def load_dataset(args):
splitter = 'scaffold'
if args['featurizer'] == 'ECFP':
featurizer = 'ECFP'
elif args['featurizer'] == 'GC':
from deepchem.feat import MolGraphConvFeaturizer
featurizer = MolGraphConvFeaturizer()
if args['dataset'] == 'BACE_classification':
from deepchem.molnet import load_bace_classification
tasks, all_dataset, transformers = load_bace_classification(
featurizer=featurizer, splitter=splitter, reload=False)
elif args['dataset'] == 'BBBP':
from deepchem.molnet import load_bbbp
tasks, all_dataset, transformers = load_bbbp(
featurizer=featurizer, splitter=splitter, reload=False)
elif args['dataset'] == 'BACE_regression':
from deepchem.molnet import load_bace_regression
tasks, all_dataset, transformers = load_bace_regression(
featurizer=featurizer, splitter=splitter, reload=False)
elif args['dataset'] == 'ClinTox':
from deepchem.molnet import load_clintox
tasks, all_dataset, transformers = load_clintox(
featurizer=featurizer, splitter=splitter, reload=False)
elif args['dataset'] == 'Delaney':
from deepchem.molnet import load_delaney
tasks, all_dataset, transformers = load_delaney(
featurizer=featurizer, splitter=splitter, reload=False)
elif args['dataset'] == 'HOPV':
from deepchem.molnet import load_hopv
tasks, all_dataset, transformers = load_hopv(
featurizer=featurizer, splitter=splitter, reload=False)
elif args['dataset'] == 'SIDER':
from deepchem.molnet import load_sider
tasks, all_dataset, transformers = load_sider(
featurizer=featurizer, splitter=splitter, reload=False)
elif args['dataset'] == 'Lipo':
from deepchem.molnet import load_lipo
tasks, all_dataset, transformers = load_lipo(
featurizer=featurizer, splitter=splitter, reload=False)
else:
raise ValueError('Unexpected dataset: {}'.format(args['dataset']))
return args, tasks, all_dataset, transformers
Script that trains multitask models on HOPV dataset.
"""
from __future__ import print_function
from __future__ import division
from __future__ import unicode_literals
import numpy as np
import deepchem as dc
from deepchem.molnet import load_hopv
# Only for debug!
np.random.seed(123)
# Load HOPV dataset
n_features = 1024
hopv_tasks, hopv_datasets, transformers = load_hopv()
train_dataset, valid_dataset, test_dataset = hopv_datasets
# Fit models
metric = [
dc.metrics.Metric(dc.metrics.pearson_r2_score, np.mean, mode="regression"),
dc.metrics.Metric(dc.metrics.mean_absolute_error,
np.mean,
mode="regression")
]
n_layers = 1
n_bypass_layers = 1
nb_epoch = 25
model = dc.models.RobustMultitaskRegressor(
len(hopv_tasks),
from __future__ import print_function
from __future__ import division
from __future__ import unicode_literals
import numpy as np
from models import GraphConvModel
np.random.seed(123)
import tensorflow as tf
tf.set_random_seed(123)
import deepchem as dc
from deepchem.molnet import load_hopv
# Load HOPV dataset
hopv_tasks, hopv_datasets, transformers = load_hopv(featurizer='GraphConv')
train_dataset, valid_dataset, test_dataset = hopv_datasets
# Fit models
metric = [
dc.metrics.Metric(dc.metrics.pearson_r2_score, np.mean, mode="regression"),
dc.metrics.Metric(dc.metrics.mean_absolute_error,
np.mean,
mode="regression")
]
# Number of features on conv-mols
n_feat = 75
# Batch size of models
batch_size = 50
model = GraphConvModel(len(hopv_tasks),
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 deepchem.molnet import load_hopv
# Only for debug!
np.random.seed(123)
# Load HOPV dataset
n_features = 1024
hopv_tasks, hopv_datasets, transformers = load_hopv()
train_dataset, valid_dataset, test_dataset = hopv_datasets
# Fit models
metric = [
dc.metrics.Metric(dc.metrics.pearson_r2_score, np.mean, mode="regression"),
dc.metrics.Metric(
dc.metrics.mean_absolute_error, np.mean, mode="regression")
]
model = dc.models.ProgressiveMultitaskRegressor(
len(hopv_tasks),
n_features,
layer_sizes=[1000],
dropouts=[.25],
learning_rate=0.001,
from __future__ import print_function
from __future__ import division
from __future__ import unicode_literals
import numpy as np
from deepchem.models import GraphConvModel
np.random.seed(123)
import tensorflow as tf
tf.set_random_seed(123)
import deepchem as dc
from deepchem.molnet import load_hopv
# Load HOPV dataset
hopv_tasks, hopv_datasets, transformers = load_hopv(featurizer='GraphConv')
train_dataset, valid_dataset, test_dataset = hopv_datasets
# Fit models
metric = [
dc.metrics.Metric(dc.metrics.pearson_r2_score, np.mean, mode="regression"),
dc.metrics.Metric(
dc.metrics.mean_absolute_error, np.mean, mode="regression")
]
# Number of features on conv-mols
n_feat = 75
# Batch size of models
batch_size = 50
model = GraphConvModel(
len(hopv_tasks), batch_size=batch_size, mode='regression')
def load_dataset(args):
splitter = 'scaffold'
if args['featurizer'] == 'ECFP':
featurizer = 'ECFP'
elif args['featurizer'] == 'GC':
from deepchem.feat import MolGraphConvFeaturizer
featurizer = MolGraphConvFeaturizer()
elif args['featurizer'] == 'AC':
from deepchem.feat import AtomicConvFeaturizer
featurizer = AtomicConvFeaturizer(frag1_num_atoms=100,
frag2_num_atoms=1000,
complex_num_atoms=1100,
max_num_neighbors=12,
neighbor_cutoff=4)
if args['dataset'] == 'BACE_classification':
from deepchem.molnet import load_bace_classification
tasks, all_dataset, transformers = load_bace_classification(
featurizer=featurizer, splitter=splitter, reload=False)
elif args['dataset'] == 'BBBP':
from deepchem.molnet import load_bbbp
tasks, all_dataset, transformers = load_bbbp(featurizer=featurizer,
splitter=splitter,
reload=False)
elif args['dataset'] == 'BACE_regression':
from deepchem.molnet import load_bace_regression
tasks, all_dataset, transformers = load_bace_regression(
featurizer=featurizer, splitter=splitter, reload=False)
elif args['dataset'] == 'ClinTox':
from deepchem.molnet import load_clintox
tasks, all_dataset, transformers = load_clintox(featurizer=featurizer,
splitter=splitter,
reload=False)
elif args['dataset'] == 'Delaney':
from deepchem.molnet import load_delaney
tasks, all_dataset, transformers = load_delaney(featurizer=featurizer,
splitter=splitter,
reload=False)
elif args['dataset'] == 'HOPV':
from deepchem.molnet import load_hopv
tasks, all_dataset, transformers = load_hopv(featurizer=featurizer,
splitter=splitter,
reload=False)
elif args['dataset'] == 'SIDER':
from deepchem.molnet import load_sider
tasks, all_dataset, transformers = load_sider(featurizer=featurizer,
splitter=splitter,
reload=False)
elif args['dataset'] == 'Lipo':
from deepchem.molnet import load_lipo
tasks, all_dataset, transformers = load_lipo(featurizer=featurizer,
splitter=splitter,
reload=False)
elif args['dataset'] == 'PDBbind':
from deepchem.molnet import load_pdbbind
tasks, all_dataset, transformers = load_pdbbind(
featurizer=featurizer,
save_dir='.',
data_dir='.',
splitter='random',
pocket=True,
set_name='core', # refined
reload=False)
else:
raise ValueError('Unexpected dataset: {}'.format(args['dataset']))
return args, tasks, all_dataset, transformers