What file formats does the Scanpy skill support?

The skill supports standard single-cell formats including .h5ad (AnnData), 10X Genomics (mtx and h5), and CSV files.

Can this skill help with cell type annotation?

Yes, it identifies marker genes for clusters and provide tools for mapping clusters to specific cell types based on known biological markers.

Can I generate figures for scientific publications?

Absolutely. The skill includes specialized workflows for creating high-resolution UMAPs, heatmaps, and dot plots tailored for scientific manuscripts.

Is batch correction included in this skill?

Yes, it supports standard batch correction methods like ComBat to mitigate technical variations across different experiments.

Scanpy Single-Cell Analysis

Name: Scanpy Single-Cell Analysis
Author: jimmc414

byjimmc414

•

324

Data Science & ML

Performs comprehensive single-cell RNA-seq data analysis, including quality control, clustering, and visualization.

About

This skill equips Claude with the capabilities of Scanpy, a scalable Python toolkit for analyzing single-cell gene expression data. It enables automated workflows for loading 10X or h5ad data, performing rigorous quality control, normalizing datasets, and executing advanced dimensionality reduction techniques like UMAP and t-SNE. Built for bioinformaticians and researchers, the skill facilitates cell type annotation, marker gene identification, and trajectory inference, streamlining the entire discovery process from raw counts to publication-ready insights.

Key Features

Leiden clustering and marker gene identification
Generation of publication-quality visualizations and plots
324 GitHub stars
Trajectory inference and pseudotime analysis using PAGA
Automated QC and filtering for single-cell datasets
Advanced dimensionality reduction via PCA, UMAP, and t-SNE

Use Cases

Executing standardized bioinformatics pipelines for scRNA-seq discovery
Comparing gene expression profiles between treated and control samples
Analyzing 10X Genomics datasets to identify and annotate cell populations

About

Key Features

Leiden clustering and marker gene identification
Generation of publication-quality visualizations and plots
324 GitHub stars
Trajectory inference and pseudotime analysis using PAGA
Automated QC and filtering for single-cell datasets
Advanced dimensionality reduction via PCA, UMAP, and t-SNE

Use Cases

Executing standardized bioinformatics pipelines for scRNA-seq discovery
Comparing gene expression profiles between treated and control samples
Analyzing 10X Genomics datasets to identify and annotate cell populations