Unverified Commit 0f2a6f11 authored by Suzukazole's avatar Suzukazole
Browse files

rerun YAPF 0.22

parent 14d55f8c

deepchem/molnet/dnasim.py

+23 −23
Original line number Diff line number Diff line
@@ -38,8 +38,8 @@ def simple_motif_embedding(motif_name, seq_length, num_seqs, GC_fraction): 
  if motif_name is None:

    embedders = []

  else:

    loaded_motifs = synthetic.LoadedEncodeMotifs(simdna.ENCODE_MOTIFS_PATH,

                                                 pseudocountProb=0.001)

    loaded_motifs = synthetic.LoadedEncodeMotifs(

        simdna.ENCODE_MOTIFS_PATH, pseudocountProb=0.001)

    substring_generator = synthetic.PwmSamplerFromLoadedMotifs(

        loaded_motifs, motif_name)

    embedders = [
@@ -73,8 +73,8 @@ def motif_density(motif_name, 
  """

  import simdna

  from simdna import synthetic

  loaded_motifs = synthetic.LoadedEncodeMotifs(simdna.ENCODE_MOTIFS_PATH,

                                               pseudocountProb=0.001)

  loaded_motifs = synthetic.LoadedEncodeMotifs(

      simdna.ENCODE_MOTIFS_PATH, pseudocountProb=0.001)

  substring_generator = synthetic.PwmSamplerFromLoadedMotifs(

      loaded_motifs, motif_name)

  if central_bp is not None:
@@ -175,8 +175,8 @@ def simulate_motif_counting(motif_name, seq_length, pos_counts, neg_counts, 
  neg_count_sequence_array, negative_embedding_arr = motif_density(

      motif_name, seq_length, num_pos, neg_counts[0], neg_counts[1],

      GC_fraction)

  sequence_arr = np.concatenate(

      (pos_count_sequence_array, neg_count_sequence_array))

  sequence_arr = np.concatenate((pos_count_sequence_array,

                                 neg_count_sequence_array))

  y = np.array([[True]] * num_pos + [[False]] * num_neg)

  embedding_arr = positive_embedding_arr + negative_embedding_arr

  return sequence_arr, y, embedding_arr
@@ -228,8 +228,8 @@ def simulate_motif_density_localization(motif_name, seq_length, center_size, 
  unlocalized_density_sequence_array, negative_embedding_arr = motif_density(

      motif_name, seq_length, num_neg, min_motif_counts, max_motif_counts,

      GC_fraction)

  sequence_arr = np.concatenate(

      (localized_density_sequence_array, unlocalized_density_sequence_array))

  sequence_arr = np.concatenate((localized_density_sequence_array,

                                 unlocalized_density_sequence_array))

  y = np.array([[True]] * num_pos + [[False]] * num_neg)

  embedding_arr = positive_embedding_arr + negative_embedding_arr

  return sequence_arr, y, embedding_arr
@@ -262,8 +262,8 @@ def simulate_multi_motif_embedding(motif_names, seq_length, min_num_motifs, 


  import simdna

  from simdna import synthetic

  loaded_motifs = synthetic.LoadedEncodeMotifs(simdna.ENCODE_MOTIFS_PATH,

                                               pseudocountProb=0.001)

  loaded_motifs = synthetic.LoadedEncodeMotifs(

      simdna.ENCODE_MOTIFS_PATH, pseudocountProb=0.001)



  def get_embedder(motif_name):

    substring_generator = synthetic.PwmSamplerFromLoadedMotifs(
@@ -288,7 +288,8 @@ def simulate_multi_motif_embedding(motif_names, seq_length, min_num_motifs, 
  sequence_arr = np.array(

      [generated_seq.seq for generated_seq in generated_sequences])

  label_generator = synthetic.IsInTraceLabelGenerator(np.asarray(motif_names))

  y = np.array([

  y = np.array(

      [

          label_generator.generateLabels(generated_seq)

          for generated_seq in generated_sequences

      ],
@@ -299,10 +300,9 @@ def simulate_multi_motif_embedding(motif_names, seq_length, min_num_motifs, 
  return sequence_arr, y, embedding_arr





def simulate_differential_accessibility(pos_motif_names, neg_motif_names,

                                        seq_length, min_num_motifs,

                                        max_num_motifs, num_pos, num_neg,

                                        GC_fraction):

def simulate_differential_accessibility(

    pos_motif_names, neg_motif_names, seq_length, min_num_motifs,

    max_num_motifs, num_pos, num_neg, GC_fraction):

  """

    Generates data for differential accessibility task.
@@ -334,8 +334,8 @@ def simulate_differential_accessibility(pos_motif_names, neg_motif_names, 
  neg_motif_sequence_arr, _, negative_embedding_arr = simulate_multi_motif_embedding(

      neg_motif_names, seq_length, min_num_motifs, max_num_motifs, num_neg,

      GC_fraction)

  sequence_arr = np.concatenate(

      (pos_motif_sequence_arr, neg_motif_sequence_arr))

  sequence_arr = np.concatenate((pos_motif_sequence_arr,

                                 neg_motif_sequence_arr))

  y = np.array([[True]] * num_pos + [[False]] * num_neg)

  embedding_arr = positive_embedding_arr + negative_embedding_arr

  return sequence_arr, y, embedding_arr
@@ -372,8 +372,8 @@ def simulate_heterodimer_grammar(motif1, motif2, seq_length, min_spacing, 
    """

  import simdna

  from simdna import synthetic

  loaded_motifs = synthetic.LoadedEncodeMotifs(simdna.ENCODE_MOTIFS_PATH,

                                               pseudocountProb=0.001)

  loaded_motifs = synthetic.LoadedEncodeMotifs(

      simdna.ENCODE_MOTIFS_PATH, pseudocountProb=0.001)

  motif1_generator = synthetic.ReverseComplementWrapper(

      synthetic.PwmSamplerFromLoadedMotifs(loaded_motifs, motif1))

  motif2_generator = synthetic.ReverseComplementWrapper(

deepchem/molnet/load_function/bace_datasets.py

+2 −3
Original line number Diff line number Diff line
@@ -18,9 +18,8 @@ class _BaceLoader(_MolnetLoader): 
    dataset_file = os.path.join(self.data_dir, "bace.csv")

    if not os.path.exists(dataset_file):

      dc.utils.data_utils.download_url(url=BACE_URL, dest_dir=self.data_dir)

    loader = dc.data.CSVLoader(tasks=self.tasks,

                               feature_field="mol",

                               featurizer=self.featurizer)

    loader = dc.data.CSVLoader(

        tasks=self.tasks, feature_field="mol", featurizer=self.featurizer)

    return loader.create_dataset(dataset_file, shard_size=8192)

deepchem/molnet/load_function/factors_datasets.py

+2 −3
Original line number Diff line number Diff line
@@ -76,9 +76,8 @@ def gen_factors(FACTORS_tasks, 
  # Featurize the FACTORS dataset

  logger.info("About to featurize the FACTORS dataset")

  featurizer = deepchem.feat.UserDefinedFeaturizer(merck_descriptors)

  loader = deepchem.data.UserCSVLoader(tasks=FACTORS_tasks,

                                       id_field="Molecule",

                                       featurizer=featurizer)

  loader = deepchem.data.UserCSVLoader(

      tasks=FACTORS_tasks, id_field="Molecule", featurizer=featurizer)



  logger.info("Featurizing the train dataset...")

  train_dataset = loader.featurize(train_files, shard_size=shard_size)

deepchem/molnet/load_function/hppb_datasets.py

+2 −3
Original line number Diff line number Diff line
@@ -32,9 +32,8 @@ class _HPPBLoader(_MolnetLoader): 
    dataset_file = os.path.join(self.data_dir, "hppb.csv")

    if not os.path.exists(dataset_file):

      dc.utils.data_utils.download_url(url=HPPB_URL, dest_dir=self.data_dir)

    loader = dc.data.CSVLoader(tasks=self.tasks,

                               feature_field="smile",

                               featurizer=self.featurizer)

    loader = dc.data.CSVLoader(

        tasks=self.tasks, feature_field="smile", featurizer=self.featurizer)

    dataset = loader.create_dataset(dataset_file, shard_size=2000)

    remove_missing_entries(dataset)

    return dataset

deepchem/molnet/load_function/kaggle_datasets.py

+4 −5
Original line number Diff line number Diff line
@@ -72,9 +72,8 @@ def gen_kaggle(KAGGLE_tasks, 
  logger.info("About to featurize KAGGLE dataset.")

  featurizer = deepchem.feat.UserDefinedFeaturizer(merck_descriptors)



  loader = deepchem.data.UserCSVLoader(tasks=KAGGLE_tasks,

                                       id_field="Molecule",

                                       featurizer=featurizer)

  loader = deepchem.data.UserCSVLoader(

      tasks=KAGGLE_tasks, id_field="Molecule", featurizer=featurizer)



  logger.info("Featurizing train datasets")

  train_dataset = loader.featurize(train_files, shard_size=shard_size)
@@ -97,8 +96,8 @@ def gen_kaggle(KAGGLE_tasks, 
  transformers = get_transformers(train_dataset)



  for transformer in transformers:

    logger.info("Performing transformations with %s" %

                transformer.__class__.__name__)

    logger.info(

        "Performing transformations with %s" % transformer.__class__.__name__)

    logger.info("Transforming datasets")

    train_dataset = transformer.transform(train_dataset)

    valid_dataset = transformer.transform(valid_dataset)

CRA Git | Maintained and supported by SUSTech CRA and CCSE