Commit 3682fdd5 authored by Bharath Ramsundar's avatar Bharath Ramsundar Committed by GitHub
Browse files

Merge pull request #696 from miaecle/BP 

Kernel SVM, KRR, ANI-1 into molnet
parents 64803600 f36de7c1

deepchem/models/tensorgraph/layers.py

+14 −0
Original line number Diff line number Diff line
@@ -573,6 +573,20 @@ class Concat(Layer): 
    return out_tensor





class Stack(Layer):



  def __init__(self, axis=1, **kwargs):

    self.axis = axis

    super(Stack, self).__init__(**kwargs)



  def create_tensor(self, in_layers=None, set_tensors=True, **kwargs):

    inputs = self._get_input_tensors(in_layers)

    out_tensor = tf.stack(inputs, axis=self.axis)

    if set_tensors:

      self.out_tensor = out_tensor

    return out_tensor





class Constant(Layer):

  """Output a constant value."""

deepchem/models/tensorgraph/models/graph_models.py

+12 −5
Original line number Diff line number Diff line
@@ -7,7 +7,7 @@ from deepchem.metrics import to_one_hot, from_one_hot 
from deepchem.models.tensorgraph.graph_layers import WeaveLayer, WeaveGather, \

    Combine_AP, Separate_AP, DTNNEmbedding, DTNNStep, DTNNGather, DAGLayer, DAGGather, DTNNExtract

from deepchem.models.tensorgraph.layers import Dense, Concat, SoftMax, SoftMaxCrossEntropy, GraphConv, BatchNorm, \

    GraphPool, GraphGather, WeightedError, Dropout, BatchNormalization

    GraphPool, GraphGather, WeightedError, Dropout, BatchNormalization, Stack

from deepchem.models.tensorgraph.layers import L2Loss, Label, Weights, Feature

from deepchem.models.tensorgraph.tensor_graph import TensorGraph

from deepchem.trans import undo_transforms
@@ -106,7 +106,10 @@ class WeaveTensorGraph(TensorGraph): 
        self.labels_fd.append(label)

        cost = L2Loss(in_layers=[label, regression])

        costs.append(cost)

    if self.mode == "classification":

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

    elif self.mode == "regression":

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

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

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

    self.set_loss(loss)
@@ -259,7 +262,7 @@ class DTNNTensorGraph(TensorGraph): 
      cost = L2Loss(in_layers=[label, regression])

      costs.append(cost)



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

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

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

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

    self.set_loss(loss)
@@ -404,8 +407,10 @@ class DAGTensorGraph(TensorGraph): 
        self.labels_fd.append(label)

        cost = L2Loss(in_layers=[label, regression])

        costs.append(cost)



    if self.mode == "classification":

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

    elif self.mode == "regression":

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

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

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

    self.set_loss(loss)
@@ -545,8 +550,10 @@ class GraphConvTensorGraph(TensorGraph): 
        self.my_labels.append(label)

        cost = L2Loss(in_layers=[label, regression])

        costs.append(cost)



    if self.mode == "classification":

      entropy = Concat(in_layers=costs, axis=-1)

    elif self.mode == "regression":

      entropy = Stack(in_layers=costs, axis=1)

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

    loss = WeightedError(in_layers=[entropy, self.my_task_weights])

    self.set_loss(loss)
@@ -604,7 +611,7 @@ class GraphConvTensorGraph(TensorGraph): 
    if not self.built:

      self.build()

    return self.evaluate_generator(

        self.default_generator(dataset),

        self.default_generator(dataset, predict=True),

        metrics,

        labels=self.my_labels,

        weights=[self.my_task_weights])

deepchem/models/tensorgraph/models/symmetry_function_regression.py

+3 −3
Original line number Diff line number Diff line
@@ -8,7 +8,7 @@ Created on Thu Jul 6 20:31:47 2017 
import numpy as np

import tensorflow as tf



from deepchem.models.tensorgraph.layers import Dense, Concat, WeightedError

from deepchem.models.tensorgraph.layers import Dense, Concat, WeightedError, Stack

from deepchem.models.tensorgraph.layers import L2Loss, Label, Weights, Feature

from deepchem.models.tensorgraph.tensor_graph import TensorGraph

from deepchem.models.tensorgraph.graph_layers import DTNNEmbedding
@@ -69,7 +69,7 @@ class BPSymmetryFunctionRegression(TensorGraph): 
      cost = L2Loss(in_layers=[label, output])

      costs.append(cost)



    all_cost = Concat(in_layers=costs, axis=0)

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

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

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

    self.set_loss(loss)
@@ -158,7 +158,7 @@ class ANIRegression(TensorGraph): 
      cost = L2Loss(in_layers=[label, output])

      costs.append(cost)



    all_cost = Concat(in_layers=costs, axis=0)

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

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

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

    self.set_loss(loss)

deepchem/molnet/check_availability.py

+25 −2
Original line number Diff line number Diff line
@@ -3,6 +3,7 @@ CheckFeaturizer = { 
    ('bace_c', 'tf'): ['ECFP', 1024],

    ('bace_c', 'tf_robust'): ['ECFP', 1024],

    ('bace_c', 'rf'): ['ECFP', 1024],

    ('bace_c', 'kernelsvm'): ['ECFP', 1024],

    ('bace_c', 'irv'): ['ECFP', 1024],

    ('bace_c', 'xgb'): ['ECFP', 1024],

    ('bace_c', 'graphconv'): ['GraphConv', 75],
@@ -12,6 +13,7 @@ CheckFeaturizer = { 
    ('bbbp', 'tf'): ['ECFP', 1024],

    ('bbbp', 'tf_robust'): ['ECFP', 1024],

    ('bbbp', 'rf'): ['ECFP', 1024],

    ('bbbp', 'kernelsvm'): ['ECFP', 1024],

    ('bbbp', 'irv'): ['ECFP', 1024],

    ('bbbp', 'xgb'): ['ECFP', 1024],

    ('bbbp', 'graphconv'): ['GraphConv', 75],
@@ -21,6 +23,7 @@ CheckFeaturizer = { 
    ('clintox', 'tf'): ['ECFP', 1024],

    ('clintox', 'tf_robust'): ['ECFP', 1024],

    ('clintox', 'rf'): ['ECFP', 1024],

    ('clintox', 'kernelsvm'): ['ECFP', 1024],

    ('clintox', 'irv'): ['ECFP', 1024],

    ('clintox', 'xgb'): ['ECFP', 1024],

    ('clintox', 'graphconv'): ['GraphConv', 75],
@@ -30,6 +33,7 @@ CheckFeaturizer = { 
    ('hiv', 'tf'): ['ECFP', 1024],

    ('hiv', 'tf_robust'): ['ECFP', 1024],

    ('hiv', 'rf'): ['ECFP', 1024],

    ('hiv', 'kernelsvm'): ['ECFP', 1024],

    ('hiv', 'irv'): ['ECFP', 1024],

    ('hiv', 'xgb'): ['ECFP', 1024],

    ('hiv', 'graphconv'): ['GraphConv', 75],
@@ -39,6 +43,7 @@ CheckFeaturizer = { 
    ('muv', 'tf'): ['ECFP', 1024],

    ('muv', 'tf_robust'): ['ECFP', 1024],

    ('muv', 'rf'): ['ECFP', 1024],

    ('muv', 'kernelsvm'): ['ECFP', 1024],

    ('muv', 'irv'): ['ECFP', 1024],

    ('muv', 'xgb'): ['ECFP', 1024],

    ('muv', 'graphconv'): ['GraphConv', 75],
@@ -49,7 +54,6 @@ CheckFeaturizer = { 
    ('pcba', 'logreg'): ['ECFP', 1024],

    ('pcba', 'tf'): ['ECFP', 1024],

    ('pcba', 'tf_robust'): ['ECFP', 1024],

    ('pcba', 'rf'): ['ECFP', 1024],

    ('pcba', 'irv'): ['ECFP', 1024],

    ('pcba', 'xgb'): ['ECFP', 1024],

    ('pcba', 'graphconv'): ['GraphConv', 75],
@@ -58,6 +62,7 @@ CheckFeaturizer = { 
    ('sider', 'tf'): ['ECFP', 1024],

    ('sider', 'tf_robust'): ['ECFP', 1024],

    ('sider', 'rf'): ['ECFP', 1024],

    ('sider', 'kernelsvm'): ['ECFP', 1024],

    ('sider', 'irv'): ['ECFP', 1024],

    ('sider', 'xgb'): ['ECFP', 1024],

    ('sider', 'graphconv'): ['GraphConv', 75],
@@ -70,6 +75,7 @@ CheckFeaturizer = { 
    ('tox21', 'tf'): ['ECFP', 1024],

    ('tox21', 'tf_robust'): ['ECFP', 1024],

    ('tox21', 'rf'): ['ECFP', 1024],

    ('tox21', 'kernelsvm'): ['ECFP', 1024],

    ('tox21', 'irv'): ['ECFP', 1024],

    ('tox21', 'xgb'): ['ECFP', 1024],

    ('tox21', 'graphconv'): ['GraphConv', 75],
@@ -82,83 +88,100 @@ CheckFeaturizer = { 
    ('toxcast', 'tf'): ['ECFP', 1024],

    ('toxcast', 'tf_robust'): ['ECFP', 1024],

    ('toxcast', 'rf'): ['ECFP', 1024],

    ('toxcast', 'kernelsvm'): ['ECFP', 1024],

    ('toxcast', 'irv'): ['ECFP', 1024],

    ('toxcast', 'xgb'): ['ECFP', 1024],

    ('toxcast', 'graphconv'): ['GraphConv', 75],

    ('toxcast', 'weave'): ['Weave', 75],

    ('bace_r', 'tf_regression'): ['ECFP', 1024],

    ('bace_r', 'rf_regression'): ['ECFP', 1024],

    ('bace_r', 'krr'): ['ECFP', 1024],

    ('bace_r', 'xgb_regression'): ['ECFP', 1024],

    ('bace_r', 'graphconvreg'): ['GraphConv', 75],

    ('bace_r', 'dag_regression'): ['GraphConv', 75],

    ('bace_r', 'weave_regression'): ['Weave', 75],

    ('chembl', 'tf_regression'): ['ECFP', 1024],

    ('chembl', 'rf_regression'): ['ECFP', 1024],

    ('chembl', 'krr'): ['ECFP', 1024],

    ('chembl', 'xgb_regression'): ['ECFP', 1024],

    ('chembl', 'graphconvreg'): ['GraphConv', 75],

    ('chembl', 'weave_regression'): ['Weave', 75],

    ('clearance', 'tf_regression'): ['ECFP', 1024],

    ('clearance', 'rf_regression'): ['ECFP', 1024],

    ('clearance', 'krr'): ['ECFP', 1024],

    ('clearance', 'xgb_regression'): ['ECFP', 1024],

    ('clearance', 'graphconvreg'): ['GraphConv', 75],

    ('clearance', 'dag_regression'): ['GraphConv', 75],

    ('clearance', 'weave_regression'): ['Weave', 75],

    ('delaney', 'tf_regression'): ['ECFP', 1024],

    ('delaney', 'rf_regression'): ['ECFP', 1024],

    ('delaney', 'krr'): ['ECFP', 1024],

    ('delaney', 'xgb_regression'): ['ECFP', 1024],

    ('delaney', 'graphconvreg'): ['GraphConv', 75],

    ('delaney', 'dag_regression'): ['GraphConv', 75],

    ('delaney', 'weave_regression'): ['Weave', 75],

    ('hopv', 'tf_regression'): ['ECFP', 1024],

    ('hopv', 'rf_regression'): ['ECFP', 1024],

    ('hopv', 'krr'): ['ECFP', 1024],

    ('hopv', 'xgb_regression'): ['ECFP', 1024],

    ('hopv', 'graphconvreg'): ['GraphConv', 75],

    ('hopv', 'dag_regression'): ['GraphConv', 75],

    ('hopv', 'weave_regression'): ['Weave', 75],

    ('lipo', 'tf_regression'): ['ECFP', 1024],

    ('lipo', 'rf_regression'): ['ECFP', 1024],

    ('lipo', 'krr'): ['ECFP', 1024],

    ('lipo', 'xgb_regression'): ['ECFP', 1024],

    ('lipo', 'graphconvreg'): ['GraphConv', 75],

    ('lipo', 'dag_regression'): ['GraphConv', 75],

    ('lipo', 'weave_regression'): ['Weave', 75],

    ('nci', 'tf_regression'): ['ECFP', 1024],

    ('nci', 'rf_regression'): ['ECFP', 1024],

    ('nci', 'krr'): ['ECFP', 1024],

    ('nci', 'xgb_regression'): ['ECFP', 1024],

    ('nci', 'graphconvreg'): ['GraphConv', 75],

    ('nci', 'weave_regression'): ['Weave', 75],

    ('ppb', 'tf_regression'): ['ECFP', 1024],

    ('ppb', 'rf_regression'): ['ECFP', 1024],

    ('ppb', 'krr'): ['ECFP', 1024],

    ('ppb', 'xgb_regression'): ['ECFP', 1024],

    ('ppb', 'graphconvreg'): ['GraphConv', 75],

    ('ppb', 'dag_regression'): ['GraphConv', 75],

    ('ppb', 'weave_regression'): ['Weave', 75],

    ('sampl', 'tf_regression'): ['ECFP', 1024],

    ('sampl', 'rf_regression'): ['ECFP', 1024],

    ('sampl', 'krr'): ['ECFP', 1024],

    ('sampl', 'xgb_regression'): ['ECFP', 1024],

    ('sampl', 'graphconvreg'): ['GraphConv', 75],

    ('sampl', 'dag_regression'): ['GraphConv', 75],

    ('sampl', 'weave_regression'): ['Weave', 75],

    ('kaggle', 'tf_regression'): [None, 14293],

    ('kaggle', 'rf_regression'): [None, 14293],

    ('kaggle', 'krr'): [None, 14293],

    ('pdbbind', 'tf_regression'): ['grid', 2052],

    ('pdbbind', 'rf_regression'): ['grid', 2052],

    ('qm7', 'tf_regression'): ['ECFP', 1024],

    ('qm7', 'rf_regression'): ['ECFP', 1024],

    ('qm7', 'krr'): ['ECFP', 1024],

    ('qm7', 'graphconvreg'): ['GraphConv', 75],

    ('qm7', 'tf_regression_ft'): ['CoulombMatrix', [23, 23]],

    ('qm7', 'dtnn'): ['CoulombMatrix', [23, 23]],

    ('qm7', 'ani'): ['BPSymmetryFunction', [23, 4]],

    ('qm7b', 'tf_regression_ft'): ['CoulombMatrix', [23, 23]],

    ('qm7b', 'dtnn'): ['CoulombMatrix', [23, 23]],

    ('qm8', 'tf_regression'): ['ECFP', 1024],

    ('qm8', 'rf_regression'): ['ECFP', 1024],

    ('qm8', 'krr'): ['ECFP', 1024],

    ('qm8', 'graphconvreg'): ['GraphConv', 75],

    ('qm8', 'tf_regression_ft'): ['CoulombMatrix', [26, 26]],

    ('qm8', 'dtnn'): ['CoulombMatrix', [26, 26]],

    ('qm8', 'ani'): ['BPSymmetryFunction', [26, 4]],

    ('qm9', 'tf_regression'): ['ECFP', 1024],

    ('qm9', 'rf_regression'): ['ECFP', 1024],

    ('qm9', 'krr'): ['ECFP', 1024],

    ('qm9', 'graphconvreg'): ['GraphConv', 75],

    ('qm9', 'tf_regression_ft'): ['CoulombMatrix', [29, 29]],

    ('qm9', 'dtnn'): ['CoulombMatrix', [29, 29]]

    ('qm9', 'dtnn'): ['CoulombMatrix', [29, 29]],

    ('qm9', 'ani'): ['BPSymmetryFunction', [29, 4]]

}



CheckSplit = {

deepchem/molnet/load_function/bbbp_datasets.py

+1 −1
Original line number Diff line number Diff line
@@ -9,7 +9,7 @@ import os 
import deepchem





def load_bbbp(featurizer='ECFP', split='index', reload=True):

def load_bbbp(featurizer='ECFP', split='random', reload=True):

  """Load blood-brain barrier penetration datasets """

  # Featurize bbb dataset

  print("About to featurize bbbp dataset.")

CRA Git | Maintained and supported by SUSTech CRA and CCSE