sc-marker-extractor

Extract per-cluster marker genes from scRNA-seq h5ad data into JSON.

Updated Mar 30, 2026

Search Tags:#differential-expression #json-output #cluster-analysis #scrna-seq #marker-genes #cell-type-annotation

Ready to run

npx skills add https://github.com/ya-way/cytoclaw-skills --skill sc-marker-extractor

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: sc-marker-extractor
Source: https://github.com/ya-way/cytoclaw-skills/tree/main/workspace/skills/sc-marker-extractor
Command: npx skills add https://github.com/ya-way/cytoclaw-skills --skill sc-marker-extractor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires numpy, pandas, scanpy, and includes scripts (resource) components.

What problem does it solve?

Extract cluster-level differential expression markers from clustered scRNA-seq data and return a machine-friendly JSON object for downstream interpretation and automation.

Core Features & Use Cases

Per-cluster marker computation: computes differential markers for each cluster (Wilcoxon rank-sum) and outputs top markers per cluster.
Structured JSON output: returns a JSON mapping of cluster IDs to ordered marker gene lists for easy programmatic consumption.
Use case: annotate cell types or compare cluster markers across multiple scRNA-seq experiments.

Quick Start

Run the script with your clustered h5ad data to produce a markers.json file containing top markers per cluster.

Frequently Asked Questions about sc-marker-extractor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract marker genes from clustered scRNA-seq data for cell type annotation?▼

Cluster marker genes are computed by running a Wilcoxon rank-sum test across clusters in your scRNA-seq dataset to identify differentially expressed genes. This extracts per-cluster marker genes and outputs a machine-friendly JSON mapping of cluster IDs to ordered gene lists for cell type annotation.

What's the best way to output scRNA-seq differential expression results as a JSON file?▼

The best way to output scRNA-seq differential expression results as JSON is to use a script that computes per-cluster markers and serializes the results. This generates a markers.json file mapping cluster IDs to ordered marker gene lists for downstream automation and interpretation.

Do I need a pre-clustered h5ad file to compute marker genes with Scanpy?▼

Yes, you need a pre-clustered h5ad file to compute marker genes with Scanpy. The extraction requires an h5ad file containing a specified cluster key to identify groups and calculate differential expression markers for JSON output.

Can I compare cluster markers across multiple scRNA-seq experiments using JSON output?▼

Yes, you can compare cluster markers across multiple scRNA-seq experiments using JSON output. Generating a machine-friendly JSON file mapping cluster IDs to top markers for each dataset enables programmatic benchmarking and comparison of cell types across experiments.

What Python packages are required to run a differential expression analysis for scRNA-seq markers?▼

The Python packages required to run differential expression analysis for scRNA-seq markers are Scanpy, NumPy, and Pandas. These dependencies enable reading h5ad data, computing Wilcoxon rank-sum tests for per-cluster markers, and generating the JSON output.