Maintainer FreedomIntelligence · Last updated April 1, 2026
Deconvolution estimates cell type proportions in each spatial spot using a reference single-cell dataset. Essential for Visium data where spots contain multiple cells.
Original source
https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills/tree/main/skills/spatial-deconvolution
Skill Snapshot
Source Doc
import cell2location
from cell2location.utils.filtering import filter_genes
from cell2location.models import RegressionModel
## Load reference scRNA-seq
adata_ref = sc.read_h5ad('reference_scrna.h5ad')
adata_ref.obs['cell_type'] = adata_ref.obs['cell_type'].astype('category')
## Load spatial data
adata_vis = sc.read_h5ad('spatial_data.h5ad')
Related skills
Cell segmentation from multiplexed tissue images. Covers deep learning (Cellpose, Mesmer) and classical approaches for nuclear and whole-cel…
Extract, process, and deduplicate reads using Unique Molecular Identifiers (UMIs) with umi_tools. Use when library prep includes UMIs and ac…
Integrate multiple scRNA-seq samples/batches using Harmony, scVI, Seurat anchors, and fastMNN. Remove technical variation while preserving b…
Automated cell type annotation using reference-based methods including CellTypist, scPred, SingleR, and Azimuth for consistent, reproducible…