AIDO.RNA-1.6B

AIDO.RNA-1.6B is a general-purpose RNA foundation model with 1.6 billion parameters, trained on 42 million non-coding RNA sequences at single-nucleotide resolution. It achieves state-of-the-art performance on a comprehensive set of tasks, including RNA secondary structure prediction, mRNA-related tasks, RNA function prediction, and RNA inverse folding. After domain adaptation, AIDO.RNA excels in modeling protein-level tasks, highlighting its potential to leverage the central dogma for enhancing biomolecular representations. For more detailed information, please refer to our paper.

Model architectural details

AIDO.RNA is an encoder-only transformer and is pre-trained using masked language modeling (MLM) objective. The model architecture parameters are as follows:

hyperparameter	value
num-layers	32
hidden-size	2,048
ffn-hidden-size	5,440
num-attn-heads	32
vocab-size	16

Pre-training data

The pre-training data contains 42 million unique ncRNA sequences from RNAcentral version 24.0.

Downstream evaluation

How to Use

Build any downstream models from this backbone with ModelGenerator

For more information, visit: Model Generator

mgen fit --model SequenceClassification --model.backbone aido_rna_1b600m --data SequenceClassificationDataModule --data.path <hf_or_local_path_to_your_dataset>
mgen test --model SequenceClassification --model.backbone aido_rna_1b600m --data SequenceClassificationDataModule --data.path <hf_or_local_path_to_your_dataset>

Or use directly in Python

Embedding

from modelgenerator.tasks import Embed
model = Embed.from_config({"model.backbone": "aido_rna_1b600m"}).eval()
transformed_batch = model.transform({"sequences": ["ACGT", "AGCT"]})
embedding = model(transformed_batch)
print(embedding.shape)
print(embedding)

Sequence-level Classification

import torch
from modelgenerator.tasks import SequenceClassification
model = SequenceClassification.from_config({"model.backbone": "aido_rna_1b600m", "model.n_classes": 2}).eval()
transformed_batch = model.transform({"sequences": ["ACGT", "AGCT"]})
logits = model(transformed_batch)
print(logits)
print(torch.argmax(logits, dim=-1))

Token-level Classification

import torch
from modelgenerator.tasks import TokenClassification
model = TokenClassification.from_config({"model.backbone": "aido_rna_1b600m", "model.n_classes": 3}).eval()
transformed_batch = model.transform({"sequences": ["ACGT", "AGCT"]})
logits = model(transformed_batch)
print(logits)
print(torch.argmax(logits, dim=-1))

Sequence-level Regression

from modelgenerator.tasks import SequenceRegression
model = SequenceRegression.from_config({"model.backbone": "aido_rna_1b600m"}).eval()
transformed_batch = model.transform({"sequences": ["ACGT", "AGCT"]})
logits = model(transformed_batch)
print(logits)

Get RNA sequence embedding

from genbio_finetune.tasks import Embed
model = Embed.from_config({"model.backbone": "aido_rna_1b600m"}).eval()
transformed_batch = model.transform({"sequences": ["ACGT", "ACGT"]})
embedding = model(transformed_batch)
print(embedding.shape)
print(embedding)

Citation

Please cite AIDO.RNA using the following BibTeX code:

@inproceedings{zou_large-scale_2024,
    title = {A Large-Scale Foundation Model for RNA Function and Structure Prediction},
    url = {https://www.biorxiv.org/content/10.1101/2024.11.28.625345v1},
    doi = {10.1101/2024.11.28.625345},
    publisher = {bioRxiv},
    author = {Zou, Shuxian and Tao, Tianhua and Mahbub, Sazan and Ellington, Caleb N. and Algayres, Robin and Li, Dian and Zhuang, Yonghao and Wang, Hongyi and Song, Le and Xing, Eric P.},
    year = {2024},
    booktitle = {NeurIPS 2024 Workshop on AI for New Drug Modalities},
}