geo-database

Locate and retrieve GEO datasets and metadata for gene expression studies.

4|1|Updated Jun 18, 2025
One-click install
npx skills add https://github.com/HolobiomicsLab/Toolomics --skill geo-database-holobiomicslab
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: geo-database
Source: https://github.com/HolobiomicsLab/Toolomics/tree/main/mcp_host/skills/scientific-skills/scientific-skills/geo-database
Command: npx skills add https://github.com/HolobiomicsLab/Toolomics --skill geo-database-holobiomicslab

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Researchers need a streamlined way to locate, download, and integrate gene expression datasets from GEO (GSE/GSM/GPL) for transcriptomics analyses.

Core Features & Use Cases

  • Search GEO for studies by accession, title, organism and data type using E-utilities and GEOparse.
  • Download and parse complete series data formats (SOFT, MINiML, series_matrix) and supplementary files, enabling cross-study analyses.
  • Analyze expression data, perform meta-analyses, and link datasets to publications for secondary analyses.

Quick Start

Begin by identifying a GEO series of interest and downloading its expression matrix or family file to load into your analysis workflow.

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 series matrix and SOFT files for gene expression analysis?

To download GEO gene expression datasets, you can retrieve series matrices, SOFT, and MINiML files using GEOparse and FTP-based workflows, then parse them for integration into downstream transcriptomics analyses.

Can I search GEO datasets by accession number and organism using E-utilities?

Yes, you can search GEO datasets by accession, title, organism, and data type using E-utilities. This allows you to locate specific gene expression studies and retrieve their associated metadata for reproducible research.

What is the best way to parse supplementary files from GEO for cross-study meta-analyses?

The best way to parse GEO supplementary files for meta-analyses is to download complete series data formats and supplementary files using GEOparse, enabling the integration of expression data across multiple studies.

Does this approach support linking GEO expression data to publications for secondary analyses?

Yes, the approach supports linking GEO expression datasets to their associated publications. This facilitates secondary analyses by providing context and metadata retrieved via E-utilities and GEOparse workflows.

How do I retrieve GPL platform annotations and GSM sample metadata from GEO?

You can retrieve GPL platform annotations and GSM sample metadata by downloading and parsing complete GEO family files. GEOparse processes these files to extract the metadata needed for transcriptomics workflows.

What formats are available when downloading GEO datasets for transcriptomics workflows?

Available GEO dataset formats include series matrices, SOFT files, MINiML files, and supplementary data. These formats are downloaded and parsed to support gene expression analysis and reproducible research.