gget

Access 20+ bioinformatics databases and analysis tools via CLI and Python.

1|2|Updated Apr 29, 2026
One-click install
npx skills add https://github.com/fuzzy-dynamics/strings --skill gget-fuzzy-dynamics
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gget
Source: https://github.com/fuzzy-dynamics/strings/tree/main/packages/skills/gget
Command: npx skills add https://github.com/fuzzy-dynamics/strings --skill gget-fuzzy-dynamics

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires gget, pandas, and includes scripts (resource) components.

What problem does it solve?

gget provides unified access to 20+ genomic databases and analysis tools from a single CLI and Python interface, simplifying discovery and data retrieval for bioinformatics tasks.

Core Features & Use Cases

  • Unified CLI and Python access to Ensembl, UniProt, NCBI, ARCHS4, OpenTargets, cBioPortal, and more.
  • Retrieve gene metadata, sequences, expression data, and enrichment results; perform fast sequence analyses (BLAST, BLAT, MSA, DIAMOND) and structural predictions (AlphaFold) within workflows.
  • Use in end-to-end pipelines from gene discovery to functional annotation, disease association, and drug target exploration (examples include finding ACE2, BRCA1, BRCA2, and other genes).

Quick Start

Install gget and run a basic query to search for a gene in a specific species.

Frequently Asked Questions about gget

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I query multiple bioinformatics databases for gene expression and sequence data in Python?

You can query 20+ bioinformatics databases for gene expression and sequence data in Python using a unified interface that returns consistent JSON or DataFrame results. It provides access to Ensembl, UniProt, NCBI, and ARCHS4 for reproducible research.

Can I perform BLAST and AlphaFold structural predictions directly from a CLI?

Yes, you can perform fast sequence analyses like BLAST, BLAT, and MSA, along with AlphaFold structural predictions directly from a CLI. This enables end-to-end functional annotation and protein structure exploration within automated pipelines.

What is the best way to retrieve gene metadata and tissue expression profiles across multiple organisms?

The best way to retrieve gene metadata and tissue expression profiles across multiple organisms is through a unified bioinformatics query interface. It standardizes outputs into JSON or DataFrame formats, streamlining gene discovery and disease association tasks.

Does this bioinformatics query tool require a specific Python environment or dependencies?

This bioinformatics query tool requires a standard Python environment with pandas installed. It operates as a Python package and CLI, needing no complex database setups to retrieve enrichment results, sequences, and structural predictions.

How do I run disease association and drug target exploration for genes like BRCA1 or ACE2?

To run disease association and drug target exploration for genes like BRCA1 or ACE2, query databases such as OpenTargets and cBioPortal through the unified Python interface. It retrieves associated metadata and functional annotations directly.

Are there limitations when using this unified CLI for large-scale genomic sequence retrieval?

While this unified CLI streamlines genomic sequence retrieval and enrichment analysis across multiple organisms, it depends on external database uptime and rate limits. Outputs are standardized as JSON or DataFrames, requiring local memory for large-scale processing.