ProtTrans is providing state of the art pretrained language models for proteins. ProtTrans was trained on thousands of GPUs from Summit and hundreds of Google TPUs using Transformers Models.
I recently checked the Prediction/ProtBert-BFD-Predict-SS3.ipynb and I am not sure about the meaning of the predictions of the model Rostlab/prot_bert_bfd_ss3
For example: {'entity': 'C', 'index': 1, 'score': 0.9472618103027344, 'word': 'M'}
I guess an entity of E means Sheet, H means Helix, and C means Others. Am I correct?
Thanks for an amazing repo
I recently checked the
Prediction/ProtBert-BFD-Predict-SS3.ipynb
and I am not sure about the meaning of the predictions of the modelRostlab/prot_bert_bfd_ss3
For example:{'entity': 'C', 'index': 1, 'score': 0.9472618103027344, 'word': 'M'}
I guess an entity of E means Sheet, H means Helix, and C means Others. Am I correct?
Could you explain this? Thank you so much.