Tooluniverse Crispr Screen Analysis

This handles the full CRISPR screen analysis pipeline, from sgRNA count matrices through gene-level scoring to pathway enrichment and drug target prioritization. It implements MAGeCK-like ranking and BAGEL-like Bayes Factor approaches, runs quality control on library distributions, and integrates with DepMap to filter out pan-essential housekeeping genes from your context-specific hits. The workflow is practical: it checks for pre-computed results first (executed notebooks, existing analysis scripts) before re-running from raw data, which matters because reanalysis can take 5-10x more turns. Built around ToolUniverse tools like Enrichr, DGIdb, and PubMed for hit validation. Most useful for essentiality screens, synthetic lethality discovery, and resistance mechanism studies where you need statistical rigor and biological context together.

skills.sh installs: 375
GitHub stars: 1.8K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add mims-harvard/tooluniverse --skill tooluniverse-crispr-screen-analysis --agent claude-code

Installs into .claude/skills of the current project.

Files

ToolUniverse CRISPR Screen Analysis

RULE ZERO — Check for pre-computed results FIRST

Before following any instruction below, scan the data folder for:

*_executed.ipynb → read with tu run read_executed_notebook '{"data_folder":"<path>","search":"<keyword>"}' and cite its cell outputs as the authoritative answer
Pre-computed result files (CSV/TSV with names like *results*, *deseq*, *enrich*, *stats*, *_simplified.csv) → read directly and report the requested value
Canonical analysis scripts (analysis.R, run_*.py, find_*.R, *.Rmd) → execute as-is and read the output

Only follow this skill's re-analysis recipe below if none of the above exist. Re-running from raw data produces different numbers than the published answer and is much slower (often 5-10× turn count).

Comprehensive skill for analyzing CRISPR-Cas9 genetic screens to identify essential genes, synthetic lethal interactions, and therapeutic targets through robust statistical analysis and pathway enrichment.