grassp.tl.aligned_umap

aligned_umap(data_list, align_data=True, return_data_objects=True, n_neighbors=20, metric='euclidean', min_dist=0.1, alignment_regularisation=0.002, n_epochs=300, random_state=None, verbose=False, n_components=2)

Calculate aligned UMAP embeddings for multiple datasets.

Parameters:

data_list List[AnnData]

List of AnnData objects to align

align_data bool (default: True)

Whether to align data by intersecting observations and variables

return_data_objects bool (default: True)

Whether to return aligned AnnData objects with UMAP embeddings

n_neighbors int (default: 20)

Number of neighbors to use for UMAP

metric str (default: 'euclidean')

Distance metric for UMAP

min_dist float (default: 0.1)

Minimum distance between points in UMAP embedding

alignment_regularisation float (default: 0.002)

Strength of alignment regularization between datasets

n_epochs int (default: 300)

Number of epochs to optimize embeddings

random_state Optional[int] (default: None)

Random seed for reproducibility

verbose bool (default: False)

Whether to display progress updates

n_components int (default: 2)

Number of dimensions for UMAP embedding

Return type:

AlignedUMAP

Returns:

data_sub_list or umap.AlignedUMAP If return_data_objects is True, returns list of aligned AnnData objects with UMAP embeddings. Otherwise returns fitted AlignedUMAP object.