search

bzho3923 / ProtLGN

22 stars 7 forks source link

Request for Test Data or Data Preparation Method for Zero-shot Prediction of Mutant Sequences #1

Open hz7-github opened 1 month ago

hz7-github commented 1 month ago

Hello, Thank you for sharing this excellent project. I am currently trying to run the project, but I am having some difficulties regarding the test data and data preparation methods for zero-shot prediction of mutant sequences. Could you please provide the test data or guide me on how to prepare the required data? Specifically, I would like to know:

  1. Is there any existing test data for mutant sequences that I can use? If so, where can I find it?
  2. If there is no existing test data, could you provide a guide or script for data preparation for zero-shot prediction? Thank you very much for your help!
AaranWang commented 1 month ago

same question.

chengnuo1 commented 1 month ago

Hello, Thank you for sharing this excellent project. I am currently trying to run the project, but I am having some difficulties regarding the test data and data preparation methods for zero-shot prediction of mutant sequences. Could you please provide the test data or guide me on how to prepare the required data? Specifically, I would like to know:

  1. Is there any existing test data for mutant sequences that I can use? If so, where can I find it?
  2. If there is no existing test data, could you provide a guide or script for data preparation for zero-shot prediction? Thank you very much for your help! Have you solved the above problem?
hz7-github commented 1 month ago

It hasn't been resolved yet.

AaranWang commented 1 month ago

It hasn't been resolved yet.

Disappearing authors

tyang816 commented 1 month ago

Hi, guys

Sorry for the late reply, we have updated the model weight, example dataset, and zero-shot scripts for ProtLGN.

  1. model weight: ckpt/ProtLGN.pt
  2. example dataset: data/example
  3. zero-shot script: script/mutant_predict.sh

And we recently developed two more advanced protein engineering tools named ProtSSN and ProSST for zero-shot prediction. We recommend you try the new models!

Best wishes, Yang Tan