def __getPolymerReferenceSequenceAssignments(self, databaseName, collectionName, polymerType, fetchLimit):
"""Get all accessions assigned to input reference sequence database for the input polymerType.
Returns:
(dict): {"1abc_1": "rcsb_polymer_entity_container_identifiers": {"reference_sequence_identifiers": []},
"rcsb_entity_source_organism"" {"ncbi_taxonomy_id": []}
"""
try:
obEx = ObjectExtractor(
self.__cfgOb,
databaseName=databaseName,
collectionName=collectionName,
cacheFilePath=None,
useCache=False,
keyAttribute="entity",
uniqueAttributes=["rcsb_id"],
cacheKwargs=None,
objectLimit=fetchLimit,
selectionQuery={"entity_poly.rcsb_entity_polymer_type": polymerType},
selectionList=[
"rcsb_id",
"rcsb_polymer_entity_container_identifiers.reference_sequence_identifiers",
"rcsb_polymer_entity_container_identifiers.auth_asym_ids",
"rcsb_entity_source_organism.ncbi_taxonomy_id",
],
)
eCount = obEx.getCount()
logger.info("Polymer entity count type %s is %d", polymerType, eCount)
objD = obEx.getObjects()
logger.info("Reading polymer entity count %d reference accession length %d ", eCount, len(objD))
#
except Exception as e:
logger.exception("Failing for %s (%s) with %s", databaseName, collectionName, str(e))
return objD
def __extractCitations(self):
"""Test case - extract unique entity source and host taxonomies"""
try:
obEx = ObjectExtractor(
self.__cfgOb,
databaseName=self.__databaseName,
collectionName=self.__collectionName,
cacheFilePath=None,
useCache=False,
keyAttribute="entry",
uniqueAttributes=["rcsb_id"],
cacheKwargs=None,
objectLimit=None,
selectionQuery={},
selectionList=["rcsb_id", "citation"],
)
eCount = obEx.getCount()
logger.info("Entry count is %d", eCount)
objD = obEx.getObjects()
# for ky, eD in objD.items():
# logger.info("%s: %r", ky, eD)
return objD
except Exception as e:
logger.exception("Failing with %s", str(e))
return {}
def __updateEntryInfo(self, cfgOb):
"""Get entry_info data"""
rD = {}
try:
obEx = ObjectExtractor(
cfgOb,
databaseName="pdbx_core",
collectionName="pdbx_core_entry",
useCache=False,
keyAttribute="entry",
uniqueAttributes=["rcsb_id"],
selectionQuery={},
selectionList=[
"rcsb_id", "rcsb_entry_info.polymer_entity_count"
],
)
#
eCount = obEx.getCount()
logger.info("Entry count is %d", eCount)
objD = obEx.getObjects()
for _, eD in objD.items():
rcsbId = eD["rcsb_id"]
try:
rD[rcsbId] = eD["rcsb_entry_info"]
except Exception:
pass
except Exception as e:
logger.exception("Failing with %s", str(e))
return rD
def testExtractEntriesBefore(self):
"""Test case - extract entries subject to date restriction"""
try:
tU = TimeUtil()
tS = tU.getTimestamp(useUtc=True, before={"days": 365 * 5})
tD = tU.getDateTimeObj(tS)
obEx = ObjectExtractor(
self.__cfgOb,
databaseName="pdbx_core",
collectionName="pdbx_core_entry",
useCache=False,
keyAttribute="entry",
uniqueAttributes=["rcsb_id"],
selectionQuery={
"rcsb_accession_info.initial_release_date": {
"$gt": tD
}
},
selectionList=["rcsb_id", "rcsb_accession_info"],
)
eD = obEx.getObjects()
eCount = obEx.getCount()
logger.info("Entry count is %d", eCount)
logger.info("Entries are %r", list(eD.keys()))
self.assertGreaterEqual(eCount, 6)
except Exception as e:
logger.exception("Failing with %s", str(e))
self.fail()
def __getPolymerReferenceSequenceAssignments(self, databaseName,
collectionName, polymerType,
**kwargs):
"""Get all accessions assigned to input reference sequence database for the input polymerType.
Returns:
(dict): {"1abc_1": "rcsb_entity_container_identifiers": {"reference_sequence_identifiers": []},
"rcsb_polymer_entity_align": [],
"rcsb_entity_source_organism"" {"ncbi_taxonomy_id": []}
"""
cachePath = kwargs.get("cachePath", ".")
exDbDir = "exdb"
cacheKwargs = kwargs.get("cacheKwargs", {"fmt": "json", "indent": 3})
useCache = kwargs.get("useCache", True)
fetchLimit = kwargs.get("fetchLimit", None)
cacheFilePath = os.path.join(cachePath, exDbDir,
"entity-poly-ref-seq-assign-cache.json")
#
try:
obEx = ObjectExtractor(
self.__cfgOb,
databaseName=databaseName,
collectionName=collectionName,
cacheFilePath=cacheFilePath,
useCache=useCache,
keyAttribute="entity",
uniqueAttributes=["rcsb_id"],
cacheKwargs=cacheKwargs,
objectLimit=fetchLimit,
selectionQuery={
"entity_poly.rcsb_entity_polymer_type": polymerType
},
selectionList=[
"rcsb_id",
"rcsb_entity_container_identifiers.reference_sequence_identifiers",
"rcsb_entity_container_identifiers.auth_asym_ids",
"rcsb_polymer_entity_align",
"rcsb_entity_source_organism.ncbi_taxonomy_id",
],
)
eCount = obEx.getCount()
logger.info("Entity count is %d", eCount)
objD = obEx.getObjects()
logger.info(
"Reading polymer entity entity count %d ref accession length %d ",
eCount, len(objD))
#
except Exception as e:
logger.exception("Failing for %s (%s) with %s", databaseName,
collectionName, str(e))
return objD
def __getReferenceData(self, databaseName, collectionName, selectD=None):
logger.info("Searching %s %s with selection query %r", databaseName, collectionName, selectD)
obEx = ObjectExtractor(
self.__cfgOb,
databaseName=databaseName,
collectionName=collectionName,
keyAttribute="rcsb_id",
uniqueAttributes=["rcsb_id"],
selectionQuery=selectD,
)
docCount = obEx.getCount()
logger.debug("Reference data match count %d", docCount)
objD = obEx.getObjects()
return objD
def __extractLigandNeighbors(self):
"""Extract unique chemical component ids involved in neighbor interactions with each
polymer and branched entity instance."""
try:
databaseName = "pdbx_core"
collectionName = "pdbx_core_polymer_entity_instance"
obEx = ObjectExtractor(
self.__cfgOb,
databaseName=databaseName,
collectionName=collectionName,
cacheFilePath=None,
useCache=False,
keyAttribute="rcsb_id",
uniqueAttributes=["rcsb_id"],
cacheKwargs=None,
objectLimit=None,
# selectionQuery={"rcsb_polymer_entity_annotation.type": annotationType},
selectionQuery=None,
selectionList=[
"rcsb_id",
"rcsb_polymer_entity_instance_container_identifiers.entry_id",
"rcsb_polymer_entity_instance_container_identifiers.entity_id",
"rcsb_polymer_entity_instance_container_identifiers.asym_id",
"rcsb_ligand_neighbors.ligand_comp_id",
"rcsb_ligand_neighbors.ligand_is_bound",
],
)
eCount = obEx.getCount()
logger.info("Total neighbor count (%d)", eCount)
rD = {}
objD = obEx.getObjects()
for _, peiD in objD.items():
try:
entryId = peiD["rcsb_polymer_entity_instance_container_identifiers"]["entry_id"]
entityId = peiD["rcsb_polymer_entity_instance_container_identifiers"]["entity_id"]
ky = entryId + "_" + entityId
for lnD in peiD["rcsb_ligand_neighbors"] if "rcsb_ligand_neighbors" in peiD else []:
if "ligand_comp_id" in lnD and "ligand_is_bound" in lnD:
rD.setdefault(ky, set()).add((lnD["ligand_comp_id"], lnD["ligand_is_bound"]))
else:
logger.warning("%s %s missing details lnD %r", entryId, entityId, lnD)
except Exception as e:
logger.exception("Failing with %s", str(e))
rD = {k: list(v) for k, v in rD.items()}
logger.info("Unique instance %d", len(rD))
return rD
except Exception as e:
logger.exception("Failing with %s", str(e))
def getReferenceSequenceDetails(self):
"""Get reference protein sequence essential details (sequence, taxonomy, name, gene, ...)"""
uD = None
try:
obEx = ObjectExtractor(
self.__cfgOb,
databaseName="uniprot_exdb",
collectionName="reference_entry",
useCache=False,
keyAttribute="uniprot",
uniqueAttributes=["rcsb_id"],
selectionQuery={},
selectionList=[
"source_scientific",
"taxonomy_id",
"rcsb_id",
"gene",
"names",
"sequence",
],
)
#
eCount = obEx.getCount()
logger.info("Reference entry count is %d", eCount)
objD = obEx.getObjects()
rD = {}
for rId, uD in objD.items():
taxId = uD["taxonomy_id"]
sn = uD["source_scientific"]
sequence = uD["sequence"]
gn = None
pn = None
if "gene" in uD:
for tD in uD["gene"]:
if tD["type"] == "primary":
gn = tD["name"]
break
for tD in uD["names"]:
if tD["nameType"] == "recommendedName":
pn = tD["name"]
break
rD[rId] = {"accession": rId, "taxId": taxId, "scientific_name": sn, "gene": gn, "name": pn, "sequence": sequence}
except Exception as e:
logger.exception("Failing uD %r with %s", uD, str(e))
#
return rD
def getBranchedDetails(self):
"""Get branched entity details (BIRD mapping and WURCS descriptors)"""
rD = {}
try:
#
obEx = ObjectExtractor(
self.__cfgOb,
databaseName="pdbx_core",
collectionName="pdbx_core_branched_entity",
useCache=False,
keyAttribute="entity",
uniqueAttributes=["rcsb_id"],
selectionQuery={},
selectionList=["rcsb_id", "pdbx_entity_branch_descriptor", "rcsb_branched_entity_container_identifiers"],
)
#
# eCount = obEx.getCount()
# logger.info("Branched entity count is %d", eCount)
objD = obEx.getObjects()
rD = {}
for _, eD in objD.items():
rcsbId = eD["rcsb_id"]
#
prdId = None
try:
pD = eD["rcsb_branched_entity_container_identifiers"]
prdId = pD["prd_id"]
except Exception:
pass
#
wurcs = None
try:
for tD in eD["pdbx_entity_branch_descriptor"]:
if tD["type"] == "WURCS":
wurcs = tD["descriptor"]
except Exception:
pass
if prdId or wurcs:
rD[rcsbId] = {"prdId": prdId, "wurcs": wurcs}
except Exception as e:
logger.exception("Failing with %s", str(e))
return rD
def getChemCompAccessionMapping(self, referenceResourceName):
"""Get the accession code mapping between chemical component identifiers and identifier(s) for the
input external reference resource.
Args:
referenceResourceName (str): resource name (e.g. DrugBank, ChEMBL, CCDC)
Returns:
dict: {referenceResourceId: chem_comp/bird_id, referenceResourceId: chem_comp/bird_id, ... }
"""
idD = {}
try:
databaseName = "bird_chem_comp_core"
collectionName = "bird_chem_comp_core"
selectD = {
"rcsb_chem_comp_related.resource_name": referenceResourceName
}
selectionList = ["rcsb_id", "rcsb_chem_comp_related"]
logger.info("Searching %s %s with selection query %r",
databaseName, collectionName, selectD)
obEx = ObjectExtractor(
self.__cfgOb,
databaseName=databaseName,
collectionName=collectionName,
keyAttribute="rcsb_id",
uniqueAttributes=["rcsb_id"],
selectionQuery=selectD,
selectionList=selectionList,
stripObjectId=True,
)
logger.info("Reference data object count %d", obEx.getCount())
objD = obEx.getObjects()
for _, doc in objD.items():
dL = doc["rcsb_chem_comp_related"] if "rcsb_chem_comp_related" in doc else []
for dD in dL:
if dD["resource_name"] == referenceResourceName and "resource_accession_code" in dD:
idD.setdefault(dD["resource_accession_code"],
[]).append(dD["comp_id"])
except Exception as e:
logger.exception("Failing with %s", str(e))
return idD
def testExtractEntityTaxonomyContent(self):
"""Test case - extract unique entity source and host taxonomies"""
try:
obEx = ObjectExtractor(
self.__cfgOb,
databaseName="pdbx_core",
collectionName="pdbx_core_polymer_entity",
cacheFilePath=os.path.join(self.__workPath,
"entity-taxonomy-test-cache.json"),
useCache=False,
keyAttribute="entity",
uniqueAttributes=["rcsb_id"],
cacheKwargs=self.__testEntryCacheKwargs,
# objectLimit=self.__objectLimitTest,
objectLimit=None,
selectionQuery=None,
selectionList=[
"rcsb_id", "rcsb_entity_source_organism.ncbi_taxonomy_id",
"rcsb_entity_host_organism.ncbi_taxonomy_id"
],
)
eCount = obEx.getCount()
logger.info("Polymer entity count is %d", eCount)
taxIdS = set()
objD = obEx.getObjects()
for _, eD in objD.items():
try:
for tD in eD["rcsb_entity_source_organism"]:
taxIdS.add(tD["ncbi_taxonomy_id"])
except Exception:
pass
try:
for tD in eD["rcsb_entity_host_organism"]:
taxIdS.add(tD["ncbi_taxonomy_id"])
except Exception:
pass
logger.info("Unique taxons %d", len(taxIdS))
except Exception as e:
logger.exception("Failing with %s", str(e))
self.fail()
def testExtractEntityTaxonomyContent(self):
"""Test case - extract unique entity source and host taxonomies"""
tL = []
try:
obEx = ObjectExtractor(
self.__cfgOb,
databaseName="pdbx_core",
collectionName="pdbx_core_polymer_entity",
useCache=False,
keyAttribute="entity",
uniqueAttributes=["rcsb_id"],
selectionQuery=None,
selectionList=["rcsb_id", "rcsb_entity_source_organism.ncbi_taxonomy_id", "rcsb_entity_host_organism.ncbi_taxonomy_id"],
)
eCount = obEx.getCount()
logger.info("Polymer entity count is %d", eCount)
objD = obEx.getObjects()
sD = {}
hD = {}
for rId, eD in objD.items():
try:
for tD in eD["rcsb_entity_source_organism"]:
sD.setdefault(rId, []).append(str(tD["ncbi_taxonomy_id"]))
except Exception:
pass
try:
for tD in eD["rcsb_entity_host_organism"]:
hD.setdefault(rId, []).append(str(tD["ncbi_taxonomy_id"]))
except Exception:
pass
for rId, taxIdL in sD.items():
tS = "|".join(sorted(set(taxIdL)))
if tS:
lS = "%s\t%s" % (rId, "|".join(sorted(set(taxIdL))))
tL.append(lS)
self.__mU.doExport(self.__entityTaxonPath, tL, fmt="list")
except Exception as e:
logger.exception("Failing with %s", str(e))
self.fail()
def testExtractEntities(self):
"""Test case - extract entities"""
try:
obEx = ObjectExtractor(
self.__cfgOb,
databaseName="pdbx_core",
collectionName="pdbx_core_polymer_entity",
cacheFilePath=os.path.join(self.__workPath,
"entity-data-test-cache.json"),
useCache=False,
keyAttribute="entity",
uniqueAttributes=["rcsb_id"],
cacheKwargs=self.__testEntryCacheKwargs,
objectLimit=self.__objectLimitTest,
)
eCount = obEx.getCount()
logger.info("Entity count is %d", eCount)
self.assertGreaterEqual(eCount, self.__objectLimitTest)
objD = obEx.getObjects()
for _, obj in objD.items():
obEx.genPathList(obj, path=None)
#
pL = obEx.getPathList(filterList=False)
logger.debug("Path list (unfiltered) %r", pL)
#
pL = obEx.getPathList()
logger.debug("Path list %r", pL)
obEx.setPathList(pL)
if self.__verbose:
for ky, obj in objD.items():
obEx.genValueList(obj, path=None)
tD = obEx.getValues()
logger.info("Index object %r %s", ky,
pprint.pformat(tD, indent=3, width=120))
except Exception as e:
logger.exception("Failing with %s", str(e))
self.fail()
def __extractEntityTaxons(self):
"""Test case - extract unique entity source and host taxonomies"""
try:
obEx = ObjectExtractor(
self.__cfgOb,
databaseName=self.__databaseName,
collectionName=self.__collectionName,
cacheFilePath=None,
useCache=False,
keyAttribute="entity",
uniqueAttributes=["rcsb_id"],
cacheKwargs=None,
objectLimit=None,
# selectionQuery={"entity.type": "polymer"},
selectionQuery=None,
selectionList=[
"rcsb_id", "rcsb_entity_source_organism.ncbi_taxonomy_id",
"rcsb_entity_host_organism.ncbi_taxonomy_id"
],
)
eCount = obEx.getCount()
logger.info("Polymer entity count is %d", eCount)
taxIdS = set()
objD = obEx.getObjects()
for _, eD in objD.items():
try:
for tD in eD["rcsb_entity_source_organism"]:
taxIdS.add(tD["ncbi_taxonomy_id"])
except Exception:
pass
try:
for tD in eD["rcsb_entity_host_organism"]:
taxIdS.add(tD["ncbi_taxonomy_id"])
except Exception:
pass
logger.info("Unique taxons %d", len(taxIdS))
return list(taxIdS)
except Exception as e:
logger.exception("Failing with %s", str(e))
def __extractEntityAnnotationIdentifiers(self, annotationType):
"""Extract unique rcsb_polymer_entity_annotation ids for the input annotation type."""
try:
databaseName = "pdbx_core"
collectionName = "pdbx_core_polymer_entity"
obEx = ObjectExtractor(
self.__cfgOb,
databaseName=databaseName,
collectionName=collectionName,
cacheFilePath=None,
useCache=False,
keyAttribute="entity",
uniqueAttributes=["rcsb_id"],
cacheKwargs=None,
objectLimit=None,
# selectionQuery={"rcsb_polymer_entity_annotation.type": annotationType},
selectionQuery=None,
selectionList=[
"rcsb_id", "rcsb_polymer_entity_annotation.annotation_id",
"rcsb_polymer_entity_annotation.type"
],
)
eCount = obEx.getCount()
logger.info(
"For type %r polymer entity annotation object count is %d",
annotationType, eCount)
idS = set()
objD = obEx.getObjects()
for _, eD in objD.items():
try:
for tD in eD["rcsb_polymer_entity_annotation"]:
if tD["type"] == annotationType:
idS.add(tD["annotation_id"])
except Exception:
pass
logger.info("Unique identifiers %d", len(idS))
return list(idS)
except Exception as e:
logger.exception("Failing with %s", str(e))
def testExtractSelectedEntityContent(self):
"""Test case - extract selected entity content
"reference_sequence_identifiers": [
{
"database_name": "UniProt",
"database_accession": "Q5SHN1",
"provenance_source": "SIFTS"
},
{
"database_name": "UniProt",
"database_accession": "Q5SHN1",
"provenance_source": "PDB"
}
]
"""
try:
obEx = ObjectExtractor(
self.__cfgOb,
databaseName="pdbx_core",
collectionName="pdbx_core_polymer_entity",
cacheFilePath=os.path.join(
self.__workPath,
"entity-selected-content-test-cache.json"),
useCache=False,
keyAttribute="entity",
uniqueAttributes=["rcsb_id"],
cacheKwargs=self.__testEntryCacheKwargs,
# objectLimit=self.__objectLimitTest,
objectLimit=None,
selectionQuery={
"entity_poly.rcsb_entity_polymer_type": "Protein"
},
selectionList=[
"rcsb_id",
"rcsb_polymer_entity_container_identifiers.reference_sequence_identifiers"
],
)
eCount = obEx.getCount()
logger.info("Entity count is %d", eCount)
#
#
if self.__objectLimitTest is not None:
self.assertGreaterEqual(eCount, self.__objectLimitTest)
objD = obEx.getObjects()
for _, obj in objD.items():
obEx.genPathList(obj, path=None)
#
pL = obEx.getPathList(filterList=False)
logger.debug("Path list (unfiltered) %r", pL)
#
pL = obEx.getPathList()
logger.debug("Path list %r", pL)
obEx.setPathList(pL)
if self.__verbose:
for ky, obj in objD.items():
obEx.genValueList(obj, path=None)
tD = obEx.getValues()
logger.info("Index object %r %s", ky,
pprint.pformat(tD, indent=3, width=120))
objD = obEx.getObjects()
# logger.info("objD.keys() %r", list(objD.keys()))
totCount = 0
difCount = 0
pdbUnpIdD = defaultdict(int)
siftsUnpIdD = defaultdict(int)
pdbDifUnpIdD = defaultdict(int)
for entityKey, eD in objD.items():
try:
siftsS = set()
pdbS = set()
for tD in eD["rcsb_polymer_entity_container_identifiers"][
"reference_sequence_identifiers"]:
if tD["database_name"] == "UniProt":
if tD["provenance_source"] == "SIFTS":
siftsS.add(tD["database_accession"])
siftsUnpIdD[tD["database_accession"]] += 1
elif tD["provenance_source"] == "PDB":
pdbS.add(tD["database_accession"])
pdbUnpIdD[tD["database_accession"]] += 1
else:
logger.debug(
"No UniProt for %r",
eD["rcsb_polymer_entity_container_identifiers"]
)
logger.debug("PDB assigned sequence length %d", len(pdbS))
logger.debug("SIFTS assigned sequence length %d",
len(siftsS))
if pdbS and siftsS:
totCount += 1
if pdbS != siftsS:
difCount += 1
for idV in pdbS:
pdbDifUnpIdD[idV] += 1
except Exception as e:
logger.warning("No identifiers for %s with %s", entityKey,
str(e))
logger.info("Total %d differences %d", totCount, difCount)
logger.info("Unique UniProt ids PDB %d SIFTS %d", len(pdbUnpIdD),
len(siftsUnpIdD))
logger.info("Unique UniProt differences %d ", len(pdbDifUnpIdD))
except Exception as e:
logger.exception("Failing with %s", str(e))
self.fail()
def testUpdateSelectedEntityContent(self):
"""Test case - update of selected entity reference sequence content"""
try:
databaseName = "pdbx_core"
collectionName = "pdbx_core_polymer_entity"
obEx = ObjectExtractor(
self.__cfgOb,
databaseName=databaseName,
collectionName=collectionName,
cacheFilePath=os.path.join(
self.__workPath,
"entity-selected-content-test-cache.json"),
useCache=False,
keyAttribute="entity",
uniqueAttributes=["rcsb_id"],
cacheKwargs=self.__testEntryCacheKwargs,
objectLimit=self.__objectLimitTest,
# objectLimit=None,
selectionQuery={
"entity_poly.rcsb_entity_polymer_type": "Protein"
},
selectionList=[
"rcsb_id",
"rcsb_polymer_entity_container_identifiers.reference_sequence_identifiers"
],
)
eCount = obEx.getCount()
logger.info("Entity count is %d", eCount)
objD = obEx.getObjects()
updateDL = []
for entityKey, eD in objD.items():
try:
selectD = {"rcsb_id": entityKey}
tL = (eD["rcsb_polymer_entity_container_identifiers"]
["reference_sequence_identifiers"]
if "reference_sequence_identifiers"
in eD["rcsb_polymer_entity_container_identifiers"]
else [])
tL.append({
"database_accession": "1111111",
"database_name": "PDB",
"provenance_source": "RCSB"
})
#
updateD = {
"rcsb_polymer_entity_container_identifiers.reference_sequence_identifiers":
tL
}
updateDL.append({"selectD": selectD, "updateD": updateD})
except Exception as e:
logger.exception("Failing with %s", str(e))
for ii, uD in enumerate(updateDL):
logger.debug(" >>>> (%d) selectD %r updateD %r", ii,
uD["selectD"], uD["updateD"])
#
obUpd = ObjectUpdater(self.__cfgOb)
numUpd = obUpd.update(databaseName, collectionName, updateDL)
self.assertGreaterEqual(numUpd, len(updateDL))
logger.info("Update count is %d", numUpd)
except Exception as e:
logger.exception("Failing with %s", str(e))
self.fail()
def getProteinSequenceDetails(self, minSeqLen=0):
"""Get protein sequence and taxonomy data (required to build protein sequence fasta file)"""
missingSrcD = {}
rD = {}
try:
unpEx = UniProtExtractor(self.__cfgOb)
unpD = unpEx.getReferenceSequenceDetails()
#
obEx = ObjectExtractor(
self.__cfgOb,
databaseName="pdbx_core",
collectionName="pdbx_core_polymer_entity",
useCache=False,
keyAttribute="entity",
uniqueAttributes=["rcsb_id"],
selectionQuery={
"entity_poly.rcsb_entity_polymer_type": "Protein"
},
selectionList=[
"rcsb_id",
"rcsb_entity_source_organism",
"rcsb_polymer_entity.rcsb_source_part_count",
"rcsb_polymer_entity.rcsb_source_taxonomy_count",
"rcsb_polymer_entity.src_method",
"entity_poly",
"rcsb_polymer_entity_align",
],
)
#
eCount = obEx.getCount()
logger.info("Polymer entity count is %d", eCount)
objD = obEx.getObjects()
rD = {}
for rId, eD in objD.items():
try:
pD = eD["entity_poly"]
seqS = pD["pdbx_seq_one_letter_code_can"]
seqLen = len(seqS)
except Exception:
logger.warning("%s no one-letter-code sequence", rId)
#
if seqLen < minSeqLen:
continue
#
srcMethod = None
try:
pD = eD["rcsb_polymer_entity"]
srcMethod = pD["src_method"]
except Exception:
pass
#
if "rcsb_entity_source_organism" not in eD:
logger.debug(
"%s No source information (%r) skipping (seqLen %d)",
rId, srcMethod, seqLen)
continue
try:
sL = []
for tD in eD["rcsb_entity_source_organism"]:
srcName = tD[
"scientific_name"] if "scientific_name" in tD else None
if "beg_seq_num" in tD and "end_seq_num" in tD:
begSeqNum = tD["beg_seq_num"]
endSeqNum = tD["end_seq_num"] if tD[
"end_seq_num"] <= seqLen else seqLen
else:
begSeqNum = 1
endSeqNum = seqLen
srcId = tD["pdbx_src_id"]
srcType = tD["source_type"]
taxId = tD[
"ncbi_taxonomy_id"] if "ncbi_taxonomy_id" in tD else -1
if srcName and taxId == -1:
missingSrcD.setdefault(srcName, []).append(rId)
orgName = tD[
"ncbi_scientific_name"] if "ncbi_scientific_name" in tD else ""
sL.append({
"srcId": srcId,
"taxId": taxId,
"orgName": orgName,
"entitySeqBeg": begSeqNum,
"entitySeqEnd": endSeqNum
})
if len(sL) == 1:
sL[0]["entitySeqBeg"] = 1
sL[0]["entitySeqEnd"] = seqLen
except Exception as e:
logger.exception("Failing for (%r) tD %r with %s", rId, tD,
str(e))
#
try:
pD = eD["rcsb_polymer_entity"]
partCount = pD["rcsb_source_part_count"]
except Exception:
logger.warning("%s no source part count", rId)
partCount = 1
try:
pD = eD["rcsb_polymer_entity"]
taxCount = pD["rcsb_source_taxonomy_count"]
except Exception:
if srcType == "synthetic":
taxCount = 0
else:
logger.warning(
"%s (srcName %r) no source taxonomy count type %r",
rId, srcName, srcType)
if srcName:
taxCount = 1
else:
taxCount = 0
#
uDL = []
try:
for tD in eD["rcsb_polymer_entity_align"]:
uD = {}
if tD["reference_database_name"] in [
"UniProt", "GenBank", "PIR", "EMBL", "NORINE",
"PRF"
]:
uD["refDbId"] = tD["reference_database_accession"]
uD["refDbName"] = tD["reference_database_name"]
uD["provSource"] = tD["provenance_source"]
if tD["reference_database_accession"] in unpD:
uD.update(
unpD[tD["reference_database_accession"]])
aL = []
for qD in tD["aligned_regions"]:
if qD["entity_beg_seq_id"] + qD[
"length"] - 1 > seqLen:
qD["length"] = seqLen - qD[
"entity_beg_seq_id"] + 1
srcId = self.__getSourcePart(
rId, sL, qD["entity_beg_seq_id"],
qD["length"])
aL.append({
"srcId":
srcId,
"entitySeqBeg":
qD["entity_beg_seq_id"],
"refSeqBeg":
qD["ref_beg_seq_id"],
"length":
qD["length"]
})
uD["alignList"] = aL
uDL.append(uD)
else:
logger.info("%s reference database %s", rId,
tD["reference_database_name"])
except Exception:
pass
rD[rId] = {
"alignmentL": uDL,
"sourceOrgL": sL,
"partCount": partCount,
"taxCount": taxCount,
"sequence": seqS,
"seqLen": seqLen
}
except Exception as e:
logger.exception("Failing with %s", str(e))
return rD, missingSrcD