Merge branch 'master' of https://github.com/deepchem/deepchem into website (ba9d30bc) · Commits · 钟慕尧 / deepchem

deepchem/models/autoencoder_models/autoencoder.py

+5 −4

Original line number	Diff line number	Diff line
		@@ -6,6 +6,7 @@ import warnings
		from deepchem.models import Model
		from deepchem.models.autoencoder_models.model import MoleculeVAE
		from deepchem.feat.one_hot import zinc_charset
		from deepchem.utils import download_url
		import os
		from subprocess import call

		@@ -64,8 +65,8 @@ class TensorflowMoleculeEncoder(Model):
		weights_file = os.path.join(current_dir, weights_filename)

		if not os.path.exists(weights_file):
		wget_command = "wget -nv -c http://karlleswing.com/misc/keras-molecule/model.h5"
		call(wget_command.split())
		download_url("http://karlleswing.com/misc/keras-molecule/model.h5",
		current_dir)
		mv_cmd = "mv model.h5 %s" % weights_file
		call(mv_cmd.split())
		return TensorflowMoleculeEncoder(
		@@ -136,8 +137,8 @@ class TensorflowMoleculeDecoder(Model):
		weights_file = os.path.join(current_dir, weights_filename)

		if not os.path.exists(weights_file):
		wget_command = "wget -nv -c http://karlleswing.com/misc/keras-molecule/model.h5"
		call(wget_command.split())
		download_url("http://karlleswing.com/misc/keras-molecule/model.h5",
		current_dir)
		mv_cmd = "mv model.h5 %s" % weights_file
		call(mv_cmd.split())
		return TensorflowMoleculeDecoder(

deepchem/models/tensorgraph/symmetry_functions.py

+17 −1

Original line number	Diff line number	Diff line
		@@ -422,11 +422,27 @@ class AtomicDifferentiatedDense(Layer):
		in_channels = inputs.get_shape().as_list()[-1]
		self.W = self.init(
		[len(self.atom_number_cases), in_channels, self.out_channels])

		self.b = model_ops.zeros((len(self.atom_number_cases), self.out_channels))
		outputs = []
		for i, atom_case in enumerate(self.atom_number_cases):

		# optimization to allow for tensorcontraction/broadcasted mmul
		# using a reshape trick. Note that the np and tf matmul behavior
		# differs when dealing with broadcasts

		a = inputs # (i,j,k)
		b = self.W[i, :, :] # (k, l)

		ai = tf.shape(a)[0]
		aj = tf.shape(a)[1]
		ak = tf.shape(a)[2]
		bl = tf.shape(b)[1]

		output = self.activation(
		tf.tensordot(inputs, self.W[i, :, :], [[2], [0]]) + self.b[i, :])
		tf.reshape(tf.matmul(tf.reshape(a, [ai * aj, ak]), b), [ai, aj, bl]) +
		self.b[i, :])

		mask = 1 - tf.to_float(tf.cast(atom_numbers - atom_case, tf.bool))
		output = tf.reshape(output * tf.expand_dims(mask, 2), (-1, self.max_atoms,
		self.out_channels))

deepchem/molnet/load_function/bace_datasets.py

+8 −16

Original line number	Diff line number	Diff line
		@@ -14,18 +14,14 @@ def load_bace_regression(featurizer='ECFP', split='random', reload=True):
		"""Load bace datasets."""
		# Featurize bace dataset
		print("About to featurize bace dataset.")
		if "DEEPCHEM_DATA_DIR" in os.environ:
		data_dir = os.environ["DEEPCHEM_DATA_DIR"]
		else:
		data_dir = "/tmp"
		data_dir = deepchem.utils.get_data_dir()
		if reload:
		save_dir = os.path.join(data_dir, "bace_r/" + featurizer + "/" + split)

		dataset_file = os.path.join(data_dir, "bace.csv")

		if not os.path.exists(dataset_file):
		os.system(
		'wget -P ' + data_dir +
		deepchem.utils.download_url(
		'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/bace.csv'
		)

		@@ -80,18 +76,14 @@ def load_bace_classification(featurizer='ECFP', split='random', reload=True):
		"""Load bace datasets."""
		# Featurize bace dataset
		print("About to featurize bace dataset.")
		if "DEEPCHEM_DATA_DIR" in os.environ:
		data_dir = os.environ["DEEPCHEM_DATA_DIR"]
		else:
		data_dir = "/tmp"
		data_dir = deepchem.utils.get_data_dir()
		if reload:
		save_dir = os.path.join(data_dir, "bace_c/" + featurizer + "/" + split)

		dataset_file = os.path.join(data_dir, "bace.csv")

		if not os.path.exists(dataset_file):
		os.system(
		'wget -P ' + data_dir +
		deepchem.utils.download_url(
		'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/bace.csv'
		)

deepchem/molnet/load_function/bbbp_datasets.py

+3 −7

Original line number	Diff line number	Diff line
		@@ -13,17 +13,13 @@ def load_bbbp(featurizer='ECFP', split='random', reload=True):
		"""Load blood-brain barrier penetration datasets """
		# Featurize bbb dataset
		print("About to featurize bbbp dataset.")
		if "DEEPCHEM_DATA_DIR" in os.environ:
		data_dir = os.environ["DEEPCHEM_DATA_DIR"]
		else:
		data_dir = "/tmp"
		data_dir = deepchem.utils.get_data_dir()
		if reload:
		save_dir = os.path.join(data_dir, "bbbp/" + featurizer + "/" + split)

		dataset_file = os.path.join(data_dir, "BBBP.csv")
		if not os.path.exists(dataset_file):
		os.system(
		'wget -P ' + data_dir +
		deepchem.utils.download_url(
		'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/BBBP.csv'
		)

deepchem/molnet/load_function/chembl_datasets.py

+17 −28

Original line number	Diff line number	Diff line
		@@ -16,45 +16,34 @@ def load_chembl(shard_size=2000,
		split="random",
		reload=True):

		if "DEEPCHEM_DATA_DIR" in os.environ:
		data_dir = os.environ["DEEPCHEM_DATA_DIR"]
		else:
		data_dir = "/tmp"
		data_dir = deepchem.utils.get_data_dir()
		if reload:
		save_dir = os.path.join(data_dir, "chembl/" + featurizer + "/" + split)

		dataset_path = os.path.join(data_dir, "chembl_%s.csv.gz" % set)
		if not os.path.exists(dataset_path):
		os.system(
		'wget -P ' + data_dir +
		deepchem.utils.download_url(
		'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/chembl_5thresh.csv.gz'
		)
		os.system(
		'wget -P ' + data_dir +
		deepchem.utils.download_url(
		'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/chembl_sparse.csv.gz'
		)
		os.system(
		'wget -P ' + os.path.join(data_dir, 'chembl_year_sets') +
		deepchem.utils.download_url(
		'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/chembl_year_sets/chembl_5thresh_ts_test.csv.gz'
		)
		os.system(
		'wget -P ' + os.path.join(data_dir, 'chembl_year_sets') +
		deepchem.utils.download_url(
		'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/chembl_year_sets/chembl_5thresh_ts_train.csv.gz'
		)
		os.system(
		'wget -P ' + os.path.join(data_dir, 'chembl_year_sets') +
		deepchem.utils.download_url(
		'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/chembl_year_sets/chembl_5thresh_ts_valid.csv.gz'
		)
		os.system(
		'wget -P ' + os.path.join(data_dir, 'chembl_year_sets') +
		deepchem.utils.download_url(
		'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/chembl_year_sets/chembl_sparse_ts_test.csv.gz'
		)
		os.system(
		'wget -P ' + os.path.join(data_dir, 'chembl_year_sets') +
		deepchem.utils.download_url(
		'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/chembl_year_sets/chembl_sparse_ts_train.csv.gz'
		)
		os.system(
		'wget -P ' + os.path.join(data_dir, 'chembl_year_sets') +
		deepchem.utils.download_url(
		'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/chembl_year_sets/chembl_sparse_ts_valid.csv.gz'
		)

Admin message