scanpy

Analyze single-cell RNA-seq data with Scanpy for clustering and trajectory inference.

15|2|Updated Dec 17, 2025
One-click install
npx skills add https://github.com/rubensliv/k-dense-ai --skill scanpy-rubensliv
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: scanpy
Source: https://github.com/rubensliv/k-dense-ai/tree/main/scientific-skills/scanpy
Command: npx skills add https://github.com/rubensliv/k-dense-ai --skill scanpy-rubensliv

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires scanpy, matplotlib, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Analyze single-cell RNA-seq data to identify cell types, clusters, and trajectories.

Core Features & Use Cases

  • End-to-end scRNA-seq analysis using Scanpy and AnnData: load data, QC, normalization, HVG selection, dimensionality reduction (PCA/UMAP/t-SNE), clustering (Leiden), marker gene identification, cell-type annotation, and trajectory inference.
  • Use Case: Prepare publication-ready cell-type maps from a new scRNA-seq dataset with minimal setup.
  • Use Case: Compare conditions or batches by aligning datasets and annotating cell states across samples.

Quick Start

Run a complete end-to-end scanpy workflow on your dataset to produce a processed AnnData with clusters and cell-type annotations.

Frequently Asked Questions about scanpy

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

FAQPage Schema
How do I analyze scRNA-seq data to identify cell types and clusters?

scRNA-seq trajectory inference maps developmental progressions by applying dimensionality reduction and pseudotime analysis to an AnnData object. This workflow orders clustered cells along continuous trajectories to infer developmental relationships and cell state transitions.

What is the best way to run trajectory inference on single-cell RNA-seq data?

scRNA-seq trajectory inference maps developmental progressions by applying dimensionality reduction and pseudotime analysis to an AnnData object. This workflow orders clustered cells along continuous trajectories to infer developmental relationships and cell state transitions.

How do I prepare publication-ready visualizations from 10X scRNA-seq data?

Scanpy scRNA-seq analysis requires a Python environment with Scanpy, AnnData, and Matplotlib installed. It accepts raw single-cell RNA-seq datasets in .h5ad, .h5, or 10X formats as input to execute the end-to-end clustering and annotation workflow.

Do I need a specific Python environment to run Scanpy single-cell analysis?

Scanpy scRNA-seq analysis requires a Python environment with Scanpy, AnnData, and Matplotlib installed. It accepts raw single-cell RNA-seq datasets in .h5ad, .h5, or 10X formats as input to execute the end-to-end clustering and annotation workflow.

Can I align and compare multiple scRNA-seq batches using this workflow?

The Scanpy workflow identifies marker genes by comparing expression distributions across Leiden clusters within the normalized AnnData object. It uses statistical testing to pinpoint genes that characterize distinct cell populations for downstream annotation.

How does single-cell RNA-seq clustering identify marker genes?

The Scanpy workflow identifies marker genes by comparing expression distributions across Leiden clusters within the normalized AnnData object. It uses statistical testing to pinpoint genes that characterize distinct cell populations for downstream annotation.