Commit 8b3e3088 authored by nitinprakash96's avatar nitinprakash96
Browse files

Merge branch 'master' of https://github.com/deepchem/deepchem

parents 241dc427 6f7b8ec7

README.md

+1 −1
Original line number Diff line number Diff line
@@ -59,7 +59,7 @@ git clone https://github.com/deepchem/deepchem.git # Clone deepchem source 
cd deepchem

bash scripts/install_deepchem_conda.sh deepchem

source activate deepchem

yes | pip install tensorflow-gpu==1.5.0      # If you want GPU support

yes | pip install tensorflow-gpu==1.6.0      # If you want GPU support

python setup.py install                                # Manual install

nosetests -a '!slow' -v deepchem --nologcapture        # Run tests

```

deepchem/data/datasets.py

+6 −6
Original line number Diff line number Diff line
@@ -200,8 +200,8 @@ class Dataset(object): 
    >>> dataset = NumpyDataset(np.ones((2,2)))

    >>> for x, y, w, id in dataset.itersamples():

    ...   print(x.tolist(), y.tolist(), w.tolist(), id)

    [1.0 1.0] [0.0] [0.0] 0

    [1.0 1.0] [0.0] [0.0] 1

    [1.0, 1.0] [0.0] [0.0] 0

    [1.0, 1.0] [0.0] [0.0] 1

    """

    raise NotImplementedError()
@@ -409,8 +409,8 @@ class NumpyDataset(Dataset): 
    >>> dataset = NumpyDataset(np.ones((2,2)))

    >>> for x, y, w, id in dataset.itersamples():

    ...   print(x.tolist(), y.tolist(), w.tolist(), id)

    [1.0 1.0] [0.0] [0.0] 0

    [1.0 1.0] [0.0] [0.0] 1

    [1.0, 1.0] [0.0] [0.0] 0

    [1.0, 1.0] [0.0] [0.0] 1

    """

    n_samples = self._X.shape[0]

    return ((self._X[i], self._y[i], self._w[i], self._ids[i])
@@ -889,8 +889,8 @@ class DiskDataset(Dataset): 
    >>> dataset = DiskDataset.from_numpy(np.ones((2,2)), np.ones((2,1)), verbose=False)

    >>> for x, y, w, id in dataset.itersamples():

    ...   print(x.tolist(), y.tolist(), w.tolist(), id)

    [1.0 1.0] [0.0] [0.0] 0

    [1.0 1.0] [0.0] [0.0] 1

    [1.0, 1.0] [1.0] [1.0] 0

    [1.0, 1.0] [1.0] [1.0] 1

    """



    def iterate(dataset):

deepchem/feat/graph_features.py

+50 −7
Original line number Diff line number Diff line
@@ -3,7 +3,6 @@ from __future__ import unicode_literals 


import numpy as np

from rdkit import Chem

import itertools, operator



from deepchem.feat import Featurizer

from deepchem.feat.mol_graphs import ConvMol, WeaveMol
@@ -199,8 +198,8 @@ def bond_features(bond, use_chirality=False): 
  ]

  if use_chirality:

    bond_feats = bond_feats + one_of_k_encoding_unk(

        str(bond.GetStereo(),

            ["STEREONONE", "STEREOANY", "STEREOZ", "STEREOE"]))

        str(bond.GetStereo()),

        ["STEREONONE", "STEREOANY", "STEREOZ", "STEREOE"])

  return np.array(bond_feats)
@@ -264,7 +263,8 @@ def find_distance(a1, num_atoms, canon_adj_list, max_distance=7): 
class ConvMolFeaturizer(Featurizer):

  name = ['conv_mol']



  def __init__(self, master_atom=False, use_chirality=False):

  def __init__(self, master_atom=False, use_chirality=False,

               atom_properties=[]):

    """

    Parameters

    ----------
@@ -274,7 +274,20 @@ class ConvMolFeaturizer(Featurizer): 
      the molecule.  This technique is briefly discussed in

      Neural Message Passing for Quantum Chemistry

      https://arxiv.org/pdf/1704.01212.pdf



    use_chirality: Boolean

      if true then make the resulting atom features aware of the 

      chirality of the molecules in question

    atom_properties: list of string or None

      properties in the RDKit Mol object to use as additional

      atom-level features in the larger molecular feature.  If None,

      then no atom-level properties are used.  Properties should be in the 

      RDKit mol object should be in the form 

      atom XXXXXXXX NAME

      where XXXXXXXX is a zero-padded 8 digit number coresponding to the

      zero-indexed atom index of each atom and NAME is the name of the property

      provided in atom_properties.  So "atom 00000000 sasa" would be the

      name of the molecule level property in mol where the solvent 

      accessible surface area of atom 0 would be stored. 



    Since ConvMol is an object and not a numpy array, need to set dtype to

    object.
@@ -282,12 +295,39 @@ class ConvMolFeaturizer(Featurizer): 
    self.dtype = object

    self.master_atom = master_atom

    self.use_chirality = use_chirality

    self.atom_properties = list(atom_properties)



  def _get_atom_properties(self, atom):

    """

    For a given input RDKit atom return the values of the properties

    requested when initializing the featurize.  See the __init__ of the

    class for a full description of the names of the properties

    

    Parameters

    ----------

    atom: RDKit.rdchem.Atom

      Atom to get the properties of

    returns a numpy lists of floats of the same size as self.atom_properties

    """

    values = []

    for prop in self.atom_properties:

      mol_prop_name = str("atom %08d %s" % (atom.GetIdx(), prop))

      try:

        values.append(float(atom.GetOwningMol().GetProp(mol_prop_name)))

      except KeyError:

        raise KeyError("No property %s found in %s in %s" %

                       (mol_prop_name, atom.GetOwningMol(), self))

    return np.array(values)



  def _featurize(self, mol):

    """Encodes mol as a ConvMol object."""

    # Get the node features

    idx_nodes = [(a.GetIdx(), atom_features(

        a, use_chirality=self.use_chirality)) for a in mol.GetAtoms()]

    idx_nodes = [(a.GetIdx(),

                  np.concatenate((atom_features(

                      a, use_chirality=self.use_chirality),

                                  self._get_atom_properties(a))))

                 for a in mol.GetAtoms()]



    idx_nodes.sort()  # Sort by ind to ensure same order as rd_kit

    idx, nodes = list(zip(*idx_nodes))
@@ -315,6 +355,9 @@ class ConvMolFeaturizer(Featurizer): 


    return ConvMol(nodes, canon_adj_list)



  def feature_length(self):

    return 75 + len(self.atom_properties)





class WeaveFeaturizer(Featurizer):

  name = ['weave_mol']

deepchem/models/__init__.py

+6 −2
Original line number Diff line number Diff line
@@ -16,8 +16,8 @@ from deepchem.models.tensorgraph.fcnet import MultiTaskFitTransformRegressor 
from deepchem.models.tensorgraph.IRV import TensorflowMultiTaskIRVClassifier

from deepchem.models.tensorgraph.robust_multitask import RobustMultitaskClassifier

from deepchem.models.tensorgraph.robust_multitask import RobustMultitaskRegressor

from deepchem.models.tensorgraph.progressive_multitask import ProgressiveMultitaskRegressor

from deepchem.models.tensorgraph.models.graph_models import WeaveTensorGraph, DTNNTensorGraph, DAGTensorGraph, GraphConvTensorGraph, MPNNTensorGraph

from deepchem.models.tensorgraph.progressive_multitask import ProgressiveMultitaskRegressor, ProgressiveMultitaskClassifier

from deepchem.models.tensorgraph.models.graph_models import WeaveTensorGraph, DTNNTensorGraph, DAGTensorGraph, GraphConvModel, MPNNTensorGraph

from deepchem.models.tensorgraph.models.symmetry_function_regression import BPSymmetryFunctionRegression, ANIRegression



from deepchem.models.tensorgraph.models.seqtoseq import SeqToSeq
@@ -25,3 +25,7 @@ from deepchem.models.tensorgraph.models.gan import GAN, WGAN 
from deepchem.models.tensorgraph.models.text_cnn import TextCNNTensorGraph

from deepchem.models.tensorgraph.sequential import Sequential

from deepchem.models.tensorgraph.models.sequence_dnn import SequenceDNN



#################### Compatibility imports for renamed TensorGraph models. Remove below with DeepChem 3.0. ####################



from deepchem.models.tensorgraph.models.graph_models import GraphConvTensorGraph

deepchem/models/tensorgraph/IRV.py

+10 −36
Original line number Diff line number Diff line
@@ -8,7 +8,7 @@ import tensorflow as tf 
from deepchem.utils.save import log

from deepchem.models.tensorgraph.tensor_graph import TensorGraph

from deepchem.models.tensorgraph.layers import Layer, SigmoidCrossEntropy, \

    Sigmoid, Feature, Label, Weights, Concat, WeightedError

    Sigmoid, Feature, Label, Weights, Concat, WeightedError, Stack

from deepchem.models.tensorgraph.layers import convert_to_layers

from deepchem.trans import undo_transforms
@@ -178,59 +178,33 @@ class TensorflowMultiTaskIRVClassifier(TensorGraph): 
       https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2750043/

    """

    self.mol_features = Feature(shape=(None, self.n_features))

    self._labels = Label(shape=(None, self.n_tasks))

    self._weights = Weights(shape=(None, self.n_tasks))

    predictions = IRVLayer(self.n_tasks, self.K, in_layers=[self.mol_features])

    costs = []

    self.labels_fd = []

    outputs = []

    for task in range(self.n_tasks):

      task_output = Slice(task, 1, in_layers=[predictions])

      sigmoid = Sigmoid(in_layers=[task_output])

      self.add_output(sigmoid)

      outputs.append(sigmoid)



      label = Label(shape=(None, 1))

      self.labels_fd.append(label)

      label = Slice(task, axis=1, in_layers=[self._labels])

      cost = SigmoidCrossEntropy(in_layers=[label, task_output])

      costs.append(cost)

    all_cost = Concat(in_layers=costs, axis=1)

    self.weights = Weights(shape=(None, self.n_tasks))

    loss = WeightedError(in_layers=[all_cost, self.weights]) + \

    loss = WeightedError(in_layers=[all_cost, self._weights]) + \

        IRVRegularize(predictions, self.penalty, in_layers=[predictions])

    self.set_loss(loss)



  def default_generator(self,

                        dataset,

                        epochs=1,

                        predict=False,

                        deterministic=True,

                        pad_batches=True):

    """TensorGraph style implementation """

    for epoch in range(epochs):

      if not predict:

        logger.info('Starting epoch %i' % epoch)

      for (X_b, y_b, w_b, ids_b) in dataset.iterbatches(

          batch_size=self.batch_size,

          deterministic=deterministic,

          pad_batches=pad_batches):



        feed_dict = dict()

        if y_b is not None:

          for index, label in enumerate(self.labels_fd):

            feed_dict[label] = y_b[:, index:index + 1]

        if w_b is not None:

          feed_dict[self.weights] = w_b

        feed_dict[self.mol_features] = X_b



        yield feed_dict

    outputs = Stack(axis=1, in_layers=outputs)

    self.add_output(outputs)



  def predict(self, dataset, transformers=[], outputs=None):

    out = super(TensorflowMultiTaskIRVClassifier, self).predict(

        dataset, transformers=transformers, outputs=outputs)

    out = np.concatenate(out, axis=1)

    out = np.round(out).astype(int)

    return out



  def predict_proba(self, dataset, transformers=[], outputs=None):

    out = super(TensorflowMultiTaskIRVClassifier, self).predict_proba(

        dataset, transformers=transformers, outputs=outputs)

    out = np.concatenate(out, axis=1)

    out = np.stack([1 - out, out], axis=2)

    return out
 
    return np.concatenate([1 - out, out], axis=2)

CRA Git | Maintained and supported by SUSTech CRA and CCSE