Commit 297eff9d authored by miaecle's avatar miaecle
Browse files

reconstruct molnet structure

parent b38bcdcc

deepchem/__init__.py

+1 −0
Original line number Diff line number Diff line
@@ -15,3 +15,4 @@ import deepchem.splits 
import deepchem.trans

import deepchem.utils

import deepchem.dock

import deepchem.molnet

deepchem/molnet/__init__.py

0 → 100644
+18 −0
Original line number Diff line number Diff line 


from deepchem.molnet.chembl_datasets import load_chembl

from deepchem.molnet.clintox_datasets import load_clintox

from deepchem.molnet.delaney_datasets import load_delaney

from deepchem.molnet.hiv_datasets import load_hiv

from deepchem.molnet.kaggle_datasets import load_kaggle

from deepchem.molnet.muv_datasets import load_muv

from deepchem.molnet.nci_datasets import load_nci

from deepchem.molnet.pcba_datasets import load_pcba

from deepchem.molnet.pdbbind_datasets import load_pdbbind_grid

from deepchem.molnet.qm7_datasets import load_qm7_from_mat, load_qm7b_from_mat

from deepchem.molnet.qm9_datasets import load_qm9

from deepchem.molnet.sampl_datasets import load_sampl

from deepchem.molnet.sider_datasets import load_sider

from deepchem.molnet.tox21_datasets import load_tox21

from deepchem.molnet.toxcast_datasets import load_toxcast



from deepchem.molnet.run_benchmark import run_benchmark

deepchem/molnet/chembl_datasets.py

0 → 100644
+94 −0
Original line number Diff line number Diff line 
"""

ChEMBL dataset loader.

"""

from __future__ import division

from __future__ import print_function

from __future__ import unicode_literals



import os

import deepchem as dc



from deepchem.molnet.chembl_tasks import chembl_tasks



def load_chembl(shard_size=2000, featurizer="ECFP", set="5thresh", split="random"):



  if "DEEPCHEM_DATA_DIR" in os.environ:

    data_dir = os.environ["DEEPCHEM_DATA_DIR"]

  else:

    data_dir = "/tmp"

  

  dataset_path = os.path.join(

      data_dir, "./chembl_%s.csv.gz" % set)

  if not os.path.exists(dataset_path):

    os.system('wget -P ' + data_dir + 

    ' http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/chembl_5thresh.csv.gz')

    os.system('wget -P ' + data_dir + 

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

    os.system('wget -P ' + os.path.join(data_dir, 'chembl_year_sets') + 

    ' http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/chembl_year_sets/chembl_5thresh_ts_test.csv.gz')

    os.system('wget -P ' + os.path.join(data_dir, 'chembl_year_sets') + 

    ' http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/chembl_year_sets/chembl_5thresh_ts_train.csv.gz')

    os.system('wget -P ' + os.path.join(data_dir, 'chembl_year_sets') + 

    ' http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/chembl_year_sets/chembl_5thresh_ts_valid.csv.gz')

    os.system('wget -P ' + os.path.join(data_dir, 'chembl_year_sets') + 

    ' http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/chembl_year_sets/chembl_sparse_ts_test.csv.gz')

    os.system('wget -P ' + os.path.join(data_dir, 'chembl_year_sets') + 

    ' http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/chembl_year_sets/chembl_sparse_ts_train.csv.gz')

    os.system('wget -P ' + os.path.join(data_dir, 'chembl_year_sets') + 

    ' http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/chembl_year_sets/chembl_sparse_ts_valid.csv.gz')



  print("About to load ChEMBL dataset.")

  if split == "year":

    train_files = os.path.join(data_dir,

        "./chembl_year_sets/chembl_%s_ts_train.csv.gz" % set)

    valid_files = os.path.join(data_dir,

        "./chembl_year_sets/chembl_%s_ts_valid.csv.gz" % set)

    test_files = os.path.join(data_dir,

        "./chembl_year_sets/chembl_%s_ts_test.csv.gz" % set)



  # Featurize ChEMBL dataset

  print("About to featurize ChEMBL dataset.")

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

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

  featurizer = featurizers[featurizer]



  loader = dc.data.CSVLoader(

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



  if split == "year":

    print("Featurizing train datasets")

    train_dataset = loader.featurize(

        train_files, shard_size=shard_size)

    print("Featurizing valid datasets")

    valid_dataset = loader.featurize(

        valid_files, shard_size=shard_size)

    print("Featurizing test datasets")

    test_dataset = loader.featurize(

        test_files, shard_size=shard_size)

  else:

    dataset = loader.featurize(dataset_path, shard_size=shard_size)

  # Initialize transformers

  print("About to transform data")

  if split == "year":

    transformers = [

        dc.trans.NormalizationTransformer(transform_y=True, dataset=train_dataset)]

    for transformer in transformers:

      train = transformer.transform(train_dataset)

      valid = transformer.transform(valid_dataset)

      test = transformer.transform(test_dataset)

  else:

    transformers = [

        dc.trans.NormalizationTransformer(transform_y=True, dataset=dataset)]

    for transformer in transformers:

      dataset = transformer.transform(dataset)



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

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

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



  if split in splitters:

    splitter = splitters[split]

    print("Performing new split.")

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



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

deepchem/molnet/chembl_tasks.py

0 → 100644
+138 −0
Original line number Diff line number Diff line 
chembl_tasks = ['CHEMBL1075051', 'CHEMBL1075104', 'CHEMBL1075145', 'CHEMBL1075189'

                , 'CHEMBL1075228', 'CHEMBL1075284', 'CHEMBL1075319', 'CHEMBL1163101'

                , 'CHEMBL1163116', 'CHEMBL1163125', 'CHEMBL1255149', 'CHEMBL1255150'

                , 'CHEMBL1293255', 'CHEMBL1293289', 'CHEMBL1293292', 'CHEMBL1741186'

                , 'CHEMBL1741195', 'CHEMBL1744525', 'CHEMBL1764940', 'CHEMBL1781'

                , 'CHEMBL1781862', 'CHEMBL1782', 'CHEMBL1784', 'CHEMBL1790', 'CHEMBL1792'

                , 'CHEMBL1795101', 'CHEMBL1795126', 'CHEMBL1800', 'CHEMBL1801', 'CHEMBL1804'

                , 'CHEMBL1806', 'CHEMBL1811', 'CHEMBL1821', 'CHEMBL1822', 'CHEMBL1824'

                , 'CHEMBL1825', 'CHEMBL1827', 'CHEMBL1829', 'CHEMBL1833', 'CHEMBL1836'

                , 'CHEMBL1844', 'CHEMBL1849', 'CHEMBL1850', 'CHEMBL1853', 'CHEMBL1855'

                , 'CHEMBL1856', 'CHEMBL1860', 'CHEMBL1862', 'CHEMBL1865', 'CHEMBL1867'

                , 'CHEMBL1868', 'CHEMBL1871', 'CHEMBL1873', 'CHEMBL1875', 'CHEMBL1878'

                , 'CHEMBL1881', 'CHEMBL1889', 'CHEMBL1892', 'CHEMBL1898', 'CHEMBL1899'

                , 'CHEMBL1900', 'CHEMBL1901', 'CHEMBL1902', 'CHEMBL1906', 'CHEMBL1907'

                , 'CHEMBL1908', 'CHEMBL1913', 'CHEMBL1914', 'CHEMBL1916', 'CHEMBL1917'

                , 'CHEMBL1919', 'CHEMBL1921', 'CHEMBL1921666', 'CHEMBL1926', 'CHEMBL1936'

                , 'CHEMBL1937', 'CHEMBL1941', 'CHEMBL1942', 'CHEMBL1944', 'CHEMBL1945'

                , 'CHEMBL1946', 'CHEMBL1947', 'CHEMBL1949', 'CHEMBL1951', 'CHEMBL1952'

                , 'CHEMBL1955', 'CHEMBL1957', 'CHEMBL1966', 'CHEMBL1968', 'CHEMBL1974'

                , 'CHEMBL1977', 'CHEMBL1978', 'CHEMBL1980', 'CHEMBL1981', 'CHEMBL1983'

                , 'CHEMBL1985', 'CHEMBL1991', 'CHEMBL1994', 'CHEMBL1995', 'CHEMBL1997'

                , 'CHEMBL2000', 'CHEMBL2001', 'CHEMBL2002', 'CHEMBL2007', 'CHEMBL2014'

                , 'CHEMBL2016', 'CHEMBL202', 'CHEMBL2027', 'CHEMBL2028', 'CHEMBL203'

                , 'CHEMBL2034', 'CHEMBL2035', 'CHEMBL2039', 'CHEMBL204', 'CHEMBL2041'

                , 'CHEMBL2047', 'CHEMBL2049', 'CHEMBL205', 'CHEMBL2056', 'CHEMBL206'

                , 'CHEMBL2061', 'CHEMBL2069', 'CHEMBL208', 'CHEMBL2083', 'CHEMBL2085'

                , 'CHEMBL209', 'CHEMBL210', 'CHEMBL2107', 'CHEMBL2108', 'CHEMBL211', 'CHEMBL213'

                , 'CHEMBL214', 'CHEMBL2146302', 'CHEMBL2147', 'CHEMBL2148', 'CHEMBL215'

                , 'CHEMBL216', 'CHEMBL217', 'CHEMBL2179', 'CHEMBL218', 'CHEMBL2185', 'CHEMBL219'

                , 'CHEMBL220', 'CHEMBL2207', 'CHEMBL2208', 'CHEMBL221', 'CHEMBL222', 'CHEMBL223'

                , 'CHEMBL224', 'CHEMBL2243', 'CHEMBL225', 'CHEMBL226', 'CHEMBL2265', 'CHEMBL227'

                , 'CHEMBL2274', 'CHEMBL2276', 'CHEMBL228', 'CHEMBL2285', 'CHEMBL2288'

                , 'CHEMBL229', 'CHEMBL2292', 'CHEMBL230', 'CHEMBL2304402', 'CHEMBL2304404'

                , 'CHEMBL231', 'CHEMBL2318', 'CHEMBL232', 'CHEMBL2326', 'CHEMBL2327'

                , 'CHEMBL2329', 'CHEMBL233', 'CHEMBL2334', 'CHEMBL2335', 'CHEMBL2337'

                , 'CHEMBL234', 'CHEMBL2345', 'CHEMBL235', 'CHEMBL236', 'CHEMBL2361', 'CHEMBL2363'

                , 'CHEMBL2366456', 'CHEMBL2366505', 'CHEMBL2366512', 'CHEMBL2366516'

                , 'CHEMBL2366517', 'CHEMBL237', 'CHEMBL2373', 'CHEMBL238', 'CHEMBL239'

                , 'CHEMBL2391', 'CHEMBL2397', 'CHEMBL240', 'CHEMBL2409', 'CHEMBL241'

                , 'CHEMBL2413', 'CHEMBL2414', 'CHEMBL242', 'CHEMBL2425', 'CHEMBL243'

                , 'CHEMBL2431', 'CHEMBL2434', 'CHEMBL244', 'CHEMBL2447', 'CHEMBL245', 'CHEMBL246'

                , 'CHEMBL2461', 'CHEMBL247', 'CHEMBL2470', 'CHEMBL2474', 'CHEMBL248'

                , 'CHEMBL2487', 'CHEMBL2488', 'CHEMBL2489', 'CHEMBL249', 'CHEMBL2492'

                , 'CHEMBL2499', 'CHEMBL251', 'CHEMBL252', 'CHEMBL2525', 'CHEMBL2527', 'CHEMBL253'

                , 'CHEMBL2534', 'CHEMBL2536', 'CHEMBL254', 'CHEMBL255', 'CHEMBL256', 'CHEMBL2563'

                , 'CHEMBL2564', 'CHEMBL2567', 'CHEMBL2568', 'CHEMBL2575', 'CHEMBL258'

                , 'CHEMBL2581', 'CHEMBL259', 'CHEMBL2590', 'CHEMBL2599', 'CHEMBL260', 'CHEMBL261'

                , 'CHEMBL2611', 'CHEMBL2617', 'CHEMBL262', 'CHEMBL2622', 'CHEMBL2637'

                , 'CHEMBL264', 'CHEMBL265', 'CHEMBL2652', 'CHEMBL2664', 'CHEMBL267', 'CHEMBL268'

                , 'CHEMBL269', 'CHEMBL2693', 'CHEMBL2695', 'CHEMBL270', 'CHEMBL2716'

                , 'CHEMBL2722', 'CHEMBL273', 'CHEMBL2730', 'CHEMBL2736', 'CHEMBL274'

                , 'CHEMBL2742', 'CHEMBL2749', 'CHEMBL275', 'CHEMBL2756', 'CHEMBL276'

                , 'CHEMBL2778', 'CHEMBL278', 'CHEMBL2781', 'CHEMBL2782', 'CHEMBL2789'

                , 'CHEMBL279', 'CHEMBL280', 'CHEMBL2803', 'CHEMBL2808', 'CHEMBL2815'

                , 'CHEMBL2820', 'CHEMBL2828', 'CHEMBL283', 'CHEMBL2830', 'CHEMBL2835'

                , 'CHEMBL284', 'CHEMBL2842', 'CHEMBL285', 'CHEMBL2851', 'CHEMBL2858', 'CHEMBL286'

                , 'CHEMBL2868', 'CHEMBL287', 'CHEMBL2871', 'CHEMBL288', 'CHEMBL2882'

                , 'CHEMBL2885', 'CHEMBL2902', 'CHEMBL2903', 'CHEMBL2916', 'CHEMBL2949'

                , 'CHEMBL2954', 'CHEMBL2959', 'CHEMBL2971', 'CHEMBL2973', 'CHEMBL2978'

                , 'CHEMBL298', 'CHEMBL299', 'CHEMBL2993', 'CHEMBL2996', 'CHEMBL2998', 'CHEMBL301'

                , 'CHEMBL3012', 'CHEMBL3018', 'CHEMBL302', 'CHEMBL3024', 'CHEMBL3025'

                , 'CHEMBL3037', 'CHEMBL304', 'CHEMBL3045', 'CHEMBL3048', 'CHEMBL3060'

                , 'CHEMBL3066', 'CHEMBL3067', 'CHEMBL3072', 'CHEMBL308', 'CHEMBL3081'

                , 'CHEMBL3085613', 'CHEMBL309', 'CHEMBL3100', 'CHEMBL3105', 'CHEMBL3106'

                , 'CHEMBL311', 'CHEMBL3114', 'CHEMBL3116', 'CHEMBL312', 'CHEMBL313', 'CHEMBL3130'

                , 'CHEMBL3138', 'CHEMBL3142', 'CHEMBL3145', 'CHEMBL3155', 'CHEMBL3157'

                , 'CHEMBL3166', 'CHEMBL318', 'CHEMBL3180', 'CHEMBL3181', 'CHEMBL319'

                , 'CHEMBL3192', 'CHEMBL3199', 'CHEMBL3202', 'CHEMBL321', 'CHEMBL322'

                , 'CHEMBL3222', 'CHEMBL3223', 'CHEMBL3227', 'CHEMBL3229', 'CHEMBL3230'

                , 'CHEMBL3231', 'CHEMBL324', 'CHEMBL3242', 'CHEMBL3247', 'CHEMBL325'

                , 'CHEMBL3254', 'CHEMBL326', 'CHEMBL3267', 'CHEMBL3286', 'CHEMBL330'

                , 'CHEMBL3305', 'CHEMBL331', 'CHEMBL3310', 'CHEMBL3314', 'CHEMBL3318'

                , 'CHEMBL332', 'CHEMBL333', 'CHEMBL3332', 'CHEMBL335', 'CHEMBL3351', 'CHEMBL3358'

                , 'CHEMBL3360', 'CHEMBL3361', 'CHEMBL3371', 'CHEMBL3374', 'CHEMBL338'

                , 'CHEMBL339', 'CHEMBL3399910', 'CHEMBL340', 'CHEMBL3403', 'CHEMBL3419'

                , 'CHEMBL3426', 'CHEMBL3437', 'CHEMBL3438', 'CHEMBL344', 'CHEMBL3464'

                , 'CHEMBL3468', 'CHEMBL3471', 'CHEMBL3473', 'CHEMBL3474', 'CHEMBL3476'

                , 'CHEMBL3486', 'CHEMBL3501', 'CHEMBL3510', 'CHEMBL3513', 'CHEMBL3522'

                , 'CHEMBL3524', 'CHEMBL3535', 'CHEMBL3553', 'CHEMBL3559', 'CHEMBL3563'

                , 'CHEMBL3568', 'CHEMBL3571', 'CHEMBL3572', 'CHEMBL3582', 'CHEMBL3587'

                , 'CHEMBL3589', 'CHEMBL3590', 'CHEMBL3594', 'CHEMBL3602', 'CHEMBL3614'

                , 'CHEMBL3623', 'CHEMBL3629', 'CHEMBL3638338', 'CHEMBL3649', 'CHEMBL3650'

                , 'CHEMBL3687', 'CHEMBL3691', 'CHEMBL3699', 'CHEMBL3706', 'CHEMBL3710'

                , 'CHEMBL3717', 'CHEMBL3729', 'CHEMBL3746', 'CHEMBL3759', 'CHEMBL3764'

                , 'CHEMBL3766', 'CHEMBL3768', 'CHEMBL3769', 'CHEMBL3772', 'CHEMBL3775'

                , 'CHEMBL3776', 'CHEMBL3778', 'CHEMBL3785', 'CHEMBL3788', 'CHEMBL3795'

                , 'CHEMBL3798', 'CHEMBL3802', 'CHEMBL3807', 'CHEMBL3815', 'CHEMBL3816'

                , 'CHEMBL3820', 'CHEMBL3833', 'CHEMBL3836', 'CHEMBL3837', 'CHEMBL3864'

                , 'CHEMBL3868', 'CHEMBL3869', 'CHEMBL3880', 'CHEMBL3884', 'CHEMBL3891'

                , 'CHEMBL3892', 'CHEMBL3910', 'CHEMBL3912', 'CHEMBL3920', 'CHEMBL3922'

                , 'CHEMBL3942', 'CHEMBL3943', 'CHEMBL3948', 'CHEMBL3952', 'CHEMBL3959'

                , 'CHEMBL3969', 'CHEMBL3974', 'CHEMBL3975', 'CHEMBL3976', 'CHEMBL3979'

                , 'CHEMBL3983', 'CHEMBL3991', 'CHEMBL3996', 'CHEMBL4005', 'CHEMBL4015'

                , 'CHEMBL4016', 'CHEMBL4018', 'CHEMBL4026', 'CHEMBL4029', 'CHEMBL4040'

                , 'CHEMBL4051', 'CHEMBL4068', 'CHEMBL4072', 'CHEMBL4073', 'CHEMBL4074'

                , 'CHEMBL4077', 'CHEMBL4078', 'CHEMBL4080', 'CHEMBL4093', 'CHEMBL4102'

                , 'CHEMBL4111', 'CHEMBL4123', 'CHEMBL4124', 'CHEMBL4128', 'CHEMBL4132'

                , 'CHEMBL4140', 'CHEMBL4142', 'CHEMBL4145', 'CHEMBL4150', 'CHEMBL4153'

                , 'CHEMBL4161', 'CHEMBL4179', 'CHEMBL4188', 'CHEMBL4191', 'CHEMBL4198'

                , 'CHEMBL4203', 'CHEMBL4204', 'CHEMBL4224', 'CHEMBL4234', 'CHEMBL4235'

                , 'CHEMBL4247', 'CHEMBL4261', 'CHEMBL4282', 'CHEMBL4296', 'CHEMBL4302'

                , 'CHEMBL4303', 'CHEMBL4306', 'CHEMBL4308', 'CHEMBL4315', 'CHEMBL4321'

                , 'CHEMBL4333', 'CHEMBL4336', 'CHEMBL4338', 'CHEMBL4354', 'CHEMBL4358'

                , 'CHEMBL4361', 'CHEMBL4372', 'CHEMBL4393', 'CHEMBL4394', 'CHEMBL4409'

                , 'CHEMBL4414', 'CHEMBL4422', 'CHEMBL4427', 'CHEMBL4429', 'CHEMBL4430'

                , 'CHEMBL4439', 'CHEMBL4441', 'CHEMBL4462', 'CHEMBL4465', 'CHEMBL4471'

                , 'CHEMBL4477', 'CHEMBL4478', 'CHEMBL4481', 'CHEMBL4482', 'CHEMBL4501'

                , 'CHEMBL4506', 'CHEMBL4508', 'CHEMBL4523', 'CHEMBL4550', 'CHEMBL4552'

                , 'CHEMBL4561', 'CHEMBL4581', 'CHEMBL4586', 'CHEMBL4588', 'CHEMBL4599'

                , 'CHEMBL4600', 'CHEMBL4608', 'CHEMBL4616', 'CHEMBL4617', 'CHEMBL4618'

                , 'CHEMBL4625', 'CHEMBL4630', 'CHEMBL4633', 'CHEMBL4641', 'CHEMBL4644'

                , 'CHEMBL4649', 'CHEMBL4652', 'CHEMBL4653', 'CHEMBL4657', 'CHEMBL4660'

                , 'CHEMBL4662', 'CHEMBL4681', 'CHEMBL4683', 'CHEMBL4685', 'CHEMBL4687'

                , 'CHEMBL4696', 'CHEMBL4698', 'CHEMBL4699', 'CHEMBL4722', 'CHEMBL4761'

                , 'CHEMBL4768', 'CHEMBL4777', 'CHEMBL4779', 'CHEMBL4780', 'CHEMBL4789'

                , 'CHEMBL4792', 'CHEMBL4793', 'CHEMBL4794', 'CHEMBL4801', 'CHEMBL4802'

                , 'CHEMBL4803', 'CHEMBL4804', 'CHEMBL4805', 'CHEMBL4816', 'CHEMBL4822'

                , 'CHEMBL4828', 'CHEMBL4829', 'CHEMBL4835', 'CHEMBL4860', 'CHEMBL4893'

                , 'CHEMBL4895', 'CHEMBL4899', 'CHEMBL4908', 'CHEMBL4919', 'CHEMBL4975'

                , 'CHEMBL4979', 'CHEMBL4980', 'CHEMBL5011', 'CHEMBL5017', 'CHEMBL5023'

                , 'CHEMBL5024', 'CHEMBL5036', 'CHEMBL5067', 'CHEMBL5071', 'CHEMBL5076'

                , 'CHEMBL5077', 'CHEMBL5080', 'CHEMBL5102', 'CHEMBL5103', 'CHEMBL5112'

                , 'CHEMBL5113', 'CHEMBL5122', 'CHEMBL5131', 'CHEMBL5136', 'CHEMBL5137'

                , 'CHEMBL5141', 'CHEMBL5145', 'CHEMBL5147', 'CHEMBL5160', 'CHEMBL5192'

                , 'CHEMBL5203', 'CHEMBL5205', 'CHEMBL5247', 'CHEMBL5251', 'CHEMBL5282'

                , 'CHEMBL5314', 'CHEMBL5328', 'CHEMBL5331', 'CHEMBL5353', 'CHEMBL5373'

                , 'CHEMBL5375', 'CHEMBL5387', 'CHEMBL5393', 'CHEMBL5407', 'CHEMBL5409'

                , 'CHEMBL5413', 'CHEMBL5414', 'CHEMBL5424', 'CHEMBL5441', 'CHEMBL5443'

                , 'CHEMBL5445', 'CHEMBL5451', 'CHEMBL5457', 'CHEMBL5462', 'CHEMBL5471'

                , 'CHEMBL5485', 'CHEMBL5491', 'CHEMBL5508', 'CHEMBL5522', 'CHEMBL5543'

                , 'CHEMBL5555', 'CHEMBL5570', 'CHEMBL5582', 'CHEMBL5631', 'CHEMBL5645'

                , 'CHEMBL5652', 'CHEMBL5658', 'CHEMBL5669', 'CHEMBL5697', 'CHEMBL5704'

                , 'CHEMBL5736', 'CHEMBL5747', 'CHEMBL5763', 'CHEMBL5769', 'CHEMBL5800'

                , 'CHEMBL5847', 'CHEMBL5879', 'CHEMBL5932', 'CHEMBL5966', 'CHEMBL5971'

                , 'CHEMBL6007', 'CHEMBL6009', 'CHEMBL6080', 'CHEMBL6084', 'CHEMBL6136'

                , 'CHEMBL6137', 'CHEMBL6140', 'CHEMBL6141', 'CHEMBL6145', 'CHEMBL6154'

                , 'CHEMBL6164', 'CHEMBL6166', 'CHEMBL6184']

deepchem/molnet/clintox_datasets.py

0 → 100644
+59 −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."""



  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, "./clintox.csv.gz")

  if not os.path.exists(dataset_file):

    os.system('wget -P ' + data_dir + 

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



  print("About to load clintox dataset.")

  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

CRA Git | Maintained and supported by SUSTech CRA and CCSE