uniprot-database

Search UniProt proteins and retrieve sequences via its REST API.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/Juancho032007/claude-scientific-skills --skill uniprot-database
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: uniprot-database
Source: https://github.com/Juancho032007/claude-scientific-skills/tree/main/scientific-databases/uniprot-database
Command: npx skills add https://github.com/Juancho032007/claude-scientific-skills --skill uniprot-database

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Manually searching and retrieving protein information from UniProt, especially for large datasets or complex queries, is inefficient and prone to errors. This Skill automates programmatic access to UniProt's REST API, saving time and ensuring consistent data retrieval for all your protein analysis needs.

Core Features & Use Cases

  • Advanced Protein Search: Query UniProt by name, gene symbol, accession, organism, GO terms, sequence length, and more using powerful search syntax.
  • Sequence Retrieval: Fetch protein sequences in FASTA or other formats for individual entries or perform batch retrieval for multiple accessions.
  • ID Mapping: Convert identifiers between UniProt and numerous external databases (e.g., PDB, Ensembl, RefSeq, KEGG) with a robust mapping service.
  • Use Case: A bioinformatician needs to retrieve the protein sequences for a list of 500 UniProt accessions, map them to their corresponding PDB IDs, and then filter for only reviewed (Swiss-Prot) entries. This skill automates the entire process, delivering clean, mapped data.

Quick Start

To search for human insulin proteins: from scripts.uniprot_client import search_proteins results = search_proteins("insulin AND organism_name:human", format="json", size=5) print(results)