scanpy

Analyze single-cell gene expression data with AnnData and scRNA-seq workflows.

19|2|Updated Jan 31, 2026

Search Tags:#data analysis #bioinformatics #single-cell #scRNA-seq #scanpy #AnnData #gene expression

Ready to run

npx skills add https://github.com/tondevrel/scientific-agent-skills --skill scanpy-tondevrel

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines the complex process of analyzing high-dimensional single-cell gene expression data, enabling researchers to identify cell populations and understand biological processes.

Core Features & Use Cases

Data Loading & Preprocessing: Handles AnnData objects, filters cells and genes, and normalizes expression counts.
Dimensionality Reduction & Visualization: Reduces data complexity using PCA and UMAP for visualization and clustering.
Cell Type Identification: Groups cells into distinct populations using clustering algorithms like Leiden.
Use Case: Researchers can use this Skill to analyze scRNA-seq data to discover rare cell types in a tissue sample or to visualize the differentiation pathways of cells.

Quick Start

Load the 'cells.h5ad' dataset and visualize cell types on a UMAP plot.

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 distinct cell populations?▼

To analyze scRNA-seq data, you load single-cell gene expression datasets into the AnnData format, apply filtering and normalization, then use dimensionality reduction and clustering algorithms like Leiden to group cells into distinct populations.

What preprocessing steps are required for accurate single-cell gene expression analysis?▼

Accurate single-cell gene expression analysis requires robust preprocessing steps including filtering cells and genes, normalizing expression counts, and applying log-transformation to the AnnData objects before performing downstream biological analysis.

Can I visualize differentiation pathways using UMAP on scRNA-seq datasets?▼

Yes, you can visualize differentiation pathways and cell populations using UMAP. The process reduces high-dimensional scRNA-seq data complexity after PCA, enabling visualization of single-cell gene expression patterns and trajectory inference.

Does this approach support trajectory inference for discovering rare cell types?▼

Yes, trajectory inference is supported for discovering rare cell types. By processing high-dimensional single-cell gene expression data through clustering and dimensionality reduction, researchers can map out and visualize cellular differentiation processes.

What is the best way to handle scalable analysis of single-cell gene expression data?▼

The best way to handle scalable analysis of single-cell gene expression data is using the AnnData format. It facilitates filtering, normalization, dimensionality reduction, and differential expression analysis for large scRNA-seq datasets.

Why do I need to normalize expression counts before clustering scRNA-seq data?▼

Normalizing expression counts before clustering scRNA-seq data is required to ensure accurate biological insights. Without proper normalization and log-transformation of the raw counts, dimensionality reduction and cell type identification algorithms may yield skewed results.