rewire.it
Task

GUE CORE-PROMOTER-DETECTION-NOTATA: Core promoter detection, dataset notata

Core promoter detection, dataset notata. Scored with MCC on GUE Core promoter detection, notata. Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12.

10 evaluations · 10 metric rows

Overview

Core promoter detection, dataset notata. Scored with MCC on GUE Core promoter detection, notata. 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.

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 CORE-PROMOTER-DETECTION-NOTATA: Core promoter detection, dataset notata

mcc (percent) · Higher values are better for this metric.

Every method GUE reports on Core promoter detection, dataset notata, scored with MCC on GUE Core promoter detection, notata.

Evaluation protocol · GUE Core promoter detection, notata (GUE split)

  1. DNABERT (3-mer) · Configuration · Author-reported evaluation69.82
  2. DNABERT (4-mer) · Configuration · Author-reported evaluation70.04
  3. DNABERT (5-mer) · Configuration · Author-reported evaluation69.81
  4. DNABERT (6-mer) · Configuration · Author-reported evaluation70.47
  5. NT-500M-human · Configuration · Author-reported evaluation64.82
  6. NT-500M-1000g · Configuration · Author-reported evaluation67.17
  7. NT-2500M-1000g · Configuration · Author-reported evaluation67.46
  8. NT-2500M-multi · Configuration · Author-reported evaluation71.58
  9. DNABERT-2 · Configuration · Author-reported evaluation68.04

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(Core promoter detection)
Values, uncertainty and evidence
mcc: original source values
Tested entityPrinted valueUncertaintyEvidence
DNABERT (3-mer) · Configuration69.82 percentNot reportedAuthor-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT (3-mer)), column(Core promoter detection notata)
DNABERT (4-mer) · Configuration70.04 percentNot reportedAuthor-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT (4-mer)), column(Core promoter detection notata)
DNABERT (5-mer) · Configuration69.81 percentNot reportedAuthor-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT (5-mer)), column(Core promoter detection notata)
DNABERT (6-mer) · Configuration70.47 percentNot reportedAuthor-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT (6-mer)), column(Core promoter detection notata)
NT-500M-human · Configuration64.82 percentNot reportedAuthor-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(NT-500M-human), column(Core promoter detection notata)
NT-500M-1000g · Configuration67.17 percentNot reportedAuthor-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(NT-500M-1000g), column(Core promoter detection notata)
NT-2500M-1000g · Configuration67.46 percentNot reportedAuthor-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(NT-2500M-1000g), column(Core promoter detection notata)
NT-2500M-multi · Configuration71.58 percentNot reportedAuthor-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(NT-2500M-multi), column(Core promoter detection notata)
DNABERT-2 · Configuration68.04 percentNot reportedAuthor-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT-2), column(Core promoter detection notata)
DNABERT-2 (further pre-trained on GUE) · Configuration69.53 percentNot reportedAuthor-reported evaluation · source checkedDNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes · Table 6, row(DNABERT-2♦), column(Core promoter detection notata)
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.

Results grouped by the exact reported evaluation
Metric and findingCoverage and uncertaintyEvidence
DNABERT-2 on GUE CORE-PROMOTER-DETECTION-NOTATA: Core promoter detection, dataset notata

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

68.04% 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(Core promoter detection notata)

Source checking is not independent reproduction.

DNABERT-2 (further pre-trained on GUE) on GUE CORE-PROMOTER-DETECTION-NOTATA: Core promoter detection, dataset notata

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

69.53% 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(Core promoter detection notata)

Source checking is not independent reproduction.

DNABERT (3-mer) on GUE CORE-PROMOTER-DETECTION-NOTATA: Core promoter detection, dataset notata

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

69.82% 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(Core promoter detection notata)

Source checking is not independent reproduction.

DNABERT (4-mer) on GUE CORE-PROMOTER-DETECTION-NOTATA: Core promoter detection, dataset notata

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

70.04% 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(Core promoter detection notata)

Source checking is not independent reproduction.

DNABERT (5-mer) on GUE CORE-PROMOTER-DETECTION-NOTATA: Core promoter detection, dataset notata

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

69.81% 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(Core promoter detection notata)

Source checking is not independent reproduction.

DNABERT (6-mer) on GUE CORE-PROMOTER-DETECTION-NOTATA: Core promoter detection, dataset notata

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

70.47% 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(Core promoter detection notata)

Source checking is not independent reproduction.

NT-2500M-1000g on GUE CORE-PROMOTER-DETECTION-NOTATA: Core promoter detection, dataset notata

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

67.46% 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(Core promoter detection notata)

Source checking is not independent reproduction.

NT-2500M-multi on GUE CORE-PROMOTER-DETECTION-NOTATA: Core promoter detection, dataset notata

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

71.58% 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(Core promoter detection notata)

Source checking is not independent reproduction.

NT-500M-1000g on GUE CORE-PROMOTER-DETECTION-NOTATA: Core promoter detection, dataset notata

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

67.17% 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(Core promoter detection notata)

Source checking is not independent reproduction.

NT-500M-human on GUE CORE-PROMOTER-DETECTION-NOTATA: Core promoter detection, dataset notata

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

64.82% 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(Core promoter detection notata)

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

Claims, original sources and review scope · Release 2026-09-17-134cd1815de8
Property and statementOriginal source and locationReview and provenance
Relationship: part of

discovery-benchmark-gue

Individual claims
DNABERT-2: Efficient Foundation Model and Benchmark for Multi-Species Genomes

Original source ↗

Table 12, row(Core promoter detection)

Version: Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256
Retrieved: 2026-09-17T08:06:28.183387+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-gue

Claim: gue-association-core-promoter-detection-notata

Source artifact SHA-256: 49300acee3e4afd44bebc3de9893c3bc310d331bd4805374e0952fdfbf366f06

Hash scope: Exact retrieved primary paper artifact bytes.

Inspected artifact

Sources and history

Release 2026-09-17-134cd1815de8 · Record review: source checked

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

Stable ID: gue-task-core-promoter-detection-notata

areas
dna-genomes
tasks
Core promoter detection, dataset notata
metric
MCC
metric direction
higher
dataset
GUE Core promoter detection, notata
protocol
Fine-tuned on the GUE training split, scored on its test split. Split sizes are in Table 12.
source locator
Table 12, row(Core promoter detection)
comparison panels
id: gue-panel-core-promoter-detection-notata; title: GUE CORE-PROMOTER-DETECTION-NOTATA: Core promoter detection, dataset notata; protocol id: gue-task-core-promoter-detection-notata; dataset id: gue-dataset-gue-core-promoter-detection-notata; metric: mcc; unit: percent; direction: higher; result ids: gue-result-dnabert-3-mer-core-promoter-detection-notata-mcc; gue-result-dnabert-4-mer-core-promoter-detection-notata-mcc; gue-result-dnabert-5-mer-core-promoter-detection-notata-mcc; gue-result-dnabert-6-mer-core-promoter-detection-notata-mcc; gue-result-nt-500m-human-core-promoter-detection-notata-mcc; gue-result-nt-500m-1000g-core-promoter-detection-notata-mcc; gue-result-nt-2500m-1000g-core-promoter-detection-notata-mcc; gue-result-nt-2500m-multi-core-promoter-detection-notata-mcc; gue-result-dnabert-2-core-promoter-detection-notata-mcc; gue-result-dnabert-2-further-pre-trained-on-gue-core-promoter-detection-notata-mcc; source ids: evidence-expansion-gue-49300ace; source locator: Table 12, row(Core promoter detection); context: Every method GUE reports on Core promoter detection, dataset notata, scored with MCC on GUE Core promoter detection, notata.; 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

Suggest a correction