netmap.downstream.clustering.downstream_recipe

netmap.downstream.clustering.downstream_recipe(grn_adata, **kwargs)

Run the standard Scanpy dimensionality-reduction and clustering pipeline.

Applies PCA, kNN graph construction, Leiden clustering, and UMAP embedding to grn_adata in sequence. All parameters have defaults and can be overridden via keyword arguments.

Parameters:

• grn_adata (anndata.AnnData) – GRN AnnData to process in-place.

• **kwargs –

  Optional parameter overrides:

  • n_neighbors (int): Leiden kNN neighbours. Default 30.

  • leiden_resolution (float): Leiden resolution. Default 0.1.

  • n_components (int): UMAP output dimensions. Default 100.

  • knn_neighbors (int): Neighbours for sc.pp.neighbors. Default 50.

  • svd_solver (str): PCA solver. Default 'randomized'.

Returns:

grn_adata with PCA, kNN, Leiden, and UMAP results

added.

Return type:

AnnData