Merge pull request #1867 from deepchem/molnet_docs

                 data_dir=None,

                 save_dir=None,

                 **kwargs):

  """Load clintox datasets."""

  """Load clintox datasets.

  The ClinTox dataset compares drugs approved by the FDA and

  drugs that have failed clinical trials for toxicity reasons.

  The dataset includes two classification tasks for 1491 drug

  compounds with known chemical structures: (1) clinical trial

  toxicity (or absence of toxicity) and (2) FDA approval status.

  List of FDA-approved drugs are compiled from the SWEETLEAD

  database, and list of drugs that failed clinical trials for

  toxicity reasons are compiled from the Aggregate Analysis of

  ClinicalTrials.gov(AACT) database.

  The data file contains a csv table, in which columns below are

  used:

     "smiles" - SMILES representation of the molecular structure

     "FDA_APPROVED" - FDA approval status

     "CT_TOX" - Clinical trial results

References:

  Gayvert, Kaitlyn M., Neel S. Madhukar, and Olivier Elemento. "A data-driven approach to predicting successes and failures of clinical trials." Cell chemical biology 23.10 (2016): 1294-1301.

  Artemov, Artem V., et al. "Integrated deep learned transcriptomic and structure-based predictor of clinical trials outcomes." bioRxiv (2016): 095653.

  Novick, Paul A., et al. "SWEETLEAD: an in silico database of approved drugs, regulated chemicals, and herbal isolates for computer-aided drug discovery." PloS one 8.11 (2013): e79568.

  Aggregate Analysis of ClincalTrials.gov (AACT) Database. https://www.ctti-clinicaltrials.org/aact-database

  """

  if data_dir is None:

    data_dir = DEFAULT_DIR

  if save_dir is None:

                 data_dir=None,

                 save_dir=None,

                 **kwargs):

  """Load delaney datasets."""

  """Load delaney datasets.

  The Delaney datasets are extracted from the following paper

  Delaney, John S. "ESOL: estimating aqueous solubility directly from molecular structure." Journal of chemical information and computer sciences 44.3 (2004): 1000-1005.

  This dataset contains 2874 measured aqueous solubility

  values. The source dataset is available in the supplemental

  material of the original paper.

  """

  # Featurize Delaney dataset

  logger.info("About to featurize Delaney dataset.")

  if data_dir is None:

  elif featurizer == "smiles2img":

    img_spec = kwargs.get("img_spec", "std")

    img_size = kwargs.get("img_size", 80)

    res = kwargs.get("res", 0.5)

    featurizer = deepchem.feat.SmilesToImage(

        img_size=img_size, img_spec=img_spec)

        img_size=img_size, img_spec=img_spec, res=res)

  loader = deepchem.data.CSVLoader(

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

def load_factors(shard_size=2000, featurizer=None, split=None, reload=True):

  """Loads FACTOR dataset; does not do train/test split"""

  """Loads FACTOR dataset; does not do train/test split

  The Factors dataset is an in-house dataset from Merck that was first introduced in the following paper:

Ramsundar, Bharath, et al. "Is multitask deep learning practical for pharma?." Journal of chemical information and modeling 57.8 (2017): 2068-2076.

  It contains 1500 Merck in-house compounds that were measured

  for IC50 of inhibition on 12 serine proteases. Unlike most of

  the other datasets featured in MoleculeNet, the Factors 

  collection does not have structures for the compounds tested

  since they were proprietary Merck compounds. However, the

  collection does feature pre-computed descriptors for these

  compounds.

  Note that the original train/valid/test split from the source

  data was preserved here, so this function doesn't allow for

  alternate modes of splitting. Similarly, since the source data

  came pre-featurized, it is not possible to apply alternative

  featurizations.

  Parameters

  ----------

  shard_size: int, optional

    Size of the DiskDataset shards to write on disk

  featurizer: optional

    Ignored since featurization pre-computed

  split: optional

    Ignored since split pre-computed

  reload: bool, optional

    Whether to automatically re-load from disk

  """

  FACTORS_tasks = [

      'T_00001', 'T_00002', 'T_00003', 'T_00004', 'T_00005', 'T_00006',

             data_dir=None,

             save_dir=None,

             **kwargs):

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

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

  The HIV dataset was introduced by the Drug Therapeutics

  Program (DTP) AIDS Antiviral Screen, which tested the ability

  to inhibit HIV replication for over 40,000 compounds.

  Screening results were evaluated and placed into three

  categories: confirmed inactive (CI),confirmed active (CA) and

  confirmed moderately active (CM). We further combine the

  latter two labels, making it a classification task between

  inactive (CI) and active (CA and CM).

  The data file contains a csv table, in which columns below

  are used:

     - "smiles": SMILES representation of the molecular structure

     - "activity": Three-class labels for screening results: CI/CM/CA

     - "HIV_active": Binary labels for screening results: 1 (CA/CM) and 0 (CI)

  References:

  AIDS Antiviral Screen Data. https://wiki.nci.nih.gov/display/NCIDTPdata/AIDS+Antiviral+Screen+Data

  """

  # Featurize hiv dataset

  logger.info("About to featurize hiv dataset.")

  if data_dir is None:

              data_dir=None,

              save_dir=None,

              **kwargs):

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

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

  The HOPV datasets consist of the "Harvard Organic

  Photovoltaic Dataset. This dataset includes 350 small

  molecules and polymers that were utilized as p-type materials

  in OPVs. Experimental properties include: HOMO [a.u.], LUMO

  [a.u.], Electrochemical gap [a.u.], Optical gap [a.u.], Power

  conversion efficiency [%], Open circuit potential [V], Short

  circuit current density [mA/cm^2], and fill factor [%].

  Theoretical calculations in the original dataset have been

  removed (for now).

  Lopez, Steven A., et al. "The Harvard organic photovoltaic dataset." Scientific data 3.1 (2016): 1-7.

  """

  # Featurize HOPV dataset

  logger.info("About to featurize HOPV dataset.")

  if data_dir is None: