def cross_validate(x, y, peak_names, output_file_path):
kf = KFold(n_splits=10, shuffle=True)
pred_all = []
corr_all = []
peak_order = []
for train_index, test_index in kf.split(x):
train_data, eval_data = x[train_index, :, :], x[test_index, :, :]
train_labels, eval_labels = y[train_index, :], y[test_index, :]
train_names, eval_name = peak_names[train_index], peak_names[
test_index]
# Data loader
train_dataset = torch.utils.data.TensorDataset(
torch.from_numpy(train_data), torch.from_numpy(train_labels))
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
batch_size=batch_size,
shuffle=False)
eval_dataset = torch.utils.data.TensorDataset(
torch.from_numpy(eval_data), torch.from_numpy(eval_labels))
eval_loader = torch.utils.data.DataLoader(dataset=eval_dataset,
batch_size=batch_size,
shuffle=False)
# create model
model = aitac.ConvNet(num_classes, num_filters).to(device)
# Loss and optimizer
criterion = aitac.pearson_loss
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
# train model
model, best_loss = aitac.train_model(train_loader, eval_loader, model,
device, criterion, optimizer,
num_epochs, output_file_path)
# Predict on test set
predictions, max_activations, max_act_index = aitac.test_model(
eval_loader, model, device)
# plot the correlations histogram
correlations = plot_utils.plot_cors(eval_labels, predictions,
output_file_path)
pred_all.append(predictions)
corr_all.append(correlations)
peak_order.append(eval_name)
pred_all = np.vstack(pred_all)
corr_all = np.hstack(corr_all)
peak_order = np.hstack(peak_order)
return pred_all, corr_all, peak_order
model.parameters()),
lr=learning_rate)
# train model
model, best_loss_valid = aitac.train_model(train_loader, valid_loader, model,
device, criterion, optimizer,
num_epochs, output_file_path)
# save the model checkpoint
torch.save(model.state_dict(), '../models/model' + model_name + '.ckpt')
#save the whole model
torch.save(model, '../models/model' + model_name + '.pth')
# Predict on test set
predictions, max_activations, max_act_index = aitac.test_model(
eval_loader, model, device)
#-------------------------------------------#
# Create Plots #
#-------------------------------------------#
# plot the correlations histogram
# returns correlation measurement for every prediction-label pair
print("Creating plots...")
#plot_utils.plot_training_loss(training_loss, output_file_path)
correlations = plot_utils.plot_cors(eval_labels, predictions, output_file_path)
plot_utils.plot_corr_variance(eval_labels, correlations, output_file_path)
torch.from_numpy(y))
data_loader = torch.utils.data.DataLoader(dataset=dataset,
batch_size=batch_size,
shuffle=False)
# load trained model
model = aitac.ConvNet(num_classes, num_filters).to(device)
checkpoint = torch.load('../models/' + model_name + '.ckpt')
model.load_state_dict(checkpoint)
#copy trained model weights to motif extraction model
motif_model = aitac.motifCNN(model).to(device)
motif_model.load_state_dict(model.state_dict())
# run predictions with full model on all data
pred_full_model, max_activations, activation_idx = aitac.test_model(
data_loader, model, device)
correlations = plot_utils.plot_cors(y, pred_full_model, output_file_path)
# find well predicted OCRs
idx = np.argwhere(np.asarray(correlations) > 0.75).squeeze()
#get data subset for well predicted OCRs to run further test
x2 = x[idx, :, :]
y2 = y[idx, :]
dataset = torch.utils.data.TensorDataset(torch.from_numpy(x2),
torch.from_numpy(y2))
data_loader = torch.utils.data.DataLoader(dataset=dataset,
batch_size=batch_size,
shuffle=False)
model_name = sys.argv[5]
# Data loader
dataset = torch.utils.data.TensorDataset(torch.from_numpy(x),
torch.from_numpy(y))
data_loader = torch.utils.data.DataLoader(dataset=dataset,
batch_size=batch_size,
shuffle=False)
# load trained model
model = aitac.ConvNet(num_classes, num_filters).to(device)
checkpoint = torch.load('../models/' + model_name + '.ckpt')
model.load_state_dict(checkpoint)
# run predictions with full model on all data
mouse_predictions, max_activations, act_index = aitac.test_model(
data_loader, model, device)
# convert predictions from mouse cell types to human cell types
map = np.genfromtxt("../human_data/mouse_human_celltypes.txt", dtype='str')
mouse_cell_types = np.genfromtxt("../data/cell_type_names.txt", dtype='str')
predictions, cell_names = plot_utils.mouse2human(mouse_predictions,
mouse_cell_types, map)
print(cell_names)
#-------------------------------------------#
# Create Plots #
#-------------------------------------------#
# plot the correlations histogram
# returns correlation measurement for every prediction-label pair
print("Creating plots...")