Interpro Database

import requests

BASE_URL = "https://www.ebi.ac.uk/interpro/api"

def interpro_get(endpoint, params=None):
    url = f"{BASE_URL}/{endpoint}"
    headers = {"Accept": "application/json"}
    response = requests.get(url, params=params, headers=headers)
    response.raise_for_status()
    return response.json()

def get_protein_entries(uniprot_id):
    """Get all InterPro entries that match a UniProt protein."""
    data = interpro_get(f"protein/UniProt/{uniprot_id}/entry/InterPro/")
    return data

# Example: Human p53 (TP53)
result = get_protein_entries("P04637")
entries = result.get("results", [])

for entry in entries:
    meta = entry["metadata"]
    print(f"  {meta['accession']} ({meta['type']}): {meta['name']}")
    # e.g., IPR011615 (domain): p53, tetramerisation domain
    #       IPR010991 (domain): p53, DNA-binding domain
    #       IPR013872 (family): p53 family

def get_entry(interpro_id):
    """Fetch details for an InterPro entry."""
    return interpro_get(f"entry/InterPro/{interpro_id}/")

# Example: Get Pfam domain PF00397 (WW domain)
ww_entry = get_entry("IPR001202")
print(f"Name: {ww_entry['metadata']['name']}")
print(f"Type: {ww_entry['metadata']['type']}")

# Also supports member database IDs:
def get_pfam_entry(pfam_id):
    return interpro_get(f"entry/Pfam/{pfam_id}/")

pfam = get_pfam_entry("PF00397")

def get_proteins_for_entry(interpro_id, database="UniProt", page_size=25):
    """Get all proteins annotated with an InterPro entry."""
    params = {"page_size": page_size}
    data = interpro_get(f"entry/InterPro/{interpro_id}/protein/{database}/", params)
    return data

# Example: Find all human kinase-domain proteins
kinase_proteins = get_proteins_for_entry("IPR000719")  # Protein kinase domain
print(f"Total proteins: {kinase_proteins['count']}")

def get_domain_architecture(uniprot_id):
    """Get the complete domain architecture of a protein."""
    data = interpro_get(f"protein/UniProt/{uniprot_id}/")
    return data

# Example: Get full domain architecture for EGFR
egfr = get_domain_architecture("P00533")

# The response includes locations of all matching entries on the sequence
for entry in egfr.get("entries", []):
    for fragment in entry.get("entry_protein_locations", []):
        for loc in fragment.get("fragments", []):
            print(f"  {entry['accession']}: {loc['start']}-{loc['end']}")

def get_go_terms_for_protein(uniprot_id):
    """Get GO terms associated with a protein via InterPro."""
    data = interpro_get(f"protein/UniProt/{uniprot_id}/")

    # GO terms are embedded in the entry metadata
    go_terms = []
    for entry in data.get("entries", []):
        go = entry.get("metadata", {}).get("go_terms", [])
        go_terms.extend(go)

    # Deduplicate
    seen = set()
    unique_go = []
    for term in go_terms:
        if term["identifier"] not in seen:
            seen.add(term["identifier"])
            unique_go.append(term)

    return unique_go

# GO terms include:
# {"identifier": "GO:0004672", "name": "protein kinase activity", "category": {"code": "F", "name": "Molecular Function"}}

def batch_lookup_proteins(uniprot_ids, database="UniProt"):
    """Look up multiple proteins and collect their InterPro entries."""
    import time
    results = {}
    for uid in uniprot_ids:
        try:
            data = interpro_get(f"protein/{database}/{uid}/entry/InterPro/")
            entries = data.get("results", [])
            results[uid] = [
                {
                    "accession": e["metadata"]["accession"],
                    "name": e["metadata"]["name"],
                    "type": e["metadata"]["type"]
                }
                for e in entries
            ]
        except Exception as e:
            results[uid] = {"error": str(e)}
        time.sleep(0.3)  # Rate limiting
    return results

# Example
proteins = ["P04637", "P00533", "P38398", "Q9Y6I9"]
domain_info = batch_lookup_proteins(proteins)
for uid, entries in domain_info.items():
    print(f"\n{uid}:")
    for e in entries[:3]:
        print(f"  - {e['accession']} ({e['type']}): {e['name']}")

def search_entries(query, entry_type=None, taxonomy_id=None):
    """Search InterPro entries by text."""
    params = {"search": query, "page_size": 20}
    if entry_type:
        params["type"] = entry_type  # family, domain, homologous_superfamily, etc.

    endpoint = "entry/InterPro/"
    if taxonomy_id:
        endpoint = f"entry/InterPro/taxonomy/UniProt/{taxonomy_id}/"

    return interpro_get(endpoint, params)

# Search for kinase-related entries
kinase_entries = search_entries("kinase", entry_type="domain")

# After running InterProScan and getting a UniProt ID:
def characterize_protein(uniprot_id):
    """Complete characterization workflow."""

    # 1. Get all annotations
    entries = get_protein_entries(uniprot_id)

    # 2. Group by type
    by_type = {}
    for e in entries.get("results", []):
        t = e["metadata"]["type"]
        by_type.setdefault(t, []).append({
            "accession": e["metadata"]["accession"],
            "name": e["metadata"]["name"]
        })

    # 3. Get GO terms
    go_terms = get_go_terms_for_protein(uniprot_id)

    return {
        "families": by_type.get("family", []),
        "domains": by_type.get("domain", []),
        "superfamilies": by_type.get("homologous_superfamily", []),
        "go_terms": go_terms
    }