BEND ENHANCER: Enhancer annotation
Enhancer annotation. Scored with AUPRC on Fulco 2019, Gasperini 2019 and Enformer enhancer set. 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.
Overview
Enhancer annotation. Scored with AUPRC on Fulco 2019, Gasperini 2019 and Enformer enhancer set. 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.
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.
- AWD-LSTM on BEND ENHANCER: Enhancer annotation
- CNN on BEND ENHANCER: Enhancer annotation
- DNABERT-2 on BEND ENHANCER: Enhancer annotation
- DNABERT on BEND ENHANCER: Enhancer annotation
- ENFORMER on BEND ENHANCER: Enhancer annotation
- GENA-LM BERT on BEND ENHANCER: Enhancer annotation
- GENA-LM BigBird on BEND ENHANCER: Enhancer annotation
- GROVER on BEND ENHANCER: Enhancer annotation
- HyenaDNA large on BEND ENHANCER: Enhancer annotation
- HyenaDNA tiny on BEND ENHANCER: Enhancer annotation
- NT-1000G on BEND ENHANCER: Enhancer annotation
- NT-H on BEND ENHANCER: Enhancer annotation
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.
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. The pooled view gathers every source table that reports the same metric and names what it does not hold constant.
BEND ENHANCER: Enhancer annotation
auprc (fraction) · Higher values are better for this metric.
Every method BEND reports on Enhancer annotation, scored with AUPRC on Fulco 2019, Gasperini 2019 and Enformer enhancer set.
Evaluation protocol · Fulco 2019, Gasperini 2019 and Enformer enhancer set (BEND split)
- ENFORMER · Configuration · Author-reported evaluation0.07
- ResNet · Configuration · Author-reported evaluation0.06
- CNN · Method · Author-reported evaluation0.03
- ResNet-LM · Method · Author-reported evaluation0.02
- AWD-LSTM · Method · Author-reported evaluation0.03
- NT-H · Method · Author-reported evaluation0.05
- NT-MS · Method · Author-reported evaluation0.06
- NT-1000G · Configuration · Author-reported evaluation0.04
- NT-V2 · Configuration · Author-reported evaluation0.05
- DNABERT · Configuration · Author-reported evaluation0.03
- DNABERT-2 · Configuration · Author-reported evaluation0.03
- GENA-LM BERT · Configuration · Author-reported evaluation0.03
- GENA-LM BigBird · Configuration · Author-reported evaluation0.04
- HyenaDNA large · Configuration · Author-reported evaluation0.03
- HyenaDNA tiny · Configuration · Author-reported evaluation0.02
- GROVER · Configuration · Author-reported evaluation0.03
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.
BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 1, row(Enhancer annotation)Values, uncertainty and evidence
| Tested entity | Printed value | Uncertainty | Evidence |
|---|---|---|---|
| ENFORMER · Configuration | 0.07 fraction | Not reported | Author-reported evaluation · source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(Expert method), column(Enhancer annotation) |
| ResNet · Configuration | 0.06 fraction | Not reported | Author-reported evaluation · source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(ResNet), column(Enhancer annotation) |
| CNN · Method | 0.03 fraction | Not reported | Author-reported evaluation · source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(CNN), column(Enhancer annotation) |
| ResNet-LM · Method | 0.02 fraction | Not reported | Author-reported evaluation · source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(ResNet-LM), column(Enhancer annotation) |
| AWD-LSTM · Method | 0.03 fraction | Not reported | Author-reported evaluation · source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(AWD-LSTM), column(Enhancer annotation) |
| NT-H · Method | 0.05 fraction | Not reported | Author-reported evaluation · source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(NT-H), column(Enhancer annotation) |
| NT-MS · Method | 0.06 fraction | Not reported | Author-reported evaluation · source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(NT-MS), column(Enhancer annotation) |
| NT-1000G · Configuration | 0.04 fraction | Not reported | Author-reported evaluation · source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(NT-1000G), column(Enhancer annotation) |
| NT-V2 · Configuration | 0.05 fraction | Not reported | Author-reported evaluation · source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(NT-V2), column(Enhancer annotation) |
| DNABERT · Configuration | 0.03 fraction | Not reported | Author-reported evaluation · source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(DNABERT), column(Enhancer annotation) |
| DNABERT-2 · Configuration | 0.03 fraction | Not reported | Author-reported evaluation · source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(DNABERT-2), column(Enhancer annotation) |
| GENA-LM BERT · Configuration | 0.03 fraction | Not reported | Author-reported evaluation · source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(GENA-LM BERT), column(Enhancer annotation) |
| GENA-LM BigBird · Configuration | 0.04 fraction | Not reported | Author-reported evaluation · source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(GENA-LM BigBird), column(Enhancer annotation) |
| HyenaDNA large · Configuration | 0.03 fraction | Not reported | Author-reported evaluation · source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(HyenaDNA large), column(Enhancer annotation) |
| HyenaDNA tiny · Configuration | 0.02 fraction | Not reported | Author-reported evaluation · source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(HyenaDNA tiny), column(Enhancer annotation) |
| GROVER · Configuration | 0.03 fraction | Not reported | Author-reported evaluation · source checkedBEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(GROVER), column(Enhancer annotation) |
Scope and limitations
- 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.
Source transcription and grouping reviewed by automated source review on 2026-09-18. These experiments were not independently reproduced by rewire.
Tested entities and results
Release 2026-09-17-134cd1815de8 · 16 evaluations · 16 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 ENHANCER: Enhancer annotation Method: AWD-LSTMTask: BEND ENHANCER: Enhancer annotationDataset subset: Fulco 2019, Gasperini 2019 and Enformer enhancer set (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 | ||
| 0.03 auprc 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(Enhancer annotation) Source checking is not independent reproduction. |
| CNN on BEND ENHANCER: Enhancer annotation Method: CNNTask: BEND ENHANCER: Enhancer annotationDataset subset: Fulco 2019, Gasperini 2019 and Enformer enhancer set (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 | ||
| 0.03 auprc 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(Enhancer annotation) Source checking is not independent reproduction. |
| DNABERT-2 on BEND ENHANCER: Enhancer annotation Configuration: DNABERT-2Task: BEND ENHANCER: Enhancer annotationDataset subset: Fulco 2019, Gasperini 2019 and Enformer enhancer set (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 | ||
| 0.03 auprc 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(Enhancer annotation) Source checking is not independent reproduction. |
| DNABERT on BEND ENHANCER: Enhancer annotation Configuration: DNABERTTask: BEND ENHANCER: Enhancer annotationDataset subset: Fulco 2019, Gasperini 2019 and Enformer enhancer set (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 | ||
| 0.03 auprc 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(Enhancer annotation) Source checking is not independent reproduction. |
| ENFORMER on BEND ENHANCER: Enhancer annotation Configuration: ENFORMERTask: BEND ENHANCER: Enhancer annotationDataset subset: Fulco 2019, Gasperini 2019 and Enformer enhancer set (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 | ||
| 0.07 auprc 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(Enhancer annotation) Source checking is not independent reproduction. |
| GENA-LM BERT on BEND ENHANCER: Enhancer annotation Configuration: GENA-LM BERTTask: BEND ENHANCER: Enhancer annotationDataset subset: Fulco 2019, Gasperini 2019 and Enformer enhancer set (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 | ||
| 0.03 auprc 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(Enhancer annotation) Source checking is not independent reproduction. |
| GENA-LM BigBird on BEND ENHANCER: Enhancer annotation Configuration: GENA-LM BigBirdTask: BEND ENHANCER: Enhancer annotationDataset subset: Fulco 2019, Gasperini 2019 and Enformer enhancer set (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 | ||
| 0.04 auprc 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(Enhancer annotation) Source checking is not independent reproduction. |
| GROVER on BEND ENHANCER: Enhancer annotation Configuration: GROVERTask: BEND ENHANCER: Enhancer annotationDataset subset: Fulco 2019, Gasperini 2019 and Enformer enhancer set (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 | ||
| 0.03 auprc 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(Enhancer annotation) Source checking is not independent reproduction. |
| HyenaDNA large on BEND ENHANCER: Enhancer annotation Configuration: HyenaDNA largeTask: BEND ENHANCER: Enhancer annotationDataset subset: Fulco 2019, Gasperini 2019 and Enformer enhancer set (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 | ||
| 0.03 auprc 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(Enhancer annotation) Source checking is not independent reproduction. |
| HyenaDNA tiny on BEND ENHANCER: Enhancer annotation Configuration: HyenaDNA tinyTask: BEND ENHANCER: Enhancer annotationDataset subset: Fulco 2019, Gasperini 2019 and Enformer enhancer set (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 | ||
| 0.02 auprc 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(Enhancer annotation) Source checking is not independent reproduction. |
| NT-1000G on BEND ENHANCER: Enhancer annotation Configuration: NT-1000GTask: BEND ENHANCER: Enhancer annotationDataset subset: Fulco 2019, Gasperini 2019 and Enformer enhancer set (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 | ||
| 0.04 auprc 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(Enhancer annotation) Source checking is not independent reproduction. |
| NT-H on BEND ENHANCER: Enhancer annotation Method: NT-HTask: BEND ENHANCER: Enhancer annotationDataset subset: Fulco 2019, Gasperini 2019 and Enformer enhancer set (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 | ||
| 0.05 auprc 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(Enhancer annotation) Source checking is not independent reproduction. |
| NT-MS on BEND ENHANCER: Enhancer annotation Method: NT-MSTask: BEND ENHANCER: Enhancer annotationDataset subset: Fulco 2019, Gasperini 2019 and Enformer enhancer set (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 | ||
| 0.06 auprc 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(Enhancer annotation) Source checking is not independent reproduction. |
| NT-V2 on BEND ENHANCER: Enhancer annotation Configuration: NT-V2Task: BEND ENHANCER: Enhancer annotationDataset subset: Fulco 2019, Gasperini 2019 and Enformer enhancer set (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 | ||
| 0.05 auprc 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(Enhancer annotation) Source checking is not independent reproduction. |
| ResNet on BEND ENHANCER: Enhancer annotation Configuration: ResNetTask: BEND ENHANCER: Enhancer annotationDataset subset: Fulco 2019, Gasperini 2019 and Enformer enhancer set (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 | ||
| 0.06 auprc 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), column(Enhancer annotation) Source checking is not independent reproduction. |
| ResNet-LM on BEND ENHANCER: Enhancer annotation Method: ResNet-LMTask: BEND ENHANCER: Enhancer annotationDataset subset: Fulco 2019, Gasperini 2019 and Enformer enhancer set (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 | ||
| 0.02 auprc 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(Enhancer annotation) 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.
1 evidence row matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
| Relationship: part of discovery-benchmark-bend Individual claims | BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks Table 1, row(Enhancer annotation) Version: Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256 | source checked automated source review · 2026-09-18 Audit detailsPrimary-source transcription with no human sign-off and no independent reproduction. Field: Claim: bend-association-enhancer 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-task-enhancer
- areas
- dna-genomes
- tasks
- Enhancer annotation
- metric
- AUPRC
- metric direction
- higher
- dataset
- Fulco 2019, Gasperini 2019 and Enformer enhancer set
- 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(Enhancer annotation)
- comparison panels
- id: bend-panel-enhancer; title: BEND ENHANCER: Enhancer annotation; protocol id: bend-task-enhancer; dataset id: bend-dataset-fulco-2019-gasperini-2019-and-enformer-enhancer-set; metric: auprc; unit: fraction; direction: higher; result ids: bend-result-enformer-enhancer-auprc; bend-result-resnet-enhancer-auprc; bend-result-cnn-enhancer-auprc; bend-result-resnet-lm-enhancer-auprc; bend-result-awd-lstm-enhancer-auprc; bend-result-nt-h-enhancer-auprc; bend-result-nt-ms-enhancer-auprc; bend-result-nt-1000g-enhancer-auprc; bend-result-nt-v2-enhancer-auprc; bend-result-dnabert-enhancer-auprc; bend-result-dnabert-2-enhancer-auprc; bend-result-gena-lm-bert-enhancer-auprc; bend-result-gena-lm-bigbird-enhancer-auprc; bend-result-hyenadna-large-enhancer-auprc; bend-result-hyenadna-tiny-enhancer-auprc; bend-result-grover-enhancer-auprc; source ids: evidence-expansion-bend-final-f709b6be; source locator: Table 1, row(Enhancer annotation); context: Every method BEND reports on Enhancer annotation, scored with AUPRC on Fulco 2019, Gasperini 2019 and Enformer enhancer set.; 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
- part of: BEND
- subject: BEND ENHANCER: part of discovery-benchmark-bend
- benchmark: AWD-LSTM on BEND ENHANCER: Enhancer annotation
- benchmark: CNN on BEND ENHANCER: Enhancer annotation
- benchmark: DNABERT-2 on BEND ENHANCER: Enhancer annotation
- benchmark: DNABERT on BEND ENHANCER: Enhancer annotation
- benchmark: ENFORMER on BEND ENHANCER: Enhancer annotation
- benchmark: GENA-LM BERT on BEND ENHANCER: Enhancer annotation
- benchmark: GENA-LM BigBird on BEND ENHANCER: Enhancer annotation
- benchmark: GROVER on BEND ENHANCER: Enhancer annotation
- benchmark: HyenaDNA large on BEND ENHANCER: Enhancer annotation
- benchmark: HyenaDNA tiny on BEND ENHANCER: Enhancer annotation
- benchmark: NT-1000G on BEND ENHANCER: Enhancer annotation
- benchmark: NT-H on BEND ENHANCER: Enhancer annotation
- benchmark: NT-MS on BEND ENHANCER: Enhancer annotation
- benchmark: NT-V2 on BEND ENHANCER: Enhancer annotation
- benchmark: ResNet on BEND ENHANCER: Enhancer annotation
- benchmark: ResNet-LM on BEND ENHANCER: Enhancer annotation