def load_fun(self, fun_path):
with open(fun_path, "r") as handle:
string = handle.read()
groups = re.split(re.compile("\r\n\r\n"), string)
for group in groups:
glines = [g.strip() for g in group.split("\n") if g.strip()]
term = glines[0].strip().lower()
keywords = self.ki.extract_keywords(term)
parent_ont_doc = Ontology(term=term,
name=term,
keywords=keywords,
ontology="cog")
parent_ont_doc.save()
for line in glines[1:]:
term = line.lower().strip().split(" ")[0]
name = " ".join(line.lower().strip().split(" ")[1:])
keywords = list(
set(parent_ont_doc.keywords +
self.ki.extract_keywords(line)))
ont_doc = Ontology(term=term,
name=name,
parent=parent_ont_doc.term,
keywords=keywords,
ontology="cog")
parent_ont_doc.children.append(term)
ont_doc.save()
def load_whog(self, whog_path):
with open(whog_path, "r") as handle:
groups = handle.read().split("_______")
for group in groups:
glines = [g.strip() for g in group.split("\n") if g.strip()]
if glines:
line = glines[0].lower()
parent = line.lower().strip().split(" ")[0]
term = line.lower().strip().split(" ")[1]
name = " ".join(line.lower().strip().split(" ")[2:])
ont_doc = Ontology(term=term,
name=name,
parent=parent,
ontology="cog")
keywords = self.ki.extract_keywords(line)
if len(parent) > 3:
for x in parent[1:-1]:
parent_ont_doc = Ontology.objects(term='[' + x +
']').get()
keywords = list(set(parent_ont_doc.keywords +
keywords))
parent_ont_doc.children.append(term)
parent_ont_doc.save()
else:
parent_ont_doc = Ontology.objects(term=parent).get()
parent_ont_doc.children.append(term)
parent_ont_doc.save()
keywords = list(set(parent_ont_doc.keywords + keywords))
ont_doc.keywords = keywords
ont_doc.save()
def create_ontology(self, ontology_db):
ontology_db.remove({"ontology": "cog"})
for ontology in self.cog:
keywords = self.ki.extract_keywords(ontology)
ont_doc = Ontology(term=ontology,
keywords=keywords,
ontology="cog")
ont_doc.save()
def load_dat(self, reactions_file, database, postfix):
with open(reactions_file) as reactions_handle:
lines = [
x for x in reactions_handle.readlines()
if not x.startswith("#")
]
records = re.split("//\n", "\n".join(lines))
for record in records:
if not record.strip():
continue
ont_doc = Ontology(ontology=self.ontology_name + postfix)
ont_doc.databases.append(database)
reaction_types = []
ec = None
for str_record in [y for y in record.split("\n") if y]:
if str_record.strip() and len(str_record.strip()) > 3:
if len(str_record.split(" - ")) > 1:
field = str_record.split(" - ")[0].strip()
try:
value = str_record.split(
" - ")[1].strip().decode("utf-8")
except UnicodeDecodeError:
continue
if field == "UNIQUE-ID":
ont_doc.term = value.lower()
elif field == "TYPES":
reaction_types.append(value)
elif field == "IN-PATHWAY":
ont_doc.parents.append(value)
elif field == "COMMON-NAME":
ont_doc.name = value
elif (field == "COMMENT") and (not ont_doc.name):
ont_doc.description = value
elif (field == "EC-NUMBER") and (not ont_doc.name):
ec = value
if not ont_doc.description:
ont_doc.description = "|".join(reaction_types)
if not ont_doc.name:
if ec:
ont_doc.name = ec
else:
ont_doc.name = ont_doc.term
ont_doc.keywords = self.ki.extract_keywords(
ont_doc.name) + [ont_doc.term]
ont_doc.types = reaction_types
if ec:
ont_doc.keywords.append(ec)
if not ont_doc.term:
print(record)
else:
ont_doc.save()
def load_pathways(self, pathways_file, database):
with open(pathways_file) as pathways_handle:
for x in pathways_handle.readlines():
if not (x.strip().startswith("#") or x.strip().startswith("UNIQUE-ID")):
line = re.sub(r'\t+', '\t', x)
term = line.split("\t")[0].strip().lower()
name = line.split("\t")[1].strip()
ont_doc = Ontology(term=term,
name=name,
ontology=self.ontology_name + "_pw",
keywords=self.ki.extract_keywords(name) + [term])
ont_doc.databases.append(database)
ont_doc.save()
def load_enzclass(self, enzclass_file_path):
root = Ontology(ontology=self.ontology_name, term="root", name="ec",
children=["ec:1.-.-.-", "ec:2.-.-.-", "ec:3.-.-.-", "ec:4.-.-.-", "ec:5.-.-.-", "ec:6.-.-.-"])
root.save()
with open(enzclass_file_path) as enzclass_handle:
for line in enzclass_handle:
if re.match(r'^[1-6][.]', line):
name = line.split(".-")[-1].strip()
term = "ec:" + line.replace(name, "").replace(" ", "").strip()
ont_doc = Ontology(ontology=self.ontology_name, term=term, name=name)
ont_doc.keywords = self.ki.extract_keywords(ont_doc.name) + [ont_doc.term]
ont_doc.save()
def _load_mongo(self):
root = Ontology(ontology=self.ontology_name,
term="root",
successors=self.root_terms,
children=self.root_terms)
root.save()
for (node, data) in self.graph.nodes_iter(
data=True): # self.graph.add_node(node, **data)
if node == "root":
raise Exception("...")
else:
successors = self.graph.successors(node)
_ancestors = self.complete_subgraph([node])
database = "biological_process"
if "go:0005575" in _ancestors:
database = "cellular_component"
if "go:0003674" in _ancestors:
database = "molecular_function"
ont_doc = Ontology(
ontology=self.ontology_name,
term=node,
name=data["name"],
database=database,
successors=self.all_successors(node, []),
children=successors,
description=self.go_dag.query_term(node.upper()).desc,
# successors_relationships=self.successors_relationships(node),
subclases=list(
set([
x.lower() for x in self.go_dag.query_term(
node.upper()).get_all_children()
])))
ont_doc.keywords = self.ki.extract_keywords(
[ont_doc.description, ont_doc.name, ont_doc.term])
ont_doc.save()