skills.rest
HolobiomicsLab
HolobiomicsLabOFFICIAL
Explore all skills by this author →
WebsiteGitHub

anndata

Create and manage annotated data matrices for single-cell genomics workflows.

4|1|Updated Jun 18, 2025
Search Tags:#bioinformatics#data-analysis#single-cell#data-structure#anndata
One-click install
npx skills add https://github.com/HolobiomicsLab/Toolomics --skill anndata-holobiomicslab
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: anndata
Source: https://github.com/HolobiomicsLab/Toolomics/tree/main/mcp_host/skills/scientific-skills/scientific-skills/anndata
Command: npx skills add https://github.com/HolobiomicsLab/Toolomics --skill anndata-holobiomicslab

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

AnnData provides a robust data structure and tooling to store, manipulate, and persist annotated data matrices (X, obs, var, etc.) for single-cell genomics workflows, enabling scalable analysis and reproducible pipelines.

Core Features & Use Cases

  • Creation and storage of AnnData objects with X, obs, var, layers, obsm, varm, uns, and raw state.
  • I/O operations across H5AD, Zarr, and other formats, with support for backed mode to handle large datasets.
  • Integration with the Scanpy/Scverse ecosystem for preprocessing, analysis, and visualization.
  • Use case: build a reproducible single-cell analysis pipeline from raw counts to PCA/UMAP with batch correction.

Quick Start

Create or load an AnnData object, annotate it with obs/var metadata, and save the result to disk.

Frequently Asked Questions about anndata

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

FAQPage Schema
How do I store and manage annotated data matrices for single-cell genomics workflows?▼

You can create and manipulate annotated data matrices using the AnnData structure, which organizes biological datasets into core components like X, obs, var, and layers for reproducible analysis pipelines.

What is the best way to handle large biological datasets that exceed available memory?▼

Large biological datasets can be processed using backed storage mode with H5AD or Zarr formats, enabling manipulation of annotated data matrices without loading the entire dataset into memory.

Does this data structure support integration with the Scanpy ecosystem for preprocessing and analysis?▼

Yes, the annotated data matrix structure integrates directly with the Scanpy and Scverse ecosystem, supporting single-cell genomics preprocessing, analysis, visualization, and batch correction workflows.

How do I save and persist single-cell genomics data to disk?▼

Single-cell genomics data is persisted to disk through comprehensive I/O operations supporting H5AD and Zarr formats, ensuring your annotated data matrices and metadata are saved for reproducible pipelines.

What metadata components are supported when annotating biological data matrices?▼

Biological data matrices support core components including X, obs, var, layers, obsm, varm, obsp, varp, uns, and raw state, providing comprehensive metadata management for single-cell genomics analysis.

Can I build a reproducible single-cell analysis pipeline from raw counts to UMAP using this structure?▼

Yes, you can build a reproducible single-cell analysis pipeline from raw counts to PCA or UMAP with batch correction by managing your data, metadata, and transformations within this annotated matrix structure.

Related Skills

Explore More Data & Analytics Skills→
shushuznshushuzn
4

anndata

Store and manipulate annotated single-cell data matrices with observation and variable metadata.

Community
Advanced
Hung-3008Hung-3008
1

scanpy

Analyze single-cell RNA-seq data to produce QC metrics, embeddings, clusters, and marker genes.

Community
Advanced
tony-zhelonkintony-zhelonkin
1

scanpy

Run standard single-cell RNA-seq analysis with Scanpy on AnnData objects.

Community
Advanced
Lord1EgyptLord1Egypt
2

cellxgene-census

Query CZ CELLxGENE Census single-cell genomics data with metadata filters.

Community
Advanced