merged changes from master

language: python

python:

- '2.7'

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"

- hash -r

- conda config --set always_yes yes --set changeps1 no

- conda config --add channels http://conda.binstar.org/omnia

- conda update -q conda

- conda info -a

- conda install pandas

- conda install -c omnia rdkit

- conda install -c omnia openbabel

- conda install joblib

- conda install -c omnia theano

- conda install -c omnia keras

- python setup.py install

script:

- nosetests -v deepchem

after_success:

- source devtools/travis-ci/after_sucess.sh

env:

  global:

  - secure: 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

  - secure: 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

* [sklearn](https://github.com/scikit-learn/scikit-learn.git)

* [numpy](https://store.continuum.io/cshop/anaconda/)

* [keras](keras.io)

* [vs-utils] (https://github.com/pandegroup/vs-utils.git)

Linux (64-bit) Installation 

------------------

python setup.py install

```

###vs_utils

Clone the vs_utils git repository

```bash

git clone https://github.com/pandegroup/vs-utils.git

```

Cd into the vs-utils directory and execute

```bash

python setup.py develop

```

###deepchem

Clone the deep_chem git repository

```bash

from rdkit import Chem

from deepchem.featurizers import Featurizer

from vs_utils.utils import pad_array

from deepchem.utils import pad_array

class CoulombMatrix(Featurizer):

from deepchem.utils.save import save_to_disk

from deepchem.utils.save import load_from_disk

from deepchem.utils.save import load_pandas_from_disk

from vs_utils.utils import ScaffoldGenerator

from deepchem.utils import ScaffoldGenerator

from deepchem.featurizers.nnscore import NNScoreComplexFeaturizer

import multiprocessing as mp

from functools import partial

    raw_df = load_pandas_from_disk(input_file)

    fields = raw_df.keys()

    log("Loaded raw data frame from file.", self.verbose)

    def process_raw_sample_helper(row, fields, input_type):

      return self._process_raw_sample(input_type, row, fields)

    process_raw_sample_helper_partial = partial(process_raw_sample_helper,

                                                fields=fields,

                                                input_type=input_type)

    processed_rows = raw_df.apply(process_raw_sample_helper_partial, axis=1)

    log("finished processing rows", self.verbose)

    raw_df = pd.DataFrame.from_records(processed_rows)

    #processed_rows = raw_df.apply(process_raw_sample_helper_partial, axis=1)

    raw_df = raw_df.apply(process_raw_sample_helper_partial, axis=1, reduce=False)

    #raw_df = pd.DataFrame.from_records(processed_rows)

    nb_sample = raw_df.shape[0]

    interval_points = np.linspace(

    if input_type == "csv":

      for ind, field in enumerate(fields):

        data[field] = _process_field(row[ind])

      return data

    elif input_type in ["pandas-pickle", "pandas-joblib"]:

      for field in fields:

        data[field] = _process_field(row[field])

    """

    Compute Binana fingerprint for complex.

    """

    ### OPEN TEMPDIR

    tempdir = tempfile.mkdtemp()

    mol_pdb_file = os.path.join(tempdir, "mol.pdb")

    with open(mol_pdb_file, "w") as mol_f:

    mol_pdb_file = tempfile.NamedTemporaryFile(suffix="pdb")

    with open(mol_pdb_file.name, "w") as mol_f:

      mol_f.writelines(mol_pdb)

    protein_pdb_file = os.path.join(tempdir, "protein.pdb")

    with open(protein_pdb_file, "w") as protein_f:

    protein_pdb_file = tempfile.NamedTemporaryFile(suffix="pdb")

    with open(protein_pdb_file.name, "w") as protein_f:

      protein_f.writelines(protein_pdb)

    mol_hyd_file = os.path.join(tempdir, "mol_hyd.pdb")

    mol_pdbqt_file = os.path.join(tempdir, "mol_hyd.pdbqt")

    mol_hyd_file = tempfile.NamedTemporaryFile(suffix="pdb")

    mol_pdbqt_file = tempfile.NamedTemporaryFile(suffix="pdbqt")

    hydrogenate_and_compute_partial_charges(

        mol_pdb_file, "pdb", tempdir, mol_hyd_file, mol_pdbqt_file)

        mol_pdb_file.name, "pdb", mol_hyd_file.name,

        mol_pdbqt_file.name)

    protein_hyd_file = os.path.join(tempdir, "protein_hyd.pdb")

    protein_pdbqt_file = os.path.join(tempdir, "protein_hyd.pdbqt")

    protein_hyd_file = tempfile.NamedTemporaryFile(suffix="pdb")

    protein_pdbqt_file = tempfile.NamedTemporaryFile(suffix="pdbqt")

    hydrogenate_and_compute_partial_charges(

        protein_pdb_file, "pdb", tempdir, protein_hyd_file, protein_pdbqt_file)

        protein_pdb_file.name, "pdb", protein_hyd_file.name,

        protein_pdbqt_file.name)

    mol_pdb_obj = PDB()

    mol_pdb_obj.load_from_files(mol_pdb_file, mol_pdbqt_file)

    mol_pdb_obj.load_from_files(mol_pdb_file.name, mol_pdbqt_file.name)

    protein_pdb_obj = PDB()

    protein_pdb_obj.load_from_files(protein_pdb_file, protein_pdbqt_file)

    protein_pdb_obj.load_from_files(

        protein_pdb_file.name, protein_pdbqt_file.name)

    features = self.binana.compute_input_vector(mol_pdb_obj, protein_pdb_obj)

    ### CLOSE TEMPDIR

    shutil.rmtree(tempdir)

    return features