ProtTrans icon indicating copy to clipboard operation
ProtTrans copied to clipboard

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.

Results 25 ProtTrans issues
Sort by recently updated
recently updated
newest added

Hello! Thanks for your great work! I'm trying to do some classification tasks on protein-protein interaction. I was wondering that as Next Sentence Prediction was not used when training these...

First of all, many thanks to the authors of ProtTrans for releasing these amazing protein language models and code. Second, for those who may be interested, there is our recent...

I want to fine tune protbert model on some protein data for language modelling task say given a protein sequence "ACDRFG" if I replace D with mask token and try...

I am trying to prepare the ProtTrans embeddings for UniRef50. Do we have such pre-computed embeddings available for download? Thanks!

Hello, thanks a lot for your great work! Question is about ProtTrans/Fine-Tuning/ProtBert-BFD-FineTuning-PyTorchLightning-Localization.ipynb It took ~8 hours of computer time to rerun this jupyter notebook on 24Gb P40 node on not...

Hi everyone, I would like to know if you have the precomputed embedding for the human proteins (not for other sequences). I am just interested in the vectors for the...

Hello, First off, thanks a lot for creating this project! I'm trying to use the cls tokens generated to perform a downstream classification task. I tried fine-tuning ProtT5_XL, but there...

Hello, I needed help on how to go about generating embedding after ProtT5 has been finetuned. I have carried out finetuning of the model using the sample code 'PT5_LoRA_Finetuning_per_residue_class.ipynb' on...

I'm looking for a faster alternative to Diamond for aligning proteins to UniRef50 so I can map identifiers to de novo proteins. Can I use this tool to accomplish this...

I am generating the embedding on my protein sequences via ProtT5 by the following code. I have total 5000 protein sequences which I am providing as list. I am fixing...