anndata

Organize annotated single-cell data with a flexible AnnData structure.

321|26|Updated Mar 10, 2026
One-click install
npx skills add https://github.com/mkurman/tamux --skill anndata-mkurman
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: anndata
Source: https://github.com/mkurman/tamux/tree/main/skills/scientific-skills/anndata
Command: npx skills add https://github.com/mkurman/tamux --skill anndata-mkurman

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

AnnData provides a flexible, memory-efficient framework for storing a data matrix X alongside rich metadata (obs, var, layers, obsm, varm, uns) to support scalable single-cell analysis workflows.

Core Features & Use Cases

  • Data model: X with aligned annotations (obs, var, layers, obsm, varm, uns, and raw) for end-to-end single-cell analyses.
  • Interoperability: built-in compatibility with Scanpy, Muon, and the broader scverse ecosystem for preprocessing, visualization, and modeling.
  • I/O and scalability: efficient reading/writing of dense and sparse data (h5ad, zarr, MTX, CSV) with backed mode to handle datasets larger than memory.

Quick Start

Create an AnnData object from a small dataset, then progressively attach metadata and embeddings, and persist to disk.

Frequently Asked Questions about anndata

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I store scRNA-seq data matrices with rich metadata in a single structure?

AnnData organizes scRNA-seq data matrices alongside aligned annotations like obs, var, layers, and uns, providing a memory-efficient framework for single-cell analysis workflows.

Can I use backed mode to process single-cell datasets larger than memory?

Backed mode enables handling large-scale single-cell datasets larger than memory by efficiently reading and writing dense or sparse data formats like h5ad and zarr.

Does the AnnData structure work with Scanpy and the scverse ecosystem?

AnnData offers built-in interoperability with Scanpy, Muon, and the broader scverse ecosystem, supporting preprocessing, visualization, and modeling for scRNA-seq workflows.

What is the best way to construct and filter annotated matrices for omics data?

Constructing and filtering annotated matrices for omics data uses a flexible structure with core components X, obs, and var, allowing progressive attachment of metadata and embeddings.

What file formats are supported for reading and writing single-cell data?

Supported I/O formats for single-cell data include h5ad, zarr, MTX, and CSV, accommodating both dense and sparse data structures for scalable analysis.

Why use a dedicated data structure for single-cell omics instead of a standard dataframe?

A dedicated single-cell structure aligns a data matrix X with multi-dimensional metadata like obsm and varm, which standard dataframes cannot natively support for omics workflows.