skills.rest
Estrella-231
Estrella-231COMMUNITY
Explore all skills by this author →
GitHub

scanpy

Run scanpy workflows on AnnData objects for single-cell RNA-seq preprocessing and exploratory analysis.

Updated May 24, 2026
Search Tags:#single-cell#scanpy#scrna-seq#trajectory inference#marker genes#qc filtering#umap clustering
One-click install
npx skills add https://github.com/Estrella-231/Mathematical_modeling_tongmeng --skill scanpy-estrella-231
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: scanpy
Source: https://github.com/Estrella-231/Mathematical_modeling_tongmeng/tree/main/.agents/skills/scanpy
Command: npx skills add https://github.com/Estrella-231/Mathematical_modeling_tongmeng --skill scanpy-estrella-231

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines exploratory single-cell RNA-seq analysis by replacing manual, error-prone steps with a consistent scanpy workflow from raw counts to embeddings, clusters, markers, and plots.

Core Features & Use Cases

  • End-to-end scRNA-seq workflow: QC, normalization, highly variable gene selection, scaling/regression, and dimensionality reduction.
  • Discovery for biology: clustering with Leiden, marker-gene ranking, and optional trajectory and pseudotime inference.
  • Visualization-ready outputs: publication-style UMAP/t-SNE plots, QC plots, heatmaps/dotplots for markers, and cell-type annotation visuals.
  • Use Case: When you have an .h5ad or 10X dataset, you can generate QC metrics, produce UMAP embeddings colored by clusters, identify marker genes per cluster, and annotate cell types using marker gene expression.

Quick Start

Run the Skill on your dataset file by loading your input .h5ad (or 10X matrix) and following the standard steps to produce filtered data, UMAP embeddings, Leiden clusters, and ranked marker genes.

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 workflow from raw counts to UMAP clustering?▼

To run scRNA-seq analysis, load an .h5ad or 10X matrix into an AnnData object and apply scanpy workflows for QC filtering, normalization, PCA/UMAP embeddings, and Leiden clustering to get processed single-cell data.

What is the best way to identify marker genes and perform differential expression in single-cell data?▼

Identifying marker genes in single-cell data involves running scanpy workflows on AnnData objects to rank genes per Leiden cluster, enabling differential expression analysis and cell-type annotation using marker gene expression.

Do I need an .h5ad file format to perform QC filtering and normalization for single-cell analysis?▼

Yes, you need AnnData-compatible inputs like an .h5ad file or a 10X matrix to perform QC filtering, normalization, and dimensionality reduction using scanpy preprocessing and visualization functions.

Can I generate publication-style UMAP and t-SNE plots directly from my 10X matrix?▼

Yes, you can generate publication-style UMAP and t-SNE plots from a 10X matrix by loading it as an AnnData object and applying scanpy plotting functions to visualize embeddings colored by clusters or marker genes.

Why does my single-cell analysis require highly variable gene selection before Leiden clustering?▼

Single-cell analysis requires highly variable gene selection and scaling before Leiden clustering to reduce noise and focus dimensionality reduction on biologically meaningful variance within the AnnData object.

Related Skills

Explore More Data & Analytics Skills→
zongtingweizongtingwei
25

scrna-preprocessing-clustering

Preprocess single-cell RNA-seq data into analysis-ready AnnData objects.

Community
Advanced
ovachieverovachiever
52

scanpy

Analyze scRNA-seq data with Scanpy workflows for QC through trajectory inference.

Community
Advanced
PharMolixPharMolix
1.1k

cellxgene-census-query

Query CZ CELLxGENE Census data by cell type, tissue, and disease.

Community
Advanced
Victory-HugoVictory-Hugo
1

scanpy

Perform end-to-end single-cell RNA-seq analysis with Scanpy.

Community
Intermediate