def encode(self, dataset, params: EncoderParams):
EncoderHelper.check_positive_class_label(
SequenceAbundanceEncoder.__name__,
params.label_config.get_label_objects())
self.comparison_data = SequenceFilterHelper.build_comparison_data(
dataset, self.context, self.comparison_attributes, params,
self.sequence_batch_size)
return self._encode_data(dataset, params)
def _get_relevant_sequence_indices(self, params, label_str,
sequence_p_values):
if self.relevant_indices_path is None:
self.relevant_indices_path = params.result_path / 'relevant_sequence_indices.pickle'
if params.learn_model:
SequenceFilterHelper._check_label_object(params, label_str)
relevant_sequence_indices = np.array(
sequence_p_values) < self.p_value_threshold
with self.relevant_indices_path.open("wb") as file:
pickle.dump(relevant_sequence_indices, file)
self._write_relevant_sequence_csv(
self.full_sequence_set[relevant_sequence_indices],
params.result_path)
else:
with self.relevant_indices_path.open("rb") as file:
relevant_sequence_indices = pickle.load(file)
return relevant_sequence_indices
def _encode_sequence_count(self, dataset: RepertoireDataset, comparison_data: ComparisonData, label: str, params: EncoderParams) -> EncodedData:
sequence_p_values_indices, indices_path, relevant_sequences_path = SequenceFilterHelper.get_relevant_sequences(dataset, params,
comparison_data, label,
self.p_value_threshold,
self.comparison_attributes,
self.relevant_indices_path)
if self.relevant_indices_path is None:
self.relevant_indices_path = indices_path
if self.relevant_sequence_csv_path is None:
self.relevant_sequence_csv_path = relevant_sequences_path
count_matrix = self._build_count_matrix(comparison_data, dataset.get_repertoire_ids(), sequence_p_values_indices)
feature_names = comparison_data.get_item_names()[sequence_p_values_indices]
encoded_data = EncodedData(count_matrix, dataset.get_metadata([label]) if params.encode_labels else None,
dataset.get_repertoire_ids(),
feature_names,
encoding=SequenceCountEncoder.__name__, info={'relevant_sequence_path': self.relevant_sequence_csv_path})
return encoded_data
def _calculate_sequence_abundance(self, dataset: RepertoireDataset,
comparison_data: ComparisonData,
label: str, params: EncoderParams):
sequence_p_values_indices, indices_path, sequence_csv_path = SequenceFilterHelper.get_relevant_sequences(
dataset=dataset,
params=params,
comparison_data=comparison_data,
label=label,
p_value_threshold=self.p_value_threshold,
comparison_attributes=self.comparison_attributes,
sequence_indices_path=self.relevant_indices_path)
if self.relevant_indices_path is None:
self.relevant_indices_path = indices_path
if self.relevant_sequence_csv_path is None:
self.relevant_sequence_csv_path = sequence_csv_path
abundance_matrix = self._build_abundance_matrix(
comparison_data, dataset.get_repertoire_ids(),
sequence_p_values_indices)
return abundance_matrix
def encode(self, dataset, params: EncoderParams):
self.comparison_data = SequenceFilterHelper.build_comparison_data(dataset, self.context, self.comparison_attributes, params,
self.sequence_batch_size)
return self._encode_data(dataset, params)
def test_find_label_associated_sequence_p_values(self):
path = EnvironmentSettings.tmp_test_path / "comparison_data_find_label_assocseqpvalues/"
PathBuilder.build(path)
repertoires = [
Repertoire.build_from_sequence_objects([ReceptorSequence()], path,
{
"l1": val,
"subject_id": subject_id
})
for val, subject_id in zip([True, True, False, False],
["rep_0", "rep_1", "rep_2", "rep_3"])
]
col_name_index = {
repertoires[index].identifier: index
for index in range(len(repertoires))
}
comparison_data = ComparisonData(
repertoire_ids=[
repertoire.identifier for repertoire in repertoires
],
comparison_attributes=["sequence_aas"],
sequence_batch_size=4,
path=path)
comparison_data.batches = [
ComparisonDataBatch(
**{
'matrix': np.array([[1., 0., 0., 0.], [1., 1., 0., 0.]]),
'items': [('GGG', ), ('III', )],
'repertoire_index_mapping': col_name_index,
'path': path,
'identifier': 0
}),
ComparisonDataBatch(
**{
'matrix': np.array([[1., 1., 0., 1.], [1., 1., 1., 1.]]),
'items': [('LLL', ), ('MMM', )],
'repertoire_index_mapping': col_name_index,
'path': path,
'identifier': 1
}),
ComparisonDataBatch(
**{
'matrix': np.array([[0., 1., 0., 0.], [0., 1., 0., 1.]]),
'items': [('DDD', ), ('EEE', )],
'repertoire_index_mapping': col_name_index,
'path': path,
'identifier': 2
}),
ComparisonDataBatch(
**{
'matrix': np.array([[0., 1., 1., 1.], [0., 0., 1., 1.]]),
'items': [('FFF', ), ('CCC', )],
'repertoire_index_mapping': col_name_index,
'path': path,
'identifier': 3
}),
ComparisonDataBatch(
**{
'matrix': np.array([[0., 0., 0., 1.]]),
'items': [('AAA', )],
'repertoire_index_mapping': col_name_index,
'path': path,
'identifier': 4
})
]
p_values = SequenceFilterHelper.find_label_associated_sequence_p_values(
comparison_data, repertoires,
Label('l1', [True, False], positive_class=True))
print(p_values)
self.assertTrue(
np.allclose([
SequenceFilterHelper.INVALID_P_VALUE, 0.1666666666666667,
0.5000000000000001, 1., SequenceFilterHelper.INVALID_P_VALUE,
0.8333333333333331, 1., 1., 2
],
p_values,
equal_nan=True))
shutil.rmtree(path)