Accesses and processes NCBI Gene Expression Omnibus (GEO) data for transcriptomics and functional genomics research.
This skill provides Claude with the specialized ability to interact with the NCBI Gene Expression Omnibus (GEO) repository, a leading public database for high-throughput genomics data. It enables researchers and developers to programmatically search for microarray and RNA-seq datasets, retrieve complex metadata for Series (GSE) and Samples (GSM), and automate the download of expression matrices using tools like GEOparse and NCBI E-utilities. By streamlining the discovery and retrieval of biological data, this skill significantly reduces the overhead involved in setting up computational pipelines for differential gene expression and comparative genomics.
주요 기능
013,719 GitHub stars
02Direct FTP download automation for SOFT and Matrix files
03Programmatic data retrieval using the GEOparse Python library
04Integration with NCBI E-utilities for high-performance metadata fetching
05Gene-centric expression profile querying across multiple studies
06Hierarchical search for GSE, GSM, GPL, and GDS accessions
사용 사례
01Retrieving platform annotations to map probe IDs to genomic features
02Locating RNA-seq datasets for specific organisms and disease conditions
03Automating the download and parsing of expression matrices for meta-analysis