NCBI GEO Database Access

关于

This skill empowers Claude to navigate and interact with the NCBI Gene Expression Omnibus (GEO), the world's largest public repository for high-throughput functional genomics data. It provides standardized implementation patterns for searching, downloading, and parsing Series (GSE), Samples (GSM), and Platforms (GPL). By leveraging specialized libraries like GEOparse and Biopython's Entrez, the skill streamlines the complex process of retrieving raw or processed expression matrices and associated metadata, making it an essential tool for bioinformaticians and researchers performing meta-analyses or validating experimental results.

主要功能

• Metadata extraction for experimental design and sample characteristics
• 0 GitHub stars
• Programmatic search of GEO DataSets and Profiles via Entrez E-utilities
• Automated retrieval of Series Matrix and SOFT files using GEOparse
• Direct FTP access patterns for high-speed downloading of large genomic datasets
• Filtering and subsetting tools for large-scale expression matrices

使用场景

• Automating the collection of experimental metadata for large-scale bioinformatics pipelines
• Identifying and downloading relevant RNA-seq or microarray datasets for differential gene expression analysis
• Performing cross-study validation of biomarkers by querying specific gene profiles across multiple series