revise.backend.runners.sp_svc_application.SpSVC

class revise.backend.runners.sp_svc_application.SpSVC(st_adata, sc_ref_adata, config, logger)

Bases: ApplicationSVC

sp-SVC class for application usage.

This class reconstructs single-cell resolution expression profiles from spatial transcriptomics data using optimal transport-based graph aggregation for each cell type.

__init__(st_adata, sc_ref_adata, config, logger)

Initialize BaseSVCAnchor.

Parameters:

• st_adata – Spatial transcriptomics AnnData object

• sc_ref_adata – Single-cell reference AnnData object

• config – Configuration object containing method parameters

• real_st_adata – Ground truth spatial data (for benchmarking, can be None)

• logger – Logger instance for logging

Methods

__init__(st_adata, sc_ref_adata, config, logger)	Initialize BaseSVCAnchor.
global_anchoring(*args, **kwargs)	Annotate spatial spots using the configured annotation method.
local_refinement()	Reconstruct single-cell resolution expression profiles.

local_refinement()

Reconstruct single-cell resolution expression profiles.

This method performs the following steps: 1. Trims spatial data by removing low-expression genes 2. For each cell type, constructs an adjacency graph 3. Uses optimal transport to find neighbor relationships 4. Aggregates neighbor expressions using graph-based smoothing 5. Optionally generates UMAP plots for visualization

The reconstructed data is stored in self.svc[“sp_svc”].

_umap_plot(adata, prefix)

Generate UMAP visualization plots.

Parameters:

• adata – AnnData object to plot

• prefix – Prefix string for output file names

This method performs preprocessing (filtering, normalization, PCA), computes clustering at multiple resolutions, and generates UMAP and spatial scatter plots saved to the result directory.