Uniprot Protein Database

pip install requests pandas

import requests

# Search for human insulin proteins (reviewed/Swiss-Prot only)
url = "https://rest.uniprot.org/uniprotkb/search"
params = {"query": "insulin AND organism_id:9606 AND reviewed:true", "format": "tsv",
          "fields": "accession,gene_names,protein_name,length"}
response = requests.get(url, params=params)
print(response.text[:500])
# accession  gene_names  protein_name  length
# P01308     INS         Insulin       110

import requests
import time

BASE = "https://rest.uniprot.org/uniprotkb/search"

def search_uniprot(query, fields=None, format="json", size=25):
    """Search UniProt with query syntax."""
    params = {"query": query, "format": format, "size": size}
    if fields:
        params["fields"] = ",".join(fields)
    resp = requests.get(BASE, params=params)
    resp.raise_for_status()
    return resp.json() if format == "json" else resp.text

# Search by gene name
results = search_uniprot("gene:BRCA1 AND reviewed:true",
                         fields=["accession", "gene_names", "organism_name", "length"])
for entry in results["results"][:3]:
    print(f"{entry['primaryAccession']} | {entry.get('genes', [{}])[0].get('geneName', {}).get('value', 'N/A')} | {entry.get('organism', {}).get('scientificName', 'N/A')}")

# Boolean operators
kinase AND organism_id:9606          # Human kinases
(diabetes OR insulin) AND reviewed:true
cancer NOT lung

# Field-specific
gene:BRCA1
accession:P12345
taxonomy_name:"Homo sapiens"
go:0005515                           # GO term: protein binding

# Range queries
length:[100 TO 500]
mass:[50000 TO 100000]

# Wildcards
gene:BRCA*

import requests

def get_protein(accession, format="json"):
    """Retrieve a single protein entry."""
    url = f"https://rest.uniprot.org/uniprotkb/{accession}"
    resp = requests.get(url, headers={"Accept": f"application/{format}"})
    resp.raise_for_status()
    return resp.json() if format == "json" else resp.text

# Get human insulin
entry = get_protein("P01308")
print(f"Protein: {entry['proteinDescription']['recommendedName']['fullName']['value']}")
print(f"Gene: {entry['genes'][0]['geneName']['value']}")
print(f"Length: {entry['sequence']['length']} aa")
print(f"Sequence: {entry['sequence']['value'][:50]}...")

# Get FASTA directly
fasta = requests.get("https://rest.uniprot.org/uniprotkb/P01308.fasta").text
print(fasta[:200])

import requests
import time

def map_ids(ids, from_db, to_db):
    """Map identifiers between databases (async job)."""
    # Submit job
    resp = requests.post("https://rest.uniprot.org/idmapping/run",
                         data={"from": from_db, "to": to_db, "ids": ",".join(ids)})
    resp.raise_for_status()
    job_id = resp.json()["jobId"]

    # Poll for completion
    while True:
        status = requests.get(f"https://rest.uniprot.org/idmapping/status/{job_id}").json()
        if "results" in status or "failedIds" in status:
            break
        time.sleep(1)

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

# UniProt → PDB mapping
results = map_ids(["P01308", "P12345"], from_db="UniProtKB_AC-ID", to_db="PDB")
for r in results.get("results", []):
    print(f"{r['from']} → PDB: {r['to']}")

# UniProt → Ensembl mapping
results = map_ids(["P01308"], from_db="UniProtKB_AC-ID", to_db="Ensembl")
for r in results.get("results", []):
    print(f"{r['from']} → Ensembl: {r['to']}")

import requests
import time

def batch_retrieve(accessions, fields=None, format="tsv"):
    """Retrieve multiple proteins by accession."""
    query = " OR ".join(f"accession:{acc}" for acc in accessions)
    params = {"query": query, "format": format}
    if fields:
        params["fields"] = ",".join(fields)
    resp = requests.get("https://rest.uniprot.org/uniprotkb/search", params=params)
    resp.raise_for_status()
    return resp.text

# Batch retrieve
accessions = ["P01308", "P12345", "Q9Y6K9"]
tsv = batch_retrieve(accessions, fields=["accession", "gene_names", "protein_name", "length"])
print(tsv)

# Streaming for large queries (no pagination needed)
def stream_query(query, format="fasta"):
    """Stream large result sets."""
    url = f"https://rest.uniprot.org/uniprotkb/stream?query={query}&format={format}"
    resp = requests.get(url, stream=True)
    resp.raise_for_status()
    for chunk in resp.iter_content(chunk_size=8192, decode_unicode=True):
        yield chunk

# Stream all human kinases as FASTA
# for chunk in stream_query("kinase AND organism_id:9606 AND reviewed:true"):
#     print(chunk[:200])

import requests

def paginate_search(query, fields=None, page_size=500):
    """Iterate all pages of a UniProt search using cursor pagination."""
    params = {"query": query, "format": "tsv", "size": page_size}
    if fields:
        params["fields"] = ",".join(fields)
    url = "https://rest.uniprot.org/uniprotkb/search"
    rows = []
    header = None
    while url:
        resp = requests.get(url, params=params)
        resp.raise_for_status()
        params = {}  # cursor is embedded in the next URL
        lines = resp.text.strip().split("\n")
        if header is None:
            header = lines[0]
        rows.extend(lines[1:])
        # Follow Link header for next page
        link = resp.headers.get("Link", "")
        url = link.split("<")[1].split(">")[0] if "<" in link else None
    return header, rows

header, rows = paginate_search(
    "kinase AND organism_id:9606 AND reviewed:true",
    fields=["accession", "gene_names", "length"]
)
print(f"Retrieved {len(rows)} proteins")
print(header)
print("\n".join(rows[:3]))

import requests
import pandas as pd
from io import StringIO

# Retrieve specific annotation fields
params = {
    "query": "gene:TP53 AND organism_id:9606 AND reviewed:true",
    "format": "tsv",
    "fields": "accession,gene_names,protein_name,go_p,go_f,go_c,cc_function,ft_domain",
}
resp = requests.get("https://rest.uniprot.org/uniprotkb/search", params=params)
df = pd.read_csv(StringIO(resp.text), sep="\t")
print(df.columns.tolist())
print(df.iloc[0])