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.
npx skills add https://github.com/mims-harvard/tooluniverse --skill tooluniverse-crispr-screen-analysis