def remote(q):
sparql = SPARQLWrapper(sparql_host)
sparql.setRequestMethod("postdirectly")
sparql.setMethod('POST')
log.debug(u'Querying: {}'.format(q))
sparql.setQuery(q)
sparql.addCustomParameter('infer', str(infer).lower())
if not ('construct' in q.lower()):
sparql.setReturnFormat(JSON)
else:
sparql.setReturnFormat(N3)
try:
results = sparql.query().convert()
except Exception as e:
raise e
if isinstance(results, str):
return results.decode('utf-8').encode('utf-8', 'replace')
else:
if 'results' in results:
return json.dumps(
results["results"]["bindings"]).decode('utf-8').encode(
'utf-8', 'replace')
else:
return json.dumps(results['boolean']).decode('utf-8').encode(
'utf-8', 'replace')
def get_pairs(infer):
offset = 0
limit = 100
total_results = set()
new_results = -1
while new_results != 0:
query_string = """
PREFIX rdfs:<http://www.w3.org/2000/01/rdf-schema#>
SELECT DISTINCT ?s ?o WHERE {
?s rdfs:subClassOf ?o.
FILTER (?s != ?o)
FILTER (?o != <http://www.w3.org/2000/01/rdf-schema#Resource>)
} OFFSET %d LIMIT %d
""" % (offset, limit)
sparql = SPARQLWrapper(STORE)
sparql.setReturnFormat(Wrapper.JSON)
sparql.setQuery(query_string)
sparql.addCustomParameter('infer', infer)
results = sparql.query().convert()
new_results = len(results["results"]["bindings"])
for result in results["results"]["bindings"]:
total_results.add((result['s']['value'], result['o']['value']))
offset = offset + limit
print "Downloaded %d relations" % len(total_results)
return total_results
def sparqlOneEndpoint( endpoint, query, apikey=None ):
out = None
try:
sparql=SPARQLWrapper(endpoint)
if apikey: sparql.addCustomParameter("apikey", apikey)
sparql.setQuery(query)
sparql.setReturnFormat(JSON)
sparql.setTimeout( 30 )
#print "\n", "# " * 7, "\n", query, "\n", "# " * 7, "\n"
out = sparql.query().convert()
except:
print "Could not process formulated query on indicated endpoint."
pass
return out
def findParents(URI):
# Returns a pathList which includes all parents per hop in tuples [(child,parent),(child,parent)]
global iup, pathList, endpoint
list_out = []
iup += 1
if iup == 1:
sparql = SPARQLWrapper(endpoint)
sparql.addCustomParameter("infer", "false")
sparql.setReturnFormat(JSON)
querystring = 'PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#> SELECT DISTINCT ?super WHERE { <' + URI[
iup - 1][0] + '> rdfs:subClassOf ?super . FILTER isURI(?super) }'
sparql.setQuery(querystring)
results = sparql.query().convert()
for x in results["results"]["bindings"]:
list_out.append((URI[iup - 1][0], x["super"]["value"]))
else:
for i in range(len(URI[iup - 1])):
sparql = SPARQLWrapper(endpoint)
sparql.addCustomParameter("infer", "false")
sparql.setReturnFormat(JSON)
querystring = 'PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#> SELECT DISTINCT ?super WHERE { <' + URI[
iup -
1][i][1] + '> rdfs:subClassOf ?super . FILTER isURI(?super) }'
sparql.setQuery(querystring)
results = sparql.query().convert()
for x in results["results"]["bindings"]:
list_out.append((URI[iup - 1][i][1], x["super"]["value"]))
if len(list_out) > 0:
URI.append(list_out)
findParents(URI)
else:
iup = 0
pathList = URI
return pathList
def query(self, queryString):
sparql_service = "http://sparql.bioontology.org/sparql/"
api_key = "7876def4-91ba-4ef2-85d4-8bf5770329dd"
sparql = SPARQLWrapper(sparql_service)
sparql.addCustomParameter("apikey", api_key)
sparql.setQuery(queryString)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
return results['results']['bindings']
def _sparql_query(self, dataset, query, format=JSON):
sparql_endpoint_select = "%s/%s/%s/%s/%s/%s" % (self.endpoint, self.version, self.path, dataset, self.sparql_path, self.sparql_select_path)
sparql_endpoint_update = "%s/%s/%s/%s/%s/%s" % (self.endpoint, self.version, self.path, dataset, self.sparql_path, self.sparql_update_path)
sparql = SPARQLWrapper(sparql_endpoint_select, sparql_endpoint_update)
sparql.addCustomParameter(self.param_key, self.key)
sparql.agent = __agent__
sparql.setMethod(POST)
sparql.setRequestMethod(POSTDIRECTLY)
sparql.setReturnFormat(format)
sparql.setQuery(query)
return sparql.query().convert()
def doQuery(self, endpoint, query, name=''):
sparql = SPARQLWrapper(endpoint)
sparql.setReturnFormat(JSON)
sparql.addCustomParameter('soft-limit', '-1')
sparql.setQuery(self.prefixes + "\n\n" + query)
self.log.info("Starting query {0}...".format(name))
tstart = time()
res = sparql.query().convert()
tend = time()
self.log.debug("... done ({0}us)".format(tend - tstart))
resultsno = len(res["results"]["bindings"])
self.log.info("Query returned {0} results.".format(resultsno))
return res
def _sparql_query(self, dataset, query, format=JSON):
sparql_endpoint_select = "%s/%s/%s/%s/%s/%s" % (
self.endpoint, self.version, self.path, dataset, self.sparql_path,
self.sparql_select_path)
sparql_endpoint_update = "%s/%s/%s/%s/%s/%s" % (
self.endpoint, self.version, self.path, dataset, self.sparql_path,
self.sparql_update_path)
sparql = SPARQLWrapper(sparql_endpoint_select, sparql_endpoint_update)
sparql.addCustomParameter(self.param_key, self.key)
sparql.agent = __agent__
sparql.setMethod(POST)
sparql.setRequestMethod(POSTDIRECTLY)
sparql.setReturnFormat(format)
sparql.setQuery(query)
return sparql.query().convert()
def doQuery(self, endpoint, query, name=''):
sparql = SPARQLWrapper(endpoint)
sparql.setReturnFormat(JSON)
sparql.addCustomParameter('soft-limit', '-1')
sparql.setQuery(self.prefixes+"\n\n"+query)
self.log.info("Starting query {0}...".format(name))
tstart = time()
res = sparql.query().convert()
tend = time()
self.log.debug("... done ({0}us)".format(tend-tstart))
resultsno = len(res["results"]["bindings"])
self.log.info("Query returned {0} results.".format(resultsno))
return res
def sparql():
app.logger.debug('You arrived at ' + url_for('sparql'))
app.logger.debug('I received the following arguments' + str(request.args) )
endpoint = request.args.get('endpoint', None)
query = request.args.get('query', None)
return_format = request.args.get('format','JSON')
app.logger.debug(return_format)
if endpoint and query :
sparql = SPARQLWrapper(endpoint)
sparql.setQuery(query)
if return_format == 'RDF':
sparql.setReturnFormat(RDF)
sparql.addCustomParameter('Accept','application/sparql-results+xml')
else :
sparql.setReturnFormat('JSON')
sparql.addCustomParameter('Accept','application/sparql-results+json')
app.logger.debug('Query:\n{}'.format(query))
app.logger.debug('Querying endpoint {}'.format(endpoint))
try :
response = sparql.query().convert()
app.logger.debug('Results were returned, yay!')
app.logger.debug(response)
if return_format == 'RDF':
app.logger.debug('Serializing to Turtle format')
app.logger.debug(response)
return response.serialize(format='turtle')
else :
app.logger.debug('Directly returning JSON format')
return jsonify(response)
except Exception as e:
app.logger.error('Something went wrong')
app.logger.error(e)
return jsonify({'result': 'Error'})
else :
return jsonify({'result': 'Error'})
def sparql():
app.logger.debug('You arrived at ' + url_for('sparql'))
app.logger.debug('I received the following arguments' + str(request.args))
endpoint = request.args.get('endpoint', None)
query = request.args.get('query', None)
return_format = request.args.get('format', 'JSON')
if endpoint and query:
sparql = SPARQLWrapper(endpoint)
sparql.setQuery(query)
if return_format == 'RDF':
sparql.setReturnFormat(RDF)
else:
sparql.setReturnFormat('JSON')
sparql.addCustomParameter('Accept',
'application/sparql-results+json')
app.logger.debug('Query:\n{}'.format(query))
app.logger.debug('Querying endpoint {}'.format(endpoint))
try:
response = sparql.query().convert()
app.logger.debug('Results were returned, yay!')
app.logger.debug(response)
if return_format == 'RDF':
app.logger.debug('Serializing to Turtle format')
return response.serialize(format='turtle')
else:
app.logger.debug('Directly returning JSON format')
return jsonify(response)
except Exception as e:
app.logger.error('Something went wrong')
app.logger.error(e)
return jsonify({'result': 'Error'})
else:
return jsonify({'result': 'Error'})
def runQuery(q_template,
param_value_dict,
return_vars,
params={},
endpoint="http://sparql.bioontology.org/sparql"):
t = Template(q_template)
q = t.substitute(**param_value_dict)
sparql = SPARQLWrapper(endpoint)
for key in params:
sparql.addCustomParameter(key, params[key])
sparql.setQuery(q)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
output = [[] for v in return_vars]
for result in results["results"]["bindings"]:
i = 0
for v in return_vars:
output[i].append(result[v]["value"])
i += 1
return output
def getDescs():
global desc,sparql,endpoint
sparql = SPARQLWrapper(endpoint)
sparql.addCustomParameter("infer","false")
sparql.setReturnFormat(JSON)
# NCI
sparql.setQuery("""
PREFIX owl: <http://www.w3.org/2002/07/owl#>
PREFIX nci:<http://ncicb.nci.nih.gov/xml/owl/EVS/Thesaurus.owl#>
SELECT ?URI ?def
WHERE {
?URI a owl:Class .
?URI nci:DEFINITION ?def .
}
""")
results = sparql.query().convert()
for x in results["results"]["bindings"]:
### Strip tags
p = re.compile(r'<.*?>')
cleanDesc = p.sub('',x["def"]["value"])
desc.append((cleanDesc,x["URI"]["value"]))
sparql.setQuery("""
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX owl: <http://www.w3.org/2002/07/owl#>
PREFIX nci:<http://ncicb.nci.nih.gov/xml/owl/EVS/Thesaurus.owl#>
SELECT ?URI ?def
WHERE {
?URI a owl:ObjectProperty .
?URI nci:DEFINITION ?def .
}""")
results = sparql.query().convert()
for x in results["results"]["bindings"]:
if 'part_of' in x["def"]["value"].lower():
desc.append([x["def"]["value"],x["URI"]["value"]])
print "Filled lists: desc. With:",str(len(desc)),"entries"
cPickle.dump(desc,open('pickle\\desc.list','w'))
def getDescs():
global desc, sparql, endpoint
sparql = SPARQLWrapper(endpoint)
sparql.addCustomParameter("infer", "false")
sparql.setReturnFormat(JSON)
# NCI
sparql.setQuery("""
PREFIX owl: <http://www.w3.org/2002/07/owl#>
PREFIX nci:<http://ncicb.nci.nih.gov/xml/owl/EVS/Thesaurus.owl#>
SELECT ?URI ?def
WHERE {
?URI a owl:Class .
?URI nci:DEFINITION ?def .
}
""")
results = sparql.query().convert()
for x in results["results"]["bindings"]:
### Strip tags
p = re.compile(r'<.*?>')
cleanDesc = p.sub('', x["def"]["value"])
desc.append((cleanDesc, x["URI"]["value"]))
sparql.setQuery("""
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX owl: <http://www.w3.org/2002/07/owl#>
PREFIX nci:<http://ncicb.nci.nih.gov/xml/owl/EVS/Thesaurus.owl#>
SELECT ?URI ?def
WHERE {
?URI a owl:ObjectProperty .
?URI nci:DEFINITION ?def .
}""")
results = sparql.query().convert()
for x in results["results"]["bindings"]:
if 'part_of' in x["def"]["value"].lower():
desc.append([x["def"]["value"], x["URI"]["value"]])
print "Filled lists: desc. With:", str(len(desc)), "entries"
cPickle.dump(desc, open('pickle\\desc.list', 'w'))
def getLabels():
global label, sparql, endpoint
label = []
print endpoint
sparql = SPARQLWrapper(endpoint)
sparql.addCustomParameter("infer", "false")
sparql.setReturnFormat(JSON)
sparql.setQuery("""
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX owl: <http://www.w3.org/2002/07/owl#>
SELECT ?URI ?label
WHERE {
?URI a owl:Class .
?URI rdfs:label ?label .
}
""")
results = sparql.query().convert()
for x in results["results"]["bindings"]:
label.append([x["label"]["value"], x["URI"]["value"]])
print "LABEL | Filled list: label. With:", str(len(label)), "entries"
# Fetch 'Part_Of' properties
sparql.setQuery("""
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX owl: <http://www.w3.org/2002/07/owl#>
SELECT ?URI ?label
WHERE {
?URI a owl:ObjectProperty .
?URI rdfs:label ?label .
}""")
results = sparql.query().convert()
for x in results["results"]["bindings"]:
if 'part_of' in x["label"]["value"].lower():
label.append([x["label"]["value"], x["URI"]["value"]])
print "LABEL | Filled list: label. With:", str(len(label)), "entries"
cPickle.dump(label, open('pickle\\label.list', 'w'))
def getLabels():
global label,sparql,endpoint
label = []
print endpoint
sparql = SPARQLWrapper(endpoint)
sparql.addCustomParameter("infer","false")
sparql.setReturnFormat(JSON)
sparql.setQuery("""
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX owl: <http://www.w3.org/2002/07/owl#>
SELECT ?URI ?label
WHERE {
?URI a owl:Class .
?URI rdfs:label ?label .
}
""")
results = sparql.query().convert()
for x in results["results"]["bindings"]:
label.append([x["label"]["value"],x["URI"]["value"]])
print "LABEL | Filled list: label. With:",str(len(label)),"entries"
# Fetch 'Part_Of' properties
sparql.setQuery("""
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX owl: <http://www.w3.org/2002/07/owl#>
SELECT ?URI ?label
WHERE {
?URI a owl:ObjectProperty .
?URI rdfs:label ?label .
}""")
results = sparql.query().convert()
for x in results["results"]["bindings"]:
if 'part_of' in x["label"]["value"].lower():
label.append([x["label"]["value"],x["URI"]["value"]])
print "LABEL | Filled list: label. With:",str(len(label)),"entries"
cPickle.dump(label,open('pickle\\label.list','w'))
def findParents(URI):
# Returns a pathList which includes all parents per hop in tuples [(child,parent),(child,parent)]
global iup, pathList, endpoint
list_out = []
iup += 1
if iup == 1:
sparql = SPARQLWrapper(endpoint)
sparql.addCustomParameter("infer", "false")
sparql.setReturnFormat(JSON)
querystring = (
"PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#> SELECT DISTINCT ?super WHERE { <"
+ URI[iup - 1][0]
+ "> rdfs:subClassOf ?super . FILTER isURI(?super) }"
)
sparql.setQuery(querystring)
results = sparql.query().convert()
for x in results["results"]["bindings"]:
list_out.append((URI[iup - 1][0], x["super"]["value"]))
else:
for i in range(len(URI[iup - 1])):
sparql = SPARQLWrapper(endpoint)
sparql.addCustomParameter("infer", "false")
sparql.setReturnFormat(JSON)
querystring = (
"PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#> SELECT DISTINCT ?super WHERE { <"
+ URI[iup - 1][i][1]
+ "> rdfs:subClassOf ?super . FILTER isURI(?super) }"
)
sparql.setQuery(querystring)
results = sparql.query().convert()
for x in results["results"]["bindings"]:
list_out.append((URI[iup - 1][i][1], x["super"]["value"]))
if len(list_out) > 0:
URI.append(list_out)
findParents(URI)
else:
iup = 0
pathList = URI
return pathList
def runQuery(query, return_format, endpoint=SPARQL_ENDPOINT, jsoni=True):
if endpoint and query :
sparql = SPARQLWrapper(endpoint)
sparql.setQuery(query)
if return_format == 'RDF':
sparql.setReturnFormat('RDF')
else :
sparql.setReturnFormat('JSON')
sparql.addCustomParameter('Accept','application/sparql-results+json')
#app.logger.debug('Query:\n{}'.format(query))
#app.logger.debug('Querying endpoint {}'.format(endpoint))
try :
response = sparql.query().convert()
# app.logger.debug('Results were returned, yay!')
# app.logger.debug(response)
if return_format == 'RDF':
# app.logger.debug('Serializing to Turtle format')
return response.serialize(format='turtle')
else :
# app.logger.debug('Directly returning JSON format')
if jsoni == True:
return jsonify(response)
else:
return json.dumps(response)
except Exception as e:
app.logger.error('Something went wrong')
app.logger.error(e)
return jsonify({'result': 'Error'})
else :
return jsonify({'result': 'Error'})
# Get Graph URIs
q = """PREFIX dcterms: <http://purl.org/dc/terms/>
PREFIX metalex: <http://www.metalex.eu/schema/1.0#>
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
PREFIX bwb: <http://doc.metalex.eu/bwb/ontology/>
SELECT DISTINCT ?x WHERE {
?x bwb:bwb-id ?id .
?x a metalex:BibliographicExpression .
}"""
sparql = SPARQLWrapper("http://doc.metalex.eu:8000/sparql/")
sparql.setQuery(q)
sparql.addCustomParameter("soft-limit", "-1")
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
for result in results['results']['bindings']:
uri = result['x']['value']
construct_query = """PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX ml: <http://www.metalex.eu/schema/1.0#>
PREFIX sem: <http://semanticweb.cs.vu.nl/2009/11/sem/>
CONSTRUCT {
?e rdf:type sem:Event .
print("seed_query didn't retrieve any classes.")
entity_graph = Graph()
return entity_graph + extract_bioportal_property_paths(
seeds=seeds,
bioportal=bioportal,
properties=properties,
verbose=verbose,
**extract_params)
if __name__ == '__main__':
#Adapted from https://github.com/ncbo/sparql-code-examples/blob/master/python/sparql1.py
BIOPORTAL_API_KEY = os.environ['BIOPORTAL_API_KEY']
bioportal = SPARQLWrapper('http://sparql.bioontology.org/sparql/')
bioportal.addCustomParameter("apikey", BIOPORTAL_API_KEY)
#We're going to use CHEAR as the base context
CHEAR_LOCATION = "/home/s/projects/TWC/chear-ontology/chear.ttl"
## This seed query will select all ChEBI classes present in CHEAR.
seed_query = """
PREFIX owl: <http://www.w3.org/2002/07/owl#>
SELECT DISTINCT ?c WHERE{
?c a owl:Class .
FILTER(regex(str(?c), "http://purl.obolibrary.org/obo/CHEBI"))
}
"""
graph = Graph()
graph.parse(CHEAR_LOCATION, format='turtle')
seeds = {row[0] for row in graph.query(seed_query)}
prefixes = """
some long prefixes here
"""
AERS = Namespace("http://aers.data2semantics.org/resource/")
DBPEDIA = Namespace("http://dbpedia.org/resource/")
SIDER = Namespace("http://www4.wiwiss.fu-berlin.de/sider/resource/sider/")
OWL = Namespace("http://www.w3.org/2002/07/owl#")
SKOS = Namespace("http://www.w3.org/2004/02/skos/core#")
if __name__ == "__main__":
wrapper = SPARQLWrapper(AERS_SPARQL_ENDPOINT)
wrapper.setReturnFormat(JSON)
wrapper.addCustomParameter("soft-limit", "-1")
q = "SELECT DISTINCT ?x1 ?x2 WHERE { ?x1 skos:exactMatch ?y . ?x2 skos:exactMatch ?y .} "
cg = ConjunctiveGraph()
print "Querying for " + q
wrapper.setQuery(prefixes + q)
raw = wrapper.query()
print "Results are in! Now converting from JSON..."
results = raw.convert()
print "Done converting ..."
resultsno = len(results["results"]["bindings"])
print "Query returned {0} results.".format(resultsno)
for res in results["results"]["bindings"]:
http://sparql-wrapper.sourceforge.net/
"""
from SPARQLWrapper import SPARQLWrapper, JSON, XML, N3, RDF
import pdb
if __name__ == "__main__":
sparql_service = "http://sparql.bioontology.org/sparql/"
#To get your API key register at http://bioportal.bioontology.org/accounts/new
api_key = "YOUR API KEY"
#Some sample query.
query_string = """
PREFIX omv: <http://omv.ontoware.org/2005/05/ontology#>
SELECT ?ont ?name ?acr
WHERE { ?ont a omv:Ontology;
omv:acronym ?acr;
omv:name ?name .
}
"""
sparql = SPARQLWrapper(sparql_service)
sparql.addCustomParameter("apikey", api_key)
sparql.setQuery(query_string)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
for result in results["results"]["bindings"]:
print result["ont"]["value"], result["name"]["value"], result["acr"][
"value"]
import re
from urllib import unquote_plus
import networkx as nx
from networkx.readwrite import json_graph
import json
from rdflib import Graph, Namespace, RDF, RDFS, Literal, URIRef
from rdflib.serializer import Serializer
import rdfextras
from app import app
endpoint = app.config['SPARQL_ENDPOINT']
sparql = SPARQLWrapper(endpoint)
sparql.setReturnFormat(JSON)
sparql.addCustomParameter('reasoning','SL')
concept_type_color_dict = {'popg': '#9edae5', 'inpo': '#ffbb78', 'elii': '#dbdb8d', 'idcn': '#9edae5', 'neop': '#2ca02c', 'vita': '#9467bd', 'inpr': '#c5b0d5', 'phsu': '#c5b0d5', 'blor': '#98df8a', 'hops': '#c7c7c7', 'menp': '#f7b6d2', 'phsf': '#d62728', 'ftcn': '#e377c2', 'anim': '#ff9896', 'food': '#bcbd22', 'grpa': '#ffbb78', 'geoa': '#2ca02c', 'hcpp': '#98df8a', 'lbtr': '#c7c7c7', 'ocdi': '#17becf', 'tisu': '#17becf', 'orch': '#7f7f7f', 'tmco': '#dbdb8d', 'clas': '#bcbd22', 'lipd': '#c49c94', 'dsyn': '#f7b6d2', 'horm': '#aec7e8', 'bact': '#2ca02c', 'grup': '#e377c2', 'bacs': '#ffbb78', 'enty': '#c5b0d5', 'resa': '#98df8a', 'medd': '#9467bd', 'cell': '#bcbd22', 'fndg': '#ff7f0e', 'sbst': '#ff9896', 'prog': '#ff9896', 'celf': '#aec7e8', 'chvf': '#1f77b4', 'diap': '#aec7e8', 'celc': '#8c564b', 'hcro': '#ff7f0e', 'inbe': '#9467bd', 'clna': '#ffbb78', 'acab': '#d62728', 'bodm': '#9467bd', 'patf': '#e377c2', 'carb': '#c7c7c7', 'bpoc': '#d62728', 'dora': '#8c564b', 'moft': '#7f7f7f', 'plnt': '#7f7f7f', 'ortf': '#f7b6d2', 'bmod': '#9edae5', 'sosy': '#dbdb8d', 'enzy': '#d62728', 'qnco': '#1f77b4', 'imft': '#7f7f7f', 'antb': '#1f77b4', 'bdsy': '#c5b0d5', 'nnon': '#9467bd', 'socb': '#c49c94', 'ocac': '#8c564b', 'bdsu': '#8c564b', 'rcpt': '#ff9896', 'nsba': '#c5b0d5', 'mnob': '#e377c2', 'orga': '#1f77b4', 'orgf': '#c7c7c7', 'lbpr': '#d62728', 'orgt': '#aec7e8', 'gngm': '#f7b6d2', 'virs': '#17becf', 'fngs': '#98df8a', 'aapp': '#17becf', 'opco': '#c49c94', 'irda': '#98df8a', 'famg': '#2ca02c', 'acty': '#ff7f0e', 'inch': '#bcbd22', 'cnce': '#9edae5', 'topp': '#ffbb78', 'spco': '#2ca02c', 'lang': '#dbdb8d', 'podg': '#aec7e8', 'mobd': '#ff9896', 'qlco': '#c49c94', 'npop': '#ff7f0e', 'hlca': '#1f77b4', 'phpr': '#ff7f0e', 'strd': '#8c564b'}
def uri_to_label(uri):
return unquote_plus(uri.encode('utf-8').replace('http://eligibility.data2semantics.org/resource/','')).replace('_',' ').lstrip('-').lstrip(' ').title()
def get_trials():
q = render_template('trials.q')
sparql.setQuery(q)
results = sparql.query().convert()
from SPARQLWrapper import SPARQLWrapper, JSON
sparql = SPARQLWrapper('http://sparql.bioontology.org/sparql/')
api_key = '5dd5cf8a-bdc9-4d46-9c3d-10aadff89444'
sparql.addCustomParameter('apikey', api_key)
q = '''
PREFIX umls: <http://bioportal.bioontology.org/ontologies/umls/>
PREFIX skos: <http://www.w3.org/2004/02/skos/core#>
PREFIX ndfrt: <http://purl.bioontology.org/ontology/NDFRT/>
SELECT *
WHERE {
?s ndfrt:NDFRT_KIND ?o;
skos:prefLabel ?label;
umls:cui ?cui;
ndfrt:SEVERITY ?severity. FILTER (regex(str(?o), "interaction", "i"))
?s ndfrt:has_participant ?targetDrug.
}
'''
sparql.setQuery(q)
sparql.setReturnFormat(JSON)
resultset = sparql.query().convert()
cache = [None, None]
for i in range(0, len(resultset['results']['bindings'])):
uri = resultset['results']['bindings'][i]['s']['value']
if uri == cache[0]:
drug1 = cache[1].rpartition('/')[2]
drug2 = resultset['results']['bindings'][i]['targetDrug'][
# Get Graph URIs
q = """PREFIX dcterms: <http://purl.org/dc/terms/>
PREFIX metalex: <http://www.metalex.eu/schema/1.0#>
PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
PREFIX bwb: <http://doc.metalex.eu/bwb/ontology/>
SELECT DISTINCT ?x WHERE {
?x bwb:bwb-id ?id .
?x a metalex:BibliographicExpression .
}"""
sparql = SPARQLWrapper("http://doc.metalex.eu:8000/sparql/")
sparql.setQuery(q)
sparql.addCustomParameter("soft-limit", "-1")
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
for result in results['results']['bindings'] :
uri = result['x']['value']
construct_query = """PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX ml: <http://www.metalex.eu/schema/1.0#>
PREFIX sem: <http://semanticweb.cs.vu.nl/2009/11/sem/>
CONSTRUCT {
?e rdf:type sem:Event .
http://sparql-wrapper.sourceforge.net/
"""
from SPARQLWrapper import SPARQLWrapper, JSON, XML, N3, RDF
import pdb
if __name__ == "__main__":
# Eventually alphasparql will be moved to http://sparql.bioontology.org/sparql/
sparql_service = "http://sparql.bioontology.org/sparql/"
# To get your API key register at http://bioportal.bioontology.org/accounts/new
api_key = "YOUR API KEY"
# Some sample query.
query_string = """
PREFIX omv: <http://omv.ontoware.org/2005/05/ontology#>
SELECT ?ont ?name ?acr
WHERE { ?ont a omv:Ontology;
omv:acronym ?acr;
omv:name ?name .
}
"""
sparql = SPARQLWrapper(sparql_service)
sparql.addCustomParameter("apikey", api_key)
sparql.setQuery(query_string)
sparql.setReturnFormat(JSON)
results = sparql.query().convert()
for result in results["results"]["bindings"]:
print result["ont"]["value"], result["name"]["value"], result["acr"]["value"]
logHandler.setFormatter(logFormatter)
log.addHandler(logHandler)
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument("endpoint", nargs='?', help="The URL of the sparql endpoint (without /sparql suffix)", default='http://eculture2.cs.vu.nl:5020')
parser.add_argument("--empty", help="Empty the 4Store model completely", action="store_true")
args = parser.parse_args()
SPARQL_BASE = args.endpoint
log.info('Using {} as 4Store location.'.format(SPARQL_BASE))
sw = SPARQLWrapper('{}/sparql/'.format(SPARQL_BASE))
sw.setReturnFormat(JSON)
sw.addCustomParameter('soft-limit','-1')
if args.empty :
yn = raw_input("Are you sure you want to delete all graphs from {} (y/n): ".format(SPARQL_BASE))
if yn == "y" :
sw.setReturnFormat(JSON)
sw.addCustomParameter('soft-limit','-1')
q = """SELECT DISTINCT ?g WHERE { GRAPH ?g { ?s ?p ?o .}} """
sw.setQuery(q)
results = sw.query().convert()
for result in results["results"]["bindings"] :
def extract_from_contexts(seed_iri,
properties,
property_f,
extract_params,
dest_dir,
verbose=False,
error=None):
'''
Loads in our seed graph from the provided IRI.
Then iterates through our provided Java property
file, which contains prefixes and IRIs for
context ontologies. Entities with the associated
prefix are pulled from the seed ontology via the seed query.
These seed entities are then used as roots for the property
crawl paths in the associated context ontology.
'''
#Read in the graph we'll pull seeds from
seed_graph = Graph().parse(seed_iri)
if verbose:
print("Loaded seed graph.")
#Connect to BioPortal
BIOPORTAL_API_KEY = os.environ['BIOPORTAL_API_KEY']
bioportal = SPARQLWrapper('http://sparql.bioontology.org/sparql/')
bioportal.addCustomParameter("apikey", BIOPORTAL_API_KEY)
print("Connected to BioPortal.")
#Create template for retrieving seed classes based on prefixes
SEED_QUERY_TEMPLATE = """
PREFIX owl: <http://www.w3.org/2002/07/owl#>
SELECT DISTINCT ?c WHERE{
?c a owl:Class .
FILTER(regex(str(?c), "%s"))
}
"""
#Read in properties file
with open(property_f, 'r') as fp:
javaprops = javaproperties.load(fp)
if verbose:
print("Read properties file.")
#Iterate through rows of properties file
for k in javaprops.keys():
if verbose:
print("==========================================")
print("Reading graph: ", str(k))
#Pull the ontology IRI and associated prefix
row = javaprops[k].split(',')
prefix = row[0]
iri = row[2]
#Check whether we have an IRI for the row
if iri == '':
if verbose:
print("No IRI provided.")
continue
if iri == seed_iri:
if verbose:
print("Context graph is same as seed graph. Skipping.")
continue
#Read in context graph from IRI, use as context
context = Graph()
FORMATS = ['xml', 'n3', 'nt', 'trix', 'turtle', 'rdfa']
read_success = False
for form in FORMATS:
try:
#If we successfully read our ontology, recurse
context = Graph().parse(iri, format=form)
read_success = True
if verbose:
print("Read as ", form, ".")
break
except Exception as e:
pass
if not read_success:
#Last-ditch effort: try to guess the file extension
try:
if verbose:
print(
"Exhausted format list. Attempting to guess format...")
context = Graph().parse(iri, format=guess_format(iri))
if verbose:
print("Read as ", guess_format(iri), ".")
break
except Exception as e:
pass
#Error handling, quiet or fast failing
if error is None:
raise Exception("Exhausted format list. Failing quickly.")
if error == 'ignore':
print("Exhausted format list. Quietly ignoring failure.")
continue
#Expand property paths from context
gout = retrieve_crawl_paths_from_context(
seed_graph=seed_graph,
context=context,
properties=properties,
seed_query=SEED_QUERY_TEMPLATE % (prefix, ),
expand_ontologies=True,
import_error=error,
verbose=verbose,
inplace=False,
extract_params=extract_params)
#Get the BioPortal extract as well
bio_seeds = {
row[0]
for row in seed_graph.query(SEED_QUERY_TEMPLATE % (prefix, ))
}
bio_gout = bioportal_retrieve_crawl_paths(
properties=properties,
bioportal=bioportal,
seeds=bio_seeds,
verbose=verbose,
extract_params=extract_params)
#Write out
gout.serialize(path.join(dest_dir, k + '.ttl'), format='turtle')
bio_gout.serialize(path.join(path.join(dest_dir, 'bioportal/'),
k + '_bioportal.ttl'),
format='turtle')
print("Wrote out extracts for " + k + ".")
del gout
PREFIX calbc-group: <http://linkedlifedata.com/resource/calbc/group/>
PREFIX drugbank: <http://www4.wiwiss.fu-berlin.de/drugbank/resource/drugbank/>
PREFIX ctcae: <http://ncicb.nci.nih.gov/xml/owl/EVS/ctcae.owl#>
"""
AERS = Namespace("http://aers.data2semantics.org/resource/")
DBPEDIA = Namespace("http://dbpedia.org/resource/")
SIDER = Namespace("http://www4.wiwiss.fu-berlin.de/sider/resource/sider/")
OWL = Namespace("http://www.w3.org/2002/07/owl#")
SKOS = Namespace("http://www.w3.org/2004/02/skos/core#")
if __name__ == '__main__':
wrapper = SPARQLWrapper(AERS_SPARQL_ENDPOINT)
wrapper.setReturnFormat(JSON)
wrapper.addCustomParameter('soft-limit', '-1')
q = "SELECT ?x ?y WHERE { ?x skos:exactMatch ?y . } "
cg = ConjunctiveGraph()
print "Querying for " + q
wrapper.setQuery(prefixes + q)
results = wrapper.query().convert()
for res in results["results"]["bindings"]:
x = res["x"]["value"]
y = res["y"]["value"]
print x, y
cg.add((URIRef(y), SKOS["exactMatch"], URIRef(x)))
prefixes = """
some long prefixes
"""
AERS = Namespace("http://aers.data2semantics.org/resource/")
DBPEDIA = Namespace("http://dbpedia.org/resource/")
SIDER = Namespace("http://www4.wiwiss.fu-berlin.de/sider/resource/sider/")
OWL = Namespace("http://www.w3.org/2002/07/owl#")
SKOS = Namespace("http://www.w3.org/2004/02/skos/core#")
if __name__ == '__main__':
wrapper = SPARQLWrapper(AERS_SPARQL_ENDPOINT)
wrapper.setReturnFormat(JSON)
wrapper.addCustomParameter('soft-limit','-1')
q = "SELECT ?x ?y WHERE { ?x skos:exactMatch ?y . } "
cg = ConjunctiveGraph()
print "Querying for "+ q
wrapper.setQuery(prefixes+q)
results = wrapper.query().convert()
for res in results["results"]["bindings"] :
x = res["x"]["value"]
y = res["y"]["value"]
print x, y
cg.add(URIRef(y),SKOS["exactMatch"],URIRef(x))
parser = argparse.ArgumentParser()
parser.add_argument(
"endpoint",
nargs='?',
help="The URL of the sparql endpoint (without /sparql suffix)",
default='http://eculture2.cs.vu.nl:5020')
parser.add_argument("--empty",
help="Empty the 4Store model completely",
action="store_true")
args = parser.parse_args()
SPARQL_BASE = args.endpoint
log.info('Using {} as 4Store location.'.format(SPARQL_BASE))
sw = SPARQLWrapper('{}/sparql/'.format(SPARQL_BASE))
sw.setReturnFormat(JSON)
sw.addCustomParameter('soft-limit', '-1')
if args.empty:
yn = raw_input(
"Are you sure you want to delete all graphs from {} (y/n): ".
format(SPARQL_BASE))
if yn == "y":
sw.setReturnFormat(JSON)
sw.addCustomParameter('soft-limit', '-1')
q = """SELECT DISTINCT ?g WHERE {
GRAPH ?g {
?s ?p ?o .
}
} """
