Loading deepchem/feat/adjacency_fingerprints.py +8 −4 Original line number Diff line number Diff line Loading @@ -134,10 +134,12 @@ def get_atom_adj_matrices(mol, return (adj_matrix.astype(np.uint8), atom_matrix.astype(np.uint8)) def featurize_mol(mol, n_atom_types, max_n_atoms, max_valence): def featurize_mol(mol, n_atom_types, max_n_atoms, max_valence, num_atoms_feature): adj_matrix, atom_matrix = get_atom_adj_matrices(mol, n_atom_types, max_n_atoms, max_valence) if num_atoms_feature: return ((adj_matrix, atom_matrix, mol.GetNumAtoms())) return ((adj_matrix, atom_matrix)) Loading @@ -147,11 +149,13 @@ class AdjacencyFingerprint(Featurizer): n_atom_types=23, max_n_atoms=200, add_hydrogens=False, max_valence=4): max_valence=4, num_atoms_feature=False): self.n_atom_types = n_atom_types self.max_n_atoms = max_n_atoms self.add_hydrogens = add_hydrogens self.max_valence = max_valence self.num_atoms_feature = num_atoms_feature def featurize(self, rdkit_mols): featurized_mols = np.empty((len(rdkit_mols)), dtype=object) Loading @@ -160,6 +164,6 @@ class AdjacencyFingerprint(Featurizer): if self.add_hydrogens: mol = Chem.AddHs(mol) featurized_mol = featurize_mol(mol, self.n_atom_types, self.max_n_atoms, self.max_valence) self.max_valence, self.num_atoms_feature) featurized_mols[idx] = featurized_mol return (featurized_mols) deepchem/models/tensorgraph/layers.py +149 −3 Original line number Diff line number Diff line Loading @@ -6,6 +6,7 @@ import tensorflow as tf import numpy as np from deepchem.nn import model_ops, initializations, regularizers, activations import math class Layer(object): Loading Loading @@ -3112,3 +3113,148 @@ class BetaShare(Layer): def set_tensors(self, tensor): self.out_tensor, self.betas = tensor class PassThroughLayer(Layer): def __init__(self, output_num, **kwargs): self.output_num = output_num super(PassThroughLayer, self).__init__(**kwargs) def create_tensor(self, in_layers=None, set_tensors=True, **kwargs): self.out_tensor = self.in_layers[0].out_tensors[self.output_num] class GraphCNNPoolLayer(Layer): def __init__(self, num_vertices, **kwargs): self.num_vertices = num_vertices super(GraphCNNPoolLayer, self).__init__(**kwargs) def create_tensor(self, in_layers=None, set_tensors=True, **kwargs): """ TODO(LESWING) self.num_vertices = 1 Parameters ---------- in_layers set_tensors kwargs Returns ------- """ in_tensors = self._get_input_tensors(in_layers) if len(in_tensors) == 3: V, A, mask = in_tensors else: V, A = in_tensors mask = None factors = self.embedding_factors( V, self.num_vertices, name='%s_Factors' % self.name) if mask is not None: factors = tf.multiply(factors, mask) factors = self.softmax_factors(factors) result = tf.matmul(factors, V, transpose_a=True) result_A = tf.reshape(A, (tf.shape(A)[0], -1, tf.shape(A)[-1])) result_A = tf.matmul(result_A, factors) result_A = tf.reshape(result_A, (tf.shape(A)[0], tf.shape(A)[-1], -1)) result_A = tf.matmul(factors, result_A, transpose_a=True) result_A = tf.reshape(result_A, (tf.shape(A)[0], self.num_vertices, A.get_shape()[2].value, self.num_vertices)) # We do not need the mask because every graph has self.num_vertices vertices now # result = make_bn(result, True, mask=None, name="%s_bn" % self.name) self.out_tensors = [result, result_A, factors] def embedding_factors(self, V, no_filters, name="default"): no_features = V.get_shape()[-1].value W = tf.get_variable( '%s_weights' % name, [no_features, no_filters], initializer=tf.truncated_normal_initializer( stddev=1.0 / math.sqrt(no_features)), dtype=tf.float32) b = tf.get_variable( '%s_bias' % self.name, [no_filters], initializer=tf.constant_initializer(0.1), dtype=tf.float32) V_reshape = tf.reshape(V, (-1, no_features)) s = tf.slice(tf.shape(V), [0], [len(V.get_shape()) - 1]) s = tf.concat([s, tf.stack([no_filters])], 0) result = tf.reshape(tf.matmul(V_reshape, W) + b, s) return result def softmax_factors(self, V, axis=1, name=None): max_value = tf.reduce_max(V, axis=axis, keep_dims=True) exp = tf.exp(tf.subtract(V, max_value)) prob = tf.div(exp, tf.reduce_sum(exp, axis=axis, keep_dims=True)) return prob def GraphCNNPool(num_vertices, **kwargs): gcnnpool_layer = GraphCNNPoolLayer(num_vertices, **kwargs) return [PassThroughLayer(x, in_layers=gcnnpool_layer) for x in range(3)] class GraphCNNLayer(Layer): def __init__(self, num_filters, **kwargs): self.num_filters = num_filters super(GraphCNNLayer, self).__init__(**kwargs) def create_tensor(self, in_layers=None, set_tensors=True, **kwargs): inputs = self._get_input_tensors(in_layers) if len(inputs) == 3: V, A, mask = inputs else: V, A = inputs mask = None no_A = A.get_shape()[2].value no_features = V.get_shape()[2].value W = tf.get_variable( '%s_weights' % self.name, [no_features * no_A, self.num_filters], initializer=tf.truncated_normal_initializer(stddev=math.sqrt( 1.0 / (no_features * (no_A + 1) * 1.0))), dtype=tf.float32) W_I = tf.get_variable( '%s_weights_I' % self.name, [no_features, self.num_filters], initializer=tf.truncated_normal_initializer(stddev=math.sqrt( 1.0 / (no_features * (no_A + 1) * 1.0))), dtype=tf.float32) b = tf.get_variable( '%s_bias' % self.name, [self.num_filters], initializer=tf.constant_initializer(0.1), dtype=tf.float32) n = self.graphConvolution(V, A) A_shape = tf.shape(A) n = tf.reshape(n, [-1, A_shape[1], no_A * no_features]) result = self.batch_mat_mult(n, W) + self.batch_mat_mult(V, W_I) + b if set_tensors: self.out_tensor = result return result def graphConvolution(self, V, A): no_A = A.get_shape()[2].value no_features = V.get_shape()[2].value A_shape = tf.shape(A) A_reshape = tf.reshape(A, tf.stack([-1, A_shape[1] * no_A, A_shape[1]])) n = tf.matmul(A_reshape, V) return tf.reshape(n, [-1, A_shape[1], no_A, no_features]) def batch_mat_mult(self, A, B): A_shape = tf.shape(A) A_reshape = tf.reshape(A, [-1, A_shape[-1]]) # So the Tensor has known dimensions if B.get_shape()[1] == None: axis_2 = -1 else: axis_2 = B.get_shape()[1] result = tf.matmul(A_reshape, B) result = tf.reshape(result, tf.stack([A_shape[0], A_shape[1], axis_2])) return result deepchem/models/tensorgraph/models/graph_models.py +153 −11 Original line number Diff line number Diff line import math import numpy as np import six import tensorflow as tf from deepchem.data import NumpyDataset from deepchem.feat.graph_features import ConvMolFeaturizer from deepchem.feat.mol_graphs import ConvMol from deepchem.metrics import to_one_hot, from_one_hot from deepchem.metrics import to_one_hot from deepchem.models.tensorgraph.graph_layers import WeaveLayer, WeaveGather, \ Combine_AP, Separate_AP, DTNNEmbedding, DTNNStep, DTNNGather, DAGLayer, \ DAGGather, DTNNExtract, MessagePassing, SetGather from deepchem.models.tensorgraph.layers import Dense, Concat, SoftMax, \ SoftMaxCrossEntropy, GraphConv, BatchNorm, \ GraphPool, GraphGather, WeightedError, Dropout, BatchNormalization, Stack GraphPool, GraphGather, WeightedError, Dropout, BatchNormalization, Stack, Layer, Flatten, GraphCNNLayer, GraphCNNPool from deepchem.models.tensorgraph.layers import L2Loss, Label, Weights, Feature from deepchem.models.tensorgraph.tensor_graph import TensorGraph from deepchem.trans import undo_transforms from deepchem.utils.evaluate import GeneratorEvaluator from deepchem.data import NumpyDataset from deepchem.data.data_loader import featurize_smiles_np from deepchem.feat.graph_features import ConvMolFeaturizer class WeaveTensorGraph(TensorGraph): Loading Loading @@ -487,6 +486,149 @@ class DAGTensorGraph(TensorGraph): yield feed_dict class PetroskiSuchTensorGraph(TensorGraph): def __init__(self, n_tasks, max_atoms=200, dropout=0.2, mode="classification", **kwargs): """ Parameters ---------- n_tasks: int Number of tasks mode: str Either "classification" or "regression" """ self.n_tasks = n_tasks self.mode = mode self.max_atoms = max_atoms self.error_bars = True if 'error_bars' in kwargs and kwargs['error_bars'] else False self.dropout = dropout kwargs['use_queue'] = False super(PetroskiSuchTensorGraph, self).__init__(**kwargs) self.build_graph() def build_graph(self): self.vertex_features = Feature(shape=(None, self.max_atoms, 75)) self.adj_matrix = Feature(shape=(None, self.max_atoms, 1, self.max_atoms)) self.mask = Feature(shape=(None, self.max_atoms, 1)) gcnn1 = BatchNorm( GraphCNNLayer( num_filters=64, in_layers=[self.vertex_features, self.adj_matrix, self.mask])) gcnn1 = Dropout(self.dropout, in_layers=gcnn1) gcnn2 = BatchNorm( GraphCNNLayer( num_filters=64, in_layers=[gcnn1, self.adj_matrix, self.mask])) gcnn2 = Dropout(self.dropout, in_layers=gcnn2) gc_pool, adj_matrix, factors = GraphCNNPool( num_vertices=32, in_layers=[gcnn2, self.adj_matrix, self.mask]) gc_pool = BatchNorm(gc_pool) gc_pool = Dropout(self.dropout, in_layers=gc_pool) gcnn3 = BatchNorm( GraphCNNLayer(num_filters=32, in_layers=[gc_pool, adj_matrix])) gcnn3 = Dropout(self.dropout, in_layers=gcnn3) gc_pool2, adj_matrix2, factors = GraphCNNPool( num_vertices=8, in_layers=[gcnn3, adj_matrix]) gc_pool2 = BatchNorm(gc_pool2) gc_pool2 = Dropout(self.dropout, in_layers=gc_pool2) flattened = Flatten(in_layers=gc_pool2) readout = Dense( out_channels=256, activation_fn=tf.nn.relu, in_layers=flattened) costs = [] self.my_labels = [] for task in range(self.n_tasks): if self.mode == 'classification': classification = Dense( out_channels=2, activation_fn=None, in_layers=[readout]) softmax = SoftMax(in_layers=[classification]) self.add_output(softmax) label = Label(shape=(None, 2)) self.my_labels.append(label) cost = SoftMaxCrossEntropy(in_layers=[label, classification]) costs.append(cost) if self.mode == 'regression': regression = Dense( out_channels=1, activation_fn=None, in_layers=[readout]) self.add_output(regression) label = Label(shape=(None, 1)) 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) def default_generator(self, dataset, epochs=1, predict=False, deterministic=True, pad_batches=True): for epoch in range(epochs): if not predict: print('Starting epoch %i' % epoch) for ind, (X_b, y_b, w_b, ids_b) in enumerate( dataset.iterbatches( self.batch_size, pad_batches=True, deterministic=deterministic)): d = {} for index, label in enumerate(self.my_labels): if self.mode == 'classification': d[label] = to_one_hot(y_b[:, index]) if self.mode == 'regression': d[label] = np.expand_dims(y_b[:, index], -1) d[self.my_task_weights] = w_b d[self.adj_matrix] = np.expand_dims(np.array([x[0] for x in X_b]), -2) d[self.vertex_features] = np.array([x[1] for x in X_b]) mask = np.zeros(shape=(self.batch_size, self.max_atoms, 1)) for i in range(self.batch_size): mask_size = X_b[i][2] mask[i][:mask_size][0] = 1 d[self.mask] = mask yield d def predict_proba_on_generator(self, generator, transformers=[]): if not self.built: self.build() with self._get_tf("Graph").as_default(): out_tensors = [x.out_tensor for x in self.outputs] results = [] for feed_dict in generator: feed_dict = { self.layers[k.name].out_tensor: v for k, v in six.iteritems(feed_dict) } feed_dict[self._training_placeholder] = 1.0 ## result = np.array(self.session.run(out_tensors, feed_dict=feed_dict)) if len(result.shape) == 3: result = np.transpose(result, axes=[1, 0, 2]) if len(transformers) > 0: result = undo_transforms(result, transformers) results.append(result) return np.concatenate(results, axis=0) def evaluate(self, dataset, metrics, transformers=[], per_task_metrics=False): if not self.built: self.build() return self.evaluate_generator( self.default_generator(dataset, predict=True), metrics, labels=self.my_labels, weights=[self.my_task_weights], per_task_metrics=per_task_metrics) class GraphConvTensorGraph(TensorGraph): def __init__(self, n_tasks, mode="classification", **kwargs): Loading examples/tox21/tox21_datasets.py +38 −13 Original line number Diff line number Diff line Loading @@ -6,40 +6,65 @@ from __future__ import division from __future__ import unicode_literals import os import deepchem import numpy as np import shutil import deepchem as dc from deepchem.data import DiskDataset def load_tox21(featurizer='ECFP', split='index'): """Load Tox21 datasets. Does not do train/test split""" # Featurize Tox21 dataset print("About to featurize Tox21 dataset.") current_dir = os.path.dirname(os.path.realpath(__file__)) dataset_file = os.path.join( current_dir, "../../datasets/tox21.csv.gz") tox21_tasks = ['NR-AR', 'NR-AR-LBD', 'NR-AhR', 'NR-Aromatase', 'NR-ER', 'NR-ER-LBD', 'NR-PPAR-gamma', 'SR-ARE', 'SR-ATAD5', 'SR-HSE', 'SR-MMP', 'SR-p53'] dataset_file = os.path.join(current_dir, "../../datasets/tox21.csv.gz") data_dir = deepchem.utils.get_data_dir() tox21_tasks = [ 'NR-AR', 'NR-AR-LBD', 'NR-AhR', 'NR-Aromatase', 'NR-ER', 'NR-ER-LBD', 'NR-PPAR-gamma', 'SR-ARE', 'SR-ATAD5', 'SR-HSE', 'SR-MMP', 'SR-p53' ] dataset_dir = os.path.join(data_dir, "tox21", featurizer, split) train, valid, test = os.path.join(dataset_dir, 'train'), os.path.join( dataset_dir, 'valid'), os.path.join(dataset_dir, 'test') if os.path.isdir(dataset_dir): train, valid, test = DiskDataset(data_dir=train), DiskDataset( data_dir=valid), DiskDataset(data_dir=test) transformers = [ dc.trans.BalancingTransformer(transform_w=True, dataset=train) ] return tox21_tasks, (train, valid, test), transformers if featurizer == 'ECFP': featurizer_func = dc.feat.CircularFingerprint(size=1024) elif featurizer == 'GraphConv': featurizer_func = dc.feat.ConvMolFeaturizer() elif featurizer == 'AdjMatrix': featurizer_func = dc.feat.AdjacencyFingerprint(num_atoms_feature=True) loader = dc.data.CSVLoader( tasks=tox21_tasks, smiles_field="smiles", featurizer=featurizer_func) dataset = loader.featurize(dataset_file, shard_size=8192) # Initialize transformers transformers = [ dc.trans.BalancingTransformer(transform_w=True, dataset=dataset)] dc.trans.BalancingTransformer(transform_w=True, dataset=dataset) ] print("About to transform data") for transformer in transformers: dataset = transformer.transform(dataset) splitters = {'index': dc.splits.IndexSplitter(), splitters = { 'index': dc.splits.IndexSplitter(), 'random': dc.splits.RandomSplitter(), 'scaffold': dc.splits.ScaffoldSplitter(), 'butina': dc.splits.ButinaSplitter()} 'butina': dc.splits.ButinaSplitter() } splitter = splitters[split] train, valid, test = splitter.train_valid_test_split(dataset) train, valid, test = splitter.train_valid_test_split( dataset, train_dir=train, valid_dir=valid, test_dir=test) return tox21_tasks, (train, valid, test), transformers examples/tox21/tox21_graphcnn.py 0 → 100644 +47 −0 Original line number Diff line number Diff line """ Script that trains graph-conv models on Tox21 dataset. """ from __future__ import division from __future__ import print_function from __future__ import unicode_literals import numpy as np import json np.random.seed(123) import tensorflow as tf tf.set_random_seed(123) import deepchem as dc from tox21_datasets import load_tox21 from deepchem.models.tensorgraph.models.graph_models import PetroskiSuchTensorGraph model_dir = "/tmp/graph_conv" # Load Tox21 dataset tox21_tasks, tox21_datasets, transformers = load_tox21(featurizer='AdjMatrix') train_dataset, valid_dataset, test_dataset = tox21_datasets print(train_dataset.data_dir) print(valid_dataset.data_dir) # Fit models metric = dc.metrics.Metric( dc.metrics.roc_auc_score, np.mean, mode="classification") # Batch size of models batch_size = 128 model = PetroskiSuchTensorGraph( len(tox21_tasks), batch_size=batch_size, mode='classification') model.fit(train_dataset, nb_epoch=10) print("Evaluating model") train_scores = model.evaluate(train_dataset, [metric], transformers) valid_scores = model.evaluate(valid_dataset, [metric], transformers) print("Train scores") print(train_scores) print("Validation scores") print(valid_scores) Loading
deepchem/feat/adjacency_fingerprints.py +8 −4 Original line number Diff line number Diff line Loading @@ -134,10 +134,12 @@ def get_atom_adj_matrices(mol, return (adj_matrix.astype(np.uint8), atom_matrix.astype(np.uint8)) def featurize_mol(mol, n_atom_types, max_n_atoms, max_valence): def featurize_mol(mol, n_atom_types, max_n_atoms, max_valence, num_atoms_feature): adj_matrix, atom_matrix = get_atom_adj_matrices(mol, n_atom_types, max_n_atoms, max_valence) if num_atoms_feature: return ((adj_matrix, atom_matrix, mol.GetNumAtoms())) return ((adj_matrix, atom_matrix)) Loading @@ -147,11 +149,13 @@ class AdjacencyFingerprint(Featurizer): n_atom_types=23, max_n_atoms=200, add_hydrogens=False, max_valence=4): max_valence=4, num_atoms_feature=False): self.n_atom_types = n_atom_types self.max_n_atoms = max_n_atoms self.add_hydrogens = add_hydrogens self.max_valence = max_valence self.num_atoms_feature = num_atoms_feature def featurize(self, rdkit_mols): featurized_mols = np.empty((len(rdkit_mols)), dtype=object) Loading @@ -160,6 +164,6 @@ class AdjacencyFingerprint(Featurizer): if self.add_hydrogens: mol = Chem.AddHs(mol) featurized_mol = featurize_mol(mol, self.n_atom_types, self.max_n_atoms, self.max_valence) self.max_valence, self.num_atoms_feature) featurized_mols[idx] = featurized_mol return (featurized_mols)
deepchem/models/tensorgraph/layers.py +149 −3 Original line number Diff line number Diff line Loading @@ -6,6 +6,7 @@ import tensorflow as tf import numpy as np from deepchem.nn import model_ops, initializations, regularizers, activations import math class Layer(object): Loading Loading @@ -3112,3 +3113,148 @@ class BetaShare(Layer): def set_tensors(self, tensor): self.out_tensor, self.betas = tensor class PassThroughLayer(Layer): def __init__(self, output_num, **kwargs): self.output_num = output_num super(PassThroughLayer, self).__init__(**kwargs) def create_tensor(self, in_layers=None, set_tensors=True, **kwargs): self.out_tensor = self.in_layers[0].out_tensors[self.output_num] class GraphCNNPoolLayer(Layer): def __init__(self, num_vertices, **kwargs): self.num_vertices = num_vertices super(GraphCNNPoolLayer, self).__init__(**kwargs) def create_tensor(self, in_layers=None, set_tensors=True, **kwargs): """ TODO(LESWING) self.num_vertices = 1 Parameters ---------- in_layers set_tensors kwargs Returns ------- """ in_tensors = self._get_input_tensors(in_layers) if len(in_tensors) == 3: V, A, mask = in_tensors else: V, A = in_tensors mask = None factors = self.embedding_factors( V, self.num_vertices, name='%s_Factors' % self.name) if mask is not None: factors = tf.multiply(factors, mask) factors = self.softmax_factors(factors) result = tf.matmul(factors, V, transpose_a=True) result_A = tf.reshape(A, (tf.shape(A)[0], -1, tf.shape(A)[-1])) result_A = tf.matmul(result_A, factors) result_A = tf.reshape(result_A, (tf.shape(A)[0], tf.shape(A)[-1], -1)) result_A = tf.matmul(factors, result_A, transpose_a=True) result_A = tf.reshape(result_A, (tf.shape(A)[0], self.num_vertices, A.get_shape()[2].value, self.num_vertices)) # We do not need the mask because every graph has self.num_vertices vertices now # result = make_bn(result, True, mask=None, name="%s_bn" % self.name) self.out_tensors = [result, result_A, factors] def embedding_factors(self, V, no_filters, name="default"): no_features = V.get_shape()[-1].value W = tf.get_variable( '%s_weights' % name, [no_features, no_filters], initializer=tf.truncated_normal_initializer( stddev=1.0 / math.sqrt(no_features)), dtype=tf.float32) b = tf.get_variable( '%s_bias' % self.name, [no_filters], initializer=tf.constant_initializer(0.1), dtype=tf.float32) V_reshape = tf.reshape(V, (-1, no_features)) s = tf.slice(tf.shape(V), [0], [len(V.get_shape()) - 1]) s = tf.concat([s, tf.stack([no_filters])], 0) result = tf.reshape(tf.matmul(V_reshape, W) + b, s) return result def softmax_factors(self, V, axis=1, name=None): max_value = tf.reduce_max(V, axis=axis, keep_dims=True) exp = tf.exp(tf.subtract(V, max_value)) prob = tf.div(exp, tf.reduce_sum(exp, axis=axis, keep_dims=True)) return prob def GraphCNNPool(num_vertices, **kwargs): gcnnpool_layer = GraphCNNPoolLayer(num_vertices, **kwargs) return [PassThroughLayer(x, in_layers=gcnnpool_layer) for x in range(3)] class GraphCNNLayer(Layer): def __init__(self, num_filters, **kwargs): self.num_filters = num_filters super(GraphCNNLayer, self).__init__(**kwargs) def create_tensor(self, in_layers=None, set_tensors=True, **kwargs): inputs = self._get_input_tensors(in_layers) if len(inputs) == 3: V, A, mask = inputs else: V, A = inputs mask = None no_A = A.get_shape()[2].value no_features = V.get_shape()[2].value W = tf.get_variable( '%s_weights' % self.name, [no_features * no_A, self.num_filters], initializer=tf.truncated_normal_initializer(stddev=math.sqrt( 1.0 / (no_features * (no_A + 1) * 1.0))), dtype=tf.float32) W_I = tf.get_variable( '%s_weights_I' % self.name, [no_features, self.num_filters], initializer=tf.truncated_normal_initializer(stddev=math.sqrt( 1.0 / (no_features * (no_A + 1) * 1.0))), dtype=tf.float32) b = tf.get_variable( '%s_bias' % self.name, [self.num_filters], initializer=tf.constant_initializer(0.1), dtype=tf.float32) n = self.graphConvolution(V, A) A_shape = tf.shape(A) n = tf.reshape(n, [-1, A_shape[1], no_A * no_features]) result = self.batch_mat_mult(n, W) + self.batch_mat_mult(V, W_I) + b if set_tensors: self.out_tensor = result return result def graphConvolution(self, V, A): no_A = A.get_shape()[2].value no_features = V.get_shape()[2].value A_shape = tf.shape(A) A_reshape = tf.reshape(A, tf.stack([-1, A_shape[1] * no_A, A_shape[1]])) n = tf.matmul(A_reshape, V) return tf.reshape(n, [-1, A_shape[1], no_A, no_features]) def batch_mat_mult(self, A, B): A_shape = tf.shape(A) A_reshape = tf.reshape(A, [-1, A_shape[-1]]) # So the Tensor has known dimensions if B.get_shape()[1] == None: axis_2 = -1 else: axis_2 = B.get_shape()[1] result = tf.matmul(A_reshape, B) result = tf.reshape(result, tf.stack([A_shape[0], A_shape[1], axis_2])) return result
deepchem/models/tensorgraph/models/graph_models.py +153 −11 Original line number Diff line number Diff line import math import numpy as np import six import tensorflow as tf from deepchem.data import NumpyDataset from deepchem.feat.graph_features import ConvMolFeaturizer from deepchem.feat.mol_graphs import ConvMol from deepchem.metrics import to_one_hot, from_one_hot from deepchem.metrics import to_one_hot from deepchem.models.tensorgraph.graph_layers import WeaveLayer, WeaveGather, \ Combine_AP, Separate_AP, DTNNEmbedding, DTNNStep, DTNNGather, DAGLayer, \ DAGGather, DTNNExtract, MessagePassing, SetGather from deepchem.models.tensorgraph.layers import Dense, Concat, SoftMax, \ SoftMaxCrossEntropy, GraphConv, BatchNorm, \ GraphPool, GraphGather, WeightedError, Dropout, BatchNormalization, Stack GraphPool, GraphGather, WeightedError, Dropout, BatchNormalization, Stack, Layer, Flatten, GraphCNNLayer, GraphCNNPool from deepchem.models.tensorgraph.layers import L2Loss, Label, Weights, Feature from deepchem.models.tensorgraph.tensor_graph import TensorGraph from deepchem.trans import undo_transforms from deepchem.utils.evaluate import GeneratorEvaluator from deepchem.data import NumpyDataset from deepchem.data.data_loader import featurize_smiles_np from deepchem.feat.graph_features import ConvMolFeaturizer class WeaveTensorGraph(TensorGraph): Loading Loading @@ -487,6 +486,149 @@ class DAGTensorGraph(TensorGraph): yield feed_dict class PetroskiSuchTensorGraph(TensorGraph): def __init__(self, n_tasks, max_atoms=200, dropout=0.2, mode="classification", **kwargs): """ Parameters ---------- n_tasks: int Number of tasks mode: str Either "classification" or "regression" """ self.n_tasks = n_tasks self.mode = mode self.max_atoms = max_atoms self.error_bars = True if 'error_bars' in kwargs and kwargs['error_bars'] else False self.dropout = dropout kwargs['use_queue'] = False super(PetroskiSuchTensorGraph, self).__init__(**kwargs) self.build_graph() def build_graph(self): self.vertex_features = Feature(shape=(None, self.max_atoms, 75)) self.adj_matrix = Feature(shape=(None, self.max_atoms, 1, self.max_atoms)) self.mask = Feature(shape=(None, self.max_atoms, 1)) gcnn1 = BatchNorm( GraphCNNLayer( num_filters=64, in_layers=[self.vertex_features, self.adj_matrix, self.mask])) gcnn1 = Dropout(self.dropout, in_layers=gcnn1) gcnn2 = BatchNorm( GraphCNNLayer( num_filters=64, in_layers=[gcnn1, self.adj_matrix, self.mask])) gcnn2 = Dropout(self.dropout, in_layers=gcnn2) gc_pool, adj_matrix, factors = GraphCNNPool( num_vertices=32, in_layers=[gcnn2, self.adj_matrix, self.mask]) gc_pool = BatchNorm(gc_pool) gc_pool = Dropout(self.dropout, in_layers=gc_pool) gcnn3 = BatchNorm( GraphCNNLayer(num_filters=32, in_layers=[gc_pool, adj_matrix])) gcnn3 = Dropout(self.dropout, in_layers=gcnn3) gc_pool2, adj_matrix2, factors = GraphCNNPool( num_vertices=8, in_layers=[gcnn3, adj_matrix]) gc_pool2 = BatchNorm(gc_pool2) gc_pool2 = Dropout(self.dropout, in_layers=gc_pool2) flattened = Flatten(in_layers=gc_pool2) readout = Dense( out_channels=256, activation_fn=tf.nn.relu, in_layers=flattened) costs = [] self.my_labels = [] for task in range(self.n_tasks): if self.mode == 'classification': classification = Dense( out_channels=2, activation_fn=None, in_layers=[readout]) softmax = SoftMax(in_layers=[classification]) self.add_output(softmax) label = Label(shape=(None, 2)) self.my_labels.append(label) cost = SoftMaxCrossEntropy(in_layers=[label, classification]) costs.append(cost) if self.mode == 'regression': regression = Dense( out_channels=1, activation_fn=None, in_layers=[readout]) self.add_output(regression) label = Label(shape=(None, 1)) 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) def default_generator(self, dataset, epochs=1, predict=False, deterministic=True, pad_batches=True): for epoch in range(epochs): if not predict: print('Starting epoch %i' % epoch) for ind, (X_b, y_b, w_b, ids_b) in enumerate( dataset.iterbatches( self.batch_size, pad_batches=True, deterministic=deterministic)): d = {} for index, label in enumerate(self.my_labels): if self.mode == 'classification': d[label] = to_one_hot(y_b[:, index]) if self.mode == 'regression': d[label] = np.expand_dims(y_b[:, index], -1) d[self.my_task_weights] = w_b d[self.adj_matrix] = np.expand_dims(np.array([x[0] for x in X_b]), -2) d[self.vertex_features] = np.array([x[1] for x in X_b]) mask = np.zeros(shape=(self.batch_size, self.max_atoms, 1)) for i in range(self.batch_size): mask_size = X_b[i][2] mask[i][:mask_size][0] = 1 d[self.mask] = mask yield d def predict_proba_on_generator(self, generator, transformers=[]): if not self.built: self.build() with self._get_tf("Graph").as_default(): out_tensors = [x.out_tensor for x in self.outputs] results = [] for feed_dict in generator: feed_dict = { self.layers[k.name].out_tensor: v for k, v in six.iteritems(feed_dict) } feed_dict[self._training_placeholder] = 1.0 ## result = np.array(self.session.run(out_tensors, feed_dict=feed_dict)) if len(result.shape) == 3: result = np.transpose(result, axes=[1, 0, 2]) if len(transformers) > 0: result = undo_transforms(result, transformers) results.append(result) return np.concatenate(results, axis=0) def evaluate(self, dataset, metrics, transformers=[], per_task_metrics=False): if not self.built: self.build() return self.evaluate_generator( self.default_generator(dataset, predict=True), metrics, labels=self.my_labels, weights=[self.my_task_weights], per_task_metrics=per_task_metrics) class GraphConvTensorGraph(TensorGraph): def __init__(self, n_tasks, mode="classification", **kwargs): Loading
examples/tox21/tox21_datasets.py +38 −13 Original line number Diff line number Diff line Loading @@ -6,40 +6,65 @@ from __future__ import division from __future__ import unicode_literals import os import deepchem import numpy as np import shutil import deepchem as dc from deepchem.data import DiskDataset def load_tox21(featurizer='ECFP', split='index'): """Load Tox21 datasets. Does not do train/test split""" # Featurize Tox21 dataset print("About to featurize Tox21 dataset.") current_dir = os.path.dirname(os.path.realpath(__file__)) dataset_file = os.path.join( current_dir, "../../datasets/tox21.csv.gz") tox21_tasks = ['NR-AR', 'NR-AR-LBD', 'NR-AhR', 'NR-Aromatase', 'NR-ER', 'NR-ER-LBD', 'NR-PPAR-gamma', 'SR-ARE', 'SR-ATAD5', 'SR-HSE', 'SR-MMP', 'SR-p53'] dataset_file = os.path.join(current_dir, "../../datasets/tox21.csv.gz") data_dir = deepchem.utils.get_data_dir() tox21_tasks = [ 'NR-AR', 'NR-AR-LBD', 'NR-AhR', 'NR-Aromatase', 'NR-ER', 'NR-ER-LBD', 'NR-PPAR-gamma', 'SR-ARE', 'SR-ATAD5', 'SR-HSE', 'SR-MMP', 'SR-p53' ] dataset_dir = os.path.join(data_dir, "tox21", featurizer, split) train, valid, test = os.path.join(dataset_dir, 'train'), os.path.join( dataset_dir, 'valid'), os.path.join(dataset_dir, 'test') if os.path.isdir(dataset_dir): train, valid, test = DiskDataset(data_dir=train), DiskDataset( data_dir=valid), DiskDataset(data_dir=test) transformers = [ dc.trans.BalancingTransformer(transform_w=True, dataset=train) ] return tox21_tasks, (train, valid, test), transformers if featurizer == 'ECFP': featurizer_func = dc.feat.CircularFingerprint(size=1024) elif featurizer == 'GraphConv': featurizer_func = dc.feat.ConvMolFeaturizer() elif featurizer == 'AdjMatrix': featurizer_func = dc.feat.AdjacencyFingerprint(num_atoms_feature=True) loader = dc.data.CSVLoader( tasks=tox21_tasks, smiles_field="smiles", featurizer=featurizer_func) dataset = loader.featurize(dataset_file, shard_size=8192) # Initialize transformers transformers = [ dc.trans.BalancingTransformer(transform_w=True, dataset=dataset)] dc.trans.BalancingTransformer(transform_w=True, dataset=dataset) ] print("About to transform data") for transformer in transformers: dataset = transformer.transform(dataset) splitters = {'index': dc.splits.IndexSplitter(), splitters = { 'index': dc.splits.IndexSplitter(), 'random': dc.splits.RandomSplitter(), 'scaffold': dc.splits.ScaffoldSplitter(), 'butina': dc.splits.ButinaSplitter()} 'butina': dc.splits.ButinaSplitter() } splitter = splitters[split] train, valid, test = splitter.train_valid_test_split(dataset) train, valid, test = splitter.train_valid_test_split( dataset, train_dir=train, valid_dir=valid, test_dir=test) return tox21_tasks, (train, valid, test), transformers
examples/tox21/tox21_graphcnn.py 0 → 100644 +47 −0 Original line number Diff line number Diff line """ Script that trains graph-conv models on Tox21 dataset. """ from __future__ import division from __future__ import print_function from __future__ import unicode_literals import numpy as np import json np.random.seed(123) import tensorflow as tf tf.set_random_seed(123) import deepchem as dc from tox21_datasets import load_tox21 from deepchem.models.tensorgraph.models.graph_models import PetroskiSuchTensorGraph model_dir = "/tmp/graph_conv" # Load Tox21 dataset tox21_tasks, tox21_datasets, transformers = load_tox21(featurizer='AdjMatrix') train_dataset, valid_dataset, test_dataset = tox21_datasets print(train_dataset.data_dir) print(valid_dataset.data_dir) # Fit models metric = dc.metrics.Metric( dc.metrics.roc_auc_score, np.mean, mode="classification") # Batch size of models batch_size = 128 model = PetroskiSuchTensorGraph( len(tox21_tasks), batch_size=batch_size, mode='classification') model.fit(train_dataset, nb_epoch=10) print("Evaluating model") train_scores = model.evaluate(train_dataset, [metric], transformers) valid_scores = model.evaluate(valid_dataset, [metric], transformers) print("Train scores") print(train_scores) print("Validation scores") print(valid_scores)
