geo-database

Search, download, and parse GEO microarray and RNA-seq datasets.

1|Updated Mar 12, 2026
One-click install
npx skills add https://github.com/yf8578/clawomics --skill geo-database-yf8578
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: geo-database
Source: https://github.com/yf8578/clawomics/tree/main/skills/geo-database
Command: npx skills add https://github.com/yf8578/clawomics --skill geo-database-yf8578

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires GEOparse, biopython, pandas, numpy, scipy, matplotlib, seaborn, statsmodels, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides programmatic access to the NCBI Gene Expression Omnibus (GEO) database, enabling users to find, download, and analyze gene expression and genomics datasets.

Core Features & Use Cases

  • Search & Retrieve: Find and download microarray and RNA-seq datasets (GSE, GSM, GPL) using various search criteria.
  • Data Parsing: Utilize libraries like GEOparse and Biopython to parse SOFT/MINiML files and extract expression matrices.
  • Analysis: Perform quality control, differential expression analysis, and clustering on downloaded data.
  • Use Case: A researcher needs to find all human RNA-seq datasets related to Alzheimer's disease, download their expression matrices, and perform a meta-analysis to identify commonly dysregulated genes.

Quick Start

Use the geo-database skill to search for human breast cancer RNA-seq datasets submitted in 2023.

Frequently Asked Questions about geo-database

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

FAQPage Schema
How do I download and parse gene expression datasets from NCBI GEO?

To download and parse gene expression datasets from NCBI GEO, this Skill provides programmatic access to search and retrieve GSE, GSM, and GPL series. It uses GEOparse and Biopython to parse SOFT/MINiML files into expression matrices for transcriptomics analysis.

What is the best way to search for specific RNA-seq datasets in the GEO database?

The best way to search for RNA-seq datasets in the GEO database is by applying specific search criteria like organism and disease. This Skill enables querying NCBI GEO to find and retrieve relevant microarray and RNA-seq datasets matching your research parameters.

Can I use GEOparse and Biopython for differential expression analysis?

Yes, you can use GEOparse and Biopython for differential expression analysis. This Skill integrates these libraries with pandas, scipy, and statsmodels to perform quality control, differential expression analysis, and clustering on retrieved gene expression data.

Does this approach support both microarray and RNA-seq data retrieval from GEO?

Yes, this approach supports both microarray and RNA-seq data retrieval from GEO. It facilitates the programmatic downloading and parsing of GSE, GSM, and GPL series datasets for comprehensive gene expression and transcriptomics analysis.

How do I extract expression matrices from SOFT files for meta-analysis?

To extract expression matrices from SOFT files for meta-analysis, this Skill parses downloaded NCBI GEO data using GEOparse. It structures the genomics data using pandas and numpy, enabling downstream quality control and identification of dysregulated genes.