uniprot-database

Query UniProt REST API for protein sequences, annotations, and ID conversions.

Updated May 10, 2026
One-click install
npx skills add https://github.com/Imad-Oute/ResearchForge --skill uniprot-database-imad-oute
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: uniprot-database
Source: https://github.com/Imad-Oute/ResearchForge/tree/main/OpenSource-Projects/claude-scientific-skills/scientific-skills/uniprot-database
Command: npx skills add https://github.com/Imad-Oute/ResearchForge --skill uniprot-database-imad-oute

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill enables direct interaction with UniProt's REST API for comprehensive protein data retrieval and analysis.

Core Features & Use Cases

  • Protein Search and Retrieval: Find proteins by name, gene, accession, or annotations, and retrieve sequences or detailed entries.
  • Identifier Mapping: Convert IDs between UniProt and external databases such as PDB, Ensembl, and GO.
  • Large Dataset Streaming: Stream extensive protein datasets efficiently for bioinformatics workflows.
  • Use Case: Researchers can retrieve all reviewed human kinases with sequences and structural info for drug target discovery.

Quick Start

Use the uniprot database skill to find reviewed human insulin proteins with their sequences.

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 sequences and annotations using the UniProt API?

You can retrieve protein sequences and annotations by querying the UniProt REST API for proteins by name, gene, or accession, and then customizing the API fields to return detailed sequence entries.

What is the best way to convert protein identifiers between UniProt and external databases?

Identifier mapping converts protein IDs between UniProt and external databases like PDB, Ensembl, and GO. This workflow requires specifying your source and target databases to execute the ID mapping process accurately.

Can I stream large protein datasets for bioinformatics workflows via the UniProt API?

Yes, large protein datasets can be streamed efficiently using the UniProt API. This approach supports bioinformatics and functional genomics workflows by handling extensive sequence and structural data retrieval without memory limitations.

Do I need to know API query syntax to search for reviewed human kinases in UniProt?

Yes, finding reviewed human kinases demands familiarity with UniProt API query syntax and field customization. You must construct specific search queries to filter reviewed entries and retrieve their structural information accurately.

Does this UniProt API integration work with Python requests for structural biology tasks?

Yes, this integration relies on the Python requests library to access the UniProt REST API. It is explicitly suitable for structural biology and drug target discovery tasks by retrieving relevant protein data programmatically.

What are the limitations of using REST API queries for functional genomics protein data?

Limitations include the necessity of understanding API query syntax and field customization for functional genomics tasks. Users must manually construct queries and handle ID mapping workflows, as automated field inference is not supported.