deepchem.molnet.load_function package

Submodules

deepchem.molnet.load_function.bace_datasets module

bace dataset loader.

deepchem.molnet.load_function.bace_datasets.load_bace_classification(featurizer='ECFP', split='random', reload=True)[source]

Load bace datasets.

deepchem.molnet.load_function.bace_datasets.load_bace_regression(featurizer='ECFP', split='random', reload=True)[source]

Load bace datasets.

deepchem.molnet.load_function.bace_features module

deepchem.molnet.load_function.bbbp_datasets module

Blood-Brain Barrier Penetration dataset loader.

deepchem.molnet.load_function.bbbp_datasets.load_bbbp(featurizer='ECFP', split='random', reload=True)[source]

Load blood-brain barrier penetration datasets

deepchem.molnet.load_function.chembl_datasets module

ChEMBL dataset loader.

deepchem.molnet.load_function.chembl_datasets.load_chembl(shard_size=2000, featurizer='ECFP', set='5thresh', split='random', reload=True)[source]

deepchem.molnet.load_function.chembl_tasks module

deepchem.molnet.load_function.clearance_datasets module

clearance dataset loader.

deepchem.molnet.load_function.clearance_datasets.load_clearance(featurizer='ECFP', split='random', reload=True)[source]

Load clearance datasets.

deepchem.molnet.load_function.clintox_datasets module

Clinical Toxicity (clintox) dataset loader. @author Caleb Geniesse

deepchem.molnet.load_function.clintox_datasets.load_clintox(featurizer='ECFP', split='index', reload=True)[source]

Load clintox datasets.

deepchem.molnet.load_function.delaney_datasets module

Delaney dataset loader.

deepchem.molnet.load_function.delaney_datasets.load_delaney(featurizer='ECFP', split='index', reload=True)[source]

Load delaney datasets.

deepchem.molnet.load_function.hiv_datasets module

hiv dataset loader.

deepchem.molnet.load_function.hiv_datasets.load_hiv(featurizer='ECFP', split='index', reload=True)[source]

Load hiv datasets. Does not do train/test split

deepchem.molnet.load_function.hopv_datasets module

HOPV dataset loader.

deepchem.molnet.load_function.hopv_datasets.load_hopv(featurizer='ECFP', split='index', reload=True)[source]

Load HOPV datasets. Does not do train/test split

deepchem.molnet.load_function.kaggle_datasets module

KAGGLE dataset loader.

deepchem.molnet.load_function.kaggle_datasets.gen_kaggle(KAGGLE_tasks, train_dir, valid_dir, test_dir, data_dir, shard_size=2000)[source]

Load KAGGLE datasets. Does not do train/test split

deepchem.molnet.load_function.kaggle_datasets.get_transformers(train_dataset)[source]

Get transformers applied to datasets.

deepchem.molnet.load_function.kaggle_datasets.load_kaggle(shard_size=2000, featurizer=None, split=None, reload=True)[source]

Loads kaggle datasets. Generates if not stored already.

deepchem.molnet.load_function.kaggle_datasets.remove_missing_entries(dataset)[source]

Remove missing entries.

Some of the datasets have missing entries that sneak in as zero’d out feature vectors. Get rid of them.

deepchem.molnet.load_function.kaggle_features module

deepchem.molnet.load_function.lipo_datasets module

Lipophilicity dataset loader.

deepchem.molnet.load_function.lipo_datasets.load_lipo(featurizer='ECFP', split='index', reload=True)[source]

Load Lipophilicity datasets.

deepchem.molnet.load_function.muv_datasets module

MUV dataset loader.

deepchem.molnet.load_function.muv_datasets.load_muv(featurizer='ECFP', split='index', reload=True, K=4)[source]

Load MUV datasets. Does not do train/test split

deepchem.molnet.load_function.nci_datasets module

NCI dataset loader. Original Author - Bharath Ramsundar Author - Aneesh Pappu

deepchem.molnet.load_function.nci_datasets.load_nci(featurizer='ECFP', shard_size=1000, split='random', reload=True)[source]

deepchem.molnet.load_function.pcba_datasets module

PCBA dataset loader.

deepchem.molnet.load_function.pcba_datasets.load_pcba(featurizer='ECFP', split='random', reload=True)[source]
deepchem.molnet.load_function.pcba_datasets.load_pcba_146(featurizer='ECFP', split='random', reload=True)[source]
deepchem.molnet.load_function.pcba_datasets.load_pcba_2475(featurizer='ECFP', split='random', reload=True)[source]
deepchem.molnet.load_function.pcba_datasets.load_pcba_dataset(featurizer='ECFP', split='random', reload=True, assay_file_name='pcba.csv.gz')[source]

Load PCBA datasets. Does not do train/test split

deepchem.molnet.load_function.pdbbind_datasets module

PDBBind dataset loader.

deepchem.molnet.load_function.pdbbind_datasets.featurize_pdbbind(data_dir=None, feat='grid', subset='core')[source]

Featurizes pdbbind according to provided featurization

deepchem.molnet.load_function.pdbbind_datasets.load_pdbbind_grid(split='random', featurizer='grid', subset='core', reload=True)[source]

Load PDBBind datasets. Does not do train/test split

deepchem.molnet.load_function.ppb_datasets module

PPB dataset loader.

deepchem.molnet.load_function.ppb_datasets.load_ppb(featurizer='ECFP', split='index', reload=True)[source]

Load PPB datasets.

deepchem.molnet.load_function.qm7_datasets module

qm7 dataset loader.

deepchem.molnet.load_function.qm7_datasets.load_qm7(featurizer='CoulombMatrix', split='random', reload=True)[source]

Load qm7 datasets.

deepchem.molnet.load_function.qm7_datasets.load_qm7_from_mat(featurizer='CoulombMatrix', split='stratified', reload=True)[source]
deepchem.molnet.load_function.qm7_datasets.load_qm7b_from_mat(featurizer='CoulombMatrix', split='stratified', reload=True)[source]

deepchem.molnet.load_function.qm8_datasets module

qm8 dataset loader.

deepchem.molnet.load_function.qm8_datasets.load_qm8(featurizer='CoulombMatrix', split='random', reload=True)[source]

deepchem.molnet.load_function.qm9_datasets module

qm9 dataset loader.

deepchem.molnet.load_function.qm9_datasets.load_qm9(featurizer='CoulombMatrix', split='random', reload=True)[source]

Load qm9 datasets.

deepchem.molnet.load_function.sampl_datasets module

SAMPL dataset loader.

deepchem.molnet.load_function.sampl_datasets.load_sampl(featurizer='ECFP', split='index', reload=True)[source]

Load SAMPL datasets.

deepchem.molnet.load_function.sider_datasets module

SIDER dataset loader.

deepchem.molnet.load_function.sider_datasets.load_sider(featurizer='ECFP', split='index', reload=True, K=4)[source]

deepchem.molnet.load_function.tox21_datasets module

Tox21 dataset loader.

deepchem.molnet.load_function.tox21_datasets.load_tox21(featurizer='ECFP', split='index', reload=True, K=4)[source]

Load Tox21 datasets. Does not do train/test split

deepchem.molnet.load_function.toxcast_datasets module

TOXCAST dataset loader.

deepchem.molnet.load_function.toxcast_datasets.load_toxcast(featurizer='ECFP', split='index', reload=True)[source]

Module contents