Store and manage annotated single-cell data matrices with metadata.
npx skills add https://github.com/fuzzy-dynamics/strings --skill anndata-fuzzy-dynamics
Please help me install this Agent Skill. Skill: anndata Source: https://github.com/fuzzy-dynamics/strings/tree/main/packages/skills/anndata Command: npx skills add https://github.com/fuzzy-dynamics/strings --skill anndata-fuzzy-dynamics
AnnData provides a unified, memory-efficient container for large, annotated matrices typical in single-cell genomics, simplifying management of data (X) and rich metadata (obs, var, layers, obsm, varm, obsp, uns) in a single object.
Load a dataset, subset cells and genes, and save the result as an H5AD file.
High-intent search queries and answers about installing and using this skill.
AnnData stores large single-cell data matrices (X) with rich metadata like obs, var, layers, and embeddings in a single unified object. This simplifies managing per-observation and per-variable annotations for end-to-end analysis workflows.
You can analyze single-cell datasets larger than memory using backed storage mode. AnnData supports H5AD and Zarr formats, enabling memory-efficient handling of large annotated data matrices without loading everything into RAM.
AnnData interoperates directly with Scanpy, Muon, and other scverse tools. This ecosystem integration supports end-to-end single-cell analysis workflows, including loading, subsetting, normalizing, and computing embeddings.
The best way to manage multiple data layers and embeddings is using the AnnData structured object model. It stores the main data matrix alongside multi-component annotations like obsm, varm, obsp, and uns, ensuring data integrity and reproducibility.
You can load and save annotated single-cell data using H5AD and Zarr file formats. AnnData supports flexible I/O for these formats, allowing you to save processed data efficiently for downstream analysis workflows.
You need backed storage when your single-cell data matrices exceed available memory. AnnData's backed mode handles datasets larger than RAM by reading data on demand from disk, ensuring scalable analysis without memory constraints.
StarlitnightlyPreprocess TCGA bulk data into annotated AnnData objects with expression and clinical metadata.
jaechang-hitsManage annotated data matrices for single-cell genomics in .h5ad and .zarr formats.
CHENyiru3Organize annotated single-cell data matrices using the AnnData structure.
Lord1EgyptManage annotated data matrices with observation and variable metadata.
