet-LM on BEND CHROMATIN: Chromatin accessibility Method: ResNet-LMTask: BEND CHROMATIN: Chromatin accessibilityDataset subset: ENCODE chromatin accessibility (BEND split) 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. Author-reported evaluation · Evaluation metadata: source checked | ||
| 0.82 auroc Unit: fraction · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(ResNet-LM), column(Chromatin accessibility) Source checking is not 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.
2 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| description The split of ENCODE chromatin accessibility that BEND evaluated on. The upstream dataset release is not catalogued here, so no claim is made that this matches its original splits. Context-only references | BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks No field-specific location recorded Version: Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| name ENCODE chromatin accessibility (BEND split) Context-only references | BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks No field-specific location recorded Version: Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256 | not individually reviewed No individual claim review recorded Audit detailsField: Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
Sources and history
Release 2026-09-17-134cd1815de8 · Record review: source checked
1 source records and release history
- BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Original source · Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256
Technical metadata and extraction receipts
Stable ID: bend-dataset-encode-chromatin-accessibility
- areas
- dna-genomes
- missing metadata
- version: unreported; url: unextracted
Related records
- dataset: AWD-LSTM on BEND CHROMATIN: Chromatin accessibility
- dataset: BASSET on BEND CHROMATIN: Chromatin accessibility
- dataset: CNN on BEND CHROMATIN: Chromatin accessibility
- dataset: DNABERT-2 on BEND CHROMATIN: Chromatin accessibility
- dataset: DNABERT on BEND CHROMATIN: Chromatin accessibility
- dataset: GENA-LM BERT on BEND CHROMATIN: Chromatin accessibility
- dataset: GENA-LM BigBird on BEND CHROMATIN: Chromatin accessibility
- dataset: GROVER on BEND CHROMATIN: Chromatin accessibility
- dataset: HyenaDNA large on BEND CHROMATIN: Chromatin accessibility
- dataset: HyenaDNA tiny on BEND CHROMATIN: Chromatin accessibility
- dataset: NT-1000G on BEND CHROMATIN: Chromatin accessibility
- dataset: NT-H on BEND CHROMATIN: Chromatin accessibility
- dataset: NT-MS on BEND CHROMATIN: Chromatin accessibility
- dataset: NT-V2 on BEND CHROMATIN: Chromatin accessibility
- dataset: ResNet-LM on BEND CHROMATIN: Chromatin accessibility