def __init__(self, dir, params):
"""
Constructor
Args:
dir (string) directory of the experiment to be run
"""
super().__init__(dir, params)
# set the logger
set_logger(os.path.join(self.dir, 'experiment.log'),
level=logging.INFO, console=True)
logging.info("Loading disease associations...")
self.diseases_dict = load_diseases(self.params["associations_path"],
self.params["disease_subset"],
exclude_splits=['none'])
logging.info("Loading network...")
self.network = Network(self.params["ppi_network"])
self.degrees = np.array(list(dict(self.network.nx.degree()).values()))
logging.info("Loading weights...")
with open(os.path.join(params["model_path"], "models", "models.tar"), "rb") as f:
split_to_model = pickle.load(f)
self.ci_weights = ci_weights = np.mean([model['ci_weight'][0, 0].numpy()
for model in split_to_model.values()], axis=0)
self.ci_weights_norm = self.ci_weights / np.sqrt(self.degrees)
logging.info("Loading drugs...")
self.drug_to_targets = load_drug_targets(params["drug_targets_path"])
def __init__(self, dir, params):
""" Initialize the disease protein prediction experiment
Args:
dir (string) The directory where the experiment should be run
"""
super().__init__(dir, params)
# set the logger
set_logger(os.path.join(dir, 'experiment.log'),
level=logging.INFO,
console=True)
# log Title
logging.info("Node set expansion evaluation")
logging.info(
"Sabri Eyuboglu, Marinka Zitnik and Jure Leskovec -- SNAP Group")
logging.info("======================================")
# load data from params file
logging.info("Loading Network...")
self.network = Network(self.params["ppi_network"],
remove_nodes=self.params.get("remove_nodes", 0),
remove_edges=self.params.get("remove_edges", 0))
logging.info("Loading Associations...")
self.diseases_dict = load_diseases(self.params["associations_path"],
self.params["disease_subset"],
exclude_splits=['none'])
# load method
self.params["method_params"]["dir"] = dir
self.method = globals()[self.params["method_class"]](
self.network, self.diseases_dict, self.params["method_params"])
def __init__(self, dir, params):
"""
"""
super().__init__(dir, params)
set_logger(os.path.join(self.dir, 'experiment.log'),
level=logging.INFO, console=True)
logging.info("Loading disease associations...")
self.diseases_dict = load_diseases(self.params["associations_path"],
self.params["disease_subset"],
exclude_splits=['none'])
logging.info("Loading network...")
self.network = Network(self.params["ppi_network"])
self.degrees = np.array(list(dict(self.network.nx.degree()).values()))
logging.info("Loading weights...")
with open(os.path.join(params["model_path"], "models", "models.tar"), "rb") as f:
split_to_model = pickle.load(f)
self.ci_weights = ci_weights = np.mean([model['ci_weight'][0, 0].numpy()
for model in split_to_model.values()], axis=0)
self.ci_weights_norm = self.ci_weights / np.sqrt(self.degrees)
logging.info("Loading enrichment study...")
geneid2go = read_ncbi_gene2go("data/go/gene2go.txt", taxids=[9606])
obodag = GODag("data/go/go-basic.obo")
self.go_study = GOEnrichmentStudy(self.network.get_names(),
geneid2go,
obodag,
propagate_counts = True,
alpha = 0.05,
methods = ['fdr_bh'])
def __init__(self, dir, params):
"""
Constructor
Args:
dir (string) directory of the experiment to be run
"""
super().__init__(dir, params)
# Set the logger
set_logger(os.path.join(self.dir, 'experiment.log'), level=logging.INFO, console=True)
# Log title
logging.info("Disease Protein Prediction")
logging.info("Sabri Eyuboglu -- SNAP Group")
logging.info("======================================")
logging.info("Loading Disease Associations...")
self.diseases_dict = load_diseases(self.params["associations_path"],
self.params["disease_subset"],
exclude_splits=['none'])
logging.info("Loading Network...")
self.network = Network(self.params["ppi_network"])
self.params["method_params"]["dir"] = dir
self.method = globals()[self.params["method_class"]](self.network,
self.diseases_dict,
self.params["method_params"])
def _load_data(self):
"""
"""
logging.info("Loading Disease Associations...")
self.diseases_dict = load_diseases(self.params["associations_path"],
exclude_splits=["none"])
print(len(self.diseases_dict))
logging.info("Loading Results...")
method_to_metrics = {}
for name, exp_dir in self.params["method_exp_dirs"].items():
metrics = pd.read_csv(os.path.join(exp_dir, "metrics.csv"),
index_col=0)
print(len(metrics))
method_to_metrics[name] = metrics
self.method_to_metrics = method_to_metrics
def _run(self):
"""
Run the experiment.
"""
logging.info("Loading network...")
network = Network(self.params["ppi_network"])
logging.info("Loading molecule associations...")
associations = {}
for association_path in self.params["association_paths"]:
dct = load_diseases(association_path)
associations.update(dct)
association_matrix, _ = build_disease_matrix(associations, network)
association_jaccard = compute_jaccard(association_matrix.T)
mi_matrix = mi_matrix = load_network_matrices(
{"mi": self.params["mi_dir"]}, network=network)["mi"]
mi_values = mi_matrix[np.triu_indices(mi_matrix.shape[0], k=1)]
adj_values = network.adj_matrix[np.triu_indices(
network.adj_matrix.shape[0], k=1)]
jaccard_values = association_jaccard[np.triu_indices(
association_jaccard.shape[0], k=1)]
k = adj_values.sum().astype(int)
statistic, pvalue = ttest_rel(
jaccard_values[np.argpartition(mi_values, -k)[-k:]],
jaccard_values[np.argpartition(adj_values, -k)[-k:]],
)
metrics = {
"test":
"ttest_rel",
"statistic":
statistic,
"pvalue":
pvalue,
"mi_mean":
jaccard_values[np.argpartition(mi_values, -k)[-k:]].mean(),
"adj_mean":
jaccard_values[np.argpartition(adj_values, -k)[-k:]].mean(),
}
with open(os.path.join(self.dir, "results.json"), "w") as f:
json.dump(metrics, f, indent=4)
def __init__(self, dir, params):
"""
Constructor
Args:
dir (string) directory of the experiment to be run
"""
super().__init__(dir, params)
# Set the logger
set_logger(os.path.join(self.dir, 'experiment.log'),
level=logging.INFO, console=True)
# Log title
logging.info("Disease Protein Prediction")
logging.info("Sabri Eyuboglu -- SNAP Group")
logging.info("======================================")
logging.info("Loading Disease Associations...")
self.diseases_dict = load_diseases(self.params["associations_path"],
self.params["disease_subset"],
exclude_splits=['none'])
logging.info("Loading Network...")
self.network = Network(self.params["ppi_network"])
logging.info("Loading enrichment study...")
obodag = GODag(self.params["go_path"])
geneid2go = read_ncbi_gene2go(self.params["gene_to_go_path"], taxids=[9606])
self.enrichment_study = GOEnrichmentStudy(self.network.get_names(),
geneid2go,
obodag,
log=None,
**self.params["enrichment_params"])
logging.info("Loading predictions...")
self.method_to_preds = {name: pd.read_csv(os.path.join(preds, "predictions.csv"),
index_col=0)
for name, preds in self.params["method_to_preds"].items()}
outputs_path = os.path.join(self.dir, "outputs.pkl")
if os.path.exists(outputs_path):
logging.info("Loading outputs...")
with open(outputs_path, 'rb') as f:
self.outputs = pickle.load(f)
else:
self.outputs = {}
def __init__(self, dir, params):
"""
Constructor
Args:
dir (string) directory of the experiment to be run
"""
super().__init__(dir, params)
# Set the logger
set_logger(os.path.join(self.dir, 'experiment.log'), level=logging.INFO, console=True)
# Log title
logging.info("Metric Significance of Diseases in the PPI Network")
logging.info("Sabri Eyuboglu -- SNAP Group")
logging.info("======================================")
logging.info("Loading Disease Associations...")
self.diseases = load_diseases(self.params["associations_path"],
self.params["disease_subset"],
exclude_splits=['none'])
def __init__(self, dir, params):
"""
Constructor
Args:
dir (string) directory of the experiment to be run
"""
super().__init__(dir, params)
# set the logger
set_logger(os.path.join(self.dir, 'experiment.log'),
level=logging.INFO, console=True)
logging.info("Loading disease associations...")
self.diseases_dict = load_diseases(self.params["associations_path"],
self.params["disease_subset"],
exclude_splits=['none'])
logging.info("Loading network...")
self.network = Network(self.params["ppi_network"])
self.degrees = np.array(list(dict(self.network.nx.degree()).values()))
def __init__(self, dir, params):
"""
Constructor
Args:
dir (string) directory of the experiment to be run
"""
super().__init__(dir, params)
# Set the logger
set_logger(os.path.join(self.dir, 'experiment.log'),
level=logging.INFO,
console=True)
# Log title
logging.info("Metric Significance of Diseases in the PPI Network")
logging.info("Sabri Eyuboglu -- SNAP Group")
logging.info("======================================")
logging.info("Loading Disease Associations...")
self.diseases = load_diseases(self.params["associations_path"],
self.params["disease_subset"],
exclude_splits=['none'])
logging.info("Loading Network...")
self.network = Network(self.params["ppi_network"])
logging.info("Loading Predictions...")
self.method_to_preds = {
name: pd.read_csv(os.path.join(preds, "predictions.csv"),
index_col=0)
for name, preds in self.params["method_to_preds"].items()
}
logging.info("Loading Protein Data...")
self.field_to_protein_data = {
field: load_mapping(path=config["path"], **config["args"])
for field, config in self.params["field_to_protein_data"].items()
}
def __init__(self, dir, params):
"""
Constructor
Args:
dir (string) directory of the experiment to be run
"""
super(Aggregate, self).__init__(dir, params)
# Set the logger
self.params = params
# Unpack parameters
self.experiments = self.params["experiments"]
self.groups_columns = self.params["groups_columns"]
# Log title
logging.info("Aggregating Experiments")
logging.info("Sabri Eyuboglu -- SNAP Group")
logging.info("======================================")
logging.info("Loading Disease Associations...")
self.diseases = load_diseases(self.params["associations_path"],
self.params["disease_subset"],
exclude_splits=['none'])
print(len(self.diseases))
def _load_data(self):
"""
"""
logging.info("Loading Disease Associations...")
self.diseases_dict = load_diseases(self.params["associations_path"])