Skip to content
Get packs

Pathway Enrichment Analysis

Run and interpret over-representation and GSEA pathway analyses on gene lists

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 can take a list of genes (for example, genes that changed in an experiment) and work out which biological pathways or gene sets they overlap more than chance would predict. It knows when to use a thresholded-list method (over-representation) versus a ranked-list method (GSEA), how to choose a background gene universe, how to correct for multiple testing, and how to avoid common interpretation mistakes. It can also run a bundled Python script that performs these analyses locally or via the public Enrichr service.

Great for

  • Bioinformaticians who have differentially expressed, screen-hit or cluster-marker gene lists and need a defensible enrichment workflow
  • Students learning how GO, KEGG or Reactome enrichment is done and why method choice matters
  • Researchers preparing publication-ready enrichment tables or dotplots

Skip it if

  • Quick single-gene or simple Enrichr lookups, where a lighter tool is enough; the skill itself points to the gget skill for these
  • Clinical or diagnostic decisions, since the outputs are exploratory research statistics and the skill does not validate them for medical use
  • Non-gene data or organisms whose identifiers do not match the chosen gene-set library, because the skill performs no identifier conversion or orthology mapping and results would be wrong

Try asking

  • “Run GO and Reactome enrichment on this list of 300 differentially expressed genes, using the tested genes as background”
  • “Do a preranked GSEA on my DESeq2 results file using the stat column and Hallmark gene sets”
  • “Which pathways are my CRISPR screen hits enriched in? Give me a publication-ready table”
  • “Explain why my enrichment results changed when I switched the background universe”
Step-by-step guide: how to use Pathway Enrichment AnalysisInstall, 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.

    pathway-enrichment.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

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

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip pathway-enrichment.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

  • Give the agent your full tested-gene list as the background; the default all-genes universe often inflates significance
  • Match gene identifiers (for example, human symbols) to the chosen gene-set library before running, since no automatic conversion is done
  • Ask for ranked GSEA on a statistic like DESeq2 stat rather than thresholding first, and set a seed for reproducible p-values

What's inside

  • references/databases-and-gene-sets.md
  • references/gseapy.md
  • references/interpretation.md
  • references/verified-api.md
  • scripts/run_enrichment.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.