geo-database

Search NCBI GEO accessions and parse series matrix files into expression matrices.

783|65|Updated Feb 27, 2026
One-click install
npx skills add https://github.com/LeonChaoX/qinyan-academic-skills --skill geo-database-leonchaox
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: geo-database
Source: https://github.com/LeonChaoX/qinyan-academic-skills/tree/main/skills/12-%E7%A7%91%E5%AD%A6%E6%95%B0%E6%8D%AE%E5%BA%93/geo-database
Command: npx skills add https://github.com/LeonChaoX/qinyan-academic-skills --skill geo-database-leonchaox

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill removes the manual effort of locating, downloading, and structuring gene expression/genomics datasets from NCBI GEO so you can move directly into downstream analysis.

Core Features & Use Cases

  • Search across GEO key accessions: locate studies (GSE), samples (GSM), platforms (GPL), curated datasets (GDS), and gene-centric expression profiles.
  • Retrieve expression data files: pull series matrices and related SOFT/Matrix-style resources for transcriptomics workflows.
  • Prepare data for analysis: convert GEO structures into expression matrices suitable for QC, differential expression, clustering, and meta-analysis.
  • Use with recommended tooling: supports GEOparse for parsing and downloading with NCBI-friendly practices, plus optional direct file access via FTP.

Quick Start

Ask the AI to download and parse a GEO series (e.g., GSE123456) and output the expression matrix ready for QC and differential expression analysis.

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 a GEO series matrix into an expression matrix for transcriptomics analysis?

You can download and parse a GEO series matrix by searching accessions like GSE or GSM, retrieving SOFT or series matrix files, and converting them into analysis-ready expression matrices. The Skill uses GEOparse to structure the output for QC and differential expression workflows.

What is the best way to search NCBI GEO datasets by keywords or accession numbers?

The best way to search NCBI GEO datasets is by using keywords, gene-centric profiles, or specific accessions including GSE, GSM, GPL, and GDS. The Skill locates matching functional genomics datasets and retrieves their associated expression tables for downstream transcriptomics analysis.

Can I use GEOparse to handle NCBI rate limits when retrieving GEO expression data?

Yes, GEOparse is the recommended tool for downloading and parsing GEO data with NCBI-friendly practices. The Skill requires GEOparse or equivalent NCBI E-utilities and FTP access to obtain metadata and expression tables while properly handling platform and sample relationships.

Does this approach support converting SOFT files into analysis-ready expression matrices?

Yes, the Skill supports parsing SOFT and series matrix-style resources retrieved from NCBI GEO. It converts these GEO structures into analysis-ready expression matrices suitable for quality control, differential expression, clustering, and meta-analysis.

Why do I need to handle platform and sample relationships when parsing GEO series matrices?

Handling platform and sample relationships is necessary because GEO datasets contain complex hierarchical metadata linking platforms (GPL) to samples (GSM). The Skill parses these relationships using GEOparse to ensure the resulting expression matrix accurately reflects the study design.