def test_output_export_clustermap(tmpdir):
os.environ['JANGGU_OUTPUT'] = tmpdir.strpath
inputs = Array("x", numpy.random.random((100, 10)))
outputs = Array('y',
numpy.random.randint(2, size=(100, 1)),
conditions=['random'])
@inputlayer
@outputdense('sigmoid')
def _model(inputs, inp, oup, params):
with inputs.use('x') as layer:
outputs = Dense(3, name='hidden')(layer)
return inputs, outputs
bwm = Janggu.create(_model, inputs=inputs, outputs=outputs, name='nptest')
bwm.compile(optimizer='adadelta', loss='binary_crossentropy')
dummy_eval = Scorer('cluster', exporter=ExportClustermap())
bwm.predict(inputs, layername='hidden', callbacks=[dummy_eval])
dummy_eval = Scorer('cluster',
exporter=ExportClustermap(
fform='eps', annot={'annot': [1] * 50 + [0] * 50}))
bwm.predict(inputs, layername='hidden', callbacks=[dummy_eval])
# check if plot was produced
assert os.path.exists(
os.path.join(tmpdir.strpath, "evaluation", bwm.name, 'hidden',
"cluster.png"))
assert os.path.exists(
os.path.join(tmpdir.strpath, "evaluation", bwm.name, 'hidden',
"cluster.eps"))
SAMPLE_2 = os.path.join(DATA_PATH, 'sample2_test.fa')
DNA_TEST = Bioseq.create_from_seq('dna',
fastafile=[SAMPLE_1, SAMPLE_2],
order=args.order,
cache=True)
Y = np.asarray([[1] for _ in range(nseqs(SAMPLE_1))] +
[[0] for _ in range(nseqs(SAMPLE_2))])
LABELS_TEST = Array('y', Y, conditions=['TF-binding'])
annot_test = pd.DataFrame(Y[:], columns=LABELS_TEST.conditions).applymap(
lambda x: 'Oct4' if x == 1 else 'Mafk').to_dict(orient='list')
# clustering plots based on hidden features
heatmap_eval = Scorer('heatmap',
exporter=ExportClustermap(annot=annot_test, z_score=1.))
# output the predictions as tables or json files
pred_tsv = Scorer('pred',
exporter=ExportTsv(annot=annot_test,
row_names=DNA_TEST.gindexer.chrs))
# do the evaluation on the independent test data
# after the evaluation and prediction has been performed,
# the callbacks further process the results allowing
# to automatically generate summary statistics or figures
# into the JANGGU_OUTPUT directory.
model.evaluate(DNA_TEST,
LABELS_TEST,
datatags=['test'],
callbacks=['auc', 'auprc', 'roc', 'auroc'])
inputs=DNA,
outputs=ReduceDim(LABELS))
model.compile(optimizer='adadelta',
loss='binary_crossentropy',
metrics=['acc'])
hist = model.fit(DNA, ReduceDim(LABELS), epochs=100, shuffle=False)
print('#' * 40)
print('loss: {}, acc: {}'.format(hist.history['loss'][-1],
hist.history['acc'][-1]))
print('#' * 40)
# clustering plots based on hidden features
heatmap_eval = Scorer('heatmap', exporter=ExportClustermap(z_score=1.))
tsne_eval = Scorer('tsne', exporter=ExportTsne())
# do the evaluation on the independent test data
model.evaluate(DNA_TEST,
ReduceDim(LABELS_TEST),
datatags=['test'],
callbacks=['auc', 'auprc', 'roc', 'prc'])
pred = model.predict(DNA_TEST)
pred = pred[:, None, None, :]
cov_pred = Cover.create_from_array('BindingProba', pred, LABELS_TEST.gindexer)
print('Oct4 predictions scores should be greater than Mafk scores:')
print('Prediction score examples for Oct4')
for i in range(4):