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

IMA logistic classifiers #38

Closed
bschilder opened this issue May 25, 2024 · 2 comments
Closed

IMA logistic classifiers #38

bschilder opened this issue May 25, 2024 · 2 comments

Comments

@bschilder
Copy link

Hi @Yanay1 , super excited to use this foundation model! Thanks for making the code and file so easy to use.

In the preprint you trained logistic classifiers on the IMA to predict the cell type identity in new datasets. I don't suppose you'd be able to share one of these pretrained classifiers for predicting cell type identity across all major cell types seen in the IMA? This would make one of the more common tasks of cell type annotation even easier.

@bschilder
Copy link
Author

After re-reading the preprint, it seems like the logistic classifiers were only trained on specific cell types for specific use cases. Given that I need to do prediction for all cell types, I've just gone ahead and trained my own classifier. Happy to share if this is helpful.

Still might be nice to share the code for the classifiers bit of the manuscript. But i'll leave that up to you.

@yassinho-f
Copy link

After re-reading the preprint, it seems like the logistic classifiers were only trained on specific cell types for specific use cases. Given that I need to do prediction for all cell types, I've just gone ahead and trained my own classifier. Happy to share if this is helpful.

Still might be nice to share the code for the classifiers bit of the manuscript. But i'll leave that up to you.

Hey @bschilder ,

sounds great, I am also interested in training the UCE embeddings of the IMA_sample.h5ad! Would you like to share the code?

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