HelloWorldLTY

Could you please try this implementation: https://github.com/HelloWorldLTY/propr_python/tree/main And share your questions or experiences with me? Thanks.

Hi, I am also intereted in the application of torch_geometric version of this model. Is it possible? Thanks a lot.

There is a following-up question for this step:  It seems that there still exists errors and warnings for this step. Moreover, for running a spatial datasetsw ith 4,000 cells...

Hi, I met same problem here even if I tried both l=120 or l=1200. I think there is lack of information for us to choose a good initial value of...

> I am not sure though but you can clone the repo to your working repo, then just import it as your other directory Thanks for your reply, but I...

Thanks a lot. I will try other versions.

Thanks for your post! I am Tianyu and I am still confused about this problem, because if I use small set data, the mnn_correct will work. For example, 

Hi, thanks for your reply. I think what I intend to access is a matrix, with genes x tfs. And the identity of this matrix represents the link strength or...

Hi, I met the same error: ``` subprocess.CalledProcessError: Command '['cmake', '--build', '.', '--config', 'TritonRelBuildWithAsserts', '-j64']' returned non-zero exit status 1. ``` Are there any efficient solutions?

Hi, I wonder if this problem was resolved or not. It seems that if I have sequence > 512 as inputs, the model will meet CUDA OOM error.