Merge pull request #1215 from miaecle/ani1

import deepchem as dc

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

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

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

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

from deepchem.models.tensorgraph.tensor_graph import TensorGraph

from deepchem.models.tensorgraph.graph_layers import DTNNEmbedding

from deepchem.models.tensorgraph.symmetry_functions import DistanceMatrix, \

  def __init__(self,

               n_tasks,

               max_atoms,

               exp_loss=False,

               activation_fn='ani',

               layer_structures=[128, 64],

               atom_number_cases=[1, 6, 7, 8, 16],

               **kwargs):

    """

    self.n_tasks = n_tasks

    self.max_atoms = max_atoms

    self.exp_loss = exp_loss

    self.activation_fn = activation_fn

    self.layer_structures = layer_structures

    self.atom_number_cases = atom_number_cases

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

        jac=self.grad_one,

        method="BFGS",

        tol=1e-6,

        options={'disp': True})

        options={

            'disp': True

        })

    return res.x.reshape((num_atoms, 3))

          self.max_atoms,

          n_hidden,

          self.atom_number_cases,

          activation='tanh',

          activation=self.activation_fn,

          in_layers=[previous_layer, self.atom_numbers])

      Hiddens.append(Hidden)

      previous_layer = Hiddens[-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])

    if self.exp_loss:

      loss = Exp(in_layers=[loss])

    self.set_loss(loss)

  def default_generator(self,

               out_channels,

               atom_number_cases=[1, 6, 7, 8],

               init='glorot_uniform',

               activation='relu',

               activation='ani',

               **kwargs):

    self.init = init  # Set weight initialization

    self.activation = activation  # Get activations

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

  @staticmethod

  def ani_activate(X):

    return tf.exp(-1 * tf.pow(X, 2))

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

    """ Generate Radial Symmetry Function """

    init_fn = initializations.get(self.init)  # Set weight initialization

    if self.activation == 'ani':

      activation_fn = self.ani_activate

    else:

      activation_fn = activations.get(self.activation)

    if in_layers is None:

      in_layers = self.in_layers

import tensorflow as tf

tf.set_random_seed(123)

import deepchem as dc

import os

import tempfile

HARTREE_TO_KCAL_PER_MOL = 627.509

# Load Tox21 dataset

tasks, datasets, transformers = dc.molnet.load_qm7_from_mat(

    featurizer='BPSymmetryFunction')

train_dataset, valid_dataset, test_dataset = datasets

    featurizer='BPSymmetryFunction', split='index', reload=False)

all_dataset = dc.data.DiskDataset.merge(datasets)

invalid_inds = []

X = all_dataset.X

for i in range(X.shape[0]):

  # Exclude all molecules having S

  if 16 in X[i, :, 0]:

    invalid_inds.append(i)

valid_inds = np.delete(np.arange(all_dataset.y.shape[0]), invalid_inds)

dataset = all_dataset.select(valid_inds)

splitter = dc.splits.RandomSplitter()

train, valid, test = splitter.train_valid_test_split(dataset)

y = dc.trans.undo_transforms(train.y, transformers) / HARTREE_TO_KCAL_PER_MOL

train = dc.data.DiskDataset.from_numpy(

    train.X, y, w=train.w, ids=train.ids, tasks=train.tasks)

y = dc.trans.undo_transforms(valid.y, transformers) / HARTREE_TO_KCAL_PER_MOL

valid = dc.data.DiskDataset.from_numpy(

    valid.X, y, w=valid.w, ids=valid.ids, tasks=valid.tasks)

y = dc.trans.undo_transforms(test.y, transformers) / HARTREE_TO_KCAL_PER_MOL

test = dc.data.DiskDataset.from_numpy(

    test.X, y, w=test.w, ids=test.ids, tasks=test.tasks)

# Batch size of models

max_atoms = 23

batch_size = 128

layer_structures = [128, 128, 64]

atom_number_cases = [1, 6, 7, 8, 16]

ANItransformer = dc.trans.ANITransformer(

    max_atoms=max_atoms, atom_cases=atom_number_cases)

train_dataset = ANItransformer.transform(train_dataset)

valid_dataset = ANItransformer.transform(valid_dataset)

test_dataset = ANItransformer.transform(test_dataset)

n_feat = ANItransformer.get_num_feats() - 1

layer_structures = [64, 64, 32]

atom_number_cases = [1, 6, 7, 8]

# Fit models

metric = [

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

]

model_dir = tempfile.mkdtemp()

lr_scedule = [1e-3, 1e-4, 1e-5, 3e-6, 1e-6, 3e-7, 1e-7, 3e-8, 1e-8, 3e-9, 1e-9]

valid_best = 100.

for lr in lr_scedule:

  model = dc.models.ANIRegression(

      len(tasks),

      max_atoms,

    n_feat,

      exp_loss=False,

      layer_structures=layer_structures,

      atom_number_cases=atom_number_cases,

      batch_size=batch_size,

    learning_rate=0.001,

      learning_rate=lr,

      use_queue=False,

    mode="regression")

# Fit trained model

model.fit(train_dataset, nb_epoch=300, checkpoint_interval=100)

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)

      mode="regression",

      model_dir=model_dir)

  if lr < 1e-3:

    model.restore()

  model.fit(train, nb_epoch=10)

  local_ct = 0

  while local_ct < 100:

    local_ct += 1

    model.fit(train, nb_epoch=1)

    train_scores = model.evaluate(train, metric)

    valid_scores = model.evaluate(valid, metric)

    print("Train MAE(kcal/mol): " +

          str(train_scores['mean_absolute_error'] * HARTREE_TO_KCAL_PER_MOL))

    print("Valid MAE(kcal/mol): " +

          str(valid_scores['mean_absolute_error'] * HARTREE_TO_KCAL_PER_MOL))

    if valid_scores['mean_absolute_error'] < valid_best:

      local_ct = 0

      valid_best = valid_scores['mean_absolute_error']

      test_scores = model.evaluate(test, metric)

      print("Test MAE(kcal/mol): " +

            str(test_scores['mean_absolute_error'] * HARTREE_TO_KCAL_PER_MOL))

import tensorflow as tf

tf.set_random_seed(123)

import deepchem as dc

from deepchem.models.tensorgraph.optimizers import ExponentialDecay

# Load Tox21 dataset

# Load QM7 dataset

tasks, datasets, transformers = dc.molnet.load_qm7_from_mat()

train_dataset, valid_dataset, test_dataset = datasets

distance_max = 9.2

n_hidden = 15

rate = ExponentialDecay(0.0001, 0.97, 5000)

model = dc.models.DTNNModel(

    len(tasks),

    n_embedding=n_embedding,

    distance_max=distance_max,

    output_activation=False,

    batch_size=batch_size,

    learning_rate=0.0001,

    learning_rate=rate,

    use_queue=False,

    mode="regression")

#model.restore()

# Fit trained model

model.fit(train_dataset, nb_epoch=1000)

model.fit(train_dataset, nb_epoch=3000)

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 [kcal/mol]")

print(train_scores)

print("Validation scores")

valid_scores = model.evaluate(valid_dataset, metric, transformers)

print("Valid scores [kcal/mol]")

print(valid_scores)

test_scores = model.evaluate(test_dataset, metric, transformers)

print("Test scores [kcal/mol]")

print(test_scores)

import deepchem as dc

import numpy as np

from deepchem.molnet import load_qm7_from_mat

from deepchem.models.tensorgraph.optimizers import ExponentialDecay

np.random.seed(123)

qm7_tasks, datasets, transformers = load_qm7_from_mat(split='stratified')

train_dataset, valid_dataset, test_dataset = datasets

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

regression_metric = [

metric = [

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

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

]

rate = ExponentialDecay(0.001, 0.95, 1000)

model = dc.models.MultiTaskFitTransformRegressor(

    n_tasks=1,

    n_features=[23, 23],

    learning_rate=0.001,

    learning_rate=rate,

    momentum=.8,

    batch_size=25,

    weight_init_stddevs=[1 / np.sqrt(400), 1 / np.sqrt(100), 1 / np.sqrt(100)],

    fit_transformers=fit_transformers,

    n_evals=10,

    seed=123)

#model.restore()

# Fit trained model

model.fit(train_dataset, nb_epoch=50)

model.save()

model.fit(train_dataset, nb_epoch=3000)

train_scores = model.evaluate(train_dataset, regression_metric, transformers)

train_scores = model.evaluate(train_dataset, metric, transformers)

print("Train scores [kcal/mol]")

print(train_scores)

valid_scores = model.evaluate(valid_dataset, regression_metric, transformers)

valid_scores = model.evaluate(valid_dataset, metric, transformers)

print("Valid scores [kcal/mol]")

print(valid_scores)

test_scores = model.evaluate(test_dataset, regression_metric, transformers)

test_scores = model.evaluate(test_dataset, metric, transformers)

print("Test scores [kcal/mol]")

print(test_scores)