AIDO.Protein-16B-v1

Model Description

We pretrained our model in three stages. This model represents the final stage, where we continued training our AIDO.Protein-16B using an additional 100 billion amino acids from Uniref90.

How to Use

Build any downstream models from this backbone

Embedding

from genbio_finetune.tasks import Embed
model = Embed.from_config({"model.backbone": "proteinfm_v1"}).eval()
collated_batch = model.collate({"sequences": ["ACGT", "AGCT"]})
embedding = model(collated_batch)
print(embedding.shape)
print(embedding)

Sequence Level Classification

import torch
from genbio_finetune.tasks import SequenceClassification
model = SequenceClassification.from_config({"model.backbone": "proteinfm_v1", "model.n_classes": 2}).eval()
collated_batch = model.collate({"sequences": ["ACGT", "AGCT"]})
logits = model(collated_batch)
print(logits)
print(torch.argmax(logits, dim=-1))

Token Level Classification

import torch
from genbio_finetune.tasks import TokenClassification
model = TokenClassification.from_config({"model.backbone": "proteinfm_v1", "model.n_classes": 3}).eval()
collated_batch = model.collate({"sequences": ["ACGT", "AGCT"]})
logits = model(collated_batch)
print(logits)
print(torch.argmax(logits, dim=-1))

Regression

from genbio_finetune.tasks import SequenceRegression
model = SequenceRegression.from_config({"model.backbone": "proteinfm_v1"}).eval()
collated_batch = model.collate({"sequences": ["ACGT", "AGCT"]})
logits = model(collated_batch)
print(logits)

Protein-Protein Interaction

Or use our one-liner CLI to finetune or evaluate any of the above!

gbft fit --model SequenceClassification --model.backbone proteinfm_v1 --data SequenceClassification --data.path <hf_or_local_path_to_your_dataset>
gbft test --model SequenceClassification --model.backbone proteinfm_v1 --data SequenceClassification --data.path <hf_or_local_path_to_your_dataset>

For more information, visit: Model Generator