anndata

Manage annotated data matrices for single-cell genomics analysis.

Updated Mar 10, 2026

Search Tags:#data structure #data management #anndata #h5ad #zarr #single-cell genomics

Ready to run

npx skills add https://github.com/felixboehm/biochem-allergy --skill anndata-felixboehm

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: anndata
Source: https://github.com/felixboehm/biochem-allergy/tree/main/.claude/skills/anndata
Command: npx skills add https://github.com/felixboehm/biochem-allergy --skill anndata-felixboehm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a robust framework for handling annotated data matrices, essential for complex data analysis, particularly in single-cell genomics.

Core Features & Use Cases

Data Structure: Efficiently store and manipulate large datasets with associated metadata (observations, variables, layers, embeddings).
Input/Output: Read and write data in various formats (h5ad, zarr, CSV, MTX, etc.) with support for large files and cloud storage.
Concatenation: Combine multiple datasets with flexible join strategies and metadata merging.
Use Case: Analyze single-cell RNA sequencing data by loading count matrices, performing normalization, dimensionality reduction (PCA, UMAP), clustering, and visualization, all while managing cell and gene annotations.

Quick Start

Use the anndata skill to read the file 'my_data.h5ad' and print its shape.

Frequently Asked Questions about anndata

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

FAQPage Schema

How do I manage large annotated data matrices for single-cell genomics analysis?▼

To manage large annotated data matrices for single-cell genomics, use a framework that efficiently stores observations, variables, layers, and embeddings. This approach handles associated metadata and sparse matrices, enabling smooth normalization and downstream visualization workflows.

What is the best way to read and write single-cell RNA sequencing data across different formats?▼

The best way to read and write single-cell RNA sequencing data is using a framework that supports multiple formats like h5ad, zarr, CSV, and MTX. This ensures efficient input/output operations, even when handling large files or accessing data directly from cloud storage.

Can I concatenate multiple single-cell datasets while preserving cell and gene annotations?▼

Yes, you can concatenate multiple single-cell datasets while preserving cell and gene annotations. The framework combines data using flexible join strategies and merges metadata, allowing you to integrate diverse count matrices without losing underlying biological context.

Does this data management approach work with sparse matrices and tools like Scanpy?▼

Yes, this data management approach works with sparse matrices and integrates directly with tools like Scanpy. It requires efficient handling of large datasets, allowing you to perform dimensionality reduction and clustering on sparse single-cell count matrices.

Why do I need an annotated data matrix structure for complex data analysis?▼

You need an annotated data matrix structure for complex data analysis to efficiently store and manipulate large datasets with associated metadata. This structure keeps observations, variables, and embeddings aligned during normalization, dimensionality reduction, and clustering.

What are the limitations when handling extremely large h5ad or zarr files?▼

When handling extremely large h5ad or zarr files, limitations can arise from memory constraints during data loading and concatenation. Efficient handling of large datasets requires careful management of sparse matrices and may depend on cloud storage capabilities.