def test_assertion_model(self):
"""
Functional test for _add_study_provenance()
"""
impc = IMPC('rdf_graph', True)
impc.graph = RDFGraph(True)
self.assertTrue(len(list(impc.graph)) == 0)
impc._add_assertion_provenance(self.assoc_curie, self.evidence_curie)
triples = """
MONARCH:test_association SEPIO:0000015 <https://monarchinitiative.org/.well-known/genid/bf92df374a884963e805> .
<https://monarchinitiative.org/.well-known/genid/bf92df374a884963e805> a SEPIO:0000001 ;
SEPIO:0000018 <https://www.mousephenotype.org/> ;
SEPIO:0000111 <https://monarchinitiative.org/.well-known/genid/evidence> .
<https://www.mousephenotype.org/> a foaf:organization ;
rdfs:label "International Mouse Phenotyping Consortium" .
"""
# dbg
logger.info(
"Assertion graph:\n %s\n", impc.graph.serialize(
format="turtle").decode("utf-8")
)
self.assertTrue(self.test_util.test_graph_equality(triples, impc.graph))
def test_assertion_model(self):
"""
Functional test for _add_study_provenance()
"""
impc = IMPC('rdf_graph', True)
impc.graph = RDFGraph(True)
self.assertTrue(len(list(impc.graph)) == 0)
impc._add_assertion_provenance(self.assoc_curie, self.evidence_curie)
triples = """
MONARCH:test_association SEPIO:0000015 <https://monarchinitiative.org/.well-known/genid/bf92df374a884963e805> .
<https://monarchinitiative.org/.well-known/genid/bf92df374a884963e805> a SEPIO:0000001 ;
SEPIO:0000018 <https://www.mousephenotype.org/> ;
SEPIO:0000111 <https://monarchinitiative.org/.well-known/genid/evidence> .
<https://www.mousephenotype.org/> a foaf:organization ;
rdfs:label "International Mouse Phenotyping Consortium" .
"""
# dbg
LOG.info(
"Assertion graph:\n %s\n", impc.graph.serialize(
format="turtle").decode("utf-8")
)
self.assertTrue(self.test_util.test_graph_equality(triples, impc.graph))
def test_assertion_model(self):
"""
Functional test for _add_study_provenance()
"""
impc = IMPC('rdf_graph', True)
impc_map = impc.open_and_parse_yaml(impc.map_files['impc_map'])
impc._add_assertion_provenance(self.assoc_curie, self.evidence_curie,
impc_map)
sparql_query = """
SELECT *
WHERE {
MONARCH:test_association OBO:SEPIO_0000015 ?assertion.
?assertion a OBO:SEPIO_0000001 ;
OBO:SEPIO_0000018 <http://www.mousephenotype.org/> ;
OBO:SEPIO_0000111 <https://monarchinitiative.org/.well-known/genid/evidence> .
<http://www.mousephenotype.org/> a foaf:organization ;
rdfs:label "International Mouse Phenotyping Consortium" .
}
"""
sparql_output = impc.graph.query(sparql_query)
# Test that query passes and returns one row
self.assertEqual(len(list(sparql_output)), 1)
def test_evidence_model(self):
"""
Functional test for _add_evidence()
"""
impc = IMPC('rdf_graph', True)
impc.graph = RDFGraph(True) # Reset graph
# Test graph is empty
self.assertTrue(len(list(impc.graph)) == 0)
(p_value, percentage_change, effect_size) = self.test_set_1[23:26]
impc._add_evidence(
self.assoc_curie, self.eco_id, p_value, percentage_change, effect_size,
self.study_curie)
triples = """
:MONARCH_test_association SEPIO:0000007 <https://monarchinitiative.org/.well-known/genid/b97a98087df7a99d8a38> .
<https://monarchinitiative.org/.well-known/genid/b97a98087df7a99d8a38> a ECO:0000015 ;
SEPIO:0000084 <https://monarchinitiative.org/.well-known/genid/b41ad2bfd375c9de8888>,
<https://monarchinitiative.org/.well-known/genid/b216606de82749b03956> ;
SEPIO:0000085 <https://monarchinitiative.org/.well-known/genid/study> .
<https://monarchinitiative.org/.well-known/genid/b216606de82749b03956> a OBI:0000175 ;
RO:0002353 <https://monarchinitiative.org/.well-known/genid/study> ;
STATO:0000129 1.637023e-10 .
<https://monarchinitiative.org/.well-known/genid/b41ad2bfd375c9de8888> a STATO:0000085 ;
RO:0002353 <https://monarchinitiative.org/.well-known/genid/study> ;
STATO:0000129 "8.885439E-007" .
"""
self.assertTrue(self.test_util.test_graph_equality(
triples, impc.graph))
def test_evidence_model(self):
"""
Functional test for _add_evidence()
"""
impc = IMPC('rdf_graph', False)
impc_map = impc.open_and_parse_yaml(impc.map_files['impc_map'])
(p_value, percentage_change, effect_size) = self.test_set_1[23:26]
impc._add_evidence(self.assoc_curie, self.eco_id, impc_map, p_value,
percentage_change, effect_size, self.study_curie)
sparql_query = """
SELECT ?assoc
WHERE {
?assoc OBO:SEPIO_0000007 ?evidenceline .
?evidenceline a OBO:ECO_0000015 ;
OBO:SEPIO_0000084 ?measure1 ;
OBO:SEPIO_0000084 ?measure2 ;
OBO:SEPIO_0000085 _:study .
?measure1 a OBO:OBI_0000175 ;
OBO:RO_0002353 _:study ;
OBO:STATO_0000129 1.637023e-10 .
?measure2 a OBO:STATO_0000085 ;
OBO:RO_0002353 _:study ;
OBO:STATO_0000129 "8.885439E-007" .
}
"""
sparql_output = impc.graph.query(sparql_query)
expected_results = [(self.assoc_iri,)]
self.assertEqual(list(sparql_output), expected_results)
def test_assertion_model(self):
"""
Functional test for _add_study_provenance()
"""
impc = IMPC('rdf_graph', True)
impc_map = impc.open_and_parse_yaml(impc.map_files['impc_map'])
impc._add_assertion_provenance(self.assoc_curie,
self.evidence_curie, impc_map)
sparql_query = """
SELECT *
WHERE {
MONARCH:test_association OBO:SEPIO_0000015 ?assertion.
?assertion a OBO:SEPIO_0000001 ;
OBO:SEPIO_0000018 <http://www.mousephenotype.org/> ;
OBO:SEPIO_0000111 <https://monarchinitiative.org/.well-known/genid/evidence> .
<http://www.mousephenotype.org/> a foaf:organization ;
rdfs:label "International Mouse Phenotyping Consortium" .
}
"""
sparql_output = impc.graph.query(sparql_query)
# Test that query passes and returns one row
self.assertEqual(len(list(sparql_output)), 1)
def test_evidence_model(self):
"""
Functional test for _add_evidence()
"""
impc = IMPC('rdf_graph', True)
impc.graph = RDFGraph(True) # Reset graph
# Test graph is empty
self.assertTrue(len(list(impc.graph)) == 0)
(p_value, percentage_change, effect_size) = self.test_set_1[23:26]
impc._add_evidence(
self.assoc_curie, self.eco_id, p_value, percentage_change, effect_size,
self.study_curie)
triples = """
:MONARCH_test_association SEPIO:0000007 <https://monarchinitiative.org/.well-known/genid/b97a98087df7a99d8a38> .
<https://monarchinitiative.org/.well-known/genid/b97a98087df7a99d8a38> a ECO:0000015 ;
SEPIO:0000084 <https://monarchinitiative.org/.well-known/genid/b41ad2bfd375c9de8888>,
<https://monarchinitiative.org/.well-known/genid/b216606de82749b03956> ;
SEPIO:0000085 <https://monarchinitiative.org/.well-known/genid/study> .
<https://monarchinitiative.org/.well-known/genid/b216606de82749b03956> a OBI:0000175 ;
RO:0002353 <https://monarchinitiative.org/.well-known/genid/study> ;
STATO:0000129 1.637023e-10 .
<https://monarchinitiative.org/.well-known/genid/b41ad2bfd375c9de8888> a STATO:0000085 ;
RO:0002353 <https://monarchinitiative.org/.well-known/genid/study> ;
STATO:0000129 "8.885439E-007" .
"""
self.assertTrue(self.test_util.test_graph_equality(
triples, impc.graph))
def test_evidence_model(self):
"""
Functional test for _add_evidence()
"""
impc = IMPC('rdf_graph', True)
impc.graph = RDFGraph(True) # Reset graph
# Test graph is empty
self.assertTrue(len(list(impc.graph)) == 0)
impc_map = impc.open_and_parse_yaml(impc.map_files['impc_map'])
(p_value, percentage_change, effect_size) = self.test_set_1[23:26]
impc._add_evidence(self.assoc_curie, self.eco_id, impc_map, p_value,
percentage_change, effect_size, self.study_curie)
triples = """
:MONARCH_test_association SEPIO:0000007 <https://monarchinitiative.org/.well-known/genid/b097a98087df7a99> .
<https://monarchinitiative.org/.well-known/genid/b097a98087df7a99> a ECO:0000015 ;
SEPIO:0000084 <https://monarchinitiative.org/.well-known/genid/b89ee584330837c9>,
<https://monarchinitiative.org/.well-known/genid/bc0eeccdea27a1d8> ;
SEPIO:0000085 <https://monarchinitiative.org/.well-known/genid/study> .
<https://monarchinitiative.org/.well-known/genid/bc0eeccdea27a1d8> a OBI:0000175 ;
RO:0002353 <https://monarchinitiative.org/.well-known/genid/study> ;
STATO:0000129 1.637023e-10 .
<https://monarchinitiative.org/.well-known/genid/b89ee584330837c9> a STATO:0000085 ;
RO:0002353 <https://monarchinitiative.org/.well-known/genid/study> ;
STATO:0000129 "8.885439E-007" .
"""
self.assertTrue(self.test_util.test_graph_equality(
triples, impc.graph))
def test_assertion_model(self):
"""
Functional test for _add_study_provenance()
"""
impc = IMPC('rdf_graph', True)
impc.graph = RDFGraph(True)
self.assertTrue(len(list(impc.graph)) == 0)
impc_map = impc.open_and_parse_yaml(impc.map_files['impc_map'])
impc._add_assertion_provenance(
self.assoc_curie, self.evidence_curie, impc_map)
triples = """
MONARCH:test_association SEPIO:0000015 <https://monarchinitiative.org/.well-known/genid/bcb2c00a5c2f9c43> .
<https://monarchinitiative.org/.well-known/genid/bcb2c00a5c2f9c43> a SEPIO:0000001 ;
SEPIO:0000018 <http://www.mousephenotype.org/> ;
SEPIO:0000111 <https://monarchinitiative.org/.well-known/genid/evidence> .
<http://www.mousephenotype.org/> a foaf:organization ;
rdfs:label "International Mouse Phenotyping Consortium" .
"""
# dbg
logger.debug("Reference graph: %s",
impc.graph.serialize(format="turtle")
.decode("utf-8")
)
self.assertTrue(self.test_util.test_graph_equality(
triples, impc.graph))
def test_evidence_model(self):
"""
Functional test for _add_evidence()
"""
impc = IMPC('rdf_graph', False)
impc_map = impc.open_and_parse_yaml(impc.map_files['impc_map'])
(p_value, percentage_change, effect_size) = self.test_set_1[23:26]
impc._add_evidence(self.assoc_curie, self.eco_id, impc_map, p_value,
percentage_change, effect_size, self.study_curie)
sparql_query = """
SELECT ?assoc
WHERE {
?assoc OBO:SEPIO_0000007 ?evidenceline .
?evidenceline a OBO:ECO_0000015 ;
OBO:SEPIO_0000084 ?measure1 ;
OBO:SEPIO_0000084 ?measure2 ;
OBO:SEPIO_0000085 _:study .
?measure1 a OBO:OBI_0000175 ;
OBO:RO_0002353 _:study ;
OBO:STATO_0000129 1.637023e-10 .
?measure2 a OBO:STATO_0000085 ;
OBO:RO_0002353 _:study ;
OBO:STATO_0000129 "8.885439E-007" .
}
"""
sparql_output = impc.graph.query(sparql_query)
expected_results = [(self.assoc_iri, )]
self.assertEqual(list(sparql_output), expected_results)
def test_provenance_model(self):
"""
Functional test for _add_study_provenance()
"""
impc = IMPC('rdf_graph', True)
impc.graph = RDFGraph(True)
self.assertTrue(len(list(impc.graph)) == 0)
(phenotyping_center, colony) = self.test_set_1[2:4]
(project_fullname, pipeline_name, pipeline_stable_id,
procedure_stable_id, procedure_name, parameter_stable_id,
parameter_name) = self.test_set_1[12:19]
(statistical_method, resource_name) = self.test_set_1[26:28]
impc._add_study_provenance(phenotyping_center, colony,
project_fullname, pipeline_name,
pipeline_stable_id, procedure_stable_id,
procedure_name, parameter_stable_id,
parameter_name, statistical_method,
resource_name)
# dbg
LOG.info("Provenance graph as turtle:\n%s\n",
impc.graph.serialize(format="turtle").decode("utf-8"))
triples = """
<https://monarchinitiative.org/.well-known/genid/bdd05a8ca155ddaf415e> a OBI:0000471 ;
BFO:0000051 OBO:STATO_0000076,
<https://www.mousephenotype.org/impress/protocol/175/15> ;
BFO:0000050 IMPRESS-procedure:15 ,
<http://www.sanger.ac.uk/science/data/mouse-genomes-project> ;
SEPIO:0000114 <https://www.mousephenotype.org/impress/parameterontologies/1867/91> ;
SEPIO:0000017 <http://www.sanger.ac.uk/> .
<https://monarchinitiative.org/.well-known/genid/b0b26361b8687b5ad9ef> a owl:NamedIndividual ;
rdfs:label "MEFW" .
<http://www.sanger.ac.uk/> a foaf:organization ;
rdfs:label "WTSI" .
<http://www.sanger.ac.uk/science/data/mouse-genomes-project> a VIVO:Project ;
rdfs:label "Wellcome Trust Sanger Institute Mouse Genetics Project" .
<https://www.mousephenotype.org/impress/parameterontologies/1867/91> a owl:NamedIndividual ;
rdfs:label "Number of ribs right (X-ray)" .
IMPRESS-procedure:15 a owl:NamedIndividual ;
rdfs:label "MGP Select Pipeline" .
<https://www.mousephenotype.org/impress/protocol/175/15> a owl:NamedIndividual ;
rdfs:label "X-ray" .
"""
# dbg
LOG.debug("Reference graph: %s",
impc.graph.serialize(format="turtle").decode("utf-8"))
self.assertTrue(self.test_util.test_graph_equality(
triples, impc.graph))
class IMPCTestCase(SourceTestCase):
def setUp(self):
self.source = IMPC('rdf_graph', True) # Skolem Yes
self.source.settestonly(True)
self._setDirToSource()
return
def tearDown(self):
self.source = None
return
class IMPCTestCase(SourceTestCase):
def setUp(self):
self.source = IMPC('rdf_graph', True)
self.source.settestonly(True)
self._setDirToSource()
return
def tearDown(self):
self.source = None
return
def test_random_data_set(self):
"""
Download dataset using fetch(), then take a row of data and
run through evidence and provenance functions to test the output
Line of data is hardcoded, but theoretically should work on any line
"""
line_to_test = 1129
count = 0
# init impc (make this a function?)
impc = IMPC('rdf_graph', True)
impress_map = json.loads(
impc.fetch_from_url(
impc.map_files['impress_map']).read().decode('utf-8'))
impc_map = impc.open_and_parse_yaml(impc.map_files['impc_map'])
# fetch file
impc.fetch(True)
file_path = '/'.join((impc.rawdir, impc.files['all']['file']))
with gzip.open(file_path, 'rt') as csvfile:
filereader = csv.reader(csvfile, delimiter=',', quotechar='\"')
for row in filereader:
count += 1
if count == line_to_test:
test_set = row
self.test_set_1 = row
break
# Some DRY violation with the above tests
(phenotyping_center, colony) = row[2:4]
(project_fullname, pipeline_name, pipeline_stable_id,
procedure_stable_id, procedure_name, parameter_stable_id,
parameter_name) = row[12:19]
(statistical_method, resource_name) = row[26:28]
(p_value, percentage_change, effect_size) = self.test_set_1[23:26]
impc._add_evidence(self.assoc_curie, self.eco_id, impc_map, p_value,
percentage_change, effect_size, self.study_curie)
impc._add_study_provenance(impc_map, impress_map, phenotyping_center,
colony, project_fullname, pipeline_name,
pipeline_stable_id, procedure_stable_id,
procedure_name, parameter_stable_id,
parameter_name, statistical_method,
resource_name)
# Note that this doesn't test much since we're dealing with
# multiple part_of and has_part links to individuals
# which results in ambiguity = hard to test
sparql_query = """
SELECT *
WHERE {
?assoc OBO:SEPIO_0000007 ?evidenceline .
?evidenceline a OBO:ECO_0000015 ;
OBO:SEPIO_0000085 <https://monarchinitiative.org/.well-known/genid/study> .
?study a OBO:OBI_0000471 ;
OBO:SEPIO_0000114 ?param ;
OBO:SEPIO_0000017 ?agent .
}
"""
sparql_output = impc.graph.query(sparql_query)
# Test that query passes and returns one row
self.assertEqual(len(list(sparql_output)), 1)
def test_provenance_model(self):
"""
Functional test for _add_study_provenance()
"""
impc = IMPC('rdf_graph', True)
impc.graph = RDFGraph(True)
self.assertTrue(len(list(impc.graph)) == 0)
(phenotyping_center,
colony) = self.test_set_1[2:4]
(project_name,
project_fullname,
pipeline_name,
pipeline_stable_id,
procedure_stable_id,
procedure_name,
parameter_stable_id,
parameter_name) = self.test_set_1[11:19]
(statistical_method, resource_name) = self.test_set_1[26:28]
impc._add_study_provenance(
phenotyping_center, colony,
project_name,
pipeline_name, pipeline_stable_id,
procedure_stable_id, procedure_name,
parameter_stable_id, parameter_name,
statistical_method, resource_name)
# dbg
LOG.info(
"Provenance graph as turtle:\n%s\n",
impc.graph.serialize(format="turtle").decode("utf-8")
)
triples = """
<https://monarchinitiative.org/.well-known/genid/b0b26361b8687b5ad9ef> a owl:NamedIndividual ;
rdfs:label "MEFW" .
<https://monarchinitiative.org/.well-known/genid/b6f14f763c8d0629360e> a OBI:0000471 ;
BFO:0000050 <http://www.sanger.ac.uk/science/data/mouse-genomes-project>,
IMPC-pipe:MGP_001 ;
BFO:0000051 STATO:0000076,
IMPC-proc:MGP_XRY_001 ;
SEPIO:0000017 <http://www.sanger.ac.uk/> ;
SEPIO:0000114 <https://www.mousephenotype.org/impress/OntologyInfo?action=list&procID=MGP_XRY_001#IMPC_XRY_008_001> .
<http://www.sanger.ac.uk/> a foaf:organization ;
rdfs:label "WTSI" .
<http://www.sanger.ac.uk/science/data/mouse-genomes-project> a VIVO:Project ;
rdfs:label "MGP" .
<https://www.mousephenotype.org/impress/OntologyInfo?action=list&procID=MGP_XRY_001#IMPC_XRY_008_001> a owl:NamedIndividual ;
rdfs:label "Number of ribs right (X-ray)" .
IMPC-pipe:MGP_001 a owl:NamedIndividual ;
rdfs:label "MGP Select Pipeline" .
IMPC-proc:MGP_XRY_001 a owl:NamedIndividual ;
rdfs:label "X-ray" .
"""
# dbg
LOG.info(
"Reference graph: %s",
impc.graph.serialize(format="turtle").decode("utf-8")
)
self.assertTrue(
self.test_util.test_graph_equality(triples, impc.graph))
def test_provenance_model(self):
"""
Functional test for _add_study_provenance()
"""
impc = IMPC('rdf_graph', True)
impc.graph = RDFGraph(True)
self.assertTrue(len(list(impc.graph)) == 0)
(phenotyping_center, colony) = self.test_set_1[2:4]
(project_fullname, pipeline_name, pipeline_stable_id,
procedure_stable_id, procedure_name, parameter_stable_id,
parameter_name) = self.test_set_1[12:19]
(statistical_method, resource_name) = self.test_set_1[26:28]
impc._add_study_provenance(
phenotyping_center, colony,
project_fullname,
pipeline_name, pipeline_stable_id,
procedure_stable_id, procedure_name,
parameter_stable_id, parameter_name,
statistical_method, resource_name, 0)
# dbg
logger.info(
"Provenance graph as turtle:\n%s\n",
impc.graph.serialize(format="turtle").decode("utf-8")
)
triples = """
<https://monarchinitiative.org/.well-known/genid/bdd05a8ca155ddaf415e> a OBI:0000471 ;
BFO:0000051 OBO:STATO_0000076,
<https://www.mousephenotype.org/impress/protocol/175/15> ;
BFO:0000050 IMPRESS-procedure:15 ,
<http://www.sanger.ac.uk/science/data/mouse-genomes-project> ;
SEPIO:0000114 <https://www.mousephenotype.org/impress/parameterontologies/1867/91> ;
SEPIO:0000017 <http://www.sanger.ac.uk/> .
<https://monarchinitiative.org/.well-known/genid/b0b26361b8687b5ad9ef> a owl:NamedIndividual ;
rdfs:label "MEFW" .
<http://www.sanger.ac.uk/> a foaf:organization ;
rdfs:label "WTSI" .
<http://www.sanger.ac.uk/science/data/mouse-genomes-project> a VIVO:Project ;
rdfs:label "Wellcome Trust Sanger Institute Mouse Genetics Project" .
<https://www.mousephenotype.org/impress/parameterontologies/1867/91> a owl:NamedIndividual ;
rdfs:label "Number of ribs right (X-ray)" .
IMPRESS-procedure:15 a owl:NamedIndividual ;
rdfs:label "MGP Select Pipeline" .
<https://www.mousephenotype.org/impress/protocol/175/15> a owl:NamedIndividual ;
rdfs:label "X-ray" .
"""
# dbg
logger.debug(
"Reference graph: %s", impc.graph.serialize(format="turtle").decode("utf-8")
)
self.assertTrue(
self.test_util.test_graph_equality(triples, impc.graph))
def setUp(self):
self.source = IMPC('rdf_graph', True)
self.source.settestonly(True)
self._setDirToSource()
return
def test_random_data_set(self):
"""
Download dataset using fetch(), then take a row of data and
run through evidence and provenance functions to test the output
Line of data is hardcoded, but theoretically should work on any line
"""
line_to_test = 1129
count = 0
# init impc (make this a function?)
impc = IMPC('rdf_graph', True)
impress_map = json.loads(
impc.fetch_from_url(impc.map_files['impress_map']).read().decode('utf-8'))
impc_map = impc.open_and_parse_yaml(impc.map_files['impc_map'])
# fetch file
impc.fetch(True)
file_path = '/'.join((impc.rawdir, impc.files['all']['file']))
with gzip.open(file_path, 'rt') as csvfile:
filereader = csv.reader(csvfile, delimiter=',', quotechar='\"')
for row in filereader:
count += 1
if count == line_to_test:
test_set = row
self.test_set_1 = row
break
# Some DRY violation with the above tests
(phenotyping_center, colony) = row[2:4]
(project_fullname, pipeline_name, pipeline_stable_id,
procedure_stable_id, procedure_name, parameter_stable_id,
parameter_name) = row[12:19]
(statistical_method, resource_name) = row[26:28]
(p_value, percentage_change, effect_size) = self.test_set_1[23:26]
impc._add_evidence(self.assoc_curie, self.eco_id, impc_map, p_value,
percentage_change, effect_size, self.study_curie)
impc._add_study_provenance(
impc_map, impress_map, phenotyping_center, colony,
project_fullname, pipeline_name, pipeline_stable_id,
procedure_stable_id, procedure_name,
parameter_stable_id, parameter_name,
statistical_method, resource_name)
# Note that this doesn't test much since we're dealing with
# multiple part_of and has_part links to individuals
# which results in ambiguity = hard to test
sparql_query = """
SELECT *
WHERE {
?assoc OBO:SEPIO_0000007 ?evidenceline .
?evidenceline a OBO:ECO_0000015 ;
OBO:SEPIO_0000085 <https://monarchinitiative.org/.well-known/genid/study> .
?study a OBO:OBI_0000471 ;
OBO:SEPIO_0000114 ?param ;
OBO:SEPIO_0000017 ?agent .
}
"""
sparql_output = impc.graph.query(sparql_query)
# Test that query passes and returns one row
self.assertEqual(len(list(sparql_output)), 1)
def setUp(self):
self.source = IMPC('rdf_graph', True) # Skolem Yes
self.source.settestonly(True)
self._setDirToSource()
return
def test_provenance_model(self):
"""
Functional test for _add_study_provenance()
"""
impc = IMPC('rdf_graph', False)
impc_map = impc.open_and_parse_yaml(impc.map_files['impc_map'])
impress_map = json.loads(
impc.fetch_from_url(impc.map_files['impress_map']).read().decode('utf-8'))
(phenotyping_center, colony) = self.test_set_1[2:4]
(project_fullname, pipeline_name, pipeline_stable_id,
procedure_stable_id, procedure_name, parameter_stable_id,
parameter_name) = self.test_set_1[12:19]
(statistical_method, resource_name) = self.test_set_1[26:28]
impc._add_study_provenance(
impc_map, impress_map, phenotyping_center, colony,
project_fullname, pipeline_name, pipeline_stable_id,
procedure_stable_id, procedure_name,
parameter_stable_id, parameter_name,
statistical_method, resource_name)
sparql_query = """
SELECT ?study
WHERE {
<https://www.mousephenotype.org/impress/procedures/15> a owl:NamedIndividual ;
rdfs:label "MGP Select Pipeline" .
<https://www.mousephenotype.org/impress/protocol/175/15> a owl:NamedIndividual ;
rdfs:label "X-ray" .
<http://www.sanger.ac.uk/> a foaf:organization ;
rdfs:label "WTSI" .
<http://www.sanger.ac.uk/science/data/mouse-genomes-project> a VIVO:Project ;
rdfs:label "Wellcome Trust Sanger Institute Mouse Genetics Project" .
<https://www.mousephenotype.org/impress/parameterontologies/1867/91> a owl:NamedIndividual ;
rdfs:label "Number of ribs right (X-ray)" .
?study a OBO:OBI_0000471 ;
OBO:BFO_0000051 OBO:STATO_0000076 ;
OBO:BFO_0000050 <https://www.mousephenotype.org/impress/procedures/15> ;
OBO:BFO_0000051 <https://www.mousephenotype.org/impress/protocol/175/15> ;
OBO:SEPIO_0000114 <https://www.mousephenotype.org/impress/parameterontologies/1867/91> ;
OBO:BFO_0000050 <http://www.sanger.ac.uk/science/data/mouse-genomes-project> ;
OBO:SEPIO_0000017 <http://www.sanger.ac.uk/> .
?colony a owl:NamedIndividual ;
rdfs:label "MEFW" .
}
"""
sparql_output = impc.graph.query(sparql_query)
# This will fail if we change our approach for
# making blank node iris, it might be better
# to check the length of the output (see test_provenance_mode)
study = BNode('bbdd05a8ca155dda')
expected_output = [(study,)]
self.assertEqual(list(sparql_output), expected_output)
def setUp(self):
self.source = IMPC()
self.source.settestonly(True)
self.source.setnobnodes(True)
self._setDirToSource()
return
def test_random_data_set(self):
"""
Download dataset using fetch(), then take a row of data and
run through evidence and provenance functions to test the output
Line of data is hardcoded, but theoretically should work on any line
"""
line_to_test = 1129
count = 0
impc = IMPC('rdf_graph', False) # Not Skolem
self.test_set_N = []
# fetch file
# impc.fetch(True)
file_path = '/'.join((impc.rawdir, impc.files['all']['file']))
with gzip.open(file_path, 'rt') as csvfile:
filereader = csv.reader(csvfile, delimiter=',', quotechar='\"')
for row in filereader:
count += 1
if count < line_to_test:
continue
elif count == line_to_test:
self.test_set_N = row
elif count > line_to_test:
LOG.info("stopped at line:\t%s\n", count)
break
# Some DRY violation with the above tests
(phenotyping_center, colony) = self.test_set_N[2:4]
(project_name,project_fullname, pipeline_name, pipeline_stable_id,
procedure_stable_id, procedure_name, parameter_stable_id,
parameter_name) = self.test_set_N[11:19]
(statistical_method, resource_name) = self.test_set_N[26:28]
(p_value, percentage_change, effect_size) = self.test_set_N[23:26]
# adding evidence
impc._add_evidence(
self.assoc_curie, self.eco_id, p_value, percentage_change, effect_size,
self.study_curie)
# adding study
impc._add_study_provenance(
phenotyping_center, colony, project_name,
pipeline_name,
pipeline_stable_id,
procedure_stable_id, procedure_name,
parameter_stable_id, parameter_name,
statistical_method, resource_name, line_to_test)
# Note that this doesn't test much since we're dealing with
# multiple part_of and has_part links to individuals
# which results in ambiguity = hard to test
# dbg
LOG.info(
"Row %i graph as ntriples:\n%s\n",
line_to_test, impc.graph.serialize(format="ntriples").decode("utf-8")
)
sparql_query = """
SELECT *
WHERE {
?assoc SEPIO:0000007 ?evidenceline .
?evidenceline a ECO:0000015 ;
SEPIO:0000085 _:study .
?study a OBI:0000471 ;
SEPIO:0000114 ?param ;
SEPIO:0000017 ?agent .
}
"""
sparql_output = impc.graph.query(sparql_query)
LOG.info(
"Test that query for row %i passes and returns one row", int(line_to_test))
# print("Sparql Output: %s\n", list(sparql_output) )
# it is an array with one list with five vars in it
self.assertEqual(len(list(sparql_output)), 1)
def test_random_data_set(self):
"""
Download dataset using fetch(), then take a row of data and
run through evidence and provenance functions to test the output
Line of data is hardcoded, but theoretically should work on any line
"""
line_to_test = 1129
count = 0
impc = IMPC('rdf_graph', False) # Not Skolem
self.test_set_N = []
# fetch file
# impc.fetch(True)
file_path = '/'.join((impc.rawdir, impc.files['all']['file']))
with gzip.open(file_path, 'rt') as csvfile:
filereader = csv.reader(csvfile, delimiter=',', quotechar='\"')
for row in filereader:
count += 1
if count < line_to_test:
continue
elif count == line_to_test:
self.test_set_N = row
elif count > line_to_test:
logger.info("stopped at line:\t%s\n", count)
break
# Some DRY violation with the above tests
(phenotyping_center, colony) = self.test_set_N[2:4]
(project_fullname, pipeline_name, pipeline_stable_id,
procedure_stable_id, procedure_name, parameter_stable_id,
parameter_name) = self.test_set_N[12:19]
(statistical_method, resource_name) = self.test_set_N[26:28]
(p_value, percentage_change, effect_size) = self.test_set_N[23:26]
# adding evidence
impc._add_evidence(
self.assoc_curie, self.eco_id, p_value, percentage_change, effect_size,
self.study_curie)
# adding study
impc._add_study_provenance(
phenotyping_center, colony, project_fullname,
pipeline_name,
pipeline_stable_id,
procedure_stable_id, procedure_name,
parameter_stable_id, parameter_name,
statistical_method, resource_name, line_to_test)
# Note that this doesn't test much since we're dealing with
# multiple part_of and has_part links to individuals
# which results in ambiguity = hard to test
# dbg
logger.info(
"Row %i graph as ntriples:\n%s\n", line_to_test, impc.graph.serialize(
format="ntriples").decode("utf-8")
)
sparql_query = """
SELECT *
WHERE {
?assoc SEPIO:0000007 ?evidenceline .
?evidenceline a ECO:0000015 ;
SEPIO:0000085 _:study .
?study a OBI:0000471 ;
SEPIO:0000114 ?param ;
SEPIO:0000017 ?agent .
}
"""
sparql_output = impc.graph.query(sparql_query)
logger.info("Test that query for row %i passes and returns one row", int(line_to_test))
# print("Sparql Output: %s\n", list(sparql_output) )
# it is an array with one list with five vars in it
self.assertEqual(len(list(sparql_output)), 1)
def test_provenance_model(self):
"""
Functional test for _add_study_provenance()
"""
impc = IMPC('rdf_graph', False)
impc_map = impc.open_and_parse_yaml(impc.map_files['impc_map'])
impress_map = json.loads(
impc.fetch_from_url(
impc.map_files['impress_map']).read().decode('utf-8'))
(phenotyping_center, colony) = self.test_set_1[2:4]
(project_fullname, pipeline_name, pipeline_stable_id,
procedure_stable_id, procedure_name, parameter_stable_id,
parameter_name) = self.test_set_1[12:19]
(statistical_method, resource_name) = self.test_set_1[26:28]
impc._add_study_provenance(impc_map, impress_map, phenotyping_center,
colony, project_fullname, pipeline_name,
pipeline_stable_id, procedure_stable_id,
procedure_name, parameter_stable_id,
parameter_name, statistical_method,
resource_name)
sparql_query = """
SELECT ?study
WHERE {
<https://www.mousephenotype.org/impress/procedures/15> a owl:NamedIndividual ;
rdfs:label "MGP Select Pipeline" .
<https://www.mousephenotype.org/impress/protocol/175/15> a owl:NamedIndividual ;
rdfs:label "X-ray" .
<http://www.sanger.ac.uk/> a foaf:organization ;
rdfs:label "WTSI" .
<http://www.sanger.ac.uk/science/data/mouse-genomes-project> a VIVO:Project ;
rdfs:label "Wellcome Trust Sanger Institute Mouse Genetics Project" .
<https://www.mousephenotype.org/impress/parameterontologies/1867/91> a owl:NamedIndividual ;
rdfs:label "Number of ribs right (X-ray)" .
?study a OBO:OBI_0000471 ;
OBO:BFO_0000051 OBO:STATO_0000076 ;
OBO:BFO_0000050 <https://www.mousephenotype.org/impress/procedures/15> ;
OBO:BFO_0000051 <https://www.mousephenotype.org/impress/protocol/175/15> ;
OBO:SEPIO_0000114 <https://www.mousephenotype.org/impress/parameterontologies/1867/91> ;
OBO:BFO_0000050 <http://www.sanger.ac.uk/science/data/mouse-genomes-project> ;
OBO:SEPIO_0000017 <http://www.sanger.ac.uk/> .
?colony a owl:NamedIndividual ;
rdfs:label "MEFW" .
}
"""
sparql_output = impc.graph.query(sparql_query)
# This will fail if we change our approach for
# making blank node iris, it might be better
# to check the length of the output (see test_provenance_mode)
study = BNode('bbdd05a8ca155dda')
expected_output = [(study, )]
self.assertEqual(list(sparql_output), expected_output)