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

What is input (Tensor) – input node representations for GearNet #57

Open
Heisenburger2020 opened this issue Dec 7, 2023 · 1 comment

Comments

@Heisenburger2020
Copy link

Dear Sir/Madam,

Thank you for your fantastic paper GearNet.

I wish to finetune Gearnet (distance prediction) for some other downstream tasks.

Now I have all atom positions and residue type and atom type. I used the same operation as fold3d to get protein. However, I do not know how can I get input (Tensor) – input node representations. I could not understand how those APIs passed this input into GearNet.

Yours Sincerely,
Jiale Zhao

@Oxer11
Copy link
Collaborator

Oxer11 commented Dec 7, 2023

Hi, thanks for the good words!

To use GearNet on your customized dataste, you can follow this tutorial, which describes how to use TorchDrug to construct data.Protein object and pass it into GearNet. Also, you can see this tutorial to learn about how to use pre-trained checkpoints.

Feel free to ask me if there are any other questions.

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