The UniProt Database skill empowers AI agents to interact directly with the world's leading protein information resource via its REST API. It provides robust capabilities for searching protein entries by gene name, organism, or accession number, retrieving sequences in FASTA format, and performing complex ID mapping across biological databases like Ensembl, PDB, and AlphaFoldDB. This skill is essential for bioinformatics workflows, allowing for high-throughput protein analysis, streaming of large datasets, and precise access to both manually curated Swiss-Prot annotations and computational TrEMBL predictions directly within a coding environment.
Key Features
01Protein sequence retrieval in multiple formats including FASTA and JSON
02High-volume ID mapping between UniProt and 40+ biological databases
03Streaming endpoints for efficient processing of large-scale protein datasets
04Advanced filtering for reviewed (Swiss-Prot) vs. unreviewed (TrEMBL) data
05Direct REST API access for comprehensive protein searches and metadata
068 GitHub stars
