scanpy-complete

What problem does it solve?

This Skill provides a comprehensive, ready-to-use reference and workflow guide for Scanpy, enabling users to perform end-to-end single-cell analysis from preprocessing to visualization with minimal setup.

Core Features & Use Cases

• End-to-end Scanpy coverage: Preprocessing, normalization, dimensionality reduction, clustering, trajectory inference, and differential expression analysis across AnnData workflows.
• Workflow guidance: Step-by-step pipelines for common tasks including pbmc-like analyses and spatial transcriptomics or multi-omics integration.
• Publication-ready examples: Rich tutorials and code snippets to recreate analyses and produce high-quality figures.

Quick Start

Install Scanpy and load a sample dataset, then run a minimal pipeline:

• pip install scanpy
• adata = sc.datasets.pbmc3k()
• sc.pp.filter_cells(adata, min_genes=200)
• sc.pp.filter_genes(adata, min_cells=3)
• sc.pp.normalize_total(adata, target_sum=1e4)
• sc.pp.log1p(adata)
• sc.tl.pca(adata)
• sc.pp.neighbors(adata)
• sc.tl.umap(adata)
• sc.tl.leiden(adata)