scib_rapids.bras

Contents

scib_rapids.bras#

scib_rapids.bras(X, labels, batch, chunk_size=256, metric='cosine', between_cluster_distances='mean_other')[source]#

Batch removal adapted silhouette (BRAS).

Parameters:

  • X (ndarray) – Array of shape (n_cells, n_features).

  • labels (ndarray) – Array of shape (n_cells,) representing label values.

  • batch (ndarray) – Array of shape (n_cells,) representing batch values.

  • chunk_size (int (default: 256)) – Size of chunks to process at a time.

  • metric (Literal['euclidean', 'cosine'] (default: 'cosine')) – ‘euclidean’ or ‘cosine’ (default).

  • between_cluster_distances (Literal['mean_other', 'furthest'] (default: 'mean_other')) – ‘mean_other’ (default) or ‘furthest’.

Return type:

float

Returns:

BRAS score

Contents