Model type
DNA transformer encoder family
Configuration
NT-1000G
Nucleotide Transformer is a family of DNA encoders pretrained on human or multispecies sequence corpora.
Sources (5)
instadeepai/nucleotide-transformer: README.md; instadeepai/nucleotide-transformer: docs/nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/agro_nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/segment_nt.md; nt: Journal full-text XML · docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and TrainingHow it worksNucleotide Transformer workflow
Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation.
Sources (5)
instadeepai/nucleotide-transformer: README.md; instadeepai/nucleotide-transformer: docs/nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/agro_nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/segment_nt.md; nt: Journal full-text XML · docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and TrainingOverview
Inputs
DNA sequences tokenized into 6-mers, with single-base handling of N and remainder bases.
Outputs
Contextual representations used in specified downstream prediction workflows.
Access
Official project documentation and implementation: https://github.com/instadeepai/nucleotide-transformer
Sources (5)
instadeepai/nucleotide-transformer: README.md; instadeepai/nucleotide-transformer: docs/nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/agro_nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/segment_nt.md; nt: Journal full-text XML · docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Traininglimited source coverage · Automated source review, 2026-09-16. All specifications and missing details
Evaluations and results
7 evaluations · 7 results. Different protocols are not a single leaderboard.
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: NT-1000G | Task: BEND CHROMATIN: Chromatin accessibility Dataset subset: ENCODE chromatin accessibility (BEND split) | 0.77 auroc fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT-1000G on BEND CHROMATIN: Chromatin accessibility 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. Aggregation: Not reported BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(NT-1000G), column(Chromatin accessibility) |
| Configuration: NT-1000G | Task: BEND CPG: CpG methylation Dataset subset: ENCODE CpG methylation (BEND split) | 0.89 auroc fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT-1000G on BEND CPG: CpG methylation 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. Aggregation: Not reported BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(NT-1000G), column(CpG methylation) |
| Configuration: NT-1000G | Task: BEND ENHANCER: Enhancer annotation Dataset subset: Fulco 2019, Gasperini 2019 and Enformer enhancer set (BEND split) | 0.04 auprc fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT-1000G on BEND ENHANCER: Enhancer annotation 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. Aggregation: Not reported BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(NT-1000G), column(Enhancer annotation) |
| Configuration: NT-1000G | Task: BEND GENE-FINDING: Gene finding Dataset subset: GENCODE (BEND split) | 0.49 mcc correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT-1000G on BEND GENE-FINDING: Gene finding 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. Aggregation: Not reported BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(NT-1000G), column(Gene finding) |
| Configuration: NT-1000G | Task: BEND HISTONE: Histone modification Dataset subset: ENCODE histone modification (BEND split) | 0.77 auroc fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT-1000G on BEND HISTONE: Histone modification 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. Aggregation: Not reported BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(NT-1000G), column(Histone modification) |
| Configuration: NT-1000G | Task: BEND VARIANT-DISEASE: Noncoding variant effects on disease Dataset subset: ClinVar disease variants (BEND split) | 0.49 auroc fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT-1000G on BEND VARIANT-DISEASE: Noncoding variant effects on disease 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. Aggregation: Not reported BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(NT-1000G), column(Noncoding variant effects on disease) |
| Configuration: NT-1000G | Task: BEND VARIANT-EXPRESSION: Noncoding variant effects on expression Dataset subset: DeepSEA expression variants (BEND split) | 0.45 auroc fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and sourceNT-1000G on BEND VARIANT-EXPRESSION: Noncoding variant effects on expression 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. Aggregation: Not reported BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks · Table 3, row(NT-1000G), column(Noncoding variant effects on expression) |
Source checking is not independent reproduction. Release 2026-09-29-06401fd5b220.
Use this model
How it works, versions and access
Related profile: Nucleotide Transformer. This page retains the exact record and its evaluation context.
This configuration
DNA language model whose frozen embeddings the BEND authors scored with a downstream head.
- record
- NT-1000G
- configuration
- Not reported
- entity type
- Configuration
How it works
How it works
Nucleotide Transformer is a family of DNA encoders pretrained on human or multispecies sequence corpora. Encoder-only transformers with 6-mer tokens; v1 uses learned positional encodings and v2 uses rotary positions and SwiGLU. The documented inputs are DNA sequences tokenized into 6-mers, with single-base handling of N and remainder bases. The output consists of contextual representations used in specified downstream prediction workflows.
Sources (5)
instadeepai/nucleotide-transformer: README.md; instadeepai/nucleotide-transformer: docs/nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/agro_nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/segment_nt.md; nt: Journal full-text XML · docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and TrainingVersions and reproducibility
NT-v1 human-reference/1000G/multispecies variants and NT-v2 50M/100M/250M/500M. NT-v3 is a separate architecture described elsewhere in the repository. v1: approximately 6kb; v2: 2,048 tokens, approximately 12kb. Exact base count depends on special and ambiguous tokens.
Sources (5)
instadeepai/nucleotide-transformer: README.md; instadeepai/nucleotide-transformer: docs/nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/agro_nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/segment_nt.md; nt: Journal full-text XML · docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and TrainingStrengths, limitations and unresolved questions
Strengths and limitations
Strengths and considerations
- The family provides multiple sizes and training corpora, allowing those factors to be compared explicitly.
Sources (5)
instadeepai/nucleotide-transformer: README.md; instadeepai/nucleotide-transformer: docs/nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/agro_nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/segment_nt.md; nt: Journal full-text XML · docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training
Limitations and conditions
- Training corpora and architectures differ across v1 and v2. A family-level name is insufficient to reproduce a score.
Sources (5)
instadeepai/nucleotide-transformer: README.md; instadeepai/nucleotide-transformer: docs/nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/agro_nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/segment_nt.md; nt: Journal full-text XML · docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training
Profile review details
Inspected pinned official documentation, relevant implementation files and named primary-paper sections. Claims are limited to those artifacts. Remaining field extraction and identity conflicts are explicit; no new performance claims, model runs or human review are implied.
Stable record: discovery-model-nucleotide-transformerSpecifications
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.
| Property | Description and evidence |
|---|---|
| Model type | DNA transformer encoder familySources (5)instadeepai/nucleotide-transformer: README.md; instadeepai/nucleotide-transformer: docs/nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/agro_nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/segment_nt.md; nt: Journal full-text XML · docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training |
| Architecture | Encoder-only transformers with 6-mer tokens; v1 uses learned positional encodings and v2 uses rotary positions and SwiGLU.Sources (5)instadeepai/nucleotide-transformer: README.md; instadeepai/nucleotide-transformer: docs/nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/agro_nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/segment_nt.md; nt: Journal full-text XML · docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training |
| Inputs | DNA sequences tokenized into 6-mers, with single-base handling of N and remainder bases.Sources (5)instadeepai/nucleotide-transformer: README.md; instadeepai/nucleotide-transformer: docs/nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/agro_nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/segment_nt.md; nt: Journal full-text XML · docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training |
| Outputs | Contextual representations used in specified downstream prediction workflows.Sources (5)instadeepai/nucleotide-transformer: README.md; instadeepai/nucleotide-transformer: docs/nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/agro_nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/segment_nt.md; nt: Journal full-text XML · docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training |
| Parameters | 50M to 2.5B across the documented v1/v2 family.Sources (5)instadeepai/nucleotide-transformer: README.md; instadeepai/nucleotide-transformer: docs/nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/agro_nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/segment_nt.md; nt: Journal full-text XML · docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training |
| Known versions | NT-v1 human-reference/1000G/multispecies variants and NT-v2 50M/100M/250M/500M. NT-v3 is a separate architecture described elsewhere in the repository.Sources (5)instadeepai/nucleotide-transformer: README.md; instadeepai/nucleotide-transformer: docs/nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/agro_nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/segment_nt.md; nt: Journal full-text XML · docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training |
| Training data | v1 variants use GRCh38, 3,202 human genomes or 850 multispecies genomes; v2 uses the multispecies corpus.Sources (5)instadeepai/nucleotide-transformer: README.md; instadeepai/nucleotide-transformer: docs/nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/agro_nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/segment_nt.md; nt: Journal full-text XML · docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training |
| Training cutoff | The paper specifies human-reference, 1000 Genomes and multispecies training collections by variant. A single latest-deposition date for all sequences is not supplied in the inspected pretraining-data section. · Not reported in inspected sourcesSources (5)instadeepai/nucleotide-transformer: README.md; instadeepai/nucleotide-transformer: docs/nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/agro_nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/segment_nt.md; nt: Journal full-text XML · docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training |
| Context limits | v1: approximately 6kb; v2: 2,048 tokens, approximately 12kb. Exact base count depends on special and ambiguous tokens.Sources (5)instadeepai/nucleotide-transformer: README.md; instadeepai/nucleotide-transformer: docs/nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/agro_nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/segment_nt.md; nt: Journal full-text XML · docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training |
| Weights licence | Separate checkpoint-distribution terms are not stated in the inspected release documentation and licence material. The source-code licence alone is not recorded as an explicit weight grant. · Not reported in inspected sourcesSources (6)instadeepai/nucleotide-transformer: README.md; instadeepai/nucleotide-transformer: docs/nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/agro_nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/segment_nt.md; nt: Journal full-text XML; instadeepai/nucleotide-transformer: LICENSE.md · docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training; LICENSE.md: licence text |
| Access | Official project documentation and implementation: https://github.com/instadeepai/nucleotide-transformerSources (5)instadeepai/nucleotide-transformer: README.md; instadeepai/nucleotide-transformer: docs/nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/agro_nucleotide_transformer.md; instadeepai/nucleotide-transformer: docs/segment_nt.md; nt: Journal full-text XML · docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training |
| Code licence | CC-BY-NC-SA-4.0Sourcesinstadeepai/nucleotide-transformer: LICENSE.md · LICENSE.md: licence text |
Evidence
Source checking verifies the cited claim or transcription. It does not establish 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 |
|---|---|---|
| Relationship: family discovery-model-nucleotide-transformer Individual claims | BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks BEND Table 2 model inventory, Table 3 NT-1000G/NT-V2 rows and Related work NT paragraph; source-labelled configuration NT-1000G | Existing reviewed locator: Table 3, row(NT-1000G) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Primary full-text snapshot retrieved 2026-09-17; exact bytes pinned by SHA-256 | source checked automated source review · 2026-09-23 Audit detailsSource review establishes this relationship only. Exact evaluated configurations and original numerical review status remain unchanged. NT-1000G and NT-V2 explicitly expanded to Nucleotide Transformer in paper; no 50M checkpoint attribution. Field: Claim: model-evaluation-identity-3c65bd4ef83d7dbadfe1 Source artifact SHA-256: Hash scope: Exact retrieved primary paper artifact bytes. |
| Relationship: family discovery-model-nucleotide-transformer Individual claims | instadeepai/nucleotide-transformer: docs/nucleotide_transformer.md BEND Table 2 model inventory, Table 3 NT-1000G/NT-V2 rows and Related work NT paragraph; source-labelled configuration NT-1000G | Existing reviewed locator: Table 3, row(NT-1000G) Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 2dc37b86e16a6970fbc731751f7719d9f676f7f9 | source checked automated source review · 2026-09-23 Audit detailsSource review establishes this relationship only. Exact evaluated configurations and original numerical review status remain unchanged. NT-1000G and NT-V2 explicitly expanded to Nucleotide Transformer in paper; no 50M checkpoint attribution. Field: Claim: model-evaluation-identity-3c65bd4ef83d7dbadfe1 Source artifact SHA-256: Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact |
Sources and history
View linked audit checks and correction history
Release 2026-09-29-06401fd5b220 · 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-method-nt-1000g
- areas
- dna-genomes
- source locator
- Table 3, row(NT-1000G)
- missing metadata
- checkpoint revision: unreported; parameters: unextracted
Related records
- family: Nucleotide Transformer
- model: NT-1000G on BEND CHROMATIN: Chromatin accessibility
- model: NT-1000G on BEND CPG: CpG methylation
- model: NT-1000G on BEND ENHANCER: Enhancer annotation
- model: NT-1000G on BEND GENE-FINDING: Gene finding
- model: NT-1000G on BEND HISTONE: Histone modification
- model: NT-1000G on BEND VARIANT-DISEASE: Noncoding variant effects on disease
- model: NT-1000G on BEND VARIANT-EXPRESSION: Noncoding variant effects on expression
- subject: NT-1000G: family Nucleotide Transformer