scanpy

Analyze single-cell RNA-seq data with Scanpy for QC, clustering, and visualization.

1|Updated Mar 19, 2026
One-click install
npx skills add https://github.com/JosephWoodall/noosphere --skill scanpy-josephwoodall
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: scanpy
Source: https://github.com/JosephWoodall/noosphere/tree/main/.agent/skills/scanpy
Command: npx skills add https://github.com/JosephWoodall/noosphere --skill scanpy-josephwoodall

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) and references (resource) components.

What problem does it solve?

Scanpy provides a scalable Python toolkit for analyzing single-cell RNA-seq data, enabling researchers to perform quality control, normalization, dimensionality reduction, clustering, and visualization within a unified workflow.

Core Features & Use Cases

  • Quality control, normalization, HVG selection, and data inspection
  • Dimensionality reduction (PCA/UMAP/t-SNE), neighborhood graphs, and visualization
  • Clustering (Leiden/Louvain) with marker gene identification and trajectory inference
  • Cell-type annotation and generation of publication-ready plots

Quick Start

Execute a complete Scanpy workflow on your AnnData object to QC, normalize, reduce dimensions, cluster, annotate, and visualize.

Frequently Asked Questions about scanpy

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

FAQPage Schema
How do I perform clustering and dimensionality reduction on scRNA-seq data?

To perform clustering and dimensionality reduction on scRNA-seq data, you can use Scanpy to execute quality control, normalization, PCA, and UMAP on an AnnData object, followed by Leiden or Louvain clustering to identify cell groups.

What is the best way to analyze h5ad files for marker gene identification?

The best way to analyze h5ad files for marker gene identification is to load the AnnData object into a Python environment with Scanpy installed, then run preprocessing modules to normalize data and detect marker genes for each cluster.

Can I use Scanpy for trajectory inference and cell-type annotation?

Yes, you can use Scanpy for trajectory inference and cell-type annotation. The toolkit supports exploratory workflows on single-cell RNA-seq datasets, allowing you to map cellular transitions and assign cell types based on marker gene expression.

Do I need a specific Python environment to run single-cell RNA-seq visualization workflows?

Yes, you need a Python environment with Scanpy installed to run single-cell RNA-seq visualization workflows. A valid AnnData object is also required to drive the core plotting, clustering, and processing modules for generating publication-ready plots.

Does this single-cell analysis workflow support 10X format datasets?

Yes, this single-cell analysis workflow supports 10X format datasets. The Scanpy toolkit is designed to ingest 10X data, perform quality control, high variable gene selection, and generate visualizations suitable for exploratory analysis.

Why does my UMAP visualization fail after neighborhood graph construction?

Your UMAP visualization may fail after neighborhood graph construction if the AnnData object lacks properly normalized high variable genes. Ensure the Scanpy preprocessing steps for scaling and PCA are completed before computing the neighborhood graph.