thor.analy.SPARKX

class thor.analy.SPARKX(rscript_path='R/run_SPARKX.R', **kwargs)[source]

Class for running SPARK-X.

Parameters:: rscript_path (str, default: “R/run_SPARKX.R”) – Path to the R script for running SPARKX.

Methods

`RUN_SPARKX_R`	Run SPARK-X with provided R script.
`compute_pattern_mean`	Compute the mean expression of each gene module.
`hierarchy_clustering`	Run hierarchical clustering with sklearn's AgglomerativeClustering on the residual matrix.
`kmeans_clustering`	Run k-means clustering with sklearn's KMeans on the residual matrix.
`load_gene_modules`	Load the gene modules of SPARK-X.
`load_result`	Load the result of SPARK-X.

RUN_SPARKX_R(adata_path=None, layer=None, out_path=None)[source]

Run SPARK-X with provided R script.

Parameters:

static compute_pattern_mean(adata, data, pattern, obskey_prefix)[source]

Compute the mean expression of each gene module.

Parameters:

adata (anndata.AnnData) – AnnData object.
data (pandas.DataFrame (n_sig_genes x n_cells)) – Residual matrix of SPARK-X.
pattern (pandas.DataFrame (n_sig_genes x 1), column is cluster, index is gene) –
obskey_prefix (str) – Prefix of the observation key.

Returns:

adata – AnnData object with the computed pattern mean.

Return type:

anndata.AnnData

hierarchy_clustering(**hc_kwargs)[source]

Run hierarchical clustering with sklearn’s AgglomerativeClustering on the residual matrix.

Parameters:: hc_kwargs (dict) – Keyword arguments for AgglomerativeClustering.
Returns:: labels – Cluster labels.
Return type:: numpy.ndarray (n_cells,)

kmeans_clustering(n_patterns, **kmeans_kwargs)[source]

Run k-means clustering with sklearn’s KMeans on the residual matrix.

Parameters:

Returns:

labels – Cluster labels.

Return type:

numpy.ndarray (n_cells,)

load_gene_modules(pattern_prefix='SP')[source]

Load the gene modules of SPARK-X.

Parameters:: pattern_prefix (str, default: “SP”) – Prefix of the gene modules.