drugex package

Subpackages

Submodules

drugex.about module

about

Created by: Martin Sicho On: 24.06.22, 10:36

drugex.dataset module

class drugex.dataset.Dataset(args)[source]

Bases: object

setVocabulary()[source]

Set up vocabulary for sequence-based datasets. :returns: * voc (VocSmiles or None) – Vocabulary object

update_voc (bool) – If True, update vocabulary

drugex.dataset.DatasetArgParser()[source]

class drugex.dataset.FragGraphDataset(args)[source]: Bases: FragmentDataset

class drugex.dataset.FragSequenceDataset(args)[source]: Bases: FragmentDataset

class drugex.dataset.FragmentDataset(args)[source]

Bases: Dataset

setPairCollectors()[source]: Set up pair collectors for fragment-based datasets. :returns: pair_collectors – Dictionary containing pair collectors :rtype: dict

class drugex.dataset.SequenceDataset(args)[source]: Bases: Dataset

drugex.dataset.load_molecules(base_dir, input_file)[source]

Loads raw SMILES from input file and transform to rdkit molecule :param base_dir: base directory, needs to contain a folder data with input file :type base_dir: str :param input_file: file containing SMILES, can be ‘sdf.gz’ or (compressed) ‘tsv’ or ‘csv’ file :type input_file: str

Returns:: list of SMILES extracted from input_file
Return type:: mols (list)

drugex.download module

drugex.generate module

drugex.train module

Module contents

__init__.py

Created by: Martin Sicho On: 06.04.22, 16:51