Skip to content

Fix issue #224 / Improve handling of unlabled cells #232

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

Open
moinfar wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Fix issue #224 / Improve handling of unlabled cells #232

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions scarches/models/scpoli/scpoli.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -235,6 +235,9 @@ def add_new_cell_type(self, latent, cell_type_name, prototypes, classes_list=Non
self.cell_type_encoder = {
k: v for k, v in zip(self.cell_types, range(len(self.cell_types)))
}
if self.unknown_ct_names is not None:
for unknown_ct in self.unknown_ct_names:
self.cell_type_encoder[unknown_ct] = -1

# Add new celltype index to hierarchy index list of prototypes
classes_list = torch.cat(
Expand Down
3 changes: 1 addition & 2 deletions scarches/models/scpoli/scpoli_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,7 +122,7 @@ def __init__(
self.unknown_ct_names_ = unknown_ct_names

if labeled_indices is None:
self.labeled_indices_ = range(len(adata))
self.labeled_indices_ = np.argwhere(adata.obs[self.cell_type_keys_].isin(self.unknown_ct_names_).to_numpy().astype(int).min(axis=1) == 0).T[0]
else:
self.labeled_indices_ = labeled_indices

Expand Down Expand Up @@ -180,7 +180,6 @@ def __init__(
if unknown_ct in self.cell_types_:
del self.cell_types_[unknown_ct]


# store model parameters
if hidden_layer_sizes is None:
self.hidden_layer_sizes_ = [int(np.ceil(np.sqrt(adata.shape[1])))]
Expand Down