Interpro Database

pip install requests pandas matplotlib

import requests

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

def interpro_get(path: str, params: dict = None) -> dict:
    """Send a GET request to the InterPro API and return parsed JSON."""
    r = requests.get(
        f"{INTERPRO_BASE}/{path}",
        params=params,
        headers={"Accept": "application/json"},
        timeout=30
    )
    r.raise_for_status()
    return r.json()

# Get domain architecture for TP53 (P04637)
# Note: `protein/uniprot/{acc}/` returns only {metadata}; the entries-per-protein
# data lives at `entry/interpro/protein/uniprot/{acc}/` and is keyed `results`.
data = interpro_get("entry/interpro/protein/uniprot/P04637/")
entries = data.get("results", [])
print(f"InterPro entries for TP53: {data.get('count')}  (this page: {len(entries)})")
for e in entries[:4]:
    m = e["metadata"]
    print(f"  {m['accession']}  {m['type']:<25}  {m['name']}")
# InterPro entries for TP53: 9
#   IPR002117  family                     p53 tumour suppressor family
#   IPR036674  homologous_superfamily     p53-like tetramerisation domain superfamily

import requests

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

def search_entries(query: str, entry_type: str = None,
                   page_size: int = 20) -> list:
    """Search InterPro entries by keyword; optionally filter by type."""
    params = {"search": query, "page_size": page_size}
    if entry_type:
        params["type"] = entry_type   # family, domain, homologous_superfamily, repeat, site
    r = requests.get(
        f"{INTERPRO_BASE}/entry/interpro/",
        params=params,
        headers={"Accept": "application/json"},
        timeout=30
    )
    r.raise_for_status()
    return r.json().get("results", [])

hits = search_entries("serine kinase", entry_type="domain")
print(f"InterPro domain entries matching 'serine kinase': {len(hits)}")
for h in hits[:5]:
    m = h["metadata"]
    print(f"  {m['accession']}  {m['type']:<10}  {m['name']}")
# InterPro domain entries matching 'serine kinase': 8
#   IPR000719  domain    Protein kinase domain
#   IPR008271  domain    Serine/threonine/tyrosine kinase, active site

# Fetch a specific InterPro entry by accession
r = requests.get(
    f"{INTERPRO_BASE}/entry/interpro/IPR000719/",
    headers={"Accept": "application/json"},
    timeout=30
)
r.raise_for_status()
meta = r.json()["metadata"]
print(f"Accession    : {meta['accession']}")
print(f"Name         : {meta['name']}")
print(f"Type         : {meta['type']}")
print(f"Member DBs   : {list(meta.get('member_databases', {}).keys())}")
go_terms = meta.get("go_terms", [])
print(f"GO terms     : {[g['identifier'] for g in go_terms[:3]]}")
# Accession    : IPR000719
# Name         : Protein kinase domain
# Type         : domain
# Member DBs   : ['pfam', 'smart', 'cdd', 'ncbifam', 'panther']
# GO terms     : ['GO:0004672', 'GO:0005524', 'GO:0006468']

import requests

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

def get_protein_domain_architecture(uniprot_acc: str) -> dict:
    """Return all InterPro entry matches for a protein. Uses the
    `entry/interpro/protein/uniprot/{acc}/` endpoint, which returns
    {count, next, previous, results}. Each result has metadata + a
    nested `proteins[0].entry_protein_locations` for the per-protein match."""
    r = requests.get(
        f"{INTERPRO_BASE}/entry/interpro/protein/uniprot/{uniprot_acc}/",
        headers={"Accept": "application/json"},
        timeout=60
    )
    r.raise_for_status()
    return r.json()

data = get_protein_domain_architecture("P04637")   # TP53
results = data.get("results", [])
# Pull length/source from the first match's nested protein record
prot0 = results[0]["proteins"][0] if results and results[0].get("proteins") else {}
print(f"Protein length : {prot0.get('protein_length')}")
print(f"Source DB      : {prot0.get('source_database')}")
print(f"InterPro entries: {data.get('count')}")
for entry in results[:6]:
    m = entry["metadata"]
    # Locations are nested under proteins[0].entry_protein_locations
    locs = entry["proteins"][0].get("entry_protein_locations", []) if entry.get("proteins") else []
    loc_str = ", ".join(
        f"{frag['start']}-{frag['end']}"
        for loc in locs for frag in loc.get("fragments", [])
    )
    print(f"  {m['accession']}  {m['type']:<25}  {m['name'][:35]:<35}  [{loc_str}]")

# Compare domain architectures of two proteins side-by-side
import pandas as pd

def domain_set(uniprot_acc: str) -> set:
    data = get_protein_domain_architecture(uniprot_acc)
    return {e["metadata"]["accession"] for e in data.get("results", [])}

brca1_domains = domain_set("P38398")   # BRCA1
tp53_domains   = domain_set("P04637")  # TP53

shared = brca1_domains & tp53_domains
unique_brca1 = brca1_domains - tp53_domains
unique_tp53  = tp53_domains - brca1_domains
print(f"Shared InterPro entries: {len(shared)}")
print(f"BRCA1-unique           : {len(unique_brca1)}")
print(f"TP53-unique            : {len(unique_tp53)}")

import requests, time

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

def get_entry_proteins(interpro_acc: str, reviewed_only: bool = True,
                       page_size: int = 50) -> list:
    """Return proteins (UniProt) containing a given InterPro entry.
    Path order is `/protein/{db}/entry/interpro/{IPR}/` — the inverse
    `entry/interpro/{IPR}/protein/{db}/` times out (408) on large families."""
    db = "reviewed" if reviewed_only else "uniprot"
    r = requests.get(
        f"{INTERPRO_BASE}/protein/{db}/entry/interpro/{interpro_acc}/",
        params={"page_size": page_size},
        headers={"Accept": "application/json"},
        timeout=60
    )
    r.raise_for_status()
    return r.json().get("results", [])

proteins = get_entry_proteins("IPR011009")   # Protein kinase-like domain SF
print(f"Reviewed proteins with IPR011009 (page 1): {len(proteins)}")
for p in proteins[:4]:
    m = p["metadata"]
    # metadata fields: accession, gene, length, name, source_database, source_organism
    print(f"  {m['accession']}  {(m.get('gene') or ''):<8}  "
          f"len={m.get('length', '?')}  "
          f"org={(m.get('source_organism') or {}).get('scientificName', '')[:30]}")

# Paginate all proteins for a family using cursor
def get_all_entry_proteins(interpro_acc: str,
                            reviewed_only: bool = True) -> list:
    INTERPRO_BASE = "https://www.ebi.ac.uk/interpro/api"
    db = "reviewed" if reviewed_only else "uniprot"
    # Path-inverted: /protein/{db}/entry/interpro/{IPR}/ is the working order
    url = f"{INTERPRO_BASE}/protein/{db}/entry/interpro/{interpro_acc}/"
    all_proteins = []
    params = {"page_size": 200}
    while url:
        r = requests.get(url, params=params,
                         headers={"Accept": "application/json"}, timeout=60)
        r.raise_for_status()
        data = r.json()
        all_proteins.extend(data.get("results", []))
        url = data.get("next")
        params = None   # next URL already has params encoded
        if url:
            time.sleep(1.0)
    return all_proteins

proteins = get_all_entry_proteins("IPR000719")   # Protein kinase domain
print(f"Total reviewed proteins with protein kinase domain: {len(proteins)}")

import requests

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

def get_entry_taxonomy(interpro_acc: str,
                        page_size: int = 50) -> list:
    """Return taxonomic summary for proteins in a given InterPro entry.
    Path-inverted: `/taxonomy/uniprot/entry/interpro/{IPR}/`. Each result
    has `metadata` (taxon: accession=taxId, name, parent, children, rank)
    and `entries[]` (representative protein-match locations for that taxon)."""
    r = requests.get(
        f"{INTERPRO_BASE}/taxonomy/uniprot/entry/interpro/{interpro_acc}/",
        params={"page_size": page_size},
        headers={"Accept": "application/json"},
        timeout=90
    )
    r.raise_for_status()
    return r.json().get("results", [])

# Use a smaller entry (p53 DBD); IPR000719 (kinase) has ~270k taxa and times out.
taxa = get_entry_taxonomy("IPR011615")
print(f"Top taxa for IPR011615 (p53 DNA-binding domain):")
for t in taxa[:8]:
    m = t["metadata"]
    print(f"  taxId={m['accession']:>10}  {m.get('name', ''):<30}  "
          f"rank={m.get('rank') or 'n/a'}")

import requests

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

def get_entry_structures(interpro_acc: str, page_size: int = 25) -> list:
    """Return PDB structures that include a match to a given InterPro entry.
    Path-inverted: `/structure/pdb/entry/interpro/{IPR}/`. The flat form with
    `?entry_interpro=...` is silently slow / 408s on this resource."""
    r = requests.get(
        f"{INTERPRO_BASE}/structure/pdb/entry/interpro/{interpro_acc}/",
        params={"page_size": page_size},
        headers={"Accept": "application/json"},
        timeout=60
    )
    r.raise_for_status()
    return r.json().get("results", [])

structures = get_entry_structures("IPR011009")   # Protein kinase-like SF
print(f"PDB structures linked to IPR011009 (page 1): {len(structures)}")
for s in structures[:5]:
    m = s["metadata"]
    print(f"  {m['accession'].upper()}  resolution={m.get('resolution', 'N/A')} Å  "
          f"experiment={m.get('experiment_type', 'N/A')}")
# PDB structures linked to IPR011009: ~8,000+
#   1A06  resolution=2.5 Å  experiment=x-ray
#   ...

import requests, time

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

def get_family_fasta(interpro_acc: str,
                      reviewed_only: bool = True,
                      max_sequences: int = 100) -> str:
    """Retrieve FASTA sequences for proteins in an InterPro entry."""
    db = "reviewed" if reviewed_only else "uniprot"
    proteins = []
    # Path-inverted: protein-list-for-entry is /protein/{db}/entry/interpro/{IPR}/
    url = f"{INTERPRO_BASE}/protein/{db}/entry/interpro/{interpro_acc}/"
    params = {"page_size": min(max_sequences, 200)}
    while url and len(proteins) < max_sequences:
        r = requests.get(url, params=params,
                         headers={"Accept": "application/json"}, timeout=60)
        r.raise_for_status()
        data = r.json()
        proteins.extend(data.get("results", []))
        url = data.get("next") if len(proteins) < max_sequences else None
        params = None
        if url:
            time.sleep(1.0)

    # Fetch FASTA from UniProt for each accession
    accessions = [p["metadata"]["accession"] for p in proteins[:max_sequences]]
    fasta_url = "https://rest.uniprot.org/uniprotkb/stream"
    query = " OR ".join(f"accession:{acc}" for acc in accessions)
    r = requests.get(fasta_url,
                     params={"query": query, "format": "fasta"},
                     timeout=120)
    r.raise_for_status()
    return r.text

fasta = get_family_fasta("IPR000719", reviewed_only=True, max_sequences=20)
seq_count = fasta.count(">")
print(f"FASTA sequences retrieved: {seq_count}")
print(fasta[:300])   # preview first sequence header + start

import requests, time

def iterate_interpro(url: str, page_size: int = 200) -> list:
    """Generic paginator for any InterPro list endpoint."""
    results = []
    params = {"page_size": page_size}
    while url:
        r = requests.get(url, params=params,
                         headers={"Accept": "application/json"}, timeout=60)
        r.raise_for_status()
        data = r.json()
        results.extend(data.get("results", []))
        url = data.get("next")
        params = None
        if url:
            time.sleep(1.0)
    return results

import requests, time, pandas as pd

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

def get_domains(uniprot_acc: str) -> list:
    """List InterPro entries for a protein. Uses the
    `entry/interpro/protein/uniprot/{acc}/` endpoint (keyed `results`)."""
    r = requests.get(
        f"{INTERPRO_BASE}/entry/interpro/protein/uniprot/{uniprot_acc}/",
        headers={"Accept": "application/json"}, timeout=60
    )
    if r.status_code == 404:
        return []
    r.raise_for_status()
    data = r.json()
    return [
        {
            "protein": uniprot_acc,
            "accession": e["metadata"]["accession"],
            "name": e["metadata"]["name"],
            "type": e["metadata"]["type"],
            "source_db": list(e["metadata"].get("member_databases", {}).keys()),
        }
        for e in data.get("results", [])
    ]

proteins = ["P04637", "P38398", "Q00987", "P10415"]  # TP53, BRCA1, MDM2, BCL2
rows = []
for acc in proteins:
    rows.extend(get_domains(acc))
    time.sleep(1.0)

df = pd.DataFrame(rows)
print(f"Total domain matches: {len(df)}")
print(df.groupby(["protein", "type"])["accession"].count().unstack(fill_value=0))

# Pivot: proteins × domain accessions
pivot = df[df["type"] == "domain"].pivot_table(
    index="protein", columns="accession", aggfunc="size", fill_value=0
)
pivot.to_csv("domain_architecture_matrix.csv")
print(f"\nDomain × protein matrix: {pivot.shape}")

import requests, time, pandas as pd

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

# Step 1: Get PDB structures linked to the protein kinase-like SF entry.
# Use the path-inverted form; the flat `?entry_interpro=` filter 408s.
r = requests.get(
    f"{INTERPRO_BASE}/structure/pdb/entry/interpro/IPR011009/",
    params={"page_size": 200},
    headers={"Accept": "application/json"}, timeout=60
)
r.raise_for_status()
structures = r.json().get("results", [])
print(f"PDB structures with IPR011009 (kinase-like SF, page 1): {len(structures)}")

rows = []
for s in structures:
    m = s["metadata"]
    rows.append({
        "pdb_id": m["accession"],
        "resolution": m.get("resolution"),
        "experiment": m.get("experiment_type", ""),
        "name": m.get("name", ""),
    })

df = pd.DataFrame(rows)
df = df.dropna(subset=["resolution"]).sort_values("resolution")
print(f"\nTop 10 highest-resolution kinase structures:")
print(df[["pdb_id", "resolution", "experiment", "name"]].head(10).to_string(index=False))
df.to_csv("kinase_structures.csv", index=False)
print(f"\nSaved kinase_structures.csv ({len(df)} X-ray / cryo-EM structures)")

import requests, time
import pandas as pd
import matplotlib.pyplot as plt

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

def get_taxonomy_counts(interpro_acc: str, page_size: int = 100,
                        max_pages: int = 5) -> pd.DataFrame:
    """Walk the taxonomy results for an InterPro entry. The API does not
    expose a per-taxon protein count at this endpoint — instead each
    paged record is one (taxon × representative protein-match) row.
    Aggregate client-side by taxon name to approximate frequency."""
    rows, url = [], f"{INTERPRO_BASE}/taxonomy/uniprot/entry/interpro/{interpro_acc}/"
    params = {"page_size": page_size}
    for _ in range(max_pages):
        if not url:
            break
        r = requests.get(url, params=params,
                         headers={"Accept": "application/json"}, timeout=90)
        r.raise_for_status()
        data = r.json()
        for t in data.get("results", []):
            m = t["metadata"]
            rows.append({
                "taxon_id": m["accession"],
                "name": m.get("name", ""),
                "rank": m.get("rank") or "",
            })
        url = data.get("next")
        params = None
        if url:
            time.sleep(1.0)
    return pd.DataFrame(rows)

IPR_ACC = "IPR011615"   # p53 DNA-binding domain (smaller; kinase 408s)
df = get_taxonomy_counts(IPR_ACC, max_pages=3)
print(f"Tax entries pulled for {IPR_ACC}: {len(df)}")

# Aggregate by name and take top 15 (each row = one rep. protein-match)
top = (df.groupby("name").size().sort_values(ascending=False).head(15)
       .reset_index(name="rep_matches"))
fig, ax = plt.subplots(figsize=(10, 5))
bars = ax.barh(top["name"], top["rep_matches"], color="#2171B5")
ax.bar_label(bars, fmt="%d", padding=3, fontsize=8)
ax.set_xlabel("Representative protein-matches")
ax.set_title(f"Taxonomic distribution of {IPR_ACC} (p53 DNA-binding domain)")
ax.invert_yaxis()
plt.tight_layout()
plt.savefig(f"{IPR_ACC}_taxonomy.png", dpi=150, bbox_inches="tight")
print(f"Saved {IPR_ACC}_taxonomy.png")