spamosaic.utils

class spamosaic.utils.Config(dictionary)[source]

Bases: object

A wrapper class that recursively converts a dictionary to an object with attribute-style access.

__dict__

Stores the nested configuration structure.

Type:: dict

spamosaic.utils.check_batch_empty(modBatch_dict, verbose=True)[source]

Checks if any batch in the modality-batch dictionary is empty and returns indices of modalities per batch.

Parameters:

modBatch_dict (dict) – Dictionary of modality -> list of AnnData objects (or None).
verbose (bool) – Whether to print out batch composition.

Returns:

List of lists indicating indices of modalities present in each batch.

Return type:

list[list[int]]

Raises:

ValueError – If any batch is completely empty.

spamosaic.utils.clustering(adata, n_cluster, used_obsm, algo='kmeans', key='tmp_clust')[source]

Performs clustering on an AnnData object using k-means or Mclust.

Parameters:

adata (AnnData) – Input data.
n_cluster (int) – Number of clusters.
used_obsm (str) – Key in .obsm to use for clustering.
algo (str) – Clustering algorithm, ‘kmeans’ or ‘mclust’.
key (str) – Key name to store clustering results in .obs.

Returns:

Annotated object with cluster assignments.

Return type:

AnnData

spamosaic.utils.dict_map(_dict, _list)[source]

Applies dictionary mapping over a list.

Parameters:

_dict (dict) – Dictionary to map from.
_list (list) – List of keys.

Returns:

Mapped values.

Return type:

list

spamosaic.utils.flip_axis(ads, axis=0)[source]

Flips the spatial coordinates of AnnData objects along a specified axis.

Parameters:

ads (list[AnnData]) – List of data objects to modify.
axis (int) – Axis to flip (0 for x, 1 for y).

spamosaic.utils.get_barc2batch(modBatch_dict)[source]

Creates a mapping from cell barcodes to their batch indices.

Parameters:: modBatch_dict (dict) – Dictionary of modality -> list of AnnData objects.
Returns:: Mapping from barcode to batch index.
Return type:: dict

spamosaic.utils.get_umap(ad, use_reps=[])[source]

Computes UMAP embeddings for given representation keys and stores them in .obsm.

Parameters:

ad (AnnData) – Input data.
use_reps (list[str]) – Keys in .obsm to compute UMAP for.

Returns:

Annotated object with new UMAPs.

Return type:

AnnData

spamosaic.utils.load_config(filepath)[source]

Loads a YAML configuration file into a Config object.

Parameters:: filepath (str) – Path to the YAML configuration file.
Returns:: Parsed configuration object.
Return type:: Config

spamosaic.utils.mclust_R(adata, num_cluster, modelNames='EEE', used_obsm='emb', random_seed=2020)[source]

Performs R’s Mclust via rpy2.

Parameters:

adata (AnnData) – AnnData object with embedding stored in .obsm.
num_cluster (int) – Desired number of clusters.
modelNames (str) – Covariance structure model in Mclust.
used_obsm (str) – Key in .obsm to use for clustering.
random_seed (int) – Random seed for reproducibility.

Returns:

Annotated object with added mclust cluster label.

Return type:

AnnData

spamosaic.utils.nn_approx(ds1, ds2, norm=True, knn=10, metric='manhattan', n_trees=10, include_distances=False)[source]

Performs approximate nearest neighbor search using Annoy.

Parameters:

ds1 (np.ndarray) – Query data (n_samples, n_features).
ds2 (np.ndarray) – Reference data (n_samples, n_features).
norm (bool) – Whether to normalize data before search.
knn (int) – Number of nearest neighbors to retrieve.
metric (str) – Distance metric for Annoy (e.g., ‘manhattan’).
n_trees (int) – Number of trees used by Annoy.
include_distances (bool) – Whether to return distances with indices.

Returns:

Indices of nearest neighbors, optionally with distances.

Return type:

np.ndarray or tuple

spamosaic.utils.plot_basis(ad, basis, color, **kwargs)[source]

Wrapper for Scanpy’s sc.pl.embedding with warning suppression.

Parameters:

ad (AnnData) – Annotated data object.
basis (str) – Key of embedding (e.g., ‘umap’).
color (str) – Variable in .obs to color by.
**kwargs – Additional plotting arguments.

spamosaic.utils.reorder(ad1, ad2)[source]

Aligns and reorders two AnnData objects to only shared barcodes.

Parameters:

ad1 (AnnData) – First data object.
ad2 (AnnData) – Second data object.

Returns:

Reordered and aligned data objects.

Return type:

Tuple[AnnData, AnnData]

spamosaic.utils.split_adata_ob(ads, ad_ref, ob='obs', key='emb')[source]

Splits a reference AnnData object’s observations or embeddings into a list of AnnData objects.

Parameters:

ads (list[AnnData]) – List of target AnnData objects.
ad_ref (AnnData) – Source AnnData object containing merged info.
ob (str) – Whether to split ‘obs’ or ‘obsm’.
key (str) – Key to split in .obs or .obsm.

Functions

`spamosaic.utils.check_batch_empty`	Checks if any batch in the modality-batch dictionary is empty and returns indices of modalities per batch.
`spamosaic.utils.clustering`	Performs clustering on an AnnData object using k-means or Mclust.
`spamosaic.utils.dict_map`	Applies dictionary mapping over a list.
`spamosaic.utils.flip_axis`	Flips the spatial coordinates of AnnData objects along a specified axis.
`spamosaic.utils.get_barc2batch`	Creates a mapping from cell barcodes to their batch indices.
`spamosaic.utils.get_umap`	Computes UMAP embeddings for given representation keys and stores them in .obsm.
`spamosaic.utils.load_config`	Loads a YAML configuration file into a Config object.
`spamosaic.utils.mclust_R`	Performs R's Mclust via rpy2.
`spamosaic.utils.nn_approx`	Performs approximate nearest neighbor search using Annoy.
`spamosaic.utils.plot_basis`	Wrapper for Scanpy's sc.pl.embedding with warning suppression.
`spamosaic.utils.reorder`	Aligns and reorders two AnnData objects to only shared barcodes.
`spamosaic.utils.split_adata_ob`	Splits a reference AnnData object's observations or embeddings into a list of AnnData objects.

Classes

spamosaic.utils.Config

A wrapper class that recursively converts a dictionary to an object with attribute-style access.