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

DestVI changed l1 loss. Expected proportions #1591

Draft
wants to merge 17 commits into
base: main
Choose a base branch
from

Conversation

canergen
Copy link
Contributor

@canergen canergen commented Jul 3, 2022

Uses proportions computed in other deconvolution method to infer cell activation state of those cells. Application activation for e.g. Cell2Location results. L1 loss changed. Still in discussion.
Optional obsm field.

@codecov
Copy link

codecov bot commented Jul 4, 2022

Codecov Report

Attention: 23 lines in your changes are missing coverage. Please review.

Comparison is base (638745a) 89.18% compared to head (8aab83f) 88.94%.
Report is 1 commits behind head on main.

Files Patch % Lines
scvi/module/_mrdeconv.py 63.26% 18 Missing ⚠️
scvi/model/_destvi.py 81.81% 4 Missing ⚠️
scvi/data/fields/_arraylike_field.py 80.00% 1 Missing ⚠️
Additional details and impacted files
@@            Coverage Diff             @@
##             main    #1591      +/-   ##
==========================================
- Coverage   89.18%   88.94%   -0.25%     
==========================================
  Files         152      152              
  Lines       12482    12536      +54     
==========================================
+ Hits        11132    11150      +18     
- Misses       1350     1386      +36     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

Copy link
Contributor

@justjhong justjhong left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Optional Obsm field implementation looks good to me

@adamgayoso
Copy link
Member

@cane11 any reason to keep this open?

@canergen
Copy link
Contributor Author

canergen commented Dec 8, 2023

@martinkim0 It's the version of destVI we are using for Curio data (other sparsity regularization). Can you have a pass?

@@ -78,7 +78,7 @@ def __init__(
n_latent: int,
n_layers: int,
dropout_decoder: float,
l1_reg: float,
celltype_reg: dict,
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I feel like this argument would be clearer if we separate it out into two arguments: celltype_regularization: Literal["l1", "entropy"] | None = None and celltype_regularization_weight: float | None = None

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

Successfully merging this pull request may close these issues.

None yet

5 participants