AIDO.RNA-650M-CDS

AIDO.RNA-650M-CDS is a domain adaptation model on the coding sequences. It was pre-trained on 9 million coding sequences released by Carlos et al. (2024) [1] based on our AIDO.RNA-650M model. For a more detailed description, refer to the SOTA model in this collection https://huggingface.co/genbio-ai/AIDO.RNA-1.6B

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_650m_cds --data SequenceClassificationDataModule --data.path <hf_or_local_path_to_your_dataset>
mgen test --model SequenceClassification --model.backbone aido_rna_650m_cds --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_650m_cds"}).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_650m_cds", "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_650m_cds", "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_650m_cds"}).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_650m_cds"}).eval()
transformed_batch = model.transform({"sequences": ["ACGT", "ACGT"]})
embedding = model(transformed_batch)
print(embedding.shape)
print(embedding)

Reference

1. Carlos Outeiral and Charlotte M Deane. Codon language embeddings provide strong signals for use in protein engineering. Nature Machine Intelligence, 6(2):170–179, 2024.