def test_one_hot_encode_sequence_site_len():
# check site
enc0, enc1 = init_encoders()
assert len(one_hot_encode_sequence('A' * 40, enc0, enc1,
mirna=False)) == 160
with pytest.raises(SystemExit):
one_hot_encode_sequence('A' * 41, enc0, enc1, mirna=False)
def test_one_hot_encode_sequence_mirna_len():
# check mirnas
enc0, enc1 = init_encoders()
assert len(one_hot_encode_sequence('', enc0, enc1)) == 120
assert len(one_hot_encode_sequence('U' * 25, enc0, enc1)) == 120
with pytest.raises(SystemExit):
one_hot_encode_sequence('U' * 31, enc0, enc1)
def test_one_hot_encode_sequence_site_wellformed():
# must not raise exception
enc0, enc1 = init_encoders()
raised = False
try:
one_hot_encode_sequence('A' * 40, enc0, enc1, mirna=False)
except SystemExit:
raised = True
assert raised == False
def predict(model, mirnas, threeutrs, use_filter=True):
"""
given the lists of pairs of mirnas and threeutrs predict their functionality
:param model : the nn to use for prediction
:param mirnas: numpy array of the mirna to check
:param threeutrs: numpy array of genes
:param use_filter: whether to use site accessibility filter or not
:return: the list of predictions
"""
preds = [0] * len(mirnas)
label_encoder, one_hot_encoder = vec.init_encoders()
for mirna, threeutr, idx in zip(tqdm(mirnas), threeutrs,
range(len(mirnas))):
pred = predict_pair(model,
mirna,
threeutr,
label_encoder,
one_hot_encoder,
use_filter=use_filter)
preds[idx] = pred
return preds
def test_one_hot_encode_sequence_site_badformed():
enc0, enc1 = init_encoders()
with pytest.raises(SystemExit):
one_hot_encode_sequence('H' * 40, enc0, enc1, mirna=False)
def test_one_hot_encode_sequence_mirna_badformed():
enc0, enc1 = init_encoders()
with pytest.raises(SystemExit):
one_hot_encode_sequence('H' * 20, enc0, enc1)