Commit 69b0aa24 authored by Bharath Ramsundar's avatar Bharath Ramsundar
Browse files

getting sweetlead working

parent 2d77aa3a

deepchem/molnet/__init__.py

+1 −0
Original line number Diff line number Diff line
@@ -22,6 +22,7 @@ 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

from deepchem.molnet.load_function.sweetlead_datasets import load_sweet

from deepchem.molnet.load_function.tox21_datasets import load_tox21

from deepchem.molnet.load_function.toxcast_datasets import load_toxcast

deepchem/molnet/load_function/sweetlead_datasets.py

0 → 100644
+61 −0
Original line number Diff line number Diff line 
"""

SWEET dataset loader.

"""

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals



import os

import numpy as np

import shutil

import deepchem as dc



def load_sweet(featurizer='ECFP', split='index', reload=True, frac_train=.8):

  """Load sweet datasets."""

  # Load Sweetlead dataset

  logger.info("About to load Sweetlead dataset.")

  data_dir = deepchem.utils.get_data_dir()

  if reload:

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



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

  if not os.path.exists(dataset_file):

    deepchem.utils.download_url(

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

    )



  # Featurize SWEET dataset

  print("About to featurize SWEET dataset.")

  if featurizer == 'ECFP':

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

  else:

    raise ValueError("Other featurizations not supported")

  SWEET_tasks = ["task"] 



  loader = dc.data.CSVLoader(

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

  dataset = loader.featurize(dataset_file)





  # Initialize transformers 

  transformers = [

      dc.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(),

      'task': deepchem.splits.TaskSplitter()

  }

  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)

    all_dataset = (train, valid, test)



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

examples/sweetlead/sweet.py

+25 −28
Original line number Diff line number Diff line
@@ -17,48 +17,45 @@ from deepchem import metrics 
from deepchem.metrics import Metric

from deepchem.models.sklearn_models import SklearnModel

from deepchem.splits import StratifiedSplitter, RandomSplitter

from sweetlead_datasets import load_sweet

#from sweetlead_datasets import load_sweet



sys.path.append('./../toxcast')

sys.path.append('./../sider')

#sys.path.append('./../toxcast')

#sys.path.append('./../sider')

#

#from tox_datasets import load_tox

#from sider_datasets import load_sider



from tox_datasets import load_tox

from sider_datasets import load_sider

#"""

#Load toxicity models now

#"""



"""

Load toxicity models now

"""



# Set some global variables up top

reload = False

verbosity = "high"

## Set some global variables up top

#reload = False

#verbosity = "high"

#

#base_tox_data_dir = "/home/apappu/deepchem-models/toxcast_models/toxcast/toxcast_data"



base_tox_data_dir = "/home/apappu/deepchem-models/toxcast_models/toxcast/toxcast_data"



tox_tasks, tox_dataset, tox_transformers = load_tox(

    base_tox_data_dir, reload=reload)

tox_tasks, tox_dataset, tox_transformers = dc.molnet.load_toxcast()



#removes directory if present -- warning

base_tox_dir = "/home/apappu/deepchem-models/toxcast_models/toxcast/toxcast_analysis"

#base_tox_dir = "/home/apappu/deepchem-models/toxcast_models/toxcast/toxcast_analysis"



tox_train_dir = os.path.join(base_tox_dir, "train_dataset")

tox_valid_dir = os.path.join(base_tox_dir, "valid_dataset")

tox_test_dir = os.path.join(base_tox_dir, "test_dataset")

tox_model_dir = os.path.join(base_tox_dir, "model")

#tox_train_dir = os.path.join(base_tox_dir, "train_dataset")

#tox_valid_dir = os.path.join(base_tox_dir, "valid_dataset")

#tox_test_dir = os.path.join(base_tox_dir, "test_dataset")

#tox_model_dir = os.path.join(base_tox_dir, "model")



tox_splitter = StratifiedSplitter()

#tox_splitter = StratifiedSplitter()



#default split is 80-10-10 train-valid-test split

tox_train_dataset, tox_valid_dataset, tox_test_dataset = tox_splitter.train_valid_test_split(

  tox_dataset, tox_train_dir, tox_valid_dir, tox_test_dir)



# Fit Logistic Regression models

tox_task_types = {task: "classification" for task in tox_tasks}

## Fit Logistic Regression models

#tox_task_types = {task: "classification" for task in tox_tasks}





classification_metric = Metric(metrics.roc_auc_score, np.mean,

                               verbosity=verbosity,

                               mode="classification")

classification_metric = Metric(metrics.roc_auc_score, np.mean, mode="classification")

params_dict = {

    "batch_size": None,

    "data_shape": tox_train_dataset.get_data_shape(),
@@ -113,7 +110,7 @@ Load sweetlead dataset now. Pass in dataset object and appropriate transformers 


base_sweet_data_dir = "/home/apappu/deepchem-models/toxcast_models/sweetlead/sweet_data"



sweet_dataset, sweet_transformers = load_sweet(

sweet_dataset, sweet_transformers = dc.molnet.load_sweet(

    base_sweet_data_dir, reload=reload)



sider_predictions = sider_model.predict(sweet_dataset, sweet_transformers)

examples/sweetlead/sweetlead_datasets.py

+0 −41
Original line number Diff line number Diff line 
"""

SWEET dataset loader.

"""

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals



import os

import numpy as np

import shutil

import deepchem as dc



def load_sweet(base_dir, frac_train=.8):

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

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



  # Load SWEET dataset

  dataset_file = os.path.join(

      current_dir, "./sweet.csv.gz")



  # Featurize SWEET dataset

  print("About to featurize SWEET dataset.")

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

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



  loader = dc.data.CSVLoader(

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

  dataset = loader.featurize(dataset_file)





  # Initialize transformers 

  transformers = [

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

  print("About to transform data")

  for transformer in transformers:

      dataset = transformer.transform(dataset)



  spliter = dc.splits.IndexSplitter()

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



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

CRA Git | Maintained and supported by SUSTech CRA and CCSE