Do I need an account to search NCBI GEO?

No public account is needed, but the skill requires an email address for Entrez E-utilities to comply with NCBI's programmatic access policies.

What accession types does this skill support?

It supports all major GEO accession types including Series (GSE), Samples (GSM), Platforms (GPL), and curated DataSets (GDS).

How does this skill handle large genomic datasets?

It provides optimized methods for downloading compressed series matrix files and supports direct FTP access for efficient batch retrieval of large files.

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

Yes, the skill is designed to handle various functional genomics data types stored in the GEO repository, including sequence-based and array-based experiments.

NCBI GEO Database Access

Name: NCBI GEO Database Access
Author: Microck

byMicrock

•

数据科学与机器学习

Accesses and retrieves gene expression and functional genomics data from the NCBI Gene Expression Omnibus (GEO).

关于

This skill provides a comprehensive toolkit for bioinformatics workflows, allowing Claude to programmatically search, download, and parse high-throughput genomics data from the NCBI GEO repository. It supports hierarchical data structures including Series (GSE), Samples (GSM), and Platforms (GPL), facilitating the retrieval of both microarray and RNA-seq datasets. By leveraging libraries like Biopython and GEOparse, it enables seamless integration of public transcriptomics data into computational analysis, quality control, and differential expression studies.

主要功能

Programmatic search of GEO DataSets and Profiles using NCBI E-utilities
Automated downloading and parsing of GSE, GSM, and GPL records via GEOparse
Direct extraction of expression matrices and series metadata for analysis
Advanced filtering of samples based on experimental conditions and metadata
Support for direct FTP access and batch retrieval of large-scale genomic files
81 GitHub stars

使用场景

Retrieving RNA-seq datasets for comparative transcriptomics analysis
Downloading specific microarray platform annotations (GPL) for probe mapping
Searching for curated gene expression profiles related to specific diseases

关于

主要功能

Programmatic search of GEO DataSets and Profiles using NCBI E-utilities
Automated downloading and parsing of GSE, GSM, and GPL records via GEOparse
Direct extraction of expression matrices and series metadata for analysis
Advanced filtering of samples based on experimental conditions and metadata
Support for direct FTP access and batch retrieval of large-scale genomic files
81 GitHub stars

使用场景

Retrieving RNA-seq datasets for comparative transcriptomics analysis
Downloading specific microarray platform annotations (GPL) for probe mapping
Searching for curated gene expression profiles related to specific diseases