def test_search_composite():
query1 = rcsb.FieldQuery("rcsb_entity_host_organism.scientific_name",
exact_match="H**o sapiens")
query2 = rcsb.FieldQuery("exptl.method", exact_match="SOLUTION NMR")
ids_1 = set(rcsb.search(query1))
ids_2 = set(rcsb.search(query2))
ids_or = set(rcsb.search(query1 | query2))
ids_and = set(rcsb.search(query1 & query2))
assert ids_or == ids_1 | ids_2
assert ids_and == ids_1 & ids_2
def test_search_field(field, molecular_definition, params, ref_ids):
query = rcsb.FieldQuery(field, molecular_definition, **params)
test_ids = rcsb.search(query)
test_count = rcsb.count(query)
assert set(test_ids) == set(ref_ids)
assert test_count == len(ref_ids)
import matplotlib.pyplot as plt
import biotite
import biotite.database.rcsb as rcsb
from datetime import datetime, time
years = np.arange(1990, datetime.today().year + 1)
xray_count = np.zeros(len(years), dtype=int)
nmr_count = np.zeros(len(years), dtype=int)
em_count = np.zeros(len(years), dtype=int)
tot_count = np.zeros(len(years), dtype=int)
# For each year fetch the list of released PDB IDs
# and count the number
for i, year in enumerate(years):
# A query that comprises one year
date_query = rcsb.FieldQuery(
"rcsb_accession_info.initial_release_date",
range_closed=(datetime.combine(datetime(year, 1, 1), time.min),
datetime.combine(datetime(year, 12, 31), time.max)))
xray_query = rcsb.FieldQuery("exptl.method",
exact_match="X-RAY DIFFRACTION")
nmr_query = rcsb.FieldQuery("exptl.method", exact_match="SOLUTION NMR")
em_query = rcsb.FieldQuery("exptl.method",
exact_match="ELECTRON MICROSCOPY")
# Get the amount of structures, that were released in that year
# AND were elucidated with the respective method
xray_count[i], nmr_count[i], em_count[i] = [
rcsb.count(date_query & method_query)
for method_query in [xray_query, nmr_query, em_query]
]
# Get the total amount of structures released in that year
tot_count[i] = rcsb.count(date_query)
pdb_ids = rcsb.search(query)
print(pdb_ids)
print(rcsb.count(query))
files = rcsb.fetch(pdb_ids, "mmtf", gettempdir())
########################################################################
# This was a simple search for the occurrence of the search term in any
# field.
# You can also search for a value in a specific field with a
# :class:`FieldQuery`.
# A complete list of the available fields and its supported operators
# is documented
# `on this page <https://search.rcsb.org/search-attributes.html>`_.
# Query for 'lacA' gene
query1 = rcsb.FieldQuery("rcsb_entity_source_organism.rcsb_gene_name.value",
exact_match="lacA")
# Query for resolution below 1.5 Å
query2 = rcsb.FieldQuery("reflns.d_resolution_high", less=1.5)
########################################################################
# The search API allows even more complex queries, e.g. for sequence
# or structure similarity. Have a look at the API reference of
# :mod:`biotite.database.rcsb`.
#
# Multiple :class:`Query` objects can be combined using the ``|`` (or)
# or ``&`` (and) operator for a more fine-grained selection.
# A :class:`FieldQuery` is negated with ``~``.
composite_query = query1 & ~query2
print(rcsb.search(composite_query))
def test_search_invalid(field, params):
invalid_query = rcsb.FieldQuery(field, **params)
with pytest.raises(RequestError, match="400"):
rcsb.search(invalid_query)
with pytest.raises(RequestError, match="400"):
rcsb.count(invalid_query)
import datetime
import concurrent.futures
import tarfile
import biotite.database.rcsb as rcsb
import biotite.structure.io.mmtf as mmtf
### Download of PDB and archive creation ###
# MMTF files are downloaded into a new directory in this path
# and the .tar archive is created here
base_path = "path/to/directoy"
# Obtain all PDB IDs using a query that includes all entries
# Each PDB entry has a title
all_id_query = rcsb.FieldQuery("struct.title")
pdb_ids = rcsb.search(all_id_query)
# Name for download directory
now = datetime.datetime.now()
mmtf_dir = os.path.join(
base_path, f"mmtf_{now.year:04d}{now.month:02d}{now.day:02d}"
)
if not os.path.isdir(mmtf_dir):
os.mkdir(mmtf_dir)
# Download all PDB IDs with parallelized HTTP requests
with concurrent.futures.ThreadPoolExecutor(max_workers=10) as executor:
for pdb_id in pdb_ids:
executor.submit(rcsb.fetch, pdb_id, "mmtf", mmtf_dir)