Pydeseq2

If you're doing differential expression analysis on bulk RNA-seq data in Python, this wraps the DESeq2 methodology into a pandas-friendly workflow. It handles the full pipeline from count normalization through Wald tests and FDR correction, with support for multi-factor designs when you need to control for batch effects or covariates. The workflow is straightforward: load your counts matrix and metadata, specify a design formula, run the fitting, then pull results with adjusted p-values. It includes optional apeGLM shrinkage for cleaner fold change estimates in visualizations. Good fit if you're migrating R-based DESeq2 workflows to Python or building RNA-seq pipelines that need to stay in the Python ecosystem.

skills.sh installs: 2K
GitHub stars: 56.6K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add k-dense-ai/scientific-agent-skills --skill pydeseq2 --agent claude-code

Installs into .claude/skills of the current project.

Files

PyDESeq2

Use this skill for bulk RNA-seq negative-binomial GLMs, with explicit biological replicates, covariates, and comparisons. Cells, sequencing lanes, and repeated measurements from the same donor are not independent biological replicates. Donor-level pseudobulk can be appropriate when its aggregation and design match the scientific question; this is not a single-cell per-cell testing workflow.

Current PyDESeq2 0.5.4 provides Wald tests and apeGLM-style coefficient shrinkage. Do not assume every feature or numerical result of current R DESeq2 is implemented identically. See API and tested versions for supported calls, AnnData storage, and source/runtime verification limits.