uniprot-database

Retrieve protein metadata, annotations, taxonomy, and sequences from UniProt databases.

2.7k|283|Updated May 13, 2026
One-click install
npx skills add https://github.com/google-deepmind/science-skills --skill uniprot-database-google-deepmind
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: uniprot-database
Source: https://github.com/google-deepmind/science-skills/tree/main/skills/uniprot_database
Command: npx skills add https://github.com/google-deepmind/science-skills --skill uniprot-database-google-deepmind

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill solves the problem of manually looking up and cross-referencing protein metadata, taxonomy, and sequences across UniProt’s databases.

Core Features & Use Cases

  • Protein discovery and annotation lookup: Search UniProtKB, UniParc, and UniRef for functional annotations, taxonomy details, and curated metadata without inventing results.
  • Scalable retrieval and ID mapping: Stream large result sets for bulk downloads and map identifiers between UniProt and 100+ external resources.
  • Graph-style discovery with SPARQL: Use SPARQL for complex queries like counting proteins, exact sequence matches (where supported), and multi-constraint retrieval.

Quick Start

Ask the agent to retrieve UniProt entry details for P04637 using the uniprot-database skill.

Frequently Asked Questions about uniprot-database

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

FAQPage Schema
How do I retrieve protein metadata and functional annotations from UniProtKB?

You can retrieve UniProt protein metadata using targeted single-entry fetches or query-based searches with pagination. This skill accesses UniProtKB functional annotations and curated metadata directly via REST endpoints without inventing results.

Can I map protein identifiers between UniProt and external databases?

Map identifiers between UniProt and 100+ external resources using the ID mapping feature. This allows cross-referencing protein accessions across various biological databases for comprehensive discovery and data integration tasks.

What is the best way to bulk download large protein sequence sets?

Stream large result sets for bulk retrieval by using the provided scripts wrapper. This method handles scalable downloads of protein sequences and metadata from UniProtKB, UniParc, and UniRef without overwhelming the REST API.

How does SPARQL querying work for complex protein discovery tasks?

SPARQL graph queries enable complex protein discovery like counting proteins and multi-constraint retrieval. This approach allows advanced filtering and exact sequence matching where supported by the UniProt database structure.

Do I need a license file to access UniProt taxonomy and sequence data?

You must optionally create a UniProt license notification file before first use to access taxonomy and sequence data. This ensures compliance with UniProt usage terms when retrieving protein entries via the deterministic scripts wrapper.