UCE icon indicating copy to clipboard operation
UCE copied to clipboard

How to get gene embeddings

Open kelimeike opened this issue 1 year ago • 3 comments

Thank you very much for providing the UCE model! It has been a great help to me. I noticed that the program only provides cell embeddings for different cells in the dataset. Is there a way to also easily obtain gene embeddings corresponding to the cells?

kelimeike avatar May 01 '24 12:05 kelimeike

You could use the ESM2 embedding files directly.

You can also load the model in python and then apply the gene_embedding_layer to those protein embeddings to get the modified smaller dimensional version that is fed into the model.

Yanay1 avatar May 02 '24 20:05 Yanay1

Thank you for your reply. Additionally, the README mentions a documentation file, and where can I find it?

kelimeike avatar May 03 '24 06:05 kelimeike

Sorry for the confusion-- by that we meant the docstrings in the code / scripts themselves, such as https://github.com/snap-stanford/UCE/blob/7b31528b84e4c8e7a9717c61e3d03ff7559c61af/eval_single_anndata.py#L1

Yanay1 avatar May 03 '24 22:05 Yanay1