geo-database

Search and download NCBI GEO datasets in SOFT or Series Matrix formats.

Updated Mar 10, 2026
One-click install
npx skills add https://github.com/Yezez9/Research-Agent --skill geo-database-yezez9
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: geo-database
Source: https://github.com/Yezez9/Research-Agent/tree/main/scientific-skills/geo-database
Command: npx skills add https://github.com/Yezez9/Research-Agent --skill geo-database-yezez9

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 search for, retrieve, and analyze gene expression and functional genomics data.

Core Features & Use Cases

  • Search GEO Datasets: Find microarray and RNA-seq datasets using keywords, organisms, or accession numbers.
  • Download Data: Retrieve SOFT, Series Matrix, or supplementary files for analysis.
  • Analyze Expression: Perform differential expression analysis, clustering, and correlation studies.
  • Use Case: A researcher needs to find all human breast cancer RNA-seq datasets submitted in the last year, download their expression matrices, and identify differentially expressed genes between tumor and normal samples.

Quick Start

Use the geo-database skill to download the series matrix file for GSE123456.

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 NCBI GEO series matrix files for gene expression analysis?

You can download and parse NCBI GEO series matrix files for gene expression analysis by using GEOparse to programmatically retrieve GSE datasets and load them into pandas DataFrames for immediate downstream processing.

Can I search for specific RNA-seq datasets in the GEO database using accession numbers and keywords?

Yes, you can search for specific RNA-seq datasets in the GEO database using accession numbers, keywords, or organisms to retrieve matching GSE, GSM, and GPL records directly through programmatic Biopython and GEOparse queries.

How do I identify differentially expressed genes from microarray data retrieved from NCBI GEO?

To identify differentially expressed genes from microarray data retrieved from NCBI GEO, you can apply statistical testing using statsmodels and scipy on the downloaded expression matrices to calculate fold changes and significance values.

Does this approach support clustering and visualization for transcriptomics data fetched from GEO?

Yes, this approach supports clustering and visualization for transcriptomics data fetched from GEO by utilizing seaborn and matplotlib to generate heatmaps and cluster maps from the normalized gene expression matrices.

What is the best way to retrieve supplementary files and SOFT formats from the Gene Expression Omnibus?

The best way to retrieve supplementary files and SOFT formats from the Gene Expression Omnibus is to use GEOparse to programmatically fetch raw and processed dataset files, enabling seamless integration into custom functional genomics pipelines.