def random_dna_features(experiment_proto, size):
"""Create a dict of feature tensors for random DNA sequences.
All features other than 'sequence' should use the default value.
Args:
experiment_proto: selection_pb2.Experiment describing the experiment.
size: scalar integer tf.Tensor giving the number of desired sequences.
Returns:
Dict[Any, labeled_tensor.LabeledTensor] providing generated features.
"""
with tf.name_scope('preprocess_random_input'):
template = selection.get_template_sequence(experiment_proto)
features = build_features(experiment_proto)
feature_tensors = {}
for k, v in features.items():
if k != 'sequence':
default_value = lt.constant(v.default_value, v.dtype, v.axes)
expanded_default = lt.expand_dims(default_value,
['batch'] + v.axes)
tiled_default = lt.tile(expanded_default, {'batch': size})
feature_tensors[k] = tiled_default
feature_tensors['sequence'] = lt.LabeledTensor(
random_dna_sequence(template, (size, )), ['batch'])
return feature_tensors
def _get_measurement_statistics(experiment_proto, statistic):
"""Extract measurement statistics from a selection_pb2.Experiment.
Args:
experiment_proto: selection_pb2.Experiment proto with saved measurement
statistics.
statistic: string giving the name of the statistic to pull out of the proto.
Returns:
LabeledTensor giving the value of the desired statistic for each output.
"""
mapping = selection.extract_measurement_statistic(experiment_proto, statistic)
output_names, data = list(zip(*sorted(mapping.items())))
return lt.constant(data, axes=[('target', list(output_names))])
def create_input_and_outputs(feature_tensors,
experiment_proto,
input_features=(SEQUENCE_ONE_HOT, ),
skip_all_zero_counts=True,
kmer_k_max=4,
additional_output=None):
"""Create inputs and outputs from parsed features.
Args:
feature_tensors: Dict[str, tf.Tensor] with parsed featured created by
`build_features`.
experiment_proto: selection_pb2.Experiment describing the experiment.
input_features: optional sequence of feature constants defined in this
module.
skip_all_zero_counts: some sequences have no counts, e.g., because they were
created artificially for validation purposes on the binding array. We want
to skip these sequences for training.
kmer_k_max: optional integer giving the maximum kmer length to use if
SEQUENCE_KMER_COUNT is in `input_features`.
additional_output: optional list of strings contains additional outputs.
Returns:
inputs: LabeledTensor with dtype=float32 and axes
[batch_axis, input_position_axis, input_channel_axis], of one-hot-encoded
rasterized sequences for input into machine learning models.
outputs: LabeledTensor with dtype=float32 and axes [batch_axis, output_axis]
denoting possible output tensors, including counts and binding array
measurements.
"""
sequence_length = experiment_proto.sequence_length
count_names = selection.all_count_names(experiment_proto)
array_names = selection.binding_array_names(experiment_proto)
sequence_tensor = feature_tensors['sequence']
batch_axis = sequence_tensor.axes['batch']
position_axis = ('position', list(range(sequence_length)))
inputs = {}
if SEQUENCE_ONE_HOT in input_features:
seq_indices = custom_ops.dna_sequence_to_indices(
sequence_tensor, sequence_length)
tensor = tf.one_hot(seq_indices, depth=4, dtype=tf.float32)
channel_axis = ('channel', list(dna.DNA_BASES))
axes = [batch_axis, position_axis, channel_axis]
one_hots = lt.LabeledTensor(tensor, axes)
inputs[SEQUENCE_ONE_HOT] = one_hots
if SEQUENCE_KMER_COUNT in input_features:
raw_counts = custom_ops.count_all_dna_kmers(sequence_tensor,
kmer_k_max)
kmer_axis = lt.Axis('kmer', _kmer_labels(kmer_k_max))
counts = lt.LabeledTensor(raw_counts, [batch_axis, kmer_axis])
means, stds = _all_kmer_mean_and_std(kmer_k_max, sequence_length)
mean_count = lt.constant(means, tf.float32, axes=[kmer_axis])
std_count = lt.constant(stds, tf.float32, axes=[kmer_axis])
inputs[SEQUENCE_KMER_COUNT] = (
(lt.cast(counts, tf.float32) - mean_count) / std_count)
if STRUCTURE_PARTITION_FUNCTION in input_features:
with tf.name_scope('structure_partition_fn'):
raw_pf_tensor = lt.expand_dims(
feature_tensors['partition_function'],
['batch', 'partition_fn_axis'])
inputs[STRUCTURE_PARTITION_FUNCTION] = lt.log(raw_pf_tensor)
output_names = count_names + array_names
outputs = [lt.cast(feature_tensors[k], tf.float32) for k in output_names]
if additional_output and additional_output[0]:
outputs += [
lt.cast(feature_tensors[k], tf.float32) for k in additional_output
]
output_names += additional_output
outputs = lt.pack(outputs, ('output', output_names), axis_position=1)
if skip_all_zero_counts:
with tf.name_scope('counts_filtering'):
counts = lt.select(outputs, {'output': count_names})
keep = lt.reduce_any(lt.not_equal(counts, 0.0), 'output')
inputs = {k: lt.boolean_mask(v, keep) for k, v in inputs.items()}
outputs = lt.boolean_mask(outputs, keep)
return inputs, outputs