seuratclustering

Cluster Seurat objects with Leiden or Louvain algorithms to identify cell populations.

22|4|Updated May 18, 2021

Search Tags:#single-cell #cluster #umap #seurat #scrna-seq #leiden

Ready to run

npx skills add https://github.com/pwwang/immunopipe --skill seuratclustering

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: seuratclustering
Source: https://github.com/pwwang/immunopipe/tree/main/skills/seuratclustering
Command: npx skills add https://github.com/pwwang/immunopipe --skill seuratclustering

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Clustering single-cell RNA-seq data to identify distinct cell populations and guide downstream annotation, enabling researchers to interpret cellular heterogeneity efficiently.

Core Features & Use Cases

Unsupervised clustering using Seurat's FindNeighbors and FindClusters with Leiden or Louvain algorithms.
Multi-resolution exploration to balance granularity and biological relevance.
UMAP visualization for intuitive interpretation and exploration of cluster structure.
Real-world workflows: after QC/normalization; when integrating data with integrated reductions; and for reference-based or annotation-driven analyses.

Quick Start

Provide a Seurat object as input (SeuratPreparing) and run SeuratClustering with default parameters.

Frequently Asked Questions about seuratclustering

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

FAQPage Schema

How do I cluster single-cell RNA-seq data to identify distinct cell populations?▼

Cluster single-cell RNA-seq data by providing a pre-processed Seurat object to run FindNeighbors and FindClusters, which identifies distinct cell populations for downstream annotation.

What is the difference between Leiden and Louvain clustering for scRNA-seq?▼

Leiden and Louvain are both algorithms supported for scRNA-seq clustering to identify cell populations. Leiden often yields more refined clusters, while multi-resolution exploration helps balance granularity and biological relevance.

Can I use integrated reductions for clustering multiple single-cell datasets in Seurat?▼

Yes, single-cell clustering supports integration-aware reductions, allowing you to cluster multiple datasets reliably after integration by utilizing the integrated reduction space.

How do I visualize UMAP embeddings after running Seurat clustering?▼

Visualize UMAP embeddings after Seurat clustering to intuitively interpret and explore the cluster structure, helping you understand cellular heterogeneity and distinct populations.

What's the best way to balance cluster granularity in single-cell data?▼

Balance cluster granularity in single-cell data through multi-resolution exploration during clustering, allowing you to adjust parameters and find the optimal balance for biological relevance.

Do I need to normalize my scRNA-seq data before running Seurat clustering?▼

Yes, you need to perform QC and normalization on your scRNA-seq data first. Provide a prepared Seurat object as input to reliably identify distinct cell populations through clustering.