What data formats are compatible with this skill?

The skill supports standard bioinformatics formats including 10X Genomics (.mtx, .h5), AnnData (.h5ad), and standard CSV/Tab-separated files.

Does this skill help with batch effect correction?

It provides implementation patterns for ComBat batch correction and guidance on integrating with other scverse tools like Harmony or scVI.

Can I generate figures for academic publications?

Yes, the skill includes optimized settings for high-resolution (300 DPI) plotting and supports exporting figures in vector formats like PDF for professional use.

How does it handle large datasets?

Scanpy is designed for scalability and memory efficiency using sparse matrices, allowing this skill to handle datasets ranging from a few thousand to hundreds of thousands of cells.

Scanpy Single-Cell Analysis

Name: Scanpy Single-Cell Analysis
Author: lifangda

bylifangda

•

データサイエンスとML

Performs comprehensive single-cell RNA-seq data analysis and visualization using the Scanpy Python framework.

概要

This skill provides a specialized bioinformatics workflow for analyzing single-cell RNA sequencing data within your development environment. Built on the scalable Scanpy toolkit and AnnData structure, it streamlines the entire analytical pipeline from raw data ingestion to advanced biological interpretation. It enables researchers to perform rigorous quality control, normalization, dimensionality reduction, and clustering while providing the tools necessary for marker gene identification and trajectory inference, ensuring reproducible and publication-quality results.

主な機能

End-to-end scRNA-seq pipeline including QC, normalization, and scaling
Advanced dimensionality reduction using PCA, UMAP, and t-SNE
Trajectory inference and pseudotime analysis with PAGA and DPT
Automated marker gene identification and cell type annotation support
Publication-ready visualization templates for heatmaps, dot plots, and UMAPs
16 GitHub stars

ユースケース

Modeling developmental lineages and cellular transitions through trajectory inference
Identifying distinct cell populations and their specific marker genes in complex tissues
Analyzing large-scale transcriptomics datasets from 10X Genomics or H5AD files

概要

主な機能

End-to-end scRNA-seq pipeline including QC, normalization, and scaling
Advanced dimensionality reduction using PCA, UMAP, and t-SNE
Trajectory inference and pseudotime analysis with PAGA and DPT
Automated marker gene identification and cell type annotation support
Publication-ready visualization templates for heatmaps, dot plots, and UMAPs
16 GitHub stars

ユースケース

Modeling developmental lineages and cellular transitions through trajectory inference
Identifying distinct cell populations and their specific marker genes in complex tissues
Analyzing large-scale transcriptomics datasets from 10X Genomics or H5AD files