scanpy

原文涵盖的主题

• Scanpy: Single-Cell Analysis
• Overview
• When to Use This Skill
• Quick Start
• Basic Import and Setup
• Loading Data
• Understanding AnnData Structure
• Standard Analysis Workflow

Scanpy is a scalable Python toolkit for analyzing single-cell RNA-seq data, built on AnnData. Apply this skill for complete single-cell workflows including quality control, normalization, dimensionality reduction, clustering, marker gene identification, visualization, and trajectory analysis. This skill should be used when: Analyzing single-cell RNA-seq data (.h5ad, 10X, CSV formats) Performing quality control on scRNA-seq datasets Creating UMAP, t-SNE, or PCA visualizations Identifying cell clusters and finding marker genes Annotating cell types based on gene expression Conducting trajectory inference or pseudotime analysis Generating publication-quality single-cell plots The AnnData object is the core data structure in scanpy: Identify and filter low-quality cells and genes: Use the QC script for automated analysis: Refer to references/plottingguide.md for comprehensive visualization examples. mingenes: Minimum genes per cell (typically 200-500) mincells: Minimum cells per gene (typically 3-10) pctcountsmt: Mitochondrial threshold (typically 5-20%) targetsum: Target counts per cell (default 1e4) ntopgenes: Number of HVGs (typically 2000-3000) minmean, maxmean, mindisp: HVG select

这里只展示节选，请以完整原文和当前要求为准。