gget

Unify access to genomic databases and analyses via CLI and Python.

1|Updated Mar 11, 2026
One-click install
npx skills add https://github.com/SciMate-AI/scicli --skill gget-scimate-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gget
Source: https://github.com/SciMate-AI/scicli/tree/main/internal/skills/bundled/claude-scientific-skills/skills/gget
Command: npx skills add https://github.com/SciMate-AI/scicli --skill gget-scimate-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

gget provides a unified command-line and Python API to access dozens of genomic databases and analysis tools, simplifying exploratory research and reproducible workflows.

Core Features & Use Cases

  • Unified access to 20+ databases and modules (Ensembl, UniProt, NCBI, PDB, ARCHS4, OpenTargets, cBioPortal, COSMIC, etc.) via a single CLI and Python interface.
  • Supports end-to-end workflows including gene discovery, metadata retrieval, sequence retrieval, enrichment analysis, disease/drug associations, single-cell data, and structure prediction with AlphaFold.
  • Setup and reproducibility features such as module setup, version references, and data caching to ensure consistent analyses across runs.

Quick Start

Launch a quick analysis by searching a gene, retrieving metadata, and fetching sequences in a single command flow.

Frequently Asked Questions about gget

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

FAQPage Schema
How do I query multiple genomic databases like Ensembl and UniProt from a single Python interface?

You can query multiple genomic databases using a unified CLI and Python interface that connects to Ensembl, UniProt, NCBI, and others. This allows you to retrieve gene metadata and fetch sequences across 20+ databases in a single workflow.

Can I perform enrichment analysis and disease association queries without switching bioinformatics tools?

Yes, enrichment analysis and disease association queries can be performed without switching tools. The unified interface accesses OpenTargets, cBioPortal, COSMIC, and ARCHS4 directly to retrieve disease and drug associations for genomic data.

What's the best way to retrieve gene sequences and structural predictions for exploratory research?

The best way to retrieve sequences and structural predictions is using a unified CLI that fetches sequence data and integrates AlphaFold. It automates end-to-end genomic data exploration by unifying access to structural and sequence databases.

Do I need standard Python tooling and special setup to access single-cell data and AlphaFold modules?

Yes, standard Python tooling is required. The interface provides specific setup commands for AlphaFold, cellxgene, and related dependencies to ensure reproducible workflows when accessing single-cell data and structural predictions.

How does data caching and module setup ensure reproducible genomic workflows?

Data caching and module setup ensure reproducible genomic workflows by storing query results and standardizing dependency versions. This maintains consistent analyses across multiple runs when accessing biological databases like Ensembl and NCBI.

Are there limitations to automating end-to-end genomic exploration across 20+ databases?

Automating genomic exploration across 20+ databases requires standard Python tooling and specific setup for dependencies like AlphaFold and cellxgene. Limitations include the need for external dependency management and module version references to maintain reproducibility.