Model type
Study-specific predictive method; this record is the paper-specific evaluated configuration.
Configuration
CodonBERT
CodonBERT learns mRNA representations using codon tokens and adapts them to mRNA-property prediction.
Sources
CodonBERT large language model for mRNA vaccines · Results (paragraph 1); Methods/Model architecture (paragraph 2)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
CodonBERT large language model for mRNA vaccines · Results/Pretrained representation model (paragraph 1); Methods/Pretraining CodonBERT (paragraph 6)At a glance
Biological inputs
Coding mRNA sequences represented as codons
Sources
CodonBERT large language model for mRNA vaccines · Results (paragraph 1); Methods/Assembly of mRNA sequences for pretraining (paragraph 2)Outputs
mRNA embeddings and task-specific property predictions
Sources
CodonBERT large language model for mRNA vaccines · Methods/Pretraining CodonBERT (paragraph 6); Results (paragraph 2)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.
| Metric and finding | Coverage and uncertainty | Evidence |
|---|---|---|
| CodonBERT: flu-vaccine mRNA property prediction codon-based model fine-tuned for downstream regression Author-reported evaluation · Evaluation metadata: needs review | ||
| 0.81 Spearman rho Unit: unitless · Direction: unknown | Uncertainty: not reported in legacy extract Scored: Not reported · Eligible: Not reported | source checkedCodonBERT large language model for mRNA vaccines · Table 2, CodonBERT row, Flu vaccines Spearman correlation column Source checking is not independent reproduction. |
How it works
How the evaluated method works
A BERT-style model treats codons as tokens. Pretraining includes masked-language modelling and an STP task described in the paper, followed by supervised downstream prediction.
Sources
CodonBERT large language model for mRNA vaccines · Results/Pretrained representation model (paragraph 1); Methods/Pretraining CodonBERT (paragraph 6)What was evaluated
The linked evaluation record identifies CodonBERT: flu-vaccine mRNA property prediction. Its dataset, split, adaptation and evidence origin remain attached to the reported results.
Sources
CodonBERT large language model for mRNA vaccines · The named evaluation’s methods and comparison table; exact preserved evaluation IDs: evaluation-b2-codonbert-vaccines-2024Strengths and limitations
Strengths and considerations
- Codon-level inputs expose coding structure directly instead of requiring the model to recover reading-frame units from single bases.
Sources
CodonBERT large language model for mRNA vaccines · Results (paragraph 2); Methods/Assembly of mRNA sequences for pretraining (paragraph 2)
Limitations and conditions
- The learned representation and task-specific property heads must be distinguished; performance depends on the mRNA assay and downstream training data.
Sources
CodonBERT large language model for mRNA vaccines · Methods/Pretraining CodonBERT (paragraph 6); Results/Evaluating CodonBERT and comparison to prior methods on supervised learning tasks (paragraph 3)
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-cd246741c378dbSpecifications
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 | Study-specific predictive method; this record is the paper-specific evaluated configuration.SourcesCodonBERT large language model for mRNA vaccines · Results/Pretrained representation model (paragraph 1); Methods/Pretraining CodonBERT (paragraph 6) |
| Architecture / procedure | A BERT-style model treats codons as tokens. Pretraining includes masked-language modelling and an STP task described in the paper, followed by supervised downstream prediction.SourcesCodonBERT large language model for mRNA vaccines · Results/Pretrained representation model (paragraph 1); Methods/Pretraining CodonBERT (paragraph 6) |
| Biological inputs | Coding mRNA sequences represented as codonsSourcesCodonBERT large language model for mRNA vaccines · Results (paragraph 1); Methods/Assembly of mRNA sequences for pretraining (paragraph 2) |
| Outputs | mRNA embeddings and task-specific property predictionsSourcesCodonBERT large language model for mRNA vaccines · Methods/Pretraining CodonBERT (paragraph 6); Results (paragraph 2) |
| Parameters | Approximately 110 million parameters; 12 layers, 12 attention heads and hidden size 768.SourcesCodonBERT large language model for mRNA vaccines · Methods/Pretraining CodonBERT (paragraph 5); Methods/Model architecture (paragraph 3) |
| Known versions / configuration | CodonBERT is the comparison-table label; that label does not specify an immutable weight revision. · Not reported in inspected sourcesSourcesCodonBERT large language model for mRNA vaccines · Model identification in the comparison table and corresponding Methods; immutable checkpoint revision is not supplied by the table label. |
| Training data / fitting | More than ten million mRNA sequences from multiple organisms; 1% of each category is held out during pretraining.SourcesCodonBERT large language model for mRNA vaccines · Methods/Pretraining CodonBERT (paragraph 5); Methods/Assembly of mRNA sequences for pretraining (paragraph 1) |
| Context limits | A maximum input/context length for this exact evaluated configuration is not established by the inspected sources. · Not reported in inspected sourcesSources (2)CodonBERT large language model for mRNA vaccines; Sanofi-Public/CodonBert README.md · Results/Pretrained representation model; Results/Evaluating CodonBERT and comparison to prior methods on supervised learning tasks; Methods/Assembly of mRNA sequences for pretraining; Methods/Model architecture; Methods/Pretraining CodonBERT; Methods/Pretraining Codon2vec; Methods/In vitro transcription, cell culture, and transfections; Methods/Comparisons to other methods; inspected for explicit maximum input length (dataset lengths and family-wide limits are not substituted); README.md at pinned repository revision |
| Access | Official study implementation and usage documentation: https://github.com/Sanofi-Public/CodonBert/blob/451a1b167c06028dfbf2ff7aa2cfdea46fbcc4f4/README.md. This pinned documentation revision is not automatically the evaluated weight revision.SourcesSanofi-Public/CodonBert README.md · README.md; installation, model download and usage instructions |
| Code licence | No explicit code licence was established from the paper’s availability statement and inspected repository-root documentation. · Not reported in inspected sourcesSourcesSanofi-Public/CodonBert README.md · README.md and repository-root licence-file search |
| 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 sourcesSourcesSanofi-Public/CodonBert 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.
20 evidence rows matching the loaded filters
| 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 | CodonBERT large language model for mRNA vaccines Results/Pretrained representation model (paragraph 1); Methods/Pretraining CodonBERT (paragraph 6) Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsPrimary 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: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram steps ["Coding mRNA sequences represented as codons","CodonBERT","mRNA embeddings and task-specific property predictions"] Individual claims | CodonBERT large language model for mRNA vaccines Results/Pretrained representation model (paragraph 1); Methods/Pretraining CodonBERT (paragraph 6) Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsPrimary 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: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Diagram title Evaluated procedure (conceptual) Individual claims | CodonBERT large language model for mRNA vaccines Results/Pretrained representation model (paragraph 1); Methods/Pretraining CodonBERT (paragraph 6) Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsPrimary 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: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Model type Study-specific predictive method; this record is the paper-specific evaluated configuration. Individual claims | CodonBERT large language model for mRNA vaccines Results/Pretrained representation model (paragraph 1); Methods/Pretraining CodonBERT (paragraph 6) Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsPrimary 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: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Architecture / procedure A BERT-style model treats codons as tokens. Pretraining includes masked-language modelling and an STP task described in the paper, followed by supervised downstream prediction. Individual claims | CodonBERT large language model for mRNA vaccines Results/Pretrained representation model (paragraph 1); Methods/Pretraining CodonBERT (paragraph 6) Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsPrimary 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: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| 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 | Sanofi-Public/CodonBert README.md README.md; checkpoint/access documentation and licence scope Version: 451a1b167c06028dfbf2ff7aa2cfdea46fbcc4f4 | unreported automated source review · 2026-09-16 Audit detailsPrimary 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: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Biological inputs Coding mRNA sequences represented as codons Individual claims | CodonBERT large language model for mRNA vaccines Results (paragraph 1); Methods/Assembly of mRNA sequences for pretraining (paragraph 2) Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsPrimary 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: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Outputs mRNA embeddings and task-specific property predictions Individual claims | CodonBERT large language model for mRNA vaccines Methods/Pretraining CodonBERT (paragraph 6); Results (paragraph 2) Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsPrimary 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: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Parameters Approximately 110 million parameters; 12 layers, 12 attention heads and hidden size 768. Individual claims | CodonBERT large language model for mRNA vaccines Methods/Pretraining CodonBERT (paragraph 5); Methods/Model architecture (paragraph 3) Version: journal full text in PMC | source checked automated source review · 2026-09-16 Audit detailsPrimary 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: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
| Known versions / configuration CodonBERT is the comparison-table label; that label does not specify an immutable weight revision. Individual claims | CodonBERT large language model for mRNA vaccines 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 | unreported automated source review · 2026-09-16 Audit detailsPrimary 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: Source artifact SHA-256: Hash scope: Hash scope not separately documented; inspect source record |
Sources and history
Release 2026-09-17-d277315f7d76 · Record review: needs review
2 source records and release history
- CodonBERT large language model for mRNA vaccines · Original source · journal full text in PMC
- Sanofi-Public/CodonBert README.md · Original source · 451a1b167c06028dfbf2ff7aa2cfdea46fbcc4f4
Technical metadata and extraction receipts
Stable ID: reported-model-cd246741c378db
- areas
- rna-transcriptomes
- entity level
- method
- version
- not stated in table
- reported name
- CodonBERT
- 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: codonbert-vaccines-2024; source locator: Results/Pretrained representation model (paragraph 1); Methods/Pretraining CodonBERT (paragraph 6) | Results (paragraph 1); Methods/Model architecture (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.