Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

How to run prediction of protein function #6

Open
CryoSky opened this issue Aug 13, 2023 · 2 comments
Open

How to run prediction of protein function #6

CryoSky opened this issue Aug 13, 2023 · 2 comments

Comments

@CryoSky
Copy link

CryoSky commented Aug 13, 2023

Hello,

Thank you again for your help in my previous issue. I can finally run the ProtST task on my cluster using one GPU. However, I need clarification about the command that you provided.

I want to predict a given protein sequence's function (GO terms). After running the following command, what do you think I should do to invoke the trained model and run the prediction? I appreciate your help in advance.

python4proc /script/run_downstream.py --config ./config/downstream_task/PretrainESM2/annotation_tune.yaml --checkpoint /work/cms16/sj52/scratch/esm-model-weights/esm2_t33_650M_UR50D.pt --dataset GeneOntology --branch BP

@KatarinaYuan
Copy link
Collaborator

Hi, the running command should be correct. And to use the ProtST-enhanced model, we just need to modify the augment in "--checkpoint" to the storage path of that ProtST-enhanced model.

As I commented in the previous issue (#5 (comment)). I'm now downloading ProtST-ESM2 checkpoint onto my current working cluster to test if there is any problem. I would come back to you once it's done.

@KatarinaYuan
Copy link
Collaborator

Please check #5 (comment)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants