c2v.tl.project_clone2vec_Poi

c2v.tl.project_clone2vec_Poi(clones_query, clones_ref, obsm_key_query='ref_gex_adjacency', uns_key_query='clone2vec_Poi_project', uns_key_ref='clone2vec_Poi', obsm_key='clone2vec_Poi', mask_key=None, max_iter=500, tol=0.0001, device=None, progress_bar=True, random_state=42, init='svd', **kwargs)

Fitting of new clones to the reference clone2vec Poisson embeddings using kNN between query and reference datasets. The function is using output embedding from the reference clone2vec model and optimizes only input embedding matrix, therefore has much faster convergence than training the whole model.

Parameters:

clones_query AnnData

The query clone-level AnnData object, typically from create_clone_adata.

clones_ref AnnData

The reference clone-level AnnData object, typically from create_clone_adata.

obsm_key_query str, optional

Key in clones_query.obsm for the graph to use, by default “ref_gex_adjacency”.

uns_key_query str, optional

Key in clones_query.uns to store the model parameters, by default “clone2vec”.

uns_key_ref str, optional

Key in clones_ref.uns to store the model parameters, by default “clone2vec”.

obsm_key str, optional

Key in clones_query.obsm to store the embeddings, by default “clone2vec”.

max_iter int, optional

Maximum number of iterations, by default 500.

tol float, optional

Tolerance for convergence, by default 1e-4.

device str | None, optional

Device to use for optimization, by default None.

progress_bar bool, optional

Whether to show a progress bar, by default True.

random_state None | int, optional

Random state for reproducibility, by default 42.

init str, optional

Initialization method for the model, by default “svd”.

**kwargs

Additional keyword arguments for the model.

mask_key str | None