skills.rest
Ketomihine
KetomihineCOMMUNITY
Explore all skills by this author →
GitHub

cellcharter-local-optimized

Identify and characterize spatial clusters in spatial-omics data using CellCharter.

1|Updated Dec 3, 2025
Search Tags:#analyze#domain#neighborhood#CellCharter#spatial-omics#multi-sample
One-click install
npx skills add https://github.com/Ketomihine/my_skills --skill cellcharter-local-optimized
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: cellcharter-local-optimized
Source: https://github.com/Ketomihine/my_skills/tree/main/cellcharter-local-optimized
Command: npx skills add https://github.com/Ketomihine/my_skills --skill cellcharter-local-optimized

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

CellCharter Local-Optimized provides a comprehensive toolkit to identify, characterize, and compare spatial clusters in spatial-omics data, enabling researchers to map tissue organization efficiently.

Core Features & Use Cases

  • Neighborhood-aware clustering: aggregate neighborhood features to identify spatial domains across tissue sections.
  • Domain shape and boundary analysis: compute boundaries and shape metrics (linearity, curl, elongation, purity) for detailed domain characterization.
  • Cross-sample and condition comparisons: align spatial clusters across multiple samples and perform differential neighborhood enrichment analyses.
  • Flexible data types: supports spatial transcriptomics, spatial proteomics, spatial epigenomics, and multiomics data, with on-demand use of scripts, references, and assets.
  • Visualization and exploration: generate intuitive plots of boundaries, enrichments, and domain metrics to facilitate interpretation.

Quick Start

Load your AnnData object with spatial coordinates, construct the spatial graph with a neighborhood approach, cluster cells using CellCharter's pipeline, and compute boundaries and shape metrics to visualize spatial domains. Then compare domains across samples and conditions.

Frequently Asked Questions about cellcharter-local-optimized

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I identify spatial domains in spatial-omics data across multiple tissue samples?▼

Spatial domain identification uses neighborhood-aware clustering to aggregate features across multi-sample tissue datasets. This approach aligns spatial clusters across samples, enabling cross-sample and condition comparisons for spatial-omics data.

Can I compute domain boundary shape metrics like linearity and curl for spatial transcriptomics data?▼

Yes, domain boundary characterization computes shape metrics including linearity, curl, elongation, and purity for spatial transcriptomics data. These metrics quantify tissue boundary structural properties to facilitate detailed domain interpretation.

What spatial data types are supported for tissue domain mapping and neighborhood analysis?▼

Tissue domain mapping supports spatial transcriptomics, spatial proteomics, spatial epigenomics, and multiomics data. Neighborhood analysis aggregates spatial features across these flexible data types to identify spatial clusters within tissue sections.

Do I need Python 3.8 and PyTorch to run spatial clustering for tissue domain mapping?▼

Yes, spatial clustering for tissue domain mapping requires Python 3.8+, PyTorch, scvi-tools, Squidpy, and TorchGMM. These dependencies provide the computational framework for neighborhood analysis and spatial graph construction using AnnData objects.

How do I compare spatial clusters across different tissue samples and experimental conditions?▼

Cross-sample spatial cluster comparison aligns clusters across multiple samples and performs differential neighborhood enrichment analyses. This process identifies condition-specific variations in tissue domain organization and neighborhood composition across spatial-omics datasets.

What is the best way to visualize spatial domain boundaries and neighborhood enrichments?▼

Visualize spatial domain boundaries and neighborhood enrichments by generating intuitive plots of boundaries, enrichments, and domain metrics. This exploration step facilitates interpretation of tissue organization and spatial cluster characteristics directly from the analysis pipeline.

Related Skills

Explore More Education & Research Skills→
KetomihineKetomihine
1

giottosuite-local

Orchestrate spatial transcriptomics analysis with Giotto Suite workflows.

Community
Advanced
ya-wayya-way

bio-spatial-transcriptomics-spatial-communication

Analyze ligand-receptor interactions in spatial transcriptomics data with Squidpy.

Community
Intermediate
StarlitnightlyStarlitnightly
1.2k

Single-cell clustering and batch correction with omicverse

Cluster and batch-correct single-cell AnnData objects with omicverse.

Community
Advanced
CHENyiru3CHENyiru3

squidpy

Analyze spatial omics data with Squidpy for neighborhood analysis and visualization.

Community
Advanced