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.

Sign up for GitHub

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

Jump to bottom

Method Spatial-MGCN #212

Open
wants to merge 14 commits into
base: main
Choose a base branch
from
Open

Method Spatial-MGCN #212

wants to merge 14 commits into from

Conversation

kbiharie
Copy link
Contributor

  • Adds method Spatial-MGCN
  • Adds config/config_1.json with hyperparameters for DLPFC
  • Original implementation calculates ARI in every epoch and chooses epoch with highest ARI, thus using the groundtruth to select the model. By default we do not calculate the ARI. This functionality can be turned on by setting CALC_ARI to True in Spatial-mgcn.py.
  • Method was tested with the DLPFC dataset and can reproduce the ARI for slide 151507 when CALC_ARI = True.

@kbiharie kbiharie linked an issue Feb 16, 2024 that may be closed by this pull request
method_Spatial-MGCN #29
Open
@kbiharie kbiharie changed the title WIP: Method Spatial-MGCN Method Spatial-MGCN Feb 16, 2024
niklasmueboe
niklasmueboe reviewed Feb 22, 2024
View reviewed changes
method/Spatial-mgcn/Spatial-mgcn.yml Outdated
- torch_geometric==2.1.0
- torch_sparse==0.6.15
- torch_scatter==2.0.9
- git+https://github.com/cs-wangbo/Spatial-MGCN@cf4412df6db6276e0c8a3f036ff0b1661adfdb35
Copy link
Collaborator

Choose a reason for hiding this comment

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

If it can be installed via pip why is the repo cloned during the run?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

It cannot be installed via pip. I updated the yml

method/Spatial-mgcn/Spatial-mgcn.py Outdated

# Normalize data: min_cells, calculate HVG and scale
sc.pp.filter_genes(adata, min_cells=100)
sc.pp.highly_variable_genes(adata, flavor="seurat_v3", n_top_genes=config["fdim"])
Copy link
Collaborator

Choose a reason for hiding this comment

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

Is there a reason not to use existing feature selection?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

I changed it to the existing feature selection now. But I left their feature selection as comments to make it easier to compare the performance of both ways.

@kbiharie kbiharie requested a review from niklasmueboe March 13, 2024 09:43
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@niklasmueboe niklasmueboe Awaiting requested review from niklasmueboe

At least 1 approving review is required to merge this pull request.

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

method_Spatial-MGCN
3 participants
@kbiharie @niklasmueboe @Divya1205