scanpy

Process single-cell RNA-seq datasets into quality-controlled AnnData outputs with clustering and marker discovery.

Updated Jul 1, 2026
One-click install
npx skills add https://github.com/jasrajtulsi/GRAD-SCOPE --skill scanpy-jasrajtulsi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: scanpy
Source: https://github.com/jasrajtulsi/GRAD-SCOPE/tree/main/.claude/skills/scanpy
Command: npx skills add https://github.com/jasrajtulsi/GRAD-SCOPE --skill scanpy-jasrajtulsi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires scanpy, pandas, numpy, matplotlib, bbknn, harmonypy, scikit-image, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill removes the manual overhead of single-cell RNA-seq analysis by turning raw or partially processed datasets into QCed, normalized, clustered, and annotated results.

Core Features & Use Cases

  • Full Scanpy workflow: run quality control, normalization, highly variable gene selection, PCA, UMAP, Leiden clustering, marker discovery, and cell-type annotation.
  • Flexible input handling: work with h5ad, 10x HDF5, 10x mtx folders, CSV, TSV, TXT, loom, and mtx inputs, then carry results forward in AnnData format.
  • Practical outputs: generate marker tables, pseudobulk-ready counts, publication-style plots, and reusable templates for common scRNA-seq tasks across exploratory and reproducible analyses.

Quick Start

Ask me to run the Scanpy single-cell workflow on your dataset and I will guide the analysis from QC through clustering, markers, and plotting using the bundled scripts.

Frequently Asked Questions about scanpy

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

FAQPage Schema
How do I run a complete scRNA-seq analysis workflow from raw data to UMAP and clustering?

To run scRNA-seq analysis end to end, this workflow applies quality control, normalization, highly variable gene selection, PCA, UMAP, and Leiden clustering to generate annotated AnnData outputs and publication-style plots.

What single-cell file formats can I use to start scRNA-seq quality control and normalization?

For scRNA-seq quality control and normalization, supported input formats include h5ad, 10x HDF5, 10x mtx folders, CSV, TSV, TXT, loom, and mtx, which are processed into AnnData-compatible outputs.

Does this scRNA-seq workflow support batch correction for multiple samples?

Yes, this scRNA-seq workflow supports batch correction across multiple samples by integrating Harmony, ComBat, and BBKNN algorithms to remove technical variation during dimensionality reduction and clustering.

How do I prepare pseudobulk counts from single-cell RNA-seq data for downstream analysis?

To prepare pseudobulk counts from single-cell RNA-seq data, the workflow aggregates single-cell expression matrices into pseudobulk-ready counts and exports marker tables for downstream differential expression analysis.

Can I use this Scanpy workflow to discover marker genes and annotate cell types?

Yes, you can use this Scanpy workflow to discover marker genes and annotate cell types, as it performs Leiden clustering, exports marker tables, and generates UMAP visualizations for exploratory scRNA-seq analysis.

What is the best way to handle doublet detection in scRNA-seq datasets before clustering?

The best way to handle doublet detection in scRNA-seq datasets before clustering is using the integrated Scrublet algorithm, which identifies potential doublets during the initial quality control phase of the Scanpy workflow.