Membrane Permeability Data (da8419d5) · Commits · 钟慕尧 / deepchem

datasets/membrane_permeability.sdf.csv

+202 −202

File changed.

Preview size limit exceeded, changes collapsed.

+7 −7

Original line number	Diff line number	Diff line
		@@ -245,7 +245,7 @@ class SDFLoader(DataLoader):
		self.clean_mols = clean_mols
		self.smiles_field = "smiles"
		self.mol_field = "mol"
		self.id_field = "mol_id"
		self.id_field = "smiles"

		def get_shards(self, input_files, shard_size):
		"""Defines a generator which returns data for each shard"""

+8 −5

Original line number	Diff line number	Diff line
		@@ -57,6 +57,7 @@ from qm9.qm9_datasets import load_qm9
		from sampl.sampl_datasets import load_sampl
		from clintox.clintox_datasets import load_clintox
		from hiv.hiv_datasets import load_hiv
		from membrane_permeability.membrane_permeability_datasets import load_permeability
		import xgboost


		@@ -92,7 +93,7 @@ def benchmark_loading_datasets(hyper_parameters,
		mode = 'classification'
		elif dataset in [
		'kaggle', 'delaney', 'nci', 'pdbbind', 'chembl', 'qm7', 'qm7b', 'qm9',
		'sampl'
		'sampl', 'membrane_permeability'
		]:
		mode = 'regression'
		else:
		@@ -160,7 +161,8 @@ def benchmark_loading_datasets(hyper_parameters,
		'qm9': load_qm9,
		'sampl': load_sampl,
		'clintox': load_clintox,
		'hiv': load_hiv
		'hiv': load_hiv,
		'membrane_permeability': load_permeability
		}

		print('-------------------------------------')
		@@ -916,8 +918,8 @@ if __name__ == '__main__':
		dest='dataset_args',
		default=[],
		help='Choice of dataset: tox21, sider, muv, toxcast, pcba, ' +
		'kaggle, delaney, nci, pdbbind, chembl, sampl, qm7, qm7b, qm9, clintox, hiv'
		)
		'kaggle, delaney, nci, pdbbind, chembl, sampl, qm7, qm7b, qm9, clintox, hiv,'
		' membrane_permeability')
		parser.add_argument(
		'-t',
		action='store_true',
		@@ -943,7 +945,8 @@ if __name__ == '__main__':
		if len(datasets) == 0:
		datasets = [
		'tox21', 'sider', 'muv', 'toxcast', 'pcba', 'clintox', 'hiv', 'sampl',
		'delaney', 'nci', 'kaggle', 'pdbbind', 'chembl', 'qm7b', 'qm9'
		'delaney', 'nci', 'kaggle', 'pdbbind', 'chembl', 'qm7b', 'qm9',
		'membrane_permeability'
		]

		#input hyperparameters

+8 −6

Original line number	Diff line number	Diff line
		@@ -15,8 +15,8 @@ def load_permeability(featurizer='ECFP', split='index'):
		"""Load membrain permeability datasets. Does not do train/test split"""
		print("About to load membrain permeability dataset.")
		current_dir = os.path.dirname(os.path.realpath(__file__))
		dataset_file = os.path.join(
		current_dir, "../../datasets/membrane_permeability.sdf")
		dataset_file = os.path.join(current_dir,
		"../../datasets/membrane_permeability.sdf")
		# Featurize permeability dataset
		print("About to featurize membrain permeability dataset.")

		@@ -31,9 +31,11 @@ def load_permeability(featurizer='ECFP', split='index'):
		tasks=permeability_tasks, clean_mols=True, featurizer=featurizer_func)
		dataset = loader.featurize(dataset_file)

		splitters = {'index': dc.splits.IndexSplitter(),
		splitters = {
		'index': dc.splits.IndexSplitter(),
		'random': dc.splits.RandomSplitter(),
		'scaffold': dc.splits.ScaffoldSplitter()}
		'scaffold': dc.splits.ScaffoldSplitter()
		}
		splitter = splitters[split]
		train, valid, test = splitter.train_valid_test_split(dataset)
		return permeability_tasks, (train, valid, test), []

+9 −9

Original line number	Diff line number	Diff line
		@@ -13,7 +13,8 @@ import deepchem as dc
		from membrain_permeability_datasets import load_permeability

		# Load Tox21 dataset
		permeability_tasks, permeability_datasets, transformers = load_permeability(featurizer='GraphConv')
		permeability_tasks, permeability_datasets, transformers = load_permeability(
		featurizer='GraphConv')
		train_dataset, valid_dataset, test_dataset = permeability_datasets

		metric = dc.metrics.Metric(dc.metrics.pearson_r2_score, np.mean)
		@@ -53,4 +54,3 @@ print(train_scores)

		print("Validation scores")
		print(valid_scores)