anndata

Create and manipulate annotated single-cell omics data matrices in Python.

18|1|Updated Dec 27, 2025
One-click install
npx skills add https://github.com/LogauaEngstrom/claude-scientific-skills --skill anndata-logauaengstrom
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: anndata
Source: https://github.com/LogauaEngstrom/claude-scientific-skills/tree/main/scientific-skills/anndata
Command: npx skills add https://github.com/LogauaEngstrom/claude-scientific-skills --skill anndata-logauaengstrom

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

AnnData-based workflows simplify managing annotated data matrices for single-cell omics in Python.

Core Features & Use Cases

  • Create and load AnnData objects with core components (X, obs, var, layers, obsm, varm, obsp, varp, uns)
  • Perform subsetting, QC, normalization, and integration within the Scanpy/scverse ecosystem
  • Efficient handling of large datasets with backed mode and diverse I/O formats

Quick Start

Create a minimal AnnData object from a small matrix, add basic obs/var metadata, and perform a quick normalization workflow.

Frequently Asked Questions about anndata

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

FAQPage Schema
How do I manage annotated data matrices for single-cell omics in Python?

Annotated data matrices are managed in Python using the AnnData object structure, which stores observations and variables alongside layers and embeddings for single-cell omics analysis.

What is the standard structure for storing single-cell data in the Scanpy ecosystem?

The standard structure for single-cell data uses X, obs, var, layers, obsm, varm, obsp, varp, and uns to store data matrices, annotations, and embeddings within the Scanpy ecosystem.

How do I create and load annotated data objects with obs and var metadata?

Create and load annotated data objects by initializing the structure with a data matrix, then adding observation (obs) and variable (var) metadata for single-cell analysis.

Can I handle large single-cell datasets efficiently without loading everything into memory?

Large single-cell datasets can be handled efficiently using backed mode, which processes annotated data matrices without loading the entire dataset into memory.

Does AnnData support diverse I/O formats for single-cell data integration?

AnnData supports diverse I/O formats, allowing single-cell data to be loaded, saved, and integrated across various file types within the scverse ecosystem.

What is the best way to perform subsetting and normalization on single-cell data?

Subsetting and normalization on single-cell data are performed by manipulating the standardized AnnData object, applying quality control and transformations within the Scanpy workflow.