def _run(self):
"""
Run the experiment.
"""
logging.info("Loading Network...")
self.ppi_networkx, self.ppi_adj, self.protein_to_node = load_network(
self.params.ppi_network)
logging.info("Loading PPI Matrices...")
self.ppi_matrices = load_ppi_matrices(self.params.ppi_matrices)
logging.info("Sorting Nodes by Degree...")
self.nodes_sorted_by_deg, self.nodes_ranked_by_deg = sort_by_degree(
self.ppi_networkx)
logging.info("Running Experiment...")
self.results = []
if self.params.n_processes > 1:
with tqdm(total=len(self.diseases)) as t:
p = Pool(self.params.n_processes)
for results in p.imap(process_disease_wrapper,
self.diseases.values()):
self.results.append(results)
t.update()
else:
with tqdm(total=len(self.diseases)) as t:
for disease in self.diseases.values():
results = self.process_disease(disease)
self.results.append(results)
t.update()
self.results = pd.DataFrame(self.results)
def _run(self):
"""
Run the experiment.
"""
logging.info("Loading Network...")
self.ppi_networkx, self.ppi_adj, self.protein_to_node = load_network(
self.params.ppi_network)
self.node_to_protein = {
node: protein
for protein, node in self.protein_to_node.items()
}
logging.info("Loading PPI Matrices...")
self.ppi_matrices = load_ppi_matrices(self.params.ppi_matrices)
logging.info("Building Degree Buckets...")
self.degree_to_bucket = build_degree_buckets(
self.ppi_networkx, min_len=self.params.min_bucket_len)
for degree, bucket in self.degree_to_bucket.items():
print("Degree: {}, Size: {}".format(degree, len(bucket)))
logging.info("Running Experiment...")
self.results = []
self.indices = []
if self.params.n_processes > 1:
with tqdm(total=len(self.diseases)) as t:
p = Pool(self.params.n_processes)
for indices, results in p.imap(process_disease_wrapper,
self.diseases.values()):
self.indices.extend(indices)
self.results.extend(results)
t.update()
else:
with tqdm(total=len(self.diseases)) as t:
for disease in self.diseases.values():
indices, results = self.process_disease(disease)
self.indices.extend(indices)
self.results.extend(results)
t.update()
index = pd.MultiIndex.from_tuples(self.indices,
names=['disease', 'protein'])
self.results = pd.DataFrame(self.results, index=index)
def __init__(self, dir):
super(CodiseaseProbExp, self).__init__(dir)
# Set the logger
set_logger(os.path.join(self.dir, 'experiment.log'),
level=logging.INFO,
console=True)
# Log title
logging.info("Co-disease probability in the PPI Network")
logging.info("Sabri Eyuboglu -- SNAP Group")
logging.info("======================================")
logging.info("Loading Network...")
self.ppi_networkx, self.ppi_adj, self.protein_to_node = load_network(
self.params.ppi_network)
logging.info("Loading Disease Associations...")
self.diseases = load_diseases(self.params.diseases_path,
self.params.disease_subset)
# unpack params
self.ppi_matrices = {
name: np.load(file)
for name, file in self.params.ppi_matrices.items()
}
self.top_k = self.params.top_k
self.n_buckets = self.params.n_buckets
self.window_length = self.params.window_length
self.smooth = self.params.smooth
self.plots = self.params.plots
if hasattr(self.params, 'codisease_matrix'):
logging.info("Loading Codisease Matrix...")
self.codisease_matrix = np.load(self.params.codisease_matrix)
else:
logging.info("Building Codisease Matrix...")
self.codisease_matrix = self.build_codisease_matrix()
params = Params(json_path)
params.update(json_path)
# Set the logger
set_logger(os.path.join(args.experiment_dir, 'experiment.log'),
level=logging.INFO,
console=True)
# Log Title
logging.info("Complementarity Sharing in Disease Pathways")
logging.info("Sabri Eyuboglu -- SNAP Group")
logging.info("======================================")
# Load data from params file
logging.info("Loading PPI Network...")
_, _, protein_to_node = load_network(params.ppi_network)
logging.info("Loading Disease Associations...")
diseases_dict = load_diseases(params.diseases_path, params.disease_subset)
logging.info("Loading PPI Matrices...")
ppi_matrices = {}
for name, path in params.ppi_matrices.items():
ppi_matrices[name] = np.load(path)
#Run Experiment
logging.info("Running Experiment...")
#Compute mean and standard deviation
means = {}
stds = {}
# Set the logger
set_logger(os.path.join(args.prediction_dir, 'experiment.log'),
level=logging.INFO,
console=True)
# Log Title
logging.info("Disease protein Prediction")
logging.info("Sabri Eyuboglu -- SNAP Group -- Stanford University")
logging.info("======================================")
# Load Data
logging.info("Loading Diseases...")
diseases = load_diseases(params.diseases_path, params.disease_subset)
logging.info("Loading PPI Network...")
ppi_networkx, ppi_network_adj, protein_to_node = load_network(
params.ppi_network)
node_to_protein = {
node: protein
for protein, node in protein_to_node.items()
}
if (params.method == "ppi_matrix"):
logging.info("Loading PPI Matrix...")
ppi_matrix = np.load(params.ppi_matrix)
elif (params.method == 'gcn'):
gcn_method = GCN(params, ppi_network_adj)
# Run Predictions
if MULTIPROCESS:
p = Pool(N_PROCESSES)
def __init__(self, dir):
""" Initialize the disease protein prediction experiment
Args:
dir (string) The directory where the experiment should be run
"""
super(DPPExperiment, self).__init__(dir)
# Set the logger
set_logger(os.path.join(args.dir, 'experiment.log'), level=logging.INFO, console=True)
# Log Title
logging.info("Disease Protein Prediction in the PPI Network")
logging.info("Sabri Eyuboglu -- SNAP Group")
logging.info("======================================")
# Load data from params file
logging.info("Loading PPI Network...")
self.ppi_networkx, self.ppi_network_adj, self.protein_to_node = load_network(self.params.ppi_network)
self.node_to_protein = {node: protein for protein, node in self.protein_to_node.items()}
logging.info("Loading Disease Associations...")
self.diseases_dict = load_diseases(self.params.diseases_path, self.params.disease_subset, ['none'])
# Load method specific data
# TODO: Build class for each method
if(self.params.method == "ppi_matrix"):
logging.info("Loading PPI Matrix...")
self.ppi_matrix = np.load(self.params.ppi_matrix)
# normalize columns of ppi_matrix
if(self.params.normalize):
if hasattr(self.params, "norm_type"):
if self.params.norm_type == "frac":
self.ppi_matrix = self.ppi_matrix / np.sum(self.ppi_matrix,
axis=0)
elif self.params.norm_type == "zscore":
self.ppi_matrix = (self.ppi_matrix - np.mean(self.ppi_matrix, axis=0)) / np.std(self.ppi_matrix, axis=0)
else:
self.ppi_matrix = (self.ppi_matrix - np.mean(self.ppi_matrix, axis=0)) / np.std(self.ppi_matrix, axis=0)
# zero out the diagonal
np.fill_diagonal(self.ppi_matrix, 0)
elif (self.params.method == 'lr'):
logging.info("Loading Feature Matrices...")
self.feature_matrices = []
for features_filename in self.params.features:
self.feature_matrices.append(
build_embedding_feature_matrix(self.protein_to_node,
features_filename))
elif (self.params.method == 'l2_rw'):
self.method = L2RandomWalk(self.params)
elif (self.params.method == 'pathway_expansion'):
self.method = PathwayExpansion(self.params,
self.ppi_networkx,
self.ppi_network_adj)
elif (self.params.method == "learned_cn"):
self.method = LearnedCN(self.dir,
self.params,
self.ppi_network_adj,
self.diseases_dict,
self.protein_to_node)
elif (self.params.method == 'gcn'):
self.method = GCN(self.params, self.ppi_network_adj)