def test_json_load():
t = ObographJsonTransformer()
t.parse(os.path.join(resource_dir, 'goslim_generic.json'))
assert t.graph.number_of_nodes() == 176
assert t.graph.number_of_edges() == 206
n1 = t.graph.nodes(data=True)['GO:0003677']
assert n1['id'] == 'GO:0003677'
assert n1['name'] == 'DNA binding'
assert n1[
'description'] == 'Any molecular function by which a gene product interacts selectively and non-covalently with DNA (deoxyribonucleic acid).'
assert n1['category'] == ['biolink:MolecularActivity']
assert 'structure-specific DNA binding' in n1['synonym']
assert 'structure specific DNA binding' in n1['synonym']
assert 'microtubule/chromatin interaction' in n1['synonym']
assert 'plasmid binding' in n1['synonym']
n2 = t.graph.nodes(data=True)['GO:0005575']
assert n2['id'] == 'GO:0005575'
assert n2['name'] == 'cellular_component'
assert n2[
'description'] == 'A location, relative to cellular compartments and structures, occupied by a macromolecular machine when it carries out a molecular function. There are two ways in which the gene ontology describes locations of gene products: (1) relative to cellular structures (e.g., cytoplasmic side of plasma membrane) or compartments (e.g., mitochondrion), and (2) the stable macromolecular complexes of which they are parts (e.g., the ribosome).'
assert n2['category'] == ['biolink:CellularComponent']
assert n2['xrefs'] == ['NIF_Subcellular:sao1337158144']
assert 'goslim_chembl' in n2['subsets']
assert 'goslim_generic' in n2['subsets']
def test_load_edge():
edge = {
"sub": "http://purl.obolibrary.org/obo/GO_0003677",
"pred": "is_a",
"obj": "http://purl.obolibrary.org/obo/GO_0003674"
}
t = ObographJsonTransformer()
t.load_edge(edge)
e = next(iter(t.graph.edges(data=True)))
assert e[2]['subject'] == 'GO:0003677'
assert e[2]['edge_label'] == 'biolink:subclass_of'
assert e[2]['relation'] == 'rdfs:subClassOf'
assert e[2]['object'] == 'GO:0003674'
def parse(self, name: str, data_file: str, source: str) -> None:
"""Processes the data_file.
Args:
name: Name of the ontology
data_file: data file to parse
source: Source name
Returns:
None.
"""
print(f"Parsing {data_file}")
transformer = ObographJsonTransformer()
transformer.parse(data_file, provided_by=source)
output_transformer = PandasTransformer(transformer.graph)
output_transformer.save(filename=os.path.join(self.output_dir, f'{name}'), output_format='tsv', mode=None)
def parse(self, name: str, data_file: str) -> None:
"""Processes the data_file.
Args:
name: Name of the ontology
data_file: data file to parse
Returns:
None.
"""
logging.info(f"Parsing {data_file}")
transformer = ObographJsonTransformer()
transformer.parse(data_file)
output_transformer = PandasTransformer(transformer.graph)
output_transformer.save(filename=os.path.join(self.output_dir,
f'{name}'),
extension='tsv',
mode=None)
def test_load_node():
node = {
"id": "http://purl.obolibrary.org/obo/GO_0005615",
"meta": {
"basicPropertyValues": [{
"pred":
"http://www.geneontology.org/formats/oboInOwl#hasOBONamespace",
"val": "cellular_component"
}]
},
"type": "CLASS",
"lbl": "extracellular space"
}
t = ObographJsonTransformer()
t.load_node(node)
n = next(iter(t.graph.nodes(data=True)))
assert n[1]['id'] == 'GO:0005615'
assert n[1]['name'] == 'extracellular space'
assert n[1]['category'] == ['biolink:CellularComponent']
def parse(self, name: str, data_file: str, source: str) -> None:
"""Processes the data_file.
:param name: Name of the ontology
:param data_file: data file to parse
:param source: Source name
:return: None.
"""
print(f"Parsing {data_file}")
transformer = ObographJsonTransformer()
compression: Optional[str]
if data_file.endswith('.gz'):
compression = 'gz'
else:
compression = None
transformer.parse(data_file,
compression=compression,
provided_by=source)
output_transformer = PandasTransformer(transformer.graph)
output_transformer.save(filename=os.path.join(self.output_dir,
f'{name}'),
output_format='tsv',
mode=None)
def test_get_category(query):
node = query[0]
t = ObographJsonTransformer()
c = t.get_category(node['id'], node)
assert c == query[1]