def test_embedding_conv_1_layer():
model = Predictor(inputs=SequenceInput(length=3,
variable_length=False,
conv_filter_sizes={2: 3}),
outputs=Output(1, activation="sigmoid"))
X = ["SAY", "FFQ"]
Y = np.array([True, False])
model.fit(X, Y)
def test_predictor_on_more_data():
predictor = Predictor(
inputs=[SequenceInput(length=20, name="x", variable_length=True)],
outputs=[Output(dim=1, activation="sigmoid", name="y")],
dense_layer_sizes=[30],
dense_activation="relu")
train_df = synthetic_peptides_by_subsequence(1000)
test_df = synthetic_peptides_by_subsequence(1000)
predictor.fit({"x": train_df.index.values},
train_df.binder.values,
epochs=20)
y_pred = predictor.predict({"x": test_df.index.values})['y']
y_pred = pandas.Series(y_pred, index=test_df.index)
binder_mean_pred = y_pred[test_df.binder].mean()
nonbinder_mean_pred = y_pred[~test_df.binder].mean()
print(binder_mean_pred, nonbinder_mean_pred)
assert binder_mean_pred > nonbinder_mean_pred * 2, (binder_mean_pred,
nonbinder_mean_pred)
def test_model_with_fixed_length_context():
model = Predictor(inputs={
"upstream":
SequenceInput(length=1, variable_length=False),
"downstream":
SequenceInput(length=1, variable_length=False),
"peptide":
SequenceInput(length=3, variable_length=True)
},
outputs=Output(1, activation="sigmoid"))
Y = np.array([True, False, True, False])
input_dict = {
"upstream": ["Q", "A", "L", "I"],
"downstream": ["S"] * 4,
"peptide": ["SYF", "QQ", "C", "GLL"]
}
model.fit(input_dict, Y, epochs=20)
Y_pred = model.predict(input_dict)
assert (Y == (Y_pred > 0.5)).all(), (Y, Y_pred)
def test_discrete_input_with_str_tokens():
pred = Predictor(inputs=DiscreteInput(choices=["x", "y", "z"],
embedding_dim=2),
outputs=Output(1, "sigmoid"))
pred.fit(["x", "x", "y", "z"], [0, 0, 0.5, 1.0], epochs=20)
assert pred.predict(["x"]) < pred.predict(["z"])
