import requests

undefined

import requests

endpoint = "https://rest.uniprot.org/uniprotkb/search"
params = {
    "query": "hemoglobin AND organism_id:9606 AND reviewed:true",
    "format": "json",
    "size": 10
}

resp = requests.get(endpoint, params=params)
results = resp.json()

for entry in results["results"]:
    acc = entry["primaryAccession"]
    name = entry["proteinDescription"]["recommendedName"]["fullName"]["value"]
    print(f"{acc}: {name}")

undefined

undefined

import requests

acc = "P53_HUMAN"  # or "P04637"
url = f"https://rest.uniprot.org/uniprotkb/{acc}.fasta"
resp = requests.get(url)
print(resp.text)

import requests

params = {
    "query": "gene:TP53 AND reviewed:true",
    "format": "tsv",
    "fields": "accession,gene_names,organism_name,length,sequence,cc_function"
}

resp = requests.get("https://rest.uniprot.org/uniprotkb/search", params=params)
print(resp.text)

undefined

See `references/api-reference.md` for the complete field catalog.

import requests
import time

def map_identifiers(ids, source_db, target_db):
    """Map identifiers from one database to another."""
    # Submit mapping job
    submit_resp = requests.post(
        "https://rest.uniprot.org/idmapping/run",
        data={
            "from": source_db,
            "to": target_db,
            "ids": ",".join(ids)
        }
    )
    job_id = submit_resp.json()["jobId"]

    # Poll until complete
    status_url = f"https://rest.uniprot.org/idmapping/status/{job_id}"
    while True:
        status_resp = requests.get(status_url)
        status_data = status_resp.json()
        if "results" in status_data or "failedIds" in status_data:
            break
        time.sleep(2)

    # Fetch results
    results_resp = requests.get(
        f"https://rest.uniprot.org/idmapping/results/{job_id}"
    )
    return results_resp.json()

undefined

import requests

params = {
    "query": "organism_id:9606 AND reviewed:true",
    "format": "fasta"
}

resp = requests.get(
    "https://rest.uniprot.org/uniprotkb/stream",
    params=params,
    stream=True
)

with open("human_proteome.fasta", "wb") as f:
    for chunk in resp.iter_content(chunk_size=8192):
        f.write(chunk)

import requests
import time

class UniProtClient:
    BASE = "https://rest.uniprot.org"

    def __init__(self, delay=0.5):
        self.delay = delay
        self.last_call = 0

    def _throttle(self):
        elapsed = time.time() - self.last_call
        if elapsed < self.delay:
            time.sleep(self.delay - elapsed)
        self.last_call = time.time()

    def get_proteins(self, accessions, batch_size=100):
        """Fetch metadata for multiple accessions."""
        results = []

        for i in range(0, len(accessions), batch_size):
            batch = accessions[i:i+batch_size]
            query = " OR ".join(f"accession:{a}" for a in batch)

            self._throttle()
            resp = requests.get(
                f"{self.BASE}/uniprotkb/search",
                params={"query": query, "format": "json", "size": batch_size}
            )

            if resp.ok:
                results.extend(resp.json().get("results", []))

        return results

undefined

import requests

def fetch_all(query, fields=None, max_results=None):
    """Retrieve all results with automatic pagination."""
    url = "https://rest.uniprot.org/uniprotkb/search"
    collected = []

    params = {
        "query": query,
        "format": "json",
        "size": 500
    }
    if fields:
        params["fields"] = ",".join(fields)

    while url:
        resp = requests.get(url, params=params if "rest.uniprot.org" in url else None)
        data = resp.json()
        collected.extend(data["results"])

        if max_results and len(collected) >= max_results:
            return collected[:max_results]

        url = resp.links.get("next", {}).get("url")
        params = None  # Next URL contains all params

    return collected

undefined

import requests

resp = requests.get(
    "https://rest.uniprot.org/uniprotkb/search",
    params={
        "query": "gene:BRCA1 AND reviewed:true",
        "format": "json",
        "size": 1
    }
)

entry = resp.json()["results"][0]

undefined

import requests
import csv

def build_dataset(query, output_path, fields):
    """Export search results to CSV."""
    resp = requests.get(
        "https://rest.uniprot.org/uniprotkb/stream",
        params={
            "query": query,
            "format": "tsv",
            "fields": ",".join(fields)
        }
    )

    with open(output_path, "w") as f:
        f.write(resp.text)

undefined