anndata

Create, read, and write AnnData objects with backed storage for large single-cell datasets.

15|2|Updated Dec 17, 2025
One-click install
npx skills add https://github.com/rubensliv/k-dense-ai --skill anndata-rubensliv
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: anndata
Source: https://github.com/rubensliv/k-dense-ai/tree/main/scientific-skills/anndata
Command: npx skills add https://github.com/rubensliv/k-dense-ai --skill anndata-rubensliv

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

AnnData provides a scalable, structured container for annotated data matrices used in single-cell genomics, enabling efficient storage, retrieval, and manipulation of X, obs, var, and multi-dimensional annotations.

Core Features & Use Cases

  • Create, read, and write AnnData objects to manage large, sparse datasets with backed storage for memory efficiency.
  • Subset, filter, concatenate, and transform data while preserving metadata and embeddings; integrate with Scanpy/scverse for end-to-end workflows.
  • Use cases include preparing scRNA-seq data, performing QC and normalization, and building reproducible pipelines across experiments.

Quick Start

Create an AnnData object from a small matrix with basic obs/var metadata and run a quick quality control check.

Frequently Asked Questions about anndata

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

FAQPage Schema
How do I manage large single-cell data matrices in Python when memory is limited?

AnnData provides backed storage for large single-cell data matrices, enabling memory-efficient reading, writing, and manipulation of datasets without loading them entirely into memory.

Can I subset and filter scRNA-seq data while preserving metadata and embeddings?

You can subset, filter, and concatenate scRNA-seq data while preserving multi-dimensional annotations like obs, var, and embeddings, ensuring metadata stays intact during transformations.

How does annotated data integrate with Scanpy and the PyData ecosystem?

AnnData objects integrate seamlessly with Scanpy and the scverse ecosystem, supporting end-to-end workflows from data preparation and QC to normalization and reproducible pipeline building.

What is the structure of an AnnData object for single-cell genomics?

An AnnData object structures single-cell genomics data using core components: X for the data matrix, obs and var for annotations, layers for alternative representations, and uns for unstructured metadata.

What's the best way to prepare scRNA-seq data for quality control and normalization?

The best way to prepare scRNA-seq data is creating an AnnData object to structure the matrix and metadata, then applying quality control and normalization steps integrated directly within Scanpy workflows.

Does backed storage in AnnData support diverse I/O formats for large datasets?

Backed storage supports diverse I/O formats for large datasets, allowing efficient reading and writing of annotated data matrices while maintaining compatibility with the broader PyData ecosystem.