Loading deepchem/feat/smiles_tokenizer.py +5 −4 Original line number Diff line number Diff line Loading @@ -14,13 +14,10 @@ from transformers import BertTokenizer SMI_REGEX_PATTERN = r"""(\[[^\]]+]|Br?|Cl?|N|O|S|P|F|I|b|c|n|o|s|p|\(|\)|\.|=| #|-|\+|\\|\/|:|~|@|\?|>>?|\*|\$|\%[0-9]{2}|[0-9])""" """ SMI_REGEX_PATTERN: str SMILES regex pattern for tokenization. Designed by Schwaller et. al. References .. [1] Philippe Schwaller, Teodoro Laino, Théophile Gaudin, Peter Bolgar, Christopher A. Hunter, Costas Bekas, and Alpha A. Lee Loading @@ -29,6 +26,10 @@ References """ SMI_REGEX_PATTERN = r"""(\[[^\]]+]|Br?|Cl?|N|O|S|P|F|I|b|c|n|o|s|p|\(|\)|\.|=| #|-|\+|\\|\/|:|~|@|\?|>>?|\*|\$|\%[0-9]{2}|[0-9])""" def get_default_tokenizer(): default_vocab_path = ( pkg_resources.resource_filename( Loading Loading
deepchem/feat/smiles_tokenizer.py +5 −4 Original line number Diff line number Diff line Loading @@ -14,13 +14,10 @@ from transformers import BertTokenizer SMI_REGEX_PATTERN = r"""(\[[^\]]+]|Br?|Cl?|N|O|S|P|F|I|b|c|n|o|s|p|\(|\)|\.|=| #|-|\+|\\|\/|:|~|@|\?|>>?|\*|\$|\%[0-9]{2}|[0-9])""" """ SMI_REGEX_PATTERN: str SMILES regex pattern for tokenization. Designed by Schwaller et. al. References .. [1] Philippe Schwaller, Teodoro Laino, Théophile Gaudin, Peter Bolgar, Christopher A. Hunter, Costas Bekas, and Alpha A. Lee Loading @@ -29,6 +26,10 @@ References """ SMI_REGEX_PATTERN = r"""(\[[^\]]+]|Br?|Cl?|N|O|S|P|F|I|b|c|n|o|s|p|\(|\)|\.|=| #|-|\+|\\|\/|:|~|@|\?|>>?|\*|\$|\%[0-9]{2}|[0-9])""" def get_default_tokenizer(): default_vocab_path = ( pkg_resources.resource_filename( Loading
