What types of GEO data can I access with this skill?

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

Is the GEOparse library required?

While the skill provides several methods, it highly recommends using the GEOparse Python library for the most efficient parsing of SOFT and Matrix files.

Does this skill help with downloading raw data?

Yes, it provides implementation patterns for downloading supplementary files via FTP and handling SRA data links for raw sequencing reads.

Can I filter searches by organism or disease?

Yes, the skill includes advanced search patterns using MeSH terms and Entrez tags to filter by organism, publication date, or specific disease conditions.

GEO Database Access

Name: GEO Database Access
Author: Activer007

byActiver007

Data Science & ML

Access and download NCBI Gene Expression Omnibus (GEO) datasets for transcriptomics and genomics research.

About

The GEO Database skill provides Claude with the specialized capability to interact with the NCBI Gene Expression Omnibus, the primary public repository for high-throughput functional genomics data. It streamlines the complex process of searching for studies (GSE), samples (GSM), and platforms (GPL), while providing implementation patterns for downloading SOFT and Matrix files. This skill is ideal for bioinformaticians and data scientists who need to automate the retrieval of RNA-seq or microarray data for differential expression analysis and multi-omic integration workflows.

Key Features

Programmatic search for GEO datasets and gene expression profiles using Entrez
Batch processing capabilities for large-scale genomic data acquisition
Automated retrieval and parsing of GEO SOFT and Series Matrix files
Metadata extraction for experimental design, organisms, and sample characteristics
0 GitHub stars
Direct FTP access patterns for raw and processed supplementary files

Use Cases

Automating the collection of public transcriptomics data for meta-analysis
Building automated pipelines for downloading and preprocessing NCBI genomics datasets
Finding gene-specific expression patterns across thousands of biological conditions

About

Key Features

Programmatic search for GEO datasets and gene expression profiles using Entrez
Batch processing capabilities for large-scale genomic data acquisition
Automated retrieval and parsing of GEO SOFT and Series Matrix files
Metadata extraction for experimental design, organisms, and sample characteristics
0 GitHub stars
Direct FTP access patterns for raw and processed supplementary files

Use Cases

Automating the collection of public transcriptomics data for meta-analysis
Building automated pipelines for downloading and preprocessing NCBI genomics datasets
Finding gene-specific expression patterns across thousands of biological conditions