def test_localaveragepooling2D(tmpdir):
os.environ['JANGGU_OUTPUT'] = tmpdir.strpath
# some test data
testin = np.ones((1, 10, 1, 3))
testin[:, :, :, 1] += 1
testin[:, :, :, 2] += 2
# test local average pooling
lin = Input((10, 1, 3))
out = LocalAveragePooling2D(3)(lin)
m = Janggu(lin, out)
testout = m.predict(testin)
np.testing.assert_equal(testout, testin[:, :8, :, :])
# more tests
testin = np.ones((1, 3, 1, 2))
testin[:, 0, :, :] = 0
testin[:, 2, :, :] = 2
testin[:, :, :, 1] += 1
# test local average pooling
lin = Input((3, 1, 2))
out = LocalAveragePooling2D(3)(lin)
m = Janggu(lin, out)
testout = m.predict(testin)
np.testing.assert_equal(testout.shape, (1, 1, 1, 2))
np.testing.assert_equal(testout[0, 0, 0, 0], 1)
np.testing.assert_equal(testout[0, 0, 0, 1], 2)
def objective(params):
print(params)
try:
train_data = get_data(params)
train_data, test = split_train_test(train_data, [test_chrom])
train, val = split_train_test(train_data, [params['val_chrom']])
# define a keras model only based on DNA
K.clear_session()
if params['inputs'] == 'epi_dna':
dnam = Janggu.create_by_name('cage_promoters_dna_only')
epim = Janggu.create_by_name('cage_promoters_epi_only')
layer = Concatenate()([
dnam.kerasmodel.layers[-2].output,
epim.kerasmodel.layers[-2].output
])
layer = Dense(1, name='geneexpr')(layer)
model = Janggu([dnam.kerasmodel.input] + epim.kerasmodel.input,
layer,
name='cage_promoters_epi_dna')
if not params['pretrained']:
# This part randomly reinitializes the network
# so that we can train it from scratch
newjointmodel = model_from_json(model.kerasmodel.to_json())
newjointmodel = Janggu(
newjointmodel.inputs,
newjointmodel.outputs,
name='cage_promoters_epi_dna_randominit')
model = newjointmodel
else:
model = Janggu.create(get_model,
params,
train_data[0],
train_data[1],
name='cage_promoters_{}'.format(
params['inputs']))
except ValueError:
main_logger.exception('objective:')
return {'status': 'fail'}
model.compile(optimizer=get_opt(params['opt']),
loss='mae',
metrics=['mse'])
hist = model.fit(
train_data[0],
train_data[1],
epochs=params['epochs'],
batch_size=64,
validation_data=[params['val_chrom']],
callbacks=[EarlyStopping(patience=5, restore_best_weights=True)])
print('#' * 40)
for key in hist.history:
print('{}: {}'.format(key, hist.history[key][-1]))
print('#' * 40)
pred_train = model.predict(train[0])
pred_val = model.predict(val[0])
pred_test = model.predict(test[0])
model.evaluate(train[0],
train[1],
callbacks=['var_explained', 'mse', 'mae', 'cor'],
datatags=['train'])
mae_val = model.evaluate(val[0],
val[1],
callbacks=['var_explained', 'mse', 'mae', 'cor'],
datatags=['val'])
mae_val = mae_val[0]
model.evaluate(test[0],
test[1],
callbacks=['var_explained', 'mse', 'mae', 'cor'],
datatags=['test'])
cor_train = np.corrcoef(train[1][:][:, 0], pred_train[:, 0])[0, 1]
cor_val = np.corrcoef(val[1][:][:, 0], pred_val[:, 0])[0, 1]
cor_test = np.corrcoef(test[1][:][:, 0], pred_test[:, 0])[0, 1]
model.summary()
main_logger.info('cor [train/val/test]: {:.2f}/{:.2f}/{:.2f}'.format(
cor_train, cor_val, cor_test))
return {
'loss': mae_val,
'status': 'ok',
'all_losses': hist.history,
'cor_train': cor_train,
'cor_val': cor_val,
'cor_test': cor_test,
'model_config': model.kerasmodel.to_json(),
'model_weights': model.kerasmodel.get_weights(),
'concrete_params': params
}
newjointmodel.outputs,
name='randominit_dnase_dna_joint_model_{}_{}'.format(
dnasename, dnaname))
newjointmodel.compile(optimizer=get_opt('amsgrad'),
loss='binary_crossentropy',
metrics=['acc'])
hist = newjointmodel.fit(
train_data[0],
train_data[1],
epochs=shared_space['epochs'],
batch_size=64,
validation_data=val_data,
callbacks=[EarlyStopping(patience=5, restore_best_weights=True)])
pred_test = newjointmodel.predict(test_data[0])
pred_val = newjointmodel.predict(val_data[0])
auprc_val = average_precision_score(val_data[1][:], pred_val)
auprc_test = average_precision_score(test_data[1][:], pred_test)
print('auprc_val: {:.2%}'.format(auprc_val))
print('auprc_test: {:.2%}'.format(auprc_test))
auprc_rand_val.append(auprc_val)
auprc_rand_test.append(auprc_test)
df = pd.DataFrame({'auprc_val': auprc_rand_val, 'auprc_test': auprc_rand_test})
df.to_csv(os.path.join(os.environ['JANGGU_OUTPUT'],
"dnase_dna_use_randominit_submodels.tsv"),
sep='\t')
