uniprot-database

Search UniProt proteins and retrieve FASTA sequences via REST API.

Updated Mar 10, 2026
One-click install
npx skills add https://github.com/Yezez9/Research-Agent --skill uniprot-database-yezez9
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: uniprot-database
Source: https://github.com/Yezez9/Research-Agent/tree/main/scientific-skills/uniprot-database
Command: npx skills add https://github.com/Yezez9/Research-Agent --skill uniprot-database-yezez9

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides direct access to the UniProt database, enabling users to search for proteins, retrieve sequences, and map identifiers without needing to navigate complex web interfaces or build custom API clients from scratch.

Core Features & Use Cases

  • Protein Search: Find proteins by name, gene, accession, organism, or GO terms using a powerful query syntax.
  • Sequence Retrieval: Get protein sequences in various formats (FASTA, TXT).
  • ID Mapping: Translate identifiers between UniProt and other major biological databases (e.g., PDB, Ensembl).
  • Batch Operations: Efficiently retrieve or map large sets of entries.
  • Use Case: A researcher needs to find all human proteins associated with a specific gene (e.g., BRCA1) and retrieve their sequences in FASTA format for downstream analysis.

Quick Start

Search for human insulin proteins and retrieve their FASTA 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 in FASTA format from UniProt?

To retrieve protein sequences in FASTA format from UniProt, use the Skill's Python scripts to query the REST API by protein name, gene, or accession, directly returning sequence data for downstream analysis.

Can I map protein identifiers between UniProt and Ensembl or PDB?

Yes, you can map protein identifiers between UniProt and other databases like Ensembl or PDB using the Skill's identifier mapping feature, which translates IDs across biological databases via the REST API endpoints.

How do I search UniProt for human proteins associated with a specific gene like BRCA1?

Search for human proteins associated with a specific gene like BRCA1 by constructing a query in the Python scripts that targets the UniProt REST API, filtering by gene name and organism to retrieve matching entries.

Does this Skill require building a custom API client to access the UniProt database?

No, this Skill provides direct REST API access to the UniProt database for protein information retrieval, eliminating the need to build a custom API client from scratch or navigate complex web interfaces.

Can I perform batch retrieval of UniProt entries for large datasets?

Yes, the Skill supports batch operations to efficiently retrieve or map large sets of UniProt entries, programmatically interacting with the API endpoints to process multiple protein identifiers simultaneously.

What query syntax is supported for searching proteins in the UniProt database?

The UniProt database search supports a query syntax that allows finding proteins by name, gene, accession, organism, or GO terms, enabling precise protein information retrieval through the REST API scripts.