def test_create_from_array_whole_genome_false(tmpdir):
os.environ['JANGGU_OUTPUT'] = tmpdir.strpath
# load the dataset
# The pseudo genome represents just a concatenation of all sequences
# in sample.fa and sample2.fa. Therefore, the results should be almost
# identically to the models obtained from classify_fasta.py.
REFGENOME = resource_filename('janggu', 'resources/pseudo_genome.fa')
# ROI contains regions spanning positive and negative examples
ROI_FILE = resource_filename('janggu', 'resources/roi_train.bed')
# PEAK_FILE only contains positive examples
PEAK_FILE = resource_filename('janggu', 'resources/scores.bed')
DNA = Bioseq.create_from_refgenome('dna', refgenome=REFGENOME,
roi=ROI_FILE,
binsize=200, stepsize=200,
order=1,
store_whole_genome=False,
datatags=['ref'])
LABELS = Cover.create_from_bed('peaks', roi=ROI_FILE,
bedfiles=PEAK_FILE,
binsize=200, stepsize=200,
resolution=200,
store_whole_genome=False,
datatags=['train'])
@inputlayer
@outputconv('sigmoid')
def double_stranded_model_dnaconv(inputs, inp, oup, params):
with inputs.use('dna') as layer:
layer = DnaConv2D(Conv2D(params[0], (params[1], 1),
activation=params[2]))(layer)
output = LocalAveragePooling2D(window_size=layer.shape.as_list()[1],
name='motif')(layer)
return inputs, output
modeltemplate = double_stranded_model_dnaconv
K.clear_session()
# create a new model object
model = Janggu.create(template=modeltemplate,
modelparams=(30, 21, 'relu'),
inputs=DNA,
outputs=LABELS)
model.compile(optimizer='adadelta', loss='binary_crossentropy',
metrics=['acc'])
pred = model.predict(DNA)
cov_out = Cover.create_from_array('BindingProba', pred, LABELS.gindexer,
store_whole_genome=False)
assert pred.shape == cov_out.shape
np.testing.assert_equal(pred, cov_out[:])
assert len(cov_out.gindexer) == len(pred)
assert len(cov_out.garray.handle) == len(pred)
def test_create_from_array_whole_genome_true(tmpdir):
os.environ['JANGGU_OUTPUT'] = tmpdir.strpath
# load the dataset
# The pseudo genome represents just a concatenation of all sequences
# in sample.fa and sample2.fa. Therefore, the results should be almost
# identically to the models obtained from classify_fasta.py.
# ROI contains regions spanning positive and negative examples
ROI_FILE = resource_filename('janggu', 'resources/roi_train.bed')
# PEAK_FILE only contains positive examples
PEAK_FILE = resource_filename('janggu', 'resources/scores.bed')
LABELS = Cover.create_from_bed('peaks', roi=ROI_FILE,
bedfiles=[PEAK_FILE]*5,
binsize=200, stepsize=200,
resolution=200,
store_whole_genome=True)
pred = LABELS[:]
for storage in ['ndarray', 'sparse', 'hdf5']:
print(storage)
cov_out = Cover.create_from_array('BindingProba', pred,
LABELS.gindexer,
cache=True,
storage=storage,
store_whole_genome=True)
np.testing.assert_equal(cov_out[:], LABELS[:])
np.testing.assert_equal(cov_out.shape, LABELS.shape)
def test_janggu_variant_prediction(tmpdir):
os.environ['JANGGU_OUTPUT'] = tmpdir.strpath
"""Test Janggu creation by shape and name. """
data_path = pkg_resources.resource_filename('janggu', 'resources/')
for order in [1, 2, 3]:
refgenome = os.path.join(data_path, 'sample_genome.fa')
vcffile = os.path.join(data_path, 'sample.vcf')
dna = Bioseq.create_from_refgenome('dna',
refgenome=refgenome,
storage='ndarray',
binsize=50,
store_whole_genome=True,
order=order)
def _cnn_model(inputs, inp, oup, params):
inputs = Input(
(50 - params['order'] + 1, 1, pow(4, params['order'])))
layer = Flatten()(inputs)
layer = Dense(params['hiddenunits'])(layer)
output = Dense(4, activation='sigmoid')(layer)
return inputs, output
model = Janggu.create(_cnn_model,
modelparams={
'hiddenunits': 2,
'order': order
},
name='dna_ctcf_HepG2-cnn')
model.predict_variant_effect(
dna,
vcffile,
conditions=['m' + str(i) for i in range(4)],
output_folder=os.path.join(os.environ['JANGGU_OUTPUT']))
assert os.path.exists(
os.path.join(os.environ['JANGGU_OUTPUT'], 'scores.hdf5'))
assert os.path.exists(
os.path.join(os.environ['JANGGU_OUTPUT'], 'snps.bed.gz'))
f = h5py.File(os.path.join(os.environ['JANGGU_OUTPUT'], 'scores.hdf5'),
'r')
gindexer = GenomicIndexer.create_from_file(
os.path.join(os.environ['JANGGU_OUTPUT'], 'snps.bed.gz'), None,
None)
cov = Cover.create_from_array('snps',
f['diffscore'],
gindexer,
store_whole_genome=True)
print(cov['chr2', 55, 65].shape)
print(cov['chr2', 55, 65])
assert np.abs(cov['chr2', 59, 60]).sum() > 0.0
assert np.abs(cov['chr2', 54, 55]).sum() == 0.0
f.close()
model = Model(xin, output)
model.compile(optimizer='adadelta',
loss='binary_crossentropy',
metrics=['acc'])
model.summary()
hist = model.fit(DNA,
LABELS,
epochs=100,
validation_data=(DNA_TEST, LABELS_TEST))
print('#' * 40)
print('loss: {}, acc: {}'.format(hist.history['loss'][-1],
hist.history['acc'][-1]))
print('#' * 40)
# convert the prediction to a cover object
pred = model.predict(DNA_TEST)
cov_pred = Cover.create_from_array('BindingProba', pred, LABELS_TEST.gindexer)
print('Prediction score examples for Oct4')
for i in range(4):
print('{}.: {}'.format(i, cov_pred[i]))
print('Prediction score examples for Mafk')
for i in range(1, 5):
print('{}.: {}'.format(i, cov_pred[-i]))
# predictions (or feature activities) can finally be exported to bigwig
cov_pred.export_to_bigwig(output_dir=args.path)
inputs=DNA,
outputs=ReduceDim(LABELS))
model.compile(optimizer='adadelta',
loss='binary_crossentropy',
metrics=['acc'])
hist = model.fit(DNA, ReduceDim(LABELS), epochs=args.epochs)
print('#' * 40)
print('loss: {}, acc: {}'.format(hist.history['loss'][-1],
hist.history['acc'][-1]))
print('#' * 40)
pred = model.predict(DNA_TEST)
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):
print('{}.: {}'.format(i, cov_pred[i]))
print('Prediction score examples for Mafk')
for i in range(1, 5):
print('{}.: {}'.format(i, cov_pred[-i]))
# Extract the 4th interval to perform input feature importance attribution
# which represents an Oct4 bound region
gi = DNA.gindexer[3]
chrom = gi.chrom
start = gi.start
end = gi.end
