anndata

Create, read, write, and manipulate AnnData objects for single-cell genomics.

52|6|Updated Nov 24, 2025
One-click install
npx skills add https://github.com/ovachiever/droid-tings --skill anndata-ovachiever
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: anndata
Source: https://github.com/ovachiever/droid-tings/tree/main/skills/anndata
Command: npx skills add https://github.com/ovachiever/droid-tings --skill anndata-ovachiever

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires anndata, pandas, numpy, and includes references (resource) components.

What problem does it solve?

AnnData provides a robust data structure to store biological measurements, annotations, and multi-dimensional data, enabling scalable analysis workflows with Scanpy and the broader scverse ecosystem.

Core Features & Use Cases

  • Core data container for omics datasets (X, obs, var, layers, obsm, uns)
  • Backed mode, sparse matrices, and memory-efficient operations
  • Subsetting, concatenation, and merging of multiple datasets
  • Integration with Scanpy, Muon, and deep learning pipelines
  • Flexible I/O across H5AD, Zarr, MTX, Loom, and more

Use cases include single-cell analysis, multi-omics integration, and large-scale dataset management.

Quick Start

Build a minimal AnnData object with X, obs, and var, then save to h5ad.

Frequently Asked Questions about anndata

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

FAQPage Schema
How do I create and store annotated data matrices for single-cell genomics analysis?

AnnData is a data structure that stores biological measurements (X matrix), cell annotations (obs), gene metadata (var), and multi-dimensional data in a single object, then saves to h5ad format for efficient single-cell analysis workflows.

Can I work with large single-cell datasets without loading everything into memory?

Yes. AnnData supports backed mode for memory-efficient operations on large h5ad files, sparse matrices, and lazy loading, enabling scalable analysis of multi-omics data without exhausting RAM.

What file formats does AnnData support for reading and writing genomics data?

AnnData handles h5ad, zarr, CSV, MTX, Loom, and 10X formats, allowing flexible I/O across common single-cell and multi-omics data sources.

How do I combine multiple annotated datasets or subset specific cells and genes?

AnnData provides subsetting, concatenation, and merging operations to combine datasets or extract cell and gene subsets while preserving annotations and multi-dimensional layers.

Does AnnData integrate with Scanpy and other tools in the scverse ecosystem?

Yes. AnnData is the core container for Scanpy, Muon, and scverse tools, enabling seamless integration with single-cell analysis pipelines and deep learning frameworks.