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

About generating protein sequences embeddings with the model #87

Open
christopher-irw opened this issue Dec 4, 2024 · 1 comment
Open

Comments

@christopher-irw
Copy link

Hi there,

Thank you for your excellent work on this project. I’m wondering if your model can be used specifically for generating embeddings of protein sequences. For instance, given a protein sequence as input, is there a function available that outputs its embedding, which can then be used for downstream tasks?

If this is possible, could you provide an example script or point to best practices for generating these embeddings effectively?

Thank you!

@gcorso
Copy link
Collaborator

gcorso commented Dec 11, 2024

Hi @christopher-irw, not without doing a bit of modification to the code. However, you should be able to relatively easily use the single and pair representation coming out of the Pairformer (these are also the features fed to the confidence model): you can do this outputting s and z here

dict_out = {"pdistogram": pdistogram}

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