"seed": seed,
"train_size": train_size,
}
if args.percentile != 50:
gene_percentile = np.percentile(dataset.df[gene].values, args.percentile)
dataset.labels = dataset.df[gene].where(dataset.df[gene] > gene_percentile).notnull().astype("int")
else:
dataset.labels = dataset.df[gene].where(dataset.df[gene] > 0).notnull().astype("int")
dataset.labels = dataset.labels.values if type(dataset.labels) == pd.Series else dataset.labels
# if labels are chosen such that only one class exists, skip the gene
# otherwise this throws a cuda device-side assert which breaks all
# subsequent experiments
if np.unique(dataset.labels).shape[0] == 1:
experiment['error'] = 'Expression distribution too narrow, skipping'
results = record_result(results, experiment, filename)
continue
try:
X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split(dataset.df, dataset.labels,
stratify=dataset.labels,
train_size=train_size,
test_size=test_size,
random_state=seed)
except ValueError:
results = record_result(results, experiment, filename)
continue
if is_first_degree:
if is_landmark:
neighbors = landmark_genes
def doMLP():
skopt_args = collections.OrderedDict()
skopt_args["lr"] = Integer(2, 5)
skopt_args["channels"] = Integer(4, 12)
skopt_args["layers"] = Integer(1, 4)
optimizer = skopt.Optimizer(dimensions=skopt_args.values(),
base_estimator="GP",
n_initial_points=3,
random_state=args.seed)
print(skopt_args)
best_valid_metric = 0
test_for_best_valid_metric = 0
best_config = None
already_done = set()
for i in range(10):
suggestion = optimizer.ask()
if str(suggestion) in already_done:
continue
already_done.add(str(suggestion))
sdict = dict(zip(skopt_args.keys(), suggestion))
sdict["lr"] = 10**float((-sdict["lr"]))
sdict["channels"] = 2**sdict["channels"]
model = models.mlp.MLP(name="MLP",
num_layer=sdict["layers"],
channels=sdict["channels"],
lr=sdict["lr"],
num_epochs=100,
patience=50,
cuda=torch.cuda.is_available(),
metric=sklearn.metrics.accuracy_score,
verbose=False,
seed=args.seed)
model.fit(X_train, y_train)
y_valid_pred = model.predict(X_valid)
valid_metric = sklearn.metrics.accuracy_score(
y_valid, np.argmax(y_valid_pred, axis=1))
opt_results = optimizer.tell(suggestion, -valid_metric)
print(opt_results)
#record metrics to write and plot
if best_valid_metric < valid_metric:
best_valid_metric = valid_metric
best_config = sdict
y_test_pred = model.predict(X_test)
test_metric = sklearn.metrics.accuracy_score(
y_test, np.argmax(y_test_pred, axis=1))
test_for_best_valid_metric = test_metric
print(i, "This result:", valid_metric, sdict)
experiment = {
"model": model.name,
"graph": "",
"num_genes": len(list(X_train.columns)),
"train_size": args.ntrain,
"seed": args.seed,
"acc": valid_metric,
'lr': sdict["lr"],
'channels': sdict["channels"],
'embedding': 0,
'num_layer': sdict["layers"],
'prepool_extralayers': 0
}
global results
results = record_result(results, experiment, filename)
print("#Final Results", test_for_best_valid_metric, best_config)
return test_metric, best_config
def doGGC():
gene_graphs = [
data.gene_graphs.OntologyGraph(neighbors=30,
embeddings_name='dl2vec',
randomize=False,
gene_names=list(features.columns),
relabel_genes=False),
]
for graph in gene_graphs:
adj = graph.adj()
for dropout in [False]: #, False]:
import gc
gc.collect()
skopt_args = collections.OrderedDict()
skopt_args["lr"] = Integer(3, 5)
skopt_args["channels"] = Integer(3, 6)
# skopt_args["embedding"]=Integer(4, 5)
skopt_args["num_layer"] = Integer(1, 3)
skopt_args["gat_heads"] = Integer(1, 3)
skopt_args["prepool_extralayers"] = Integer(0, 1)
optimizer = skopt.Optimizer(dimensions=skopt_args.values(),
base_estimator="GP",
n_initial_points=4,
random_state=args.seed)
print(skopt_args)
best_valid_metric = 0
test_for_best_valid_metric = 0
best_config = None
already_done = set()
for i in range(100):
import gc
gc.collect()
suggestion = optimizer.ask()
if str(suggestion) in already_done:
continue
already_done.add(str(suggestion))
sdict = dict(zip(skopt_args.keys(), suggestion))
sdict["lr"] = 10**float((-sdict["lr"]))
sdict["channels"] = 2**sdict["channels"]
sdict["gat_heads"] = 2**sdict["gat_heads"]
sdict["embedding"] = 2 # 2**sdict["embedding"]
print(sdict)
neighbors = graph.nx_graph
intersection_nodes = np.intersect1d(X_train.columns,
neighbors.nodes)
x_train = X_train[list(intersection_nodes)].copy()
x_valid = X_valid[list(intersection_nodes)].copy()
toremove = set(neighbors.nodes)
toremove = toremove.difference(intersection_nodes)
neighbors.remove_nodes_from(toremove)
adj = sparse.csr_matrix(nx.to_numpy_matrix(neighbors))
model = models.gnn.GCN(
name="GAT",
dropout=dropout,
gnn="GAT",
gat_heads=sdict["gat_heads"],
cuda=torch.cuda.is_available(),
num_layer=sdict["num_layer"],
prepool_extralayers=sdict["prepool_extralayers"],
channels=sdict["channels"],
embedding=sdict["channels"], #sdict["embedding"],
aggregation=None,
lr=sdict["lr"],
num_epochs=100,
patience=40,
verbose=True,
seed=args.seed)
try:
model.fit(x_train, y_train, adj)
with torch.no_grad():
model.eval()
y_valid_pred = model.predict(x_valid)
valid_metric = sklearn.metrics.accuracy_score(
y_valid, np.argmax(y_valid_pred, axis=1))
opt_results = optimizer.tell(suggestion, -valid_metric)
# #record metrics to write and plot
# if best_valid_metric < valid_metric:
# best_valid_metric = valid_metric
# print("best_valid_metric", best_valid_metric, sdict)
# best_config = sdict
# y_test_pred = model.predict(x_test)
# test_metric = sklearn.metrics.accuracy_score(y_test, np.argmax(y_test_pred,axis=1))
# test_for_best_valid_metric = test_metric
experiment = {
"model": model.name,
"graph": graph.graph_name,
"num_genes": len(x_train.columns),
"train_size": args.ntrain,
"seed": args.seed,
"acc": valid_metric,
'lr': sdict["lr"],
'channels': sdict["channels"],
'embedding': sdict["embedding"],
'num_layer': sdict["num_layer"],
'prepool_extralayers': sdict["prepool_extralayers"]
}
print(i, "This result:", valid_metric, experiment)
global results
results = record_result(results, experiment, filename)
except Exception as e:
print(e)
logging.error(logging.traceback.format_exc())
# cleanup
model.best_model = None
del model
torch.cuda.empty_cache()
print("#Final Results", test_for_best_valid_metric, best_config)
return test_for_best_valid_metric, best_config
def doGGC():
# if args.graph == "stringdb":
# graph = data.gene_graphs.StringDBGraph(datastore="./data")
# elif args.graph == "genemania":
# graph = data.gene_graphs.GeneManiaGraph()
# elif args.graph == "ontology":
# graph = data.gene_graphs.OntologyGraph(neighbors=30, embeddings_name='el')
# else:
# print("unknown graph")
# sys.exit(1)
gene_graphs = [
OntologyGraph(neighbors=30, embeddings_name='dl2vec', randomize=False, gene_names=list(features.columns), relabel_genes=False),
OntologyGraph(neighbors=30, embeddings_name='el', randomize=False, gene_names=list(features.columns), relabel_genes=False)]
# data.gene_graphs.OntologyGraph(neighbors=n, embeddings_name=emb)
# for n in [30] #[500, 100, 30, 10]
# for emb in ['el', 'dl2vec', 'opa2vec', 'opa2vec_go']] + [
# data.gene_graphs.GeneManiaGraph(),
# data.gene_graphs.StringDBGraph(datastore="./data")]
# data.gene_graphs.OntologyGraph(neighbors=30, embeddings_name='el'),
# data.gene_graphs.OntologyGraph(neighbors=30, embeddings_name='el'),
# gene_graphs = [data.gene_graphs.OntologyGraph(neighbors=100, embeddings_name='el')]
# data.gene_graphs.GeneManiaGraph(),
# data.gene_graphs.StringDBGraph(datastore="./data")]
for graph in gene_graphs:
adj = graph.adj()
for num_genes in [1000, 16000]:
for dropout in [True, False]: #, False]:
import gc
gc.collect()
skopt_args = collections.OrderedDict()
# skopt_args["lr"]=Integer(3, 4)
skopt_args["channels"]=Integer(4, 9)
# skopt_args["embedding"]=Integer(4, 5)
skopt_args["num_layer"]=Integer(0, 4)
skopt_args["prepool_extralayers"]=Integer(0, 3)
optimizer = skopt.Optimizer(dimensions=skopt_args.values(),
base_estimator="GP",
n_initial_points=4,
random_state=args.seed)
print(skopt_args)
best_valid_metric = 0
test_for_best_valid_metric = 0
best_config = None
already_done = set()
for i in range(15):
import gc
gc.collect()
suggestion = optimizer.ask()
if str(suggestion) in already_done:
continue
already_done.add(str(suggestion))
sdict = dict(zip(skopt_args.keys(),suggestion))
sdict["lr"] = 0.001 #10**float((-sdict["lr"]))
sdict["channels"] = 2**sdict["channels"]
sdict["embedding"] = 2# 2**sdict["embedding"]
print(sdict)
gene = 'ESR1'
neighbors = graph.bfs_sample_neighbors(gene, num_genes*1.5)
intersection_nodes = np.intersect1d(features.columns, neighbors.nodes)
x_train = X_train[list(intersection_nodes)[:num_genes]].copy()
x_valid = X_valid[list(intersection_nodes)[:num_genes]].copy()
x_test = X_test[list(intersection_nodes)[:num_genes]].copy()
toremove = set(neighbors.nodes)
toremove = toremove.difference(intersection_nodes)
neighbors.remove_nodes_from(toremove)
adj = sparse.csr_matrix(nx.to_numpy_matrix(neighbors))
model = models.gcn.GCN(name="GCN_noemb" + ("_dropout" if dropout else ""), #_lay3_chan64_emb32_dropout_agg_hierarchy",
dropout=dropout,
cuda=torch.cuda.is_available(),
num_layer=sdict["num_layer"],
prepool_extralayers=sdict["prepool_extralayers"],
channels=sdict["channels"],
embedding=sdict["embedding"], # sdict["embedding"],
aggregation="hierarchy",
lr=sdict["lr"],
num_epochs=100,
patience=30,
verbose=False,
seed=args.seed
)
try:
model.fit(x_train, y_train, adj)
with torch.no_grad():
model.eval()
y_valid_pred = model.predict(x_valid)
valid_metric = sklearn.metrics.accuracy_score(y_valid, np.argmax(y_valid_pred,axis=1))
opt_results = optimizer.tell(suggestion, - valid_metric)
# #record metrics to write and plot
# if best_valid_metric < valid_metric:
# best_valid_metric = valid_metric
# print("best_valid_metric", best_valid_metric, sdict)
# best_config = sdict
# y_test_pred = model.predict(x_test)
# test_metric = sklearn.metrics.accuracy_score(y_test, np.argmax(y_test_pred,axis=1))
# test_for_best_valid_metric = test_metric
experiment = {
"model": model.name,
"graph": graph.graph_name,
"num_genes": num_genes,
"train_size": args.ntrain,
"seed": args.seed,
"acc": valid_metric,
'lr': sdict["lr"],
'channels': sdict["channels"],
'embedding': sdict["embedding"],
'num_layer': sdict["num_layer"],
'prepool_extralayers': sdict["prepool_extralayers"]
}
print(i, num_genes, "This result:",valid_metric, experiment)
global results
results = record_result(results, experiment, filename)
except Exception as e:
print(e)
logging.error(logging.traceback.format_exc())
# cleanup
model.best_model = None
del model
torch.cuda.empty_cache()
print("#Final Results", test_for_best_valid_metric, best_config)
return test_for_best_valid_metric, best_config