What is the AnnData Claude Code Skill used for?

It provides specialized guidance and implementation patterns for the AnnData Python library, which is the standard for storing and manipulating annotated data matrices in single-cell biology.

Can this skill help with large-scale genomic datasets?

Yes, it includes patterns for memory optimization, such as using disk-backed mode, sparse matrices, and chunked processing to handle data larger than RAM.

Which file formats are supported by this skill?

The skill provides patterns for working with .h5ad, .zarr, .loom, .mtx (10X format), and standard CSV files.

How does it handle metadata and embeddings?

It offers structured methods for managing cell-level (obs) and gene-level (var) metadata, as well as storing multi-dimensional embeddings like PCA, UMAP, and t-SNE in the obsm attribute.

AnnData Genomics Toolkit

Name: AnnData Genomics Toolkit
Author: lifangda

bylifangda

•

Data Science & ML

Manipulates and manages AnnData objects for single-cell genomics workflows, including scRNA-seq data processing and file management.

The AnnData skill provides specialized capabilities for Claude to handle the industry-standard Python format for annotated data matrices in single-cell genomics. It enables seamless creation, manipulation, and storage of complex biological datasets, covering critical tasks like metadata annotation (obs/var), layer management, and dimensionality reduction embeddings like PCA and UMAP. Designed for bioinformaticians and data scientists, this skill ensures best practices for memory-efficient subsetting, dataset concatenation, and high-performance file I/O using formats like .h5ad and .zarr.

Key Features

01Efficient creation of AnnData objects from sparse or dense matrices

02Memory-efficient data subsetting using optimized views and copies

03Robust file I/O support for .h5ad, .zarr, .loom, and 10X formats

04Advanced metadata management for cell (obs) and gene (var) annotations

05Complex dataset concatenation with custom join and merge strategies

0616 GitHub stars

Use Cases

01Integrating and batch-correcting multi-experimental genomic data

02Processing massive datasets using disk-backed mode and chunked operations

03Quality control and preprocessing of scRNA-seq datasets

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add lifangda/claude-plugins anndata

For use in Claude.ai and ChatGPT

Download Skill