Workflow for read alignment, sorting, indexing, mapping statistics, and downstream-ready alignment artifacts.
The English summary is being prepared. Showing the original description.
Query UniProt protein database. Use when user asks about protein sequences, functions, annotations, domains, or protein identifiers. Triggers on "uniprot", "protein function", "protein sequence", "gene product", "protein info".
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Query the UniProt REST API for protein information.
import requests
import json
BASE_URL = "https://rest.uniprot.org"
# 1. Search by gene name (default: human, reviewed/Swiss-Prot)
def search_uniprot(gene_name, organism_id=9606, max_results=5):
url = f"{BASE_URL}/uniprotkb/search"
params = {
"query": f"gene_exact:{gene_name} AND organism_id:{organism_id} AND reviewed:true",
"format": "json",
"size": max_results,
"fields": "accession,id,gene_names,protein_name,organism_name,length,cc_function,ft_domain,sequence"
}
r = requests.get(url, params=params)
r.raise_for_status()
return r.json()
# 2. Get by accession ID
def get_uniprot_entry(accession):
url = f"{BASE_URL}/uniprotkb/{accession}.json"
r = requests.get(url)
r.raise_for_status()
return r.json()
# 3. Get FASTA sequence
def get_fasta(accession):
url = f"{BASE_URL}/uniprotkb/{accession}.fasta"
r = requests.get(url)
r.raise_for_status()
return r.text
# Example usage
data = search_uniprot("TP53")
for entry in data.get("results", []):
acc = entry["primaryAccession"]
name = entry.get("proteinDescription", {}).get("recommendedName", {}).get("fullName", {}).get("value", "N/A")
gene = entry.get("genes", [{}])[0].get("geneName", {}).get("value", "N/A")
length = entry.get("sequence", {}).get("length", "N/A")
# Extract function
functions = [c["texts"][0]["value"] for c in entry.get("comments", []) if c["commentType"] == "FUNCTION"]
func_text = functions[0][:200] if functions else "N/A"
print(f"Accession: {acc}")
print(f"Protein: {name}")
print(f"Gene: {gene}")
print(f"Length: {length} aa")
print(f"Function: {func_text}")
gene_exact:BRCA1 AND organism_id:9606keyword:kinase AND organism_id:9606cc_disease:cancer AND organism_id:9606go:apoptosis AND organism_id:9606Present: Accession, protein name, gene, organism, length, function summary, and UniProt link.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Workflow for read alignment, sorting, indexing, mapping statistics, and downstream-ready alignment artifacts.
The English summary is being prepared. Showing the original description.
Validate protein designs using AlphaFold2 structure prediction. Use this skill when: (1) Validating designed sequences fold correctly, (2) Predicting binder-target complex structures, (3) Calculating confidence metrics (pLDDT, pTM, ipTM), (4) Self-consistency validation of designs, (5) Multi-chain complex prediction with AlphaFold-Multimer. For faster single-chain prediction, use esm. For QC thresholds, use protein-qc.
The English summary is being prepared. Showing the original description.
AlphaFold2 / AlphaFold-Multimer structure prediction for validation and confidence scoring. Use this skill when: (1) Validating designed sequences fold correctly, (2) Predicting binder-target complex structures, (3) Calculating confidence metrics (pLDDT, pTM, ipTM), (4) Self-consistency validation of designs, (5) Multi-chain complex prediction with AlphaFold-Multimer. For faster single-chain prediction, use esm2-sequence-scoring. For QC thresholds, use protein-design-qc.
The English summary is being prepared. Showing the original description.
Workflow for event-level and isoform-level splicing analysis with sashimi-ready outputs and splice QC.
The English summary is being prepared. Showing the original description.
ATAC-seq processing with assay QC, MACS3 peak calling, consensus peak matrices, differential accessibility, and motif or footprint follow-up.
The English summary is being prepared. Showing the original description.
End-to-end binder design using BindCraft hallucination. Use this skill when: (1) Designing protein binders with built-in AF2 validation, (2) Running production-quality binder campaigns, (3) Using different design protocols (fast, default, slow), (4) Need joint backbone and sequence optimization, (5) Want high experimental success rate. For backbone-only generation, use rfdiffusion. For QC thresholds, use protein-qc. For tool selection guidance, use binder-design.
The English summary is being prepared. Showing the original description.