Views
No views yet
1from transformers import AlbertForMaskedLM, AlbertTokenizer, pipeline
2
3>>>> tokenizer = AlbertTokenizer.from_pretrained("virtual-human-chc/prot_albert", do_lower_case=False )
4>>>> model = AlbertForMaskedLM.from_pretrained("virtual-human-chc/prot_albert")
5>>>> unmasker = pipeline('fill-mask', model=model, tokenizer=tokenizer)
6>>>> unmasker('D L I P T S S K L V V [MASK] D T S L Q V K K A F F A L V T')
7
8{'score': 0.10074187070131302, 'token': 13, 'token_str': 'L', 'sequence': 'D L I P T S S K L V V L D T S L Q V K K A F F A L V T'},
9{'score': 0.08413360267877579, 'token': 14, 'token_str': 'S', 'sequence': 'D L I P T S S K L V V S D T S L Q V K K A F F A L V T'},
10{'score': 0.07617155462503433, 'token': 18, 'token_str': 'V', 'sequence': 'D L I P T S S K L V V V D T S L Q V K K A F F A L V T'},
11{'score': 0.06521160155534744, 'token': 19, 'token_str': 'T', 'sequence': 'D L I P T S S K L V V T D T S L Q V K K A F F A L V T'},
12{'score': 0.06321343779563904, 'token': 15, 'token_str': 'A', 'sequence': 'D L I P T S S K L V V A D T S L Q V K K A F F A L V T'}]1from transformers import AutoModel, AlbertTokenizer, pipeline
2import re
3
4tokenizer = AlbertTokenizer.from_pretrained("virtual-human-chc/prot_albert", do_lower_case=False)
5
6model = AutoModel.from_pretrained("virtual-human-chc/prot_albert")
7
8fe = pipeline('feature-extraction', model=model, tokenizer=tokenizer, device=0)
9
10sequences_Example = ["A E T C Z A O", "S K T Z P"]
11
12sequences_Example = [re.sub(r"[UZOB]", "X", sequence) for sequence in sequences_Example]
13
14embedding = fe(sequences_Example)
15
16print(embedding)