Model type
Plant DNA transformer encoder
Configuration
AgroNT: promoter strength, maize protoplasts
AgroNT learns DNA representations from plant reference genomes for plant molecular prediction tasks.
Sources (7)
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; InstaDeepAI/agro-nucleotide-transformer-1b: README.md; InstaDeepAI/agro-nucleotide-transformer-1b: config.json; agront: Journal full-text XML · AgroNT paper Methods: Architecture, Pre-training dataset and Pre-training strategy; official model-card licence metadataHow it worksAgro Nucleotide Transformer workflow
Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation.
Sources (7)
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; InstaDeepAI/agro-nucleotide-transformer-1b: README.md; InstaDeepAI/agro-nucleotide-transformer-1b: config.json; agront: Journal full-text XML · AgroNT paper Methods: Architecture, Pre-training dataset and Pre-training strategy; official model-card licence metadataOverview
Inputs
Plant DNA sequence, with standalone tokens for ambiguous or remainder bases.
Outputs
DNA embeddings for downstream regulatory, RNA-processing or expression tasks.
Access
Official project documentation and implementation: https://github.com/instadeepai/nucleotide-transformer
Sources (7)
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; InstaDeepAI/agro-nucleotide-transformer-1b: README.md; InstaDeepAI/agro-nucleotide-transformer-1b: config.json; agront: Journal full-text XML · AgroNT paper Methods: Architecture, Pre-training dataset and Pre-training strategy; official model-card licence metadatalimited source coverage · Automated source review, 2026-09-16. All specifications and missing details
Evaluations and results
3 evaluations · 3 results. Different protocols are not a single leaderboard.
Sorted by R² (higher is better). The best value in each column is highlighted. Decimals are rounded for display; each value links to the printed value and its source.
All 3 result rows with coverage, uncertainty and sources
Filter evaluations
Applied filters: All linked evaluations
| Tested configuration | Protocol and dataset | Finding | Evidence and details |
|---|---|---|---|
| Configuration: AgroNT: promoter strength, maize protoplasts | Protocol: PGB promoter strength maize protoplasts: A. thaliana: promoter strength prediction Dataset subset: promoter strength test sequences: maize protoplasts: A. thaliana (PGB promoter strength split) | 0.62 R² unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and source170 bp assay sequences; original study train/test datasets, as described in Methods Sec21. R² is scored separately by assay system and sequence class. Fitted model checkpoint, seeds and scored counts are not established here. Aggregation: Not reported AgroNT Figure 3e source table · Figures/Fig3_panele.txt, line 2 (data row 1), column R2; Species=A. thaliana; Model=Maize model; Type=AgroNT |
| Configuration: AgroNT: promoter strength, maize protoplasts | Protocol: PGB promoter strength maize protoplasts: S. bicolor: promoter strength prediction Dataset subset: promoter strength test sequences: maize protoplasts: S. bicolor (PGB promoter strength split) | 0.68 R² unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and source170 bp assay sequences; original study train/test datasets, as described in Methods Sec21. R² is scored separately by assay system and sequence class. Fitted model checkpoint, seeds and scored counts are not established here. Aggregation: Not reported AgroNT Figure 3e source table · Figures/Fig3_panele.txt, line 3 (data row 2), column R2; Species=S. bicolor; Model=Maize model; Type=AgroNT |
| Configuration: AgroNT: promoter strength, maize protoplasts | Protocol: PGB promoter strength maize protoplasts: Z. mays: promoter strength prediction Dataset subset: promoter strength test sequences: maize protoplasts: Z. mays (PGB promoter strength split) | 0.71 R² unitless · higher Uncertainty: Not yet extracted Coverage: Not reported scored / Not reported eligible | Author-reported evaluation · Source checkedMethods, coverage and source170 bp assay sequences; original study train/test datasets, as described in Methods Sec21. R² is scored separately by assay system and sequence class. Fitted model checkpoint, seeds and scored counts are not established here. Aggregation: Not reported AgroNT Figure 3e source table · Figures/Fig3_panele.txt, line 4 (data row 3), column R2; Species=Z. mays; Model=Maize model; Type=AgroNT |
Source checking is not independent reproduction. Release 2026-11-02-a7f03c9e55a5.
Use this configuration
How it works, versions and access
Related profile: Agro Nucleotide Transformer. This page retains the exact record and its evaluation context.
This configuration
AgroNT with task-specific regression and IA3 fine-tuning, as described in the paper. Exact fitted checkpoint is unreported.
- record
- AgroNT: promoter strength, maize protoplasts
- configuration
- Not reported
- entity type
- Configuration
How it works
How it works
One-billion-parameter encoder-only transformer with 40 attention blocks, hidden width 1,500, learned positional embeddings and a six-mer masked-language-model head. The documented inputs are plant DNA sequence, with standalone tokens for ambiguous or remainder bases. The output consists of DNA embeddings for downstream regulatory, RNA-processing or expression tasks.
Sources (7)
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; InstaDeepAI/agro-nucleotide-transformer-1b: README.md; InstaDeepAI/agro-nucleotide-transformer-1b: config.json; agront: Journal full-text XML · AgroNT paper Methods: Architecture, Pre-training dataset and Pre-training strategy; official model-card licence metadataVersions and reproducibility
1B_agro_nt pretrained model. 1,024 tokens, approximately 6kb of unambiguous sequence rather than an unconditional 6,144-base guarantee.
Sources (7)
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; InstaDeepAI/agro-nucleotide-transformer-1b: README.md; InstaDeepAI/agro-nucleotide-transformer-1b: config.json; agront: Journal full-text XML · AgroNT paper Methods: Architecture, Pre-training dataset and Pre-training strategy; official model-card licence metadataStrengths, limitations and unresolved questions
Strengths and limitations
Strengths and considerations
- Pretraining explicitly targets plant reference genomes, predominantly crop species.
Sources (7)
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; InstaDeepAI/agro-nucleotide-transformer-1b: README.md; InstaDeepAI/agro-nucleotide-transformer-1b: config.json; agront: Journal full-text XML · AgroNT paper Methods: Architecture, Pre-training dataset and Pre-training strategy; official model-card licence metadata
Limitations and conditions
- The context is counted in tokens: the class token and ambiguous bases reduce the maximum number of ordinary bases represented. Predictions outside the studied species/tasks need separate evaluation.
Sources (7)
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; InstaDeepAI/agro-nucleotide-transformer-1b: README.md; InstaDeepAI/agro-nucleotide-transformer-1b: config.json; agront: Journal full-text XML · AgroNT paper Methods: Architecture, Pre-training dataset and Pre-training strategy; official model-card licence metadata
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-agro-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.
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.
3 evidence rows matching the loaded filters
| Property and statement | Original source and location | Review and provenance |
|---|---|---|
Facets: method types1 values
| AgroNT Figure 3e source table AgroNT is a pretrained genomic language model Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 78ec8156c2ffb3e5475277fdb7eb603294224e53 | conflicting claim ["automated-source-review"] · 2026-10-12 Audit detailsCorrect the method type from none to foundation_model (use-case baseline review 2026-10-12, table 2). Evidence from docs/reviews/use-cases/baselines-2026-10-12.md. Independent review 2026-10-12: approved. See docs/reviews/2026-10-12-method-type-corrections.md. Conflicting source claim: Field: Claim: metadata-correction-tags-20261012-cc60483055117ca69524 Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Facets: method types1 values
| AgroNT: published methods and Figure 3 AgroNT is a pretrained genomic language model Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: Version of record, 2024-07-09; retrieved XML snapshot | conflicting claim ["automated-source-review"] · 2026-10-12 Audit detailsCorrect the method type from none to foundation_model (use-case baseline review 2026-10-12, table 2). Evidence from docs/reviews/use-cases/baselines-2026-10-12.md. Independent review 2026-10-12: approved. See docs/reviews/2026-10-12-method-type-corrections.md. Conflicting source claim: Field: Claim: metadata-correction-tags-20261012-cc60483055117ca69524 Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Relationship: family discovery-model-agro-nucleotide-transformer Individual claims | AgroNT: published methods and Figure 3 Methods: Fine-tuning strategy (Sec16), Promoter and terminator strength prediction (Sec21); Figure 3 caption Version: Version of record, 2024-07-09; retrieved XML snapshot | source checked ["automated-source-review"] · 2026-09-23 Audit detailsPrimary methods and figure identity; no exact fitted checkpoint inferred. Field: Claim: agront-2024-fig3e-method-agront-promoter-strength-maize-protoplasts-family-claim Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
Release 2026-11-02-a7f03c9e55a5 · Record review: source checked
2 source records and release history
- AgroNT Figure 3e source table · Original source · 78ec8156c2ffb3e5475277fdb7eb603294224e53
- AgroNT: published methods and Figure 3 · Original source · Version of record, 2024-07-09; retrieved XML snapshot
Technical metadata and extraction receipts
Stable ID: agront-2024-fig3e-method-agront-promoter-strength-maize-protoplasts
- areas
- dna-genomes
- method types
- foundation_model
- source locator
- Fig3_panele.txt, Type=AgroNT, Model=Maize model; Methods: Fine-tuning strategy (Sec16), Promoter and terminator strength prediction (Sec21); Figure 3 caption
- missing metadata
- checkpoint revision: reason: unreported; parameters: reason: unextracted
Related records
- family: Agro Nucleotide Transformer
- system: AgroNT: promoter strength, maize protoplasts on PGB promoter strength maize protoplasts: A. thaliana: promoter strength prediction
- system: AgroNT: promoter strength, maize protoplasts on PGB promoter strength maize protoplasts: S. bicolor: promoter strength prediction
- system: AgroNT: promoter strength, maize protoplasts on PGB promoter strength maize protoplasts: Z. mays: promoter strength prediction
- subject: AgroNT: promoter strength, maize protoplasts: AgroNT family
- subject: AgroNT: promoter strength, maize protoplasts: facets.method_types