Can I use this for trajectory inference?

Yes, the skill provides specific workflows for PAGA (Partition-based graph abstraction) and diffusion pseudotime analysis.

Is the visualization customizable for publications?

Absolutely. The skill includes a dedicated plotting guide and high-resolution settings for generating frame-free PDF plots suitable for scientific journals.

How does it handle batch effects?

It includes guidance for ComBat batch correction and provides references for integrating with other tools like Harmony or scVI.

What file formats does this Scanpy skill support?

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

Scanpy Single-Cell Analysis

Name: Scanpy Single-Cell Analysis
Author: x-cmd

byx-cmd

•

Ciencia de Datos y ML

Performs comprehensive single-cell RNA-seq analysis workflows including quality control, clustering, and cell type annotation.

Acerca de

Scanpy is a specialized Python-based toolkit designed for large-scale single-cell RNA-seq data analysis built on the AnnData structure. This skill enables Claude to guide users through the entire bioinformatics pipeline, from loading 10X Genomics or h5ad data to performing quality control, dimensionality reduction via UMAP or t-SNE, and identifying marker genes for cell type annotation. It provides pre-configured scripts for automated QC and publication-quality visualizations, making it an essential resource for bioinformaticians and researchers needing robust, reproducible analysis patterns.

Características Principales

End-to-end scRNA-seq workflows from raw data to cell annotation
Cluster identification using Leiden and Louvain algorithms
Advanced dimensionality reduction using PCA, UMAP, and t-SNE
Automated quality control and filtering with mitochondrial gene detection
8 GitHub stars
Publication-ready visualization tools for heatmaps, dot plots, and trajectories

Casos de Uso

Performing trajectory inference to study cell differentiation and pseudotime
Analyzing 10X Genomics data to identify distinct cell populations
Generating high-quality figures for bioinformatics publications and reports

Acerca de

Características Principales

End-to-end scRNA-seq workflows from raw data to cell annotation
Cluster identification using Leiden and Louvain algorithms
Advanced dimensionality reduction using PCA, UMAP, and t-SNE
Automated quality control and filtering with mitochondrial gene detection
8 GitHub stars
Publication-ready visualization tools for heatmaps, dot plots, and trajectories

Casos de Uso

Performing trajectory inference to study cell differentiation and pseudotime
Analyzing 10X Genomics data to identify distinct cell populations
Generating high-quality figures for bioinformatics publications and reports