simba.tl.embed

simba.tl.embed(adata_ref, list_adata_query, T=0.5, list_T=None, percentile=0, n_top=None, list_percentile=None, use_precomputed=False)[source]

Embed a list of query datasets along with reference dataset into the same space

Parameters:

  • adata_ref (AnnData) – Reference anndata.

  • list_adata_query (list) – A list query anndata objects

  • T (float) – Temperature parameter shared by all query adata objects. It controls the output probability distribution. when T goes to inf, it becomes a discrete uniform distribution, each query becomes the average of reference; when T goes to zero, softargmax converges to arg max, each query is approximately the best of reference.

  • list_T (list, (default: None)) – A list of temperature parameters. It corresponds to each of query data. Once it’s specified, it will override T.

  • n_top (float (default: None)) – The number of top reference entities to include when transforming entities in query data. It is used to filter out low-probability reference entities. All reference entities used by default.

  • percentile (int (default: 0)) – Percentile (0-100) of reference entities to exclude when transforming entities in query data. It is used to filter out low-probability reference entities. All reference entities used by default.

  • list_percentile (list, (default: None)) – A list of percentile parameters. It corresponds to each of query data. Once it’s specified, it will override percentile.

Returns:

  • adata_all (AnnData) – Store #entities × #dimensions.

  • updates adata_query with the following field.

  • softmax (array_like (.layers[‘softmax’])) – Store #observations × #dimensions softmax transformed data matrix.