AI Blocks › Research a topic properly
Single-cell RNA analysis pipeline
Give it single-cell counts. Get cleaned data, cell clusters, marker genes and plots from start to finish.
Single-cell RNA analysis pipeline 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: expert
Made by K-Dense. See the original on GitHub; we copied it as it is, with its licence.
What it does
Cleaned single-cell data, cell clusters, marker genes and plots, from raw counts to a finished analysis. You run one chain instead of stitching steps together. It uses Scanpy. It confirms the input holds raw counts, then runs quality control, normalisation, and picks highly variable genes. Next come PCA, UMAP or t-SNE and clustering. It ranks marker genes per cluster, and prepares sample-level sums for differential expression between conditions. Batch tools like Harmony or BBKNN are available. R objects must first be converted to h5ad. You need Python 3.12 or newer and Scanpy installed.
You give it
- Single-cell raw counts in h5ad or similar
- Python 3.12 or newer with Scanpy
- Sample and condition labels (optional)
- Species and tissue notes (optional)
You get
- Quality-controlled, normalised data
- Clusters and UMAP plots
- Marker gene lists
- Data prepared for condition comparison
Use it when
- You have a raw count matrix and want clusters and markers.
- You need a standard QC and normalisation run you can repeat.
- You want UMAP plots to share with your lab.
- You are preparing data for sample-level differential expression.
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 code.