String Database Ppi

uv pip install requests pandas

import requests
import time

STRING_API = "https://string-db.org/api"

def string_query(endpoint, params, fmt="tsv"):
    """Reusable helper for all STRING API calls."""
    url = f"{STRING_API}/{fmt}/{endpoint}"
    params.setdefault("caller_identity", "python_script")
    response = requests.get(url, params=params)
    response.raise_for_status()
    return response.text

# Map gene names to STRING IDs (always do this first)
result = string_query("get_string_ids", {
    "identifiers": "TP53\nBRCA1\nEGFR",
    "species": 9606
})
print(result)

# Get interaction network
time.sleep(1)
network = string_query("network", {
    "identifiers": "TP53%0dBRCA1%0dMDM2",
    "species": 9606,
    "required_score": 400
})
print(network[:500])

# Map gene names to STRING IDs
result = string_query("get_string_ids", {
    "identifiers": "TP53\nBRCA1\nEGFR",
    "species": 9606,
    "limit": 1,        # matches per identifier
    "echo_query": 1    # include query term in output
})

# Parse the mapping
import pandas as pd
import io
df = pd.read_csv(io.StringIO(result), sep='\t')
id_map = dict(zip(df['queryItem'], df['stringId']))
print(id_map)
# {'TP53': '9606.ENSP00000269305', 'BRCA1': '9606.ENSP00000...', ...}

# Get PPI network with confidence scores
network = string_query("network", {
    "identifiers": "TP53%0dBRCA1%0dMDM2%0dATM%0dCHEK2",
    "species": 9606,
    "required_score": 400,
    "network_type": "functional"  # or "physical"
})

# Parse network edges
time.sleep(1)
df = pd.read_csv(io.StringIO(network), sep='\t')
print(f"Found {len(df)} interactions")
print(df[['preferredName_A', 'preferredName_B', 'score']].head())

# Expand network with additional interactors
expanded = string_query("network", {
    "identifiers": "TP53",
    "species": 9606,
    "add_nodes": 10,  # add 10 most connected proteins
    "required_score": 700
})

# Get PNG network image
url = f"{STRING_API}/image/network"
params = {
    "identifiers": "TP53%0dMDM2%0dATM%0dCHEK2%0dBRCA1",
    "species": 9606,
    "required_score": 700,
    "network_flavor": "evidence",  # "evidence", "confidence", or "actions"
    "caller_identity": "python_script"
}
response = requests.get(url, params=params)
with open("network.png", "wb") as f:
    f.write(response.content)

# Discover top interaction partners
partners = string_query("interaction_partners", {
    "identifiers": "TP53",
    "species": 9606,
    "limit": 20,
    "required_score": 700
})

df = pd.read_csv(io.StringIO(partners), sep='\t')
print(f"Top 20 TP53 interactors:")
print(df[['preferredName_B', 'score']].head(10))

# GO, KEGG, Pfam, InterPro, SMART, UniProt Keywords enrichment
# Statistical method: Fisher's exact test with Benjamini-Hochberg FDR correction
enrichment = string_query("enrichment", {
    "identifiers": "TP53%0dMDM2%0dATM%0dCHEK2%0dBRCA1%0dATR%0dTP73",
    "species": 9606
})

df = pd.read_csv(io.StringIO(enrichment), sep='\t')
significant = df[df['fdr'] < 0.05]
print(f"Significant terms: {len(significant)}")

# Group by annotation category
for cat, group in significant.groupby('category'):
    print(f"\n{cat}: {len(group)} terms")
    for _, row in group.head(3).iterrows():
        print(f"  {row['description']} (FDR={row['fdr']:.2e})")

import json

# Test if proteins form a significant functional module
result = string_query("ppi_enrichment", {
    "identifiers": "TP53%0dMDM2%0dATM%0dCHEK2%0dBRCA1",
    "species": 9606,
    "required_score": 400
}, fmt="json")

data = json.loads(result)
print(f"Observed edges: {data['number_of_edges']}")
print(f"Expected edges: {data['expected_number_of_edges']}")
print(f"P-value: {data['p_value']}")
# p < 0.05 → proteins form a significantly enriched network

# Get homology/similarity between proteins
homology = string_query("homology", {
    "identifiers": "TP53%0dTP63%0dTP73",
    "species": 9606
})
print(homology)

import requests, pandas as pd, io, json, time

STRING_API = "https://string-db.org/api"
def string_query(endpoint, params, fmt="tsv"):
    url = f"{STRING_API}/{fmt}/{endpoint}"
    params.setdefault("caller_identity", "python_script")
    response = requests.get(url, params=params)
    response.raise_for_status()
    time.sleep(1)
    return response.text

genes = "TP53%0dBRCA1%0dATM%0dCHEK2%0dMDM2%0dATR%0dBRCA2"

# Step 1: Map identifiers
mapping = string_query("get_string_ids", {"identifiers": genes.replace("%0d", "\n"), "species": 9606})

# Step 2: Get interaction network
network = string_query("network", {"identifiers": genes, "species": 9606, "required_score": 400})
net_df = pd.read_csv(io.StringIO(network), sep='\t')
print(f"Network: {len(net_df)} interactions")

# Step 3: Test PPI enrichment
ppi = json.loads(string_query("ppi_enrichment", {"identifiers": genes, "species": 9606}, fmt="json"))
print(f"PPI enrichment p-value: {ppi['p_value']}")

# Step 4: Functional enrichment
enrich = string_query("enrichment", {"identifiers": genes, "species": 9606})
enrich_df = pd.read_csv(io.StringIO(enrich), sep='\t')
sig = enrich_df[enrich_df['fdr'] < 0.05]
print(f"Significant GO/KEGG terms: {len(sig)}")

# Step 5: Save network image
img_resp = requests.get(f"{STRING_API}/image/network", params={
    "identifiers": genes, "species": 9606, "required_score": 400,
    "network_flavor": "evidence", "caller_identity": "python_script"
})
with open("protein_network.png", "wb") as f:
    f.write(img_resp.content)

# Start with seed proteins, discover connected functional modules
seed = "TP53"

# Step 1: Get high-confidence interaction partners
partners = string_query("interaction_partners", {
    "identifiers": seed, "species": 9606, "limit": 30, "required_score": 700
})
df = pd.read_csv(io.StringIO(partners), sep='\t')
all_proteins = list(set(df['preferredName_A'].tolist() + df['preferredName_B'].tolist()))
print(f"Expanded network: {len(all_proteins)} proteins")

# Step 2: Enrichment on expanded set
expanded_ids = "%0d".join(all_proteins[:50])
enrichment = string_query("enrichment", {"identifiers": expanded_ids, "species": 9606})
enrich_df = pd.read_csv(io.StringIO(enrichment), sep='\t')
modules = enrich_df[enrich_df['fdr'] < 0.001]
print(f"Highly significant terms: {len(modules)}")

# Compare protein interactions across species
for species, name, gene in [(9606, "Human", "TP53"), (10090, "Mouse", "Trp53")]:
    network = string_query("network", {
        "identifiers": gene, "species": species,
        "required_score": 700, "add_nodes": 5
    })
    df = pd.read_csv(io.StringIO(network), sep='\t')
    print(f"{name} ({gene}): {len(df)} interactions at score >= 700")

import pandas as pd, io

enrichment_tsv = string_query("enrichment", {
    "identifiers": "TP53%0dBRCA1%0dATM", "species": 9606
})
df = pd.read_csv(io.StringIO(enrichment_tsv), sep='\t')
# Columns: category, term, description, number_of_genes, p_value, fdr
kegg = df[df['category'] == 'KEGG'].sort_values('fdr')
print(kegg[['description', 'fdr']].head(5))

import time

protein_lists = [["TP53", "MDM2"], ["EGFR", "ERBB2"], ["BRCA1", "BRCA2"]]
results = []
for proteins in protein_lists:
    ids = "%0d".join(proteins)
    network = string_query("network", {"identifiers": ids, "species": 9606})
    results.append(network)
    time.sleep(1)  # respect rate limits

version = string_query("version", {})
print(f"STRING version: {version.strip()}")
# Include in methods section: "STRING v{version}, accessed {date}"