You can deploy this model and start earning money today!

genbio-ai/
GB.RNA-300M-MARS

Name: GB.RNA-300M-MARS
Rating: 2.5 (185 reviews)

pytorch

rnabert

other

Views

No views yet

GB.RNA-300M

GB.RNA-300M-MARS is a 300 million parameter RNA foundation model pre-trained on 886 million RNA sequences from the MARS database.

For a more detailed description, refer to the SOTA model in this collection https://huggingface.co/genbio-ai/GB.RNA-1.6B

How to Use

Build any downstream models from this backbone with ModelGenerator

For more information, visit: Model Generator

bash

mgen fit --model SequenceClassification --model.backbone aido_rna_300m_mars --data SequenceClassificationDataModule --data.path <hf_or_local_path_to_your_dataset>
mgen test --model SequenceClassification --model.backbone aido_rna_300m_mars --data SequenceClassificationDataModule --data.path <hf_or_local_path_to_your_dataset>

Or use directly in Python

Embedding

python

from modelgenerator.tasks import Embed
model = Embed.from_config({"model.backbone": "aido_rna_300m_mars"}).eval()
transformed_batch = model.transform({"sequences": ["ACGT", "AGCT"]})
embedding = model(transformed_batch)
print(embedding.shape)
print(embedding)

Sequence-level Classification

python

import torch
from modelgenerator.tasks import SequenceClassification
model = SequenceClassification.from_config({"model.backbone": "aido_rna_300m_mars", "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

python

import torch
from modelgenerator.tasks import TokenClassification
model = TokenClassification.from_config({"model.backbone": "aido_rna_300m_mars", "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

python

from modelgenerator.tasks import SequenceRegression
model = SequenceRegression.from_config({"model.backbone": "aido_rna_300m_mars"}).eval()
transformed_batch = model.transform({"sequences": ["ACGT", "AGCT"]})
logits = model(transformed_batch)
print(logits)

Get RNA sequence embedding

python

from genbio_finetune.tasks import Embed
model = Embed.from_config({"model.backbone": "aido_rna_300m_mars"}).eval()
transformed_batch = model.transform({"sequences": ["ACGT", "ACGT"]})
embedding = model(transformed_batch)
print(embedding.shape)
print(embedding)

genbio-ai/GB.RNA-300M-MARS

GB.RNA-300M

How to Use

Build any downstream models from this backbone with ModelGenerator

Or use directly in Python

Embedding

Sequence-level Classification

Token-level Classification

Sequence-level Regression

Get RNA sequence embedding

genbio-ai/
GB.RNA-300M-MARS