Is there a template to start a new analysis?

Yes, the skill includes an analysis_template.py script that provides a complete end-to-end workflow from data loading to annotation.

Which clustering algorithms are recommended?

The skill primarily utilizes the Leiden algorithm for clustering due to its efficiency and biological relevance, though it also supports Louvain.

What file formats does the Scanpy skill support?

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

Does it support publication-quality plotting?

Absolutely. It includes a comprehensive plotting guide for creating high-DPI PDFs, heatmaps, and customized UMAP visualizations.

Can this skill help with batch effect correction?

Yes, it provides guidance and code for ComBat batch correction and integration with other tools like Harmony or scVI.

Scanpy Single-Cell Analysis

Name: Scanpy Single-Cell Analysis
Author: Microck

byMicrock

•

数据科学与机器学习

Performs comprehensive single-cell RNA-seq analysis including quality control, clustering, and cell type annotation using the Scanpy framework.

关于

This skill equips Claude with specialized knowledge and workflows for Scanpy, the industry-standard Python toolkit for single-cell genomics. It enables automated quality control, normalization, dimensionality reduction (PCA/UMAP), and sophisticated clustering using the Leiden algorithm. Users can leverage this skill to identify marker genes, annotate cell types, and perform trajectory inference, while generating publication-quality visualizations for complex biological datasets. It includes bundled templates and scripts to accelerate bioinformatics research from raw data to biological insight.

主要功能

Marker gene identification and automated cell type annotation workflows
Generation of publication-ready figures, heatmaps, and dot plots
Trajectory inference and pseudotime analysis using PAGA and DPT
81 GitHub stars
Advanced dimensionality reduction including UMAP, t-SNE, and PCA visualization
Automated quality control and mitochondrial gene filtering for scRNA-seq data

使用场景

Investigating cellular differentiation paths and lineages through trajectory analysis
Analyzing 10X Genomics or .h5ad single-cell transcriptomics datasets
Identifying distinct cell populations and their biological markers in complex tissues

关于

主要功能

Marker gene identification and automated cell type annotation workflows
Generation of publication-ready figures, heatmaps, and dot plots
Trajectory inference and pseudotime analysis using PAGA and DPT
81 GitHub stars
Advanced dimensionality reduction including UMAP, t-SNE, and PCA visualization
Automated quality control and mitochondrial gene filtering for scRNA-seq data

使用场景

Investigating cellular differentiation paths and lineages through trajectory analysis
Analyzing 10X Genomics or .h5ad single-cell transcriptomics datasets
Identifying distinct cell populations and their biological markers in complex tissues