def test_read_dna_from_biostring_order_1():
data_path = pkg_resources.resource_filename('janggu', 'resources/')
order = 1
filename = os.path.join(data_path, 'sample.fa')
seqs = sequences_from_fasta(filename)
with pytest.raises(ValueError):
data = Bioseq.create_from_seq('train',
fastafile=seqs,
storage='sparse',
order=order,
cache=False)
data = Bioseq.create_from_seq('train',
fastafile=seqs,
order=order,
cache=False)
np.testing.assert_equal(len(data), 3897)
np.testing.assert_equal(data.shape, (3897, 200, 1, 4))
np.testing.assert_equal(
data[0][0, :10, 0, :],
np.asarray([[0, 1, 0, 0], [1, 0, 0, 0], [0, 1, 0, 0], [1, 0, 0, 0],
[0, 0, 1, 0], [0, 1, 0, 0], [1, 0, 0, 0], [0, 0, 1, 0],
[1, 0, 0, 0], [0, 0, 1, 0]],
dtype='int8'))
def test_read_protein_sequences():
data_path = pkg_resources.resource_filename('janggu', 'resources/')
order = 1
filename = os.path.join(data_path, 'sample_protein.fa')
data = Bioseq.create_from_seq('train', fastafile=filename,
order=order, seqtype='protein', fixedlen=1000)
np.testing.assert_equal(len(data), 3)
np.testing.assert_equal(data.shape, (3, 1000, 1, 20))
np.testing.assert_equal(
data[0][0, :4, 0, :],
np.asarray([[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0]], dtype='int8'))
np.testing.assert_equal(
data[0][0, -2:, 0, :], np.zeros((2, 20), dtype='int8'))
data = Bioseq.create_from_seq('train', fastafile=filename,
order=order, seqtype='protein', fixedlen=5)
np.testing.assert_equal(len(data), 3)
np.testing.assert_equal(data.shape, (3, 5, 1, 20))
np.testing.assert_equal(
data[0][0, :4, 0, :],
np.asarray([[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0]], dtype='int8'))
def test_read_dna_from_fasta_order_2():
data_path = pkg_resources.resource_filename('janggu', 'resources/')
order = 2
filename = os.path.join(data_path, 'sample.fa')
for store_genome in [True, False]:
data = Bioseq.create_from_seq('train',
fastafile=filename,
order=order,
cache=False)
np.testing.assert_equal(len(data), 3897)
np.testing.assert_equal(data.shape, (3897, 199, 1, 16))
np.testing.assert_equal(
data[0][0, :10, 0, :],
np.asarray([[0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],
[0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0]],
dtype='int8'))
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][:])
Note however, that this is a simplification
that might not always work. In general, one would
need to parse for '>' occurrences.
"""
return sum((1 for line in open(filename) if line[0] == '>'))
# load the dataset
DATA_PATH = pkg_resources.resource_filename('janggu', 'resources/')
SAMPLE_1 = os.path.join(DATA_PATH, 'sample.fa')
SAMPLE_2 = os.path.join(DATA_PATH, 'sample2.fa')
# DNA sequences in one-hot encoding will be used as input
DNA = Bioseq.create_from_seq('dna',
fastafile=[SAMPLE_1, SAMPLE_2],
order=args.order,
cache=True)
# An array of 1/0 will be used as labels for training
Y = np.asarray([[1] for line in range(nseqs(SAMPLE_1))] +
[[0] for line in range(nseqs(SAMPLE_2))])
LABELS = Array('y', Y, conditions=['TF-binding'])
annot = pd.DataFrame(Y[:], columns=LABELS.conditions).applymap(
lambda x: 'Oct4' if x == 1 else 'Mafk').to_dict(orient='list')
# Define the model templates
@inputlayer
@outputdense('sigmoid')
def single_stranded_model(inputs, inp, oup, params):
Note however, that this is a simplification
that might not always work. In general, one would
need to parse for '>' occurrences.
"""
return sum((1 for line in open(filename) if line[0] == '>'))
# load the dataset
DATA_PATH = pkg_resources.resource_filename('janggu', 'resources/')
SAMPLE_1 = os.path.join(DATA_PATH, 'sample.fa')
SAMPLE_2 = os.path.join(DATA_PATH, 'sample2.fa')
# DNA sequences in one-hot encoding will be used as input
DNA = Bioseq.create_from_seq('dna',
fastafile=[SAMPLE_1, SAMPLE_2],
order=args.order,
datatags=['train'],
cache=True)
# An array of 1/0 will be used as labels for training
Y = np.asarray([1 for line in range(nseqs(SAMPLE_1))] +
[0 for line in range(nseqs(SAMPLE_2))])
LABELS = Array('y', Y, conditions=['TF-binding'])
annot = pd.DataFrame(Y[:], columns=LABELS.conditions).applymap(
lambda x: 'Oct4' if x == 1 else 'Mafk').to_dict(orient='list')
# evaluation metrics from sklearn.metrics
def wrap_roc(y_true, y_pred):
fpr, tpr, _ = roc_curve(y_true, y_pred)
aux = str('({:.2%})'.format(roc_auc_score(y_true, y_pred)))
