Does this skill include automated quality control?

Yes, it includes a dedicated QC script and workflow to automatically filter low-quality cells and genes based on mitochondrial content and count density.

How does this skill handle batch correction?

It provides built-in patterns for ComBat batch correction and provides guidance for integrating with external tools like Harmony or scVI.

What file formats does the Scanpy skill support?

The skill supports all standard single-cell formats including .h5ad (AnnData), 10X Genomics (MTX and H5), and CSV files.

Can I use this for trajectory inference?

Absolutely. The skill provides implementation patterns for PAGA (Partition-based graph abstraction) and diffusion pseudotime analysis.

Scanpy Single-Cell Analysis

Name: Scanpy Single-Cell Analysis
Author: pur3v4d3r

bypur3v4d3r

•

数据科学与机器学习

Analyzes single-cell RNA-seq data with standardized workflows for quality control, clustering, and cell type annotation.

关于

This skill provides a comprehensive environment for single-cell transcriptomics analysis using the Scanpy library and AnnData structure. It enables researchers and developers to process raw 10X or .h5ad data through end-to-end pipelines including quality control filtering, normalization, dimensionality reduction (PCA, UMAP), and Leiden clustering. By incorporating bioinformatics best practices, it streamlines the identification of marker genes, trajectory inference, and the creation of publication-quality visualizations within the Claude Code environment.

主要功能

Automated quality control and mitochondrial gene filtering
Leiden clustering and automated marker gene identification
Publication-quality plotting and visualization templates
Trajectory inference and pseudotime analysis using PAGA
1 GitHub stars
Advanced dimensionality reduction via PCA, UMAP, and t-SNE

使用场景

Performing differential expression analysis between experimental conditions
Processing raw 10X Genomics datasets into annotated cell-type clusters
Generating standardized QC reports and high-resolution genomic visualizations

关于

主要功能

Automated quality control and mitochondrial gene filtering
Leiden clustering and automated marker gene identification
Publication-quality plotting and visualization templates
Trajectory inference and pseudotime analysis using PAGA
1 GitHub stars
Advanced dimensionality reduction via PCA, UMAP, and t-SNE

使用场景

Performing differential expression analysis between experimental conditions
Processing raw 10X Genomics datasets into annotated cell-type clusters
Generating standardized QC reports and high-resolution genomic visualizations