yapf

  return deepchem.data.DiskDataset(dataset_dir), tasks

def load_pdbbind(featurizer="grid", split="random", subset="core", reload=True):

  """Loads and featurizes PDBBind dataset."""

def load_pdbbind_grid(split="random",

                      featurizer="grid",

                      subset="core",

    return tasks, (train, valid, test), transformers

def load_pdbbind(featurizer="grid", split="random", subset="core", reload=True):

  """Load and featurize raw PDBBind dataset."""

  pdbbind_tasks = ["-logKd/Ki"]

  data_dir = deepchem.utils.get_data_dir()

  if reload:

    save_dir = os.path.join(data_dir, "pdbbind/" + featurizer + "/" + str(split))

    save_dir = os.path.join(data_dir,

                            "pdbbind/" + featurizer + "/" + str(split))

    loaded, all_dataset, transformers = deepchem.utils.save.load_dataset_from_disk(

        save_dir)

    if loaded:

      pdb = line[0]

      if len(pdb) == 4:

        pdbs.append(pdb)

  protein_files = [os.path.join(data_folder, pdb, "%s_protein.pdb" % pdb)

               for pdb in pdbs]

  ligand_files = [os.path.join(data_folder, pdb, "%s_ligand.sdf" % pdb)

               for pdb in pdbs]

  protein_files = [

      os.path.join(data_folder, pdb, "%s_protein.pdb" % pdb) for pdb in pdbs

  ]

  ligand_files = [

      os.path.join(data_folder, pdb, "%s_ligand.sdf" % pdb) for pdb in pdbs

  ]

  # Extract labels

  labels = []

  with open(labels_file, "r") as f:

  else:

    raise ValueError("Featurizer not supported")

  print("Featurizing Complexes")

  features = featurizer.featurize_complexes(ligand_files, protein_files, log_every_n=1)

  features = featurizer.featurize_complexes(

      ligand_files, protein_files, log_every_n=1)

  dataset = deepchem.data.DiskDataset.from_numpy(features, labels)

  # No transformations of data

  transformers = []