Manage annotated data matrices in h5ad and zarr formats.
npx skills add https://github.com/Sologa/codex-pipeline --skill anndata-sologa
Please help me install this Agent Skill. Skill: anndata Source: https://github.com/Sologa/codex-pipeline/tree/main/.codex/skills/anndata Command: npx skills add https://github.com/Sologa/codex-pipeline --skill anndata-sologa
This Skill provides a standardized way to handle large, annotated data matrices common in single-cell genomics and other scientific fields, simplifying data storage, manipulation, and analysis.
Load the 'my_data.h5ad' file into an AnnData object for analysis.
High-intent search queries and answers about installing and using this skill.
You can manage annotated data matrices by storing expression matrices alongside observation and variable metadata, enabling efficient subsetting, filtering, and transformation for single-cell genomics analysis.
Reading and writing large h5ad files is supported through efficient I/O operations, including a backed mode that allows you to process large datasets without loading them entirely into memory.
Yes, you can perform complex data manipulation such as subsetting, filtering, concatenation, and transformation of observation and variable annotations within the unified data structure.
Yes, zarr format is fully supported for both reading and writing annotated data matrices, providing an alternative to h5ad for flexible storage and access.
The standard data structure stores count matrices in an X layer alongside observation (obs) and variable (var) metadata, simplifying normalization, dimensionality reduction, and clustering tasks.
gexijinIdentify differential expression in bulk RNA-seq count matrices using DESeq2.
tondevrelTrain classification, regression, and clustering models with scikit-learn.
jackspaceGenerate unsupervised embeddings for genomic intervals from BED files.
seb1nPerform systematic exploratory data analysis on tabular datasets with pandas and ydata-profiling.
