gdb7

"""

Script that trains graph-conv models on Tox21 dataset.

"""

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals

import numpy as np

import tensorflow as tf

import deepchem as dc

from keras import backend as K

from gdb7_datasets import load_gdb7

# Only for debug!

np.random.seed(123)

g = tf.Graph()

sess = tf.Session(graph=g)

K.set_session(sess)

with g.as_default():

  # Load Tox21 dataset

  tf.set_random_seed(123)

  gdb7_tasks, gdb7_datasets, transformers = load_gdb7(featurizer='GraphConv', split='indice')

  train_dataset, valid_dataset, test_dataset = gdb7_datasets

  # Fit models

  metric = [dc.metrics.Metric(dc.metrics.mean_absolute_error, mode="regression"), 

            dc.metrics.Metric(dc.metrics.pearson_r2_score, mode="regression")]

  # Do setup required for tf/keras models

  # Number of features on conv-mols

  n_feat = 75

  # Batch size of models

  batch_size = 128

  graph_model = dc.nn.SequentialGraph(n_feat)

  graph_model.add(dc.nn.GraphConv(128, activation='relu'))

  graph_model.add(dc.nn.BatchNormalization(epsilon=1e-5, mode=1))

  graph_model.add(dc.nn.GraphPool())

  graph_model.add(dc.nn.GraphConv(128, activation='relu'))

  graph_model.add(dc.nn.BatchNormalization(epsilon=1e-5, mode=1))

  graph_model.add(dc.nn.GraphPool())

  # Gather Projection

  graph_model.add(dc.nn.Dense(256, activation='relu'))

  graph_model.add(dc.nn.BatchNormalization(epsilon=1e-5, mode=1))

  graph_model.add(dc.nn.GraphGather(batch_size, activation="tanh"))

  # Dense post-processing layer

  with tf.Session() as sess:

    model = dc.models.MultitaskGraphRegressor(

      sess, graph_model, len(gdb7_tasks), batch_size=batch_size,

      learning_rate=1e-3, learning_rate_decay_time=1000,

      optimizer_type="adam", beta1=.9, beta2=.999)

    # Fit trained model

    model.fit(train_dataset, nb_epoch=20)

    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)

"""

Script that trains multitask models on gdb7 dataset.

"""

from __future__ import print_function

from __future__ import division

from __future__ import unicode_literals

import os

import shutil

import numpy as np

import deepchem as dc

from gdb7_datasets import load_gdb7

# Only for debug!

np.random.seed(123)

# Load gdb7 dataset

n_features = 1024

gdb7_tasks, gdb7_datasets, transformers = load_gdb7(featurizer='ECFP', split='indice')

train_dataset, valid_dataset, test_dataset = gdb7_datasets

# Fit models

metric = [dc.metrics.Metric(dc.metrics.mean_absolute_error, mode="regression"), 

          dc.metrics.Metric(dc.metrics.pearson_r2_score, mode="regression")]

model = dc.models.TensorflowMultiTaskRegressor(

    len(gdb7_tasks), n_features, layer_sizes=[1000], dropouts=[.25],

    learning_rate=0.001, batch_size=50, verbosity="high")

# Fit trained model

model.fit(train_dataset)

model.save()

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)

import deepchem as dc

import numpy as np

from gdb7_datasets import load_gdb7_from_mat

from gdb7_datasets import load_gdb7

np.random.seed(123)

split = 0

num_atoms = 23

gdb7_tasks, datasets, transformers = load_gdb7_from_mat(split)

train_dataset, test_dataset = datasets

#gdb7_tasks, datasets, transformers = load_gdb7_from_mat(split)

#train_dataset, test_dataset = datasets

gdb7_tasks, datasets, transformers = load_gdb7(split='indice')

train_dataset, test_dataset, _ = datasets

fit_transformers = [dc.trans.CoulombFitTransformer(train_dataset)]

regression_metric = [dc.metrics.Metric(dc.metrics.mean_absolute_error, mode="regression"),