geo-database

Search and download NCBI GEO microarray and RNA-seq datasets in SOFT and Matrix formats.

8|Updated Jan 13, 2026
One-click install
npx skills add https://github.com/hxk622/TokenDance --skill geo-database-hxk622
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: geo-database
Source: https://github.com/hxk622/TokenDance/tree/main/backend/app/skills/builtin/scientific/bioinformatics/geo-database
Command: npx skills add https://github.com/hxk622/TokenDance --skill geo-database-hxk622

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires GEOparse, biopython, pandas, numpy, scipy, matplotlib, seaborn, statsmodels, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides programmatic access to the NCBI Gene Expression Omnibus (GEO) database, enabling researchers to search, retrieve, and analyze gene expression and genomics data.

Core Features & Use Cases

  • Search & Retrieve: Find and download microarray and RNA-seq datasets (GSE, GSM, GPL).
  • Data Formats: Access data in SOFT and Matrix formats for transcriptomics and expression analysis.
  • Use Case: A biologist needs to find all human gene expression datasets related to a specific cancer type, download the associated data, and perform differential expression analysis.

Quick Start

Use the geo-database skill to search for gene expression datasets related to 'Alzheimer's disease' in 'Homo sapiens'.

Frequently Asked Questions about geo-database

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

FAQPage Schema
How do I download RNA-seq datasets from NCBI GEO for transcriptomics analysis?

You retrieve RNA-seq datasets from NCBI GEO by programmatically searching and downloading microarray and RNA-seq data in SOFT and Matrix formats using GEOparse and Biopython for transcriptomics analysis.

What is the best way to search for specific gene expression data in the GEO database?

Searching for gene expression data in the GEO database involves programmatically querying NCBI GEO to find and retrieve relevant datasets by matching specific GSE, GSM, and GPL accession records.

Can I use Python to retrieve microarray data from NCBI GEO in SOFT format?

Yes, you can use Python to retrieve microarray data from NCBI GEO in SOFT format by utilizing libraries like Biopython and GEOparse to access and parse datasets for expression analysis.

Does this approach support searching for human gene expression datasets related to a specific disease?

Yes, searching for human gene expression datasets related to a specific disease is supported by programmatically querying the NCBI GEO database to retrieve matching transcriptomics and genomics data.

What data formats are available when downloading genomics data from GEO?

The available data formats when downloading genomics data from GEO include SOFT and Matrix formats, which are accessible for microarray and RNA-seq datasets to support expression analysis.

What Python libraries are needed to access and parse GEO datasets?

Accessing and parsing GEO datasets requires Python libraries including GEOparse for handling SOFT files, Biopython for biological data retrieval, and pandas with numpy for data manipulation.