scimilarity.cell_search_knn

class scimilarity.cell_search_knn.CellSearchKNN(model_path, use_gpu=False)

Bases: CellEmbedding

A class for searching similar cells using cell embeddings kNN.

Parameters:

• model_path (str) –

• use_gpu (bool) –

get_nearest_neighbors(embeddings, k=50, ef=100)

Get nearest neighbors. Used by classes that inherit from CellEmbedding and have an instantiated kNN.

Parameters:

• embeddings (numpy.ndarray) – Embeddings as a numpy array.

• k (int, default: 50) – The number of nearest neighbors.

• ef (int, default: 100) – The size of the dynamic list for the nearest neighbors. See https://github.com/nmslib/hnswlib/blob/master/ALGO_PARAMS.md

Returns:

• nn_idxs (numpy.ndarray) – A 2D numpy array of nearest neighbor indices [num_cells x k].

• nn_dists (numpy.ndarray) – A 2D numpy array of nearest neighbor distances [num_cells x k].

Return type:

Tuple[numpy.ndarray, numpy.ndarray]

Examples

>>> nn_idxs, nn_dists = get_nearest_neighbors(embeddings)

load_knn_index(knn_file)

Load the kNN index file

Parameters:

knn_file (str) – Filename of the kNN index.