def initialize(hparams, train_dataset, val_dataset, test_dataset,
kernel_data):
data = {
"train": train_dataset,
"val": val_dataset,
"test": test_dataset,
"kernel_data": kernel_data
}
# metrics
metrics = [
mt.Metric(mt.rms_score, np.nanmean),
mt.Metric(mt.concordance_index, np.nanmean),
mt.Metric(mt.pearson_r2_score, np.nanmean)
]
return data, hparams['reg_lambda'], metrics
def initialize(hparams, train_dataset, val_dataset, test_dataset):
M, all_comps, all_prots = train_dataset['labels'], train_dataset[
'compounds'], train_dataset['proteins']
model = MatrixFactorization(len(all_comps),
len(all_prots),
k=hparams['latent_dim'])
if cuda:
model = model.cuda()
# optimizer configuration
optimizer = {
"adadelta": torch.optim.Adadelta,
"adagrad": torch.optim.Adagrad,
"adam": torch.optim.Adam,
"adamax": torch.optim.Adamax,
"asgd": torch.optim.ASGD,
"rmsprop": torch.optim.RMSprop,
"Rprop": torch.optim.Rprop,
"sgd": torch.optim.SGD,
}.get(hparams["optimizer"].lower(), None)
assert optimizer is not None, "{} optimizer could not be found"
# filter optimizer arguments
optim_kwargs = dict()
optim_key = hparams["optimizer"]
for k, v in hparams.items():
if "optimizer__" in k:
attribute_tup = k.split("__")
if optim_key == attribute_tup[1] or attribute_tup[
1] == "global":
optim_kwargs[attribute_tup[2]] = v
optimizer = optimizer(model.parameters(), **optim_kwargs)
# metrics
metrics = [
mt.Metric(mt.rms_score, np.nanmean),
mt.Metric(mt.concordance_index, np.nanmean),
mt.Metric(mt.pearson_r2_score, np.nanmean)
]
return model, optimizer, all_comps, all_prots, M, metrics
def initialize(hparams,
train_dataset,
val_dataset,
test_dataset,
cuda_devices=None,
mode="regression"):
# create network
model = create_integrated_net(hparams)
print("Number of trainable parameters = {}".format(
count_parameters(model)))
if cuda:
model = model.cuda()
# data loaders
train_data_loader = DataLoader(dataset=train_dataset,
batch_size=hparams["tr_batch_size"],
shuffle=True,
collate_fn=lambda x: x)
val_data_loader = DataLoader(dataset=val_dataset,
batch_size=hparams["val_batch_size"],
shuffle=False,
collate_fn=lambda x: x)
test_data_loader = None
if test_dataset is not None:
test_data_loader = DataLoader(
dataset=test_dataset,
batch_size=hparams["test_batch_size"],
shuffle=False,
collate_fn=lambda x: x)
# optimizer configuration
optimizer = {
"adadelta": torch.optim.Adadelta,
"adagrad": torch.optim.Adagrad,
"adam": torch.optim.Adam,
"adamax": torch.optim.Adamax,
"asgd": torch.optim.ASGD,
"rmsprop": torch.optim.RMSprop,
"Rprop": torch.optim.Rprop,
"sgd": torch.optim.SGD,
}.get(hparams["optimizer"].lower(), None)
assert optimizer is not None, "{} optimizer could not be found"
# filter optimizer arguments
optim_kwargs = dict()
optim_key = hparams["optimizer"]
for k, v in hparams.items():
if "optimizer__" in k:
attribute_tup = k.split("__")
if optim_key == attribute_tup[1] or attribute_tup[
1] == "global":
optim_kwargs[attribute_tup[2]] = v
optimizer = optimizer(model.parameters(), **optim_kwargs)
# metrics
metrics = [
mt.Metric(mt.rms_score, np.nanmean),
mt.Metric(mt.concordance_index, np.nanmean),
mt.Metric(mt.pearson_r2_score, np.nanmean)
]
return model, optimizer, {
"train": train_data_loader,
"val": val_data_loader,
"test": test_data_loader
}, metrics
def initialize(hparams,
train_dataset,
val_dataset,
test_dataset,
cuda_devices=None,
mode="regression"):
# create networks
generator = create_integrated_net(hparams)
discriminator = create_discriminator_net(hparams)
print("Number of trainable parameters: generator={}, discriminator={}".
format(count_parameters(generator),
count_parameters(discriminator)))
if cuda:
generator = generator.cuda()
discriminator = discriminator.cuda()
# data loaders
train_data_loader = DataLoader(dataset=train_dataset,
batch_size=hparams["tr_batch_size"],
shuffle=True,
collate_fn=lambda x: x)
val_data_loader = DataLoader(dataset=val_dataset,
batch_size=hparams["val_batch_size"],
shuffle=False,
collate_fn=lambda x: x)
test_data_loader = None
if test_dataset is not None:
test_data_loader = DataLoader(
dataset=test_dataset,
batch_size=hparams["test_batch_size"],
shuffle=False,
collate_fn=lambda x: x)
# filter optimizer arguments
optimizer_disc = optimizer_gen = None
for suffix in ["_gen", "_disc"]:
key = "optimizer{}".format(suffix)
# optimizer configuration
optimizer = {
"adadelta": torch.optim.Adadelta,
"adagrad": torch.optim.Adagrad,
"adam": torch.optim.Adam,
"adamax": torch.optim.Adamax,
"asgd": torch.optim.ASGD,
"rmsprop": torch.optim.RMSprop,
"Rprop": torch.optim.Rprop,
"sgd": torch.optim.SGD,
}.get(hparams[key].lower(), None)
assert optimizer is not None, "{} optimizer could not be found"
optim_kwargs = dict()
optim_key = hparams[key]
for k, v in hparams.items():
if "optimizer{}__".format(suffix) in k:
attribute_tup = k.split("__")
if optim_key == attribute_tup[1] or attribute_tup[
1] == "global":
optim_kwargs[attribute_tup[2]] = v
if suffix == "_gen":
optimizer_gen = optimizer(generator.parameters(),
**optim_kwargs)
else:
optimizer_disc = optimizer(discriminator.parameters(),
**optim_kwargs)
# metrics
metrics = [
mt.Metric(mt.rms_score, np.nanmean),
mt.Metric(mt.concordance_index, np.nanmean),
mt.Metric(mt.pearson_r2_score, np.nanmean)
]
return (generator, discriminator), (optimizer_gen, optimizer_disc), \
{"train": train_data_loader,
"val": val_data_loader,
"test": test_data_loader}, metrics, hparams["weighted_loss"], hparams["neigh_dist"]
def initialize(hparams,
train_dataset,
val_dataset,
test_dataset,
protein_profile,
cuda_devices=None,
mode="regression"):
frozen_models = FrozenModels()
# create network
view_lbl = hparams["view"]
create_comp_model = {
"ecfp4": create_ecfp_net,
"ecfp8": create_ecfp_net,
"weave": create_weave_net,
"gconv": create_gconv_net,
"gnn": create_gnn_net
}.get(view_lbl)
comp_model = create_comp_model(hparams)
# pt_embeddings = create_torch_embeddings(frozen_models_hook=frozen_models,
# np_embeddings=protein_embeddings)
func_callback = None
comp_net_pcnn = ProtCnnForward(
prot2vec=Prot2Vec(protein_profile=protein_profile,
vocab_size=hparams["prot"]["vocab_size"],
embedding_dim=hparams["prot"]["dim"],
batch_first=True),
prot_cnn_model=ProteinCNNAttention(
dim=hparams["prot"]["dim"],
window=hparams["prot"]["window"],
num_layers=hparams["prot"]["prot_cnn_num_layers"],
attn_hook=func_callback),
comp_model=comp_model)
p = 2 * hparams["prot"]["dim"]
layers = [comp_net_pcnn]
for dim in hparams["hdims"]:
layers.append(nn.Linear(p, dim))
layers.append(nn.BatchNorm1d(dim))
layers.append(nn.ReLU())
layers.append(nn.Dropout(hparams["dprob"]))
p = dim
# Output layer
layers.append(
nn.Linear(in_features=p, out_features=hparams["output_dim"]))
model = nn.Sequential(*layers)
print("Number of trainable parameters = {}".format(
count_parameters(model)))
if cuda:
model = model.cuda()
# data loaders
train_data_loader = DataLoader(dataset=train_dataset,
batch_size=10 if hparams["explain_mode"]
else hparams["tr_batch_size"],
shuffle=True,
collate_fn=lambda x: x)
val_data_loader = DataLoader(dataset=val_dataset,
batch_size=10 if hparams["explain_mode"]
else hparams["val_batch_size"],
shuffle=False,
collate_fn=lambda x: x)
test_data_loader = None
if test_dataset is not None:
test_data_loader = DataLoader(
dataset=test_dataset,
batch_size=10
if hparams["explain_mode"] else hparams["test_batch_size"],
shuffle=False,
collate_fn=lambda x: x)
# optimizer configuration
optimizer = {
"adadelta": torch.optim.Adadelta,
"adagrad": torch.optim.Adagrad,
"adam": torch.optim.Adam,
"adamax": torch.optim.Adamax,
"asgd": torch.optim.ASGD,
"rmsprop": torch.optim.RMSprop,
"Rprop": torch.optim.Rprop,
"sgd": torch.optim.SGD,
}.get(hparams["optimizer"].lower(), None)
assert optimizer is not None, "{} optimizer could not be found"
# filter optimizer arguments
optim_kwargs = dict()
optim_key = hparams["optimizer"]
for k, v in hparams.items():
if "optimizer__" in k:
attribute_tup = k.split("__")
if optim_key == attribute_tup[1] or attribute_tup[
1] == "global":
optim_kwargs[attribute_tup[2]] = v
optimizer = optimizer(model.parameters(), **optim_kwargs)
# metrics
metrics = [
mt.Metric(mt.rms_score, np.nanmean),
mt.Metric(mt.concordance_index, np.nanmean),
mt.Metric(mt.pearson_r2_score, np.nanmean)
]
return model, optimizer, {
"train": train_data_loader,
"val": val_data_loader,
"test": test_data_loader
}, metrics, frozen_models