File size: 541 Bytes
b712bbf |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 |
# ProtAlbert
```python
from transformers import AutoModel, AlbertTokenizer, pipeline
import re
tokenizer = AlbertTokenizer.from_pretrained("Rostlab/prot_albert", do_lower_case=False)
model = AutoModel.from_pretrained("Rostlab/prot_albert")
fe = pipeline('feature-extraction', model=model, tokenizer=tokenizer, device=0)
sequences_Example = ["A E T C Z A O", "S K T Z P"]
sequences_Example = [re.sub(r"[UZOB]", "X", sequence) for sequence in sequences_Example]
embedding = fe(sequences_Example)
print(embedding)
``` |