Commit ff86541a authored by unknown's avatar unknown
Browse files

Merge remote-tracking branch 'remotes/mine/qm' into DAG

parents 1ea69f5f d4a5703b

deepchem/molnet/check_availability.py

+9 −0
Original line number Diff line number Diff line
@@ -142,12 +142,21 @@ CheckFeaturizer = { 
    ('kaggle', 'rf_regression'): [None, 14293],

    ('pdbbind', 'tf_regression'): ['grid', 2052],

    ('pdbbind', 'rf_regression'): ['grid', 2052],

    ('qm7', 'tf_regression'): ['ECFP', 1024],

    ('qm7', 'rf_regression'): ['ECFP', 1024],

    ('qm7', 'graphconvreg'): ['GraphConv', 75],

    ('qm7', 'tf_regression_ft'): ['CoulombMatrix', [23, 23]],

    ('qm7', 'dtnn'): ['CoulombMatrix', [23, 23]],

    ('qm7b', 'tf_regression_ft'): ['CoulombMatrix', [23, 23]],

    ('qm7b', 'dtnn'): ['CoulombMatrix', [23, 23]],

    ('qm8', 'tf_regression'): ['ECFP', 1024],

    ('qm8', 'rf_regression'): ['ECFP', 1024],

    ('qm8', 'graphconvreg'): ['GraphConv', 75],

    ('qm8', 'tf_regression_ft'): ['CoulombMatrix', [26, 26]],

    ('qm8', 'dtnn'): ['CoulombMatrix', [26, 26]],

    ('qm9', 'tf_regression'): ['ECFP', 1024],

    ('qm9', 'rf_regression'): ['ECFP', 1024],

    ('qm9', 'graphconvreg'): ['GraphConv', 75],

    ('qm9', 'tf_regression_ft'): ['CoulombMatrix', [29, 29]],

    ('qm9', 'dtnn'): ['CoulombMatrix', [29, 29]]

}

deepchem/molnet/load_function/pdbbind_datasets.py

+72 −17
Original line number Diff line number Diff line
@@ -52,9 +52,10 @@ def featurize_pdbbind(data_dir=None, feat="grid", subset="core"): 


def load_pdbbind_grid(split="random",

                      featurizer="grid",

                      subset="full",

                      subset="core",

                      reload=True):

  """Load PDBBind datasets. Does not do train/test split"""

  if featurizer == 'grid':

    dataset, tasks = featurize_pdbbind(feat=featurizer, subset=subset)



    splitters = {
@@ -71,5 +72,59 @@ def load_pdbbind_grid(split="random", 
      valid = transformer.transform(valid)

    for transformer in transformers:

      test = transformer.transform(test)

  else:

    if "DEEPCHEM_DATA_DIR" in os.environ:

      data_dir = os.environ["DEEPCHEM_DATA_DIR"]

    else:

      data_dir = "/tmp"

    if reload:

      save_dir = os.path.join(data_dir, "pdbbind_" + subset + "/" + featurizer + "/" + split)



    dataset_file = os.path.join(data_dir, subset + "_smiles_labels.csv")



    if not os.path.exists(dataset_file):

      os.system(

          'wget -P ' + data_dir +

          ' http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/' + subset + "_smiles_labels.csv"

      )



    tasks = ["-logKd/Ki"]

    if reload:

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

          save_dir)

      if loaded:

        return tasks, all_dataset, transformers



    if featurizer == 'ECFP':

      featurizer = deepchem.feat.CircularFingerprint(size=1024)

    elif featurizer == 'GraphConv':

      featurizer = deepchem.feat.ConvMolFeaturizer()

    elif featurizer == 'Weave':

      featurizer = deepchem.feat.WeaveFeaturizer()

    elif featurizer == 'Raw':

      featurizer = deepchem.feat.RawFeaturizer()



    loader = deepchem.data.CSVLoader(

        tasks=tasks, smiles_field="smiles", featurizer=featurizer)

    dataset = loader.featurize(dataset_file, shard_size=8192)

    transformers = [

        deepchem.trans.NormalizationTransformer(

            transform_y=True, dataset=dataset)

    ]



    for transformer in transformers:

      dataset = transformer.transform(dataset)



    splitters = {

        'index': deepchem.splits.IndexSplitter(),

        'random': deepchem.splits.RandomSplitter(),

        'scaffold': deepchem.splits.ScaffoldSplitter()

    }

    splitter = splitters[split]

    train, valid, test = splitter.train_valid_test_split(dataset)



    if reload:

      deepchem.utils.save.save_dataset_to_disk(save_dir, train, valid, test,

                                               transformers)



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

deepchem/molnet/load_function/qm7_datasets.py

+46 −18
Original line number Diff line number Diff line
@@ -18,7 +18,18 @@ def load_qm7_from_mat(featurizer='CoulombMatrix', 
    data_dir = os.environ["DEEPCHEM_DATA_DIR"]

  else:

    data_dir = "/tmp"

  if reload:

    save_dir = os.path.join(data_dir, "qm7/" + featurizer + "/" + split)

    

  qm7_tasks = ["u0_atom"]



  if reload:

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

        save_dir)

    if loaded:

      return qm7_tasks, all_dataset, transformers

  

  if featurizer == 'CoulombMatrix':

    dataset_file = os.path.join(data_dir, "qm7.mat")



    if not os.path.exists(dataset_file):
@@ -26,14 +37,29 @@ def load_qm7_from_mat(featurizer='CoulombMatrix', 
          'wget -P ' + data_dir +

          ' http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/qm7.mat'

      )



    dataset = scipy.io.loadmat(dataset_file)



    X = dataset['X']

    y = dataset['T']

    w = np.ones_like(y)

    dataset = deepchem.data.DiskDataset.from_numpy(X, y, w, ids=None)

  print(len(dataset))

  else:

    dataset_file = os.path.join(data_dir, "qm7.csv")

    if not os.path.exists(dataset_file):

      os.system(

          'wget -P ' + data_dir +

          ' http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/qm7.csv '

      )

    if featurizer == 'ECFP':

      featurizer = deepchem.feat.CircularFingerprint(size=1024)

    elif featurizer == 'GraphConv':

      featurizer = deepchem.feat.ConvMolFeaturizer()

    elif featurizer == 'Weave':

      featurizer = deepchem.feat.WeaveFeaturizer()

    elif featurizer == 'Raw':

      featurizer = deepchem.feat.RawFeaturizer()

    loader = deepchem.data.CSVLoader(

        tasks=qm7_tasks, smiles_field="smiles", featurizer=featurizer)

    dataset = loader.featurize(dataset_file)

      

  splitters = {

      'index': deepchem.splits.IndexSplitter(),
@@ -54,8 +80,10 @@ def load_qm7_from_mat(featurizer='CoulombMatrix', 
    train_dataset = transformer.transform(train_dataset)

    valid_dataset = transformer.transform(valid_dataset)

    test_dataset = transformer.transform(test_dataset)

  if reload:

    deepchem.utils.save.save_dataset_to_disk(

        save_dir, train_dataset, valid_dataset, test_dataset, transformers)

    

  qm7_tasks = np.arange(y.shape[0])

  return qm7_tasks, (train_dataset, valid_dataset, test_dataset), transformers

deepchem/molnet/load_function/qm8_datasets.py

+33 −13
Original line number Diff line number Diff line
@@ -17,6 +17,7 @@ def load_qm8(featurizer='CoulombMatrix', split='random', reload=True): 
  if reload:

    save_dir = os.path.join(data_dir, "qm8/" + featurizer + "/" + split)



  if featurizer == 'CoulombMatrix':

    dataset_file = os.path.join(data_dir, "qm8.sdf")



    if not os.path.exists(dataset_file):
@@ -26,6 +27,13 @@ def load_qm8(featurizer='CoulombMatrix', split='random', reload=True): 
      )

      os.system('tar -zxvf ' + os.path.join(data_dir, 'gdb8.tar.gz') + ' -C ' +

                data_dir)

  else:

    dataset_file = os.path.join(data_dir, "qm8.csv")

    if not os.path.exists(dataset_file):

      os.system(

          'wget -P ' + data_dir +

          ' http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/qm8.csv '

      )



  qm8_tasks = [

      "E1-CC2", "E2-CC2", "f1-CC2", "f2-CC2", "E1-PBE0", "E2-PBE0", "f1-PBE0",
@@ -46,6 +54,18 @@ def load_qm8(featurizer='CoulombMatrix', split='random', reload=True): 
        smiles_field="smiles",

        mol_field="mol",

        featurizer=featurizer)

  else:

    if featurizer == 'ECFP':

      featurizer = deepchem.feat.CircularFingerprint(size=1024)

    elif featurizer == 'GraphConv':

      featurizer = deepchem.feat.ConvMolFeaturizer()

    elif featurizer == 'Weave':

      featurizer = deepchem.feat.WeaveFeaturizer()

    elif featurizer == 'Raw':

      featurizer = deepchem.feat.RawFeaturizer()

    loader = deepchem.data.CSVLoader(

        tasks=qm8_tasks, smiles_field="smiles", featurizer=featurizer)

    

  dataset = loader.featurize(dataset_file)

  splitters = {

      'index': deepchem.splits.IndexSplitter(),

deepchem/molnet/load_function/qm9_datasets.py

+35 −13
Original line number Diff line number Diff line
@@ -20,6 +20,8 @@ def load_qm9(featurizer='CoulombMatrix', split='random', reload=True): 
  if reload:

    save_dir = os.path.join(data_dir, "qm9/" + featurizer + "/" + split)





  if featurizer == 'CoulombMatrix':

    dataset_file = os.path.join(data_dir, "gdb9.sdf")



    if not os.path.exists(dataset_file):
@@ -29,6 +31,13 @@ def load_qm9(featurizer='CoulombMatrix', split='random', reload=True): 
      )

      os.system('tar -zxvf ' + os.path.join(data_dir, 'gdb9.tar.gz') + ' -C ' +

                data_dir)

  else:

    dataset_file = os.path.join(data_dir, "qm9.csv")

    if not os.path.exists(dataset_file):

      os.system(

          'wget -P ' + data_dir +

          ' http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/qm9.csv '

      )

      

  qm9_tasks = [

      "A", "B", "C", "mu", "alpha", "homo", "lumo", "gap", "r2", "zpve", "cv",
@@ -48,6 +57,19 @@ def load_qm9(featurizer='CoulombMatrix', split='random', reload=True): 
        smiles_field="smiles",

        mol_field="mol",

        featurizer=featurizer)

  else:

    if featurizer == 'ECFP':

      featurizer = deepchem.feat.CircularFingerprint(size=1024)

    elif featurizer == 'GraphConv':

      featurizer = deepchem.feat.ConvMolFeaturizer()

    elif featurizer == 'Weave':

      featurizer = deepchem.feat.WeaveFeaturizer()

    elif featurizer == 'Raw':

      featurizer = deepchem.feat.RawFeaturizer()

    loader = deepchem.data.CSVLoader(

        tasks=qm9_tasks, smiles_field="smiles", featurizer=featurizer)





  dataset = loader.featurize(dataset_file)

  splitters = {

      'index': deepchem.splits.IndexSplitter(),

CRA Git | Maintained and supported by SUSTech CRA and CCSE