Accesses the world's leading protein sequence and functional information resource via the UniProt REST API.
The UniProt Database skill enables Claude to interact directly with the UniProt Knowledgebase, providing comprehensive tools for searching protein entries by name, gene symbol, or accession. It facilitates the retrieval of protein sequences in multiple formats, including FASTA, and allows for sophisticated ID mapping between UniProt and dozens of external biological databases like PDB, Ensembl, and RefSeq. Designed for researchers and developers in bioinformatics and drug discovery, this skill streamlines scientific data gathering, supports batch processing of up to 100,000 IDs, and provides access to both manually curated Swiss-Prot and computationally predicted TrEMBL annotations.
Key Features
01Customizable field selection for optimized and efficient data transfer
02Comprehensive protein search by gene name, accession, organism, or taxonomy
03High-performance sequence retrieval in FASTA, JSON, and TSV formats
04Automated ID mapping between UniProt and 40+ external biological databases
05Support for streaming large protein datasets for autonomous discovery workflows
06324 GitHub stars
Use Cases
01Automated bioinformatics workflows for drug target identification and analysis
02Retrieving functional annotations and Gene Ontology (GO) terms for protein-protein interaction studies
03Batch mapping protein identifiers between genomic and proteomic databases
