Inquiry regarding Lung Organoid Model and RuntimeError during heoca_query.run_scpoli().

Hi developers,

Thank you for providing such valuable resources on GitHub. I'm currently working on lung organoid single-cell data analysis and have found your paper and GitHub page to be extremely helpful references.

However, I have two questions:

Firstly, I noticed that the link to download the lung organoid model seems to be the same as the intestine organoid model (hioca), and I couldn't locate the model for lung organoids on your Zenodo page (8186773). I understand that your paper hasn't been published yet, but if it's possible for you to share the lung organoid model with me, it would be a great opportunity for me.

Secondly, I encountered a RuntimeError during heoca_query.run_scpoli(). Here's the detailed error message:

Leiden Clustering successful. Found 33 clusters.
 |████████████████████| 100.0%  - val_loss: 406.4587848166 - val_cvae_loss: 406.4587848166 - val_prototype_loss: 0.0000000000 - val_unlabeled_loss: 0.0000000000
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/data/User/juhyunk/miniforge3/envs/sc2heoca/lib/python3.9/site-packages/sc2heoca/sc2heoca.py", line 114, in run_scpoli
    results_dict = scpoli_query.classify(adata0.X, adata0.obs["sample_id"].values)
  File "/data/User/juhyunk/miniforge3/envs/sc2heoca/lib/python3.9/site-packages/scarches/models/scpoli/scpoli_model.py", line 389, in classify
    x[batch, :].to(device),
RuntimeError: indices should be either on CPU or on the same device as the indexed tensor (CPU)

Could you please provide some setting guidance on how to fix this issue?

Thank you very much!

devsystemslab / sc2heoca

Inquiry regarding Lung Organoid Model and RuntimeError during heoca_query.run_scpoli(). #1