def in_silico_mutagenesis(model: Model,
encoded_sequences: np.ndarray) -> np.ndarray:
"""Computes in-silico-mutagenesis scores
Parameters
----------
model: Model
This can be any model that accepts inputs of the required shape and produces
an output of shape `(N_sequences, N_tasks)`.
encoded_sequences: np.ndarray
A numpy array of shape `(N_sequences, N_letters, sequence_length, 1)`
Returns
-------
np.ndarray
A numpy array of ISM scores. The shape is `(num_task, N_sequences, N_letters, sequence_length, 1)`.
"""
# Shape (N_sequences, num_tasks)
wild_type_predictions = model.predict(NumpyDataset(encoded_sequences))
# check whether wild_type_predictions is np.ndarray or not
assert isinstance(wild_type_predictions, np.ndarray)
num_tasks = wild_type_predictions.shape[1]
# Shape (N_sequences, N_letters, sequence_length, 1, num_tasks)
mutagenesis_scores = np.empty(
encoded_sequences.shape + (num_tasks,), dtype=np.float32)
# Shape (N_sequences, num_tasks, 1, 1, 1)
wild_type_predictions = wild_type_predictions[:, np.newaxis, np.newaxis,
np.newaxis]
for sequence_index, (sequence, wild_type_prediction) in enumerate(
zip(encoded_sequences, wild_type_predictions)):
# Mutates every position of the sequence to every letter
# Shape (N_letters * sequence_length, N_letters, sequence_length, 1)
# Breakdown:
# Shape of sequence[np.newaxis] (1, N_letters, sequence_length, 1)
mutated_sequences = np.repeat(
sequence[np.newaxis], np.prod(sequence.shape), axis=0)
# remove wild-type
# len(arange) = N_letters * sequence_length
arange = np.arange(len(mutated_sequences))
# len(horizontal cycle) = N_letters * sequence_length
horizontal_cycle = np.tile(np.arange(sequence.shape[1]), sequence.shape[0])
mutated_sequences[arange, :, horizontal_cycle, :] = 0
# add mutant
vertical_repeat = np.repeat(np.arange(sequence.shape[0]), sequence.shape[1])
mutated_sequences[arange, vertical_repeat, horizontal_cycle, :] = 1
# make mutant predictions
mutated_predictions = model.predict(NumpyDataset(mutated_sequences))
# check whether wild_type_predictions is np.ndarray or not
assert isinstance(mutated_predictions, np.ndarray)
mutated_predictions = mutated_predictions.reshape(sequence.shape +
(num_tasks,))
mutagenesis_scores[
sequence_index] = wild_type_prediction - mutated_predictions
rolled_scores = np.rollaxis(mutagenesis_scores, -1)
return rolled_scores
def predict(self, dataset, transformers=[], batch_size=None,
pad_batches=False):
"""
Uses self to make predictions on provided Dataset object.
This is overridden to make sure the batch size is always valid for Tensorflow.
Returns:
y_pred: numpy ndarray of shape (n_samples,)
"""
return Model.predict(self, dataset, transformers,
self.model_instance.batch_size, True)
