geo-database

Search and download NCBI GEO datasets with GEOparse and E-utilities.

298|27|Updated Feb 18, 2026
One-click install
npx skills add https://github.com/jaechang-hits/SciAgent-Skills --skill geo-database-jaechang-hits
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: geo-database
Source: https://github.com/jaechang-hits/SciAgent-Skills/tree/main/skills/genomics-bioinformatics/geo-database
Command: npx skills add https://github.com/jaechang-hits/SciAgent-Skills --skill geo-database-jaechang-hits

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires GEOparse, requests, pandas, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill simplifies the process of finding, downloading, and parsing gene expression datasets from the NCBI Gene Expression Omnibus (GEO) database, enabling researchers to quickly access and analyze public functional genomics data.

Core Features & Use Cases

  • Search GEO: Find datasets by keywords, organism, or platform using NCBI E-utilities.
  • Download & Parse: Retrieve and process entire GEO Series (GSE) records, including expression matrices and sample metadata, using GEOparse.
  • Extract Metadata: Obtain detailed information about samples (GSM) and platforms (GPL).
  • Use Case: A researcher needs to find all human RNA-seq datasets related to lung cancer to perform a meta-analysis. This Skill can search GEO, download relevant datasets, and extract the expression values and sample annotations into a usable format.

Quick Start

Use the geo-database skill to download and parse the GSE2553 series.

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 GEO gene expression datasets programmatically?

You can download and parse GEO gene expression datasets programmatically using GEOparse and NCBI E-utilities to retrieve GSE series records, extract expression matrices, and parse GSM sample and GPL platform metadata.

Can I search NCBI GEO for specific organisms or platforms?

Yes, you can search NCBI GEO by keywords, organism, or platform using E-utilities to find relevant functional genomics datasets before downloading the series records for further analysis.

What is the best way to extract expression matrices from GEO series records?

The best way to extract expression matrices from GEO series records is by parsing GSE entries with GEOparse, which processes the downloaded data and isolates the expression values alongside sample annotations.

Does GEOparse work with pandas for processing gene expression data?

Yes, GEOparse works with pandas to process gene expression data, allowing you to structure the parsed GSE, GSM, and GPL metadata into dataframes for downstream bioinformatics analysis.

How do I retrieve sample and platform metadata from a GSE series?

You retrieve sample and platform metadata from a GSE series by parsing the GEO record with GEOparse, which separates the GSM sample information and GPL platform annotations into structured formats.