What protein data can I access with this skill?

You can access protein sequences, gene names, functional annotations, GO terms, and cross-references from both the Swiss-Prot (manually curated) and TrEMBL (automatically annotated) databases.

How do I ensure I am only getting high-quality, reviewed data?

You can use the 'reviewed:true' filter in your search queries to specifically target Swiss-Prot entries, which have been manually reviewed by UniProt curators.

Does this skill support large-scale data exports?

Yes, it utilizes the UniProt stream endpoint to handle large result sets that exceed standard pagination limits, making it suitable for downloading complete datasets.

Is there a limit to how many IDs I can process at once?

The integrated UniProt mapping workflow supports jobs of up to 100,000 identifiers per request, with results stored on the server for 7 days.

Can I map IDs from other databases like Ensembl or PDB?

Yes, the skill supports the UniProt ID mapping service, allowing you to convert identifiers between UniProt and dozens of external databases including Ensembl, RefSeq, PDB, and AlphaFoldDB.

UniProt Protein Database

Name: UniProt Protein Database
Author: Yezez9

byYezez9

0•

데이터 과학 및 ML

Accesses UniProt's comprehensive protein sequence and functional information via REST API for bioinformatic analysis and data retrieval.

This skill empowers Claude to interact directly with the UniProt database, the world's leading resource for protein sequence and functional information. It enables users to perform complex protein searches, retrieve high-quality FASTA sequences, map identifiers across different biological databases, and access detailed functional annotations like GO terms and domains. Designed for bioinformatics workflows, it supports both individual entry retrieval and large-scale data streaming, making it an essential tool for protein-centric research and data science projects requiring curated biological data.

주요 기능

010 GitHub stars

02Multi-database ID mapping between UniProt, Ensembl, RefSeq, and PDB

03Large dataset streaming for high-volume bioinformatic queries

04Comprehensive protein search by name, gene, or accession number

05Access to curated Swiss-Prot and unreviewed TrEMBL annotations

06High-speed FASTA sequence retrieval and batch processing

사용 사례

01Automating protein sequence retrieval for molecular biology research

02Extracting functional protein annotations and GO terms for large-scale data analysis

03Mapping biological identifiers between multiple genomics and proteomics databases

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add yezez9/research-agent uniprot-database

For use in Claude.ai and ChatGPT

주요 기능

010 GitHub stars

02Multi-database ID mapping between UniProt, Ensembl, RefSeq, and PDB

03Large dataset streaming for high-volume bioinformatic queries

04Comprehensive protein search by name, gene, or accession number

05Access to curated Swiss-Prot and unreviewed TrEMBL annotations

06High-speed FASTA sequence retrieval and batch processing

사용 사례

01Automating protein sequence retrieval for molecular biology research

02Extracting functional protein annotations and GO terms for large-scale data analysis

03Mapping biological identifiers between multiple genomics and proteomics databases

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add yezez9/research-agent uniprot-database

For use in Claude.ai and ChatGPT