Commit d9869f00 authored by Bharath Ramsundar's avatar Bharath Ramsundar Committed by GitHub
Browse files

Merge pull request #484 from miaecle/molnet 

dc.molnet update
parents 49ae1606 5f1c379b

README.md

+324 −215

File changed.

Preview size limit exceeded, changes collapsed.

deepchem/molnet/__init__.py

+8 −0
Original line number Diff line number Diff line
@@ -2,16 +2,23 @@ from __future__ import print_function 
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

from deepchem.molnet.load_function.delaney_datasets import load_delaney

from deepchem.molnet.load_function.hiv_datasets import load_hiv

from deepchem.molnet.load_function.hopv_datasets import load_hopv

from deepchem.molnet.load_function.kaggle_datasets import load_kaggle

from deepchem.molnet.load_function.lipo_datasets import load_lipo

from deepchem.molnet.load_function.muv_datasets import load_muv

from deepchem.molnet.load_function.nci_datasets import load_nci

from deepchem.molnet.load_function.pcba_datasets import load_pcba

from deepchem.molnet.load_function.pdbbind_datasets import load_pdbbind_grid

from deepchem.molnet.load_function.ppb_datasets import load_ppb

from deepchem.molnet.load_function.qm7_datasets import load_qm7_from_mat, load_qm7b_from_mat

from deepchem.molnet.load_function.qm8_datasets import load_qm8

from deepchem.molnet.load_function.qm9_datasets import load_qm9

from deepchem.molnet.load_function.sampl_datasets import load_sampl

from deepchem.molnet.load_function.sider_datasets import load_sider
@@ -19,3 +26,4 @@ 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

from deepchem.molnet.run_benchmark_low_data import run_benchmark_low_data

deepchem/molnet/check_availability.py

0 → 100644
+127 −0
Original line number Diff line number Diff line 
CheckFeaturizer = {

    ('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],

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

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

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

    ('muv', 'siamese'): ['GraphConv', 75],

    ('muv', 'attn'): ['GraphConv', 75],

    ('muv', 'res'): ['GraphConv', 75],

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

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

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

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

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

    ('pcba', '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],

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

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

    ('sider', 'res'): ['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],

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

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

    ('tox21', 'res'): ['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],

    ('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],

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

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

    ('qm7', 'tf_regression_ft'): [None, [23, 23]],

    ('qm7b', 'tf_regression_ft'): [None, [23, 23]],

    ('qm8', 'tf_regression_ft'): [None, [26, 26]],

    ('qm9', 'tf_regression_ft'): [None, [29, 29]]

}



CheckSplit = {

    'bace_c': ['random', 'scaffold'],

    'bace_r': ['random', 'scaffold'],

    'bbbp': ['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'],

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

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

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

    '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'],

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

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

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

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

}

deepchem/molnet/load_function/bace_datasets.py

0 → 100644
+113 −0
Original line number Diff line number Diff line 
"""

bace dataset loader.

"""

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals



import os

import deepchem

from deepchem.molnet.load_function.bace_features import bace_user_specified_features





def load_bace_regression(featurizer=None, split='random'):

  """Load bace datasets."""

  # Featurize bace dataset

  print("About to featurize bace 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, "bace.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/bace.csv '

    )



  bace_tasks = ["pIC50"]

  if featurizer == 'ECFP':

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

  elif featurizer == 'GraphConv':

    featurizer = deepchem.feat.ConvMolFeaturizer()

  elif featurizer == 'Raw':

    featurizer = deepchem.feat.RawFeaturizer()

  elif featurizer == None:

    featurizer = deepchem.feat.UserDefinedFeaturizer(

        bace_user_specified_features)



  loader = deepchem.data.CSVLoader(

      tasks=bace_tasks, smiles_field="mol", featurizer=featurizer)



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

  # Initialize transformers 

  transformers = [

      deepchem.trans.NormalizationTransformer(

          transform_y=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 bace_tasks, (train, valid, test), transformers





def load_bace_classification(featurizer=None, split='random'):

  """Load bace datasets."""

  # Featurize bace dataset

  print("About to featurize bace 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, "bace.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/bace.csv '

    )



  bace_tasks = ["Class"]

  if featurizer == 'ECFP':

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

  elif featurizer == 'GraphConv':

    featurizer = deepchem.feat.ConvMolFeaturizer()

  elif featurizer == 'Raw':

    featurizer = deepchem.feat.RawFeaturizer()

  elif featurizer == None:

    featurizer = deepchem.feat.UserDefinedFeaturizer(

        bace_user_specified_features)



  loader = deepchem.data.CSVLoader(

      tasks=bace_tasks, smiles_field="mol", 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 bace_tasks, (train, valid, test), transformers

deepchem/molnet/load_function/bace_features.py

0 → 100644
+221 −0

File added.

Preview size limit exceeded, changes collapsed.

CRA Git | Maintained and supported by SUSTech CRA and CCSE