Commit History
-
Update README.md
1294c07
-
Update README.md
1e1c462 -
Update README.md
bd6f161
-
Upload tokenizer
4e990ac -
Upload BertForSequenceClassification
ef30d5e
-
Upload tokenizer
bc92582 -
Upload BertForSequenceClassification
e50b6df -
Update README.md
ecf60fd -
Create README.md
__Purpose__: classifies protein sequence into Thermophilic (> 60C) or Mesophilic (<40C) by host organism growth temperature. __Training__: ProteinBERT (Rostlab/prot_bert) was fine tuned on a class balanced version of learn2therm (see [here]()), about 250k protein amino acid sequences. Training parameters below: TODO See the [training repository](https://github.com/BeckResearchLab/learn2thermML) for code. __Usage__: Prepare sequences identically to using the original pretrained model: ``` from transformers import BertModelForSequenceClassification, BertTokenizer import torch import re tokenizer = BertTokenizer.from_pretrained("evankomp/learn2therm", do_lower_case=False ) model = BertModelForSequenceClassification.from_pretrained("evankomp/learn2therm") sequence_Example = "A E T C Z A O" sequence_Example = re.sub(r"[UZOB]", "X", sequence_Example) encoded_input = tokenizer(sequence_Example, return_tensors='pt') output = torch.argmax(model(**encoded_input), dim=1) ``` 1 indicates the…2a53964
-
Upload tokenizer
407f706 -
Upload BertForSequenceClassification
5c65faf -
reset remote
Evan Komp42e5a73 -
Upload tokenizer
e10138a -
Training in progress, step 2
1abefbb -
ignore tensorboard callback outputs
Evan Komp21cda64 -
Training in progress, step 2
e84271a -
Training in progress, step 2
66aebf0 -
Upload tokenizer
5fdaff3 -
update model card README.md
46d6a31 -
End of training
d12a4dc -
Upload tokenizer
7b03b96 -
update model card README.md
7590b67 -
End of training
7848aca
-
initial commit
293dc27