def test_janggu_influence_genomic(tmpdir):
os.environ['JANGGU_OUTPUT'] = tmpdir.strpath
"""Test Janggu creation by shape and name. """
data_path = pkg_resources.resource_filename('janggu', 'resources/')
bed_file = os.path.join(data_path, 'sample.bed')
csvfile = os.path.join(data_path, 'sample.csv')
refgenome = os.path.join(data_path, 'sample_genome.fa')
dna = Bioseq.create_from_refgenome('dna',
refgenome=refgenome,
storage='ndarray',
binsize=50,
roi=bed_file,
order=1)
df = pd.read_csv(csvfile, header=None)
ctcf = Array('ctcf', df.values, conditions=['peaks'])
@inputlayer
@outputdense('sigmoid')
def _cnn_model(inputs, inp, oup, params):
layer = inputs['dna']
layer = Flatten()(layer)
output = Dense(params[0])(layer)
return inputs, output
model = Janggu.create(_cnn_model,
modelparams=(2, ),
inputs=dna,
outputs=ctcf,
name='dna_ctcf_HepG2-cnn')
model.compile(optimizer='adadelta', loss='binary_crossentropy')
# check with some nice offset
iv = dna.gindexer[0]
chrom, start, end = iv.chrom, iv.start, iv.end
influence = input_attribution(model,
dna,
chrom=chrom,
start=start,
end=end)
# check with an odd offset
# chrom, start, end =
influence2 = input_attribution(model,
dna,
chrom=chrom,
start=start - 1,
end=end + 1)
np.testing.assert_equal(influence[0][:], influence2[0][:][:, 1:-1])
def test_janggu_influence_fasta(tmpdir):
data_path = pkg_resources.resource_filename('janggu', 'resources/')
order = 1
filename = os.path.join(data_path, 'sample.fa')
data = Bioseq.create_from_seq('dna',
fastafile=filename,
order=order,
cache=False)
dna = data
@inputlayer
def _cnn_model(inputs, inp, oup, params):
layer = inputs['dna']
layer = Flatten()(layer)
output = Dense(params[0])(layer)
output = Dense(1, activation='sigmoid')(output)
return inputs, output
model = Janggu.create(_cnn_model,
modelparams=(2, ),
inputs=data,
name='dna_ctcf_HepG2-cnn')
#model.compile(optimizer='adadelta', loss='binary_crossentropy')
# check with some nice offset
iv = dna.gindexer[0]
chrom, start, end = iv.chrom, iv.start, iv.end
influence = input_attribution(model,
dna,
chrom=chrom,
start=start,
end=end)
influence2 = input_attribution(model, dna, idx=0)
np.testing.assert_equal(influence[0][:], influence2[0][:])
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
attr_oct = input_attribution(model, DNA, chrom=chrom, start=start, end=end)
# visualize the important sequence features
plotGenomeTrack(SeqTrack(attr_oct[0]), chrom, start, end).savefig(
os.path.join(args.path,
'influence_oct4_example_order{}.png'.format(args.order)))
# For the comparison, extract an interval
# representing a Mafk bound region and visualize the
# important features.
gi = DNA.gindexer[7796]
chrom = gi.chrom
start = gi.start
end = gi.end
attr_mafk = input_attribution(model, DNA, chrom=chrom, start=start, end=end)