> Access UniProt for protein sequence and annotation retrieval. (2) Finding functional annotations, (3) Getting domain boundaries, (4) Finding homologs and variants, (5) Cross-referencing to PDB structures. For structure retrieval, use pdb. For sequence design, use proteinmpnn.
npx skills add https://github.com/BioTender-max/awesome-bio-agent-skills --skill uniprot
Note: This skill uses the UniProt REST API directly. No Modal deployment needed - all operations run locally via HTTP requests.
# FASTA format
curl "https://rest.uniprot.org/uniprotkb/P00533.fasta"
# JSON format with annotations
curl "https://rest.uniprot.org/uniprotkb/P00533.json"
import requests
def get_uniprot_sequence(accession):
"""Fetch sequence from UniProt."""
url = f"https://rest.uniprot.org/uniprotkb/{accession}.fasta"
response = requests.get(url)
if response.ok:
lines = response.text.strip().split('\n')
header = lines[0]
sequence = ''.join(lines[1:])
return header, sequence
return None, None
def get_uniprot_entry(accession):
"""Fetch full UniProt entry as JSON."""
url = f"https://rest.uniprot.org/uniprotkb/{accession}.json"
response = requests.get(url)
return response.json() if response.ok else None
entry = get_uniprot_entry("P00533")
print(f"Protein: {entry['proteinDescription']['recommendedName']['fullName']['value']}")
def get_domains(accession):
"""Extract domain annotations."""
entry = get_uniprot_entry(accession)
domains = []
for feature in entry.get('features', []):
if feature['type'] == 'Domain':
domains.append({
'name': feature.get('description', ''),
'start': feature['location']['start']['value'],
'end': feature['location']['end']['value']
})
return domains
# Example: EGFR domains
domains = get_domains("P00533")
# [{'name': 'Kinase', 'start': 712, 'end': 979}, ...]
def search_uniprot(query, organism=None, limit=10):
"""Search UniProt by query."""
url = "https://rest.uniprot.org/uniprotkb/search"
params = {
"query": query,
"format": "json",
"size": limit
}
if organism:
params["query"] += f" AND organism_id:{organism}"
response = requests.get(url, params=params)
return response.json()['results']
# Search for human EGFR
results = search_uniprot("EGFR", organism=9606)
# Use UniProt BLAST
# https://www.uniprot.org/blast
def get_pdb_references(accession):
"""Get PDB structures for UniProt entry."""
entry = get_uniprot_entry(accession)
pdbs = []
for xref in entry.get('uniProtKBCrossReferences', []):
if xref['database'] == 'PDB':
pdbs.append({
'pdb_id': xref['id'],
'method': xref.get('properties', [{}])[0].get('value', ''),
'chains': xref.get('properties', [{}])[1].get('value', '')
})
return pdbs
# Example: PDB structures for EGFR
pdbs = get_pdb_references("P00533")
# 1. Find protein by name
results = search_uniprot("insulin receptor", organism=9606)
# 2. Get accession
accession = results[0]['primaryAccession'] # e.g., P06213
# 3. Get domains
domains = get_domains(accession)
# 4. Find PDB structure
pdbs = get_pdb_references(accession)
# 5. Download best structure for design
def get_sequence_variants(accession):
"""Get natural variants from UniProt."""
entry = get_uniprot_entry(accession)
variants = []
for feature in entry.get('features', []):
if feature['type'] == 'Natural variant':
variants.append({
'position': feature['location']['start']['value'],
'original': feature.get('alternativeSequence', {}).get('originalSequence', ''),
'variant': feature.get('alternativeSequence', {}).get('alternativeSequences', [''])[0],
'description': feature.get('description', '')
})
return variants
| Endpoint | Description |
|----------|-------------|
| /uniprotkb/{id}.fasta | FASTA sequence |
| /uniprotkb/{id}.json | Full entry JSON |
| /uniprotkb/search | Search entries |
| /uniprotkb/stream | Batch download |
Entry not found: Check accession format (e.g., P00533)
Rate limits: Add delay between requests
Large downloads: Use stream endpoint with pagination
Next: Use sequence with esm for embeddings or colabfold for structure.
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take biotender-max/uniprot from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.