RNA Models
RNA foundation models capture the sequence, structural, and functional diversity of the transcriptome, spanning mRNA splicing prediction, non-coding RNA classification, and RNA secondary structure prediction. Unlike DNA, RNA folds into complex three-dimensional structures that directly determine its function, making structure-aware modeling essential for understanding ribozymes, regulatory elements, and RNA-protein interactions. These models are enabling breakthroughs in RNA therapeutic design, including optimized mRNA vaccines and small interfering RNAs.
20 models in this category
Notable Models
Top-rated rna models from our evaluations
CodonFM
NVIDIA / Arc Institute
A family of codon-resolution language models trained on 130 million coding sequences from 20,000 species, revealing context-dependent codon grammar governing translation and mRNA stability.
5' UTR-LM
Princeton University
A transformer language model pretrained on 5' UTR sequences across five species to predict mRNA translation efficiency, ribosome loading, and expression levels.
AIDO.RNA
genbio.ai
A 1.6-billion-parameter RNA foundation model pretrained on 42 million non-coding RNA sequences, achieving state-of-the-art performance across 24 of 26 RNA understanding benchmarks.
ERNIE-RNA
Tsinghua University
A structure-enhanced RNA language model that incorporates base-pairing constraints into self-attention, achieving state-of-the-art RNA structure and function prediction.
GenerRNA
Preferred Networks
Transformer-based generative language model for de novo RNA sequence design, pre-trained on 16 million sequences to generate novel, structurally stable RNAs.
Orthrus
Bowang Lab
Mamba-based mature RNA foundation model using contrastive learning on splice isoforms and 400+ mammalian species orthologs for mRNA property prediction.