class BaseGraph(object):
"""
Class representing a graph. We do not use pure graph_tool.Graph for we want
to be able to easily change this library. Neither we use inheritance
as graph_tool has inconvenient licence.
"""
def __init__(self):
self._g = None
self._node_dict = {}
self._syn_to_vertex_map = None
self._lemma_to_nodes_dict = None
self._lu_on_vertex_dict = None
def use_graph_tool(self):
"""
Returns underlying graph_tool.Graph. It should be avoided at all costs.
"""
return self._g
def get_node_for_synset_id(self, syn_id):
"""
Lazy function to makes the map of synset identifiers to nodes into
the graph. The building of map is made only on the first funcion call.
The first and the next calls of this function will return the built map.
"""
if not self._syn_to_vertex_map:
self._syn_to_vertex_map = {}
for node in self.all_nodes():
if node.synset:
synset_id = node.synset.synset_id
self._syn_to_vertex_map[synset_id] = node
return self._syn_to_vertex_map.get(syn_id, None)
def pickle(self, filename):
self._g.save(filename)
def unpickle(self, filename):
self._g = load_graph(filename)
def init_graph(self, drctd=False):
self._g = Graph(directed=drctd)
def copy_graph_from(self, g):
self._g = g._g.copy()
def set_directed(self, drctd):
self._g.set_directed(drctd)
def is_directed(self):
return self._g.is_directed()
def merge_graphs(self, g1, g2):
self._g = graph_union(g1._g, g2._g, internal_props=True)
# Node operations:
def all_nodes(self):
for node in self._g.vertices():
yield BaseNode(self._g, node)
def create_node_attribute(self, name, kind, value=None):
if not self.has_node_attribute(name):
node_attr = self._g.new_vertex_property(kind, value)
self._g.vertex_properties[name] = node_attr
def create_node_attributes(self, node_attributes_list):
for attr in node_attributes_list:
if not self.has_node_attribute(attr[0]):
node_attr = self._g.new_vertex_property(attr[1])
self._g.vertex_properties[attr[0]] = node_attr
def has_node_attribute(self, name):
""" Checks if a node attribute already exists """
return name in self._g.vertex_properties
def delete_node_attribute(self, name):
""" Delete node attribute """
del self._g.vertex_properties[name]
def add_node(self, name, node_attributes_list=None):
if node_attributes_list is None:
node_attributes_list = []
if name not in self._node_dict:
new_node = self._g.add_vertex()
self._node_dict[name] = BaseNode(self._g, new_node)
for attr in node_attributes_list:
self._g.vertex_properties[attr[0]][new_node] = attr[1]
return self._node_dict[name]
def get_node(self, name):
return self._node_dict[name]
def remove_node(self, name):
self._g.remove_vertex(self._node_dict[name]._node)
del self._node_dict[name]
def nodes_filter(self,
nodes_to_filter_set,
inverted=False,
replace=False,
soft=False):
"""
Filters out nodes from set
Args:
nodes_to_filter_set (Iterable): Nodes which fill be filtered out.
inverted (bool): If True, nodes NOT in set will be filtered out.
Defaults to False.
replace (bool): Replace current filter instead of combining the two.
Defaults to False.
soft (bool): Hide nodes without removing them so they can be restored
with reset_nodes_filter. Defaults to False.
"""
predicate = lambda node: node not in nodes_to_filter_set
self.nodes_filter_conditional(predicate, inverted, replace, soft)
def nodes_filter_conditional(self,
predicate,
inverted=False,
replace=False,
soft=False):
"""
Filters node based on a predicate
Args:
predicate (Callable): Predicate returning False for nodes that should be
filtered out.
inverted (bool): Invert condition. Defaults to False.
replace (bool): Replace current filter instead of combining the two.
Defaults to False.
soft (bool): Hide nodes without removing them so they can be restored
with reset_nodes_filter. Defaults to False.
"""
(old_filter, old_inverted) = self._g.get_vertex_filter()
new_filter = self._g.new_vertex_property("bool")
for node in self.all_nodes():
kept = predicate(node) != inverted
if not replace and old_filter:
old_kept = bool(old_filter[node._node]) != old_inverted
kept = kept and old_kept
new_filter[node._node] = kept
self._g.set_vertex_filter(new_filter, False)
if not soft:
self.apply_nodes_filter()
def apply_nodes_filter(self):
""" Removes nodes that are currently filtered out """
self._g.purge_vertices()
def reset_nodes_filter(self):
""" Clears node filter """
self._g.set_vertex_filter(None)
# Edge operations:
def num_edges(self):
return self._g.num_edges()
def all_edges(self):
for e in self._g.edges():
yield BaseEdge(self._g, e)
def get_edges_between(self, source, target):
"""
Return all edges between source and target. Source and target can be either
BaseNode or integer.
"""
if isinstance(source, BaseNode):
source = source._node
if isinstance(target, BaseNode):
target = target._node
for e in self._g.edge(source, target, all_edges=True):
yield BaseEdge(self._g, e)
def get_edge(self, source, target, add_missing=False):
"""
Return some edge between source and target. Source and target can be either
BaseNode or integer.
"""
if isinstance(source, BaseNode):
source = source._node
if isinstance(target, BaseNode):
target = target._node
e = self._g.edge(source, target, add_missing)
if e is not None:
return BaseEdge(self._g, e)
else:
return None
def create_edge_attribute(self, name, kind, value=None):
if not self.has_edge_attribute(name):
edge_attr = self._g.new_edge_property(kind, value)
self._g.edge_properties[name] = edge_attr
def alias_edge_attribute(self, name, alias):
self._g.edge_properties[alias] = self._g.edge_properties[name]
def create_edge_attributes(self, edge_attributes_list):
for attr in edge_attributes_list:
if not self.has_edge_attribute(attr[0]):
edge_attr = self._g.new_edge_property(attr[1])
self._g.edge_properties[attr[0]] = edge_attr
def has_edge_attribute(self, name):
""" Checks if an edge attribute already existst """
return name in self._g.edge_properties
def delete_edge_attribute(self, name):
""" Delete edge attribute """
del self._g.edge_properties[name]
def add_edge(self, parent, child, edge_attributes_list=None):
if edge_attributes_list is None:
edge_attributes_list = []
new_edge = self._g.add_edge(parent._node, child._node)
for attr in edge_attributes_list:
self._g.edge_properties[attr[0]][new_edge] = attr[1]
return BaseEdge(self._g, new_edge)
def edges_filter(self, edges_to_filter_set):
edge_filter = self._g.new_edge_property("bool")
for e in self.all_edges():
if e in edges_to_filter_set:
edge_filter[e._edge] = False
else:
edge_filter[e._edge] = True
self._g.set_edge_filter(edge_filter)
self._g.purge_edges()
def ungraph_tool(self, thingy, lemma_on_only_synset_node_dict):
"""
Converts given data structure so that it no longer have any graph_tool dependencies.
"""
logger = logging.getLogger(__name__)
if type(thingy) == dict:
return {
self.ungraph_tool(k, lemma_on_only_synset_node_dict):
self.ungraph_tool(thingy[k], lemma_on_only_synset_node_dict)
for k in thingy
}
nodes_to_translate = set()
for vset in lemma_on_only_synset_node_dict.values():
for v in vset:
nodes_to_translate.add(v)
if type(thingy) == gt.PropertyMap:
dct = {}
if thingy.key_type() == 'v':
for node in nodes_to_translate:
dct[node] = thingy[node.use_graph_tool()]
elif thingy.key_type() == 'e':
for edge in self.all_edges():
dct[edge] = thingy[edge.use_graph_tool()]
else:
logger.error('Unknown property type %s', thingy.key_type())
raise NotImplemented
return dct
def generate_lemma_to_nodes_dict_synsets(self):
"""
This method generates a utility dictionary, which maps lemmas to
corresponding node objects. It is expensive in menas of time
needed to generate the dictionary. It should therefore be executed
at the beginning of the runtime and later its results should be reused
as many times as needed without re-executing the function.
"""
lemma_to_nodes_dict = defaultdict(set)
for node in self.all_nodes():
try:
lu_set = node.synset.lu_set
except KeyError:
continue
for lu in lu_set:
lemma = lu.lemma.lower()
lemma_to_nodes_dict[lemma].add(node)
self._lemma_to_nodes_dict = lemma_to_nodes_dict
def generate_lemma_to_nodes_dict_lexical_units(self):
"""
This method generates a utility dictionary, which maps lemmas to
corresponding node objects. It is expensive in menas of time
needed to generate the dictionary. It should therefore be executed
at the beginning of the runtime and later its results should be reused
as many times as needed without re-executing the function.
"""
lemma_to_nodes_dict = defaultdict(set)
for node in self.all_nodes():
try:
lemma = node.lu.lemma.lower()
lemma_to_nodes_dict[lemma].add(node)
except:
continue
self._lemma_to_nodes_dict = lemma_to_nodes_dict
@property
def lemma_to_nodes_dict(self):
return self._lemma_to_nodes_dict
def _make_lu_on_v_dict(self):
"""
Makes dictionary lu on vertex
"""
lu_on_vertex_dict = defaultdict(set)
for node in self.all_nodes():
try:
nl = node.lu
except Exception:
continue
if nl:
lu_on_vertex_dict[node.lu.lu_id] = node
self._lu_on_vertex_dict = lu_on_vertex_dict
def import_e_coli_ppi(save=False, export=False):
'''
Imports the dataset E_Coli and saves it as a graph (Snap, GTools and Greach format).
'''
saveLoadFolder = "E_Coli"
graphName = "E_Coli"
graphFile = "../Data/Graphs/" + saveLoadFolder + "/E_Coli_Edge_List.txt"
# labelsFile = "../Data/Graphs/"+saveLoadFolder+"/E_Coli_Essential_Genes.txt"
labelsFile = "../Data/Graphs/" + saveLoadFolder + "/E_Coli_Labels.csv"
g = Graph(directed=False)
# interactionWeight = g.new_edge_property("double")
proteinNameToNode = dict()
with open(graphFile, "r") as inF:
for line in inF:
# splitted = line.rstrip().split('|')
# fromNode = splitted[1].strip()
# toNode = splitted[3].strip()
# weight = float(splitted[4])
fromNode, toNode = line.strip().split()
fromNode = fromNode.strip()
toNode = toNode.strip()
# print fromNode, toNode
# print fromNode, toNode, weight
if fromNode not in proteinNameToNode:
newNode = g.add_vertex()
proteinNameToNode[fromNode] = int(newNode)
if toNode not in proteinNameToNode:
newNode = g.add_vertex()
proteinNameToNode[toNode] = int(newNode)
source = proteinNameToNode[fromNode]
target = proteinNameToNode[toNode]
edge = g.add_edge(g.vertex(source), g.vertex(target))
# interactionWeight[edge] = weight
essentiality = g.new_vertex_property("short")
essentiality.a = 0
symbolToInt = {'N': 0, 'E': 1, '?': '2', 'X': 3}
print g
import csv
with open(labelsFile, "r") as inFile:
count = 0
data = [row for row in csv.reader(inFile.read().splitlines())]
for pair in data:
proteinName, attribute = pair
try:
essentiality.a[proteinNameToNode[
proteinName.lower()]] = symbolToInt[attribute]
except:
count += 1
print count
g.vp["essentiality"] = essentiality
lethalOrNot = essentiality.a == 0
lethalOrNot += essentiality.a == 1
lethality = g.new_vertex_property("boolean")
lethality.a = lethalOrNot
g.set_vertex_filter(lethality)
g.purge_vertices()
print g
p()
lethality.a = 0
lethality.a[essentiality.a == 1] = 1
g.vp["lethality"] = lethality
# lethality = g.new_vertex_property("boolean")
# lethality.a = 0
# with open(labelsFile, "r") as inF:
# for line in inF:
# try:
# nodeID = proteinNameToNode[line.rstrip()]
# lethality.a[nodeID] = 1
# except: #we don't have this node in the PPI net
# pass
#
#
# g.vp["lethality"] = lethality
# # g.ep["weights"] = interactionWeight
g = graph_analysis.IO.make_simple_graph(g, undirected=True, gcc=True)
if save:
graph_analysis.IO.save_data(
"../Data/Graphs/" + saveLoadFolder + "/" + graphName + ".GT.graph",
g)
if export:
exportToSnapAndGreach(graphName, saveLoadFolder)
return g