GB.DNA-300M

GB.DNA-300M

For a more detailed description, refer to the SOTA model in this collection https://huggingface.co/genbio-ai/GB.DNA-7B

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_dna_300m --data SequenceClassificationDataModule --data.path <hf_or_local_path_to_your_dataset>
mgen test --model SequenceClassification --model.backbone aido_dna_300m --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_dna_300m"}).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_dna_300m", "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_dna_300m", "model.n_classes": 3}).eval()
transformed_batch = model.transform({"sequences": ["ACGT", "AGCT"]})
logits = model(transformed_batch)
print(logits)
print(torch.argmax(logits, dim=-1))

Regression

from modelgenerator.tasks import SequenceRegression
model = SequenceRegression.from_config({"model.backbone": "aido_dna_300m"}).eval()
transformed_batch = model.transform({"sequences": ["ACGT", "AGCT"]})
logits = model(transformed_batch)
print(logits)