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

Peptide Discovery #9

Open
shahik opened this issue Mar 16, 2021 · 2 comments
Open

Peptide Discovery #9

shahik opened this issue Mar 16, 2021 · 2 comments

Comments

@shahik
Copy link

shahik commented Mar 16, 2021

Hi,
thanks for the code. How can I generate only peptides (smaller proteins) using transfer learning, can I finetune (valid_data) on peptides or is there some tweak etc? thanks!

@JoshuaMeyers
Copy link
Collaborator

Hey @shahik, sounds like an interesting project. GuacaMol is a benchmark suite for comparing small molecule generators, while the baseline methods we provide can be tweaked in the direction of peptides. This is out of scope for our repository, however for a simple specialised approach see: https://joss.theoj.org/papers/10.21105/joss.01992.

@shahik shahik closed this as completed Mar 16, 2021
@shahik shahik reopened this May 18, 2021
@shahik
Copy link
Author

shahik commented May 18, 2021

Hi,
I have used this repo and it produces smaller proteins. Limitations include the validity of proteins, it's very poor as I was able to convert only 2 valid pdb structure from generated smiles. 2nd it's not suitable for peptide bonds discovery. 3rd Transformers have taken over RNNs!

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