rewire.it
model · family

RNA-FM

RNA-FM is a pretrained RNA sequence encoder for structural and functional representation learning.

0 evaluations · 0 metric rows

At a glance

Explanatory profile: source reviewed · Automated source review, 2026-09-16. This does not change the review status of its results.

Inputs, outputs and configuration
PropertyDescription and evidence
RNA-FM trainingRepository reports more than 23 million non-coding RNA sequencesml4bio/RNA-FM official source · README.md: introduction and Foundation Models and Extended Ecosystem
Model typeNot extracted or verified for this record.
Known versionsNot extracted or verified for this record.
Context limitsNot extracted or verified for this record.
AccessNot extracted or verified for this record.
Code licenceNot extracted or verified for this record.
Weights licenceNot extracted or verified for this record.

Versions and evaluated configurations

How it works

Conceptual procedure

Schematic of the documented input, computation and output; not an executable configuration.

Conceptual procedureRNA sequence. Then: RNA tokens. Then: Pretrained transformer. Then: Contextual embeddings. Then: Task-specific predictorRNA sequenceRNA tokensPretrained transformerContextual embeddingsTask-specific predictor
Read the diagram as text
  1. RNA sequence
  2. RNA tokens
  3. Pretrained transformer
  4. Contextual embeddings
  5. Task-specific predictor
ml4bio/RNA-FM official source · README.md: introduction and Foundation Models and Extended Ecosystem

A BERT-style transformer encodes RNA tokens into contextual embeddings after self-supervised sequence training. Structural or functional predictions require the corresponding downstream model; RNA-FM alone should not be labelled as a complete 3D folding pipeline.

ml4bio/RNA-FM official source · README.md: introduction and Foundation Models and Extended Ecosystem

Benchmarks and results

Release 2026-09-16-d74d282221a9 · 0 evaluations · 0 metric rows. Different protocols are not a single leaderboard.

No evaluations linked in this release.

Strengths and limitations

Strengths supported by sources

  • Reusable representations do not require experimental labels during pretraining.ml4bio/RNA-FM official source · README.md: introduction and Foundation Models and Extended Ecosystem

Limitations and conditions

  • The ncRNA encoder and the coding-sequence mRNA-FM extension have different training modalities and should not share checkpoint identities.ml4bio/RNA-FM official source · README.md: introduction and Foundation Models and Extended Ecosystem
Profile review details

Primary project documentation or paper inspected for the explanatory claims and cited locations. Reviewed coverage concerns this narrative, not complete metadata, independent reproduction or a performance ranking.

Stable record: discovery-model-rna-fm

Applicable tests and references

Applicability is distinct from a completed evaluation.

  • BEACON · Proposed association

Sources and history

Release 2026-09-16-d74d282221a9 · Record review: discovered

Download this release
Technical metadata and extraction receipts

Stable ID: discovery-model-rna-fm

areas
rna
access
official_source_linked
benchmark applicability
candidate; not evidence of a reported evaluation
candidate benchmark ids
discovery-benchmark-beacon
entity level
family
missing metadata
checkpoint: unextracted; code licence: unextracted; parameters: unextracted; training cutoff: unextracted; training data: unextracted; version: unextracted; weights licence: unextracted
reported name
RNA-FM
version
Not reported
Related records

Suggest a correction