def reference_store(source='', identifier=''):
"""
:param source: database source to be referenced (key name from source_qids)
:param ref_type: type of WD reference statement (imported from, stated in) (key names from prop_ids)
:return: PBB_Core reference object for database source
"""
source_items = {'uniprot': 'Q905695',
'ncbi_gene': 'Q20641742',
'ncbi_taxonomy': 'Q13711410',
'swiss_prot': 'Q2629752',
'trembl': 'Q22935315'}
prop_ids = {'uniprot': 'P352',
'ncbi_gene': 'P351',
'ncbi_taxonomy': 'P685',
'ncbi_locus_tag': 'P2393'
}
refs = [PBB_Core.WDItemID(value=source_items[source], prop_nr='P248', is_reference=True),
PBB_Core.WDItemID(value='Q1860', prop_nr='P407', is_reference=True),
PBB_Core.WDString(value=identifier, prop_nr=prop_ids[source], is_reference=True),
PBB_Core.WDTime(str(strftime("+%Y-%m-%dT00:00:00Z", gmtime())), prop_nr='P813', is_reference=True)
]
for ref in refs:
ref.overwrite_references = True
return refs
def make_reference(self,
stated_in,
source_element,
source_element_name,
source_element_prop,
date=time.strftime('+%Y-%m-%dT00:00:00Z'),
date_property='P813'):
ref = [[
PBB_Core.WDItemID(value=stated_in,
prop_nr='P248',
is_reference=True), # stated in
PBB_Core.WDString(value=source_element,
prop_nr=source_element_prop,
is_reference=True), # source element
PBB_Core.WDItemID(value='Q1860', prop_nr='P407',
is_reference=True), # language of work
PBB_Core.WDMonolingualText(value=source_element_name,
language='en',
prop_nr='P1476',
is_reference=True),
PBB_Core.WDTime(time=date,
prop_nr=date_property,
is_reference=True) # publication date
]]
# this will overwrite all existing references of a WD claim value.
for x in ref[0]:
x.overwrite_references = True
return ref
def __init__(self, object):
self.logincreds = object["logincreds"]
self.name = object["uberonLabel"]
self.uberon = object["uberon"]
self.uberon_id = self.uberon.replace("http://purl.obolibrary.org/obo/UBERON_", "")
self.wikidata_id = object["wikidata_id"]
self.start = object["start"]
self.graph = object["graph"]
subcls = URIRef("http://www.w3.org/2000/01/rdf-schema#subClassOf")
id = URIRef("http://www.geneontology.org/formats/oboInOwl#id")
hasExactSyn = URIRef("http://www.geneontology.org/formats/oboInOwl#hasExactSynonym")
print(self.uberon_id)
print(self.name)
refStatedIn = PBB_Core.WDItemID(21552738, prop_nr='P248', is_reference=True)
refStatedIn.overwrite_references = True
refImported = PBB_Core.WDItemID(value=7876491, prop_nr='P143', is_reference=True)
refImported.overwrite_references = True
timeStringNow = strftime("+%Y-%m-%dT00:00:00Z", gmtime())
refRetrieved = PBB_Core.WDTime(timeStringNow, prop_nr='P813', is_reference=True)
refRetrieved.overwrite_references = True
ub_reference = [refStatedIn, refImported, refRetrieved]
if self.uberon_id in self.wikidata_id.keys():
self.wdid = self.wikidata_id[self.uberon_id.replace("UBERON:", "")]
else:
self.wdid = None
self.synonyms = []
for synonym in self.graph.objects(URIRef(self.uberon), hasExactSyn):
self.synonyms.append(str(synonym))
prep = dict()
prep["P279"] = [PBB_Core.WDItemID(value='Q4936952', prop_nr='P279', references=[copy.deepcopy(ub_reference)])]
prep["P1554"] = [PBB_Core.WDString(value=self.uberon_id, prop_nr='P1554', references=[copy.deepcopy(ub_reference)])]
print(self.uberon)
prep["P1709"] = [PBB_Core.WDUrl(value=self.uberon, prop_nr='P1709', references=[copy.deepcopy(ub_reference)])]
data2add = []
for key in prep.keys():
for statement in prep[key]:
data2add.append(statement)
print(statement.prop_nr, statement.value)
if self.wdid is not None:
wdPage = PBB_Core.WDItemEngine(self.wdid, item_name=self.name, data=data2add, server="www.wikidata.org", domain="anatomical_structure",append_value=['P279'])
else:
wdPage = PBB_Core.WDItemEngine(item_name=self.name, data=data2add, server="www.wikidata.org", domain="anatomical_structure", append_value=['P279'])
if len(self.synonyms) >0:
wdPage.set_aliases(aliases=self.synonyms, lang='en', append=True)
print(self.synonyms)
for syn in self.synonyms:
print(syn)
wdPage.write(self.logincreds)
print("======")
sys.exit()
def create_reference(self):
first_ref = PBB_Core.WDItemID(value='Q905695', prop_nr='P248', is_reference=True)
first_ref.overwrite_references = True
return [
first_ref,
PBB_Core.WDString(value=self.uniprot, prop_nr='P352', is_reference=True),
PBB_Core.WDTime(time=time.strftime('+%Y-%m-%dT00:00:00Z', time.gmtime()), prop_nr='P813',
is_reference=True),
PBB_Core.WDItemID(value='Q1860', prop_nr='P407', is_reference=True), # language of work
]
def __init__(self, object):
self.logincreds = object["logincreds"]
self.source = object["source"]
self.ortholog = object["ortholog"]
self.species = object["speciesWdID"]
# Prepare references
refStatedInHomologeneBuild = PBB_Core.WDItemID(value='Q20976936',
prop_nr='P248',
is_reference=True)
refImportedFromHomologen = PBB_Core.WDItemID(value='Q468215',
prop_nr='P143',
is_reference=True)
timeStringNow = strftime("+%Y-%m-%dT00:00:00Z", gmtime())
refRetrieved = PBB_Core.WDTime(timeStringNow,
prop_nr='P813',
is_reference=True)
homologene_reference = [[
refStatedInHomologeneBuild, refImportedFromHomologen, refRetrieved
]]
# Prepare qualifiers
humanQualifier = PBB_Core.WDItemID(value='Q5',
prop_nr='P703',
is_qualifier=True)
mouseQualifier = PBB_Core.WDItemID(value='Q83310',
prop_nr='P703',
is_qualifier=True)
# Prepare the items to add
if self.species == "Q5":
orthologValue = PBB_Core.WDItemID(value=self.ortholog,
prop_nr='P684',
references=homologene_reference,
qualifiers=[humanQualifier])
elif self.species == "Q83310":
orthologValue = PBB_Core.WDItemID(value=self.ortholog,
prop_nr='P684',
references=homologene_reference,
qualifiers=[mouseQualifier])
wdPage = PBB_Core.WDItemEngine(wd_item_id=self.source,
data=[orthologValue],
server="www.wikidata.org",
domain="genes")
print(wdPage.wd_json_representation)
wdPage.write(self.logincreds)
def create_reference(self):
return [
PBB_Core.WDItemID(value=self.ontology_ref_item,
prop_nr='P248',
is_reference=True),
PBB_Core.WDItemID(value='Q22230760',
prop_nr='P143',
is_reference=True),
PBB_Core.WDTime(time=time.strftime('+%Y-%m-%dT00:00:00Z',
time.gmtime()),
prop_nr='P813',
is_reference=True),
PBB_Core.WDItemID(value='Q1860', prop_nr='P407',
is_reference=True), # language of work
]
def generate_refs(iuphar_ligand):
ref_list = [[]]
ref_list[0].extend([
PBB_Core.WDItemID(value='Q2793172', prop_nr='P248',
is_reference=True), # stated in
PBB_Core.WDString(value=iuphar_ligand,
prop_nr='P595',
is_reference=True), # source element
])
ref_list[0].extend([
PBB_Core.WDItemID(value='Q1860', prop_nr='P407',
is_reference=True), # language of work
# PBB_Core.WDMonolingualText(value=source_element_name, language='en',
# prop_nr='P1476', is_reference=True),
PBB_Core.WDTime(time=time.strftime('+%Y-%m-%dT00:00:00Z'),
prop_nr='P813',
is_reference=True) # publication date
])
return ref_list
def generate_refs(ref_source_id):
ref_list = [[]]
if ref_source_id.startswith('C'):
ref_list[0].extend([
PBB_Core.WDItemID(value='Q6120337', prop_nr='P248', is_reference=True), # stated in
PBB_Core.WDString(value=ref_source_id, prop_nr='P592', is_reference=True), # source element
])
elif ref_source_id.startswith('N'):
ref_list[0].extend([
PBB_Core.WDItemID(value='Q21008030', prop_nr='P248', is_reference=True), # stated in
PBB_Core.WDString(value=ref_source_id, prop_nr='P2115', is_reference=True), # source element
])
ref_list[0].extend([
PBB_Core.WDItemID(value='Q1860', prop_nr='P407', is_reference=True), # language of work
# PBB_Core.WDMonolingualText(value=source_element_name, language='en',
# prop_nr='P1476', is_reference=True),
PBB_Core.WDTime(time=time.strftime('+%Y-%m-%dT00:00:00Z'), prop_nr='P813', is_reference=True) # publication date
])
return ref_list
def __init__(self, object):
"""
constructor
:param wd_do_content: Wikidata item id
:param do_id: Identifier of the disease in Disease Ontology
:param label: Primary label of the disease in Disease Ontology
:param synonyms: All synonyms for the disease captured in the Disease Ontology
:param xrefs: a dictionary with all external references of the Disease captured in the Disease Ontology
"""
# Reference section
doVersionURL = object[1]
doClass = object[0]
self.logincreds = object[3]
self.wd_doMappings = object[2]
self.start = object[4]
self.wd_do_content = doClass
PBB_Debug.prettyPrint(self.wd_do_content)
self.do_id = self.getDoValue(self.wd_do_content,
'.//oboInOwl:id')[0].text
print(self.do_id)
self.name = self.getDoValue(self.wd_do_content,
'.//rdfs:label')[0].text
print(self.name)
classDescription = self.getDoValue(
self.wd_do_content,
'.//oboInOwl:hasDefinition/oboInOwl:Definition/rdfs:label')
if len(classDescription) > 0:
self.description = classDescription[0].text
if self.do_id in object[2].keys():
self.wdid = "Q" + str(object[2][self.do_id])
else:
self.wdid = None
if len(self.getDoValue(self.wd_do_content,
'.//owl:deprecated')) > 0 and self.getDoValue(
self.wd_do_content,
'.//owl:deprecated')[0].text == "true":
self.rank = "deprecated"
else:
self.rank = "normal"
self.synonyms = []
for synonym in self.getDoValue(self.wd_do_content,
'.//oboInOwl:hasExactSynonym'):
self.synonyms.append(synonym.text)
self.subclasses = []
for subclass in self.getDoValue(self.wd_do_content,
'.//rdfs:subClassOf'):
parts = subclass.get(
'{http://www.w3.org/1999/02/22-rdf-syntax-ns#}resource').split(
"DOID_")
if len(parts) > 1:
self.subclasses.append("DOID:" + parts[1])
if "DOID:4" in self.subclasses:
self.subclasses.remove("DOID:4")
self.xrefs = dict()
for xref in self.getDoValue(self.wd_do_content,
'.//oboInOwl:hasDbXref'):
if not xref.text.split(":")[0] in self.xrefs.keys():
self.xrefs[xref.text.split(":")[0]] = []
self.xrefs[xref.text.split(":")[0]].append(xref.text.split(":")[1])
refStatedIn = PBB_Core.WDUrl(value=doVersionURL,
prop_nr='P1065',
is_reference=True)
refStatedIn.overwrite_references = True
refImported = PBB_Core.WDItemID(value=5282129,
prop_nr='P248',
is_reference=True)
refImported.overwrite_references = True
timeStringNow = strftime("+%Y-%m-%dT00:00:00Z", gmtime())
refRetrieved = PBB_Core.WDTime(timeStringNow,
prop_nr='P813',
is_reference=True)
refRetrieved.overwrite_references = True
do_reference = [refImported, refRetrieved, refStatedIn]
prep = dict()
prep["P279"] = [
PBB_Core.WDItemID(value='Q12136',
prop_nr='P279',
references=[copy.deepcopy(do_reference)],
rank=self.rank)
]
# Subclass of disease
for subclass in self.subclasses:
if subclass in self.wd_doMappings.keys():
prep["P279"].append(
PBB_Core.WDItemID(value=self.wd_doMappings[subclass],
prop_nr='P279',
references=[copy.deepcopy(do_reference)],
rank=self.rank))
if "Orphanet" in self.xrefs.keys():
prep["P1550"] = []
if isinstance(self.xrefs["Orphanet"], list):
for id in self.xrefs["Orphanet"]:
prep["P1550"].append(
PBB_Core.WDString(
value=self.xrefs["Orphanet"],
prop_nr='P1550',
references=[copy.deepcopy(do_reference)],
rank=self.rank))
else:
prep["P1550"] = [
PBB_Core.WDString(value=self.xrefs["Orphanet"],
prop_nr='P1550',
references=[copy.deepcopy(do_reference)],
rank=self.rank)
]
#disease Ontology
prep["P699"] = [
PBB_Core.WDString(value=self.do_id,
prop_nr='P699',
references=[do_reference],
rank=self.rank)
]
if "url" in self.xrefs.keys():
if isinstance(self.xrefs["url"], list):
for i in self.xrefs["url"]:
if "//en.wikipedia.org/wiki/" in i:
wikilink = self.i.replace("//en.wikipedia.org/wiki/",
"").replace("_", "")
else:
wikilink = None
else:
if "//en.wikipedia.org/wiki/" in xrefs["url"]:
wikilink = xrefs["url"].replace("//en.wikipedia.org/wiki/",
"").replace("_", "")
else:
wikilink = None
else:
wikilink = None
if "ICD10CM" in self.xrefs.keys():
prep["P494"] = []
if isinstance(self.xrefs["ICD10CM"], list):
for id in self.xrefs["ICD10CM"]:
prep["P494"].append(
PBB_Core.WDString(
value=id,
prop_nr='P494',
references=[copy.deepcopy(do_reference)],
rank=self.rank))
else:
prep["P494"] = [
PBB_Core.WDString(value=self.xrefs["ICD10CM"],
prop_nr='P494',
references=[copy.deepcopy(do_reference)],
rank=self.rank)
]
if "ICD9CM" in self.xrefs.keys():
prep["P493"] = []
if isinstance(self.xrefs["ICD9CM"], list):
for id in self.xrefs["ICD9CM"]:
prep["P493"].append(
PBB_Core.WDString(
value=id,
prop_nr='P493',
references=[copy.deepcopy(do_reference)],
rank=self.rank))
else:
prep["P493"] = [
PBB_Core.WDString(value=self.xrefs["ICD9CM"],
prop_nr='P493',
references=[copy.deepcopy(do_reference)],
rank=self.rank)
]
if "MSH" in self.xrefs.keys():
prep["P486"] = []
if isinstance(self.xrefs["MSH"], list):
for id in self.xrefs["MSH"]:
prep["P486"].append(
PBB_Core.WDString(
value=id,
prop_nr='P486',
references=[copy.deepcopy(do_reference)],
rank=self.rank))
else:
prep["P486"] = [
PBB_Core.WDString(value=self.xrefs["MSH"],
prop_nr='P486',
references=[copy.deepcopy(do_reference)],
rank=self.rank)
]
if "NCI" in self.xrefs.keys():
prep["P1748"] = []
if isinstance(self.xrefs["NCI"], list):
for id in self.xrefs["NCI"]:
prep["P1748"].append(
PBB_Core.WDString(
value=id,
prop_nr='P1748',
references=[copy.deepcopy(do_reference)],
rank=self.rank))
else:
prep["P1748"] = [
PBB_Core.WDString(value=self.xrefs["NCI"],
prop_nr='P1748',
references=[copy.deepcopy(do_reference)],
rank=self.rank)
]
if "OMIM" in self.xrefs.keys():
prep["P492"] = []
if isinstance(self.xrefs["OMIM"], list):
for id in self.xrefs["OMIM"]:
prep["P492"].append(
PBB_Core.WDString(
value=id,
prop_nr='P492',
references=[copy.deepcopy(do_reference)],
rank=self.rank))
else:
prep["P492"] = [
PBB_Core.WDString(value=self.xrefs["OMIM"],
prop_nr='P492',
references=[copy.deepcopy(do_reference)],
rank=self.rank)
]
print(self.wdid)
data2add = []
for key in prep.keys():
for statement in prep[key]:
data2add.append(statement)
print(statement.prop_nr, statement.value)
if self.wdid is not None:
wdPage = PBB_Core.WDItemEngine(self.wdid,
item_name=self.name,
data=data2add,
server="www.wikidata.org",
domain="diseases",
append_value=['P279'])
else:
wdPage = PBB_Core.WDItemEngine(item_name=self.name,
data=data2add,
server="www.wikidata.org",
domain="diseases",
append_value=['P279'])
# wdPage.set_description(description='Human disease', lang='en')
if wikilink is not None:
wdPage.set_sitelink(site="enwiki", title=wikilink)
if self.synonyms is not None:
wdPage.set_aliases(aliases=self.synonyms, lang='en', append=True)
self.wd_json_representation = wdPage.get_wd_json_representation()
PBB_Debug.prettyPrint(self.wd_json_representation)
wdPage.write(self.logincreds)
if not os.path.exists('./json_dumps'):
os.makedirs('./json_dumps')
f = open('./json_dumps/' + self.do_id.replace(":", "_") + '.json',
'w+')
pprint.pprint(self.wd_json_representation, stream=f)
f.close()
PBB_Core.WDItemEngine.log(
'INFO',
'{main_data_id}, "{exception_type}", "{message}", {wd_id}, {duration}'
.format(main_data_id=self.do_id,
exception_type='',
message=f.name,
wd_id=self.wdid,
duration=time.time() - self.start))
for gene in genes:
for lgene in list_genes:
if gene == lgene['symbol']:
lgene['operon'] = {'operon': operon, 'strand': strand}
f.close()
return list_genes
ops = combine_resources()
#pprint.pprint(ops)
genestot = len(ops)
count = 0
reference = [
PBB_Core.WDString(value='19448609', prop_nr='P698', is_reference=True),
PBB_Core.WDTime(str(strftime("+%Y-%m-%dT00:00:00Z", gmtime())),
prop_nr='P813',
is_reference=True)
]
for ref in reference:
ref.overwrite_references = True
login = PBB_login.WDLogin(sys.argv[1], sys.argv[2])
for gene in ops:
statements = []
if 'locus_tag' in gene.keys():
item_name = '{} {}'.format(gene['name'], gene['locus_tag'])
if 'operon' in gene.keys():
count += 1
if count > 640:
wd_operon = los.listeria_operons[gene['operon']
def __init__(self, object):
# Populate variables with different values
self.geneSymbols = object["geneSymbols"]
self.logincreds = object["logincreds"]
self.goTerms = object["goTerms"]
self.version = object["results"]["bindings"][0]["upversion"]["value"]
self.uniprot = object["results"]["bindings"][0]["uniprot"]["value"]
self.uniprotId = object["id"]
self.name = object["results"]["bindings"][0]["plabel"]["value"]
self.start = object["start"]
self.entrezWikidataIds = object["entrezWikidataIds"]
up_in_wd = search_wd(self.name)
self.wdid = None
hits = []
for result in up_in_wd["search"]:
if result["match"]["text"] == up_in_wd["searchinfo"]["search"]:
hits.append(result)
print(result["match"]["text"])
if len(hits) > 0:
valid = []
for hit in hits:
hitPage = PBB_Core.WDItemEngine(item_name=hit["label"],
wd_item_id=hit["id"],
data=[],
server="www.wikidata.org",
domain="proteins")
json_rep = hitPage.get_wd_json_representation()
proteinClaim = False
geneClaim = False
speciesClaim = False
if "P279" in json_rep["claims"].keys():
for it in json_rep["claims"]["P279"]:
if it["mainsnak"]["datavalue"]["value"][
"numeric-id"] == 8054:
proteinClaim = True
break
if it["mainsnak"]["datavalue"]["value"][
"numeric-id"] == 7187:
geneClaim = True
break
if it["mainsnak"]["datavalue"]["value"][
"numeric-id"] == 407355:
proteinClaim = True
break
if "P31" in json_rep["claims"].keys():
for it in json_rep["claims"]["P31"]:
if it["mainsnak"]["datavalue"]["value"][
"numeric-id"] == 8047:
proteinClaim = True
break
if it["mainsnak"]["datavalue"]["value"][
"numeric-id"] == 8054:
proteinClaim = True
break
if "P703" in json_rep["claims"].keys():
for it in json_rep["claims"]["P703"]:
if it["mainsnak"]["datavalue"]["value"][
"numeric-id"] == 5:
speciesClaim = True
break
if len(json_rep["claims"]) == 0:
raise Exception(hit["id"] +
" has an indentical label as " +
self.uniprotId + ", but with no claims")
elif ("P352" in json_rep["claims"].keys()
or "P705" in json_rep["claims"].keys() or proteinClaim):
valid.append(hit["id"])
elif geneClaim:
self.wdid = None
else:
raise Exception(hit["id"] + " has an identical label as " +
self.uniprotId +
" but with no valid protein claims")
if len(valid) == 1:
self.wdid = valid[0]
elif len(valid) > 1:
raise Exception(
self.uniprotId +
" There are multiple valid Wikidata items that might be applicable. "
+ str(valid))
if "gene_id" in object["results"]["bindings"][0].keys():
self.gene_id = []
for geneId in object["results"]["bindings"][0]["gene_id"][
"value"].split(";"):
if geneId != "":
self.gene_id.append(geneId)
if "ecName" in object["results"]["bindings"][0].keys():
self.ecname = []
self.ecname.append(
object["results"]["bindings"][0]["ecName"]["value"])
self.alias = []
for syn in object["results"]["bindings"][0]["upalias"]["value"].split(
";"):
if syn != "":
self.alias.append(syn)
if "pdbid" in object["results"]["bindings"][0].keys(
) and object["results"]["bindings"][0]["pdbid"]["value"] != "":
self.pdb = []
for pdbId in object["results"]["bindings"][0]["pdbid"][
"value"].split(";"):
self.pdb.append(
pdbId.replace("http://rdf.wwpdb.org/pdb/",
"").replace(" ", ""))
if "refseqid" in object["results"]["bindings"][0].keys():
self.refseq = []
for refseqId in object["results"]["bindings"][0]["refseqid"][
"value"].split(";"):
self.refseq.append(
refseqId.replace("http://purl.uniprot.org/refseq/",
"").replace(" ", ""))
if "ensemblp" in object["results"]["bindings"][0].keys(
) and object["results"]["bindings"][0]["ensemblp"]["value"] != "":
self.ensemblp = []
for ensP in object["results"]["bindings"][0]["ensemblp"][
"value"].split(";"):
self.ensemblp.append(
ensP.replace("http://purl.uniprot.org/ensembl/",
"").replace(" ", ""))
# Prepare references
refStatedIn = PBB_Core.WDItemID(value=2629752,
prop_nr='P248',
is_reference=True)
refStatedIn.overwrite_references = True
refURL = "http://www.uniprot.org/uniprot/" + self.uniprotId + ".txt?version=" + str(
self.version)
refReferenceURL = PBB_Core.WDUrl(value=refURL,
prop_nr='P854',
is_reference=True)
refReferenceURL.overwrite_references = True
refImported = PBB_Core.WDItemID(value=905695,
prop_nr='P143',
is_reference=True)
refImported.overwrite_references = True
timeStringNow = strftime("+%Y-%m-%dT00:00:00Z", gmtime())
refRetrieved = PBB_Core.WDTime(timeStringNow,
prop_nr='P813',
is_reference=True)
refRetrieved.overwrite_references = True
protein_reference = [[
refStatedIn, refImported, refRetrieved, refReferenceURL
]]
references = dict()
proteinPrep = dict()
genePrep = dict()
# P279 = subclass of
proteinPrep['P279'] = [
PBB_Core.WDItemID(value="Q8054",
prop_nr='P279',
references=protein_reference)
]
# P703 = found in taxon
proteinPrep['P703'] = [
PBB_Core.WDItemID(value="Q5",
prop_nr='P703',
references=protein_reference)
]
# P352 = UniprotID
proteinPrep['P352'] = [
PBB_Core.WDString(value=self.uniprotId,
prop_nr='P352',
references=protein_reference)
]
# P591 = ec number
if "ecname" in vars(self):
proteinPrep['P591'] = []
for i in range(len(self.ecname)):
proteinPrep['P591'].append(
PBB_Core.WDString(value=self.ecname[i],
prop_nr='P591',
references=protein_reference))
# P638 = PDBID
if "pdb" in vars(self) and len(self.pdb) > 0:
proteinPrep['P638'] = []
for i in range(len(self.pdb)):
proteinPrep['P638'].append(
PBB_Core.WDString(value=self.pdb[i],
prop_nr='P638',
references=protein_reference))
# P637 = Refseq Protein ID
if "refseq" in vars(self) and len(self.refseq) > 0:
proteinPrep['P637'] = []
for i in range(len(self.refseq)):
proteinPrep['P637'].append(
PBB_Core.WDString(value=self.refseq[i],
prop_nr='P637',
references=protein_reference))
# P705 = Ensembl Protein ID
if "ensemblp" in vars(self) and len(self.ensemblp) > 0:
proteinPrep['P705'] = []
for i in range(len(self.ensemblp)):
proteinPrep['P705'].append(
PBB_Core.WDString(value=self.ensemblp[i],
prop_nr='P705',
references=protein_reference))
"""
# P686 = Gene Ontology ID
proteinPrep["P680"] = []
proteinPrep["P681"] = []
proteinPrep["P682"] = []
for result in self.goTerms["results"]["bindings"]:
statement = [
PBB_Core.WDString(value=result["go"]["value"].replace("http://purl.obolibrary.org/obo/GO_", "GO:"),
prop_nr='P686', references=protein_reference)]
goWdPage = PBB_Core.WDItemEngine(item_name=result["goLabel"]["value"], data=statement,
server="www.wikidata.org", domain="proteins")
if goWdPage.get_description() == "":
goWdPage.set_description("Gene Ontology term")
js = goWdPage.get_wd_json_representation()
goWdId = goWdPage.write(self.logincreds)
if result["parentLabel"]["value"] == "molecular_function":
exists = False
for i in range(len(proteinPrep["P680"])):
if proteinPrep["P680"][i].value == goWdId:
exists = True
if not exists:
proteinPrep["P680"].append(
PBB_Core.WDItemID(value=goWdId, prop_nr='P680', references=protein_reference))
if result["parentLabel"]["value"] == "cellular_component":
exists = False
for i in range(len(proteinPrep["P681"])):
if proteinPrep["P681"][i].value == goWdId:
exists = True
if not exists:
proteinPrep["P681"].append(
PBB_Core.WDItemID(value=goWdId, prop_nr='P681', references=protein_reference))
if result["parentLabel"]["value"] == "biological_process":
exists = False
for i in range(len(proteinPrep["P682"])):
if proteinPrep["P682"][i].value == goWdId:
exists = True
if not exists:
proteinPrep["P682"].append(
PBB_Core.WDItemID(value=goWdId, prop_nr='P682', references=protein_reference))
"""
# P702 = Encoded by
if "gene_id" in vars(self) and len(self.gene_id) > 0:
proteinPrep['P702'] = []
proteinPrep['P702'].append(
PBB_Core.WDItemID(
value=self.entrezWikidataIds[self.gene_id[0].replace(
"http://purl.uniprot.org/geneid/",
"").replace(" ", "")],
prop_nr='P702',
references=protein_reference))
proteinData2Add = []
for key in proteinPrep.keys():
for statement in proteinPrep[key]:
proteinData2Add.append(statement)
print(statement.prop_nr, statement.value)
if self.wdid is None:
wdProteinpage = PBB_Core.WDItemEngine(item_name=self.name,
data=proteinData2Add,
server="www.wikidata.org",
domain="proteins",
append_value=['P279'])
else:
wdProteinpage = PBB_Core.WDItemEngine(wd_item_id=self.wdid,
item_name=self.name,
data=proteinData2Add,
server="www.wikidata.org",
domain="proteins",
append_value=['P279'])
if len(self.alias) > 0:
wdProteinpage.set_aliases(aliases=self.alias,
lang='en',
append=True)
if wdProteinpage.get_description() == "":
wdProteinpage.set_description(description='human protein',
lang='en')
if wdProteinpage.get_description(lang="de") == "":
wdProteinpage.set_description(description='humanes Protein',
lang='de')
if wdProteinpage.get_description(lang="nl") == "":
wdProteinpage.set_description(description='menselijk eiwit',
lang='nl')
if wdProteinpage.get_description(
lang="fr") == "" or wdProteinpage.get_description(
lang="fr") == "protéine":
wdProteinpage.set_description(description='protéine humaine',
lang='fr')
self.wd_json_representation = wdProteinpage.get_wd_json_representation(
)
PBB_Debug.prettyPrint(self.wd_json_representation)
wdProteinpage.write(self.logincreds)
print(wdProteinpage.wd_item_id)
if not os.path.exists('./json_dumps'):
os.makedirs('./json_dumps')
f = open('./json_dumps/' + self.uniprotId + '.json', 'w+')
pprint.pprint(self.wd_json_representation, stream=f)
f.close()
PBB_Core.WDItemEngine.log(
'INFO',
'{main_data_id}, "{exception_type}", "{message}", {wd_id}, {duration}'
.format(main_data_id=self.uniprotId,
exception_type='',
message=f.name,
wd_id=self.wdid,
duration=time.time() - self.start))
print("===============")
str(gnsym_gemma_ids[values["Gene Symbol"]]),
prop_nr='P854',
is_reference=True)
refURL2 = PBB_Core.WDUrl(value=values["Web Link"],
prop_nr='P854',
is_reference=True)
refImported = PBB_Core.WDItemID(value='Q22330995',
prop_nr='P143',
is_reference=True)
refImported.overwrite_references = True
refStated = PBB_Core.WDItemID(value='Q22978334',
prop_nr='P248',
is_reference=True)
timeStringNow = strftime("+%Y-%m-%dT00:00:00Z", gmtime())
refRetrieved = PBB_Core.WDTime(timeStringNow,
prop_nr='P813',
is_reference=True)
refRetrieved.overwrite_references = True
gnasscn_reference = [[
refURL, refURL2, refStated, refImported, refRetrieved
]]
value = PBB_Core.WDItemID(value=disease_wdid,
prop_nr="P2293",
references=gnasscn_reference)
# Get a pointer to the Wikidata page on the gene under scrutiny
wd_gene_page = PBB_Core.WDItemEngine(
wd_item_id=values["gene_wdid"],
data=[value],
server="www.wikidata.org",
domain="genes")