Source code for deepchem.molnet.load_function.muv_datasets

"""
MUV dataset loader.
"""
from __future__ import print_function
from __future__ import division
from __future__ import unicode_literals

import os
import deepchem


[docs]def load_muv(featurizer='ECFP', split='index', reload=True, K=4): """Load MUV datasets. Does not do train/test split""" # Load MUV dataset print("About to load MUV dataset.") data_dir = deepchem.utils.get_data_dir() if reload: save_dir = os.path.join(data_dir, "muv/" + featurizer + "/" + split) dataset_file = os.path.join(data_dir, "muv.csv.gz") if not os.path.exists(dataset_file): deepchem.utils.download_url( 'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/muv.csv.gz' ) MUV_tasks = sorted([ 'MUV-692', 'MUV-689', 'MUV-846', 'MUV-859', 'MUV-644', 'MUV-548', 'MUV-852', 'MUV-600', 'MUV-810', 'MUV-712', 'MUV-737', 'MUV-858', 'MUV-713', 'MUV-733', 'MUV-652', 'MUV-466', 'MUV-832' ]) if reload: loaded, all_dataset, transformers = deepchem.utils.save.load_dataset_from_disk( save_dir) if loaded: return MUV_tasks, all_dataset, transformers # Featurize MUV dataset print("About to featurize MUV dataset.") if featurizer == 'ECFP': featurizer = deepchem.feat.CircularFingerprint(size=1024) elif featurizer == 'GraphConv': featurizer = deepchem.feat.ConvMolFeaturizer() elif featurizer == 'Weave': featurizer = deepchem.feat.WeaveFeaturizer() elif featurizer == 'Raw': featurizer = deepchem.feat.RawFeaturizer() loader = deepchem.data.CSVLoader( tasks=MUV_tasks, smiles_field="smiles", featurizer=featurizer) dataset = loader.featurize(dataset_file) # Initialize transformers transformers = [ deepchem.trans.BalancingTransformer(transform_w=True, dataset=dataset) ] print("About to transform data") for transformer in transformers: dataset = transformer.transform(dataset) splitters = { 'index': deepchem.splits.IndexSplitter(), 'random': deepchem.splits.RandomSplitter(), 'scaffold': deepchem.splits.ScaffoldSplitter(), 'task': deepchem.splits.TaskSplitter() } splitter = splitters[split] if split == 'task': fold_datasets = splitter.k_fold_split(dataset, K) all_dataset = fold_datasets else: train, valid, test = splitter.train_valid_test_split(dataset) if reload: deepchem.utils.save.save_dataset_to_disk(save_dir, train, valid, test, transformers) all_dataset = (train, valid, test) return MUV_tasks, all_dataset, transformers