Integrates with the NCBI Gene Expression Omnibus (GEO) to search, download, and analyze high-throughput functional genomics datasets.
The GEO Database skill empowers researchers and developers to programmatically access NCBI's vast repository of transcriptomics and genomics data directly within Claude. It provides specialized patterns for querying series (GSE), samples (GSM), and platforms (GPL), and automates the retrieval of SOFT and Matrix files using libraries like GEOparse and Bio.Entrez. This skill is essential for bioinformatics workflows, facilitating the meta-analysis of gene expression and the integration of public biological data into computational pipelines with ease.
主要功能
01Automated parsing of series matrix and SOFT files with GEOparse integration
02Batch downloading of supplementary files and raw sequencing data from NCBI FTP servers
03Pre-configured patterns for integrating GEO data into Python bioinformatics stacks
041 GitHub stars
05Advanced search for GSE, GSM, and GPL accessions using MeSH terms and filters
06Programmatic metadata extraction for experimental design and sample characteristics
使用场景
01Extracting transcriptomics data for differential gene expression meta-analysis
02Retrieving specific platform annotations (GPL) to map probes to gene symbols
03Automating the search for public RNA-seq datasets related to specific diseases or organisms
