spatial-domains
OfficialDiscover tissue regions in spatial data.
Education & Research#bioinformatics#spatial transcriptomics#clustering#domain identification#tissue region#niche discovery
AuthorTianGzlab
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill automates the identification of distinct tissue regions and spatial niches within spatial transcriptomics data, eliminating the need for manual, inconsistent parameter tuning across different clustering methods.
Core Features & Use Cases
- Automated Domain Identification: Utilizes multiple advanced algorithms (Leiden, SpaGCN, STAGATE, GraphST, BANKSY) to partition spatial transcriptomics data into biologically meaningful domains.
- Visualization & Reporting: Generates annotated spatial maps, UMAP plots, and comprehensive reports detailing domain characteristics and reproducibility.
- Use Case: A researcher has a Visium dataset and wants to identify distinct cell populations within different anatomical regions of a tumor. This Skill can automatically cluster the spatial spots into these regions, visualize them on the tissue, and provide a summary report.
Quick Start
Use the spatial-domains skill to identify tissue regions in the provided 'my_spatial_data.h5ad' file.
Dependency Matrix
Required Modules
scanpysquidpymatplotlibnumpypandasscipyscikit-learntorchSpaGCNSTAGATE_pyGGraphSTbanksy
Components
scriptsreferences
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: spatial-domains Download link: https://github.com/TianGzlab/OmicsClaw/archive/main.zip#spatial-domains Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.