anndata

Create and manipulate annotated matrices for single-cell analysis in H5AD format.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/Org-GAgent/result-interpreter --skill anndata-org-gagent
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: anndata
Source: https://github.com/Org-GAgent/result-interpreter/tree/main/.skills/scientific-skills/anndata
Command: npx skills add https://github.com/Org-GAgent/result-interpreter --skill anndata-org-gagent

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

AnnData provides a unified data container to store a dense or sparse expression matrix (X) alongside observation metadata (obs), variable metadata (var), and multi-dimensional annotations (obsm, varm, obsp, varp, uns) to support scalable single-cell experiments and beyond.

Core Features & Use Cases

  • Data structure: X, obs, var, layers, obsm, varm, obsp, varp, uns for rich annotations and flexible workflows.
  • I/O & interoperability: read/write across H5AD and related formats, with backed mode and memory-efficient options, enabling seamless integration with the scverse ecosystem (Scanpy, Muon, and friends).
  • Common workflows: construct, subset, concatenate, and manipulate AnnData objects for preprocessing, analysis, and visualization.

Quick Start

Install AnnData and load a sample h5ad to inspect X, obs, and var.

Frequently Asked Questions about anndata

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

FAQPage Schema
What is the best way to store annotated single-cell expression matrices with metadata?

AnnData provides a unified data container to store a dense or sparse expression matrix (X) alongside observation metadata (obs), variable metadata (var), and multi-dimensional annotations (obsm, varm, obsp, varp, uns) for scalable single-cell experiments.

How do I create and manipulate anndata objects for scRNA-seq analysis?

You can construct, subset, concatenate, and manipulate anndata objects using the core data model with X, obs, var, layers, obsm, varm, obsp, varp, and uns to support flexible preprocessing, analysis, and visualization workflows.

Can I read and write h5ad files in backed mode for memory-efficient single-cell analysis?

AnnData supports reading and writing across H5AD and Zarr formats with backed mode and memory-efficient options, enabling seamless integration with the scverse ecosystem like Scanpy for large-scale single-cell workflows.

Does anndata integrate with Scanpy and PyTorch for downstream single-cell workflows?

AnnData ensures compatibility with downstream tools like Scanpy and PyTorch within the scverse ecosystem, allowing seamless transitions from data preprocessing and manipulation to advanced visualization and modeling tasks.

What are the limitations of using anndata for multi-dimensional annotations?

While AnnData robustly manages multi-dimensional annotations (obsm, varm, obsp, varp) and handles memory via backed mode, its scope is strictly limited to organizing and validating data structures rather than performing statistical analysis.