Model

mRNA-FM

mRNA-FM encodes coding RNA with codon-level tokens to produce representations for downstream analysis.

Sources (2)

ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Foundation Models table and mRNA-FM quick-start example

Results are available for configurations using this model. Their fitted heads, extra inputs and evaluation settings are kept separate below.

1 evaluated configuration using this model

How it worksmRNA-FM workflow

Conceptual summary of the documented data flow; optional inputs and configured downstream stages must be reported for a reproducible evaluation.

Sources (2)

ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Foundation Models table and mRNA-FM quick-start example

Overview

Model type

Codon-token RNA transformer encoder

Sources (2)

ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Foundation Models table and mRNA-FM quick-start example

Inputs

Coding RNA in the correct reading frame, with sequence length divisible by three.

Sources (2)

ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Foundation Models table and mRNA-FM quick-start example

Outputs

Contextual token embeddings for a specified downstream RNA task.

Sources (2)

ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Foundation Models table and mRNA-FM quick-start example

Access

Official project documentation and implementation: https://github.com/ml4bio/RNA-FM

Sources (2)

ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Foundation Models table and mRNA-FM quick-start example

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

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.

mrna-fm Pipeline · 8 metric rows

Use this model

How it works, versions and access

Related profile: RNA-FM. This page retains the exact record and its evaluation context.

How it works

mRNA-FM encodes coding RNA with codon-level tokens to produce representations for downstream analysis. 12-layer transformer encoder with hidden width 1,280 and codon-level input tokens. The documented inputs are coding RNA in the correct reading frame, with sequence length divisible by three. The output consists of contextual token embeddings for a specified downstream RNA task.

Sources (2)

ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Foundation Models table and mRNA-FM quick-start example

Versions and reproducibility

mrna_fm_t12; distinct from base-tokenized rna_fm_t12. The applicable input limits require configuration-specific checking.

Sources (2)

ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Foundation Models table and mRNA-FM quick-start example

Strengths, limitations and unresolved questions

Strengths and limitations

Strengths and considerations

The repository exposes embedding extraction and examples for downstream RNA analyses.
Sources (2)
ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Foundation Models table and mRNA-FM quick-start example

Limitations and conditions

Base-level RNA-FM and codon-level mRNA-FM are not interchangeable. The task head and tokenization must be specified in each evaluation.
Sources (2)
ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Foundation Models table and mRNA-FM quick-start example

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. Follow-up retrieved the complete original RNA-FM PDF and inspected the full pinned Geneformer repository inventory; unavailable labels were updated only where new evidence resolved the earlier retrieval gap.

Stable record: catalog-model-mrna-fm

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	Codon-token RNA transformer encoder Sources (2) ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Foundation Models table and mRNA-FM quick-start example
Architecture	12-layer transformer encoder with hidden width 1,280 and codon-level input tokens. Sources (2) ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Foundation Models table and mRNA-FM quick-start example
Inputs	Coding RNA in the correct reading frame, with sequence length divisible by three. Sources (2) ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Foundation Models table and mRNA-FM quick-start example
Outputs	Contextual token embeddings for a specified downstream RNA task. Sources (2) ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Foundation Models table and mRNA-FM quick-start example
Parameters	239M, as printed in the official Foundation Models table. Sources (2) ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Foundation Models table and mRNA-FM quick-start example
Known versions	mrna_fm_t12; distinct from base-tokenized rna_fm_t12. Sources (2) ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Foundation Models table and mRNA-FM quick-start example
Training data	45M messenger RNA sequences, as printed in the official Foundation Models table. Sources (2) ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Foundation Models table and mRNA-FM quick-start example
Training cutoff	The official model table reports 45M coding RNAs but does not identify a latest-data date for that separate mRNA-FM corpus. · Not reported in inspected sources Sources (2) ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Foundation Models table and mRNA-FM quick-start example
Context limits	The inspected mRNA-FM usage example and loader do not specify a validated maximum codon-sequence length. The retrieved original RNA-FM paper describes the nucleotide-based non-coding RNA model; its limit cannot establish the separate mRNA-FM checkpoint limit. · Not reported in inspected sources Sources (3) ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py; RNA-FM original methods, arXiv v5 · Official README: Foundation Models and mRNA-FM quick start; loader; original RNA-FM paper Methods, pp.22–23
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 (3) ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py; ml4bio/RNA-FM: LICENSE · README.md: Foundation Models table and mRNA-FM quick-start example; LICENSE: licence text
Access	Official project documentation and implementation: https://github.com/ml4bio/RNA-FM Sources (2) ml4bio/RNA-FM: README.md; ml4bio/RNA-FM: fm/pretrained.py · README.md: Foundation Models table and mRNA-FM quick-start example
Code licence	MIT Sources ml4bio/RNA-FM: LICENSE · LICENSE: 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.

42 evidence rows matching the loaded filters

Claims, original sources and review scope · Release 2026-09-23-2b89723c6dd9
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	ml4bio/RNA-FM: fm/pretrained.py Original source ↗ README.md: Foundation Models table and mRNA-FM quick-start example Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 348951516e0963d22bbb33b3c9fc18c89081d38e Retrieved: 2026-09-16T19:46:19.769679+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. Follow-up retrieved the complete original RNA-FM PDF and inspected the full pinned Geneformer repository inventory; unavailable labels were updated only where new evidence resolved the earlier retrieval gap. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `ab7271f8dbb876dbc5e2010e2d88b086088aada096f04149436d315a4f256aac` 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	ml4bio/RNA-FM: README.md Original source ↗ README.md: Foundation Models table and mRNA-FM quick-start example Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 348951516e0963d22bbb33b3c9fc18c89081d38e Retrieved: 2026-09-16T19:46:19.769679+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. Follow-up retrieved the complete original RNA-FM PDF and inspected the full pinned Geneformer repository inventory; unavailable labels were updated only where new evidence resolved the earlier retrieval gap. Field: `attributes.profile.diagram.caption` Source artifact SHA-256: `f9f1c1d62adc471661ca98b30c0250e9f3ce0cff7433830f149f5f48ea41c3da` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram steps Coding RNA Codon tokenizer 12-layer transformer encoder Contextual codon representations Individual claims	ml4bio/RNA-FM: fm/pretrained.py Original source ↗ README.md: Foundation Models table and mRNA-FM quick-start example Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 348951516e0963d22bbb33b3c9fc18c89081d38e Retrieved: 2026-09-16T19:46:19.769679+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. Follow-up retrieved the complete original RNA-FM PDF and inspected the full pinned Geneformer repository inventory; unavailable labels were updated only where new evidence resolved the earlier retrieval gap. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `ab7271f8dbb876dbc5e2010e2d88b086088aada096f04149436d315a4f256aac` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram steps Coding RNA Codon tokenizer 12-layer transformer encoder Contextual codon representations Individual claims	ml4bio/RNA-FM: README.md Original source ↗ README.md: Foundation Models table and mRNA-FM quick-start example Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 348951516e0963d22bbb33b3c9fc18c89081d38e Retrieved: 2026-09-16T19:46:19.769679+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. Follow-up retrieved the complete original RNA-FM PDF and inspected the full pinned Geneformer repository inventory; unavailable labels were updated only where new evidence resolved the earlier retrieval gap. Field: `attributes.profile.diagram.steps` Source artifact SHA-256: `f9f1c1d62adc471661ca98b30c0250e9f3ce0cff7433830f149f5f48ea41c3da` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram title mRNA-FM workflow Individual claims	ml4bio/RNA-FM: fm/pretrained.py Original source ↗ README.md: Foundation Models table and mRNA-FM quick-start example Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 348951516e0963d22bbb33b3c9fc18c89081d38e Retrieved: 2026-09-16T19:46:19.769679+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. Follow-up retrieved the complete original RNA-FM PDF and inspected the full pinned Geneformer repository inventory; unavailable labels were updated only where new evidence resolved the earlier retrieval gap. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `ab7271f8dbb876dbc5e2010e2d88b086088aada096f04149436d315a4f256aac` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Diagram title mRNA-FM workflow Individual claims	ml4bio/RNA-FM: README.md Original source ↗ README.md: Foundation Models table and mRNA-FM quick-start example Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 348951516e0963d22bbb33b3c9fc18c89081d38e Retrieved: 2026-09-16T19:46:19.769679+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. Follow-up retrieved the complete original RNA-FM PDF and inspected the full pinned Geneformer repository inventory; unavailable labels were updated only where new evidence resolved the earlier retrieval gap. Field: `attributes.profile.diagram.title` Source artifact SHA-256: `f9f1c1d62adc471661ca98b30c0250e9f3ce0cff7433830f149f5f48ea41c3da` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Model type Codon-token RNA transformer encoder Individual claims	ml4bio/RNA-FM: fm/pretrained.py Original source ↗ README.md: Foundation Models table and mRNA-FM quick-start example Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 348951516e0963d22bbb33b3c9fc18c89081d38e Retrieved: 2026-09-16T19:46:19.769679+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. Follow-up retrieved the complete original RNA-FM PDF and inspected the full pinned Geneformer repository inventory; unavailable labels were updated only where new evidence resolved the earlier retrieval gap. Field: `attributes.profile.facts.0.value` Source artifact SHA-256: `ab7271f8dbb876dbc5e2010e2d88b086088aada096f04149436d315a4f256aac` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Model type Codon-token RNA transformer encoder Individual claims	ml4bio/RNA-FM: README.md Original source ↗ README.md: Foundation Models table and mRNA-FM quick-start example Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 348951516e0963d22bbb33b3c9fc18c89081d38e Retrieved: 2026-09-16T19:46:19.769679+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. Follow-up retrieved the complete original RNA-FM PDF and inspected the full pinned Geneformer repository inventory; unavailable labels were updated only where new evidence resolved the earlier retrieval gap. Field: `attributes.profile.facts.0.value` Source artifact SHA-256: `f9f1c1d62adc471661ca98b30c0250e9f3ce0cff7433830f149f5f48ea41c3da` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Architecture 12-layer transformer encoder with hidden width 1,280 and codon-level input tokens. Individual claims	ml4bio/RNA-FM: fm/pretrained.py Original source ↗ README.md: Foundation Models table and mRNA-FM quick-start example Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 348951516e0963d22bbb33b3c9fc18c89081d38e Retrieved: 2026-09-16T19:46:19.769679+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. Follow-up retrieved the complete original RNA-FM PDF and inspected the full pinned Geneformer repository inventory; unavailable labels were updated only where new evidence resolved the earlier retrieval gap. Field: `attributes.profile.facts.1.value` Source artifact SHA-256: `ab7271f8dbb876dbc5e2010e2d88b086088aada096f04149436d315a4f256aac` Hash scope: SHA-256 of retrieved original artifact bytes Format: original_artifact Inspected artifact
Architecture 12-layer transformer encoder with hidden width 1,280 and codon-level input tokens. Individual claims	ml4bio/RNA-FM: README.md Original source ↗ README.md: Foundation Models table and mRNA-FM quick-start example Shared locator for this statement’s cited sources; not a separate locator for each citation. Version: 348951516e0963d22bbb33b3c9fc18c89081d38e Retrieved: 2026-09-16T19:46:19.769679+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. Follow-up retrieved the complete original RNA-FM PDF and inspected the full pinned Geneformer repository inventory; unavailable labels were updated only where new evidence resolved the earlier retrieval gap. Field: `attributes.profile.facts.1.value` Source artifact SHA-256: `f9f1c1d62adc471661ca98b30c0250e9f3ce0cff7433830f149f5f48ea41c3da` 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 2026-09-23-2b89723c6dd9 · Record review: discovered

5 source records and release history

mRNA-FM official resource · Original source · Not reported
ml4bio/RNA-FM: README.md · Original source · 348951516e0963d22bbb33b3c9fc18c89081d38e
ml4bio/RNA-FM: fm/pretrained.py · Original source · 348951516e0963d22bbb33b3c9fc18c89081d38e
RNA-FM original methods, arXiv v5 · Original source · 2204.00300v5
ml4bio/RNA-FM: LICENSE · Original source · 348951516e0963d22bbb33b3c9fc18c89081d38e

Download this release

Technical metadata and extraction receipts

Stable ID: catalog-model-mrna-fm

areas: rna-transcriptomes
method types: foundation model
entity level: family
version: codon-tokenised
reported name: mRNA-FM
access: Public checkpoint trained on coding sequences (CDS); input must be codon aligned. UTR-only sequences are outside its training modality.
method type: foundation model
historical missing metadata: checkpoint revision: not_yet_extracted; training data: not_yet_extracted; licence: not_yet_extracted
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-fd8e332abdf04a75195b; evidence-official-e17e3864c464d981afc7; source locator: README.md: Foundation Models table and mRNA-FM quick-start example; ambiguities: None recorded

Related records

variant of: RNA-FM
uses model: mrna-fm
subject: mRNA-FM: variant of RNA-FM

Suggest a correction