anndata

Store and manage annotated single-cell data in AnnData objects.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/must1f/Dissertaion-Project --skill anndata-must1f
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: anndata
Source: https://github.com/must1f/Dissertaion-Project/tree/main/.agents/skills/anndata
Command: npx skills add https://github.com/must1f/Dissertaion-Project --skill anndata-must1f

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

AnnData provides a compact, extensible data structure to store a gene expression matrix (X) plus rich annotations (obs, var, uns, layers, obsm, varm, obsp) in single-cell experiments, enabling integrated analysis workflows without data misalignment.

Core Features & Use Cases

  • Core data structure components: X, obs, var, layers, obsm, varm, obsp, uns, and raw for end-to-end single-cell analysis.
  • Interoperability and persistence: read/write to h5ad, integration with Scanpy, Muon, and the scverse ecosystem; concatenation, backends, and memory-efficient operations.
  • Use cases include building annotated datasets, batch integration previews, reproducible preprocessing pipelines, and scalable data management for large cohorts.

Quick Start

Install anndata and create a minimal AnnData object from a dense matrix with basic obs and var annotations.

Frequently Asked Questions about anndata

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

FAQPage Schema
How do I store single-cell RNA-seq data with annotations to prevent misalignment?

To store single-cell RNA-seq data and prevent misalignment, use the AnnData structure. It keeps the gene expression matrix and rich annotations like obs, var, and uns integrated within a single object for aligned analysis workflows.

What is the best way to manage large scRNA-seq cohorts without running out of memory?

The best way to manage large scRNA-seq cohorts is using AnnData's backed mode. This memory-efficient approach enables scalable data management by reading h5ad files directly from disk rather than loading everything into RAM.

Can I use AnnData objects with Scanpy and the scverse ecosystem?

Yes, you can use AnnData objects with Scanpy and the scverse ecosystem. AnnData is designed for interoperability, serving as the core data structure for creating, editing, and persisting objects across these specific analysis workflows.

How do I concatenate multiple single-cell datasets into one object?

You concatenate multiple single-cell datasets by using the built-in concatenation features of the AnnData structure. This merges multiple annotated single-cell objects while maintaining reproducible metadata handling across the combined dataset.

Does single-cell data management support reading and writing h5ad files?

Yes, single-cell data management with AnnData supports robust file I/O. You can easily read and write h5ad files to persist AnnData objects, ensuring your annotated gene expression matrices and metadata are saved reproducibly.

What components are needed to build an annotated single-cell dataset?

To build an annotated single-cell dataset, you need core components like X for the expression matrix, obs and var for annotations, layers for alternative matrices, plus obsm, varm, obsp, and uns for multidimensional and unstructured metadata.