Loading deepchem/molnet/load_function/uspto_datasets.py +13 −12 Original line number Diff line number Diff line Loading @@ -72,13 +72,13 @@ def load_uspto( """Load USPTO Datasets. USPTO is a dataset of over 1.8 Million organic chemical reactions extracted from US patents and patent applications. The dataset is stored in the from of src and tgt . The src contains the SMILES for the reactants and reagent in the form reactant>reagent the tgt contains the SMILES for the product SMILES. from US patents and patent applications. The reactions present in the dataset are split into the source(src) and target(tgt) columns. The src column contains the SMILES of the reactant and reagent molecules in the form reactant>reagent. The tgt contains the SMILES of the product molecules. Molnet provides ability to load subsets of USPTO such as MIT, STEREO and 50K. The MIT dataset contains around 480k reactions Molnet provides ability to load subsets of the USPTO dataset namely MIT, STEREO and 50K. The MIT dataset contains around 480k reactions The STEREO dataset contains around 1 Million Reactions. The 50K dataset contatins 50,000 reactions with an additional label indicating the class of reaction to which it belongs. The loader uses the Loading Loading @@ -109,6 +109,7 @@ def load_uspto( a directory to save the dataset in subset : str (default 'MIT') Subset of dataset to download. 'FULL', 'MIT', 'STEREO', and '50K' are supported. Returns ------- tasks, datasets, transformers : tuple Loading @@ -122,7 +123,7 @@ def load_uspto( to dataset. ---------- .. [1] Lowe, D.. (2017). Chemical reactions from US patents (1976-Sep2016) (Version 1). figshare. https://doi.org/10.6084/m9.figshare.5104873.v1 ([]) (Version 1). figshare. https://doi.org/10.6084/m9.figshare.5104873.v1 .. [2] Schwaller, P., Laino, T., Gaudin, T., Bolgar, P., Hunter, C. A., Bekas, C., & Lee, A. A. (2019). Molecular transformer: a model for uncertainty-calibrated chemical reaction prediction. Loading deepchem/molnet/tests/test_uspto.py 0 → 100644 +0 −0 Empty file added. Loading
deepchem/molnet/load_function/uspto_datasets.py +13 −12 Original line number Diff line number Diff line Loading @@ -72,13 +72,13 @@ def load_uspto( """Load USPTO Datasets. USPTO is a dataset of over 1.8 Million organic chemical reactions extracted from US patents and patent applications. The dataset is stored in the from of src and tgt . The src contains the SMILES for the reactants and reagent in the form reactant>reagent the tgt contains the SMILES for the product SMILES. from US patents and patent applications. The reactions present in the dataset are split into the source(src) and target(tgt) columns. The src column contains the SMILES of the reactant and reagent molecules in the form reactant>reagent. The tgt contains the SMILES of the product molecules. Molnet provides ability to load subsets of USPTO such as MIT, STEREO and 50K. The MIT dataset contains around 480k reactions Molnet provides ability to load subsets of the USPTO dataset namely MIT, STEREO and 50K. The MIT dataset contains around 480k reactions The STEREO dataset contains around 1 Million Reactions. The 50K dataset contatins 50,000 reactions with an additional label indicating the class of reaction to which it belongs. The loader uses the Loading Loading @@ -109,6 +109,7 @@ def load_uspto( a directory to save the dataset in subset : str (default 'MIT') Subset of dataset to download. 'FULL', 'MIT', 'STEREO', and '50K' are supported. Returns ------- tasks, datasets, transformers : tuple Loading @@ -122,7 +123,7 @@ def load_uspto( to dataset. ---------- .. [1] Lowe, D.. (2017). Chemical reactions from US patents (1976-Sep2016) (Version 1). figshare. https://doi.org/10.6084/m9.figshare.5104873.v1 ([]) (Version 1). figshare. https://doi.org/10.6084/m9.figshare.5104873.v1 .. [2] Schwaller, P., Laino, T., Gaudin, T., Bolgar, P., Hunter, C. A., Bekas, C., & Lee, A. A. (2019). Molecular transformer: a model for uncertainty-calibrated chemical reaction prediction. Loading
