Model

Nucleotide Transformer

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 Training

263 evaluations · 265 results · 20 evaluated configurations using this model

How 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)

Overview

Model type

DNA transformer encoder family

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)

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

Evaluations and results

263 evaluations · 265 results. Different protocols are not a single leaderboard.

Filter evaluations

Tested model or methodProtocolDatasetEvaluation setupMetricEvidence origin

Applied filters: All linked evaluations

Exact evaluated configurations and original reported results
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 checked Methods, coverage and source NT-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 checked Methods, coverage and source NT-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 checked Methods, coverage and source NT-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 checked Methods, coverage and source NT-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 checked Methods, coverage and source NT-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 checked Methods, coverage and source NT-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 checked Methods, coverage and source NT-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)
Configuration: NT-V2	Task: BEND CHROMATIN: Chromatin accessibility Dataset subset: ENCODE chromatin accessibility (BEND split)	0.8 auroc fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source NT-V2 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-V2), column(Chromatin accessibility)
Configuration: NT-V2	Task: BEND CPG: CpG methylation Dataset subset: ENCODE CpG methylation (BEND split)	0.91 auroc fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source NT-V2 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-V2), column(CpG methylation)
Configuration: NT-V2	Task: BEND ENHANCER: Enhancer annotation Dataset subset: Fulco 2019, Gasperini 2019 and Enformer enhancer set (BEND split)	0.05 auprc fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source NT-V2 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-V2), column(Enhancer annotation)
Configuration: NT-V2	Task: BEND GENE-FINDING: Gene finding Dataset subset: GENCODE (BEND split)	0.64 mcc correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source NT-V2 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-V2), column(Gene finding)
Configuration: NT-V2	Task: BEND HISTONE: Histone modification Dataset subset: ENCODE histone modification (BEND split)	0.76 auroc fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source NT-V2 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-V2), column(Histone modification)
Configuration: NT-V2	Task: BEND VARIANT-DISEASE: Noncoding variant effects on disease Dataset subset: ClinVar disease variants (BEND split)	0.48 auroc fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source NT-V2 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-V2), column(Noncoding variant effects on disease)
Configuration: NT-V2	Task: BEND VARIANT-EXPRESSION: Noncoding variant effects on expression Dataset subset: DeepSEA expression variants (BEND split)	0.48 auroc fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source NT-V2 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-V2), column(Noncoding variant effects on expression)
Configuration: Nucleotide Transformer (fine-tuned)	Task: DART-Eval CA-AUROC-GM12878: Chromatin activity prediction, GM12878, positives against negatives Dataset subset: ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.938 auroc fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Nucleotide Transformer (fine-tuned) on DART-Eval CA-AUROC-GM12878: Chromatin activity prediction, GM12878, positives against negatives Separating positive GM12878 peaks from matched negatives. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 5, row(Fine-Tuned NT), column(CA-AUROC-GM12878)
Configuration: Nucleotide Transformer (fine-tuned)	Task: DART-Eval CA-AUROC-H1ESC: Chromatin activity prediction, H1ESC, positives against negatives Dataset subset: ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.958 auroc fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Nucleotide Transformer (fine-tuned) on DART-Eval CA-AUROC-H1ESC: Chromatin activity prediction, H1ESC, positives against negatives Separating positive H1ESC peaks from matched negatives. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 5, row(Fine-Tuned NT), column(CA-AUROC-H1ESC)
Configuration: Nucleotide Transformer (fine-tuned)	Task: DART-Eval CA-AUROC-HEPG2: Chromatin activity prediction, HEPG2, positives against negatives Dataset subset: ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.922 auroc fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Nucleotide Transformer (fine-tuned) on DART-Eval CA-AUROC-HEPG2: Chromatin activity prediction, HEPG2, positives against negatives Separating positive HEPG2 peaks from matched negatives. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 5, row(Fine-Tuned NT), column(CA-AUROC-HEPG2)
Configuration: Nucleotide Transformer (fine-tuned)	Task: DART-Eval CA-AUROC-IMR90: Chromatin activity prediction, IMR90, positives against negatives Dataset subset: ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.975 auroc fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Nucleotide Transformer (fine-tuned) on DART-Eval CA-AUROC-IMR90: Chromatin activity prediction, IMR90, positives against negatives Separating positive IMR90 peaks from matched negatives. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 5, row(Fine-Tuned NT), column(CA-AUROC-IMR90)
Configuration: Nucleotide Transformer (fine-tuned)	Task: DART-Eval CA-AUROC-K562: Chromatin activity prediction, K562, positives against negatives Dataset subset: ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.941 auroc fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Nucleotide Transformer (fine-tuned) on DART-Eval CA-AUROC-K562: Chromatin activity prediction, K562, positives against negatives Separating positive K562 peaks from matched negatives. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 5, row(Fine-Tuned NT), column(CA-AUROC-K562)
Configuration: Nucleotide Transformer (fine-tuned)	Task: DART-Eval CA-SPEARMAN-GM12878: Chromatin activity prediction, GM12878, positives only Dataset subset: ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.515 spearman_r correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Nucleotide Transformer (fine-tuned) on DART-Eval CA-SPEARMAN-GM12878: Chromatin activity prediction, GM12878, positives only Rank correlation with measured accessibility among positive GM12878 peaks. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 5, row(Fine-Tuned NT), column(CA-SPEARMAN-GM12878)
Configuration: Nucleotide Transformer (fine-tuned)	Task: DART-Eval CA-SPEARMAN-H1ESC: Chromatin activity prediction, H1ESC, positives only Dataset subset: ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.737 spearman_r correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Nucleotide Transformer (fine-tuned) on DART-Eval CA-SPEARMAN-H1ESC: Chromatin activity prediction, H1ESC, positives only Rank correlation with measured accessibility among positive H1ESC peaks. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 5, row(Fine-Tuned NT), column(CA-SPEARMAN-H1ESC)
Configuration: Nucleotide Transformer (fine-tuned)	Task: DART-Eval CA-SPEARMAN-HEPG2: Chromatin activity prediction, HEPG2, positives only Dataset subset: ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.513 spearman_r correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Nucleotide Transformer (fine-tuned) on DART-Eval CA-SPEARMAN-HEPG2: Chromatin activity prediction, HEPG2, positives only Rank correlation with measured accessibility among positive HEPG2 peaks. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 5, row(Fine-Tuned NT), column(CA-SPEARMAN-HEPG2)
Configuration: Nucleotide Transformer (fine-tuned)	Task: DART-Eval CA-SPEARMAN-IMR90: Chromatin activity prediction, IMR90, positives only Dataset subset: ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.489 spearman_r correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Nucleotide Transformer (fine-tuned) on DART-Eval CA-SPEARMAN-IMR90: Chromatin activity prediction, IMR90, positives only Rank correlation with measured accessibility among positive IMR90 peaks. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 5, row(Fine-Tuned NT), column(CA-SPEARMAN-IMR90)
Configuration: Nucleotide Transformer (fine-tuned)	Task: DART-Eval CA-SPEARMAN-K562: Chromatin activity prediction, K562, positives only Dataset subset: ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.583 spearman_r correlation · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Nucleotide Transformer (fine-tuned) on DART-Eval CA-SPEARMAN-K562: Chromatin activity prediction, K562, positives only Rank correlation with measured accessibility among positive K562 peaks. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 5, row(Fine-Tuned NT), column(CA-SPEARMAN-K562)
Configuration: Nucleotide Transformer (fine-tuned)	Task: DART-Eval CTS-ACC: Cell-type-specific element classification, overall accuracy Dataset subset: ENCODE chromatin accessibility peaks in five cell lines (DART-Eval split)	0.632 accuracy fraction · higher Uncertainty: Not reported Coverage: Not reported scored / Not reported eligible	Author-reported evaluation · Source checked Methods, coverage and source Nucleotide Transformer (fine-tuned) on DART-Eval CTS-ACC: Cell-type-specific element classification, overall accuracy Classify which of five cell lines a accessible element belongs to. Aggregation: Not reported DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA · Table 4, row(Fine-Tuned Nucleotide Transformer), column(CTS-ACC)

Source checking is not independent reproduction. Release 2026-09-29-06401fd5b220.

Related configurations, pipelines and services

These configurations, services and pipelines use this model within their own configurations. Their results, where available, are not assigned to the underlying model.

NT-2.5b-1000g Pipeline · 16 results
NT-2.5b-Multi Pipeline · 16 results
NT-v2 Pipeline · 7 results
nt-2.5b-1000g Pipeline · 8 results
nt-2.5b-multi-species Pipeline · 8 results
nt-500m-1000g Pipeline · 8 results
nt-500m-human-ref Pipeline · 8 results
nt-v2–100m-multi-species Pipeline · 8 results
nt-v2–250m-multi-species Pipeline · 8 results
nt-v2–500m-multi-species Pipeline · 8 results
nt-v2–50m-multi-species Pipeline · 8 results
NTv2† Pipeline · 6 results
Nucleotide Transformer + NN (middle) Pipeline · 1 result
SegmentNT-10kb Configuration · 28 results
SegmentNT-20kb Configuration · 28 results
SegmentNT-30kb Configuration · 28 results
SegmentNT-3kb Configuration · 28 results
SegmentNT-3kb (NTv1 human; 2.5B) Configuration · 28 results
SegmentNT-3kb (only head) Configuration · 28 results
SegmentNT-3kb-single-task (x14) Configuration · 28 results

Use this model

How it works, versions and access

Versions and evaluated configurations

NT-1000G · family
NT-V2 · family
Nucleotide Transformer v2 · variant of
Nucleotide Transformer (fine-tuned) · family
Nucleotide Transformer (probed) · family
Nucleotide Transformer (zero-shot) · family
Nucleotide Transformer (zero-shot embedding) · family
Nucleotide Transformer (zero-shot likelihood) · family
NT-v2-50M-MS · family
NT-2500M-1000g · family
NT-2500M-multi · family
NT-500M-1000g · family
NT-500M-human · family
NT · family
N.T.-500m · family
N.T.-v2-500m · family
N.T.-v2-50m · family
Nucleotide Transformers V2 · family
NT-v2 · family

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)

Versions 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)

Strengths, 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-transformer

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 transformer encoder 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
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 sources 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
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 sources Sources (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-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 Training
Code licence	CC-BY-NC-SA-4.0 Sources instadeepai/nucleotide-transformer: LICENSE.md · LICENSE.md: licence text

Applicable tests and references

Applicability is distinct from a completed evaluation.

GENEB · Proposed association

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.

97 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-29-06401fd5b220
Property and statement	Original source and location	Review and provenance
Diagram caption Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation. Individual claims	instadeepai/nucleotide-transformer: README.md Original source ↗ docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 2dc37b86e16a6970fbc731751f7719d9f676f7f9 Retrieved: 2026-09-16T19:46:19.364532+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `9f51bbb20c4c5c36e77fb03ca1c5c36236e287c48a1ee31f53150545d421ec25` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram caption Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation. Individual claims	instadeepai/nucleotide-transformer: docs/segment_nt.md Original source ↗ docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 2dc37b86e16a6970fbc731751f7719d9f676f7f9 Retrieved: 2026-09-16T19:46:19.364532+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `8eec4580ba64ab944fb9b42674be70ffe793135f3503cce8640f5b08f8290f7a` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram caption Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation. Individual claims	instadeepai/nucleotide-transformer: docs/agro_nucleotide_transformer.md Original source ↗ docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 2dc37b86e16a6970fbc731751f7719d9f676f7f9 Retrieved: 2026-09-16T19:46:19.364532+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `23e27d40473bbabadac45c56e8e282349f0b053da85fda89ff2125b5fe381fc6` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram caption Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation. Individual claims	instadeepai/nucleotide-transformer: docs/nucleotide_transformer.md Original source ↗ docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 2dc37b86e16a6970fbc731751f7719d9f676f7f9 Retrieved: 2026-09-16T19:46:19.364532+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `ab16d582de98652526b5cebb120eec969328f9db29dc741826bcd81c397e0672` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram caption Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation. Individual claims	nt: Journal full-text XML Original source ↗ docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Retrieved page snapshot; no immutable publisher revision supplied Retrieved: 2026-09-16T20:16:14.422628+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `7c3b78a4f38ef053a08e466222e5662dd9711d91c535512d0b35d459d1fc7249` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram steps DNA sequence 6-mer tokenization Selected NT encoder Representation or adapted predictor Individual claims	instadeepai/nucleotide-transformer: README.md Original source ↗ docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 2dc37b86e16a6970fbc731751f7719d9f676f7f9 Retrieved: 2026-09-16T19:46:19.364532+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `9f51bbb20c4c5c36e77fb03ca1c5c36236e287c48a1ee31f53150545d421ec25` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram steps DNA sequence 6-mer tokenization Selected NT encoder Representation or adapted predictor Individual claims	instadeepai/nucleotide-transformer: docs/segment_nt.md Original source ↗ docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 2dc37b86e16a6970fbc731751f7719d9f676f7f9 Retrieved: 2026-09-16T19:46:19.364532+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `8eec4580ba64ab944fb9b42674be70ffe793135f3503cce8640f5b08f8290f7a` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram steps DNA sequence 6-mer tokenization Selected NT encoder Representation or adapted predictor Individual claims	instadeepai/nucleotide-transformer: docs/agro_nucleotide_transformer.md Original source ↗ docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 2dc37b86e16a6970fbc731751f7719d9f676f7f9 Retrieved: 2026-09-16T19:46:19.364532+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `23e27d40473bbabadac45c56e8e282349f0b053da85fda89ff2125b5fe381fc6` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram steps DNA sequence 6-mer tokenization Selected NT encoder Representation or adapted predictor Individual claims	instadeepai/nucleotide-transformer: docs/nucleotide_transformer.md Original source ↗ docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 2dc37b86e16a6970fbc731751f7719d9f676f7f9 Retrieved: 2026-09-16T19:46:19.364532+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `ab16d582de98652526b5cebb120eec969328f9db29dc741826bcd81c397e0672` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram steps DNA sequence 6-mer tokenization Selected NT encoder Representation or adapted predictor Individual claims	nt: Journal full-text XML Original source ↗ docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Retrieved page snapshot; no immutable publisher revision supplied Retrieved: 2026-09-16T20:16:14.422628+00:00	source checked automated source review · 2026-09-16 Audit 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. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `7c3b78a4f38ef053a08e466222e5662dd9711d91c535512d0b35d459d1fc7249` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact

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

Sources and history

View linked audit checks and correction history

Release 2026-09-29-06401fd5b220 · Record review: discovered

7 source records and release history

instadeepai/nucleotide-transformer official source · Original source · 2dc37b86e16a6970fbc731751f7719d9f676f7f9
instadeepai/nucleotide-transformer: README.md · Original source · 2dc37b86e16a6970fbc731751f7719d9f676f7f9
instadeepai/nucleotide-transformer: docs/nucleotide_transformer.md · Original source · 2dc37b86e16a6970fbc731751f7719d9f676f7f9
instadeepai/nucleotide-transformer: docs/agro_nucleotide_transformer.md · Original source · 2dc37b86e16a6970fbc731751f7719d9f676f7f9
instadeepai/nucleotide-transformer: docs/segment_nt.md · Original source · 2dc37b86e16a6970fbc731751f7719d9f676f7f9
nt: Journal full-text XML · Original source · Retrieved page snapshot; no immutable publisher revision supplied
instadeepai/nucleotide-transformer: LICENSE.md · Original source · 2dc37b86e16a6970fbc731751f7719d9f676f7f9

Download this release

Technical metadata and extraction receipts

Stable ID: discovery-model-nucleotide-transformer

areas: genomics
access: official_source_linked
benchmark applicability: candidate; not evidence of a reported evaluation
candidate benchmark ids: discovery-benchmark-geneb
entity level: family
reported name: Nucleotide Transformer
version: Not reported
historical missing metadata: checkpoint: unextracted; code licence: unextracted; parameters: unextracted; training cutoff: unextracted; training data: unextracted; version: unextracted; weights licence: unextracted
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.
entity classification: review date: 2026-09-17; rationale: The cited profile describes a named learned biological predictor or representation model/family. Preserve this identity separately from task-specific fitting, individual checkpoints, pipelines and hosted access.; source ids: evidence-official-18d8f4d5fc3f6616922d; evidence-official-657e83427ab59f3aec83; evidence-official-56f02d45976d011d80aa; evidence-official-4920952f9b3c4b8909a0; evidence-official-aadbeb0f10ec55d34f5f; source locator: docs/nucleotide_transformer.md: Model Variants and Sizes, Tokenization and How to use; Nucleotide Transformer paper Methods: Architecture, Pre-training datasets and Training; ambiguities: None recorded

Related records

applicable to: GENEB
family: NT-1000G
family: NT-V2
variant of: Nucleotide Transformer v2
family: Nucleotide Transformer (fine-tuned)
family: Nucleotide Transformer (probed)
family: Nucleotide Transformer (zero-shot)
family: Nucleotide Transformer (zero-shot embedding)
family: Nucleotide Transformer (zero-shot likelihood)
family: NT-v2-50M-MS
family: NT-2500M-1000g
family: NT-2500M-multi
family: NT-500M-1000g
family: NT-500M-human
uses model: NT-2.5b-1000g
uses model: NT-2.5b-Multi
uses model: NT-v2
family: NT
uses model: nt-2.5b-1000g
uses model: nt-2.5b-multi-species
uses model: nt-500m-1000g
uses model: nt-500m-human-ref
uses model: nt-v2–100m-multi-species
uses model: nt-v2–250m-multi-species
uses model: nt-v2–500m-multi-species
uses model: nt-v2–50m-multi-species
family: N.T.-500m
family: N.T.-v2-500m
family: N.T.-v2-50m
family: Nucleotide Transformers V2
uses model: NTv2†
uses model: Nucleotide Transformer + NN (middle)
family: NT-v2
uses model: SegmentNT-10kb
uses model: SegmentNT-20kb
uses model: SegmentNT-30kb
uses model: SegmentNT-3kb
uses model: SegmentNT-3kb (NTv1 human; 2.5B)
uses model: SegmentNT-3kb (only head)
uses model: SegmentNT-3kb-single-task (x14)

Suggest a correction