GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac
Epigenetic marks prediction, dataset H4ac. Scored with MCC on GUE Epigenetic marks prediction, H4ac. Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12.
Overview
Epigenetic marks prediction, dataset H4ac. Scored with MCC on GUE Epigenetic marks prediction, H4ac. Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12.
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.
- DNABERT-2 on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac
- DNABERT-2 (further pre-trained on GUE) on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac
- DNABERT (3-mer) on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac
- DNABERT (4-mer) on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac
- DNABERT (5-mer) on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac
- DNABERT (6-mer) on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac
- NT-2500M-1000g on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac
- NT-2500M-multi on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac
- NT-500M-1000g on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac
- NT-500M-human on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac
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.
GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac
mcc (percent) · Higher values are better for this metric.
Every method GUE reports on Epigenetic marks prediction, dataset H4ac, scored with MCC on GUE Epigenetic marks prediction, H4ac.
Evaluation protocol · GUE Epigenetic marks prediction, H4ac (GUE split)
- DNABERT (3-mer) · Configuration · Author-reported evaluation38.60
- DNABERT (4-mer) · Configuration · Author-reported evaluation36.40
- DNABERT (5-mer) · Configuration · Author-reported evaluation37.48
- DNABERT (6-mer) · Configuration · Author-reported evaluation37.43
- NT-500M-human · Configuration · Author-reported evaluation33.74
- NT-500M-1000g · Configuration · Author-reported evaluation36.79
- NT-2500M-1000g · Configuration · Author-reported evaluation41.46
- NT-2500M-multi · Configuration · Author-reported evaluation49.13
- DNABERT-2 · Configuration · Author-reported evaluation50.43
- DNABERT-2 (further pre-trained on GUE) · Configuration · Author-reported evaluation50.35
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.
DNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 12, row(Epigenetic marks prediction)Values, uncertainty and evidence
| Tested entity | Printed value | Uncertainty | Evidence |
|---|---|---|---|
| DNABERT (3-mer) · Configuration | 38.60 percent | Not reported | Author-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT (3-mer)), column(Epigenetic marks prediction H4ac) |
| DNABERT (4-mer) · Configuration | 36.40 percent | Not reported | Author-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT (4-mer)), column(Epigenetic marks prediction H4ac) |
| DNABERT (5-mer) · Configuration | 37.48 percent | Not reported | Author-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT (5-mer)), column(Epigenetic marks prediction H4ac) |
| DNABERT (6-mer) · Configuration | 37.43 percent | Not reported | Author-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT (6-mer)), column(Epigenetic marks prediction H4ac) |
| NT-500M-human · Configuration | 33.74 percent | Not reported | Author-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(NT-500M-human), column(Epigenetic marks prediction H4ac) |
| NT-500M-1000g · Configuration | 36.79 percent | Not reported | Author-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(NT-500M-1000g), column(Epigenetic marks prediction H4ac) |
| NT-2500M-1000g · Configuration | 41.46 percent | Not reported | Author-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(NT-2500M-1000g), column(Epigenetic marks prediction H4ac) |
| NT-2500M-multi · Configuration | 49.13 percent | Not reported | Author-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(NT-2500M-multi), column(Epigenetic marks prediction H4ac) |
| DNABERT-2 · Configuration | 50.43 percent | Not reported | Author-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT-2), column(Epigenetic marks prediction H4ac) |
| DNABERT-2 (further pre-trained on GUE) · Configuration | 50.35 percent | Not reported | Author-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT-2♦), column(Epigenetic marks prediction H4ac) |
Scope and limitations
- Author-reported numbers, source checked but not independently reproduced.
- Scores are MCC, except Covid variant classification which is F1, both on a 0 to 100 scale.
- The diamond entry is DNABERT-2 with further pre-training on the GUE training sets, so it is not directly comparable to the others.
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 · 10 evaluations · 10 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 |
|---|---|---|
| DNABERT-2 on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac Configuration: DNABERT-2Task: GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4acDataset subset: GUE Epigenetic marks prediction, H4ac (GUE split) Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12. Author-reported evaluation · Evaluation metadata: source checked | ||
| 50.43% mcc Unit: percent · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT-2), column(Epigenetic marks prediction H4ac) Source checking is not independent reproduction. |
| DNABERT-2 (further pre-trained on GUE) on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac Configuration: DNABERT-2 (further pre-trained on GUE)Task: GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4acDataset subset: GUE Epigenetic marks prediction, H4ac (GUE split) Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12. Author-reported evaluation · Evaluation metadata: source checked | ||
| 50.35% mcc Unit: percent · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT-2♦), column(Epigenetic marks prediction H4ac) Source checking is not independent reproduction. |
| DNABERT (3-mer) on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac Configuration: DNABERT (3-mer)Task: GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4acDataset subset: GUE Epigenetic marks prediction, H4ac (GUE split) Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12. Author-reported evaluation · Evaluation metadata: source checked | ||
| 38.60% mcc Unit: percent · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT (3-mer)), column(Epigenetic marks prediction H4ac) Source checking is not independent reproduction. |
| DNABERT (4-mer) on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac Configuration: DNABERT (4-mer)Task: GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4acDataset subset: GUE Epigenetic marks prediction, H4ac (GUE split) Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12. Author-reported evaluation · Evaluation metadata: source checked | ||
| 36.40% mcc Unit: percent · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT (4-mer)), column(Epigenetic marks prediction H4ac) Source checking is not independent reproduction. |
| DNABERT (5-mer) on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac Configuration: DNABERT (5-mer)Task: GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4acDataset subset: GUE Epigenetic marks prediction, H4ac (GUE split) Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12. Author-reported evaluation · Evaluation metadata: source checked | ||
| 37.48% mcc Unit: percent · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT (5-mer)), column(Epigenetic marks prediction H4ac) Source checking is not independent reproduction. |
| DNABERT (6-mer) on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac Configuration: DNABERT (6-mer)Task: GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4acDataset subset: GUE Epigenetic marks prediction, H4ac (GUE split) Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12. Author-reported evaluation · Evaluation metadata: source checked | ||
| 37.43% mcc Unit: percent · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT (6-mer)), column(Epigenetic marks prediction H4ac) Source checking is not independent reproduction. |
| NT-2500M-1000g on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac Configuration: NT-2500M-1000gTask: GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4acDataset subset: GUE Epigenetic marks prediction, H4ac (GUE split) Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12. Author-reported evaluation · Evaluation metadata: source checked | ||
| 41.46% mcc Unit: percent · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(NT-2500M-1000g), column(Epigenetic marks prediction H4ac) Source checking is not independent reproduction. |
| NT-2500M-multi on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac Configuration: NT-2500M-multiTask: GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4acDataset subset: GUE Epigenetic marks prediction, H4ac (GUE split) Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12. Author-reported evaluation · Evaluation metadata: source checked | ||
| 49.13% mcc Unit: percent · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(NT-2500M-multi), column(Epigenetic marks prediction H4ac) Source checking is not independent reproduction. |
| NT-500M-1000g on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac Configuration: NT-500M-1000gTask: GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4acDataset subset: GUE Epigenetic marks prediction, H4ac (GUE split) Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12. Author-reported evaluation · Evaluation metadata: source checked | ||
| 36.79% mcc Unit: percent · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(NT-500M-1000g), column(Epigenetic marks prediction H4ac) Source checking is not independent reproduction. |
| NT-500M-human on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac Configuration: NT-500M-humanTask: GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4acDataset subset: GUE Epigenetic marks prediction, H4ac (GUE split) Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12. Author-reported evaluation · Evaluation metadata: source checked | ||
| 33.74% mcc Unit: percent · Direction: higher | Uncertainty: Not reported Scored: Not reported · Eligible: Not reported | source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(NT-500M-human), column(Epigenetic marks prediction H4ac) 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-gue Individual claims | DNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes Table 12, row(Epigenetic marks prediction) 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: gue-association-epigenetic-marks-prediction-h4ac 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
- DNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Original source · Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256
Technical metadata and extraction receipts
Stable ID: gue-task-epigenetic-marks-prediction-h4ac
- areas
- dna-genomes
- tasks
- Epigenetic marks prediction, dataset H4ac
- metric
- MCC
- metric direction
- higher
- dataset
- GUE Epigenetic marks prediction, H4ac
- protocol
- Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12.
- source locator
- Table 12, row(Epigenetic marks prediction)
- comparison panels
- id: gue-panel-epigenetic-marks-prediction-h4ac; title: GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac; protocol id: gue-task-epigenetic-marks-prediction-h4ac; dataset id: gue-dataset-gue-epigenetic-marks-prediction-h4ac; metric: mcc; unit: percent; direction: higher; result ids: gue-result-dnabert-3-mer-epigenetic-marks-prediction-h4ac-mcc; gue-result-dnabert-4-mer-epigenetic-marks-prediction-h4ac-mcc; gue-result-dnabert-5-mer-epigenetic-marks-prediction-h4ac-mcc; gue-result-dnabert-6-mer-epigenetic-marks-prediction-h4ac-mcc; gue-result-nt-500m-human-epigenetic-marks-prediction-h4ac-mcc; gue-result-nt-500m-1000g-epigenetic-marks-prediction-h4ac-mcc; gue-result-nt-2500m-1000g-epigenetic-marks-prediction-h4ac-mcc; gue-result-nt-2500m-multi-epigenetic-marks-prediction-h4ac-mcc; gue-result-dnabert-2-epigenetic-marks-prediction-h4ac-mcc; gue-result-dnabert-2-further-pre-trained-on-gue-epigenetic-marks-prediction-h4ac-mcc; source ids: evidence-expansion-gue-49300ace; source locator: Table 12, row(Epigenetic marks prediction); context: Every method GUE reports on Epigenetic marks prediction, dataset H4ac, scored with MCC on GUE Epigenetic marks prediction, H4ac.; caveats: Author-reported numbers, source checked but not independently reproduced.; Scores are MCC, except Covid variant classification which is F1, both on a 0 to 100 scale.; The diamond entry is DNABERT-2 with further pre-training on the GUE training sets, so it is not directly comparable to the others.; review: method: automated_source_review; date: 2026-09-18
Related records
- part of: GUE
- subject: GUE EPIGENETIC-MARKS-PREDICTION-H4AC: part of discovery-benchmark-gue
- benchmark: DNABERT-2 on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac
- benchmark: DNABERT-2 (further pre-trained on GUE) on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac
- benchmark: DNABERT (3-mer) on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac
- benchmark: DNABERT (4-mer) on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac
- benchmark: DNABERT (5-mer) on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac
- benchmark: DNABERT (6-mer) on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac
- benchmark: NT-2500M-1000g on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac
- benchmark: NT-2500M-multi on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac
- benchmark: NT-500M-1000g on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac
- benchmark: NT-500M-human on GUE EPIGENETIC-MARKS-PREDICTION-H4AC: Epigenetic marks prediction, dataset H4ac