Manage annotated data matrices with AnnData for single-cell genomics analysis.
npx skills add https://github.com/jackspace/ClaudeSkillz --skill anndata
Please help me install this Agent Skill. Skill: anndata Source: https://github.com/jackspace/ClaudeSkillz/tree/main/skills/scientific-pkg-anndata Command: npx skills add https://github.com/jackspace/ClaudeSkillz --skill anndata
AnnData provides a structured container for X, obs, var, and other components, enabling efficient storage, manipulation, and analysis of annotated data for single-cell genomics and beyond.
Create an AnnData object with a small X matrix and basic metadata, then subset by a condition.
High-intent search queries and answers about installing and using this skill.
AnnData is a structured container that stores annotated data matrices (X, obs, var, layers) for single-cell genomics. It enables efficient storage, manipulation, and analysis of large sparse matrices in Python, integrating seamlessly with scanpy and the scverse ecosystem for RNA-seq pipelines.
AnnData reads and writes h5ad, zarr, csv, and loom formats. The h5ad format is native and optimized for AnnData objects, while zarr enables backed mode for memory-efficient access to large datasets without loading everything into RAM.
Yes. AnnData supports filtering, slicing, transposing, and deriving metadata across observations and variables. You can subset by conditions on obs or var columns, enabling targeted analysis of cell populations or gene subsets in single-cell workflows.
AnnData handles large, sparse matrices efficiently through backed mode and memory-optimized data structures. Its comprehensive components (X, layers, obsm, varm, obsp, varp, uns) store expression data, embeddings, distances, and metadata without duplicating memory across formats.
Yes. AnnData is designed for scverse integration and is the standard object format for scanpy and related analysis tools. It enables end-to-end single-cell RNA-seq pipelines and multi-omics workflows within the scverse ecosystem.
Yes. AnnData supports concatenating objects to combine data from multiple samples or batches. This enables integration of large multi-omics datasets while preserving metadata in obs, var, and uns components.
anthropicsFilter low-quality cells from single-cell RNA-seq data using MAD-based QC.
jaechang-hitsAnalyze single-cell RNA-seq data with Scanpy from QC to marker identification.
awslabsProcess 10X Genomics single-cell RNA-seq data into annotated AnnData objects.
jaechang-hitsManage annotated data matrices for single-cell genomics in .h5ad and .zarr formats.
