Loading README.md +15 −6 Original line number Diff line number Diff line Loading @@ -245,12 +245,18 @@ Scaffold splitting |Dataset |Model |Splitting |Train score/R2|Valid score/R2| |----------------|--------------------|------------|--------------|--------------| |delaney |MT-NN regression |Index |0.773 |0.574 | | |graphconv regression|Index |0.991 |0.825 | | |MT-NN regression |Random |0.769 |0.591 | | |graphconv regression|Random |0.996 |0.873 | | |MT-NN regression |Scaffold |0.782 |0.426 | | |graphconv regression|Scaffold |0.994 |0.606 | |delaney |MT-NN regression |Index |0.868 |0.578 | | |graphconv regression|Index |0.967 |0.790 | | |MT-NN regression |Random |0.865 |0.574 | | |graphconv regression|Random |0.964 |0.782 | | |MT-NN regression |Scaffold |0.866 |0.342 | | |graphconv regression|Scaffold |0.967 |0.606 | |sampl |MT-NN regression |Index |0.917 |0.764 | | |graphconv regression|Index |0.982 |0.864 | | |MT-NN regression |Random |0.908 |0.830 | | |graphconv regression|Random |0.987 |0.868 | | |MT-NN regression |Scaffold |0.891 |0.217 | | |graphconv regression|Scaffold |0.985 |0.666 | |nci |MT-NN regression |Index |0.171 |0.062 | | |graphconv regression|Index |0.123 |0.048 | | |MT-NN regression |Random |0.168 |0.085 | Loading Loading @@ -286,6 +292,7 @@ Number of tasks and examples in the datasets |sider |27 |1427 | |toxcast |617 |8615 | |delaney |1 |1128 | |sampl |1 |643 | |kaggle |15 |173065 | |nci |60 |19127 | |pdbbind(core) |1 |195 | Loading Loading @@ -322,6 +329,8 @@ Time needed for benchmark test(~20h in total) | |graph convolution |80 |900 | |delaney |MT-NN regression |10 |40 | | |graphconv regression|10 |40 | |sampl |MT-NN regression |10 |30 | | |graphconv regression|10 |40 | |nci |MT-NN regression |400 |1200 | | |graphconv regression|400 |2500 | |pdbbind(core) |MT-NN regression |0(featurized) |30 | Loading examples/benchmark.py +6 −5 Original line number Diff line number Diff line Loading @@ -52,6 +52,7 @@ from nci.nci_datasets import load_nci from pdbbind.pdbbind_datasets import load_pdbbind_grid from chembl.chembl_datasets import load_chembl from gdb7.gdb7_datasets import load_gdb7 from sampl.sampl_datasets import load_sampl def benchmark_loading_datasets(hyper_parameters, dataset='tox21', model='tf', split=None, Loading @@ -77,7 +78,8 @@ def benchmark_loading_datasets(hyper_parameters, if dataset in ['muv', 'pcba', 'tox21', 'sider', 'toxcast']: mode = 'classification' elif dataset in ['kaggle', 'delaney', 'nci', 'pdbbind', 'chembl', 'gdb7']: elif dataset in ['kaggle', 'delaney', 'nci', 'pdbbind', 'chembl', 'gdb7', 'sampl']: mode = 'regression' else: raise ValueError('Dataset not supported') Loading Loading @@ -130,7 +132,8 @@ def benchmark_loading_datasets(hyper_parameters, 'sider': load_sider, 'toxcast': load_toxcast, 'kaggle': load_kaggle, 'delaney': load_delaney, 'pdbbind': load_pdbbind_grid, 'chembl': load_chembl, 'gdb7': load_gdb7} 'chembl': load_chembl, 'gdb7': load_gdb7, 'sampl': load_sampl} print('-------------------------------------') print('Benchmark %s on dataset: %s' % (model, dataset)) Loading Loading @@ -163,8 +166,6 @@ def benchmark_loading_datasets(hyper_parameters, model=model) elif mode == 'regression': metric = 'r2' if dataset in ['gdb7']: metric = 'mae' train_score, valid_score = benchmark_regression( train_dataset, valid_dataset, tasks, transformers, hp, n_features, metric=metric, Loading Loading @@ -594,7 +595,7 @@ if __name__ == '__main__': 'dropouts': [0.25, 0.25], 'penalty': 0.0005, 'penalty_type': 'l2', 'batch_size': 128, 'nb_epoch': 50, 'learning_rate': 0.00008}] 'learning_rate': 0.0008}] hps['graphconvreg'] = [{'batch_size': 128, 'nb_epoch': 20, 'learning_rate': 0.0005, 'n_filters': 128, Loading examples/SAMPL/SAMPL.csv→examples/sampl/SAMPL.csv +0 −0 File moved. View file examples/sampl/__init__.py 0 → 100644 +0 −0 Empty file added. examples/SAMPL/SAMPL_datasets.py→examples/sampl/sampl_datasets.py +2 −2 Original line number Diff line number Diff line Loading @@ -10,14 +10,14 @@ import numpy as np import shutil import deepchem as dc def load_SAMPL(featurizer='ECFP', split='index'): def load_sampl(featurizer='ECFP', split='index'): """Load SAMPL datasets.""" # Featurize SAMPL dataset print("About to featurize SAMPL dataset.") current_dir = os.path.dirname(os.path.realpath(__file__)) dataset_file = os.path.join( current_dir, "./SAMPL.csv") SAMPL_tasks = ['expt', 'calc'] SAMPL_tasks = ['expt'] if featurizer == 'ECFP': featurizer = dc.feat.CircularFingerprint(size=1024) elif featurizer == 'GraphConv': Loading Loading
README.md +15 −6 Original line number Diff line number Diff line Loading @@ -245,12 +245,18 @@ Scaffold splitting |Dataset |Model |Splitting |Train score/R2|Valid score/R2| |----------------|--------------------|------------|--------------|--------------| |delaney |MT-NN regression |Index |0.773 |0.574 | | |graphconv regression|Index |0.991 |0.825 | | |MT-NN regression |Random |0.769 |0.591 | | |graphconv regression|Random |0.996 |0.873 | | |MT-NN regression |Scaffold |0.782 |0.426 | | |graphconv regression|Scaffold |0.994 |0.606 | |delaney |MT-NN regression |Index |0.868 |0.578 | | |graphconv regression|Index |0.967 |0.790 | | |MT-NN regression |Random |0.865 |0.574 | | |graphconv regression|Random |0.964 |0.782 | | |MT-NN regression |Scaffold |0.866 |0.342 | | |graphconv regression|Scaffold |0.967 |0.606 | |sampl |MT-NN regression |Index |0.917 |0.764 | | |graphconv regression|Index |0.982 |0.864 | | |MT-NN regression |Random |0.908 |0.830 | | |graphconv regression|Random |0.987 |0.868 | | |MT-NN regression |Scaffold |0.891 |0.217 | | |graphconv regression|Scaffold |0.985 |0.666 | |nci |MT-NN regression |Index |0.171 |0.062 | | |graphconv regression|Index |0.123 |0.048 | | |MT-NN regression |Random |0.168 |0.085 | Loading Loading @@ -286,6 +292,7 @@ Number of tasks and examples in the datasets |sider |27 |1427 | |toxcast |617 |8615 | |delaney |1 |1128 | |sampl |1 |643 | |kaggle |15 |173065 | |nci |60 |19127 | |pdbbind(core) |1 |195 | Loading Loading @@ -322,6 +329,8 @@ Time needed for benchmark test(~20h in total) | |graph convolution |80 |900 | |delaney |MT-NN regression |10 |40 | | |graphconv regression|10 |40 | |sampl |MT-NN regression |10 |30 | | |graphconv regression|10 |40 | |nci |MT-NN regression |400 |1200 | | |graphconv regression|400 |2500 | |pdbbind(core) |MT-NN regression |0(featurized) |30 | Loading
examples/benchmark.py +6 −5 Original line number Diff line number Diff line Loading @@ -52,6 +52,7 @@ from nci.nci_datasets import load_nci from pdbbind.pdbbind_datasets import load_pdbbind_grid from chembl.chembl_datasets import load_chembl from gdb7.gdb7_datasets import load_gdb7 from sampl.sampl_datasets import load_sampl def benchmark_loading_datasets(hyper_parameters, dataset='tox21', model='tf', split=None, Loading @@ -77,7 +78,8 @@ def benchmark_loading_datasets(hyper_parameters, if dataset in ['muv', 'pcba', 'tox21', 'sider', 'toxcast']: mode = 'classification' elif dataset in ['kaggle', 'delaney', 'nci', 'pdbbind', 'chembl', 'gdb7']: elif dataset in ['kaggle', 'delaney', 'nci', 'pdbbind', 'chembl', 'gdb7', 'sampl']: mode = 'regression' else: raise ValueError('Dataset not supported') Loading Loading @@ -130,7 +132,8 @@ def benchmark_loading_datasets(hyper_parameters, 'sider': load_sider, 'toxcast': load_toxcast, 'kaggle': load_kaggle, 'delaney': load_delaney, 'pdbbind': load_pdbbind_grid, 'chembl': load_chembl, 'gdb7': load_gdb7} 'chembl': load_chembl, 'gdb7': load_gdb7, 'sampl': load_sampl} print('-------------------------------------') print('Benchmark %s on dataset: %s' % (model, dataset)) Loading Loading @@ -163,8 +166,6 @@ def benchmark_loading_datasets(hyper_parameters, model=model) elif mode == 'regression': metric = 'r2' if dataset in ['gdb7']: metric = 'mae' train_score, valid_score = benchmark_regression( train_dataset, valid_dataset, tasks, transformers, hp, n_features, metric=metric, Loading Loading @@ -594,7 +595,7 @@ if __name__ == '__main__': 'dropouts': [0.25, 0.25], 'penalty': 0.0005, 'penalty_type': 'l2', 'batch_size': 128, 'nb_epoch': 50, 'learning_rate': 0.00008}] 'learning_rate': 0.0008}] hps['graphconvreg'] = [{'batch_size': 128, 'nb_epoch': 20, 'learning_rate': 0.0005, 'n_filters': 128, Loading
examples/SAMPL/SAMPL_datasets.py→examples/sampl/sampl_datasets.py +2 −2 Original line number Diff line number Diff line Loading @@ -10,14 +10,14 @@ import numpy as np import shutil import deepchem as dc def load_SAMPL(featurizer='ECFP', split='index'): def load_sampl(featurizer='ECFP', split='index'): """Load SAMPL datasets.""" # Featurize SAMPL dataset print("About to featurize SAMPL dataset.") current_dir = os.path.dirname(os.path.realpath(__file__)) dataset_file = os.path.join( current_dir, "./SAMPL.csv") SAMPL_tasks = ['expt', 'calc'] SAMPL_tasks = ['expt'] if featurizer == 'ECFP': featurizer = dc.feat.CircularFingerprint(size=1024) elif featurizer == 'GraphConv': Loading
