Loading deep_chem/models/__init__.py +0 −3 Original line number Diff line number Diff line Loading @@ -46,9 +46,6 @@ class Model(object): @staticmethod def model_builder(model_type, task_types, model_params, initialize_raw_model=True): print("model_builder()") print("model_params") print(model_params) if model_type in Model.registered_model_types: model = Model.registered_model_types[model_type]( task_types, model_params, initialize_raw_model) Loading deep_chem/scripts/modeler.py +18 −16 Original line number Diff line number Diff line Loading @@ -73,22 +73,23 @@ def add_train_test_command(subparsers): choices=["normalize-and-truncate"], help="Transforms to apply to input data.") train_test_cmd.add_argument( "--output-transforms", type=str, default="", help="Comma-separated list (no spaces) of transforms to apply to output data.\n" "Supported transforms are 'log' and 'normalize'. 'None' will be taken\n" "--output-transforms", nargs="+", default=[], help="Supported transforms are 'log' and 'normalize'. 'None' will be taken\n" "to mean no transforms are required.") train_test_cmd.add_argument( "--feature-types", type=str, required=1, help="Comma-separated list (no spaces) of types of featurizations to use.\n" "Each featurization must correspond to subdirectory in generated\n" "data directory.") "--feature-types", nargs="+", required=1, choices=["features", "fingerprints", "descriptors"], help="Featurizations of data to use.\n" "'features' denotes user-defined features.\n" "'fingerprints' denotes ECFP fingeprints.\n" "'descriptors' denotes RDKit chem descriptors.\n") train_test_cmd.add_argument( "--paths", nargs="+", required=1, help="Paths to input datasets.") train_test_cmd.add_argument( "--splittype", type=str, default="scaffold", choices=["scaffold", "random", "specified"], help="Type of train/test data-splitting. 'scaffold' uses Bemis-Murcko scaffolds.\n" help="Type of train/test data-split. 'scaffold' uses Bemis-Murcko scaffolds.\n" "specified requires that split be in original data.") train_test_cmd.add_argument( "--weight-positives", type=bool, default=False, Loading Loading @@ -215,22 +216,23 @@ def add_model_command(subparsers): choices=["normalize-and-truncate"], help="Transforms to apply to input data.") train_test_group.add_argument( "--output-transforms", type=str, default="", help="Comma-separated list (no spaces) of transforms to apply to output data.\n" "Supported transforms are log and normalize.") "--output-transforms", nargs="+", default=[], help="Supported transforms are log and normalize.") train_test_group.add_argument( "--mode", default="singletask", choices=["singletask", "multitask"], help="Type of model being built.") train_test_group.add_argument( "--feature-types", type=str, required=1, help="Comma-separated list (no spaces) of types of featurizations to use.\n" "Each featurization must correspond to subdirectory in generated\n" "data directory.") "--feature-types", nargs="+", required=1, choices=["features", "fingerprints", "descriptors"], help="Featurizations of data to use.\n" "'features' denotes user-defined features.\n" "'fingerprints' denotes ECFP fingeprints.\n" "'descriptors' denotes RDKit chem descriptors.\n") train_test_group.add_argument( "--splittype", type=str, default="scaffold", choices=["scaffold", "random", "specified"], help="Type of train/test data-splitting. 'scaffold' uses Bemis-Murcko scaffolds.\n" help="Type of train/test data-split. 'scaffold' uses Bemis-Murcko scaffolds.\n" "specified requires that split be in original data.") add_model_group(model_cmd) Loading deep_chem/utils/evaluate.py +5 −0 Original line number Diff line number Diff line Loading @@ -51,6 +51,11 @@ def compute_y_pred(model, data_dir, csv_out, split): split_df = metadata_df.loc[metadata_df['split'] == split] nb_batch = split_df.shape[0] print("compute_y_pred()") print("split_df.shape") print(split_df.shape) # TODO(rbharath/enf): This is only for GPU models, and is currently depends # on magic numbers. MAX_GPU_RAM = float(691007488/50) for i, row in split_df.iterrows(): Loading deep_chem/utils/featurize.py +10 −7 Original line number Diff line number Diff line Loading @@ -101,10 +101,9 @@ def process_field(data, field_type): elif field_type == "ndarray": return data def generate_scaffold(smiles_elt, include_chirality=False, smiles_field="smiles"): def generate_scaffold(smiles, include_chirality=False, smiles_field="smiles"): """Compute the Bemis-Murcko scaffold for a SMILES string.""" smiles_string = smiles_elt[smiles_field] mol = Chem.MolFromSmiles(smiles_string) mol = Chem.MolFromSmiles(smiles) engine = ScaffoldGenerator(include_chirality=include_chirality) scaffold = engine.get_scaffold(mol) return scaffold Loading Loading @@ -222,10 +221,14 @@ def featurize_inputs(feature_dir, input_files, input_type, fields, field_types, feature_fields, task_fields, smiles_field, split_field, id_field, threshold): featurize_input_partial = partial(featurize_input, feature_dir=feature_dir, input_type=input_type, fields=fields, field_types=field_types, feature_fields=feature_fields, task_fields=task_fields, smiles_field=smiles_field, split_field=split_field, id_field=id_field, threshold=threshold) featurize_input_partial = partial(featurize_input, feature_dir=feature_dir, input_type=input_type, fields=fields, field_types=field_types, feature_fields=feature_fields, task_fields=task_fields, smiles_field=smiles_field, split_field=split_field, id_field=id_field, threshold=threshold) #for input_file in input_files: # featurize_input_partial(input_file) Loading deep_chem/utils/preprocess.py +90 −392 File changed.Preview size limit exceeded, changes collapsed. Show changes Loading
deep_chem/models/__init__.py +0 −3 Original line number Diff line number Diff line Loading @@ -46,9 +46,6 @@ class Model(object): @staticmethod def model_builder(model_type, task_types, model_params, initialize_raw_model=True): print("model_builder()") print("model_params") print(model_params) if model_type in Model.registered_model_types: model = Model.registered_model_types[model_type]( task_types, model_params, initialize_raw_model) Loading
deep_chem/scripts/modeler.py +18 −16 Original line number Diff line number Diff line Loading @@ -73,22 +73,23 @@ def add_train_test_command(subparsers): choices=["normalize-and-truncate"], help="Transforms to apply to input data.") train_test_cmd.add_argument( "--output-transforms", type=str, default="", help="Comma-separated list (no spaces) of transforms to apply to output data.\n" "Supported transforms are 'log' and 'normalize'. 'None' will be taken\n" "--output-transforms", nargs="+", default=[], help="Supported transforms are 'log' and 'normalize'. 'None' will be taken\n" "to mean no transforms are required.") train_test_cmd.add_argument( "--feature-types", type=str, required=1, help="Comma-separated list (no spaces) of types of featurizations to use.\n" "Each featurization must correspond to subdirectory in generated\n" "data directory.") "--feature-types", nargs="+", required=1, choices=["features", "fingerprints", "descriptors"], help="Featurizations of data to use.\n" "'features' denotes user-defined features.\n" "'fingerprints' denotes ECFP fingeprints.\n" "'descriptors' denotes RDKit chem descriptors.\n") train_test_cmd.add_argument( "--paths", nargs="+", required=1, help="Paths to input datasets.") train_test_cmd.add_argument( "--splittype", type=str, default="scaffold", choices=["scaffold", "random", "specified"], help="Type of train/test data-splitting. 'scaffold' uses Bemis-Murcko scaffolds.\n" help="Type of train/test data-split. 'scaffold' uses Bemis-Murcko scaffolds.\n" "specified requires that split be in original data.") train_test_cmd.add_argument( "--weight-positives", type=bool, default=False, Loading Loading @@ -215,22 +216,23 @@ def add_model_command(subparsers): choices=["normalize-and-truncate"], help="Transforms to apply to input data.") train_test_group.add_argument( "--output-transforms", type=str, default="", help="Comma-separated list (no spaces) of transforms to apply to output data.\n" "Supported transforms are log and normalize.") "--output-transforms", nargs="+", default=[], help="Supported transforms are log and normalize.") train_test_group.add_argument( "--mode", default="singletask", choices=["singletask", "multitask"], help="Type of model being built.") train_test_group.add_argument( "--feature-types", type=str, required=1, help="Comma-separated list (no spaces) of types of featurizations to use.\n" "Each featurization must correspond to subdirectory in generated\n" "data directory.") "--feature-types", nargs="+", required=1, choices=["features", "fingerprints", "descriptors"], help="Featurizations of data to use.\n" "'features' denotes user-defined features.\n" "'fingerprints' denotes ECFP fingeprints.\n" "'descriptors' denotes RDKit chem descriptors.\n") train_test_group.add_argument( "--splittype", type=str, default="scaffold", choices=["scaffold", "random", "specified"], help="Type of train/test data-splitting. 'scaffold' uses Bemis-Murcko scaffolds.\n" help="Type of train/test data-split. 'scaffold' uses Bemis-Murcko scaffolds.\n" "specified requires that split be in original data.") add_model_group(model_cmd) Loading
deep_chem/utils/evaluate.py +5 −0 Original line number Diff line number Diff line Loading @@ -51,6 +51,11 @@ def compute_y_pred(model, data_dir, csv_out, split): split_df = metadata_df.loc[metadata_df['split'] == split] nb_batch = split_df.shape[0] print("compute_y_pred()") print("split_df.shape") print(split_df.shape) # TODO(rbharath/enf): This is only for GPU models, and is currently depends # on magic numbers. MAX_GPU_RAM = float(691007488/50) for i, row in split_df.iterrows(): Loading
deep_chem/utils/featurize.py +10 −7 Original line number Diff line number Diff line Loading @@ -101,10 +101,9 @@ def process_field(data, field_type): elif field_type == "ndarray": return data def generate_scaffold(smiles_elt, include_chirality=False, smiles_field="smiles"): def generate_scaffold(smiles, include_chirality=False, smiles_field="smiles"): """Compute the Bemis-Murcko scaffold for a SMILES string.""" smiles_string = smiles_elt[smiles_field] mol = Chem.MolFromSmiles(smiles_string) mol = Chem.MolFromSmiles(smiles) engine = ScaffoldGenerator(include_chirality=include_chirality) scaffold = engine.get_scaffold(mol) return scaffold Loading Loading @@ -222,10 +221,14 @@ def featurize_inputs(feature_dir, input_files, input_type, fields, field_types, feature_fields, task_fields, smiles_field, split_field, id_field, threshold): featurize_input_partial = partial(featurize_input, feature_dir=feature_dir, input_type=input_type, fields=fields, field_types=field_types, feature_fields=feature_fields, task_fields=task_fields, smiles_field=smiles_field, split_field=split_field, id_field=id_field, threshold=threshold) featurize_input_partial = partial(featurize_input, feature_dir=feature_dir, input_type=input_type, fields=fields, field_types=field_types, feature_fields=feature_fields, task_fields=task_fields, smiles_field=smiles_field, split_field=split_field, id_field=id_field, threshold=threshold) #for input_file in input_files: # featurize_input_partial(input_file) Loading
deep_chem/utils/preprocess.py +90 −392 File changed.Preview size limit exceeded, changes collapsed. Show changes
