search

tttianhao / CLEAN

CLEAN: a contrastive learning model for high-quality functional prediction of proteins
MIT License
217 stars 41 forks source link

How to get embedding distance between the query protein and the CLEAN-predicted EC number #34

Closed kaden1670 closed 11 months ago

kaden1670 commented 12 months ago

Hello, I am reaching out to follow up on issue #32, which was marked as closed. I was wondering if it might be possible to revisit the follow up question in that thread or get further clarification. I greatly appreciate your time and assistance in this matter.

Thank you!

canallee commented 11 months ago

Hi, in the actual implementation, the checkpoint is loaded through checkpoint = torch.load('./data/pretrained/'+ train_data +'.pth'), can you verify that './data/pretrained/'+ train_data +'.pth') exists?

kaden1670 commented 11 months ago

These are the contents of CLEAN/app/data/pretrained : 100.pt 70.pt gmm_ensumble.pkl split100.pth split70.pth

So when passing in an input filename, there is no corresponding pth file.

canallee commented 11 months ago

You should be using train_data="split100", and not "split100.pth"