scanpy

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

22|4|Updated May 25, 2026

Search Tags:#visualization #trajectory #single-cell #quality-control #clustering #scanpy #rna-seq

Ready to run

npx skills add https://github.com/crazymsn/academic-skills --skill scanpy-crazymsn

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: scanpy
Source: https://github.com/crazymsn/academic-skills/tree/main/academic-skills/scanpy
Command: npx skills add https://github.com/crazymsn/academic-skills --skill scanpy-crazymsn

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Streamline end-to-end analysis of single-cell RNA-seq data, enabling researchers to perform quality control, normalization, dimensionality reduction, clustering, and visualization with a consistent workflow.

Core Features & Use Cases

QC metrics calculation and filtering to remove low-quality cells and genes.
Normalization, scaling, HVG selection, and downstream dimensionality reduction (PCA/UMAP/t-SNE) with clustering and marker gene analysis.
Trajectory inference (PAGA/dpt) and differential expression to explore cell lineage and state transitions.
Reproducible templates and references to standard workflows for consistent analyses across datasets.

Quick Start

Load your scRNA-seq data into an AnnData object and run the included end-to-end workflow to reproduce typical scRNA-seq analyses.

Frequently Asked Questions about scanpy

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

FAQPage Schema

How do I run an end-to-end single-cell RNA-seq analysis workflow?▼

Single-cell RNA-seq analysis workflows can be run end-to-end by loading data into an AnnData object and applying steps for QC, normalization, HVG selection, PCA, UMAP, Leiden clustering, and marker gene identification.

What is trajectory inference in scRNA-seq and how does it work?▼

Trajectory inference in scRNA-seq maps cell lineage and state transitions using PAGA and diffusion pseudotime to model dynamic developmental processes across cell populations.

Can I use Scanpy with matplotlib for dimensionality reduction visualization?▼

Yes, Scanpy works with matplotlib to generate visualizations for dimensionality reduction, including plots for PCA, UMAP, and t-SNE embeddings of normalized single-cell datasets.

What's the best way to perform quality control on scRNA-seq data?▼

Quality control for scRNA-seq data involves calculating QC metrics to filter out low-quality cells and genes, ensuring that only high-variance features proceed to normalization and clustering.

Does this single-cell RNA-seq pipeline support reproducible analyses across datasets?▼

Yes, the pipeline provides reproducible templates and references for standard workflows, ensuring consistent quality control, normalization, and clustering analyses across multiple scRNA-seq datasets.

When should I use Leiden clustering for single-cell data?▼

Leiden clustering should be used after dimensionality reduction on normalized scRNA-seq data to accurately group cells into distinct populations based on their gene expression profiles.