Commit 8545a632 authored by miaecle's avatar miaecle
Browse files

refining module

parent 72025959

deepchem/molnet/__init__.py

+1 −1
Original line number Diff line number Diff line
@@ -3,6 +3,7 @@ from __future__ import division 
from __future__ import unicode_literals



from deepchem.molnet.load_function.bace_datasets import load_bace_classification, load_bace_regression

from deepchem.molnet.load_function.bbbp_datasets import load_bbbp

from deepchem.molnet.load_function.chembl_datasets import load_chembl

from deepchem.molnet.load_function.clearance_datasets import load_clearance

from deepchem.molnet.load_function.clintox_datasets import load_clintox
@@ -24,5 +25,4 @@ from deepchem.molnet.load_function.sider_datasets import load_sider 
from deepchem.molnet.load_function.tox21_datasets import load_tox21

from deepchem.molnet.load_function.toxcast_datasets import load_toxcast





from deepchem.molnet.run_benchmark import run_benchmark

deepchem/molnet/check_availability.py

+63 −56
Original line number Diff line number Diff line 
CheckFeaturizer = {

('tox21', 'logreg'):      ['ECFP', 1024],

('tox21', 'tf'):          ['ECFP', 1024],

('tox21', 'tf_robust'):   ['ECFP', 1024],

('tox21', 'rf'):          ['ECFP', 1024],

('tox21', 'irv'):         ['ECFP', 1024],

('tox21', 'graphconv'):   ['GraphConv', 75],

('bace_c', 'logreg'):     ['ECFP', 1024],

('bace_c', 'tf'):         ['ECFP', 1024],

('bace_c', 'tf_robust'):  ['ECFP', 1024],

('bace_c', 'rf'):         ['ECFP', 1024],

('bace_c', 'irv'):        ['ECFP', 1024],

('bace_c', 'graphconv'):  ['GraphConv', 75],

('bbbp', 'logreg'):       ['ECFP', 1024],

('bbbp', 'tf'):           ['ECFP', 1024],

('bbbp', 'tf_robust'):    ['ECFP', 1024],

('bbbp', 'rf'):           ['ECFP', 1024],

('bbbp', 'irv'):          ['ECFP', 1024],

('bbbp', 'graphconv'):    ['GraphConv', 75],

('clintox', 'logreg'):    ['ECFP', 1024],

('clintox', 'tf'):        ['ECFP', 1024],

('clintox', 'tf_robust'): ['ECFP', 1024],

('clintox', 'rf'):        ['ECFP', 1024],

('clintox', 'irv'):       ['ECFP', 1024],

('clintox', 'graphconv'): ['GraphConv', 75],

('hiv', 'logreg'):        ['ECFP', 1024],

('hiv', 'tf'):            ['ECFP', 1024],

('hiv', 'tf_robust'):     ['ECFP', 1024],

('hiv', 'rf'):            ['ECFP', 1024],

('hiv', 'irv'):           ['ECFP', 1024],

('hiv', 'graphconv'):     ['GraphConv', 75],

('muv', 'logreg'):        ['ECFP', 1024],

('muv', 'tf'):            ['ECFP', 1024],

('muv', 'tf_robust'):     ['ECFP', 1024],
@@ -17,64 +35,52 @@ CheckFeaturizer = { 
('pcba', 'rf'):           ['ECFP', 1024],

('pcba', 'irv'):          ['ECFP', 1024],

('pcba', 'graphconv'):    ['GraphConv', 75],

('toxcast', 'logreg'):    ['ECFP', 1024],

('toxcast', 'tf'):        ['ECFP', 1024],

('toxcast', 'tf_robust'): ['ECFP', 1024],

('toxcast', 'rf'):        ['ECFP', 1024],

('toxcast', 'irv'):       ['ECFP', 1024],

('toxcast', 'graphconv'): ['GraphConv', 75],

('sider', 'logreg'):      ['ECFP', 1024],

('sider', 'tf'):          ['ECFP', 1024],

('sider', 'tf_robust'):   ['ECFP', 1024],

('sider', 'rf'):          ['ECFP', 1024],

('sider', 'irv'):         ['ECFP', 1024],

('sider', 'graphconv'):   ['GraphConv', 75],

('clintox', 'logreg'):    ['ECFP', 1024],

('clintox', 'tf'):        ['ECFP', 1024],

('clintox', 'tf_robust'): ['ECFP', 1024],

('clintox', 'rf'):        ['ECFP', 1024],

('clintox', 'irv'):       ['ECFP', 1024],

('clintox', 'graphconv'): ['GraphConv', 75],

('hiv', 'logreg'):        ['ECFP', 1024],

('hiv', 'tf'):            ['ECFP', 1024],

('hiv', 'tf_robust'):     ['ECFP', 1024],

('hiv', 'rf'):            ['ECFP', 1024],

('hiv', 'irv'):           ['ECFP', 1024],

('hiv', 'graphconv'):     ['GraphConv', 75],

('bace_c', 'logreg'):     ['ECFP', 1024],

('bace_c', 'tf'):         ['ECFP', 1024],

('bace_c', 'tf_robust'):  ['ECFP', 1024],

('bace_c', 'rf'):         ['ECFP', 1024],

('bace_c', 'irv'):        ['ECFP', 1024],

('bace_c', 'graphconv'):  ['GraphConv', 75],

('tox21', 'logreg'):      ['ECFP', 1024],

('tox21', 'tf'):          ['ECFP', 1024],

('tox21', 'tf_robust'):   ['ECFP', 1024],

('tox21', 'rf'):          ['ECFP', 1024],

('tox21', 'irv'):         ['ECFP', 1024],

('tox21', 'graphconv'):   ['GraphConv', 75],

('toxcast', 'logreg'):    ['ECFP', 1024],

('toxcast', 'tf'):        ['ECFP', 1024],

('toxcast', 'tf_robust'): ['ECFP', 1024],

('toxcast', 'rf'):        ['ECFP', 1024],

('toxcast', 'irv'):       ['ECFP', 1024],

('toxcast', 'graphconv'): ['GraphConv', 75],



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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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



('kaggle', 'tf_regression'):  [None, 14293],

('kaggle', 'rf_regression'):  [None, 14293],
@@ -87,27 +93,28 @@ CheckFeaturizer = { 
}



CheckSplit = {

'tox21':  ['index', 'random', 'scaffold', 'butina'],

'muv':    ['index', 'random', 'scaffold'], 

'pcba':   ['index', 'random', 'scaffold'],

'sider':  ['index', 'random', 'scaffold'],

'toxcast':['index', 'random', 'scaffold'], 

'clintox':['index', 'random', 'scaffold'], 

'hiv':    ['index', 'random', 'scaffold', 'butina'],

'bace_c': ['index', 'random'],

'delaney':['index', 'random', 'scaffold'],

'sampl':  ['index', 'random', 'scaffold'],

'nci':    ['index', 'random', 'scaffold'],

'chembl': ['index', 'random', 'scaffold', 'year'],

'bace_r': ['index', 'random'],

'bbbp':   ['index', 'random', 'scaffold'],

'chembl': ['index', 'random', 'scaffold', 'year'],

'clearance': ['index', 'random', 'scaffold'],

'clintox':['index', 'random', 'scaffold'], 

'delaney':['index', 'random', 'scaffold'],

'hiv':    ['index', 'random', 'scaffold', 'butina'],

'hopv':    ['index', 'random', 'scaffold', 'butina'],

'lipo':    ['index', 'random', 'scaffold'],

'ppb':    ['index', 'random', 'scaffold'],

'kaggle': ['index'], # already splitted, no splitter required

'lipo':    ['index', 'random', 'scaffold'],

'muv':    ['index', 'random', 'scaffold'], 

'nci':    ['index', 'random', 'scaffold'],

'pcba':   ['index', 'random', 'scaffold'],

'pdbbind':['index', 'random'],

'ppb':    ['index', 'random', 'scaffold'],

'qm7':    ['index', 'random', 'stratified'],

'qm7b':   ['index', 'random', 'stratified'],

'qm8':    ['index', 'random', 'stratified'],

'qm9':    ['index', 'random', 'stratified']

'qm9':    ['index', 'random', 'stratified'],

'sampl':  ['index', 'random', 'scaffold'],

'sider':  ['index', 'random', 'scaffold'],

'tox21':  ['index', 'random', 'scaffold', 'butina'],

'toxcast':['index', 'random', 'scaffold']

}

deepchem/molnet/load_function/bbbp_datasets.py

0 → 100644
+55 −0
Original line number Diff line number Diff line 
"""

Blood-Brain Barrier Penetration dataset loader.

"""

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals



import os

import deepchem





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

  """Load blood-brain barrier penetration datasets """

  # Featurize bbb dataset

  print("About to featurize bbbp dataset.")

  if "DEEPCHEM_DATA_DIR" in os.environ:

    data_dir = os.environ["DEEPCHEM_DATA_DIR"]

  else:

    data_dir = "/tmp"



  dataset_file = os.path.join(data_dir, "BBBP.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/BBBP.csv'

    )



  bbbp_tasks = ["p_np"]

  if featurizer == 'ECFP':

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

  elif featurizer == 'GraphConv':

    featurizer = deepchem.feat.ConvMolFeaturizer()

  elif featurizer == 'Raw':

    featurizer = deepchem.feat.RawFeaturizer()



  loader = deepchem.data.CSVLoader(

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

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

  # Initialize transformers 

  transformers = [

      deepchem.trans.BalancingTransformer(transform_w=True, dataset=dataset)

  ]



  print("About to transform data")

  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)

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

deepchem/molnet/run_benchmark.py

+41 −35
Original line number Diff line number Diff line
@@ -24,16 +24,18 @@ def run_benchmark(datasets, 
                  featurizer=None,

                  n_features=0,

                  out_path='.',

                  test=False):

                  hyper_parameters=None,

                  test=False,

                  seed=123):

  """

  Run benchmark test on designated datasets with deepchem(or user-defined) model

  

  Parameters

  ----------

  datasets: list of string

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

      toxcast, pcba, delaney, kaggle, nci, clintox, hiv, pdbbind, chembl,

      qm7, qm7b, qm9, sampl

      choice of which datasets to use, should be: bace_c, bace_r, bbbp, chembl,

      clearance, clintox, delaney, hiv, hopv, kaggle, lipo, muv, nci, pcba, 

      pdbbind, ppb, qm7, qm7b, qm8, qm9, sampl, sider, tox21, toxcast 

  model: string or user-defined model stucture

      choice of which model to use, deepchem provides implementation of

      logistic regression, random forest, multitask network,
@@ -56,25 +58,26 @@ def run_benchmark(datasets, 
  """

  for dataset in datasets:

    if dataset in [

        'muv', 'pcba', 'tox21', 'sider', 'toxcast', 'clintox', 'hiv', 'bace_c'

        'bace_c', 'bbbp', 'clintox', 'hiv', 'muv', 'pcba', 'sider', 

        'tox21',  'toxcast'

    ]:

      mode = 'classification'

      if metric == None:

        metric = [

            deepchem.metrics.Metric(deepchem.metrics.roc_auc_score, np.mean)

        ]

        metric = 'auc'

    elif dataset in [

        'kaggle', 'delaney', 'nci', 'pdbbind', 'chembl', 'qm7', 'qm7b', 'qm8', 'qm9',

        'sampl', 'bace_r', 'clearance', 'hopv', 'lipo', 'ppb'

        'bace_r', 'chembl', 'clearance', 'delaney', 'hopv', 'kaggle', 'lipo', 

        'nci', 'pdbbind', 'ppb',  'qm7', 'qm7b', 'qm8', 'qm9', 'sampl'

    ]:

      mode = 'regression'

      if metric == None:

        metric = [

            deepchem.metrics.Metric(deepchem.metrics.pearson_r2_score, np.mean)

        ]

        metric = 'r2'

    else:

      raise ValueError('Dataset not supported')



    metric_all = {'auc': deepchem.metrics.Metric(deepchem.metrics.roc_auc_score, np.mean),

                  'r2': deepchem.metrics.Metric(deepchem.metrics.pearson_r2_score, np.mean)}

    metric = [metric_all[metric]]



    if featurizer == None and isinstance(model, str):

      # Assigning featurizer if not user defined

      pair = (dataset, model)
@@ -88,29 +91,30 @@ def run_benchmark(datasets, 
      continue



    loading_functions = {

        'tox21': deepchem.molnet.load_tox21,

        'bace_c': deepchem.molnet.load_bace_classification,

        'bace_r': deepchem.molnet.load_bace_regression,

        'bbbp': deepchem.molnet.load_bbbp,

        'chembl': deepchem.molnet.load_chembl,

        'clearance': deepchem.molnet.load_clearance,

        'clintox': deepchem.molnet.load_clintox,

        'delaney': deepchem.molnet.load_delaney,

        'hiv': deepchem.molnet.load_hiv,

        'hopv': deepchem.molnet.load_hopv,

        'kaggle': deepchem.molnet.load_kaggle,

        'lipo': deepchem.molnet.load_lipo,

        'muv': deepchem.molnet.load_muv,

        'pcba': deepchem.molnet.load_pcba,

        'nci': deepchem.molnet.load_nci,

        'sider': deepchem.molnet.load_sider,

        'toxcast': deepchem.molnet.load_toxcast,

        'kaggle': deepchem.molnet.load_kaggle,

        'delaney': deepchem.molnet.load_delaney,

        'pcba': deepchem.molnet.load_pcba,

        'pdbbind': deepchem.molnet.load_pdbbind_grid,

        'chembl': deepchem.molnet.load_chembl,

        'ppb': deepchem.molnet.load_ppb,

        'qm7': deepchem.molnet.load_qm7_from_mat,

        'qm7b': deepchem.molnet.load_qm7b_from_mat,

        'qm8': deepchem.molnet.load_qm8,

        'qm9': deepchem.molnet.load_qm9,

        'sampl': deepchem.molnet.load_sampl,

        'clintox': deepchem.molnet.load_clintox,

        'hiv': deepchem.molnet.load_hiv,

        'bace_c': deepchem.molnet.load_bace_classification,

        'bace_r': deepchem.molnet.load_bace_regression,

        'clearance': deepchem.molnet.load_clearance,

        'hopv': deepchem.molnet.load_hopv,

        'lipo': deepchem.molnet.load_lipo,

        'ppb': deepchem.molnet.load_ppb

        'sider': deepchem.molnet.load_sider,

        'tox21': deepchem.molnet.load_tox21,

        'toxcast': deepchem.molnet.load_toxcast

    }



    print('-------------------------------------')
@@ -126,9 +130,7 @@ def run_benchmark(datasets, 
          featurizer=featurizer)



    train_dataset, valid_dataset, test_dataset = all_dataset

    if dataset in ['pdbbind']:

      n_features = train_dataset.get_data_shape()[0]

      print(n_features)



    time_start_fitting = time.time()

    train_score = {}

    valid_score = {}
@@ -144,8 +146,10 @@ def run_benchmark(datasets, 
            transformers,

            n_features,

            metric,

            model=model,

            test=test)

            model,

            test=test,

            hyper_parameters=hyper_parameters,

            seed=seed)

      elif mode == 'regression':

        train_score, valid_score, test_score = benchmark_regression(

            train_dataset,
@@ -155,8 +159,10 @@ def run_benchmark(datasets, 
            transformers,

            n_features,

            metric,

            model=model,

            test=test)

            model,

            test=test,

            hyper_parameters=hyper_parameters,

            seed=seed)

    else:

      model.fit(train_dataset)

      train_score['user_defined'] = model.evaluate(train_dataset, metric,

examples/benchmark.py

+61 −900

File changed.

Preview size limit exceeded, changes collapsed.

CRA Git | Maintained and supported by SUSTech CRA and CCSE