AI Blocks › Research a topic properly
CRISPR screen hit ranker
Give it guide read counts. Get quality checks and a ranked gene hit list with effect sizes.
CRISPR screen hit ranker is a free AI skill for the job "Research a topic properly". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · MIT licence · Made by K-Dense · Level: advanced
Made by K-Dense. See the original on GitHub; we copied it as it is, with its licence.
What it does
A quality-checked ranked list of genes from a pooled CRISPR screen, with effect sizes and false discovery rates. You see which genes truly rise or fall between conditions and whether the data can be trusted. You give it guide read counts or raw sequencing reads. The skill validates the guide library and the comparisons you want to make. It then measures replicate agreement and library quality before testing. MAGeCK runs the count and test steps for knockout, CRISPRi or CRISPRa screens, in enrichment or depletion contrasts. Output is a gene ranking with effect size and FDR. It needs command line tools and Python installed. Public dependency lookups belong in a different skill.
You give it
- Guide count matrix or FASTQ files
- Guide library file
- Sample groups and comparison
- MAGeCK installed
You get
- Library and replicate QC
- Ranked gene hit list
- Effect sizes and FDR
- Commands used
Use it when
- You finished a knockout screen and have a count table.
- You need to check replicate quality before trusting hits.
- You want to compare treated and control cells.
- You have raw reads and must produce counts first.
How to use it
- Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
- Ask for the job in your own words. Your AI opens the skill when it fits.
- It works best when your AI can run command line tools.