c2v.tl.clone2vec#
- c2v.tl.clone2vec(clones, z_dim=10, obsp_key='gex_adjacency', mask_key=None, max_iter=500, learning_rate=0.001, device=None, progress_bar=True, obsm_key='clone2vec', uns_key='clone2vec', random_state=4, init='svd', init_obsm=None, batch_size=128, early_stopping_patience=5, early_stopping_min_delta=0.0001)#
Learn a clonal embedding using Skip-Gram and store the embeddings.
- Parameters:
- clones AnnData
The clone-level AnnData object, typically from create_clone_adata.
- z_dim int, optional
Dimensionality of the clonal embedding, by default 10.
- obsp_key str, optional
Key in clones.obsp for the graph to use, by default “gex_adjacency”.
- max_iter int, optional
Maximum number of iterations for optimization, by default 500.
- learning_rate float | None, optional
Learning rate for optimization, by default 0.001.
- device str | None, optional
Device to use for computation, by default None.
- progress_bar bool, optional
Whether to show a progress bar, by default True.
- obsm_key str, optional
Key in clones.obsm to store the embeddings, by default “c2v”.
- uns_key str, optional
Key in clones.uns to store the results, by default “c2v”.
- random_state None | int, optional
Random state for reproducibility, by default 4.
- init Literal["svd", "random", "custom"], optional
Initialization method, if “svd”, uses SVD on the log1p-transformed counts, by default “svd”.
- init_obsm str | None, optional
Key in clones.obsm for custom initialization, by default None.
- batch_size int, optional
Batch size for optimization, by default 128.
- early_stopping_patience int, optional
Number of iterations with no improvement to wait before stopping, by default 5.
- early_stopping_min_delta float, optional
Minimum change in loss to qualify as an improvement, by default 1e-4.
- mask_key str | None
- Return type: