What problem does it solve?
This Skill provides a standardized way to handle annotated data matrices, crucial for complex biological datasets, by offering efficient storage, manipulation, and integration with specialized analysis tools.
Core Features & Use Cases
- Data Structure: Handles annotated matrices (X, obs, var, layers, obsm, etc.) for large-scale biological data.
- I/O Operations: Reads and writes data in various formats (h5ad, zarr, CSV, etc.), supporting large datasets with backed mode.
- Integration: Seamlessly works with the scverse ecosystem (Scanpy, Muon, scvi-tools).
- Use Case: Analyze single-cell RNA sequencing data by loading an
.h5ad file, performing quality control filtering, normalizing counts, and computing PCA and UMAP embeddings using Scanpy.
Quick Start
Load the AnnData object from the file 'my_data.h5ad' and print its shape.