Can I use this for both Microarray and RNA-seq data?

Yes, it supports searching and retrieving both array-based and sequence-based functional genomics data stored in the GEO repository.

How does it handle large data downloads?

The skill provides implementation patterns for both GEOparse-based downloads and direct FTP access for handling large-scale supplementary files and raw data.

Does this skill require an NCBI API key?

NCBI doesn't require a traditional API key, but the skill follows best practices by configuring Entrez.email to identify requests and avoid rate-limiting.

What types of genomic data can this skill retrieve?

The skill can access all NCBI GEO formats, including Series (GSE) for full experiments, Samples (GSM) for individual data points, and Platforms (GPL) for technology annotations.

NCBI GEO Data Integration

Name: NCBI GEO Data Integration
Author: BbgnsurfTech

byBbgnsurfTech

•

Ciencia de Datos y ML

Accesses and processes gene expression and functional genomics data from the NCBI Gene Expression Omnibus repository.

This skill enables researchers and bioinformaticians to programmatically interact with the NCBI Gene Expression Omnibus (GEO), the world's largest public repository for high-throughput gene expression data. It provides standardized implementation patterns for searching, downloading, and parsing complex genomic datasets including Series (GSE), Samples (GSM), and Platforms (GPL). By bridging the gap between natural language queries and technical bioinformatics libraries like GEOparse and Biopython, it streamlines the discovery and preparation of transcriptomics data for downstream computational analysis.

Características Principales

01Hierarchical data management for experimental metadata and sample characteristics

02Integration with Pandas for immediate expression matrix manipulation

03Automated parsing of SOFT and Matrix files via the GEOparse library

04Programmatic searching of GEO DataSets and Profiles using NCBI E-utilities

05Direct FTP access patterns for bulk downloading of supplementary and raw data

063 GitHub stars

Casos de Uso

01Automating the collection of RNA-seq datasets for large-scale meta-analysis

02Building reproducible bioinformatics pipelines that incorporate public experimental data

03Searching and retrieving specific gene expression patterns across thousands of studies

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add bbgnsurftech/claude-skills-collection geo-database

For use in Claude.ai and ChatGPT

Download Skill