Protein Subcellular Localization Prediction Biot5

Protein Subcellular Localization Prediction

Predict subcellular localization for proteins from their amino acid sequences using the BioT5 model.

When to Use

• You have a protein FASTA sequence and need to know its cellular location
• You want to identify if a protein is cytoplasmic, nuclear, membrane-bound, or secreted
• You need quick localization insights without experimental data
• You're characterizing novel or unannotated protein sequences

Workflow

from open_biomed.data import Protein, Text
from open_biomed.core.pipeline import InferencePipeline

# Create protein from FASTA sequence
protein = Protein.from_fasta("YOUR_AMINO_ACID_SEQUENCE")

# Create the question for subcellular localization
question = Text.from_str(
    "Please provide information about the subcellular localization of this protein."
)

# Load the BioT5 model for protein question answering
pipeline = InferencePipeline(
    task="protein_question_answering",
    model="biot5",
    model_ckpt="./checkpoints/server/protein_question_answering_biot5.ckpt",
    device="cuda:0"
)

# Run inference to get localization prediction
outputs = pipeline.run(protein=protein, text=question)
localization = outputs[0][0].str
print(localization)