past.Evaluation.mclust_R

past.Evaluation.mclust_R(adata, num_cluster, refine=False, num_nbs=6, modelNames='EEE', used_obsm='embedding', random_seed=666)

Clustering using the mclust algorithm.

Parameters:

  • adata – target dataset of anndata format with latent feature stored in adata.obsm[used_obsm]

  • num_cluster – cluster number

  • refine – whether or not refine clustering results, if True, spatial coordinate should be stored in adata.obsm[“spatial”]

  • num_nbs – number of neighbors to consider when refining clustering labels, valid only if refine is True

  • modelNames – parameter in mclust R package, implying different data distribution

  • used_obsm – key of adata.obsm implying latent features

  • random_seed – seed for reproduction

Returns:

target dataset of anndata format with mclust clustering result stored in adata.obs[“mclust”] and refined clustering result stored in adata.obs[“mclust_refined”] if refined is True

Return type:

scanpy.annndata