scverse

What problem does it solve?

Single-cell RNA-seq analysis is intricate, requiring coordinated steps across data structures, preprocessing, and visualization. This skill provides pattern-based workflows using AnnData and Scanpy to simplify building reproducible pipelines for QC, normalization, dimensionality reduction, clustering, and visualization.

Core Features & Use Cases

• Pattern-based workflows for common scRNA-seq analyses using AnnData and Scanpy.
• Standard preprocessing pipelines including QC metrics, normalization, HVG selection, and scaling.
• Dimensionality reduction and clustering workflows (PCA, UMAP, Leiden/Louvain) with visualization guidance.
• I/O patterns for reading/writing .h5ad data and applying scalable workflows to real datasets.

Quick Start

Load a sample AnnData object and apply the standard scverse workflow: QC metrics, filtering, normalization, HVG identification, PCA, neighbor graph construction, and clustering with Leiden, followed by visualization with UMAP.