def test_two_nodes(self, method):
G = nx.Graph()
G.add_edge(0, 1, weight=1)
A = nx.laplacian_matrix(G)
assert almost_equal(nx.algebraic_connectivity(G, tol=1e-12, method=method), 2)
x = nx.fiedler_vector(G, tol=1e-12, method=method)
check_eigenvector(A, 2, x)
def main():
J = make_suspicious_graph()
utils.plot_graph_random(J)
LG = nx.laplacian_matrix(J)
eigen_values = LA.eig(LG.toarray())
eigen_values = (np.around(eigen_values[0]), eigen_values[1])
sorted_eigen_values = []
for i in range(len(eigen_values[0])):
sorted_eigen_values.append(
(abs(eigen_values[0][i]), eigen_values[1][i]))
sort(sorted_eigen_values)
internal_fiedler_vector = nx.fiedler_vector(J)
print("Fiedler Value: " + str(sorted_eigen_values[1][0]))
print("Fiedler Vector: " + str(sorted_eigen_values[1][1]))
print("Internal Fiedler Vector: " + str())
fiedler_partition = partition_fiedler(internal_fiedler_vector)
print("J Nodes")
print(J.nodes)
print("Fiedler Partition")
print(fiedler_partition)
plot_partition(J, fiedler_partition)
def test_path(self, method):
G = nx.path_graph(8)
A = nx.laplacian_matrix(G)
sigma = 2 - sqrt(2 + sqrt(2))
ac = nx.algebraic_connectivity(G, tol=1e-12, method=method)
assert almost_equal(ac, sigma)
x = nx.fiedler_vector(G, tol=1e-12, method=method)
check_eigenvector(A, sigma, x)
def test_seed_argument(self, method):
G = nx.cycle_graph(8)
A = nx.laplacian_matrix(G)
sigma = 2 - sqrt(2)
ac = nx.algebraic_connectivity(G, tol=1e-12, method=method, seed=1)
assert almost_equal(ac, sigma)
x = nx.fiedler_vector(G, tol=1e-12, method=method, seed=1)
check_eigenvector(A, sigma, x)
def test_abbreviation_of_method(self):
G = nx.path_graph(8)
A = nx.laplacian_matrix(G)
sigma = 2 - sqrt(2 + sqrt(2))
ac = nx.algebraic_connectivity(G, tol=1e-12, method="tracemin")
assert almost_equal(ac, sigma)
x = nx.fiedler_vector(G, tol=1e-12, method="tracemin")
check_eigenvector(A, sigma, x)
def test_abbreviation_of_method(self):
G = nx.path_graph(8)
A = nx.laplacian_matrix(G)
sigma = 2 - sqrt(2 + sqrt(2))
ac = nx.algebraic_connectivity(G, tol=1e-12, method='tracemin')
assert_almost_equal(ac, sigma)
x = nx.fiedler_vector(G, tol=1e-12, method='tracemin')
check_eigenvector(A, sigma, x)
def test_cycle(self):
G = nx.cycle_graph(8)
A = nx.laplacian_matrix(G)
sigma = 2 - sqrt(2)
for method in self._methods:
ac = nx.algebraic_connectivity(G, tol=1e-12, method=method)
assert_almost_equal(ac, sigma)
x = nx.fiedler_vector(G, tol=1e-12, method=method)
check_eigenvector(A, sigma, x)
def test_cycle(self, method):
pytest.importorskip("scipy")
G = nx.cycle_graph(8)
A = nx.laplacian_matrix(G)
sigma = 2 - sqrt(2)
ac = nx.algebraic_connectivity(G, tol=1e-12, method=method)
assert almost_equal(ac, sigma)
x = nx.fiedler_vector(G, tol=1e-12, method=method)
check_eigenvector(A, sigma, x)
def test_two_nodes(self, method):
pytest.importorskip("scipy")
G = nx.Graph()
G.add_edge(0, 1, weight=1)
A = nx.laplacian_matrix(G)
assert nx.algebraic_connectivity(
G, tol=1e-12, method=method) == pytest.approx(2, abs=1e-7)
x = nx.fiedler_vector(G, tol=1e-12, method=method)
check_eigenvector(A, 2, x)
def test_abbreviation_of_method(self):
pytest.importorskip("scipy")
G = nx.path_graph(8)
A = nx.laplacian_matrix(G)
sigma = 2 - sqrt(2 + sqrt(2))
ac = nx.algebraic_connectivity(G, tol=1e-12, method="tracemin")
assert ac == pytest.approx(sigma, abs=1e-7)
x = nx.fiedler_vector(G, tol=1e-12, method="tracemin")
check_eigenvector(A, sigma, x)
def test_seed_argument(self, method):
pytest.importorskip("scipy")
G = nx.cycle_graph(8)
A = nx.laplacian_matrix(G)
sigma = 2 - sqrt(2)
ac = nx.algebraic_connectivity(G, tol=1e-12, method=method, seed=1)
assert ac == pytest.approx(sigma, abs=1e-7)
x = nx.fiedler_vector(G, tol=1e-12, method=method, seed=1)
check_eigenvector(A, sigma, x)
def test_problematic_graph_issue_2381(self, method):
G = nx.path_graph(4)
G.add_edges_from([(4, 2), (5, 1)])
A = nx.laplacian_matrix(G)
sigma = 0.438447187191
ac = nx.algebraic_connectivity(G, tol=1e-12, method=method)
assert almost_equal(ac, sigma)
x = nx.fiedler_vector(G, tol=1e-12, method=method)
check_eigenvector(A, sigma, x)
def test_problematic_graph_issue_2381(self):
G = nx.path_graph(4)
G.add_edges_from([(4, 2), (5, 1)])
A = nx.laplacian_matrix(G)
sigma = 0.438447187191
for method in self._methods:
ac = nx.algebraic_connectivity(G, tol=1e-12, method=method)
assert_almost_equal(ac, sigma)
x = nx.fiedler_vector(G, tol=1e-12, method=method)
check_eigenvector(A, sigma, x)
def test_problematic_graph_issue_2381(self, method):
pytest.importorskip("scipy")
G = nx.path_graph(4)
G.add_edges_from([(4, 2), (5, 1)])
A = nx.laplacian_matrix(G)
sigma = 0.438447187191
ac = nx.algebraic_connectivity(G, tol=1e-12, method=method)
assert ac == pytest.approx(sigma, abs=1e-7)
x = nx.fiedler_vector(G, tol=1e-12, method=method)
check_eigenvector(A, sigma, x)
def test_two_nodes(self):
G = nx.Graph()
G.add_edge(0, 1, weight=1)
A = nx.laplacian_matrix(G)
for method in self._methods:
assert_almost_equal(nx.algebraic_connectivity(
G, tol=1e-12, method=method), 2)
x = nx.fiedler_vector(G, tol=1e-12, method=method)
check_eigenvector(A, 2, x)
G = nx.MultiGraph()
G.add_edge(0, 0, spam=1e8)
G.add_edge(0, 1, spam=1)
G.add_edge(0, 1, spam=-2)
A = -3 * nx.laplacian_matrix(G, weight='spam')
for method in self._methods:
assert_almost_equal(nx.algebraic_connectivity(
G, weight='spam', tol=1e-12, method=method), 6)
x = nx.fiedler_vector(G, weight='spam', tol=1e-12, method=method)
check_eigenvector(A, 6, x)
def test_two_nodes_multigraph(self, method):
G = nx.MultiGraph()
G.add_edge(0, 0, spam=1e8)
G.add_edge(0, 1, spam=1)
G.add_edge(0, 1, spam=-2)
A = -3 * nx.laplacian_matrix(G, weight="spam")
assert almost_equal(
nx.algebraic_connectivity(G, weight="spam", tol=1e-12, method=method), 6
)
x = nx.fiedler_vector(G, weight="spam", tol=1e-12, method=method)
check_eigenvector(A, 6, x)
def find_communities(self):
dolphin_count = len(self._nodes)
fiedler_vector = nx.fiedler_vector(self._graph)
X_data = np.array(fiedler_vector).reshape((len(fiedler_vector), 1))
kmeans = KMeans(n_clusters=2).fit(X_data)
negative_cluster = [i for i in range(len(kmeans.labels_)) if kmeans.labels_[i] == 0]
positive_cluster = [i for i in range(len(kmeans.labels_)) if kmeans.labels_[i] == 1]
assert len(negative_cluster) + len(positive_cluster) == dolphin_count
positive_dolphins = [self._nodes[i] for i in positive_cluster]
negative_dolphins = [self._nodes[i] for i in negative_cluster]
return positive_dolphins, negative_dolphins
def ComputeFiedlerVector(G):
"""
Given a graph adjacency matrix, return a Fielder vector.
"""
# TODO: implement a case where it converts to a networkx graph if G is a numpy array
if type(G) == type(np.ndarray((1, 1, 1), dtype=float)):
G = nx.to_networkx_graph(G)
v = nx.fiedler_vector(G)
return v
def spectral_partitioning(G):
labels = []
fiedler = nx.fiedler_vector(G, method='lanczos')
median = np.median(fiedler)
labels = []
for i in range(len(fiedler)):
if (fiedler[i] < median):
labels.append(-1)
else:
labels.append(1)
#print("labels:")
#print(labels)
return labels
def test_two_nodes_multigraph(self, method):
pytest.importorskip("scipy")
G = nx.MultiGraph()
G.add_edge(0, 0, spam=1e8)
G.add_edge(0, 1, spam=1)
G.add_edge(0, 1, spam=-2)
A = -3 * nx.laplacian_matrix(G, weight="spam")
assert nx.algebraic_connectivity(G,
weight="spam",
tol=1e-12,
method=method) == pytest.approx(
6, abs=1e-7)
x = nx.fiedler_vector(G, weight="spam", tol=1e-12, method=method)
check_eigenvector(A, 6, x)
def test_buckminsterfullerene(self):
G = nx.Graph([
(1, 10), (1, 41), (1, 59), (2, 12), (2, 42), (2, 60), (3, 6),
(3, 43), (3, 57), (4, 8), (4, 44), (4, 58), (5, 13), (5, 56),
(5, 57), (6, 10), (6, 31), (7, 14), (7, 56), (7, 58), (8, 12),
(8, 32), (9, 23), (9, 53), (9, 59), (10, 15), (11, 24), (11, 53),
(11, 60), (12, 16), (13, 14), (13, 25), (14, 26), (15, 27),
(15, 49), (16, 28), (16, 50), (17, 18), (17, 19), (17, 54), (18,
20),
(18, 55), (19, 23), (19, 41), (20, 24), (20, 42), (21, 31), (21,
33),
(21, 57), (22, 32), (22, 34), (22, 58), (23, 24), (25, 35), (25,
43),
(26, 36), (26, 44), (27, 51), (27, 59), (28, 52), (28, 60), (29,
33),
(29, 34), (29, 56), (30, 51), (30, 52), (30, 53), (31, 47), (32,
48),
(33, 45), (34, 46), (35, 36), (35, 37), (36, 38), (37, 39), (37,
49),
(38, 40), (38, 50), (39, 40), (39, 51), (40, 52), (41, 47),
(42, 48), (43, 49), (44, 50), (45, 46), (45, 54), (46, 55),
(47, 54), (48, 55)
])
for normalized in (False, True):
if not normalized:
A = nx.laplacian_matrix(G)
sigma = 0.2434017461399311
else:
A = nx.normalized_laplacian_matrix(G)
sigma = 0.08113391537997749
for method in methods:
try:
assert almost_equal(
nx.algebraic_connectivity(G,
normalized=normalized,
tol=1e-12,
method=method), sigma)
x = nx.fiedler_vector(G,
normalized=normalized,
tol=1e-12,
method=method)
check_eigenvector(A, sigma, x)
except nx.NetworkXError as e:
if e.args not in (('Cholesky solver unavailable.', ),
('LU solver unavailable.', )):
raise
def normalized_cut(G): # C = laplacian_complete(L.shape[0]) # isqrtC = sqrtmi(C) # M = scipy.sparse.csr_matrix.dot(scipy.sparse.csr_matrix.dot(isqrtC, L), isqrtC) # (eigvals, eigvecs) = scipy.linalg.eigh(M,eigvals=(1,1)) # print(L.todense()) Gcc=sorted(networkx.connected_component_subgraphs(G), key = len, reverse=True) G0=Gcc[0] if networkx.number_of_nodes(G) == networkx.number_of_nodes(G0): x = networkx.fiedler_vector(G, method='lobpcg',tol=1e-5) x = sweep(x, G) else: x = separate_lcc(G, G0) return numpy.array(x)
def ratio_cut(G):
"""
Computes ratio-cut of G based on second eigenvector of the Laplacian.
Input:
* G: Graph
Output:
* x: Indicator vector
"""
Gcc = sorted(nx.connected_component_subgraphs(G), key=len, reverse=True)
G0 = Gcc[0]
if nx.number_of_nodes(G) == nx.number_of_nodes(G0):
scipy.random.seed(1)
x = nx.fiedler_vector(G, method=_method, tol=1e-5)
x = sweep(x, G)
else:
# In case G is not connected
x = separate_lcc(G, G0)
return np.array(x)
def normalized_cut(G):
# C = laplacian_complete(L.shape[0])
# isqrtC = sqrtmi(C)
# M = scipy.sparse.csr_matrix.dot(scipy.sparse.csr_matrix.dot(isqrtC, L), isqrtC)
# (eigvals, eigvecs) = scipy.linalg.eigh(M,eigvals=(1,1))
# print(L.todense())
Gcc = sorted(networkx.connected_component_subgraphs(G),
key=len,
reverse=True)
G0 = Gcc[0]
if networkx.number_of_nodes(G) == networkx.number_of_nodes(G0):
x = networkx.fiedler_vector(G, method='lobpcg', tol=1e-5)
x = sweep(x, G)
else:
x = separate_lcc(G, G0)
return numpy.array(x)
def fiedler_vector(g, _weight, _normalized=False, _out_path=None):
try:
start = time.time()
fv = nx.fiedler_vector(g, weight=_weight, normalized=_normalized)
node_list = list(g.nodes)
data = {}
for i in range(len(node_list)):
data[node_list[i]] = fv[i]
ret = {'name': 'fiedler', 'normalized': _normalized, 'weight': _weight, 'num_of_nodes': g.number_of_nodes(),
'num_of_edges': g.number_of_edges(), 'process_time': (time.time() - start),
'data': __normalize_filter(data), 'ranked': __rank_filter(data)}
if _out_path is not None:
graph_io.write_json_data(_out_path, ret)
return ret
except nx.exception.NetworkXError:
print(">>> FAILED (fiedler_vector): processing error. maybe graph not connected?")
return None
def adj_mat():
A = nx.from_numpy_matrix(np.array([
[0, 1, 1, 0, 0, 1, 0, 0, 1, 1],
[1, 0, 1, 0, 0, 0, 0, 0, 0, 0],
[1, 1, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 1, 1, 0, 0, 0, 0],
[0, 0, 0, 1, 0, 1, 0, 0, 0, 0],
[1, 0, 0, 1, 1, 0, 1, 1, 0, 0],
[0, 0, 0, 0, 0, 1, 0, 1, 0, 0],
[0, 0, 0, 0, 0, 1, 1, 0, 0, 0],
[1, 0, 0, 0, 0, 0, 0, 0, 0, 1],
[1, 0, 0, 0, 0, 0, 0, 0, 1, 0]]))
fiedler_vector = nx.fiedler_vector(A)
LG = nx.laplacian_matrix(A)
print(np.linalg.eigvals(LG.toarray()))
print(fiedler_vector)
partition = ([], [])
for i in range(len(fiedler_vector)):
if fiedler_vector[i] > 0:
partition[1].append(i)
else:
partition[0].append(i)
plot_partition(A, partition)
def test_buckminsterfullerene(self):
G = nx.Graph(
[(1, 10), (1, 41), (1, 59), (2, 12), (2, 42), (2, 60), (3, 6),
(3, 43), (3, 57), (4, 8), (4, 44), (4, 58), (5, 13), (5, 56),
(5, 57), (6, 10), (6, 31), (7, 14), (7, 56), (7, 58), (8, 12),
(8, 32), (9, 23), (9, 53), (9, 59), (10, 15), (11, 24), (11, 53),
(11, 60), (12, 16), (13, 14), (13, 25), (14, 26), (15, 27),
(15, 49), (16, 28), (16, 50), (17, 18), (17, 19), (17, 54),
(18, 20), (18, 55), (19, 23), (19, 41), (20, 24), (20, 42),
(21, 31), (21, 33), (21, 57), (22, 32), (22, 34), (22, 58),
(23, 24), (25, 35), (25, 43), (26, 36), (26, 44), (27, 51),
(27, 59), (28, 52), (28, 60), (29, 33), (29, 34), (29, 56),
(30, 51), (30, 52), (30, 53), (31, 47), (32, 48), (33, 45),
(34, 46), (35, 36), (35, 37), (36, 38), (37, 39), (37, 49),
(38, 40), (38, 50), (39, 40), (39, 51), (40, 52), (41, 47),
(42, 48), (43, 49), (44, 50), (45, 46), (45, 54), (46, 55),
(47, 54), (48, 55)])
for normalized in (False, True):
if not normalized:
A = nx.laplacian_matrix(G)
sigma = 0.2434017461399311
else:
A = nx.normalized_laplacian_matrix(G)
sigma = 0.08113391537997749
for method in methods:
try:
assert_almost_equal(nx.algebraic_connectivity(
G, normalized=normalized, tol=1e-12, method=method),
sigma)
x = nx.fiedler_vector(G, normalized=normalized, tol=1e-12,
method=method)
check_eigenvector(A, sigma, x)
except nx.NetworkXError as e:
if e.args not in (('Cholesky solver unavailable.',),
('LU solver unavailable.',)):
raise
def test_buckminsterfullerene(self, normalized, sigma, laplacian_fn,
method):
pytest.importorskip("scipy")
G = nx.Graph([
(1, 10),
(1, 41),
(1, 59),
(2, 12),
(2, 42),
(2, 60),
(3, 6),
(3, 43),
(3, 57),
(4, 8),
(4, 44),
(4, 58),
(5, 13),
(5, 56),
(5, 57),
(6, 10),
(6, 31),
(7, 14),
(7, 56),
(7, 58),
(8, 12),
(8, 32),
(9, 23),
(9, 53),
(9, 59),
(10, 15),
(11, 24),
(11, 53),
(11, 60),
(12, 16),
(13, 14),
(13, 25),
(14, 26),
(15, 27),
(15, 49),
(16, 28),
(16, 50),
(17, 18),
(17, 19),
(17, 54),
(18, 20),
(18, 55),
(19, 23),
(19, 41),
(20, 24),
(20, 42),
(21, 31),
(21, 33),
(21, 57),
(22, 32),
(22, 34),
(22, 58),
(23, 24),
(25, 35),
(25, 43),
(26, 36),
(26, 44),
(27, 51),
(27, 59),
(28, 52),
(28, 60),
(29, 33),
(29, 34),
(29, 56),
(30, 51),
(30, 52),
(30, 53),
(31, 47),
(32, 48),
(33, 45),
(34, 46),
(35, 36),
(35, 37),
(36, 38),
(37, 39),
(37, 49),
(38, 40),
(38, 50),
(39, 40),
(39, 51),
(40, 52),
(41, 47),
(42, 48),
(43, 49),
(44, 50),
(45, 46),
(45, 54),
(46, 55),
(47, 54),
(48, 55),
])
A = laplacian_fn(G)
try:
assert nx.algebraic_connectivity(G,
normalized=normalized,
tol=1e-12,
method=method) == pytest.approx(
sigma, abs=1e-7)
x = nx.fiedler_vector(G,
normalized=normalized,
tol=1e-12,
method=method)
check_eigenvector(A, sigma, x)
except nx.NetworkXError as err:
if err.args not in (
("Cholesky solver unavailable.", ),
("LU solver unavailable.", ),
):
raise
def test_fiedler_vector_tracemin_chol():
"""Test that "tracemin_chol" raises an exception."""
pytest.importorskip("scipy")
G = nx.barbell_graph(5, 4)
with pytest.raises(nx.NetworkXError):
nx.fiedler_vector(G, method="tracemin_chol")
def completed_graph(inchikey):
#graphs generated using PIBAS dataset, UniChem and Bio2RDF
G6 = nx.Graph()
G8 = nx.Graph()
#we start from PIBAS local ontology and for a given InChiKey we found compound acronym
sparql = SPARQLWrapper("http://cpctas-lcmb.pmf.kg.ac.rs:2020/sparql")
url = 'https://www.ebi.ac.uk/unichem/rest/inchikey/'+inchikey
#print url
j=0
storage = StringIO()
c = pycurl.Curl()
c.setopt(c.URL, url)
c.setopt(c.WRITEFUNCTION, storage.write)
c.perform()
c.close()
content = storage.getvalue()
unichem_content = json.loads(content)
for rs in unichem_content:
src_compound_id= rs['src_compound_id']
url = 'https://www.ebi.ac.uk/unichem/rest/sources/'+rs['src_id']
storage = StringIO()
c = pycurl.Curl()
c.setopt(c.URL, url)
c.setopt(c.WRITEFUNCTION, storage.write)
c.perform()
c.close()
content = storage.getvalue()
unichem_src_name = json.loads(content)
for rs in unichem_src_name:
name=rs['name']
#print name
G6.add_node(j,name_label=name+'/'+src_compound_id)
j=j+1
bio2rdf_dataset=['bindingdb','pubchem','pharmgkb','chebi','kegg_ligand','pdb','drugbank','chembl','pibas','ndc']
num1=G6.number_of_nodes()
nodes1=G6.nodes()
for x in range(0, num1):
if((G6.node[x]['name_label']).split('/')[0] in bio2rdf_dataset):
sparql = SPARQLWrapper("http://cpctas-lcmb.pmf.kg.ac.rs:2020/sparql")
if((G6.node[x]['name_label']).split('/')[0]=='kegg_ligand'):
sparql.setQuery(
"""
PREFIX bindingdb: <http://bio2rdf.org/bindingdb:>
PREFIX pubchem: <http://bio2rdf.org/pubchem:>
PREFIX pharmgkb: <http://bio2rdf.org/pharmgkb:>
PREFIX chebi: <http://bio2rdf.org/chebi:>
PREFIX kegg_ligand: <http://bio2rdf.org/kegg:>
PREFIX pdb: <http://bio2rdf.org/pdb:>
PREFIX drugbank: <http://bio2rdf.org/drugbank:>
PREFIX chembl: <http://bio2rdf.org/chembl:>
PREFIX ndc: <http://bio2rdf.org/ndc:>
select ?p ?o
WHERE
{
SERVICE SILENT<http://kegg.bio2rdf.org/sparql> {
OPTIONAL{
%s:%s ?p ?o.
FILTER(CONTAINS(str(?p),"http://bio2rdf.org/kegg_vocabulary:x-drugbank") || CONTAINS(str(?p),"http://bio2rdf.org/kegg_vocabulary:x-pubchem.compound") || CONTAINS(str(?p),"http://bio2rdf.org/kegg_vocabulary:x-kegg") || CONTAINS(str(?p),"http://bio2rdf.org/kegg_vocabulary:x-chembl") || CONTAINS(str(?p),"http://bio2rdf.org/kegg_vocabulary:x-chebi") || CONTAINS(str(?p),"http://bio2rdf.org/kegg_vocabulary:same-as")).
}
}
}
""" % (((G6.node[x]['name_label']).split('/')[0]),((G6.node[x]['name_label']).split('/')[1])))
else:
sparql.setQuery(
"""
PREFIX bindingdb: <http://bio2rdf.org/bindingdb:>
PREFIX pubchem: <http://bio2rdf.org/pubchem:>
PREFIX pharmgkb: <http://bio2rdf.org/pharmgkb:>
PREFIX chebi: <http://bio2rdf.org/chebi:>
PREFIX kegg_ligand: <http://bio2rdf.org/kegg:>
PREFIX pdb: <http://bio2rdf.org/pdb:>
PREFIX drugbank: <http://bio2rdf.org/drugbank:>
PREFIX chembl: <http://bio2rdf.org/chembl:>
PREFIX ndc: <http://bio2rdf.org/ndc:>
select ?p ?o
WHERE
{
SERVICE SILENT<http://%s.bio2rdf.org/sparql> {
OPTIONAL{
%s:%s ?p ?o.
FILTER(CONTAINS(str(?p),"http://bio2rdf.org/%s_vocabulary:x-drugbank") || CONTAINS(str(?p),"http://bio2rdf.org/%s_vocabulary:x-pubchem.compound") || CONTAINS(str(?p),"http://bio2rdf.org/%s_vocabulary:x-kegg") || CONTAINS(str(?p),"http://bio2rdf.org/%s_vocabulary:x-chembl") || CONTAINS(str(?p),"http://bio2rdf.org/%s_vocabulary:x-chebi") || CONTAINS(str(?p),"http://bio2rdf.org/%s_vocabulary:x-ndc") || CONTAINS(str(?p),"http://bio2rdf.org/%s_vocabulary:same-as")).
}
}
}
""" % (((G6.node[x]['name_label']).split('/')[0]),((G6.node[x]['name_label']).split('/')[0]),((G6.node[x]['name_label']).split('/')[1]),((G6.node[x]['name_label']).split('/')[0]),((G6.node[x]['name_label']).split('/')[0]),((G6.node[x]['name_label']).split('/')[0]),((G6.node[x]['name_label']).split('/')[0]),((G6.node[x]['name_label']).split('/')[0]),((G6.node[x]['name_label']).split('/')[0]),((G6.node[x]['name_label']).split('/')[0])))
sparql.setReturnFormat(JSON)
final_results1 = sparql.query().convert()
try:
v=G6.number_of_nodes()
for result1 in final_results1["results"]["bindings"]:
if(result1["o"]["value"]!=""):
node_for_add=result1["o"]["value"]
node_of_second_level=node_for_add.split("/")[-1]
if(node_of_second_level.split(':')[0]=='kegg'):
node_for_add='kegg_ligand/'+node_of_second_level.split(':')[1]
else:
node_for_add=node_of_second_level.split(':')[0]+'/'+node_of_second_level.split(':')[1]
#print node_for_add
compare_node=[]
for x in range(0,G6.number_of_nodes()):
compare_node.append(str((G6.node[x]['name_label']).split('/')[0])+'/'+str((G6.node[x]['name_label']).split('/')[1]))
if(node_for_add not in compare_node):
G6.add_node(v,name_label=node_for_add,predicate=result1["p"]["value"])
v=v+1
#print v
except:
continue
nodes=G6.nodes()
#print nodes
edges = combinations(nodes, 2)
G6.add_nodes_from(nodes)
G6.add_edges_from(edges)
num1=G6.number_of_nodes()
nodes1=G6.nodes()
left_graph_for_remove=[]
for x in range(0, num1):
if(((G6.node[x]['name_label']).split('/')[0] not in bio2rdf_dataset)):
G6.remove_node(x)
nodes1=G6.nodes()
#print nodes1
custom_labels1={}
for x in nodes1:
custom_labels1[x] = str(x)+':'+G6.node[x]['name_label']
#create and draw graph G6
pos=nx.circular_layout(G6,dim=2, scale=100)
plt.clf()
nx.draw(G6, labels=custom_labels1, with_labels=True)
plt.savefig('/var/www/specint.org/public_html/specint/img/completed_graph_bio2rdf_'+inchikey+'.png')
#******************Using Chem2Bio2RDF***********************************************************************************
sparql = SPARQLWrapper("http://cpctas-lcmb.pmf.kg.ac.rs:2020/sparql")
G7 = nx.Graph()
index_for_new_graph=max(G6.nodes())
url = 'https://www.ebi.ac.uk/unichem/rest/inchikey/'+inchikey
#print url
j=index_for_new_graph+1
storage = StringIO()
c = pycurl.Curl()
c.setopt(c.URL, url)
c.setopt(c.WRITEFUNCTION, storage.write)
c.perform()
c.close()
content = storage.getvalue()
unichem_content = json.loads(content)
for rs in unichem_content:
src_compound_id= rs['src_compound_id']
url = 'https://www.ebi.ac.uk/unichem/rest/sources/'+rs['src_id']
storage = StringIO()
c = pycurl.Curl()
c.setopt(c.URL, url)
c.setopt(c.WRITEFUNCTION, storage.write)
c.perform()
c.close()
content = storage.getvalue()
unichem_src_name = json.loads(content)
for rs in unichem_src_name:
name=rs['name']
G7.add_node(j,name_label=name+'/'+src_compound_id)
j=j+1
chem2bio2rdf_dataset=['bindingdb','pubchem','chebi','kegg_ligand','kegg','pdb','drugbank','chembl','uniprot','matador','ctd','dcdb','hgnc','pharmgkb','hprd']
num1=G7.number_of_nodes()
nodes1=G7.nodes()
for x in range(index_for_new_graph+1,index_for_new_graph+num1):
if(((G7.node[x]['name_label']).split('/')[0] in bio2rdf_dataset) and ("chembl" not in (G7.node[x]['name_label']).split('/')[0])):
sparql = SPARQLWrapper("http://cpctas-lcmb.pmf.kg.ac.rs:2020/sparql")
if((G7.node[x]['name_label']).split('/')[0]=='kegg_ligand'):
sparql.setQuery(
"""
PREFIX bindingdb: <http://chem2bio2rdf.org/bindingdb/resource/>
PREFIX pubchem: <http://chem2bio2rdf.org/pubchem/resource/>
PREFIX uniprot: <http://chem2bio2rdf.org/uniprot/resource/>
PREFIX chebi: <http://chem2bio2rdf.org/chebi/resource/chebi/CHEBI~>
PREFIX kegg_ligand: <http://chem2bio2rdf.org/kegg/resource/kegg_ligand/>
PREFIX pdb: <http://chem2bio2rdf.org/pdb/resource/pdb_ligand/>
PREFIX drugbank: <http://chem2bio2rdf.org/drugbank/resource/>
PREFIX matador: <http://chem2bio2rdf.org/matador/resource/>
PREFIX chembl: <http://chem2bio2rdf.org/chembl/resource/>
PREFIX uniprot: <http://chem2bio2rdf.org/uniprot/resource/>
PREFIX db: <http://chem2bio2rdf.org/kegg/resource/>
select ?o
WHERE
{
SERVICE SILENT<http://cheminfov.informatics.indiana.edu:8080/kegg/sparql> {
OPTIONAL{
%s:%s db:CID ?o.
}
}
}
""" % (((G7.node[x]['name_label']).split('/')[0]),((G7.node[x]['name_label']).split('/')[1])))
elif((G7.node[x]['name_label']).split('/')[0]=='drugbank'):
sparql.setQuery(
"""
PREFIX db:<http://chem2bio2rdf.org/drugbank/resource/>
PREFIX drugbank:<http://chem2bio2rdf.org/drugbank/resource/drugbank_drug/>
select ?o
WHERE
{
SERVICE SILENT<http://147.91.203.161:8890/sparql>{
drugbank:%s db:CID ?o.
}
}
""" % (G7.node[x]['name_label']).split('/')[1])
else:
sparql.setQuery(
"""
PREFIX bindingdb: <http://bio2rdf.org/bindingdb:>
PREFIX pubchem: <http://bio2rdf.org/pubchem:>
PREFIX pharmgkb: <http://bio2rdf.org/pharmgkb:>
PREFIX chebi: <http://bio2rdf.org/chebi:>
PREFIX kegg_ligand: <http://bio2rdf.org/kegg:>
PREFIX pdb: <http://bio2rdf.org/pdb:>
PREFIX drugbank: <http://bio2rdf.org/drugbank:>
PREFIX chembl: <http://bio2rdf.org/chembl:>
PREFIX ndc: <http://bio2rdf.org/ndc:>
PREFIX db: <http://chem2bio2rdf.org/%s/resource/>
select ?o
WHERE
{
SERVICE SILENT<http://cheminfov.informatics.indiana.edu:8080/%s/sparql> {
OPTIONAL{
%s:%s db:CID ?o.
}
}
}
""" % (((G7.node[x]['name_label']).split('/')[0]),((G7.node[x]['name_label']).split('/')[0]),((G7.node[x]['name_label']).split('/')[0]),((G7.node[x]['name_label']).split('/')[1])))
sparql.setReturnFormat(JSON)
final_results1 = sparql.query().convert()
try:
v=G7.number_of_nodes()
for result1 in final_results1["results"]["bindings"]:
if(result1["o"]["value"]!=""):
node_for_add=result1["o"]["value"]
node_of_second_level=node_for_add.split("/")[-1]
if(node_of_second_level.split(':')[0]=='kegg'):
node_for_add='kegg_ligand/'+node_of_second_level.split(':')[1]
else:
node_for_add=node_of_second_level.split(':')[0]+'/'+node_of_second_level.split(':')[1]
#print node_for_add
compare_node=[]
for x in range(index_for_new_graph+1,index_for_new_graph+num1):
compare_node.append(str((G7.node[x]['name_label']).split('/')[0])+'/'+str((G7.node[x]['name_label']).split('/')[1]))
if(node_for_add not in compare_node):
G7.add_node(v,name_label=node_for_add,predicate=result1["p"]["value"])
v=v+1
#print v
except:
continue
nodes=G7.nodes()
#print nodes
edges = combinations(nodes, 2)
G7.add_nodes_from(nodes)
G7.add_edges_from(edges)
num1=G7.number_of_nodes()
nodes1=G7.nodes()
left_graph_for_remove=[]
for x in nodes1:
if(((G7.node[x]['name_label']).split('/')[0] not in chem2bio2rdf_dataset)):
G7.remove_node(x)
nodes1=G7.nodes()
custom_labels1={}
for x in nodes1:
custom_labels1[x] = str(x)+':'+G7.node[x]['name_label']
#create and draw graph G7
pos=nx.circular_layout(G7,dim=2, scale=100)
plt.clf()
nx.draw(G7, labels=custom_labels1, with_labels=True)
plt.savefig('/var/www/specint.org/public_html/specint/img/completed_graph_chem2bio2rdf_'+inchikey+'.png')
#*************Join grpahs*************************
G10=nx.union(G6,G7)
nodes1=G10.nodes()
custom_labels1={}
for x in nodes1:
custom_labels1[x] = str(x)+':'+G10.node[x]['name_label']
#create and draw graph G10
pos=nx.circular_layout(G10,dim=2, scale=300)
plt.clf()
nx.draw(G10, labels=custom_labels1, with_labels=True)
plt.savefig('/var/www/specint.org/public_html/specint/img/completed_graph_'+inchikey+'.eps',format='eps', dpi=300)
plt.savefig('/var/www/specint.org/public_html/specint/img/completed_graph_'+inchikey+'.png')
#************************Removing node************************
nodes_for_connection=[]
nodes_value_for_connection=[]
values_for_connected_nodes=['pubchem']
#for x in values_for_connected_nodes:
#values_for_connected_nodes.remove(x)
#print values_for_connected_nodes
for x in values_for_connected_nodes:
#connection_node=random.choice(values_for_connected_nodes)
connection_node=x
#print connection_node
nodes5=G10.nodes()
for x in nodes5:
if((G10.node[x]['name_label']).split('/')[0]==connection_node):
nodes_for_connection.append(x)
nodes_value_for_connection.append((G10.node[x]['name_label']).split('/')[1])
#print nodes_for_connection
if(len(nodes_for_connection)>=2):
my_array_for_node_connected=[]
for x in range(0,len(nodes_value_for_connection)-1):
for y in range(x+1,len(nodes_value_for_connection)):
if(nodes_value_for_connection[x]==nodes_value_for_connection[y]):
my_array_for_node_connected.append(nodes_for_connection[x])
my_array_for_node_connected.append(nodes_for_connection[y])
#print my_array_for_node_connected
#print max(my_array_for_node_connected)
#print min(my_array_for_node_connected)
G10.remove_node(max(my_array_for_node_connected))
for_delete=G10.nodes()
#print for_delete
position=(G10.nodes()).index(min(my_array_for_node_connected))
#print position
for x in for_delete:
if((x>min(my_array_for_node_connected)) and (x not in G6.nodes())):
G10.add_edge(min(my_array_for_node_connected),x)
nodes1=G10.nodes()
custom_labels1={}
for x in nodes1:
custom_labels1[x] = str(x)+':'+G10.node[x]['name_label']
#create and draw graph G10
pos=nx.circular_layout(G10,dim=2, scale=300)
plt.clf()
nx.draw(G10, labels=custom_labels1, with_labels=True)
plt.savefig('/var/www/specint.org/public_html/specint/img/completed_graph_'+inchikey+'.eps',format='eps', dpi=300)
plt.savefig('/var/www/specint.org/public_html/specint/img/completed_graph_'+inchikey+'.png')
#H = nx.Graph()
#H.add_nodes_from(G10.nodes())
#H.add_edges_from(G10.edges())
image='myimage_for_completed_graph.png'
fv=nx.fiedler_vector(G10,method='lobpcg')
create_python_file(G10.nodes(),G10.edges(), inchikey)
return {'fv':fv, 'connection_node':connection_node}
break
else:
#return completed_graph(inchikey)
#continue
return {'fv':'Undirected graph is not connected! Please, try again!'}
#completed_graph("IHUNBGSDBOWDMA-AQFIFDHZSA-N")
def approx_min_conductance_partitioning(g: LightMultiGraph, max_k=1):
"""
Approximate minimum conductance partinioning. I'm using the median method as referenced here:
http://www.ieor.berkeley.edu/~goldberg/pubs/krishnan-recsys-final2.pdf
:param g: graph to recursively partition
:param max_k: upper bound of number of nodes allowed in the leaves
:return: a dendrogram
"""
lvl = []
node_list = list(g.nodes())
if len(node_list) <= max_k:
assert len(node_list) > 0
return node_list
if not nx.is_connected(g):
for p in nx.connected_component_subgraphs(g):
lvl.append(approx_min_conductance_partitioning(p, max_k))
assert len(lvl) > 0
return lvl
assert nx.is_connected(g), "g is not connected in cond"
fiedler_vector = nx.fiedler_vector(g, method='lanczos')
p1, p2 = set(), set()
fiedler_dict = {}
for idx, n in enumerate(fiedler_vector):
fiedler_dict[idx] = n
fiedler_vector = [
(k, fiedler_dict[k])
for k in sorted(fiedler_dict, key=fiedler_dict.get, reverse=True)
]
half_idx = len(fiedler_vector) // 2 # floor division
for idx, _ in fiedler_vector:
if half_idx > 0:
p1.add(node_list[idx])
else:
p2.add(node_list[idx])
half_idx -= 1 # decrement so halfway through it crosses 0 and puts into p2
sg1 = g.subgraph(p1)
sg2 = g.subgraph(p2)
iter_count = 0
while not (nx.is_connected(sg1) and nx.is_connected(sg2)):
sg1 = g.subgraph(p1)
sg2 = g.subgraph(p2)
# Hack to check and fix non connected subgraphs
if not nx.is_connected(sg1):
for sg in sorted(nx.connected_component_subgraphs(sg1),
key=len,
reverse=True)[1:]:
p2.update(sg.nodes())
for n in sg.nodes():
p1.remove(n)
sg2 = g.subgraph(p2) # updating sg2 since p2 has changed
if not nx.is_connected(sg2):
for sg in sorted(nx.connected_component_subgraphs(sg2),
key=len,
reverse=True)[1:]:
p1.update(sg.nodes())
for n in sg.nodes():
p2.remove(n)
iter_count += 1
if iter_count > 2:
print('it took {} iterations to stabilize'.format(iter_count))
assert nx.is_connected(sg1) and nx.is_connected(
sg2), "subgraphs are not connected in cond"
lvl.append(approx_min_conductance_partitioning(sg1, max_k))
lvl.append(approx_min_conductance_partitioning(sg2, max_k))
assert (len(lvl) > 0)
return lvl
def sccf_helper(seed_num, graph=None, graph_json_filename=None, graph_json_str=None):
# parse the graph
G = None
if graph is not None:
G = graph
elif graph_json_filename is not None:
G = util.load_graph(graph_json_filename=graph_json_filename)
else:
G = util.load_graph(graph_json_str=graph_json_str)
# initialize queue for subgraphs
# try to get about 2 nodes in each cluster
node_per_cluster = 2
max_depth = int(math.ceil(np.log2(seed_num / node_per_cluster))) + 1
cluster_queue = Queue.Queue()
cluster_queue.put(G)
# divide graph into 2**max_depth clusters
while (cluster_queue.qsize() < 2**max_depth ):
G_curr = cluster_queue.get()
# work only on the largest connected component
G_curr_c = max(nx.connected_component_subgraphs(G_curr), key=len)
if (G_curr_c.size() < 2 * node_per_cluster):
# put it back if cluster is too small
cluster_queue.put(G_curr_c)
continue
# get fiedler vector
fiedler_vector = nx.fiedler_vector(G_curr_c, normalized=True, tol=1e-01)
node_list_sub_1 = []
node_list_sub_2 = []
node_list = G_curr_c.nodes()
# split positive and negative terms in fielder vector
for i in range(len(fiedler_vector)):
if (fiedler_vector[i] >= 0):
node_list_sub_1.append(node_list[i])
else:
node_list_sub_2.append(node_list[i])
# seperate the graph into two subgraphs
if (len(node_list_sub_1) >= node_per_cluster):
# ignore clusters too small
G_sub_1 = G_curr_c.subgraph(node_list_sub_1)
cluster_queue.put(G_sub_1)
if (len(node_list_sub_2) >= node_per_cluster):
# ignore clusters too small
G_sub_2 = G_curr_c.subgraph(node_list_sub_2)
cluster_queue.put(G_sub_2)
# get node_per_cluster highest degree nodes from each cluster
candidate_nodes = []
candidate_neighbors = {}
while not (cluster_queue.empty()):
G_curr = cluster_queue.get()
# measure used to pick node with in clusters
degree_dict = nx.closeness_centrality(G_curr)
node_keys = sorted(degree_dict, key=degree_dict.get,
reverse=True)[:node_per_cluster]
for i in node_keys:
# append i and a neighbor of i
if (i not in candidate_nodes):
candidate_nodes.append(i)
candidate_neighbors[i] = list(nx.all_neighbors(G, i))
# return candidate nodes and neighbors
return candidate_nodes, candidate_neighbors
ursi = graph_filename[4:13]
ursis.append(ursi)
try:
y[i, :] = np.hstack(
(df1.loc[ursi, 'CCI'], df1.loc[ursi, :].iloc[4:].as_matrix()))
graph_data = np.load(root_dir + graphtype + '/' + graph_filename)
# print('graph shape:', graph_data.shape)
g = nx.Graph(graph_data)
laplacian = nx.laplacian_matrix(g)
spectrum = nx.laplacian_spectrum(g)
connectivity = nx.fiedler_vector(g)
communities = nx.k_clique_communities(g, 5)
print('Laplacian shape:', laplacian.shape)
print('Spectrum shape:', spectrum.shape)
print('Connectivity:', connectivity)
print('Communities:', communities.shape)
# feature extraction
rich_coeff_at_degree = rich_club_coefficient(g, normalized=False)
rich_keys = list(rich_coeff_at_degree.keys())
rich_vals = list(rich_coeff_at_degree.values())
rich_hist, bin_edges = np.histogram(rich_vals, n_roi // 10)
def calcularVetorFiedlerNetworkx(grafo):
return nx.fiedler_vector(grafo)
#!/usr/bin/env python
import networkx as nx
import numpy as np
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
G = nx.Graph()
G.add_node(0)
G.add_node(7)
G.add_node(9)
G.add_node(10)
G.add_node(19)
G.add_edge(0,9)
G.add_edge(0,7)
G.add_edge(7,9)
G.add_edge(7,10)
G.add_edge(7,19)
G.add_edge(10,19)
print G.nodes()
print nx.fiedler_vector(G,method='lobpcg')
pos=nx.circular_layout(G,dim=50, scale=100)
plt.clf()
nx.draw(G,with_labels=True)
plt.savefig('C:/Users/Branko/Desktop/ZKZFPRUSWCYSGT-UHFFFAOYSA-N_unoriented.png')
def spectrum_cluster(seed_num, graph_json_filename=None, graph_json_str=None):
"""
Identifies clusters in the network using laplacian spectrum, and loops over
each cluster to pick the node with largest degree until seed_num nodes were
chosen.
Parameters:
seed_num: Number of nodes to choose.
graph_json_filename: Filename where the adjacency list lives as JSON.
graph_json_str: Graph as an adjacency list string in JSON.
Return: List of the chosen nodes.
"""
# parse the graph
G = None
if graph_json_str is None:
G = util.load_graph(graph_json_filename=graph_json_filename)
else:
G = util.load_graph(graph_json_str=graph_json_str)
# initialize queue for subgraphs
# try to get about 2 nodes in each cluster
node_per_cluster = 2
max_depth = int(math.ceil(np.log2(seed_num / node_per_cluster))) + 1
cluster_queue = Queue.Queue()
cluster_queue.put(G)
# divide graph into 2**max_depth clusters
while (cluster_queue.qsize() < 2**max_depth ):
G_curr = cluster_queue.get()
# work only on the largest connected component
G_curr_c = max(nx.connected_component_subgraphs(G_curr), key=len)
if (G_curr_c.size() < 2 * node_per_cluster):
# put it back if cluster is too small
cluster_queue.put(G_curr_c)
continue
# get fiedler vector
fiedler_vector = nx.fiedler_vector(G_curr_c, normalized=True, tol=1e-04)
node_list_sub_1 = []
node_list_sub_2 = []
node_list = G_curr_c.nodes()
# split positive and negative terms in fielder vector
for i in range(len(fiedler_vector)):
if (fiedler_vector[i] >= 0):
node_list_sub_1.append(node_list[i])
else:
node_list_sub_2.append(node_list[i])
# seperate the graph into two subgraphs
if (len(node_list_sub_1) >= node_per_cluster):
# ignore clusters too small
G_sub_1 = G_curr_c.subgraph(node_list_sub_1)
cluster_queue.put(G_sub_1)
if (len(node_list_sub_2) >= node_per_cluster):
# ignore clusters too small
G_sub_2 = G_curr_c.subgraph(node_list_sub_2)
cluster_queue.put(G_sub_2)
# get node_per_cluster highest degree nodes from each cluster
candidate_nodes = []
while not (cluster_queue.empty()):
G_curr = cluster_queue.get()
# measure used to pick node with in clusters
degree_dict = nx.degree(G_curr)
node_keys = sorted(degree_dict, key=degree_dict.get,
reverse=True)[:node_per_cluster]
for i in node_keys:
candidate_nodes.append(i)
# randomly pick seed_num nodes from candidate_nodes
rtn = list(np.random.choice(candidate_nodes, replace=False, size=seed_num))
return rtn