alterlab-scanpy

Run end-to-end single-cell RNA-seq analysis with Scanpy on AnnData objects.

58|9|Updated Mar 16, 2026
One-click install
npx skills add https://github.com/AlterLab-IEU/AlterLab-Academic-Skills --skill alterlab-scanpy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: alterlab-scanpy
Source: https://github.com/AlterLab-IEU/AlterLab-Academic-Skills/tree/main/skills/bioinformatics/alterlab-scanpy
Command: npx skills add https://github.com/AlterLab-IEU/AlterLab-Academic-Skills --skill alterlab-scanpy

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Streamlines end-to-end single-cell RNA-seq analysis by providing a ready-to-use Scanpy workflow that handles QC, normalization, feature selection, dimensionality reduction, clustering, and annotation, reducing setup time and improving reproducibility.

Core Features & Use Cases

  • End-to-end scRNA-seq pipeline including quality control, normalization, HVG selection, PCA/UMAP, Leiden clustering, marker gene identification, and cell-type annotation.
  • Trajectory inference with PAGA/dpt and straightforward export of processed data and metadata for downstream reporting.

Quick Start

Run the included template on your scRNA-seq data to execute a full Scanpy workflow from loading to clustering and annotation.

Frequently Asked Questions about alterlab-scanpy

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

FAQPage Schema
How do I perform end-to-end scRNA-seq analysis from quality control to trajectory inference?

End-to-end scRNA-seq analysis applies Scanpy to AnnData objects for quality control, normalization, HVG selection, dimensionality reduction, clustering, and PAGA/dpt trajectory inference in a reproducible workflow.

Can I use Scanpy for Leiden clustering and marker gene identification on my single-cell dataset?

Yes, Scanpy performs Leiden and Louvain clustering on single-cell datasets, followed by marker gene identification and standardized export of metadata CSVs and processed .h5ad files for downstream reporting.

What is the best way to export processed scRNA-seq data and metadata for integration into reports?

The best way to export scRNA-seq data is using a standardized Scanpy workflow that generates processed .h5ad files, metadata CSVs, and marker lists suitable for direct integration into downstream analytical reports.

Does this scRNA-seq workflow require AnnData objects as input for normalization and HVG selection?

Yes, the scRNA-seq workflow requires AnnData objects as input to execute HVG-focused preprocessing, normalization, and subsequent dimensionality reduction steps within the Scanpy pipeline.

What limitations should I expect when running trajectory inference with PAGA on diverse scRNA-seq datasets?

Trajectory inference with PAGA is encapsulated in a standardized workflow for diverse scRNA-seq datasets, meaning results are bound by the preprocessing steps, HVG selection quality, and inherent limitations of the Scanpy implementation.