Skip to content
Get packs

PyDESeq2 Differential Expression

Run bulk RNA-seq differential expression analysis with PyDESeq2 and validated statistical workflows

Source Download skill
Repository
K-Dense-AI/scientific-agent-skills
Stars
55,780
Licence
MIT
Files
6 files

What it does

Once installed, the agent follows a careful, statistics-aware workflow for finding genes that change between experimental groups in bulk RNA-seq data. It checks that count tables and sample metadata line up, fits a negative-binomial model with PyDESeq2, tests a specific comparison, and exports tables and optional volcano and MA plots. It also warns about common mistakes, such as treating single cells as independent replicates or using normalized values like TPM as model inputs.

Great for

  • Bioinformatics researchers who want a Python alternative to R DESeq2 for bulk RNA-seq
  • Students learning differential expression analysis who need guardrails on design and contrasts
  • Analysts who have raw integer counts and biological replicates and need reproducible outputs with a manifest

Skip it if

  • Single-cell per-cell testing, because cells from the same donor are not independent replicates and the skill says so explicitly
  • Clinical or diagnostic decisions without expert statistical review, since results depend on design choices and assumptions
  • Datasets with TPM, FPKM, log, or VST values as the only input, which the model does not accept as raw counts

Try asking

  • “Run a DESeq2 analysis comparing treated versus control samples with batch as a covariate, using counts.csv and metadata.csv”
  • “Set up a PyDESeq2 Wald test contrast for condition and export shrunken log2 fold changes plus a volcano plot”
  • “Check my count matrix and metadata for problems before fitting a differential expression model”
Step-by-step guide: how to use PyDESeq2 Differential ExpressionInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 6 original files, the MIT licence and an attribution note.

    pydeseq2.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip pydeseq2.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip pydeseq2.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Put raw integer counts in the correct orientation and use --no-transpose if your counts file is already samples by genes, since the driver defaults to genes by samples
  • Set the prespecified min-counts filter and alpha before running, and use a fresh output directory for each run
  • Use the Python API rather than the CLI for interaction terms, continuous effects, or thresholded tests, since the CLI does not expose them

What's inside

  • references/analysis_patterns.md
  • references/api_reference.md
  • references/core_workflow_steps.md
  • references/workflow_guide.md
  • scripts/run_deseq2_analysis.py
  • SKILL.md

Redistributed unmodified from K-Dense-AI/scientific-agent-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.