pemsley/coot/pdbe-api

import json
# Example 1: Get structure summary (returns string)
result = coot.coot_get_url_as_string_py("https://www.ebi.ac.uk/pdbe/api/pdb/entry/summary/4wa9")
data = json.loads(result)
# Example 2: Download gzipped coordinates (returns bytes)
import gzip
compressed = coot.coot_get_url_as_string_py("https://files.rcsb.org/download/4wa9.cif.gz")
decompressed = gzip.decompress(compressed)
imol = coot.read_coordinates_as_string(decompressed.decode('utf-8'), "4wa9")

import json
pdb_id = "4wa9"
url = f"https://www.ebi.ac.uk/pdbe/api/pdb/entry/summary/{pdb_id}"
result = coot.coot_get_url_as_string_py(url)
# Handle both string and bytes responses
if isinstance(result, bytes):
   result = result.decode('utf-8')
data = json.loads(result)
# Extract key information
entry = data[pdb_id][0]
print(f"Title: {entry['title']}")
print(f"Release date: {entry['release_date']}")
print(f"Revision date: {entry['revision_date']}")
print(f"Method: {entry['experimental_method']}")
print(f"Authors: {entry['entry_authors']}")

import json
pdb_id = "4wa9"
url = f"https://www.ebi.ac.uk/pdbe/api/pdb/entry/molecules/{pdb_id}"
result = coot.coot_get_url_as_string_py(url)
if isinstance(result, bytes):
   result = result.decode('utf-8')
data = json.loads(result)
if pdb_id in data:
   for entity in data[pdb_id]:
      molecule_name = entity.get('molecule_name', ['N/A'])[0] if isinstance(entity.get('molecule_name', []), list) else entity.get('molecule_name', 'N/A')
      source = entity.get('source', [{}])[0] if isinstance(entity.get('source', []), list) else entity.get('source', {})
      organism = source.get('organism_scientific_name', 'N/A')
      expression_host = source.get('expression_host_scientific_name', 'N/A')
      
      print(f"Molecule: {molecule_name}")
      print(f"  Source organism: {organism}")
      if expression_host != 'N/A' and expression_host != organism:
         print(f"  Expression host: {expression_host}")

import json
comp_id = "AXI"  # 3-letter code
url = f"https://www.ebi.ac.uk/pdbe/api/pdb/compound/summary/{comp_id}"
result = coot.coot_get_url_as_string_py(url)
if isinstance(result, bytes):
   result = result.decode('utf-8')
data = json.loads(result)
compound = data[comp_id][0]
print(f"Name: {compound['name']}")
print(f"Formula: {compound['formula']}")
print(f"Weight: {compound['weight']}")
print(f"Creation date: {compound['creation_date']}")
print(f"Revision date: {compound['revision_date']}")
print(f"InChI: {compound['inchi']}")
print(f"SMILES: {compound['smiles'][0]['name']}")

import gzip
# Download current version from RCSB
pdb_id = "4wa9"
url = f"https://files.rcsb.org/download/{pdb_id}.cif.gz"
print(f"Downloading {pdb_id}...")
compressed = coot.coot_get_url_as_string_py(url)
print(f"Downloaded {len(compressed)} bytes (compressed)")
# Decompress
decompressed = gzip.decompress(compressed)
print(f"Decompressed to {len(decompressed)} bytes")
# Load into Coot
imol = coot.read_coordinates_as_string(decompressed.decode('utf-8'), f"{pdb_id}")
print(f"Loaded as molecule {imol}")

import json
pdb_id = "4wa9"
url = f"https://www.ebi.ac.uk/pdbe/api/validation/residuewise_outlier_summary/entry/{pdb_id}"
result = coot.coot_get_url_as_string_py(url)
if isinstance(result, bytes):
   result = result.decode('utf-8')
# Note: Response may have multiple JSON objects, parse carefully
# Access specific chain/residue validation data

import json
pdb_id = "4wa9"
url = f"https://www.ebi.ac.uk/pdbe/api/pdb/entry/status/{pdb_id}"
result = coot.coot_get_url_as_string_py(url)
if isinstance(result, bytes):
   result = result.decode('utf-8')
data = json.loads(result)
status = data[pdb_id][0]
print(f"Status: {status['status_code']}")  # REL = released, OBS = obsolete
print(f"Since: {status['since']}")
print(f"Superseded by: {status['superceded_by']}")
print(f"Obsoletes: {status['obsoletes']}")

import json
pdb_id = "4wa9"
url = f"https://www.ebi.ac.uk/pdbe/api/pdb/entry/ligand_monomers/{pdb_id}"
result = coot.coot_get_url_as_string_py(url)
if isinstance(result, bytes):
   result = result.decode('utf-8')
data = json.loads(result)
# Access ligand information per chain
for entity in data[pdb_id]:
    print(f"Chain: {entity['chain_id']}")
    for ligand in entity.get('ligands', []):
        print(f"  Ligand: {ligand['chem_comp_id']}")
        print(f"  Residue: {ligand['author_residue_number']}")

import json
pdb_id = "2hyy"
url = f"https://www.ebi.ac.uk/pdbe/api/pdb/entry/assembly/{pdb_id}"
result = coot.coot_get_url_as_string_py(url)
if isinstance(result, bytes):
   result = result.decode('utf-8')
data = json.loads(result)
for assembly in data[pdb_id]:
    print(f"Assembly {assembly['assembly_id']}: {assembly['name']}")
    print(f"  Form: {assembly['form']}")
    print(f"  Preferred: {assembly['preferred']}")

# Example: Human kinases with resolution < 2Å from 2024
query = 'release_year:2024 AND organism_scientific_name:"Homo sapiens" AND molecule_name:*kinase* AND resolution:[* TO 2.0]'

import json
# Simple search for high-resolution X-ray structures from 2024
query = "release_year:2024 AND experimental_method:\"X-ray diffraction\" AND resolution:[* TO 1.5]"
url = f"https://www.ebi.ac.uk/pdbe/search/pdb/select?q={query}&wt=json&rows=10&fl=pdb_id,title,resolution"
result = coot.coot_get_url_as_string_py(url)
if isinstance(result, bytes):
   result = result.decode('utf-8')
data = json.loads(result)
print(f"Found {data['response']['numFound']} structures")
for doc in data['response']['docs']:
    print(f"  {doc['pdb_id']}: {doc.get('resolution', 'N/A')}Å")
    print(f"    {doc.get('title', 'N/A')[:70]}")