Unverified Commit d0fac17d authored by Bharath Ramsundar's avatar Bharath Ramsundar Committed by GitHub
Browse files

Merge pull request #893 from lilleswing/rdkit-upgrade 

[READY TO MERGE] rdkit upgrade
parents faab4d73 09aa2a2d

deepchem/data/datasets.py

+18 −0
Original line number Diff line number Diff line
@@ -17,6 +17,7 @@ from pandas import read_hdf 
import tempfile

import time

import shutil

import json

from multiprocessing.dummy import Pool



__author__ = "Bharath Ramsundar"
@@ -432,6 +433,23 @@ class NumpyDataset(Dataset): 
    """

    return NumpyDataset(ds.X, ds.y, ds.w, ds.ids)



  @staticmethod

  def to_json(self, fname):

    d = {

        'X': self.X.tolist(),

        'y': self.y.tolist(),

        'w': self.w.tolist(),

        'ids': self.ids.tolist()

    }

    with open(fname, 'w') as fout:

      json.dump(d, fout)



  @staticmethod

  def from_json(fname):

    with open(fname) as fin:

      d = json.load(fin)

      return NumpyDataset(d['X'], d['y'], d['w'], d['ids'])





class DiskDataset(Dataset):

  """

deepchem/dock/tests/test_pose_scoring.py

+7 −13
Original line number Diff line number Diff line
@@ -18,6 +18,8 @@ import numpy as np 
import deepchem as dc

from sklearn.ensemble import RandomForestRegressor

from subprocess import call

from deepchem.utils import download_url

from deepchem.utils import get_data_dir





class TestPoseScoring(unittest.TestCase):
@@ -27,20 +29,14 @@ class TestPoseScoring(unittest.TestCase): 


  def setUp(self):

    """Downloads dataset."""

    call(

        "wget -nv -c http://deepchem.io.s3-website-us-west-1.amazonaws.com/featurized_datasets/core_grid.tar.gz".

        split())

    call("tar -zxvf core_grid.tar.gz".split())

    self.core_dataset = dc.data.DiskDataset("core_grid/")



  def tearDown(self):

    """Removes dataset"""

    call("rm -rf core_grid/".split())

    download_url(

        "http://deepchem.io.s3-website-us-west-1.amazonaws.com/featurized_datasets/core_grid.json"

    )

    json_fname = os.path.join(get_data_dir(), 'core_grid.json')

    self.core_dataset = dc.data.NumpyDataset.from_json(json_fname)



  def test_pose_scorer_init(self):

    """Tests that pose-score works."""

    if sys.version_info >= (3, 0):

      return

    sklearn_model = RandomForestRegressor(n_estimators=10)

    model = dc.models.SklearnModel(sklearn_model)

    print("About to fit model on core set")
@@ -50,8 +46,6 @@ class TestPoseScoring(unittest.TestCase): 


  def test_pose_scorer_score(self):

    """Tests that scores are generated"""

    if sys.version_info >= (3, 0):

      return

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

    protein_file = os.path.join(current_dir, "1jld_protein.pdb")

    ligand_file = os.path.join(current_dir, "1jld_ligand.sdf")

deepchem/feat/basic.py

+33 −116
Original line number Diff line number Diff line
@@ -44,123 +44,41 @@ class RDKitDescriptors(Featurizer): 


  # (ytz): This is done to avoid future compatibility issues like inclusion of

  # the 3D descriptors or changing the feature size.

  allowedDescriptors = set(['MaxAbsPartialCharge',

    'MinPartialCharge',

    'MinAbsPartialCharge',

    'HeavyAtomMolWt',

    'MaxAbsEStateIndex',

    'NumRadicalElectrons',

    'NumValenceElectrons',

    'MinAbsEStateIndex',

    'MaxEStateIndex',

    'MaxPartialCharge',

    'MinEStateIndex',

    'ExactMolWt',

    'MolWt',

    'BalabanJ',

    'BertzCT',

    'Chi0',

    'Chi0n',

    'Chi0v',

    'Chi1',

    'Chi1n',

    'Chi1v',

    'Chi2n',

    'Chi2v',

    'Chi3n',

    'Chi3v',

    'Chi4n',

    'Chi4v',

    'HallKierAlpha',

    'Ipc',

    'Kappa1',

    'Kappa2',

    'Kappa3',

    'LabuteASA',

    'PEOE_VSA1',

    'PEOE_VSA10',

    'PEOE_VSA11',

    'PEOE_VSA12',

    'PEOE_VSA13',

    'PEOE_VSA14',

    'PEOE_VSA2',

    'PEOE_VSA3',

    'PEOE_VSA4',

    'PEOE_VSA5',

    'PEOE_VSA6',

    'PEOE_VSA7',

    'PEOE_VSA8',

    'PEOE_VSA9',

    'SMR_VSA1',

    'SMR_VSA10',

    'SMR_VSA2',

    'SMR_VSA3',

    'SMR_VSA4',

    'SMR_VSA5',

    'SMR_VSA6',

    'SMR_VSA7',

    'SMR_VSA8',

    'SMR_VSA9',

    'SlogP_VSA1',

    'SlogP_VSA10',

    'SlogP_VSA11',

    'SlogP_VSA12',

    'SlogP_VSA2',

    'SlogP_VSA3',

    'SlogP_VSA4',

    'SlogP_VSA5',

    'SlogP_VSA6',

    'SlogP_VSA7',

    'SlogP_VSA8',

    'SlogP_VSA9',

    'TPSA',

    'EState_VSA1',

    'EState_VSA10',

    'EState_VSA11',

    'EState_VSA2',

    'EState_VSA3',

    'EState_VSA4',

    'EState_VSA5',

    'EState_VSA6',

    'EState_VSA7',

    'EState_VSA8',

    'EState_VSA9',

    'VSA_EState1',

    'VSA_EState10',

    'VSA_EState2',

    'VSA_EState3',

    'VSA_EState4',

    'VSA_EState5',

    'VSA_EState6',

    'VSA_EState7',

    'VSA_EState8',

    'VSA_EState9',

    'FractionCSP3',

    'HeavyAtomCount',

    'NHOHCount',

    'NOCount',

    'NumAliphaticCarbocycles',

    'NumAliphaticHeterocycles',

    'NumAliphaticRings',

    'NumAromaticCarbocycles',

    'NumAromaticHeterocycles',

    'NumAromaticRings',

    'NumHAcceptors',

    'NumHDonors',

    'NumHeteroatoms',

    'NumRotatableBonds',

    'NumSaturatedCarbocycles',

    'NumSaturatedHeterocycles',

    'NumSaturatedRings',

    'RingCount',

    'MolLogP',

    'MolMR'])



  allowedDescriptors = set([

      'MaxAbsPartialCharge', 'MinPartialCharge', 'MinAbsPartialCharge',

      'HeavyAtomMolWt', 'MaxAbsEStateIndex', 'NumRadicalElectrons',

      'NumValenceElectrons', 'MinAbsEStateIndex', 'MaxEStateIndex',

      'MaxPartialCharge', 'MinEStateIndex', 'ExactMolWt', 'MolWt', 'BalabanJ',

      'BertzCT', 'Chi0', 'Chi0n', 'Chi0v', 'Chi1', 'Chi1n', 'Chi1v', 'Chi2n',

      'Chi2v', 'Chi3n', 'Chi3v', 'Chi4n', 'Chi4v', 'HallKierAlpha', 'Ipc',

      'Kappa1', 'Kappa2', 'Kappa3', 'LabuteASA', 'PEOE_VSA1', 'PEOE_VSA10',

      'PEOE_VSA11', 'PEOE_VSA12', 'PEOE_VSA13', 'PEOE_VSA14', 'PEOE_VSA2',

      'PEOE_VSA3', 'PEOE_VSA4', 'PEOE_VSA5', 'PEOE_VSA6', 'PEOE_VSA7',

      'PEOE_VSA8', 'PEOE_VSA9', 'SMR_VSA1', 'SMR_VSA10', 'SMR_VSA2', 'SMR_VSA3',

      'SMR_VSA4', 'SMR_VSA5', 'SMR_VSA6', 'SMR_VSA7', 'SMR_VSA8', 'SMR_VSA9',

      'SlogP_VSA1', 'SlogP_VSA10', 'SlogP_VSA11', 'SlogP_VSA12', 'SlogP_VSA2',

      'SlogP_VSA3', 'SlogP_VSA4', 'SlogP_VSA5', 'SlogP_VSA6', 'SlogP_VSA7',

      'SlogP_VSA8', 'SlogP_VSA9', 'TPSA', 'EState_VSA1', 'EState_VSA10',

      'EState_VSA11', 'EState_VSA2', 'EState_VSA3', 'EState_VSA4',

      'EState_VSA5', 'EState_VSA6', 'EState_VSA7', 'EState_VSA8', 'EState_VSA9',

      'VSA_EState1', 'VSA_EState10', 'VSA_EState2', 'VSA_EState3',

      'VSA_EState4', 'VSA_EState5', 'VSA_EState6', 'VSA_EState7', 'VSA_EState8',

      'VSA_EState9', 'FractionCSP3', 'HeavyAtomCount', 'NHOHCount', 'NOCount',

      'NumAliphaticCarbocycles', 'NumAliphaticHeterocycles',

      'NumAliphaticRings', 'NumAromaticCarbocycles', 'NumAromaticHeterocycles',

      'NumAromaticRings', 'NumHAcceptors', 'NumHDonors', 'NumHeteroatoms',

      'NumRotatableBonds', 'NumSaturatedCarbocycles',

      'NumSaturatedHeterocycles', 'NumSaturatedRings', 'RingCount', 'MolLogP',

      'MolMR'

  ])



  def __init__(self):

    self.descriptors = []

    self.descList = []

    for descriptor, function in Descriptors.descList:

      if descriptor in self.allowedDescriptors:

        self.descriptors.append(descriptor)

        self.descList.append((descriptor, function))



  def _featurize(self, mol):

    """
@@ -172,7 +90,6 @@ class RDKitDescriptors(Featurizer): 
        Molecule.

    """

    rval = []

    for desc_name, function in Descriptors.descList:

      if desc_name in self.allowedDescriptors:

    for desc_name, function in self.descList:

      rval.append(function(mol))

    return rval

deepchem/feat/tests/test_basic.py

+5 −2
Original line number Diff line number Diff line
@@ -13,6 +13,7 @@ class TestMolecularWeight(unittest.TestCase): 
  """

  Test MolecularWeight.

  """



  def setUp(self):

    """

    Set up tests.
@@ -32,6 +33,7 @@ class TestRDKitDescriptors(unittest.TestCase): 
  """

  Test RDKitDescriptors.

  """



  def setUp(self):

    """

    Set up tests.
@@ -46,5 +48,6 @@ class TestRDKitDescriptors(unittest.TestCase): 
    """

    descriptors = self.engine([self.mol])

    assert np.allclose(

      descriptors[0, self.engine.descriptors.index('ExactMolWt')], 180,

        descriptors[0, self.engine.descriptors.index('ExactMolWt')],

        180,

        atol=0.1)

deepchem/trans/transformers.py

+8 −6
Original line number Diff line number Diff line
@@ -491,7 +491,7 @@ class PowerTransformer(Transformer): 
  def untransform(self, z):

    # print("Cannot undo Power Transformer, for now.")

    n_powers = len(self.powers)

    orig_len = (z.shape[1]) / n_powers

    orig_len = (z.shape[1]) // n_powers

    z = z[:, :orig_len]

    z = np.power(z, 1 / self.powers[0])

    return z
@@ -736,8 +736,8 @@ class IRVTransformer(): 
    print('start similarity calculation')

    time1 = time.time()

    similarity = IRVTransformer.matrix_mul(X_target, np.transpose(self.X)) / (

        n_features - IRVTransformer.matrix_mul(1 - X_target,

                                               np.transpose(1 - self.X)))

        n_features -

        IRVTransformer.matrix_mul(1 - X_target, np.transpose(1 - self.X)))

    time2 = time.time()

    print('similarity calculation takes %i s' % (time2 - time1))

    for i in range(self.n_tasks):
@@ -784,8 +784,8 @@ class IRVTransformer(): 
    X_trans = []

    for count in range(X_length // 5000 + 1):

      X_trans.append(

          self.X_transform(dataset.X[count * 5000:min((count + 1) * 5000,

                                                      X_length), :]))

          self.X_transform(

              dataset.X[count * 5000:min((count + 1) * 5000, X_length), :]))

    X_trans = np.concatenate(X_trans, axis=0)

    return NumpyDataset(X_trans, dataset.y, dataset.w, ids=None)
@@ -993,7 +993,9 @@ class ANITransformer(Transformer): 
        end = min((start + 1) * batch_size, X.shape[0])

        X_batch = X[(start * batch_size):end]

        output = self.sess.run(

            [self.outputs], feed_dict={self.inputs: X_batch})[0]

            [self.outputs], feed_dict={

                self.inputs: X_batch

            })[0]

        X_out.append(output)

        num_transformed = num_transformed + X_batch.shape[0]

        print('%i samples transformed' % num_transformed)

CRA Git | Maintained and supported by SUSTech CRA and CCSE