Emdb Database

pip install requests pandas matplotlib

import requests

EMDB_API   = "https://www.ebi.ac.uk/emdb/api"
EBI_SEARCH = "https://www.ebi.ac.uk/ebisearch/ws/rest/emdb"

# Keyword search via EBI Search WS (NOT /emdb/api/search/, which ignores q=)
r = requests.get(EBI_SEARCH,
                 params={"query": "sars-cov-2 spike", "size": 5, "format": "json",
                         "fields": "id,name,resolution,em_method,organism"},
                 timeout=30)
r.raise_for_status()
res = r.json()
print(f"Total hits: {res['hitCount']}")
for e in res["entries"]:
    f = e["fields"]
    name = (f.get("name") or [""])[0][:60]
    resol = (f.get("resolution") or ["?"])[0]
    print(f"  {e['id']}: {name}  ({resol} Å)")

import requests, pandas as pd

EBI_SEARCH = "https://www.ebi.ac.uk/ebisearch/ws/rest/emdb"

def emdb_search(query, size=20, start=0,
                fields="id,name,resolution,em_method,organism"):
    r = requests.get(EBI_SEARCH,
                     params={"query": query, "size": size, "start": start,
                             "format": "json", "fields": fields},
                     timeout=30)
    r.raise_for_status()
    return r.json()

data = emdb_search("ribosome 70S", size=10)
rows = []
for e in data["entries"]:
    f = e["fields"]
    rows.append({
        "emdb_id": e["id"],
        "name": (f.get("name") or [""])[0],
        "resolution_A": float((f.get("resolution") or [0])[0] or 0) or None,
        "em_method": (f.get("em_method") or [""])[0],
        "organism": (f.get("organism") or [""])[0],
    })
df = pd.DataFrame(rows)
print(f"hitCount={data['hitCount']}; first {len(df)} rows:")
print(df.to_string(index=False))

# Paged retrieval — iterate `start` until exhausting hitCount
def emdb_search_all(query, size=100, max_pages=5,
                    fields="id,name,resolution,em_method"):
    out = []
    for page in range(max_pages):
        d = emdb_search(query, size=size, start=page * size, fields=fields)
        if not d["entries"]:
            break
        out.extend(d["entries"])
        if len(out) >= d["hitCount"]:
            break
    return out

hits = emdb_search_all("ferritin", size=50, max_pages=2)
print(f"Pulled {len(hits)} ferritin entries")

import requests

EMDB_API = "https://www.ebi.ac.uk/emdb/api"

def emdb_entry(emdb_id):
    r = requests.get(f"{EMDB_API}/entry/{emdb_id}", timeout=30)
    r.raise_for_status()
    return r.json()

e = emdb_entry("EMD-30210")  # nsp12-nsp7-nsp8 + Remdesivir (RdRp)
print(f"Title       : {e['admin']['title']}")
print(f"Status      : {e['admin']['current_status']}")
print(f"Key dates   : {e['admin'].get('key_dates')}")

sd = e["structure_determination_list"]["structure_determination"][0]
ip = sd["image_processing"][0]
res = ip["final_reconstruction"]["resolution"]
print(f"Method      : {sd['method']}")
print(f"Resolution  : {res['valueOf_']} {res['units']}  (type: {res['res_type']})")

import requests

EMDB_API = "https://www.ebi.ac.uk/emdb/api"
e = requests.get(f"{EMDB_API}/entry/EMD-30210", timeout=30).json()

m = e["map"]
print(f"Map file     : {m.get('file')}")          # e.g. emd_30210.map.gz
print(f"Format       : {m.get('format')}")        # 'CCP4'
print(f"Dimensions   : {m.get('dimensions')}")    # {'col': ..., 'row': ..., 'sec': ...}
print(f"Axis order   : {m.get('axis_order')}")    # {'fast': 'X', 'medium': 'Y', 'slow': 'Z'}
print(f"Contour list : {m.get('contour_list')}")  # recommended threshold(s)

# Conventional FTP/HTTPS download URL pattern (mirror at EBI):
EMDB_FTP = "https://ftp.ebi.ac.uk/pub/databases/emdb/structures"
emdb_num = "EMD-30210"
print(f"Download URL : {EMDB_FTP}/{emdb_num}/map/{m['file']}")

import requests

EMDB_API = "https://www.ebi.ac.uk/emdb/api"
e = requests.get(f"{EMDB_API}/entry/EMD-30210", timeout=30).json()

pdblist = e.get("crossreferences", {}).get("pdb_list", {})
pdb_refs = pdblist.get("pdb_reference", []) if isinstance(pdblist, dict) else []
print(f"Fitted PDB entries: {len(pdb_refs)}")
for ref in pdb_refs:
    in_frame = (ref.get("relationship") or {}).get("in_frame")
    print(f"  {ref['pdb_id'].upper():6s}  relationship={in_frame}")
# 7BV2  relationship=FULLOVERLAP

import requests

EMDB_API = "https://www.ebi.ac.uk/emdb/api"
e = requests.get(f"{EMDB_API}/entry/EMD-30210", timeout=30).json()

citations = e.get("crossreferences", {}).get("citation_list", {})
primary = citations.get("primary_citation", {})
ct = primary.get("citation_type") or primary

title   = (ct.get("title") or "").strip()
journal = ct.get("journal") or ct.get("book_title")
year    = ct.get("year")
authors = [a.get("name") or a.get("name_str")
           for a in (ct.get("author") or ct.get("author_order") or [])
           if a]
xrefs = ct.get("external_references", []) or ct.get("xref", [])

doi = next((x.get("valueOf_") for x in xrefs if x.get("type") == "DOI"), None)
pmid = next((x.get("valueOf_") for x in xrefs if x.get("type") == "PUBMED"), None)

print(f"Title   : {title[:80]}")
print(f"Journal : {journal} ({year})")
print(f"Authors : {', '.join(a for a in authors[:5] if a)}{'...' if len(authors) > 5 else ''}")
print(f"DOI     : {doi}")
print(f"PMID    : {pmid}")

import requests

EMDB_API = "https://www.ebi.ac.uk/emdb/api"
e = requests.get(f"{EMDB_API}/entry/EMD-30210", timeout=30).json()

sample = e.get("sample", {})
sm_list = (sample.get("supramolecule_list") or {}).get("supramolecule", [])
for sm in sm_list:
    ns = sm.get("natural_source") or sm.get("natural_source_list", {}).get("natural_source") or []
    if isinstance(ns, dict):
        ns = [ns]
    for n in ns:
        org = (n.get("organism") or {}).get("valueOf_")
        print(f"  Supramolecule '{sm.get('name', {}).get('valueOf_', '?')}': {org}")

import requests, time, pandas as pd

EBI_SEARCH = "https://www.ebi.ac.uk/ebisearch/ws/rest/emdb"
EMDB_API   = "https://www.ebi.ac.uk/emdb/api"

# Step 1: keyword search via EBI Search
hits = []
for start in (0, 50):
    r = requests.get(EBI_SEARCH,
        params={"query": "sars-cov-2 spike", "size": 50, "start": start,
                "format": "json", "fields": "id,name,resolution"},
        timeout=30)
    r.raise_for_status()
    hits.extend(r.json()["entries"])
    time.sleep(0.2)

# Step 2: filter to resolution ≤ 3.0 Å (skip entries with missing field)
rows = []
for h in hits:
    f = h["fields"]
    name = (f.get("name") or [""])[0]
    try:
        resol = float((f.get("resolution") or [None])[0])
    except (TypeError, ValueError):
        continue
    if resol <= 3.0:
        rows.append({"emdb_id": h["id"], "resolution_A": resol, "name": name[:60]})

df = pd.DataFrame(rows).sort_values("resolution_A")
print(f"Spike entries ≤ 3.0 Å: {len(df)}")
print(df.head(10).to_string(index=False))

# Step 3: pull fitted PDB ids for the top 5
for emdb_id in df["emdb_id"].head(5):
    e = requests.get(f"{EMDB_API}/entry/{emdb_id}", timeout=30).json()
    pdblist = e.get("crossreferences", {}).get("pdb_list", {}) or {}
    pdbs = [p["pdb_id"].upper() for p in pdblist.get("pdb_reference", [])]
    print(f"  {emdb_id} -> PDB: {', '.join(pdbs) if pdbs else '(none fitted)'}")
    time.sleep(0.2)

import requests, time, pandas as pd

EBI_SEARCH = "https://www.ebi.ac.uk/ebisearch/ws/rest/emdb"
EMDB_API   = "https://www.ebi.ac.uk/emdb/api"
EMDB_FTP   = "https://ftp.ebi.ac.uk/pub/databases/emdb/structures"

def cohort_table(query, size=10):
    r = requests.get(EBI_SEARCH,
        params={"query": query, "size": size, "format": "json", "fields": "id"},
        timeout=30)
    r.raise_for_status()
    rows = []
    for h in r.json()["entries"]:
        emdb_id = h["id"]
        e = requests.get(f"{EMDB_API}/entry/{emdb_id}", timeout=30).json()
        sd = e["structure_determination_list"]["structure_determination"][0]
        ip = sd["image_processing"][0]
        try:
            resol = float(ip["final_reconstruction"]["resolution"]["valueOf_"])
        except (KeyError, ValueError, TypeError):
            resol = None
        m = e["map"]
        rows.append({
            "emdb_id": emdb_id,
            "title": e["admin"]["title"][:60],
            "method": sd.get("method"),
            "resolution_A": resol,
            "map_url": f"{EMDB_FTP}/{emdb_id}/map/{m['file']}" if m.get("file") else None,
        })
        time.sleep(0.2)
    return pd.DataFrame(rows)

df = cohort_table("ribosome 70S bacterial", size=6)
print(df.to_string(index=False))
df.to_csv("emdb_cohort.csv", index=False)