Can this skill handle large datasets?

Yes, it utilizes the UniProt stream endpoint specifically designed for downloading complete datasets without the overhead of pagination.

Can I filter for only reviewed proteins?

Yes, you can use the 'reviewed:true' filter to retrieve only high-quality Swiss-Prot entries, which have been manually curated by experts.

Is it possible to retrieve specific protein domains?

Yes, you can customize the retrieved fields to include 'ft_domain' or 'ft_site' to access specific feature annotations for each protein entry.

How many IDs can I map at once?

The UniProt ID mapping service integrated into this skill supports batch jobs of up to 100,000 identifiers at a time.

What formats are supported for sequence retrieval?

The skill supports multiple formats including FASTA, JSON, TSV, XML, Excel, and RDF, depending on your data processing needs.

UniProt Protein Database

Name: UniProt Protein Database
Author: K-Dense-AI

byK-Dense-AI

•

3,719

データサイエンスとML

Provides direct REST API access to UniProt for protein sequence retrieval, identifier mapping, and comprehensive functional annotation searches.

概要

The UniProt Database skill enables Claude to interact directly with the world's leading resource for protein sequence and functional information. It allows researchers and bioinformaticians to search for proteins by gene, accession, or name, retrieve sequences in FASTA format, and map identifiers across various biological databases like Ensembl and PDB. By providing access to both manually curated (Swiss-Prot) and computationally predicted (TrEMBL) data, this skill facilitates sophisticated protein analysis and automated data retrieval directly within a development or research workflow.

主な機能

High-speed sequence retrieval in FASTA, JSON, and TSV formats
Cross-database identifier mapping between UniProt, PDB, RefSeq, and Ensembl
Customizable field selection to optimize API response data and performance
Comprehensive protein search by gene, name, organism, or GO terms
Streaming support for efficient large-scale protein dataset exports
3,719 GitHub stars

ユースケース

Automating the retrieval of protein sequences for specific gene lists
Mapping disparate biological identifiers into a unified format for downstream analysis
Filtering and extracting high-quality, manually curated protein annotations from Swiss-Prot

概要

主な機能

High-speed sequence retrieval in FASTA, JSON, and TSV formats
Cross-database identifier mapping between UniProt, PDB, RefSeq, and Ensembl
Customizable field selection to optimize API response data and performance
Comprehensive protein search by gene, name, organism, or GO terms
Streaming support for efficient large-scale protein dataset exports
3,719 GitHub stars

ユースケース

Automating the retrieval of protein sequences for specific gene lists
Mapping disparate biological identifiers into a unified format for downstream analysis
Filtering and extracting high-quality, manually curated protein annotations from Swiss-Prot