Loading deepchem/molnet/__init__.py +2 −0 Original line number Diff line number Diff line Loading @@ -31,6 +31,8 @@ from deepchem.molnet.load_function.uspto_datasets import load_uspto from deepchem.molnet.load_function.uv_datasets import load_uv from deepchem.molnet.load_function.factors_datasets import load_factors from deepchem.molnet.load_function.kinase_datasets import load_kinase from deepchem.molnet.load_function.thermosol_datasets import load_thermosol from deepchem.molnet.load_function.hppb_datasets import load_hppb from deepchem.molnet.dnasim import simulate_motif_density_localization from deepchem.molnet.dnasim import simulate_motif_counting Loading deepchem/molnet/load_function/hppb_datasets.py 0 → 100644 +117 −0 Original line number Diff line number Diff line """ HPPB Dataset Loader. """ from __future__ import division from __future__ import unicode_literals import os import logging import deepchem import numpy as np logger = logging.getLogger(__name__) HPPB_URL = "http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/hppb.csv" DEFAULT_DATA_DIR = deepchem.utils.get_data_dir() def remove_missing_entries(dataset): """Remove missing entries. Some of the datasets have missing entries that sneak in as zero'd out feature vectors. Get rid of them. """ for i, (X, y, w, ids) in enumerate(dataset.itershards()): available_rows = X.any(axis=1) logger.info("Shard %d has %d missing entries." % (i, np.count_nonzero(~available_rows))) X = X[available_rows] y = y[available_rows] w = w[available_rows] ids = ids[available_rows] dataset.set_shard(i, X, y, w, ids) def load_hppb(featurizer="ECFP", data_dir=None, save_dir=None, split=None, split_seed=None, reload=True): """Loads the thermodynamic solubility datasets.""" # Featurizer hppb dataset logger.info("About to featurize hppb dataset...") hppb_tasks = ["target"] #Task is solubility in pH 7.4 buffer if data_dir is None: data_dir = DEFAULT_DATA_DIR if save_dir is None: save_dir = os.path.join(DEFAULT_DATA_DIR, "hppb", featurizer, str(split)) if reload: if not os.path.exists(save_dir): logger.warning("{} does not exist. Creating one.".format(save_dir)) else: logger.info("{} exists. Loading featurized datasets.".format(save_dir)) loaded, all_dataset, transformers = deepchem.utils.save.load_dataset_from_disk( save_dir) if loaded: return hppb_tasks, all_dataset, transformers dataset_file = os.path.join(data_dir, "hppb.csv") if not os.path.exists(dataset_file): logger.info("{} does not exist. Downloading it.".format(dataset_file)) deepchem.utils.download_url(url=hppb_URL, dest_dir=data_dir) 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() elif featurizer == 'AdjacencyConv': featurizer = deepchem.feat.AdjacencyFingerprint( max_n_atoms=150, max_valence=6) logger.info("Featurizing datasets.") loader = deepchem.data.CSVLoader( tasks=hppb_tasks, smiles_field='smile', featurizer=featurizer) dataset = loader.featurize(input_files=[dataset_file], shard_size=2000) logger.info("Removing missing entries...") remove_missing_entries(dataset) if split == None: logger.info("About to transform the data...") for transformer in transformers: logger.info("Transforming the dataset with transformer ", transformer.__class__.__name__) dataset = transformer.transform(dataset) return hppb_tasks, (dataset, None, None), transformers splitters = { 'index': deepchem.splits.IndexSplitter(), 'random': deepchem.splits.RandomSplitter(), 'scaffold': deepchem.splits.ScaffoldSplitter(), 'butina': deepchem.splits.ButinaSplitter(), } splitter = splitters[split] train, valid, test = splitter.train_valid_test_split(dataset, seed=split_seed) transformers = [] logger.info("About to transform the data...") for transformer in transformers: logger.info("Transforming the data with transformer ", transformer.__class__.__name__) train = transformer.transform(train) valid = transformer.transform(valid) test = transformer.transform(test) if reload: logger.info("Saving file to {}.".format(save_dir)) deepchem.utils.save.save_dataset_to_disk(save_dir, train, valid, test, transformers) return hppb_tasks, (train, valid, test), transformers deepchem/molnet/load_function/thermosol_datasets.py 0 → 100644 +118 −0 Original line number Diff line number Diff line """ Thermodynamic Solubility Dataset Loader """ from __future__ import division from __future__ import unicode_literals import os import logging import deepchem import numpy as np logger = logging.getLogger(__name__) THERMOSOL_URL = "http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/thermosol.csv" DEFAULT_DATA_DIR = deepchem.utils.get_data_dir() def remove_missing_entries(dataset): """Remove missing entries. Some of the datasets have missing entries that sneak in as zero'd out feature vectors. Get rid of them. """ for i, (X, y, w, ids) in enumerate(dataset.itershards()): available_rows = X.any(axis=1) logger.info("Shard %d has %d missing entries." % (i, np.count_nonzero(~available_rows))) X = X[available_rows] y = y[available_rows] w = w[available_rows] ids = ids[available_rows] dataset.set_shard(i, X, y, w, ids) def load_thermosol(featurizer="ECFP", data_dir=None, save_dir=None, split=None, split_seed=None, reload=True): """Loads the thermodynamic solubility datasets.""" # Featurizer thermosol dataset logger.info("About to featurize thermosol dataset...") thermosol_tasks = ["target"] #Task is solubility in pH 7.4 buffer if data_dir is None: data_dir = DEFAULT_DATA_DIR if save_dir is None: save_dir = os.path.join(DEFAULT_DATA_DIR, "thermosol", featurizer, str(split)) if reload: if not os.path.exists(save_dir): logger.warning("{} does not exist. Creating one.".format(save_dir)) else: logger.info("{} exists. Loading featurized datasets.".format(save_dir)) loaded, all_dataset, transformers = deepchem.utils.save.load_dataset_from_disk( save_dir) if loaded: return thermosol_tasks, all_dataset, transformers dataset_file = os.path.join(data_dir, "thermosol.csv") if not os.path.exists(dataset_file): logger.info("{} does not exist. Downloading it.".format(dataset_file)) deepchem.utils.download_url(url=THERMOSOL_URL, dest_dir=data_dir) 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() elif featurizer == 'AdjacencyConv': featurizer = deepchem.feat.AdjacencyFingerprint( max_n_atoms=150, max_valence=6) logger.info("Featurizing datasets.") loader = deepchem.data.CSVLoader( tasks=thermosol_tasks, smiles_field='smile', featurizer=featurizer) dataset = loader.featurize(input_files=[dataset_file], shard_size=2000) logger.info("Removing missing entries...") remove_missing_entries(dataset) if split == None: logger.info("About to transform the data...") for transformer in transformers: logger.info("Transforming the dataset with transformer ", transformer.__class__.__name__) dataset = transformer.transform(dataset) return thermosol_tasks, (dataset, None, None), transformers splitters = { 'index': deepchem.splits.IndexSplitter(), 'random': deepchem.splits.RandomSplitter(), 'scaffold': deepchem.splits.ScaffoldSplitter(), 'butina': deepchem.splits.ButinaSplitter(), } splitter = splitters[split] train, valid, test = splitter.train_valid_test_split(dataset, seed=split_seed) transformers = [] logger.info("About to transform the data...") for transformer in transformers: logger.info("Transforming the data with transformer ", transformer.__class__.__name__) train = transformer.transform(train) valid = transformer.transform(valid) test = transformer.transform(test) if reload: logger.info("Saving file to {}.".format(save_dir)) deepchem.utils.save.save_dataset_to_disk(save_dir, train, valid, test, transformers) return thermosol_tasks, (train, valid, test), transformers deepchem/molnet/run_benchmark.py +6 −1 Original line number Diff line number Diff line Loading @@ -90,7 +90,8 @@ def run_benchmark(datasets, ] elif dataset in [ 'bace_r', 'chembl', 'clearance', 'delaney', 'hopv', 'kaggle', 'lipo', 'nci', 'pdbbind', 'ppb', 'qm7', 'qm7b', 'qm8', 'qm9', 'sampl' 'nci', 'pdbbind', 'ppb', 'qm7', 'qm7b', 'qm8', 'qm9', 'sampl', 'thermosol' ]: mode = 'regression' if metric == None: Loading Loading @@ -123,6 +124,7 @@ def run_benchmark(datasets, 'factors': deepchem.molnet.load_factors, 'hiv': deepchem.molnet.load_hiv, 'hopv': deepchem.molnet.load_hopv, 'hppb': deepchem.molnet.load_hppb, 'kaggle': deepchem.molnet.load_kaggle, 'kinase': deepchem.molnet.load_kinase, 'lipo': deepchem.molnet.load_lipo, Loading @@ -139,6 +141,7 @@ def run_benchmark(datasets, 'qm9': deepchem.molnet.load_qm9, 'sampl': deepchem.molnet.load_sampl, 'sider': deepchem.molnet.load_sider, 'thermosol': deepchem.molnet.load_thermosol, 'tox21': deepchem.molnet.load_tox21, 'toxcast': deepchem.molnet.load_toxcast, 'uv': deepchem.molnet.load_uv, Loading Loading @@ -272,6 +275,7 @@ def load_dataset(dataset, featurizer, split='random'): 'factors': deepchem.molnet.load_factors, 'hiv': deepchem.molnet.load_hiv, 'hopv': deepchem.molnet.load_hopv, 'hppb': deepchem.molnet.load_hppb, 'kaggle': deepchem.molnet.load_kaggle, 'kinase': deepchem.molnet.load_kinase, 'lipo': deepchem.molnet.load_lipo, Loading @@ -289,6 +293,7 @@ def load_dataset(dataset, featurizer, split='random'): 'qm9': deepchem.molnet.load_qm9, 'sampl': deepchem.molnet.load_sampl, 'sider': deepchem.molnet.load_sider, 'thermosol': deepchem.molnet.load_thermosol, 'tox21': deepchem.molnet.load_tox21, 'toxcast': deepchem.molnet.load_toxcast, 'uv': deepchem.molnet.load_uv Loading Loading
deepchem/molnet/__init__.py +2 −0 Original line number Diff line number Diff line Loading @@ -31,6 +31,8 @@ from deepchem.molnet.load_function.uspto_datasets import load_uspto from deepchem.molnet.load_function.uv_datasets import load_uv from deepchem.molnet.load_function.factors_datasets import load_factors from deepchem.molnet.load_function.kinase_datasets import load_kinase from deepchem.molnet.load_function.thermosol_datasets import load_thermosol from deepchem.molnet.load_function.hppb_datasets import load_hppb from deepchem.molnet.dnasim import simulate_motif_density_localization from deepchem.molnet.dnasim import simulate_motif_counting Loading
deepchem/molnet/load_function/hppb_datasets.py 0 → 100644 +117 −0 Original line number Diff line number Diff line """ HPPB Dataset Loader. """ from __future__ import division from __future__ import unicode_literals import os import logging import deepchem import numpy as np logger = logging.getLogger(__name__) HPPB_URL = "http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/hppb.csv" DEFAULT_DATA_DIR = deepchem.utils.get_data_dir() def remove_missing_entries(dataset): """Remove missing entries. Some of the datasets have missing entries that sneak in as zero'd out feature vectors. Get rid of them. """ for i, (X, y, w, ids) in enumerate(dataset.itershards()): available_rows = X.any(axis=1) logger.info("Shard %d has %d missing entries." % (i, np.count_nonzero(~available_rows))) X = X[available_rows] y = y[available_rows] w = w[available_rows] ids = ids[available_rows] dataset.set_shard(i, X, y, w, ids) def load_hppb(featurizer="ECFP", data_dir=None, save_dir=None, split=None, split_seed=None, reload=True): """Loads the thermodynamic solubility datasets.""" # Featurizer hppb dataset logger.info("About to featurize hppb dataset...") hppb_tasks = ["target"] #Task is solubility in pH 7.4 buffer if data_dir is None: data_dir = DEFAULT_DATA_DIR if save_dir is None: save_dir = os.path.join(DEFAULT_DATA_DIR, "hppb", featurizer, str(split)) if reload: if not os.path.exists(save_dir): logger.warning("{} does not exist. Creating one.".format(save_dir)) else: logger.info("{} exists. Loading featurized datasets.".format(save_dir)) loaded, all_dataset, transformers = deepchem.utils.save.load_dataset_from_disk( save_dir) if loaded: return hppb_tasks, all_dataset, transformers dataset_file = os.path.join(data_dir, "hppb.csv") if not os.path.exists(dataset_file): logger.info("{} does not exist. Downloading it.".format(dataset_file)) deepchem.utils.download_url(url=hppb_URL, dest_dir=data_dir) 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() elif featurizer == 'AdjacencyConv': featurizer = deepchem.feat.AdjacencyFingerprint( max_n_atoms=150, max_valence=6) logger.info("Featurizing datasets.") loader = deepchem.data.CSVLoader( tasks=hppb_tasks, smiles_field='smile', featurizer=featurizer) dataset = loader.featurize(input_files=[dataset_file], shard_size=2000) logger.info("Removing missing entries...") remove_missing_entries(dataset) if split == None: logger.info("About to transform the data...") for transformer in transformers: logger.info("Transforming the dataset with transformer ", transformer.__class__.__name__) dataset = transformer.transform(dataset) return hppb_tasks, (dataset, None, None), transformers splitters = { 'index': deepchem.splits.IndexSplitter(), 'random': deepchem.splits.RandomSplitter(), 'scaffold': deepchem.splits.ScaffoldSplitter(), 'butina': deepchem.splits.ButinaSplitter(), } splitter = splitters[split] train, valid, test = splitter.train_valid_test_split(dataset, seed=split_seed) transformers = [] logger.info("About to transform the data...") for transformer in transformers: logger.info("Transforming the data with transformer ", transformer.__class__.__name__) train = transformer.transform(train) valid = transformer.transform(valid) test = transformer.transform(test) if reload: logger.info("Saving file to {}.".format(save_dir)) deepchem.utils.save.save_dataset_to_disk(save_dir, train, valid, test, transformers) return hppb_tasks, (train, valid, test), transformers
deepchem/molnet/load_function/thermosol_datasets.py 0 → 100644 +118 −0 Original line number Diff line number Diff line """ Thermodynamic Solubility Dataset Loader """ from __future__ import division from __future__ import unicode_literals import os import logging import deepchem import numpy as np logger = logging.getLogger(__name__) THERMOSOL_URL = "http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/thermosol.csv" DEFAULT_DATA_DIR = deepchem.utils.get_data_dir() def remove_missing_entries(dataset): """Remove missing entries. Some of the datasets have missing entries that sneak in as zero'd out feature vectors. Get rid of them. """ for i, (X, y, w, ids) in enumerate(dataset.itershards()): available_rows = X.any(axis=1) logger.info("Shard %d has %d missing entries." % (i, np.count_nonzero(~available_rows))) X = X[available_rows] y = y[available_rows] w = w[available_rows] ids = ids[available_rows] dataset.set_shard(i, X, y, w, ids) def load_thermosol(featurizer="ECFP", data_dir=None, save_dir=None, split=None, split_seed=None, reload=True): """Loads the thermodynamic solubility datasets.""" # Featurizer thermosol dataset logger.info("About to featurize thermosol dataset...") thermosol_tasks = ["target"] #Task is solubility in pH 7.4 buffer if data_dir is None: data_dir = DEFAULT_DATA_DIR if save_dir is None: save_dir = os.path.join(DEFAULT_DATA_DIR, "thermosol", featurizer, str(split)) if reload: if not os.path.exists(save_dir): logger.warning("{} does not exist. Creating one.".format(save_dir)) else: logger.info("{} exists. Loading featurized datasets.".format(save_dir)) loaded, all_dataset, transformers = deepchem.utils.save.load_dataset_from_disk( save_dir) if loaded: return thermosol_tasks, all_dataset, transformers dataset_file = os.path.join(data_dir, "thermosol.csv") if not os.path.exists(dataset_file): logger.info("{} does not exist. Downloading it.".format(dataset_file)) deepchem.utils.download_url(url=THERMOSOL_URL, dest_dir=data_dir) 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() elif featurizer == 'AdjacencyConv': featurizer = deepchem.feat.AdjacencyFingerprint( max_n_atoms=150, max_valence=6) logger.info("Featurizing datasets.") loader = deepchem.data.CSVLoader( tasks=thermosol_tasks, smiles_field='smile', featurizer=featurizer) dataset = loader.featurize(input_files=[dataset_file], shard_size=2000) logger.info("Removing missing entries...") remove_missing_entries(dataset) if split == None: logger.info("About to transform the data...") for transformer in transformers: logger.info("Transforming the dataset with transformer ", transformer.__class__.__name__) dataset = transformer.transform(dataset) return thermosol_tasks, (dataset, None, None), transformers splitters = { 'index': deepchem.splits.IndexSplitter(), 'random': deepchem.splits.RandomSplitter(), 'scaffold': deepchem.splits.ScaffoldSplitter(), 'butina': deepchem.splits.ButinaSplitter(), } splitter = splitters[split] train, valid, test = splitter.train_valid_test_split(dataset, seed=split_seed) transformers = [] logger.info("About to transform the data...") for transformer in transformers: logger.info("Transforming the data with transformer ", transformer.__class__.__name__) train = transformer.transform(train) valid = transformer.transform(valid) test = transformer.transform(test) if reload: logger.info("Saving file to {}.".format(save_dir)) deepchem.utils.save.save_dataset_to_disk(save_dir, train, valid, test, transformers) return thermosol_tasks, (train, valid, test), transformers
deepchem/molnet/run_benchmark.py +6 −1 Original line number Diff line number Diff line Loading @@ -90,7 +90,8 @@ def run_benchmark(datasets, ] elif dataset in [ 'bace_r', 'chembl', 'clearance', 'delaney', 'hopv', 'kaggle', 'lipo', 'nci', 'pdbbind', 'ppb', 'qm7', 'qm7b', 'qm8', 'qm9', 'sampl' 'nci', 'pdbbind', 'ppb', 'qm7', 'qm7b', 'qm8', 'qm9', 'sampl', 'thermosol' ]: mode = 'regression' if metric == None: Loading Loading @@ -123,6 +124,7 @@ def run_benchmark(datasets, 'factors': deepchem.molnet.load_factors, 'hiv': deepchem.molnet.load_hiv, 'hopv': deepchem.molnet.load_hopv, 'hppb': deepchem.molnet.load_hppb, 'kaggle': deepchem.molnet.load_kaggle, 'kinase': deepchem.molnet.load_kinase, 'lipo': deepchem.molnet.load_lipo, Loading @@ -139,6 +141,7 @@ def run_benchmark(datasets, 'qm9': deepchem.molnet.load_qm9, 'sampl': deepchem.molnet.load_sampl, 'sider': deepchem.molnet.load_sider, 'thermosol': deepchem.molnet.load_thermosol, 'tox21': deepchem.molnet.load_tox21, 'toxcast': deepchem.molnet.load_toxcast, 'uv': deepchem.molnet.load_uv, Loading Loading @@ -272,6 +275,7 @@ def load_dataset(dataset, featurizer, split='random'): 'factors': deepchem.molnet.load_factors, 'hiv': deepchem.molnet.load_hiv, 'hopv': deepchem.molnet.load_hopv, 'hppb': deepchem.molnet.load_hppb, 'kaggle': deepchem.molnet.load_kaggle, 'kinase': deepchem.molnet.load_kinase, 'lipo': deepchem.molnet.load_lipo, Loading @@ -289,6 +293,7 @@ def load_dataset(dataset, featurizer, split='random'): 'qm9': deepchem.molnet.load_qm9, 'sampl': deepchem.molnet.load_sampl, 'sider': deepchem.molnet.load_sider, 'thermosol': deepchem.molnet.load_thermosol, 'tox21': deepchem.molnet.load_tox21, 'toxcast': deepchem.molnet.load_toxcast, 'uv': deepchem.molnet.load_uv Loading
