Merge remote-tracking branch 'origin/master'

python:

- '2.7'

sudo: required

dist: trusty

install:

- sudo apt-get update

- wget http://repo.continuum.io/archive/Anaconda2-2.4.1-Linux-x86_64.sh -O anaconda.sh;

- bash anaconda.sh -b -p $HOME/anaconda

- export PATH="$HOME/anaconda/bin:$PATH"

- pip install nglview

- conda install -c omnia mdtraj 

- python setup.py install

- conda install -c https://conda.anaconda.org/jjhelmus tensorflow

script:

- nosetests -v deepchem

- nosetests -v deepchem --nologcapture

after_success:

- source devtools/travis-ci/after_sucess.sh

# AWS access_key and secret key secured through travis secure var api.

Contains methods for generating a pdbbind dataset mapping

  complexes (protein + ligand) to experimental binding measurement.

"""

from __future__ import print_function

import pickle

import os

import pandas as pd

  pdb_directories = [pdb.replace('/', '') for pdb in glob('*/')]

  for pdb_dir in pdb_directories:

    print "About to extract ligand and protein input files"

    print("About to extract ligand and protein input files")

    pdb_id = os.path.basename(pdb_dir)

    ligand_pdb = None

    protein_pdb = None

      elif re.search("_ligand.mol2$", f):

        ligand_mol2 = f

    print "Extracted Input Files:"

    print("Extracted Input Files:")

    print (ligand_pdb, protein_pdb, ligand_mol2)

    if not ligand_pdb or not protein_pdb or not ligand_mol2:

      raise ValueError("Required files not present for %s" % pdb_dir)

    except:

      ligand_mol2_lines = []

    print "About to compute ligand smiles string."

    print("About to compute ligand smiles string.")

    ligand_mol = Chem.MolFromPDBFile(ligand_pdb_path)

    if ligand_mol is None:

      continue

from deepchem.utils.save import save_to_disk

from deepchem.utils.save import load_from_disk

from deepchem.featurizers.featurize import FeaturizedSamples

from deepchem.utils.save import log

# TODO(rbharath): The semantics of this class are very difficult to debug.

# Multiple transformations of the data are performed on disk, and computations

  Wrapper class for dataset transformed into X, y, w numpy ndarrays.

  """

  def __init__(self, data_dir=None, tasks=[], samples=None, featurizers=None, 

               use_user_specified_features=False):

               use_user_specified_features=False,

               high_verbosity=False):

    """

    Turns featurized dataframes into numpy files, writes them & metadata to disk.

    """

    if not os.path.exists(data_dir):

      os.makedirs(data_dir)

    self.data_dir = data_dir

    self.high_verbosity = high_verbosity

    if featurizers is not None:

      feature_types = [featurizer.__class__.__name__ for featurizer in featurizers]

    """

    return self.metadata_df.shape[0]

  # TODO(rbharath): There is a dangerous mixup in semantics. If itershards() is

  # called without calling transform(), it will explode. Maybe have a separate

  # initialization function to avoid this problem.

  def itershards(self):

  def _itershards(self):

    """

    Iterates over all shards in dataset.

    """

      ids = load_from_disk(row['ids'])

      yield (X, y, w, ids)

  def iterbatches(self, batch_size, epoch=1):

    """

    Returns minibatches from dataset.

    """

    for i, (X, y, w, ids) in enumerate(self._itershards()):

      log("Iterating on shard-%s/epoch-%s" % (str(i+1), str(epoch+1)),

          self.high_verbosity)

      nb_sample = np.shape(X)[0]

      interval_points = np.linspace(

          0, nb_sample, np.ceil(float(nb_sample)/batch_size)+1, dtype=int)

      for j in range(len(interval_points)-1):

        log("Iterating on batch-%s/shard-%s/epoch-%s" %

            (str(j+1), str(i+1), str(epoch+1)), self.high_verbosity)

        indices = range(interval_points[j], interval_points[j+1])

        X_batch = X[indices, :]

        y_batch = y[indices]

        w_batch = w[indices]

        ids_batch = ids[indices]

        yield (X_batch, y_batch, w_batch, ids_batch)

  def __len__(self):

    """

    Finds number of elements in dataset.

    output_transforms = ["normalize"]

    model_params = {}

    task_types = {"log-solubility": "regression"}

    input_file = "../../utils/test/example.csv"

    input_file = "../../models/test/example.csv"

    train_samples, valid_samples, test_samples = (

        self._featurize_train_valid_test_split(

            splittype, input_file, task_types.keys(), frac_train=.8,

    output_transforms = ["normalize"]

    model_params = {}

    task_types = {"log-solubility": "regression"}

    input_file = "../../utils/test/example.csv"

    input_file = "../../models/test/example.csv"

    train_samples, test_samples = (

        self._featurize_train_valid_test_split(

            splittype, input_file, task_types.keys(), frac_train=.8,

    output_transforms = ["normalize"]

    model_params = {}

    task_types = {"log-solubility": "regression"}

    input_file = "../../utils/test/example.csv"

    input_file = "../../models/test/example.csv"

    train_samples, valid_samples, test_samples = (

        self._featurize_train_valid_test_split(

            splittype, input_file, task_types.keys(), frac_train=.8,

    output_transforms = ["normalize"]

    model_params = {}

    task_types = {"log-solubility": "regression"}

    input_file = "../../utils/test/example.csv"

    input_file = "../../models/test/example.csv"

    train_samples, test_samples = (

        self._featurize_train_valid_test_split(

            splittype, input_file, task_types.keys(), frac_train=.8,

    """

    Run simple tests with NNScore.

    """

    # TODO(rbharath): This is failing on older machines. Going to turn off for

    # now

    pass

    '''

    # Currently, just verifies that nothing crashes.

    for _, ligand_pdb, protein_pdb in self.test_cases:

      _ = self.nnscore_featurizer.featurize_complexes(

          [ligand_pdb], [protein_pdb])

    '''