Configuration

DNABERT-2

This DNABERT-2 row is a comparator in the EDEN genomic-classification paper.

Sources

EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning · Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 12); Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 2)

1 evaluation · 1 metric row

How it worksEvaluated procedure (conceptual)

Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings.

Sources

EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning · Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 2); Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 11)

At a glance

Model type

DNA sequence transformer; this record is the paper-specific evaluated configuration.

Sources

MAGICS-LAB/DNABERT_2 README.md · README.md model description

Biological inputs

DNA sequences from genomic classification benchmarks

Sources

EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning · Related work (paragraph 1); Proposed method: EDEN framework/Biological interpretation of EDN/Relationship to known biological patterns (paragraph 1)

Outputs

Task-specific genomic class predictions

Sources

EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning · Proposed method: EDEN framework/Multiscale EDN generation using K-mer concept/Biologically-informed multiscale representation (paragraph 1); Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 12)

limited source coverage · Automated source review, 2026-09-16. All specifications and missing details

Evaluations and results

Release 2026-09-17-d277315f7d76 · 1 evaluation · 1 metric row. Different protocols are not a single leaderboard.

Evaluation setupMetricEvidence origin

Results grouped by the exact reported evaluation
Metric and finding	Coverage and uncertainty	Evidence
DNABERT-2: human core-promoter classification Configuration: DNABERT-2Task: human core-promoter classificationDataset: GUE H-CPD DNABERT-2 comparator in consolidated H-CPD table; rerun provenance not explicit Result quoted from another source · Evaluation metadata: needs review
70.52% MCC Unit: percent · Direction: unknown	Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported	source checkedEDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning · Table 5, DNABERT-2 row, H-CPD (MCC) column Source checking is not independent reproduction.

How it works

How the evaluated method works

DNABERT-2 is a pretrained DNA transformer with a downstream classification procedure; the EDEN paper imports comparator values from their respective original studies.

Sources

EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning · Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 2); Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 11)

Underlying method and version boundaries

DNABERT-2 replaces overlapping k-mer tokens with byte-pair encoding and uses ALiBi positional biases. The official 117M model produces 768-dimensional token representations; downstream classifiers and pooling choices are separate configuration details.

Sources

MAGICS-LAB/DNABERT_2 README.md · README.md; introduction, model description, pretrained-model and usage sections at pinned revision

What was evaluated

The linked evaluation record identifies DNABERT-2: human core-promoter classification. Its dataset, split, adaptation and evidence origin remain attached to the reported results.

Sources

EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-b2-eden-genomic-classification-2026

Strengths and limitations

Strengths and considerations

Provides a previously published transformer reference alongside smaller feature-based classifiers.
Sources
EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning · Proposed method: EDEN framework/Multiscale EDN generation using K-mer concept/Biologically-informed multiscale representation (paragraph 3); Proposed method: EDEN framework/Multiscale EDN generation using K-mer concept/Fundamental Distinction from Convolutional Operations (paragraph 2)

Limitations and conditions

Table 5 states that comparator values come from their respective studies. They are quoted evidence, not fresh independent DNABERT-2 runs by the EDEN authors.
Sources
EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning · Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 2); Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 10)

Profile review details

Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction.

Stable record: reported-model-2cb8118b4c77c0

Specifications

Inputs, training, access and other details

Explanatory profile: limited source coverage · Automated source review, 2026-09-16. Review applies to the cited claims; unresolved fields are listed below. Numerical results retain their own review status.

Inputs, outputs and configuration
Property	Description and evidence
Model type	DNA sequence transformer; this record is the paper-specific evaluated configuration. Sources MAGICS-LAB/DNABERT_2 README.md · README.md model description
Architecture / procedure	DNABERT-2 is a pretrained DNA transformer with a downstream classification procedure; the EDEN paper imports comparator values from their respective original studies. Sources EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning · Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 2); Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 11)
Biological inputs	DNA sequences from genomic classification benchmarks Sources EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning · Related work (paragraph 1); Proposed method: EDEN framework/Biological interpretation of EDN/Relationship to known biological patterns (paragraph 1)
Outputs	Task-specific genomic class predictions Sources EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning · Proposed method: EDEN framework/Multiscale EDN generation using K-mer concept/Biologically-informed multiscale representation (paragraph 1); Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 12)
Parameters	117 million parameters as specified in the comparison. Sources EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning · Experimental setup, results, and discussion/Discussion (paragraph 3); Table Tab3 (paragraph 1)
Known versions / configuration	DNABERT-2 is the comparison-table label; that label does not specify an immutable weight revision. · Not reported in inspected sources Sources EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning · Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label.
Training data / fitting	This row is quoted from the DNABERT-2/GUE comparison rather than a new EDEN training run. The EDEN table does not independently establish the exact upstream fine-tuning configuration. Sources EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning · Table 5 and corresponding comparison description
Context limits	A maximum input/context length for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sources Sources (2) EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning; MAGICS-LAB/DNABERT_2 README.md · Proposed method: EDEN framework; Proposed method: EDEN framework/EDN numerical representation; Proposed method: EDEN framework/Multiscale EDN generation using K-mer concept; Proposed method: EDEN framework/Multiscale EDN generation using K-mer concept/A unified framework for sequence encoding; Proposed method: EDEN framework/Multiscale EDN generation using K-mer concept/Biologically-informed multiscale representation; Proposed method: EDEN framework/Multiscale EDN generation using K-mer concept/KDE analysis and bandwidth selection; Proposed method: EDEN framework/Multiscale EDN generation using K-mer concept/Fundamental Distinction from Convolutional Operations; Proposed method: EDEN framework/Multiscale EDN generation using K-mer concept/Computational efficiency and representation properties; inspected for explicit maximum input length (dataset lengths and family-wide limits are not substituted); README.md at pinned repository revision
Access	Official upstream implementation and usage documentation: https://github.com/MAGICS-LAB/DNABERT_2/blob/f25bed9ee20db966dff39e5c1571249d04e36404/README.md. This pinned documentation revision is not automatically the evaluated weight revision. Sources MAGICS-LAB/DNABERT_2 README.md · README.md; installation, model download and usage instructions
Code licence	Apache 2.0 (upstream repository code at the cited revision; this does not establish every dependency or historical checkpoint licence). Sources MAGICS-LAB/DNABERT_2 LICENSE · LICENSE; complete licence text
Weights licence	The inspected model-access documentation does not explicitly identify terms for this exact evaluated checkpoint or fitted head; repository code terms are shown separately. · Not reported in inspected sources Sources MAGICS-LAB/DNABERT_2 README.md · README.md; checkpoint/access documentation and licence scope

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.

21 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-17-d277315f7d76
Property and statement	Original source and location	Review and provenance
Diagram caption Conceptual input–method–output guide. Check the procedure text and linked evaluation for fitted components, additional inputs and exact settings. Individual claims	EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning Original source ↗ Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 2); Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 11) Version: journal full text in PMC Retrieved: 2026-09-16T10:33:37.531Z	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `38a6e26b3caffe8e021a2b0b672218e783aca9ee42046765e323946813015e65` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram steps ["DNA sequences from genomic classification benchmarks","DNABERT-2","Task-specific genomic class predictions"] Individual claims	EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning Original source ↗ Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 2); Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 11) Version: journal full text in PMC Retrieved: 2026-09-16T10:33:37.531Z	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `38a6e26b3caffe8e021a2b0b672218e783aca9ee42046765e323946813015e65` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Diagram title Evaluated procedure (conceptual) Individual claims	EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning Original source ↗ Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 2); Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 11) Version: journal full text in PMC Retrieved: 2026-09-16T10:33:37.531Z	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `38a6e26b3caffe8e021a2b0b672218e783aca9ee42046765e323946813015e65` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Model type DNA sequence transformer; this record is the paper-specific evaluated configuration. Individual claims	MAGICS-LAB/DNABERT_2 README.md Original source ↗ README.md model description Version: f25bed9ee20db966dff39e5c1571249d04e36404 Retrieved: 2026-09-16T20:00:02.624261+00:00	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.0.value` Source artifact SHA-256: `734a8cec5f667d74d421bf3b273ad7e256216109636da45aa7ceba21cd34de16` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Architecture / procedure DNABERT-2 is a pretrained DNA transformer with a downstream classification procedure; the EDEN paper imports comparator values from their respective original studies. Individual claims	EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning Original source ↗ Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 2); Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 11) Version: journal full text in PMC Retrieved: 2026-09-16T10:33:37.531Z	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.1.value` Source artifact SHA-256: `38a6e26b3caffe8e021a2b0b672218e783aca9ee42046765e323946813015e65` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Weights licence The inspected model-access documentation does not explicitly identify terms for this exact evaluated checkpoint or fitted head; repository code terms are shown separately. Individual claims	MAGICS-LAB/DNABERT_2 README.md Original source ↗ README.md; checkpoint/access documentation and licence scope Version: f25bed9ee20db966dff39e5c1571249d04e36404 Retrieved: 2026-09-16T20:00:02.624261+00:00	unreported automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.10.value` Source artifact SHA-256: `734a8cec5f667d74d421bf3b273ad7e256216109636da45aa7ceba21cd34de16` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Biological inputs DNA sequences from genomic classification benchmarks Individual claims	EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning Original source ↗ Related work (paragraph 1); Proposed method: EDEN framework/Biological interpretation of EDN/Relationship to known biological patterns (paragraph 1) Version: journal full text in PMC Retrieved: 2026-09-16T10:33:37.531Z	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.2.value` Source artifact SHA-256: `38a6e26b3caffe8e021a2b0b672218e783aca9ee42046765e323946813015e65` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Outputs Task-specific genomic class predictions Individual claims	EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning Original source ↗ Proposed method: EDEN framework/Multiscale EDN generation using K-mer concept/Biologically-informed multiscale representation (paragraph 1); Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 12) Version: journal full text in PMC Retrieved: 2026-09-16T10:33:37.531Z	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.3.value` Source artifact SHA-256: `38a6e26b3caffe8e021a2b0b672218e783aca9ee42046765e323946813015e65` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Parameters 117 million parameters as specified in the comparison. Individual claims	EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning Original source ↗ Experimental setup, results, and discussion/Discussion (paragraph 3); Table Tab3 (paragraph 1) Version: journal full text in PMC Retrieved: 2026-09-16T10:33:37.531Z	source checked automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.4.value` Source artifact SHA-256: `38a6e26b3caffe8e021a2b0b672218e783aca9ee42046765e323946813015e65` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact
Known versions / configuration DNABERT-2 is the comparison-table label; that label does not specify an immutable weight revision. Individual claims	EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning Original source ↗ Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label. Version: journal full text in PMC Retrieved: 2026-09-16T10:33:37.531Z	unreported automated source review · 2026-09-16 Audit details Primary full text and the available official implementation/model documentation were inspected. Explanatory claims are source-backed; unresolved exact-configuration metadata is labelled explicitly. This is automated review, not a human review or independent benchmark reproduction. Field: `attributes.profile.facts.5.value` Source artifact SHA-256: `38a6e26b3caffe8e021a2b0b672218e783aca9ee42046765e323946813015e65` Hash scope: Hash scope not separately documented; inspect source record Inspected artifact

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

Sources and history

Release 2026-09-17-d277315f7d76 · Record review: needs review

3 source records and release history

EDEN: multiscale expected density of nucleotide encoding for enhanced DNA sequence classification with hybrid deep learning · Original source · journal full text in PMC
MAGICS-LAB/DNABERT_2 README.md · Original source · f25bed9ee20db966dff39e5c1571249d04e36404
MAGICS-LAB/DNABERT_2 LICENSE · Original source · f25bed9ee20db966dff39e5c1571249d04e36404

Download this release

Technical metadata and extraction receipts

Stable ID: reported-model-2cb8118b4c77c0

areas: dna-genomes
entity level: method
version: not stated in table
reported name: DNABERT-2
historical missing metadata: checkpoint revision: not_reported_in_legacy_extract; training data: not_reported_in_legacy_extract; licence: not_reported_in_legacy_extract
metadata review scope: historical_missing_metadata preserves the original discovery state. Current descriptive evidence and missingness are recorded in profile.facts; numerical-result review is separate.
legacy kinds: model
entity classification: review date: 2026-09-17; rationale: This source-scoped entry preserves the method/configuration actually named in an evaluation. It is neither a global family identity nor proof of an immutable checkpoint; the linked evaluation retains adaptation, fitting and scoring details.; source ids: eden-genomic-classification-2026; evidence-reported-base-dnabert2-readme-md; source locator: Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 2); Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 11) | README.md model description | Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 12); Experimental setup, results, and discussion/Comparison with state-of-the-art methods (paragraph 2); ambiguities: Configuration means the source-labelled evaluated identity. It does not establish missing checkpoint hashes, default settings or equivalence to same-named records in other papers.

Related records

model: DNABERT-2: human core-promoter classification

Suggest a correction