geo-database

Retrieve gene expression datasets from NCBI GEO by accession ID.

21|2|Updated Dec 8, 2025
One-click install
npx skills add https://github.com/silverstein/claude-scientific-skills-desktop --skill geo-database-silverstein
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: geo-database
Source: https://github.com/silverstein/claude-scientific-skills-desktop/tree/main/corpus/geo-database
Command: npx skills add https://github.com/silverstein/claude-scientific-skills-desktop --skill geo-database-silverstein

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

The geo-database skill helps you find and retrieve gene expression and functional genomics datasets from NCBI GEO without manually navigating multiple accession types and file formats.

Core Features & Use Cases

  • GEO accession understanding: clarifies the differences between Series (GSE), Sample (GSM), Platform (GPL), DataSet (GDS), and Profiles so you can choose the right entry to fetch.
  • Targeted searching: supports keyword and structured query patterns for GEO DataSets and gene-centric GEO Profiles (e.g., by organism, platform, disease, or publication date).
  • Data retrieval for analysis: guides downloading and parsing common GEO data artifacts such as SOFT, MINiML, series matrix files, and supplementary files for downstream expression analysis.
  • Recommended programmatic workflows: emphasizes using GEOparse for series-level access, plus NCBI E-utilities for metadata search and batch operations.

Quick Start

Use the geo-database skill to search GEO for RNA-seq studies in Homo sapiens related to a specific condition and return the relevant GSE/GSM accessions for downloading expression matrices.

Frequently Asked Questions about geo-database

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

FAQPage Schema
How do I download GEO gene expression datasets using GSE accession IDs?

To download GEO gene expression datasets, search NCBI GEO by Series (GSE) accession IDs to extract expression-ready series matrix files, SOFT, and MINiML formats for downstream transcriptomics analysis.

What is the difference between GSE, GSM, and GPL accession types in NCBI GEO?

GEO accession hierarchy distinguishes Series (GSE) as full studies, Sample (GSM) as individual samples, and Platform (GPL) as array specifications, guiding which entry point to fetch for your expression data retrieval.

Can I search NCBI GEO for RNA-seq studies by organism and disease condition?

You can search NCBI GEO DataSets and gene-centric Profiles using structured query patterns filtered by organism, platform, disease, or publication date to identify relevant transcriptomics studies.

Does GEOparse work for extracting series matrix files from GEO?

GEOparse is the recommended programmatic workflow for series-level GEO access, supporting series matrix extraction alongside NCBI E-utilities for metadata search and batch operations with rate-limit best practices.

What is the best way to retrieve bulk supplementary files from GEO for transcriptomics research?

Bulk retrieval of GEO supplementary files and expression matrices is best handled through E-utilities and FTP-based access patterns with caching, supporting sample- and platform-aware interpretation for transcriptomics workflows.

Are there limitations when querying large GEO datasets for downstream expression analysis?

Querying large GEO datasets requires rate-limit best practices and caching due to E-utilities and FTP access constraints, ensuring stable retrieval of series matrices and supplementary files without connection interruptions.