geo-database

Retrieve and parse NCBI GEO gene expression datasets via FTP and E-utilities.

Updated Mar 30, 2026

Search Tags:#bioinformatics #geo #data-retrieval #gene-expression #transcriptomics #ftp-download #geoparse

Ready to run

npx skills add https://github.com/ya-way/cytoclaw-skills --skill geo-database-ya-way

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: geo-database
Source: https://github.com/ya-way/cytoclaw-skills/tree/main/workspace/skills/labclaw-lit-geo-database
Command: npx skills add https://github.com/ya-way/cytoclaw-skills --skill geo-database-ya-way

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

GEO data access has historically been manual, fragmented, and time-consuming, hindering researchers who need scalable access to public gene expression datasets for transcriptomics and functional genomics.

Core Features & Use Cases

Programmatic search, download, and parsing of GEO datasets (GSE, GSM, GPL) including series matrices and SOFT/MINiML formats.
Cross-study data collection and metadata extraction for comparative analyses, meta-analyses, and reproducibility.
Use cases include building expression compendia, benchmarking pipelines, and integrating GEO data into downstream analyses.

Quick Start

Install GEOparse and Biopython, then run a sample workflow to fetch a GEO series and extract its expression matrix.

Frequently Asked Questions about geo-database

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

FAQPage Schema

How do I programmatically download GEO series matrices and metadata for transcriptomics analysis?▼

Programmatic GEO data retrieval is handled by searching and parsing GSE, GSM, and GPL records via FTP and E-utilities. You can download series matrices and extract metadata directly into your workflow for downstream transcriptomics analysis.

Can I use Biopython and GEOparse to extract cross-study gene expression data from different platforms?▼

Yes, Biopython and GEOparse support cross-study data collection and metadata extraction across different platforms and organisms. This enables comparative analyses and meta-analyses by aggregating gene expression data from multiple GEO datasets.

What is the best way to build a gene expression compendium from public NCBI GEO datasets?▼

The best way to build an expression compendium is using automated workflows to search, filter, and parse GEO datasets. By retrieving series matrices and metadata programmatically, you can integrate multiple public gene expression datasets into a unified compendium.

Does this approach support downloading SOFT and MINiML formats in addition to series matrices?▼

Yes, the data retrieval process supports downloading and parsing SOFT and MINiML formats alongside series matrices. This ensures comprehensive access to GEO metadata and expression values for functional genomics and reproducibility studies.

How do I filter GEO datasets by organism and platform when collecting data for meta-analysis?▼

You can filter GEO datasets by applying parsing and filtering workflows to the extracted metadata. This allows you to select specific organisms, platforms, and study types to construct targeted datasets for cross-study meta-analyses.

What are the limitations of using E-utilities and FTP for large-scale GEO data retrieval?▼

Large-scale GEO data retrieval via E-utilities and FTP is limited by network bandwidth and NCBI rate limits. When building extensive expression compendia, parsing efficiency and local storage capacity also constrain the scalability of cross-study data collection.