Commit 31aaf9c2 authored by Bharath Ramsundar's avatar Bharath Ramsundar Committed by GitHub
Browse files

Merge pull request #383 from calebgeniesse/clinical_trials 

clintox dataset
parents 73d71f26 10209c98

README.md

+13 −0
Original line number Diff line number Diff line
@@ -212,6 +212,10 @@ Index splitting 
|           |Multitask network   |0.830              |0.678              |

|           |robust MT-NN        |0.825              |0.680              |

|           |graph convolution   |0.821              |0.720              |

|clintox    |logistic regression |0.967              |0.676              |

|           |Multitask network   |0.934              |0.830              |

|           |robust MT-NN        |0.949              |0.827              |

|           |graph convolution   |0.946              |0.860              |



Random splitting
@@ -237,6 +241,10 @@ Random splitting 
|           |Multitask network   |0.836        	     |0.684              |

|           |robust MT-NN        |0.822              |0.681              |

|           |graph convolution   |0.820        	     |0.717              |

|clintox    |logistic regression |0.972              |0.725              |

|           |Multitask network   |0.951              |0.834              |

|           |robust MT-NN        |0.959              |0.830              |

|           |graph convolution   |0.975              |0.876              |



Scaffold splitting
@@ -262,6 +270,10 @@ Scaffold splitting 
|           |Multitask network   |0.828              |0.617              |

|           |robust MT-NN        |0.830              |0.614              |

|           |graph convolution   |0.832              |0.638              |

|clintox    |logistic regression |0.960              |0.803              |

|           |Multitask network   |0.947              |0.862              |

|           |robust MT-NN        |0.953              |0.890              |

|           |graph convolution   |0.957              |0.823              |



* Regression
@@ -313,6 +325,7 @@ Number of tasks and examples in the datasets 
|pcba            |128        |439863     |

|sider           |27         |1427       |

|toxcast         |617        |8615       |

|clintox         |2          |1491       |

|delaney         |1          |1128       |

|sampl           |1          |643        |

|kaggle          |15         |173065     |

examples/benchmark.py

+7 −6
Original line number Diff line number Diff line
@@ -53,6 +53,7 @@ from pdbbind.pdbbind_datasets import load_pdbbind_grid 
from chembl.chembl_datasets import load_chembl

from gdb7.gdb7_datasets import load_gdb7

from sampl.sampl_datasets import load_sampl

from clintox.clintox_datasets import load_clintox



def benchmark_loading_datasets(hyper_parameters, 

                               dataset='tox21', model='tf', split=None,
@@ -66,7 +67,7 @@ def benchmark_loading_datasets(hyper_parameters, 
      hyper parameters including dropout rate, learning rate, etc.

  dataset: string, optional (default='tox21')

      choice of which dataset to use, should be: tox21, muv, sider, 

      toxcast, pcba, delaney, kaggle, nci

      toxcast, pcba, delaney, kaggle, nci, clintox

  model: string,  optional (default='tf')

      choice of which model to use, should be: rf, tf, tf_robust, logreg,

      graphconv, tf_regression, graphconvreg
@@ -76,7 +77,7 @@ def benchmark_loading_datasets(hyper_parameters, 
      path of result file

  """

  

  if dataset in ['muv', 'pcba', 'tox21', 'sider', 'toxcast']:

  if dataset in ['muv', 'pcba', 'tox21', 'sider', 'toxcast', 'clintox']:

    mode = 'classification'

  elif dataset in ['kaggle', 'delaney', 'nci', 'pdbbind', 'chembl', 

                   'gdb7', 'sampl']:
@@ -133,7 +134,7 @@ def benchmark_loading_datasets(hyper_parameters, 
                       'kaggle': load_kaggle, 'delaney': load_delaney,

                       'pdbbind': load_pdbbind_grid,

                       'chembl': load_chembl, 'gdb7': load_gdb7,

                       'sampl': load_sampl}

                       'sampl': load_sampl, 'clintox': load_clintox}

  

  print('-------------------------------------')

  print('Benchmark %s on dataset: %s' % (model, dataset))
@@ -545,7 +546,7 @@ if __name__ == '__main__': 
           'tf_regression, graphconvreg')

  parser.add_argument('-d', action='append', dest='dataset_args', default=[], 

      help='Choice of dataset: tox21, sider, muv, toxcast, pcba, ' + 

           'kaggle, delaney, nci, pdbbindi, chembl, gdb7')

           'kaggle, delaney, nci, pdbbindi, chembl, gdb7, clintox')

  args = parser.parse_args()

  #Datasets and models used in the benchmark test

  splitters = args.splitter_args
@@ -558,7 +559,7 @@ if __name__ == '__main__': 
    models = ['tf', 'tf_robust', 'logreg', 'graphconv', 

              'tf_regression', 'graphconvreg']

  if len(datasets) == 0:

    datasets = ['tox21', 'sider', 'muv', 'toxcast', 'pcba', 

    datasets = ['tox21', 'sider', 'muv', 'toxcast', 'pcba', 'clintox',

                'delaney', 'nci', 'kaggle', 'pdbbind', 'chembl', 'gdb7']



  #input hyperparameters
@@ -604,7 +605,7 @@ if __name__ == '__main__': 


  for split in splitters:

    for dataset in datasets:

      if dataset in ['tox21', 'sider', 'muv', 'toxcast', 'pcba']:

      if dataset in ['tox21', 'sider', 'muv', 'toxcast', 'pcba', 'clintox']:

        for model in models:

          if model in ['tf', 'tf_robust', 'logreg', 'graphconv']:

            benchmark_loading_datasets(

examples/clintox/__init__.py

0 → 100644
+0 −0

Empty file added.

examples/clintox/clintox_datasets.py

0 → 100644
+52 −0
Original line number Diff line number Diff line 
"""

Clinical Toxicity (clintox) dataset loader.

@author Caleb Geniesse

"""



from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals



import os

import deepchem as dc





def load_clintox(featurizer='ECFP', split='index'):

  """Load clintox datasets."""



  # Load clintox dataset

  print("About to load clintox dataset.")

  current_dir = os.path.dirname(os.path.realpath(__file__))

  dataset_file = os.path.join(

      current_dir, "./datasets/clintox.csv.gz")

  dataset = dc.utils.save.load_from_disk(dataset_file)

  clintox_tasks = dataset.columns.values[1:].tolist()

  print("Tasks in dataset: %s" % (clintox_tasks))

  print("Number of tasks in dataset: %s" % str(len(clintox_tasks)))

  print("Number of examples in dataset: %s" % str(dataset.shape[0]))



  # Featurize clintox dataset

  print("About to featurize clintox dataset.")

  featurizers = {'ECFP': dc.feat.CircularFingerprint(size=1024),

                 'GraphConv': dc.feat.ConvMolFeaturizer()}

  featurizer = featurizers[featurizer]

  loader = dc.data.CSVLoader(

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

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



  # Transform clintox dataset

  print("About to transform clintox dataset.")

  transformers = [

      dc.trans.BalancingTransformer(transform_w=True, dataset=dataset)]

  for transformer in transformers:

    dataset = transformer.transform(dataset)



  # Split clintox dataset

  print("About to split clintox dataset.")

  splitters = {'index': dc.splits.IndexSplitter(),

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

               'scaffold': dc.splits.ScaffoldSplitter()}

  splitter = splitters[split]

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



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

examples/clintox/clintox_graph_conv.py

0 → 100644
+72 −0
Original line number Diff line number Diff line 
"""

Script that trains graph-conv models on clintox dataset.

@author Caleb Geniesse

"""

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals



import numpy as np

import tensorflow as tf

from keras import backend as K



import deepchem as dc

from clintox_datasets import load_clintox



# Only for debug!

np.random.seed(123)



g = tf.Graph()

sess = tf.Session(graph=g)

K.set_session(sess)



with g.as_default():

  # Load clintox dataset

  n_features = 1024

  clintox_tasks, clintox_datasets, transformers = load_clintox(

      featurizer='GraphConv', split='random')

  train_dataset, valid_dataset, test_dataset = clintox_datasets



  # Fit models

  metric = dc.metrics.Metric(dc.metrics.roc_auc_score, np.mean,

                             mode="classification")



  # Do setup required for tf/keras models

  # Number of features on conv-mols

  n_feat = 75

  # Batch size of models

  batch_size = 50

  graph_model = dc.nn.SequentialGraph(n_feat)

  graph_model.add(dc.nn.GraphConv(64, activation='relu'))

  graph_model.add(dc.nn.BatchNormalization(epsilon=1e-5, mode=1))

  graph_model.add(dc.nn.GraphPool())

  graph_model.add(dc.nn.GraphConv(64, activation='relu'))

  graph_model.add(dc.nn.BatchNormalization(epsilon=1e-5, mode=1))

  graph_model.add(dc.nn.GraphPool())

  # Gather Projection

  graph_model.add(dc.nn.Dense(128, activation='relu'))

  graph_model.add(dc.nn.BatchNormalization(epsilon=1e-5, mode=1))

  graph_model.add(dc.nn.GraphGather(batch_size, activation="tanh"))

  # Dense post-processing layer



  with tf.Session() as sess:

    model = dc.models.MultitaskGraphClassifier(sess, graph_model,

                                               len(clintox_tasks),

                                               batch_size=batch_size,

                                               learning_rate=1e-3,

                                               learning_rate_decay_time=1000,

                                               optimizer_type="adam",

                                               beta1=.9, beta2=.999)



    # Fit trained model

    model.fit(train_dataset, nb_epoch=10)



    print("Evaluating model")

    train_scores = model.evaluate(train_dataset, [metric], transformers)

    valid_scores = model.evaluate(valid_dataset, [metric], transformers)



    print("Train scores")

    print(train_scores)



    print("Validation scores")

    print(valid_scores)

CRA Git | Maintained and supported by SUSTech CRA and CCSE