def __selectObjectIds(self, databaseName, collectionName, selectionQueryD):
"""Return a list of object identifiers for the input selection query."""
try:
with Connection(cfgOb=self.__cfgOb,
resourceName=self.__resourceName) as client:
mg = MongoDbUtil(client)
if mg.collectionExists(databaseName, collectionName):
logger.info("%s %s document count is %d", databaseName,
collectionName,
mg.count(databaseName, collectionName))
qD = {}
if selectionQueryD:
qD.update(selectionQueryD)
selectL = ["_id"]
dL = mg.fetch(databaseName,
collectionName,
selectL,
queryD=qD)
logger.info("Selection %r fetch result count %d", selectL,
len(dL))
except Exception as e:
logger.exception("Failing with %s", str(e))
return dL
def __selectEntries(self, **kwargs):
"""Return a dictionary of PDB entries satifying the input conditions (e.g. method, resolution limit)"""
dbName = kwargs.get("dbName", "pdbx_core")
collectionName = kwargs.get("collectionName", "pdbx_core_entry")
selectionQueryD = kwargs.get("entrySelectionQuery", {})
#
entryD = {}
try:
with Connection(cfgOb=self.__cfgOb, resourceName=self.__resourceName) as client:
mg = MongoDbUtil(client)
if mg.collectionExists(dbName, collectionName):
logger.info("%s %s document count is %d", dbName, collectionName, mg.count(dbName, collectionName))
qD = {}
if selectionQueryD:
qD.update(qD)
selectL = ["rcsb_entry_container_identifiers"]
dL = mg.fetch(dbName, collectionName, selectL, queryD=qD)
logger.info("Selection %r fetch result count %d", selectL, len(dL))
#
for dD in dL:
#
if (
("rcsb_entry_container_identifiers" in dD)
and ("entry_id" in dD["rcsb_entry_container_identifiers"])
and ("polymer_entity_ids" in dD["rcsb_entry_container_identifiers"])
and dD["rcsb_entry_container_identifiers"]["polymer_entity_ids"]
):
entryD[dD["rcsb_entry_container_identifiers"]["entry_id"]] = {"polymer_entity_ids": dD["rcsb_entry_container_identifiers"]["polymer_entity_ids"]}
except Exception as e:
logger.exception("Failing with %s", str(e))
return entryD
def getEntityIds(self, entryIdList):
""" """
dbName = "pdbx_core"
collectionName = "pdbx_core_polymer_entity"
docD = {}
try:
with Connection(cfgOb=self.__cfgOb,
resourceName=self.__resourceName) as client:
mg = MongoDbUtil(client)
if mg.collectionExists(dbName, collectionName):
logger.info("%s %s document count is %d",
dbName, collectionName,
mg.count(dbName, collectionName))
for entryId in entryIdList:
qD = {
"rcsb_polymer_entity_container_identifiers.entry_id":
entryId
}
selectL = ["rcsb_polymer_entity_container_identifiers"]
tL = mg.fetch(dbName,
collectionName,
selectL,
queryD=qD)
#
logger.debug("Selection %r fetch result count %d",
selectL, len(tL))
docD[entryId] = [
vv["rcsb_polymer_entity_container_identifiers"]
for vv in tL
]
logger.debug("docD is %r", docD)
except Exception as e:
logger.exception("Failing with %s", str(e))
return docD
def getEntryInfo(self, **kwargs):
"""Return a dictionary of PDB entries satifying the input conditions (e.g. method, resolution limit)"""
resLimit = kwargs.get("resLimit", 3.5)
expMethod = kwargs.get("expMethod", "X-ray")
#
dbName = kwargs.get("dbName", "pdbx_core")
collectionName = kwargs.get("collectionName", "pdbx_core_entry")
#
entryD = {}
try:
with Connection(cfgOb=self.__cfgOb,
resourceName=self.__resourceName) as client:
mg = MongoDbUtil(client)
if mg.collectionExists(dbName, collectionName):
logger.info("%s %s document count is %d",
dbName, collectionName,
mg.count(dbName, collectionName))
qD = {
"rcsb_entry_info.experimental_method": expMethod,
"refine.0.ls_d_res_high": {
"$lte": resLimit
}
}
selectL = [
"rcsb_entry_container_identifiers", "rcsb_entry_info",
"refine"
]
dL = mg.fetch(dbName, collectionName, selectL, queryD=qD)
logger.info("Selection %r fetch result count %d", selectL,
len(dL))
#
for dV in dL:
if "rcsb_entry_container_identifiers" not in dV:
continue
entryId = dV["rcsb_entry_container_identifiers"][
"entry_id"]
entryD[entryId] = {}
if "rcsb_entry_info" in dV and "polymer_composition" in dV[
"rcsb_entry_info"]:
entryD[entryId] = {
"polymer_composition":
dV["rcsb_entry_info"]["polymer_composition"],
"experimental_method":
dV["rcsb_entry_info"]["experimental_method"],
}
if "refine" in dV and dV[
"refine"] and "ls_d_res_high" in dV["refine"][
0]:
entryD[entryId]["ls_d_res_high"] = dV["refine"][0][
"ls_d_res_high"]
logger.debug("Got res %r",
dV["refine"][0]["ls_d_res_high"])
except Exception as e:
logger.exception("Failing with %s", str(e))
return entryD
def __selectObjects(self, **kwargs):
"""Return a dictionary of objects satisfying the input conditions (e.g. method, resolution limit)"""
databaseName = kwargs.get("databaseName", "pdbx_core")
collectionName = kwargs.get("collectionName", "pdbx_core_entry")
selectionQueryD = kwargs.get("selectionQuery", {})
#
uniqueAttributes = kwargs.get("uniqueAttributes", ["rcsb_id"])
#
tV = kwargs.get("objectLimit", None)
objLimit = int(tV) if tV is not None else None
stripObjectId = kwargs.get("stripObjectId", False)
logIncrement = kwargs.get("logIncrement", 10000)
#
objectD = {}
try:
with Connection(cfgOb=self.__cfgOb,
resourceName=self.__resourceName) as client:
mg = MongoDbUtil(client)
if mg.collectionExists(databaseName, collectionName):
logger.info("%s %s document count is %d", databaseName,
collectionName,
mg.count(databaseName, collectionName))
qD = {}
if selectionQueryD:
qD.update(selectionQueryD)
selectL = ["_id"]
dL = mg.fetch(databaseName,
collectionName,
selectL,
queryD=qD)
numDoc = len(dL) if dL else 0
logger.info("Selection %r fetch result count %d", selectL,
numDoc)
#
for ii, dD in enumerate(dL, 1):
if "_id" not in dD:
continue
rObj = mg.fetchOne(databaseName, collectionName, "_id",
dD["_id"])
if stripObjectId and rObj and "_id" in rObj:
rObj.pop("_id")
else:
rObj["_id"] = str(rObj["_id"])
#
stKey = ".".join([rObj[ky] for ky in uniqueAttributes])
objectD[stKey] = copy.copy(rObj)
if objLimit and ii >= objLimit:
break
logger.debug("Saving %d %s", ii, stKey)
if ii % logIncrement == 0 or ii == numDoc:
logger.info("Extracting object (%d of %d)", ii,
numDoc)
except Exception as e:
logger.exception("Failing with %s", str(e))
return objectD
def __select(self, **kwargs):
"""Return a dictionary of object content satisfying the input conditions
(e.g. method, resolution limit) and selection options.
"""
databaseName = kwargs.get("databaseName", "pdbx_core")
collectionName = kwargs.get("collectionName", "pdbx_core_entry")
selectionQueryD = kwargs.get("selectionQuery", {})
uniqueAttributes = kwargs.get("uniqueAttributes", ["rcsb_id"])
selectL = kwargs.get("selectionList", [])
stripObjectId = kwargs.get("stripObjectId", False)
#
tV = kwargs.get("objectLimit", None)
objLimit = int(tV) if tV is not None else None
#
objectD = {}
try:
with Connection(cfgOb=self.__cfgOb,
resourceName=self.__resourceName) as client:
mg = MongoDbUtil(client)
if mg.collectionExists(databaseName, collectionName):
logger.info("%s %s document count is %d", databaseName,
collectionName,
mg.count(databaseName, collectionName))
qD = {}
if selectionQueryD:
qD.update(selectionQueryD)
dL = mg.fetch(databaseName,
collectionName,
selectL,
queryD=qD,
suppressId=True)
logger.info("Selection %r fetch result count %d", selectL,
len(dL))
#
for ii, rObj in enumerate(dL, 1):
stKey = ".".join([rObj[ky] for ky in uniqueAttributes])
if stripObjectId and rObj and "_id" in rObj:
rObj.pop("_id")
objectD[stKey] = copy.copy(rObj)
if objLimit and ii >= objLimit:
break
# logger.debug("Saving %d %s", ii, stKey)
# logger.debug("Current objectD keys %r", list(objectD.keys()))
except Exception as e:
logger.exception("Failing with %s", str(e))
return objectD
def __selectPolymerEntities(self, entryD, **kwargs):
"""Skeleton entity selector recovering essential biological sequence mapping features
for macromolecules (default type = protein).
"1CP9": {
"polymer_entity_ids": [
"1",
"2"
],
"selected_polymer_entities": {
"1": {
"rcsb_multiple_source_flag": "N",
"asym_ids": [
"A"
],
"auth_asym_ids": [
"A"
],
"entity_id": "1",
"type": "polypeptide(L)",
"rcsb_entity_polymer_type": "Protein",
"rcsb_entity_source_organism": [
{
"ncbi_taxonomy_id": 587,
"beg_seq_num": 1,
"end_seq_num": 205,
"ncbi_scientific_name": "Providencia rettgeri"
}
],
"struct_ref": [
{
"id": "1",
"db_name": "UNP",
"pdbx_db_accession": "Q7WZI9",
"entity_id": "1",
"pdbx_seq_one_letter_code": "QSTQIKIERDNYGVPHIYANDTYSLFYGYGYA...",
"alignD": {
"A": [
{
"align_id": "1",
"ref_id": "1",
"pdbx_PDB_id_code": "1CP9",
"pdbx_strand_id": "A",
"seq_align_beg": 1,
"seq_align_end": 205,
"pdbx_db_accession": "Q7WZI9",
"db_align_beg": 24,
"db_align_end": 228,
"pdbx_auth_seq_align_beg": "1",
"pdbx_auth_seq_align_end": "205",
"rcsb_entity_id": "1"
}
]
}
}
]
},
"2": {
"rcsb_multiple_source_flag": "N",
"asym_ids": [
"B"
],
"auth_asym_ids": [
"B"
],
"entity_id": "2",
"type": "polypeptide(L)",
"rcsb_entity_polymer_type": "Protein",
"rcsb_entity_source_organism": [
{
"ncbi_taxonomy_id": 587,
"beg_seq_num": 1,
"end_seq_num": 553,
"ncbi_scientific_name": "Providencia rettgeri"
}
],
"struct_ref": [
{
"id": "2",
"db_name": "UNP",
"pdbx_db_accession": "Q7WZI9",
"entity_id": "2",
"pdbx_seq_one_letter_code": "SNVWLVGKTKASGAKAILLNGPQFGWFNPAYTYGIGLHG",
"alignD": {
"B": [
{
"align_id": "2",
"ref_id": "2",
"pdbx_PDB_id_code": "1CP9",
"pdbx_strand_id": "B",
"seq_align_beg": 1,
"seq_align_end": 553,
"pdbx_db_accession": "Q7WZI9",
"db_align_beg": 285,
"db_align_end": 837,
"pdbx_auth_seq_align_beg": "1",
"pdbx_auth_seq_align_end": "553",
"rcsb_entity_id": "2"
}
]
}
}
]
}
}
},
"""
dbName = kwargs.get("dbName", "pdbx_core")
collectionName = kwargs.get("collectionName", "pdbx_core_polymer_entity")
resultKey = kwargs.get("resultKey", "selected_polymer_entities")
entryLimit = kwargs.get("entryLimit", None)
selectionQueryD = kwargs.get("entitySelectionQuery", {"entity_poly.rcsb_entity_polymer_type": "Protein"})
#
try:
with Connection(cfgOb=self.__cfgOb, resourceName=self.__resourceName) as client:
mg = MongoDbUtil(client)
if mg.collectionExists(dbName, collectionName):
logger.info("%s %s document count is %d", dbName, collectionName, mg.count(dbName, collectionName))
selectL = [
"rcsb_polymer_entity_container_identifiers",
"entity.rcsb_multiple_source_flag",
"entity_poly.type",
"entity_poly.rcsb_entity_polymer_type",
"entity_poly.pdbx_seq_one_letter_code_can",
"rcsb_entity_source_organism.ncbi_taxonomy_id",
"rcsb_entity_source_organism.ncbi_scientific_name",
"rcsb_entity_source_organism.beg_seq_num",
"rcsb_entity_source_organism.end_seq_num",
"struct_ref.id",
"struct_ref.pdbx_db_accession",
"struct_ref.db_name",
"struct_ref.entity_id",
"struct_ref.pdbx_seq_one_letter_code",
"struct_ref.pdbx_align_begin",
"struct_ref_seq",
#
"entity_src_nat.pdbx_ncbi_taxonomy_id",
"entity_src_gen.pdbx_gene_src_ncbi_taxonomy_id",
"entity_src_gen.pdbx_host_org_ncbi_taxonomy_id",
"pdbx_entity_src_syn.ncbi_taxonomy_id",
]
iCount = 0
for entryId in entryD:
#
if resultKey in entryD[entryId]:
continue
#
qD = {"rcsb_polymer_entity_container_identifiers.entry_id": entryId}
qD.update(selectionQueryD)
#
dL = mg.fetch(dbName, collectionName, selectL, queryD=qD)
logger.debug("%s query %r fetch result count %d", entryId, qD, len(dL))
eD = {}
for ii, dD in enumerate(dL, 1):
rD = {}
logger.debug("%s (%4d) d is %r", entryId, ii, dD)
if "entity" in dD:
rD["rcsb_multiple_source_flag"] = dD["entity"]["rcsb_multiple_source_flag"] if "rcsb_multiple_source_flag" in dD["entity"] else "N"
#
if "rcsb_polymer_entity_container_identifiers" in dD:
rD["asym_ids"] = dD["rcsb_entity_container_identifiers"]["asym_ids"] if "asym_ids" in dD["rcsb_entity_container_identifiers"] else []
rD["auth_asym_ids"] = dD["rcsb_entity_container_identifiers"]["auth_asym_ids"] if "auth_asym_ids" in dD["rcsb_entity_container_identifiers"] else []
rD["entity_id"] = dD["rcsb_entity_container_identifiers"]["entity_id"]
#
if "entity_poly" in dD:
rD["type"] = dD["entity_poly"]["type"] if "type" in dD["entity_poly"] else None
rD["rcsb_entity_polymer_type"] = dD["entity_poly"]["rcsb_entity_polymer_type"] if "rcsb_entity_polymer_type" in dD["entity_poly"] else None
rD["entity_polymer_length"] = len(dD["entity_poly"]["pdbx_seq_one_letter_code_can"]) if "pdbx_seq_one_letter_code_can" in dD["entity_poly"] else 0
#
tL = []
if "rcsb_entity_source_organism" in dD:
for tD in dD["rcsb_entity_source_organism"]:
tL.append(tD)
rD["rcsb_entity_source_organism"] = copy.copy(tL)
#
qDL = []
if "struct_ref" in dD:
for tD in dD["struct_ref"]:
if "db_name" in tD:
tD["db_name"] = str(tD["db_name"]).upper().strip()
tD["db_name"] = "UNP" if tD["db_name"] in ["TREMBL"] else tD["db_name"]
qDL.append(tD)
if "struct_ref_seq" in dD:
for qD in qDL:
refId = qD["id"]
alignL = []
for tD in dD["struct_ref_seq"]:
if refId == tD["ref_id"]:
alignL.append(tD)
# qD['align_list'] = copy.copy(aL)
for align in alignL:
authAsymId = align["pdbx_strand_id"]
qD.setdefault("alignD", {}).setdefault(authAsymId, []).append(align)
rD["struct_ref"] = qDL
#
taxIdL = []
if "entity_src_nat" in dD:
for tD in dD["entity_src_nat"]:
if "pdbx_ncbi_taxonomy_id" in tD:
taxIdL.append(tD["pdbx_ncbi_taxonomy_id"])
if "entity_src_gen" in dD:
for tD in dD["entity_src_gen"]:
if "pdbx_gene_src_ncbi_taxonomy_id" in tD:
taxIdL.append(tD["pdbx_gene_src_ncbi_taxonomy_id"])
if "pdbx_host_org_ncbi_taxonomy_id" in tD:
taxIdL.append(tD["pdbx_host_org_ncbi_taxonomy_id"])
if "pdbx_entity_src_syn" in dD:
for tD in dD["pdbx_entity_src_syn"]:
if "ncbi_taxonomy_id" in tD:
taxIdL.append(tD["ncbi_taxonomy_id"])
qL = []
for taxId in taxIdL:
ttL = [int(t.strip()) for t in taxId.split(",") if t.strip().isdigit()]
qL.extend(ttL)
logger.debug("TaxId list %r", qL)
rD["original_taxonomy_ids"] = copy.copy(list(set(qL)))
#
if "entity_id" in rD:
eD[rD["entity_id"]] = copy.copy(rD)
entryD[entryId][resultKey] = copy.copy(eD)
iCount += 1
if iCount % 1000 == 0:
logger.info("Completed fetch %d/%d entries", iCount, len(entryD))
if entryLimit and iCount >= entryLimit:
logger.info("Quitting after %d", iCount)
break
except Exception as e:
logger.exception("Failing with %s", str(e))
return entryD
def testSingleIndexSelect(self):
"""Test case - create collection, create simple single index, insert document list, read check documents.
"""
try:
logger.debug("Starting testSingleIndexSelect")
with Connection(cfgOb=self.__cfgOb,
resourceName=self.__resourceName) as client:
nDocs = 100
mg = MongoDbUtil(client)
ok = mg.createCollection(self.__dbName, self.__collectionName)
self.assertTrue(ok)
ok = mg.databaseExists(self.__dbName)
self.assertTrue(ok)
ok = mg.collectionExists(self.__dbName, self.__collectionName)
self.assertTrue(ok)
#
# Create before insert
ok = mg.createIndex(self.__dbName,
self.__collectionName,
keyList=["DOC_ID"],
indexName="primary",
indexType="DESCENDING",
uniqueFlag=True)
self.assertTrue(ok)
dList = []
for ii in range(nDocs):
dObj = self.__makeDataObj(2, 5, 5, ii)
dList.append(dObj)
#
keyName = "DOC_ID"
rIdL = mg.insertList(self.__dbName,
self.__collectionName,
dList,
keyNames=[keyName],
salvage=True)
self.assertEqual(len(dList), len(rIdL))
#
for ii in range(nDocs):
kVal = "DOC_%d" % ii
rObj = mg.fetchOne(self.__dbName, self.__collectionName,
"DOC_ID", kVal)
# logger.debug("Return Object %s" % pprint.pformat(rObj))
rObj.pop("_id", None)
dList[ii].pop("_id", None)
self.assertEqual(len(dList[ii]), len(rObj))
self.assertEqual(dList[ii], rObj)
#
ok = mg.dropIndex(self.__dbName,
self.__collectionName,
indexName="primary")
self.assertTrue(ok)
ok = mg.createIndex(self.__dbName,
self.__collectionName,
keyList=["DOC_ID"],
indexName="primary",
indexType="DESCENDING",
uniqueFlag=True)
self.assertTrue(ok)
ok = mg.reIndex(self.__dbName, self.__collectionName)
self.assertTrue(ok)
#
with Connection(cfgOb=self.__cfgOb,
resourceName=self.__resourceName) as client:
mg = MongoDbUtil(client)
ii = mg.count(self.__dbName, self.__collectionName)
logger.debug("collection length %d", ii)
#
dList = mg.fetch(self.__dbName, self.__collectionName,
["DOC_ID"])
self.assertEqual(len(dList), nDocs)
logger.debug("Fetch length %d", len(dList))
for ii, dD in enumerate(dList):
logger.debug("Fetch num %d: %r", ii, dD)
#
dList = mg.fetch(self.__dbName,
self.__collectionName,
["category_0.attribute_0"],
queryD={"category_0.attribute_0": "val_0_0"})
self.assertEqual(len(dList), nDocs)
logger.debug("Fetch length %d", len(dList))
for ii, dD in enumerate(dList):
logger.debug("Fetch num %d: %r", ii, dD)
except Exception as e:
logger.exception("Failing with %s", str(e))
self.fail()
def getEntityInstances(self, entryD, **kwargs):
"""Get the selected validation data for the instances in the input entry dictionary.
entryD[entryId]['selected_polymer_entities'][entityId]['validation'] = {}
Add keys: 'pdbx_vrpt_instance_results' and 'pdbx_unobs_or_zero_occ_residues' to the validation dictionary above.
Args:
resourceName (str): resource name (e.g. DrugBank, CCDC)
**kwargs: unused
Returns:
entryD: { }
"""
dbName = kwargs.get("dbName", "pdbx_core")
collectionName = kwargs.get("collectionName",
"pdbx_core_polymer_entity_instance")
savePath = kwargs.get("savePath", "entry-data.pic")
saveKwargs = kwargs.get("saveKwargs", {"fmt": "pickle"})
entryLimit = kwargs.get("entryLimit", None)
#
try:
optF = False
iCount = 0
with Connection(cfgOb=self.__cfgOb,
resourceName=self.__resourceName) as client:
mg = MongoDbUtil(client)
if mg.collectionExists(dbName, collectionName):
logger.info("%s %s total document count is %d",
dbName, collectionName,
mg.count(dbName, collectionName))
#
for entryId, dV in entryD.items():
for entityId, peD in dV[
"selected_polymer_entities"].items():
# if 'anal_instances' in peD:
# continue
vD = {}
for asymId in peD["asym_ids"]:
qD = {
"rcsb_polymer_entity_instance_container_identifiers.entry_id":
entryId,
"rcsb_polymer_entity_instance_container_identifiers.asym_id":
asymId,
}
# qD = {'rcsb_entity_instance_container_validation_identifiers.entity_type': 'polymer'}
# selectL = ['pdbx_vrpt_instance_results', 'pdbx_unobs_or_zero_occ_residues']
selectL = ["pdbx_vrpt_instance_results"]
tL = mg.fetch(dbName,
collectionName,
selectL,
queryD=qD)
dV = {}
if not tL:
logger.info(
"No validation data for %s %s %s(%s)",
dbName, collectionName, entryId,
asymId)
continue
#
logger.debug(
">>> %s %s (%s) dict key length %d ",
collectionName, entryId, asymId,
len(tL[0]))
#
if optF:
dV["pdbx_vrpt_instance_results"] = tL[0][
"pdbx_vrpt_instance_results"] if "pdbx_vrpt_instance_results" in tL[
0] else []
dV["pdbx_unobs_or_zero_occ_residues"] = tL[0][
"pdbx_unobs_or_zero_occ_residues"] if "pdbx_unobs_or_zero_occ_residues" in tL[
0] else []
#
if optF:
urdL = tL[0][
"pdbx_unobs_or_zero_occ_residues"] if "pdbx_unobs_or_zero_occ_residues" in tL[
0] else []
oL = [{
"label_seq_id": urd["label_seq_id"],
"label_comp_id": urd["label_comp_id"]
} for urd in urdL]
dV["pdbx_unobs_or_zero_occ_residues"] = oL
#
try:
irdL = tL[0][
"pdbx_vrpt_instance_results"] if "pdbx_vrpt_instance_results" in tL[
0] else []
oL = [{
"label_seq_id": ird["label_seq_id"],
"label_comp_id": ird["label_comp_id"]
} for ird in irdL]
dV["pdbx_vrpt_instance_results_seq"] = oL
except Exception as e:
logger.error(
"Failing with entryId %s entityId %s asymId %s bad validation data %s",
entryId, entityId, asymId, str(e))
#
try:
irdL = tL[0][
"pdbx_vrpt_instance_results"] if "pdbx_vrpt_instance_results" in tL[
0] else []
oL = [{
"OWAB": ird["OWAB"],
"label_seq_id": ird["label_seq_id"],
"label_comp_id": ird["label_comp_id"]
} for ird in irdL]
dV["pdbx_vrpt_instance_results_occ"] = oL
except Exception as e:
logger.debug(
"Failing with entryId %s entityId %s asymId %s bad validation data %s",
entryId, entityId, asymId, str(e))
vD[asymId] = copy.copy(dV)
#
analD = self.analEntity(entryId, peD, vD)
entryD[entryId]["selected_polymer_entities"][
entityId]["anal_instances"] = copy.copy(analD)
iCount += 1
if iCount % 500 == 0:
logger.info("Completed %d/%d entries", iCount,
len(entryD))
if iCount % 2000 == 0:
ok = self.__mU.doExport(savePath, entryD,
**saveKwargs)
logger.info(
"Saved polymer entity instance results (%d) status %r in %s",
iCount, ok, savePath)
if entryLimit and iCount >= entryLimit:
break
ok = self.__mU.doExport(savePath, entryD, **saveKwargs)
logger.info(
"Saved polymer instance results (%d) entries %d status %r in %s",
iCount, len(entryD), ok, savePath)
except Exception as e:
logger.exception("Failing with %s", str(e))
return entryD
def getPolymerEntities(self, entryD, **kwargs):
"""Add 'selected_polymer_entities' satisfying the input contiditions and add this to the input entry dictionary."""
dbName = kwargs.get("dbName", "pdbx_core")
collectionName = kwargs.get("collectionName",
"pdbx_core_polymer_entity")
resultKey = kwargs.get("resultKey", "selected_polymer_entities")
savePath = kwargs.get("savePath", "entry-data.pic")
entryLimit = kwargs.get("entryLimit", None)
saveKwargs = kwargs.get("saveKwargs", {"fmt": "pickle"})
#
try:
with Connection(cfgOb=self.__cfgOb,
resourceName=self.__resourceName) as client:
mg = MongoDbUtil(client)
if mg.collectionExists(dbName, collectionName):
logger.info("%s %s document count is %d",
dbName, collectionName,
mg.count(dbName, collectionName))
selectL = [
"rcsb_polymer_entity_container_identifiers",
"entity_poly.type",
"entity_poly.pdbx_seq_one_letter_code_can",
"rcsb_entity_source_organism.ncbi_taxonomy_id",
"rcsb_entity_source_organism.ncbi_scientific_name",
"struct_ref.pdbx_seq_one_letter_code",
"struct_ref.pdbx_db_accession",
"struct_ref.db_name",
"struct_ref.entity_id",
]
iCount = 0
for entryId in entryD:
#
if resultKey in entryD[entryId]:
continue
#
qD = {
"rcsb_polymer_entity_container_identifiers.entry_id":
entryId,
"entity_poly.rcsb_entity_polymer_type": "Protein",
"entity.rcsb_multiple_source_flag": "N",
}
#
dL = mg.fetch(dbName,
collectionName,
selectL,
queryD=qD)
logger.debug("%s query %r fetch result count %d",
entryId, qD, len(dL))
eD = {}
for ii, dV in enumerate(dL, 1):
rD = {}
logger.debug("%s (%4d) d is %r", entryId, ii, dV)
if "rcsb_polymer_entity_container_identifiers" in dV and "asym_ids" in dV[
"rcsb_polymer_entity_container_identifiers"]:
rD["asym_ids"] = dV[
"rcsb_polymer_entity_container_identifiers"][
"asym_ids"]
rD["entity_id"] = dV[
"rcsb_polymer_entity_container_identifiers"][
"entity_id"]
if "entity_poly" in dV and "type" in dV[
"entity_poly"]:
rD["type"] = dV["entity_poly"]["type"]
rD["seq_one_letter_code_can"] = dV[
"entity_poly"][
"pdbx_seq_one_letter_code_can"]
if "rcsb_entity_source_organism" in dV:
rD["ncbi_taxonomy_id"] = dV[
"rcsb_entity_source_organism"][0][
"ncbi_taxonomy_id"] if "ncbi_taxonomy_id" in dV[
"rcsb_entity_source_organism"][
0] else None
rD["ncbi_scientific_name"] = (
dV["rcsb_entity_source_organism"][0]
["ncbi_scientific_name"]
if "ncbi_scientific_name"
in dV["rcsb_entity_source_organism"][0]
else None)
if "struct_ref" in dV and len(
dV["struct_ref"]) == 1:
rD["seq_one_letter_code_ref"] = dV["struct_ref"][
0]["pdbx_seq_one_letter_code"] if "pdbx_seq_one_letter_code" in dV[
"struct_ref"][0] else None
rD["db_accession"] = dV["struct_ref"][0][
"pdbx_db_accession"] if "pdbx_db_accession" in dV[
"struct_ref"][0] else None
rD["db_name"] = dV["struct_ref"][0][
"db_name"] if "db_name" in dV[
"struct_ref"][0] else None
#
refDbName = rD["db_name"]
dbAccession = rD["db_accession"]
dbRefSeq = self.__seqCache[
dbAccession] if dbAccession in self.__seqCache else None
if refDbName in ["UNP"] and not dbRefSeq:
dbRefSeq = self.__fetchUniprot(dbAccession)
self.__seqCache[dbAccession] = dbRefSeq
logger.debug("Fetch uniprot %r", dbRefSeq)
rD["ref_db_seq"] = dbRefSeq
else:
rD["seq_one_letter_code_ref"] = rD[
"db_accession"] = rD["db_name"] = None
#
if "entity_id" in rD:
eD[rD["entity_id"]] = copy.copy(rD)
entryD[entryId][resultKey] = copy.copy(eD)
iCount += 1
if iCount % 10 == 0:
logger.info(
"Completed polymer entities fetch %d/%d entries",
iCount, len(entryD))
if iCount % 2000 == 0:
ok = self.__mU.doExport(savePath, entryD,
**saveKwargs)
logger.info(
"Saved polymer entity results (%d) status %r in %s",
iCount, ok, savePath)
if entryLimit and iCount >= entryLimit:
logger.info("Quitting after %d", iCount)
break
#
# for entryId in entryD:
# logger.debug(">> %s docD %r" % (entryId, entryD[entryId]))
ok = self.__mU.doExport(savePath, entryD, **saveKwargs)
logger.info(
"Saved polymer entity results (%d) entries %d status %r in %s",
iCount, len(entryD), ok, savePath)
except Exception as e:
logger.exception("Failing with %s", str(e))
return entryD